- 'css_for_each_descendant_post'
- 'css_for_each_descendant_pre'
- 'device_for_each_child_node'
+ - 'dma_fence_chain_for_each'
- 'drm_atomic_crtc_for_each_plane'
- 'drm_atomic_crtc_state_for_each_plane'
- 'drm_atomic_crtc_state_for_each_plane_state'
- 'drm_atomic_for_each_plane_damage'
+ - 'drm_client_for_each_connector_iter'
+ - 'drm_client_for_each_modeset'
- 'drm_connector_for_each_possible_encoder'
- 'drm_for_each_connector_iter'
- 'drm_for_each_crtc'
- 'drm_mm_for_each_node_in_range'
- 'drm_mm_for_each_node_safe'
- 'flow_action_for_each'
+ - 'for_each_active_dev_scope'
- 'for_each_active_drhd_unit'
- 'for_each_active_iommu'
- 'for_each_available_child_of_node'
- 'for_each_cpu_not'
- 'for_each_cpu_wrap'
- 'for_each_dev_addr'
+ - 'for_each_dev_scope'
+ - 'for_each_displayid_db'
- 'for_each_dma_cap_mask'
- 'for_each_dpcm_be'
- 'for_each_dpcm_be_rollback'
- 'for_each_evictable_lru'
- 'for_each_fib6_node_rt_rcu'
- 'for_each_fib6_walker_rt'
+ - 'for_each_free_mem_pfn_range_in_zone'
+ - 'for_each_free_mem_pfn_range_in_zone_from'
- 'for_each_free_mem_range'
- 'for_each_free_mem_range_reverse'
- 'for_each_func_rsrc'
- 'for_each_ip_tunnel_rcu'
- 'for_each_irq_nr'
- 'for_each_link_codecs'
+ - 'for_each_link_platforms'
- 'for_each_lru'
- 'for_each_matching_node'
- 'for_each_matching_node_and_match'
- 'ide_port_for_each_present_dev'
- 'idr_for_each_entry'
- 'idr_for_each_entry_continue'
+ - 'idr_for_each_entry_continue_ul'
- 'idr_for_each_entry_ul'
+ - 'in_dev_for_each_ifa_rcu'
+ - 'in_dev_for_each_ifa_rtnl'
- 'inet_bind_bucket_for_each'
- 'inet_lhash2_for_each_icsk_rcu'
- 'key_for_each'
- 'media_device_for_each_intf'
- 'media_device_for_each_link'
- 'media_device_for_each_pad'
- - 'mp_bvec_for_each_page'
- - 'mp_bvec_for_each_segment'
- 'nanddev_io_for_each_page'
- 'netdev_for_each_lower_dev'
- 'netdev_for_each_lower_private'
- 'radix_tree_for_each_slot'
- 'radix_tree_for_each_tagged'
- 'rbtree_postorder_for_each_entry_safe'
+ - 'rdma_for_each_block'
- 'rdma_for_each_port'
- 'resource_list_for_each_entry'
- 'resource_list_for_each_entry_safe'
- 'rhl_for_each_entry_rcu'
- 'rhl_for_each_rcu'
- 'rht_for_each'
- - 'rht_for_each_from'
- 'rht_for_each_entry'
- 'rht_for_each_entry_from'
- 'rht_for_each_entry_rcu'
- 'rht_for_each_entry_rcu_from'
- 'rht_for_each_entry_safe'
+ - 'rht_for_each_from'
- 'rht_for_each_rcu'
- 'rht_for_each_rcu_from'
- '__rq_for_each_bio'
# Kdevelop4
*.kdev4
+
+# Clang's compilation database file
+/compile_commands.json
Dengcheng Zhu <dzhu@wavecomp.com> <dczhu@mips.com>
Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com>
Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
Domen Puncer <domen@coderock.org>
Douglas Gilbert <dougg@torque.net>
Ed L. Cashin <ecashin@coraid.com>
Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
<javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
Jean Tourrilhes <jt@hpl.hp.com>
+<jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
Jeff Garzik <jgarzik@pretzel.yyz.us>
Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
Juha Yrjola <at solidboot.com>
Juha Yrjola <juha.yrjola@nokia.com>
Juha Yrjola <juha.yrjola@solidboot.com>
+Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
Kay Sievers <kay.sievers@vrfy.org>
Kenneth W Chen <kenneth.w.chen@intel.com>
Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
+Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com>
Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
Mark Brown <broonie@sirena.org.uk>
Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com>
Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com>
+Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com>
+Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com>
Mayuresh Janorkar <mayur@ti.com>
Michael Buesch <m@bues.ch>
Michel Dänzer <michel@tungstengraphics.com>
:numbered:
pci
- picebus-howto
+ pciebus-howto
pci-iov-howto
msi-howto
acpi-info
.. note::
Implementation details for the powerpc platform are discussed in
- the file Documentation/powerpc/eeh-pci-error-recovery.txt
+ the file Documentation/powerpc/eeh-pci-error-recovery.rst
As of this writing, there is a growing list of device drivers with
patches implementing error recovery. Not all of these patches are in
- drivers/net/cxgb3
- drivers/net/s2io.c
- drivers/net/qlge
+
+The End
+-------
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+===========================================
+The PCI Express Port Bus Driver Guide HOWTO
+===========================================
+
+:Author: Tom L Nguyen tom.l.nguyen@intel.com 11/03/2004
+:Copyright: |copy| 2004 Intel Corporation
+
+About this guide
+================
+
+This guide describes the basics of the PCI Express Port Bus driver
+and provides information on how to enable the service drivers to
+register/unregister with the PCI Express Port Bus Driver.
+
+
+What is the PCI Express Port Bus Driver
+=======================================
+
+A PCI Express Port is a logical PCI-PCI Bridge structure. There
+are two types of PCI Express Port: the Root Port and the Switch
+Port. The Root Port originates a PCI Express link from a PCI Express
+Root Complex and the Switch Port connects PCI Express links to
+internal logical PCI buses. The Switch Port, which has its secondary
+bus representing the switch's internal routing logic, is called the
+switch's Upstream Port. The switch's Downstream Port is bridging from
+switch's internal routing bus to a bus representing the downstream
+PCI Express link from the PCI Express Switch.
+
+A PCI Express Port can provide up to four distinct functions,
+referred to in this document as services, depending on its port type.
+PCI Express Port's services include native hotplug support (HP),
+power management event support (PME), advanced error reporting
+support (AER), and virtual channel support (VC). These services may
+be handled by a single complex driver or be individually distributed
+and handled by corresponding service drivers.
+
+Why use the PCI Express Port Bus Driver?
+========================================
+
+In existing Linux kernels, the Linux Device Driver Model allows a
+physical device to be handled by only a single driver. The PCI
+Express Port is a PCI-PCI Bridge device with multiple distinct
+services. To maintain a clean and simple solution each service
+may have its own software service driver. In this case several
+service drivers will compete for a single PCI-PCI Bridge device.
+For example, if the PCI Express Root Port native hotplug service
+driver is loaded first, it claims a PCI-PCI Bridge Root Port. The
+kernel therefore does not load other service drivers for that Root
+Port. In other words, it is impossible to have multiple service
+drivers load and run on a PCI-PCI Bridge device simultaneously
+using the current driver model.
+
+To enable multiple service drivers running simultaneously requires
+having a PCI Express Port Bus driver, which manages all populated
+PCI Express Ports and distributes all provided service requests
+to the corresponding service drivers as required. Some key
+advantages of using the PCI Express Port Bus driver are listed below:
+
+ - Allow multiple service drivers to run simultaneously on
+ a PCI-PCI Bridge Port device.
+
+ - Allow service drivers implemented in an independent
+ staged approach.
+
+ - Allow one service driver to run on multiple PCI-PCI Bridge
+ Port devices.
+
+ - Manage and distribute resources of a PCI-PCI Bridge Port
+ device to requested service drivers.
+
+Configuring the PCI Express Port Bus Driver vs. Service Drivers
+===============================================================
+
+Including the PCI Express Port Bus Driver Support into the Kernel
+-----------------------------------------------------------------
+
+Including the PCI Express Port Bus driver depends on whether the PCI
+Express support is included in the kernel config. The kernel will
+automatically include the PCI Express Port Bus driver as a kernel
+driver when the PCI Express support is enabled in the kernel.
+
+Enabling Service Driver Support
+-------------------------------
+
+PCI device drivers are implemented based on Linux Device Driver Model.
+All service drivers are PCI device drivers. As discussed above, it is
+impossible to load any service driver once the kernel has loaded the
+PCI Express Port Bus Driver. To meet the PCI Express Port Bus Driver
+Model requires some minimal changes on existing service drivers that
+imposes no impact on the functionality of existing service drivers.
+
+A service driver is required to use the two APIs shown below to
+register its service with the PCI Express Port Bus driver (see
+section 5.2.1 & 5.2.2). It is important that a service driver
+initializes the pcie_port_service_driver data structure, included in
+header file /include/linux/pcieport_if.h, before calling these APIs.
+Failure to do so will result an identity mismatch, which prevents
+the PCI Express Port Bus driver from loading a service driver.
+
+pcie_port_service_register
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+::
+
+ int pcie_port_service_register(struct pcie_port_service_driver *new)
+
+This API replaces the Linux Driver Model's pci_register_driver API. A
+service driver should always calls pcie_port_service_register at
+module init. Note that after service driver being loaded, calls
+such as pci_enable_device(dev) and pci_set_master(dev) are no longer
+necessary since these calls are executed by the PCI Port Bus driver.
+
+pcie_port_service_unregister
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+::
+
+ void pcie_port_service_unregister(struct pcie_port_service_driver *new)
+
+pcie_port_service_unregister replaces the Linux Driver Model's
+pci_unregister_driver. It's always called by service driver when a
+module exits.
+
+Sample Code
+~~~~~~~~~~~
+
+Below is sample service driver code to initialize the port service
+driver data structure.
+::
+
+ static struct pcie_port_service_id service_id[] = { {
+ .vendor = PCI_ANY_ID,
+ .device = PCI_ANY_ID,
+ .port_type = PCIE_RC_PORT,
+ .service_type = PCIE_PORT_SERVICE_AER,
+ }, { /* end: all zeroes */ }
+ };
+
+ static struct pcie_port_service_driver root_aerdrv = {
+ .name = (char *)device_name,
+ .id_table = &service_id[0],
+
+ .probe = aerdrv_load,
+ .remove = aerdrv_unload,
+
+ .suspend = aerdrv_suspend,
+ .resume = aerdrv_resume,
+ };
+
+Below is a sample code for registering/unregistering a service
+driver.
+::
+
+ static int __init aerdrv_service_init(void)
+ {
+ int retval = 0;
+
+ retval = pcie_port_service_register(&root_aerdrv);
+ if (!retval) {
+ /*
+ * FIX ME
+ */
+ }
+ return retval;
+ }
+
+ static void __exit aerdrv_service_exit(void)
+ {
+ pcie_port_service_unregister(&root_aerdrv);
+ }
+
+ module_init(aerdrv_service_init);
+ module_exit(aerdrv_service_exit);
+
+Possible Resource Conflicts
+===========================
+
+Since all service drivers of a PCI-PCI Bridge Port device are
+allowed to run simultaneously, below lists a few of possible resource
+conflicts with proposed solutions.
+
+MSI and MSI-X Vector Resource
+-----------------------------
+
+Once MSI or MSI-X interrupts are enabled on a device, it stays in this
+mode until they are disabled again. Since service drivers of the same
+PCI-PCI Bridge port share the same physical device, if an individual
+service driver enables or disables MSI/MSI-X mode it may result
+unpredictable behavior.
+
+To avoid this situation all service drivers are not permitted to
+switch interrupt mode on its device. The PCI Express Port Bus driver
+is responsible for determining the interrupt mode and this should be
+transparent to service drivers. Service drivers need to know only
+the vector IRQ assigned to the field irq of struct pcie_device, which
+is passed in when the PCI Express Port Bus driver probes each service
+driver. Service drivers should use (struct pcie_device*)dev->irq to
+call request_irq/free_irq. In addition, the interrupt mode is stored
+in the field interrupt_mode of struct pcie_device.
+
+PCI Memory/IO Mapped Regions
+----------------------------
+
+Service drivers for PCI Express Power Management (PME), Advanced
+Error Reporting (AER), Hot-Plug (HP) and Virtual Channel (VC) access
+PCI configuration space on the PCI Express port. In all cases the
+registers accessed are independent of each other. This patch assumes
+that all service drivers will be well behaved and not overwrite
+other service driver's configuration settings.
+
+PCI Config Registers
+--------------------
+
+Each service driver runs its PCI config operations on its own
+capability structure except the PCI Express capability structure, in
+which Root Control register and Device Control register are shared
+between PME and AER. This patch assumes that all service drivers
+will be well behaved and not overwrite other service driver's
+configuration settings.
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-.. include:: <isonum.txt>
-
-===========================================
-The PCI Express Port Bus Driver Guide HOWTO
-===========================================
-
-:Author: Tom L Nguyen tom.l.nguyen@intel.com 11/03/2004
-:Copyright: |copy| 2004 Intel Corporation
-
-About this guide
-================
-
-This guide describes the basics of the PCI Express Port Bus driver
-and provides information on how to enable the service drivers to
-register/unregister with the PCI Express Port Bus Driver.
-
-
-What is the PCI Express Port Bus Driver
-=======================================
-
-A PCI Express Port is a logical PCI-PCI Bridge structure. There
-are two types of PCI Express Port: the Root Port and the Switch
-Port. The Root Port originates a PCI Express link from a PCI Express
-Root Complex and the Switch Port connects PCI Express links to
-internal logical PCI buses. The Switch Port, which has its secondary
-bus representing the switch's internal routing logic, is called the
-switch's Upstream Port. The switch's Downstream Port is bridging from
-switch's internal routing bus to a bus representing the downstream
-PCI Express link from the PCI Express Switch.
-
-A PCI Express Port can provide up to four distinct functions,
-referred to in this document as services, depending on its port type.
-PCI Express Port's services include native hotplug support (HP),
-power management event support (PME), advanced error reporting
-support (AER), and virtual channel support (VC). These services may
-be handled by a single complex driver or be individually distributed
-and handled by corresponding service drivers.
-
-Why use the PCI Express Port Bus Driver?
-========================================
-
-In existing Linux kernels, the Linux Device Driver Model allows a
-physical device to be handled by only a single driver. The PCI
-Express Port is a PCI-PCI Bridge device with multiple distinct
-services. To maintain a clean and simple solution each service
-may have its own software service driver. In this case several
-service drivers will compete for a single PCI-PCI Bridge device.
-For example, if the PCI Express Root Port native hotplug service
-driver is loaded first, it claims a PCI-PCI Bridge Root Port. The
-kernel therefore does not load other service drivers for that Root
-Port. In other words, it is impossible to have multiple service
-drivers load and run on a PCI-PCI Bridge device simultaneously
-using the current driver model.
-
-To enable multiple service drivers running simultaneously requires
-having a PCI Express Port Bus driver, which manages all populated
-PCI Express Ports and distributes all provided service requests
-to the corresponding service drivers as required. Some key
-advantages of using the PCI Express Port Bus driver are listed below:
-
- - Allow multiple service drivers to run simultaneously on
- a PCI-PCI Bridge Port device.
-
- - Allow service drivers implemented in an independent
- staged approach.
-
- - Allow one service driver to run on multiple PCI-PCI Bridge
- Port devices.
-
- - Manage and distribute resources of a PCI-PCI Bridge Port
- device to requested service drivers.
-
-Configuring the PCI Express Port Bus Driver vs. Service Drivers
-===============================================================
-
-Including the PCI Express Port Bus Driver Support into the Kernel
------------------------------------------------------------------
-
-Including the PCI Express Port Bus driver depends on whether the PCI
-Express support is included in the kernel config. The kernel will
-automatically include the PCI Express Port Bus driver as a kernel
-driver when the PCI Express support is enabled in the kernel.
-
-Enabling Service Driver Support
--------------------------------
-
-PCI device drivers are implemented based on Linux Device Driver Model.
-All service drivers are PCI device drivers. As discussed above, it is
-impossible to load any service driver once the kernel has loaded the
-PCI Express Port Bus Driver. To meet the PCI Express Port Bus Driver
-Model requires some minimal changes on existing service drivers that
-imposes no impact on the functionality of existing service drivers.
-
-A service driver is required to use the two APIs shown below to
-register its service with the PCI Express Port Bus driver (see
-section 5.2.1 & 5.2.2). It is important that a service driver
-initializes the pcie_port_service_driver data structure, included in
-header file /include/linux/pcieport_if.h, before calling these APIs.
-Failure to do so will result an identity mismatch, which prevents
-the PCI Express Port Bus driver from loading a service driver.
-
-pcie_port_service_register
-~~~~~~~~~~~~~~~~~~~~~~~~~~
-::
-
- int pcie_port_service_register(struct pcie_port_service_driver *new)
-
-This API replaces the Linux Driver Model's pci_register_driver API. A
-service driver should always calls pcie_port_service_register at
-module init. Note that after service driver being loaded, calls
-such as pci_enable_device(dev) and pci_set_master(dev) are no longer
-necessary since these calls are executed by the PCI Port Bus driver.
-
-pcie_port_service_unregister
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-::
-
- void pcie_port_service_unregister(struct pcie_port_service_driver *new)
-
-pcie_port_service_unregister replaces the Linux Driver Model's
-pci_unregister_driver. It's always called by service driver when a
-module exits.
-
-Sample Code
-~~~~~~~~~~~
-
-Below is sample service driver code to initialize the port service
-driver data structure.
-::
-
- static struct pcie_port_service_id service_id[] = { {
- .vendor = PCI_ANY_ID,
- .device = PCI_ANY_ID,
- .port_type = PCIE_RC_PORT,
- .service_type = PCIE_PORT_SERVICE_AER,
- }, { /* end: all zeroes */ }
- };
-
- static struct pcie_port_service_driver root_aerdrv = {
- .name = (char *)device_name,
- .id_table = &service_id[0],
-
- .probe = aerdrv_load,
- .remove = aerdrv_unload,
-
- .suspend = aerdrv_suspend,
- .resume = aerdrv_resume,
- };
-
-Below is a sample code for registering/unregistering a service
-driver.
-::
-
- static int __init aerdrv_service_init(void)
- {
- int retval = 0;
-
- retval = pcie_port_service_register(&root_aerdrv);
- if (!retval) {
- /*
- * FIX ME
- */
- }
- return retval;
- }
-
- static void __exit aerdrv_service_exit(void)
- {
- pcie_port_service_unregister(&root_aerdrv);
- }
-
- module_init(aerdrv_service_init);
- module_exit(aerdrv_service_exit);
-
-Possible Resource Conflicts
-===========================
-
-Since all service drivers of a PCI-PCI Bridge Port device are
-allowed to run simultaneously, below lists a few of possible resource
-conflicts with proposed solutions.
-
-MSI and MSI-X Vector Resource
------------------------------
-
-Once MSI or MSI-X interrupts are enabled on a device, it stays in this
-mode until they are disabled again. Since service drivers of the same
-PCI-PCI Bridge port share the same physical device, if an individual
-service driver enables or disables MSI/MSI-X mode it may result
-unpredictable behavior.
-
-To avoid this situation all service drivers are not permitted to
-switch interrupt mode on its device. The PCI Express Port Bus driver
-is responsible for determining the interrupt mode and this should be
-transparent to service drivers. Service drivers need to know only
-the vector IRQ assigned to the field irq of struct pcie_device, which
-is passed in when the PCI Express Port Bus driver probes each service
-driver. Service drivers should use (struct pcie_device*)dev->irq to
-call request_irq/free_irq. In addition, the interrupt mode is stored
-in the field interrupt_mode of struct pcie_device.
-
-PCI Memory/IO Mapped Regions
-----------------------------
-
-Service drivers for PCI Express Power Management (PME), Advanced
-Error Reporting (AER), Hot-Plug (HP) and Virtual Channel (VC) access
-PCI configuration space on the PCI Express port. In all cases the
-registers accessed are independent of each other. This patch assumes
-that all service drivers will be well behaved and not overwrite
-other service driver's configuration settings.
-
-PCI Config Registers
---------------------
-
-Each service driver runs its PCI config operations on its own
-capability structure except the PCI Express capability structure, in
-which Root Control register and Device Control register are shared
-between PME and AER. This patch assumes that all service drivers
-will be well behaved and not overwrite other service driver's
-configuration settings.
Using hlist_nulls to protect read-mostly linked lists and
objects using SLAB_TYPESAFE_BY_RCU allocations.
-Please read the basics in Documentation/RCU/listRCU.txt
+Please read the basics in Documentation/RCU/listRCU.rst
Using special makers (called 'nulls') is a convenient way
to solve following problem :
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = 'Linux Kernel User Documentation'
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'linux-user.tex', 'Linux Kernel User Documentation',
- 'The kernel development community', 'manual'),
-]
The following CVE entries describe Spectre variants:
- ============= ======================= =================
+ ============= ======================= ==========================
CVE-2017-5753 Bounds check bypass Spectre variant 1
CVE-2017-5715 Branch target injection Spectre variant 2
- ============= ======================= =================
+ CVE-2019-1125 Spectre v1 swapgs Spectre variant 1 (swapgs)
+ ============= ======================= ==========================
Problem
-------
over the network, see :ref:`[12] <spec_ref12>`. However such attacks
are difficult, low bandwidth, fragile, and are considered low risk.
+Note that, despite "Bounds Check Bypass" name, Spectre variant 1 is not
+only about user-controlled array bounds checks. It can affect any
+conditional checks. The kernel entry code interrupt, exception, and NMI
+handlers all have conditional swapgs checks. Those may be problematic
+in the context of Spectre v1, as kernel code can speculatively run with
+a user GS.
+
Spectre variant 2 (Branch Target Injection)
-------------------------------------------
1. A user process attacking the kernel
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Spectre variant 1
+~~~~~~~~~~~~~~~~~
+
The attacker passes a parameter to the kernel via a register or
via a known address in memory during a syscall. Such parameter may
be used later by the kernel as an index to an array or to derive
potentially be influenced for Spectre attacks, new "nospec" accessor
macros are used to prevent speculative loading of data.
- Spectre variant 2 attacker can :ref:`poison <poison_btb>` the branch
+Spectre variant 1 (swapgs)
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+ An attacker can train the branch predictor to speculatively skip the
+ swapgs path for an interrupt or exception. If they initialize
+ the GS register to a user-space value, if the swapgs is speculatively
+ skipped, subsequent GS-related percpu accesses in the speculation
+ window will be done with the attacker-controlled GS value. This
+ could cause privileged memory to be accessed and leaked.
+
+ For example:
+
+ ::
+
+ if (coming from user space)
+ swapgs
+ mov %gs:<percpu_offset>, %reg
+ mov (%reg), %reg1
+
+ When coming from user space, the CPU can speculatively skip the
+ swapgs, and then do a speculative percpu load using the user GS
+ value. So the user can speculatively force a read of any kernel
+ value. If a gadget exists which uses the percpu value as an address
+ in another load/store, then the contents of the kernel value may
+ become visible via an L1 side channel attack.
+
+ A similar attack exists when coming from kernel space. The CPU can
+ speculatively do the swapgs, causing the user GS to get used for the
+ rest of the speculative window.
+
+Spectre variant 2
+~~~~~~~~~~~~~~~~~
+
+ A spectre variant 2 attacker can :ref:`poison <poison_btb>` the branch
target buffer (BTB) before issuing syscall to launch an attack.
After entering the kernel, the kernel could use the poisoned branch
target buffer on indirect jump and jump to gadget code in speculative
The possible values in this file are:
- ======================================= =================================
- 'Mitigation: __user pointer sanitation' Protection in kernel on a case by
- case base with explicit pointer
- sanitation.
- ======================================= =================================
+ .. list-table::
+
+ * - 'Not affected'
+ - The processor is not vulnerable.
+ * - 'Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers'
+ - The swapgs protections are disabled; otherwise it has
+ protection in the kernel on a case by case base with explicit
+ pointer sanitation and usercopy LFENCE barriers.
+ * - 'Mitigation: usercopy/swapgs barriers and __user pointer sanitization'
+ - Protection in the kernel on a case by case base with explicit
+ pointer sanitation, usercopy LFENCE barriers, and swapgs LFENCE
+ barriers.
However, the protections are put in place on a case by case basis,
and there is no guarantee that all possible attack vectors for Spectre
1. Kernel mitigation
^^^^^^^^^^^^^^^^^^^^
+Spectre variant 1
+~~~~~~~~~~~~~~~~~
+
For the Spectre variant 1, vulnerable kernel code (as determined
by code audit or scanning tools) is annotated on a case by case
basis to use nospec accessor macros for bounds clipping :ref:`[2]
<spec_ref2>` to avoid any usable disclosure gadgets. However, it may
not cover all attack vectors for Spectre variant 1.
+ Copy-from-user code has an LFENCE barrier to prevent the access_ok()
+ check from being mis-speculated. The barrier is done by the
+ barrier_nospec() macro.
+
+ For the swapgs variant of Spectre variant 1, LFENCE barriers are
+ added to interrupt, exception and NMI entry where needed. These
+ barriers are done by the FENCE_SWAPGS_KERNEL_ENTRY and
+ FENCE_SWAPGS_USER_ENTRY macros.
+
+Spectre variant 2
+~~~~~~~~~~~~~~~~~
+
For Spectre variant 2 mitigation, the compiler turns indirect calls or
jumps in the kernel into equivalent return trampolines (retpolines)
:ref:`[3] <spec_ref3>` :ref:`[9] <spec_ref9>` to go to the target
Spectre variant 2 mitigation can be disabled or force enabled at the
kernel command line.
+ nospectre_v1
+
+ [X86,PPC] Disable mitigations for Spectre Variant 1
+ (bounds check bypass). With this option data leaks are
+ possible in the system.
+
nospectre_v2
[X86] Disable all mitigations for the Spectre variant 2
mem_encrypt=on: Activate SME
mem_encrypt=off: Do not activate SME
- Refer to Documentation/virtual/kvm/amd-memory-encryption.rst
+ Refer to Documentation/virt/kvm/amd-memory-encryption.rst
for details on when memory encryption can be activated.
mem_sleep_default= [SUSPEND] Default system suspend mode:
expose users to several CPU vulnerabilities.
Equivalent to: nopti [X86,PPC]
kpti=0 [ARM64]
- nospectre_v1 [PPC]
+ nospectre_v1 [X86,PPC]
nobp=0 [S390]
nospectre_v2 [X86,PPC,S390,ARM64]
spectre_v2_user=off [X86]
nosmt=force: Force disable SMT, cannot be undone
via the sysfs control file.
- nospectre_v1 [PPC] Disable mitigations for Spectre Variant 1 (bounds
- check bypass). With this option data leaks are possible
- in the system.
+ nospectre_v1 [X86,PPC] Disable mitigations for Spectre Variant 1
+ (bounds check bypass). With this option data leaks are
+ possible in the system.
nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
the Spectre variant 2 (indirect branch prediction)
Run specified binary instead of /init from the ramdisk,
used for early userspace startup. See initrd.
+ rdrand= [X86]
+ force - Override the decision by the kernel to hide the
+ advertisement of RDRAND support (this affects
+ certain AMD processors because of buggy BIOS
+ support, specifically around the suspend/resume
+ path).
+
rdt= [HW,X86,RDT]
Turn on/off individual RDT features. List is:
cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
collapses sequences of basic pages into huge pages.
The THP behaviour is controlled via :ref:`sysfs <thp_sysfs>`
-interface and using madivse(2) and prctl(2) system calls.
+interface and using madvise(2) and prctl(2) system calls.
Transparent Hugepage Support maximizes the usefulness of free memory
if compared to the reservation approach of hugetlbfs by allowing all
802 E802 protocol ax25 AX25
ethernet Ethernet protocol rose X.25 PLP layer
ipv4 IP version 4 x25 X.25 protocol
- ipx IPX token-ring IBM token ring
bridge Bridging decnet DEC net
ipv6 IP version 6 tipc TIPC
========= =================== = ========== ==================
(network) that the route leads to, the router (may be directly connected), the
route flags, and the device the route is using.
-
-5. IPX
-------
-
-The IPX protocol has no tunable values in proc/sys/net.
-
-The IPX protocol does, however, provide proc/net/ipx. This lists each IPX
-socket giving the local and remote addresses in Novell format (that is
-network:node:port). In accordance with the strange Novell tradition,
-everything but the port is in hex. Not_Connected is displayed for sockets that
-are not tied to a specific remote address. The Tx and Rx queue sizes indicate
-the number of bytes pending for transmission and reception. The state
-indicates the state the socket is in and the uid is the owning uid of the
-socket.
-
-The /proc/net/ipx_interface file lists all IPX interfaces. For each interface
-it gives the network number, the node number, and indicates if the network is
-the primary network. It also indicates which device it is bound to (or
-Internal for internal networks) and the Frame Type if appropriate. Linux
-supports 802.3, 802.2, 802.2 SNAP and DIX (Blue Book) ethernet framing for
-IPX.
-
-The /proc/net/ipx_route table holds a list of IPX routes. For each route it
-gives the destination network, the router node (or Directly) and the network
-address of the router (or Connected) for internal networks.
-
-6. TIPC
+5. TIPC
-------
tipc_rmem
import os
import sphinx
+from subprocess import check_output
+
# Get Sphinx version
major, minor, patch = sphinx.version_info[:3]
\\setsansfont{DejaVu Sans}
\\setromanfont{DejaVu Serif}
\\setmonofont{DejaVu Sans Mono}
-
'''
}
+# At least one book (translations) may have Asian characters
+# with are only displayed if xeCJK is used
+
+cjk_cmd = check_output(['fc-list', '--format="%{family[0]}\n"']).decode('utf-8', 'ignore')
+if cjk_cmd.find("Noto Sans CJK SC") >= 0:
+ print ("enabling CJK for LaTeX builder")
+ latex_elements['preamble'] += '''
+ % This is needed for translations
+ \\usepackage{xeCJK}
+ \\setCJKmainfont{Noto Sans CJK SC}
+ '''
+
# Fix reference escape troubles with Sphinx 1.4.x
if major == 1 and minor > 3:
latex_elements['preamble'] += '\\renewcommand*{\\DUrole}[2]{ #2 }\n'
'The kernel development community', 'manual'),
]
+# Add all other index files from Documentation/ subdirectories
+for fn in os.listdir('.'):
+ doc = os.path.join(fn, "index")
+ if os.path.exists(doc + ".rst"):
+ has = False
+ for l in latex_documents:
+ if l[0] == doc:
+ has = True
+ break
+ if not has:
+ latex_documents.append((doc, fn + '.tex',
+ 'Linux %s Documentation' % fn.capitalize(),
+ 'The kernel development community',
+ 'manual'))
+
# The name of an image file (relative to this directory) to place at the top of
# the title page.
#latex_logo = None
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Core-API Documentation"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'core-api.tex', project,
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = 'Linux Kernel Crypto API'
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'crypto-api.tex', 'Linux Kernel Crypto API manual',
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Development tools for the kernel"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'dev-tools.tex', project,
- 'The kernel development community', 'manual'),
-]
DT_DOCS = $(shell \
cd $(srctree)/$(src) && \
- find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \
+ find * \( -name '*.yaml' ! \
+ -name $(DT_TMP_SCHEMA) ! \
+ -name '*.example.dt.yaml' \) \
)
DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS))
https://www.devicetree.org/specifications/
[6] ARM Linux Kernel documentation - Booting AArch64 Linux
- Documentation/arm64/booting.txt
+ Documentation/arm64/booting.rst
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/arm/shmobile.yaml#
+$id: http://devicetree.org/schemas/arm/renesas.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Renesas SH-Mobile, R-Mobile, and R-Car Platform Device Tree Bindings
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/arm/milbeaut.yaml#
+$id: http://devicetree.org/schemas/arm/socionext/milbeaut.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Milbeaut platforms device tree bindings
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/arm/ti/davinci.yaml#
+$id: http://devicetree.org/schemas/arm/ti/ti,davinci.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Texas Instruments DaVinci Platforms Device Tree Bindings
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/phy/allwinner,sun4i-a10-ccu.yaml#
+$id: http://devicetree.org/schemas/clock/allwinner,sun4i-a10-ccu.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Allwinner Clock Control Unit Device Tree Bindings
# Copyright 2019 Linaro Ltd.
%YAML 1.2
---
-$id: "http://devicetree.org/schemas/firmware/intel-ixp4xx-network-processing-engine.yaml#"
+$id: "http://devicetree.org/schemas/firmware/intel,ixp4xx-network-processing-engine.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Intel IXP4xx Network Processing Engine
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/iio/accelerometers/adi,adxl345.yaml#
+$id: http://devicetree.org/schemas/iio/accel/adi,adxl345.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Analog Devices ADXL345/ADXL375 3-Axis Digital Accelerometers
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/iio/accelerometers/adi,adxl372.yaml#
+$id: http://devicetree.org/schemas/iio/accel/adi,adxl372.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Analog Devices ADXL372 3-Axis, +/-(200g) Digital Accelerometer
- compatible: should be "amazon,al-fic"
- reg: physical base address and size of the registers
- interrupt-controller: identifies the node as an interrupt controller
-- #interrupt-cells: must be 2.
- First cell defines the index of the interrupt within the controller.
- Second cell is used to specify the trigger type and must be one of the
- following:
- - bits[3:0] trigger type and level flags
- 1 = low-to-high edge triggered
- 4 = active high level-sensitive
-- interrupt-parent: specifies the parent interrupt controller.
+- #interrupt-cells : must be 2. Specifies the number of cells needed to encode
+ an interrupt source. Supported trigger types are low-to-high edge
+ triggered and active high level-sensitive.
- interrupts: describes which input line in the interrupt parent, this
fic's output is connected to. This field property depends on the parent's
binding
+Please refer to interrupts.txt in this directory for details of the common
+Interrupt Controllers bindings used by client devices.
+
Example:
-amazon_fic: interrupt-controller@0xfd8a8500 {
+amazon_fic: interrupt-controller@fd8a8500 {
compatible = "amazon,al-fic";
interrupt-controller;
#interrupt-cells = <2>;
# Copyright 2018 Linaro Ltd.
%YAML 1.2
---
-$id: "http://devicetree.org/schemas/interrupt/intel-ixp4xx-interrupt.yaml#"
+$id: "http://devicetree.org/schemas/interrupt-controller/intel,ixp4xx-interrupt.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Intel IXP4xx XScale Networking Processors Interrupt Controller
* ARC-HS Interrupt Distribution Unit
- This optional 2nd level interrupt controller can be used in SMP configurations for
- dynamic IRQ routing, load balancing of common/external IRQs towards core intc.
+ This optional 2nd level interrupt controller can be used in SMP configurations
+ for dynamic IRQ routing, load balancing of common/external IRQs towards core
+ intc.
Properties:
- compatible: "snps,archs-idu-intc"
- interrupt-controller: This is an interrupt controller.
-- #interrupt-cells: Must be <1>.
-
- Value of the cell specifies the "common" IRQ from peripheral to IDU. Number N
- of the particular interrupt line of IDU corresponds to the line N+24 of the
- core interrupt controller.
-
- intc accessed via the special ARC AUX register interface, hence "reg" property
- is not specified.
+- #interrupt-cells: Must be <1> or <2>.
+
+ Value of the first cell specifies the "common" IRQ from peripheral to IDU.
+ Number N of the particular interrupt line of IDU corresponds to the line N+24
+ of the core interrupt controller.
+
+ The (optional) second cell specifies any of the following flags:
+ - bits[3:0] trigger type and level flags
+ 1 = low-to-high edge triggered
+ 2 = NOT SUPPORTED (high-to-low edge triggered)
+ 4 = active high level-sensitive <<< DEFAULT
+ 8 = NOT SUPPORTED (active low level-sensitive)
+ When no second cell is specified, the interrupt is assumed to be level
+ sensitive.
+
+ The interrupt controller is accessed via the special ARC AUX register
+ interface, hence "reg" property is not specified.
Example:
core_intc: core-interrupt-controller {
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+# Copyright 2019 Linaro Ltd.
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/misc/intel,ixp4xx-ahb-queue-manager.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Intel IXP4xx AHB Queue Manager
+
+maintainers:
+ - Linus Walleij <linus.walleij@linaro.org>
+
+description: |
+ The IXP4xx AHB Queue Manager maintains queues as circular buffers in
+ an 8KB embedded SRAM along with hardware pointers. It is used by both
+ the XScale processor and the NPEs (Network Processing Units) in the
+ IXP4xx for accelerating queues, especially for networking. Clients pick
+ queues from the queue manager with foo-queue = <&qmgr N> where the
+ &qmgr is a phandle to the queue manager and N is the queue resource
+ number. The queue resources available and their specific purpose
+ on a certain IXP4xx system will vary.
+
+properties:
+ compatible:
+ items:
+ - const: intel,ixp4xx-ahb-queue-manager
+
+ reg:
+ maxItems: 1
+
+ interrupts:
+ items:
+ - description: Interrupt for queues 0-31
+ - description: Interrupt for queues 32-63
+
+required:
+ - compatible
+ - reg
+ - interrupts
+
+examples:
+ - |
+ #include <dt-bindings/interrupt-controller/irq.h>
+
+ qmgr: queue-manager@60000000 {
+ compatible = "intel,ixp4xx-ahb-queue-manager";
+ reg = <0x60000000 0x4000>;
+ interrupts = <3 IRQ_TYPE_LEVEL_HIGH>, <4 IRQ_TYPE_LEVEL_HIGH>;
+ };
+++ /dev/null
-# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
-# Copyright 2019 Linaro Ltd.
-%YAML 1.2
----
-$id: "http://devicetree.org/schemas/misc/intel-ixp4xx-ahb-queue-manager.yaml#"
-$schema: "http://devicetree.org/meta-schemas/core.yaml#"
-
-title: Intel IXP4xx AHB Queue Manager
-
-maintainers:
- - Linus Walleij <linus.walleij@linaro.org>
-
-description: |
- The IXP4xx AHB Queue Manager maintains queues as circular buffers in
- an 8KB embedded SRAM along with hardware pointers. It is used by both
- the XScale processor and the NPEs (Network Processing Units) in the
- IXP4xx for accelerating queues, especially for networking. Clients pick
- queues from the queue manager with foo-queue = <&qmgr N> where the
- &qmgr is a phandle to the queue manager and N is the queue resource
- number. The queue resources available and their specific purpose
- on a certain IXP4xx system will vary.
-
-properties:
- compatible:
- items:
- - const: intel,ixp4xx-ahb-queue-manager
-
- reg:
- maxItems: 1
-
- interrupts:
- items:
- - description: Interrupt for queues 0-31
- - description: Interrupt for queues 32-63
-
-required:
- - compatible
- - reg
- - interrupts
-
-examples:
- - |
- #include <dt-bindings/interrupt-controller/irq.h>
-
- qmgr: queue-manager@60000000 {
- compatible = "intel,ixp4xx-ahb-queue-manager";
- reg = <0x60000000 0x4000>;
- interrupts = <3 IRQ_TYPE_LEVEL_HIGH>, <4 IRQ_TYPE_LEVEL_HIGH>;
- };
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/net/allwinner,sun8i-a83t-gmac.yaml#
+$id: http://devicetree.org/schemas/net/allwinner,sun8i-a83t-emac.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Allwinner A83t EMAC Device Tree Bindings
- "microchip,ksz8565"
- "microchip,ksz9893"
- "microchip,ksz9563"
+ - "microchip,ksz8563"
Optional properties:
- phy-mode : See ethernet.txt file in the same directory
Optional properties:
-- phy-reset-gpios : Should specify the gpio for phy reset
-- phy-reset-duration : Reset duration in milliseconds. Should present
- only if property "phy-reset-gpios" is available. Missing the property
- will have the duration be 1 millisecond. Numbers greater than 1000 are
- invalid and 1 millisecond will be used instead.
-- phy-reset-active-high : If present then the reset sequence using the GPIO
- specified in the "phy-reset-gpios" property is reversed (H=reset state,
- L=operation state).
-- phy-reset-post-delay : Post reset delay in milliseconds. If present then
- a delay of phy-reset-post-delay milliseconds will be observed after the
- phy-reset-gpios has been toggled. Can be omitted thus no delay is
- observed. Delay is in range of 1ms to 1000ms. Other delays are invalid.
- phy-supply : regulator that powers the Ethernet PHY.
- phy-handle : phandle to the PHY device connected to this device.
- fixed-link : Assume a fixed link. See fixed-link.txt in the same directory.
For imx6sx, "int0" handles all 3 queues and ENET_MII. "pps" is for the pulse
per second interrupt associated with 1588 precision time protocol(PTP).
-
Optional subnodes:
- mdio : specifies the mdio bus in the FEC, used as a container for phy nodes
according to phy.txt in the same directory
+Deprecated optional properties:
+ To avoid these, create a phy node according to phy.txt in the same
+ directory, and point the fec's "phy-handle" property to it. Then use
+ the phy's reset binding, again described by phy.txt.
+- phy-reset-gpios : Should specify the gpio for phy reset
+- phy-reset-duration : Reset duration in milliseconds. Should present
+ only if property "phy-reset-gpios" is available. Missing the property
+ will have the duration be 1 millisecond. Numbers greater than 1000 are
+ invalid and 1 millisecond will be used instead.
+- phy-reset-active-high : If present then the reset sequence using the GPIO
+ specified in the "phy-reset-gpios" property is reversed (H=reset state,
+ L=operation state).
+- phy-reset-post-delay : Post reset delay in milliseconds. If present then
+ a delay of phy-reset-post-delay milliseconds will be observed after the
+ phy-reset-gpios has been toggled. Can be omitted thus no delay is
+ observed. Delay is in range of 1ms to 1000ms. Other delays are invalid.
+
Example:
ethernet@83fec000 {
Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs.
Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC.
Use "cdns,zynqmp-gem" for Zynq Ultrascale+ MPSoC.
- Use "sifive,fu540-macb" for SiFive FU540-C000 SoC.
+ Use "sifive,fu540-c000-gem" for SiFive FU540-C000 SoC.
Or the generic form: "cdns,emac".
- reg: Address and length of the register set for the device
- For "sifive,fu540-macb", second range is required to specify the
+ For "sifive,fu540-c000-gem", second range is required to specify the
address and length of the registers for GEMGXL Management block.
- interrupts: Should contain macb interrupt
- phy-mode: See ethernet.txt file in the same directory.
examples:
- |
- sid@1c23800 {
+ efuse@1c23800 {
compatible = "allwinner,sun4i-a10-sid";
reg = <0x01c23800 0x10>;
};
- |
- sid@1c23800 {
+ efuse@1c23800 {
compatible = "allwinner,sun7i-a20-sid";
reg = <0x01c23800 0x200>;
};
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/nvmem/nvmem-consumer.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NVMEM (Non Volatile Memory) Consumer Device Tree Bindings
+
+maintainers:
+ - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+select: true
+
+properties:
+ nvmem:
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ description:
+ List of phandle to the nvmem providers.
+
+ nvmem-cells:
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ description:
+ List of phandle to the nvmem data cells.
+
+ nvmem-names:
+ $ref: /schemas/types.yaml#/definitions/string-array
+ description:
+ Names for the each nvmem provider.
+
+ nvmem-cell-names:
+ $ref: /schemas/types.yaml#/definitions/string-array
+ description:
+ Names for each nvmem-cells specified.
+
+dependencies:
+ nvmem-names: [ nvmem ]
+ nvmem-cell-names: [ nvmem-cells ]
+
+examples:
+ - |
+ tsens {
+ /* ... */
+ nvmem-cells = <&tsens_calibration>;
+ nvmem-cell-names = "calibration";
+ };
-= NVMEM(Non Volatile Memory) Data Device Tree Bindings =
-
-This binding is intended to represent the location of hardware
-configuration data stored in NVMEMs like eeprom, efuses and so on.
-
-On a significant proportion of boards, the manufacturer has stored
-some data on NVMEM, for the OS to be able to retrieve these information
-and act upon it. Obviously, the OS has to know about where to retrieve
-these data from, and where they are stored on the storage device.
-
-This document is here to document this.
-
-= Data providers =
-Contains bindings specific to provider drivers and data cells as children
-of this node.
-
-Optional properties:
- read-only: Mark the provider as read only.
-
-= Data cells =
-These are the child nodes of the provider which contain data cell
-information like offset and size in nvmem provider.
-
-Required properties:
-reg: specifies the offset in byte within the storage device.
-
-Optional properties:
-
-bits: Is pair of bit location and number of bits, which specifies offset
- in bit and number of bits within the address range specified by reg property.
- Offset takes values from 0-7.
-
-For example:
-
- /* Provider */
- qfprom: qfprom@700000 {
- ...
-
- /* Data cells */
- tsens_calibration: calib@404 {
- reg = <0x404 0x10>;
- };
-
- tsens_calibration_bckp: calib_bckp@504 {
- reg = <0x504 0x11>;
- bits = <6 128>
- };
-
- pvs_version: pvs-version@6 {
- reg = <0x6 0x2>
- bits = <7 2>
- };
-
- speed_bin: speed-bin@c{
- reg = <0xc 0x1>;
- bits = <2 3>;
-
- };
- ...
- };
-
-= Data consumers =
-Are device nodes which consume nvmem data cells/providers.
-
-Required-properties:
-nvmem-cells: list of phandle to the nvmem data cells.
-nvmem-cell-names: names for the each nvmem-cells specified. Required if
- nvmem-cells is used.
-
-Optional-properties:
-nvmem : list of phandles to nvmem providers.
-nvmem-names: names for the each nvmem provider. required if nvmem is used.
-
-For example:
-
- tsens {
- ...
- nvmem-cells = <&tsens_calibration>;
- nvmem-cell-names = "calibration";
- };
+This file has been moved to nvmem.yaml and nvmem-consumer.yaml.
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/nvmem/nvmem.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NVMEM (Non Volatile Memory) Device Tree Bindings
+
+maintainers:
+ - Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+
+description: |
+ This binding is intended to represent the location of hardware
+ configuration data stored in NVMEMs like eeprom, efuses and so on.
+
+ On a significant proportion of boards, the manufacturer has stored
+ some data on NVMEM, for the OS to be able to retrieve these
+ information and act upon it. Obviously, the OS has to know about
+ where to retrieve these data from, and where they are stored on the
+ storage device.
+
+properties:
+ $nodename:
+ pattern: "^(eeprom|efuse|nvram)(@.*|-[0-9a-f])*$"
+
+ "#address-cells":
+ const: 1
+
+ "#size-cells":
+ const: 1
+
+ read-only:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Mark the provider as read only.
+
+patternProperties:
+ "^.*@[0-9a-f]+$":
+ type: object
+
+ properties:
+ reg:
+ maxItems: 1
+ description:
+ Offset and size in bytes within the storage device.
+
+ bits:
+ maxItems: 1
+ items:
+ items:
+ - minimum: 0
+ maximum: 7
+ description:
+ Offset in bit within the address range specified by reg.
+ - minimum: 1
+ description:
+ Size in bit within the address range specified by reg.
+
+ required:
+ - reg
+
+ additionalProperties: false
+
+examples:
+ - |
+ qfprom: eeprom@700000 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+
+ /* ... */
+
+ /* Data cells */
+ tsens_calibration: calib@404 {
+ reg = <0x404 0x10>;
+ };
+
+ tsens_calibration_bckp: calib_bckp@504 {
+ reg = <0x504 0x11>;
+ bits = <6 128>;
+ };
+
+ pvs_version: pvs-version@6 {
+ reg = <0x6 0x2>;
+ bits = <7 2>;
+ };
+
+ speed_bin: speed-bin@c{
+ reg = <0xc 0x1>;
+ bits = <2 3>;
+ };
+ };
+
+...
# SPDX-License-Identifier: GPL-2.0
%YAML 1.2
---
-$id: http://devicetree.org/schemas/display/allwinner,sun6i-a31-mipi-dphy.yaml#
+$id: http://devicetree.org/schemas/phy/allwinner,sun6i-a31-mipi-dphy.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Allwinner A31 MIPI D-PHY Controller Device Tree Bindings
hwlocks: true
st,syscfg:
- $ref: "/schemas/types.yaml#/definitions/phandle-array"
+ allOf:
+ - $ref: "/schemas/types.yaml#/definitions/phandle-array"
description: Should be phandle/offset/mask
items:
- description: Phandle to the syscon node which includes IRQ mux selection.
+++ /dev/null
-===================
-RISC-V CPU Bindings
-===================
-
-The device tree allows to describe the layout of CPUs in a system through
-the "cpus" node, which in turn contains a number of subnodes (ie "cpu")
-defining properties for every cpu.
-
-Bindings for CPU nodes follow the Devicetree Specification, available from:
-
-https://www.devicetree.org/specifications/
-
-with updates for 32-bit and 64-bit RISC-V systems provided in this document.
-
-===========
-Terminology
-===========
-
-This document uses some terminology common to the RISC-V community that is not
-widely used, the definitions of which are listed here:
-
-* hart: A hardware execution context, which contains all the state mandated by
- the RISC-V ISA: a PC and some registers. This terminology is designed to
- disambiguate software's view of execution contexts from any particular
- microarchitectural implementation strategy. For example, my Intel laptop is
- described as having one socket with two cores, each of which has two hyper
- threads. Therefore this system has four harts.
-
-=====================================
-cpus and cpu node bindings definition
-=====================================
-
-The RISC-V architecture, in accordance with the Devicetree Specification,
-requires the cpus and cpu nodes to be present and contain the properties
-described below.
-
-- cpus node
-
- Description: Container of cpu nodes
-
- The node name must be "cpus".
-
- A cpus node must define the following properties:
-
- - #address-cells
- Usage: required
- Value type: <u32>
- Definition: must be set to 1
- - #size-cells
- Usage: required
- Value type: <u32>
- Definition: must be set to 0
-
-- cpu node
-
- Description: Describes a hart context
-
- PROPERTIES
-
- - device_type
- Usage: required
- Value type: <string>
- Definition: must be "cpu"
- - reg
- Usage: required
- Value type: <u32>
- Definition: The hart ID of this CPU node
- - compatible:
- Usage: required
- Value type: <stringlist>
- Definition: must contain "riscv", may contain one of
- "sifive,rocket0"
- - mmu-type:
- Usage: optional
- Value type: <string>
- Definition: Specifies the CPU's MMU type. Possible values are
- "riscv,sv32"
- "riscv,sv39"
- "riscv,sv48"
- - riscv,isa:
- Usage: required
- Value type: <string>
- Definition: Contains the RISC-V ISA string of this hart. These
- ISA strings are defined by the RISC-V ISA manual.
-
-Example: SiFive Freedom U540G Development Kit
----------------------------------------------
-
-This system contains two harts: a hart marked as disabled that's used for
-low-level system tasks and should be ignored by Linux, and a second hart that
-Linux is allowed to run on.
-
- cpus {
- #address-cells = <1>;
- #size-cells = <0>;
- timebase-frequency = <1000000>;
- cpu@0 {
- clock-frequency = <1600000000>;
- compatible = "sifive,rocket0", "riscv";
- device_type = "cpu";
- i-cache-block-size = <64>;
- i-cache-sets = <128>;
- i-cache-size = <16384>;
- next-level-cache = <&L15 &L0>;
- reg = <0>;
- riscv,isa = "rv64imac";
- status = "disabled";
- L10: interrupt-controller {
- #interrupt-cells = <1>;
- compatible = "riscv,cpu-intc";
- interrupt-controller;
- };
- };
- cpu@1 {
- clock-frequency = <1600000000>;
- compatible = "sifive,rocket0", "riscv";
- d-cache-block-size = <64>;
- d-cache-sets = <64>;
- d-cache-size = <32768>;
- d-tlb-sets = <1>;
- d-tlb-size = <32>;
- device_type = "cpu";
- i-cache-block-size = <64>;
- i-cache-sets = <64>;
- i-cache-size = <32768>;
- i-tlb-sets = <1>;
- i-tlb-size = <32>;
- mmu-type = "riscv,sv39";
- next-level-cache = <&L15 &L0>;
- reg = <1>;
- riscv,isa = "rv64imafdc";
- status = "okay";
- tlb-split;
- L13: interrupt-controller {
- #interrupt-cells = <1>;
- compatible = "riscv,cpu-intc";
- interrupt-controller;
- };
- };
- };
-
-Example: Spike ISA Simulator with 1 Hart
-----------------------------------------
-
-This device tree matches the Spike ISA golden model as run with `spike -p1`.
-
- cpus {
- cpu@0 {
- device_type = "cpu";
- reg = <0x00000000>;
- status = "okay";
- compatible = "riscv";
- riscv,isa = "rv64imafdc";
- mmu-type = "riscv,sv48";
- clock-frequency = <0x3b9aca00>;
- interrupt-controller {
- #interrupt-cells = <0x00000001>;
- interrupt-controller;
- compatible = "riscv,cpu-intc";
- }
- }
- }
- Paul Walmsley <paul.walmsley@sifive.com>
- Palmer Dabbelt <palmer@sifive.com>
+description: |
+ This document uses some terminology common to the RISC-V community
+ that is not widely used, the definitions of which are listed here:
+
+ hart: A hardware execution context, which contains all the state
+ mandated by the RISC-V ISA: a PC and some registers. This
+ terminology is designed to disambiguate software's view of execution
+ contexts from any particular microarchitectural implementation
+ strategy. For example, an Intel laptop containing one socket with
+ two cores, each of which has two hyperthreads, could be described as
+ having four harts.
+
properties:
compatible:
items:
User-Level ISA document, available from
https://riscv.org/specifications/
+ While the isa strings in ISA specification are case
+ insensitive, letters in the riscv,isa string must be all
+ lowercase to simplify parsing.
+
timebase-frequency:
type: integer
minimum: 1
compatible:
items:
- enum:
- - sifive,freedom-unleashed-a00
+ - sifive,hifive-unleashed-a00
- const: sifive,fu540-c000
- const: sifive,fu540
...
Compatible of the SPI device.
reg:
- maxItems: 1
minimum: 0
maximum: 256
description:
# Copyright 2018 Linaro Ltd.
%YAML 1.2
---
-$id: "http://devicetree.org/schemas/timer/intel-ixp4xx-timer.yaml#"
+$id: "http://devicetree.org/schemas/timer/intel,ixp4xx-timer.yaml#"
$schema: "http://devicetree.org/meta-schemas/core.yaml#"
title: Intel IXP4xx XScale Networking Processors Timers
- power-on-time-ms : Specifies the time it takes from the time the host
initiates the power-on sequence to a port until the port has adequate
power. The value is given in ms in a 0 - 510 range (default is 100ms).
- - swap-dx-lanes : Specifies the downstream ports which will swap the
- differential-pair (D+/D-), default is not-swapped.
- - swap-us-lanes : Selects the upstream port differential-pair (D+/D-)
- swapping (boolean, default is not-swapped)
+ - swap-dx-lanes : Specifies the ports which will swap the differential-pair
+ (D+/D-), default is not-swapped.
Examples:
usb2512b@2c {
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = 'Linux Kernel Documentation Guide'
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'kernel-doc-guide.tex', 'Linux Kernel Documentation Guide',
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Linux 802.11 Driver Developer's Guide"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', '80211.tex', project,
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "The Linux driver implementer's API guide"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'driver-api.tex', project,
- 'The kernel development community', 'manual'),
-]
Several sysfs attributes are generated by the Generic Counter interface,
and reside under the /sys/bus/counter/devices/counterX directory, where
counterX refers to the respective counter device. Please see
-Documentation/ABI/testing/sys-bus-counter-generic-sysfs for detailed
+Documentation/ABI/testing/sysfs-bus-counter for detailed
information on each Generic Counter interface sysfs attribute.
Through these sysfs attributes, programs and scripts may interact with
For a more detailed breakdown of the available Generic Counter interface
sysfs attributes, please refer to the
-Documentation/ABI/testing/sys-bus-counter file.
+Documentation/ABI/testing/sysfs-bus-counter file.
The Signals and Counts associated with the Counter device are registered
to the system as well by the counter_register function. The
In order to get reference to a PHY without help from DeviceTree, the framework
offers lookups which can be compared to clkdev that allow clk structures to be
-bound to devices. A lookup can be made be made during runtime when a handle to
-the struct phy already exists.
+bound to devices. A lookup can be made during runtime when a handle to the
+struct phy already exists.
The framework offers the following API for registering and unregistering the
lookups::
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Device Power Management"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'pm.tex', project,
- 'The kernel development community', 'manual'),
-]
- T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl
currently the only two server side copy mechanisms supported)
-b) improved sparse file support
+b) improved sparse file support (fiemap and SEEK_HOLE are implemented
+but additional features would be supportable by the protocol).
c) Directory entry caching relies on a 1 second timer, rather than
using Directory Leases, currently only the root file handle is cached longer
d) quota support (needs minor kernel change since quota calls
to make it to network filesystems or deviceless filesystems)
-e) Additional use cases where we use "compoounding" (e.g. open/query/close
-and open/setinfo/close) to reduce the number of roundtrips, and also
-open to reduce redundant opens (using deferred close and reference counts more).
+e) Additional use cases can be optimized to use "compounding"
+(e.g. open/query/close and open/setinfo/close) to reduce the number
+of roundtrips to the server and improve performance. Various cases
+(stat, statfs, create, unlink, mkdir) already have been improved by
+using compounding but more can be done. In addition we could significantly
+reduce redundant opens by using deferred close (with handle caching leases)
+and better using reference counters on file handles.
f) Finish inotify support so kde and gnome file list windows
will autorefresh (partially complete by Asser). Needs minor kernel
exists. Also better integration with winbind for resolving SID owners
k) Add tools to take advantage of more smb3 specific ioctls and features
-(passthrough ioctl/fsctl for sending various SMB3 fsctls to the server
-is in progress, and a passthrough query_info call is already implemented
-in cifs.ko to allow smb3 info levels queries to be sent from userspace)
+(passthrough ioctl/fsctl is now implemented in cifs.ko to allow sending
+various SMB3 fsctls and query info and set info calls directly from user space)
+Add tools to make setting various non-POSIX metadata attributes easier
+from tools (e.g. extending what was done in smb-info tool).
l) encrypted file support
m) improved stats gathering tools (perhaps integration with nfsometer?)
to extend and make easier to use what is currently in /proc/fs/cifs/Stats
-n) allow setting more NTFS/SMB3 file attributes remotely (currently limited to compressed
-file attribute via chflags) and improve user space tools for managing and
-viewing them.
+n) Add support for claims based ACLs ("DAC")
o) mount helper GUI (to simplify the various configuration options on mount)
w) Add support for additional strong encryption types, and additional spnego
authentication mechanisms (see MS-SMB2)
+x) Finish support for SMB3.1.1 compression
+
KNOWN BUGS
====================================
See http://bugzilla.samba.org - search on product "CifsVFS" for
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Linux Filesystems API"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'filesystems.tex', project,
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Linux GPU Driver Developer's Guide"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'gpu.tex', project,
- 'The kernel development community', 'manual'),
-]
Addresses scanned: PCI space
- Datasheet: http://support.amd.com/us/Processor_TechDocs/32559.pdf
+ Datasheet: http://www.amd.com/system/files/TechDocs/32559.pdf
Author: Rudolf Marek
netlabel/index
networking/index
pcmcia/index
+ power/index
target/index
timers/index
watchdog/index
+ virtual/index
input/index
hwmon/index
gpu/index
arm64/index
ia64/index
m68k/index
+ powerpc/index
riscv/index
s390/index
sh/index
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "The Linux input driver subsystem"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'linux-input.tex', project,
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Kernel Hacking Guides"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'kernel-hacking.tex', project,
- 'The kernel development community', 'manual'),
-]
**changes** the list will have to get the write lock.
NOTE! RCU is better for list traversal, but requires careful
- attention to design detail (see Documentation/RCU/listRCU.txt).
+ attention to design detail (see Documentation/RCU/listRCU.rst).
Also, you cannot "upgrade" a read-lock to a write-lock, so if you at _any_
time need to do any changes (even if you don't do it every time), you have
NOTE! We are working hard to remove reader-writer spinlocks in most
cases, so please don't add a new one without consensus. (Instead, see
- Documentation/RCU/rcu.txt for complete information.)
+ Documentation/RCU/rcu.rst for complete information.)
----
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = 'Linux Kernel Development Documentation'
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'maintainer.tex', 'Linux Kernel Development Documentation',
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-# SPDX-License-Identifier: GPL-2.0
-
-project = 'Linux Media Subsystem Documentation'
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'media.tex', 'Linux Media Subsystem Documentation',
- 'The kernel development community', 'manual'),
-]
[*] For information on bus mastering DMA and coherency please read:
- Documentation/PCI/pci.rst
+ Documentation/driver-api/pci/pci.rst
Documentation/DMA-API-HOWTO.txt
Documentation/DMA-API.txt
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Linux Networking Documentation"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'networking.tex', project,
- 'The kernel development community', 'manual'),
-]
Following minimum set of TLS-related statistics should be reported
by the driver:
- * ``rx_tls_decrypted`` - number of successfully decrypted TLS segments
- * ``tx_tls_encrypted`` - number of in-order TLS segments passed to device
- for encryption
+ * ``rx_tls_decrypted_packets`` - number of successfully decrypted RX packets
+ which were part of a TLS stream.
+ * ``rx_tls_decrypted_bytes`` - number of TLS payload bytes in RX packets
+ which were successfully decrypted.
+ * ``tx_tls_encrypted_packets`` - number of TX packets passed to the device
+ for encryption of their TLS payload.
+ * ``tx_tls_encrypted_bytes`` - number of TLS payload bytes in TX packets
+ passed to the device for encryption.
+ * ``tx_tls_ctx`` - number of TLS TX HW offload contexts added to device for
+ encryption.
* ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream
- but did not arrive in the expected order
- * ``tx_tls_drop_no_sync_data`` - number of TX packets dropped because
- they arrived out of order and associated record could not be found
+ but did not arrive in the expected order.
+ * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of
+ a TLS stream dropped, because they arrived out of order and associated
+ record could not be found.
+ * ``tx_tls_drop_bypass_req`` - number of TX packets which were part of a TLS
+ stream dropped, because they contain both data that has been encrypted by
+ software and data that expects hardware crypto offload.
Notable corner cases, exceptions and additional requirements
============================================================
These flags will be acted upon accordingly by the core ``ktls`` code.
TLS device feature flags only control adding of new TLS connection
offloads, old connections will remain active after flags are cleared.
-
-Known bugs
-==========
-
-skb_orphan() leaks clear text
------------------------------
-
-Currently drivers depend on the :c:member:`sk` member of
-:c:type:`struct sk_buff <sk_buff>` to identify segments requiring
-encryption. Any operation which removes or does not preserve the socket
-association such as :c:func:`skb_orphan` or :c:func:`skb_clone`
-will cause the driver to miss the packets and lead to clear text leaks.
-
-Redirects leak clear text
--------------------------
-
-In the RX direction, if segment has already been decrypted by the device
-and it gets redirected or mirrored - clear text will be transmitted out.
media, receives them from user space program and instead of sending
packets via physical media sends them to the user space program.
-Let's say that you configured IPX on the tap0, then whenever
-the kernel sends an IPX packet to tap0, it is passed to the application
+Let's say that you configured IPv6 on the tap0, then whenever
+the kernel sends an IPv6 packet to tap0, it is passed to the application
(VTun for example). The application encrypts, compresses and sends it to
the other side over TCP or UDP. The application on the other side decompresses
and decrypts the data received and writes the packet to the TAP device,
-:orphan:
+.. SPDX-License-Identifier: GPL-2.0
================
Power Management
+++ /dev/null
-DAWR issues on POWER9
-============================
-
-On POWER9 the Data Address Watchpoint Register (DAWR) can cause a checkstop
-if it points to cache inhibited (CI) memory. Currently Linux has no way to
-disinguish CI memory when configuring the DAWR, so (for now) the DAWR is
-disabled by this commit:
-
- commit 9654153158d3e0684a1bdb76dbababdb7111d5a0
- Author: Michael Neuling <mikey@neuling.org>
- Date: Tue Mar 27 15:37:24 2018 +1100
- powerpc: Disable DAWR in the base POWER9 CPU features
-
-Technical Details:
-============================
-
-DAWR has 6 different ways of being set.
-1) ptrace
-2) h_set_mode(DAWR)
-3) h_set_dabr()
-4) kvmppc_set_one_reg()
-5) xmon
-
-For ptrace, we now advertise zero breakpoints on POWER9 via the
-PPC_PTRACE_GETHWDBGINFO call. This results in GDB falling back to
-software emulation of the watchpoint (which is slow).
-
-h_set_mode(DAWR) and h_set_dabr() will now return an error to the
-guest on a POWER9 host. Current Linux guests ignore this error, so
-they will silently not get the DAWR.
-
-kvmppc_set_one_reg() will store the value in the vcpu but won't
-actually set it on POWER9 hardware. This is done so we don't break
-migration from POWER8 to POWER9, at the cost of silently losing the
-DAWR on the migration.
-
-For xmon, the 'bd' command will return an error on P9.
-
-Consequences for users
-============================
-
-For GDB watchpoints (ie 'watch' command) on POWER9 bare metal , GDB
-will accept the command. Unfortunately since there is no hardware
-support for the watchpoint, GDB will software emulate the watchpoint
-making it run very slowly.
-
-The same will also be true for any guests started on a POWER9
-host. The watchpoint will fail and GDB will fall back to software
-emulation.
-
-If a guest is started on a POWER8 host, GDB will accept the watchpoint
-and configure the hardware to use the DAWR. This will run at full
-speed since it can use the hardware emulation. Unfortunately if this
-guest is migrated to a POWER9 host, the watchpoint will be lost on the
-POWER9. Loads and stores to the watchpoint locations will not be
-trapped in GDB. The watchpoint is remembered, so if the guest is
-migrated back to the POWER8 host, it will start working again.
-
-Force enabling the DAWR
-=============================
-Kernels (since ~v5.2) have an option to force enable the DAWR via:
-
- echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous
-
-This enables the DAWR even on POWER9.
-
-This is a dangerous setting, USE AT YOUR OWN RISK.
-
-Some users may not care about a bad user crashing their box
-(ie. single user/desktop systems) and really want the DAWR. This
-allows them to force enable DAWR.
-
-This flag can also be used to disable DAWR access. Once this is
-cleared, all DAWR access should be cleared immediately and your
-machine once again safe from crashing.
-
-Userspace may get confused by toggling this. If DAWR is force
-enabled/disabled between getting the number of breakpoints (via
-PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an
-inconsistent view of what's available. Similarly for guests.
-
-For the DAWR to be enabled in a KVM guest, the DAWR needs to be force
-enabled in the host AND the guest. For this reason, this won't work on
-POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the
-dawr_enable_dangerous file will fail if the hypervisor doesn't support
-writing the DAWR.
-
-To double check the DAWR is working, run this kernel selftest:
- tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
-Any errors/failures/skips mean something is wrong.
--- /dev/null
+========================
+The PowerPC boot wrapper
+========================
+
+Copyright (C) Secret Lab Technologies Ltd.
+
+PowerPC image targets compresses and wraps the kernel image (vmlinux) with
+a boot wrapper to make it usable by the system firmware. There is no
+standard PowerPC firmware interface, so the boot wrapper is designed to
+be adaptable for each kind of image that needs to be built.
+
+The boot wrapper can be found in the arch/powerpc/boot/ directory. The
+Makefile in that directory has targets for all the available image types.
+The different image types are used to support all of the various firmware
+interfaces found on PowerPC platforms. OpenFirmware is the most commonly
+used firmware type on general purpose PowerPC systems from Apple, IBM and
+others. U-Boot is typically found on embedded PowerPC hardware, but there
+are a handful of other firmware implementations which are also popular. Each
+firmware interface requires a different image format.
+
+The boot wrapper is built from the makefile in arch/powerpc/boot/Makefile and
+it uses the wrapper script (arch/powerpc/boot/wrapper) to generate target
+image. The details of the build system is discussed in the next section.
+Currently, the following image format targets exist:
+
+ ==================== ========================================================
+ cuImage.%: Backwards compatible uImage for older version of
+ U-Boot (for versions that don't understand the device
+ tree). This image embeds a device tree blob inside
+ the image. The boot wrapper, kernel and device tree
+ are all embedded inside the U-Boot uImage file format
+ with boot wrapper code that extracts data from the old
+ bd_info structure and loads the data into the device
+ tree before jumping into the kernel.
+
+ Because of the series of #ifdefs found in the
+ bd_info structure used in the old U-Boot interfaces,
+ cuImages are platform specific. Each specific
+ U-Boot platform has a different platform init file
+ which populates the embedded device tree with data
+ from the platform specific bd_info file. The platform
+ specific cuImage platform init code can be found in
+ `arch/powerpc/boot/cuboot.*.c`. Selection of the correct
+ cuImage init code for a specific board can be found in
+ the wrapper structure.
+
+ dtbImage.%: Similar to zImage, except device tree blob is embedded
+ inside the image instead of provided by firmware. The
+ output image file can be either an elf file or a flat
+ binary depending on the platform.
+
+ dtbImages are used on systems which do not have an
+ interface for passing a device tree directly.
+ dtbImages are similar to simpleImages except that
+ dtbImages have platform specific code for extracting
+ data from the board firmware, but simpleImages do not
+ talk to the firmware at all.
+
+ PlayStation 3 support uses dtbImage. So do Embedded
+ Planet boards using the PlanetCore firmware. Board
+ specific initialization code is typically found in a
+ file named arch/powerpc/boot/<platform>.c; but this
+ can be overridden by the wrapper script.
+
+ simpleImage.%: Firmware independent compressed image that does not
+ depend on any particular firmware interface and embeds
+ a device tree blob. This image is a flat binary that
+ can be loaded to any location in RAM and jumped to.
+ Firmware cannot pass any configuration data to the
+ kernel with this image type and it depends entirely on
+ the embedded device tree for all information.
+
+ The simpleImage is useful for booting systems with
+ an unknown firmware interface or for booting from
+ a debugger when no firmware is present (such as on
+ the Xilinx Virtex platform). The only assumption that
+ simpleImage makes is that RAM is correctly initialized
+ and that the MMU is either off or has RAM mapped to
+ base address 0.
+
+ simpleImage also supports inserting special platform
+ specific initialization code to the start of the bootup
+ sequence. The virtex405 platform uses this feature to
+ ensure that the cache is invalidated before caching
+ is enabled. Platform specific initialization code is
+ added as part of the wrapper script and is keyed on
+ the image target name. For example, all
+ simpleImage.virtex405-* targets will add the
+ virtex405-head.S initialization code (This also means
+ that the dts file for virtex405 targets should be
+ named (virtex405-<board>.dts). Search the wrapper
+ script for 'virtex405' and see the file
+ arch/powerpc/boot/virtex405-head.S for details.
+
+ treeImage.%; Image format for used with OpenBIOS firmware found
+ on some ppc4xx hardware. This image embeds a device
+ tree blob inside the image.
+
+ uImage: Native image format used by U-Boot. The uImage target
+ does not add any boot code. It just wraps a compressed
+ vmlinux in the uImage data structure. This image
+ requires a version of U-Boot that is able to pass
+ a device tree to the kernel at boot. If using an older
+ version of U-Boot, then you need to use a cuImage
+ instead.
+
+ zImage.%: Image format which does not embed a device tree.
+ Used by OpenFirmware and other firmware interfaces
+ which are able to supply a device tree. This image
+ expects firmware to provide the device tree at boot.
+ Typically, if you have general purpose PowerPC
+ hardware then you want this image format.
+ ==================== ========================================================
+
+Image types which embed a device tree blob (simpleImage, dtbImage, treeImage,
+and cuImage) all generate the device tree blob from a file in the
+arch/powerpc/boot/dts/ directory. The Makefile selects the correct device
+tree source based on the name of the target. Therefore, if the kernel is
+built with 'make treeImage.walnut simpleImage.virtex405-ml403', then the
+build system will use arch/powerpc/boot/dts/walnut.dts to build
+treeImage.walnut and arch/powerpc/boot/dts/virtex405-ml403.dts to build
+the simpleImage.virtex405-ml403.
+
+Two special targets called 'zImage' and 'zImage.initrd' also exist. These
+targets build all the default images as selected by the kernel configuration.
+Default images are selected by the boot wrapper Makefile
+(arch/powerpc/boot/Makefile) by adding targets to the $image-y variable. Look
+at the Makefile to see which default image targets are available.
+
+How it is built
+---------------
+arch/powerpc is designed to support multiplatform kernels, which means
+that a single vmlinux image can be booted on many different target boards.
+It also means that the boot wrapper must be able to wrap for many kinds of
+images on a single build. The design decision was made to not use any
+conditional compilation code (#ifdef, etc) in the boot wrapper source code.
+All of the boot wrapper pieces are buildable at any time regardless of the
+kernel configuration. Building all the wrapper bits on every kernel build
+also ensures that obscure parts of the wrapper are at the very least compile
+tested in a large variety of environments.
+
+The wrapper is adapted for different image types at link time by linking in
+just the wrapper bits that are appropriate for the image type. The 'wrapper
+script' (found in arch/powerpc/boot/wrapper) is called by the Makefile and
+is responsible for selecting the correct wrapper bits for the image type.
+The arguments are well documented in the script's comment block, so they
+are not repeated here. However, it is worth mentioning that the script
+uses the -p (platform) argument as the main method of deciding which wrapper
+bits to compile in. Look for the large 'case "$platform" in' block in the
+middle of the script. This is also the place where platform specific fixups
+can be selected by changing the link order.
+
+In particular, care should be taken when working with cuImages. cuImage
+wrapper bits are very board specific and care should be taken to make sure
+the target you are trying to build is supported by the wrapper bits.
+++ /dev/null
-The PowerPC boot wrapper
-------------------------
-Copyright (C) Secret Lab Technologies Ltd.
-
-PowerPC image targets compresses and wraps the kernel image (vmlinux) with
-a boot wrapper to make it usable by the system firmware. There is no
-standard PowerPC firmware interface, so the boot wrapper is designed to
-be adaptable for each kind of image that needs to be built.
-
-The boot wrapper can be found in the arch/powerpc/boot/ directory. The
-Makefile in that directory has targets for all the available image types.
-The different image types are used to support all of the various firmware
-interfaces found on PowerPC platforms. OpenFirmware is the most commonly
-used firmware type on general purpose PowerPC systems from Apple, IBM and
-others. U-Boot is typically found on embedded PowerPC hardware, but there
-are a handful of other firmware implementations which are also popular. Each
-firmware interface requires a different image format.
-
-The boot wrapper is built from the makefile in arch/powerpc/boot/Makefile and
-it uses the wrapper script (arch/powerpc/boot/wrapper) to generate target
-image. The details of the build system is discussed in the next section.
-Currently, the following image format targets exist:
-
- cuImage.%: Backwards compatible uImage for older version of
- U-Boot (for versions that don't understand the device
- tree). This image embeds a device tree blob inside
- the image. The boot wrapper, kernel and device tree
- are all embedded inside the U-Boot uImage file format
- with boot wrapper code that extracts data from the old
- bd_info structure and loads the data into the device
- tree before jumping into the kernel.
- Because of the series of #ifdefs found in the
- bd_info structure used in the old U-Boot interfaces,
- cuImages are platform specific. Each specific
- U-Boot platform has a different platform init file
- which populates the embedded device tree with data
- from the platform specific bd_info file. The platform
- specific cuImage platform init code can be found in
- arch/powerpc/boot/cuboot.*.c. Selection of the correct
- cuImage init code for a specific board can be found in
- the wrapper structure.
- dtbImage.%: Similar to zImage, except device tree blob is embedded
- inside the image instead of provided by firmware. The
- output image file can be either an elf file or a flat
- binary depending on the platform.
- dtbImages are used on systems which do not have an
- interface for passing a device tree directly.
- dtbImages are similar to simpleImages except that
- dtbImages have platform specific code for extracting
- data from the board firmware, but simpleImages do not
- talk to the firmware at all.
- PlayStation 3 support uses dtbImage. So do Embedded
- Planet boards using the PlanetCore firmware. Board
- specific initialization code is typically found in a
- file named arch/powerpc/boot/<platform>.c; but this
- can be overridden by the wrapper script.
- simpleImage.%: Firmware independent compressed image that does not
- depend on any particular firmware interface and embeds
- a device tree blob. This image is a flat binary that
- can be loaded to any location in RAM and jumped to.
- Firmware cannot pass any configuration data to the
- kernel with this image type and it depends entirely on
- the embedded device tree for all information.
- The simpleImage is useful for booting systems with
- an unknown firmware interface or for booting from
- a debugger when no firmware is present (such as on
- the Xilinx Virtex platform). The only assumption that
- simpleImage makes is that RAM is correctly initialized
- and that the MMU is either off or has RAM mapped to
- base address 0.
- simpleImage also supports inserting special platform
- specific initialization code to the start of the bootup
- sequence. The virtex405 platform uses this feature to
- ensure that the cache is invalidated before caching
- is enabled. Platform specific initialization code is
- added as part of the wrapper script and is keyed on
- the image target name. For example, all
- simpleImage.virtex405-* targets will add the
- virtex405-head.S initialization code (This also means
- that the dts file for virtex405 targets should be
- named (virtex405-<board>.dts). Search the wrapper
- script for 'virtex405' and see the file
- arch/powerpc/boot/virtex405-head.S for details.
- treeImage.%; Image format for used with OpenBIOS firmware found
- on some ppc4xx hardware. This image embeds a device
- tree blob inside the image.
- uImage: Native image format used by U-Boot. The uImage target
- does not add any boot code. It just wraps a compressed
- vmlinux in the uImage data structure. This image
- requires a version of U-Boot that is able to pass
- a device tree to the kernel at boot. If using an older
- version of U-Boot, then you need to use a cuImage
- instead.
- zImage.%: Image format which does not embed a device tree.
- Used by OpenFirmware and other firmware interfaces
- which are able to supply a device tree. This image
- expects firmware to provide the device tree at boot.
- Typically, if you have general purpose PowerPC
- hardware then you want this image format.
-
-Image types which embed a device tree blob (simpleImage, dtbImage, treeImage,
-and cuImage) all generate the device tree blob from a file in the
-arch/powerpc/boot/dts/ directory. The Makefile selects the correct device
-tree source based on the name of the target. Therefore, if the kernel is
-built with 'make treeImage.walnut simpleImage.virtex405-ml403', then the
-build system will use arch/powerpc/boot/dts/walnut.dts to build
-treeImage.walnut and arch/powerpc/boot/dts/virtex405-ml403.dts to build
-the simpleImage.virtex405-ml403.
-
-Two special targets called 'zImage' and 'zImage.initrd' also exist. These
-targets build all the default images as selected by the kernel configuration.
-Default images are selected by the boot wrapper Makefile
-(arch/powerpc/boot/Makefile) by adding targets to the $image-y variable. Look
-at the Makefile to see which default image targets are available.
-
-How it is built
----------------
-arch/powerpc is designed to support multiplatform kernels, which means
-that a single vmlinux image can be booted on many different target boards.
-It also means that the boot wrapper must be able to wrap for many kinds of
-images on a single build. The design decision was made to not use any
-conditional compilation code (#ifdef, etc) in the boot wrapper source code.
-All of the boot wrapper pieces are buildable at any time regardless of the
-kernel configuration. Building all the wrapper bits on every kernel build
-also ensures that obscure parts of the wrapper are at the very least compile
-tested in a large variety of environments.
-
-The wrapper is adapted for different image types at link time by linking in
-just the wrapper bits that are appropriate for the image type. The 'wrapper
-script' (found in arch/powerpc/boot/wrapper) is called by the Makefile and
-is responsible for selecting the correct wrapper bits for the image type.
-The arguments are well documented in the script's comment block, so they
-are not repeated here. However, it is worth mentioning that the script
-uses the -p (platform) argument as the main method of deciding which wrapper
-bits to compile in. Look for the large 'case "$platform" in' block in the
-middle of the script. This is also the place where platform specific fixups
-can be selected by changing the link order.
-
-In particular, care should be taken when working with cuImages. cuImage
-wrapper bits are very board specific and care should be taken to make sure
-the target you are trying to build is supported by the wrapper bits.
--- /dev/null
+============
+CPU Families
+============
+
+This document tries to summarise some of the different cpu families that exist
+and are supported by arch/powerpc.
+
+
+Book3S (aka sPAPR)
+------------------
+
+- Hash MMU
+- Mix of 32 & 64 bit::
+
+ +--------------+ +----------------+
+ | Old POWER | --------------> | RS64 (threads) |
+ +--------------+ +----------------+
+ |
+ |
+ v
+ +--------------+ +----------------+ +------+
+ | 601 | --------------> | 603 | ---> | e300 |
+ +--------------+ +----------------+ +------+
+ | |
+ | |
+ v v
+ +--------------+ +----------------+ +-------+
+ | 604 | | 750 (G3) | ---> | 750CX |
+ +--------------+ +----------------+ +-------+
+ | | |
+ | | |
+ v v v
+ +--------------+ +----------------+ +-------+
+ | 620 (64 bit) | | 7400 | | 750CL |
+ +--------------+ +----------------+ +-------+
+ | | |
+ | | |
+ v v v
+ +--------------+ +----------------+ +-------+
+ | POWER3/630 | | 7410 | | 750FX |
+ +--------------+ +----------------+ +-------+
+ | |
+ | |
+ v v
+ +--------------+ +----------------+
+ | POWER3+ | | 7450 |
+ +--------------+ +----------------+
+ | |
+ | |
+ v v
+ +--------------+ +----------------+
+ | POWER4 | | 7455 |
+ +--------------+ +----------------+
+ | |
+ | |
+ v v
+ +--------------+ +-------+ +----------------+
+ | POWER4+ | --> | 970 | | 7447 |
+ +--------------+ +-------+ +----------------+
+ | | |
+ | | |
+ v v v
+ +--------------+ +-------+ +----------------+
+ | POWER5 | | 970FX | | 7448 |
+ +--------------+ +-------+ +----------------+
+ | | |
+ | | |
+ v v v
+ +--------------+ +-------+ +----------------+
+ | POWER5+ | | 970MP | | e600 |
+ +--------------+ +-------+ +----------------+
+ |
+ |
+ v
+ +--------------+
+ | POWER5++ |
+ +--------------+
+ |
+ |
+ v
+ +--------------+ +-------+
+ | POWER6 | <-?-> | Cell |
+ +--------------+ +-------+
+ |
+ |
+ v
+ +--------------+
+ | POWER7 |
+ +--------------+
+ |
+ |
+ v
+ +--------------+
+ | POWER7+ |
+ +--------------+
+ |
+ |
+ v
+ +--------------+
+ | POWER8 |
+ +--------------+
+
+
+ +---------------+
+ | PA6T (64 bit) |
+ +---------------+
+
+
+IBM BookE
+---------
+
+- Software loaded TLB.
+- All 32 bit::
+
+ +--------------+
+ | 401 |
+ +--------------+
+ |
+ |
+ v
+ +--------------+
+ | 403 |
+ +--------------+
+ |
+ |
+ v
+ +--------------+
+ | 405 |
+ +--------------+
+ |
+ |
+ v
+ +--------------+
+ | 440 |
+ +--------------+
+ |
+ |
+ v
+ +--------------+ +----------------+
+ | 450 | --> | BG/P |
+ +--------------+ +----------------+
+ |
+ |
+ v
+ +--------------+
+ | 460 |
+ +--------------+
+ |
+ |
+ v
+ +--------------+
+ | 476 |
+ +--------------+
+
+
+Motorola/Freescale 8xx
+----------------------
+
+- Software loaded with hardware assist.
+- All 32 bit::
+
+ +-------------+
+ | MPC8xx Core |
+ +-------------+
+
+
+Freescale BookE
+---------------
+
+- Software loaded TLB.
+- e6500 adds HW loaded indirect TLB entries.
+- Mix of 32 & 64 bit::
+
+ +--------------+
+ | e200 |
+ +--------------+
+
+
+ +--------------------------------+
+ | e500 |
+ +--------------------------------+
+ |
+ |
+ v
+ +--------------------------------+
+ | e500v2 |
+ +--------------------------------+
+ |
+ |
+ v
+ +--------------------------------+
+ | e500mc (Book3e) |
+ +--------------------------------+
+ |
+ |
+ v
+ +--------------------------------+
+ | e5500 (64 bit) |
+ +--------------------------------+
+ |
+ |
+ v
+ +--------------------------------+
+ | e6500 (HW TLB) (Multithreaded) |
+ +--------------------------------+
+
+
+IBM A2 core
+-----------
+
+- Book3E, software loaded TLB + HW loaded indirect TLB entries.
+- 64 bit::
+
+ +--------------+ +----------------+
+ | A2 core | --> | WSP |
+ +--------------+ +----------------+
+ |
+ |
+ v
+ +--------------+
+ | BG/Q |
+ +--------------+
+++ /dev/null
-CPU Families
-============
-
-This document tries to summarise some of the different cpu families that exist
-and are supported by arch/powerpc.
-
-
-Book3S (aka sPAPR)
-------------------
-
- - Hash MMU
- - Mix of 32 & 64 bit
-
- +--------------+ +----------------+
- | Old POWER | --------------> | RS64 (threads) |
- +--------------+ +----------------+
- |
- |
- v
- +--------------+ +----------------+ +------+
- | 601 | --------------> | 603 | ---> | e300 |
- +--------------+ +----------------+ +------+
- | |
- | |
- v v
- +--------------+ +----------------+ +-------+
- | 604 | | 750 (G3) | ---> | 750CX |
- +--------------+ +----------------+ +-------+
- | | |
- | | |
- v v v
- +--------------+ +----------------+ +-------+
- | 620 (64 bit) | | 7400 | | 750CL |
- +--------------+ +----------------+ +-------+
- | | |
- | | |
- v v v
- +--------------+ +----------------+ +-------+
- | POWER3/630 | | 7410 | | 750FX |
- +--------------+ +----------------+ +-------+
- | |
- | |
- v v
- +--------------+ +----------------+
- | POWER3+ | | 7450 |
- +--------------+ +----------------+
- | |
- | |
- v v
- +--------------+ +----------------+
- | POWER4 | | 7455 |
- +--------------+ +----------------+
- | |
- | |
- v v
- +--------------+ +-------+ +----------------+
- | POWER4+ | --> | 970 | | 7447 |
- +--------------+ +-------+ +----------------+
- | | |
- | | |
- v v v
- +--------------+ +-------+ +----------------+
- | POWER5 | | 970FX | | 7448 |
- +--------------+ +-------+ +----------------+
- | | |
- | | |
- v v v
- +--------------+ +-------+ +----------------+
- | POWER5+ | | 970MP | | e600 |
- +--------------+ +-------+ +----------------+
- |
- |
- v
- +--------------+
- | POWER5++ |
- +--------------+
- |
- |
- v
- +--------------+ +-------+
- | POWER6 | <-?-> | Cell |
- +--------------+ +-------+
- |
- |
- v
- +--------------+
- | POWER7 |
- +--------------+
- |
- |
- v
- +--------------+
- | POWER7+ |
- +--------------+
- |
- |
- v
- +--------------+
- | POWER8 |
- +--------------+
-
-
- +---------------+
- | PA6T (64 bit) |
- +---------------+
-
-
-IBM BookE
----------
-
- - Software loaded TLB.
- - All 32 bit
-
- +--------------+
- | 401 |
- +--------------+
- |
- |
- v
- +--------------+
- | 403 |
- +--------------+
- |
- |
- v
- +--------------+
- | 405 |
- +--------------+
- |
- |
- v
- +--------------+
- | 440 |
- +--------------+
- |
- |
- v
- +--------------+ +----------------+
- | 450 | --> | BG/P |
- +--------------+ +----------------+
- |
- |
- v
- +--------------+
- | 460 |
- +--------------+
- |
- |
- v
- +--------------+
- | 476 |
- +--------------+
-
-
-Motorola/Freescale 8xx
-----------------------
-
- - Software loaded with hardware assist.
- - All 32 bit
-
- +-------------+
- | MPC8xx Core |
- +-------------+
-
-
-Freescale BookE
----------------
-
- - Software loaded TLB.
- - e6500 adds HW loaded indirect TLB entries.
- - Mix of 32 & 64 bit
-
- +--------------+
- | e200 |
- +--------------+
-
-
- +--------------------------------+
- | e500 |
- +--------------------------------+
- |
- |
- v
- +--------------------------------+
- | e500v2 |
- +--------------------------------+
- |
- |
- v
- +--------------------------------+
- | e500mc (Book3e) |
- +--------------------------------+
- |
- |
- v
- +--------------------------------+
- | e5500 (64 bit) |
- +--------------------------------+
- |
- |
- v
- +--------------------------------+
- | e6500 (HW TLB) (Multithreaded) |
- +--------------------------------+
-
-
-IBM A2 core
------------
-
- - Book3E, software loaded TLB + HW loaded indirect TLB entries.
- - 64 bit
-
- +--------------+ +----------------+
- | A2 core | --> | WSP |
- +--------------+ +----------------+
- |
- |
- v
- +--------------+
- | BG/Q |
- +--------------+
--- /dev/null
+============
+CPU Features
+============
+
+Hollis Blanchard <hollis@austin.ibm.com>
+5 Jun 2002
+
+This document describes the system (including self-modifying code) used in the
+PPC Linux kernel to support a variety of PowerPC CPUs without requiring
+compile-time selection.
+
+Early in the boot process the ppc32 kernel detects the current CPU type and
+chooses a set of features accordingly. Some examples include Altivec support,
+split instruction and data caches, and if the CPU supports the DOZE and NAP
+sleep modes.
+
+Detection of the feature set is simple. A list of processors can be found in
+arch/powerpc/kernel/cputable.c. The PVR register is masked and compared with
+each value in the list. If a match is found, the cpu_features of cur_cpu_spec
+is assigned to the feature bitmask for this processor and a __setup_cpu
+function is called.
+
+C code may test 'cur_cpu_spec[smp_processor_id()]->cpu_features' for a
+particular feature bit. This is done in quite a few places, for example
+in ppc_setup_l2cr().
+
+Implementing cpufeatures in assembly is a little more involved. There are
+several paths that are performance-critical and would suffer if an array
+index, structure dereference, and conditional branch were added. To avoid the
+performance penalty but still allow for runtime (rather than compile-time) CPU
+selection, unused code is replaced by 'nop' instructions. This nop'ing is
+based on CPU 0's capabilities, so a multi-processor system with non-identical
+processors will not work (but such a system would likely have other problems
+anyways).
+
+After detecting the processor type, the kernel patches out sections of code
+that shouldn't be used by writing nop's over it. Using cpufeatures requires
+just 2 macros (found in arch/powerpc/include/asm/cputable.h), as seen in head.S
+transfer_to_handler::
+
+ #ifdef CONFIG_ALTIVEC
+ BEGIN_FTR_SECTION
+ mfspr r22,SPRN_VRSAVE /* if G4, save vrsave register value */
+ stw r22,THREAD_VRSAVE(r23)
+ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+ #endif /* CONFIG_ALTIVEC */
+
+If CPU 0 supports Altivec, the code is left untouched. If it doesn't, both
+instructions are replaced with nop's.
+
+The END_FTR_SECTION macro has two simpler variations: END_FTR_SECTION_IFSET
+and END_FTR_SECTION_IFCLR. These simply test if a flag is set (in
+cur_cpu_spec[0]->cpu_features) or is cleared, respectively. These two macros
+should be used in the majority of cases.
+
+The END_FTR_SECTION macros are implemented by storing information about this
+code in the '__ftr_fixup' ELF section. When do_cpu_ftr_fixups
+(arch/powerpc/kernel/misc.S) is invoked, it will iterate over the records in
+__ftr_fixup, and if the required feature is not present it will loop writing
+nop's from each BEGIN_FTR_SECTION to END_FTR_SECTION.
+++ /dev/null
-Hollis Blanchard <hollis@austin.ibm.com>
-5 Jun 2002
-
-This document describes the system (including self-modifying code) used in the
-PPC Linux kernel to support a variety of PowerPC CPUs without requiring
-compile-time selection.
-
-Early in the boot process the ppc32 kernel detects the current CPU type and
-chooses a set of features accordingly. Some examples include Altivec support,
-split instruction and data caches, and if the CPU supports the DOZE and NAP
-sleep modes.
-
-Detection of the feature set is simple. A list of processors can be found in
-arch/powerpc/kernel/cputable.c. The PVR register is masked and compared with
-each value in the list. If a match is found, the cpu_features of cur_cpu_spec
-is assigned to the feature bitmask for this processor and a __setup_cpu
-function is called.
-
-C code may test 'cur_cpu_spec[smp_processor_id()]->cpu_features' for a
-particular feature bit. This is done in quite a few places, for example
-in ppc_setup_l2cr().
-
-Implementing cpufeatures in assembly is a little more involved. There are
-several paths that are performance-critical and would suffer if an array
-index, structure dereference, and conditional branch were added. To avoid the
-performance penalty but still allow for runtime (rather than compile-time) CPU
-selection, unused code is replaced by 'nop' instructions. This nop'ing is
-based on CPU 0's capabilities, so a multi-processor system with non-identical
-processors will not work (but such a system would likely have other problems
-anyways).
-
-After detecting the processor type, the kernel patches out sections of code
-that shouldn't be used by writing nop's over it. Using cpufeatures requires
-just 2 macros (found in arch/powerpc/include/asm/cputable.h), as seen in head.S
-transfer_to_handler:
-
- #ifdef CONFIG_ALTIVEC
- BEGIN_FTR_SECTION
- mfspr r22,SPRN_VRSAVE /* if G4, save vrsave register value */
- stw r22,THREAD_VRSAVE(r23)
- END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
- #endif /* CONFIG_ALTIVEC */
-
-If CPU 0 supports Altivec, the code is left untouched. If it doesn't, both
-instructions are replaced with nop's.
-
-The END_FTR_SECTION macro has two simpler variations: END_FTR_SECTION_IFSET
-and END_FTR_SECTION_IFCLR. These simply test if a flag is set (in
-cur_cpu_spec[0]->cpu_features) or is cleared, respectively. These two macros
-should be used in the majority of cases.
-
-The END_FTR_SECTION macros are implemented by storing information about this
-code in the '__ftr_fixup' ELF section. When do_cpu_ftr_fixups
-(arch/powerpc/kernel/misc.S) is invoked, it will iterate over the records in
-__ftr_fixup, and if the required feature is not present it will loop writing
-nop's from each BEGIN_FTR_SECTION to END_FTR_SECTION.
--- /dev/null
+====================================
+Coherent Accelerator Interface (CXL)
+====================================
+
+Introduction
+============
+
+ The coherent accelerator interface is designed to allow the
+ coherent connection of accelerators (FPGAs and other devices) to a
+ POWER system. These devices need to adhere to the Coherent
+ Accelerator Interface Architecture (CAIA).
+
+ IBM refers to this as the Coherent Accelerator Processor Interface
+ or CAPI. In the kernel it's referred to by the name CXL to avoid
+ confusion with the ISDN CAPI subsystem.
+
+ Coherent in this context means that the accelerator and CPUs can
+ both access system memory directly and with the same effective
+ addresses.
+
+
+Hardware overview
+=================
+
+ ::
+
+ POWER8/9 FPGA
+ +----------+ +---------+
+ | | | |
+ | CPU | | AFU |
+ | | | |
+ | | | |
+ | | | |
+ +----------+ +---------+
+ | PHB | | |
+ | +------+ | PSL |
+ | | CAPP |<------>| |
+ +---+------+ PCIE +---------+
+
+ The POWER8/9 chip has a Coherently Attached Processor Proxy (CAPP)
+ unit which is part of the PCIe Host Bridge (PHB). This is managed
+ by Linux by calls into OPAL. Linux doesn't directly program the
+ CAPP.
+
+ The FPGA (or coherently attached device) consists of two parts.
+ The POWER Service Layer (PSL) and the Accelerator Function Unit
+ (AFU). The AFU is used to implement specific functionality behind
+ the PSL. The PSL, among other things, provides memory address
+ translation services to allow each AFU direct access to userspace
+ memory.
+
+ The AFU is the core part of the accelerator (eg. the compression,
+ crypto etc function). The kernel has no knowledge of the function
+ of the AFU. Only userspace interacts directly with the AFU.
+
+ The PSL provides the translation and interrupt services that the
+ AFU needs. This is what the kernel interacts with. For example, if
+ the AFU needs to read a particular effective address, it sends
+ that address to the PSL, the PSL then translates it, fetches the
+ data from memory and returns it to the AFU. If the PSL has a
+ translation miss, it interrupts the kernel and the kernel services
+ the fault. The context to which this fault is serviced is based on
+ who owns that acceleration function.
+
+ - POWER8 and PSL Version 8 are compliant to the CAIA Version 1.0.
+ - POWER9 and PSL Version 9 are compliant to the CAIA Version 2.0.
+
+ This PSL Version 9 provides new features such as:
+
+ * Interaction with the nest MMU on the P9 chip.
+ * Native DMA support.
+ * Supports sending ASB_Notify messages for host thread wakeup.
+ * Supports Atomic operations.
+ * etc.
+
+ Cards with a PSL9 won't work on a POWER8 system and cards with a
+ PSL8 won't work on a POWER9 system.
+
+AFU Modes
+=========
+
+ There are two programming modes supported by the AFU. Dedicated
+ and AFU directed. AFU may support one or both modes.
+
+ When using dedicated mode only one MMU context is supported. In
+ this mode, only one userspace process can use the accelerator at
+ time.
+
+ When using AFU directed mode, up to 16K simultaneous contexts can
+ be supported. This means up to 16K simultaneous userspace
+ applications may use the accelerator (although specific AFUs may
+ support fewer). In this mode, the AFU sends a 16 bit context ID
+ with each of its requests. This tells the PSL which context is
+ associated with each operation. If the PSL can't translate an
+ operation, the ID can also be accessed by the kernel so it can
+ determine the userspace context associated with an operation.
+
+
+MMIO space
+==========
+
+ A portion of the accelerator MMIO space can be directly mapped
+ from the AFU to userspace. Either the whole space can be mapped or
+ just a per context portion. The hardware is self describing, hence
+ the kernel can determine the offset and size of the per context
+ portion.
+
+
+Interrupts
+==========
+
+ AFUs may generate interrupts that are destined for userspace. These
+ are received by the kernel as hardware interrupts and passed onto
+ userspace by a read syscall documented below.
+
+ Data storage faults and error interrupts are handled by the kernel
+ driver.
+
+
+Work Element Descriptor (WED)
+=============================
+
+ The WED is a 64-bit parameter passed to the AFU when a context is
+ started. Its format is up to the AFU hence the kernel has no
+ knowledge of what it represents. Typically it will be the
+ effective address of a work queue or status block where the AFU
+ and userspace can share control and status information.
+
+
+
+
+User API
+========
+
+1. AFU character devices
+
+ For AFUs operating in AFU directed mode, two character device
+ files will be created. /dev/cxl/afu0.0m will correspond to a
+ master context and /dev/cxl/afu0.0s will correspond to a slave
+ context. Master contexts have access to the full MMIO space an
+ AFU provides. Slave contexts have access to only the per process
+ MMIO space an AFU provides.
+
+ For AFUs operating in dedicated process mode, the driver will
+ only create a single character device per AFU called
+ /dev/cxl/afu0.0d. This will have access to the entire MMIO space
+ that the AFU provides (like master contexts in AFU directed).
+
+ The types described below are defined in include/uapi/misc/cxl.h
+
+ The following file operations are supported on both slave and
+ master devices.
+
+ A userspace library libcxl is available here:
+
+ https://github.com/ibm-capi/libcxl
+
+ This provides a C interface to this kernel API.
+
+open
+----
+
+ Opens the device and allocates a file descriptor to be used with
+ the rest of the API.
+
+ A dedicated mode AFU only has one context and only allows the
+ device to be opened once.
+
+ An AFU directed mode AFU can have many contexts, the device can be
+ opened once for each context that is available.
+
+ When all available contexts are allocated the open call will fail
+ and return -ENOSPC.
+
+ Note:
+ IRQs need to be allocated for each context, which may limit
+ the number of contexts that can be created, and therefore
+ how many times the device can be opened. The POWER8 CAPP
+ supports 2040 IRQs and 3 are used by the kernel, so 2037 are
+ left. If 1 IRQ is needed per context, then only 2037
+ contexts can be allocated. If 4 IRQs are needed per context,
+ then only 2037/4 = 509 contexts can be allocated.
+
+
+ioctl
+-----
+
+ CXL_IOCTL_START_WORK:
+ Starts the AFU context and associates it with the current
+ process. Once this ioctl is successfully executed, all memory
+ mapped into this process is accessible to this AFU context
+ using the same effective addresses. No additional calls are
+ required to map/unmap memory. The AFU memory context will be
+ updated as userspace allocates and frees memory. This ioctl
+ returns once the AFU context is started.
+
+ Takes a pointer to a struct cxl_ioctl_start_work
+
+ ::
+
+ struct cxl_ioctl_start_work {
+ __u64 flags;
+ __u64 work_element_descriptor;
+ __u64 amr;
+ __s16 num_interrupts;
+ __s16 reserved1;
+ __s32 reserved2;
+ __u64 reserved3;
+ __u64 reserved4;
+ __u64 reserved5;
+ __u64 reserved6;
+ };
+
+ flags:
+ Indicates which optional fields in the structure are
+ valid.
+
+ work_element_descriptor:
+ The Work Element Descriptor (WED) is a 64-bit argument
+ defined by the AFU. Typically this is an effective
+ address pointing to an AFU specific structure
+ describing what work to perform.
+
+ amr:
+ Authority Mask Register (AMR), same as the powerpc
+ AMR. This field is only used by the kernel when the
+ corresponding CXL_START_WORK_AMR value is specified in
+ flags. If not specified the kernel will use a default
+ value of 0.
+
+ num_interrupts:
+ Number of userspace interrupts to request. This field
+ is only used by the kernel when the corresponding
+ CXL_START_WORK_NUM_IRQS value is specified in flags.
+ If not specified the minimum number required by the
+ AFU will be allocated. The min and max number can be
+ obtained from sysfs.
+
+ reserved fields:
+ For ABI padding and future extensions
+
+ CXL_IOCTL_GET_PROCESS_ELEMENT:
+ Get the current context id, also known as the process element.
+ The value is returned from the kernel as a __u32.
+
+
+mmap
+----
+
+ An AFU may have an MMIO space to facilitate communication with the
+ AFU. If it does, the MMIO space can be accessed via mmap. The size
+ and contents of this area are specific to the particular AFU. The
+ size can be discovered via sysfs.
+
+ In AFU directed mode, master contexts are allowed to map all of
+ the MMIO space and slave contexts are allowed to only map the per
+ process MMIO space associated with the context. In dedicated
+ process mode the entire MMIO space can always be mapped.
+
+ This mmap call must be done after the START_WORK ioctl.
+
+ Care should be taken when accessing MMIO space. Only 32 and 64-bit
+ accesses are supported by POWER8. Also, the AFU will be designed
+ with a specific endianness, so all MMIO accesses should consider
+ endianness (recommend endian(3) variants like: le64toh(),
+ be64toh() etc). These endian issues equally apply to shared memory
+ queues the WED may describe.
+
+
+read
+----
+
+ Reads events from the AFU. Blocks if no events are pending
+ (unless O_NONBLOCK is supplied). Returns -EIO in the case of an
+ unrecoverable error or if the card is removed.
+
+ read() will always return an integral number of events.
+
+ The buffer passed to read() must be at least 4K bytes.
+
+ The result of the read will be a buffer of one or more events,
+ each event is of type struct cxl_event, of varying size::
+
+ struct cxl_event {
+ struct cxl_event_header header;
+ union {
+ struct cxl_event_afu_interrupt irq;
+ struct cxl_event_data_storage fault;
+ struct cxl_event_afu_error afu_error;
+ };
+ };
+
+ The struct cxl_event_header is defined as
+
+ ::
+
+ struct cxl_event_header {
+ __u16 type;
+ __u16 size;
+ __u16 process_element;
+ __u16 reserved1;
+ };
+
+ type:
+ This defines the type of event. The type determines how
+ the rest of the event is structured. These types are
+ described below and defined by enum cxl_event_type.
+
+ size:
+ This is the size of the event in bytes including the
+ struct cxl_event_header. The start of the next event can
+ be found at this offset from the start of the current
+ event.
+
+ process_element:
+ Context ID of the event.
+
+ reserved field:
+ For future extensions and padding.
+
+ If the event type is CXL_EVENT_AFU_INTERRUPT then the event
+ structure is defined as
+
+ ::
+
+ struct cxl_event_afu_interrupt {
+ __u16 flags;
+ __u16 irq; /* Raised AFU interrupt number */
+ __u32 reserved1;
+ };
+
+ flags:
+ These flags indicate which optional fields are present
+ in this struct. Currently all fields are mandatory.
+
+ irq:
+ The IRQ number sent by the AFU.
+
+ reserved field:
+ For future extensions and padding.
+
+ If the event type is CXL_EVENT_DATA_STORAGE then the event
+ structure is defined as
+
+ ::
+
+ struct cxl_event_data_storage {
+ __u16 flags;
+ __u16 reserved1;
+ __u32 reserved2;
+ __u64 addr;
+ __u64 dsisr;
+ __u64 reserved3;
+ };
+
+ flags:
+ These flags indicate which optional fields are present in
+ this struct. Currently all fields are mandatory.
+
+ address:
+ The address that the AFU unsuccessfully attempted to
+ access. Valid accesses will be handled transparently by the
+ kernel but invalid accesses will generate this event.
+
+ dsisr:
+ This field gives information on the type of fault. It is a
+ copy of the DSISR from the PSL hardware when the address
+ fault occurred. The form of the DSISR is as defined in the
+ CAIA.
+
+ reserved fields:
+ For future extensions
+
+ If the event type is CXL_EVENT_AFU_ERROR then the event structure
+ is defined as
+
+ ::
+
+ struct cxl_event_afu_error {
+ __u16 flags;
+ __u16 reserved1;
+ __u32 reserved2;
+ __u64 error;
+ };
+
+ flags:
+ These flags indicate which optional fields are present in
+ this struct. Currently all fields are Mandatory.
+
+ error:
+ Error status from the AFU. Defined by the AFU.
+
+ reserved fields:
+ For future extensions and padding
+
+
+2. Card character device (powerVM guest only)
+
+ In a powerVM guest, an extra character device is created for the
+ card. The device is only used to write (flash) a new image on the
+ FPGA accelerator. Once the image is written and verified, the
+ device tree is updated and the card is reset to reload the updated
+ image.
+
+open
+----
+
+ Opens the device and allocates a file descriptor to be used with
+ the rest of the API. The device can only be opened once.
+
+ioctl
+-----
+
+CXL_IOCTL_DOWNLOAD_IMAGE / CXL_IOCTL_VALIDATE_IMAGE:
+ Starts and controls flashing a new FPGA image. Partial
+ reconfiguration is not supported (yet), so the image must contain
+ a copy of the PSL and AFU(s). Since an image can be quite large,
+ the caller may have to iterate, splitting the image in smaller
+ chunks.
+
+ Takes a pointer to a struct cxl_adapter_image::
+
+ struct cxl_adapter_image {
+ __u64 flags;
+ __u64 data;
+ __u64 len_data;
+ __u64 len_image;
+ __u64 reserved1;
+ __u64 reserved2;
+ __u64 reserved3;
+ __u64 reserved4;
+ };
+
+ flags:
+ These flags indicate which optional fields are present in
+ this struct. Currently all fields are mandatory.
+
+ data:
+ Pointer to a buffer with part of the image to write to the
+ card.
+
+ len_data:
+ Size of the buffer pointed to by data.
+
+ len_image:
+ Full size of the image.
+
+
+Sysfs Class
+===========
+
+ A cxl sysfs class is added under /sys/class/cxl to facilitate
+ enumeration and tuning of the accelerators. Its layout is
+ described in Documentation/ABI/testing/sysfs-class-cxl
+
+
+Udev rules
+==========
+
+ The following udev rules could be used to create a symlink to the
+ most logical chardev to use in any programming mode (afuX.Yd for
+ dedicated, afuX.Ys for afu directed), since the API is virtually
+ identical for each::
+
+ SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b"
+ SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \
+ KERNEL=="afu[0-9]*.[0-9]*s", SYMLINK="cxl/%b"
+++ /dev/null
-Coherent Accelerator Interface (CXL)
-====================================
-
-Introduction
-============
-
- The coherent accelerator interface is designed to allow the
- coherent connection of accelerators (FPGAs and other devices) to a
- POWER system. These devices need to adhere to the Coherent
- Accelerator Interface Architecture (CAIA).
-
- IBM refers to this as the Coherent Accelerator Processor Interface
- or CAPI. In the kernel it's referred to by the name CXL to avoid
- confusion with the ISDN CAPI subsystem.
-
- Coherent in this context means that the accelerator and CPUs can
- both access system memory directly and with the same effective
- addresses.
-
-
-Hardware overview
-=================
-
- POWER8/9 FPGA
- +----------+ +---------+
- | | | |
- | CPU | | AFU |
- | | | |
- | | | |
- | | | |
- +----------+ +---------+
- | PHB | | |
- | +------+ | PSL |
- | | CAPP |<------>| |
- +---+------+ PCIE +---------+
-
- The POWER8/9 chip has a Coherently Attached Processor Proxy (CAPP)
- unit which is part of the PCIe Host Bridge (PHB). This is managed
- by Linux by calls into OPAL. Linux doesn't directly program the
- CAPP.
-
- The FPGA (or coherently attached device) consists of two parts.
- The POWER Service Layer (PSL) and the Accelerator Function Unit
- (AFU). The AFU is used to implement specific functionality behind
- the PSL. The PSL, among other things, provides memory address
- translation services to allow each AFU direct access to userspace
- memory.
-
- The AFU is the core part of the accelerator (eg. the compression,
- crypto etc function). The kernel has no knowledge of the function
- of the AFU. Only userspace interacts directly with the AFU.
-
- The PSL provides the translation and interrupt services that the
- AFU needs. This is what the kernel interacts with. For example, if
- the AFU needs to read a particular effective address, it sends
- that address to the PSL, the PSL then translates it, fetches the
- data from memory and returns it to the AFU. If the PSL has a
- translation miss, it interrupts the kernel and the kernel services
- the fault. The context to which this fault is serviced is based on
- who owns that acceleration function.
-
- POWER8 <-----> PSL Version 8 is compliant to the CAIA Version 1.0.
- POWER9 <-----> PSL Version 9 is compliant to the CAIA Version 2.0.
- This PSL Version 9 provides new features such as:
- * Interaction with the nest MMU on the P9 chip.
- * Native DMA support.
- * Supports sending ASB_Notify messages for host thread wakeup.
- * Supports Atomic operations.
- * ....
-
- Cards with a PSL9 won't work on a POWER8 system and cards with a
- PSL8 won't work on a POWER9 system.
-
-AFU Modes
-=========
-
- There are two programming modes supported by the AFU. Dedicated
- and AFU directed. AFU may support one or both modes.
-
- When using dedicated mode only one MMU context is supported. In
- this mode, only one userspace process can use the accelerator at
- time.
-
- When using AFU directed mode, up to 16K simultaneous contexts can
- be supported. This means up to 16K simultaneous userspace
- applications may use the accelerator (although specific AFUs may
- support fewer). In this mode, the AFU sends a 16 bit context ID
- with each of its requests. This tells the PSL which context is
- associated with each operation. If the PSL can't translate an
- operation, the ID can also be accessed by the kernel so it can
- determine the userspace context associated with an operation.
-
-
-MMIO space
-==========
-
- A portion of the accelerator MMIO space can be directly mapped
- from the AFU to userspace. Either the whole space can be mapped or
- just a per context portion. The hardware is self describing, hence
- the kernel can determine the offset and size of the per context
- portion.
-
-
-Interrupts
-==========
-
- AFUs may generate interrupts that are destined for userspace. These
- are received by the kernel as hardware interrupts and passed onto
- userspace by a read syscall documented below.
-
- Data storage faults and error interrupts are handled by the kernel
- driver.
-
-
-Work Element Descriptor (WED)
-=============================
-
- The WED is a 64-bit parameter passed to the AFU when a context is
- started. Its format is up to the AFU hence the kernel has no
- knowledge of what it represents. Typically it will be the
- effective address of a work queue or status block where the AFU
- and userspace can share control and status information.
-
-
-
-
-User API
-========
-
-1. AFU character devices
-
- For AFUs operating in AFU directed mode, two character device
- files will be created. /dev/cxl/afu0.0m will correspond to a
- master context and /dev/cxl/afu0.0s will correspond to a slave
- context. Master contexts have access to the full MMIO space an
- AFU provides. Slave contexts have access to only the per process
- MMIO space an AFU provides.
-
- For AFUs operating in dedicated process mode, the driver will
- only create a single character device per AFU called
- /dev/cxl/afu0.0d. This will have access to the entire MMIO space
- that the AFU provides (like master contexts in AFU directed).
-
- The types described below are defined in include/uapi/misc/cxl.h
-
- The following file operations are supported on both slave and
- master devices.
-
- A userspace library libcxl is available here:
- https://github.com/ibm-capi/libcxl
- This provides a C interface to this kernel API.
-
-open
-----
-
- Opens the device and allocates a file descriptor to be used with
- the rest of the API.
-
- A dedicated mode AFU only has one context and only allows the
- device to be opened once.
-
- An AFU directed mode AFU can have many contexts, the device can be
- opened once for each context that is available.
-
- When all available contexts are allocated the open call will fail
- and return -ENOSPC.
-
- Note: IRQs need to be allocated for each context, which may limit
- the number of contexts that can be created, and therefore
- how many times the device can be opened. The POWER8 CAPP
- supports 2040 IRQs and 3 are used by the kernel, so 2037 are
- left. If 1 IRQ is needed per context, then only 2037
- contexts can be allocated. If 4 IRQs are needed per context,
- then only 2037/4 = 509 contexts can be allocated.
-
-
-ioctl
------
-
- CXL_IOCTL_START_WORK:
- Starts the AFU context and associates it with the current
- process. Once this ioctl is successfully executed, all memory
- mapped into this process is accessible to this AFU context
- using the same effective addresses. No additional calls are
- required to map/unmap memory. The AFU memory context will be
- updated as userspace allocates and frees memory. This ioctl
- returns once the AFU context is started.
-
- Takes a pointer to a struct cxl_ioctl_start_work:
-
- struct cxl_ioctl_start_work {
- __u64 flags;
- __u64 work_element_descriptor;
- __u64 amr;
- __s16 num_interrupts;
- __s16 reserved1;
- __s32 reserved2;
- __u64 reserved3;
- __u64 reserved4;
- __u64 reserved5;
- __u64 reserved6;
- };
-
- flags:
- Indicates which optional fields in the structure are
- valid.
-
- work_element_descriptor:
- The Work Element Descriptor (WED) is a 64-bit argument
- defined by the AFU. Typically this is an effective
- address pointing to an AFU specific structure
- describing what work to perform.
-
- amr:
- Authority Mask Register (AMR), same as the powerpc
- AMR. This field is only used by the kernel when the
- corresponding CXL_START_WORK_AMR value is specified in
- flags. If not specified the kernel will use a default
- value of 0.
-
- num_interrupts:
- Number of userspace interrupts to request. This field
- is only used by the kernel when the corresponding
- CXL_START_WORK_NUM_IRQS value is specified in flags.
- If not specified the minimum number required by the
- AFU will be allocated. The min and max number can be
- obtained from sysfs.
-
- reserved fields:
- For ABI padding and future extensions
-
- CXL_IOCTL_GET_PROCESS_ELEMENT:
- Get the current context id, also known as the process element.
- The value is returned from the kernel as a __u32.
-
-
-mmap
-----
-
- An AFU may have an MMIO space to facilitate communication with the
- AFU. If it does, the MMIO space can be accessed via mmap. The size
- and contents of this area are specific to the particular AFU. The
- size can be discovered via sysfs.
-
- In AFU directed mode, master contexts are allowed to map all of
- the MMIO space and slave contexts are allowed to only map the per
- process MMIO space associated with the context. In dedicated
- process mode the entire MMIO space can always be mapped.
-
- This mmap call must be done after the START_WORK ioctl.
-
- Care should be taken when accessing MMIO space. Only 32 and 64-bit
- accesses are supported by POWER8. Also, the AFU will be designed
- with a specific endianness, so all MMIO accesses should consider
- endianness (recommend endian(3) variants like: le64toh(),
- be64toh() etc). These endian issues equally apply to shared memory
- queues the WED may describe.
-
-
-read
-----
-
- Reads events from the AFU. Blocks if no events are pending
- (unless O_NONBLOCK is supplied). Returns -EIO in the case of an
- unrecoverable error or if the card is removed.
-
- read() will always return an integral number of events.
-
- The buffer passed to read() must be at least 4K bytes.
-
- The result of the read will be a buffer of one or more events,
- each event is of type struct cxl_event, of varying size.
-
- struct cxl_event {
- struct cxl_event_header header;
- union {
- struct cxl_event_afu_interrupt irq;
- struct cxl_event_data_storage fault;
- struct cxl_event_afu_error afu_error;
- };
- };
-
- The struct cxl_event_header is defined as:
-
- struct cxl_event_header {
- __u16 type;
- __u16 size;
- __u16 process_element;
- __u16 reserved1;
- };
-
- type:
- This defines the type of event. The type determines how
- the rest of the event is structured. These types are
- described below and defined by enum cxl_event_type.
-
- size:
- This is the size of the event in bytes including the
- struct cxl_event_header. The start of the next event can
- be found at this offset from the start of the current
- event.
-
- process_element:
- Context ID of the event.
-
- reserved field:
- For future extensions and padding.
-
- If the event type is CXL_EVENT_AFU_INTERRUPT then the event
- structure is defined as:
-
- struct cxl_event_afu_interrupt {
- __u16 flags;
- __u16 irq; /* Raised AFU interrupt number */
- __u32 reserved1;
- };
-
- flags:
- These flags indicate which optional fields are present
- in this struct. Currently all fields are mandatory.
-
- irq:
- The IRQ number sent by the AFU.
-
- reserved field:
- For future extensions and padding.
-
- If the event type is CXL_EVENT_DATA_STORAGE then the event
- structure is defined as:
-
- struct cxl_event_data_storage {
- __u16 flags;
- __u16 reserved1;
- __u32 reserved2;
- __u64 addr;
- __u64 dsisr;
- __u64 reserved3;
- };
-
- flags:
- These flags indicate which optional fields are present in
- this struct. Currently all fields are mandatory.
-
- address:
- The address that the AFU unsuccessfully attempted to
- access. Valid accesses will be handled transparently by the
- kernel but invalid accesses will generate this event.
-
- dsisr:
- This field gives information on the type of fault. It is a
- copy of the DSISR from the PSL hardware when the address
- fault occurred. The form of the DSISR is as defined in the
- CAIA.
-
- reserved fields:
- For future extensions
-
- If the event type is CXL_EVENT_AFU_ERROR then the event structure
- is defined as:
-
- struct cxl_event_afu_error {
- __u16 flags;
- __u16 reserved1;
- __u32 reserved2;
- __u64 error;
- };
-
- flags:
- These flags indicate which optional fields are present in
- this struct. Currently all fields are Mandatory.
-
- error:
- Error status from the AFU. Defined by the AFU.
-
- reserved fields:
- For future extensions and padding
-
-
-2. Card character device (powerVM guest only)
-
- In a powerVM guest, an extra character device is created for the
- card. The device is only used to write (flash) a new image on the
- FPGA accelerator. Once the image is written and verified, the
- device tree is updated and the card is reset to reload the updated
- image.
-
-open
-----
-
- Opens the device and allocates a file descriptor to be used with
- the rest of the API. The device can only be opened once.
-
-ioctl
------
-
-CXL_IOCTL_DOWNLOAD_IMAGE:
-CXL_IOCTL_VALIDATE_IMAGE:
- Starts and controls flashing a new FPGA image. Partial
- reconfiguration is not supported (yet), so the image must contain
- a copy of the PSL and AFU(s). Since an image can be quite large,
- the caller may have to iterate, splitting the image in smaller
- chunks.
-
- Takes a pointer to a struct cxl_adapter_image:
- struct cxl_adapter_image {
- __u64 flags;
- __u64 data;
- __u64 len_data;
- __u64 len_image;
- __u64 reserved1;
- __u64 reserved2;
- __u64 reserved3;
- __u64 reserved4;
- };
-
- flags:
- These flags indicate which optional fields are present in
- this struct. Currently all fields are mandatory.
-
- data:
- Pointer to a buffer with part of the image to write to the
- card.
-
- len_data:
- Size of the buffer pointed to by data.
-
- len_image:
- Full size of the image.
-
-
-Sysfs Class
-===========
-
- A cxl sysfs class is added under /sys/class/cxl to facilitate
- enumeration and tuning of the accelerators. Its layout is
- described in Documentation/ABI/testing/sysfs-class-cxl
-
-
-Udev rules
-==========
-
- The following udev rules could be used to create a symlink to the
- most logical chardev to use in any programming mode (afuX.Yd for
- dedicated, afuX.Ys for afu directed), since the API is virtually
- identical for each:
-
- SUBSYSTEM=="cxl", ATTRS{mode}=="dedicated_process", SYMLINK="cxl/%b"
- SUBSYSTEM=="cxl", ATTRS{mode}=="afu_directed", \
- KERNEL=="afu[0-9]*.[0-9]*s", SYMLINK="cxl/%b"
--- /dev/null
+================================
+Coherent Accelerator (CXL) Flash
+================================
+
+Introduction
+============
+
+ The IBM Power architecture provides support for CAPI (Coherent
+ Accelerator Power Interface), which is available to certain PCIe slots
+ on Power 8 systems. CAPI can be thought of as a special tunneling
+ protocol through PCIe that allow PCIe adapters to look like special
+ purpose co-processors which can read or write an application's
+ memory and generate page faults. As a result, the host interface to
+ an adapter running in CAPI mode does not require the data buffers to
+ be mapped to the device's memory (IOMMU bypass) nor does it require
+ memory to be pinned.
+
+ On Linux, Coherent Accelerator (CXL) kernel services present CAPI
+ devices as a PCI device by implementing a virtual PCI host bridge.
+ This abstraction simplifies the infrastructure and programming
+ model, allowing for drivers to look similar to other native PCI
+ device drivers.
+
+ CXL provides a mechanism by which user space applications can
+ directly talk to a device (network or storage) bypassing the typical
+ kernel/device driver stack. The CXL Flash Adapter Driver enables a
+ user space application direct access to Flash storage.
+
+ The CXL Flash Adapter Driver is a kernel module that sits in the
+ SCSI stack as a low level device driver (below the SCSI disk and
+ protocol drivers) for the IBM CXL Flash Adapter. This driver is
+ responsible for the initialization of the adapter, setting up the
+ special path for user space access, and performing error recovery. It
+ communicates directly the Flash Accelerator Functional Unit (AFU)
+ as described in Documentation/powerpc/cxl.rst.
+
+ The cxlflash driver supports two, mutually exclusive, modes of
+ operation at the device (LUN) level:
+
+ - Any flash device (LUN) can be configured to be accessed as a
+ regular disk device (i.e.: /dev/sdc). This is the default mode.
+
+ - Any flash device (LUN) can be configured to be accessed from
+ user space with a special block library. This mode further
+ specifies the means of accessing the device and provides for
+ either raw access to the entire LUN (referred to as direct
+ or physical LUN access) or access to a kernel/AFU-mediated
+ partition of the LUN (referred to as virtual LUN access). The
+ segmentation of a disk device into virtual LUNs is assisted
+ by special translation services provided by the Flash AFU.
+
+Overview
+========
+
+ The Coherent Accelerator Interface Architecture (CAIA) introduces a
+ concept of a master context. A master typically has special privileges
+ granted to it by the kernel or hypervisor allowing it to perform AFU
+ wide management and control. The master may or may not be involved
+ directly in each user I/O, but at the minimum is involved in the
+ initial setup before the user application is allowed to send requests
+ directly to the AFU.
+
+ The CXL Flash Adapter Driver establishes a master context with the
+ AFU. It uses memory mapped I/O (MMIO) for this control and setup. The
+ Adapter Problem Space Memory Map looks like this::
+
+ +-------------------------------+
+ | 512 * 64 KB User MMIO |
+ | (per context) |
+ | User Accessible |
+ +-------------------------------+
+ | 512 * 128 B per context |
+ | Provisioning and Control |
+ | Trusted Process accessible |
+ +-------------------------------+
+ | 64 KB Global |
+ | Trusted Process accessible |
+ +-------------------------------+
+
+ This driver configures itself into the SCSI software stack as an
+ adapter driver. The driver is the only entity that is considered a
+ Trusted Process to program the Provisioning and Control and Global
+ areas in the MMIO Space shown above. The master context driver
+ discovers all LUNs attached to the CXL Flash adapter and instantiates
+ scsi block devices (/dev/sdb, /dev/sdc etc.) for each unique LUN
+ seen from each path.
+
+ Once these scsi block devices are instantiated, an application
+ written to a specification provided by the block library may get
+ access to the Flash from user space (without requiring a system call).
+
+ This master context driver also provides a series of ioctls for this
+ block library to enable this user space access. The driver supports
+ two modes for accessing the block device.
+
+ The first mode is called a virtual mode. In this mode a single scsi
+ block device (/dev/sdb) may be carved up into any number of distinct
+ virtual LUNs. The virtual LUNs may be resized as long as the sum of
+ the sizes of all the virtual LUNs, along with the meta-data associated
+ with it does not exceed the physical capacity.
+
+ The second mode is called the physical mode. In this mode a single
+ block device (/dev/sdb) may be opened directly by the block library
+ and the entire space for the LUN is available to the application.
+
+ Only the physical mode provides persistence of the data. i.e. The
+ data written to the block device will survive application exit and
+ restart and also reboot. The virtual LUNs do not persist (i.e. do
+ not survive after the application terminates or the system reboots).
+
+
+Block library API
+=================
+
+ Applications intending to get access to the CXL Flash from user
+ space should use the block library, as it abstracts the details of
+ interfacing directly with the cxlflash driver that are necessary for
+ performing administrative actions (i.e.: setup, tear down, resize).
+ The block library can be thought of as a 'user' of services,
+ implemented as IOCTLs, that are provided by the cxlflash driver
+ specifically for devices (LUNs) operating in user space access
+ mode. While it is not a requirement that applications understand
+ the interface between the block library and the cxlflash driver,
+ a high-level overview of each supported service (IOCTL) is provided
+ below.
+
+ The block library can be found on GitHub:
+ http://github.com/open-power/capiflash
+
+
+CXL Flash Driver LUN IOCTLs
+===========================
+
+ Users, such as the block library, that wish to interface with a flash
+ device (LUN) via user space access need to use the services provided
+ by the cxlflash driver. As these services are implemented as ioctls,
+ a file descriptor handle must first be obtained in order to establish
+ the communication channel between a user and the kernel. This file
+ descriptor is obtained by opening the device special file associated
+ with the scsi disk device (/dev/sdb) that was created during LUN
+ discovery. As per the location of the cxlflash driver within the
+ SCSI protocol stack, this open is actually not seen by the cxlflash
+ driver. Upon successful open, the user receives a file descriptor
+ (herein referred to as fd1) that should be used for issuing the
+ subsequent ioctls listed below.
+
+ The structure definitions for these IOCTLs are available in:
+ uapi/scsi/cxlflash_ioctl.h
+
+DK_CXLFLASH_ATTACH
+------------------
+
+ This ioctl obtains, initializes, and starts a context using the CXL
+ kernel services. These services specify a context id (u16) by which
+ to uniquely identify the context and its allocated resources. The
+ services additionally provide a second file descriptor (herein
+ referred to as fd2) that is used by the block library to initiate
+ memory mapped I/O (via mmap()) to the CXL flash device and poll for
+ completion events. This file descriptor is intentionally installed by
+ this driver and not the CXL kernel services to allow for intermediary
+ notification and access in the event of a non-user-initiated close(),
+ such as a killed process. This design point is described in further
+ detail in the description for the DK_CXLFLASH_DETACH ioctl.
+
+ There are a few important aspects regarding the "tokens" (context id
+ and fd2) that are provided back to the user:
+
+ - These tokens are only valid for the process under which they
+ were created. The child of a forked process cannot continue
+ to use the context id or file descriptor created by its parent
+ (see DK_CXLFLASH_VLUN_CLONE for further details).
+
+ - These tokens are only valid for the lifetime of the context and
+ the process under which they were created. Once either is
+ destroyed, the tokens are to be considered stale and subsequent
+ usage will result in errors.
+
+ - A valid adapter file descriptor (fd2 >= 0) is only returned on
+ the initial attach for a context. Subsequent attaches to an
+ existing context (DK_CXLFLASH_ATTACH_REUSE_CONTEXT flag present)
+ do not provide the adapter file descriptor as it was previously
+ made known to the application.
+
+ - When a context is no longer needed, the user shall detach from
+ the context via the DK_CXLFLASH_DETACH ioctl. When this ioctl
+ returns with a valid adapter file descriptor and the return flag
+ DK_CXLFLASH_APP_CLOSE_ADAP_FD is present, the application _must_
+ close the adapter file descriptor following a successful detach.
+
+ - When this ioctl returns with a valid fd2 and the return flag
+ DK_CXLFLASH_APP_CLOSE_ADAP_FD is present, the application _must_
+ close fd2 in the following circumstances:
+
+ + Following a successful detach of the last user of the context
+ + Following a successful recovery on the context's original fd2
+ + In the child process of a fork(), following a clone ioctl,
+ on the fd2 associated with the source context
+
+ - At any time, a close on fd2 will invalidate the tokens. Applications
+ should exercise caution to only close fd2 when appropriate (outlined
+ in the previous bullet) to avoid premature loss of I/O.
+
+DK_CXLFLASH_USER_DIRECT
+-----------------------
+ This ioctl is responsible for transitioning the LUN to direct
+ (physical) mode access and configuring the AFU for direct access from
+ user space on a per-context basis. Additionally, the block size and
+ last logical block address (LBA) are returned to the user.
+
+ As mentioned previously, when operating in user space access mode,
+ LUNs may be accessed in whole or in part. Only one mode is allowed
+ at a time and if one mode is active (outstanding references exist),
+ requests to use the LUN in a different mode are denied.
+
+ The AFU is configured for direct access from user space by adding an
+ entry to the AFU's resource handle table. The index of the entry is
+ treated as a resource handle that is returned to the user. The user
+ is then able to use the handle to reference the LUN during I/O.
+
+DK_CXLFLASH_USER_VIRTUAL
+------------------------
+ This ioctl is responsible for transitioning the LUN to virtual mode
+ of access and configuring the AFU for virtual access from user space
+ on a per-context basis. Additionally, the block size and last logical
+ block address (LBA) are returned to the user.
+
+ As mentioned previously, when operating in user space access mode,
+ LUNs may be accessed in whole or in part. Only one mode is allowed
+ at a time and if one mode is active (outstanding references exist),
+ requests to use the LUN in a different mode are denied.
+
+ The AFU is configured for virtual access from user space by adding
+ an entry to the AFU's resource handle table. The index of the entry
+ is treated as a resource handle that is returned to the user. The
+ user is then able to use the handle to reference the LUN during I/O.
+
+ By default, the virtual LUN is created with a size of 0. The user
+ would need to use the DK_CXLFLASH_VLUN_RESIZE ioctl to adjust the grow
+ the virtual LUN to a desired size. To avoid having to perform this
+ resize for the initial creation of the virtual LUN, the user has the
+ option of specifying a size as part of the DK_CXLFLASH_USER_VIRTUAL
+ ioctl, such that when success is returned to the user, the
+ resource handle that is provided is already referencing provisioned
+ storage. This is reflected by the last LBA being a non-zero value.
+
+ When a LUN is accessible from more than one port, this ioctl will
+ return with the DK_CXLFLASH_ALL_PORTS_ACTIVE return flag set. This
+ provides the user with a hint that I/O can be retried in the event
+ of an I/O error as the LUN can be reached over multiple paths.
+
+DK_CXLFLASH_VLUN_RESIZE
+-----------------------
+ This ioctl is responsible for resizing a previously created virtual
+ LUN and will fail if invoked upon a LUN that is not in virtual
+ mode. Upon success, an updated last LBA is returned to the user
+ indicating the new size of the virtual LUN associated with the
+ resource handle.
+
+ The partitioning of virtual LUNs is jointly mediated by the cxlflash
+ driver and the AFU. An allocation table is kept for each LUN that is
+ operating in the virtual mode and used to program a LUN translation
+ table that the AFU references when provided with a resource handle.
+
+ This ioctl can return -EAGAIN if an AFU sync operation takes too long.
+ In addition to returning a failure to user, cxlflash will also schedule
+ an asynchronous AFU reset. Should the user choose to retry the operation,
+ it is expected to succeed. If this ioctl fails with -EAGAIN, the user
+ can either retry the operation or treat it as a failure.
+
+DK_CXLFLASH_RELEASE
+-------------------
+ This ioctl is responsible for releasing a previously obtained
+ reference to either a physical or virtual LUN. This can be
+ thought of as the inverse of the DK_CXLFLASH_USER_DIRECT or
+ DK_CXLFLASH_USER_VIRTUAL ioctls. Upon success, the resource handle
+ is no longer valid and the entry in the resource handle table is
+ made available to be used again.
+
+ As part of the release process for virtual LUNs, the virtual LUN
+ is first resized to 0 to clear out and free the translation tables
+ associated with the virtual LUN reference.
+
+DK_CXLFLASH_DETACH
+------------------
+ This ioctl is responsible for unregistering a context with the
+ cxlflash driver and release outstanding resources that were
+ not explicitly released via the DK_CXLFLASH_RELEASE ioctl. Upon
+ success, all "tokens" which had been provided to the user from the
+ DK_CXLFLASH_ATTACH onward are no longer valid.
+
+ When the DK_CXLFLASH_APP_CLOSE_ADAP_FD flag was returned on a successful
+ attach, the application _must_ close the fd2 associated with the context
+ following the detach of the final user of the context.
+
+DK_CXLFLASH_VLUN_CLONE
+----------------------
+ This ioctl is responsible for cloning a previously created
+ context to a more recently created context. It exists solely to
+ support maintaining user space access to storage after a process
+ forks. Upon success, the child process (which invoked the ioctl)
+ will have access to the same LUNs via the same resource handle(s)
+ as the parent, but under a different context.
+
+ Context sharing across processes is not supported with CXL and
+ therefore each fork must be met with establishing a new context
+ for the child process. This ioctl simplifies the state management
+ and playback required by a user in such a scenario. When a process
+ forks, child process can clone the parents context by first creating
+ a context (via DK_CXLFLASH_ATTACH) and then using this ioctl to
+ perform the clone from the parent to the child.
+
+ The clone itself is fairly simple. The resource handle and lun
+ translation tables are copied from the parent context to the child's
+ and then synced with the AFU.
+
+ When the DK_CXLFLASH_APP_CLOSE_ADAP_FD flag was returned on a successful
+ attach, the application _must_ close the fd2 associated with the source
+ context (still resident/accessible in the parent process) following the
+ clone. This is to avoid a stale entry in the file descriptor table of the
+ child process.
+
+ This ioctl can return -EAGAIN if an AFU sync operation takes too long.
+ In addition to returning a failure to user, cxlflash will also schedule
+ an asynchronous AFU reset. Should the user choose to retry the operation,
+ it is expected to succeed. If this ioctl fails with -EAGAIN, the user
+ can either retry the operation or treat it as a failure.
+
+DK_CXLFLASH_VERIFY
+------------------
+ This ioctl is used to detect various changes such as the capacity of
+ the disk changing, the number of LUNs visible changing, etc. In cases
+ where the changes affect the application (such as a LUN resize), the
+ cxlflash driver will report the changed state to the application.
+
+ The user calls in when they want to validate that a LUN hasn't been
+ changed in response to a check condition. As the user is operating out
+ of band from the kernel, they will see these types of events without
+ the kernel's knowledge. When encountered, the user's architected
+ behavior is to call in to this ioctl, indicating what they want to
+ verify and passing along any appropriate information. For now, only
+ verifying a LUN change (ie: size different) with sense data is
+ supported.
+
+DK_CXLFLASH_RECOVER_AFU
+-----------------------
+ This ioctl is used to drive recovery (if such an action is warranted)
+ of a specified user context. Any state associated with the user context
+ is re-established upon successful recovery.
+
+ User contexts are put into an error condition when the device needs to
+ be reset or is terminating. Users are notified of this error condition
+ by seeing all 0xF's on an MMIO read. Upon encountering this, the
+ architected behavior for a user is to call into this ioctl to recover
+ their context. A user may also call into this ioctl at any time to
+ check if the device is operating normally. If a failure is returned
+ from this ioctl, the user is expected to gracefully clean up their
+ context via release/detach ioctls. Until they do, the context they
+ hold is not relinquished. The user may also optionally exit the process
+ at which time the context/resources they held will be freed as part of
+ the release fop.
+
+ When the DK_CXLFLASH_APP_CLOSE_ADAP_FD flag was returned on a successful
+ attach, the application _must_ unmap and close the fd2 associated with the
+ original context following this ioctl returning success and indicating that
+ the context was recovered (DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET).
+
+DK_CXLFLASH_MANAGE_LUN
+----------------------
+ This ioctl is used to switch a LUN from a mode where it is available
+ for file-system access (legacy), to a mode where it is set aside for
+ exclusive user space access (superpipe). In case a LUN is visible
+ across multiple ports and adapters, this ioctl is used to uniquely
+ identify each LUN by its World Wide Node Name (WWNN).
+
+
+CXL Flash Driver Host IOCTLs
+============================
+
+ Each host adapter instance that is supported by the cxlflash driver
+ has a special character device associated with it to enable a set of
+ host management function. These character devices are hosted in a
+ class dedicated for cxlflash and can be accessed via `/dev/cxlflash/*`.
+
+ Applications can be written to perform various functions using the
+ host ioctl APIs below.
+
+ The structure definitions for these IOCTLs are available in:
+ uapi/scsi/cxlflash_ioctl.h
+
+HT_CXLFLASH_LUN_PROVISION
+-------------------------
+ This ioctl is used to create and delete persistent LUNs on cxlflash
+ devices that lack an external LUN management interface. It is only
+ valid when used with AFUs that support the LUN provision capability.
+
+ When sufficient space is available, LUNs can be created by specifying
+ the target port to host the LUN and a desired size in 4K blocks. Upon
+ success, the LUN ID and WWID of the created LUN will be returned and
+ the SCSI bus can be scanned to detect the change in LUN topology. Note
+ that partial allocations are not supported. Should a creation fail due
+ to a space issue, the target port can be queried for its current LUN
+ geometry.
+
+ To remove a LUN, the device must first be disassociated from the Linux
+ SCSI subsystem. The LUN deletion can then be initiated by specifying a
+ target port and LUN ID. Upon success, the LUN geometry associated with
+ the port will be updated to reflect new number of provisioned LUNs and
+ available capacity.
+
+ To query the LUN geometry of a port, the target port is specified and
+ upon success, the following information is presented:
+
+ - Maximum number of provisioned LUNs allowed for the port
+ - Current number of provisioned LUNs for the port
+ - Maximum total capacity of provisioned LUNs for the port (4K blocks)
+ - Current total capacity of provisioned LUNs for the port (4K blocks)
+
+ With this information, the number of available LUNs and capacity can be
+ can be calculated.
+
+HT_CXLFLASH_AFU_DEBUG
+---------------------
+ This ioctl is used to debug AFUs by supporting a command pass-through
+ interface. It is only valid when used with AFUs that support the AFU
+ debug capability.
+
+ With exception of buffer management, AFU debug commands are opaque to
+ cxlflash and treated as pass-through. For debug commands that do require
+ data transfer, the user supplies an adequately sized data buffer and must
+ specify the data transfer direction with respect to the host. There is a
+ maximum transfer size of 256K imposed. Note that partial read completions
+ are not supported - when errors are experienced with a host read data
+ transfer, the data buffer is not copied back to the user.
+++ /dev/null
-Introduction
-============
-
- The IBM Power architecture provides support for CAPI (Coherent
- Accelerator Power Interface), which is available to certain PCIe slots
- on Power 8 systems. CAPI can be thought of as a special tunneling
- protocol through PCIe that allow PCIe adapters to look like special
- purpose co-processors which can read or write an application's
- memory and generate page faults. As a result, the host interface to
- an adapter running in CAPI mode does not require the data buffers to
- be mapped to the device's memory (IOMMU bypass) nor does it require
- memory to be pinned.
-
- On Linux, Coherent Accelerator (CXL) kernel services present CAPI
- devices as a PCI device by implementing a virtual PCI host bridge.
- This abstraction simplifies the infrastructure and programming
- model, allowing for drivers to look similar to other native PCI
- device drivers.
-
- CXL provides a mechanism by which user space applications can
- directly talk to a device (network or storage) bypassing the typical
- kernel/device driver stack. The CXL Flash Adapter Driver enables a
- user space application direct access to Flash storage.
-
- The CXL Flash Adapter Driver is a kernel module that sits in the
- SCSI stack as a low level device driver (below the SCSI disk and
- protocol drivers) for the IBM CXL Flash Adapter. This driver is
- responsible for the initialization of the adapter, setting up the
- special path for user space access, and performing error recovery. It
- communicates directly the Flash Accelerator Functional Unit (AFU)
- as described in Documentation/powerpc/cxl.txt.
-
- The cxlflash driver supports two, mutually exclusive, modes of
- operation at the device (LUN) level:
-
- - Any flash device (LUN) can be configured to be accessed as a
- regular disk device (i.e.: /dev/sdc). This is the default mode.
-
- - Any flash device (LUN) can be configured to be accessed from
- user space with a special block library. This mode further
- specifies the means of accessing the device and provides for
- either raw access to the entire LUN (referred to as direct
- or physical LUN access) or access to a kernel/AFU-mediated
- partition of the LUN (referred to as virtual LUN access). The
- segmentation of a disk device into virtual LUNs is assisted
- by special translation services provided by the Flash AFU.
-
-Overview
-========
-
- The Coherent Accelerator Interface Architecture (CAIA) introduces a
- concept of a master context. A master typically has special privileges
- granted to it by the kernel or hypervisor allowing it to perform AFU
- wide management and control. The master may or may not be involved
- directly in each user I/O, but at the minimum is involved in the
- initial setup before the user application is allowed to send requests
- directly to the AFU.
-
- The CXL Flash Adapter Driver establishes a master context with the
- AFU. It uses memory mapped I/O (MMIO) for this control and setup. The
- Adapter Problem Space Memory Map looks like this:
-
- +-------------------------------+
- | 512 * 64 KB User MMIO |
- | (per context) |
- | User Accessible |
- +-------------------------------+
- | 512 * 128 B per context |
- | Provisioning and Control |
- | Trusted Process accessible |
- +-------------------------------+
- | 64 KB Global |
- | Trusted Process accessible |
- +-------------------------------+
-
- This driver configures itself into the SCSI software stack as an
- adapter driver. The driver is the only entity that is considered a
- Trusted Process to program the Provisioning and Control and Global
- areas in the MMIO Space shown above. The master context driver
- discovers all LUNs attached to the CXL Flash adapter and instantiates
- scsi block devices (/dev/sdb, /dev/sdc etc.) for each unique LUN
- seen from each path.
-
- Once these scsi block devices are instantiated, an application
- written to a specification provided by the block library may get
- access to the Flash from user space (without requiring a system call).
-
- This master context driver also provides a series of ioctls for this
- block library to enable this user space access. The driver supports
- two modes for accessing the block device.
-
- The first mode is called a virtual mode. In this mode a single scsi
- block device (/dev/sdb) may be carved up into any number of distinct
- virtual LUNs. The virtual LUNs may be resized as long as the sum of
- the sizes of all the virtual LUNs, along with the meta-data associated
- with it does not exceed the physical capacity.
-
- The second mode is called the physical mode. In this mode a single
- block device (/dev/sdb) may be opened directly by the block library
- and the entire space for the LUN is available to the application.
-
- Only the physical mode provides persistence of the data. i.e. The
- data written to the block device will survive application exit and
- restart and also reboot. The virtual LUNs do not persist (i.e. do
- not survive after the application terminates or the system reboots).
-
-
-Block library API
-=================
-
- Applications intending to get access to the CXL Flash from user
- space should use the block library, as it abstracts the details of
- interfacing directly with the cxlflash driver that are necessary for
- performing administrative actions (i.e.: setup, tear down, resize).
- The block library can be thought of as a 'user' of services,
- implemented as IOCTLs, that are provided by the cxlflash driver
- specifically for devices (LUNs) operating in user space access
- mode. While it is not a requirement that applications understand
- the interface between the block library and the cxlflash driver,
- a high-level overview of each supported service (IOCTL) is provided
- below.
-
- The block library can be found on GitHub:
- http://github.com/open-power/capiflash
-
-
-CXL Flash Driver LUN IOCTLs
-===========================
-
- Users, such as the block library, that wish to interface with a flash
- device (LUN) via user space access need to use the services provided
- by the cxlflash driver. As these services are implemented as ioctls,
- a file descriptor handle must first be obtained in order to establish
- the communication channel between a user and the kernel. This file
- descriptor is obtained by opening the device special file associated
- with the scsi disk device (/dev/sdb) that was created during LUN
- discovery. As per the location of the cxlflash driver within the
- SCSI protocol stack, this open is actually not seen by the cxlflash
- driver. Upon successful open, the user receives a file descriptor
- (herein referred to as fd1) that should be used for issuing the
- subsequent ioctls listed below.
-
- The structure definitions for these IOCTLs are available in:
- uapi/scsi/cxlflash_ioctl.h
-
-DK_CXLFLASH_ATTACH
-------------------
-
- This ioctl obtains, initializes, and starts a context using the CXL
- kernel services. These services specify a context id (u16) by which
- to uniquely identify the context and its allocated resources. The
- services additionally provide a second file descriptor (herein
- referred to as fd2) that is used by the block library to initiate
- memory mapped I/O (via mmap()) to the CXL flash device and poll for
- completion events. This file descriptor is intentionally installed by
- this driver and not the CXL kernel services to allow for intermediary
- notification and access in the event of a non-user-initiated close(),
- such as a killed process. This design point is described in further
- detail in the description for the DK_CXLFLASH_DETACH ioctl.
-
- There are a few important aspects regarding the "tokens" (context id
- and fd2) that are provided back to the user:
-
- - These tokens are only valid for the process under which they
- were created. The child of a forked process cannot continue
- to use the context id or file descriptor created by its parent
- (see DK_CXLFLASH_VLUN_CLONE for further details).
-
- - These tokens are only valid for the lifetime of the context and
- the process under which they were created. Once either is
- destroyed, the tokens are to be considered stale and subsequent
- usage will result in errors.
-
- - A valid adapter file descriptor (fd2 >= 0) is only returned on
- the initial attach for a context. Subsequent attaches to an
- existing context (DK_CXLFLASH_ATTACH_REUSE_CONTEXT flag present)
- do not provide the adapter file descriptor as it was previously
- made known to the application.
-
- - When a context is no longer needed, the user shall detach from
- the context via the DK_CXLFLASH_DETACH ioctl. When this ioctl
- returns with a valid adapter file descriptor and the return flag
- DK_CXLFLASH_APP_CLOSE_ADAP_FD is present, the application _must_
- close the adapter file descriptor following a successful detach.
-
- - When this ioctl returns with a valid fd2 and the return flag
- DK_CXLFLASH_APP_CLOSE_ADAP_FD is present, the application _must_
- close fd2 in the following circumstances:
-
- + Following a successful detach of the last user of the context
- + Following a successful recovery on the context's original fd2
- + In the child process of a fork(), following a clone ioctl,
- on the fd2 associated with the source context
-
- - At any time, a close on fd2 will invalidate the tokens. Applications
- should exercise caution to only close fd2 when appropriate (outlined
- in the previous bullet) to avoid premature loss of I/O.
-
-DK_CXLFLASH_USER_DIRECT
------------------------
- This ioctl is responsible for transitioning the LUN to direct
- (physical) mode access and configuring the AFU for direct access from
- user space on a per-context basis. Additionally, the block size and
- last logical block address (LBA) are returned to the user.
-
- As mentioned previously, when operating in user space access mode,
- LUNs may be accessed in whole or in part. Only one mode is allowed
- at a time and if one mode is active (outstanding references exist),
- requests to use the LUN in a different mode are denied.
-
- The AFU is configured for direct access from user space by adding an
- entry to the AFU's resource handle table. The index of the entry is
- treated as a resource handle that is returned to the user. The user
- is then able to use the handle to reference the LUN during I/O.
-
-DK_CXLFLASH_USER_VIRTUAL
-------------------------
- This ioctl is responsible for transitioning the LUN to virtual mode
- of access and configuring the AFU for virtual access from user space
- on a per-context basis. Additionally, the block size and last logical
- block address (LBA) are returned to the user.
-
- As mentioned previously, when operating in user space access mode,
- LUNs may be accessed in whole or in part. Only one mode is allowed
- at a time and if one mode is active (outstanding references exist),
- requests to use the LUN in a different mode are denied.
-
- The AFU is configured for virtual access from user space by adding
- an entry to the AFU's resource handle table. The index of the entry
- is treated as a resource handle that is returned to the user. The
- user is then able to use the handle to reference the LUN during I/O.
-
- By default, the virtual LUN is created with a size of 0. The user
- would need to use the DK_CXLFLASH_VLUN_RESIZE ioctl to adjust the grow
- the virtual LUN to a desired size. To avoid having to perform this
- resize for the initial creation of the virtual LUN, the user has the
- option of specifying a size as part of the DK_CXLFLASH_USER_VIRTUAL
- ioctl, such that when success is returned to the user, the
- resource handle that is provided is already referencing provisioned
- storage. This is reflected by the last LBA being a non-zero value.
-
- When a LUN is accessible from more than one port, this ioctl will
- return with the DK_CXLFLASH_ALL_PORTS_ACTIVE return flag set. This
- provides the user with a hint that I/O can be retried in the event
- of an I/O error as the LUN can be reached over multiple paths.
-
-DK_CXLFLASH_VLUN_RESIZE
------------------------
- This ioctl is responsible for resizing a previously created virtual
- LUN and will fail if invoked upon a LUN that is not in virtual
- mode. Upon success, an updated last LBA is returned to the user
- indicating the new size of the virtual LUN associated with the
- resource handle.
-
- The partitioning of virtual LUNs is jointly mediated by the cxlflash
- driver and the AFU. An allocation table is kept for each LUN that is
- operating in the virtual mode and used to program a LUN translation
- table that the AFU references when provided with a resource handle.
-
- This ioctl can return -EAGAIN if an AFU sync operation takes too long.
- In addition to returning a failure to user, cxlflash will also schedule
- an asynchronous AFU reset. Should the user choose to retry the operation,
- it is expected to succeed. If this ioctl fails with -EAGAIN, the user
- can either retry the operation or treat it as a failure.
-
-DK_CXLFLASH_RELEASE
--------------------
- This ioctl is responsible for releasing a previously obtained
- reference to either a physical or virtual LUN. This can be
- thought of as the inverse of the DK_CXLFLASH_USER_DIRECT or
- DK_CXLFLASH_USER_VIRTUAL ioctls. Upon success, the resource handle
- is no longer valid and the entry in the resource handle table is
- made available to be used again.
-
- As part of the release process for virtual LUNs, the virtual LUN
- is first resized to 0 to clear out and free the translation tables
- associated with the virtual LUN reference.
-
-DK_CXLFLASH_DETACH
-------------------
- This ioctl is responsible for unregistering a context with the
- cxlflash driver and release outstanding resources that were
- not explicitly released via the DK_CXLFLASH_RELEASE ioctl. Upon
- success, all "tokens" which had been provided to the user from the
- DK_CXLFLASH_ATTACH onward are no longer valid.
-
- When the DK_CXLFLASH_APP_CLOSE_ADAP_FD flag was returned on a successful
- attach, the application _must_ close the fd2 associated with the context
- following the detach of the final user of the context.
-
-DK_CXLFLASH_VLUN_CLONE
-----------------------
- This ioctl is responsible for cloning a previously created
- context to a more recently created context. It exists solely to
- support maintaining user space access to storage after a process
- forks. Upon success, the child process (which invoked the ioctl)
- will have access to the same LUNs via the same resource handle(s)
- as the parent, but under a different context.
-
- Context sharing across processes is not supported with CXL and
- therefore each fork must be met with establishing a new context
- for the child process. This ioctl simplifies the state management
- and playback required by a user in such a scenario. When a process
- forks, child process can clone the parents context by first creating
- a context (via DK_CXLFLASH_ATTACH) and then using this ioctl to
- perform the clone from the parent to the child.
-
- The clone itself is fairly simple. The resource handle and lun
- translation tables are copied from the parent context to the child's
- and then synced with the AFU.
-
- When the DK_CXLFLASH_APP_CLOSE_ADAP_FD flag was returned on a successful
- attach, the application _must_ close the fd2 associated with the source
- context (still resident/accessible in the parent process) following the
- clone. This is to avoid a stale entry in the file descriptor table of the
- child process.
-
- This ioctl can return -EAGAIN if an AFU sync operation takes too long.
- In addition to returning a failure to user, cxlflash will also schedule
- an asynchronous AFU reset. Should the user choose to retry the operation,
- it is expected to succeed. If this ioctl fails with -EAGAIN, the user
- can either retry the operation or treat it as a failure.
-
-DK_CXLFLASH_VERIFY
-------------------
- This ioctl is used to detect various changes such as the capacity of
- the disk changing, the number of LUNs visible changing, etc. In cases
- where the changes affect the application (such as a LUN resize), the
- cxlflash driver will report the changed state to the application.
-
- The user calls in when they want to validate that a LUN hasn't been
- changed in response to a check condition. As the user is operating out
- of band from the kernel, they will see these types of events without
- the kernel's knowledge. When encountered, the user's architected
- behavior is to call in to this ioctl, indicating what they want to
- verify and passing along any appropriate information. For now, only
- verifying a LUN change (ie: size different) with sense data is
- supported.
-
-DK_CXLFLASH_RECOVER_AFU
------------------------
- This ioctl is used to drive recovery (if such an action is warranted)
- of a specified user context. Any state associated with the user context
- is re-established upon successful recovery.
-
- User contexts are put into an error condition when the device needs to
- be reset or is terminating. Users are notified of this error condition
- by seeing all 0xF's on an MMIO read. Upon encountering this, the
- architected behavior for a user is to call into this ioctl to recover
- their context. A user may also call into this ioctl at any time to
- check if the device is operating normally. If a failure is returned
- from this ioctl, the user is expected to gracefully clean up their
- context via release/detach ioctls. Until they do, the context they
- hold is not relinquished. The user may also optionally exit the process
- at which time the context/resources they held will be freed as part of
- the release fop.
-
- When the DK_CXLFLASH_APP_CLOSE_ADAP_FD flag was returned on a successful
- attach, the application _must_ unmap and close the fd2 associated with the
- original context following this ioctl returning success and indicating that
- the context was recovered (DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET).
-
-DK_CXLFLASH_MANAGE_LUN
-----------------------
- This ioctl is used to switch a LUN from a mode where it is available
- for file-system access (legacy), to a mode where it is set aside for
- exclusive user space access (superpipe). In case a LUN is visible
- across multiple ports and adapters, this ioctl is used to uniquely
- identify each LUN by its World Wide Node Name (WWNN).
-
-
-CXL Flash Driver Host IOCTLs
-============================
-
- Each host adapter instance that is supported by the cxlflash driver
- has a special character device associated with it to enable a set of
- host management function. These character devices are hosted in a
- class dedicated for cxlflash and can be accessed via /dev/cxlflash/*.
-
- Applications can be written to perform various functions using the
- host ioctl APIs below.
-
- The structure definitions for these IOCTLs are available in:
- uapi/scsi/cxlflash_ioctl.h
-
-HT_CXLFLASH_LUN_PROVISION
--------------------------
- This ioctl is used to create and delete persistent LUNs on cxlflash
- devices that lack an external LUN management interface. It is only
- valid when used with AFUs that support the LUN provision capability.
-
- When sufficient space is available, LUNs can be created by specifying
- the target port to host the LUN and a desired size in 4K blocks. Upon
- success, the LUN ID and WWID of the created LUN will be returned and
- the SCSI bus can be scanned to detect the change in LUN topology. Note
- that partial allocations are not supported. Should a creation fail due
- to a space issue, the target port can be queried for its current LUN
- geometry.
-
- To remove a LUN, the device must first be disassociated from the Linux
- SCSI subsystem. The LUN deletion can then be initiated by specifying a
- target port and LUN ID. Upon success, the LUN geometry associated with
- the port will be updated to reflect new number of provisioned LUNs and
- available capacity.
-
- To query the LUN geometry of a port, the target port is specified and
- upon success, the following information is presented:
-
- - Maximum number of provisioned LUNs allowed for the port
- - Current number of provisioned LUNs for the port
- - Maximum total capacity of provisioned LUNs for the port (4K blocks)
- - Current total capacity of provisioned LUNs for the port (4K blocks)
-
- With this information, the number of available LUNs and capacity can be
- can be calculated.
-
-HT_CXLFLASH_AFU_DEBUG
----------------------
- This ioctl is used to debug AFUs by supporting a command pass-through
- interface. It is only valid when used with AFUs that support the AFU
- debug capability.
-
- With exception of buffer management, AFU debug commands are opaque to
- cxlflash and treated as pass-through. For debug commands that do require
- data transfer, the user supplies an adequately sized data buffer and must
- specify the data transfer direction with respect to the host. There is a
- maximum transfer size of 256K imposed. Note that partial read completions
- are not supported - when errors are experienced with a host read data
- transfer, the data buffer is not copied back to the user.
--- /dev/null
+=====================
+DAWR issues on POWER9
+=====================
+
+On POWER9 the Data Address Watchpoint Register (DAWR) can cause a checkstop
+if it points to cache inhibited (CI) memory. Currently Linux has no way to
+disinguish CI memory when configuring the DAWR, so (for now) the DAWR is
+disabled by this commit::
+
+ commit 9654153158d3e0684a1bdb76dbababdb7111d5a0
+ Author: Michael Neuling <mikey@neuling.org>
+ Date: Tue Mar 27 15:37:24 2018 +1100
+ powerpc: Disable DAWR in the base POWER9 CPU features
+
+Technical Details:
+==================
+
+DAWR has 6 different ways of being set.
+1) ptrace
+2) h_set_mode(DAWR)
+3) h_set_dabr()
+4) kvmppc_set_one_reg()
+5) xmon
+
+For ptrace, we now advertise zero breakpoints on POWER9 via the
+PPC_PTRACE_GETHWDBGINFO call. This results in GDB falling back to
+software emulation of the watchpoint (which is slow).
+
+h_set_mode(DAWR) and h_set_dabr() will now return an error to the
+guest on a POWER9 host. Current Linux guests ignore this error, so
+they will silently not get the DAWR.
+
+kvmppc_set_one_reg() will store the value in the vcpu but won't
+actually set it on POWER9 hardware. This is done so we don't break
+migration from POWER8 to POWER9, at the cost of silently losing the
+DAWR on the migration.
+
+For xmon, the 'bd' command will return an error on P9.
+
+Consequences for users
+======================
+
+For GDB watchpoints (ie 'watch' command) on POWER9 bare metal , GDB
+will accept the command. Unfortunately since there is no hardware
+support for the watchpoint, GDB will software emulate the watchpoint
+making it run very slowly.
+
+The same will also be true for any guests started on a POWER9
+host. The watchpoint will fail and GDB will fall back to software
+emulation.
+
+If a guest is started on a POWER8 host, GDB will accept the watchpoint
+and configure the hardware to use the DAWR. This will run at full
+speed since it can use the hardware emulation. Unfortunately if this
+guest is migrated to a POWER9 host, the watchpoint will be lost on the
+POWER9. Loads and stores to the watchpoint locations will not be
+trapped in GDB. The watchpoint is remembered, so if the guest is
+migrated back to the POWER8 host, it will start working again.
+
+Force enabling the DAWR
+=======================
+Kernels (since ~v5.2) have an option to force enable the DAWR via::
+
+ echo Y > /sys/kernel/debug/powerpc/dawr_enable_dangerous
+
+This enables the DAWR even on POWER9.
+
+This is a dangerous setting, USE AT YOUR OWN RISK.
+
+Some users may not care about a bad user crashing their box
+(ie. single user/desktop systems) and really want the DAWR. This
+allows them to force enable DAWR.
+
+This flag can also be used to disable DAWR access. Once this is
+cleared, all DAWR access should be cleared immediately and your
+machine once again safe from crashing.
+
+Userspace may get confused by toggling this. If DAWR is force
+enabled/disabled between getting the number of breakpoints (via
+PTRACE_GETHWDBGINFO) and setting the breakpoint, userspace will get an
+inconsistent view of what's available. Similarly for guests.
+
+For the DAWR to be enabled in a KVM guest, the DAWR needs to be force
+enabled in the host AND the guest. For this reason, this won't work on
+POWERVM as it doesn't allow the HCALL to work. Writes of 'Y' to the
+dawr_enable_dangerous file will fail if the hypervisor doesn't support
+writing the DAWR.
+
+To double check the DAWR is working, run this kernel selftest:
+
+ tools/testing/selftests/powerpc/ptrace/ptrace-hwbreak.c
+
+Any errors/failures/skips mean something is wrong.
--- /dev/null
+===================================
+DSCR (Data Stream Control Register)
+===================================
+
+DSCR register in powerpc allows user to have some control of prefetch of data
+stream in the processor. Please refer to the ISA documents or related manual
+for more detailed information regarding how to use this DSCR to attain this
+control of the prefetches . This document here provides an overview of kernel
+support for DSCR, related kernel objects, it's functionalities and exported
+user interface.
+
+(A) Data Structures:
+
+ (1) thread_struct::
+
+ dscr /* Thread DSCR value */
+ dscr_inherit /* Thread has changed default DSCR */
+
+ (2) PACA::
+
+ dscr_default /* per-CPU DSCR default value */
+
+ (3) sysfs.c::
+
+ dscr_default /* System DSCR default value */
+
+(B) Scheduler Changes:
+
+ Scheduler will write the per-CPU DSCR default which is stored in the
+ CPU's PACA value into the register if the thread has dscr_inherit value
+ cleared which means that it has not changed the default DSCR till now.
+ If the dscr_inherit value is set which means that it has changed the
+ default DSCR value, scheduler will write the changed value which will
+ now be contained in thread struct's dscr into the register instead of
+ the per-CPU default PACA based DSCR value.
+
+ NOTE: Please note here that the system wide global DSCR value never
+ gets used directly in the scheduler process context switch at all.
+
+(C) SYSFS Interface:
+
+ - Global DSCR default: /sys/devices/system/cpu/dscr_default
+ - CPU specific DSCR default: /sys/devices/system/cpu/cpuN/dscr
+
+ Changing the global DSCR default in the sysfs will change all the CPU
+ specific DSCR defaults immediately in their PACA structures. Again if
+ the current process has the dscr_inherit clear, it also writes the new
+ value into every CPU's DSCR register right away and updates the current
+ thread's DSCR value as well.
+
+ Changing the CPU specific DSCR default value in the sysfs does exactly
+ the same thing as above but unlike the global one above, it just changes
+ stuff for that particular CPU instead for all the CPUs on the system.
+
+(D) User Space Instructions:
+
+ The DSCR register can be accessed in the user space using any of these
+ two SPR numbers available for that purpose.
+
+ (1) Problem state SPR: 0x03 (Un-privileged, POWER8 only)
+ (2) Privileged state SPR: 0x11 (Privileged)
+
+ Accessing DSCR through privileged SPR number (0x11) from user space
+ works, as it is emulated following an illegal instruction exception
+ inside the kernel. Both mfspr and mtspr instructions are emulated.
+
+ Accessing DSCR through user level SPR (0x03) from user space will first
+ create a facility unavailable exception. Inside this exception handler
+ all mfspr instruction based read attempts will get emulated and returned
+ where as the first mtspr instruction based write attempts will enable
+ the DSCR facility for the next time around (both for read and write) by
+ setting DSCR facility in the FSCR register.
+
+(E) Specifics about 'dscr_inherit':
+
+ The thread struct element 'dscr_inherit' represents whether the thread
+ in question has attempted and changed the DSCR itself using any of the
+ following methods. This element signifies whether the thread wants to
+ use the CPU default DSCR value or its own changed DSCR value in the
+ kernel.
+
+ (1) mtspr instruction (SPR number 0x03)
+ (2) mtspr instruction (SPR number 0x11)
+ (3) ptrace interface (Explicitly set user DSCR value)
+
+ Any child of the process created after this event in the process inherits
+ this same behaviour as well.
+++ /dev/null
- DSCR (Data Stream Control Register)
- ================================================
-
-DSCR register in powerpc allows user to have some control of prefetch of data
-stream in the processor. Please refer to the ISA documents or related manual
-for more detailed information regarding how to use this DSCR to attain this
-control of the prefetches . This document here provides an overview of kernel
-support for DSCR, related kernel objects, it's functionalities and exported
-user interface.
-
-(A) Data Structures:
-
- (1) thread_struct:
- dscr /* Thread DSCR value */
- dscr_inherit /* Thread has changed default DSCR */
-
- (2) PACA:
- dscr_default /* per-CPU DSCR default value */
-
- (3) sysfs.c:
- dscr_default /* System DSCR default value */
-
-(B) Scheduler Changes:
-
- Scheduler will write the per-CPU DSCR default which is stored in the
- CPU's PACA value into the register if the thread has dscr_inherit value
- cleared which means that it has not changed the default DSCR till now.
- If the dscr_inherit value is set which means that it has changed the
- default DSCR value, scheduler will write the changed value which will
- now be contained in thread struct's dscr into the register instead of
- the per-CPU default PACA based DSCR value.
-
- NOTE: Please note here that the system wide global DSCR value never
- gets used directly in the scheduler process context switch at all.
-
-(C) SYSFS Interface:
-
- Global DSCR default: /sys/devices/system/cpu/dscr_default
- CPU specific DSCR default: /sys/devices/system/cpu/cpuN/dscr
-
- Changing the global DSCR default in the sysfs will change all the CPU
- specific DSCR defaults immediately in their PACA structures. Again if
- the current process has the dscr_inherit clear, it also writes the new
- value into every CPU's DSCR register right away and updates the current
- thread's DSCR value as well.
-
- Changing the CPU specific DSCR default value in the sysfs does exactly
- the same thing as above but unlike the global one above, it just changes
- stuff for that particular CPU instead for all the CPUs on the system.
-
-(D) User Space Instructions:
-
- The DSCR register can be accessed in the user space using any of these
- two SPR numbers available for that purpose.
-
- (1) Problem state SPR: 0x03 (Un-privileged, POWER8 only)
- (2) Privileged state SPR: 0x11 (Privileged)
-
- Accessing DSCR through privileged SPR number (0x11) from user space
- works, as it is emulated following an illegal instruction exception
- inside the kernel. Both mfspr and mtspr instructions are emulated.
-
- Accessing DSCR through user level SPR (0x03) from user space will first
- create a facility unavailable exception. Inside this exception handler
- all mfspr instruction based read attempts will get emulated and returned
- where as the first mtspr instruction based write attempts will enable
- the DSCR facility for the next time around (both for read and write) by
- setting DSCR facility in the FSCR register.
-
-(E) Specifics about 'dscr_inherit':
-
- The thread struct element 'dscr_inherit' represents whether the thread
- in question has attempted and changed the DSCR itself using any of the
- following methods. This element signifies whether the thread wants to
- use the CPU default DSCR value or its own changed DSCR value in the
- kernel.
-
- (1) mtspr instruction (SPR number 0x03)
- (2) mtspr instruction (SPR number 0x11)
- (3) ptrace interface (Explicitly set user DSCR value)
-
- Any child of the process created after this event in the process inherits
- this same behaviour as well.
--- /dev/null
+==========================
+PCI Bus EEH Error Recovery
+==========================
+
+Linas Vepstas <linas@austin.ibm.com>
+
+12 January 2005
+
+
+Overview:
+---------
+The IBM POWER-based pSeries and iSeries computers include PCI bus
+controller chips that have extended capabilities for detecting and
+reporting a large variety of PCI bus error conditions. These features
+go under the name of "EEH", for "Enhanced Error Handling". The EEH
+hardware features allow PCI bus errors to be cleared and a PCI
+card to be "rebooted", without also having to reboot the operating
+system.
+
+This is in contrast to traditional PCI error handling, where the
+PCI chip is wired directly to the CPU, and an error would cause
+a CPU machine-check/check-stop condition, halting the CPU entirely.
+Another "traditional" technique is to ignore such errors, which
+can lead to data corruption, both of user data or of kernel data,
+hung/unresponsive adapters, or system crashes/lockups. Thus,
+the idea behind EEH is that the operating system can become more
+reliable and robust by protecting it from PCI errors, and giving
+the OS the ability to "reboot"/recover individual PCI devices.
+
+Future systems from other vendors, based on the PCI-E specification,
+may contain similar features.
+
+
+Causes of EEH Errors
+--------------------
+EEH was originally designed to guard against hardware failure, such
+as PCI cards dying from heat, humidity, dust, vibration and bad
+electrical connections. The vast majority of EEH errors seen in
+"real life" are due to either poorly seated PCI cards, or,
+unfortunately quite commonly, due to device driver bugs, device firmware
+bugs, and sometimes PCI card hardware bugs.
+
+The most common software bug, is one that causes the device to
+attempt to DMA to a location in system memory that has not been
+reserved for DMA access for that card. This is a powerful feature,
+as it prevents what; otherwise, would have been silent memory
+corruption caused by the bad DMA. A number of device driver
+bugs have been found and fixed in this way over the past few
+years. Other possible causes of EEH errors include data or
+address line parity errors (for example, due to poor electrical
+connectivity due to a poorly seated card), and PCI-X split-completion
+errors (due to software, device firmware, or device PCI hardware bugs).
+The vast majority of "true hardware failures" can be cured by
+physically removing and re-seating the PCI card.
+
+
+Detection and Recovery
+----------------------
+In the following discussion, a generic overview of how to detect
+and recover from EEH errors will be presented. This is followed
+by an overview of how the current implementation in the Linux
+kernel does it. The actual implementation is subject to change,
+and some of the finer points are still being debated. These
+may in turn be swayed if or when other architectures implement
+similar functionality.
+
+When a PCI Host Bridge (PHB, the bus controller connecting the
+PCI bus to the system CPU electronics complex) detects a PCI error
+condition, it will "isolate" the affected PCI card. Isolation
+will block all writes (either to the card from the system, or
+from the card to the system), and it will cause all reads to
+return all-ff's (0xff, 0xffff, 0xffffffff for 8/16/32-bit reads).
+This value was chosen because it is the same value you would
+get if the device was physically unplugged from the slot.
+This includes access to PCI memory, I/O space, and PCI config
+space. Interrupts; however, will continued to be delivered.
+
+Detection and recovery are performed with the aid of ppc64
+firmware. The programming interfaces in the Linux kernel
+into the firmware are referred to as RTAS (Run-Time Abstraction
+Services). The Linux kernel does not (should not) access
+the EEH function in the PCI chipsets directly, primarily because
+there are a number of different chipsets out there, each with
+different interfaces and quirks. The firmware provides a
+uniform abstraction layer that will work with all pSeries
+and iSeries hardware (and be forwards-compatible).
+
+If the OS or device driver suspects that a PCI slot has been
+EEH-isolated, there is a firmware call it can make to determine if
+this is the case. If so, then the device driver should put itself
+into a consistent state (given that it won't be able to complete any
+pending work) and start recovery of the card. Recovery normally
+would consist of resetting the PCI device (holding the PCI #RST
+line high for two seconds), followed by setting up the device
+config space (the base address registers (BAR's), latency timer,
+cache line size, interrupt line, and so on). This is followed by a
+reinitialization of the device driver. In a worst-case scenario,
+the power to the card can be toggled, at least on hot-plug-capable
+slots. In principle, layers far above the device driver probably
+do not need to know that the PCI card has been "rebooted" in this
+way; ideally, there should be at most a pause in Ethernet/disk/USB
+I/O while the card is being reset.
+
+If the card cannot be recovered after three or four resets, the
+kernel/device driver should assume the worst-case scenario, that the
+card has died completely, and report this error to the sysadmin.
+In addition, error messages are reported through RTAS and also through
+syslogd (/var/log/messages) to alert the sysadmin of PCI resets.
+The correct way to deal with failed adapters is to use the standard
+PCI hotplug tools to remove and replace the dead card.
+
+
+Current PPC64 Linux EEH Implementation
+--------------------------------------
+At this time, a generic EEH recovery mechanism has been implemented,
+so that individual device drivers do not need to be modified to support
+EEH recovery. This generic mechanism piggy-backs on the PCI hotplug
+infrastructure, and percolates events up through the userspace/udev
+infrastructure. Following is a detailed description of how this is
+accomplished.
+
+EEH must be enabled in the PHB's very early during the boot process,
+and if a PCI slot is hot-plugged. The former is performed by
+eeh_init() in arch/powerpc/platforms/pseries/eeh.c, and the later by
+drivers/pci/hotplug/pSeries_pci.c calling in to the eeh.c code.
+EEH must be enabled before a PCI scan of the device can proceed.
+Current Power5 hardware will not work unless EEH is enabled;
+although older Power4 can run with it disabled. Effectively,
+EEH can no longer be turned off. PCI devices *must* be
+registered with the EEH code; the EEH code needs to know about
+the I/O address ranges of the PCI device in order to detect an
+error. Given an arbitrary address, the routine
+pci_get_device_by_addr() will find the pci device associated
+with that address (if any).
+
+The default arch/powerpc/include/asm/io.h macros readb(), inb(), insb(),
+etc. include a check to see if the i/o read returned all-0xff's.
+If so, these make a call to eeh_dn_check_failure(), which in turn
+asks the firmware if the all-ff's value is the sign of a true EEH
+error. If it is not, processing continues as normal. The grand
+total number of these false alarms or "false positives" can be
+seen in /proc/ppc64/eeh (subject to change). Normally, almost
+all of these occur during boot, when the PCI bus is scanned, where
+a large number of 0xff reads are part of the bus scan procedure.
+
+If a frozen slot is detected, code in
+arch/powerpc/platforms/pseries/eeh.c will print a stack trace to
+syslog (/var/log/messages). This stack trace has proven to be very
+useful to device-driver authors for finding out at what point the EEH
+error was detected, as the error itself usually occurs slightly
+beforehand.
+
+Next, it uses the Linux kernel notifier chain/work queue mechanism to
+allow any interested parties to find out about the failure. Device
+drivers, or other parts of the kernel, can use
+`eeh_register_notifier(struct notifier_block *)` to find out about EEH
+events. The event will include a pointer to the pci device, the
+device node and some state info. Receivers of the event can "do as
+they wish"; the default handler will be described further in this
+section.
+
+To assist in the recovery of the device, eeh.c exports the
+following functions:
+
+rtas_set_slot_reset()
+ assert the PCI #RST line for 1/8th of a second
+rtas_configure_bridge()
+ ask firmware to configure any PCI bridges
+ located topologically under the pci slot.
+eeh_save_bars() and eeh_restore_bars():
+ save and restore the PCI
+ config-space info for a device and any devices under it.
+
+
+A handler for the EEH notifier_block events is implemented in
+drivers/pci/hotplug/pSeries_pci.c, called handle_eeh_events().
+It saves the device BAR's and then calls rpaphp_unconfig_pci_adapter().
+This last call causes the device driver for the card to be stopped,
+which causes uevents to go out to user space. This triggers
+user-space scripts that might issue commands such as "ifdown eth0"
+for ethernet cards, and so on. This handler then sleeps for 5 seconds,
+hoping to give the user-space scripts enough time to complete.
+It then resets the PCI card, reconfigures the device BAR's, and
+any bridges underneath. It then calls rpaphp_enable_pci_slot(),
+which restarts the device driver and triggers more user-space
+events (for example, calling "ifup eth0" for ethernet cards).
+
+
+Device Shutdown and User-Space Events
+-------------------------------------
+This section documents what happens when a pci slot is unconfigured,
+focusing on how the device driver gets shut down, and on how the
+events get delivered to user-space scripts.
+
+Following is an example sequence of events that cause a device driver
+close function to be called during the first phase of an EEH reset.
+The following sequence is an example of the pcnet32 device driver::
+
+ rpa_php_unconfig_pci_adapter (struct slot *) // in rpaphp_pci.c
+ {
+ calls
+ pci_remove_bus_device (struct pci_dev *) // in /drivers/pci/remove.c
+ {
+ calls
+ pci_destroy_dev (struct pci_dev *)
+ {
+ calls
+ device_unregister (&dev->dev) // in /drivers/base/core.c
+ {
+ calls
+ device_del (struct device *)
+ {
+ calls
+ bus_remove_device() // in /drivers/base/bus.c
+ {
+ calls
+ device_release_driver()
+ {
+ calls
+ struct device_driver->remove() which is just
+ pci_device_remove() // in /drivers/pci/pci_driver.c
+ {
+ calls
+ struct pci_driver->remove() which is just
+ pcnet32_remove_one() // in /drivers/net/pcnet32.c
+ {
+ calls
+ unregister_netdev() // in /net/core/dev.c
+ {
+ calls
+ dev_close() // in /net/core/dev.c
+ {
+ calls dev->stop();
+ which is just pcnet32_close() // in pcnet32.c
+ {
+ which does what you wanted
+ to stop the device
+ }
+ }
+ }
+ which
+ frees pcnet32 device driver memory
+ }
+ }}}}}}
+
+
+in drivers/pci/pci_driver.c,
+struct device_driver->remove() is just pci_device_remove()
+which calls struct pci_driver->remove() which is pcnet32_remove_one()
+which calls unregister_netdev() (in net/core/dev.c)
+which calls dev_close() (in net/core/dev.c)
+which calls dev->stop() which is pcnet32_close()
+which then does the appropriate shutdown.
+
+---
+
+Following is the analogous stack trace for events sent to user-space
+when the pci device is unconfigured::
+
+ rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c
+ calls
+ pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c
+ calls
+ pci_destroy_dev (struct pci_dev *) {
+ calls
+ device_unregister (&dev->dev) { // in /drivers/base/core.c
+ calls
+ device_del(struct device * dev) { // in /drivers/base/core.c
+ calls
+ kobject_del() { //in /libs/kobject.c
+ calls
+ kobject_uevent() { // in /libs/kobject.c
+ calls
+ kset_uevent() { // in /lib/kobject.c
+ calls
+ kset->uevent_ops->uevent() // which is really just
+ a call to
+ dev_uevent() { // in /drivers/base/core.c
+ calls
+ dev->bus->uevent() which is really just a call to
+ pci_uevent () { // in drivers/pci/hotplug.c
+ which prints device name, etc....
+ }
+ }
+ then kobject_uevent() sends a netlink uevent to userspace
+ --> userspace uevent
+ (during early boot, nobody listens to netlink events and
+ kobject_uevent() executes uevent_helper[], which runs the
+ event process /sbin/hotplug)
+ }
+ }
+ kobject_del() then calls sysfs_remove_dir(), which would
+ trigger any user-space daemon that was watching /sysfs,
+ and notice the delete event.
+
+
+Pro's and Con's of the Current Design
+-------------------------------------
+There are several issues with the current EEH software recovery design,
+which may be addressed in future revisions. But first, note that the
+big plus of the current design is that no changes need to be made to
+individual device drivers, so that the current design throws a wide net.
+The biggest negative of the design is that it potentially disturbs
+network daemons and file systems that didn't need to be disturbed.
+
+- A minor complaint is that resetting the network card causes
+ user-space back-to-back ifdown/ifup burps that potentially disturb
+ network daemons, that didn't need to even know that the pci
+ card was being rebooted.
+
+- A more serious concern is that the same reset, for SCSI devices,
+ causes havoc to mounted file systems. Scripts cannot post-facto
+ unmount a file system without flushing pending buffers, but this
+ is impossible, because I/O has already been stopped. Thus,
+ ideally, the reset should happen at or below the block layer,
+ so that the file systems are not disturbed.
+
+ Reiserfs does not tolerate errors returned from the block device.
+ Ext3fs seems to be tolerant, retrying reads/writes until it does
+ succeed. Both have been only lightly tested in this scenario.
+
+ The SCSI-generic subsystem already has built-in code for performing
+ SCSI device resets, SCSI bus resets, and SCSI host-bus-adapter
+ (HBA) resets. These are cascaded into a chain of attempted
+ resets if a SCSI command fails. These are completely hidden
+ from the block layer. It would be very natural to add an EEH
+ reset into this chain of events.
+
+- If a SCSI error occurs for the root device, all is lost unless
+ the sysadmin had the foresight to run /bin, /sbin, /etc, /var
+ and so on, out of ramdisk/tmpfs.
+
+
+Conclusions
+-----------
+There's forward progress ...
+++ /dev/null
-
-
- PCI Bus EEH Error Recovery
- --------------------------
- Linas Vepstas
- <linas@austin.ibm.com>
- 12 January 2005
-
-
-Overview:
----------
-The IBM POWER-based pSeries and iSeries computers include PCI bus
-controller chips that have extended capabilities for detecting and
-reporting a large variety of PCI bus error conditions. These features
-go under the name of "EEH", for "Enhanced Error Handling". The EEH
-hardware features allow PCI bus errors to be cleared and a PCI
-card to be "rebooted", without also having to reboot the operating
-system.
-
-This is in contrast to traditional PCI error handling, where the
-PCI chip is wired directly to the CPU, and an error would cause
-a CPU machine-check/check-stop condition, halting the CPU entirely.
-Another "traditional" technique is to ignore such errors, which
-can lead to data corruption, both of user data or of kernel data,
-hung/unresponsive adapters, or system crashes/lockups. Thus,
-the idea behind EEH is that the operating system can become more
-reliable and robust by protecting it from PCI errors, and giving
-the OS the ability to "reboot"/recover individual PCI devices.
-
-Future systems from other vendors, based on the PCI-E specification,
-may contain similar features.
-
-
-Causes of EEH Errors
---------------------
-EEH was originally designed to guard against hardware failure, such
-as PCI cards dying from heat, humidity, dust, vibration and bad
-electrical connections. The vast majority of EEH errors seen in
-"real life" are due to either poorly seated PCI cards, or,
-unfortunately quite commonly, due to device driver bugs, device firmware
-bugs, and sometimes PCI card hardware bugs.
-
-The most common software bug, is one that causes the device to
-attempt to DMA to a location in system memory that has not been
-reserved for DMA access for that card. This is a powerful feature,
-as it prevents what; otherwise, would have been silent memory
-corruption caused by the bad DMA. A number of device driver
-bugs have been found and fixed in this way over the past few
-years. Other possible causes of EEH errors include data or
-address line parity errors (for example, due to poor electrical
-connectivity due to a poorly seated card), and PCI-X split-completion
-errors (due to software, device firmware, or device PCI hardware bugs).
-The vast majority of "true hardware failures" can be cured by
-physically removing and re-seating the PCI card.
-
-
-Detection and Recovery
-----------------------
-In the following discussion, a generic overview of how to detect
-and recover from EEH errors will be presented. This is followed
-by an overview of how the current implementation in the Linux
-kernel does it. The actual implementation is subject to change,
-and some of the finer points are still being debated. These
-may in turn be swayed if or when other architectures implement
-similar functionality.
-
-When a PCI Host Bridge (PHB, the bus controller connecting the
-PCI bus to the system CPU electronics complex) detects a PCI error
-condition, it will "isolate" the affected PCI card. Isolation
-will block all writes (either to the card from the system, or
-from the card to the system), and it will cause all reads to
-return all-ff's (0xff, 0xffff, 0xffffffff for 8/16/32-bit reads).
-This value was chosen because it is the same value you would
-get if the device was physically unplugged from the slot.
-This includes access to PCI memory, I/O space, and PCI config
-space. Interrupts; however, will continued to be delivered.
-
-Detection and recovery are performed with the aid of ppc64
-firmware. The programming interfaces in the Linux kernel
-into the firmware are referred to as RTAS (Run-Time Abstraction
-Services). The Linux kernel does not (should not) access
-the EEH function in the PCI chipsets directly, primarily because
-there are a number of different chipsets out there, each with
-different interfaces and quirks. The firmware provides a
-uniform abstraction layer that will work with all pSeries
-and iSeries hardware (and be forwards-compatible).
-
-If the OS or device driver suspects that a PCI slot has been
-EEH-isolated, there is a firmware call it can make to determine if
-this is the case. If so, then the device driver should put itself
-into a consistent state (given that it won't be able to complete any
-pending work) and start recovery of the card. Recovery normally
-would consist of resetting the PCI device (holding the PCI #RST
-line high for two seconds), followed by setting up the device
-config space (the base address registers (BAR's), latency timer,
-cache line size, interrupt line, and so on). This is followed by a
-reinitialization of the device driver. In a worst-case scenario,
-the power to the card can be toggled, at least on hot-plug-capable
-slots. In principle, layers far above the device driver probably
-do not need to know that the PCI card has been "rebooted" in this
-way; ideally, there should be at most a pause in Ethernet/disk/USB
-I/O while the card is being reset.
-
-If the card cannot be recovered after three or four resets, the
-kernel/device driver should assume the worst-case scenario, that the
-card has died completely, and report this error to the sysadmin.
-In addition, error messages are reported through RTAS and also through
-syslogd (/var/log/messages) to alert the sysadmin of PCI resets.
-The correct way to deal with failed adapters is to use the standard
-PCI hotplug tools to remove and replace the dead card.
-
-
-Current PPC64 Linux EEH Implementation
---------------------------------------
-At this time, a generic EEH recovery mechanism has been implemented,
-so that individual device drivers do not need to be modified to support
-EEH recovery. This generic mechanism piggy-backs on the PCI hotplug
-infrastructure, and percolates events up through the userspace/udev
-infrastructure. Following is a detailed description of how this is
-accomplished.
-
-EEH must be enabled in the PHB's very early during the boot process,
-and if a PCI slot is hot-plugged. The former is performed by
-eeh_init() in arch/powerpc/platforms/pseries/eeh.c, and the later by
-drivers/pci/hotplug/pSeries_pci.c calling in to the eeh.c code.
-EEH must be enabled before a PCI scan of the device can proceed.
-Current Power5 hardware will not work unless EEH is enabled;
-although older Power4 can run with it disabled. Effectively,
-EEH can no longer be turned off. PCI devices *must* be
-registered with the EEH code; the EEH code needs to know about
-the I/O address ranges of the PCI device in order to detect an
-error. Given an arbitrary address, the routine
-pci_get_device_by_addr() will find the pci device associated
-with that address (if any).
-
-The default arch/powerpc/include/asm/io.h macros readb(), inb(), insb(),
-etc. include a check to see if the i/o read returned all-0xff's.
-If so, these make a call to eeh_dn_check_failure(), which in turn
-asks the firmware if the all-ff's value is the sign of a true EEH
-error. If it is not, processing continues as normal. The grand
-total number of these false alarms or "false positives" can be
-seen in /proc/ppc64/eeh (subject to change). Normally, almost
-all of these occur during boot, when the PCI bus is scanned, where
-a large number of 0xff reads are part of the bus scan procedure.
-
-If a frozen slot is detected, code in
-arch/powerpc/platforms/pseries/eeh.c will print a stack trace to
-syslog (/var/log/messages). This stack trace has proven to be very
-useful to device-driver authors for finding out at what point the EEH
-error was detected, as the error itself usually occurs slightly
-beforehand.
-
-Next, it uses the Linux kernel notifier chain/work queue mechanism to
-allow any interested parties to find out about the failure. Device
-drivers, or other parts of the kernel, can use
-eeh_register_notifier(struct notifier_block *) to find out about EEH
-events. The event will include a pointer to the pci device, the
-device node and some state info. Receivers of the event can "do as
-they wish"; the default handler will be described further in this
-section.
-
-To assist in the recovery of the device, eeh.c exports the
-following functions:
-
-rtas_set_slot_reset() -- assert the PCI #RST line for 1/8th of a second
-rtas_configure_bridge() -- ask firmware to configure any PCI bridges
- located topologically under the pci slot.
-eeh_save_bars() and eeh_restore_bars(): save and restore the PCI
- config-space info for a device and any devices under it.
-
-
-A handler for the EEH notifier_block events is implemented in
-drivers/pci/hotplug/pSeries_pci.c, called handle_eeh_events().
-It saves the device BAR's and then calls rpaphp_unconfig_pci_adapter().
-This last call causes the device driver for the card to be stopped,
-which causes uevents to go out to user space. This triggers
-user-space scripts that might issue commands such as "ifdown eth0"
-for ethernet cards, and so on. This handler then sleeps for 5 seconds,
-hoping to give the user-space scripts enough time to complete.
-It then resets the PCI card, reconfigures the device BAR's, and
-any bridges underneath. It then calls rpaphp_enable_pci_slot(),
-which restarts the device driver and triggers more user-space
-events (for example, calling "ifup eth0" for ethernet cards).
-
-
-Device Shutdown and User-Space Events
--------------------------------------
-This section documents what happens when a pci slot is unconfigured,
-focusing on how the device driver gets shut down, and on how the
-events get delivered to user-space scripts.
-
-Following is an example sequence of events that cause a device driver
-close function to be called during the first phase of an EEH reset.
-The following sequence is an example of the pcnet32 device driver.
-
- rpa_php_unconfig_pci_adapter (struct slot *) // in rpaphp_pci.c
- {
- calls
- pci_remove_bus_device (struct pci_dev *) // in /drivers/pci/remove.c
- {
- calls
- pci_destroy_dev (struct pci_dev *)
- {
- calls
- device_unregister (&dev->dev) // in /drivers/base/core.c
- {
- calls
- device_del (struct device *)
- {
- calls
- bus_remove_device() // in /drivers/base/bus.c
- {
- calls
- device_release_driver()
- {
- calls
- struct device_driver->remove() which is just
- pci_device_remove() // in /drivers/pci/pci_driver.c
- {
- calls
- struct pci_driver->remove() which is just
- pcnet32_remove_one() // in /drivers/net/pcnet32.c
- {
- calls
- unregister_netdev() // in /net/core/dev.c
- {
- calls
- dev_close() // in /net/core/dev.c
- {
- calls dev->stop();
- which is just pcnet32_close() // in pcnet32.c
- {
- which does what you wanted
- to stop the device
- }
- }
- }
- which
- frees pcnet32 device driver memory
- }
- }}}}}}
-
-
- in drivers/pci/pci_driver.c,
- struct device_driver->remove() is just pci_device_remove()
- which calls struct pci_driver->remove() which is pcnet32_remove_one()
- which calls unregister_netdev() (in net/core/dev.c)
- which calls dev_close() (in net/core/dev.c)
- which calls dev->stop() which is pcnet32_close()
- which then does the appropriate shutdown.
-
----
-Following is the analogous stack trace for events sent to user-space
-when the pci device is unconfigured.
-
-rpa_php_unconfig_pci_adapter() { // in rpaphp_pci.c
- calls
- pci_remove_bus_device (struct pci_dev *) { // in /drivers/pci/remove.c
- calls
- pci_destroy_dev (struct pci_dev *) {
- calls
- device_unregister (&dev->dev) { // in /drivers/base/core.c
- calls
- device_del(struct device * dev) { // in /drivers/base/core.c
- calls
- kobject_del() { //in /libs/kobject.c
- calls
- kobject_uevent() { // in /libs/kobject.c
- calls
- kset_uevent() { // in /lib/kobject.c
- calls
- kset->uevent_ops->uevent() // which is really just
- a call to
- dev_uevent() { // in /drivers/base/core.c
- calls
- dev->bus->uevent() which is really just a call to
- pci_uevent () { // in drivers/pci/hotplug.c
- which prints device name, etc....
- }
- }
- then kobject_uevent() sends a netlink uevent to userspace
- --> userspace uevent
- (during early boot, nobody listens to netlink events and
- kobject_uevent() executes uevent_helper[], which runs the
- event process /sbin/hotplug)
- }
- }
- kobject_del() then calls sysfs_remove_dir(), which would
- trigger any user-space daemon that was watching /sysfs,
- and notice the delete event.
-
-
-Pro's and Con's of the Current Design
--------------------------------------
-There are several issues with the current EEH software recovery design,
-which may be addressed in future revisions. But first, note that the
-big plus of the current design is that no changes need to be made to
-individual device drivers, so that the current design throws a wide net.
-The biggest negative of the design is that it potentially disturbs
-network daemons and file systems that didn't need to be disturbed.
-
--- A minor complaint is that resetting the network card causes
- user-space back-to-back ifdown/ifup burps that potentially disturb
- network daemons, that didn't need to even know that the pci
- card was being rebooted.
-
--- A more serious concern is that the same reset, for SCSI devices,
- causes havoc to mounted file systems. Scripts cannot post-facto
- unmount a file system without flushing pending buffers, but this
- is impossible, because I/O has already been stopped. Thus,
- ideally, the reset should happen at or below the block layer,
- so that the file systems are not disturbed.
-
- Reiserfs does not tolerate errors returned from the block device.
- Ext3fs seems to be tolerant, retrying reads/writes until it does
- succeed. Both have been only lightly tested in this scenario.
-
- The SCSI-generic subsystem already has built-in code for performing
- SCSI device resets, SCSI bus resets, and SCSI host-bus-adapter
- (HBA) resets. These are cascaded into a chain of attempted
- resets if a SCSI command fails. These are completely hidden
- from the block layer. It would be very natural to add an EEH
- reset into this chain of events.
-
--- If a SCSI error occurs for the root device, all is lost unless
- the sysadmin had the foresight to run /bin, /sbin, /etc, /var
- and so on, out of ramdisk/tmpfs.
-
-
-Conclusions
------------
-There's forward progress ...
-
-
--- /dev/null
+======================
+Firmware-Assisted Dump
+======================
+
+July 2011
+
+The goal of firmware-assisted dump is to enable the dump of
+a crashed system, and to do so from a fully-reset system, and
+to minimize the total elapsed time until the system is back
+in production use.
+
+- Firmware assisted dump (fadump) infrastructure is intended to replace
+ the existing phyp assisted dump.
+- Fadump uses the same firmware interfaces and memory reservation model
+ as phyp assisted dump.
+- Unlike phyp dump, fadump exports the memory dump through /proc/vmcore
+ in the ELF format in the same way as kdump. This helps us reuse the
+ kdump infrastructure for dump capture and filtering.
+- Unlike phyp dump, userspace tool does not need to refer any sysfs
+ interface while reading /proc/vmcore.
+- Unlike phyp dump, fadump allows user to release all the memory reserved
+ for dump, with a single operation of echo 1 > /sys/kernel/fadump_release_mem.
+- Once enabled through kernel boot parameter, fadump can be
+ started/stopped through /sys/kernel/fadump_registered interface (see
+ sysfs files section below) and can be easily integrated with kdump
+ service start/stop init scripts.
+
+Comparing with kdump or other strategies, firmware-assisted
+dump offers several strong, practical advantages:
+
+- Unlike kdump, the system has been reset, and loaded
+ with a fresh copy of the kernel. In particular,
+ PCI and I/O devices have been reinitialized and are
+ in a clean, consistent state.
+- Once the dump is copied out, the memory that held the dump
+ is immediately available to the running kernel. And therefore,
+ unlike kdump, fadump doesn't need a 2nd reboot to get back
+ the system to the production configuration.
+
+The above can only be accomplished by coordination with,
+and assistance from the Power firmware. The procedure is
+as follows:
+
+- The first kernel registers the sections of memory with the
+ Power firmware for dump preservation during OS initialization.
+ These registered sections of memory are reserved by the first
+ kernel during early boot.
+
+- When a system crashes, the Power firmware will save
+ the low memory (boot memory of size larger of 5% of system RAM
+ or 256MB) of RAM to the previous registered region. It will
+ also save system registers, and hardware PTE's.
+
+ NOTE:
+ The term 'boot memory' means size of the low memory chunk
+ that is required for a kernel to boot successfully when
+ booted with restricted memory. By default, the boot memory
+ size will be the larger of 5% of system RAM or 256MB.
+ Alternatively, user can also specify boot memory size
+ through boot parameter 'crashkernel=' which will override
+ the default calculated size. Use this option if default
+ boot memory size is not sufficient for second kernel to
+ boot successfully. For syntax of crashkernel= parameter,
+ refer to Documentation/admin-guide/kdump/kdump.rst. If any offset is
+ provided in crashkernel= parameter, it will be ignored
+ as fadump uses a predefined offset to reserve memory
+ for boot memory dump preservation in case of a crash.
+
+- After the low memory (boot memory) area has been saved, the
+ firmware will reset PCI and other hardware state. It will
+ *not* clear the RAM. It will then launch the bootloader, as
+ normal.
+
+- The freshly booted kernel will notice that there is a new
+ node (ibm,dump-kernel) in the device tree, indicating that
+ there is crash data available from a previous boot. During
+ the early boot OS will reserve rest of the memory above
+ boot memory size effectively booting with restricted memory
+ size. This will make sure that the second kernel will not
+ touch any of the dump memory area.
+
+- User-space tools will read /proc/vmcore to obtain the contents
+ of memory, which holds the previous crashed kernel dump in ELF
+ format. The userspace tools may copy this info to disk, or
+ network, nas, san, iscsi, etc. as desired.
+
+- Once the userspace tool is done saving dump, it will echo
+ '1' to /sys/kernel/fadump_release_mem to release the reserved
+ memory back to general use, except the memory required for
+ next firmware-assisted dump registration.
+
+ e.g.::
+
+ # echo 1 > /sys/kernel/fadump_release_mem
+
+Please note that the firmware-assisted dump feature
+is only available on Power6 and above systems with recent
+firmware versions.
+
+Implementation details:
+-----------------------
+
+During boot, a check is made to see if firmware supports
+this feature on that particular machine. If it does, then
+we check to see if an active dump is waiting for us. If yes
+then everything but boot memory size of RAM is reserved during
+early boot (See Fig. 2). This area is released once we finish
+collecting the dump from user land scripts (e.g. kdump scripts)
+that are run. If there is dump data, then the
+/sys/kernel/fadump_release_mem file is created, and the reserved
+memory is held.
+
+If there is no waiting dump data, then only the memory required
+to hold CPU state, HPTE region, boot memory dump and elfcore
+header, is usually reserved at an offset greater than boot memory
+size (see Fig. 1). This area is *not* released: this region will
+be kept permanently reserved, so that it can act as a receptacle
+for a copy of the boot memory content in addition to CPU state
+and HPTE region, in the case a crash does occur. Since this reserved
+memory area is used only after the system crash, there is no point in
+blocking this significant chunk of memory from production kernel.
+Hence, the implementation uses the Linux kernel's Contiguous Memory
+Allocator (CMA) for memory reservation if CMA is configured for kernel.
+With CMA reservation this memory will be available for applications to
+use it, while kernel is prevented from using it. With this fadump will
+still be able to capture all of the kernel memory and most of the user
+space memory except the user pages that were present in CMA region::
+
+ o Memory Reservation during first kernel
+
+ Low memory Top of memory
+ 0 boot memory size |
+ | | |<--Reserved dump area -->| |
+ V V | Permanent Reservation | V
+ +-----------+----------/ /---+---+----+-----------+----+------+
+ | | |CPU|HPTE| DUMP |ELF | |
+ +-----------+----------/ /---+---+----+-----------+----+------+
+ | ^
+ | |
+ \ /
+ -------------------------------------------
+ Boot memory content gets transferred to
+ reserved area by firmware at the time of
+ crash
+ Fig. 1
+
+ o Memory Reservation during second kernel after crash
+
+ Low memory Top of memory
+ 0 boot memory size |
+ | |<------------- Reserved dump area ----------- -->|
+ V V V
+ +-----------+----------/ /---+---+----+-----------+----+------+
+ | | |CPU|HPTE| DUMP |ELF | |
+ +-----------+----------/ /---+---+----+-----------+----+------+
+ | |
+ V V
+ Used by second /proc/vmcore
+ kernel to boot
+ Fig. 2
+
+Currently the dump will be copied from /proc/vmcore to a
+a new file upon user intervention. The dump data available through
+/proc/vmcore will be in ELF format. Hence the existing kdump
+infrastructure (kdump scripts) to save the dump works fine with
+minor modifications.
+
+The tools to examine the dump will be same as the ones
+used for kdump.
+
+How to enable firmware-assisted dump (fadump):
+----------------------------------------------
+
+1. Set config option CONFIG_FA_DUMP=y and build kernel.
+2. Boot into linux kernel with 'fadump=on' kernel cmdline option.
+ By default, fadump reserved memory will be initialized as CMA area.
+ Alternatively, user can boot linux kernel with 'fadump=nocma' to
+ prevent fadump to use CMA.
+3. Optionally, user can also set 'crashkernel=' kernel cmdline
+ to specify size of the memory to reserve for boot memory dump
+ preservation.
+
+NOTE:
+ 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead
+ use 'crashkernel=' to specify size of the memory to reserve
+ for boot memory dump preservation.
+ 2. If firmware-assisted dump fails to reserve memory then it
+ will fallback to existing kdump mechanism if 'crashkernel='
+ option is set at kernel cmdline.
+ 3. if user wants to capture all of user space memory and ok with
+ reserved memory not available to production system, then
+ 'fadump=nocma' kernel parameter can be used to fallback to
+ old behaviour.
+
+Sysfs/debugfs files:
+--------------------
+
+Firmware-assisted dump feature uses sysfs file system to hold
+the control files and debugfs file to display memory reserved region.
+
+Here is the list of files under kernel sysfs:
+
+ /sys/kernel/fadump_enabled
+ This is used to display the fadump status.
+
+ - 0 = fadump is disabled
+ - 1 = fadump is enabled
+
+ This interface can be used by kdump init scripts to identify if
+ fadump is enabled in the kernel and act accordingly.
+
+ /sys/kernel/fadump_registered
+ This is used to display the fadump registration status as well
+ as to control (start/stop) the fadump registration.
+
+ - 0 = fadump is not registered.
+ - 1 = fadump is registered and ready to handle system crash.
+
+ To register fadump echo 1 > /sys/kernel/fadump_registered and
+ echo 0 > /sys/kernel/fadump_registered for un-register and stop the
+ fadump. Once the fadump is un-registered, the system crash will not
+ be handled and vmcore will not be captured. This interface can be
+ easily integrated with kdump service start/stop.
+
+ /sys/kernel/fadump_release_mem
+ This file is available only when fadump is active during
+ second kernel. This is used to release the reserved memory
+ region that are held for saving crash dump. To release the
+ reserved memory echo 1 to it::
+
+ echo 1 > /sys/kernel/fadump_release_mem
+
+ After echo 1, the content of the /sys/kernel/debug/powerpc/fadump_region
+ file will change to reflect the new memory reservations.
+
+ The existing userspace tools (kdump infrastructure) can be easily
+ enhanced to use this interface to release the memory reserved for
+ dump and continue without 2nd reboot.
+
+Here is the list of files under powerpc debugfs:
+(Assuming debugfs is mounted on /sys/kernel/debug directory.)
+
+ /sys/kernel/debug/powerpc/fadump_region
+ This file shows the reserved memory regions if fadump is
+ enabled otherwise this file is empty. The output format
+ is::
+
+ <region>: [<start>-<end>] <reserved-size> bytes, Dumped: <dump-size>
+
+ e.g.
+ Contents when fadump is registered during first kernel::
+
+ # cat /sys/kernel/debug/powerpc/fadump_region
+ CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0
+ HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0
+ DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0
+
+ Contents when fadump is active during second kernel::
+
+ # cat /sys/kernel/debug/powerpc/fadump_region
+ CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020
+ HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000
+ DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000
+ : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000
+
+NOTE:
+ Please refer to Documentation/filesystems/debugfs.txt on
+ how to mount the debugfs filesystem.
+
+
+TODO:
+-----
+ - Need to come up with the better approach to find out more
+ accurate boot memory size that is required for a kernel to
+ boot successfully when booted with restricted memory.
+ - The fadump implementation introduces a fadump crash info structure
+ in the scratch area before the ELF core header. The idea of introducing
+ this structure is to pass some important crash info data to the second
+ kernel which will help second kernel to populate ELF core header with
+ correct data before it gets exported through /proc/vmcore. The current
+ design implementation does not address a possibility of introducing
+ additional fields (in future) to this structure without affecting
+ compatibility. Need to come up with the better approach to address this.
+
+ The possible approaches are:
+
+ 1. Introduce version field for version tracking, bump up the version
+ whenever a new field is added to the structure in future. The version
+ field can be used to find out what fields are valid for the current
+ version of the structure.
+ 2. Reserve the area of predefined size (say PAGE_SIZE) for this
+ structure and have unused area as reserved (initialized to zero)
+ for future field additions.
+
+ The advantage of approach 1 over 2 is we don't need to reserve extra space.
+
+Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+
+This document is based on the original documentation written for phyp
+
+assisted dump by Linas Vepstas and Manish Ahuja.
+++ /dev/null
-
- Firmware-Assisted Dump
- ------------------------
- July 2011
-
-The goal of firmware-assisted dump is to enable the dump of
-a crashed system, and to do so from a fully-reset system, and
-to minimize the total elapsed time until the system is back
-in production use.
-
-- Firmware assisted dump (fadump) infrastructure is intended to replace
- the existing phyp assisted dump.
-- Fadump uses the same firmware interfaces and memory reservation model
- as phyp assisted dump.
-- Unlike phyp dump, fadump exports the memory dump through /proc/vmcore
- in the ELF format in the same way as kdump. This helps us reuse the
- kdump infrastructure for dump capture and filtering.
-- Unlike phyp dump, userspace tool does not need to refer any sysfs
- interface while reading /proc/vmcore.
-- Unlike phyp dump, fadump allows user to release all the memory reserved
- for dump, with a single operation of echo 1 > /sys/kernel/fadump_release_mem.
-- Once enabled through kernel boot parameter, fadump can be
- started/stopped through /sys/kernel/fadump_registered interface (see
- sysfs files section below) and can be easily integrated with kdump
- service start/stop init scripts.
-
-Comparing with kdump or other strategies, firmware-assisted
-dump offers several strong, practical advantages:
-
--- Unlike kdump, the system has been reset, and loaded
- with a fresh copy of the kernel. In particular,
- PCI and I/O devices have been reinitialized and are
- in a clean, consistent state.
--- Once the dump is copied out, the memory that held the dump
- is immediately available to the running kernel. And therefore,
- unlike kdump, fadump doesn't need a 2nd reboot to get back
- the system to the production configuration.
-
-The above can only be accomplished by coordination with,
-and assistance from the Power firmware. The procedure is
-as follows:
-
--- The first kernel registers the sections of memory with the
- Power firmware for dump preservation during OS initialization.
- These registered sections of memory are reserved by the first
- kernel during early boot.
-
--- When a system crashes, the Power firmware will save
- the low memory (boot memory of size larger of 5% of system RAM
- or 256MB) of RAM to the previous registered region. It will
- also save system registers, and hardware PTE's.
-
- NOTE: The term 'boot memory' means size of the low memory chunk
- that is required for a kernel to boot successfully when
- booted with restricted memory. By default, the boot memory
- size will be the larger of 5% of system RAM or 256MB.
- Alternatively, user can also specify boot memory size
- through boot parameter 'crashkernel=' which will override
- the default calculated size. Use this option if default
- boot memory size is not sufficient for second kernel to
- boot successfully. For syntax of crashkernel= parameter,
- refer to Documentation/admin-guide/kdump/kdump.rst. If any offset is
- provided in crashkernel= parameter, it will be ignored
- as fadump uses a predefined offset to reserve memory
- for boot memory dump preservation in case of a crash.
-
--- After the low memory (boot memory) area has been saved, the
- firmware will reset PCI and other hardware state. It will
- *not* clear the RAM. It will then launch the bootloader, as
- normal.
-
--- The freshly booted kernel will notice that there is a new
- node (ibm,dump-kernel) in the device tree, indicating that
- there is crash data available from a previous boot. During
- the early boot OS will reserve rest of the memory above
- boot memory size effectively booting with restricted memory
- size. This will make sure that the second kernel will not
- touch any of the dump memory area.
-
--- User-space tools will read /proc/vmcore to obtain the contents
- of memory, which holds the previous crashed kernel dump in ELF
- format. The userspace tools may copy this info to disk, or
- network, nas, san, iscsi, etc. as desired.
-
--- Once the userspace tool is done saving dump, it will echo
- '1' to /sys/kernel/fadump_release_mem to release the reserved
- memory back to general use, except the memory required for
- next firmware-assisted dump registration.
-
- e.g.
- # echo 1 > /sys/kernel/fadump_release_mem
-
-Please note that the firmware-assisted dump feature
-is only available on Power6 and above systems with recent
-firmware versions.
-
-Implementation details:
-----------------------
-
-During boot, a check is made to see if firmware supports
-this feature on that particular machine. If it does, then
-we check to see if an active dump is waiting for us. If yes
-then everything but boot memory size of RAM is reserved during
-early boot (See Fig. 2). This area is released once we finish
-collecting the dump from user land scripts (e.g. kdump scripts)
-that are run. If there is dump data, then the
-/sys/kernel/fadump_release_mem file is created, and the reserved
-memory is held.
-
-If there is no waiting dump data, then only the memory required
-to hold CPU state, HPTE region, boot memory dump and elfcore
-header, is usually reserved at an offset greater than boot memory
-size (see Fig. 1). This area is *not* released: this region will
-be kept permanently reserved, so that it can act as a receptacle
-for a copy of the boot memory content in addition to CPU state
-and HPTE region, in the case a crash does occur. Since this reserved
-memory area is used only after the system crash, there is no point in
-blocking this significant chunk of memory from production kernel.
-Hence, the implementation uses the Linux kernel's Contiguous Memory
-Allocator (CMA) for memory reservation if CMA is configured for kernel.
-With CMA reservation this memory will be available for applications to
-use it, while kernel is prevented from using it. With this fadump will
-still be able to capture all of the kernel memory and most of the user
-space memory except the user pages that were present in CMA region.
-
- o Memory Reservation during first kernel
-
- Low memory Top of memory
- 0 boot memory size |
- | | |<--Reserved dump area -->| |
- V V | Permanent Reservation | V
- +-----------+----------/ /---+---+----+-----------+----+------+
- | | |CPU|HPTE| DUMP |ELF | |
- +-----------+----------/ /---+---+----+-----------+----+------+
- | ^
- | |
- \ /
- -------------------------------------------
- Boot memory content gets transferred to
- reserved area by firmware at the time of
- crash
- Fig. 1
-
- o Memory Reservation during second kernel after crash
-
- Low memory Top of memory
- 0 boot memory size |
- | |<------------- Reserved dump area ----------- -->|
- V V V
- +-----------+----------/ /---+---+----+-----------+----+------+
- | | |CPU|HPTE| DUMP |ELF | |
- +-----------+----------/ /---+---+----+-----------+----+------+
- | |
- V V
- Used by second /proc/vmcore
- kernel to boot
- Fig. 2
-
-Currently the dump will be copied from /proc/vmcore to a
-a new file upon user intervention. The dump data available through
-/proc/vmcore will be in ELF format. Hence the existing kdump
-infrastructure (kdump scripts) to save the dump works fine with
-minor modifications.
-
-The tools to examine the dump will be same as the ones
-used for kdump.
-
-How to enable firmware-assisted dump (fadump):
--------------------------------------
-
-1. Set config option CONFIG_FA_DUMP=y and build kernel.
-2. Boot into linux kernel with 'fadump=on' kernel cmdline option.
- By default, fadump reserved memory will be initialized as CMA area.
- Alternatively, user can boot linux kernel with 'fadump=nocma' to
- prevent fadump to use CMA.
-3. Optionally, user can also set 'crashkernel=' kernel cmdline
- to specify size of the memory to reserve for boot memory dump
- preservation.
-
-NOTE: 1. 'fadump_reserve_mem=' parameter has been deprecated. Instead
- use 'crashkernel=' to specify size of the memory to reserve
- for boot memory dump preservation.
- 2. If firmware-assisted dump fails to reserve memory then it
- will fallback to existing kdump mechanism if 'crashkernel='
- option is set at kernel cmdline.
- 3. if user wants to capture all of user space memory and ok with
- reserved memory not available to production system, then
- 'fadump=nocma' kernel parameter can be used to fallback to
- old behaviour.
-
-Sysfs/debugfs files:
-------------
-
-Firmware-assisted dump feature uses sysfs file system to hold
-the control files and debugfs file to display memory reserved region.
-
-Here is the list of files under kernel sysfs:
-
- /sys/kernel/fadump_enabled
-
- This is used to display the fadump status.
- 0 = fadump is disabled
- 1 = fadump is enabled
-
- This interface can be used by kdump init scripts to identify if
- fadump is enabled in the kernel and act accordingly.
-
- /sys/kernel/fadump_registered
-
- This is used to display the fadump registration status as well
- as to control (start/stop) the fadump registration.
- 0 = fadump is not registered.
- 1 = fadump is registered and ready to handle system crash.
-
- To register fadump echo 1 > /sys/kernel/fadump_registered and
- echo 0 > /sys/kernel/fadump_registered for un-register and stop the
- fadump. Once the fadump is un-registered, the system crash will not
- be handled and vmcore will not be captured. This interface can be
- easily integrated with kdump service start/stop.
-
- /sys/kernel/fadump_release_mem
-
- This file is available only when fadump is active during
- second kernel. This is used to release the reserved memory
- region that are held for saving crash dump. To release the
- reserved memory echo 1 to it:
-
- echo 1 > /sys/kernel/fadump_release_mem
-
- After echo 1, the content of the /sys/kernel/debug/powerpc/fadump_region
- file will change to reflect the new memory reservations.
-
- The existing userspace tools (kdump infrastructure) can be easily
- enhanced to use this interface to release the memory reserved for
- dump and continue without 2nd reboot.
-
-Here is the list of files under powerpc debugfs:
-(Assuming debugfs is mounted on /sys/kernel/debug directory.)
-
- /sys/kernel/debug/powerpc/fadump_region
-
- This file shows the reserved memory regions if fadump is
- enabled otherwise this file is empty. The output format
- is:
- <region>: [<start>-<end>] <reserved-size> bytes, Dumped: <dump-size>
-
- e.g.
- Contents when fadump is registered during first kernel
-
- # cat /sys/kernel/debug/powerpc/fadump_region
- CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0
- HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0
- DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0
-
- Contents when fadump is active during second kernel
-
- # cat /sys/kernel/debug/powerpc/fadump_region
- CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020
- HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000
- DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000
- : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000
-
-NOTE: Please refer to Documentation/filesystems/debugfs.txt on
- how to mount the debugfs filesystem.
-
-
-TODO:
------
- o Need to come up with the better approach to find out more
- accurate boot memory size that is required for a kernel to
- boot successfully when booted with restricted memory.
- o The fadump implementation introduces a fadump crash info structure
- in the scratch area before the ELF core header. The idea of introducing
- this structure is to pass some important crash info data to the second
- kernel which will help second kernel to populate ELF core header with
- correct data before it gets exported through /proc/vmcore. The current
- design implementation does not address a possibility of introducing
- additional fields (in future) to this structure without affecting
- compatibility. Need to come up with the better approach to address this.
- The possible approaches are:
- 1. Introduce version field for version tracking, bump up the version
- whenever a new field is added to the structure in future. The version
- field can be used to find out what fields are valid for the current
- version of the structure.
- 2. Reserve the area of predefined size (say PAGE_SIZE) for this
- structure and have unused area as reserved (initialized to zero)
- for future field additions.
- The advantage of approach 1 over 2 is we don't need to reserve extra space.
----
-Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
-This document is based on the original documentation written for phyp
-assisted dump by Linas Vepstas and Manish Ahuja.
--- /dev/null
+===============================================================
+HVCS IBM "Hypervisor Virtual Console Server" Installation Guide
+===============================================================
+
+for Linux Kernel 2.6.4+
+
+Copyright (C) 2004 IBM Corporation
+
+.. ===========================================================================
+.. NOTE:Eight space tabs are the optimum editor setting for reading this file.
+.. ===========================================================================
+
+
+Author(s): Ryan S. Arnold <rsa@us.ibm.com>
+
+Date Created: March, 02, 2004
+Last Changed: August, 24, 2004
+
+.. Table of contents:
+
+ 1. Driver Introduction:
+ 2. System Requirements
+ 3. Build Options:
+ 3.1 Built-in:
+ 3.2 Module:
+ 4. Installation:
+ 5. Connection:
+ 6. Disconnection:
+ 7. Configuration:
+ 8. Questions & Answers:
+ 9. Reporting Bugs:
+
+1. Driver Introduction:
+=======================
+
+This is the device driver for the IBM Hypervisor Virtual Console Server,
+"hvcs". The IBM hvcs provides a tty driver interface to allow Linux user
+space applications access to the system consoles of logically partitioned
+operating systems (Linux and AIX) running on the same partitioned Power5
+ppc64 system. Physical hardware consoles per partition are not practical
+on this hardware so system consoles are accessed by this driver using
+firmware interfaces to virtual terminal devices.
+
+2. System Requirements:
+=======================
+
+This device driver was written using 2.6.4 Linux kernel APIs and will only
+build and run on kernels of this version or later.
+
+This driver was written to operate solely on IBM Power5 ppc64 hardware
+though some care was taken to abstract the architecture dependent firmware
+calls from the driver code.
+
+Sysfs must be mounted on the system so that the user can determine which
+major and minor numbers are associated with each vty-server. Directions
+for sysfs mounting are outside the scope of this document.
+
+3. Build Options:
+=================
+
+The hvcs driver registers itself as a tty driver. The tty layer
+dynamically allocates a block of major and minor numbers in a quantity
+requested by the registering driver. The hvcs driver asks the tty layer
+for 64 of these major/minor numbers by default to use for hvcs device node
+entries.
+
+If the default number of device entries is adequate then this driver can be
+built into the kernel. If not, the default can be over-ridden by inserting
+the driver as a module with insmod parameters.
+
+3.1 Built-in:
+-------------
+
+The following menuconfig example demonstrates selecting to build this
+driver into the kernel::
+
+ Device Drivers --->
+ Character devices --->
+ <*> IBM Hypervisor Virtual Console Server Support
+
+Begin the kernel make process.
+
+3.2 Module:
+-----------
+
+The following menuconfig example demonstrates selecting to build this
+driver as a kernel module::
+
+ Device Drivers --->
+ Character devices --->
+ <M> IBM Hypervisor Virtual Console Server Support
+
+The make process will build the following kernel modules:
+
+ - hvcs.ko
+ - hvcserver.ko
+
+To insert the module with the default allocation execute the following
+commands in the order they appear::
+
+ insmod hvcserver.ko
+ insmod hvcs.ko
+
+The hvcserver module contains architecture specific firmware calls and must
+be inserted first, otherwise the hvcs module will not find some of the
+symbols it expects.
+
+To override the default use an insmod parameter as follows (requesting 4
+tty devices as an example)::
+
+ insmod hvcs.ko hvcs_parm_num_devs=4
+
+There is a maximum number of dev entries that can be specified on insmod.
+We think that 1024 is currently a decent maximum number of server adapters
+to allow. This can always be changed by modifying the constant in the
+source file before building.
+
+NOTE: The length of time it takes to insmod the driver seems to be related
+to the number of tty interfaces the registering driver requests.
+
+In order to remove the driver module execute the following command::
+
+ rmmod hvcs.ko
+
+The recommended method for installing hvcs as a module is to use depmod to
+build a current modules.dep file in /lib/modules/`uname -r` and then
+execute::
+
+ modprobe hvcs hvcs_parm_num_devs=4
+
+The modules.dep file indicates that hvcserver.ko needs to be inserted
+before hvcs.ko and modprobe uses this file to smartly insert the modules in
+the proper order.
+
+The following modprobe command is used to remove hvcs and hvcserver in the
+proper order::
+
+ modprobe -r hvcs
+
+4. Installation:
+================
+
+The tty layer creates sysfs entries which contain the major and minor
+numbers allocated for the hvcs driver. The following snippet of "tree"
+output of the sysfs directory shows where these numbers are presented::
+
+ sys/
+ |-- *other sysfs base dirs*
+ |
+ |-- class
+ | |-- *other classes of devices*
+ | |
+ | `-- tty
+ | |-- *other tty devices*
+ | |
+ | |-- hvcs0
+ | | `-- dev
+ | |-- hvcs1
+ | | `-- dev
+ | |-- hvcs2
+ | | `-- dev
+ | |-- hvcs3
+ | | `-- dev
+ | |
+ | |-- *other tty devices*
+ |
+ |-- *other sysfs base dirs*
+
+For the above examples the following output is a result of cat'ing the
+"dev" entry in the hvcs directory::
+
+ Pow5:/sys/class/tty/hvcs0/ # cat dev
+ 254:0
+
+ Pow5:/sys/class/tty/hvcs1/ # cat dev
+ 254:1
+
+ Pow5:/sys/class/tty/hvcs2/ # cat dev
+ 254:2
+
+ Pow5:/sys/class/tty/hvcs3/ # cat dev
+ 254:3
+
+The output from reading the "dev" attribute is the char device major and
+minor numbers that the tty layer has allocated for this driver's use. Most
+systems running hvcs will already have the device entries created or udev
+will do it automatically.
+
+Given the example output above, to manually create a /dev/hvcs* node entry
+mknod can be used as follows::
+
+ mknod /dev/hvcs0 c 254 0
+ mknod /dev/hvcs1 c 254 1
+ mknod /dev/hvcs2 c 254 2
+ mknod /dev/hvcs3 c 254 3
+
+Using mknod to manually create the device entries makes these device nodes
+persistent. Once created they will exist prior to the driver insmod.
+
+Attempting to connect an application to /dev/hvcs* prior to insertion of
+the hvcs module will result in an error message similar to the following::
+
+ "/dev/hvcs*: No such device".
+
+NOTE: Just because there is a device node present doesn't mean that there
+is a vty-server device configured for that node.
+
+5. Connection
+=============
+
+Since this driver controls devices that provide a tty interface a user can
+interact with the device node entries using any standard tty-interactive
+method (e.g. "cat", "dd", "echo"). The intent of this driver however, is
+to provide real time console interaction with a Linux partition's console,
+which requires the use of applications that provide bi-directional,
+interactive I/O with a tty device.
+
+Applications (e.g. "minicom" and "screen") that act as terminal emulators
+or perform terminal type control sequence conversion on the data being
+passed through them are NOT acceptable for providing interactive console
+I/O. These programs often emulate antiquated terminal types (vt100 and
+ANSI) and expect inbound data to take the form of one of these supported
+terminal types but they either do not convert, or do not _adequately_
+convert, outbound data into the terminal type of the terminal which invoked
+them (though screen makes an attempt and can apparently be configured with
+much termcap wrestling.)
+
+For this reason kermit and cu are two of the recommended applications for
+interacting with a Linux console via an hvcs device. These programs simply
+act as a conduit for data transfer to and from the tty device. They do not
+require inbound data to take the form of a particular terminal type, nor do
+they cook outbound data to a particular terminal type.
+
+In order to ensure proper functioning of console applications one must make
+sure that once connected to a /dev/hvcs console that the console's $TERM
+env variable is set to the exact terminal type of the terminal emulator
+used to launch the interactive I/O application. If one is using xterm and
+kermit to connect to /dev/hvcs0 when the console prompt becomes available
+one should "export TERM=xterm" on the console. This tells ncurses
+applications that are invoked from the console that they should output
+control sequences that xterm can understand.
+
+As a precautionary measure an hvcs user should always "exit" from their
+session before disconnecting an application such as kermit from the device
+node. If this is not done, the next user to connect to the console will
+continue using the previous user's logged in session which includes
+using the $TERM variable that the previous user supplied.
+
+Hotplug add and remove of vty-server adapters affects which /dev/hvcs* node
+is used to connect to each vty-server adapter. In order to determine which
+vty-server adapter is associated with which /dev/hvcs* node a special sysfs
+attribute has been added to each vty-server sysfs entry. This entry is
+called "index" and showing it reveals an integer that refers to the
+/dev/hvcs* entry to use to connect to that device. For instance cating the
+index attribute of vty-server adapter 30000004 shows the following::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat index
+ 2
+
+This index of '2' means that in order to connect to vty-server adapter
+30000004 the user should interact with /dev/hvcs2.
+
+It should be noted that due to the system hotplug I/O capabilities of a
+system the /dev/hvcs* entry that interacts with a particular vty-server
+adapter is not guaranteed to remain the same across system reboots. Look
+in the Q & A section for more on this issue.
+
+6. Disconnection
+================
+
+As a security feature to prevent the delivery of stale data to an
+unintended target the Power5 system firmware disables the fetching of data
+and discards that data when a connection between a vty-server and a vty has
+been severed. As an example, when a vty-server is immediately disconnected
+from a vty following output of data to the vty the vty adapter may not have
+enough time between when it received the data interrupt and when the
+connection was severed to fetch the data from firmware before the fetch is
+disabled by firmware.
+
+When hvcs is being used to serve consoles this behavior is not a huge issue
+because the adapter stays connected for large amounts of time following
+almost all data writes. When hvcs is being used as a tty conduit to tunnel
+data between two partitions [see Q & A below] this is a huge problem
+because the standard Linux behavior when cat'ing or dd'ing data to a device
+is to open the tty, send the data, and then close the tty. If this driver
+manually terminated vty-server connections on tty close this would close
+the vty-server and vty connection before the target vty has had a chance to
+fetch the data.
+
+Additionally, disconnecting a vty-server and vty only on module removal or
+adapter removal is impractical because other vty-servers in other
+partitions may require the usage of the target vty at any time.
+
+Due to this behavioral restriction disconnection of vty-servers from the
+connected vty is a manual procedure using a write to a sysfs attribute
+outlined below, on the other hand the initial vty-server connection to a
+vty is established automatically by this driver. Manual vty-server
+connection is never required.
+
+In order to terminate the connection between a vty-server and vty the
+"vterm_state" sysfs attribute within each vty-server's sysfs entry is used.
+Reading this attribute reveals the current connection state of the
+vty-server adapter. A zero means that the vty-server is not connected to a
+vty. A one indicates that a connection is active.
+
+Writing a '0' (zero) to the vterm_state attribute will disconnect the VTERM
+connection between the vty-server and target vty ONLY if the vterm_state
+previously read '1'. The write directive is ignored if the vterm_state
+read '0' or if any value other than '0' was written to the vterm_state
+attribute. The following example will show the method used for verifying
+the vty-server connection status and disconnecting a vty-server connection::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat vterm_state
+ 1
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # echo 0 > vterm_state
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat vterm_state
+ 0
+
+All vty-server connections are automatically terminated when the device is
+hotplug removed and when the module is removed.
+
+7. Configuration
+================
+
+Each vty-server has a sysfs entry in the /sys/devices/vio directory, which
+is symlinked in several other sysfs tree directories, notably under the
+hvcs driver entry, which looks like the following example::
+
+ Pow5:/sys/bus/vio/drivers/hvcs # ls
+ . .. 30000003 30000004 rescan
+
+By design, firmware notifies the hvcs driver of vty-server lifetimes and
+partner vty removals but not the addition of partner vtys. Since an HMC
+Super Admin can add partner info dynamically we have provided the hvcs
+driver sysfs directory with the "rescan" update attribute which will query
+firmware and update the partner info for all the vty-servers that this
+driver manages. Writing a '1' to the attribute triggers the update. An
+explicit example follows:
+
+ Pow5:/sys/bus/vio/drivers/hvcs # echo 1 > rescan
+
+Reading the attribute will indicate a state of '1' or '0'. A one indicates
+that an update is in process. A zero indicates that an update has
+completed or was never executed.
+
+Vty-server entries in this directory are a 32 bit partition unique unit
+address that is created by firmware. An example vty-server sysfs entry
+looks like the following::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # ls
+ . current_vty devspec name partner_vtys
+ .. index partner_clcs vterm_state
+
+Each entry is provided, by default with a "name" attribute. Reading the
+"name" attribute will reveal the device type as shown in the following
+example::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000003 # cat name
+ vty-server
+
+Each entry is also provided, by default, with a "devspec" attribute which
+reveals the full device specification when read, as shown in the following
+example::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat devspec
+ /vdevice/vty-server@30000004
+
+Each vty-server sysfs dir is provided with two read-only attributes that
+provide lists of easily parsed partner vty data: "partner_vtys" and
+"partner_clcs"::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat partner_vtys
+ 30000000
+ 30000001
+ 30000002
+ 30000000
+ 30000000
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat partner_clcs
+ U5112.428.103048A-V3-C0
+ U5112.428.103048A-V3-C2
+ U5112.428.103048A-V3-C3
+ U5112.428.103048A-V4-C0
+ U5112.428.103048A-V5-C0
+
+Reading partner_vtys returns a list of partner vtys. Vty unit address
+numbering is only per-partition-unique so entries will frequently repeat.
+
+Reading partner_clcs returns a list of "converged location codes" which are
+composed of a system serial number followed by "-V*", where the '*' is the
+target partition number, and "-C*", where the '*' is the slot of the
+adapter. The first vty partner corresponds to the first clc item, the
+second vty partner to the second clc item, etc.
+
+A vty-server can only be connected to a single vty at a time. The entry,
+"current_vty" prints the clc of the currently selected partner vty when
+read.
+
+The current_vty can be changed by writing a valid partner clc to the entry
+as in the following example::
+
+ Pow5:/sys/bus/vio/drivers/hvcs/30000004 # echo U5112.428.10304
+ 8A-V4-C0 > current_vty
+
+Changing the current_vty when a vty-server is already connected to a vty
+does not affect the current connection. The change takes effect when the
+currently open connection is freed.
+
+Information on the "vterm_state" attribute was covered earlier on the
+chapter entitled "disconnection".
+
+8. Questions & Answers:
+=======================
+
+Q: What are the security concerns involving hvcs?
+
+A: There are three main security concerns:
+
+ 1. The creator of the /dev/hvcs* nodes has the ability to restrict
+ the access of the device entries to certain users or groups. It
+ may be best to create a special hvcs group privilege for providing
+ access to system consoles.
+
+ 2. To provide network security when grabbing the console it is
+ suggested that the user connect to the console hosting partition
+ using a secure method, such as SSH or sit at a hardware console.
+
+ 3. Make sure to exit the user session when done with a console or
+ the next vty-server connection (which may be from another
+ partition) will experience the previously logged in session.
+
+---------------------------------------------------------------------------
+
+Q: How do I multiplex a console that I grab through hvcs so that other
+people can see it:
+
+A: You can use "screen" to directly connect to the /dev/hvcs* device and
+setup a session on your machine with the console group privileges. As
+pointed out earlier by default screen doesn't provide the termcap settings
+for most terminal emulators to provide adequate character conversion from
+term type "screen" to others. This means that curses based programs may
+not display properly in screen sessions.
+
+---------------------------------------------------------------------------
+
+Q: Why are the colors all messed up?
+Q: Why are the control characters acting strange or not working?
+Q: Why is the console output all strange and unintelligible?
+
+A: Please see the preceding section on "Connection" for a discussion of how
+applications can affect the display of character control sequences.
+Additionally, just because you logged into the console using and xterm
+doesn't mean someone else didn't log into the console with the HMC console
+(vt320) before you and leave the session logged in. The best thing to do
+is to export TERM to the terminal type of your terminal emulator when you
+get the console. Additionally make sure to "exit" the console before you
+disconnect from the console. This will ensure that the next user gets
+their own TERM type set when they login.
+
+---------------------------------------------------------------------------
+
+Q: When I try to CONNECT kermit to an hvcs device I get:
+"Sorry, can't open connection: /dev/hvcs*"What is happening?
+
+A: Some other Power5 console mechanism has a connection to the vty and
+isn't giving it up. You can try to force disconnect the consoles from the
+HMC by right clicking on the partition and then selecting "close terminal".
+Otherwise you have to hunt down the people who have console authority. It
+is possible that you already have the console open using another kermit
+session and just forgot about it. Please review the console options for
+Power5 systems to determine the many ways a system console can be held.
+
+OR
+
+A: Another user may not have a connectivity method currently attached to a
+/dev/hvcs device but the vterm_state may reveal that they still have the
+vty-server connection established. They need to free this using the method
+outlined in the section on "Disconnection" in order for others to connect
+to the target vty.
+
+OR
+
+A: The user profile you are using to execute kermit probably doesn't have
+permissions to use the /dev/hvcs* device.
+
+OR
+
+A: You probably haven't inserted the hvcs.ko module yet but the /dev/hvcs*
+entry still exists (on systems without udev).
+
+OR
+
+A: There is not a corresponding vty-server device that maps to an existing
+/dev/hvcs* entry.
+
+---------------------------------------------------------------------------
+
+Q: When I try to CONNECT kermit to an hvcs device I get:
+"Sorry, write access to UUCP lockfile directory denied."
+
+A: The /dev/hvcs* entry you have specified doesn't exist where you said it
+does? Maybe you haven't inserted the module (on systems with udev).
+
+---------------------------------------------------------------------------
+
+Q: If I already have one Linux partition installed can I use hvcs on said
+partition to provide the console for the install of a second Linux
+partition?
+
+A: Yes granted that your are connected to the /dev/hvcs* device using
+kermit or cu or some other program that doesn't provide terminal emulation.
+
+---------------------------------------------------------------------------
+
+Q: Can I connect to more than one partition's console at a time using this
+driver?
+
+A: Yes. Of course this means that there must be more than one vty-server
+configured for this partition and each must point to a disconnected vty.
+
+---------------------------------------------------------------------------
+
+Q: Does the hvcs driver support dynamic (hotplug) addition of devices?
+
+A: Yes, if you have dlpar and hotplug enabled for your system and it has
+been built into the kernel the hvcs drivers is configured to dynamically
+handle additions of new devices and removals of unused devices.
+
+---------------------------------------------------------------------------
+
+Q: For some reason /dev/hvcs* doesn't map to the same vty-server adapter
+after a reboot. What happened?
+
+A: Assignment of vty-server adapters to /dev/hvcs* entries is always done
+in the order that the adapters are exposed. Due to hotplug capabilities of
+this driver assignment of hotplug added vty-servers may be in a different
+order than how they would be exposed on module load. Rebooting or
+reloading the module after dynamic addition may result in the /dev/hvcs*
+and vty-server coupling changing if a vty-server adapter was added in a
+slot between two other vty-server adapters. Refer to the section above
+on how to determine which vty-server goes with which /dev/hvcs* node.
+Hint; look at the sysfs "index" attribute for the vty-server.
+
+---------------------------------------------------------------------------
+
+Q: Can I use /dev/hvcs* as a conduit to another partition and use a tty
+device on that partition as the other end of the pipe?
+
+A: Yes, on Power5 platforms the hvc_console driver provides a tty interface
+for extra /dev/hvc* devices (where /dev/hvc0 is most likely the console).
+In order to get a tty conduit working between the two partitions the HMC
+Super Admin must create an additional "serial server" for the target
+partition with the HMC gui which will show up as /dev/hvc* when the target
+partition is rebooted.
+
+The HMC Super Admin then creates an additional "serial client" for the
+current partition and points this at the target partition's newly created
+"serial server" adapter (remember the slot). This shows up as an
+additional /dev/hvcs* device.
+
+Now a program on the target system can be configured to read or write to
+/dev/hvc* and another program on the current partition can be configured to
+read or write to /dev/hvcs*. Now you have a tty conduit between two
+partitions.
+
+---------------------------------------------------------------------------
+
+9. Reporting Bugs:
+==================
+
+The proper channel for reporting bugs is either through the Linux OS
+distribution company that provided your OS or by posting issues to the
+PowerPC development mailing list at:
+
+linuxppc-dev@lists.ozlabs.org
+
+This request is to provide a documented and searchable public exchange
+of the problems and solutions surrounding this driver for the benefit of
+all users.
+++ /dev/null
-===========================================================================
- HVCS
- IBM "Hypervisor Virtual Console Server" Installation Guide
- for Linux Kernel 2.6.4+
- Copyright (C) 2004 IBM Corporation
-
-===========================================================================
-NOTE:Eight space tabs are the optimum editor setting for reading this file.
-===========================================================================
-
- Author(s) : Ryan S. Arnold <rsa@us.ibm.com>
- Date Created: March, 02, 2004
- Last Changed: August, 24, 2004
-
----------------------------------------------------------------------------
-Table of contents:
-
- 1. Driver Introduction:
- 2. System Requirements
- 3. Build Options:
- 3.1 Built-in:
- 3.2 Module:
- 4. Installation:
- 5. Connection:
- 6. Disconnection:
- 7. Configuration:
- 8. Questions & Answers:
- 9. Reporting Bugs:
-
----------------------------------------------------------------------------
-1. Driver Introduction:
-
-This is the device driver for the IBM Hypervisor Virtual Console Server,
-"hvcs". The IBM hvcs provides a tty driver interface to allow Linux user
-space applications access to the system consoles of logically partitioned
-operating systems (Linux and AIX) running on the same partitioned Power5
-ppc64 system. Physical hardware consoles per partition are not practical
-on this hardware so system consoles are accessed by this driver using
-firmware interfaces to virtual terminal devices.
-
----------------------------------------------------------------------------
-2. System Requirements:
-
-This device driver was written using 2.6.4 Linux kernel APIs and will only
-build and run on kernels of this version or later.
-
-This driver was written to operate solely on IBM Power5 ppc64 hardware
-though some care was taken to abstract the architecture dependent firmware
-calls from the driver code.
-
-Sysfs must be mounted on the system so that the user can determine which
-major and minor numbers are associated with each vty-server. Directions
-for sysfs mounting are outside the scope of this document.
-
----------------------------------------------------------------------------
-3. Build Options:
-
-The hvcs driver registers itself as a tty driver. The tty layer
-dynamically allocates a block of major and minor numbers in a quantity
-requested by the registering driver. The hvcs driver asks the tty layer
-for 64 of these major/minor numbers by default to use for hvcs device node
-entries.
-
-If the default number of device entries is adequate then this driver can be
-built into the kernel. If not, the default can be over-ridden by inserting
-the driver as a module with insmod parameters.
-
----------------------------------------------------------------------------
-3.1 Built-in:
-
-The following menuconfig example demonstrates selecting to build this
-driver into the kernel.
-
- Device Drivers --->
- Character devices --->
- <*> IBM Hypervisor Virtual Console Server Support
-
-Begin the kernel make process.
-
----------------------------------------------------------------------------
-3.2 Module:
-
-The following menuconfig example demonstrates selecting to build this
-driver as a kernel module.
-
- Device Drivers --->
- Character devices --->
- <M> IBM Hypervisor Virtual Console Server Support
-
-The make process will build the following kernel modules:
-
- hvcs.ko
- hvcserver.ko
-
-To insert the module with the default allocation execute the following
-commands in the order they appear:
-
- insmod hvcserver.ko
- insmod hvcs.ko
-
-The hvcserver module contains architecture specific firmware calls and must
-be inserted first, otherwise the hvcs module will not find some of the
-symbols it expects.
-
-To override the default use an insmod parameter as follows (requesting 4
-tty devices as an example):
-
- insmod hvcs.ko hvcs_parm_num_devs=4
-
-There is a maximum number of dev entries that can be specified on insmod.
-We think that 1024 is currently a decent maximum number of server adapters
-to allow. This can always be changed by modifying the constant in the
-source file before building.
-
-NOTE: The length of time it takes to insmod the driver seems to be related
-to the number of tty interfaces the registering driver requests.
-
-In order to remove the driver module execute the following command:
-
- rmmod hvcs.ko
-
-The recommended method for installing hvcs as a module is to use depmod to
-build a current modules.dep file in /lib/modules/`uname -r` and then
-execute:
-
-modprobe hvcs hvcs_parm_num_devs=4
-
-The modules.dep file indicates that hvcserver.ko needs to be inserted
-before hvcs.ko and modprobe uses this file to smartly insert the modules in
-the proper order.
-
-The following modprobe command is used to remove hvcs and hvcserver in the
-proper order:
-
-modprobe -r hvcs
-
----------------------------------------------------------------------------
-4. Installation:
-
-The tty layer creates sysfs entries which contain the major and minor
-numbers allocated for the hvcs driver. The following snippet of "tree"
-output of the sysfs directory shows where these numbers are presented:
-
- sys/
- |-- *other sysfs base dirs*
- |
- |-- class
- | |-- *other classes of devices*
- | |
- | `-- tty
- | |-- *other tty devices*
- | |
- | |-- hvcs0
- | | `-- dev
- | |-- hvcs1
- | | `-- dev
- | |-- hvcs2
- | | `-- dev
- | |-- hvcs3
- | | `-- dev
- | |
- | |-- *other tty devices*
- |
- |-- *other sysfs base dirs*
-
-For the above examples the following output is a result of cat'ing the
-"dev" entry in the hvcs directory:
-
- Pow5:/sys/class/tty/hvcs0/ # cat dev
- 254:0
-
- Pow5:/sys/class/tty/hvcs1/ # cat dev
- 254:1
-
- Pow5:/sys/class/tty/hvcs2/ # cat dev
- 254:2
-
- Pow5:/sys/class/tty/hvcs3/ # cat dev
- 254:3
-
-The output from reading the "dev" attribute is the char device major and
-minor numbers that the tty layer has allocated for this driver's use. Most
-systems running hvcs will already have the device entries created or udev
-will do it automatically.
-
-Given the example output above, to manually create a /dev/hvcs* node entry
-mknod can be used as follows:
-
- mknod /dev/hvcs0 c 254 0
- mknod /dev/hvcs1 c 254 1
- mknod /dev/hvcs2 c 254 2
- mknod /dev/hvcs3 c 254 3
-
-Using mknod to manually create the device entries makes these device nodes
-persistent. Once created they will exist prior to the driver insmod.
-
-Attempting to connect an application to /dev/hvcs* prior to insertion of
-the hvcs module will result in an error message similar to the following:
-
- "/dev/hvcs*: No such device".
-
-NOTE: Just because there is a device node present doesn't mean that there
-is a vty-server device configured for that node.
-
----------------------------------------------------------------------------
-5. Connection
-
-Since this driver controls devices that provide a tty interface a user can
-interact with the device node entries using any standard tty-interactive
-method (e.g. "cat", "dd", "echo"). The intent of this driver however, is
-to provide real time console interaction with a Linux partition's console,
-which requires the use of applications that provide bi-directional,
-interactive I/O with a tty device.
-
-Applications (e.g. "minicom" and "screen") that act as terminal emulators
-or perform terminal type control sequence conversion on the data being
-passed through them are NOT acceptable for providing interactive console
-I/O. These programs often emulate antiquated terminal types (vt100 and
-ANSI) and expect inbound data to take the form of one of these supported
-terminal types but they either do not convert, or do not _adequately_
-convert, outbound data into the terminal type of the terminal which invoked
-them (though screen makes an attempt and can apparently be configured with
-much termcap wrestling.)
-
-For this reason kermit and cu are two of the recommended applications for
-interacting with a Linux console via an hvcs device. These programs simply
-act as a conduit for data transfer to and from the tty device. They do not
-require inbound data to take the form of a particular terminal type, nor do
-they cook outbound data to a particular terminal type.
-
-In order to ensure proper functioning of console applications one must make
-sure that once connected to a /dev/hvcs console that the console's $TERM
-env variable is set to the exact terminal type of the terminal emulator
-used to launch the interactive I/O application. If one is using xterm and
-kermit to connect to /dev/hvcs0 when the console prompt becomes available
-one should "export TERM=xterm" on the console. This tells ncurses
-applications that are invoked from the console that they should output
-control sequences that xterm can understand.
-
-As a precautionary measure an hvcs user should always "exit" from their
-session before disconnecting an application such as kermit from the device
-node. If this is not done, the next user to connect to the console will
-continue using the previous user's logged in session which includes
-using the $TERM variable that the previous user supplied.
-
-Hotplug add and remove of vty-server adapters affects which /dev/hvcs* node
-is used to connect to each vty-server adapter. In order to determine which
-vty-server adapter is associated with which /dev/hvcs* node a special sysfs
-attribute has been added to each vty-server sysfs entry. This entry is
-called "index" and showing it reveals an integer that refers to the
-/dev/hvcs* entry to use to connect to that device. For instance cating the
-index attribute of vty-server adapter 30000004 shows the following.
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat index
- 2
-
-This index of '2' means that in order to connect to vty-server adapter
-30000004 the user should interact with /dev/hvcs2.
-
-It should be noted that due to the system hotplug I/O capabilities of a
-system the /dev/hvcs* entry that interacts with a particular vty-server
-adapter is not guaranteed to remain the same across system reboots. Look
-in the Q & A section for more on this issue.
-
----------------------------------------------------------------------------
-6. Disconnection
-
-As a security feature to prevent the delivery of stale data to an
-unintended target the Power5 system firmware disables the fetching of data
-and discards that data when a connection between a vty-server and a vty has
-been severed. As an example, when a vty-server is immediately disconnected
-from a vty following output of data to the vty the vty adapter may not have
-enough time between when it received the data interrupt and when the
-connection was severed to fetch the data from firmware before the fetch is
-disabled by firmware.
-
-When hvcs is being used to serve consoles this behavior is not a huge issue
-because the adapter stays connected for large amounts of time following
-almost all data writes. When hvcs is being used as a tty conduit to tunnel
-data between two partitions [see Q & A below] this is a huge problem
-because the standard Linux behavior when cat'ing or dd'ing data to a device
-is to open the tty, send the data, and then close the tty. If this driver
-manually terminated vty-server connections on tty close this would close
-the vty-server and vty connection before the target vty has had a chance to
-fetch the data.
-
-Additionally, disconnecting a vty-server and vty only on module removal or
-adapter removal is impractical because other vty-servers in other
-partitions may require the usage of the target vty at any time.
-
-Due to this behavioral restriction disconnection of vty-servers from the
-connected vty is a manual procedure using a write to a sysfs attribute
-outlined below, on the other hand the initial vty-server connection to a
-vty is established automatically by this driver. Manual vty-server
-connection is never required.
-
-In order to terminate the connection between a vty-server and vty the
-"vterm_state" sysfs attribute within each vty-server's sysfs entry is used.
-Reading this attribute reveals the current connection state of the
-vty-server adapter. A zero means that the vty-server is not connected to a
-vty. A one indicates that a connection is active.
-
-Writing a '0' (zero) to the vterm_state attribute will disconnect the VTERM
-connection between the vty-server and target vty ONLY if the vterm_state
-previously read '1'. The write directive is ignored if the vterm_state
-read '0' or if any value other than '0' was written to the vterm_state
-attribute. The following example will show the method used for verifying
-the vty-server connection status and disconnecting a vty-server connection.
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat vterm_state
- 1
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # echo 0 > vterm_state
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat vterm_state
- 0
-
-All vty-server connections are automatically terminated when the device is
-hotplug removed and when the module is removed.
-
----------------------------------------------------------------------------
-7. Configuration
-
-Each vty-server has a sysfs entry in the /sys/devices/vio directory, which
-is symlinked in several other sysfs tree directories, notably under the
-hvcs driver entry, which looks like the following example:
-
- Pow5:/sys/bus/vio/drivers/hvcs # ls
- . .. 30000003 30000004 rescan
-
-By design, firmware notifies the hvcs driver of vty-server lifetimes and
-partner vty removals but not the addition of partner vtys. Since an HMC
-Super Admin can add partner info dynamically we have provided the hvcs
-driver sysfs directory with the "rescan" update attribute which will query
-firmware and update the partner info for all the vty-servers that this
-driver manages. Writing a '1' to the attribute triggers the update. An
-explicit example follows:
-
- Pow5:/sys/bus/vio/drivers/hvcs # echo 1 > rescan
-
-Reading the attribute will indicate a state of '1' or '0'. A one indicates
-that an update is in process. A zero indicates that an update has
-completed or was never executed.
-
-Vty-server entries in this directory are a 32 bit partition unique unit
-address that is created by firmware. An example vty-server sysfs entry
-looks like the following:
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # ls
- . current_vty devspec name partner_vtys
- .. index partner_clcs vterm_state
-
-Each entry is provided, by default with a "name" attribute. Reading the
-"name" attribute will reveal the device type as shown in the following
-example:
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000003 # cat name
- vty-server
-
-Each entry is also provided, by default, with a "devspec" attribute which
-reveals the full device specification when read, as shown in the following
-example:
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat devspec
- /vdevice/vty-server@30000004
-
-Each vty-server sysfs dir is provided with two read-only attributes that
-provide lists of easily parsed partner vty data: "partner_vtys" and
-"partner_clcs".
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat partner_vtys
- 30000000
- 30000001
- 30000002
- 30000000
- 30000000
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # cat partner_clcs
- U5112.428.103048A-V3-C0
- U5112.428.103048A-V3-C2
- U5112.428.103048A-V3-C3
- U5112.428.103048A-V4-C0
- U5112.428.103048A-V5-C0
-
-Reading partner_vtys returns a list of partner vtys. Vty unit address
-numbering is only per-partition-unique so entries will frequently repeat.
-
-Reading partner_clcs returns a list of "converged location codes" which are
-composed of a system serial number followed by "-V*", where the '*' is the
-target partition number, and "-C*", where the '*' is the slot of the
-adapter. The first vty partner corresponds to the first clc item, the
-second vty partner to the second clc item, etc.
-
-A vty-server can only be connected to a single vty at a time. The entry,
-"current_vty" prints the clc of the currently selected partner vty when
-read.
-
-The current_vty can be changed by writing a valid partner clc to the entry
-as in the following example:
-
- Pow5:/sys/bus/vio/drivers/hvcs/30000004 # echo U5112.428.10304
- 8A-V4-C0 > current_vty
-
-Changing the current_vty when a vty-server is already connected to a vty
-does not affect the current connection. The change takes effect when the
-currently open connection is freed.
-
-Information on the "vterm_state" attribute was covered earlier on the
-chapter entitled "disconnection".
-
----------------------------------------------------------------------------
-8. Questions & Answers:
-===========================================================================
-Q: What are the security concerns involving hvcs?
-
-A: There are three main security concerns:
-
- 1. The creator of the /dev/hvcs* nodes has the ability to restrict
- the access of the device entries to certain users or groups. It
- may be best to create a special hvcs group privilege for providing
- access to system consoles.
-
- 2. To provide network security when grabbing the console it is
- suggested that the user connect to the console hosting partition
- using a secure method, such as SSH or sit at a hardware console.
-
- 3. Make sure to exit the user session when done with a console or
- the next vty-server connection (which may be from another
- partition) will experience the previously logged in session.
-
----------------------------------------------------------------------------
-Q: How do I multiplex a console that I grab through hvcs so that other
-people can see it:
-
-A: You can use "screen" to directly connect to the /dev/hvcs* device and
-setup a session on your machine with the console group privileges. As
-pointed out earlier by default screen doesn't provide the termcap settings
-for most terminal emulators to provide adequate character conversion from
-term type "screen" to others. This means that curses based programs may
-not display properly in screen sessions.
-
----------------------------------------------------------------------------
-Q: Why are the colors all messed up?
-Q: Why are the control characters acting strange or not working?
-Q: Why is the console output all strange and unintelligible?
-
-A: Please see the preceding section on "Connection" for a discussion of how
-applications can affect the display of character control sequences.
-Additionally, just because you logged into the console using and xterm
-doesn't mean someone else didn't log into the console with the HMC console
-(vt320) before you and leave the session logged in. The best thing to do
-is to export TERM to the terminal type of your terminal emulator when you
-get the console. Additionally make sure to "exit" the console before you
-disconnect from the console. This will ensure that the next user gets
-their own TERM type set when they login.
-
----------------------------------------------------------------------------
-Q: When I try to CONNECT kermit to an hvcs device I get:
-"Sorry, can't open connection: /dev/hvcs*"What is happening?
-
-A: Some other Power5 console mechanism has a connection to the vty and
-isn't giving it up. You can try to force disconnect the consoles from the
-HMC by right clicking on the partition and then selecting "close terminal".
-Otherwise you have to hunt down the people who have console authority. It
-is possible that you already have the console open using another kermit
-session and just forgot about it. Please review the console options for
-Power5 systems to determine the many ways a system console can be held.
-
-OR
-
-A: Another user may not have a connectivity method currently attached to a
-/dev/hvcs device but the vterm_state may reveal that they still have the
-vty-server connection established. They need to free this using the method
-outlined in the section on "Disconnection" in order for others to connect
-to the target vty.
-
-OR
-
-A: The user profile you are using to execute kermit probably doesn't have
-permissions to use the /dev/hvcs* device.
-
-OR
-
-A: You probably haven't inserted the hvcs.ko module yet but the /dev/hvcs*
-entry still exists (on systems without udev).
-
-OR
-
-A: There is not a corresponding vty-server device that maps to an existing
-/dev/hvcs* entry.
-
----------------------------------------------------------------------------
-Q: When I try to CONNECT kermit to an hvcs device I get:
-"Sorry, write access to UUCP lockfile directory denied."
-
-A: The /dev/hvcs* entry you have specified doesn't exist where you said it
-does? Maybe you haven't inserted the module (on systems with udev).
-
----------------------------------------------------------------------------
-Q: If I already have one Linux partition installed can I use hvcs on said
-partition to provide the console for the install of a second Linux
-partition?
-
-A: Yes granted that your are connected to the /dev/hvcs* device using
-kermit or cu or some other program that doesn't provide terminal emulation.
-
----------------------------------------------------------------------------
-Q: Can I connect to more than one partition's console at a time using this
-driver?
-
-A: Yes. Of course this means that there must be more than one vty-server
-configured for this partition and each must point to a disconnected vty.
-
----------------------------------------------------------------------------
-Q: Does the hvcs driver support dynamic (hotplug) addition of devices?
-
-A: Yes, if you have dlpar and hotplug enabled for your system and it has
-been built into the kernel the hvcs drivers is configured to dynamically
-handle additions of new devices and removals of unused devices.
-
----------------------------------------------------------------------------
-Q: For some reason /dev/hvcs* doesn't map to the same vty-server adapter
-after a reboot. What happened?
-
-A: Assignment of vty-server adapters to /dev/hvcs* entries is always done
-in the order that the adapters are exposed. Due to hotplug capabilities of
-this driver assignment of hotplug added vty-servers may be in a different
-order than how they would be exposed on module load. Rebooting or
-reloading the module after dynamic addition may result in the /dev/hvcs*
-and vty-server coupling changing if a vty-server adapter was added in a
-slot between two other vty-server adapters. Refer to the section above
-on how to determine which vty-server goes with which /dev/hvcs* node.
-Hint; look at the sysfs "index" attribute for the vty-server.
-
----------------------------------------------------------------------------
-Q: Can I use /dev/hvcs* as a conduit to another partition and use a tty
-device on that partition as the other end of the pipe?
-
-A: Yes, on Power5 platforms the hvc_console driver provides a tty interface
-for extra /dev/hvc* devices (where /dev/hvc0 is most likely the console).
-In order to get a tty conduit working between the two partitions the HMC
-Super Admin must create an additional "serial server" for the target
-partition with the HMC gui which will show up as /dev/hvc* when the target
-partition is rebooted.
-
-The HMC Super Admin then creates an additional "serial client" for the
-current partition and points this at the target partition's newly created
-"serial server" adapter (remember the slot). This shows up as an
-additional /dev/hvcs* device.
-
-Now a program on the target system can be configured to read or write to
-/dev/hvc* and another program on the current partition can be configured to
-read or write to /dev/hvcs*. Now you have a tty conduit between two
-partitions.
-
----------------------------------------------------------------------------
-9. Reporting Bugs:
-
-The proper channel for reporting bugs is either through the Linux OS
-distribution company that provided your OS or by posting issues to the
-PowerPC development mailing list at:
-
-linuxppc-dev@lists.ozlabs.org
-
-This request is to provide a documented and searchable public exchange
-of the problems and solutions surrounding this driver for the benefit of
-all users.
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+=======
+powerpc
+=======
+
+.. toctree::
+ :maxdepth: 1
+
+ bootwrapper
+ cpu_families
+ cpu_features
+ cxl
+ cxlflash
+ dawr-power9
+ dscr
+ eeh-pci-error-recovery
+ firmware-assisted-dump
+ hvcs
+ isa-versions
+ mpc52xx
+ pci_iov_resource_on_powernv
+ pmu-ebb
+ ptrace
+ qe_firmware
+ syscall64-abi
+ transactional_memory
+
+.. only:: subproject and html
+
+ Indices
+ =======
+
+ * :ref:`genindex`
-:orphan:
-
+==========================
CPU to ISA Version Mapping
==========================
Mapping of some CPU versions to relevant ISA versions.
-========= ====================
+========= ====================================================================
CPU Architecture version
-========= ====================
+========= ====================================================================
Power9 Power ISA v3.0B
Power8 Power ISA v2.07
Power7 Power ISA v2.06
- PowerPC Virtual Environment Architecture Book II v2.01
- PowerPC Operating Environment Architecture Book III v2.01
- Plus Altivec/VMX ~= 2.03
-========= ====================
+========= ====================================================================
Key Features
PPC970 No
========== ====
-========== ====================
+========== ====================================
CPU Transactional Memory
-========== ====================
+========== ====================================
Power9 Yes (* see transactional_memory.txt)
Power8 Yes
Power7 No
Power5+ No
Power5 No
PPC970 No
-========== ====================
+========== ====================================
--- /dev/null
+=============================
+Linux 2.6.x on MPC52xx family
+=============================
+
+For the latest info, go to http://www.246tNt.com/mpc52xx/
+
+To compile/use :
+
+ - U-Boot::
+
+ # <edit Makefile to set ARCH=ppc & CROSS_COMPILE=... ( also EXTRAVERSION
+ if you wish to ).
+ # make lite5200_defconfig
+ # make uImage
+
+ then, on U-boot:
+ => tftpboot 200000 uImage
+ => tftpboot 400000 pRamdisk
+ => bootm 200000 400000
+
+ - DBug::
+
+ # <edit Makefile to set ARCH=ppc & CROSS_COMPILE=... ( also EXTRAVERSION
+ if you wish to ).
+ # make lite5200_defconfig
+ # cp your_initrd.gz arch/ppc/boot/images/ramdisk.image.gz
+ # make zImage.initrd
+ # make
+
+ then in DBug:
+ DBug> dn -i zImage.initrd.lite5200
+
+
+Some remarks:
+
+ - The port is named mpc52xxx, and config options are PPC_MPC52xx. The MGT5100
+ is not supported, and I'm not sure anyone is interesting in working on it
+ so. I didn't took 5xxx because there's apparently a lot of 5xxx that have
+ nothing to do with the MPC5200. I also included the 'MPC' for the same
+ reason.
+ - Of course, I inspired myself from the 2.4 port. If you think I forgot to
+ mention you/your company in the copyright of some code, I'll correct it
+ ASAP.
+++ /dev/null
-Linux 2.6.x on MPC52xx family
------------------------------
-
-For the latest info, go to http://www.246tNt.com/mpc52xx/
-
-To compile/use :
-
- - U-Boot:
- # <edit Makefile to set ARCH=ppc & CROSS_COMPILE=... ( also EXTRAVERSION
- if you wish to ).
- # make lite5200_defconfig
- # make uImage
-
- then, on U-boot:
- => tftpboot 200000 uImage
- => tftpboot 400000 pRamdisk
- => bootm 200000 400000
-
- - DBug:
- # <edit Makefile to set ARCH=ppc & CROSS_COMPILE=... ( also EXTRAVERSION
- if you wish to ).
- # make lite5200_defconfig
- # cp your_initrd.gz arch/ppc/boot/images/ramdisk.image.gz
- # make zImage.initrd
- # make
-
- then in DBug:
- DBug> dn -i zImage.initrd.lite5200
-
-
-Some remarks :
- - The port is named mpc52xxx, and config options are PPC_MPC52xx. The MGT5100
- is not supported, and I'm not sure anyone is interesting in working on it
- so. I didn't took 5xxx because there's apparently a lot of 5xxx that have
- nothing to do with the MPC5200. I also included the 'MPC' for the same
- reason.
- - Of course, I inspired myself from the 2.4 port. If you think I forgot to
- mention you/your company in the copyright of some code, I'll correct it
- ASAP.
--- /dev/null
+===================================================
+PCI Express I/O Virtualization Resource on Powerenv
+===================================================
+
+Wei Yang <weiyang@linux.vnet.ibm.com>
+
+Benjamin Herrenschmidt <benh@au1.ibm.com>
+
+Bjorn Helgaas <bhelgaas@google.com>
+
+26 Aug 2014
+
+This document describes the requirement from hardware for PCI MMIO resource
+sizing and assignment on PowerKVM and how generic PCI code handles this
+requirement. The first two sections describe the concepts of Partitionable
+Endpoints and the implementation on P8 (IODA2). The next two sections talks
+about considerations on enabling SRIOV on IODA2.
+
+1. Introduction to Partitionable Endpoints
+==========================================
+
+A Partitionable Endpoint (PE) is a way to group the various resources
+associated with a device or a set of devices to provide isolation between
+partitions (i.e., filtering of DMA, MSIs etc.) and to provide a mechanism
+to freeze a device that is causing errors in order to limit the possibility
+of propagation of bad data.
+
+There is thus, in HW, a table of PE states that contains a pair of "frozen"
+state bits (one for MMIO and one for DMA, they get set together but can be
+cleared independently) for each PE.
+
+When a PE is frozen, all stores in any direction are dropped and all loads
+return all 1's value. MSIs are also blocked. There's a bit more state that
+captures things like the details of the error that caused the freeze etc., but
+that's not critical.
+
+The interesting part is how the various PCIe transactions (MMIO, DMA, ...)
+are matched to their corresponding PEs.
+
+The following section provides a rough description of what we have on P8
+(IODA2). Keep in mind that this is all per PHB (PCI host bridge). Each PHB
+is a completely separate HW entity that replicates the entire logic, so has
+its own set of PEs, etc.
+
+2. Implementation of Partitionable Endpoints on P8 (IODA2)
+==========================================================
+
+P8 supports up to 256 Partitionable Endpoints per PHB.
+
+ * Inbound
+
+ For DMA, MSIs and inbound PCIe error messages, we have a table (in
+ memory but accessed in HW by the chip) that provides a direct
+ correspondence between a PCIe RID (bus/dev/fn) with a PE number.
+ We call this the RTT.
+
+ - For DMA we then provide an entire address space for each PE that can
+ contain two "windows", depending on the value of PCI address bit 59.
+ Each window can be configured to be remapped via a "TCE table" (IOMMU
+ translation table), which has various configurable characteristics
+ not described here.
+
+ - For MSIs, we have two windows in the address space (one at the top of
+ the 32-bit space and one much higher) which, via a combination of the
+ address and MSI value, will result in one of the 2048 interrupts per
+ bridge being triggered. There's a PE# in the interrupt controller
+ descriptor table as well which is compared with the PE# obtained from
+ the RTT to "authorize" the device to emit that specific interrupt.
+
+ - Error messages just use the RTT.
+
+ * Outbound. That's where the tricky part is.
+
+ Like other PCI host bridges, the Power8 IODA2 PHB supports "windows"
+ from the CPU address space to the PCI address space. There is one M32
+ window and sixteen M64 windows. They have different characteristics.
+ First what they have in common: they forward a configurable portion of
+ the CPU address space to the PCIe bus and must be naturally aligned
+ power of two in size. The rest is different:
+
+ - The M32 window:
+
+ * Is limited to 4GB in size.
+
+ * Drops the top bits of the address (above the size) and replaces
+ them with a configurable value. This is typically used to generate
+ 32-bit PCIe accesses. We configure that window at boot from FW and
+ don't touch it from Linux; it's usually set to forward a 2GB
+ portion of address space from the CPU to PCIe
+ 0x8000_0000..0xffff_ffff. (Note: The top 64KB are actually
+ reserved for MSIs but this is not a problem at this point; we just
+ need to ensure Linux doesn't assign anything there, the M32 logic
+ ignores that however and will forward in that space if we try).
+
+ * It is divided into 256 segments of equal size. A table in the chip
+ maps each segment to a PE#. That allows portions of the MMIO space
+ to be assigned to PEs on a segment granularity. For a 2GB window,
+ the segment granularity is 2GB/256 = 8MB.
+
+ Now, this is the "main" window we use in Linux today (excluding
+ SR-IOV). We basically use the trick of forcing the bridge MMIO windows
+ onto a segment alignment/granularity so that the space behind a bridge
+ can be assigned to a PE.
+
+ Ideally we would like to be able to have individual functions in PEs
+ but that would mean using a completely different address allocation
+ scheme where individual function BARs can be "grouped" to fit in one or
+ more segments.
+
+ - The M64 windows:
+
+ * Must be at least 256MB in size.
+
+ * Do not translate addresses (the address on PCIe is the same as the
+ address on the PowerBus). There is a way to also set the top 14
+ bits which are not conveyed by PowerBus but we don't use this.
+
+ * Can be configured to be segmented. When not segmented, we can
+ specify the PE# for the entire window. When segmented, a window
+ has 256 segments; however, there is no table for mapping a segment
+ to a PE#. The segment number *is* the PE#.
+
+ * Support overlaps. If an address is covered by multiple windows,
+ there's a defined ordering for which window applies.
+
+ We have code (fairly new compared to the M32 stuff) that exploits that
+ for large BARs in 64-bit space:
+
+ We configure an M64 window to cover the entire region of address space
+ that has been assigned by FW for the PHB (about 64GB, ignore the space
+ for the M32, it comes out of a different "reserve"). We configure it
+ as segmented.
+
+ Then we do the same thing as with M32, using the bridge alignment
+ trick, to match to those giant segments.
+
+ Since we cannot remap, we have two additional constraints:
+
+ - We do the PE# allocation *after* the 64-bit space has been assigned
+ because the addresses we use directly determine the PE#. We then
+ update the M32 PE# for the devices that use both 32-bit and 64-bit
+ spaces or assign the remaining PE# to 32-bit only devices.
+
+ - We cannot "group" segments in HW, so if a device ends up using more
+ than one segment, we end up with more than one PE#. There is a HW
+ mechanism to make the freeze state cascade to "companion" PEs but
+ that only works for PCIe error messages (typically used so that if
+ you freeze a switch, it freezes all its children). So we do it in
+ SW. We lose a bit of effectiveness of EEH in that case, but that's
+ the best we found. So when any of the PEs freezes, we freeze the
+ other ones for that "domain". We thus introduce the concept of
+ "master PE" which is the one used for DMA, MSIs, etc., and "secondary
+ PEs" that are used for the remaining M64 segments.
+
+ We would like to investigate using additional M64 windows in "single
+ PE" mode to overlay over specific BARs to work around some of that, for
+ example for devices with very large BARs, e.g., GPUs. It would make
+ sense, but we haven't done it yet.
+
+3. Considerations for SR-IOV on PowerKVM
+========================================
+
+ * SR-IOV Background
+
+ The PCIe SR-IOV feature allows a single Physical Function (PF) to
+ support several Virtual Functions (VFs). Registers in the PF's SR-IOV
+ Capability control the number of VFs and whether they are enabled.
+
+ When VFs are enabled, they appear in Configuration Space like normal
+ PCI devices, but the BARs in VF config space headers are unusual. For
+ a non-VF device, software uses BARs in the config space header to
+ discover the BAR sizes and assign addresses for them. For VF devices,
+ software uses VF BAR registers in the *PF* SR-IOV Capability to
+ discover sizes and assign addresses. The BARs in the VF's config space
+ header are read-only zeros.
+
+ When a VF BAR in the PF SR-IOV Capability is programmed, it sets the
+ base address for all the corresponding VF(n) BARs. For example, if the
+ PF SR-IOV Capability is programmed to enable eight VFs, and it has a
+ 1MB VF BAR0, the address in that VF BAR sets the base of an 8MB region.
+ This region is divided into eight contiguous 1MB regions, each of which
+ is a BAR0 for one of the VFs. Note that even though the VF BAR
+ describes an 8MB region, the alignment requirement is for a single VF,
+ i.e., 1MB in this example.
+
+ There are several strategies for isolating VFs in PEs:
+
+ - M32 window: There's one M32 window, and it is split into 256
+ equally-sized segments. The finest granularity possible is a 256MB
+ window with 1MB segments. VF BARs that are 1MB or larger could be
+ mapped to separate PEs in this window. Each segment can be
+ individually mapped to a PE via the lookup table, so this is quite
+ flexible, but it works best when all the VF BARs are the same size. If
+ they are different sizes, the entire window has to be small enough that
+ the segment size matches the smallest VF BAR, which means larger VF
+ BARs span several segments.
+
+ - Non-segmented M64 window: A non-segmented M64 window is mapped entirely
+ to a single PE, so it could only isolate one VF.
+
+ - Single segmented M64 windows: A segmented M64 window could be used just
+ like the M32 window, but the segments can't be individually mapped to
+ PEs (the segment number is the PE#), so there isn't as much
+ flexibility. A VF with multiple BARs would have to be in a "domain" of
+ multiple PEs, which is not as well isolated as a single PE.
+
+ - Multiple segmented M64 windows: As usual, each window is split into 256
+ equally-sized segments, and the segment number is the PE#. But if we
+ use several M64 windows, they can be set to different base addresses
+ and different segment sizes. If we have VFs that each have a 1MB BAR
+ and a 32MB BAR, we could use one M64 window to assign 1MB segments and
+ another M64 window to assign 32MB segments.
+
+ Finally, the plan to use M64 windows for SR-IOV, which will be described
+ more in the next two sections. For a given VF BAR, we need to
+ effectively reserve the entire 256 segments (256 * VF BAR size) and
+ position the VF BAR to start at the beginning of a free range of
+ segments/PEs inside that M64 window.
+
+ The goal is of course to be able to give a separate PE for each VF.
+
+ The IODA2 platform has 16 M64 windows, which are used to map MMIO
+ range to PE#. Each M64 window defines one MMIO range and this range is
+ divided into 256 segments, with each segment corresponding to one PE.
+
+ We decide to leverage this M64 window to map VFs to individual PEs, since
+ SR-IOV VF BARs are all the same size.
+
+ But doing so introduces another problem: total_VFs is usually smaller
+ than the number of M64 window segments, so if we map one VF BAR directly
+ to one M64 window, some part of the M64 window will map to another
+ device's MMIO range.
+
+ IODA supports 256 PEs, so segmented windows contain 256 segments, so if
+ total_VFs is less than 256, we have the situation in Figure 1.0, where
+ segments [total_VFs, 255] of the M64 window may map to some MMIO range on
+ other devices::
+
+ 0 1 total_VFs - 1
+ +------+------+- -+------+------+
+ | | | ... | | |
+ +------+------+- -+------+------+
+
+ VF(n) BAR space
+
+ 0 1 total_VFs - 1 255
+ +------+------+- -+------+------+- -+------+------+
+ | | | ... | | | ... | | |
+ +------+------+- -+------+------+- -+------+------+
+
+ M64 window
+
+ Figure 1.0 Direct map VF(n) BAR space
+
+ Our current solution is to allocate 256 segments even if the VF(n) BAR
+ space doesn't need that much, as shown in Figure 1.1::
+
+ 0 1 total_VFs - 1 255
+ +------+------+- -+------+------+- -+------+------+
+ | | | ... | | | ... | | |
+ +------+------+- -+------+------+- -+------+------+
+
+ VF(n) BAR space + extra
+
+ 0 1 total_VFs - 1 255
+ +------+------+- -+------+------+- -+------+------+
+ | | | ... | | | ... | | |
+ +------+------+- -+------+------+- -+------+------+
+
+ M64 window
+
+ Figure 1.1 Map VF(n) BAR space + extra
+
+ Allocating the extra space ensures that the entire M64 window will be
+ assigned to this one SR-IOV device and none of the space will be
+ available for other devices. Note that this only expands the space
+ reserved in software; there are still only total_VFs VFs, and they only
+ respond to segments [0, total_VFs - 1]. There's nothing in hardware that
+ responds to segments [total_VFs, 255].
+
+4. Implications for the Generic PCI Code
+========================================
+
+The PCIe SR-IOV spec requires that the base of the VF(n) BAR space be
+aligned to the size of an individual VF BAR.
+
+In IODA2, the MMIO address determines the PE#. If the address is in an M32
+window, we can set the PE# by updating the table that translates segments
+to PE#s. Similarly, if the address is in an unsegmented M64 window, we can
+set the PE# for the window. But if it's in a segmented M64 window, the
+segment number is the PE#.
+
+Therefore, the only way to control the PE# for a VF is to change the base
+of the VF(n) BAR space in the VF BAR. If the PCI core allocates the exact
+amount of space required for the VF(n) BAR space, the VF BAR value is fixed
+and cannot be changed.
+
+On the other hand, if the PCI core allocates additional space, the VF BAR
+value can be changed as long as the entire VF(n) BAR space remains inside
+the space allocated by the core.
+
+Ideally the segment size will be the same as an individual VF BAR size.
+Then each VF will be in its own PE. The VF BARs (and therefore the PE#s)
+are contiguous. If VF0 is in PE(x), then VF(n) is in PE(x+n). If we
+allocate 256 segments, there are (256 - numVFs) choices for the PE# of VF0.
+
+If the segment size is smaller than the VF BAR size, it will take several
+segments to cover a VF BAR, and a VF will be in several PEs. This is
+possible, but the isolation isn't as good, and it reduces the number of PE#
+choices because instead of consuming only numVFs segments, the VF(n) BAR
+space will consume (numVFs * n) segments. That means there aren't as many
+available segments for adjusting base of the VF(n) BAR space.
+++ /dev/null
-Wei Yang <weiyang@linux.vnet.ibm.com>
-Benjamin Herrenschmidt <benh@au1.ibm.com>
-Bjorn Helgaas <bhelgaas@google.com>
-26 Aug 2014
-
-This document describes the requirement from hardware for PCI MMIO resource
-sizing and assignment on PowerKVM and how generic PCI code handles this
-requirement. The first two sections describe the concepts of Partitionable
-Endpoints and the implementation on P8 (IODA2). The next two sections talks
-about considerations on enabling SRIOV on IODA2.
-
-1. Introduction to Partitionable Endpoints
-
-A Partitionable Endpoint (PE) is a way to group the various resources
-associated with a device or a set of devices to provide isolation between
-partitions (i.e., filtering of DMA, MSIs etc.) and to provide a mechanism
-to freeze a device that is causing errors in order to limit the possibility
-of propagation of bad data.
-
-There is thus, in HW, a table of PE states that contains a pair of "frozen"
-state bits (one for MMIO and one for DMA, they get set together but can be
-cleared independently) for each PE.
-
-When a PE is frozen, all stores in any direction are dropped and all loads
-return all 1's value. MSIs are also blocked. There's a bit more state that
-captures things like the details of the error that caused the freeze etc., but
-that's not critical.
-
-The interesting part is how the various PCIe transactions (MMIO, DMA, ...)
-are matched to their corresponding PEs.
-
-The following section provides a rough description of what we have on P8
-(IODA2). Keep in mind that this is all per PHB (PCI host bridge). Each PHB
-is a completely separate HW entity that replicates the entire logic, so has
-its own set of PEs, etc.
-
-2. Implementation of Partitionable Endpoints on P8 (IODA2)
-
-P8 supports up to 256 Partitionable Endpoints per PHB.
-
- * Inbound
-
- For DMA, MSIs and inbound PCIe error messages, we have a table (in
- memory but accessed in HW by the chip) that provides a direct
- correspondence between a PCIe RID (bus/dev/fn) with a PE number.
- We call this the RTT.
-
- - For DMA we then provide an entire address space for each PE that can
- contain two "windows", depending on the value of PCI address bit 59.
- Each window can be configured to be remapped via a "TCE table" (IOMMU
- translation table), which has various configurable characteristics
- not described here.
-
- - For MSIs, we have two windows in the address space (one at the top of
- the 32-bit space and one much higher) which, via a combination of the
- address and MSI value, will result in one of the 2048 interrupts per
- bridge being triggered. There's a PE# in the interrupt controller
- descriptor table as well which is compared with the PE# obtained from
- the RTT to "authorize" the device to emit that specific interrupt.
-
- - Error messages just use the RTT.
-
- * Outbound. That's where the tricky part is.
-
- Like other PCI host bridges, the Power8 IODA2 PHB supports "windows"
- from the CPU address space to the PCI address space. There is one M32
- window and sixteen M64 windows. They have different characteristics.
- First what they have in common: they forward a configurable portion of
- the CPU address space to the PCIe bus and must be naturally aligned
- power of two in size. The rest is different:
-
- - The M32 window:
-
- * Is limited to 4GB in size.
-
- * Drops the top bits of the address (above the size) and replaces
- them with a configurable value. This is typically used to generate
- 32-bit PCIe accesses. We configure that window at boot from FW and
- don't touch it from Linux; it's usually set to forward a 2GB
- portion of address space from the CPU to PCIe
- 0x8000_0000..0xffff_ffff. (Note: The top 64KB are actually
- reserved for MSIs but this is not a problem at this point; we just
- need to ensure Linux doesn't assign anything there, the M32 logic
- ignores that however and will forward in that space if we try).
-
- * It is divided into 256 segments of equal size. A table in the chip
- maps each segment to a PE#. That allows portions of the MMIO space
- to be assigned to PEs on a segment granularity. For a 2GB window,
- the segment granularity is 2GB/256 = 8MB.
-
- Now, this is the "main" window we use in Linux today (excluding
- SR-IOV). We basically use the trick of forcing the bridge MMIO windows
- onto a segment alignment/granularity so that the space behind a bridge
- can be assigned to a PE.
-
- Ideally we would like to be able to have individual functions in PEs
- but that would mean using a completely different address allocation
- scheme where individual function BARs can be "grouped" to fit in one or
- more segments.
-
- - The M64 windows:
-
- * Must be at least 256MB in size.
-
- * Do not translate addresses (the address on PCIe is the same as the
- address on the PowerBus). There is a way to also set the top 14
- bits which are not conveyed by PowerBus but we don't use this.
-
- * Can be configured to be segmented. When not segmented, we can
- specify the PE# for the entire window. When segmented, a window
- has 256 segments; however, there is no table for mapping a segment
- to a PE#. The segment number *is* the PE#.
-
- * Support overlaps. If an address is covered by multiple windows,
- there's a defined ordering for which window applies.
-
- We have code (fairly new compared to the M32 stuff) that exploits that
- for large BARs in 64-bit space:
-
- We configure an M64 window to cover the entire region of address space
- that has been assigned by FW for the PHB (about 64GB, ignore the space
- for the M32, it comes out of a different "reserve"). We configure it
- as segmented.
-
- Then we do the same thing as with M32, using the bridge alignment
- trick, to match to those giant segments.
-
- Since we cannot remap, we have two additional constraints:
-
- - We do the PE# allocation *after* the 64-bit space has been assigned
- because the addresses we use directly determine the PE#. We then
- update the M32 PE# for the devices that use both 32-bit and 64-bit
- spaces or assign the remaining PE# to 32-bit only devices.
-
- - We cannot "group" segments in HW, so if a device ends up using more
- than one segment, we end up with more than one PE#. There is a HW
- mechanism to make the freeze state cascade to "companion" PEs but
- that only works for PCIe error messages (typically used so that if
- you freeze a switch, it freezes all its children). So we do it in
- SW. We lose a bit of effectiveness of EEH in that case, but that's
- the best we found. So when any of the PEs freezes, we freeze the
- other ones for that "domain". We thus introduce the concept of
- "master PE" which is the one used for DMA, MSIs, etc., and "secondary
- PEs" that are used for the remaining M64 segments.
-
- We would like to investigate using additional M64 windows in "single
- PE" mode to overlay over specific BARs to work around some of that, for
- example for devices with very large BARs, e.g., GPUs. It would make
- sense, but we haven't done it yet.
-
-3. Considerations for SR-IOV on PowerKVM
-
- * SR-IOV Background
-
- The PCIe SR-IOV feature allows a single Physical Function (PF) to
- support several Virtual Functions (VFs). Registers in the PF's SR-IOV
- Capability control the number of VFs and whether they are enabled.
-
- When VFs are enabled, they appear in Configuration Space like normal
- PCI devices, but the BARs in VF config space headers are unusual. For
- a non-VF device, software uses BARs in the config space header to
- discover the BAR sizes and assign addresses for them. For VF devices,
- software uses VF BAR registers in the *PF* SR-IOV Capability to
- discover sizes and assign addresses. The BARs in the VF's config space
- header are read-only zeros.
-
- When a VF BAR in the PF SR-IOV Capability is programmed, it sets the
- base address for all the corresponding VF(n) BARs. For example, if the
- PF SR-IOV Capability is programmed to enable eight VFs, and it has a
- 1MB VF BAR0, the address in that VF BAR sets the base of an 8MB region.
- This region is divided into eight contiguous 1MB regions, each of which
- is a BAR0 for one of the VFs. Note that even though the VF BAR
- describes an 8MB region, the alignment requirement is for a single VF,
- i.e., 1MB in this example.
-
- There are several strategies for isolating VFs in PEs:
-
- - M32 window: There's one M32 window, and it is split into 256
- equally-sized segments. The finest granularity possible is a 256MB
- window with 1MB segments. VF BARs that are 1MB or larger could be
- mapped to separate PEs in this window. Each segment can be
- individually mapped to a PE via the lookup table, so this is quite
- flexible, but it works best when all the VF BARs are the same size. If
- they are different sizes, the entire window has to be small enough that
- the segment size matches the smallest VF BAR, which means larger VF
- BARs span several segments.
-
- - Non-segmented M64 window: A non-segmented M64 window is mapped entirely
- to a single PE, so it could only isolate one VF.
-
- - Single segmented M64 windows: A segmented M64 window could be used just
- like the M32 window, but the segments can't be individually mapped to
- PEs (the segment number is the PE#), so there isn't as much
- flexibility. A VF with multiple BARs would have to be in a "domain" of
- multiple PEs, which is not as well isolated as a single PE.
-
- - Multiple segmented M64 windows: As usual, each window is split into 256
- equally-sized segments, and the segment number is the PE#. But if we
- use several M64 windows, they can be set to different base addresses
- and different segment sizes. If we have VFs that each have a 1MB BAR
- and a 32MB BAR, we could use one M64 window to assign 1MB segments and
- another M64 window to assign 32MB segments.
-
- Finally, the plan to use M64 windows for SR-IOV, which will be described
- more in the next two sections. For a given VF BAR, we need to
- effectively reserve the entire 256 segments (256 * VF BAR size) and
- position the VF BAR to start at the beginning of a free range of
- segments/PEs inside that M64 window.
-
- The goal is of course to be able to give a separate PE for each VF.
-
- The IODA2 platform has 16 M64 windows, which are used to map MMIO
- range to PE#. Each M64 window defines one MMIO range and this range is
- divided into 256 segments, with each segment corresponding to one PE.
-
- We decide to leverage this M64 window to map VFs to individual PEs, since
- SR-IOV VF BARs are all the same size.
-
- But doing so introduces another problem: total_VFs is usually smaller
- than the number of M64 window segments, so if we map one VF BAR directly
- to one M64 window, some part of the M64 window will map to another
- device's MMIO range.
-
- IODA supports 256 PEs, so segmented windows contain 256 segments, so if
- total_VFs is less than 256, we have the situation in Figure 1.0, where
- segments [total_VFs, 255] of the M64 window may map to some MMIO range on
- other devices:
-
- 0 1 total_VFs - 1
- +------+------+- -+------+------+
- | | | ... | | |
- +------+------+- -+------+------+
-
- VF(n) BAR space
-
- 0 1 total_VFs - 1 255
- +------+------+- -+------+------+- -+------+------+
- | | | ... | | | ... | | |
- +------+------+- -+------+------+- -+------+------+
-
- M64 window
-
- Figure 1.0 Direct map VF(n) BAR space
-
- Our current solution is to allocate 256 segments even if the VF(n) BAR
- space doesn't need that much, as shown in Figure 1.1:
-
- 0 1 total_VFs - 1 255
- +------+------+- -+------+------+- -+------+------+
- | | | ... | | | ... | | |
- +------+------+- -+------+------+- -+------+------+
-
- VF(n) BAR space + extra
-
- 0 1 total_VFs - 1 255
- +------+------+- -+------+------+- -+------+------+
- | | | ... | | | ... | | |
- +------+------+- -+------+------+- -+------+------+
-
- M64 window
-
- Figure 1.1 Map VF(n) BAR space + extra
-
- Allocating the extra space ensures that the entire M64 window will be
- assigned to this one SR-IOV device and none of the space will be
- available for other devices. Note that this only expands the space
- reserved in software; there are still only total_VFs VFs, and they only
- respond to segments [0, total_VFs - 1]. There's nothing in hardware that
- responds to segments [total_VFs, 255].
-
-4. Implications for the Generic PCI Code
-
-The PCIe SR-IOV spec requires that the base of the VF(n) BAR space be
-aligned to the size of an individual VF BAR.
-
-In IODA2, the MMIO address determines the PE#. If the address is in an M32
-window, we can set the PE# by updating the table that translates segments
-to PE#s. Similarly, if the address is in an unsegmented M64 window, we can
-set the PE# for the window. But if it's in a segmented M64 window, the
-segment number is the PE#.
-
-Therefore, the only way to control the PE# for a VF is to change the base
-of the VF(n) BAR space in the VF BAR. If the PCI core allocates the exact
-amount of space required for the VF(n) BAR space, the VF BAR value is fixed
-and cannot be changed.
-
-On the other hand, if the PCI core allocates additional space, the VF BAR
-value can be changed as long as the entire VF(n) BAR space remains inside
-the space allocated by the core.
-
-Ideally the segment size will be the same as an individual VF BAR size.
-Then each VF will be in its own PE. The VF BARs (and therefore the PE#s)
-are contiguous. If VF0 is in PE(x), then VF(n) is in PE(x+n). If we
-allocate 256 segments, there are (256 - numVFs) choices for the PE# of VF0.
-
-If the segment size is smaller than the VF BAR size, it will take several
-segments to cover a VF BAR, and a VF will be in several PEs. This is
-possible, but the isolation isn't as good, and it reduces the number of PE#
-choices because instead of consuming only numVFs segments, the VF(n) BAR
-space will consume (numVFs * n) segments. That means there aren't as many
-available segments for adjusting base of the VF(n) BAR space.
--- /dev/null
+========================
+PMU Event Based Branches
+========================
+
+Event Based Branches (EBBs) are a feature which allows the hardware to
+branch directly to a specified user space address when certain events occur.
+
+The full specification is available in Power ISA v2.07:
+
+ https://www.power.org/documentation/power-isa-version-2-07/
+
+One type of event for which EBBs can be configured is PMU exceptions. This
+document describes the API for configuring the Power PMU to generate EBBs,
+using the Linux perf_events API.
+
+
+Terminology
+-----------
+
+Throughout this document we will refer to an "EBB event" or "EBB events". This
+just refers to a struct perf_event which has set the "EBB" flag in its
+attr.config. All events which can be configured on the hardware PMU are
+possible "EBB events".
+
+
+Background
+----------
+
+When a PMU EBB occurs it is delivered to the currently running process. As such
+EBBs can only sensibly be used by programs for self-monitoring.
+
+It is a feature of the perf_events API that events can be created on other
+processes, subject to standard permission checks. This is also true of EBB
+events, however unless the target process enables EBBs (via mtspr(BESCR)) no
+EBBs will ever be delivered.
+
+This makes it possible for a process to enable EBBs for itself, but not
+actually configure any events. At a later time another process can come along
+and attach an EBB event to the process, which will then cause EBBs to be
+delivered to the first process. It's not clear if this is actually useful.
+
+
+When the PMU is configured for EBBs, all PMU interrupts are delivered to the
+user process. This means once an EBB event is scheduled on the PMU, no non-EBB
+events can be configured. This means that EBB events can not be run
+concurrently with regular 'perf' commands, or any other perf events.
+
+It is however safe to run 'perf' commands on a process which is using EBBs. The
+kernel will in general schedule the EBB event, and perf will be notified that
+its events could not run.
+
+The exclusion between EBB events and regular events is implemented using the
+existing "pinned" and "exclusive" attributes of perf_events. This means EBB
+events will be given priority over other events, unless they are also pinned.
+If an EBB event and a regular event are both pinned, then whichever is enabled
+first will be scheduled and the other will be put in error state. See the
+section below titled "Enabling an EBB event" for more information.
+
+
+Creating an EBB event
+---------------------
+
+To request that an event is counted using EBB, the event code should have bit
+63 set.
+
+EBB events must be created with a particular, and restrictive, set of
+attributes - this is so that they interoperate correctly with the rest of the
+perf_events subsystem.
+
+An EBB event must be created with the "pinned" and "exclusive" attributes set.
+Note that if you are creating a group of EBB events, only the leader can have
+these attributes set.
+
+An EBB event must NOT set any of the "inherit", "sample_period", "freq" or
+"enable_on_exec" attributes.
+
+An EBB event must be attached to a task. This is specified to perf_event_open()
+by passing a pid value, typically 0 indicating the current task.
+
+All events in a group must agree on whether they want EBB. That is all events
+must request EBB, or none may request EBB.
+
+EBB events must specify the PMC they are to be counted on. This ensures
+userspace is able to reliably determine which PMC the event is scheduled on.
+
+
+Enabling an EBB event
+---------------------
+
+Once an EBB event has been successfully opened, it must be enabled with the
+perf_events API. This can be achieved either via the ioctl() interface, or the
+prctl() interface.
+
+However, due to the design of the perf_events API, enabling an event does not
+guarantee that it has been scheduled on the PMU. To ensure that the EBB event
+has been scheduled on the PMU, you must perform a read() on the event. If the
+read() returns EOF, then the event has not been scheduled and EBBs are not
+enabled.
+
+This behaviour occurs because the EBB event is pinned and exclusive. When the
+EBB event is enabled it will force all other non-pinned events off the PMU. In
+this case the enable will be successful. However if there is already an event
+pinned on the PMU then the enable will not be successful.
+
+
+Reading an EBB event
+--------------------
+
+It is possible to read() from an EBB event. However the results are
+meaningless. Because interrupts are being delivered to the user process the
+kernel is not able to count the event, and so will return a junk value.
+
+
+Closing an EBB event
+--------------------
+
+When an EBB event is finished with, you can close it using close() as for any
+regular event. If this is the last EBB event the PMU will be deconfigured and
+no further PMU EBBs will be delivered.
+
+
+EBB Handler
+-----------
+
+The EBB handler is just regular userspace code, however it must be written in
+the style of an interrupt handler. When the handler is entered all registers
+are live (possibly) and so must be saved somehow before the handler can invoke
+other code.
+
+It's up to the program how to handle this. For C programs a relatively simple
+option is to create an interrupt frame on the stack and save registers there.
+
+Fork
+----
+
+EBB events are not inherited across fork. If the child process wishes to use
+EBBs it should open a new event for itself. Similarly the EBB state in
+BESCR/EBBHR/EBBRR is cleared across fork().
+++ /dev/null
-PMU Event Based Branches
-========================
-
-Event Based Branches (EBBs) are a feature which allows the hardware to
-branch directly to a specified user space address when certain events occur.
-
-The full specification is available in Power ISA v2.07:
-
- https://www.power.org/documentation/power-isa-version-2-07/
-
-One type of event for which EBBs can be configured is PMU exceptions. This
-document describes the API for configuring the Power PMU to generate EBBs,
-using the Linux perf_events API.
-
-
-Terminology
------------
-
-Throughout this document we will refer to an "EBB event" or "EBB events". This
-just refers to a struct perf_event which has set the "EBB" flag in its
-attr.config. All events which can be configured on the hardware PMU are
-possible "EBB events".
-
-
-Background
-----------
-
-When a PMU EBB occurs it is delivered to the currently running process. As such
-EBBs can only sensibly be used by programs for self-monitoring.
-
-It is a feature of the perf_events API that events can be created on other
-processes, subject to standard permission checks. This is also true of EBB
-events, however unless the target process enables EBBs (via mtspr(BESCR)) no
-EBBs will ever be delivered.
-
-This makes it possible for a process to enable EBBs for itself, but not
-actually configure any events. At a later time another process can come along
-and attach an EBB event to the process, which will then cause EBBs to be
-delivered to the first process. It's not clear if this is actually useful.
-
-
-When the PMU is configured for EBBs, all PMU interrupts are delivered to the
-user process. This means once an EBB event is scheduled on the PMU, no non-EBB
-events can be configured. This means that EBB events can not be run
-concurrently with regular 'perf' commands, or any other perf events.
-
-It is however safe to run 'perf' commands on a process which is using EBBs. The
-kernel will in general schedule the EBB event, and perf will be notified that
-its events could not run.
-
-The exclusion between EBB events and regular events is implemented using the
-existing "pinned" and "exclusive" attributes of perf_events. This means EBB
-events will be given priority over other events, unless they are also pinned.
-If an EBB event and a regular event are both pinned, then whichever is enabled
-first will be scheduled and the other will be put in error state. See the
-section below titled "Enabling an EBB event" for more information.
-
-
-Creating an EBB event
----------------------
-
-To request that an event is counted using EBB, the event code should have bit
-63 set.
-
-EBB events must be created with a particular, and restrictive, set of
-attributes - this is so that they interoperate correctly with the rest of the
-perf_events subsystem.
-
-An EBB event must be created with the "pinned" and "exclusive" attributes set.
-Note that if you are creating a group of EBB events, only the leader can have
-these attributes set.
-
-An EBB event must NOT set any of the "inherit", "sample_period", "freq" or
-"enable_on_exec" attributes.
-
-An EBB event must be attached to a task. This is specified to perf_event_open()
-by passing a pid value, typically 0 indicating the current task.
-
-All events in a group must agree on whether they want EBB. That is all events
-must request EBB, or none may request EBB.
-
-EBB events must specify the PMC they are to be counted on. This ensures
-userspace is able to reliably determine which PMC the event is scheduled on.
-
-
-Enabling an EBB event
----------------------
-
-Once an EBB event has been successfully opened, it must be enabled with the
-perf_events API. This can be achieved either via the ioctl() interface, or the
-prctl() interface.
-
-However, due to the design of the perf_events API, enabling an event does not
-guarantee that it has been scheduled on the PMU. To ensure that the EBB event
-has been scheduled on the PMU, you must perform a read() on the event. If the
-read() returns EOF, then the event has not been scheduled and EBBs are not
-enabled.
-
-This behaviour occurs because the EBB event is pinned and exclusive. When the
-EBB event is enabled it will force all other non-pinned events off the PMU. In
-this case the enable will be successful. However if there is already an event
-pinned on the PMU then the enable will not be successful.
-
-
-Reading an EBB event
---------------------
-
-It is possible to read() from an EBB event. However the results are
-meaningless. Because interrupts are being delivered to the user process the
-kernel is not able to count the event, and so will return a junk value.
-
-
-Closing an EBB event
---------------------
-
-When an EBB event is finished with, you can close it using close() as for any
-regular event. If this is the last EBB event the PMU will be deconfigured and
-no further PMU EBBs will be delivered.
-
-
-EBB Handler
------------
-
-The EBB handler is just regular userspace code, however it must be written in
-the style of an interrupt handler. When the handler is entered all registers
-are live (possibly) and so must be saved somehow before the handler can invoke
-other code.
-
-It's up to the program how to handle this. For C programs a relatively simple
-option is to create an interrupt frame on the stack and save registers there.
-
-Fork
-----
-
-EBB events are not inherited across fork. If the child process wishes to use
-EBBs it should open a new event for itself. Similarly the EBB state in
-BESCR/EBBHR/EBBRR is cleared across fork().
--- /dev/null
+======
+Ptrace
+======
+
+GDB intends to support the following hardware debug features of BookE
+processors:
+
+4 hardware breakpoints (IAC)
+2 hardware watchpoints (read, write and read-write) (DAC)
+2 value conditions for the hardware watchpoints (DVC)
+
+For that, we need to extend ptrace so that GDB can query and set these
+resources. Since we're extending, we're trying to create an interface
+that's extendable and that covers both BookE and server processors, so
+that GDB doesn't need to special-case each of them. We added the
+following 3 new ptrace requests.
+
+1. PTRACE_PPC_GETHWDEBUGINFO
+============================
+
+Query for GDB to discover the hardware debug features. The main info to
+be returned here is the minimum alignment for the hardware watchpoints.
+BookE processors don't have restrictions here, but server processors have
+an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid
+adding special cases to GDB based on what it sees in AUXV.
+
+Since we're at it, we added other useful info that the kernel can return to
+GDB: this query will return the number of hardware breakpoints, hardware
+watchpoints and whether it supports a range of addresses and a condition.
+The query will fill the following structure provided by the requesting process::
+
+ struct ppc_debug_info {
+ unit32_t version;
+ unit32_t num_instruction_bps;
+ unit32_t num_data_bps;
+ unit32_t num_condition_regs;
+ unit32_t data_bp_alignment;
+ unit32_t sizeof_condition; /* size of the DVC register */
+ uint64_t features; /* bitmask of the individual flags */
+ };
+
+features will have bits indicating whether there is support for::
+
+ #define PPC_DEBUG_FEATURE_INSN_BP_RANGE 0x1
+ #define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x2
+ #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4
+ #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8
+ #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10
+
+2. PTRACE_SETHWDEBUG
+
+Sets a hardware breakpoint or watchpoint, according to the provided structure::
+
+ struct ppc_hw_breakpoint {
+ uint32_t version;
+ #define PPC_BREAKPOINT_TRIGGER_EXECUTE 0x1
+ #define PPC_BREAKPOINT_TRIGGER_READ 0x2
+ #define PPC_BREAKPOINT_TRIGGER_WRITE 0x4
+ uint32_t trigger_type; /* only some combinations allowed */
+ #define PPC_BREAKPOINT_MODE_EXACT 0x0
+ #define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE 0x1
+ #define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE 0x2
+ #define PPC_BREAKPOINT_MODE_MASK 0x3
+ uint32_t addr_mode; /* address match mode */
+
+ #define PPC_BREAKPOINT_CONDITION_MODE 0x3
+ #define PPC_BREAKPOINT_CONDITION_NONE 0x0
+ #define PPC_BREAKPOINT_CONDITION_AND 0x1
+ #define PPC_BREAKPOINT_CONDITION_EXACT 0x1 /* different name for the same thing as above */
+ #define PPC_BREAKPOINT_CONDITION_OR 0x2
+ #define PPC_BREAKPOINT_CONDITION_AND_OR 0x3
+ #define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000 /* byte enable bits */
+ #define PPC_BREAKPOINT_CONDITION_BE(n) (1<<((n)+16))
+ uint32_t condition_mode; /* break/watchpoint condition flags */
+
+ uint64_t addr;
+ uint64_t addr2;
+ uint64_t condition_value;
+ };
+
+A request specifies one event, not necessarily just one register to be set.
+For instance, if the request is for a watchpoint with a condition, both the
+DAC and DVC registers will be set in the same request.
+
+With this GDB can ask for all kinds of hardware breakpoints and watchpoints
+that the BookE supports. COMEFROM breakpoints available in server processors
+are not contemplated, but that is out of the scope of this work.
+
+ptrace will return an integer (handle) uniquely identifying the breakpoint or
+watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG
+request to ask for its removal. Return -ENOSPC if the requested breakpoint
+can't be allocated on the registers.
+
+Some examples of using the structure to:
+
+- set a breakpoint in the first breakpoint register::
+
+ p.version = PPC_DEBUG_CURRENT_VERSION;
+ p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+ p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
+ p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
+ p.addr = (uint64_t) address;
+ p.addr2 = 0;
+ p.condition_value = 0;
+
+- set a watchpoint which triggers on reads in the second watchpoint register::
+
+ p.version = PPC_DEBUG_CURRENT_VERSION;
+ p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ;
+ p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
+ p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
+ p.addr = (uint64_t) address;
+ p.addr2 = 0;
+ p.condition_value = 0;
+
+- set a watchpoint which triggers only with a specific value::
+
+ p.version = PPC_DEBUG_CURRENT_VERSION;
+ p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ;
+ p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
+ p.condition_mode = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL;
+ p.addr = (uint64_t) address;
+ p.addr2 = 0;
+ p.condition_value = (uint64_t) condition;
+
+- set a ranged hardware breakpoint::
+
+ p.version = PPC_DEBUG_CURRENT_VERSION;
+ p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE;
+ p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
+ p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
+ p.addr = (uint64_t) begin_range;
+ p.addr2 = (uint64_t) end_range;
+ p.condition_value = 0;
+
+- set a watchpoint in server processors (BookS)::
+
+ p.version = 1;
+ p.trigger_type = PPC_BREAKPOINT_TRIGGER_RW;
+ p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
+ or
+ p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
+
+ p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
+ p.addr = (uint64_t) begin_range;
+ /* For PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE addr2 needs to be specified, where
+ * addr2 - addr <= 8 Bytes.
+ */
+ p.addr2 = (uint64_t) end_range;
+ p.condition_value = 0;
+
+3. PTRACE_DELHWDEBUG
+
+Takes an integer which identifies an existing breakpoint or watchpoint
+(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the
+corresponding breakpoint or watchpoint..
+++ /dev/null
-GDB intends to support the following hardware debug features of BookE
-processors:
-
-4 hardware breakpoints (IAC)
-2 hardware watchpoints (read, write and read-write) (DAC)
-2 value conditions for the hardware watchpoints (DVC)
-
-For that, we need to extend ptrace so that GDB can query and set these
-resources. Since we're extending, we're trying to create an interface
-that's extendable and that covers both BookE and server processors, so
-that GDB doesn't need to special-case each of them. We added the
-following 3 new ptrace requests.
-
-1. PTRACE_PPC_GETHWDEBUGINFO
-
-Query for GDB to discover the hardware debug features. The main info to
-be returned here is the minimum alignment for the hardware watchpoints.
-BookE processors don't have restrictions here, but server processors have
-an 8-byte alignment restriction for hardware watchpoints. We'd like to avoid
-adding special cases to GDB based on what it sees in AUXV.
-
-Since we're at it, we added other useful info that the kernel can return to
-GDB: this query will return the number of hardware breakpoints, hardware
-watchpoints and whether it supports a range of addresses and a condition.
-The query will fill the following structure provided by the requesting process:
-
-struct ppc_debug_info {
- unit32_t version;
- unit32_t num_instruction_bps;
- unit32_t num_data_bps;
- unit32_t num_condition_regs;
- unit32_t data_bp_alignment;
- unit32_t sizeof_condition; /* size of the DVC register */
- uint64_t features; /* bitmask of the individual flags */
-};
-
-features will have bits indicating whether there is support for:
-
-#define PPC_DEBUG_FEATURE_INSN_BP_RANGE 0x1
-#define PPC_DEBUG_FEATURE_INSN_BP_MASK 0x2
-#define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x4
-#define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x8
-#define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x10
-
-2. PTRACE_SETHWDEBUG
-
-Sets a hardware breakpoint or watchpoint, according to the provided structure:
-
-struct ppc_hw_breakpoint {
- uint32_t version;
-#define PPC_BREAKPOINT_TRIGGER_EXECUTE 0x1
-#define PPC_BREAKPOINT_TRIGGER_READ 0x2
-#define PPC_BREAKPOINT_TRIGGER_WRITE 0x4
- uint32_t trigger_type; /* only some combinations allowed */
-#define PPC_BREAKPOINT_MODE_EXACT 0x0
-#define PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE 0x1
-#define PPC_BREAKPOINT_MODE_RANGE_EXCLUSIVE 0x2
-#define PPC_BREAKPOINT_MODE_MASK 0x3
- uint32_t addr_mode; /* address match mode */
-
-#define PPC_BREAKPOINT_CONDITION_MODE 0x3
-#define PPC_BREAKPOINT_CONDITION_NONE 0x0
-#define PPC_BREAKPOINT_CONDITION_AND 0x1
-#define PPC_BREAKPOINT_CONDITION_EXACT 0x1 /* different name for the same thing as above */
-#define PPC_BREAKPOINT_CONDITION_OR 0x2
-#define PPC_BREAKPOINT_CONDITION_AND_OR 0x3
-#define PPC_BREAKPOINT_CONDITION_BE_ALL 0x00ff0000 /* byte enable bits */
-#define PPC_BREAKPOINT_CONDITION_BE(n) (1<<((n)+16))
- uint32_t condition_mode; /* break/watchpoint condition flags */
-
- uint64_t addr;
- uint64_t addr2;
- uint64_t condition_value;
-};
-
-A request specifies one event, not necessarily just one register to be set.
-For instance, if the request is for a watchpoint with a condition, both the
-DAC and DVC registers will be set in the same request.
-
-With this GDB can ask for all kinds of hardware breakpoints and watchpoints
-that the BookE supports. COMEFROM breakpoints available in server processors
-are not contemplated, but that is out of the scope of this work.
-
-ptrace will return an integer (handle) uniquely identifying the breakpoint or
-watchpoint just created. This integer will be used in the PTRACE_DELHWDEBUG
-request to ask for its removal. Return -ENOSPC if the requested breakpoint
-can't be allocated on the registers.
-
-Some examples of using the structure to:
-
-- set a breakpoint in the first breakpoint register
-
- p.version = PPC_DEBUG_CURRENT_VERSION;
- p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE;
- p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
- p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
- p.addr = (uint64_t) address;
- p.addr2 = 0;
- p.condition_value = 0;
-
-- set a watchpoint which triggers on reads in the second watchpoint register
-
- p.version = PPC_DEBUG_CURRENT_VERSION;
- p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ;
- p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
- p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
- p.addr = (uint64_t) address;
- p.addr2 = 0;
- p.condition_value = 0;
-
-- set a watchpoint which triggers only with a specific value
-
- p.version = PPC_DEBUG_CURRENT_VERSION;
- p.trigger_type = PPC_BREAKPOINT_TRIGGER_READ;
- p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
- p.condition_mode = PPC_BREAKPOINT_CONDITION_AND | PPC_BREAKPOINT_CONDITION_BE_ALL;
- p.addr = (uint64_t) address;
- p.addr2 = 0;
- p.condition_value = (uint64_t) condition;
-
-- set a ranged hardware breakpoint
-
- p.version = PPC_DEBUG_CURRENT_VERSION;
- p.trigger_type = PPC_BREAKPOINT_TRIGGER_EXECUTE;
- p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
- p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
- p.addr = (uint64_t) begin_range;
- p.addr2 = (uint64_t) end_range;
- p.condition_value = 0;
-
-- set a watchpoint in server processors (BookS)
-
- p.version = 1;
- p.trigger_type = PPC_BREAKPOINT_TRIGGER_RW;
- p.addr_mode = PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE;
- or
- p.addr_mode = PPC_BREAKPOINT_MODE_EXACT;
-
- p.condition_mode = PPC_BREAKPOINT_CONDITION_NONE;
- p.addr = (uint64_t) begin_range;
- /* For PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE addr2 needs to be specified, where
- * addr2 - addr <= 8 Bytes.
- */
- p.addr2 = (uint64_t) end_range;
- p.condition_value = 0;
-
-3. PTRACE_DELHWDEBUG
-
-Takes an integer which identifies an existing breakpoint or watchpoint
-(i.e., the value returned from PTRACE_SETHWDEBUG), and deletes the
-corresponding breakpoint or watchpoint..
--- /dev/null
+=========================================
+Freescale QUICC Engine Firmware Uploading
+=========================================
+
+(c) 2007 Timur Tabi <timur at freescale.com>,
+ Freescale Semiconductor
+
+.. Table of Contents
+
+ I - Software License for Firmware
+
+ II - Microcode Availability
+
+ III - Description and Terminology
+
+ IV - Microcode Programming Details
+
+ V - Firmware Structure Layout
+
+ VI - Sample Code for Creating Firmware Files
+
+Revision Information
+====================
+
+November 30, 2007: Rev 1.0 - Initial version
+
+I - Software License for Firmware
+=================================
+
+Each firmware file comes with its own software license. For information on
+the particular license, please see the license text that is distributed with
+the firmware.
+
+II - Microcode Availability
+===========================
+
+Firmware files are distributed through various channels. Some are available on
+http://opensource.freescale.com. For other firmware files, please contact
+your Freescale representative or your operating system vendor.
+
+III - Description and Terminology
+=================================
+
+In this document, the term 'microcode' refers to the sequence of 32-bit
+integers that compose the actual QE microcode.
+
+The term 'firmware' refers to a binary blob that contains the microcode as
+well as other data that
+
+ 1) describes the microcode's purpose
+ 2) describes how and where to upload the microcode
+ 3) specifies the values of various registers
+ 4) includes additional data for use by specific device drivers
+
+Firmware files are binary files that contain only a firmware.
+
+IV - Microcode Programming Details
+===================================
+
+The QE architecture allows for only one microcode present in I-RAM for each
+RISC processor. To replace any current microcode, a full QE reset (which
+disables the microcode) must be performed first.
+
+QE microcode is uploaded using the following procedure:
+
+1) The microcode is placed into I-RAM at a specific location, using the
+ IRAM.IADD and IRAM.IDATA registers.
+
+2) The CERCR.CIR bit is set to 0 or 1, depending on whether the firmware
+ needs split I-RAM. Split I-RAM is only meaningful for SOCs that have
+ QEs with multiple RISC processors, such as the 8360. Splitting the I-RAM
+ allows each processor to run a different microcode, effectively creating an
+ asymmetric multiprocessing (AMP) system.
+
+3) The TIBCR trap registers are loaded with the addresses of the trap handlers
+ in the microcode.
+
+4) The RSP.ECCR register is programmed with the value provided.
+
+5) If necessary, device drivers that need the virtual traps and extended mode
+ data will use them.
+
+Virtual Microcode Traps
+
+These virtual traps are conditional branches in the microcode. These are
+"soft" provisional introduced in the ROMcode in order to enable higher
+flexibility and save h/w traps If new features are activated or an issue is
+being fixed in the RAM package utilizing they should be activated. This data
+structure signals the microcode which of these virtual traps is active.
+
+This structure contains 6 words that the application should copy to some
+specific been defined. This table describes the structure::
+
+ ---------------------------------------------------------------
+ | Offset in | | Destination Offset | Size of |
+ | array | Protocol | within PRAM | Operand |
+ --------------------------------------------------------------|
+ | 0 | Ethernet | 0xF8 | 4 bytes |
+ | | interworking | | |
+ ---------------------------------------------------------------
+ | 4 | ATM | 0xF8 | 4 bytes |
+ | | interworking | | |
+ ---------------------------------------------------------------
+ | 8 | PPP | 0xF8 | 4 bytes |
+ | | interworking | | |
+ ---------------------------------------------------------------
+ | 12 | Ethernet RX | 0x22 | 1 byte |
+ | | Distributor Page | | |
+ ---------------------------------------------------------------
+ | 16 | ATM Globtal | 0x28 | 1 byte |
+ | | Params Table | | |
+ ---------------------------------------------------------------
+ | 20 | Insert Frame | 0xF8 | 4 bytes |
+ ---------------------------------------------------------------
+
+
+Extended Modes
+
+This is a double word bit array (64 bits) that defines special functionality
+which has an impact on the software drivers. Each bit has its own impact
+and has special instructions for the s/w associated with it. This structure is
+described in this table::
+
+ -----------------------------------------------------------------------
+ | Bit # | Name | Description |
+ -----------------------------------------------------------------------
+ | 0 | General | Indicates that prior to each host command |
+ | | push command | given by the application, the software must |
+ | | | assert a special host command (push command)|
+ | | | CECDR = 0x00800000. |
+ | | | CECR = 0x01c1000f. |
+ -----------------------------------------------------------------------
+ | 1 | UCC ATM | Indicates that after issuing ATM RX INIT |
+ | | RX INIT | command, the host must issue another special|
+ | | push command | command (push command) and immediately |
+ | | | following that re-issue the ATM RX INIT |
+ | | | command. (This makes the sequence of |
+ | | | initializing the ATM receiver a sequence of |
+ | | | three host commands) |
+ | | | CECDR = 0x00800000. |
+ | | | CECR = 0x01c1000f. |
+ -----------------------------------------------------------------------
+ | 2 | Add/remove | Indicates that following the specific host |
+ | | command | command: "Add/Remove entry in Hash Lookup |
+ | | validation | Table" used in Interworking setup, the user |
+ | | | must issue another command. |
+ | | | CECDR = 0xce000003. |
+ | | | CECR = 0x01c10f58. |
+ -----------------------------------------------------------------------
+ | 3 | General push | Indicates that the s/w has to initialize |
+ | | command | some pointers in the Ethernet thread pages |
+ | | | which are used when Header Compression is |
+ | | | activated. The full details of these |
+ | | | pointers is located in the software drivers.|
+ -----------------------------------------------------------------------
+ | 4 | General push | Indicates that after issuing Ethernet TX |
+ | | command | INIT command, user must issue this command |
+ | | | for each SNUM of Ethernet TX thread. |
+ | | | CECDR = 0x00800003. |
+ | | | CECR = 0x7'b{0}, 8'b{Enet TX thread SNUM}, |
+ | | | 1'b{1}, 12'b{0}, 4'b{1} |
+ -----------------------------------------------------------------------
+ | 5 - 31 | N/A | Reserved, set to zero. |
+ -----------------------------------------------------------------------
+
+V - Firmware Structure Layout
+==============================
+
+QE microcode from Freescale is typically provided as a header file. This
+header file contains macros that define the microcode binary itself as well as
+some other data used in uploading that microcode. The format of these files
+do not lend themselves to simple inclusion into other code. Hence,
+the need for a more portable format. This section defines that format.
+
+Instead of distributing a header file, the microcode and related data are
+embedded into a binary blob. This blob is passed to the qe_upload_firmware()
+function, which parses the blob and performs everything necessary to upload
+the microcode.
+
+All integers are big-endian. See the comments for function
+qe_upload_firmware() for up-to-date implementation information.
+
+This structure supports versioning, where the version of the structure is
+embedded into the structure itself. To ensure forward and backwards
+compatibility, all versions of the structure must use the same 'qe_header'
+structure at the beginning.
+
+'header' (type: struct qe_header):
+ The 'length' field is the size, in bytes, of the entire structure,
+ including all the microcode embedded in it, as well as the CRC (if
+ present).
+
+ The 'magic' field is an array of three bytes that contains the letters
+ 'Q', 'E', and 'F'. This is an identifier that indicates that this
+ structure is a QE Firmware structure.
+
+ The 'version' field is a single byte that indicates the version of this
+ structure. If the layout of the structure should ever need to be
+ changed to add support for additional types of microcode, then the
+ version number should also be changed.
+
+The 'id' field is a null-terminated string(suitable for printing) that
+identifies the firmware.
+
+The 'count' field indicates the number of 'microcode' structures. There
+must be one and only one 'microcode' structure for each RISC processor.
+Therefore, this field also represents the number of RISC processors for this
+SOC.
+
+The 'soc' structure contains the SOC numbers and revisions used to match
+the microcode to the SOC itself. Normally, the microcode loader should
+check the data in this structure with the SOC number and revisions, and
+only upload the microcode if there's a match. However, this check is not
+made on all platforms.
+
+Although it is not recommended, you can specify '0' in the soc.model
+field to skip matching SOCs altogether.
+
+The 'model' field is a 16-bit number that matches the actual SOC. The
+'major' and 'minor' fields are the major and minor revision numbers,
+respectively, of the SOC.
+
+For example, to match the 8323, revision 1.0::
+
+ soc.model = 8323
+ soc.major = 1
+ soc.minor = 0
+
+'padding' is necessary for structure alignment. This field ensures that the
+'extended_modes' field is aligned on a 64-bit boundary.
+
+'extended_modes' is a bitfield that defines special functionality which has an
+impact on the device drivers. Each bit has its own impact and has special
+instructions for the driver associated with it. This field is stored in
+the QE library and available to any driver that calles qe_get_firmware_info().
+
+'vtraps' is an array of 8 words that contain virtual trap values for each
+virtual traps. As with 'extended_modes', this field is stored in the QE
+library and available to any driver that calles qe_get_firmware_info().
+
+'microcode' (type: struct qe_microcode):
+ For each RISC processor there is one 'microcode' structure. The first
+ 'microcode' structure is for the first RISC, and so on.
+
+ The 'id' field is a null-terminated string suitable for printing that
+ identifies this particular microcode.
+
+ 'traps' is an array of 16 words that contain hardware trap values
+ for each of the 16 traps. If trap[i] is 0, then this particular
+ trap is to be ignored (i.e. not written to TIBCR[i]). The entire value
+ is written as-is to the TIBCR[i] register, so be sure to set the EN
+ and T_IBP bits if necessary.
+
+ 'eccr' is the value to program into the ECCR register.
+
+ 'iram_offset' is the offset into IRAM to start writing the
+ microcode.
+
+ 'count' is the number of 32-bit words in the microcode.
+
+ 'code_offset' is the offset, in bytes, from the beginning of this
+ structure where the microcode itself can be found. The first
+ microcode binary should be located immediately after the 'microcode'
+ array.
+
+ 'major', 'minor', and 'revision' are the major, minor, and revision
+ version numbers, respectively, of the microcode. If all values are 0,
+ then these fields are ignored.
+
+ 'reserved' is necessary for structure alignment. Since 'microcode'
+ is an array, the 64-bit 'extended_modes' field needs to be aligned
+ on a 64-bit boundary, and this can only happen if the size of
+ 'microcode' is a multiple of 8 bytes. To ensure that, we add
+ 'reserved'.
+
+After the last microcode is a 32-bit CRC. It can be calculated using
+this algorithm::
+
+ u32 crc32(const u8 *p, unsigned int len)
+ {
+ unsigned int i;
+ u32 crc = 0;
+
+ while (len--) {
+ crc ^= *p++;
+ for (i = 0; i < 8; i++)
+ crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0);
+ }
+ return crc;
+ }
+
+VI - Sample Code for Creating Firmware Files
+============================================
+
+A Python program that creates firmware binaries from the header files normally
+distributed by Freescale can be found on http://opensource.freescale.com.
+++ /dev/null
- Freescale QUICC Engine Firmware Uploading
- -----------------------------------------
-
-(c) 2007 Timur Tabi <timur at freescale.com>,
- Freescale Semiconductor
-
-Table of Contents
-=================
-
- I - Software License for Firmware
-
- II - Microcode Availability
-
- III - Description and Terminology
-
- IV - Microcode Programming Details
-
- V - Firmware Structure Layout
-
- VI - Sample Code for Creating Firmware Files
-
-Revision Information
-====================
-
-November 30, 2007: Rev 1.0 - Initial version
-
-I - Software License for Firmware
-=================================
-
-Each firmware file comes with its own software license. For information on
-the particular license, please see the license text that is distributed with
-the firmware.
-
-II - Microcode Availability
-===========================
-
-Firmware files are distributed through various channels. Some are available on
-http://opensource.freescale.com. For other firmware files, please contact
-your Freescale representative or your operating system vendor.
-
-III - Description and Terminology
-================================
-
-In this document, the term 'microcode' refers to the sequence of 32-bit
-integers that compose the actual QE microcode.
-
-The term 'firmware' refers to a binary blob that contains the microcode as
-well as other data that
-
- 1) describes the microcode's purpose
- 2) describes how and where to upload the microcode
- 3) specifies the values of various registers
- 4) includes additional data for use by specific device drivers
-
-Firmware files are binary files that contain only a firmware.
-
-IV - Microcode Programming Details
-===================================
-
-The QE architecture allows for only one microcode present in I-RAM for each
-RISC processor. To replace any current microcode, a full QE reset (which
-disables the microcode) must be performed first.
-
-QE microcode is uploaded using the following procedure:
-
-1) The microcode is placed into I-RAM at a specific location, using the
- IRAM.IADD and IRAM.IDATA registers.
-
-2) The CERCR.CIR bit is set to 0 or 1, depending on whether the firmware
- needs split I-RAM. Split I-RAM is only meaningful for SOCs that have
- QEs with multiple RISC processors, such as the 8360. Splitting the I-RAM
- allows each processor to run a different microcode, effectively creating an
- asymmetric multiprocessing (AMP) system.
-
-3) The TIBCR trap registers are loaded with the addresses of the trap handlers
- in the microcode.
-
-4) The RSP.ECCR register is programmed with the value provided.
-
-5) If necessary, device drivers that need the virtual traps and extended mode
- data will use them.
-
-Virtual Microcode Traps
-
-These virtual traps are conditional branches in the microcode. These are
-"soft" provisional introduced in the ROMcode in order to enable higher
-flexibility and save h/w traps If new features are activated or an issue is
-being fixed in the RAM package utilizing they should be activated. This data
-structure signals the microcode which of these virtual traps is active.
-
-This structure contains 6 words that the application should copy to some
-specific been defined. This table describes the structure.
-
- ---------------------------------------------------------------
- | Offset in | | Destination Offset | Size of |
- | array | Protocol | within PRAM | Operand |
- --------------------------------------------------------------|
- | 0 | Ethernet | 0xF8 | 4 bytes |
- | | interworking | | |
- ---------------------------------------------------------------
- | 4 | ATM | 0xF8 | 4 bytes |
- | | interworking | | |
- ---------------------------------------------------------------
- | 8 | PPP | 0xF8 | 4 bytes |
- | | interworking | | |
- ---------------------------------------------------------------
- | 12 | Ethernet RX | 0x22 | 1 byte |
- | | Distributor Page | | |
- ---------------------------------------------------------------
- | 16 | ATM Globtal | 0x28 | 1 byte |
- | | Params Table | | |
- ---------------------------------------------------------------
- | 20 | Insert Frame | 0xF8 | 4 bytes |
- ---------------------------------------------------------------
-
-
-Extended Modes
-
-This is a double word bit array (64 bits) that defines special functionality
-which has an impact on the software drivers. Each bit has its own impact
-and has special instructions for the s/w associated with it. This structure is
-described in this table:
-
- -----------------------------------------------------------------------
- | Bit # | Name | Description |
- -----------------------------------------------------------------------
- | 0 | General | Indicates that prior to each host command |
- | | push command | given by the application, the software must |
- | | | assert a special host command (push command)|
- | | | CECDR = 0x00800000. |
- | | | CECR = 0x01c1000f. |
- -----------------------------------------------------------------------
- | 1 | UCC ATM | Indicates that after issuing ATM RX INIT |
- | | RX INIT | command, the host must issue another special|
- | | push command | command (push command) and immediately |
- | | | following that re-issue the ATM RX INIT |
- | | | command. (This makes the sequence of |
- | | | initializing the ATM receiver a sequence of |
- | | | three host commands) |
- | | | CECDR = 0x00800000. |
- | | | CECR = 0x01c1000f. |
- -----------------------------------------------------------------------
- | 2 | Add/remove | Indicates that following the specific host |
- | | command | command: "Add/Remove entry in Hash Lookup |
- | | validation | Table" used in Interworking setup, the user |
- | | | must issue another command. |
- | | | CECDR = 0xce000003. |
- | | | CECR = 0x01c10f58. |
- -----------------------------------------------------------------------
- | 3 | General push | Indicates that the s/w has to initialize |
- | | command | some pointers in the Ethernet thread pages |
- | | | which are used when Header Compression is |
- | | | activated. The full details of these |
- | | | pointers is located in the software drivers.|
- -----------------------------------------------------------------------
- | 4 | General push | Indicates that after issuing Ethernet TX |
- | | command | INIT command, user must issue this command |
- | | | for each SNUM of Ethernet TX thread. |
- | | | CECDR = 0x00800003. |
- | | | CECR = 0x7'b{0}, 8'b{Enet TX thread SNUM}, |
- | | | 1'b{1}, 12'b{0}, 4'b{1} |
- -----------------------------------------------------------------------
- | 5 - 31 | N/A | Reserved, set to zero. |
- -----------------------------------------------------------------------
-
-V - Firmware Structure Layout
-==============================
-
-QE microcode from Freescale is typically provided as a header file. This
-header file contains macros that define the microcode binary itself as well as
-some other data used in uploading that microcode. The format of these files
-do not lend themselves to simple inclusion into other code. Hence,
-the need for a more portable format. This section defines that format.
-
-Instead of distributing a header file, the microcode and related data are
-embedded into a binary blob. This blob is passed to the qe_upload_firmware()
-function, which parses the blob and performs everything necessary to upload
-the microcode.
-
-All integers are big-endian. See the comments for function
-qe_upload_firmware() for up-to-date implementation information.
-
-This structure supports versioning, where the version of the structure is
-embedded into the structure itself. To ensure forward and backwards
-compatibility, all versions of the structure must use the same 'qe_header'
-structure at the beginning.
-
-'header' (type: struct qe_header):
- The 'length' field is the size, in bytes, of the entire structure,
- including all the microcode embedded in it, as well as the CRC (if
- present).
-
- The 'magic' field is an array of three bytes that contains the letters
- 'Q', 'E', and 'F'. This is an identifier that indicates that this
- structure is a QE Firmware structure.
-
- The 'version' field is a single byte that indicates the version of this
- structure. If the layout of the structure should ever need to be
- changed to add support for additional types of microcode, then the
- version number should also be changed.
-
-The 'id' field is a null-terminated string(suitable for printing) that
-identifies the firmware.
-
-The 'count' field indicates the number of 'microcode' structures. There
-must be one and only one 'microcode' structure for each RISC processor.
-Therefore, this field also represents the number of RISC processors for this
-SOC.
-
-The 'soc' structure contains the SOC numbers and revisions used to match
-the microcode to the SOC itself. Normally, the microcode loader should
-check the data in this structure with the SOC number and revisions, and
-only upload the microcode if there's a match. However, this check is not
-made on all platforms.
-
-Although it is not recommended, you can specify '0' in the soc.model
-field to skip matching SOCs altogether.
-
-The 'model' field is a 16-bit number that matches the actual SOC. The
-'major' and 'minor' fields are the major and minor revision numbers,
-respectively, of the SOC.
-
-For example, to match the 8323, revision 1.0:
- soc.model = 8323
- soc.major = 1
- soc.minor = 0
-
-'padding' is necessary for structure alignment. This field ensures that the
-'extended_modes' field is aligned on a 64-bit boundary.
-
-'extended_modes' is a bitfield that defines special functionality which has an
-impact on the device drivers. Each bit has its own impact and has special
-instructions for the driver associated with it. This field is stored in
-the QE library and available to any driver that calles qe_get_firmware_info().
-
-'vtraps' is an array of 8 words that contain virtual trap values for each
-virtual traps. As with 'extended_modes', this field is stored in the QE
-library and available to any driver that calles qe_get_firmware_info().
-
-'microcode' (type: struct qe_microcode):
- For each RISC processor there is one 'microcode' structure. The first
- 'microcode' structure is for the first RISC, and so on.
-
- The 'id' field is a null-terminated string suitable for printing that
- identifies this particular microcode.
-
- 'traps' is an array of 16 words that contain hardware trap values
- for each of the 16 traps. If trap[i] is 0, then this particular
- trap is to be ignored (i.e. not written to TIBCR[i]). The entire value
- is written as-is to the TIBCR[i] register, so be sure to set the EN
- and T_IBP bits if necessary.
-
- 'eccr' is the value to program into the ECCR register.
-
- 'iram_offset' is the offset into IRAM to start writing the
- microcode.
-
- 'count' is the number of 32-bit words in the microcode.
-
- 'code_offset' is the offset, in bytes, from the beginning of this
- structure where the microcode itself can be found. The first
- microcode binary should be located immediately after the 'microcode'
- array.
-
- 'major', 'minor', and 'revision' are the major, minor, and revision
- version numbers, respectively, of the microcode. If all values are 0,
- then these fields are ignored.
-
- 'reserved' is necessary for structure alignment. Since 'microcode'
- is an array, the 64-bit 'extended_modes' field needs to be aligned
- on a 64-bit boundary, and this can only happen if the size of
- 'microcode' is a multiple of 8 bytes. To ensure that, we add
- 'reserved'.
-
-After the last microcode is a 32-bit CRC. It can be calculated using
-this algorithm:
-
-u32 crc32(const u8 *p, unsigned int len)
-{
- unsigned int i;
- u32 crc = 0;
-
- while (len--) {
- crc ^= *p++;
- for (i = 0; i < 8; i++)
- crc = (crc >> 1) ^ ((crc & 1) ? 0xedb88320 : 0);
- }
- return crc;
-}
-
-VI - Sample Code for Creating Firmware Files
-============================================
-
-A Python program that creates firmware binaries from the header files normally
-distributed by Freescale can be found on http://opensource.freescale.com.
--- /dev/null
+===============================================
+Power Architecture 64-bit Linux system call ABI
+===============================================
+
+syscall
+=======
+
+syscall calling sequence\ [1]_ matches the Power Architecture 64-bit ELF ABI
+specification C function calling sequence, including register preservation
+rules, with the following differences.
+
+.. [1] Some syscalls (typically low-level management functions) may have
+ different calling sequences (e.g., rt_sigreturn).
+
+Parameters and return value
+---------------------------
+The system call number is specified in r0.
+
+There is a maximum of 6 integer parameters to a syscall, passed in r3-r8.
+
+Both a return value and a return error code are returned. cr0.SO is the return
+error code, and r3 is the return value or error code. When cr0.SO is clear,
+the syscall succeeded and r3 is the return value. When cr0.SO is set, the
+syscall failed and r3 is the error code that generally corresponds to errno.
+
+Stack
+-----
+System calls do not modify the caller's stack frame. For example, the caller's
+stack frame LR and CR save fields are not used.
+
+Register preservation rules
+---------------------------
+Register preservation rules match the ELF ABI calling sequence with the
+following differences:
+
+=========== ============= ========================================
+r0 Volatile (System call number.)
+r3 Volatile (Parameter 1, and return value.)
+r4-r8 Volatile (Parameters 2-6.)
+cr0 Volatile (cr0.SO is the return error condition)
+cr1, cr5-7 Nonvolatile
+lr Nonvolatile
+=========== ============= ========================================
+
+All floating point and vector data registers as well as control and status
+registers are nonvolatile.
+
+Invocation
+----------
+The syscall is performed with the sc instruction, and returns with execution
+continuing at the instruction following the sc instruction.
+
+Transactional Memory
+--------------------
+Syscall behavior can change if the processor is in transactional or suspended
+transaction state, and the syscall can affect the behavior of the transaction.
+
+If the processor is in suspended state when a syscall is made, the syscall
+will be performed as normal, and will return as normal. The syscall will be
+performed in suspended state, so its side effects will be persistent according
+to the usual transactional memory semantics. A syscall may or may not result
+in the transaction being doomed by hardware.
+
+If the processor is in transactional state when a syscall is made, then the
+behavior depends on the presence of PPC_FEATURE2_HTM_NOSC in the AT_HWCAP2 ELF
+auxiliary vector.
+
+- If present, which is the case for newer kernels, then the syscall will not
+ be performed and the transaction will be doomed by the kernel with the
+ failure code TM_CAUSE_SYSCALL | TM_CAUSE_PERSISTENT in the TEXASR SPR.
+
+- If not present (older kernels), then the kernel will suspend the
+ transactional state and the syscall will proceed as in the case of a
+ suspended state syscall, and will resume the transactional state before
+ returning to the caller. This case is not well defined or supported, so this
+ behavior should not be relied upon.
+
+
+vsyscall
+========
+
+vsyscall calling sequence matches the syscall calling sequence, with the
+following differences. Some vsyscalls may have different calling sequences.
+
+Parameters and return value
+---------------------------
+r0 is not used as an input. The vsyscall is selected by its address.
+
+Stack
+-----
+The vsyscall may or may not use the caller's stack frame save areas.
+
+Register preservation rules
+---------------------------
+
+=========== ========
+r0 Volatile
+cr1, cr5-7 Volatile
+lr Volatile
+=========== ========
+
+Invocation
+----------
+The vsyscall is performed with a branch-with-link instruction to the vsyscall
+function address.
+
+Transactional Memory
+--------------------
+vsyscalls will run in the same transactional state as the caller. A vsyscall
+may or may not result in the transaction being doomed by hardware.
+++ /dev/null
-===============================================
-Power Architecture 64-bit Linux system call ABI
-===============================================
-
-syscall
-=======
-
-syscall calling sequence[*] matches the Power Architecture 64-bit ELF ABI
-specification C function calling sequence, including register preservation
-rules, with the following differences.
-
-[*] Some syscalls (typically low-level management functions) may have
- different calling sequences (e.g., rt_sigreturn).
-
-Parameters and return value
----------------------------
-The system call number is specified in r0.
-
-There is a maximum of 6 integer parameters to a syscall, passed in r3-r8.
-
-Both a return value and a return error code are returned. cr0.SO is the return
-error code, and r3 is the return value or error code. When cr0.SO is clear,
-the syscall succeeded and r3 is the return value. When cr0.SO is set, the
-syscall failed and r3 is the error code that generally corresponds to errno.
-
-Stack
------
-System calls do not modify the caller's stack frame. For example, the caller's
-stack frame LR and CR save fields are not used.
-
-Register preservation rules
----------------------------
-Register preservation rules match the ELF ABI calling sequence with the
-following differences:
-
-r0: Volatile. (System call number.)
-r3: Volatile. (Parameter 1, and return value.)
-r4-r8: Volatile. (Parameters 2-6.)
-cr0: Volatile (cr0.SO is the return error condition)
-cr1, cr5-7: Nonvolatile.
-lr: Nonvolatile.
-
-All floating point and vector data registers as well as control and status
-registers are nonvolatile.
-
-Invocation
-----------
-The syscall is performed with the sc instruction, and returns with execution
-continuing at the instruction following the sc instruction.
-
-Transactional Memory
---------------------
-Syscall behavior can change if the processor is in transactional or suspended
-transaction state, and the syscall can affect the behavior of the transaction.
-
-If the processor is in suspended state when a syscall is made, the syscall
-will be performed as normal, and will return as normal. The syscall will be
-performed in suspended state, so its side effects will be persistent according
-to the usual transactional memory semantics. A syscall may or may not result
-in the transaction being doomed by hardware.
-
-If the processor is in transactional state when a syscall is made, then the
-behavior depends on the presence of PPC_FEATURE2_HTM_NOSC in the AT_HWCAP2 ELF
-auxiliary vector.
-
-- If present, which is the case for newer kernels, then the syscall will not
- be performed and the transaction will be doomed by the kernel with the
- failure code TM_CAUSE_SYSCALL | TM_CAUSE_PERSISTENT in the TEXASR SPR.
-
-- If not present (older kernels), then the kernel will suspend the
- transactional state and the syscall will proceed as in the case of a
- suspended state syscall, and will resume the transactional state before
- returning to the caller. This case is not well defined or supported, so this
- behavior should not be relied upon.
-
-
-vsyscall
-========
-
-vsyscall calling sequence matches the syscall calling sequence, with the
-following differences. Some vsyscalls may have different calling sequences.
-
-Parameters and return value
----------------------------
-r0 is not used as an input. The vsyscall is selected by its address.
-
-Stack
------
-The vsyscall may or may not use the caller's stack frame save areas.
-
-Register preservation rules
----------------------------
-r0: Volatile.
-cr1, cr5-7: Volatile.
-lr: Volatile.
-
-Invocation
-----------
-The vsyscall is performed with a branch-with-link instruction to the vsyscall
-function address.
-
-Transactional Memory
---------------------
-vsyscalls will run in the same transactional state as the caller. A vsyscall
-may or may not result in the transaction being doomed by hardware.
--- /dev/null
+============================
+Transactional Memory support
+============================
+
+POWER kernel support for this feature is currently limited to supporting
+its use by user programs. It is not currently used by the kernel itself.
+
+This file aims to sum up how it is supported by Linux and what behaviour you
+can expect from your user programs.
+
+
+Basic overview
+==============
+
+Hardware Transactional Memory is supported on POWER8 processors, and is a
+feature that enables a different form of atomic memory access. Several new
+instructions are presented to delimit transactions; transactions are
+guaranteed to either complete atomically or roll back and undo any partial
+changes.
+
+A simple transaction looks like this::
+
+ begin_move_money:
+ tbegin
+ beq abort_handler
+
+ ld r4, SAVINGS_ACCT(r3)
+ ld r5, CURRENT_ACCT(r3)
+ subi r5, r5, 1
+ addi r4, r4, 1
+ std r4, SAVINGS_ACCT(r3)
+ std r5, CURRENT_ACCT(r3)
+
+ tend
+
+ b continue
+
+ abort_handler:
+ ... test for odd failures ...
+
+ /* Retry the transaction if it failed because it conflicted with
+ * someone else: */
+ b begin_move_money
+
+
+The 'tbegin' instruction denotes the start point, and 'tend' the end point.
+Between these points the processor is in 'Transactional' state; any memory
+references will complete in one go if there are no conflicts with other
+transactional or non-transactional accesses within the system. In this
+example, the transaction completes as though it were normal straight-line code
+IF no other processor has touched SAVINGS_ACCT(r3) or CURRENT_ACCT(r3); an
+atomic move of money from the current account to the savings account has been
+performed. Even though the normal ld/std instructions are used (note no
+lwarx/stwcx), either *both* SAVINGS_ACCT(r3) and CURRENT_ACCT(r3) will be
+updated, or neither will be updated.
+
+If, in the meantime, there is a conflict with the locations accessed by the
+transaction, the transaction will be aborted by the CPU. Register and memory
+state will roll back to that at the 'tbegin', and control will continue from
+'tbegin+4'. The branch to abort_handler will be taken this second time; the
+abort handler can check the cause of the failure, and retry.
+
+Checkpointed registers include all GPRs, FPRs, VRs/VSRs, LR, CCR/CR, CTR, FPCSR
+and a few other status/flag regs; see the ISA for details.
+
+Causes of transaction aborts
+============================
+
+- Conflicts with cache lines used by other processors
+- Signals
+- Context switches
+- See the ISA for full documentation of everything that will abort transactions.
+
+
+Syscalls
+========
+
+Syscalls made from within an active transaction will not be performed and the
+transaction will be doomed by the kernel with the failure code TM_CAUSE_SYSCALL
+| TM_CAUSE_PERSISTENT.
+
+Syscalls made from within a suspended transaction are performed as normal and
+the transaction is not explicitly doomed by the kernel. However, what the
+kernel does to perform the syscall may result in the transaction being doomed
+by the hardware. The syscall is performed in suspended mode so any side
+effects will be persistent, independent of transaction success or failure. No
+guarantees are provided by the kernel about which syscalls will affect
+transaction success.
+
+Care must be taken when relying on syscalls to abort during active transactions
+if the calls are made via a library. Libraries may cache values (which may
+give the appearance of success) or perform operations that cause transaction
+failure before entering the kernel (which may produce different failure codes).
+Examples are glibc's getpid() and lazy symbol resolution.
+
+
+Signals
+=======
+
+Delivery of signals (both sync and async) during transactions provides a second
+thread state (ucontext/mcontext) to represent the second transactional register
+state. Signal delivery 'treclaim's to capture both register states, so signals
+abort transactions. The usual ucontext_t passed to the signal handler
+represents the checkpointed/original register state; the signal appears to have
+arisen at 'tbegin+4'.
+
+If the sighandler ucontext has uc_link set, a second ucontext has been
+delivered. For future compatibility the MSR.TS field should be checked to
+determine the transactional state -- if so, the second ucontext in uc->uc_link
+represents the active transactional registers at the point of the signal.
+
+For 64-bit processes, uc->uc_mcontext.regs->msr is a full 64-bit MSR and its TS
+field shows the transactional mode.
+
+For 32-bit processes, the mcontext's MSR register is only 32 bits; the top 32
+bits are stored in the MSR of the second ucontext, i.e. in
+uc->uc_link->uc_mcontext.regs->msr. The top word contains the transactional
+state TS.
+
+However, basic signal handlers don't need to be aware of transactions
+and simply returning from the handler will deal with things correctly:
+
+Transaction-aware signal handlers can read the transactional register state
+from the second ucontext. This will be necessary for crash handlers to
+determine, for example, the address of the instruction causing the SIGSEGV.
+
+Example signal handler::
+
+ void crash_handler(int sig, siginfo_t *si, void *uc)
+ {
+ ucontext_t *ucp = uc;
+ ucontext_t *transactional_ucp = ucp->uc_link;
+
+ if (ucp_link) {
+ u64 msr = ucp->uc_mcontext.regs->msr;
+ /* May have transactional ucontext! */
+ #ifndef __powerpc64__
+ msr |= ((u64)transactional_ucp->uc_mcontext.regs->msr) << 32;
+ #endif
+ if (MSR_TM_ACTIVE(msr)) {
+ /* Yes, we crashed during a transaction. Oops. */
+ fprintf(stderr, "Transaction to be restarted at 0x%llx, but "
+ "crashy instruction was at 0x%llx\n",
+ ucp->uc_mcontext.regs->nip,
+ transactional_ucp->uc_mcontext.regs->nip);
+ }
+ }
+
+ fix_the_problem(ucp->dar);
+ }
+
+When in an active transaction that takes a signal, we need to be careful with
+the stack. It's possible that the stack has moved back up after the tbegin.
+The obvious case here is when the tbegin is called inside a function that
+returns before a tend. In this case, the stack is part of the checkpointed
+transactional memory state. If we write over this non transactionally or in
+suspend, we are in trouble because if we get a tm abort, the program counter and
+stack pointer will be back at the tbegin but our in memory stack won't be valid
+anymore.
+
+To avoid this, when taking a signal in an active transaction, we need to use
+the stack pointer from the checkpointed state, rather than the speculated
+state. This ensures that the signal context (written tm suspended) will be
+written below the stack required for the rollback. The transaction is aborted
+because of the treclaim, so any memory written between the tbegin and the
+signal will be rolled back anyway.
+
+For signals taken in non-TM or suspended mode, we use the
+normal/non-checkpointed stack pointer.
+
+Any transaction initiated inside a sighandler and suspended on return
+from the sighandler to the kernel will get reclaimed and discarded.
+
+Failure cause codes used by kernel
+==================================
+
+These are defined in <asm/reg.h>, and distinguish different reasons why the
+kernel aborted a transaction:
+
+ ====================== ================================
+ TM_CAUSE_RESCHED Thread was rescheduled.
+ TM_CAUSE_TLBI Software TLB invalid.
+ TM_CAUSE_FAC_UNAV FP/VEC/VSX unavailable trap.
+ TM_CAUSE_SYSCALL Syscall from active transaction.
+ TM_CAUSE_SIGNAL Signal delivered.
+ TM_CAUSE_MISC Currently unused.
+ TM_CAUSE_ALIGNMENT Alignment fault.
+ TM_CAUSE_EMULATE Emulation that touched memory.
+ ====================== ================================
+
+These can be checked by the user program's abort handler as TEXASR[0:7]. If
+bit 7 is set, it indicates that the error is consider persistent. For example
+a TM_CAUSE_ALIGNMENT will be persistent while a TM_CAUSE_RESCHED will not.
+
+GDB
+===
+
+GDB and ptrace are not currently TM-aware. If one stops during a transaction,
+it looks like the transaction has just started (the checkpointed state is
+presented). The transaction cannot then be continued and will take the failure
+handler route. Furthermore, the transactional 2nd register state will be
+inaccessible. GDB can currently be used on programs using TM, but not sensibly
+in parts within transactions.
+
+POWER9
+======
+
+TM on POWER9 has issues with storing the complete register state. This
+is described in this commit::
+
+ commit 4bb3c7a0208fc13ca70598efd109901a7cd45ae7
+ Author: Paul Mackerras <paulus@ozlabs.org>
+ Date: Wed Mar 21 21:32:01 2018 +1100
+ KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9
+
+To account for this different POWER9 chips have TM enabled in
+different ways.
+
+On POWER9N DD2.01 and below, TM is disabled. ie
+HWCAP2[PPC_FEATURE2_HTM] is not set.
+
+On POWER9N DD2.1 TM is configured by firmware to always abort a
+transaction when tm suspend occurs. So tsuspend will cause a
+transaction to be aborted and rolled back. Kernel exceptions will also
+cause the transaction to be aborted and rolled back and the exception
+will not occur. If userspace constructs a sigcontext that enables TM
+suspend, the sigcontext will be rejected by the kernel. This mode is
+advertised to users with HWCAP2[PPC_FEATURE2_HTM_NO_SUSPEND] set.
+HWCAP2[PPC_FEATURE2_HTM] is not set in this mode.
+
+On POWER9N DD2.2 and above, KVM and POWERVM emulate TM for guests (as
+described in commit 4bb3c7a0208f), hence TM is enabled for guests
+ie. HWCAP2[PPC_FEATURE2_HTM] is set for guest userspace. Guests that
+makes heavy use of TM suspend (tsuspend or kernel suspend) will result
+in traps into the hypervisor and hence will suffer a performance
+degradation. Host userspace has TM disabled
+ie. HWCAP2[PPC_FEATURE2_HTM] is not set. (although we make enable it
+at some point in the future if we bring the emulation into host
+userspace context switching).
+
+POWER9C DD1.2 and above are only available with POWERVM and hence
+Linux only runs as a guest. On these systems TM is emulated like on
+POWER9N DD2.2.
+
+Guest migration from POWER8 to POWER9 will work with POWER9N DD2.2 and
+POWER9C DD1.2. Since earlier POWER9 processors don't support TM
+emulation, migration from POWER8 to POWER9 is not supported there.
+++ /dev/null
-Transactional Memory support
-============================
-
-POWER kernel support for this feature is currently limited to supporting
-its use by user programs. It is not currently used by the kernel itself.
-
-This file aims to sum up how it is supported by Linux and what behaviour you
-can expect from your user programs.
-
-
-Basic overview
-==============
-
-Hardware Transactional Memory is supported on POWER8 processors, and is a
-feature that enables a different form of atomic memory access. Several new
-instructions are presented to delimit transactions; transactions are
-guaranteed to either complete atomically or roll back and undo any partial
-changes.
-
-A simple transaction looks like this:
-
-begin_move_money:
- tbegin
- beq abort_handler
-
- ld r4, SAVINGS_ACCT(r3)
- ld r5, CURRENT_ACCT(r3)
- subi r5, r5, 1
- addi r4, r4, 1
- std r4, SAVINGS_ACCT(r3)
- std r5, CURRENT_ACCT(r3)
-
- tend
-
- b continue
-
-abort_handler:
- ... test for odd failures ...
-
- /* Retry the transaction if it failed because it conflicted with
- * someone else: */
- b begin_move_money
-
-
-The 'tbegin' instruction denotes the start point, and 'tend' the end point.
-Between these points the processor is in 'Transactional' state; any memory
-references will complete in one go if there are no conflicts with other
-transactional or non-transactional accesses within the system. In this
-example, the transaction completes as though it were normal straight-line code
-IF no other processor has touched SAVINGS_ACCT(r3) or CURRENT_ACCT(r3); an
-atomic move of money from the current account to the savings account has been
-performed. Even though the normal ld/std instructions are used (note no
-lwarx/stwcx), either *both* SAVINGS_ACCT(r3) and CURRENT_ACCT(r3) will be
-updated, or neither will be updated.
-
-If, in the meantime, there is a conflict with the locations accessed by the
-transaction, the transaction will be aborted by the CPU. Register and memory
-state will roll back to that at the 'tbegin', and control will continue from
-'tbegin+4'. The branch to abort_handler will be taken this second time; the
-abort handler can check the cause of the failure, and retry.
-
-Checkpointed registers include all GPRs, FPRs, VRs/VSRs, LR, CCR/CR, CTR, FPCSR
-and a few other status/flag regs; see the ISA for details.
-
-Causes of transaction aborts
-============================
-
-- Conflicts with cache lines used by other processors
-- Signals
-- Context switches
-- See the ISA for full documentation of everything that will abort transactions.
-
-
-Syscalls
-========
-
-Syscalls made from within an active transaction will not be performed and the
-transaction will be doomed by the kernel with the failure code TM_CAUSE_SYSCALL
-| TM_CAUSE_PERSISTENT.
-
-Syscalls made from within a suspended transaction are performed as normal and
-the transaction is not explicitly doomed by the kernel. However, what the
-kernel does to perform the syscall may result in the transaction being doomed
-by the hardware. The syscall is performed in suspended mode so any side
-effects will be persistent, independent of transaction success or failure. No
-guarantees are provided by the kernel about which syscalls will affect
-transaction success.
-
-Care must be taken when relying on syscalls to abort during active transactions
-if the calls are made via a library. Libraries may cache values (which may
-give the appearance of success) or perform operations that cause transaction
-failure before entering the kernel (which may produce different failure codes).
-Examples are glibc's getpid() and lazy symbol resolution.
-
-
-Signals
-=======
-
-Delivery of signals (both sync and async) during transactions provides a second
-thread state (ucontext/mcontext) to represent the second transactional register
-state. Signal delivery 'treclaim's to capture both register states, so signals
-abort transactions. The usual ucontext_t passed to the signal handler
-represents the checkpointed/original register state; the signal appears to have
-arisen at 'tbegin+4'.
-
-If the sighandler ucontext has uc_link set, a second ucontext has been
-delivered. For future compatibility the MSR.TS field should be checked to
-determine the transactional state -- if so, the second ucontext in uc->uc_link
-represents the active transactional registers at the point of the signal.
-
-For 64-bit processes, uc->uc_mcontext.regs->msr is a full 64-bit MSR and its TS
-field shows the transactional mode.
-
-For 32-bit processes, the mcontext's MSR register is only 32 bits; the top 32
-bits are stored in the MSR of the second ucontext, i.e. in
-uc->uc_link->uc_mcontext.regs->msr. The top word contains the transactional
-state TS.
-
-However, basic signal handlers don't need to be aware of transactions
-and simply returning from the handler will deal with things correctly:
-
-Transaction-aware signal handlers can read the transactional register state
-from the second ucontext. This will be necessary for crash handlers to
-determine, for example, the address of the instruction causing the SIGSEGV.
-
-Example signal handler:
-
- void crash_handler(int sig, siginfo_t *si, void *uc)
- {
- ucontext_t *ucp = uc;
- ucontext_t *transactional_ucp = ucp->uc_link;
-
- if (ucp_link) {
- u64 msr = ucp->uc_mcontext.regs->msr;
- /* May have transactional ucontext! */
-#ifndef __powerpc64__
- msr |= ((u64)transactional_ucp->uc_mcontext.regs->msr) << 32;
-#endif
- if (MSR_TM_ACTIVE(msr)) {
- /* Yes, we crashed during a transaction. Oops. */
- fprintf(stderr, "Transaction to be restarted at 0x%llx, but "
- "crashy instruction was at 0x%llx\n",
- ucp->uc_mcontext.regs->nip,
- transactional_ucp->uc_mcontext.regs->nip);
- }
- }
-
- fix_the_problem(ucp->dar);
- }
-
-When in an active transaction that takes a signal, we need to be careful with
-the stack. It's possible that the stack has moved back up after the tbegin.
-The obvious case here is when the tbegin is called inside a function that
-returns before a tend. In this case, the stack is part of the checkpointed
-transactional memory state. If we write over this non transactionally or in
-suspend, we are in trouble because if we get a tm abort, the program counter and
-stack pointer will be back at the tbegin but our in memory stack won't be valid
-anymore.
-
-To avoid this, when taking a signal in an active transaction, we need to use
-the stack pointer from the checkpointed state, rather than the speculated
-state. This ensures that the signal context (written tm suspended) will be
-written below the stack required for the rollback. The transaction is aborted
-because of the treclaim, so any memory written between the tbegin and the
-signal will be rolled back anyway.
-
-For signals taken in non-TM or suspended mode, we use the
-normal/non-checkpointed stack pointer.
-
-Any transaction initiated inside a sighandler and suspended on return
-from the sighandler to the kernel will get reclaimed and discarded.
-
-Failure cause codes used by kernel
-==================================
-
-These are defined in <asm/reg.h>, and distinguish different reasons why the
-kernel aborted a transaction:
-
- TM_CAUSE_RESCHED Thread was rescheduled.
- TM_CAUSE_TLBI Software TLB invalid.
- TM_CAUSE_FAC_UNAV FP/VEC/VSX unavailable trap.
- TM_CAUSE_SYSCALL Syscall from active transaction.
- TM_CAUSE_SIGNAL Signal delivered.
- TM_CAUSE_MISC Currently unused.
- TM_CAUSE_ALIGNMENT Alignment fault.
- TM_CAUSE_EMULATE Emulation that touched memory.
-
-These can be checked by the user program's abort handler as TEXASR[0:7]. If
-bit 7 is set, it indicates that the error is consider persistent. For example
-a TM_CAUSE_ALIGNMENT will be persistent while a TM_CAUSE_RESCHED will not.
-
-GDB
-===
-
-GDB and ptrace are not currently TM-aware. If one stops during a transaction,
-it looks like the transaction has just started (the checkpointed state is
-presented). The transaction cannot then be continued and will take the failure
-handler route. Furthermore, the transactional 2nd register state will be
-inaccessible. GDB can currently be used on programs using TM, but not sensibly
-in parts within transactions.
-
-POWER9
-======
-
-TM on POWER9 has issues with storing the complete register state. This
-is described in this commit:
-
- commit 4bb3c7a0208fc13ca70598efd109901a7cd45ae7
- Author: Paul Mackerras <paulus@ozlabs.org>
- Date: Wed Mar 21 21:32:01 2018 +1100
- KVM: PPC: Book3S HV: Work around transactional memory bugs in POWER9
-
-To account for this different POWER9 chips have TM enabled in
-different ways.
-
-On POWER9N DD2.01 and below, TM is disabled. ie
-HWCAP2[PPC_FEATURE2_HTM] is not set.
-
-On POWER9N DD2.1 TM is configured by firmware to always abort a
-transaction when tm suspend occurs. So tsuspend will cause a
-transaction to be aborted and rolled back. Kernel exceptions will also
-cause the transaction to be aborted and rolled back and the exception
-will not occur. If userspace constructs a sigcontext that enables TM
-suspend, the sigcontext will be rejected by the kernel. This mode is
-advertised to users with HWCAP2[PPC_FEATURE2_HTM_NO_SUSPEND] set.
-HWCAP2[PPC_FEATURE2_HTM] is not set in this mode.
-
-On POWER9N DD2.2 and above, KVM and POWERVM emulate TM for guests (as
-described in commit 4bb3c7a0208f), hence TM is enabled for guests
-ie. HWCAP2[PPC_FEATURE2_HTM] is set for guest userspace. Guests that
-makes heavy use of TM suspend (tsuspend or kernel suspend) will result
-in traps into the hypervisor and hence will suffer a performance
-degradation. Host userspace has TM disabled
-ie. HWCAP2[PPC_FEATURE2_HTM] is not set. (although we make enable it
-at some point in the future if we bring the emulation into host
-userspace context switching).
-
-POWER9C DD1.2 and above are only available with POWERVM and hence
-Linux only runs as a guest. On these systems TM is emulated like on
-POWER9N DD2.2.
-
-Guest migration from POWER8 to POWER9 will work with POWER9N DD2.2 and
-POWER9C DD1.2. Since earlier POWER9 processors don't support TM
-emulation, migration from POWER8 to POWER9 is not supported there.
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = 'Linux Kernel Development Documentation'
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'process.tex', 'Linux Kernel Development Documentation',
- 'The kernel development community', 'manual'),
-]
lead to a crash, possible overwriting sensitive contents at the end of the
stack (when built without `CONFIG_THREAD_INFO_IN_TASK=y`), or overwriting
memory adjacent to the stack (when built without `CONFIG_VMAP_STACK=y`)
+
+Implicit switch case fall-through
+---------------------------------
+The C language allows switch cases to "fall through" when
+a "break" statement is missing at the end of a case. This,
+however, introduces ambiguity in the code, as it's not always
+clear if the missing break is intentional or a bug. As there
+have been a long list of flaws `due to missing "break" statements
+<https://cwe.mitre.org/data/definitions/484.html>`_, we no longer allow
+"implicit fall-through". In order to identify an intentional fall-through
+case, we have adopted the marking used by static analyzers: a comment
+saying `/* Fall through */`. Once the C++17 `__attribute__((fallthrough))`
+is more widely handled by C compilers, static analyzers, and IDEs, we can
+switch to using that instead.
--- /dev/null
+Embargoed hardware issues
+=========================
+
+Scope
+-----
+
+Hardware issues which result in security problems are a different category
+of security bugs than pure software bugs which only affect the Linux
+kernel.
+
+Hardware issues like Meltdown, Spectre, L1TF etc. must be treated
+differently because they usually affect all Operating Systems ("OS") and
+therefore need coordination across different OS vendors, distributions,
+hardware vendors and other parties. For some of the issues, software
+mitigations can depend on microcode or firmware updates, which need further
+coordination.
+
+.. _Contact:
+
+Contact
+-------
+
+The Linux kernel hardware security team is separate from the regular Linux
+kernel security team.
+
+The team only handles the coordination of embargoed hardware security
+issues. Reports of pure software security bugs in the Linux kernel are not
+handled by this team and the reporter will be guided to contact the regular
+Linux kernel security team (:ref:`Documentation/admin-guide/
+<securitybugs>`) instead.
+
+The team can be contacted by email at <hardware-security@kernel.org>. This
+is a private list of security officers who will help you to coordinate an
+issue according to our documented process.
+
+The list is encrypted and email to the list can be sent by either PGP or
+S/MIME encrypted and must be signed with the reporter's PGP key or S/MIME
+certificate. The list's PGP key and S/MIME certificate are available from
+https://www.kernel.org/....
+
+While hardware security issues are often handled by the affected hardware
+vendor, we welcome contact from researchers or individuals who have
+identified a potential hardware flaw.
+
+Hardware security officers
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The current team of hardware security officers:
+
+ - Linus Torvalds (Linux Foundation Fellow)
+ - Greg Kroah-Hartman (Linux Foundation Fellow)
+ - Thomas Gleixner (Linux Foundation Fellow)
+
+Operation of mailing-lists
+^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The encrypted mailing-lists which are used in our process are hosted on
+Linux Foundation's IT infrastructure. By providing this service Linux
+Foundation's director of IT Infrastructure security technically has the
+ability to access the embargoed information, but is obliged to
+confidentiality by his employment contract. Linux Foundation's director of
+IT Infrastructure security is also responsible for the kernel.org
+infrastructure.
+
+The Linux Foundation's current director of IT Infrastructure security is
+Konstantin Ryabitsev.
+
+
+Non-disclosure agreements
+-------------------------
+
+The Linux kernel hardware security team is not a formal body and therefore
+unable to enter into any non-disclosure agreements. The kernel community
+is aware of the sensitive nature of such issues and offers a Memorandum of
+Understanding instead.
+
+
+Memorandum of Understanding
+---------------------------
+
+The Linux kernel community has a deep understanding of the requirement to
+keep hardware security issues under embargo for coordination between
+different OS vendors, distributors, hardware vendors and other parties.
+
+The Linux kernel community has successfully handled hardware security
+issues in the past and has the necessary mechanisms in place to allow
+community compliant development under embargo restrictions.
+
+The Linux kernel community has a dedicated hardware security team for
+initial contact, which oversees the process of handling such issues under
+embargo rules.
+
+The hardware security team identifies the developers (domain experts) who
+will form the initial response team for a particular issue. The initial
+response team can bring in further developers (domain experts) to address
+the issue in the best technical way.
+
+All involved developers pledge to adhere to the embargo rules and to keep
+the received information confidential. Violation of the pledge will lead to
+immediate exclusion from the current issue and removal from all related
+mailing-lists. In addition, the hardware security team will also exclude
+the offender from future issues. The impact of this consequence is a highly
+effective deterrent in our community. In case a violation happens the
+hardware security team will inform the involved parties immediately. If you
+or anyone becomes aware of a potential violation, please report it
+immediately to the Hardware security officers.
+
+
+Process
+^^^^^^^
+
+Due to the globally distributed nature of Linux kernel development,
+face-to-face meetings are almost impossible to address hardware security
+issues. Phone conferences are hard to coordinate due to time zones and
+other factors and should be only used when absolutely necessary. Encrypted
+email has been proven to be the most effective and secure communication
+method for these types of issues.
+
+Start of Disclosure
+"""""""""""""""""""
+
+Disclosure starts by contacting the Linux kernel hardware security team by
+email. This initial contact should contain a description of the problem and
+a list of any known affected hardware. If your organization builds or
+distributes the affected hardware, we encourage you to also consider what
+other hardware could be affected.
+
+The hardware security team will provide an incident-specific encrypted
+mailing-list which will be used for initial discussion with the reporter,
+further disclosure and coordination.
+
+The hardware security team will provide the disclosing party a list of
+developers (domain experts) who should be informed initially about the
+issue after confirming with the developers that they will adhere to this
+Memorandum of Understanding and the documented process. These developers
+form the initial response team and will be responsible for handling the
+issue after initial contact. The hardware security team is supporting the
+response team, but is not necessarily involved in the mitigation
+development process.
+
+While individual developers might be covered by a non-disclosure agreement
+via their employer, they cannot enter individual non-disclosure agreements
+in their role as Linux kernel developers. They will, however, agree to
+adhere to this documented process and the Memorandum of Understanding.
+
+
+Disclosure
+""""""""""
+
+The disclosing party provides detailed information to the initial response
+team via the specific encrypted mailing-list.
+
+From our experience the technical documentation of these issues is usually
+a sufficient starting point and further technical clarification is best
+done via email.
+
+Mitigation development
+""""""""""""""""""""""
+
+The initial response team sets up an encrypted mailing-list or repurposes
+an existing one if appropriate. The disclosing party should provide a list
+of contacts for all other parties who have already been, or should be,
+informed about the issue. The response team contacts these parties so they
+can name experts who should be subscribed to the mailing-list.
+
+Using a mailing-list is close to the normal Linux development process and
+has been successfully used in developing mitigations for various hardware
+security issues in the past.
+
+The mailing-list operates in the same way as normal Linux development.
+Patches are posted, discussed and reviewed and if agreed on applied to a
+non-public git repository which is only accessible to the participating
+developers via a secure connection. The repository contains the main
+development branch against the mainline kernel and backport branches for
+stable kernel versions as necessary.
+
+The initial response team will identify further experts from the Linux
+kernel developer community as needed and inform the disclosing party about
+their participation. Bringing in experts can happen at any time of the
+development process and often needs to be handled in a timely manner.
+
+Coordinated release
+"""""""""""""""""""
+
+The involved parties will negotiate the date and time where the embargo
+ends. At that point the prepared mitigations are integrated into the
+relevant kernel trees and published.
+
+While we understand that hardware security issues need coordinated embargo
+time, the embargo time should be constrained to the minimum time which is
+required for all involved parties to develop, test and prepare the
+mitigations. Extending embargo time artificially to meet conference talk
+dates or other non-technical reasons is creating more work and burden for
+the involved developers and response teams as the patches need to be kept
+up to date in order to follow the ongoing upstream kernel development,
+which might create conflicting changes.
+
+CVE assignment
+""""""""""""""
+
+Neither the hardware security team nor the initial response team assign
+CVEs, nor are CVEs required for the development process. If CVEs are
+provided by the disclosing party they can be used for documentation
+purposes.
+
+Process ambassadors
+-------------------
+
+For assistance with this process we have established ambassadors in various
+organizations, who can answer questions about or provide guidance on the
+reporting process and further handling. Ambassadors are not involved in the
+disclosure of a particular issue, unless requested by a response team or by
+an involved disclosed party. The current ambassadors list:
+
+ ============= ========================================================
+ ARM
+ AMD
+ IBM
+ Intel
+ Qualcomm Trilok Soni <tsoni@codeaurora.org>
+
+ Microsoft Sasha Levin <sashal@kernel.org>
+ VMware
+ Xen Andrew Cooper <andrew.cooper3@citrix.com>
+
+ Canonical Tyler Hicks <tyhicks@canonical.com>
+ Debian Ben Hutchings <ben@decadent.org.uk>
+ Oracle Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+ Red Hat Josh Poimboeuf <jpoimboe@redhat.com>
+ SUSE Jiri Kosina <jkosina@suse.cz>
+
+ Amazon
+ Google Kees Cook <keescook@chromium.org>
+ ============= ========================================================
+
+If you want your organization to be added to the ambassadors list, please
+contact the hardware security team. The nominated ambassador has to
+understand and support our process fully and is ideally well connected in
+the Linux kernel community.
+
+Encrypted mailing-lists
+-----------------------
+
+We use encrypted mailing-lists for communication. The operating principle
+of these lists is that email sent to the list is encrypted either with the
+list's PGP key or with the list's S/MIME certificate. The mailing-list
+software decrypts the email and re-encrypts it individually for each
+subscriber with the subscriber's PGP key or S/MIME certificate. Details
+about the mailing-list software and the setup which is used to ensure the
+security of the lists and protection of the data can be found here:
+https://www.kernel.org/....
+
+List keys
+^^^^^^^^^
+
+For initial contact see :ref:`Contact`. For incident specific mailing-lists
+the key and S/MIME certificate are conveyed to the subscribers by email
+sent from the specific list.
+
+Subscription to incident specific lists
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Subscription is handled by the response teams. Disclosed parties who want
+to participate in the communication send a list of potential subscribers to
+the response team so the response team can validate subscription requests.
+
+Each subscriber needs to send a subscription request to the response team
+by email. The email must be signed with the subscriber's PGP key or S/MIME
+certificate. If a PGP key is used, it must be available from a public key
+server and is ideally connected to the Linux kernel's PGP web of trust. See
+also: https://www.kernel.org/signature.html.
+
+The response team verifies that the subscriber request is valid and adds
+the subscriber to the list. After subscription the subscriber will receive
+email from the mailing-list which is signed either with the list's PGP key
+or the list's S/MIME certificate. The subscriber's email client can extract
+the PGP key or the S/MIME certificate from the signature so the subscriber
+can send encrypted email to the list.
+
submit-checklist
kernel-docs
deprecated
+ embargoed-hardware-issues
These are some overall technical guides that have been put here for now for
lack of a better place.
add it to an iommu_group and a vfio_group. Then we could pass through
the mdev to a guest.
+
+VFIO-CCW Regions
+----------------
+
+The vfio-ccw driver exposes MMIO regions to accept requests from and return
+results to userspace.
+
vfio-ccw I/O region
-------------------
ret_code stores a return code for each access of the region.
+This region is always available.
+
+vfio-ccw cmd region
+-------------------
+
+The vfio-ccw cmd region is used to accept asynchronous instructions
+from userspace::
+
+ #define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0)
+ #define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1)
+ struct ccw_cmd_region {
+ __u32 command;
+ __u32 ret_code;
+ } __packed;
+
+This region is exposed via region type VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD.
+
+Currently, CLEAR SUBCHANNEL and HALT SUBCHANNEL use this region.
+
vfio-ccw operation details
--------------------------
through DASD/ECKD device online in a guest now and use it as a block
device.
-While the current code allows the guest to start channel programs via
-START SUBCHANNEL, support for HALT SUBCHANNEL or CLEAR SUBCHANNEL is
-not yet implemented.
+The current code allows the guest to start channel programs via
+START SUBCHANNEL, and to issue HALT SUBCHANNEL and CLEAR SUBCHANNEL.
vfio-ccw supports classic (command mode) channel I/O only. Transport
mode (HPF) is not supported.
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "SuperH architecture implementation manual"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'sh.tex', project,
- 'The kernel development community', 'manual'),
-]
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Linux Sound Subsystem Documentation"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'sound.tex', project,
- 'The kernel development community', 'manual'),
-]
and os.path.normpath(namespace["__file__"]) != os.path.normpath(config_file) ):
config_file = os.path.abspath(config_file)
+ # Let's avoid one conf.py file just due to latex_documents
+ start = config_file.find('Documentation/')
+ if start >= 0:
+ start = config_file.find('/', start + 1)
+
+ end = config_file.rfind('/')
+ if start >= 0 and end > 0:
+ dir = config_file[start + 1:end]
+
+ print("source directory: %s" % dir)
+ new_latex_docs = []
+ latex_documents = namespace['latex_documents']
+
+ for l in latex_documents:
+ if l[0].find(dir + '/') == 0:
+ has = True
+ fn = l[0][len(dir) + 1:]
+ new_latex_docs.append((fn, l[1], l[2], l[3], l[4]))
+ break
+
+ namespace['latex_documents'] = new_latex_docs
+
+ # If there is an extra conf.py file, load it
if os.path.isfile(config_file):
sys.stdout.write("load additional sphinx-config: %s\n" % config_file)
config = namespace.copy()
del config['__file__']
namespace.update(config)
else:
- sys.stderr.write("WARNING: additional sphinx-config not found: %s\n" % config_file)
+ config = namespace.copy()
+ config['tags'].add("subproject")
+ namespace.update(config)
* Per inserire blocchi di testo con caratteri a dimensione fissa (codici di
esempio, casi d'uso, eccetera): utilizzate ``::`` quando non è necessario
evidenziare la sintassi, specialmente per piccoli frammenti; invece,
- utilizzate ``.. code-block:: <language>`` per blocchi di più lunghi che
- potranno beneficiare dell'avere la sintassi evidenziata.
+ utilizzate ``.. code-block:: <language>`` per blocchi più lunghi che
+ beneficeranno della sintassi evidenziata. Per un breve pezzo di codice da
+ inserire nel testo, usate \`\`.
Il dominio C
Il nome della funzione (per esempio ioctl) rimane nel testo ma il nome del suo
riferimento cambia da ``ioctl`` a ``VIDIOC_LOG_STATUS``. Anche la voce
-nell'indice cambia in ``VIDIOC_LOG_STATUS`` e si potrà quindi fare riferimento
-a questa funzione scrivendo:
-
-.. code-block:: rst
-
- :c:func:`VIDIOC_LOG_STATUS`
+nell'indice cambia in ``VIDIOC_LOG_STATUS``.
+
+Notate che per una funzione non c'è bisogno di usare ``c:func:`` per generarne
+i riferimenti nella documentazione. Grazie a qualche magica estensione a
+Sphinx, il sistema di generazione della documentazione trasformerà
+automaticamente un riferimento ad una ``funzione()`` in un riferimento
+incrociato quando questa ha una voce nell'indice. Se trovate degli usi di
+``c:func:`` nella documentazione del kernel, sentitevi liberi di rimuoverli.
Tabelle a liste
code-of-conduct
development-process
submitting-patches
+ programming-language
coding-style
maintainer-pgp-guide
email-clients
.. include:: ../disclaimer-ita.rst
:Original: :ref:`Documentation/process/kernel-docs.rst <kernel_docs>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
.. _it_kernel_docs:
Indice di documenti per le persone interessate a capire e/o scrivere per il kernel Linux
========================================================================================
-.. warning::
-
- TODO ancora da tradurre
+.. note::
+ Questo documento contiene riferimenti a documenti in lingua inglese; inoltre
+ utilizza dai campi *ReStructuredText* di supporto alla ricerca e che per
+ questo motivo è meglio non tradurre al fine di garantirne un corretto
+ utilizzo.
+ Per questi motivi il documento non verrà tradotto. Per favore fate
+ riferimento al documento originale in lingua inglese.
kernel.
Se per qualche ragione preferite rimanere con sottochiavi RSA, nel comando
- precedente, sostituite "ed25519" con "rsa2048".
+ precedente, sostituite "ed25519" con "rsa2048". In aggiunta, se avete
+ intenzione di usare un dispositivo hardware che non supporta le chiavi
+ ED25519 ECC, come la Nitrokey Pro o la Yubikey, allora dovreste usare
+ "nistp256" al posto di "ed25519".
Copia di riserva della chiave primaria per gestire il recupero da disastro
--------------------------------------------------------------------------
soluzioni disponibili:
- `Nitrokey Start`_: è Open hardware e Free Software, è basata sul progetto
- `GnuK`_ della FSIJ. Ha il supporto per chiavi ECC, ma meno funzionalità di
- sicurezza (come la resistenza alla manomissione o alcuni attacchi ad un
- canale laterale).
+ `GnuK`_ della FSIJ. Questo è uno dei pochi dispositivi a supportare le chiavi
+ ECC ED25519, ma offre meno funzionalità di sicurezza (come la resistenza
+ alla manomissione o alcuni attacchi ad un canale laterale).
- `Nitrokey Pro`_: è simile alla Nitrokey Start, ma è più resistente alla
- manomissione e offre più funzionalità di sicurezza, ma l'ECC.
-- `Yubikey 4`_: l'hardware e il software sono proprietari, ma è più economica
+ manomissione e offre più funzionalità di sicurezza. La Pro 2 supporta la
+ crittografia ECC (NISTP).
+- `Yubikey 5`_: l'hardware e il software sono proprietari, ma è più economica
della Nitrokey Pro ed è venduta anche con porta USB-C il che è utile con i
computer portatili più recenti. In aggiunta, offre altre funzionalità di
- sicurezza come FIDO, U2F, ma non l'ECC
+ sicurezza come FIDO, U2F, e ora supporta anche le chiavi ECC (NISTP)
`Su LWN c'è una buona recensione`_ dei modelli elencati qui sopra e altri.
+La scelta dipenderà dal costo, dalla disponibilità nella vostra area
+geografica e vostre considerazioni sull'hardware aperto/proprietario.
+
Se volete usare chiavi ECC, la vostra migliore scelta sul mercato è la
Nitrokey Start.
.. _`Nitrokey Start`: https://shop.nitrokey.com/shop/product/nitrokey-start-6
-.. _`Nitrokey Pro`: https://shop.nitrokey.com/shop/product/nitrokey-pro-3
-.. _`Yubikey 4`: https://www.yubico.com/product/yubikey-4-series/
+.. _`Nitrokey Pro 2`: https://shop.nitrokey.com/shop/product/nitrokey-pro-2-3
+.. _`Yubikey 5`: https://www.yubico.com/product/yubikey-5-overview/
.. _Gnuk: http://www.fsij.org/doc-gnuk/
.. _`Su LWN c'è una buona recensione`: https://lwn.net/Articles/736231/
--- /dev/null
+.. include:: ../disclaimer-ita.rst
+
+:Original: :ref:`Documentation/process/programming-language.rst <programming_language>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_programming_language:
+
+Linguaggio di programmazione
+============================
+
+Il kernel è scritto nel linguaggio di programmazione C [c-language]_.
+Più precisamente, il kernel viene compilato con ``gcc`` [gcc]_ usando
+l'opzione ``-std=gnu89`` [gcc-c-dialect-options]_: il dialetto GNU
+dello standard ISO C90 (con l'aggiunta di alcune funzionalità da C99)
+
+Questo dialetto contiene diverse estensioni al linguaggio [gnu-extensions]_,
+e molte di queste vengono usate sistematicamente dal kernel.
+
+Il kernel offre un certo livello di supporto per la compilazione con ``clang``
+[clang]_ e ``icc`` [icc]_ su diverse architetture, tuttavia in questo momento
+il supporto non è completo e richiede delle patch aggiuntive.
+
+Attributi
+---------
+
+Una delle estensioni più comuni e usate nel kernel sono gli attributi
+[gcc-attribute-syntax]_. Gli attributi permettono di aggiungere una semantica,
+definita dell'implementazione, alle entità del linguaggio (come le variabili,
+le funzioni o i tipi) senza dover fare importanti modifiche sintattiche al
+linguaggio stesso (come l'aggiunta di nuove parole chiave) [n2049]_.
+
+In alcuni casi, gli attributi sono opzionali (ovvero un compilatore che non
+dovesse supportarli dovrebbe produrre comunque codice corretto, anche se
+più lento o che non esegue controlli aggiuntivi durante la compilazione).
+
+Il kernel definisce alcune pseudo parole chiave (per esempio ``__pure``)
+in alternativa alla sintassi GNU per gli attributi (per esempio
+``__attribute__((__pure__))``) allo scopo di mostrare quali funzionalità si
+possono usare e/o per accorciare il codice.
+
+Per maggiori informazioni consultate il file d'intestazione
+``include/linux/compiler_attributes.h``.
+
+.. [c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards
+.. [gcc] https://gcc.gnu.org
+.. [clang] https://clang.llvm.org
+.. [icc] https://software.intel.com/en-us/c-compilers
+.. [gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html
+.. [gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html
+.. [gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html
+.. [n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf
[*] 버스 마스터링 DMA 와 일관성에 대해서는 다음을 참고하시기 바랍니다:
- Documentation/PCI/pci.rst
+ Documentation/driver-api/pci/pci.rst
Documentation/DMA-API-HOWTO.txt
Documentation/DMA-API.txt
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "The Linux kernel user-space API guide"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'userspace-api.tex', project,
- 'The kernel development community', 'manual'),
-]
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+============================
+Linux Virtualization Support
+============================
+
+.. toctree::
+ :maxdepth: 2
+
+ kvm/index
+ paravirt_ops
+
+.. only:: html and subproject
+
+ Indices
+ =======
+
+ * :ref:`genindex`
--- /dev/null
+======================================
+Secure Encrypted Virtualization (SEV)
+======================================
+
+Overview
+========
+
+Secure Encrypted Virtualization (SEV) is a feature found on AMD processors.
+
+SEV is an extension to the AMD-V architecture which supports running
+virtual machines (VMs) under the control of a hypervisor. When enabled,
+the memory contents of a VM will be transparently encrypted with a key
+unique to that VM.
+
+The hypervisor can determine the SEV support through the CPUID
+instruction. The CPUID function 0x8000001f reports information related
+to SEV::
+
+ 0x8000001f[eax]:
+ Bit[1] indicates support for SEV
+ ...
+ [ecx]:
+ Bits[31:0] Number of encrypted guests supported simultaneously
+
+If support for SEV is present, MSR 0xc001_0010 (MSR_K8_SYSCFG) and MSR 0xc001_0015
+(MSR_K7_HWCR) can be used to determine if it can be enabled::
+
+ 0xc001_0010:
+ Bit[23] 1 = memory encryption can be enabled
+ 0 = memory encryption can not be enabled
+
+ 0xc001_0015:
+ Bit[0] 1 = memory encryption can be enabled
+ 0 = memory encryption can not be enabled
+
+When SEV support is available, it can be enabled in a specific VM by
+setting the SEV bit before executing VMRUN.::
+
+ VMCB[0x90]:
+ Bit[1] 1 = SEV is enabled
+ 0 = SEV is disabled
+
+SEV hardware uses ASIDs to associate a memory encryption key with a VM.
+Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value
+defined in the CPUID 0x8000001f[ecx] field.
+
+SEV Key Management
+==================
+
+The SEV guest key management is handled by a separate processor called the AMD
+Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure
+key management interface to perform common hypervisor activities such as
+encrypting bootstrap code, snapshot, migrating and debugging the guest. For more
+information, see the SEV Key Management spec [api-spec]_
+
+KVM implements the following commands to support common lifecycle events of SEV
+guests, such as launching, running, snapshotting, migrating and decommissioning.
+
+1. KVM_SEV_INIT
+---------------
+
+The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform
+context. In a typical workflow, this command should be the first command issued.
+
+Returns: 0 on success, -negative on error
+
+2. KVM_SEV_LAUNCH_START
+-----------------------
+
+The KVM_SEV_LAUNCH_START command is used for creating the memory encryption
+context. To create the encryption context, user must provide a guest policy,
+the owner's public Diffie-Hellman (PDH) key and session information.
+
+Parameters: struct kvm_sev_launch_start (in/out)
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_start {
+ __u32 handle; /* if zero then firmware creates a new handle */
+ __u32 policy; /* guest's policy */
+
+ __u64 dh_uaddr; /* userspace address pointing to the guest owner's PDH key */
+ __u32 dh_len;
+
+ __u64 session_addr; /* userspace address which points to the guest session information */
+ __u32 session_len;
+ };
+
+On success, the 'handle' field contains a new handle and on error, a negative value.
+
+For more details, see SEV spec Section 6.2.
+
+3. KVM_SEV_LAUNCH_UPDATE_DATA
+-----------------------------
+
+The KVM_SEV_LAUNCH_UPDATE_DATA is used for encrypting a memory region. It also
+calculates a measurement of the memory contents. The measurement is a signature
+of the memory contents that can be sent to the guest owner as an attestation
+that the memory was encrypted correctly by the firmware.
+
+Parameters (in): struct kvm_sev_launch_update_data
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_update {
+ __u64 uaddr; /* userspace address to be encrypted (must be 16-byte aligned) */
+ __u32 len; /* length of the data to be encrypted (must be 16-byte aligned) */
+ };
+
+For more details, see SEV spec Section 6.3.
+
+4. KVM_SEV_LAUNCH_MEASURE
+-------------------------
+
+The KVM_SEV_LAUNCH_MEASURE command is used to retrieve the measurement of the
+data encrypted by the KVM_SEV_LAUNCH_UPDATE_DATA command. The guest owner may
+wait to provide the guest with confidential information until it can verify the
+measurement. Since the guest owner knows the initial contents of the guest at
+boot, the measurement can be verified by comparing it to what the guest owner
+expects.
+
+Parameters (in): struct kvm_sev_launch_measure
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_measure {
+ __u64 uaddr; /* where to copy the measurement */
+ __u32 len; /* length of measurement blob */
+ };
+
+For more details on the measurement verification flow, see SEV spec Section 6.4.
+
+5. KVM_SEV_LAUNCH_FINISH
+------------------------
+
+After completion of the launch flow, the KVM_SEV_LAUNCH_FINISH command can be
+issued to make the guest ready for the execution.
+
+Returns: 0 on success, -negative on error
+
+6. KVM_SEV_GUEST_STATUS
+-----------------------
+
+The KVM_SEV_GUEST_STATUS command is used to retrieve status information about a
+SEV-enabled guest.
+
+Parameters (out): struct kvm_sev_guest_status
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_guest_status {
+ __u32 handle; /* guest handle */
+ __u32 policy; /* guest policy */
+ __u8 state; /* guest state (see enum below) */
+ };
+
+SEV guest state:
+
+::
+
+ enum {
+ SEV_STATE_INVALID = 0;
+ SEV_STATE_LAUNCHING, /* guest is currently being launched */
+ SEV_STATE_SECRET, /* guest is being launched and ready to accept the ciphertext data */
+ SEV_STATE_RUNNING, /* guest is fully launched and running */
+ SEV_STATE_RECEIVING, /* guest is being migrated in from another SEV machine */
+ SEV_STATE_SENDING /* guest is getting migrated out to another SEV machine */
+ };
+
+7. KVM_SEV_DBG_DECRYPT
+----------------------
+
+The KVM_SEV_DEBUG_DECRYPT command can be used by the hypervisor to request the
+firmware to decrypt the data at the given memory region.
+
+Parameters (in): struct kvm_sev_dbg
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_dbg {
+ __u64 src_uaddr; /* userspace address of data to decrypt */
+ __u64 dst_uaddr; /* userspace address of destination */
+ __u32 len; /* length of memory region to decrypt */
+ };
+
+The command returns an error if the guest policy does not allow debugging.
+
+8. KVM_SEV_DBG_ENCRYPT
+----------------------
+
+The KVM_SEV_DEBUG_ENCRYPT command can be used by the hypervisor to request the
+firmware to encrypt the data at the given memory region.
+
+Parameters (in): struct kvm_sev_dbg
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_dbg {
+ __u64 src_uaddr; /* userspace address of data to encrypt */
+ __u64 dst_uaddr; /* userspace address of destination */
+ __u32 len; /* length of memory region to encrypt */
+ };
+
+The command returns an error if the guest policy does not allow debugging.
+
+9. KVM_SEV_LAUNCH_SECRET
+------------------------
+
+The KVM_SEV_LAUNCH_SECRET command can be used by the hypervisor to inject secret
+data after the measurement has been validated by the guest owner.
+
+Parameters (in): struct kvm_sev_launch_secret
+
+Returns: 0 on success, -negative on error
+
+::
+
+ struct kvm_sev_launch_secret {
+ __u64 hdr_uaddr; /* userspace address containing the packet header */
+ __u32 hdr_len;
+
+ __u64 guest_uaddr; /* the guest memory region where the secret should be injected */
+ __u32 guest_len;
+
+ __u64 trans_uaddr; /* the hypervisor memory region which contains the secret */
+ __u32 trans_len;
+ };
+
+References
+==========
+
+
+See [white-paper]_, [api-spec]_, [amd-apm]_ and [kvm-forum]_ for more info.
+
+.. [white-paper] http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf
+.. [api-spec] http://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf
+.. [amd-apm] http://support.amd.com/TechDocs/24593.pdf (section 15.34)
+.. [kvm-forum] http://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf
--- /dev/null
+The Definitive KVM (Kernel-based Virtual Machine) API Documentation
+===================================================================
+
+1. General description
+----------------------
+
+The kvm API is a set of ioctls that are issued to control various aspects
+of a virtual machine. The ioctls belong to three classes:
+
+ - System ioctls: These query and set global attributes which affect the
+ whole kvm subsystem. In addition a system ioctl is used to create
+ virtual machines.
+
+ - VM ioctls: These query and set attributes that affect an entire virtual
+ machine, for example memory layout. In addition a VM ioctl is used to
+ create virtual cpus (vcpus) and devices.
+
+ VM ioctls must be issued from the same process (address space) that was
+ used to create the VM.
+
+ - vcpu ioctls: These query and set attributes that control the operation
+ of a single virtual cpu.
+
+ vcpu ioctls should be issued from the same thread that was used to create
+ the vcpu, except for asynchronous vcpu ioctl that are marked as such in
+ the documentation. Otherwise, the first ioctl after switching threads
+ could see a performance impact.
+
+ - device ioctls: These query and set attributes that control the operation
+ of a single device.
+
+ device ioctls must be issued from the same process (address space) that
+ was used to create the VM.
+
+2. File descriptors
+-------------------
+
+The kvm API is centered around file descriptors. An initial
+open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
+can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this
+handle will create a VM file descriptor which can be used to issue VM
+ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will
+create a virtual cpu or device and return a file descriptor pointing to
+the new resource. Finally, ioctls on a vcpu or device fd can be used
+to control the vcpu or device. For vcpus, this includes the important
+task of actually running guest code.
+
+In general file descriptors can be migrated among processes by means
+of fork() and the SCM_RIGHTS facility of unix domain socket. These
+kinds of tricks are explicitly not supported by kvm. While they will
+not cause harm to the host, their actual behavior is not guaranteed by
+the API. See "General description" for details on the ioctl usage
+model that is supported by KVM.
+
+It is important to note that althought VM ioctls may only be issued from
+the process that created the VM, a VM's lifecycle is associated with its
+file descriptor, not its creator (process). In other words, the VM and
+its resources, *including the associated address space*, are not freed
+until the last reference to the VM's file descriptor has been released.
+For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will
+not be freed until both the parent (original) process and its child have
+put their references to the VM's file descriptor.
+
+Because a VM's resources are not freed until the last reference to its
+file descriptor is released, creating additional references to a VM via
+via fork(), dup(), etc... without careful consideration is strongly
+discouraged and may have unwanted side effects, e.g. memory allocated
+by and on behalf of the VM's process may not be freed/unaccounted when
+the VM is shut down.
+
+
+3. Extensions
+-------------
+
+As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
+incompatible change are allowed. However, there is an extension
+facility that allows backward-compatible extensions to the API to be
+queried and used.
+
+The extension mechanism is not based on the Linux version number.
+Instead, kvm defines extension identifiers and a facility to query
+whether a particular extension identifier is available. If it is, a
+set of ioctls is available for application use.
+
+
+4. API description
+------------------
+
+This section describes ioctls that can be used to control kvm guests.
+For each ioctl, the following information is provided along with a
+description:
+
+ Capability: which KVM extension provides this ioctl. Can be 'basic',
+ which means that is will be provided by any kernel that supports
+ API version 12 (see section 4.1), a KVM_CAP_xyz constant, which
+ means availability needs to be checked with KVM_CHECK_EXTENSION
+ (see section 4.4), or 'none' which means that while not all kernels
+ support this ioctl, there's no capability bit to check its
+ availability: for kernels that don't support the ioctl,
+ the ioctl returns -ENOTTY.
+
+ Architectures: which instruction set architectures provide this ioctl.
+ x86 includes both i386 and x86_64.
+
+ Type: system, vm, or vcpu.
+
+ Parameters: what parameters are accepted by the ioctl.
+
+ Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
+ are not detailed, but errors with specific meanings are.
+
+
+4.1 KVM_GET_API_VERSION
+
+Capability: basic
+Architectures: all
+Type: system ioctl
+Parameters: none
+Returns: the constant KVM_API_VERSION (=12)
+
+This identifies the API version as the stable kvm API. It is not
+expected that this number will change. However, Linux 2.6.20 and
+2.6.21 report earlier versions; these are not documented and not
+supported. Applications should refuse to run if KVM_GET_API_VERSION
+returns a value other than 12. If this check passes, all ioctls
+described as 'basic' will be available.
+
+
+4.2 KVM_CREATE_VM
+
+Capability: basic
+Architectures: all
+Type: system ioctl
+Parameters: machine type identifier (KVM_VM_*)
+Returns: a VM fd that can be used to control the new virtual machine.
+
+The new VM has no virtual cpus and no memory.
+You probably want to use 0 as machine type.
+
+In order to create user controlled virtual machines on S390, check
+KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
+privileged user (CAP_SYS_ADMIN).
+
+To use hardware assisted virtualization on MIPS (VZ ASE) rather than
+the default trap & emulate implementation (which changes the virtual
+memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
+flag KVM_VM_MIPS_VZ.
+
+
+On arm64, the physical address size for a VM (IPA Size limit) is limited
+to 40bits by default. The limit can be configured if the host supports the
+extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
+KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type
+identifier, where IPA_Bits is the maximum width of any physical
+address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
+machine type identifier.
+
+e.g, to configure a guest to use 48bit physical address size :
+
+ vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48));
+
+The requested size (IPA_Bits) must be :
+ 0 - Implies default size, 40bits (for backward compatibility)
+
+ or
+
+ N - Implies N bits, where N is a positive integer such that,
+ 32 <= N <= Host_IPA_Limit
+
+Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and
+is dependent on the CPU capability and the kernel configuration. The limit can
+be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
+ioctl() at run-time.
+
+Please note that configuring the IPA size does not affect the capability
+exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
+size of the address translated by the stage2 level (guest physical to
+host physical address translations).
+
+
+4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
+
+Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_msr_list (in/out)
+Returns: 0 on success; -1 on error
+Errors:
+ EFAULT: the msr index list cannot be read from or written to
+ E2BIG: the msr index list is to be to fit in the array specified by
+ the user.
+
+struct kvm_msr_list {
+ __u32 nmsrs; /* number of msrs in entries */
+ __u32 indices[0];
+};
+
+The user fills in the size of the indices array in nmsrs, and in return
+kvm adjusts nmsrs to reflect the actual number of msrs and fills in the
+indices array with their numbers.
+
+KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported. The list
+varies by kvm version and host processor, but does not change otherwise.
+
+Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
+not returned in the MSR list, as different vcpus can have a different number
+of banks, as set via the KVM_X86_SETUP_MCE ioctl.
+
+KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed
+to the KVM_GET_MSRS system ioctl. This lets userspace probe host capabilities
+and processor features that are exposed via MSRs (e.g., VMX capabilities).
+This list also varies by kvm version and host processor, but does not change
+otherwise.
+
+
+4.4 KVM_CHECK_EXTENSION
+
+Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
+Architectures: all
+Type: system ioctl, vm ioctl
+Parameters: extension identifier (KVM_CAP_*)
+Returns: 0 if unsupported; 1 (or some other positive integer) if supported
+
+The API allows the application to query about extensions to the core
+kvm API. Userspace passes an extension identifier (an integer) and
+receives an integer that describes the extension availability.
+Generally 0 means no and 1 means yes, but some extensions may report
+additional information in the integer return value.
+
+Based on their initialization different VMs may have different capabilities.
+It is thus encouraged to use the vm ioctl to query for capabilities (available
+with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
+
+4.5 KVM_GET_VCPU_MMAP_SIZE
+
+Capability: basic
+Architectures: all
+Type: system ioctl
+Parameters: none
+Returns: size of vcpu mmap area, in bytes
+
+The KVM_RUN ioctl (cf.) communicates with userspace via a shared
+memory region. This ioctl returns the size of that region. See the
+KVM_RUN documentation for details.
+
+
+4.6 KVM_SET_MEMORY_REGION
+
+Capability: basic
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_memory_region (in)
+Returns: 0 on success, -1 on error
+
+This ioctl is obsolete and has been removed.
+
+
+4.7 KVM_CREATE_VCPU
+
+Capability: basic
+Architectures: all
+Type: vm ioctl
+Parameters: vcpu id (apic id on x86)
+Returns: vcpu fd on success, -1 on error
+
+This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
+The vcpu id is an integer in the range [0, max_vcpu_id).
+
+The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
+the KVM_CHECK_EXTENSION ioctl() at run-time.
+The maximum possible value for max_vcpus can be retrieved using the
+KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
+
+If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
+cpus max.
+If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
+same as the value returned from KVM_CAP_NR_VCPUS.
+
+The maximum possible value for max_vcpu_id can be retrieved using the
+KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.
+
+If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id
+is the same as the value returned from KVM_CAP_MAX_VCPUS.
+
+On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
+threads in one or more virtual CPU cores. (This is because the
+hardware requires all the hardware threads in a CPU core to be in the
+same partition.) The KVM_CAP_PPC_SMT capability indicates the number
+of vcpus per virtual core (vcore). The vcore id is obtained by
+dividing the vcpu id by the number of vcpus per vcore. The vcpus in a
+given vcore will always be in the same physical core as each other
+(though that might be a different physical core from time to time).
+Userspace can control the threading (SMT) mode of the guest by its
+allocation of vcpu ids. For example, if userspace wants
+single-threaded guest vcpus, it should make all vcpu ids be a multiple
+of the number of vcpus per vcore.
+
+For virtual cpus that have been created with S390 user controlled virtual
+machines, the resulting vcpu fd can be memory mapped at page offset
+KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
+cpu's hardware control block.
+
+
+4.8 KVM_GET_DIRTY_LOG (vm ioctl)
+
+Capability: basic
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_dirty_log (in/out)
+Returns: 0 on success, -1 on error
+
+/* for KVM_GET_DIRTY_LOG */
+struct kvm_dirty_log {
+ __u32 slot;
+ __u32 padding;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding;
+ };
+};
+
+Given a memory slot, return a bitmap containing any pages dirtied
+since the last call to this ioctl. Bit 0 is the first page in the
+memory slot. Ensure the entire structure is cleared to avoid padding
+issues.
+
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
+the address space for which you want to return the dirty bitmap.
+They must be less than the value that KVM_CHECK_EXTENSION returns for
+the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+
+The bits in the dirty bitmap are cleared before the ioctl returns, unless
+KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information,
+see the description of the capability.
+
+4.9 KVM_SET_MEMORY_ALIAS
+
+Capability: basic
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_memory_alias (in)
+Returns: 0 (success), -1 (error)
+
+This ioctl is obsolete and has been removed.
+
+
+4.10 KVM_RUN
+
+Capability: basic
+Architectures: all
+Type: vcpu ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+Errors:
+ EINTR: an unmasked signal is pending
+
+This ioctl is used to run a guest virtual cpu. While there are no
+explicit parameters, there is an implicit parameter block that can be
+obtained by mmap()ing the vcpu fd at offset 0, with the size given by
+KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct
+kvm_run' (see below).
+
+
+4.11 KVM_GET_REGS
+
+Capability: basic
+Architectures: all except ARM, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_regs (out)
+Returns: 0 on success, -1 on error
+
+Reads the general purpose registers from the vcpu.
+
+/* x86 */
+struct kvm_regs {
+ /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+ __u64 rax, rbx, rcx, rdx;
+ __u64 rsi, rdi, rsp, rbp;
+ __u64 r8, r9, r10, r11;
+ __u64 r12, r13, r14, r15;
+ __u64 rip, rflags;
+};
+
+/* mips */
+struct kvm_regs {
+ /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+ __u64 gpr[32];
+ __u64 hi;
+ __u64 lo;
+ __u64 pc;
+};
+
+
+4.12 KVM_SET_REGS
+
+Capability: basic
+Architectures: all except ARM, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_regs (in)
+Returns: 0 on success, -1 on error
+
+Writes the general purpose registers into the vcpu.
+
+See KVM_GET_REGS for the data structure.
+
+
+4.13 KVM_GET_SREGS
+
+Capability: basic
+Architectures: x86, ppc
+Type: vcpu ioctl
+Parameters: struct kvm_sregs (out)
+Returns: 0 on success, -1 on error
+
+Reads special registers from the vcpu.
+
+/* x86 */
+struct kvm_sregs {
+ struct kvm_segment cs, ds, es, fs, gs, ss;
+ struct kvm_segment tr, ldt;
+ struct kvm_dtable gdt, idt;
+ __u64 cr0, cr2, cr3, cr4, cr8;
+ __u64 efer;
+ __u64 apic_base;
+ __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
+};
+
+/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
+
+interrupt_bitmap is a bitmap of pending external interrupts. At most
+one bit may be set. This interrupt has been acknowledged by the APIC
+but not yet injected into the cpu core.
+
+
+4.14 KVM_SET_SREGS
+
+Capability: basic
+Architectures: x86, ppc
+Type: vcpu ioctl
+Parameters: struct kvm_sregs (in)
+Returns: 0 on success, -1 on error
+
+Writes special registers into the vcpu. See KVM_GET_SREGS for the
+data structures.
+
+
+4.15 KVM_TRANSLATE
+
+Capability: basic
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_translation (in/out)
+Returns: 0 on success, -1 on error
+
+Translates a virtual address according to the vcpu's current address
+translation mode.
+
+struct kvm_translation {
+ /* in */
+ __u64 linear_address;
+
+ /* out */
+ __u64 physical_address;
+ __u8 valid;
+ __u8 writeable;
+ __u8 usermode;
+ __u8 pad[5];
+};
+
+
+4.16 KVM_INTERRUPT
+
+Capability: basic
+Architectures: x86, ppc, mips
+Type: vcpu ioctl
+Parameters: struct kvm_interrupt (in)
+Returns: 0 on success, negative on failure.
+
+Queues a hardware interrupt vector to be injected.
+
+/* for KVM_INTERRUPT */
+struct kvm_interrupt {
+ /* in */
+ __u32 irq;
+};
+
+X86:
+
+Returns: 0 on success,
+ -EEXIST if an interrupt is already enqueued
+ -EINVAL the the irq number is invalid
+ -ENXIO if the PIC is in the kernel
+ -EFAULT if the pointer is invalid
+
+Note 'irq' is an interrupt vector, not an interrupt pin or line. This
+ioctl is useful if the in-kernel PIC is not used.
+
+PPC:
+
+Queues an external interrupt to be injected. This ioctl is overleaded
+with 3 different irq values:
+
+a) KVM_INTERRUPT_SET
+
+ This injects an edge type external interrupt into the guest once it's ready
+ to receive interrupts. When injected, the interrupt is done.
+
+b) KVM_INTERRUPT_UNSET
+
+ This unsets any pending interrupt.
+
+ Only available with KVM_CAP_PPC_UNSET_IRQ.
+
+c) KVM_INTERRUPT_SET_LEVEL
+
+ This injects a level type external interrupt into the guest context. The
+ interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
+ is triggered.
+
+ Only available with KVM_CAP_PPC_IRQ_LEVEL.
+
+Note that any value for 'irq' other than the ones stated above is invalid
+and incurs unexpected behavior.
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
+MIPS:
+
+Queues an external interrupt to be injected into the virtual CPU. A negative
+interrupt number dequeues the interrupt.
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
+
+4.17 KVM_DEBUG_GUEST
+
+Capability: basic
+Architectures: none
+Type: vcpu ioctl
+Parameters: none)
+Returns: -1 on error
+
+Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead.
+
+
+4.18 KVM_GET_MSRS
+
+Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
+Architectures: x86
+Type: system ioctl, vcpu ioctl
+Parameters: struct kvm_msrs (in/out)
+Returns: number of msrs successfully returned;
+ -1 on error
+
+When used as a system ioctl:
+Reads the values of MSR-based features that are available for the VM. This
+is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values.
+The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST
+in a system ioctl.
+
+When used as a vcpu ioctl:
+Reads model-specific registers from the vcpu. Supported msr indices can
+be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl.
+
+struct kvm_msrs {
+ __u32 nmsrs; /* number of msrs in entries */
+ __u32 pad;
+
+ struct kvm_msr_entry entries[0];
+};
+
+struct kvm_msr_entry {
+ __u32 index;
+ __u32 reserved;
+ __u64 data;
+};
+
+Application code should set the 'nmsrs' member (which indicates the
+size of the entries array) and the 'index' member of each array entry.
+kvm will fill in the 'data' member.
+
+
+4.19 KVM_SET_MSRS
+
+Capability: basic
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_msrs (in)
+Returns: 0 on success, -1 on error
+
+Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the
+data structures.
+
+Application code should set the 'nmsrs' member (which indicates the
+size of the entries array), and the 'index' and 'data' members of each
+array entry.
+
+
+4.20 KVM_SET_CPUID
+
+Capability: basic
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_cpuid (in)
+Returns: 0 on success, -1 on error
+
+Defines the vcpu responses to the cpuid instruction. Applications
+should use the KVM_SET_CPUID2 ioctl if available.
+
+
+struct kvm_cpuid_entry {
+ __u32 function;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding;
+};
+
+/* for KVM_SET_CPUID */
+struct kvm_cpuid {
+ __u32 nent;
+ __u32 padding;
+ struct kvm_cpuid_entry entries[0];
+};
+
+
+4.21 KVM_SET_SIGNAL_MASK
+
+Capability: basic
+Architectures: all
+Type: vcpu ioctl
+Parameters: struct kvm_signal_mask (in)
+Returns: 0 on success, -1 on error
+
+Defines which signals are blocked during execution of KVM_RUN. This
+signal mask temporarily overrides the threads signal mask. Any
+unblocked signal received (except SIGKILL and SIGSTOP, which retain
+their traditional behaviour) will cause KVM_RUN to return with -EINTR.
+
+Note the signal will only be delivered if not blocked by the original
+signal mask.
+
+/* for KVM_SET_SIGNAL_MASK */
+struct kvm_signal_mask {
+ __u32 len;
+ __u8 sigset[0];
+};
+
+
+4.22 KVM_GET_FPU
+
+Capability: basic
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_fpu (out)
+Returns: 0 on success, -1 on error
+
+Reads the floating point state from the vcpu.
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+ __u8 fpr[8][16];
+ __u16 fcw;
+ __u16 fsw;
+ __u8 ftwx; /* in fxsave format */
+ __u8 pad1;
+ __u16 last_opcode;
+ __u64 last_ip;
+ __u64 last_dp;
+ __u8 xmm[16][16];
+ __u32 mxcsr;
+ __u32 pad2;
+};
+
+
+4.23 KVM_SET_FPU
+
+Capability: basic
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_fpu (in)
+Returns: 0 on success, -1 on error
+
+Writes the floating point state to the vcpu.
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+ __u8 fpr[8][16];
+ __u16 fcw;
+ __u16 fsw;
+ __u8 ftwx; /* in fxsave format */
+ __u8 pad1;
+ __u16 last_opcode;
+ __u64 last_ip;
+ __u64 last_dp;
+ __u8 xmm[16][16];
+ __u32 mxcsr;
+ __u32 pad2;
+};
+
+
+4.24 KVM_CREATE_IRQCHIP
+
+Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
+Architectures: x86, ARM, arm64, s390
+Type: vm ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+
+Creates an interrupt controller model in the kernel.
+On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
+future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both
+PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
+On ARM/arm64, a GICv2 is created. Any other GIC versions require the usage of
+KVM_CREATE_DEVICE, which also supports creating a GICv2. Using
+KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2.
+On s390, a dummy irq routing table is created.
+
+Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
+before KVM_CREATE_IRQCHIP can be used.
+
+
+4.25 KVM_IRQ_LINE
+
+Capability: KVM_CAP_IRQCHIP
+Architectures: x86, arm, arm64
+Type: vm ioctl
+Parameters: struct kvm_irq_level
+Returns: 0 on success, -1 on error
+
+Sets the level of a GSI input to the interrupt controller model in the kernel.
+On some architectures it is required that an interrupt controller model has
+been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
+interrupts require the level to be set to 1 and then back to 0.
+
+On real hardware, interrupt pins can be active-low or active-high. This
+does not matter for the level field of struct kvm_irq_level: 1 always
+means active (asserted), 0 means inactive (deasserted).
+
+x86 allows the operating system to program the interrupt polarity
+(active-low/active-high) for level-triggered interrupts, and KVM used
+to consider the polarity. However, due to bitrot in the handling of
+active-low interrupts, the above convention is now valid on x86 too.
+This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED. Userspace
+should not present interrupts to the guest as active-low unless this
+capability is present (or unless it is not using the in-kernel irqchip,
+of course).
+
+
+ARM/arm64 can signal an interrupt either at the CPU level, or at the
+in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
+use PPIs designated for specific cpus. The irq field is interpreted
+like this:
+
+ bits: | 31 ... 24 | 23 ... 16 | 15 ... 0 |
+ field: | irq_type | vcpu_index | irq_id |
+
+The irq_type field has the following values:
+- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
+- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
+ (the vcpu_index field is ignored)
+- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
+
+(The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
+
+In both cases, level is used to assert/deassert the line.
+
+struct kvm_irq_level {
+ union {
+ __u32 irq; /* GSI */
+ __s32 status; /* not used for KVM_IRQ_LEVEL */
+ };
+ __u32 level; /* 0 or 1 */
+};
+
+
+4.26 KVM_GET_IRQCHIP
+
+Capability: KVM_CAP_IRQCHIP
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_irqchip (in/out)
+Returns: 0 on success, -1 on error
+
+Reads the state of a kernel interrupt controller created with
+KVM_CREATE_IRQCHIP into a buffer provided by the caller.
+
+struct kvm_irqchip {
+ __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
+ __u32 pad;
+ union {
+ char dummy[512]; /* reserving space */
+ struct kvm_pic_state pic;
+ struct kvm_ioapic_state ioapic;
+ } chip;
+};
+
+
+4.27 KVM_SET_IRQCHIP
+
+Capability: KVM_CAP_IRQCHIP
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_irqchip (in)
+Returns: 0 on success, -1 on error
+
+Sets the state of a kernel interrupt controller created with
+KVM_CREATE_IRQCHIP from a buffer provided by the caller.
+
+struct kvm_irqchip {
+ __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
+ __u32 pad;
+ union {
+ char dummy[512]; /* reserving space */
+ struct kvm_pic_state pic;
+ struct kvm_ioapic_state ioapic;
+ } chip;
+};
+
+
+4.28 KVM_XEN_HVM_CONFIG
+
+Capability: KVM_CAP_XEN_HVM
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_xen_hvm_config (in)
+Returns: 0 on success, -1 on error
+
+Sets the MSR that the Xen HVM guest uses to initialize its hypercall
+page, and provides the starting address and size of the hypercall
+blobs in userspace. When the guest writes the MSR, kvm copies one
+page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
+memory.
+
+struct kvm_xen_hvm_config {
+ __u32 flags;
+ __u32 msr;
+ __u64 blob_addr_32;
+ __u64 blob_addr_64;
+ __u8 blob_size_32;
+ __u8 blob_size_64;
+ __u8 pad2[30];
+};
+
+
+4.29 KVM_GET_CLOCK
+
+Capability: KVM_CAP_ADJUST_CLOCK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_clock_data (out)
+Returns: 0 on success, -1 on error
+
+Gets the current timestamp of kvmclock as seen by the current guest. In
+conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
+such as migration.
+
+When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
+set of bits that KVM can return in struct kvm_clock_data's flag member.
+
+The only flag defined now is KVM_CLOCK_TSC_STABLE. If set, the returned
+value is the exact kvmclock value seen by all VCPUs at the instant
+when KVM_GET_CLOCK was called. If clear, the returned value is simply
+CLOCK_MONOTONIC plus a constant offset; the offset can be modified
+with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock,
+but the exact value read by each VCPU could differ, because the host
+TSC is not stable.
+
+struct kvm_clock_data {
+ __u64 clock; /* kvmclock current value */
+ __u32 flags;
+ __u32 pad[9];
+};
+
+
+4.30 KVM_SET_CLOCK
+
+Capability: KVM_CAP_ADJUST_CLOCK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_clock_data (in)
+Returns: 0 on success, -1 on error
+
+Sets the current timestamp of kvmclock to the value specified in its parameter.
+In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
+such as migration.
+
+struct kvm_clock_data {
+ __u64 clock; /* kvmclock current value */
+ __u32 flags;
+ __u32 pad[9];
+};
+
+
+4.31 KVM_GET_VCPU_EVENTS
+
+Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
+Architectures: x86, arm, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_vcpu_event (out)
+Returns: 0 on success, -1 on error
+
+X86:
+
+Gets currently pending exceptions, interrupts, and NMIs as well as related
+states of the vcpu.
+
+struct kvm_vcpu_events {
+ struct {
+ __u8 injected;
+ __u8 nr;
+ __u8 has_error_code;
+ __u8 pending;
+ __u32 error_code;
+ } exception;
+ struct {
+ __u8 injected;
+ __u8 nr;
+ __u8 soft;
+ __u8 shadow;
+ } interrupt;
+ struct {
+ __u8 injected;
+ __u8 pending;
+ __u8 masked;
+ __u8 pad;
+ } nmi;
+ __u32 sipi_vector;
+ __u32 flags;
+ struct {
+ __u8 smm;
+ __u8 pending;
+ __u8 smm_inside_nmi;
+ __u8 latched_init;
+ } smi;
+ __u8 reserved[27];
+ __u8 exception_has_payload;
+ __u64 exception_payload;
+};
+
+The following bits are defined in the flags field:
+
+- KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
+ interrupt.shadow contains a valid state.
+
+- KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
+ valid state.
+
+- KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
+ exception_has_payload, exception_payload, and exception.pending
+ fields contain a valid state. This bit will be set whenever
+ KVM_CAP_EXCEPTION_PAYLOAD is enabled.
+
+ARM/ARM64:
+
+If the guest accesses a device that is being emulated by the host kernel in
+such a way that a real device would generate a physical SError, KVM may make
+a virtual SError pending for that VCPU. This system error interrupt remains
+pending until the guest takes the exception by unmasking PSTATE.A.
+
+Running the VCPU may cause it to take a pending SError, or make an access that
+causes an SError to become pending. The event's description is only valid while
+the VPCU is not running.
+
+This API provides a way to read and write the pending 'event' state that is not
+visible to the guest. To save, restore or migrate a VCPU the struct representing
+the state can be read then written using this GET/SET API, along with the other
+guest-visible registers. It is not possible to 'cancel' an SError that has been
+made pending.
+
+A device being emulated in user-space may also wish to generate an SError. To do
+this the events structure can be populated by user-space. The current state
+should be read first, to ensure no existing SError is pending. If an existing
+SError is pending, the architecture's 'Multiple SError interrupts' rules should
+be followed. (2.5.3 of DDI0587.a "ARM Reliability, Availability, and
+Serviceability (RAS) Specification").
+
+SError exceptions always have an ESR value. Some CPUs have the ability to
+specify what the virtual SError's ESR value should be. These systems will
+advertise KVM_CAP_ARM_INJECT_SERROR_ESR. In this case exception.has_esr will
+always have a non-zero value when read, and the agent making an SError pending
+should specify the ISS field in the lower 24 bits of exception.serror_esr. If
+the system supports KVM_CAP_ARM_INJECT_SERROR_ESR, but user-space sets the events
+with exception.has_esr as zero, KVM will choose an ESR.
+
+Specifying exception.has_esr on a system that does not support it will return
+-EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
+will return -EINVAL.
+
+struct kvm_vcpu_events {
+ struct {
+ __u8 serror_pending;
+ __u8 serror_has_esr;
+ /* Align it to 8 bytes */
+ __u8 pad[6];
+ __u64 serror_esr;
+ } exception;
+ __u32 reserved[12];
+};
+
+4.32 KVM_SET_VCPU_EVENTS
+
+Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
+Architectures: x86, arm, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_vcpu_event (in)
+Returns: 0 on success, -1 on error
+
+X86:
+
+Set pending exceptions, interrupts, and NMIs as well as related states of the
+vcpu.
+
+See KVM_GET_VCPU_EVENTS for the data structure.
+
+Fields that may be modified asynchronously by running VCPUs can be excluded
+from the update. These fields are nmi.pending, sipi_vector, smi.smm,
+smi.pending. Keep the corresponding bits in the flags field cleared to
+suppress overwriting the current in-kernel state. The bits are:
+
+KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
+KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct.
+
+If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
+the flags field to signal that interrupt.shadow contains a valid state and
+shall be written into the VCPU.
+
+KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
+
+If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD
+can be set in the flags field to signal that the
+exception_has_payload, exception_payload, and exception.pending fields
+contain a valid state and shall be written into the VCPU.
+
+ARM/ARM64:
+
+Set the pending SError exception state for this VCPU. It is not possible to
+'cancel' an Serror that has been made pending.
+
+See KVM_GET_VCPU_EVENTS for the data structure.
+
+
+4.33 KVM_GET_DEBUGREGS
+
+Capability: KVM_CAP_DEBUGREGS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_debugregs (out)
+Returns: 0 on success, -1 on error
+
+Reads debug registers from the vcpu.
+
+struct kvm_debugregs {
+ __u64 db[4];
+ __u64 dr6;
+ __u64 dr7;
+ __u64 flags;
+ __u64 reserved[9];
+};
+
+
+4.34 KVM_SET_DEBUGREGS
+
+Capability: KVM_CAP_DEBUGREGS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_debugregs (in)
+Returns: 0 on success, -1 on error
+
+Writes debug registers into the vcpu.
+
+See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
+yet and must be cleared on entry.
+
+
+4.35 KVM_SET_USER_MEMORY_REGION
+
+Capability: KVM_CAP_USER_MEMORY
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_userspace_memory_region (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_userspace_memory_region {
+ __u32 slot;
+ __u32 flags;
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+ __u64 userspace_addr; /* start of the userspace allocated memory */
+};
+
+/* for kvm_memory_region::flags */
+#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
+#define KVM_MEM_READONLY (1UL << 1)
+
+This ioctl allows the user to create, modify or delete a guest physical
+memory slot. Bits 0-15 of "slot" specify the slot id and this value
+should be less than the maximum number of user memory slots supported per
+VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS.
+Slots may not overlap in guest physical address space.
+
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
+specifies the address space which is being modified. They must be
+less than the value that KVM_CHECK_EXTENSION returns for the
+KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces
+are unrelated; the restriction on overlapping slots only applies within
+each address space.
+
+Deleting a slot is done by passing zero for memory_size. When changing
+an existing slot, it may be moved in the guest physical memory space,
+or its flags may be modified, but it may not be resized.
+
+Memory for the region is taken starting at the address denoted by the
+field userspace_addr, which must point at user addressable memory for
+the entire memory slot size. Any object may back this memory, including
+anonymous memory, ordinary files, and hugetlbfs.
+
+It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
+be identical. This allows large pages in the guest to be backed by large
+pages in the host.
+
+The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
+KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of
+writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to
+use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
+to make a new slot read-only. In this case, writes to this memory will be
+posted to userspace as KVM_EXIT_MMIO exits.
+
+When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
+the memory region are automatically reflected into the guest. For example, an
+mmap() that affects the region will be made visible immediately. Another
+example is madvise(MADV_DROP).
+
+It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
+The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
+allocation and is deprecated.
+
+
+4.36 KVM_SET_TSS_ADDR
+
+Capability: KVM_CAP_SET_TSS_ADDR
+Architectures: x86
+Type: vm ioctl
+Parameters: unsigned long tss_address (in)
+Returns: 0 on success, -1 on error
+
+This ioctl defines the physical address of a three-page region in the guest
+physical address space. The region must be within the first 4GB of the
+guest physical address space and must not conflict with any memory slot
+or any mmio address. The guest may malfunction if it accesses this memory
+region.
+
+This ioctl is required on Intel-based hosts. This is needed on Intel hardware
+because of a quirk in the virtualization implementation (see the internals
+documentation when it pops into existence).
+
+
+4.37 KVM_ENABLE_CAP
+
+Capability: KVM_CAP_ENABLE_CAP
+Architectures: mips, ppc, s390
+Type: vcpu ioctl
+Parameters: struct kvm_enable_cap (in)
+Returns: 0 on success; -1 on error
+
+Capability: KVM_CAP_ENABLE_CAP_VM
+Architectures: all
+Type: vcpu ioctl
+Parameters: struct kvm_enable_cap (in)
+Returns: 0 on success; -1 on error
+
++Not all extensions are enabled by default. Using this ioctl the application
+can enable an extension, making it available to the guest.
+
+On systems that do not support this ioctl, it always fails. On systems that
+do support it, it only works for extensions that are supported for enablement.
+
+To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
+be used.
+
+struct kvm_enable_cap {
+ /* in */
+ __u32 cap;
+
+The capability that is supposed to get enabled.
+
+ __u32 flags;
+
+A bitfield indicating future enhancements. Has to be 0 for now.
+
+ __u64 args[4];
+
+Arguments for enabling a feature. If a feature needs initial values to
+function properly, this is the place to put them.
+
+ __u8 pad[64];
+};
+
+The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
+for vm-wide capabilities.
+
+4.38 KVM_GET_MP_STATE
+
+Capability: KVM_CAP_MP_STATE
+Architectures: x86, s390, arm, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_mp_state (out)
+Returns: 0 on success; -1 on error
+
+struct kvm_mp_state {
+ __u32 mp_state;
+};
+
+Returns the vcpu's current "multiprocessing state" (though also valid on
+uniprocessor guests).
+
+Possible values are:
+
+ - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64]
+ - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP)
+ which has not yet received an INIT signal [x86]
+ - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is
+ now ready for a SIPI [x86]
+ - KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and
+ is waiting for an interrupt [x86]
+ - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector
+ accessible via KVM_GET_VCPU_EVENTS) [x86]
+ - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64]
+ - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390]
+ - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted)
+ [s390]
+ - KVM_MP_STATE_LOAD: the vcpu is in a special load/startup state
+ [s390]
+
+On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
+
+For arm/arm64:
+
+The only states that are valid are KVM_MP_STATE_STOPPED and
+KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
+
+4.39 KVM_SET_MP_STATE
+
+Capability: KVM_CAP_MP_STATE
+Architectures: x86, s390, arm, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_mp_state (in)
+Returns: 0 on success; -1 on error
+
+Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
+arguments.
+
+On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
+in-kernel irqchip, the multiprocessing state must be maintained by userspace on
+these architectures.
+
+For arm/arm64:
+
+The only states that are valid are KVM_MP_STATE_STOPPED and
+KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
+
+4.40 KVM_SET_IDENTITY_MAP_ADDR
+
+Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
+Architectures: x86
+Type: vm ioctl
+Parameters: unsigned long identity (in)
+Returns: 0 on success, -1 on error
+
+This ioctl defines the physical address of a one-page region in the guest
+physical address space. The region must be within the first 4GB of the
+guest physical address space and must not conflict with any memory slot
+or any mmio address. The guest may malfunction if it accesses this memory
+region.
+
+Setting the address to 0 will result in resetting the address to its default
+(0xfffbc000).
+
+This ioctl is required on Intel-based hosts. This is needed on Intel hardware
+because of a quirk in the virtualization implementation (see the internals
+documentation when it pops into existence).
+
+Fails if any VCPU has already been created.
+
+4.41 KVM_SET_BOOT_CPU_ID
+
+Capability: KVM_CAP_SET_BOOT_CPU_ID
+Architectures: x86
+Type: vm ioctl
+Parameters: unsigned long vcpu_id
+Returns: 0 on success, -1 on error
+
+Define which vcpu is the Bootstrap Processor (BSP). Values are the same
+as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default
+is vcpu 0.
+
+
+4.42 KVM_GET_XSAVE
+
+Capability: KVM_CAP_XSAVE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xsave (out)
+Returns: 0 on success, -1 on error
+
+struct kvm_xsave {
+ __u32 region[1024];
+};
+
+This ioctl would copy current vcpu's xsave struct to the userspace.
+
+
+4.43 KVM_SET_XSAVE
+
+Capability: KVM_CAP_XSAVE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xsave (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_xsave {
+ __u32 region[1024];
+};
+
+This ioctl would copy userspace's xsave struct to the kernel.
+
+
+4.44 KVM_GET_XCRS
+
+Capability: KVM_CAP_XCRS
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xcrs (out)
+Returns: 0 on success, -1 on error
+
+struct kvm_xcr {
+ __u32 xcr;
+ __u32 reserved;
+ __u64 value;
+};
+
+struct kvm_xcrs {
+ __u32 nr_xcrs;
+ __u32 flags;
+ struct kvm_xcr xcrs[KVM_MAX_XCRS];
+ __u64 padding[16];
+};
+
+This ioctl would copy current vcpu's xcrs to the userspace.
+
+
+4.45 KVM_SET_XCRS
+
+Capability: KVM_CAP_XCRS
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_xcrs (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_xcr {
+ __u32 xcr;
+ __u32 reserved;
+ __u64 value;
+};
+
+struct kvm_xcrs {
+ __u32 nr_xcrs;
+ __u32 flags;
+ struct kvm_xcr xcrs[KVM_MAX_XCRS];
+ __u64 padding[16];
+};
+
+This ioctl would set vcpu's xcr to the value userspace specified.
+
+
+4.46 KVM_GET_SUPPORTED_CPUID
+
+Capability: KVM_CAP_EXT_CPUID
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+ __u32 nent;
+ __u32 padding;
+ struct kvm_cpuid_entry2 entries[0];
+};
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
+
+struct kvm_cpuid_entry2 {
+ __u32 function;
+ __u32 index;
+ __u32 flags;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features which are supported by both the
+hardware and kvm in its default configuration. Userspace can use the
+information returned by this ioctl to construct cpuid information (for
+KVM_SET_CPUID2) that is consistent with hardware, kernel, and
+userspace capabilities, and with user requirements (for example, the
+user may wish to constrain cpuid to emulate older hardware, or for
+feature consistency across a cluster).
+
+Note that certain capabilities, such as KVM_CAP_X86_DISABLE_EXITS, may
+expose cpuid features (e.g. MONITOR) which are not supported by kvm in
+its default configuration. If userspace enables such capabilities, it
+is responsible for modifying the results of this ioctl appropriately.
+
+Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
+with the 'nent' field indicating the number of entries in the variable-size
+array 'entries'. If the number of entries is too low to describe the cpu
+capabilities, an error (E2BIG) is returned. If the number is too high,
+the 'nent' field is adjusted and an error (ENOMEM) is returned. If the
+number is just right, the 'nent' field is adjusted to the number of valid
+entries in the 'entries' array, which is then filled.
+
+The entries returned are the host cpuid as returned by the cpuid instruction,
+with unknown or unsupported features masked out. Some features (for example,
+x2apic), may not be present in the host cpu, but are exposed by kvm if it can
+emulate them efficiently. The fields in each entry are defined as follows:
+
+ function: the eax value used to obtain the entry
+ index: the ecx value used to obtain the entry (for entries that are
+ affected by ecx)
+ flags: an OR of zero or more of the following:
+ KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
+ if the index field is valid
+ KVM_CPUID_FLAG_STATEFUL_FUNC:
+ if cpuid for this function returns different values for successive
+ invocations; there will be several entries with the same function,
+ all with this flag set
+ KVM_CPUID_FLAG_STATE_READ_NEXT:
+ for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
+ the first entry to be read by a cpu
+ eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+ this function/index combination
+
+The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
+as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
+support. Instead it is reported via
+
+ ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
+
+if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
+feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
+
+
+4.47 KVM_PPC_GET_PVINFO
+
+Capability: KVM_CAP_PPC_GET_PVINFO
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_ppc_pvinfo (out)
+Returns: 0 on success, !0 on error
+
+struct kvm_ppc_pvinfo {
+ __u32 flags;
+ __u32 hcall[4];
+ __u8 pad[108];
+};
+
+This ioctl fetches PV specific information that need to be passed to the guest
+using the device tree or other means from vm context.
+
+The hcall array defines 4 instructions that make up a hypercall.
+
+If any additional field gets added to this structure later on, a bit for that
+additional piece of information will be set in the flags bitmap.
+
+The flags bitmap is defined as:
+
+ /* the host supports the ePAPR idle hcall
+ #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
+4.52 KVM_SET_GSI_ROUTING
+
+Capability: KVM_CAP_IRQ_ROUTING
+Architectures: x86 s390 arm arm64
+Type: vm ioctl
+Parameters: struct kvm_irq_routing (in)
+Returns: 0 on success, -1 on error
+
+Sets the GSI routing table entries, overwriting any previously set entries.
+
+On arm/arm64, GSI routing has the following limitation:
+- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
+
+struct kvm_irq_routing {
+ __u32 nr;
+ __u32 flags;
+ struct kvm_irq_routing_entry entries[0];
+};
+
+No flags are specified so far, the corresponding field must be set to zero.
+
+struct kvm_irq_routing_entry {
+ __u32 gsi;
+ __u32 type;
+ __u32 flags;
+ __u32 pad;
+ union {
+ struct kvm_irq_routing_irqchip irqchip;
+ struct kvm_irq_routing_msi msi;
+ struct kvm_irq_routing_s390_adapter adapter;
+ struct kvm_irq_routing_hv_sint hv_sint;
+ __u32 pad[8];
+ } u;
+};
+
+/* gsi routing entry types */
+#define KVM_IRQ_ROUTING_IRQCHIP 1
+#define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
+#define KVM_IRQ_ROUTING_HV_SINT 4
+
+flags:
+- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
+ type, specifies that the devid field contains a valid value. The per-VM
+ KVM_CAP_MSI_DEVID capability advertises the requirement to provide
+ the device ID. If this capability is not available, userspace should
+ never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
+- zero otherwise
+
+struct kvm_irq_routing_irqchip {
+ __u32 irqchip;
+ __u32 pin;
+};
+
+struct kvm_irq_routing_msi {
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+ union {
+ __u32 pad;
+ __u32 devid;
+ };
+};
+
+If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
+for the device that wrote the MSI message. For PCI, this is usually a
+BFD identifier in the lower 16 bits.
+
+On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
+feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
+address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
+address_hi must be zero.
+
+struct kvm_irq_routing_s390_adapter {
+ __u64 ind_addr;
+ __u64 summary_addr;
+ __u64 ind_offset;
+ __u32 summary_offset;
+ __u32 adapter_id;
+};
+
+struct kvm_irq_routing_hv_sint {
+ __u32 vcpu;
+ __u32 sint;
+};
+
+
+4.55 KVM_SET_TSC_KHZ
+
+Capability: KVM_CAP_TSC_CONTROL
+Architectures: x86
+Type: vcpu ioctl
+Parameters: virtual tsc_khz
+Returns: 0 on success, -1 on error
+
+Specifies the tsc frequency for the virtual machine. The unit of the
+frequency is KHz.
+
+
+4.56 KVM_GET_TSC_KHZ
+
+Capability: KVM_CAP_GET_TSC_KHZ
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: virtual tsc-khz on success, negative value on error
+
+Returns the tsc frequency of the guest. The unit of the return value is
+KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
+error.
+
+
+4.57 KVM_GET_LAPIC
+
+Capability: KVM_CAP_IRQCHIP
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_lapic_state (out)
+Returns: 0 on success, -1 on error
+
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+ char regs[KVM_APIC_REG_SIZE];
+};
+
+Reads the Local APIC registers and copies them into the input argument. The
+data format and layout are the same as documented in the architecture manual.
+
+If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
+enabled, then the format of APIC_ID register depends on the APIC mode
+(reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in
+the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID
+which is stored in bits 31-24 of the APIC register, or equivalently in
+byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then
+be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.
+
+If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
+always uses xAPIC format.
+
+
+4.58 KVM_SET_LAPIC
+
+Capability: KVM_CAP_IRQCHIP
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_lapic_state (in)
+Returns: 0 on success, -1 on error
+
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+ char regs[KVM_APIC_REG_SIZE];
+};
+
+Copies the input argument into the Local APIC registers. The data format
+and layout are the same as documented in the architecture manual.
+
+The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
+regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
+See the note in KVM_GET_LAPIC.
+
+
+4.59 KVM_IOEVENTFD
+
+Capability: KVM_CAP_IOEVENTFD
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_ioeventfd (in)
+Returns: 0 on success, !0 on error
+
+This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
+within the guest. A guest write in the registered address will signal the
+provided event instead of triggering an exit.
+
+struct kvm_ioeventfd {
+ __u64 datamatch;
+ __u64 addr; /* legal pio/mmio address */
+ __u32 len; /* 0, 1, 2, 4, or 8 bytes */
+ __s32 fd;
+ __u32 flags;
+ __u8 pad[36];
+};
+
+For the special case of virtio-ccw devices on s390, the ioevent is matched
+to a subchannel/virtqueue tuple instead.
+
+The following flags are defined:
+
+#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
+#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
+#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
+#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+ (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
+
+If datamatch flag is set, the event will be signaled only if the written value
+to the registered address is equal to datamatch in struct kvm_ioeventfd.
+
+For virtio-ccw devices, addr contains the subchannel id and datamatch the
+virtqueue index.
+
+With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
+the kernel will ignore the length of guest write and may get a faster vmexit.
+The speedup may only apply to specific architectures, but the ioeventfd will
+work anyway.
+
+4.60 KVM_DIRTY_TLB
+
+Capability: KVM_CAP_SW_TLB
+Architectures: ppc
+Type: vcpu ioctl
+Parameters: struct kvm_dirty_tlb (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_dirty_tlb {
+ __u64 bitmap;
+ __u32 num_dirty;
+};
+
+This must be called whenever userspace has changed an entry in the shared
+TLB, prior to calling KVM_RUN on the associated vcpu.
+
+The "bitmap" field is the userspace address of an array. This array
+consists of a number of bits, equal to the total number of TLB entries as
+determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
+nearest multiple of 64.
+
+Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
+array.
+
+The array is little-endian: the bit 0 is the least significant bit of the
+first byte, bit 8 is the least significant bit of the second byte, etc.
+This avoids any complications with differing word sizes.
+
+The "num_dirty" field is a performance hint for KVM to determine whether it
+should skip processing the bitmap and just invalidate everything. It must
+be set to the number of set bits in the bitmap.
+
+
+4.62 KVM_CREATE_SPAPR_TCE
+
+Capability: KVM_CAP_SPAPR_TCE
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce (in)
+Returns: file descriptor for manipulating the created TCE table
+
+This creates a virtual TCE (translation control entry) table, which
+is an IOMMU for PAPR-style virtual I/O. It is used to translate
+logical addresses used in virtual I/O into guest physical addresses,
+and provides a scatter/gather capability for PAPR virtual I/O.
+
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+ __u64 liobn;
+ __u32 window_size;
+};
+
+The liobn field gives the logical IO bus number for which to create a
+TCE table. The window_size field specifies the size of the DMA window
+which this TCE table will translate - the table will contain one 64
+bit TCE entry for every 4kiB of the DMA window.
+
+When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
+table has been created using this ioctl(), the kernel will handle it
+in real mode, updating the TCE table. H_PUT_TCE calls for other
+liobns will cause a vm exit and must be handled by userspace.
+
+The return value is a file descriptor which can be passed to mmap(2)
+to map the created TCE table into userspace. This lets userspace read
+the entries written by kernel-handled H_PUT_TCE calls, and also lets
+userspace update the TCE table directly which is useful in some
+circumstances.
+
+
+4.63 KVM_ALLOCATE_RMA
+
+Capability: KVM_CAP_PPC_RMA
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_allocate_rma (out)
+Returns: file descriptor for mapping the allocated RMA
+
+This allocates a Real Mode Area (RMA) from the pool allocated at boot
+time by the kernel. An RMA is a physically-contiguous, aligned region
+of memory used on older POWER processors to provide the memory which
+will be accessed by real-mode (MMU off) accesses in a KVM guest.
+POWER processors support a set of sizes for the RMA that usually
+includes 64MB, 128MB, 256MB and some larger powers of two.
+
+/* for KVM_ALLOCATE_RMA */
+struct kvm_allocate_rma {
+ __u64 rma_size;
+};
+
+The return value is a file descriptor which can be passed to mmap(2)
+to map the allocated RMA into userspace. The mapped area can then be
+passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
+RMA for a virtual machine. The size of the RMA in bytes (which is
+fixed at host kernel boot time) is returned in the rma_size field of
+the argument structure.
+
+The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
+is supported; 2 if the processor requires all virtual machines to have
+an RMA, or 1 if the processor can use an RMA but doesn't require it,
+because it supports the Virtual RMA (VRMA) facility.
+
+
+4.64 KVM_NMI
+
+Capability: KVM_CAP_USER_NMI
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+
+Queues an NMI on the thread's vcpu. Note this is well defined only
+when KVM_CREATE_IRQCHIP has not been called, since this is an interface
+between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP
+has been called, this interface is completely emulated within the kernel.
+
+To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
+following algorithm:
+
+ - pause the vcpu
+ - read the local APIC's state (KVM_GET_LAPIC)
+ - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
+ - if so, issue KVM_NMI
+ - resume the vcpu
+
+Some guests configure the LINT1 NMI input to cause a panic, aiding in
+debugging.
+
+
+4.65 KVM_S390_UCAS_MAP
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_ucas_mapping (in)
+Returns: 0 in case of success
+
+The parameter is defined like this:
+ struct kvm_s390_ucas_mapping {
+ __u64 user_addr;
+ __u64 vcpu_addr;
+ __u64 length;
+ };
+
+This ioctl maps the memory at "user_addr" with the length "length" to
+the vcpu's address space starting at "vcpu_addr". All parameters need to
+be aligned by 1 megabyte.
+
+
+4.66 KVM_S390_UCAS_UNMAP
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_ucas_mapping (in)
+Returns: 0 in case of success
+
+The parameter is defined like this:
+ struct kvm_s390_ucas_mapping {
+ __u64 user_addr;
+ __u64 vcpu_addr;
+ __u64 length;
+ };
+
+This ioctl unmaps the memory in the vcpu's address space starting at
+"vcpu_addr" with the length "length". The field "user_addr" is ignored.
+All parameters need to be aligned by 1 megabyte.
+
+
+4.67 KVM_S390_VCPU_FAULT
+
+Capability: KVM_CAP_S390_UCONTROL
+Architectures: s390
+Type: vcpu ioctl
+Parameters: vcpu absolute address (in)
+Returns: 0 in case of success
+
+This call creates a page table entry on the virtual cpu's address space
+(for user controlled virtual machines) or the virtual machine's address
+space (for regular virtual machines). This only works for minor faults,
+thus it's recommended to access subject memory page via the user page
+table upfront. This is useful to handle validity intercepts for user
+controlled virtual machines to fault in the virtual cpu's lowcore pages
+prior to calling the KVM_RUN ioctl.
+
+
+4.68 KVM_SET_ONE_REG
+
+Capability: KVM_CAP_ONE_REG
+Architectures: all
+Type: vcpu ioctl
+Parameters: struct kvm_one_reg (in)
+Returns: 0 on success, negative value on failure
+Errors:
+ ENOENT: no such register
+ EINVAL: invalid register ID, or no such register
+ EPERM: (arm64) register access not allowed before vcpu finalization
+(These error codes are indicative only: do not rely on a specific error
+code being returned in a specific situation.)
+
+struct kvm_one_reg {
+ __u64 id;
+ __u64 addr;
+};
+
+Using this ioctl, a single vcpu register can be set to a specific value
+defined by user space with the passed in struct kvm_one_reg, where id
+refers to the register identifier as described below and addr is a pointer
+to a variable with the respective size. There can be architecture agnostic
+and architecture specific registers. Each have their own range of operation
+and their own constants and width. To keep track of the implemented
+registers, find a list below:
+
+ Arch | Register | Width (bits)
+ | |
+ PPC | KVM_REG_PPC_HIOR | 64
+ PPC | KVM_REG_PPC_IAC1 | 64
+ PPC | KVM_REG_PPC_IAC2 | 64
+ PPC | KVM_REG_PPC_IAC3 | 64
+ PPC | KVM_REG_PPC_IAC4 | 64
+ PPC | KVM_REG_PPC_DAC1 | 64
+ PPC | KVM_REG_PPC_DAC2 | 64
+ PPC | KVM_REG_PPC_DABR | 64
+ PPC | KVM_REG_PPC_DSCR | 64
+ PPC | KVM_REG_PPC_PURR | 64
+ PPC | KVM_REG_PPC_SPURR | 64
+ PPC | KVM_REG_PPC_DAR | 64
+ PPC | KVM_REG_PPC_DSISR | 32
+ PPC | KVM_REG_PPC_AMR | 64
+ PPC | KVM_REG_PPC_UAMOR | 64
+ PPC | KVM_REG_PPC_MMCR0 | 64
+ PPC | KVM_REG_PPC_MMCR1 | 64
+ PPC | KVM_REG_PPC_MMCRA | 64
+ PPC | KVM_REG_PPC_MMCR2 | 64
+ PPC | KVM_REG_PPC_MMCRS | 64
+ PPC | KVM_REG_PPC_SIAR | 64
+ PPC | KVM_REG_PPC_SDAR | 64
+ PPC | KVM_REG_PPC_SIER | 64
+ PPC | KVM_REG_PPC_PMC1 | 32
+ PPC | KVM_REG_PPC_PMC2 | 32
+ PPC | KVM_REG_PPC_PMC3 | 32
+ PPC | KVM_REG_PPC_PMC4 | 32
+ PPC | KVM_REG_PPC_PMC5 | 32
+ PPC | KVM_REG_PPC_PMC6 | 32
+ PPC | KVM_REG_PPC_PMC7 | 32
+ PPC | KVM_REG_PPC_PMC8 | 32
+ PPC | KVM_REG_PPC_FPR0 | 64
+ ...
+ PPC | KVM_REG_PPC_FPR31 | 64
+ PPC | KVM_REG_PPC_VR0 | 128
+ ...
+ PPC | KVM_REG_PPC_VR31 | 128
+ PPC | KVM_REG_PPC_VSR0 | 128
+ ...
+ PPC | KVM_REG_PPC_VSR31 | 128
+ PPC | KVM_REG_PPC_FPSCR | 64
+ PPC | KVM_REG_PPC_VSCR | 32
+ PPC | KVM_REG_PPC_VPA_ADDR | 64
+ PPC | KVM_REG_PPC_VPA_SLB | 128
+ PPC | KVM_REG_PPC_VPA_DTL | 128
+ PPC | KVM_REG_PPC_EPCR | 32
+ PPC | KVM_REG_PPC_EPR | 32
+ PPC | KVM_REG_PPC_TCR | 32
+ PPC | KVM_REG_PPC_TSR | 32
+ PPC | KVM_REG_PPC_OR_TSR | 32
+ PPC | KVM_REG_PPC_CLEAR_TSR | 32
+ PPC | KVM_REG_PPC_MAS0 | 32
+ PPC | KVM_REG_PPC_MAS1 | 32
+ PPC | KVM_REG_PPC_MAS2 | 64
+ PPC | KVM_REG_PPC_MAS7_3 | 64
+ PPC | KVM_REG_PPC_MAS4 | 32
+ PPC | KVM_REG_PPC_MAS6 | 32
+ PPC | KVM_REG_PPC_MMUCFG | 32
+ PPC | KVM_REG_PPC_TLB0CFG | 32
+ PPC | KVM_REG_PPC_TLB1CFG | 32
+ PPC | KVM_REG_PPC_TLB2CFG | 32
+ PPC | KVM_REG_PPC_TLB3CFG | 32
+ PPC | KVM_REG_PPC_TLB0PS | 32
+ PPC | KVM_REG_PPC_TLB1PS | 32
+ PPC | KVM_REG_PPC_TLB2PS | 32
+ PPC | KVM_REG_PPC_TLB3PS | 32
+ PPC | KVM_REG_PPC_EPTCFG | 32
+ PPC | KVM_REG_PPC_ICP_STATE | 64
+ PPC | KVM_REG_PPC_VP_STATE | 128
+ PPC | KVM_REG_PPC_TB_OFFSET | 64
+ PPC | KVM_REG_PPC_SPMC1 | 32
+ PPC | KVM_REG_PPC_SPMC2 | 32
+ PPC | KVM_REG_PPC_IAMR | 64
+ PPC | KVM_REG_PPC_TFHAR | 64
+ PPC | KVM_REG_PPC_TFIAR | 64
+ PPC | KVM_REG_PPC_TEXASR | 64
+ PPC | KVM_REG_PPC_FSCR | 64
+ PPC | KVM_REG_PPC_PSPB | 32
+ PPC | KVM_REG_PPC_EBBHR | 64
+ PPC | KVM_REG_PPC_EBBRR | 64
+ PPC | KVM_REG_PPC_BESCR | 64
+ PPC | KVM_REG_PPC_TAR | 64
+ PPC | KVM_REG_PPC_DPDES | 64
+ PPC | KVM_REG_PPC_DAWR | 64
+ PPC | KVM_REG_PPC_DAWRX | 64
+ PPC | KVM_REG_PPC_CIABR | 64
+ PPC | KVM_REG_PPC_IC | 64
+ PPC | KVM_REG_PPC_VTB | 64
+ PPC | KVM_REG_PPC_CSIGR | 64
+ PPC | KVM_REG_PPC_TACR | 64
+ PPC | KVM_REG_PPC_TCSCR | 64
+ PPC | KVM_REG_PPC_PID | 64
+ PPC | KVM_REG_PPC_ACOP | 64
+ PPC | KVM_REG_PPC_VRSAVE | 32
+ PPC | KVM_REG_PPC_LPCR | 32
+ PPC | KVM_REG_PPC_LPCR_64 | 64
+ PPC | KVM_REG_PPC_PPR | 64
+ PPC | KVM_REG_PPC_ARCH_COMPAT | 32
+ PPC | KVM_REG_PPC_DABRX | 32
+ PPC | KVM_REG_PPC_WORT | 64
+ PPC | KVM_REG_PPC_SPRG9 | 64
+ PPC | KVM_REG_PPC_DBSR | 32
+ PPC | KVM_REG_PPC_TIDR | 64
+ PPC | KVM_REG_PPC_PSSCR | 64
+ PPC | KVM_REG_PPC_DEC_EXPIRY | 64
+ PPC | KVM_REG_PPC_PTCR | 64
+ PPC | KVM_REG_PPC_TM_GPR0 | 64
+ ...
+ PPC | KVM_REG_PPC_TM_GPR31 | 64
+ PPC | KVM_REG_PPC_TM_VSR0 | 128
+ ...
+ PPC | KVM_REG_PPC_TM_VSR63 | 128
+ PPC | KVM_REG_PPC_TM_CR | 64
+ PPC | KVM_REG_PPC_TM_LR | 64
+ PPC | KVM_REG_PPC_TM_CTR | 64
+ PPC | KVM_REG_PPC_TM_FPSCR | 64
+ PPC | KVM_REG_PPC_TM_AMR | 64
+ PPC | KVM_REG_PPC_TM_PPR | 64
+ PPC | KVM_REG_PPC_TM_VRSAVE | 64
+ PPC | KVM_REG_PPC_TM_VSCR | 32
+ PPC | KVM_REG_PPC_TM_DSCR | 64
+ PPC | KVM_REG_PPC_TM_TAR | 64
+ PPC | KVM_REG_PPC_TM_XER | 64
+ | |
+ MIPS | KVM_REG_MIPS_R0 | 64
+ ...
+ MIPS | KVM_REG_MIPS_R31 | 64
+ MIPS | KVM_REG_MIPS_HI | 64
+ MIPS | KVM_REG_MIPS_LO | 64
+ MIPS | KVM_REG_MIPS_PC | 64
+ MIPS | KVM_REG_MIPS_CP0_INDEX | 32
+ MIPS | KVM_REG_MIPS_CP0_ENTRYLO0 | 64
+ MIPS | KVM_REG_MIPS_CP0_ENTRYLO1 | 64
+ MIPS | KVM_REG_MIPS_CP0_CONTEXT | 64
+ MIPS | KVM_REG_MIPS_CP0_CONTEXTCONFIG| 32
+ MIPS | KVM_REG_MIPS_CP0_USERLOCAL | 64
+ MIPS | KVM_REG_MIPS_CP0_XCONTEXTCONFIG| 64
+ MIPS | KVM_REG_MIPS_CP0_PAGEMASK | 32
+ MIPS | KVM_REG_MIPS_CP0_PAGEGRAIN | 32
+ MIPS | KVM_REG_MIPS_CP0_SEGCTL0 | 64
+ MIPS | KVM_REG_MIPS_CP0_SEGCTL1 | 64
+ MIPS | KVM_REG_MIPS_CP0_SEGCTL2 | 64
+ MIPS | KVM_REG_MIPS_CP0_PWBASE | 64
+ MIPS | KVM_REG_MIPS_CP0_PWFIELD | 64
+ MIPS | KVM_REG_MIPS_CP0_PWSIZE | 64
+ MIPS | KVM_REG_MIPS_CP0_WIRED | 32
+ MIPS | KVM_REG_MIPS_CP0_PWCTL | 32
+ MIPS | KVM_REG_MIPS_CP0_HWRENA | 32
+ MIPS | KVM_REG_MIPS_CP0_BADVADDR | 64
+ MIPS | KVM_REG_MIPS_CP0_BADINSTR | 32
+ MIPS | KVM_REG_MIPS_CP0_BADINSTRP | 32
+ MIPS | KVM_REG_MIPS_CP0_COUNT | 32
+ MIPS | KVM_REG_MIPS_CP0_ENTRYHI | 64
+ MIPS | KVM_REG_MIPS_CP0_COMPARE | 32
+ MIPS | KVM_REG_MIPS_CP0_STATUS | 32
+ MIPS | KVM_REG_MIPS_CP0_INTCTL | 32
+ MIPS | KVM_REG_MIPS_CP0_CAUSE | 32
+ MIPS | KVM_REG_MIPS_CP0_EPC | 64
+ MIPS | KVM_REG_MIPS_CP0_PRID | 32
+ MIPS | KVM_REG_MIPS_CP0_EBASE | 64
+ MIPS | KVM_REG_MIPS_CP0_CONFIG | 32
+ MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32
+ MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32
+ MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32
+ MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32
+ MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32
+ MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32
+ MIPS | KVM_REG_MIPS_CP0_XCONTEXT | 64
+ MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64
+ MIPS | KVM_REG_MIPS_CP0_KSCRATCH1 | 64
+ MIPS | KVM_REG_MIPS_CP0_KSCRATCH2 | 64
+ MIPS | KVM_REG_MIPS_CP0_KSCRATCH3 | 64
+ MIPS | KVM_REG_MIPS_CP0_KSCRATCH4 | 64
+ MIPS | KVM_REG_MIPS_CP0_KSCRATCH5 | 64
+ MIPS | KVM_REG_MIPS_CP0_KSCRATCH6 | 64
+ MIPS | KVM_REG_MIPS_CP0_MAAR(0..63) | 64
+ MIPS | KVM_REG_MIPS_COUNT_CTL | 64
+ MIPS | KVM_REG_MIPS_COUNT_RESUME | 64
+ MIPS | KVM_REG_MIPS_COUNT_HZ | 64
+ MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32
+ MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64
+ MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128
+ MIPS | KVM_REG_MIPS_FCR_IR | 32
+ MIPS | KVM_REG_MIPS_FCR_CSR | 32
+ MIPS | KVM_REG_MIPS_MSA_IR | 32
+ MIPS | KVM_REG_MIPS_MSA_CSR | 32
+
+ARM registers are mapped using the lower 32 bits. The upper 16 of that
+is the register group type, or coprocessor number:
+
+ARM core registers have the following id bit patterns:
+ 0x4020 0000 0010 <index into the kvm_regs struct:16>
+
+ARM 32-bit CP15 registers have the following id bit patterns:
+ 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
+
+ARM 64-bit CP15 registers have the following id bit patterns:
+ 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
+
+ARM CCSIDR registers are demultiplexed by CSSELR value:
+ 0x4020 0000 0011 00 <csselr:8>
+
+ARM 32-bit VFP control registers have the following id bit patterns:
+ 0x4020 0000 0012 1 <regno:12>
+
+ARM 64-bit FP registers have the following id bit patterns:
+ 0x4030 0000 0012 0 <regno:12>
+
+ARM firmware pseudo-registers have the following bit pattern:
+ 0x4030 0000 0014 <regno:16>
+
+
+arm64 registers are mapped using the lower 32 bits. The upper 16 of
+that is the register group type, or coprocessor number:
+
+arm64 core/FP-SIMD registers have the following id bit patterns. Note
+that the size of the access is variable, as the kvm_regs structure
+contains elements ranging from 32 to 128 bits. The index is a 32bit
+value in the kvm_regs structure seen as a 32bit array.
+ 0x60x0 0000 0010 <index into the kvm_regs struct:16>
+
+Specifically:
+ Encoding Register Bits kvm_regs member
+----------------------------------------------------------------
+ 0x6030 0000 0010 0000 X0 64 regs.regs[0]
+ 0x6030 0000 0010 0002 X1 64 regs.regs[1]
+ ...
+ 0x6030 0000 0010 003c X30 64 regs.regs[30]
+ 0x6030 0000 0010 003e SP 64 regs.sp
+ 0x6030 0000 0010 0040 PC 64 regs.pc
+ 0x6030 0000 0010 0042 PSTATE 64 regs.pstate
+ 0x6030 0000 0010 0044 SP_EL1 64 sp_el1
+ 0x6030 0000 0010 0046 ELR_EL1 64 elr_el1
+ 0x6030 0000 0010 0048 SPSR_EL1 64 spsr[KVM_SPSR_EL1] (alias SPSR_SVC)
+ 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT]
+ 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND]
+ 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ]
+ 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ]
+ 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] (*)
+ 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] (*)
+ ...
+ 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] (*)
+ 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr
+ 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr
+
+(*) These encodings are not accepted for SVE-enabled vcpus. See
+ KVM_ARM_VCPU_INIT.
+
+ The equivalent register content can be accessed via bits [127:0] of
+ the corresponding SVE Zn registers instead for vcpus that have SVE
+ enabled (see below).
+
+arm64 CCSIDR registers are demultiplexed by CSSELR value:
+ 0x6020 0000 0011 00 <csselr:8>
+
+arm64 system registers have the following id bit patterns:
+ 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
+
+arm64 firmware pseudo-registers have the following bit pattern:
+ 0x6030 0000 0014 <regno:16>
+
+arm64 SVE registers have the following bit patterns:
+ 0x6080 0000 0015 00 <n:5> <slice:5> Zn bits[2048*slice + 2047 : 2048*slice]
+ 0x6050 0000 0015 04 <n:4> <slice:5> Pn bits[256*slice + 255 : 256*slice]
+ 0x6050 0000 0015 060 <slice:5> FFR bits[256*slice + 255 : 256*slice]
+ 0x6060 0000 0015 ffff KVM_REG_ARM64_SVE_VLS pseudo-register
+
+Access to register IDs where 2048 * slice >= 128 * max_vq will fail with
+ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit
+quadwords: see (**) below.
+
+These registers are only accessible on vcpus for which SVE is enabled.
+See KVM_ARM_VCPU_INIT for details.
+
+In addition, except for KVM_REG_ARM64_SVE_VLS, these registers are not
+accessible until the vcpu's SVE configuration has been finalized
+using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). See KVM_ARM_VCPU_INIT
+and KVM_ARM_VCPU_FINALIZE for more information about this procedure.
+
+KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector
+lengths supported by the vcpu to be discovered and configured by
+userspace. When transferred to or from user memory via KVM_GET_ONE_REG
+or KVM_SET_ONE_REG, the value of this register is of type
+__u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as
+follows:
+
+__u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS];
+
+if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX &&
+ ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
+ ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1))
+ /* Vector length vq * 16 bytes supported */
+else
+ /* Vector length vq * 16 bytes not supported */
+
+(**) The maximum value vq for which the above condition is true is
+max_vq. This is the maximum vector length available to the guest on
+this vcpu, and determines which register slices are visible through
+this ioctl interface.
+
+(See Documentation/arm64/sve.rst for an explanation of the "vq"
+nomenclature.)
+
+KVM_REG_ARM64_SVE_VLS is only accessible after KVM_ARM_VCPU_INIT.
+KVM_ARM_VCPU_INIT initialises it to the best set of vector lengths that
+the host supports.
+
+Userspace may subsequently modify it if desired until the vcpu's SVE
+configuration is finalized using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE).
+
+Apart from simply removing all vector lengths from the host set that
+exceed some value, support for arbitrarily chosen sets of vector lengths
+is hardware-dependent and may not be available. Attempting to configure
+an invalid set of vector lengths via KVM_SET_ONE_REG will fail with
+EINVAL.
+
+After the vcpu's SVE configuration is finalized, further attempts to
+write this register will fail with EPERM.
+
+
+MIPS registers are mapped using the lower 32 bits. The upper 16 of that is
+the register group type:
+
+MIPS core registers (see above) have the following id bit patterns:
+ 0x7030 0000 0000 <reg:16>
+
+MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
+patterns depending on whether they're 32-bit or 64-bit registers:
+ 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit)
+ 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit)
+
+Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_MIPS_CP0_ENTRYLO1 are the MIPS64
+versions of the EntryLo registers regardless of the word size of the host
+hardware, host kernel, guest, and whether XPA is present in the guest, i.e.
+with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and
+the PFNX field starting at bit 30.
+
+MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit
+patterns:
+ 0x7030 0000 0001 01 <reg:8>
+
+MIPS KVM control registers (see above) have the following id bit patterns:
+ 0x7030 0000 0002 <reg:16>
+
+MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following
+id bit patterns depending on the size of the register being accessed. They are
+always accessed according to the current guest FPU mode (Status.FR and
+Config5.FRE), i.e. as the guest would see them, and they become unpredictable
+if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector
+registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they
+overlap the FPU registers:
+ 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
+ 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
+ 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)
+
+MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the
+following id bit patterns:
+ 0x7020 0000 0003 01 <0:3> <reg:5>
+
+MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the
+following id bit patterns:
+ 0x7020 0000 0003 02 <0:3> <reg:5>
+
+
+4.69 KVM_GET_ONE_REG
+
+Capability: KVM_CAP_ONE_REG
+Architectures: all
+Type: vcpu ioctl
+Parameters: struct kvm_one_reg (in and out)
+Returns: 0 on success, negative value on failure
+Errors include:
+ ENOENT: no such register
+ EINVAL: invalid register ID, or no such register
+ EPERM: (arm64) register access not allowed before vcpu finalization
+(These error codes are indicative only: do not rely on a specific error
+code being returned in a specific situation.)
+
+This ioctl allows to receive the value of a single register implemented
+in a vcpu. The register to read is indicated by the "id" field of the
+kvm_one_reg struct passed in. On success, the register value can be found
+at the memory location pointed to by "addr".
+
+The list of registers accessible using this interface is identical to the
+list in 4.68.
+
+
+4.70 KVM_KVMCLOCK_CTRL
+
+Capability: KVM_CAP_KVMCLOCK_CTRL
+Architectures: Any that implement pvclocks (currently x86 only)
+Type: vcpu ioctl
+Parameters: None
+Returns: 0 on success, -1 on error
+
+This signals to the host kernel that the specified guest is being paused by
+userspace. The host will set a flag in the pvclock structure that is checked
+from the soft lockup watchdog. The flag is part of the pvclock structure that
+is shared between guest and host, specifically the second bit of the flags
+field of the pvclock_vcpu_time_info structure. It will be set exclusively by
+the host and read/cleared exclusively by the guest. The guest operation of
+checking and clearing the flag must an atomic operation so
+load-link/store-conditional, or equivalent must be used. There are two cases
+where the guest will clear the flag: when the soft lockup watchdog timer resets
+itself or when a soft lockup is detected. This ioctl can be called any time
+after pausing the vcpu, but before it is resumed.
+
+
+4.71 KVM_SIGNAL_MSI
+
+Capability: KVM_CAP_SIGNAL_MSI
+Architectures: x86 arm arm64
+Type: vm ioctl
+Parameters: struct kvm_msi (in)
+Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
+
+Directly inject a MSI message. Only valid with in-kernel irqchip that handles
+MSI messages.
+
+struct kvm_msi {
+ __u32 address_lo;
+ __u32 address_hi;
+ __u32 data;
+ __u32 flags;
+ __u32 devid;
+ __u8 pad[12];
+};
+
+flags: KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM
+ KVM_CAP_MSI_DEVID capability advertises the requirement to provide
+ the device ID. If this capability is not available, userspace
+ should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
+
+If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
+for the device that wrote the MSI message. For PCI, this is usually a
+BFD identifier in the lower 16 bits.
+
+On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
+feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
+address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
+address_hi must be zero.
+
+
+4.71 KVM_CREATE_PIT2
+
+Capability: KVM_CAP_PIT2
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pit_config (in)
+Returns: 0 on success, -1 on error
+
+Creates an in-kernel device model for the i8254 PIT. This call is only valid
+after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
+parameters have to be passed:
+
+struct kvm_pit_config {
+ __u32 flags;
+ __u32 pad[15];
+};
+
+Valid flags are:
+
+#define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */
+
+PIT timer interrupts may use a per-VM kernel thread for injection. If it
+exists, this thread will have a name of the following pattern:
+
+kvm-pit/<owner-process-pid>
+
+When running a guest with elevated priorities, the scheduling parameters of
+this thread may have to be adjusted accordingly.
+
+This IOCTL replaces the obsolete KVM_CREATE_PIT.
+
+
+4.72 KVM_GET_PIT2
+
+Capability: KVM_CAP_PIT_STATE2
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pit_state2 (out)
+Returns: 0 on success, -1 on error
+
+Retrieves the state of the in-kernel PIT model. Only valid after
+KVM_CREATE_PIT2. The state is returned in the following structure:
+
+struct kvm_pit_state2 {
+ struct kvm_pit_channel_state channels[3];
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+Valid flags are:
+
+/* disable PIT in HPET legacy mode */
+#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+
+This IOCTL replaces the obsolete KVM_GET_PIT.
+
+
+4.73 KVM_SET_PIT2
+
+Capability: KVM_CAP_PIT_STATE2
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pit_state2 (in)
+Returns: 0 on success, -1 on error
+
+Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
+See KVM_GET_PIT2 for details on struct kvm_pit_state2.
+
+This IOCTL replaces the obsolete KVM_SET_PIT.
+
+
+4.74 KVM_PPC_GET_SMMU_INFO
+
+Capability: KVM_CAP_PPC_GET_SMMU_INFO
+Architectures: powerpc
+Type: vm ioctl
+Parameters: None
+Returns: 0 on success, -1 on error
+
+This populates and returns a structure describing the features of
+the "Server" class MMU emulation supported by KVM.
+This can in turn be used by userspace to generate the appropriate
+device-tree properties for the guest operating system.
+
+The structure contains some global information, followed by an
+array of supported segment page sizes:
+
+ struct kvm_ppc_smmu_info {
+ __u64 flags;
+ __u32 slb_size;
+ __u32 pad;
+ struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
+ };
+
+The supported flags are:
+
+ - KVM_PPC_PAGE_SIZES_REAL:
+ When that flag is set, guest page sizes must "fit" the backing
+ store page sizes. When not set, any page size in the list can
+ be used regardless of how they are backed by userspace.
+
+ - KVM_PPC_1T_SEGMENTS
+ The emulated MMU supports 1T segments in addition to the
+ standard 256M ones.
+
+ - KVM_PPC_NO_HASH
+ This flag indicates that HPT guests are not supported by KVM,
+ thus all guests must use radix MMU mode.
+
+The "slb_size" field indicates how many SLB entries are supported
+
+The "sps" array contains 8 entries indicating the supported base
+page sizes for a segment in increasing order. Each entry is defined
+as follow:
+
+ struct kvm_ppc_one_seg_page_size {
+ __u32 page_shift; /* Base page shift of segment (or 0) */
+ __u32 slb_enc; /* SLB encoding for BookS */
+ struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
+ };
+
+An entry with a "page_shift" of 0 is unused. Because the array is
+organized in increasing order, a lookup can stop when encoutering
+such an entry.
+
+The "slb_enc" field provides the encoding to use in the SLB for the
+page size. The bits are in positions such as the value can directly
+be OR'ed into the "vsid" argument of the slbmte instruction.
+
+The "enc" array is a list which for each of those segment base page
+size provides the list of supported actual page sizes (which can be
+only larger or equal to the base page size), along with the
+corresponding encoding in the hash PTE. Similarly, the array is
+8 entries sorted by increasing sizes and an entry with a "0" shift
+is an empty entry and a terminator:
+
+ struct kvm_ppc_one_page_size {
+ __u32 page_shift; /* Page shift (or 0) */
+ __u32 pte_enc; /* Encoding in the HPTE (>>12) */
+ };
+
+The "pte_enc" field provides a value that can OR'ed into the hash
+PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
+into the hash PTE second double word).
+
+4.75 KVM_IRQFD
+
+Capability: KVM_CAP_IRQFD
+Architectures: x86 s390 arm arm64
+Type: vm ioctl
+Parameters: struct kvm_irqfd (in)
+Returns: 0 on success, -1 on error
+
+Allows setting an eventfd to directly trigger a guest interrupt.
+kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
+kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When
+an event is triggered on the eventfd, an interrupt is injected into
+the guest using the specified gsi pin. The irqfd is removed using
+the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
+and kvm_irqfd.gsi.
+
+With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
+mechanism allowing emulation of level-triggered, irqfd-based
+interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
+additional eventfd in the kvm_irqfd.resamplefd field. When operating
+in resample mode, posting of an interrupt through kvm_irq.fd asserts
+the specified gsi in the irqchip. When the irqchip is resampled, such
+as from an EOI, the gsi is de-asserted and the user is notified via
+kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
+the interrupt if the device making use of it still requires service.
+Note that closing the resamplefd is not sufficient to disable the
+irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
+and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
+
+On arm/arm64, gsi routing being supported, the following can happen:
+- in case no routing entry is associated to this gsi, injection fails
+- in case the gsi is associated to an irqchip routing entry,
+ irqchip.pin + 32 corresponds to the injected SPI ID.
+- in case the gsi is associated to an MSI routing entry, the MSI
+ message and device ID are translated into an LPI (support restricted
+ to GICv3 ITS in-kernel emulation).
+
+4.76 KVM_PPC_ALLOCATE_HTAB
+
+Capability: KVM_CAP_PPC_ALLOC_HTAB
+Architectures: powerpc
+Type: vm ioctl
+Parameters: Pointer to u32 containing hash table order (in/out)
+Returns: 0 on success, -1 on error
+
+This requests the host kernel to allocate an MMU hash table for a
+guest using the PAPR paravirtualization interface. This only does
+anything if the kernel is configured to use the Book 3S HV style of
+virtualization. Otherwise the capability doesn't exist and the ioctl
+returns an ENOTTY error. The rest of this description assumes Book 3S
+HV.
+
+There must be no vcpus running when this ioctl is called; if there
+are, it will do nothing and return an EBUSY error.
+
+The parameter is a pointer to a 32-bit unsigned integer variable
+containing the order (log base 2) of the desired size of the hash
+table, which must be between 18 and 46. On successful return from the
+ioctl, the value will not be changed by the kernel.
+
+If no hash table has been allocated when any vcpu is asked to run
+(with the KVM_RUN ioctl), the host kernel will allocate a
+default-sized hash table (16 MB).
+
+If this ioctl is called when a hash table has already been allocated,
+with a different order from the existing hash table, the existing hash
+table will be freed and a new one allocated. If this is ioctl is
+called when a hash table has already been allocated of the same order
+as specified, the kernel will clear out the existing hash table (zero
+all HPTEs). In either case, if the guest is using the virtualized
+real-mode area (VRMA) facility, the kernel will re-create the VMRA
+HPTEs on the next KVM_RUN of any vcpu.
+
+4.77 KVM_S390_INTERRUPT
+
+Capability: basic
+Architectures: s390
+Type: vm ioctl, vcpu ioctl
+Parameters: struct kvm_s390_interrupt (in)
+Returns: 0 on success, -1 on error
+
+Allows to inject an interrupt to the guest. Interrupts can be floating
+(vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
+
+Interrupt parameters are passed via kvm_s390_interrupt:
+
+struct kvm_s390_interrupt {
+ __u32 type;
+ __u32 parm;
+ __u64 parm64;
+};
+
+type can be one of the following:
+
+KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm
+KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
+KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
+KVM_S390_RESTART (vcpu) - restart
+KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
+KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
+KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
+ parameters in parm and parm64
+KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
+KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
+KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
+KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
+ I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
+ I/O interruption parameters in parm (subchannel) and parm64 (intparm,
+ interruption subclass)
+KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
+ machine check interrupt code in parm64 (note that
+ machine checks needing further payload are not
+ supported by this ioctl)
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
+4.78 KVM_PPC_GET_HTAB_FD
+
+Capability: KVM_CAP_PPC_HTAB_FD
+Architectures: powerpc
+Type: vm ioctl
+Parameters: Pointer to struct kvm_get_htab_fd (in)
+Returns: file descriptor number (>= 0) on success, -1 on error
+
+This returns a file descriptor that can be used either to read out the
+entries in the guest's hashed page table (HPT), or to write entries to
+initialize the HPT. The returned fd can only be written to if the
+KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
+can only be read if that bit is clear. The argument struct looks like
+this:
+
+/* For KVM_PPC_GET_HTAB_FD */
+struct kvm_get_htab_fd {
+ __u64 flags;
+ __u64 start_index;
+ __u64 reserved[2];
+};
+
+/* Values for kvm_get_htab_fd.flags */
+#define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1)
+#define KVM_GET_HTAB_WRITE ((__u64)0x2)
+
+The `start_index' field gives the index in the HPT of the entry at
+which to start reading. It is ignored when writing.
+
+Reads on the fd will initially supply information about all
+"interesting" HPT entries. Interesting entries are those with the
+bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
+all entries. When the end of the HPT is reached, the read() will
+return. If read() is called again on the fd, it will start again from
+the beginning of the HPT, but will only return HPT entries that have
+changed since they were last read.
+
+Data read or written is structured as a header (8 bytes) followed by a
+series of valid HPT entries (16 bytes) each. The header indicates how
+many valid HPT entries there are and how many invalid entries follow
+the valid entries. The invalid entries are not represented explicitly
+in the stream. The header format is:
+
+struct kvm_get_htab_header {
+ __u32 index;
+ __u16 n_valid;
+ __u16 n_invalid;
+};
+
+Writes to the fd create HPT entries starting at the index given in the
+header; first `n_valid' valid entries with contents from the data
+written, then `n_invalid' invalid entries, invalidating any previously
+valid entries found.
+
+4.79 KVM_CREATE_DEVICE
+
+Capability: KVM_CAP_DEVICE_CTRL
+Type: vm ioctl
+Parameters: struct kvm_create_device (in/out)
+Returns: 0 on success, -1 on error
+Errors:
+ ENODEV: The device type is unknown or unsupported
+ EEXIST: Device already created, and this type of device may not
+ be instantiated multiple times
+
+ Other error conditions may be defined by individual device types or
+ have their standard meanings.
+
+Creates an emulated device in the kernel. The file descriptor returned
+in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
+
+If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
+device type is supported (not necessarily whether it can be created
+in the current vm).
+
+Individual devices should not define flags. Attributes should be used
+for specifying any behavior that is not implied by the device type
+number.
+
+struct kvm_create_device {
+ __u32 type; /* in: KVM_DEV_TYPE_xxx */
+ __u32 fd; /* out: device handle */
+ __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
+};
+
+4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
+
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+ KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+Type: device ioctl, vm ioctl, vcpu ioctl
+Parameters: struct kvm_device_attr
+Returns: 0 on success, -1 on error
+Errors:
+ ENXIO: The group or attribute is unknown/unsupported for this device
+ or hardware support is missing.
+ EPERM: The attribute cannot (currently) be accessed this way
+ (e.g. read-only attribute, or attribute that only makes
+ sense when the device is in a different state)
+
+ Other error conditions may be defined by individual device types.
+
+Gets/sets a specified piece of device configuration and/or state. The
+semantics are device-specific. See individual device documentation in
+the "devices" directory. As with ONE_REG, the size of the data
+transferred is defined by the particular attribute.
+
+struct kvm_device_attr {
+ __u32 flags; /* no flags currently defined */
+ __u32 group; /* device-defined */
+ __u64 attr; /* group-defined */
+ __u64 addr; /* userspace address of attr data */
+};
+
+4.81 KVM_HAS_DEVICE_ATTR
+
+Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
+ KVM_CAP_VCPU_ATTRIBUTES for vcpu device
+Type: device ioctl, vm ioctl, vcpu ioctl
+Parameters: struct kvm_device_attr
+Returns: 0 on success, -1 on error
+Errors:
+ ENXIO: The group or attribute is unknown/unsupported for this device
+ or hardware support is missing.
+
+Tests whether a device supports a particular attribute. A successful
+return indicates the attribute is implemented. It does not necessarily
+indicate that the attribute can be read or written in the device's
+current state. "addr" is ignored.
+
+4.82 KVM_ARM_VCPU_INIT
+
+Capability: basic
+Architectures: arm, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_vcpu_init (in)
+Returns: 0 on success; -1 on error
+Errors:
+ EINVAL: the target is unknown, or the combination of features is invalid.
+ ENOENT: a features bit specified is unknown.
+
+This tells KVM what type of CPU to present to the guest, and what
+optional features it should have. This will cause a reset of the cpu
+registers to their initial values. If this is not called, KVM_RUN will
+return ENOEXEC for that vcpu.
+
+Note that because some registers reflect machine topology, all vcpus
+should be created before this ioctl is invoked.
+
+Userspace can call this function multiple times for a given vcpu, including
+after the vcpu has been run. This will reset the vcpu to its initial
+state. All calls to this function after the initial call must use the same
+target and same set of feature flags, otherwise EINVAL will be returned.
+
+Possible features:
+ - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
+ Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on
+ and execute guest code when KVM_RUN is called.
+ - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
+ Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
+ - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
+ backward compatible with v0.2) for the CPU.
+ Depends on KVM_CAP_ARM_PSCI_0_2.
+ - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
+ Depends on KVM_CAP_ARM_PMU_V3.
+
+ - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication
+ for arm64 only.
+ Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS.
+ If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
+ both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
+ KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
+ requested.
+
+ - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication
+ for arm64 only.
+ Depends on KVM_CAP_ARM_PTRAUTH_GENERIC.
+ If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
+ both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
+ KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
+ requested.
+
+ - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only).
+ Depends on KVM_CAP_ARM_SVE.
+ Requires KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
+
+ * After KVM_ARM_VCPU_INIT:
+
+ - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the
+ initial value of this pseudo-register indicates the best set of
+ vector lengths possible for a vcpu on this host.
+
+ * Before KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
+
+ - KVM_RUN and KVM_GET_REG_LIST are not available;
+
+ - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access
+ the scalable archietctural SVE registers
+ KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or
+ KVM_REG_ARM64_SVE_FFR;
+
+ - KVM_REG_ARM64_SVE_VLS may optionally be written using
+ KVM_SET_ONE_REG, to modify the set of vector lengths available
+ for the vcpu.
+
+ * After KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
+
+ - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can
+ no longer be written using KVM_SET_ONE_REG.
+
+4.83 KVM_ARM_PREFERRED_TARGET
+
+Capability: basic
+Architectures: arm, arm64
+Type: vm ioctl
+Parameters: struct struct kvm_vcpu_init (out)
+Returns: 0 on success; -1 on error
+Errors:
+ ENODEV: no preferred target available for the host
+
+This queries KVM for preferred CPU target type which can be emulated
+by KVM on underlying host.
+
+The ioctl returns struct kvm_vcpu_init instance containing information
+about preferred CPU target type and recommended features for it. The
+kvm_vcpu_init->features bitmap returned will have feature bits set if
+the preferred target recommends setting these features, but this is
+not mandatory.
+
+The information returned by this ioctl can be used to prepare an instance
+of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
+in VCPU matching underlying host.
+
+
+4.84 KVM_GET_REG_LIST
+
+Capability: basic
+Architectures: arm, arm64, mips
+Type: vcpu ioctl
+Parameters: struct kvm_reg_list (in/out)
+Returns: 0 on success; -1 on error
+Errors:
+ E2BIG: the reg index list is too big to fit in the array specified by
+ the user (the number required will be written into n).
+
+struct kvm_reg_list {
+ __u64 n; /* number of registers in reg[] */
+ __u64 reg[0];
+};
+
+This ioctl returns the guest registers that are supported for the
+KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
+
+
+4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
+
+Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
+Architectures: arm, arm64
+Type: vm ioctl
+Parameters: struct kvm_arm_device_address (in)
+Returns: 0 on success, -1 on error
+Errors:
+ ENODEV: The device id is unknown
+ ENXIO: Device not supported on current system
+ EEXIST: Address already set
+ E2BIG: Address outside guest physical address space
+ EBUSY: Address overlaps with other device range
+
+struct kvm_arm_device_addr {
+ __u64 id;
+ __u64 addr;
+};
+
+Specify a device address in the guest's physical address space where guests
+can access emulated or directly exposed devices, which the host kernel needs
+to know about. The id field is an architecture specific identifier for a
+specific device.
+
+ARM/arm64 divides the id field into two parts, a device id and an
+address type id specific to the individual device.
+
+ bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
+ field: | 0x00000000 | device id | addr type id |
+
+ARM/arm64 currently only require this when using the in-kernel GIC
+support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
+as the device id. When setting the base address for the guest's
+mapping of the VGIC virtual CPU and distributor interface, the ioctl
+must be called after calling KVM_CREATE_IRQCHIP, but before calling
+KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
+base addresses will return -EEXIST.
+
+Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
+should be used instead.
+
+
+4.86 KVM_PPC_RTAS_DEFINE_TOKEN
+
+Capability: KVM_CAP_PPC_RTAS
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_rtas_token_args
+Returns: 0 on success, -1 on error
+
+Defines a token value for a RTAS (Run Time Abstraction Services)
+service in order to allow it to be handled in the kernel. The
+argument struct gives the name of the service, which must be the name
+of a service that has a kernel-side implementation. If the token
+value is non-zero, it will be associated with that service, and
+subsequent RTAS calls by the guest specifying that token will be
+handled by the kernel. If the token value is 0, then any token
+associated with the service will be forgotten, and subsequent RTAS
+calls by the guest for that service will be passed to userspace to be
+handled.
+
+4.87 KVM_SET_GUEST_DEBUG
+
+Capability: KVM_CAP_SET_GUEST_DEBUG
+Architectures: x86, s390, ppc, arm64
+Type: vcpu ioctl
+Parameters: struct kvm_guest_debug (in)
+Returns: 0 on success; -1 on error
+
+struct kvm_guest_debug {
+ __u32 control;
+ __u32 pad;
+ struct kvm_guest_debug_arch arch;
+};
+
+Set up the processor specific debug registers and configure vcpu for
+handling guest debug events. There are two parts to the structure, the
+first a control bitfield indicates the type of debug events to handle
+when running. Common control bits are:
+
+ - KVM_GUESTDBG_ENABLE: guest debugging is enabled
+ - KVM_GUESTDBG_SINGLESTEP: the next run should single-step
+
+The top 16 bits of the control field are architecture specific control
+flags which can include the following:
+
+ - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64]
+ - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390, arm64]
+ - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86]
+ - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86]
+ - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390]
+
+For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints
+are enabled in memory so we need to ensure breakpoint exceptions are
+correctly trapped and the KVM run loop exits at the breakpoint and not
+running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP
+we need to ensure the guest vCPUs architecture specific registers are
+updated to the correct (supplied) values.
+
+The second part of the structure is architecture specific and
+typically contains a set of debug registers.
+
+For arm64 the number of debug registers is implementation defined and
+can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
+KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
+indicating the number of supported registers.
+
+When debug events exit the main run loop with the reason
+KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
+structure containing architecture specific debug information.
+
+4.88 KVM_GET_EMULATED_CPUID
+
+Capability: KVM_CAP_EXT_EMUL_CPUID
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+ __u32 nent;
+ __u32 flags;
+ struct kvm_cpuid_entry2 entries[0];
+};
+
+The member 'flags' is used for passing flags from userspace.
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
+
+struct kvm_cpuid_entry2 {
+ __u32 function;
+ __u32 index;
+ __u32 flags;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features which are emulated by
+kvm.Userspace can use the information returned by this ioctl to query
+which features are emulated by kvm instead of being present natively.
+
+Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
+structure with the 'nent' field indicating the number of entries in
+the variable-size array 'entries'. If the number of entries is too low
+to describe the cpu capabilities, an error (E2BIG) is returned. If the
+number is too high, the 'nent' field is adjusted and an error (ENOMEM)
+is returned. If the number is just right, the 'nent' field is adjusted
+to the number of valid entries in the 'entries' array, which is then
+filled.
+
+The entries returned are the set CPUID bits of the respective features
+which kvm emulates, as returned by the CPUID instruction, with unknown
+or unsupported feature bits cleared.
+
+Features like x2apic, for example, may not be present in the host cpu
+but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
+emulated efficiently and thus not included here.
+
+The fields in each entry are defined as follows:
+
+ function: the eax value used to obtain the entry
+ index: the ecx value used to obtain the entry (for entries that are
+ affected by ecx)
+ flags: an OR of zero or more of the following:
+ KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
+ if the index field is valid
+ KVM_CPUID_FLAG_STATEFUL_FUNC:
+ if cpuid for this function returns different values for successive
+ invocations; there will be several entries with the same function,
+ all with this flag set
+ KVM_CPUID_FLAG_STATE_READ_NEXT:
+ for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
+ the first entry to be read by a cpu
+ eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+ this function/index combination
+
+4.89 KVM_S390_MEM_OP
+
+Capability: KVM_CAP_S390_MEM_OP
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_mem_op (in)
+Returns: = 0 on success,
+ < 0 on generic error (e.g. -EFAULT or -ENOMEM),
+ > 0 if an exception occurred while walking the page tables
+
+Read or write data from/to the logical (virtual) memory of a VCPU.
+
+Parameters are specified via the following structure:
+
+struct kvm_s390_mem_op {
+ __u64 gaddr; /* the guest address */
+ __u64 flags; /* flags */
+ __u32 size; /* amount of bytes */
+ __u32 op; /* type of operation */
+ __u64 buf; /* buffer in userspace */
+ __u8 ar; /* the access register number */
+ __u8 reserved[31]; /* should be set to 0 */
+};
+
+The type of operation is specified in the "op" field. It is either
+KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
+KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The
+KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check
+whether the corresponding memory access would create an access exception
+(without touching the data in the memory at the destination). In case an
+access exception occurred while walking the MMU tables of the guest, the
+ioctl returns a positive error number to indicate the type of exception.
+This exception is also raised directly at the corresponding VCPU if the
+flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field.
+
+The start address of the memory region has to be specified in the "gaddr"
+field, and the length of the region in the "size" field. "buf" is the buffer
+supplied by the userspace application where the read data should be written
+to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written
+is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL
+when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access
+register number to be used.
+
+The "reserved" field is meant for future extensions. It is not used by
+KVM with the currently defined set of flags.
+
+4.90 KVM_S390_GET_SKEYS
+
+Capability: KVM_CAP_S390_SKEYS
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_skeys
+Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
+ keys, negative value on error
+
+This ioctl is used to get guest storage key values on the s390
+architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
+
+struct kvm_s390_skeys {
+ __u64 start_gfn;
+ __u64 count;
+ __u64 skeydata_addr;
+ __u32 flags;
+ __u32 reserved[9];
+};
+
+The start_gfn field is the number of the first guest frame whose storage keys
+you want to get.
+
+The count field is the number of consecutive frames (starting from start_gfn)
+whose storage keys to get. The count field must be at least 1 and the maximum
+allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
+will cause the ioctl to return -EINVAL.
+
+The skeydata_addr field is the address to a buffer large enough to hold count
+bytes. This buffer will be filled with storage key data by the ioctl.
+
+4.91 KVM_S390_SET_SKEYS
+
+Capability: KVM_CAP_S390_SKEYS
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_skeys
+Returns: 0 on success, negative value on error
+
+This ioctl is used to set guest storage key values on the s390
+architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
+See section on KVM_S390_GET_SKEYS for struct definition.
+
+The start_gfn field is the number of the first guest frame whose storage keys
+you want to set.
+
+The count field is the number of consecutive frames (starting from start_gfn)
+whose storage keys to get. The count field must be at least 1 and the maximum
+allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
+will cause the ioctl to return -EINVAL.
+
+The skeydata_addr field is the address to a buffer containing count bytes of
+storage keys. Each byte in the buffer will be set as the storage key for a
+single frame starting at start_gfn for count frames.
+
+Note: If any architecturally invalid key value is found in the given data then
+the ioctl will return -EINVAL.
+
+4.92 KVM_S390_IRQ
+
+Capability: KVM_CAP_S390_INJECT_IRQ
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_irq (in)
+Returns: 0 on success, -1 on error
+Errors:
+ EINVAL: interrupt type is invalid
+ type is KVM_S390_SIGP_STOP and flag parameter is invalid value
+ type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
+ than the maximum of VCPUs
+ EBUSY: type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped
+ type is KVM_S390_SIGP_STOP and a stop irq is already pending
+ type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
+ is already pending
+
+Allows to inject an interrupt to the guest.
+
+Using struct kvm_s390_irq as a parameter allows
+to inject additional payload which is not
+possible via KVM_S390_INTERRUPT.
+
+Interrupt parameters are passed via kvm_s390_irq:
+
+struct kvm_s390_irq {
+ __u64 type;
+ union {
+ struct kvm_s390_io_info io;
+ struct kvm_s390_ext_info ext;
+ struct kvm_s390_pgm_info pgm;
+ struct kvm_s390_emerg_info emerg;
+ struct kvm_s390_extcall_info extcall;
+ struct kvm_s390_prefix_info prefix;
+ struct kvm_s390_stop_info stop;
+ struct kvm_s390_mchk_info mchk;
+ char reserved[64];
+ } u;
+};
+
+type can be one of the following:
+
+KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
+KVM_S390_PROGRAM_INT - program check; parameters in .pgm
+KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
+KVM_S390_RESTART - restart; no parameters
+KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
+KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
+KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
+KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
+KVM_S390_MCHK - machine check interrupt; parameters in .mchk
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
+4.94 KVM_S390_GET_IRQ_STATE
+
+Capability: KVM_CAP_S390_IRQ_STATE
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_irq_state (out)
+Returns: >= number of bytes copied into buffer,
+ -EINVAL if buffer size is 0,
+ -ENOBUFS if buffer size is too small to fit all pending interrupts,
+ -EFAULT if the buffer address was invalid
+
+This ioctl allows userspace to retrieve the complete state of all currently
+pending interrupts in a single buffer. Use cases include migration
+and introspection. The parameter structure contains the address of a
+userspace buffer and its length:
+
+struct kvm_s390_irq_state {
+ __u64 buf;
+ __u32 flags; /* will stay unused for compatibility reasons */
+ __u32 len;
+ __u32 reserved[4]; /* will stay unused for compatibility reasons */
+};
+
+Userspace passes in the above struct and for each pending interrupt a
+struct kvm_s390_irq is copied to the provided buffer.
+
+The structure contains a flags and a reserved field for future extensions. As
+the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and
+reserved, these fields can not be used in the future without breaking
+compatibility.
+
+If -ENOBUFS is returned the buffer provided was too small and userspace
+may retry with a bigger buffer.
+
+4.95 KVM_S390_SET_IRQ_STATE
+
+Capability: KVM_CAP_S390_IRQ_STATE
+Architectures: s390
+Type: vcpu ioctl
+Parameters: struct kvm_s390_irq_state (in)
+Returns: 0 on success,
+ -EFAULT if the buffer address was invalid,
+ -EINVAL for an invalid buffer length (see below),
+ -EBUSY if there were already interrupts pending,
+ errors occurring when actually injecting the
+ interrupt. See KVM_S390_IRQ.
+
+This ioctl allows userspace to set the complete state of all cpu-local
+interrupts currently pending for the vcpu. It is intended for restoring
+interrupt state after a migration. The input parameter is a userspace buffer
+containing a struct kvm_s390_irq_state:
+
+struct kvm_s390_irq_state {
+ __u64 buf;
+ __u32 flags; /* will stay unused for compatibility reasons */
+ __u32 len;
+ __u32 reserved[4]; /* will stay unused for compatibility reasons */
+};
+
+The restrictions for flags and reserved apply as well.
+(see KVM_S390_GET_IRQ_STATE)
+
+The userspace memory referenced by buf contains a struct kvm_s390_irq
+for each interrupt to be injected into the guest.
+If one of the interrupts could not be injected for some reason the
+ioctl aborts.
+
+len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
+and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
+which is the maximum number of possibly pending cpu-local interrupts.
+
+4.96 KVM_SMI
+
+Capability: KVM_CAP_X86_SMM
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+
+Queues an SMI on the thread's vcpu.
+
+4.97 KVM_CAP_PPC_MULTITCE
+
+Capability: KVM_CAP_PPC_MULTITCE
+Architectures: ppc
+Type: vm
+
+This capability means the kernel is capable of handling hypercalls
+H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
+space. This significantly accelerates DMA operations for PPC KVM guests.
+User space should expect that its handlers for these hypercalls
+are not going to be called if user space previously registered LIOBN
+in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
+
+In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
+user space might have to advertise it for the guest. For example,
+IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
+present in the "ibm,hypertas-functions" device-tree property.
+
+The hypercalls mentioned above may or may not be processed successfully
+in the kernel based fast path. If they can not be handled by the kernel,
+they will get passed on to user space. So user space still has to have
+an implementation for these despite the in kernel acceleration.
+
+This capability is always enabled.
+
+4.98 KVM_CREATE_SPAPR_TCE_64
+
+Capability: KVM_CAP_SPAPR_TCE_64
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce_64 (in)
+Returns: file descriptor for manipulating the created TCE table
+
+This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
+windows, described in 4.62 KVM_CREATE_SPAPR_TCE
+
+This capability uses extended struct in ioctl interface:
+
+/* for KVM_CAP_SPAPR_TCE_64 */
+struct kvm_create_spapr_tce_64 {
+ __u64 liobn;
+ __u32 page_shift;
+ __u32 flags;
+ __u64 offset; /* in pages */
+ __u64 size; /* in pages */
+};
+
+The aim of extension is to support an additional bigger DMA window with
+a variable page size.
+KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and
+a bus offset of the corresponding DMA window, @size and @offset are numbers
+of IOMMU pages.
+
+@flags are not used at the moment.
+
+The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.
+
+4.99 KVM_REINJECT_CONTROL
+
+Capability: KVM_CAP_REINJECT_CONTROL
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_reinject_control (in)
+Returns: 0 on success,
+ -EFAULT if struct kvm_reinject_control cannot be read,
+ -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
+
+i8254 (PIT) has two modes, reinject and !reinject. The default is reinject,
+where KVM queues elapsed i8254 ticks and monitors completion of interrupt from
+vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its
+interrupt whenever there isn't a pending interrupt from i8254.
+!reinject mode injects an interrupt as soon as a tick arrives.
+
+struct kvm_reinject_control {
+ __u8 pit_reinject;
+ __u8 reserved[31];
+};
+
+pit_reinject = 0 (!reinject mode) is recommended, unless running an old
+operating system that uses the PIT for timing (e.g. Linux 2.4.x).
+
+4.100 KVM_PPC_CONFIGURE_V3_MMU
+
+Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_ppc_mmuv3_cfg (in)
+Returns: 0 on success,
+ -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read,
+ -EINVAL if the configuration is invalid
+
+This ioctl controls whether the guest will use radix or HPT (hashed
+page table) translation, and sets the pointer to the process table for
+the guest.
+
+struct kvm_ppc_mmuv3_cfg {
+ __u64 flags;
+ __u64 process_table;
+};
+
+There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and
+KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest
+to use radix tree translation, and if clear, to use HPT translation.
+KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest
+to be able to use the global TLB and SLB invalidation instructions;
+if clear, the guest may not use these instructions.
+
+The process_table field specifies the address and size of the guest
+process table, which is in the guest's space. This field is formatted
+as the second doubleword of the partition table entry, as defined in
+the Power ISA V3.00, Book III section 5.7.6.1.
+
+4.101 KVM_PPC_GET_RMMU_INFO
+
+Capability: KVM_CAP_PPC_RADIX_MMU
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_ppc_rmmu_info (out)
+Returns: 0 on success,
+ -EFAULT if struct kvm_ppc_rmmu_info cannot be written,
+ -EINVAL if no useful information can be returned
+
+This ioctl returns a structure containing two things: (a) a list
+containing supported radix tree geometries, and (b) a list that maps
+page sizes to put in the "AP" (actual page size) field for the tlbie
+(TLB invalidate entry) instruction.
+
+struct kvm_ppc_rmmu_info {
+ struct kvm_ppc_radix_geom {
+ __u8 page_shift;
+ __u8 level_bits[4];
+ __u8 pad[3];
+ } geometries[8];
+ __u32 ap_encodings[8];
+};
+
+The geometries[] field gives up to 8 supported geometries for the
+radix page table, in terms of the log base 2 of the smallest page
+size, and the number of bits indexed at each level of the tree, from
+the PTE level up to the PGD level in that order. Any unused entries
+will have 0 in the page_shift field.
+
+The ap_encodings gives the supported page sizes and their AP field
+encodings, encoded with the AP value in the top 3 bits and the log
+base 2 of the page size in the bottom 6 bits.
+
+4.102 KVM_PPC_RESIZE_HPT_PREPARE
+
+Capability: KVM_CAP_SPAPR_RESIZE_HPT
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_ppc_resize_hpt (in)
+Returns: 0 on successful completion,
+ >0 if a new HPT is being prepared, the value is an estimated
+ number of milliseconds until preparation is complete
+ -EFAULT if struct kvm_reinject_control cannot be read,
+ -EINVAL if the supplied shift or flags are invalid
+ -ENOMEM if unable to allocate the new HPT
+ -ENOSPC if there was a hash collision when moving existing
+ HPT entries to the new HPT
+ -EIO on other error conditions
+
+Used to implement the PAPR extension for runtime resizing of a guest's
+Hashed Page Table (HPT). Specifically this starts, stops or monitors
+the preparation of a new potential HPT for the guest, essentially
+implementing the H_RESIZE_HPT_PREPARE hypercall.
+
+If called with shift > 0 when there is no pending HPT for the guest,
+this begins preparation of a new pending HPT of size 2^(shift) bytes.
+It then returns a positive integer with the estimated number of
+milliseconds until preparation is complete.
+
+If called when there is a pending HPT whose size does not match that
+requested in the parameters, discards the existing pending HPT and
+creates a new one as above.
+
+If called when there is a pending HPT of the size requested, will:
+ * If preparation of the pending HPT is already complete, return 0
+ * If preparation of the pending HPT has failed, return an error
+ code, then discard the pending HPT.
+ * If preparation of the pending HPT is still in progress, return an
+ estimated number of milliseconds until preparation is complete.
+
+If called with shift == 0, discards any currently pending HPT and
+returns 0 (i.e. cancels any in-progress preparation).
+
+flags is reserved for future expansion, currently setting any bits in
+flags will result in an -EINVAL.
+
+Normally this will be called repeatedly with the same parameters until
+it returns <= 0. The first call will initiate preparation, subsequent
+ones will monitor preparation until it completes or fails.
+
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
+4.103 KVM_PPC_RESIZE_HPT_COMMIT
+
+Capability: KVM_CAP_SPAPR_RESIZE_HPT
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_ppc_resize_hpt (in)
+Returns: 0 on successful completion,
+ -EFAULT if struct kvm_reinject_control cannot be read,
+ -EINVAL if the supplied shift or flags are invalid
+ -ENXIO is there is no pending HPT, or the pending HPT doesn't
+ have the requested size
+ -EBUSY if the pending HPT is not fully prepared
+ -ENOSPC if there was a hash collision when moving existing
+ HPT entries to the new HPT
+ -EIO on other error conditions
+
+Used to implement the PAPR extension for runtime resizing of a guest's
+Hashed Page Table (HPT). Specifically this requests that the guest be
+transferred to working with the new HPT, essentially implementing the
+H_RESIZE_HPT_COMMIT hypercall.
+
+This should only be called after KVM_PPC_RESIZE_HPT_PREPARE has
+returned 0 with the same parameters. In other cases
+KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or
+-EBUSY, though others may be possible if the preparation was started,
+but failed).
+
+This will have undefined effects on the guest if it has not already
+placed itself in a quiescent state where no vcpu will make MMU enabled
+memory accesses.
+
+On succsful completion, the pending HPT will become the guest's active
+HPT and the previous HPT will be discarded.
+
+On failure, the guest will still be operating on its previous HPT.
+
+struct kvm_ppc_resize_hpt {
+ __u64 flags;
+ __u32 shift;
+ __u32 pad;
+};
+
+4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: system ioctl
+Parameters: u64 mce_cap (out)
+Returns: 0 on success, -1 on error
+
+Returns supported MCE capabilities. The u64 mce_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register. Supported
+capabilities will have the corresponding bits set.
+
+4.105 KVM_X86_SETUP_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: u64 mcg_cap (in)
+Returns: 0 on success,
+ -EFAULT if u64 mcg_cap cannot be read,
+ -EINVAL if the requested number of banks is invalid,
+ -EINVAL if requested MCE capability is not supported.
+
+Initializes MCE support for use. The u64 mcg_cap parameter
+has the same format as the MSR_IA32_MCG_CAP register and
+specifies which capabilities should be enabled. The maximum
+supported number of error-reporting banks can be retrieved when
+checking for KVM_CAP_MCE. The supported capabilities can be
+retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
+
+4.106 KVM_X86_SET_MCE
+
+Capability: KVM_CAP_MCE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_x86_mce (in)
+Returns: 0 on success,
+ -EFAULT if struct kvm_x86_mce cannot be read,
+ -EINVAL if the bank number is invalid,
+ -EINVAL if VAL bit is not set in status field.
+
+Inject a machine check error (MCE) into the guest. The input
+parameter is:
+
+struct kvm_x86_mce {
+ __u64 status;
+ __u64 addr;
+ __u64 misc;
+ __u64 mcg_status;
+ __u8 bank;
+ __u8 pad1[7];
+ __u64 pad2[3];
+};
+
+If the MCE being reported is an uncorrected error, KVM will
+inject it as an MCE exception into the guest. If the guest
+MCG_STATUS register reports that an MCE is in progress, KVM
+causes an KVM_EXIT_SHUTDOWN vmexit.
+
+Otherwise, if the MCE is a corrected error, KVM will just
+store it in the corresponding bank (provided this bank is
+not holding a previously reported uncorrected error).
+
+4.107 KVM_S390_GET_CMMA_BITS
+
+Capability: KVM_CAP_S390_CMMA_MIGRATION
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_cmma_log (in, out)
+Returns: 0 on success, a negative value on error
+
+This ioctl is used to get the values of the CMMA bits on the s390
+architecture. It is meant to be used in two scenarios:
+- During live migration to save the CMMA values. Live migration needs
+ to be enabled via the KVM_REQ_START_MIGRATION VM property.
+- To non-destructively peek at the CMMA values, with the flag
+ KVM_S390_CMMA_PEEK set.
+
+The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired
+values are written to a buffer whose location is indicated via the "values"
+member in the kvm_s390_cmma_log struct. The values in the input struct are
+also updated as needed.
+Each CMMA value takes up one byte.
+
+struct kvm_s390_cmma_log {
+ __u64 start_gfn;
+ __u32 count;
+ __u32 flags;
+ union {
+ __u64 remaining;
+ __u64 mask;
+ };
+ __u64 values;
+};
+
+start_gfn is the number of the first guest frame whose CMMA values are
+to be retrieved,
+
+count is the length of the buffer in bytes,
+
+values points to the buffer where the result will be written to.
+
+If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be
+KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with
+other ioctls.
+
+The result is written in the buffer pointed to by the field values, and
+the values of the input parameter are updated as follows.
+
+Depending on the flags, different actions are performed. The only
+supported flag so far is KVM_S390_CMMA_PEEK.
+
+The default behaviour if KVM_S390_CMMA_PEEK is not set is:
+start_gfn will indicate the first page frame whose CMMA bits were dirty.
+It is not necessarily the same as the one passed as input, as clean pages
+are skipped.
+
+count will indicate the number of bytes actually written in the buffer.
+It can (and very often will) be smaller than the input value, since the
+buffer is only filled until 16 bytes of clean values are found (which
+are then not copied in the buffer). Since a CMMA migration block needs
+the base address and the length, for a total of 16 bytes, we will send
+back some clean data if there is some dirty data afterwards, as long as
+the size of the clean data does not exceed the size of the header. This
+allows to minimize the amount of data to be saved or transferred over
+the network at the expense of more roundtrips to userspace. The next
+invocation of the ioctl will skip over all the clean values, saving
+potentially more than just the 16 bytes we found.
+
+If KVM_S390_CMMA_PEEK is set:
+the existing storage attributes are read even when not in migration
+mode, and no other action is performed;
+
+the output start_gfn will be equal to the input start_gfn,
+
+the output count will be equal to the input count, except if the end of
+memory has been reached.
+
+In both cases:
+the field "remaining" will indicate the total number of dirty CMMA values
+still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is
+not enabled.
+
+mask is unused.
+
+values points to the userspace buffer where the result will be stored.
+
+This ioctl can fail with -ENOMEM if not enough memory can be allocated to
+complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
+KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with
+-EFAULT if the userspace address is invalid or if no page table is
+present for the addresses (e.g. when using hugepages).
+
+4.108 KVM_S390_SET_CMMA_BITS
+
+Capability: KVM_CAP_S390_CMMA_MIGRATION
+Architectures: s390
+Type: vm ioctl
+Parameters: struct kvm_s390_cmma_log (in)
+Returns: 0 on success, a negative value on error
+
+This ioctl is used to set the values of the CMMA bits on the s390
+architecture. It is meant to be used during live migration to restore
+the CMMA values, but there are no restrictions on its use.
+The ioctl takes parameters via the kvm_s390_cmma_values struct.
+Each CMMA value takes up one byte.
+
+struct kvm_s390_cmma_log {
+ __u64 start_gfn;
+ __u32 count;
+ __u32 flags;
+ union {
+ __u64 remaining;
+ __u64 mask;
+ };
+ __u64 values;
+};
+
+start_gfn indicates the starting guest frame number,
+
+count indicates how many values are to be considered in the buffer,
+
+flags is not used and must be 0.
+
+mask indicates which PGSTE bits are to be considered.
+
+remaining is not used.
+
+values points to the buffer in userspace where to store the values.
+
+This ioctl can fail with -ENOMEM if not enough memory can be allocated to
+complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
+the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or
+if the flags field was not 0, with -EFAULT if the userspace address is
+invalid, if invalid pages are written to (e.g. after the end of memory)
+or if no page table is present for the addresses (e.g. when using
+hugepages).
+
+4.109 KVM_PPC_GET_CPU_CHAR
+
+Capability: KVM_CAP_PPC_GET_CPU_CHAR
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_ppc_cpu_char (out)
+Returns: 0 on successful completion
+ -EFAULT if struct kvm_ppc_cpu_char cannot be written
+
+This ioctl gives userspace information about certain characteristics
+of the CPU relating to speculative execution of instructions and
+possible information leakage resulting from speculative execution (see
+CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is
+returned in struct kvm_ppc_cpu_char, which looks like this:
+
+struct kvm_ppc_cpu_char {
+ __u64 character; /* characteristics of the CPU */
+ __u64 behaviour; /* recommended software behaviour */
+ __u64 character_mask; /* valid bits in character */
+ __u64 behaviour_mask; /* valid bits in behaviour */
+};
+
+For extensibility, the character_mask and behaviour_mask fields
+indicate which bits of character and behaviour have been filled in by
+the kernel. If the set of defined bits is extended in future then
+userspace will be able to tell whether it is running on a kernel that
+knows about the new bits.
+
+The character field describes attributes of the CPU which can help
+with preventing inadvertent information disclosure - specifically,
+whether there is an instruction to flash-invalidate the L1 data cache
+(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
+to a mode where entries can only be used by the thread that created
+them, whether the bcctr[l] instruction prevents speculation, and
+whether a speculation barrier instruction (ori 31,31,0) is provided.
+
+The behaviour field describes actions that software should take to
+prevent inadvertent information disclosure, and thus describes which
+vulnerabilities the hardware is subject to; specifically whether the
+L1 data cache should be flushed when returning to user mode from the
+kernel, and whether a speculation barrier should be placed between an
+array bounds check and the array access.
+
+These fields use the same bit definitions as the new
+H_GET_CPU_CHARACTERISTICS hypercall.
+
+4.110 KVM_MEMORY_ENCRYPT_OP
+
+Capability: basic
+Architectures: x86
+Type: system
+Parameters: an opaque platform specific structure (in/out)
+Returns: 0 on success; -1 on error
+
+If the platform supports creating encrypted VMs then this ioctl can be used
+for issuing platform-specific memory encryption commands to manage those
+encrypted VMs.
+
+Currently, this ioctl is used for issuing Secure Encrypted Virtualization
+(SEV) commands on AMD Processors. The SEV commands are defined in
+Documentation/virt/kvm/amd-memory-encryption.rst.
+
+4.111 KVM_MEMORY_ENCRYPT_REG_REGION
+
+Capability: basic
+Architectures: x86
+Type: system
+Parameters: struct kvm_enc_region (in)
+Returns: 0 on success; -1 on error
+
+This ioctl can be used to register a guest memory region which may
+contain encrypted data (e.g. guest RAM, SMRAM etc).
+
+It is used in the SEV-enabled guest. When encryption is enabled, a guest
+memory region may contain encrypted data. The SEV memory encryption
+engine uses a tweak such that two identical plaintext pages, each at
+different locations will have differing ciphertexts. So swapping or
+moving ciphertext of those pages will not result in plaintext being
+swapped. So relocating (or migrating) physical backing pages for the SEV
+guest will require some additional steps.
+
+Note: The current SEV key management spec does not provide commands to
+swap or migrate (move) ciphertext pages. Hence, for now we pin the guest
+memory region registered with the ioctl.
+
+4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION
+
+Capability: basic
+Architectures: x86
+Type: system
+Parameters: struct kvm_enc_region (in)
+Returns: 0 on success; -1 on error
+
+This ioctl can be used to unregister the guest memory region registered
+with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
+
+4.113 KVM_HYPERV_EVENTFD
+
+Capability: KVM_CAP_HYPERV_EVENTFD
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_hyperv_eventfd (in)
+
+This ioctl (un)registers an eventfd to receive notifications from the guest on
+the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
+causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number
+(bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
+
+struct kvm_hyperv_eventfd {
+ __u32 conn_id;
+ __s32 fd;
+ __u32 flags;
+ __u32 padding[3];
+};
+
+The conn_id field should fit within 24 bits:
+
+#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
+
+The acceptable values for the flags field are:
+
+#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
+
+Returns: 0 on success,
+ -EINVAL if conn_id or flags is outside the allowed range
+ -ENOENT on deassign if the conn_id isn't registered
+ -EEXIST on assign if the conn_id is already registered
+
+4.114 KVM_GET_NESTED_STATE
+
+Capability: KVM_CAP_NESTED_STATE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_nested_state (in/out)
+Returns: 0 on success, -1 on error
+Errors:
+ E2BIG: the total state size exceeds the value of 'size' specified by
+ the user; the size required will be written into size.
+
+struct kvm_nested_state {
+ __u16 flags;
+ __u16 format;
+ __u32 size;
+
+ union {
+ struct kvm_vmx_nested_state_hdr vmx;
+ struct kvm_svm_nested_state_hdr svm;
+
+ /* Pad the header to 128 bytes. */
+ __u8 pad[120];
+ } hdr;
+
+ union {
+ struct kvm_vmx_nested_state_data vmx[0];
+ struct kvm_svm_nested_state_data svm[0];
+ } data;
+};
+
+#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
+#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
+#define KVM_STATE_NESTED_EVMCS 0x00000004
+
+#define KVM_STATE_NESTED_FORMAT_VMX 0
+#define KVM_STATE_NESTED_FORMAT_SVM 1
+
+#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
+
+#define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001
+#define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002
+
+struct kvm_vmx_nested_state_hdr {
+ __u64 vmxon_pa;
+ __u64 vmcs12_pa;
+
+ struct {
+ __u16 flags;
+ } smm;
+};
+
+struct kvm_vmx_nested_state_data {
+ __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+ __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
+};
+
+This ioctl copies the vcpu's nested virtualization state from the kernel to
+userspace.
+
+The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE
+to the KVM_CHECK_EXTENSION ioctl().
+
+4.115 KVM_SET_NESTED_STATE
+
+Capability: KVM_CAP_NESTED_STATE
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_nested_state (in)
+Returns: 0 on success, -1 on error
+
+This copies the vcpu's kvm_nested_state struct from userspace to the kernel.
+For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
+
+4.116 KVM_(UN)REGISTER_COALESCED_MMIO
+
+Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
+ KVM_CAP_COALESCED_PIO (for coalesced pio)
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_coalesced_mmio_zone
+Returns: 0 on success, < 0 on error
+
+Coalesced I/O is a performance optimization that defers hardware
+register write emulation so that userspace exits are avoided. It is
+typically used to reduce the overhead of emulating frequently accessed
+hardware registers.
+
+When a hardware register is configured for coalesced I/O, write accesses
+do not exit to userspace and their value is recorded in a ring buffer
+that is shared between kernel and userspace.
+
+Coalesced I/O is used if one or more write accesses to a hardware
+register can be deferred until a read or a write to another hardware
+register on the same device. This last access will cause a vmexit and
+userspace will process accesses from the ring buffer before emulating
+it. That will avoid exiting to userspace on repeated writes.
+
+Coalesced pio is based on coalesced mmio. There is little difference
+between coalesced mmio and pio except that coalesced pio records accesses
+to I/O ports.
+
+4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
+
+Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
+Architectures: x86, arm, arm64, mips
+Type: vm ioctl
+Parameters: struct kvm_dirty_log (in)
+Returns: 0 on success, -1 on error
+
+/* for KVM_CLEAR_DIRTY_LOG */
+struct kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ void __user *dirty_bitmap; /* one bit per page */
+ __u64 padding;
+ };
+};
+
+The ioctl clears the dirty status of pages in a memory slot, according to
+the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
+field. Bit 0 of the bitmap corresponds to page "first_page" in the
+memory slot, and num_pages is the size in bits of the input bitmap.
+first_page must be a multiple of 64; num_pages must also be a multiple of
+64 unless first_page + num_pages is the size of the memory slot. For each
+bit that is set in the input bitmap, the corresponding page is marked "clean"
+in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
+(for example via write-protection, or by clearing the dirty bit in
+a page table entry).
+
+If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
+the address space for which you want to return the dirty bitmap.
+They must be less than the value that KVM_CHECK_EXTENSION returns for
+the KVM_CAP_MULTI_ADDRESS_SPACE capability.
+
+This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
+is enabled; for more information, see the description of the capability.
+However, it can always be used as long as KVM_CHECK_EXTENSION confirms
+that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present.
+
+4.118 KVM_GET_SUPPORTED_HV_CPUID
+
+Capability: KVM_CAP_HYPERV_CPUID
+Architectures: x86
+Type: vcpu ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+ __u32 nent;
+ __u32 padding;
+ struct kvm_cpuid_entry2 entries[0];
+};
+
+struct kvm_cpuid_entry2 {
+ __u32 function;
+ __u32 index;
+ __u32 flags;
+ __u32 eax;
+ __u32 ebx;
+ __u32 ecx;
+ __u32 edx;
+ __u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in
+KVM. Userspace can use the information returned by this ioctl to construct
+cpuid information presented to guests consuming Hyper-V enlightenments (e.g.
+Windows or Hyper-V guests).
+
+CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level
+Functional Specification (TLFS). These leaves can't be obtained with
+KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature
+leaves (0x40000000, 0x40000001).
+
+Currently, the following list of CPUID leaves are returned:
+ HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
+ HYPERV_CPUID_INTERFACE
+ HYPERV_CPUID_VERSION
+ HYPERV_CPUID_FEATURES
+ HYPERV_CPUID_ENLIGHTMENT_INFO
+ HYPERV_CPUID_IMPLEMENT_LIMITS
+ HYPERV_CPUID_NESTED_FEATURES
+
+HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
+enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
+
+Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
+with the 'nent' field indicating the number of entries in the variable-size
+array 'entries'. If the number of entries is too low to describe all Hyper-V
+feature leaves, an error (E2BIG) is returned. If the number is more or equal
+to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the
+number of valid entries in the 'entries' array, which is then filled.
+
+'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
+userspace should not expect to get any particular value there.
+
+4.119 KVM_ARM_VCPU_FINALIZE
+
+Architectures: arm, arm64
+Type: vcpu ioctl
+Parameters: int feature (in)
+Returns: 0 on success, -1 on error
+Errors:
+ EPERM: feature not enabled, needs configuration, or already finalized
+ EINVAL: feature unknown or not present
+
+Recognised values for feature:
+ arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE)
+
+Finalizes the configuration of the specified vcpu feature.
+
+The vcpu must already have been initialised, enabling the affected feature, by
+means of a successful KVM_ARM_VCPU_INIT call with the appropriate flag set in
+features[].
+
+For affected vcpu features, this is a mandatory step that must be performed
+before the vcpu is fully usable.
+
+Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be
+configured by use of ioctls such as KVM_SET_ONE_REG. The exact configuration
+that should be performaned and how to do it are feature-dependent.
+
+Other calls that depend on a particular feature being finalized, such as
+KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with
+-EPERM unless the feature has already been finalized by means of a
+KVM_ARM_VCPU_FINALIZE call.
+
+See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization
+using this ioctl.
+
+4.120 KVM_SET_PMU_EVENT_FILTER
+
+Capability: KVM_CAP_PMU_EVENT_FILTER
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_pmu_event_filter (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_pmu_event_filter {
+ __u32 action;
+ __u32 nevents;
+ __u32 fixed_counter_bitmap;
+ __u32 flags;
+ __u32 pad[4];
+ __u64 events[0];
+};
+
+This ioctl restricts the set of PMU events that the guest can program.
+The argument holds a list of events which will be allowed or denied.
+The eventsel+umask of each event the guest attempts to program is compared
+against the events field to determine whether the guest should have access.
+The events field only controls general purpose counters; fixed purpose
+counters are controlled by the fixed_counter_bitmap.
+
+No flags are defined yet, the field must be zero.
+
+Valid values for 'action':
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
+
+5. The kvm_run structure
+------------------------
+
+Application code obtains a pointer to the kvm_run structure by
+mmap()ing a vcpu fd. From that point, application code can control
+execution by changing fields in kvm_run prior to calling the KVM_RUN
+ioctl, and obtain information about the reason KVM_RUN returned by
+looking up structure members.
+
+struct kvm_run {
+ /* in */
+ __u8 request_interrupt_window;
+
+Request that KVM_RUN return when it becomes possible to inject external
+interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
+
+ __u8 immediate_exit;
+
+This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
+exits immediately, returning -EINTR. In the common scenario where a
+signal is used to "kick" a VCPU out of KVM_RUN, this field can be used
+to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability.
+Rather than blocking the signal outside KVM_RUN, userspace can set up
+a signal handler that sets run->immediate_exit to a non-zero value.
+
+This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available.
+
+ __u8 padding1[6];
+
+ /* out */
+ __u32 exit_reason;
+
+When KVM_RUN has returned successfully (return value 0), this informs
+application code why KVM_RUN has returned. Allowable values for this
+field are detailed below.
+
+ __u8 ready_for_interrupt_injection;
+
+If request_interrupt_window has been specified, this field indicates
+an interrupt can be injected now with KVM_INTERRUPT.
+
+ __u8 if_flag;
+
+The value of the current interrupt flag. Only valid if in-kernel
+local APIC is not used.
+
+ __u16 flags;
+
+More architecture-specific flags detailing state of the VCPU that may
+affect the device's behavior. The only currently defined flag is
+KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
+VCPU is in system management mode.
+
+ /* in (pre_kvm_run), out (post_kvm_run) */
+ __u64 cr8;
+
+The value of the cr8 register. Only valid if in-kernel local APIC is
+not used. Both input and output.
+
+ __u64 apic_base;
+
+The value of the APIC BASE msr. Only valid if in-kernel local
+APIC is not used. Both input and output.
+
+ union {
+ /* KVM_EXIT_UNKNOWN */
+ struct {
+ __u64 hardware_exit_reason;
+ } hw;
+
+If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
+reasons. Further architecture-specific information is available in
+hardware_exit_reason.
+
+ /* KVM_EXIT_FAIL_ENTRY */
+ struct {
+ __u64 hardware_entry_failure_reason;
+ } fail_entry;
+
+If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
+to unknown reasons. Further architecture-specific information is
+available in hardware_entry_failure_reason.
+
+ /* KVM_EXIT_EXCEPTION */
+ struct {
+ __u32 exception;
+ __u32 error_code;
+ } ex;
+
+Unused.
+
+ /* KVM_EXIT_IO */
+ struct {
+#define KVM_EXIT_IO_IN 0
+#define KVM_EXIT_IO_OUT 1
+ __u8 direction;
+ __u8 size; /* bytes */
+ __u16 port;
+ __u32 count;
+ __u64 data_offset; /* relative to kvm_run start */
+ } io;
+
+If exit_reason is KVM_EXIT_IO, then the vcpu has
+executed a port I/O instruction which could not be satisfied by kvm.
+data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
+where kvm expects application code to place the data for the next
+KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array.
+
+ /* KVM_EXIT_DEBUG */
+ struct {
+ struct kvm_debug_exit_arch arch;
+ } debug;
+
+If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
+for which architecture specific information is returned.
+
+ /* KVM_EXIT_MMIO */
+ struct {
+ __u64 phys_addr;
+ __u8 data[8];
+ __u32 len;
+ __u8 is_write;
+ } mmio;
+
+If exit_reason is KVM_EXIT_MMIO, then the vcpu has
+executed a memory-mapped I/O instruction which could not be satisfied
+by kvm. The 'data' member contains the written data if 'is_write' is
+true, and should be filled by application code otherwise.
+
+The 'data' member contains, in its first 'len' bytes, the value as it would
+appear if the VCPU performed a load or store of the appropriate width directly
+to the byte array.
+
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
+ KVM_EXIT_EPR the corresponding
+operations are complete (and guest state is consistent) only after userspace
+has re-entered the kernel with KVM_RUN. The kernel side will first finish
+incomplete operations and then check for pending signals. Userspace
+can re-enter the guest with an unmasked signal pending to complete
+pending operations.
+
+ /* KVM_EXIT_HYPERCALL */
+ struct {
+ __u64 nr;
+ __u64 args[6];
+ __u64 ret;
+ __u32 longmode;
+ __u32 pad;
+ } hypercall;
+
+Unused. This was once used for 'hypercall to userspace'. To implement
+such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
+Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
+
+ /* KVM_EXIT_TPR_ACCESS */
+ struct {
+ __u64 rip;
+ __u32 is_write;
+ __u32 pad;
+ } tpr_access;
+
+To be documented (KVM_TPR_ACCESS_REPORTING).
+
+ /* KVM_EXIT_S390_SIEIC */
+ struct {
+ __u8 icptcode;
+ __u64 mask; /* psw upper half */
+ __u64 addr; /* psw lower half */
+ __u16 ipa;
+ __u32 ipb;
+ } s390_sieic;
+
+s390 specific.
+
+ /* KVM_EXIT_S390_RESET */
+#define KVM_S390_RESET_POR 1
+#define KVM_S390_RESET_CLEAR 2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT 8
+#define KVM_S390_RESET_IPL 16
+ __u64 s390_reset_flags;
+
+s390 specific.
+
+ /* KVM_EXIT_S390_UCONTROL */
+ struct {
+ __u64 trans_exc_code;
+ __u32 pgm_code;
+ } s390_ucontrol;
+
+s390 specific. A page fault has occurred for a user controlled virtual
+machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
+resolved by the kernel.
+The program code and the translation exception code that were placed
+in the cpu's lowcore are presented here as defined by the z Architecture
+Principles of Operation Book in the Chapter for Dynamic Address Translation
+(DAT)
+
+ /* KVM_EXIT_DCR */
+ struct {
+ __u32 dcrn;
+ __u32 data;
+ __u8 is_write;
+ } dcr;
+
+Deprecated - was used for 440 KVM.
+
+ /* KVM_EXIT_OSI */
+ struct {
+ __u64 gprs[32];
+ } osi;
+
+MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
+hypercalls and exit with this exit struct that contains all the guest gprs.
+
+If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
+Userspace can now handle the hypercall and when it's done modify the gprs as
+necessary. Upon guest entry all guest GPRs will then be replaced by the values
+in this struct.
+
+ /* KVM_EXIT_PAPR_HCALL */
+ struct {
+ __u64 nr;
+ __u64 ret;
+ __u64 args[9];
+ } papr_hcall;
+
+This is used on 64-bit PowerPC when emulating a pSeries partition,
+e.g. with the 'pseries' machine type in qemu. It occurs when the
+guest does a hypercall using the 'sc 1' instruction. The 'nr' field
+contains the hypercall number (from the guest R3), and 'args' contains
+the arguments (from the guest R4 - R12). Userspace should put the
+return code in 'ret' and any extra returned values in args[].
+The possible hypercalls are defined in the Power Architecture Platform
+Requirements (PAPR) document available from www.power.org (free
+developer registration required to access it).
+
+ /* KVM_EXIT_S390_TSCH */
+ struct {
+ __u16 subchannel_id;
+ __u16 subchannel_nr;
+ __u32 io_int_parm;
+ __u32 io_int_word;
+ __u32 ipb;
+ __u8 dequeued;
+ } s390_tsch;
+
+s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
+and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
+interrupt for the target subchannel has been dequeued and subchannel_id,
+subchannel_nr, io_int_parm and io_int_word contain the parameters for that
+interrupt. ipb is needed for instruction parameter decoding.
+
+ /* KVM_EXIT_EPR */
+ struct {
+ __u32 epr;
+ } epr;
+
+On FSL BookE PowerPC chips, the interrupt controller has a fast patch
+interrupt acknowledge path to the core. When the core successfully
+delivers an interrupt, it automatically populates the EPR register with
+the interrupt vector number and acknowledges the interrupt inside
+the interrupt controller.
+
+In case the interrupt controller lives in user space, we need to do
+the interrupt acknowledge cycle through it to fetch the next to be
+delivered interrupt vector using this exit.
+
+It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
+external interrupt has just been delivered into the guest. User space
+should put the acknowledged interrupt vector into the 'epr' field.
+
+ /* KVM_EXIT_SYSTEM_EVENT */
+ struct {
+#define KVM_SYSTEM_EVENT_SHUTDOWN 1
+#define KVM_SYSTEM_EVENT_RESET 2
+#define KVM_SYSTEM_EVENT_CRASH 3
+ __u32 type;
+ __u64 flags;
+ } system_event;
+
+If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
+a system-level event using some architecture specific mechanism (hypercall
+or some special instruction). In case of ARM/ARM64, this is triggered using
+HVC instruction based PSCI call from the vcpu. The 'type' field describes
+the system-level event type. The 'flags' field describes architecture
+specific flags for the system-level event.
+
+Valid values for 'type' are:
+ KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
+ VM. Userspace is not obliged to honour this, and if it does honour
+ this does not need to destroy the VM synchronously (ie it may call
+ KVM_RUN again before shutdown finally occurs).
+ KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
+ As with SHUTDOWN, userspace can choose to ignore the request, or
+ to schedule the reset to occur in the future and may call KVM_RUN again.
+ KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
+ has requested a crash condition maintenance. Userspace can choose
+ to ignore the request, or to gather VM memory core dump and/or
+ reset/shutdown of the VM.
+
+ /* KVM_EXIT_IOAPIC_EOI */
+ struct {
+ __u8 vector;
+ } eoi;
+
+Indicates that the VCPU's in-kernel local APIC received an EOI for a
+level-triggered IOAPIC interrupt. This exit only triggers when the
+IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled);
+the userspace IOAPIC should process the EOI and retrigger the interrupt if
+it is still asserted. Vector is the LAPIC interrupt vector for which the
+EOI was received.
+
+ struct kvm_hyperv_exit {
+#define KVM_EXIT_HYPERV_SYNIC 1
+#define KVM_EXIT_HYPERV_HCALL 2
+ __u32 type;
+ union {
+ struct {
+ __u32 msr;
+ __u64 control;
+ __u64 evt_page;
+ __u64 msg_page;
+ } synic;
+ struct {
+ __u64 input;
+ __u64 result;
+ __u64 params[2];
+ } hcall;
+ } u;
+ };
+ /* KVM_EXIT_HYPERV */
+ struct kvm_hyperv_exit hyperv;
+Indicates that the VCPU exits into userspace to process some tasks
+related to Hyper-V emulation.
+Valid values for 'type' are:
+ KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
+Hyper-V SynIC state change. Notification is used to remap SynIC
+event/message pages and to enable/disable SynIC messages/events processing
+in userspace.
+
+ /* Fix the size of the union. */
+ char padding[256];
+ };
+
+ /*
+ * shared registers between kvm and userspace.
+ * kvm_valid_regs specifies the register classes set by the host
+ * kvm_dirty_regs specified the register classes dirtied by userspace
+ * struct kvm_sync_regs is architecture specific, as well as the
+ * bits for kvm_valid_regs and kvm_dirty_regs
+ */
+ __u64 kvm_valid_regs;
+ __u64 kvm_dirty_regs;
+ union {
+ struct kvm_sync_regs regs;
+ char padding[SYNC_REGS_SIZE_BYTES];
+ } s;
+
+If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
+certain guest registers without having to call SET/GET_*REGS. Thus we can
+avoid some system call overhead if userspace has to handle the exit.
+Userspace can query the validity of the structure by checking
+kvm_valid_regs for specific bits. These bits are architecture specific
+and usually define the validity of a groups of registers. (e.g. one bit
+ for general purpose registers)
+
+Please note that the kernel is allowed to use the kvm_run structure as the
+primary storage for certain register types. Therefore, the kernel may use the
+values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
+
+};
+
+
+
+6. Capabilities that can be enabled on vCPUs
+--------------------------------------------
+
+There are certain capabilities that change the behavior of the virtual CPU or
+the virtual machine when enabled. To enable them, please see section 4.37.
+Below you can find a list of capabilities and what their effect on the vCPU or
+the virtual machine is when enabling them.
+
+The following information is provided along with the description:
+
+ Architectures: which instruction set architectures provide this ioctl.
+ x86 includes both i386 and x86_64.
+
+ Target: whether this is a per-vcpu or per-vm capability.
+
+ Parameters: what parameters are accepted by the capability.
+
+ Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
+ are not detailed, but errors with specific meanings are.
+
+
+6.1 KVM_CAP_PPC_OSI
+
+Architectures: ppc
+Target: vcpu
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables interception of OSI hypercalls that otherwise would
+be treated as normal system calls to be injected into the guest. OSI hypercalls
+were invented by Mac-on-Linux to have a standardized communication mechanism
+between the guest and the host.
+
+When this capability is enabled, KVM_EXIT_OSI can occur.
+
+
+6.2 KVM_CAP_PPC_PAPR
+
+Architectures: ppc
+Target: vcpu
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables interception of PAPR hypercalls. PAPR hypercalls are
+done using the hypercall instruction "sc 1".
+
+It also sets the guest privilege level to "supervisor" mode. Usually the guest
+runs in "hypervisor" privilege mode with a few missing features.
+
+In addition to the above, it changes the semantics of SDR1. In this mode, the
+HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
+HTAB invisible to the guest.
+
+When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
+
+
+6.3 KVM_CAP_SW_TLB
+
+Architectures: ppc
+Target: vcpu
+Parameters: args[0] is the address of a struct kvm_config_tlb
+Returns: 0 on success; -1 on error
+
+struct kvm_config_tlb {
+ __u64 params;
+ __u64 array;
+ __u32 mmu_type;
+ __u32 array_len;
+};
+
+Configures the virtual CPU's TLB array, establishing a shared memory area
+between userspace and KVM. The "params" and "array" fields are userspace
+addresses of mmu-type-specific data structures. The "array_len" field is an
+safety mechanism, and should be set to the size in bytes of the memory that
+userspace has reserved for the array. It must be at least the size dictated
+by "mmu_type" and "params".
+
+While KVM_RUN is active, the shared region is under control of KVM. Its
+contents are undefined, and any modification by userspace results in
+boundedly undefined behavior.
+
+On return from KVM_RUN, the shared region will reflect the current state of
+the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB
+to tell KVM which entries have been changed, prior to calling KVM_RUN again
+on this vcpu.
+
+For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+ - The "params" field is of type "struct kvm_book3e_206_tlb_params".
+ - The "array" field points to an array of type "struct
+ kvm_book3e_206_tlb_entry".
+ - The array consists of all entries in the first TLB, followed by all
+ entries in the second TLB.
+ - Within a TLB, entries are ordered first by increasing set number. Within a
+ set, entries are ordered by way (increasing ESEL).
+ - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
+ where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
+ - The tsize field of mas1 shall be set to 4K on TLB0, even though the
+ hardware ignores this value for TLB0.
+
+6.4 KVM_CAP_S390_CSS_SUPPORT
+
+Architectures: s390
+Target: vcpu
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables support for handling of channel I/O instructions.
+
+TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
+handled in-kernel, while the other I/O instructions are passed to userspace.
+
+When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
+SUBCHANNEL intercepts.
+
+Note that even though this capability is enabled per-vcpu, the complete
+virtual machine is affected.
+
+6.5 KVM_CAP_PPC_EPR
+
+Architectures: ppc
+Target: vcpu
+Parameters: args[0] defines whether the proxy facility is active
+Returns: 0 on success; -1 on error
+
+This capability enables or disables the delivery of interrupts through the
+external proxy facility.
+
+When enabled (args[0] != 0), every time the guest gets an external interrupt
+delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
+to receive the topmost interrupt vector.
+
+When disabled (args[0] == 0), behavior is as if this facility is unsupported.
+
+When this capability is enabled, KVM_EXIT_EPR can occur.
+
+6.6 KVM_CAP_IRQ_MPIC
+
+Architectures: ppc
+Parameters: args[0] is the MPIC device fd
+ args[1] is the MPIC CPU number for this vcpu
+
+This capability connects the vcpu to an in-kernel MPIC device.
+
+6.7 KVM_CAP_IRQ_XICS
+
+Architectures: ppc
+Target: vcpu
+Parameters: args[0] is the XICS device fd
+ args[1] is the XICS CPU number (server ID) for this vcpu
+
+This capability connects the vcpu to an in-kernel XICS device.
+
+6.8 KVM_CAP_S390_IRQCHIP
+
+Architectures: s390
+Target: vm
+Parameters: none
+
+This capability enables the in-kernel irqchip for s390. Please refer to
+"4.24 KVM_CREATE_IRQCHIP" for details.
+
+6.9 KVM_CAP_MIPS_FPU
+
+Architectures: mips
+Target: vcpu
+Parameters: args[0] is reserved for future use (should be 0).
+
+This capability allows the use of the host Floating Point Unit by the guest. It
+allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is
+done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed
+(depending on the current guest FPU register mode), and the Status.FR,
+Config5.FRE bits are accessible via the KVM API and also from the guest,
+depending on them being supported by the FPU.
+
+6.10 KVM_CAP_MIPS_MSA
+
+Architectures: mips
+Target: vcpu
+Parameters: args[0] is reserved for future use (should be 0).
+
+This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
+It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest.
+Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
+accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
+the guest.
+
+6.74 KVM_CAP_SYNC_REGS
+Architectures: s390, x86
+Target: s390: always enabled, x86: vcpu
+Parameters: none
+Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
+sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
+
+As described above in the kvm_sync_regs struct info in section 5 (kvm_run):
+KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers
+without having to call SET/GET_*REGS". This reduces overhead by eliminating
+repeated ioctl calls for setting and/or getting register values. This is
+particularly important when userspace is making synchronous guest state
+modifications, e.g. when emulating and/or intercepting instructions in
+userspace.
+
+For s390 specifics, please refer to the source code.
+
+For x86:
+- the register sets to be copied out to kvm_run are selectable
+ by userspace (rather that all sets being copied out for every exit).
+- vcpu_events are available in addition to regs and sregs.
+
+For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to
+function as an input bit-array field set by userspace to indicate the
+specific register sets to be copied out on the next exit.
+
+To indicate when userspace has modified values that should be copied into
+the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set.
+This is done using the same bitflags as for the 'kvm_valid_regs' field.
+If the dirty bit is not set, then the register set values will not be copied
+into the vCPU even if they've been modified.
+
+Unused bitfields in the bitarrays must be set to zero.
+
+struct kvm_sync_regs {
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_vcpu_events events;
+};
+
+6.75 KVM_CAP_PPC_IRQ_XIVE
+
+Architectures: ppc
+Target: vcpu
+Parameters: args[0] is the XIVE device fd
+ args[1] is the XIVE CPU number (server ID) for this vcpu
+
+This capability connects the vcpu to an in-kernel XIVE device.
+
+7. Capabilities that can be enabled on VMs
+------------------------------------------
+
+There are certain capabilities that change the behavior of the virtual
+machine when enabled. To enable them, please see section 4.37. Below
+you can find a list of capabilities and what their effect on the VM
+is when enabling them.
+
+The following information is provided along with the description:
+
+ Architectures: which instruction set architectures provide this ioctl.
+ x86 includes both i386 and x86_64.
+
+ Parameters: what parameters are accepted by the capability.
+
+ Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
+ are not detailed, but errors with specific meanings are.
+
+
+7.1 KVM_CAP_PPC_ENABLE_HCALL
+
+Architectures: ppc
+Parameters: args[0] is the sPAPR hcall number
+ args[1] is 0 to disable, 1 to enable in-kernel handling
+
+This capability controls whether individual sPAPR hypercalls (hcalls)
+get handled by the kernel or not. Enabling or disabling in-kernel
+handling of an hcall is effective across the VM. On creation, an
+initial set of hcalls are enabled for in-kernel handling, which
+consists of those hcalls for which in-kernel handlers were implemented
+before this capability was implemented. If disabled, the kernel will
+not to attempt to handle the hcall, but will always exit to userspace
+to handle it. Note that it may not make sense to enable some and
+disable others of a group of related hcalls, but KVM does not prevent
+userspace from doing that.
+
+If the hcall number specified is not one that has an in-kernel
+implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
+error.
+
+7.2 KVM_CAP_S390_USER_SIGP
+
+Architectures: s390
+Parameters: none
+
+This capability controls which SIGP orders will be handled completely in user
+space. With this capability enabled, all fast orders will be handled completely
+in the kernel:
+- SENSE
+- SENSE RUNNING
+- EXTERNAL CALL
+- EMERGENCY SIGNAL
+- CONDITIONAL EMERGENCY SIGNAL
+
+All other orders will be handled completely in user space.
+
+Only privileged operation exceptions will be checked for in the kernel (or even
+in the hardware prior to interception). If this capability is not enabled, the
+old way of handling SIGP orders is used (partially in kernel and user space).
+
+7.3 KVM_CAP_S390_VECTOR_REGISTERS
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, negative value on error
+
+Allows use of the vector registers introduced with z13 processor, and
+provides for the synchronization between host and user space. Will
+return -EINVAL if the machine does not support vectors.
+
+7.4 KVM_CAP_S390_USER_STSI
+
+Architectures: s390
+Parameters: none
+
+This capability allows post-handlers for the STSI instruction. After
+initial handling in the kernel, KVM exits to user space with
+KVM_EXIT_S390_STSI to allow user space to insert further data.
+
+Before exiting to userspace, kvm handlers should fill in s390_stsi field of
+vcpu->run:
+struct {
+ __u64 addr;
+ __u8 ar;
+ __u8 reserved;
+ __u8 fc;
+ __u8 sel1;
+ __u16 sel2;
+} s390_stsi;
+
+@addr - guest address of STSI SYSIB
+@fc - function code
+@sel1 - selector 1
+@sel2 - selector 2
+@ar - access register number
+
+KVM handlers should exit to userspace with rc = -EREMOTE.
+
+7.5 KVM_CAP_SPLIT_IRQCHIP
+
+Architectures: x86
+Parameters: args[0] - number of routes reserved for userspace IOAPICs
+Returns: 0 on success, -1 on error
+
+Create a local apic for each processor in the kernel. This can be used
+instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
+IOAPIC and PIC (and also the PIT, even though this has to be enabled
+separately).
+
+This capability also enables in kernel routing of interrupt requests;
+when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
+used in the IRQ routing table. The first args[0] MSI routes are reserved
+for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes,
+a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
+
+Fails if VCPU has already been created, or if the irqchip is already in the
+kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
+
+7.6 KVM_CAP_S390_RI
+
+Architectures: s390
+Parameters: none
+
+Allows use of runtime-instrumentation introduced with zEC12 processor.
+Will return -EINVAL if the machine does not support runtime-instrumentation.
+Will return -EBUSY if a VCPU has already been created.
+
+7.7 KVM_CAP_X2APIC_API
+
+Architectures: x86
+Parameters: args[0] - features that should be enabled
+Returns: 0 on success, -EINVAL when args[0] contains invalid features
+
+Valid feature flags in args[0] are
+
+#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
+
+Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
+KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
+allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their
+respective sections.
+
+KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
+in logical mode or with more than 255 VCPUs. Otherwise, KVM treats 0xff
+as a broadcast even in x2APIC mode in order to support physical x2APIC
+without interrupt remapping. This is undesirable in logical mode,
+where 0xff represents CPUs 0-7 in cluster 0.
+
+7.8 KVM_CAP_S390_USER_INSTR0
+
+Architectures: s390
+Parameters: none
+
+With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
+be intercepted and forwarded to user space. User space can use this
+mechanism e.g. to realize 2-byte software breakpoints. The kernel will
+not inject an operating exception for these instructions, user space has
+to take care of that.
+
+This capability can be enabled dynamically even if VCPUs were already
+created and are running.
+
+7.9 KVM_CAP_S390_GS
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success; -EINVAL if the machine does not support
+ guarded storage; -EBUSY if a VCPU has already been created.
+
+Allows use of guarded storage for the KVM guest.
+
+7.10 KVM_CAP_S390_AIS
+
+Architectures: s390
+Parameters: none
+
+Allow use of adapter-interruption suppression.
+Returns: 0 on success; -EBUSY if a VCPU has already been created.
+
+7.11 KVM_CAP_PPC_SMT
+
+Architectures: ppc
+Parameters: vsmt_mode, flags
+
+Enabling this capability on a VM provides userspace with a way to set
+the desired virtual SMT mode (i.e. the number of virtual CPUs per
+virtual core). The virtual SMT mode, vsmt_mode, must be a power of 2
+between 1 and 8. On POWER8, vsmt_mode must also be no greater than
+the number of threads per subcore for the host. Currently flags must
+be 0. A successful call to enable this capability will result in
+vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is
+subsequently queried for the VM. This capability is only supported by
+HV KVM, and can only be set before any VCPUs have been created.
+The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT
+modes are available.
+
+7.12 KVM_CAP_PPC_FWNMI
+
+Architectures: ppc
+Parameters: none
+
+With this capability a machine check exception in the guest address
+space will cause KVM to exit the guest with NMI exit reason. This
+enables QEMU to build error log and branch to guest kernel registered
+machine check handling routine. Without this capability KVM will
+branch to guests' 0x200 interrupt vector.
+
+7.13 KVM_CAP_X86_DISABLE_EXITS
+
+Architectures: x86
+Parameters: args[0] defines which exits are disabled
+Returns: 0 on success, -EINVAL when args[0] contains invalid exits
+
+Valid bits in args[0] are
+
+#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
+#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
+
+Enabling this capability on a VM provides userspace with a way to no
+longer intercept some instructions for improved latency in some
+workloads, and is suggested when vCPUs are associated to dedicated
+physical CPUs. More bits can be added in the future; userspace can
+just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
+all such vmexits.
+
+Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
+
+7.14 KVM_CAP_S390_HPAGE_1M
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, -EINVAL if hpage module parameter was not set
+ or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL
+ flag set
+
+With this capability the KVM support for memory backing with 1m pages
+through hugetlbfs can be enabled for a VM. After the capability is
+enabled, cmma can't be enabled anymore and pfmfi and the storage key
+interpretation are disabled. If cmma has already been enabled or the
+hpage module parameter is not set to 1, -EINVAL is returned.
+
+While it is generally possible to create a huge page backed VM without
+this capability, the VM will not be able to run.
+
+7.15 KVM_CAP_MSR_PLATFORM_INFO
+
+Architectures: x86
+Parameters: args[0] whether feature should be enabled or not
+
+With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
+a #GP would be raised when the guest tries to access. Currently, this
+capability does not enable write permissions of this MSR for the guest.
+
+7.16 KVM_CAP_PPC_NESTED_HV
+
+Architectures: ppc
+Parameters: none
+Returns: 0 on success, -EINVAL when the implementation doesn't support
+ nested-HV virtualization.
+
+HV-KVM on POWER9 and later systems allows for "nested-HV"
+virtualization, which provides a way for a guest VM to run guests that
+can run using the CPU's supervisor mode (privileged non-hypervisor
+state). Enabling this capability on a VM depends on the CPU having
+the necessary functionality and on the facility being enabled with a
+kvm-hv module parameter.
+
+7.17 KVM_CAP_EXCEPTION_PAYLOAD
+
+Architectures: x86
+Parameters: args[0] whether feature should be enabled or not
+
+With this capability enabled, CR2 will not be modified prior to the
+emulated VM-exit when L1 intercepts a #PF exception that occurs in
+L2. Similarly, for kvm-intel only, DR6 will not be modified prior to
+the emulated VM-exit when L1 intercepts a #DB exception that occurs in
+L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or
+#DB) exception for L2, exception.has_payload will be set and the
+faulting address (or the new DR6 bits*) will be reported in the
+exception_payload field. Similarly, when userspace injects a #PF (or
+#DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set
+exception.has_payload and to put the faulting address (or the new DR6
+bits*) in the exception_payload field.
+
+This capability also enables exception.pending in struct
+kvm_vcpu_events, which allows userspace to distinguish between pending
+and injected exceptions.
+
+
+* For the new DR6 bits, note that bit 16 is set iff the #DB exception
+ will clear DR6.RTM.
+
+7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
+
+Architectures: x86, arm, arm64, mips
+Parameters: args[0] whether feature should be enabled or not
+
+With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
+clear and write-protect all pages that are returned as dirty.
+Rather, userspace will have to do this operation separately using
+KVM_CLEAR_DIRTY_LOG.
+
+At the cost of a slightly more complicated operation, this provides better
+scalability and responsiveness for two reasons. First,
+KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather
+than requiring to sync a full memslot; this ensures that KVM does not
+take spinlocks for an extended period of time. Second, in some cases a
+large amount of time can pass between a call to KVM_GET_DIRTY_LOG and
+userspace actually using the data in the page. Pages can be modified
+during this time, which is inefficint for both the guest and userspace:
+the guest will incur a higher penalty due to write protection faults,
+while userspace can see false reports of dirty pages. Manual reprotection
+helps reducing this time, improving guest performance and reducing the
+number of dirty log false positives.
+
+KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name
+KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make
+it hard or impossible to use it correctly. The availability of
+KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed.
+Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT.
+
+8. Other capabilities.
+----------------------
+
+This section lists capabilities that give information about other
+features of the KVM implementation.
+
+8.1 KVM_CAP_PPC_HWRNG
+
+Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel has an implementation of the
+H_RANDOM hypercall backed by a hardware random-number generator.
+If present, the kernel H_RANDOM handler can be enabled for guest use
+with the KVM_CAP_PPC_ENABLE_HCALL capability.
+
+8.2 KVM_CAP_HYPERV_SYNIC
+
+Architectures: x86
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel has an implementation of the
+Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
+used to support Windows Hyper-V based guest paravirt drivers(VMBus).
+
+In order to use SynIC, it has to be activated by setting this
+capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
+will disable the use of APIC hardware virtualization even if supported
+by the CPU, as it's incompatible with SynIC auto-EOI behavior.
+
+8.3 KVM_CAP_PPC_RADIX_MMU
+
+Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel can support guests using the
+radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
+processor).
+
+8.4 KVM_CAP_PPC_HASH_MMU_V3
+
+Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel can support guests using the
+hashed page table MMU defined in Power ISA V3.00 (as implemented in
+the POWER9 processor), including in-memory segment tables.
+
+8.5 KVM_CAP_MIPS_VZ
+
+Architectures: mips
+
+This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
+it is available, means that full hardware assisted virtualization capabilities
+of the hardware are available for use through KVM. An appropriate
+KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which
+utilises it.
+
+If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
+available, it means that the VM is using full hardware assisted virtualization
+capabilities of the hardware. This is useful to check after creating a VM with
+KVM_VM_MIPS_DEFAULT.
+
+The value returned by KVM_CHECK_EXTENSION should be compared against known
+values (see below). All other values are reserved. This is to allow for the
+possibility of other hardware assisted virtualization implementations which
+may be incompatible with the MIPS VZ ASE.
+
+ 0: The trap & emulate implementation is in use to run guest code in user
+ mode. Guest virtual memory segments are rearranged to fit the guest in the
+ user mode address space.
+
+ 1: The MIPS VZ ASE is in use, providing full hardware assisted
+ virtualization, including standard guest virtual memory segments.
+
+8.6 KVM_CAP_MIPS_TE
+
+Architectures: mips
+
+This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
+it is available, means that the trap & emulate implementation is available to
+run guest code in user mode, even if KVM_CAP_MIPS_VZ indicates that hardware
+assisted virtualisation is also available. KVM_VM_MIPS_TE (0) must be passed
+to KVM_CREATE_VM to create a VM which utilises it.
+
+If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
+available, it means that the VM is using trap & emulate.
+
+8.7 KVM_CAP_MIPS_64BIT
+
+Architectures: mips
+
+This capability indicates the supported architecture type of the guest, i.e. the
+supported register and address width.
+
+The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
+kvm VM handle correspond roughly to the CP0_Config.AT register field, and should
+be checked specifically against known values (see below). All other values are
+reserved.
+
+ 0: MIPS32 or microMIPS32.
+ Both registers and addresses are 32-bits wide.
+ It will only be possible to run 32-bit guest code.
+
+ 1: MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
+ Registers are 64-bits wide, but addresses are 32-bits wide.
+ 64-bit guest code may run but cannot access MIPS64 memory segments.
+ It will also be possible to run 32-bit guest code.
+
+ 2: MIPS64 or microMIPS64 with access to all address segments.
+ Both registers and addresses are 64-bits wide.
+ It will be possible to run 64-bit or 32-bit guest code.
+
+8.9 KVM_CAP_ARM_USER_IRQ
+
+Architectures: arm, arm64
+This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
+that if userspace creates a VM without an in-kernel interrupt controller, it
+will be notified of changes to the output level of in-kernel emulated devices,
+which can generate virtual interrupts, presented to the VM.
+For such VMs, on every return to userspace, the kernel
+updates the vcpu's run->s.regs.device_irq_level field to represent the actual
+output level of the device.
+
+Whenever kvm detects a change in the device output level, kvm guarantees at
+least one return to userspace before running the VM. This exit could either
+be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
+userspace can always sample the device output level and re-compute the state of
+the userspace interrupt controller. Userspace should always check the state
+of run->s.regs.device_irq_level on every kvm exit.
+The value in run->s.regs.device_irq_level can represent both level and edge
+triggered interrupt signals, depending on the device. Edge triggered interrupt
+signals will exit to userspace with the bit in run->s.regs.device_irq_level
+set exactly once per edge signal.
+
+The field run->s.regs.device_irq_level is available independent of
+run->kvm_valid_regs or run->kvm_dirty_regs bits.
+
+If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
+number larger than 0 indicating the version of this capability is implemented
+and thereby which bits in in run->s.regs.device_irq_level can signal values.
+
+Currently the following bits are defined for the device_irq_level bitmap:
+
+ KVM_CAP_ARM_USER_IRQ >= 1:
+
+ KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer
+ KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer
+ KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal
+
+Future versions of kvm may implement additional events. These will get
+indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
+listed above.
+
+8.10 KVM_CAP_PPC_SMT_POSSIBLE
+
+Architectures: ppc
+
+Querying this capability returns a bitmap indicating the possible
+virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N
+(counting from the right) is set, then a virtual SMT mode of 2^N is
+available.
+
+8.11 KVM_CAP_HYPERV_SYNIC2
+
+Architectures: x86
+
+This capability enables a newer version of Hyper-V Synthetic interrupt
+controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
+doesn't clear SynIC message and event flags pages when they are enabled by
+writing to the respective MSRs.
+
+8.12 KVM_CAP_HYPERV_VP_INDEX
+
+Architectures: x86
+
+This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its
+value is used to denote the target vcpu for a SynIC interrupt. For
+compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this
+capability is absent, userspace can still query this msr's value.
+
+8.13 KVM_CAP_S390_AIS_MIGRATION
+
+Architectures: s390
+Parameters: none
+
+This capability indicates if the flic device will be able to get/set the
+AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
+to discover this without having to create a flic device.
+
+8.14 KVM_CAP_S390_PSW
+
+Architectures: s390
+
+This capability indicates that the PSW is exposed via the kvm_run structure.
+
+8.15 KVM_CAP_S390_GMAP
+
+Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+be anywhere in the user memory address space, as long as the memory slots are
+aligned and sized to a segment (1MB) boundary.
+
+8.16 KVM_CAP_S390_COW
+
+Architectures: s390
+
+This capability indicates that the user space memory used as guest mapping can
+use copy-on-write semantics as well as dirty pages tracking via read-only page
+tables.
+
+8.17 KVM_CAP_S390_BPB
+
+Architectures: s390
+
+This capability indicates that kvm will implement the interfaces to handle
+reset, migration and nested KVM for branch prediction blocking. The stfle
+facility 82 should not be provided to the guest without this capability.
+
+8.18 KVM_CAP_HYPERV_TLBFLUSH
+
+Architectures: x86
+
+This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
+hypercalls:
+HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx,
+HvFlushVirtualAddressList, HvFlushVirtualAddressListEx.
+
+8.19 KVM_CAP_ARM_INJECT_SERROR_ESR
+
+Architectures: arm, arm64
+
+This capability indicates that userspace can specify (via the
+KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it
+takes a virtual SError interrupt exception.
+If KVM advertises this capability, userspace can only specify the ISS field for
+the ESR syndrome. Other parts of the ESR, such as the EC are generated by the
+CPU when the exception is taken. If this virtual SError is taken to EL1 using
+AArch64, this value will be reported in the ISS field of ESR_ELx.
+
+See KVM_CAP_VCPU_EVENTS for more details.
+8.20 KVM_CAP_HYPERV_SEND_IPI
+
+Architectures: x86
+
+This capability indicates that KVM supports paravirtualized Hyper-V IPI send
+hypercalls:
+HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
--- /dev/null
+* Internal ABI between the kernel and HYP
+
+This file documents the interaction between the Linux kernel and the
+hypervisor layer when running Linux as a hypervisor (for example
+KVM). It doesn't cover the interaction of the kernel with the
+hypervisor when running as a guest (under Xen, KVM or any other
+hypervisor), or any hypervisor-specific interaction when the kernel is
+used as a host.
+
+On arm and arm64 (without VHE), the kernel doesn't run in hypervisor
+mode, but still needs to interact with it, allowing a built-in
+hypervisor to be either installed or torn down.
+
+In order to achieve this, the kernel must be booted at HYP (arm) or
+EL2 (arm64), allowing it to install a set of stubs before dropping to
+SVC/EL1. These stubs are accessible by using a 'hvc #0' instruction,
+and only act on individual CPUs.
+
+Unless specified otherwise, any built-in hypervisor must implement
+these functions (see arch/arm{,64}/include/asm/virt.h):
+
+* r0/x0 = HVC_SET_VECTORS
+ r1/x1 = vectors
+
+ Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors'
+ must be a physical address, and respect the alignment requirements
+ of the architecture. Only implemented by the initial stubs, not by
+ Linux hypervisors.
+
+* r0/x0 = HVC_RESET_VECTORS
+
+ Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials
+ stubs' exception vector value. This effectively disables an existing
+ hypervisor.
+
+* r0/x0 = HVC_SOFT_RESTART
+ r1/x1 = restart address
+ x2 = x0's value when entering the next payload (arm64)
+ x3 = x1's value when entering the next payload (arm64)
+ x4 = x2's value when entering the next payload (arm64)
+
+ Mask all exceptions, disable the MMU, move the arguments into place
+ (arm64 only), and jump to the restart address while at HYP/EL2. This
+ hypercall is not expected to return to its caller.
+
+Any other value of r0/x0 triggers a hypervisor-specific handling,
+which is not documented here.
+
+The return value of a stub hypercall is held by r0/x0, and is 0 on
+success, and HVC_STUB_ERR on error. A stub hypercall is allowed to
+clobber any of the caller-saved registers (x0-x18 on arm64, r0-r3 and
+ip on arm). It is thus recommended to use a function call to perform
+the hypercall.
--- /dev/null
+KVM implements the PSCI (Power State Coordination Interface)
+specification in order to provide services such as CPU on/off, reset
+and power-off to the guest.
+
+The PSCI specification is regularly updated to provide new features,
+and KVM implements these updates if they make sense from a virtualization
+point of view.
+
+This means that a guest booted on two different versions of KVM can
+observe two different "firmware" revisions. This could cause issues if
+a given guest is tied to a particular PSCI revision (unlikely), or if
+a migration causes a different PSCI version to be exposed out of the
+blue to an unsuspecting guest.
+
+In order to remedy this situation, KVM exposes a set of "firmware
+pseudo-registers" that can be manipulated using the GET/SET_ONE_REG
+interface. These registers can be saved/restored by userspace, and set
+to a convenient value if required.
+
+The following register is defined:
+
+* KVM_REG_ARM_PSCI_VERSION:
+
+ - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set
+ (and thus has already been initialized)
+ - Returns the current PSCI version on GET_ONE_REG (defaulting to the
+ highest PSCI version implemented by KVM and compatible with v0.2)
+ - Allows any PSCI version implemented by KVM and compatible with
+ v0.2 to be set with SET_ONE_REG
+ - Affects the whole VM (even if the register view is per-vcpu)
+
+* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
+ Holds the state of the firmware support to mitigate CVE-2017-5715, as
+ offered by KVM to the guest via a HVC call. The workaround is described
+ under SMCCC_ARCH_WORKAROUND_1 in [1].
+ Accepted values are:
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: KVM does not offer
+ firmware support for the workaround. The mitigation status for the
+ guest is unknown.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: The workaround HVC call is
+ available to the guest and required for the mitigation.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: The workaround HVC call
+ is available to the guest, but it is not needed on this VCPU.
+
+* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
+ Holds the state of the firmware support to mitigate CVE-2018-3639, as
+ offered by KVM to the guest via a HVC call. The workaround is described
+ under SMCCC_ARCH_WORKAROUND_2 in [1].
+ Accepted values are:
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: A workaround is not
+ available. KVM does not offer firmware support for the workaround.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: The workaround state is
+ unknown. KVM does not offer firmware support for the workaround.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: The workaround is available,
+ and can be disabled by a vCPU. If
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for
+ this vCPU.
+ KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: The workaround is
+ always active on this vCPU or it is not needed.
+
+[1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+KVM CPUID bits
+==============
+
+:Author: Glauber Costa <glommer@gmail.com>
+
+A guest running on a kvm host, can check some of its features using
+cpuid. This is not always guaranteed to work, since userspace can
+mask-out some, or even all KVM-related cpuid features before launching
+a guest.
+
+KVM cpuid functions are:
+
+function: KVM_CPUID_SIGNATURE (0x40000000)
+
+returns::
+
+ eax = 0x40000001
+ ebx = 0x4b4d564b
+ ecx = 0x564b4d56
+ edx = 0x4d
+
+Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
+The value in eax corresponds to the maximum cpuid function present in this leaf,
+and will be updated if more functions are added in the future.
+Note also that old hosts set eax value to 0x0. This should
+be interpreted as if the value was 0x40000001.
+This function queries the presence of KVM cpuid leafs.
+
+function: define KVM_CPUID_FEATURES (0x40000001)
+
+returns::
+
+ ebx, ecx
+ eax = an OR'ed group of (1 << flag)
+
+where ``flag`` is defined as below:
+
+================================= =========== ================================
+flag value meaning
+================================= =========== ================================
+KVM_FEATURE_CLOCKSOURCE 0 kvmclock available at msrs
+ 0x11 and 0x12
+
+KVM_FEATURE_NOP_IO_DELAY 1 not necessary to perform delays
+ on PIO operations
+
+KVM_FEATURE_MMU_OP 2 deprecated
+
+KVM_FEATURE_CLOCKSOURCE2 3 kvmclock available at msrs
+
+ 0x4b564d00 and 0x4b564d01
+KVM_FEATURE_ASYNC_PF 4 async pf can be enabled by
+ writing to msr 0x4b564d02
+
+KVM_FEATURE_STEAL_TIME 5 steal time can be enabled by
+ writing to msr 0x4b564d03
+
+KVM_FEATURE_PV_EOI 6 paravirtualized end of interrupt
+ handler can be enabled by
+ writing to msr 0x4b564d04
+
+KVM_FEATURE_PV_UNHAULT 7 guest checks this feature bit
+ before enabling paravirtualized
+ spinlock support
+
+KVM_FEATURE_PV_TLB_FLUSH 9 guest checks this feature bit
+ before enabling paravirtualized
+ tlb flush
+
+KVM_FEATURE_ASYNC_PF_VMEXIT 10 paravirtualized async PF VM EXIT
+ can be enabled by setting bit 2
+ when writing to msr 0x4b564d02
+
+KVM_FEATURE_PV_SEND_IPI 11 guest checks this feature bit
+ before enabling paravirtualized
+ sebd IPIs
+
+KVM_FEATURE_PV_POLL_CONTROL 12 host-side polling on HLT can
+ be disabled by writing
+ to msr 0x4b564d05.
+
+KVM_FEATURE_PV_SCHED_YIELD 13 guest checks this feature bit
+ before using paravirtualized
+ sched yield.
+
+KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24 host will warn if no guest-side
+ per-cpu warps are expeced in
+ kvmclock
+================================= =========== ================================
+
+::
+
+ edx = an OR'ed group of (1 << flag)
+
+Where ``flag`` here is defined as below:
+
+================== ============ =================================
+flag value meaning
+================== ============ =================================
+KVM_HINTS_REALTIME 0 guest checks this feature bit to
+ determine that vCPUs are never
+ preempted for an unlimited time
+ allowing optimizations
+================== ============ =================================
--- /dev/null
+This directory contains specific device bindings for KVM_CAP_DEVICE_CTRL.
--- /dev/null
+ARM Virtual Interrupt Translation Service (ITS)
+===============================================
+
+Device types supported:
+ KVM_DEV_TYPE_ARM_VGIC_ITS ARM Interrupt Translation Service Controller
+
+The ITS allows MSI(-X) interrupts to be injected into guests. This extension is
+optional. Creating a virtual ITS controller also requires a host GICv3 (see
+arm-vgic-v3.txt), but does not depend on having physical ITS controllers.
+
+There can be multiple ITS controllers per guest, each of them has to have
+a separate, non-overlapping MMIO region.
+
+
+Groups:
+ KVM_DEV_ARM_VGIC_GRP_ADDR
+ Attributes:
+ KVM_VGIC_ITS_ADDR_TYPE (rw, 64-bit)
+ Base address in the guest physical address space of the GICv3 ITS
+ control register frame.
+ This address needs to be 64K aligned and the region covers 128K.
+ Errors:
+ -E2BIG: Address outside of addressable IPA range
+ -EINVAL: Incorrectly aligned address
+ -EEXIST: Address already configured
+ -EFAULT: Invalid user pointer for attr->addr.
+ -ENODEV: Incorrect attribute or the ITS is not supported.
+
+
+ KVM_DEV_ARM_VGIC_GRP_CTRL
+ Attributes:
+ KVM_DEV_ARM_VGIC_CTRL_INIT
+ request the initialization of the ITS, no additional parameter in
+ kvm_device_attr.addr.
+
+ KVM_DEV_ARM_ITS_CTRL_RESET
+ reset the ITS, no additional parameter in kvm_device_attr.addr.
+ See "ITS Reset State" section.
+
+ KVM_DEV_ARM_ITS_SAVE_TABLES
+ save the ITS table data into guest RAM, at the location provisioned
+ by the guest in corresponding registers/table entries.
+
+ The layout of the tables in guest memory defines an ABI. The entries
+ are laid out in little endian format as described in the last paragraph.
+
+ KVM_DEV_ARM_ITS_RESTORE_TABLES
+ restore the ITS tables from guest RAM to ITS internal structures.
+
+ The GICV3 must be restored before the ITS and all ITS registers but
+ the GITS_CTLR must be restored before restoring the ITS tables.
+
+ The GITS_IIDR read-only register must also be restored before
+ calling KVM_DEV_ARM_ITS_RESTORE_TABLES as the IIDR revision field
+ encodes the ABI revision.
+
+ The expected ordering when restoring the GICv3/ITS is described in section
+ "ITS Restore Sequence".
+
+ Errors:
+ -ENXIO: ITS not properly configured as required prior to setting
+ this attribute
+ -ENOMEM: Memory shortage when allocating ITS internal data
+ -EINVAL: Inconsistent restored data
+ -EFAULT: Invalid guest ram access
+ -EBUSY: One or more VCPUS are running
+ -EACCES: The virtual ITS is backed by a physical GICv4 ITS, and the
+ state is not available
+
+ KVM_DEV_ARM_VGIC_GRP_ITS_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes the offset of the
+ ITS register, relative to the ITS control frame base address
+ (ITS_base).
+
+ kvm_device_attr.addr points to a __u64 value whatever the width
+ of the addressed register (32/64 bits). 64 bit registers can only
+ be accessed with full length.
+
+ Writes to read-only registers are ignored by the kernel except for:
+ - GITS_CREADR. It must be restored otherwise commands in the queue
+ will be re-executed after restoring CWRITER. GITS_CREADR must be
+ restored before restoring the GITS_CTLR which is likely to enable the
+ ITS. Also it must be restored after GITS_CBASER since a write to
+ GITS_CBASER resets GITS_CREADR.
+ - GITS_IIDR. The Revision field encodes the table layout ABI revision.
+ In the future we might implement direct injection of virtual LPIs.
+ This will require an upgrade of the table layout and an evolution of
+ the ABI. GITS_IIDR must be restored before calling
+ KVM_DEV_ARM_ITS_RESTORE_TABLES.
+
+ For other registers, getting or setting a register has the same
+ effect as reading/writing the register on real hardware.
+ Errors:
+ -ENXIO: Offset does not correspond to any supported register
+ -EFAULT: Invalid user pointer for attr->addr
+ -EINVAL: Offset is not 64-bit aligned
+ -EBUSY: one or more VCPUS are running
+
+ ITS Restore Sequence:
+ -------------------------
+
+The following ordering must be followed when restoring the GIC and the ITS:
+a) restore all guest memory and create vcpus
+b) restore all redistributors
+c) provide the ITS base address
+ (KVM_DEV_ARM_VGIC_GRP_ADDR)
+d) restore the ITS in the following order:
+ 1. Restore GITS_CBASER
+ 2. Restore all other GITS_ registers, except GITS_CTLR!
+ 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES)
+ 4. Restore GITS_CTLR
+
+Then vcpus can be started.
+
+ ITS Table ABI REV0:
+ -------------------
+
+ Revision 0 of the ABI only supports the features of a virtual GICv3, and does
+ not support a virtual GICv4 with support for direct injection of virtual
+ interrupts for nested hypervisors.
+
+ The device table and ITT are indexed by the DeviceID and EventID,
+ respectively. The collection table is not indexed by CollectionID, and the
+ entries in the collection are listed in no particular order.
+ All entries are 8 bytes.
+
+ Device Table Entry (DTE):
+
+ bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 |
+ values: | V | next | ITT_addr | Size |
+
+ where;
+ - V indicates whether the entry is valid. If not, other fields
+ are not meaningful.
+ - next: equals to 0 if this entry is the last one; otherwise it
+ corresponds to the DeviceID offset to the next DTE, capped by
+ 2^14 -1.
+ - ITT_addr matches bits [51:8] of the ITT address (256 Byte aligned).
+ - Size specifies the supported number of bits for the EventID,
+ minus one
+
+ Collection Table Entry (CTE):
+
+ bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 |
+ values: | V | RES0 | RDBase | ICID |
+
+ where:
+ - V indicates whether the entry is valid. If not, other fields are
+ not meaningful.
+ - RES0: reserved field with Should-Be-Zero-or-Preserved behavior.
+ - RDBase is the PE number (GICR_TYPER.Processor_Number semantic),
+ - ICID is the collection ID
+
+ Interrupt Translation Entry (ITE):
+
+ bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 |
+ values: | next | pINTID | ICID |
+
+ where:
+ - next: equals to 0 if this entry is the last one; otherwise it corresponds
+ to the EventID offset to the next ITE capped by 2^16 -1.
+ - pINTID is the physical LPI ID; if zero, it means the entry is not valid
+ and other fields are not meaningful.
+ - ICID is the collection ID
+
+ ITS Reset State:
+ ----------------
+
+RESET returns the ITS to the same state that it was when first created and
+initialized. When the RESET command returns, the following things are
+guaranteed:
+
+- The ITS is not enabled and quiescent
+ GITS_CTLR.Enabled = 0 .Quiescent=1
+- There is no internally cached state
+- No collection or device table are used
+ GITS_BASER<n>.Valid = 0
+- GITS_CBASER = 0, GITS_CREADR = 0, GITS_CWRITER = 0
+- The ABI version is unchanged and remains the one set when the ITS
+ device was first created.
--- /dev/null
+ARM Virtual Generic Interrupt Controller v3 and later (VGICv3)
+==============================================================
+
+
+Device types supported:
+ KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0
+
+Only one VGIC instance may be instantiated through this API. The created VGIC
+will act as the VM interrupt controller, requiring emulated user-space devices
+to inject interrupts to the VGIC instead of directly to CPUs. It is not
+possible to create both a GICv3 and GICv2 on the same VM.
+
+Creating a guest GICv3 device requires a host GICv3 as well.
+
+
+Groups:
+ KVM_DEV_ARM_VGIC_GRP_ADDR
+ Attributes:
+ KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit)
+ Base address in the guest physical address space of the GICv3 distributor
+ register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
+ This address needs to be 64K aligned and the region covers 64 KByte.
+
+ KVM_VGIC_V3_ADDR_TYPE_REDIST (rw, 64-bit)
+ Base address in the guest physical address space of the GICv3
+ redistributor register mappings. There are two 64K pages for each
+ VCPU and all of the redistributor pages are contiguous.
+ Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
+ This address needs to be 64K aligned.
+
+ KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION (rw, 64-bit)
+ The attribute data pointed to by kvm_device_attr.addr is a __u64 value:
+ bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0
+ values: | count | base | flags | index
+ - index encodes the unique redistributor region index
+ - flags: reserved for future use, currently 0
+ - base field encodes bits [51:16] of the guest physical base address
+ of the first redistributor in the region.
+ - count encodes the number of redistributors in the region. Must be
+ greater than 0.
+ There are two 64K pages for each redistributor in the region and
+ redistributors are laid out contiguously within the region. Regions
+ are filled with redistributors in the index order. The sum of all
+ region count fields must be greater than or equal to the number of
+ VCPUs. Redistributor regions must be registered in the incremental
+ index order, starting from index 0.
+ The characteristics of a specific redistributor region can be read
+ by presetting the index field in the attr data.
+ Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
+
+ It is invalid to mix calls with KVM_VGIC_V3_ADDR_TYPE_REDIST and
+ KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes.
+
+ Errors:
+ -E2BIG: Address outside of addressable IPA range
+ -EINVAL: Incorrectly aligned address, bad redistributor region
+ count/index, mixed redistributor region attribute usage
+ -EEXIST: Address already configured
+ -ENOENT: Attempt to read the characteristics of a non existing
+ redistributor region
+ -ENXIO: The group or attribute is unknown/unsupported for this device
+ or hardware support is missing.
+ -EFAULT: Invalid user pointer for attr->addr.
+
+
+ KVM_DEV_ARM_VGIC_GRP_DIST_REGS
+ KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes two values:
+ bits: | 63 .... 32 | 31 .... 0 |
+ values: | mpidr | offset |
+
+ All distributor regs are (rw, 32-bit) and kvm_device_attr.addr points to a
+ __u32 value. 64-bit registers must be accessed by separately accessing the
+ lower and higher word.
+
+ Writes to read-only registers are ignored by the kernel.
+
+ KVM_DEV_ARM_VGIC_GRP_DIST_REGS accesses the main distributor registers.
+ KVM_DEV_ARM_VGIC_GRP_REDIST_REGS accesses the redistributor of the CPU
+ specified by the mpidr.
+
+ The offset is relative to the "[Re]Distributor base address" as defined
+ in the GICv3/4 specs. Getting or setting such a register has the same
+ effect as reading or writing the register on real hardware, except for the
+ following registers: GICD_STATUSR, GICR_STATUSR, GICD_ISPENDR,
+ GICR_ISPENDR0, GICD_ICPENDR, and GICR_ICPENDR0. These registers behave
+ differently when accessed via this interface compared to their
+ architecturally defined behavior to allow software a full view of the
+ VGIC's internal state.
+
+ The mpidr field is used to specify which
+ redistributor is accessed. The mpidr is ignored for the distributor.
+
+ The mpidr encoding is based on the affinity information in the
+ architecture defined MPIDR, and the field is encoded as follows:
+ | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
+ | Aff3 | Aff2 | Aff1 | Aff0 |
+
+ Note that distributor fields are not banked, but return the same value
+ regardless of the mpidr used to access the register.
+
+ GICD_IIDR.Revision is updated when the KVM implementation is changed in a
+ way directly observable by the guest or userspace. Userspace should read
+ GICD_IIDR from KVM and write back the read value to confirm its expected
+ behavior is aligned with the KVM implementation. Userspace should set
+ GICD_IIDR before setting any other registers to ensure the expected
+ behavior.
+
+
+ The GICD_STATUSR and GICR_STATUSR registers are architecturally defined such
+ that a write of a clear bit has no effect, whereas a write with a set bit
+ clears that value. To allow userspace to freely set the values of these two
+ registers, setting the attributes with the register offsets for these two
+ registers simply sets the non-reserved bits to the value written.
+
+
+ Accesses (reads and writes) to the GICD_ISPENDR register region and
+ GICR_ISPENDR0 registers get/set the value of the latched pending state for
+ the interrupts.
+
+ This is identical to the value returned by a guest read from ISPENDR for an
+ edge triggered interrupt, but may differ for level triggered interrupts.
+ For edge triggered interrupts, once an interrupt becomes pending (whether
+ because of an edge detected on the input line or because of a guest write
+ to ISPENDR) this state is "latched", and only cleared when either the
+ interrupt is activated or when the guest writes to ICPENDR. A level
+ triggered interrupt may be pending either because the level input is held
+ high by a device, or because of a guest write to the ISPENDR register. Only
+ ISPENDR writes are latched; if the device lowers the line level then the
+ interrupt is no longer pending unless the guest also wrote to ISPENDR, and
+ conversely writes to ICPENDR or activations of the interrupt do not clear
+ the pending status if the line level is still being held high. (These
+ rules are documented in the GICv3 specification descriptions of the ICPENDR
+ and ISPENDR registers.) For a level triggered interrupt the value accessed
+ here is that of the latch which is set by ISPENDR and cleared by ICPENDR or
+ interrupt activation, whereas the value returned by a guest read from
+ ISPENDR is the logical OR of the latch value and the input line level.
+
+ Raw access to the latch state is provided to userspace so that it can save
+ and restore the entire GIC internal state (which is defined by the
+ combination of the current input line level and the latch state, and cannot
+ be deduced from purely the line level and the value of the ISPENDR
+ registers).
+
+ Accesses to GICD_ICPENDR register region and GICR_ICPENDR0 registers have
+ RAZ/WI semantics, meaning that reads always return 0 and writes are always
+ ignored.
+
+ Errors:
+ -ENXIO: Getting or setting this register is not yet supported
+ -EBUSY: One or more VCPUs are running
+
+
+ KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS
+ Attributes:
+ The attr field of kvm_device_attr encodes two values:
+ bits: | 63 .... 32 | 31 .... 16 | 15 .... 0 |
+ values: | mpidr | RES | instr |
+
+ The mpidr field encodes the CPU ID based on the affinity information in the
+ architecture defined MPIDR, and the field is encoded as follows:
+ | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
+ | Aff3 | Aff2 | Aff1 | Aff0 |
+
+ The instr field encodes the system register to access based on the fields
+ defined in the A64 instruction set encoding for system register access
+ (RES means the bits are reserved for future use and should be zero):
+
+ | 15 ... 14 | 13 ... 11 | 10 ... 7 | 6 ... 3 | 2 ... 0 |
+ | Op 0 | Op1 | CRn | CRm | Op2 |
+
+ All system regs accessed through this API are (rw, 64-bit) and
+ kvm_device_attr.addr points to a __u64 value.
+
+ KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS accesses the CPU interface registers for the
+ CPU specified by the mpidr field.
+
+ CPU interface registers access is not implemented for AArch32 mode.
+ Error -ENXIO is returned when accessed in AArch32 mode.
+ Errors:
+ -ENXIO: Getting or setting this register is not yet supported
+ -EBUSY: VCPU is running
+ -EINVAL: Invalid mpidr or register value supplied
+
+
+ KVM_DEV_ARM_VGIC_GRP_NR_IRQS
+ Attributes:
+ A value describing the number of interrupts (SGI, PPI and SPI) for
+ this GIC instance, ranging from 64 to 1024, in increments of 32.
+
+ kvm_device_attr.addr points to a __u32 value.
+
+ Errors:
+ -EINVAL: Value set is out of the expected range
+ -EBUSY: Value has already be set.
+
+
+ KVM_DEV_ARM_VGIC_GRP_CTRL
+ Attributes:
+ KVM_DEV_ARM_VGIC_CTRL_INIT
+ request the initialization of the VGIC, no additional parameter in
+ kvm_device_attr.addr.
+ KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES
+ save all LPI pending bits into guest RAM pending tables.
+
+ The first kB of the pending table is not altered by this operation.
+ Errors:
+ -ENXIO: VGIC not properly configured as required prior to calling
+ this attribute
+ -ENODEV: no online VCPU
+ -ENOMEM: memory shortage when allocating vgic internal data
+ -EFAULT: Invalid guest ram access
+ -EBUSY: One or more VCPUS are running
+
+
+ KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO
+ Attributes:
+ The attr field of kvm_device_attr encodes the following values:
+ bits: | 63 .... 32 | 31 .... 10 | 9 .... 0 |
+ values: | mpidr | info | vINTID |
+
+ The vINTID specifies which set of IRQs is reported on.
+
+ The info field specifies which information userspace wants to get or set
+ using this interface. Currently we support the following info values:
+
+ VGIC_LEVEL_INFO_LINE_LEVEL:
+ Get/Set the input level of the IRQ line for a set of 32 contiguously
+ numbered interrupts.
+ vINTID must be a multiple of 32.
+
+ kvm_device_attr.addr points to a __u32 value which will contain a
+ bitmap where a set bit means the interrupt level is asserted.
+
+ Bit[n] indicates the status for interrupt vINTID + n.
+
+ SGIs and any interrupt with a higher ID than the number of interrupts
+ supported, will be RAZ/WI. LPIs are always edge-triggered and are
+ therefore not supported by this interface.
+
+ PPIs are reported per VCPU as specified in the mpidr field, and SPIs are
+ reported with the same value regardless of the mpidr specified.
+
+ The mpidr field encodes the CPU ID based on the affinity information in the
+ architecture defined MPIDR, and the field is encoded as follows:
+ | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
+ | Aff3 | Aff2 | Aff1 | Aff0 |
+ Errors:
+ -EINVAL: vINTID is not multiple of 32 or
+ info field is not VGIC_LEVEL_INFO_LINE_LEVEL
--- /dev/null
+ARM Virtual Generic Interrupt Controller v2 (VGIC)
+==================================================
+
+Device types supported:
+ KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0
+
+Only one VGIC instance may be instantiated through either this API or the
+legacy KVM_CREATE_IRQCHIP API. The created VGIC will act as the VM interrupt
+controller, requiring emulated user-space devices to inject interrupts to the
+VGIC instead of directly to CPUs.
+
+GICv3 implementations with hardware compatibility support allow creating a
+guest GICv2 through this interface. For information on creating a guest GICv3
+device and guest ITS devices, see arm-vgic-v3.txt. It is not possible to
+create both a GICv3 and GICv2 device on the same VM.
+
+
+Groups:
+ KVM_DEV_ARM_VGIC_GRP_ADDR
+ Attributes:
+ KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit)
+ Base address in the guest physical address space of the GIC distributor
+ register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
+ This address needs to be 4K aligned and the region covers 4 KByte.
+
+ KVM_VGIC_V2_ADDR_TYPE_CPU (rw, 64-bit)
+ Base address in the guest physical address space of the GIC virtual cpu
+ interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
+ This address needs to be 4K aligned and the region covers 4 KByte.
+ Errors:
+ -E2BIG: Address outside of addressable IPA range
+ -EINVAL: Incorrectly aligned address
+ -EEXIST: Address already configured
+ -ENXIO: The group or attribute is unknown/unsupported for this device
+ or hardware support is missing.
+ -EFAULT: Invalid user pointer for attr->addr.
+
+ KVM_DEV_ARM_VGIC_GRP_DIST_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes two values:
+ bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
+ values: | reserved | vcpu_index | offset |
+
+ All distributor regs are (rw, 32-bit)
+
+ The offset is relative to the "Distributor base address" as defined in the
+ GICv2 specs. Getting or setting such a register has the same effect as
+ reading or writing the register on the actual hardware from the cpu whose
+ index is specified with the vcpu_index field. Note that most distributor
+ fields are not banked, but return the same value regardless of the
+ vcpu_index used to access the register.
+
+ GICD_IIDR.Revision is updated when the KVM implementation of an emulated
+ GICv2 is changed in a way directly observable by the guest or userspace.
+ Userspace should read GICD_IIDR from KVM and write back the read value to
+ confirm its expected behavior is aligned with the KVM implementation.
+ Userspace should set GICD_IIDR before setting any other registers (both
+ KVM_DEV_ARM_VGIC_GRP_DIST_REGS and KVM_DEV_ARM_VGIC_GRP_CPU_REGS) to ensure
+ the expected behavior. Unless GICD_IIDR has been set from userspace, writes
+ to the interrupt group registers (GICD_IGROUPR) are ignored.
+ Errors:
+ -ENXIO: Getting or setting this register is not yet supported
+ -EBUSY: One or more VCPUs are running
+ -EINVAL: Invalid vcpu_index supplied
+
+ KVM_DEV_ARM_VGIC_GRP_CPU_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes two values:
+ bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
+ values: | reserved | vcpu_index | offset |
+
+ All CPU interface regs are (rw, 32-bit)
+
+ The offset specifies the offset from the "CPU interface base address" as
+ defined in the GICv2 specs. Getting or setting such a register has the
+ same effect as reading or writing the register on the actual hardware.
+
+ The Active Priorities Registers APRn are implementation defined, so we set a
+ fixed format for our implementation that fits with the model of a "GICv2
+ implementation without the security extensions" which we present to the
+ guest. This interface always exposes four register APR[0-3] describing the
+ maximum possible 128 preemption levels. The semantics of the register
+ indicate if any interrupts in a given preemption level are in the active
+ state by setting the corresponding bit.
+
+ Thus, preemption level X has one or more active interrupts if and only if:
+
+ APRn[X mod 32] == 0b1, where n = X / 32
+
+ Bits for undefined preemption levels are RAZ/WI.
+
+ Note that this differs from a CPU's view of the APRs on hardware in which
+ a GIC without the security extensions expose group 0 and group 1 active
+ priorities in separate register groups, whereas we show a combined view
+ similar to GICv2's GICH_APR.
+
+ For historical reasons and to provide ABI compatibility with userspace we
+ export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
+ field in the lower 5 bits of a word, meaning that userspace must always
+ use the lower 5 bits to communicate with the KVM device and must shift the
+ value left by 3 places to obtain the actual priority mask level.
+
+ Errors:
+ -ENXIO: Getting or setting this register is not yet supported
+ -EBUSY: One or more VCPUs are running
+ -EINVAL: Invalid vcpu_index supplied
+
+ KVM_DEV_ARM_VGIC_GRP_NR_IRQS
+ Attributes:
+ A value describing the number of interrupts (SGI, PPI and SPI) for
+ this GIC instance, ranging from 64 to 1024, in increments of 32.
+
+ Errors:
+ -EINVAL: Value set is out of the expected range
+ -EBUSY: Value has already be set, or GIC has already been initialized
+ with default values.
+
+ KVM_DEV_ARM_VGIC_GRP_CTRL
+ Attributes:
+ KVM_DEV_ARM_VGIC_CTRL_INIT
+ request the initialization of the VGIC or ITS, no additional parameter
+ in kvm_device_attr.addr.
+ Errors:
+ -ENXIO: VGIC not properly configured as required prior to calling
+ this attribute
+ -ENODEV: no online VCPU
+ -ENOMEM: memory shortage when allocating vgic internal data
--- /dev/null
+MPIC interrupt controller
+=========================
+
+Device types supported:
+ KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0
+ KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2
+
+Only one MPIC instance, of any type, may be instantiated. The created
+MPIC will act as the system interrupt controller, connecting to each
+vcpu's interrupt inputs.
+
+Groups:
+ KVM_DEV_MPIC_GRP_MISC
+ Attributes:
+ KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit)
+ Base address of the 256 KiB MPIC register space. Must be
+ naturally aligned. A value of zero disables the mapping.
+ Reset value is zero.
+
+ KVM_DEV_MPIC_GRP_REGISTER (rw, 32-bit)
+ Access an MPIC register, as if the access were made from the guest.
+ "attr" is the byte offset into the MPIC register space. Accesses
+ must be 4-byte aligned.
+
+ MSIs may be signaled by using this attribute group to write
+ to the relevant MSIIR.
+
+ KVM_DEV_MPIC_GRP_IRQ_ACTIVE (rw, 32-bit)
+ IRQ input line for each standard openpic source. 0 is inactive and 1
+ is active, regardless of interrupt sense.
+
+ For edge-triggered interrupts: Writing 1 is considered an activating
+ edge, and writing 0 is ignored. Reading returns 1 if a previously
+ signaled edge has not been acknowledged, and 0 otherwise.
+
+ "attr" is the IRQ number. IRQ numbers for standard sources are the
+ byte offset of the relevant IVPR from EIVPR0, divided by 32.
+
+IRQ Routing:
+
+ The MPIC emulation supports IRQ routing. Only a single MPIC device can
+ be instantiated. Once that device has been created, it's available as
+ irqchip id 0.
+
+ This irqchip 0 has 256 interrupt pins, which expose the interrupts in
+ the main array of interrupt sources (a.k.a. "SRC" interrupts).
+
+ The numbering is the same as the MPIC device tree binding -- based on
+ the register offset from the beginning of the sources array, without
+ regard to any subdivisions in chip documentation such as "internal"
+ or "external" interrupts.
+
+ Access to non-SRC interrupts is not implemented through IRQ routing mechanisms.
--- /dev/null
+FLIC (floating interrupt controller)
+====================================
+
+FLIC handles floating (non per-cpu) interrupts, i.e. I/O, service and some
+machine check interruptions. All interrupts are stored in a per-vm list of
+pending interrupts. FLIC performs operations on this list.
+
+Only one FLIC instance may be instantiated.
+
+FLIC provides support to
+- add interrupts (KVM_DEV_FLIC_ENQUEUE)
+- inspect currently pending interrupts (KVM_FLIC_GET_ALL_IRQS)
+- purge all pending floating interrupts (KVM_DEV_FLIC_CLEAR_IRQS)
+- purge one pending floating I/O interrupt (KVM_DEV_FLIC_CLEAR_IO_IRQ)
+- enable/disable for the guest transparent async page faults
+- register and modify adapter interrupt sources (KVM_DEV_FLIC_ADAPTER_*)
+- modify AIS (adapter-interruption-suppression) mode state (KVM_DEV_FLIC_AISM)
+- inject adapter interrupts on a specified adapter (KVM_DEV_FLIC_AIRQ_INJECT)
+- get/set all AIS mode states (KVM_DEV_FLIC_AISM_ALL)
+
+Groups:
+ KVM_DEV_FLIC_ENQUEUE
+ Passes a buffer and length into the kernel which are then injected into
+ the list of pending interrupts.
+ attr->addr contains the pointer to the buffer and attr->attr contains
+ the length of the buffer.
+ The format of the data structure kvm_s390_irq as it is copied from userspace
+ is defined in usr/include/linux/kvm.h.
+
+ KVM_DEV_FLIC_GET_ALL_IRQS
+ Copies all floating interrupts into a buffer provided by userspace.
+ When the buffer is too small it returns -ENOMEM, which is the indication
+ for userspace to try again with a bigger buffer.
+ -ENOBUFS is returned when the allocation of a kernelspace buffer has
+ failed.
+ -EFAULT is returned when copying data to userspace failed.
+ All interrupts remain pending, i.e. are not deleted from the list of
+ currently pending interrupts.
+ attr->addr contains the userspace address of the buffer into which all
+ interrupt data will be copied.
+ attr->attr contains the size of the buffer in bytes.
+
+ KVM_DEV_FLIC_CLEAR_IRQS
+ Simply deletes all elements from the list of currently pending floating
+ interrupts. No interrupts are injected into the guest.
+
+ KVM_DEV_FLIC_CLEAR_IO_IRQ
+ Deletes one (if any) I/O interrupt for a subchannel identified by the
+ subsystem identification word passed via the buffer specified by
+ attr->addr (address) and attr->attr (length).
+
+ KVM_DEV_FLIC_APF_ENABLE
+ Enables async page faults for the guest. So in case of a major page fault
+ the host is allowed to handle this async and continues the guest.
+
+ KVM_DEV_FLIC_APF_DISABLE_WAIT
+ Disables async page faults for the guest and waits until already pending
+ async page faults are done. This is necessary to trigger a completion interrupt
+ for every init interrupt before migrating the interrupt list.
+
+ KVM_DEV_FLIC_ADAPTER_REGISTER
+ Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter
+ describing the adapter to register:
+
+struct kvm_s390_io_adapter {
+ __u32 id;
+ __u8 isc;
+ __u8 maskable;
+ __u8 swap;
+ __u8 flags;
+};
+
+ id contains the unique id for the adapter, isc the I/O interruption subclass
+ to use, maskable whether this adapter may be masked (interrupts turned off),
+ swap whether the indicators need to be byte swapped, and flags contains
+ further characteristics of the adapter.
+ Currently defined values for 'flags' are:
+ - KVM_S390_ADAPTER_SUPPRESSIBLE: adapter is subject to AIS
+ (adapter-interrupt-suppression) facility. This flag only has an effect if
+ the AIS capability is enabled.
+ Unknown flag values are ignored.
+
+
+ KVM_DEV_FLIC_ADAPTER_MODIFY
+ Modifies attributes of an existing I/O adapter interrupt source. Takes
+ a kvm_s390_io_adapter_req specifying the adapter and the operation:
+
+struct kvm_s390_io_adapter_req {
+ __u32 id;
+ __u8 type;
+ __u8 mask;
+ __u16 pad0;
+ __u64 addr;
+};
+
+ id specifies the adapter and type the operation. The supported operations
+ are:
+
+ KVM_S390_IO_ADAPTER_MASK
+ mask or unmask the adapter, as specified in mask
+
+ KVM_S390_IO_ADAPTER_MAP
+ perform a gmap translation for the guest address provided in addr,
+ pin a userspace page for the translated address and add it to the
+ list of mappings
+ Note: A new mapping will be created unconditionally; therefore,
+ the calling code should avoid making duplicate mappings.
+
+ KVM_S390_IO_ADAPTER_UNMAP
+ release a userspace page for the translated address specified in addr
+ from the list of mappings
+
+ KVM_DEV_FLIC_AISM
+ modify the adapter-interruption-suppression mode for a given isc if the
+ AIS capability is enabled. Takes a kvm_s390_ais_req describing:
+
+struct kvm_s390_ais_req {
+ __u8 isc;
+ __u16 mode;
+};
+
+ isc contains the target I/O interruption subclass, mode the target
+ adapter-interruption-suppression mode. The following modes are
+ currently supported:
+ - KVM_S390_AIS_MODE_ALL: ALL-Interruptions Mode, i.e. airq injection
+ is always allowed;
+ - KVM_S390_AIS_MODE_SINGLE: SINGLE-Interruption Mode, i.e. airq
+ injection is only allowed once and the following adapter interrupts
+ will be suppressed until the mode is set again to ALL-Interruptions
+ or SINGLE-Interruption mode.
+
+ KVM_DEV_FLIC_AIRQ_INJECT
+ Inject adapter interrupts on a specified adapter.
+ attr->attr contains the unique id for the adapter, which allows for
+ adapter-specific checks and actions.
+ For adapters subject to AIS, handle the airq injection suppression for
+ an isc according to the adapter-interruption-suppression mode on condition
+ that the AIS capability is enabled.
+
+ KVM_DEV_FLIC_AISM_ALL
+ Gets or sets the adapter-interruption-suppression mode for all ISCs. Takes
+ a kvm_s390_ais_all describing:
+
+struct kvm_s390_ais_all {
+ __u8 simm; /* Single-Interruption-Mode mask */
+ __u8 nimm; /* No-Interruption-Mode mask *
+};
+
+ simm contains Single-Interruption-Mode mask for all ISCs, nimm contains
+ No-Interruption-Mode mask for all ISCs. Each bit in simm and nimm corresponds
+ to an ISC (MSB0 bit 0 to ISC 0 and so on). The combination of simm bit and
+ nimm bit presents AIS mode for a ISC.
+
+ KVM_DEV_FLIC_AISM_ALL is indicated by KVM_CAP_S390_AIS_MIGRATION.
+
+Note: The KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR device ioctls executed on
+FLIC with an unknown group or attribute gives the error code EINVAL (instead of
+ENXIO, as specified in the API documentation). It is not possible to conclude
+that a FLIC operation is unavailable based on the error code resulting from a
+usage attempt.
+
+Note: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a zero
+schid is specified.
--- /dev/null
+Generic vcpu interface
+====================================
+
+The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct
+kvm_device_attr as other devices, but targets VCPU-wide settings and controls.
+
+The groups and attributes per virtual cpu, if any, are architecture specific.
+
+1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL
+Architectures: ARM64
+
+1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ
+Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
+ pointer to an int
+Returns: -EBUSY: The PMU overflow interrupt is already set
+ -ENXIO: The overflow interrupt not set when attempting to get it
+ -ENODEV: PMUv3 not supported
+ -EINVAL: Invalid PMU overflow interrupt number supplied or
+ trying to set the IRQ number without using an in-kernel
+ irqchip.
+
+A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
+number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
+type must be same for each vcpu. As a PPI, the interrupt number is the same for
+all vcpus, while as an SPI it must be a separate number per vcpu.
+
+1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
+Parameters: no additional parameter in kvm_device_attr.addr
+Returns: -ENODEV: PMUv3 not supported or GIC not initialized
+ -ENXIO: PMUv3 not properly configured or in-kernel irqchip not
+ configured as required prior to calling this attribute
+ -EBUSY: PMUv3 already initialized
+
+Request the initialization of the PMUv3. If using the PMUv3 with an in-kernel
+virtual GIC implementation, this must be done after initializing the in-kernel
+irqchip.
+
+
+2. GROUP: KVM_ARM_VCPU_TIMER_CTRL
+Architectures: ARM,ARM64
+
+2.1. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_VTIMER
+2.2. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_PTIMER
+Parameters: in kvm_device_attr.addr the address for the timer interrupt is a
+ pointer to an int
+Returns: -EINVAL: Invalid timer interrupt number
+ -EBUSY: One or more VCPUs has already run
+
+A value describing the architected timer interrupt number when connected to an
+in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the
+attribute overrides the default values (see below).
+
+KVM_ARM_VCPU_TIMER_IRQ_VTIMER: The EL1 virtual timer intid (default: 27)
+KVM_ARM_VCPU_TIMER_IRQ_PTIMER: The EL1 physical timer intid (default: 30)
+
+Setting the same PPI for different timers will prevent the VCPUs from running.
+Setting the interrupt number on a VCPU configures all VCPUs created at that
+time to use the number provided for a given timer, overwriting any previously
+configured values on other VCPUs. Userspace should configure the interrupt
+numbers on at least one VCPU after creating all VCPUs and before running any
+VCPUs.
--- /dev/null
+VFIO virtual device
+===================
+
+Device types supported:
+ KVM_DEV_TYPE_VFIO
+
+Only one VFIO instance may be created per VM. The created device
+tracks VFIO groups in use by the VM and features of those groups
+important to the correctness and acceleration of the VM. As groups
+are enabled and disabled for use by the VM, KVM should be updated
+about their presence. When registered with KVM, a reference to the
+VFIO-group is held by KVM.
+
+Groups:
+ KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_GROUP attributes:
+ KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+ kvm_device_attr.addr points to an int32_t file descriptor
+ for the VFIO group.
+ KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+ kvm_device_attr.addr points to an int32_t file descriptor
+ for the VFIO group.
+ KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
+ allocated by sPAPR KVM.
+ kvm_device_attr.addr points to a struct:
+
+ struct kvm_vfio_spapr_tce {
+ __s32 groupfd;
+ __s32 tablefd;
+ };
+
+ where
+ @groupfd is a file descriptor for a VFIO group;
+ @tablefd is a file descriptor for a TCE table allocated via
+ KVM_CREATE_SPAPR_TCE.
--- /dev/null
+Generic vm interface
+====================================
+
+The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
+KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same
+struct kvm_device_attr as other devices, but targets VM-wide settings
+and controls.
+
+The groups and attributes per virtual machine, if any, are architecture
+specific.
+
+1. GROUP: KVM_S390_VM_MEM_CTRL
+Architectures: s390
+
+1.1. ATTRIBUTE: KVM_S390_VM_MEM_ENABLE_CMMA
+Parameters: none
+Returns: -EBUSY if a vcpu is already defined, otherwise 0
+
+Enables Collaborative Memory Management Assist (CMMA) for the virtual machine.
+
+1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA
+Parameters: none
+Returns: -EINVAL if CMMA was not enabled
+ 0 otherwise
+
+Clear the CMMA status for all guest pages, so any pages the guest marked
+as unused are again used any may not be reclaimed by the host.
+
+1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE
+Parameters: in attr->addr the address for the new limit of guest memory
+Returns: -EFAULT if the given address is not accessible
+ -EINVAL if the virtual machine is of type UCONTROL
+ -E2BIG if the given guest memory is to big for that machine
+ -EBUSY if a vcpu is already defined
+ -ENOMEM if not enough memory is available for a new shadow guest mapping
+ 0 otherwise
+
+Allows userspace to query the actual limit and set a new limit for
+the maximum guest memory size. The limit will be rounded up to
+2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by
+the number of page table levels. In the case that there is no limit we will set
+the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX).
+
+2. GROUP: KVM_S390_VM_CPU_MODEL
+Architectures: s390
+
+2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o)
+
+Allows user space to retrieve machine and kvm specific cpu related information:
+
+struct kvm_s390_vm_cpu_machine {
+ __u64 cpuid; # CPUID of host
+ __u32 ibc; # IBC level range offered by host
+ __u8 pad[4];
+ __u64 fac_mask[256]; # set of cpu facilities enabled by KVM
+ __u64 fac_list[256]; # set of cpu facilities offered by host
+}
+
+Parameters: address of buffer to store the machine related cpu data
+ of type struct kvm_s390_vm_cpu_machine*
+Returns: -EFAULT if the given address is not accessible from kernel space
+ -ENOMEM if not enough memory is available to process the ioctl
+ 0 in case of success
+
+2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w)
+
+Allows user space to retrieve or request to change cpu related information for a vcpu:
+
+struct kvm_s390_vm_cpu_processor {
+ __u64 cpuid; # CPUID currently (to be) used by this vcpu
+ __u16 ibc; # IBC level currently (to be) used by this vcpu
+ __u8 pad[6];
+ __u64 fac_list[256]; # set of cpu facilities currently (to be) used
+ # by this vcpu
+}
+
+KVM does not enforce or limit the cpu model data in any form. Take the information
+retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration
+setups. Instruction interceptions triggered by additionally set facility bits that
+are not handled by KVM need to by imlemented in the VM driver code.
+
+Parameters: address of buffer to store/set the processor related cpu
+ data of type struct kvm_s390_vm_cpu_processor*.
+Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case)
+ -EFAULT if the given address is not accessible from kernel space
+ -ENOMEM if not enough memory is available to process the ioctl
+ 0 in case of success
+
+2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o)
+
+Allows user space to retrieve available cpu features. A feature is available if
+provided by the hardware and supported by kvm. In theory, cpu features could
+even be completely emulated by kvm.
+
+struct kvm_s390_vm_cpu_feat {
+ __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering
+};
+
+Parameters: address of a buffer to load the feature list from.
+Returns: -EFAULT if the given address is not accessible from kernel space.
+ 0 in case of success.
+
+2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w)
+
+Allows user space to retrieve or change enabled cpu features for all VCPUs of a
+VM. Features that are not available cannot be enabled.
+
+See 2.3. for a description of the parameter struct.
+
+Parameters: address of a buffer to store/load the feature list from.
+Returns: -EFAULT if the given address is not accessible from kernel space.
+ -EINVAL if a cpu feature that is not available is to be enabled.
+ -EBUSY if at least one VCPU has already been defined.
+ 0 in case of success.
+
+2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o)
+
+Allows user space to retrieve available cpu subfunctions without any filtering
+done by a set IBC. These subfunctions are indicated to the guest VCPU via
+query or "test bit" subfunctions and used e.g. by cpacf functions, plo and ptff.
+
+A subfunction block is only valid if KVM_S390_VM_CPU_MACHINE contains the
+STFL(E) bit introducing the affected instruction. If the affected instruction
+indicates subfunctions via a "query subfunction", the response block is
+contained in the returned struct. If the affected instruction
+indicates subfunctions via a "test bit" mechanism, the subfunction codes are
+contained in the returned struct in MSB 0 bit numbering.
+
+struct kvm_s390_vm_cpu_subfunc {
+ u8 plo[32]; # always valid (ESA/390 feature)
+ u8 ptff[16]; # valid with TOD-clock steering
+ u8 kmac[16]; # valid with Message-Security-Assist
+ u8 kmc[16]; # valid with Message-Security-Assist
+ u8 km[16]; # valid with Message-Security-Assist
+ u8 kimd[16]; # valid with Message-Security-Assist
+ u8 klmd[16]; # valid with Message-Security-Assist
+ u8 pckmo[16]; # valid with Message-Security-Assist-Extension 3
+ u8 kmctr[16]; # valid with Message-Security-Assist-Extension 4
+ u8 kmf[16]; # valid with Message-Security-Assist-Extension 4
+ u8 kmo[16]; # valid with Message-Security-Assist-Extension 4
+ u8 pcc[16]; # valid with Message-Security-Assist-Extension 4
+ u8 ppno[16]; # valid with Message-Security-Assist-Extension 5
+ u8 kma[16]; # valid with Message-Security-Assist-Extension 8
+ u8 kdsa[16]; # valid with Message-Security-Assist-Extension 9
+ u8 reserved[1792]; # reserved for future instructions
+};
+
+Parameters: address of a buffer to load the subfunction blocks from.
+Returns: -EFAULT if the given address is not accessible from kernel space.
+ 0 in case of success.
+
+2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w)
+
+Allows user space to retrieve or change cpu subfunctions to be indicated for
+all VCPUs of a VM. This attribute will only be available if kernel and
+hardware support are in place.
+
+The kernel uses the configured subfunction blocks for indication to
+the guest. A subfunction block will only be used if the associated STFL(E) bit
+has not been disabled by user space (so the instruction to be queried is
+actually available for the guest).
+
+As long as no data has been written, a read will fail. The IBC will be used
+to determine available subfunctions in this case, this will guarantee backward
+compatibility.
+
+See 2.5. for a description of the parameter struct.
+
+Parameters: address of a buffer to store/load the subfunction blocks from.
+Returns: -EFAULT if the given address is not accessible from kernel space.
+ -EINVAL when reading, if there was no write yet.
+ -EBUSY if at least one VCPU has already been defined.
+ 0 in case of success.
+
+3. GROUP: KVM_S390_VM_TOD
+Architectures: s390
+
+3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
+
+Allows user space to set/get the TOD clock extension (u8) (superseded by
+KVM_S390_VM_TOD_EXT).
+
+Parameters: address of a buffer in user space to store the data (u8) to
+Returns: -EFAULT if the given address is not accessible from kernel space
+ -EINVAL if setting the TOD clock extension to != 0 is not supported
+
+3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
+
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64).
+
+Parameters: address of a buffer in user space to store the data (u64) to
+Returns: -EFAULT if the given address is not accessible from kernel space
+
+3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
+also allows user space to get/set it. If the guest CPU model does not support
+it, it is stored as 0 and not allowed to be set to a value != 0.
+
+Parameters: address of a buffer in user space to store the data
+ (kvm_s390_vm_tod_clock) to
+Returns: -EFAULT if the given address is not accessible from kernel space
+ -EINVAL if setting the TOD clock extension to != 0 is not supported
+
+4. GROUP: KVM_S390_VM_CRYPTO
+Architectures: s390
+
+4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o)
+
+Allows user space to enable aes key wrapping, including generating a new
+wrapping key.
+
+Parameters: none
+Returns: 0
+
+4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o)
+
+Allows user space to enable dea key wrapping, including generating a new
+wrapping key.
+
+Parameters: none
+Returns: 0
+
+4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o)
+
+Allows user space to disable aes key wrapping, clearing the wrapping key.
+
+Parameters: none
+Returns: 0
+
+4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o)
+
+Allows user space to disable dea key wrapping, clearing the wrapping key.
+
+Parameters: none
+Returns: 0
+
+5. GROUP: KVM_S390_VM_MIGRATION
+Architectures: s390
+
+5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o)
+
+Allows userspace to stop migration mode, needed for PGSTE migration.
+Setting this attribute when migration mode is not active will have no
+effects.
+
+Parameters: none
+Returns: 0
+
+5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o)
+
+Allows userspace to start migration mode, needed for PGSTE migration.
+Setting this attribute when migration mode is already active will have
+no effects.
+
+Parameters: none
+Returns: -ENOMEM if there is not enough free memory to start migration mode
+ -EINVAL if the state of the VM is invalid (e.g. no memory defined)
+ 0 in case of success.
+
+5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o)
+
+Allows userspace to query the status of migration mode.
+
+Parameters: address of a buffer in user space to store the data (u64) to;
+ the data itself is either 0 if migration mode is disabled or 1
+ if it is enabled
+Returns: -EFAULT if the given address is not accessible from kernel space
+ 0 in case of success.
--- /dev/null
+XICS interrupt controller
+
+Device type supported: KVM_DEV_TYPE_XICS
+
+Groups:
+ KVM_DEV_XICS_SOURCES
+ Attributes: One per interrupt source, indexed by the source number.
+
+This device emulates the XICS (eXternal Interrupt Controller
+Specification) defined in PAPR. The XICS has a set of interrupt
+sources, each identified by a 20-bit source number, and a set of
+Interrupt Control Presentation (ICP) entities, also called "servers",
+each associated with a virtual CPU.
+
+The ICP entities are created by enabling the KVM_CAP_IRQ_ARCH
+capability for each vcpu, specifying KVM_CAP_IRQ_XICS in args[0] and
+the interrupt server number (i.e. the vcpu number from the XICS's
+point of view) in args[1] of the kvm_enable_cap struct. Each ICP has
+64 bits of state which can be read and written using the
+KVM_GET_ONE_REG and KVM_SET_ONE_REG ioctls on the vcpu. The 64 bit
+state word has the following bitfields, starting at the
+least-significant end of the word:
+
+* Unused, 16 bits
+
+* Pending interrupt priority, 8 bits
+ Zero is the highest priority, 255 means no interrupt is pending.
+
+* Pending IPI (inter-processor interrupt) priority, 8 bits
+ Zero is the highest priority, 255 means no IPI is pending.
+
+* Pending interrupt source number, 24 bits
+ Zero means no interrupt pending, 2 means an IPI is pending
+
+* Current processor priority, 8 bits
+ Zero is the highest priority, meaning no interrupts can be
+ delivered, and 255 is the lowest priority.
+
+Each source has 64 bits of state that can be read and written using
+the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the
+KVM_DEV_XICS_SOURCES attribute group, with the attribute number being
+the interrupt source number. The 64 bit state word has the following
+bitfields, starting from the least-significant end of the word:
+
+* Destination (server number), 32 bits
+ This specifies where the interrupt should be sent, and is the
+ interrupt server number specified for the destination vcpu.
+
+* Priority, 8 bits
+ This is the priority specified for this interrupt source, where 0 is
+ the highest priority and 255 is the lowest. An interrupt with a
+ priority of 255 will never be delivered.
+
+* Level sensitive flag, 1 bit
+ This bit is 1 for a level-sensitive interrupt source, or 0 for
+ edge-sensitive (or MSI).
+
+* Masked flag, 1 bit
+ This bit is set to 1 if the interrupt is masked (cannot be delivered
+ regardless of its priority), for example by the ibm,int-off RTAS
+ call, or 0 if it is not masked.
+
+* Pending flag, 1 bit
+ This bit is 1 if the source has a pending interrupt, otherwise 0.
+
+Only one XICS instance may be created per VM.
--- /dev/null
+POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1)
+==========================================================
+
+Device types supported:
+ KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1
+
+This device acts as a VM interrupt controller. It provides the KVM
+interface to configure the interrupt sources of a VM in the underlying
+POWER9 XIVE interrupt controller.
+
+Only one XIVE instance may be instantiated. A guest XIVE device
+requires a POWER9 host and the guest OS should have support for the
+XIVE native exploitation interrupt mode. If not, it should run using
+the legacy interrupt mode, referred as XICS (POWER7/8).
+
+* Device Mappings
+
+ The KVM device exposes different MMIO ranges of the XIVE HW which
+ are required for interrupt management. These are exposed to the
+ guest in VMAs populated with a custom VM fault handler.
+
+ 1. Thread Interrupt Management Area (TIMA)
+
+ Each thread has an associated Thread Interrupt Management context
+ composed of a set of registers. These registers let the thread
+ handle priority management and interrupt acknowledgment. The most
+ important are :
+
+ - Interrupt Pending Buffer (IPB)
+ - Current Processor Priority (CPPR)
+ - Notification Source Register (NSR)
+
+ They are exposed to software in four different pages each proposing
+ a view with a different privilege. The first page is for the
+ physical thread context and the second for the hypervisor. Only the
+ third (operating system) and the fourth (user level) are exposed the
+ guest.
+
+ 2. Event State Buffer (ESB)
+
+ Each source is associated with an Event State Buffer (ESB) with
+ either a pair of even/odd pair of pages which provides commands to
+ manage the source: to trigger, to EOI, to turn off the source for
+ instance.
+
+ 3. Device pass-through
+
+ When a device is passed-through into the guest, the source
+ interrupts are from a different HW controller (PHB4) and the ESB
+ pages exposed to the guest should accommadate this change.
+
+ The passthru_irq helpers, kvmppc_xive_set_mapped() and
+ kvmppc_xive_clr_mapped() are called when the device HW irqs are
+ mapped into or unmapped from the guest IRQ number space. The KVM
+ device extends these helpers to clear the ESB pages of the guest IRQ
+ number being mapped and then lets the VM fault handler repopulate.
+ The handler will insert the ESB page corresponding to the HW
+ interrupt of the device being passed-through or the initial IPI ESB
+ page if the device has being removed.
+
+ The ESB remapping is fully transparent to the guest and the OS
+ device driver. All handling is done within VFIO and the above
+ helpers in KVM-PPC.
+
+* Groups:
+
+ 1. KVM_DEV_XIVE_GRP_CTRL
+ Provides global controls on the device
+ Attributes:
+ 1.1 KVM_DEV_XIVE_RESET (write only)
+ Resets the interrupt controller configuration for sources and event
+ queues. To be used by kexec and kdump.
+ Errors: none
+
+ 1.2 KVM_DEV_XIVE_EQ_SYNC (write only)
+ Sync all the sources and queues and mark the EQ pages dirty. This
+ to make sure that a consistent memory state is captured when
+ migrating the VM.
+ Errors: none
+
+ 2. KVM_DEV_XIVE_GRP_SOURCE (write only)
+ Initializes a new source in the XIVE device and mask it.
+ Attributes:
+ Interrupt source number (64-bit)
+ The kvm_device_attr.addr points to a __u64 value:
+ bits: | 63 .... 2 | 1 | 0
+ values: | unused | level | type
+ - type: 0:MSI 1:LSI
+ - level: assertion level in case of an LSI.
+ Errors:
+ -E2BIG: Interrupt source number is out of range
+ -ENOMEM: Could not create a new source block
+ -EFAULT: Invalid user pointer for attr->addr.
+ -ENXIO: Could not allocate underlying HW interrupt
+
+ 3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only)
+ Configures source targeting
+ Attributes:
+ Interrupt source number (64-bit)
+ The kvm_device_attr.addr points to a __u64 value:
+ bits: | 63 .... 33 | 32 | 31 .. 3 | 2 .. 0
+ values: | eisn | mask | server | priority
+ - priority: 0-7 interrupt priority level
+ - server: CPU number chosen to handle the interrupt
+ - mask: mask flag (unused)
+ - eisn: Effective Interrupt Source Number
+ Errors:
+ -ENOENT: Unknown source number
+ -EINVAL: Not initialized source number
+ -EINVAL: Invalid priority
+ -EINVAL: Invalid CPU number.
+ -EFAULT: Invalid user pointer for attr->addr.
+ -ENXIO: CPU event queues not configured or configuration of the
+ underlying HW interrupt failed
+ -EBUSY: No CPU available to serve interrupt
+
+ 4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
+ Configures an event queue of a CPU
+ Attributes:
+ EQ descriptor identifier (64-bit)
+ The EQ descriptor identifier is a tuple (server, priority) :
+ bits: | 63 .... 32 | 31 .. 3 | 2 .. 0
+ values: | unused | server | priority
+ The kvm_device_attr.addr points to :
+ struct kvm_ppc_xive_eq {
+ __u32 flags;
+ __u32 qshift;
+ __u64 qaddr;
+ __u32 qtoggle;
+ __u32 qindex;
+ __u8 pad[40];
+ };
+ - flags: queue flags
+ KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
+ forces notification without using the coalescing mechanism
+ provided by the XIVE END ESBs.
+ - qshift: queue size (power of 2)
+ - qaddr: real address of queue
+ - qtoggle: current queue toggle bit
+ - qindex: current queue index
+ - pad: reserved for future use
+ Errors:
+ -ENOENT: Invalid CPU number
+ -EINVAL: Invalid priority
+ -EINVAL: Invalid flags
+ -EINVAL: Invalid queue size
+ -EINVAL: Invalid queue address
+ -EFAULT: Invalid user pointer for attr->addr.
+ -EIO: Configuration of the underlying HW failed
+
+ 5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only)
+ Synchronize the source to flush event notifications
+ Attributes:
+ Interrupt source number (64-bit)
+ Errors:
+ -ENOENT: Unknown source number
+ -EINVAL: Not initialized source number
+
+* VCPU state
+
+ The XIVE IC maintains VP interrupt state in an internal structure
+ called the NVT. When a VP is not dispatched on a HW processor
+ thread, this structure can be updated by HW if the VP is the target
+ of an event notification.
+
+ It is important for migration to capture the cached IPB from the NVT
+ as it synthesizes the priorities of the pending interrupts. We
+ capture a bit more to report debug information.
+
+ KVM_REG_PPC_VP_STATE (2 * 64bits)
+ bits: | 63 .... 32 | 31 .... 0 |
+ values: | TIMA word0 | TIMA word1 |
+ bits: | 127 .......... 64 |
+ values: | unused |
+
+* Migration:
+
+ Saving the state of a VM using the XIVE native exploitation mode
+ should follow a specific sequence. When the VM is stopped :
+
+ 1. Mask all sources (PQ=01) to stop the flow of events.
+
+ 2. Sync the XIVE device with the KVM control KVM_DEV_XIVE_EQ_SYNC to
+ flush any in-flight event notification and to stabilize the EQs. At
+ this stage, the EQ pages are marked dirty to make sure they are
+ transferred in the migration sequence.
+
+ 3. Capture the state of the source targeting, the EQs configuration
+ and the state of thread interrupt context registers.
+
+ Restore is similar :
+
+ 1. Restore the EQ configuration. As targeting depends on it.
+ 2. Restore targeting
+ 3. Restore the thread interrupt contexts
+ 4. Restore the source states
+ 5. Let the vCPU run
--- /dev/null
+The KVM halt polling system
+===========================
+
+The KVM halt polling system provides a feature within KVM whereby the latency
+of a guest can, under some circumstances, be reduced by polling in the host
+for some time period after the guest has elected to no longer run by cedeing.
+That is, when a guest vcpu has ceded, or in the case of powerpc when all of the
+vcpus of a single vcore have ceded, the host kernel polls for wakeup conditions
+before giving up the cpu to the scheduler in order to let something else run.
+
+Polling provides a latency advantage in cases where the guest can be run again
+very quickly by at least saving us a trip through the scheduler, normally on
+the order of a few micro-seconds, although performance benefits are workload
+dependant. In the event that no wakeup source arrives during the polling
+interval or some other task on the runqueue is runnable the scheduler is
+invoked. Thus halt polling is especially useful on workloads with very short
+wakeup periods where the time spent halt polling is minimised and the time
+savings of not invoking the scheduler are distinguishable.
+
+The generic halt polling code is implemented in:
+
+ virt/kvm/kvm_main.c: kvm_vcpu_block()
+
+The powerpc kvm-hv specific case is implemented in:
+
+ arch/powerpc/kvm/book3s_hv.c: kvmppc_vcore_blocked()
+
+Halt Polling Interval
+=====================
+
+The maximum time for which to poll before invoking the scheduler, referred to
+as the halt polling interval, is increased and decreased based on the perceived
+effectiveness of the polling in an attempt to limit pointless polling.
+This value is stored in either the vcpu struct:
+
+ kvm_vcpu->halt_poll_ns
+
+or in the case of powerpc kvm-hv, in the vcore struct:
+
+ kvmppc_vcore->halt_poll_ns
+
+Thus this is a per vcpu (or vcore) value.
+
+During polling if a wakeup source is received within the halt polling interval,
+the interval is left unchanged. In the event that a wakeup source isn't
+received during the polling interval (and thus schedule is invoked) there are
+two options, either the polling interval and total block time[0] were less than
+the global max polling interval (see module params below), or the total block
+time was greater than the global max polling interval.
+
+In the event that both the polling interval and total block time were less than
+the global max polling interval then the polling interval can be increased in
+the hope that next time during the longer polling interval the wake up source
+will be received while the host is polling and the latency benefits will be
+received. The polling interval is grown in the function grow_halt_poll_ns() and
+is multiplied by the module parameters halt_poll_ns_grow and
+halt_poll_ns_grow_start.
+
+In the event that the total block time was greater than the global max polling
+interval then the host will never poll for long enough (limited by the global
+max) to wakeup during the polling interval so it may as well be shrunk in order
+to avoid pointless polling. The polling interval is shrunk in the function
+shrink_halt_poll_ns() and is divided by the module parameter
+halt_poll_ns_shrink, or set to 0 iff halt_poll_ns_shrink == 0.
+
+It is worth noting that this adjustment process attempts to hone in on some
+steady state polling interval but will only really do a good job for wakeups
+which come at an approximately constant rate, otherwise there will be constant
+adjustment of the polling interval.
+
+[0] total block time: the time between when the halt polling function is
+ invoked and a wakeup source received (irrespective of
+ whether the scheduler is invoked within that function).
+
+Module Parameters
+=================
+
+The kvm module has 3 tuneable module parameters to adjust the global max
+polling interval as well as the rate at which the polling interval is grown and
+shrunk. These variables are defined in include/linux/kvm_host.h and as module
+parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
+powerpc kvm-hv case.
+
+Module Parameter | Description | Default Value
+--------------------------------------------------------------------------------
+halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT
+ | interval which defines |
+ | the ceiling value of the |
+ | polling interval for | (per arch value)
+ | each vcpu. |
+--------------------------------------------------------------------------------
+halt_poll_ns_grow | The value by which the | 2
+ | halt polling interval is |
+ | multiplied in the |
+ | grow_halt_poll_ns() |
+ | function. |
+--------------------------------------------------------------------------------
+halt_poll_ns_grow_start | The initial value to grow | 10000
+ | to from zero in the |
+ | grow_halt_poll_ns() |
+ | function. |
+--------------------------------------------------------------------------------
+halt_poll_ns_shrink | The value by which the | 0
+ | halt polling interval is |
+ | divided in the |
+ | shrink_halt_poll_ns() |
+ | function. |
+--------------------------------------------------------------------------------
+
+These module parameters can be set from the debugfs files in:
+
+ /sys/module/kvm/parameters/
+
+Note: that these module parameters are system wide values and are not able to
+ be tuned on a per vm basis.
+
+Further Notes
+=============
+
+- Care should be taken when setting the halt_poll_ns module parameter as a
+large value has the potential to drive the cpu usage to 100% on a machine which
+would be almost entirely idle otherwise. This is because even if a guest has
+wakeups during which very little work is done and which are quite far apart, if
+the period is shorter than the global max polling interval (halt_poll_ns) then
+the host will always poll for the entire block time and thus cpu utilisation
+will go to 100%.
+
+- Halt polling essentially presents a trade off between power usage and latency
+and the module parameters should be used to tune the affinity for this. Idle
+cpu time is essentially converted to host kernel time with the aim of decreasing
+latency when entering the guest.
+
+- Halt polling will only be conducted by the host when no other tasks are
+runnable on that cpu, otherwise the polling will cease immediately and
+schedule will be invoked to allow that other task to run. Thus this doesn't
+allow a guest to denial of service the cpu.
--- /dev/null
+Linux KVM Hypercall:
+===================
+X86:
+ KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall
+ instruction. The hypervisor can replace it with instructions that are
+ guaranteed to be supported.
+
+ Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
+ The hypercall number should be placed in rax and the return value will be
+ placed in rax. No other registers will be clobbered unless explicitly stated
+ by the particular hypercall.
+
+S390:
+ R2-R7 are used for parameters 1-6. In addition, R1 is used for hypercall
+ number. The return value is written to R2.
+
+ S390 uses diagnose instruction as hypercall (0x500) along with hypercall
+ number in R1.
+
+ For further information on the S390 diagnose call as supported by KVM,
+ refer to Documentation/virt/kvm/s390-diag.txt.
+
+ PowerPC:
+ It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
+ Return value is placed in R3.
+
+ KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
+ property inside the device tree's /hypervisor node.
+ For more information refer to Documentation/virt/kvm/ppc-pv.txt
+
+MIPS:
+ KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall
+ number in $2 (v0). Up to four arguments may be placed in $4-$7 (a0-a3) and
+ the return value is placed in $2 (v0).
+
+KVM Hypercalls Documentation
+===========================
+The template for each hypercall is:
+1. Hypercall name.
+2. Architecture(s)
+3. Status (deprecated, obsolete, active)
+4. Purpose
+
+1. KVM_HC_VAPIC_POLL_IRQ
+------------------------
+Architecture: x86
+Status: active
+Purpose: Trigger guest exit so that the host can check for pending
+interrupts on reentry.
+
+2. KVM_HC_MMU_OP
+------------------------
+Architecture: x86
+Status: deprecated.
+Purpose: Support MMU operations such as writing to PTE,
+flushing TLB, release PT.
+
+3. KVM_HC_FEATURES
+------------------------
+Architecture: PPC
+Status: active
+Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid
+used to enumerate which hypercalls are available. On PPC, either device tree
+based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration
+mechanism (which is this hypercall) can be used.
+
+4. KVM_HC_PPC_MAP_MAGIC_PAGE
+------------------------
+Architecture: PPC
+Status: active
+Purpose: To enable communication between the hypervisor and guest there is a
+shared page that contains parts of supervisor visible register state.
+The guest can map this shared page to access its supervisor register through
+memory using this hypercall.
+
+5. KVM_HC_KICK_CPU
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to wakeup a vcpu from HLT state
+Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest
+kernel mode for an event to occur (ex: a spinlock to become available) can
+execute HLT instruction once it has busy-waited for more than a threshold
+time-interval. Execution of HLT instruction would cause the hypervisor to put
+the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the
+same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall,
+specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0)
+is used in the hypercall for future use.
+
+
+6. KVM_HC_CLOCK_PAIRING
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to synchronize host and guest clocks.
+Usage:
+
+a0: guest physical address where host copies
+"struct kvm_clock_offset" structure.
+
+a1: clock_type, ATM only KVM_CLOCK_PAIRING_WALLCLOCK (0)
+is supported (corresponding to the host's CLOCK_REALTIME clock).
+
+ struct kvm_clock_pairing {
+ __s64 sec;
+ __s64 nsec;
+ __u64 tsc;
+ __u32 flags;
+ __u32 pad[9];
+ };
+
+ Where:
+ * sec: seconds from clock_type clock.
+ * nsec: nanoseconds from clock_type clock.
+ * tsc: guest TSC value used to calculate sec/nsec pair
+ * flags: flags, unused (0) at the moment.
+
+The hypercall lets a guest compute a precise timestamp across
+host and guest. The guest can use the returned TSC value to
+compute the CLOCK_REALTIME for its clock, at the same instant.
+
+Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,
+or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.
+
+6. KVM_HC_SEND_IPI
+------------------------
+Architecture: x86
+Status: active
+Purpose: Send IPIs to multiple vCPUs.
+
+a0: lower part of the bitmap of destination APIC IDs
+a1: higher part of the bitmap of destination APIC IDs
+a2: the lowest APIC ID in bitmap
+a3: APIC ICR
+
+The hypercall lets a guest send multicast IPIs, with at most 128
+128 destinations per hypercall in 64-bit mode and 64 vCPUs per
+hypercall in 32-bit mode. The destinations are represented by a
+bitmap contained in the first two arguments (a0 and a1). Bit 0 of
+a0 corresponds to the APIC ID in the third argument (a2), bit 1
+corresponds to the APIC ID a2+1, and so on.
+
+Returns the number of CPUs to which the IPIs were delivered successfully.
+
+7. KVM_HC_SCHED_YIELD
+------------------------
+Architecture: x86
+Status: active
+Purpose: Hypercall used to yield if the IPI target vCPU is preempted
+
+a0: destination APIC ID
+
+Usage example: When sending a call-function IPI-many to vCPUs, yield if
+any of the IPI target vCPUs was preempted.
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+===
+KVM
+===
+
+.. toctree::
+ :maxdepth: 2
+
+ amd-memory-encryption
+ cpuid
+ vcpu-requests
--- /dev/null
+KVM Lock Overview
+=================
+
+1. Acquisition Orders
+---------------------
+
+The acquisition orders for mutexes are as follows:
+
+- kvm->lock is taken outside vcpu->mutex
+
+- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
+
+- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
+ them together is quite rare.
+
+On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
+
+Everything else is a leaf: no other lock is taken inside the critical
+sections.
+
+2: Exception
+------------
+
+Fast page fault:
+
+Fast page fault is the fast path which fixes the guest page fault out of
+the mmu-lock on x86. Currently, the page fault can be fast in one of the
+following two cases:
+
+1. Access Tracking: The SPTE is not present, but it is marked for access
+tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to
+restore the saved R/X bits. This is described in more detail later below.
+
+2. Write-Protection: The SPTE is present and the fault is
+caused by write-protect. That means we just need to change the W bit of the
+spte.
+
+What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and
+SPTE_MMU_WRITEABLE bit on the spte:
+- SPTE_HOST_WRITEABLE means the gfn is writable on host.
+- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when
+ the gfn is writable on guest mmu and it is not write-protected by shadow
+ page write-protection.
+
+On fast page fault path, we will use cmpxchg to atomically set the spte W
+bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or
+restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This
+is safe because whenever changing these bits can be detected by cmpxchg.
+
+But we need carefully check these cases:
+1): The mapping from gfn to pfn
+The mapping from gfn to pfn may be changed since we can only ensure the pfn
+is not changed during cmpxchg. This is a ABA problem, for example, below case
+will happen:
+
+At the beginning:
+gpte = gfn1
+gfn1 is mapped to pfn1 on host
+spte is the shadow page table entry corresponding with gpte and
+spte = pfn1
+
+ VCPU 0 VCPU0
+on fast page fault path:
+
+ old_spte = *spte;
+ pfn1 is swapped out:
+ spte = 0;
+
+ pfn1 is re-alloced for gfn2.
+
+ gpte is changed to point to
+ gfn2 by the guest:
+ spte = pfn1;
+
+ if (cmpxchg(spte, old_spte, old_spte+W)
+ mark_page_dirty(vcpu->kvm, gfn1)
+ OOPS!!!
+
+We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap.
+
+For direct sp, we can easily avoid it since the spte of direct sp is fixed
+to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic()
+to pin gfn to pfn, because after gfn_to_pfn_atomic():
+- We have held the refcount of pfn that means the pfn can not be freed and
+ be reused for another gfn.
+- The pfn is writable that means it can not be shared between different gfns
+ by KSM.
+
+Then, we can ensure the dirty bitmaps is correctly set for a gfn.
+
+Currently, to simplify the whole things, we disable fast page fault for
+indirect shadow page.
+
+2): Dirty bit tracking
+In the origin code, the spte can be fast updated (non-atomically) if the
+spte is read-only and the Accessed bit has already been set since the
+Accessed bit and Dirty bit can not be lost.
+
+But it is not true after fast page fault since the spte can be marked
+writable between reading spte and updating spte. Like below case:
+
+At the beginning:
+spte.W = 0
+spte.Accessed = 1
+
+ VCPU 0 VCPU0
+In mmu_spte_clear_track_bits():
+
+ old_spte = *spte;
+
+ /* 'if' condition is satisfied. */
+ if (old_spte.Accessed == 1 &&
+ old_spte.W == 0)
+ spte = 0ull;
+ on fast page fault path:
+ spte.W = 1
+ memory write on the spte:
+ spte.Dirty = 1
+
+
+ else
+ old_spte = xchg(spte, 0ull)
+
+
+ if (old_spte.Accessed == 1)
+ kvm_set_pfn_accessed(spte.pfn);
+ if (old_spte.Dirty == 1)
+ kvm_set_pfn_dirty(spte.pfn);
+ OOPS!!!
+
+The Dirty bit is lost in this case.
+
+In order to avoid this kind of issue, we always treat the spte as "volatile"
+if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means,
+the spte is always atomically updated in this case.
+
+3): flush tlbs due to spte updated
+If the spte is updated from writable to readonly, we should flush all TLBs,
+otherwise rmap_write_protect will find a read-only spte, even though the
+writable spte might be cached on a CPU's TLB.
+
+As mentioned before, the spte can be updated to writable out of mmu-lock on
+fast page fault path, in order to easily audit the path, we see if TLBs need
+be flushed caused by this reason in mmu_spte_update() since this is a common
+function to update spte (present -> present).
+
+Since the spte is "volatile" if it can be updated out of mmu-lock, we always
+atomically update the spte, the race caused by fast page fault can be avoided,
+See the comments in spte_has_volatile_bits() and mmu_spte_update().
+
+Lockless Access Tracking:
+
+This is used for Intel CPUs that are using EPT but do not support the EPT A/D
+bits. In this case, when the KVM MMU notifier is called to track accesses to a
+page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present
+by clearing the RWX bits in the PTE and storing the original R & X bits in
+some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the
+PTE (using the ignored bit 62). When the VM tries to access the page later on,
+a fault is generated and the fast page fault mechanism described above is used
+to atomically restore the PTE to a Present state. The W bit is not saved when
+the PTE is marked for access tracking and during restoration to the Present
+state, the W bit is set depending on whether or not it was a write access. If
+it wasn't, then the W bit will remain clear until a write access happens, at
+which time it will be set using the Dirty tracking mechanism described above.
+
+3. Reference
+------------
+
+Name: kvm_lock
+Type: mutex
+Arch: any
+Protects: - vm_list
+
+Name: kvm_count_lock
+Type: raw_spinlock_t
+Arch: any
+Protects: - hardware virtualization enable/disable
+Comment: 'raw' because hardware enabling/disabling must be atomic /wrt
+ migration.
+
+Name: kvm_arch::tsc_write_lock
+Type: raw_spinlock
+Arch: x86
+Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset}
+ - tsc offset in vmcb
+Comment: 'raw' because updating the tsc offsets must not be preempted.
+
+Name: kvm->mmu_lock
+Type: spinlock_t
+Arch: any
+Protects: -shadow page/shadow tlb entry
+Comment: it is a spinlock since it is used in mmu notifier.
+
+Name: kvm->srcu
+Type: srcu lock
+Arch: any
+Protects: - kvm->memslots
+ - kvm->buses
+Comment: The srcu read lock must be held while accessing memslots (e.g.
+ when using gfn_to_* functions) and while accessing in-kernel
+ MMIO/PIO address->device structure mapping (kvm->buses).
+ The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu
+ if it is needed by multiple functions.
+
+Name: blocked_vcpu_on_cpu_lock
+Type: spinlock_t
+Arch: x86
+Protects: blocked_vcpu_on_cpu
+Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts.
+ When VT-d posted-interrupts is supported and the VM has assigned
+ devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu
+ protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues
+ wakeup notification event since external interrupts from the
+ assigned devices happens, we will find the vCPU on the list to
+ wakeup.
--- /dev/null
+The x86 kvm shadow mmu
+======================
+
+The mmu (in arch/x86/kvm, files mmu.[ch] and paging_tmpl.h) is responsible
+for presenting a standard x86 mmu to the guest, while translating guest
+physical addresses to host physical addresses.
+
+The mmu code attempts to satisfy the following requirements:
+
+- correctness: the guest should not be able to determine that it is running
+ on an emulated mmu except for timing (we attempt to comply
+ with the specification, not emulate the characteristics of
+ a particular implementation such as tlb size)
+- security: the guest must not be able to touch host memory not assigned
+ to it
+- performance: minimize the performance penalty imposed by the mmu
+- scaling: need to scale to large memory and large vcpu guests
+- hardware: support the full range of x86 virtualization hardware
+- integration: Linux memory management code must be in control of guest memory
+ so that swapping, page migration, page merging, transparent
+ hugepages, and similar features work without change
+- dirty tracking: report writes to guest memory to enable live migration
+ and framebuffer-based displays
+- footprint: keep the amount of pinned kernel memory low (most memory
+ should be shrinkable)
+- reliability: avoid multipage or GFP_ATOMIC allocations
+
+Acronyms
+========
+
+pfn host page frame number
+hpa host physical address
+hva host virtual address
+gfn guest frame number
+gpa guest physical address
+gva guest virtual address
+ngpa nested guest physical address
+ngva nested guest virtual address
+pte page table entry (used also to refer generically to paging structure
+ entries)
+gpte guest pte (referring to gfns)
+spte shadow pte (referring to pfns)
+tdp two dimensional paging (vendor neutral term for NPT and EPT)
+
+Virtual and real hardware supported
+===================================
+
+The mmu supports first-generation mmu hardware, which allows an atomic switch
+of the current paging mode and cr3 during guest entry, as well as
+two-dimensional paging (AMD's NPT and Intel's EPT). The emulated hardware
+it exposes is the traditional 2/3/4 level x86 mmu, with support for global
+pages, pae, pse, pse36, cr0.wp, and 1GB pages. Emulated hardware also
+able to expose NPT capable hardware on NPT capable hosts.
+
+Translation
+===========
+
+The primary job of the mmu is to program the processor's mmu to translate
+addresses for the guest. Different translations are required at different
+times:
+
+- when guest paging is disabled, we translate guest physical addresses to
+ host physical addresses (gpa->hpa)
+- when guest paging is enabled, we translate guest virtual addresses, to
+ guest physical addresses, to host physical addresses (gva->gpa->hpa)
+- when the guest launches a guest of its own, we translate nested guest
+ virtual addresses, to nested guest physical addresses, to guest physical
+ addresses, to host physical addresses (ngva->ngpa->gpa->hpa)
+
+The primary challenge is to encode between 1 and 3 translations into hardware
+that support only 1 (traditional) and 2 (tdp) translations. When the
+number of required translations matches the hardware, the mmu operates in
+direct mode; otherwise it operates in shadow mode (see below).
+
+Memory
+======
+
+Guest memory (gpa) is part of the user address space of the process that is
+using kvm. Userspace defines the translation between guest addresses and user
+addresses (gpa->hva); note that two gpas may alias to the same hva, but not
+vice versa.
+
+These hvas may be backed using any method available to the host: anonymous
+memory, file backed memory, and device memory. Memory might be paged by the
+host at any time.
+
+Events
+======
+
+The mmu is driven by events, some from the guest, some from the host.
+
+Guest generated events:
+- writes to control registers (especially cr3)
+- invlpg/invlpga instruction execution
+- access to missing or protected translations
+
+Host generated events:
+- changes in the gpa->hpa translation (either through gpa->hva changes or
+ through hva->hpa changes)
+- memory pressure (the shrinker)
+
+Shadow pages
+============
+
+The principal data structure is the shadow page, 'struct kvm_mmu_page'. A
+shadow page contains 512 sptes, which can be either leaf or nonleaf sptes. A
+shadow page may contain a mix of leaf and nonleaf sptes.
+
+A nonleaf spte allows the hardware mmu to reach the leaf pages and
+is not related to a translation directly. It points to other shadow pages.
+
+A leaf spte corresponds to either one or two translations encoded into
+one paging structure entry. These are always the lowest level of the
+translation stack, with optional higher level translations left to NPT/EPT.
+Leaf ptes point at guest pages.
+
+The following table shows translations encoded by leaf ptes, with higher-level
+translations in parentheses:
+
+ Non-nested guests:
+ nonpaging: gpa->hpa
+ paging: gva->gpa->hpa
+ paging, tdp: (gva->)gpa->hpa
+ Nested guests:
+ non-tdp: ngva->gpa->hpa (*)
+ tdp: (ngva->)ngpa->gpa->hpa
+
+(*) the guest hypervisor will encode the ngva->gpa translation into its page
+ tables if npt is not present
+
+Shadow pages contain the following information:
+ role.level:
+ The level in the shadow paging hierarchy that this shadow page belongs to.
+ 1=4k sptes, 2=2M sptes, 3=1G sptes, etc.
+ role.direct:
+ If set, leaf sptes reachable from this page are for a linear range.
+ Examples include real mode translation, large guest pages backed by small
+ host pages, and gpa->hpa translations when NPT or EPT is active.
+ The linear range starts at (gfn << PAGE_SHIFT) and its size is determined
+ by role.level (2MB for first level, 1GB for second level, 0.5TB for third
+ level, 256TB for fourth level)
+ If clear, this page corresponds to a guest page table denoted by the gfn
+ field.
+ role.quadrant:
+ When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit
+ sptes. That means a guest page table contains more ptes than the host,
+ so multiple shadow pages are needed to shadow one guest page.
+ For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the
+ first or second 512-gpte block in the guest page table. For second-level
+ page tables, each 32-bit gpte is converted to two 64-bit sptes
+ (since each first-level guest page is shadowed by two first-level
+ shadow pages) so role.quadrant takes values in the range 0..3. Each
+ quadrant maps 1GB virtual address space.
+ role.access:
+ Inherited guest access permissions in the form uwx. Note execute
+ permission is positive, not negative.
+ role.invalid:
+ The page is invalid and should not be used. It is a root page that is
+ currently pinned (by a cpu hardware register pointing to it); once it is
+ unpinned it will be destroyed.
+ role.gpte_is_8_bytes:
+ Reflects the size of the guest PTE for which the page is valid, i.e. '1'
+ if 64-bit gptes are in use, '0' if 32-bit gptes are in use.
+ role.nxe:
+ Contains the value of efer.nxe for which the page is valid.
+ role.cr0_wp:
+ Contains the value of cr0.wp for which the page is valid.
+ role.smep_andnot_wp:
+ Contains the value of cr4.smep && !cr0.wp for which the page is valid
+ (pages for which this is true are different from other pages; see the
+ treatment of cr0.wp=0 below).
+ role.smap_andnot_wp:
+ Contains the value of cr4.smap && !cr0.wp for which the page is valid
+ (pages for which this is true are different from other pages; see the
+ treatment of cr0.wp=0 below).
+ role.ept_sp:
+ This is a virtual flag to denote a shadowed nested EPT page. ept_sp
+ is true if "cr0_wp && smap_andnot_wp", an otherwise invalid combination.
+ role.smm:
+ Is 1 if the page is valid in system management mode. This field
+ determines which of the kvm_memslots array was used to build this
+ shadow page; it is also used to go back from a struct kvm_mmu_page
+ to a memslot, through the kvm_memslots_for_spte_role macro and
+ __gfn_to_memslot.
+ role.ad_disabled:
+ Is 1 if the MMU instance cannot use A/D bits. EPT did not have A/D
+ bits before Haswell; shadow EPT page tables also cannot use A/D bits
+ if the L1 hypervisor does not enable them.
+ gfn:
+ Either the guest page table containing the translations shadowed by this
+ page, or the base page frame for linear translations. See role.direct.
+ spt:
+ A pageful of 64-bit sptes containing the translations for this page.
+ Accessed by both kvm and hardware.
+ The page pointed to by spt will have its page->private pointing back
+ at the shadow page structure.
+ sptes in spt point either at guest pages, or at lower-level shadow pages.
+ Specifically, if sp1 and sp2 are shadow pages, then sp1->spt[n] may point
+ at __pa(sp2->spt). sp2 will point back at sp1 through parent_pte.
+ The spt array forms a DAG structure with the shadow page as a node, and
+ guest pages as leaves.
+ gfns:
+ An array of 512 guest frame numbers, one for each present pte. Used to
+ perform a reverse map from a pte to a gfn. When role.direct is set, any
+ element of this array can be calculated from the gfn field when used, in
+ this case, the array of gfns is not allocated. See role.direct and gfn.
+ root_count:
+ A counter keeping track of how many hardware registers (guest cr3 or
+ pdptrs) are now pointing at the page. While this counter is nonzero, the
+ page cannot be destroyed. See role.invalid.
+ parent_ptes:
+ The reverse mapping for the pte/ptes pointing at this page's spt. If
+ parent_ptes bit 0 is zero, only one spte points at this page and
+ parent_ptes points at this single spte, otherwise, there exists multiple
+ sptes pointing at this page and (parent_ptes & ~0x1) points at a data
+ structure with a list of parent sptes.
+ unsync:
+ If true, then the translations in this page may not match the guest's
+ translation. This is equivalent to the state of the tlb when a pte is
+ changed but before the tlb entry is flushed. Accordingly, unsync ptes
+ are synchronized when the guest executes invlpg or flushes its tlb by
+ other means. Valid for leaf pages.
+ unsync_children:
+ How many sptes in the page point at pages that are unsync (or have
+ unsynchronized children).
+ unsync_child_bitmap:
+ A bitmap indicating which sptes in spt point (directly or indirectly) at
+ pages that may be unsynchronized. Used to quickly locate all unsychronized
+ pages reachable from a given page.
+ clear_spte_count:
+ Only present on 32-bit hosts, where a 64-bit spte cannot be written
+ atomically. The reader uses this while running out of the MMU lock
+ to detect in-progress updates and retry them until the writer has
+ finished the write.
+ write_flooding_count:
+ A guest may write to a page table many times, causing a lot of
+ emulations if the page needs to be write-protected (see "Synchronized
+ and unsynchronized pages" below). Leaf pages can be unsynchronized
+ so that they do not trigger frequent emulation, but this is not
+ possible for non-leafs. This field counts the number of emulations
+ since the last time the page table was actually used; if emulation
+ is triggered too frequently on this page, KVM will unmap the page
+ to avoid emulation in the future.
+
+Reverse map
+===========
+
+The mmu maintains a reverse mapping whereby all ptes mapping a page can be
+reached given its gfn. This is used, for example, when swapping out a page.
+
+Synchronized and unsynchronized pages
+=====================================
+
+The guest uses two events to synchronize its tlb and page tables: tlb flushes
+and page invalidations (invlpg).
+
+A tlb flush means that we need to synchronize all sptes reachable from the
+guest's cr3. This is expensive, so we keep all guest page tables write
+protected, and synchronize sptes to gptes when a gpte is written.
+
+A special case is when a guest page table is reachable from the current
+guest cr3. In this case, the guest is obliged to issue an invlpg instruction
+before using the translation. We take advantage of that by removing write
+protection from the guest page, and allowing the guest to modify it freely.
+We synchronize modified gptes when the guest invokes invlpg. This reduces
+the amount of emulation we have to do when the guest modifies multiple gptes,
+or when the a guest page is no longer used as a page table and is used for
+random guest data.
+
+As a side effect we have to resynchronize all reachable unsynchronized shadow
+pages on a tlb flush.
+
+
+Reaction to events
+==================
+
+- guest page fault (or npt page fault, or ept violation)
+
+This is the most complicated event. The cause of a page fault can be:
+
+ - a true guest fault (the guest translation won't allow the access) (*)
+ - access to a missing translation
+ - access to a protected translation
+ - when logging dirty pages, memory is write protected
+ - synchronized shadow pages are write protected (*)
+ - access to untranslatable memory (mmio)
+
+ (*) not applicable in direct mode
+
+Handling a page fault is performed as follows:
+
+ - if the RSV bit of the error code is set, the page fault is caused by guest
+ accessing MMIO and cached MMIO information is available.
+ - walk shadow page table
+ - check for valid generation number in the spte (see "Fast invalidation of
+ MMIO sptes" below)
+ - cache the information to vcpu->arch.mmio_gva, vcpu->arch.access and
+ vcpu->arch.mmio_gfn, and call the emulator
+ - If both P bit and R/W bit of error code are set, this could possibly
+ be handled as a "fast page fault" (fixed without taking the MMU lock). See
+ the description in Documentation/virt/kvm/locking.txt.
+ - if needed, walk the guest page tables to determine the guest translation
+ (gva->gpa or ngpa->gpa)
+ - if permissions are insufficient, reflect the fault back to the guest
+ - determine the host page
+ - if this is an mmio request, there is no host page; cache the info to
+ vcpu->arch.mmio_gva, vcpu->arch.access and vcpu->arch.mmio_gfn
+ - walk the shadow page table to find the spte for the translation,
+ instantiating missing intermediate page tables as necessary
+ - If this is an mmio request, cache the mmio info to the spte and set some
+ reserved bit on the spte (see callers of kvm_mmu_set_mmio_spte_mask)
+ - try to unsynchronize the page
+ - if successful, we can let the guest continue and modify the gpte
+ - emulate the instruction
+ - if failed, unshadow the page and let the guest continue
+ - update any translations that were modified by the instruction
+
+invlpg handling:
+
+ - walk the shadow page hierarchy and drop affected translations
+ - try to reinstantiate the indicated translation in the hope that the
+ guest will use it in the near future
+
+Guest control register updates:
+
+- mov to cr3
+ - look up new shadow roots
+ - synchronize newly reachable shadow pages
+
+- mov to cr0/cr4/efer
+ - set up mmu context for new paging mode
+ - look up new shadow roots
+ - synchronize newly reachable shadow pages
+
+Host translation updates:
+
+ - mmu notifier called with updated hva
+ - look up affected sptes through reverse map
+ - drop (or update) translations
+
+Emulating cr0.wp
+================
+
+If tdp is not enabled, the host must keep cr0.wp=1 so page write protection
+works for the guest kernel, not guest guest userspace. When the guest
+cr0.wp=1, this does not present a problem. However when the guest cr0.wp=0,
+we cannot map the permissions for gpte.u=1, gpte.w=0 to any spte (the
+semantics require allowing any guest kernel access plus user read access).
+
+We handle this by mapping the permissions to two possible sptes, depending
+on fault type:
+
+- kernel write fault: spte.u=0, spte.w=1 (allows full kernel access,
+ disallows user access)
+- read fault: spte.u=1, spte.w=0 (allows full read access, disallows kernel
+ write access)
+
+(user write faults generate a #PF)
+
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+ the kernel may now execute it. We handle this by also setting spte.nx.
+ If we get a user fetch or read fault, we'll change spte.u=1 and
+ spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when
+ shadow paging is in use.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+ page, it can not be reused when CR4.SMAP is enabled. We set
+ CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+ here we do not care the case that CR4.SMAP is enabled since KVM will
+ directly inject #PF to guest due to failed permission check.
+
+To prevent an spte that was converted into a kernel page with cr0.wp=0
+from being written by the kernel after cr0.wp has changed to 1, we make
+the value of cr0.wp part of the page role. This means that an spte created
+with one value of cr0.wp cannot be used when cr0.wp has a different value -
+it will simply be missed by the shadow page lookup code. A similar issue
+exists when an spte created with cr0.wp=0 and cr4.smep=0 is used after
+changing cr4.smep to 1. To avoid this, the value of !cr0.wp && cr4.smep
+is also made a part of the page role.
+
+Large pages
+===========
+
+The mmu supports all combinations of large and small guest and host pages.
+Supported page sizes include 4k, 2M, 4M, and 1G. 4M pages are treated as
+two separate 2M pages, on both guest and host, since the mmu always uses PAE
+paging.
+
+To instantiate a large spte, four constraints must be satisfied:
+
+- the spte must point to a large host page
+- the guest pte must be a large pte of at least equivalent size (if tdp is
+ enabled, there is no guest pte and this condition is satisfied)
+- if the spte will be writeable, the large page frame may not overlap any
+ write-protected pages
+- the guest page must be wholly contained by a single memory slot
+
+To check the last two conditions, the mmu maintains a ->disallow_lpage set of
+arrays for each memory slot and large page size. Every write protected page
+causes its disallow_lpage to be incremented, thus preventing instantiation of
+a large spte. The frames at the end of an unaligned memory slot have
+artificially inflated ->disallow_lpages so they can never be instantiated.
+
+Fast invalidation of MMIO sptes
+===============================
+
+As mentioned in "Reaction to events" above, kvm will cache MMIO
+information in leaf sptes. When a new memslot is added or an existing
+memslot is changed, this information may become stale and needs to be
+invalidated. This also needs to hold the MMU lock while walking all
+shadow pages, and is made more scalable with a similar technique.
+
+MMIO sptes have a few spare bits, which are used to store a
+generation number. The global generation number is stored in
+kvm_memslots(kvm)->generation, and increased whenever guest memory info
+changes.
+
+When KVM finds an MMIO spte, it checks the generation number of the spte.
+If the generation number of the spte does not equal the global generation
+number, it will ignore the cached MMIO information and handle the page
+fault through the slow path.
+
+Since only 19 bits are used to store generation-number on mmio spte, all
+pages are zapped when there is an overflow.
+
+Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
+times, the last one happening when the generation number is retrieved and
+stored into the MMIO spte. Thus, the MMIO spte might be created based on
+out-of-date information, but with an up-to-date generation number.
+
+To avoid this, the generation number is incremented again after synchronize_srcu
+returns; thus, bit 63 of kvm_memslots(kvm)->generation set to 1 only during a
+memslot update, while some SRCU readers might be using the old copy. We do not
+want to use an MMIO sptes created with an odd generation number, and we can do
+this without losing a bit in the MMIO spte. The "update in-progress" bit of the
+generation is not stored in MMIO spte, and is so is implicitly zero when the
+generation is extracted out of the spte. If KVM is unlucky and creates an MMIO
+spte while an update is in-progress, the next access to the spte will always be
+a cache miss. For example, a subsequent access during the update window will
+miss due to the in-progress flag diverging, while an access after the update
+window closes will have a higher generation number (as compared to the spte).
+
+
+Further reading
+===============
+
+- NPT presentation from KVM Forum 2008
+ http://www.linux-kvm.org/images/c/c8/KvmForum2008%24kdf2008_21.pdf
+
--- /dev/null
+KVM-specific MSRs.
+Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
+=====================================================
+
+KVM makes use of some custom MSRs to service some requests.
+
+Custom MSRs have a range reserved for them, that goes from
+0x4b564d00 to 0x4b564dff. There are MSRs outside this area,
+but they are deprecated and their use is discouraged.
+
+Custom MSR list
+--------
+
+The current supported Custom MSR list is:
+
+MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00
+
+ data: 4-byte alignment physical address of a memory area which must be
+ in guest RAM. This memory is expected to hold a copy of the following
+ structure:
+
+ struct pvclock_wall_clock {
+ u32 version;
+ u32 sec;
+ u32 nsec;
+ } __attribute__((__packed__));
+
+ whose data will be filled in by the hypervisor. The hypervisor is only
+ guaranteed to update this data at the moment of MSR write.
+ Users that want to reliably query this information more than once have
+ to write more than once to this MSR. Fields have the following meanings:
+
+ version: guest has to check version before and after grabbing
+ time information and check that they are both equal and even.
+ An odd version indicates an in-progress update.
+
+ sec: number of seconds for wallclock at time of boot.
+
+ nsec: number of nanoseconds for wallclock at time of boot.
+
+ In order to get the current wallclock time, the system_time from
+ MSR_KVM_SYSTEM_TIME_NEW needs to be added.
+
+ Note that although MSRs are per-CPU entities, the effect of this
+ particular MSR is global.
+
+ Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
+ leaf prior to usage.
+
+MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01
+
+ data: 4-byte aligned physical address of a memory area which must be in
+ guest RAM, plus an enable bit in bit 0. This memory is expected to hold
+ a copy of the following structure:
+
+ struct pvclock_vcpu_time_info {
+ u32 version;
+ u32 pad0;
+ u64 tsc_timestamp;
+ u64 system_time;
+ u32 tsc_to_system_mul;
+ s8 tsc_shift;
+ u8 flags;
+ u8 pad[2];
+ } __attribute__((__packed__)); /* 32 bytes */
+
+ whose data will be filled in by the hypervisor periodically. Only one
+ write, or registration, is needed for each VCPU. The interval between
+ updates of this structure is arbitrary and implementation-dependent.
+ The hypervisor may update this structure at any time it sees fit until
+ anything with bit0 == 0 is written to it.
+
+ Fields have the following meanings:
+
+ version: guest has to check version before and after grabbing
+ time information and check that they are both equal and even.
+ An odd version indicates an in-progress update.
+
+ tsc_timestamp: the tsc value at the current VCPU at the time
+ of the update of this structure. Guests can subtract this value
+ from current tsc to derive a notion of elapsed time since the
+ structure update.
+
+ system_time: a host notion of monotonic time, including sleep
+ time at the time this structure was last updated. Unit is
+ nanoseconds.
+
+ tsc_to_system_mul: multiplier to be used when converting
+ tsc-related quantity to nanoseconds
+
+ tsc_shift: shift to be used when converting tsc-related
+ quantity to nanoseconds. This shift will ensure that
+ multiplication with tsc_to_system_mul does not overflow.
+ A positive value denotes a left shift, a negative value
+ a right shift.
+
+ The conversion from tsc to nanoseconds involves an additional
+ right shift by 32 bits. With this information, guests can
+ derive per-CPU time by doing:
+
+ time = (current_tsc - tsc_timestamp)
+ if (tsc_shift >= 0)
+ time <<= tsc_shift;
+ else
+ time >>= -tsc_shift;
+ time = (time * tsc_to_system_mul) >> 32
+ time = time + system_time
+
+ flags: bits in this field indicate extended capabilities
+ coordinated between the guest and the hypervisor. Availability
+ of specific flags has to be checked in 0x40000001 cpuid leaf.
+ Current flags are:
+
+ flag bit | cpuid bit | meaning
+ -------------------------------------------------------------
+ | | time measures taken across
+ 0 | 24 | multiple cpus are guaranteed to
+ | | be monotonic
+ -------------------------------------------------------------
+ | | guest vcpu has been paused by
+ 1 | N/A | the host
+ | | See 4.70 in api.txt
+ -------------------------------------------------------------
+
+ Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
+ leaf prior to usage.
+
+
+MSR_KVM_WALL_CLOCK: 0x11
+
+ data and functioning: same as MSR_KVM_WALL_CLOCK_NEW. Use that instead.
+
+ This MSR falls outside the reserved KVM range and may be removed in the
+ future. Its usage is deprecated.
+
+ Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid
+ leaf prior to usage.
+
+MSR_KVM_SYSTEM_TIME: 0x12
+
+ data and functioning: same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead.
+
+ This MSR falls outside the reserved KVM range and may be removed in the
+ future. Its usage is deprecated.
+
+ Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid
+ leaf prior to usage.
+
+ The suggested algorithm for detecting kvmclock presence is then:
+
+ if (!kvm_para_available()) /* refer to cpuid.txt */
+ return NON_PRESENT;
+
+ flags = cpuid_eax(0x40000001);
+ if (flags & 3) {
+ msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
+ msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
+ return PRESENT;
+ } else if (flags & 0) {
+ msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
+ msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
+ return PRESENT;
+ } else
+ return NON_PRESENT;
+
+MSR_KVM_ASYNC_PF_EN: 0x4b564d02
+ data: Bits 63-6 hold 64-byte aligned physical address of a
+ 64 byte memory area which must be in guest RAM and must be
+ zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
+ when asynchronous page faults are enabled on the vcpu 0 when
+ disabled. Bit 1 is 1 if asynchronous page faults can be injected
+ when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
+ are delivered to L1 as #PF vmexits. Bit 2 can be set only if
+ KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID.
+
+ First 4 byte of 64 byte memory location will be written to by
+ the hypervisor at the time of asynchronous page fault (APF)
+ injection to indicate type of asynchronous page fault. Value
+ of 1 means that the page referred to by the page fault is not
+ present. Value 2 means that the page is now available. Disabling
+ interrupt inhibits APFs. Guest must not enable interrupt
+ before the reason is read, or it may be overwritten by another
+ APF. Since APF uses the same exception vector as regular page
+ fault guest must reset the reason to 0 before it does
+ something that can generate normal page fault. If during page
+ fault APF reason is 0 it means that this is regular page
+ fault.
+
+ During delivery of type 1 APF cr2 contains a token that will
+ be used to notify a guest when missing page becomes
+ available. When page becomes available type 2 APF is sent with
+ cr2 set to the token associated with the page. There is special
+ kind of token 0xffffffff which tells vcpu that it should wake
+ up all processes waiting for APFs and no individual type 2 APFs
+ will be sent.
+
+ If APF is disabled while there are outstanding APFs, they will
+ not be delivered.
+
+ Currently type 2 APF will be always delivered on the same vcpu as
+ type 1 was, but guest should not rely on that.
+
+MSR_KVM_STEAL_TIME: 0x4b564d03
+
+ data: 64-byte alignment physical address of a memory area which must be
+ in guest RAM, plus an enable bit in bit 0. This memory is expected to
+ hold a copy of the following structure:
+
+ struct kvm_steal_time {
+ __u64 steal;
+ __u32 version;
+ __u32 flags;
+ __u8 preempted;
+ __u8 u8_pad[3];
+ __u32 pad[11];
+ }
+
+ whose data will be filled in by the hypervisor periodically. Only one
+ write, or registration, is needed for each VCPU. The interval between
+ updates of this structure is arbitrary and implementation-dependent.
+ The hypervisor may update this structure at any time it sees fit until
+ anything with bit0 == 0 is written to it. Guest is required to make sure
+ this structure is initialized to zero.
+
+ Fields have the following meanings:
+
+ version: a sequence counter. In other words, guest has to check
+ this field before and after grabbing time information and make
+ sure they are both equal and even. An odd version indicates an
+ in-progress update.
+
+ flags: At this point, always zero. May be used to indicate
+ changes in this structure in the future.
+
+ steal: the amount of time in which this vCPU did not run, in
+ nanoseconds. Time during which the vcpu is idle, will not be
+ reported as steal time.
+
+ preempted: indicate the vCPU who owns this struct is running or
+ not. Non-zero values mean the vCPU has been preempted. Zero
+ means the vCPU is not preempted. NOTE, it is always zero if the
+ the hypervisor doesn't support this field.
+
+MSR_KVM_EOI_EN: 0x4b564d04
+ data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0
+ when disabled. Bit 1 is reserved and must be zero. When PV end of
+ interrupt is enabled (bit 0 set), bits 63-2 hold a 4-byte aligned
+ physical address of a 4 byte memory area which must be in guest RAM and
+ must be zeroed.
+
+ The first, least significant bit of 4 byte memory location will be
+ written to by the hypervisor, typically at the time of interrupt
+ injection. Value of 1 means that guest can skip writing EOI to the apic
+ (using MSR or MMIO write); instead, it is sufficient to signal
+ EOI by clearing the bit in guest memory - this location will
+ later be polled by the hypervisor.
+ Value of 0 means that the EOI write is required.
+
+ It is always safe for the guest to ignore the optimization and perform
+ the APIC EOI write anyway.
+
+ Hypervisor is guaranteed to only modify this least
+ significant bit while in the current VCPU context, this means that
+ guest does not need to use either lock prefix or memory ordering
+ primitives to synchronise with the hypervisor.
+
+ However, hypervisor can set and clear this memory bit at any time:
+ therefore to make sure hypervisor does not interrupt the
+ guest and clear the least significant bit in the memory area
+ in the window between guest testing it to detect
+ whether it can skip EOI apic write and between guest
+ clearing it to signal EOI to the hypervisor,
+ guest must both read the least significant bit in the memory area and
+ clear it using a single CPU instruction, such as test and clear, or
+ compare and exchange.
+
+MSR_KVM_POLL_CONTROL: 0x4b564d05
+ Control host-side polling.
+
+ data: Bit 0 enables (1) or disables (0) host-side HLT polling logic.
+
+ KVM guests can request the host not to poll on HLT, for example if
+ they are performing polling themselves.
+
--- /dev/null
+Nested VMX
+==========
+
+Overview
+---------
+
+On Intel processors, KVM uses Intel's VMX (Virtual-Machine eXtensions)
+to easily and efficiently run guest operating systems. Normally, these guests
+*cannot* themselves be hypervisors running their own guests, because in VMX,
+guests cannot use VMX instructions.
+
+The "Nested VMX" feature adds this missing capability - of running guest
+hypervisors (which use VMX) with their own nested guests. It does so by
+allowing a guest to use VMX instructions, and correctly and efficiently
+emulating them using the single level of VMX available in the hardware.
+
+We describe in much greater detail the theory behind the nested VMX feature,
+its implementation and its performance characteristics, in the OSDI 2010 paper
+"The Turtles Project: Design and Implementation of Nested Virtualization",
+available at:
+
+ http://www.usenix.org/events/osdi10/tech/full_papers/Ben-Yehuda.pdf
+
+
+Terminology
+-----------
+
+Single-level virtualization has two levels - the host (KVM) and the guests.
+In nested virtualization, we have three levels: The host (KVM), which we call
+L0, the guest hypervisor, which we call L1, and its nested guest, which we
+call L2.
+
+
+Running nested VMX
+------------------
+
+The nested VMX feature is disabled by default. It can be enabled by giving
+the "nested=1" option to the kvm-intel module.
+
+No modifications are required to user space (qemu). However, qemu's default
+emulated CPU type (qemu64) does not list the "VMX" CPU feature, so it must be
+explicitly enabled, by giving qemu one of the following options:
+
+ -cpu host (emulated CPU has all features of the real CPU)
+
+ -cpu qemu64,+vmx (add just the vmx feature to a named CPU type)
+
+
+ABIs
+----
+
+Nested VMX aims to present a standard and (eventually) fully-functional VMX
+implementation for the a guest hypervisor to use. As such, the official
+specification of the ABI that it provides is Intel's VMX specification,
+namely volume 3B of their "Intel 64 and IA-32 Architectures Software
+Developer's Manual". Not all of VMX's features are currently fully supported,
+but the goal is to eventually support them all, starting with the VMX features
+which are used in practice by popular hypervisors (KVM and others).
+
+As a VMX implementation, nested VMX presents a VMCS structure to L1.
+As mandated by the spec, other than the two fields revision_id and abort,
+this structure is *opaque* to its user, who is not supposed to know or care
+about its internal structure. Rather, the structure is accessed through the
+VMREAD and VMWRITE instructions.
+Still, for debugging purposes, KVM developers might be interested to know the
+internals of this structure; This is struct vmcs12 from arch/x86/kvm/vmx.c.
+
+The name "vmcs12" refers to the VMCS that L1 builds for L2. In the code we
+also have "vmcs01", the VMCS that L0 built for L1, and "vmcs02" is the VMCS
+which L0 builds to actually run L2 - how this is done is explained in the
+aforementioned paper.
+
+For convenience, we repeat the content of struct vmcs12 here. If the internals
+of this structure changes, this can break live migration across KVM versions.
+VMCS12_REVISION (from vmx.c) should be changed if struct vmcs12 or its inner
+struct shadow_vmcs is ever changed.
+
+ typedef u64 natural_width;
+ struct __packed vmcs12 {
+ /* According to the Intel spec, a VMCS region must start with
+ * these two user-visible fields */
+ u32 revision_id;
+ u32 abort;
+
+ u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
+ u32 padding[7]; /* room for future expansion */
+
+ u64 io_bitmap_a;
+ u64 io_bitmap_b;
+ u64 msr_bitmap;
+ u64 vm_exit_msr_store_addr;
+ u64 vm_exit_msr_load_addr;
+ u64 vm_entry_msr_load_addr;
+ u64 tsc_offset;
+ u64 virtual_apic_page_addr;
+ u64 apic_access_addr;
+ u64 ept_pointer;
+ u64 guest_physical_address;
+ u64 vmcs_link_pointer;
+ u64 guest_ia32_debugctl;
+ u64 guest_ia32_pat;
+ u64 guest_ia32_efer;
+ u64 guest_pdptr0;
+ u64 guest_pdptr1;
+ u64 guest_pdptr2;
+ u64 guest_pdptr3;
+ u64 host_ia32_pat;
+ u64 host_ia32_efer;
+ u64 padding64[8]; /* room for future expansion */
+ natural_width cr0_guest_host_mask;
+ natural_width cr4_guest_host_mask;
+ natural_width cr0_read_shadow;
+ natural_width cr4_read_shadow;
+ natural_width cr3_target_value0;
+ natural_width cr3_target_value1;
+ natural_width cr3_target_value2;
+ natural_width cr3_target_value3;
+ natural_width exit_qualification;
+ natural_width guest_linear_address;
+ natural_width guest_cr0;
+ natural_width guest_cr3;
+ natural_width guest_cr4;
+ natural_width guest_es_base;
+ natural_width guest_cs_base;
+ natural_width guest_ss_base;
+ natural_width guest_ds_base;
+ natural_width guest_fs_base;
+ natural_width guest_gs_base;
+ natural_width guest_ldtr_base;
+ natural_width guest_tr_base;
+ natural_width guest_gdtr_base;
+ natural_width guest_idtr_base;
+ natural_width guest_dr7;
+ natural_width guest_rsp;
+ natural_width guest_rip;
+ natural_width guest_rflags;
+ natural_width guest_pending_dbg_exceptions;
+ natural_width guest_sysenter_esp;
+ natural_width guest_sysenter_eip;
+ natural_width host_cr0;
+ natural_width host_cr3;
+ natural_width host_cr4;
+ natural_width host_fs_base;
+ natural_width host_gs_base;
+ natural_width host_tr_base;
+ natural_width host_gdtr_base;
+ natural_width host_idtr_base;
+ natural_width host_ia32_sysenter_esp;
+ natural_width host_ia32_sysenter_eip;
+ natural_width host_rsp;
+ natural_width host_rip;
+ natural_width paddingl[8]; /* room for future expansion */
+ u32 pin_based_vm_exec_control;
+ u32 cpu_based_vm_exec_control;
+ u32 exception_bitmap;
+ u32 page_fault_error_code_mask;
+ u32 page_fault_error_code_match;
+ u32 cr3_target_count;
+ u32 vm_exit_controls;
+ u32 vm_exit_msr_store_count;
+ u32 vm_exit_msr_load_count;
+ u32 vm_entry_controls;
+ u32 vm_entry_msr_load_count;
+ u32 vm_entry_intr_info_field;
+ u32 vm_entry_exception_error_code;
+ u32 vm_entry_instruction_len;
+ u32 tpr_threshold;
+ u32 secondary_vm_exec_control;
+ u32 vm_instruction_error;
+ u32 vm_exit_reason;
+ u32 vm_exit_intr_info;
+ u32 vm_exit_intr_error_code;
+ u32 idt_vectoring_info_field;
+ u32 idt_vectoring_error_code;
+ u32 vm_exit_instruction_len;
+ u32 vmx_instruction_info;
+ u32 guest_es_limit;
+ u32 guest_cs_limit;
+ u32 guest_ss_limit;
+ u32 guest_ds_limit;
+ u32 guest_fs_limit;
+ u32 guest_gs_limit;
+ u32 guest_ldtr_limit;
+ u32 guest_tr_limit;
+ u32 guest_gdtr_limit;
+ u32 guest_idtr_limit;
+ u32 guest_es_ar_bytes;
+ u32 guest_cs_ar_bytes;
+ u32 guest_ss_ar_bytes;
+ u32 guest_ds_ar_bytes;
+ u32 guest_fs_ar_bytes;
+ u32 guest_gs_ar_bytes;
+ u32 guest_ldtr_ar_bytes;
+ u32 guest_tr_ar_bytes;
+ u32 guest_interruptibility_info;
+ u32 guest_activity_state;
+ u32 guest_sysenter_cs;
+ u32 host_ia32_sysenter_cs;
+ u32 padding32[8]; /* room for future expansion */
+ u16 virtual_processor_id;
+ u16 guest_es_selector;
+ u16 guest_cs_selector;
+ u16 guest_ss_selector;
+ u16 guest_ds_selector;
+ u16 guest_fs_selector;
+ u16 guest_gs_selector;
+ u16 guest_ldtr_selector;
+ u16 guest_tr_selector;
+ u16 host_es_selector;
+ u16 host_cs_selector;
+ u16 host_ss_selector;
+ u16 host_ds_selector;
+ u16 host_fs_selector;
+ u16 host_gs_selector;
+ u16 host_tr_selector;
+ };
+
+
+Authors
+-------
+
+These patches were written by:
+ Abel Gordon, abelg <at> il.ibm.com
+ Nadav Har'El, nyh <at> il.ibm.com
+ Orit Wasserman, oritw <at> il.ibm.com
+ Ben-Ami Yassor, benami <at> il.ibm.com
+ Muli Ben-Yehuda, muli <at> il.ibm.com
+
+With contributions by:
+ Anthony Liguori, aliguori <at> us.ibm.com
+ Mike Day, mdday <at> us.ibm.com
+ Michael Factor, factor <at> il.ibm.com
+ Zvi Dubitzky, dubi <at> il.ibm.com
+
+And valuable reviews by:
+ Avi Kivity, avi <at> redhat.com
+ Gleb Natapov, gleb <at> redhat.com
+ Marcelo Tosatti, mtosatti <at> redhat.com
+ Kevin Tian, kevin.tian <at> intel.com
+ and others.
--- /dev/null
+The PPC KVM paravirtual interface
+=================================
+
+The basic execution principle by which KVM on PowerPC works is to run all kernel
+space code in PR=1 which is user space. This way we trap all privileged
+instructions and can emulate them accordingly.
+
+Unfortunately that is also the downfall. There are quite some privileged
+instructions that needlessly return us to the hypervisor even though they
+could be handled differently.
+
+This is what the PPC PV interface helps with. It takes privileged instructions
+and transforms them into unprivileged ones with some help from the hypervisor.
+This cuts down virtualization costs by about 50% on some of my benchmarks.
+
+The code for that interface can be found in arch/powerpc/kernel/kvm*
+
+Querying for existence
+======================
+
+To find out if we're running on KVM or not, we leverage the device tree. When
+Linux is running on KVM, a node /hypervisor exists. That node contains a
+compatible property with the value "linux,kvm".
+
+Once you determined you're running under a PV capable KVM, you can now use
+hypercalls as described below.
+
+KVM hypercalls
+==============
+
+Inside the device tree's /hypervisor node there's a property called
+'hypercall-instructions'. This property contains at most 4 opcodes that make
+up the hypercall. To call a hypercall, just call these instructions.
+
+The parameters are as follows:
+
+ Register IN OUT
+
+ r0 - volatile
+ r3 1st parameter Return code
+ r4 2nd parameter 1st output value
+ r5 3rd parameter 2nd output value
+ r6 4th parameter 3rd output value
+ r7 5th parameter 4th output value
+ r8 6th parameter 5th output value
+ r9 7th parameter 6th output value
+ r10 8th parameter 7th output value
+ r11 hypercall number 8th output value
+ r12 - volatile
+
+Hypercall definitions are shared in generic code, so the same hypercall numbers
+apply for x86 and powerpc alike with the exception that each KVM hypercall
+also needs to be ORed with the KVM vendor code which is (42 << 16).
+
+Return codes can be as follows:
+
+ Code Meaning
+
+ 0 Success
+ 12 Hypercall not implemented
+ <0 Error
+
+The magic page
+==============
+
+To enable communication between the hypervisor and guest there is a new shared
+page that contains parts of supervisor visible register state. The guest can
+map this shared page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE.
+
+With this hypercall issued the guest always gets the magic page mapped at the
+desired location. The first parameter indicates the effective address when the
+MMU is enabled. The second parameter indicates the address in real mode, if
+applicable to the target. For now, we always map the page to -4096. This way we
+can access it using absolute load and store functions. The following
+instruction reads the first field of the magic page:
+
+ ld rX, -4096(0)
+
+The interface is designed to be extensible should there be need later to add
+additional registers to the magic page. If you add fields to the magic page,
+also define a new hypercall feature to indicate that the host can give you more
+registers. Only if the host supports the additional features, make use of them.
+
+The magic page layout is described by struct kvm_vcpu_arch_shared
+in arch/powerpc/include/asm/kvm_para.h.
+
+Magic page features
+===================
+
+When mapping the magic page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE,
+a second return value is passed to the guest. This second return value contains
+a bitmap of available features inside the magic page.
+
+The following enhancements to the magic page are currently available:
+
+ KVM_MAGIC_FEAT_SR Maps SR registers r/w in the magic page
+ KVM_MAGIC_FEAT_MAS0_TO_SPRG7 Maps MASn, ESR, PIR and high SPRGs
+
+For enhanced features in the magic page, please check for the existence of the
+feature before using them!
+
+Magic page flags
+================
+
+In addition to features that indicate whether a host is capable of a particular
+feature we also have a channel for a guest to tell the guest whether it's capable
+of something. This is what we call "flags".
+
+Flags are passed to the host in the low 12 bits of the Effective Address.
+
+The following flags are currently available for a guest to expose:
+
+ MAGIC_PAGE_FLAG_NOT_MAPPED_NX Guest handles NX bits correctly wrt magic page
+
+MSR bits
+========
+
+The MSR contains bits that require hypervisor intervention and bits that do
+not require direct hypervisor intervention because they only get interpreted
+when entering the guest or don't have any impact on the hypervisor's behavior.
+
+The following bits are safe to be set inside the guest:
+
+ MSR_EE
+ MSR_RI
+
+If any other bit changes in the MSR, please still use mtmsr(d).
+
+Patched instructions
+====================
+
+The "ld" and "std" instructions are transformed to "lwz" and "stw" instructions
+respectively on 32 bit systems with an added offset of 4 to accommodate for big
+endianness.
+
+The following is a list of mapping the Linux kernel performs when running as
+guest. Implementing any of those mappings is optional, as the instruction traps
+also act on the shared page. So calling privileged instructions still works as
+before.
+
+From To
+==== ==
+
+mfmsr rX ld rX, magic_page->msr
+mfsprg rX, 0 ld rX, magic_page->sprg0
+mfsprg rX, 1 ld rX, magic_page->sprg1
+mfsprg rX, 2 ld rX, magic_page->sprg2
+mfsprg rX, 3 ld rX, magic_page->sprg3
+mfsrr0 rX ld rX, magic_page->srr0
+mfsrr1 rX ld rX, magic_page->srr1
+mfdar rX ld rX, magic_page->dar
+mfdsisr rX lwz rX, magic_page->dsisr
+
+mtmsr rX std rX, magic_page->msr
+mtsprg 0, rX std rX, magic_page->sprg0
+mtsprg 1, rX std rX, magic_page->sprg1
+mtsprg 2, rX std rX, magic_page->sprg2
+mtsprg 3, rX std rX, magic_page->sprg3
+mtsrr0 rX std rX, magic_page->srr0
+mtsrr1 rX std rX, magic_page->srr1
+mtdar rX std rX, magic_page->dar
+mtdsisr rX stw rX, magic_page->dsisr
+
+tlbsync nop
+
+mtmsrd rX, 0 b <special mtmsr section>
+mtmsr rX b <special mtmsr section>
+
+mtmsrd rX, 1 b <special mtmsrd section>
+
+[Book3S only]
+mtsrin rX, rY b <special mtsrin section>
+
+[BookE only]
+wrteei [0|1] b <special wrteei section>
+
+
+Some instructions require more logic to determine what's going on than a load
+or store instruction can deliver. To enable patching of those, we keep some
+RAM around where we can live translate instructions to. What happens is the
+following:
+
+ 1) copy emulation code to memory
+ 2) patch that code to fit the emulated instruction
+ 3) patch that code to return to the original pc + 4
+ 4) patch the original instruction to branch to the new code
+
+That way we can inject an arbitrary amount of code as replacement for a single
+instruction. This allows us to check for pending interrupts when setting EE=1
+for example.
+
+Hypercall ABIs in KVM on PowerPC
+=================================
+1) KVM hypercalls (ePAPR)
+
+These are ePAPR compliant hypercall implementation (mentioned above). Even
+generic hypercalls are implemented here, like the ePAPR idle hcall. These are
+available on all targets.
+
+2) PAPR hypercalls
+
+PAPR hypercalls are needed to run server PowerPC PAPR guests (-M pseries in QEMU).
+These are the same hypercalls that pHyp, the POWER hypervisor implements. Some of
+them are handled in the kernel, some are handled in user space. This is only
+available on book3s_64.
+
+3) OSI hypercalls
+
+Mac-on-Linux is another user of KVM on PowerPC, which has its own hypercall (long
+before KVM). This is supported to maintain compatibility. All these hypercalls get
+forwarded to user space. This is only useful on book3s_32, but can be used with
+book3s_64 as well.
--- /dev/null
+Review checklist for kvm patches
+================================
+
+1. The patch must follow Documentation/process/coding-style.rst and
+ Documentation/process/submitting-patches.rst.
+
+2. Patches should be against kvm.git master branch.
+
+3. If the patch introduces or modifies a new userspace API:
+ - the API must be documented in Documentation/virt/kvm/api.txt
+ - the API must be discoverable using KVM_CHECK_EXTENSION
+
+4. New state must include support for save/restore.
+
+5. New features must default to off (userspace should explicitly request them).
+ Performance improvements can and should default to on.
+
+6. New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2
+
+7. Emulator changes should be accompanied by unit tests for qemu-kvm.git
+ kvm/test directory.
+
+8. Changes should be vendor neutral when possible. Changes to common code
+ are better than duplicating changes to vendor code.
+
+9. Similarly, prefer changes to arch independent code than to arch dependent
+ code.
+
+10. User/kernel interfaces and guest/host interfaces must be 64-bit clean
+ (all variables and sizes naturally aligned on 64-bit; use specific types
+ only - u64 rather than ulong).
+
+11. New guest visible features must either be documented in a hardware manual
+ or be accompanied by documentation.
+
+12. Features must be robust against reset and kexec - for example, shared
+ host/guest memory must be unshared to prevent the host from writing to
+ guest memory that the guest has not reserved for this purpose.
--- /dev/null
+The s390 DIAGNOSE call on KVM
+=============================
+
+KVM on s390 supports the DIAGNOSE call for making hypercalls, both for
+native hypercalls and for selected hypercalls found on other s390
+hypervisors.
+
+Note that bits are numbered as by the usual s390 convention (most significant
+bit on the left).
+
+
+General remarks
+---------------
+
+DIAGNOSE calls by the guest cause a mandatory intercept. This implies
+all supported DIAGNOSE calls need to be handled by either KVM or its
+userspace.
+
+All DIAGNOSE calls supported by KVM use the RS-a format:
+
+--------------------------------------
+| '83' | R1 | R3 | B2 | D2 |
+--------------------------------------
+0 8 12 16 20 31
+
+The second-operand address (obtained by the base/displacement calculation)
+is not used to address data. Instead, bits 48-63 of this address specify
+the function code, and bits 0-47 are ignored.
+
+The supported DIAGNOSE function codes vary by the userspace used. For
+DIAGNOSE function codes not specific to KVM, please refer to the
+documentation for the s390 hypervisors defining them.
+
+
+DIAGNOSE function code 'X'500' - KVM virtio functions
+-----------------------------------------------------
+
+If the function code specifies 0x500, various virtio-related functions
+are performed.
+
+General register 1 contains the virtio subfunction code. Supported
+virtio subfunctions depend on KVM's userspace. Generally, userspace
+provides either s390-virtio (subcodes 0-2) or virtio-ccw (subcode 3).
+
+Upon completion of the DIAGNOSE instruction, general register 2 contains
+the function's return code, which is either a return code or a subcode
+specific value.
+
+Subcode 0 - s390-virtio notification and early console printk
+ Handled by userspace.
+
+Subcode 1 - s390-virtio reset
+ Handled by userspace.
+
+Subcode 2 - s390-virtio set status
+ Handled by userspace.
+
+Subcode 3 - virtio-ccw notification
+ Handled by either userspace or KVM (ioeventfd case).
+
+ General register 2 contains a subchannel-identification word denoting
+ the subchannel of the virtio-ccw proxy device to be notified.
+
+ General register 3 contains the number of the virtqueue to be notified.
+
+ General register 4 contains a 64bit identifier for KVM usage (the
+ kvm_io_bus cookie). If general register 4 does not contain a valid
+ identifier, it is ignored.
+
+ After completion of the DIAGNOSE call, general register 2 may contain
+ a 64bit identifier (in the kvm_io_bus cookie case), or a negative
+ error value, if an internal error occurred.
+
+ See also the virtio standard for a discussion of this hypercall.
+
+
+DIAGNOSE function code 'X'501 - KVM breakpoint
+----------------------------------------------
+
+If the function code specifies 0x501, breakpoint functions may be performed.
+This function code is handled by userspace.
+
+This diagnose function code has no subfunctions and uses no parameters.
--- /dev/null
+
+ Timekeeping Virtualization for X86-Based Architectures
+
+ Zachary Amsden <zamsden@redhat.com>
+ Copyright (c) 2010, Red Hat. All rights reserved.
+
+1) Overview
+2) Timing Devices
+3) TSC Hardware
+4) Virtualization Problems
+
+=========================================================================
+
+1) Overview
+
+One of the most complicated parts of the X86 platform, and specifically,
+the virtualization of this platform is the plethora of timing devices available
+and the complexity of emulating those devices. In addition, virtualization of
+time introduces a new set of challenges because it introduces a multiplexed
+division of time beyond the control of the guest CPU.
+
+First, we will describe the various timekeeping hardware available, then
+present some of the problems which arise and solutions available, giving
+specific recommendations for certain classes of KVM guests.
+
+The purpose of this document is to collect data and information relevant to
+timekeeping which may be difficult to find elsewhere, specifically,
+information relevant to KVM and hardware-based virtualization.
+
+=========================================================================
+
+2) Timing Devices
+
+First we discuss the basic hardware devices available. TSC and the related
+KVM clock are special enough to warrant a full exposition and are described in
+the following section.
+
+2.1) i8254 - PIT
+
+One of the first timer devices available is the programmable interrupt timer,
+or PIT. The PIT has a fixed frequency 1.193182 MHz base clock and three
+channels which can be programmed to deliver periodic or one-shot interrupts.
+These three channels can be configured in different modes and have individual
+counters. Channel 1 and 2 were not available for general use in the original
+IBM PC, and historically were connected to control RAM refresh and the PC
+speaker. Now the PIT is typically integrated as part of an emulated chipset
+and a separate physical PIT is not used.
+
+The PIT uses I/O ports 0x40 - 0x43. Access to the 16-bit counters is done
+using single or multiple byte access to the I/O ports. There are 6 modes
+available, but not all modes are available to all timers, as only timer 2
+has a connected gate input, required for modes 1 and 5. The gate line is
+controlled by port 61h, bit 0, as illustrated in the following diagram.
+
+ -------------- ----------------
+| | | |
+| 1.1932 MHz |---------->| CLOCK OUT | ---------> IRQ 0
+| Clock | | | |
+ -------------- | +->| GATE TIMER 0 |
+ | ----------------
+ |
+ | ----------------
+ | | |
+ |------>| CLOCK OUT | ---------> 66.3 KHZ DRAM
+ | | | (aka /dev/null)
+ | +->| GATE TIMER 1 |
+ | ----------------
+ |
+ | ----------------
+ | | |
+ |------>| CLOCK OUT | ---------> Port 61h, bit 5
+ | | |
+Port 61h, bit 0 ---------->| GATE TIMER 2 | \_.---- ____
+ ---------------- _| )--|LPF|---Speaker
+ / *---- \___/
+Port 61h, bit 1 -----------------------------------/
+
+The timer modes are now described.
+
+Mode 0: Single Timeout. This is a one-shot software timeout that counts down
+ when the gate is high (always true for timers 0 and 1). When the count
+ reaches zero, the output goes high.
+
+Mode 1: Triggered One-shot. The output is initially set high. When the gate
+ line is set high, a countdown is initiated (which does not stop if the gate is
+ lowered), during which the output is set low. When the count reaches zero,
+ the output goes high.
+
+Mode 2: Rate Generator. The output is initially set high. When the countdown
+ reaches 1, the output goes low for one count and then returns high. The value
+ is reloaded and the countdown automatically resumes. If the gate line goes
+ low, the count is halted. If the output is low when the gate is lowered, the
+ output automatically goes high (this only affects timer 2).
+
+Mode 3: Square Wave. This generates a high / low square wave. The count
+ determines the length of the pulse, which alternates between high and low
+ when zero is reached. The count only proceeds when gate is high and is
+ automatically reloaded on reaching zero. The count is decremented twice at
+ each clock to generate a full high / low cycle at the full periodic rate.
+ If the count is even, the clock remains high for N/2 counts and low for N/2
+ counts; if the clock is odd, the clock is high for (N+1)/2 counts and low
+ for (N-1)/2 counts. Only even values are latched by the counter, so odd
+ values are not observed when reading. This is the intended mode for timer 2,
+ which generates sine-like tones by low-pass filtering the square wave output.
+
+Mode 4: Software Strobe. After programming this mode and loading the counter,
+ the output remains high until the counter reaches zero. Then the output
+ goes low for 1 clock cycle and returns high. The counter is not reloaded.
+ Counting only occurs when gate is high.
+
+Mode 5: Hardware Strobe. After programming and loading the counter, the
+ output remains high. When the gate is raised, a countdown is initiated
+ (which does not stop if the gate is lowered). When the counter reaches zero,
+ the output goes low for 1 clock cycle and then returns high. The counter is
+ not reloaded.
+
+In addition to normal binary counting, the PIT supports BCD counting. The
+command port, 0x43 is used to set the counter and mode for each of the three
+timers.
+
+PIT commands, issued to port 0x43, using the following bit encoding:
+
+Bit 7-4: Command (See table below)
+Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined)
+Bit 0 : Binary (0) / BCD (1)
+
+Command table:
+
+0000 - Latch Timer 0 count for port 0x40
+ sample and hold the count to be read in port 0x40;
+ additional commands ignored until counter is read;
+ mode bits ignored.
+
+0001 - Set Timer 0 LSB mode for port 0x40
+ set timer to read LSB only and force MSB to zero;
+ mode bits set timer mode
+
+0010 - Set Timer 0 MSB mode for port 0x40
+ set timer to read MSB only and force LSB to zero;
+ mode bits set timer mode
+
+0011 - Set Timer 0 16-bit mode for port 0x40
+ set timer to read / write LSB first, then MSB;
+ mode bits set timer mode
+
+0100 - Latch Timer 1 count for port 0x41 - as described above
+0101 - Set Timer 1 LSB mode for port 0x41 - as described above
+0110 - Set Timer 1 MSB mode for port 0x41 - as described above
+0111 - Set Timer 1 16-bit mode for port 0x41 - as described above
+
+1000 - Latch Timer 2 count for port 0x42 - as described above
+1001 - Set Timer 2 LSB mode for port 0x42 - as described above
+1010 - Set Timer 2 MSB mode for port 0x42 - as described above
+1011 - Set Timer 2 16-bit mode for port 0x42 as described above
+
+1101 - General counter latch
+ Latch combination of counters into corresponding ports
+ Bit 3 = Counter 2
+ Bit 2 = Counter 1
+ Bit 1 = Counter 0
+ Bit 0 = Unused
+
+1110 - Latch timer status
+ Latch combination of counter mode into corresponding ports
+ Bit 3 = Counter 2
+ Bit 2 = Counter 1
+ Bit 1 = Counter 0
+
+ The output of ports 0x40-0x42 following this command will be:
+
+ Bit 7 = Output pin
+ Bit 6 = Count loaded (0 if timer has expired)
+ Bit 5-4 = Read / Write mode
+ 01 = MSB only
+ 10 = LSB only
+ 11 = LSB / MSB (16-bit)
+ Bit 3-1 = Mode
+ Bit 0 = Binary (0) / BCD mode (1)
+
+2.2) RTC
+
+The second device which was available in the original PC was the MC146818 real
+time clock. The original device is now obsolete, and usually emulated by the
+system chipset, sometimes by an HPET and some frankenstein IRQ routing.
+
+The RTC is accessed through CMOS variables, which uses an index register to
+control which bytes are read. Since there is only one index register, read
+of the CMOS and read of the RTC require lock protection (in addition, it is
+dangerous to allow userspace utilities such as hwclock to have direct RTC
+access, as they could corrupt kernel reads and writes of CMOS memory).
+
+The RTC generates an interrupt which is usually routed to IRQ 8. The interrupt
+can function as a periodic timer, an additional once a day alarm, and can issue
+interrupts after an update of the CMOS registers by the MC146818 is complete.
+The type of interrupt is signalled in the RTC status registers.
+
+The RTC will update the current time fields by battery power even while the
+system is off. The current time fields should not be read while an update is
+in progress, as indicated in the status register.
+
+The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be
+programmed to a 32kHz divider if the RTC is to count seconds.
+
+This is the RAM map originally used for the RTC/CMOS:
+
+Location Size Description
+------------------------------------------
+00h byte Current second (BCD)
+01h byte Seconds alarm (BCD)
+02h byte Current minute (BCD)
+03h byte Minutes alarm (BCD)
+04h byte Current hour (BCD)
+05h byte Hours alarm (BCD)
+06h byte Current day of week (BCD)
+07h byte Current day of month (BCD)
+08h byte Current month (BCD)
+09h byte Current year (BCD)
+0Ah byte Register A
+ bit 7 = Update in progress
+ bit 6-4 = Divider for clock
+ 000 = 4.194 MHz
+ 001 = 1.049 MHz
+ 010 = 32 kHz
+ 10X = test modes
+ 110 = reset / disable
+ 111 = reset / disable
+ bit 3-0 = Rate selection for periodic interrupt
+ 000 = periodic timer disabled
+ 001 = 3.90625 uS
+ 010 = 7.8125 uS
+ 011 = .122070 mS
+ 100 = .244141 mS
+ ...
+ 1101 = 125 mS
+ 1110 = 250 mS
+ 1111 = 500 mS
+0Bh byte Register B
+ bit 7 = Run (0) / Halt (1)
+ bit 6 = Periodic interrupt enable
+ bit 5 = Alarm interrupt enable
+ bit 4 = Update-ended interrupt enable
+ bit 3 = Square wave interrupt enable
+ bit 2 = BCD calendar (0) / Binary (1)
+ bit 1 = 12-hour mode (0) / 24-hour mode (1)
+ bit 0 = 0 (DST off) / 1 (DST enabled)
+OCh byte Register C (read only)
+ bit 7 = interrupt request flag (IRQF)
+ bit 6 = periodic interrupt flag (PF)
+ bit 5 = alarm interrupt flag (AF)
+ bit 4 = update interrupt flag (UF)
+ bit 3-0 = reserved
+ODh byte Register D (read only)
+ bit 7 = RTC has power
+ bit 6-0 = reserved
+32h byte Current century BCD (*)
+ (*) location vendor specific and now determined from ACPI global tables
+
+2.3) APIC
+
+On Pentium and later processors, an on-board timer is available to each CPU
+as part of the Advanced Programmable Interrupt Controller. The APIC is
+accessed through memory-mapped registers and provides interrupt service to each
+CPU, used for IPIs and local timer interrupts.
+
+Although in theory the APIC is a safe and stable source for local interrupts,
+in practice, many bugs and glitches have occurred due to the special nature of
+the APIC CPU-local memory-mapped hardware. Beware that CPU errata may affect
+the use of the APIC and that workarounds may be required. In addition, some of
+these workarounds pose unique constraints for virtualization - requiring either
+extra overhead incurred from extra reads of memory-mapped I/O or additional
+functionality that may be more computationally expensive to implement.
+
+Since the APIC is documented quite well in the Intel and AMD manuals, we will
+avoid repetition of the detail here. It should be pointed out that the APIC
+timer is programmed through the LVT (local vector timer) register, is capable
+of one-shot or periodic operation, and is based on the bus clock divided down
+by the programmable divider register.
+
+2.4) HPET
+
+HPET is quite complex, and was originally intended to replace the PIT / RTC
+support of the X86 PC. It remains to be seen whether that will be the case, as
+the de facto standard of PC hardware is to emulate these older devices. Some
+systems designated as legacy free may support only the HPET as a hardware timer
+device.
+
+The HPET spec is rather loose and vague, requiring at least 3 hardware timers,
+but allowing implementation freedom to support many more. It also imposes no
+fixed rate on the timer frequency, but does impose some extremal values on
+frequency, error and slew.
+
+In general, the HPET is recommended as a high precision (compared to PIT /RTC)
+time source which is independent of local variation (as there is only one HPET
+in any given system). The HPET is also memory-mapped, and its presence is
+indicated through ACPI tables by the BIOS.
+
+Detailed specification of the HPET is beyond the current scope of this
+document, as it is also very well documented elsewhere.
+
+2.5) Offboard Timers
+
+Several cards, both proprietary (watchdog boards) and commonplace (e1000) have
+timing chips built into the cards which may have registers which are accessible
+to kernel or user drivers. To the author's knowledge, using these to generate
+a clocksource for a Linux or other kernel has not yet been attempted and is in
+general frowned upon as not playing by the agreed rules of the game. Such a
+timer device would require additional support to be virtualized properly and is
+not considered important at this time as no known operating system does this.
+
+=========================================================================
+
+3) TSC Hardware
+
+The TSC or time stamp counter is relatively simple in theory; it counts
+instruction cycles issued by the processor, which can be used as a measure of
+time. In practice, due to a number of problems, it is the most complicated
+timekeeping device to use.
+
+The TSC is represented internally as a 64-bit MSR which can be read with the
+RDMSR, RDTSC, or RDTSCP (when available) instructions. In the past, hardware
+limitations made it possible to write the TSC, but generally on old hardware it
+was only possible to write the low 32-bits of the 64-bit counter, and the upper
+32-bits of the counter were cleared. Now, however, on Intel processors family
+0Fh, for models 3, 4 and 6, and family 06h, models e and f, this restriction
+has been lifted and all 64-bits are writable. On AMD systems, the ability to
+write the TSC MSR is not an architectural guarantee.
+
+The TSC is accessible from CPL-0 and conditionally, for CPL > 0 software by
+means of the CR4.TSD bit, which when enabled, disables CPL > 0 TSC access.
+
+Some vendors have implemented an additional instruction, RDTSCP, which returns
+atomically not just the TSC, but an indicator which corresponds to the
+processor number. This can be used to index into an array of TSC variables to
+determine offset information in SMP systems where TSCs are not synchronized.
+The presence of this instruction must be determined by consulting CPUID feature
+bits.
+
+Both VMX and SVM provide extension fields in the virtualization hardware which
+allows the guest visible TSC to be offset by a constant. Newer implementations
+promise to allow the TSC to additionally be scaled, but this hardware is not
+yet widely available.
+
+3.1) TSC synchronization
+
+The TSC is a CPU-local clock in most implementations. This means, on SMP
+platforms, the TSCs of different CPUs may start at different times depending
+on when the CPUs are powered on. Generally, CPUs on the same die will share
+the same clock, however, this is not always the case.
+
+The BIOS may attempt to resynchronize the TSCs during the poweron process and
+the operating system or other system software may attempt to do this as well.
+Several hardware limitations make the problem worse - if it is not possible to
+write the full 64-bits of the TSC, it may be impossible to match the TSC in
+newly arriving CPUs to that of the rest of the system, resulting in
+unsynchronized TSCs. This may be done by BIOS or system software, but in
+practice, getting a perfectly synchronized TSC will not be possible unless all
+values are read from the same clock, which generally only is possible on single
+socket systems or those with special hardware support.
+
+3.2) TSC and CPU hotplug
+
+As touched on already, CPUs which arrive later than the boot time of the system
+may not have a TSC value that is synchronized with the rest of the system.
+Either system software, BIOS, or SMM code may actually try to establish the TSC
+to a value matching the rest of the system, but a perfect match is usually not
+a guarantee. This can have the effect of bringing a system from a state where
+TSC is synchronized back to a state where TSC synchronization flaws, however
+small, may be exposed to the OS and any virtualization environment.
+
+3.3) TSC and multi-socket / NUMA
+
+Multi-socket systems, especially large multi-socket systems are likely to have
+individual clocksources rather than a single, universally distributed clock.
+Since these clocks are driven by different crystals, they will not have
+perfectly matched frequency, and temperature and electrical variations will
+cause the CPU clocks, and thus the TSCs to drift over time. Depending on the
+exact clock and bus design, the drift may or may not be fixed in absolute
+error, and may accumulate over time.
+
+In addition, very large systems may deliberately slew the clocks of individual
+cores. This technique, known as spread-spectrum clocking, reduces EMI at the
+clock frequency and harmonics of it, which may be required to pass FCC
+standards for telecommunications and computer equipment.
+
+It is recommended not to trust the TSCs to remain synchronized on NUMA or
+multiple socket systems for these reasons.
+
+3.4) TSC and C-states
+
+C-states, or idling states of the processor, especially C1E and deeper sleep
+states may be problematic for TSC as well. The TSC may stop advancing in such
+a state, resulting in a TSC which is behind that of other CPUs when execution
+is resumed. Such CPUs must be detected and flagged by the operating system
+based on CPU and chipset identifications.
+
+The TSC in such a case may be corrected by catching it up to a known external
+clocksource.
+
+3.5) TSC frequency change / P-states
+
+To make things slightly more interesting, some CPUs may change frequency. They
+may or may not run the TSC at the same rate, and because the frequency change
+may be staggered or slewed, at some points in time, the TSC rate may not be
+known other than falling within a range of values. In this case, the TSC will
+not be a stable time source, and must be calibrated against a known, stable,
+external clock to be a usable source of time.
+
+Whether the TSC runs at a constant rate or scales with the P-state is model
+dependent and must be determined by inspecting CPUID, chipset or vendor
+specific MSR fields.
+
+In addition, some vendors have known bugs where the P-state is actually
+compensated for properly during normal operation, but when the processor is
+inactive, the P-state may be raised temporarily to service cache misses from
+other processors. In such cases, the TSC on halted CPUs could advance faster
+than that of non-halted processors. AMD Turion processors are known to have
+this problem.
+
+3.6) TSC and STPCLK / T-states
+
+External signals given to the processor may also have the effect of stopping
+the TSC. This is typically done for thermal emergency power control to prevent
+an overheating condition, and typically, there is no way to detect that this
+condition has happened.
+
+3.7) TSC virtualization - VMX
+
+VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
+instructions, which is enough for full virtualization of TSC in any manner. In
+addition, VMX allows passing through the host TSC plus an additional TSC_OFFSET
+field specified in the VMCS. Special instructions must be used to read and
+write the VMCS field.
+
+3.8) TSC virtualization - SVM
+
+SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
+instructions, which is enough for full virtualization of TSC in any manner. In
+addition, SVM allows passing through the host TSC plus an additional offset
+field specified in the SVM control block.
+
+3.9) TSC feature bits in Linux
+
+In summary, there is no way to guarantee the TSC remains in perfect
+synchronization unless it is explicitly guaranteed by the architecture. Even
+if so, the TSCs in multi-sockets or NUMA systems may still run independently
+despite being locally consistent.
+
+The following feature bits are used by Linux to signal various TSC attributes,
+but they can only be taken to be meaningful for UP or single node systems.
+
+X86_FEATURE_TSC : The TSC is available in hardware
+X86_FEATURE_RDTSCP : The RDTSCP instruction is available
+X86_FEATURE_CONSTANT_TSC : The TSC rate is unchanged with P-states
+X86_FEATURE_NONSTOP_TSC : The TSC does not stop in C-states
+X86_FEATURE_TSC_RELIABLE : TSC sync checks are skipped (VMware)
+
+4) Virtualization Problems
+
+Timekeeping is especially problematic for virtualization because a number of
+challenges arise. The most obvious problem is that time is now shared between
+the host and, potentially, a number of virtual machines. Thus the virtual
+operating system does not run with 100% usage of the CPU, despite the fact that
+it may very well make that assumption. It may expect it to remain true to very
+exacting bounds when interrupt sources are disabled, but in reality only its
+virtual interrupt sources are disabled, and the machine may still be preempted
+at any time. This causes problems as the passage of real time, the injection
+of machine interrupts and the associated clock sources are no longer completely
+synchronized with real time.
+
+This same problem can occur on native hardware to a degree, as SMM mode may
+steal cycles from the naturally on X86 systems when SMM mode is used by the
+BIOS, but not in such an extreme fashion. However, the fact that SMM mode may
+cause similar problems to virtualization makes it a good justification for
+solving many of these problems on bare metal.
+
+4.1) Interrupt clocking
+
+One of the most immediate problems that occurs with legacy operating systems
+is that the system timekeeping routines are often designed to keep track of
+time by counting periodic interrupts. These interrupts may come from the PIT
+or the RTC, but the problem is the same: the host virtualization engine may not
+be able to deliver the proper number of interrupts per second, and so guest
+time may fall behind. This is especially problematic if a high interrupt rate
+is selected, such as 1000 HZ, which is unfortunately the default for many Linux
+guests.
+
+There are three approaches to solving this problem; first, it may be possible
+to simply ignore it. Guests which have a separate time source for tracking
+'wall clock' or 'real time' may not need any adjustment of their interrupts to
+maintain proper time. If this is not sufficient, it may be necessary to inject
+additional interrupts into the guest in order to increase the effective
+interrupt rate. This approach leads to complications in extreme conditions,
+where host load or guest lag is too much to compensate for, and thus another
+solution to the problem has risen: the guest may need to become aware of lost
+ticks and compensate for them internally. Although promising in theory, the
+implementation of this policy in Linux has been extremely error prone, and a
+number of buggy variants of lost tick compensation are distributed across
+commonly used Linux systems.
+
+Windows uses periodic RTC clocking as a means of keeping time internally, and
+thus requires interrupt slewing to keep proper time. It does use a low enough
+rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in
+practice.
+
+4.2) TSC sampling and serialization
+
+As the highest precision time source available, the cycle counter of the CPU
+has aroused much interest from developers. As explained above, this timer has
+many problems unique to its nature as a local, potentially unstable and
+potentially unsynchronized source. One issue which is not unique to the TSC,
+but is highlighted because of its very precise nature is sampling delay. By
+definition, the counter, once read is already old. However, it is also
+possible for the counter to be read ahead of the actual use of the result.
+This is a consequence of the superscalar execution of the instruction stream,
+which may execute instructions out of order. Such execution is called
+non-serialized. Forcing serialized execution is necessary for precise
+measurement with the TSC, and requires a serializing instruction, such as CPUID
+or an MSR read.
+
+Since CPUID may actually be virtualized by a trap and emulate mechanism, this
+serialization can pose a performance issue for hardware virtualization. An
+accurate time stamp counter reading may therefore not always be available, and
+it may be necessary for an implementation to guard against "backwards" reads of
+the TSC as seen from other CPUs, even in an otherwise perfectly synchronized
+system.
+
+4.3) Timespec aliasing
+
+Additionally, this lack of serialization from the TSC poses another challenge
+when using results of the TSC when measured against another time source. As
+the TSC is much higher precision, many possible values of the TSC may be read
+while another clock is still expressing the same value.
+
+That is, you may read (T,T+10) while external clock C maintains the same value.
+Due to non-serialized reads, you may actually end up with a range which
+fluctuates - from (T-1.. T+10). Thus, any time calculated from a TSC, but
+calibrated against an external value may have a range of valid values.
+Re-calibrating this computation may actually cause time, as computed after the
+calibration, to go backwards, compared with time computed before the
+calibration.
+
+This problem is particularly pronounced with an internal time source in Linux,
+the kernel time, which is expressed in the theoretically high resolution
+timespec - but which advances in much larger granularity intervals, sometimes
+at the rate of jiffies, and possibly in catchup modes, at a much larger step.
+
+This aliasing requires care in the computation and recalibration of kvmclock
+and any other values derived from TSC computation (such as TSC virtualization
+itself).
+
+4.4) Migration
+
+Migration of a virtual machine raises problems for timekeeping in two ways.
+First, the migration itself may take time, during which interrupts cannot be
+delivered, and after which, the guest time may need to be caught up. NTP may
+be able to help to some degree here, as the clock correction required is
+typically small enough to fall in the NTP-correctable window.
+
+An additional concern is that timers based off the TSC (or HPET, if the raw bus
+clock is exposed) may now be running at different rates, requiring compensation
+in some way in the hypervisor by virtualizing these timers. In addition,
+migrating to a faster machine may preclude the use of a passthrough TSC, as a
+faster clock cannot be made visible to a guest without the potential of time
+advancing faster than usual. A slower clock is less of a problem, as it can
+always be caught up to the original rate. KVM clock avoids these problems by
+simply storing multipliers and offsets against the TSC for the guest to convert
+back into nanosecond resolution values.
+
+4.5) Scheduling
+
+Since scheduling may be based on precise timing and firing of interrupts, the
+scheduling algorithms of an operating system may be adversely affected by
+virtualization. In theory, the effect is random and should be universally
+distributed, but in contrived as well as real scenarios (guest device access,
+causes of virtualization exits, possible context switch), this may not always
+be the case. The effect of this has not been well studied.
+
+In an attempt to work around this, several implementations have provided a
+paravirtualized scheduler clock, which reveals the true amount of CPU time for
+which a virtual machine has been running.
+
+4.6) Watchdogs
+
+Watchdog timers, such as the lock detector in Linux may fire accidentally when
+running under hardware virtualization due to timer interrupts being delayed or
+misinterpretation of the passage of real time. Usually, these warnings are
+spurious and can be ignored, but in some circumstances it may be necessary to
+disable such detection.
+
+4.7) Delays and precision timing
+
+Precise timing and delays may not be possible in a virtualized system. This
+can happen if the system is controlling physical hardware, or issues delays to
+compensate for slower I/O to and from devices. The first issue is not solvable
+in general for a virtualized system; hardware control software can't be
+adequately virtualized without a full real-time operating system, which would
+require an RT aware virtualization platform.
+
+The second issue may cause performance problems, but this is unlikely to be a
+significant issue. In many cases these delays may be eliminated through
+configuration or paravirtualization.
+
+4.8) Covert channels and leaks
+
+In addition to the above problems, time information will inevitably leak to the
+guest about the host in anything but a perfect implementation of virtualized
+time. This may allow the guest to infer the presence of a hypervisor (as in a
+red-pill type detection), and it may allow information to leak between guests
+by using CPU utilization itself as a signalling channel. Preventing such
+problems would require completely isolated virtual time which may not track
+real time any longer. This may be useful in certain security or QA contexts,
+but in general isn't recommended for real-world deployment scenarios.
--- /dev/null
+=================
+KVM VCPU Requests
+=================
+
+Overview
+========
+
+KVM supports an internal API enabling threads to request a VCPU thread to
+perform some activity. For example, a thread may request a VCPU to flush
+its TLB with a VCPU request. The API consists of the following functions::
+
+ /* Check if any requests are pending for VCPU @vcpu. */
+ bool kvm_request_pending(struct kvm_vcpu *vcpu);
+
+ /* Check if VCPU @vcpu has request @req pending. */
+ bool kvm_test_request(int req, struct kvm_vcpu *vcpu);
+
+ /* Clear request @req for VCPU @vcpu. */
+ void kvm_clear_request(int req, struct kvm_vcpu *vcpu);
+
+ /*
+ * Check if VCPU @vcpu has request @req pending. When the request is
+ * pending it will be cleared and a memory barrier, which pairs with
+ * another in kvm_make_request(), will be issued.
+ */
+ bool kvm_check_request(int req, struct kvm_vcpu *vcpu);
+
+ /*
+ * Make request @req of VCPU @vcpu. Issues a memory barrier, which pairs
+ * with another in kvm_check_request(), prior to setting the request.
+ */
+ void kvm_make_request(int req, struct kvm_vcpu *vcpu);
+
+ /* Make request @req of all VCPUs of the VM with struct kvm @kvm. */
+ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
+
+Typically a requester wants the VCPU to perform the activity as soon
+as possible after making the request. This means most requests
+(kvm_make_request() calls) are followed by a call to kvm_vcpu_kick(),
+and kvm_make_all_cpus_request() has the kicking of all VCPUs built
+into it.
+
+VCPU Kicks
+----------
+
+The goal of a VCPU kick is to bring a VCPU thread out of guest mode in
+order to perform some KVM maintenance. To do so, an IPI is sent, forcing
+a guest mode exit. However, a VCPU thread may not be in guest mode at the
+time of the kick. Therefore, depending on the mode and state of the VCPU
+thread, there are two other actions a kick may take. All three actions
+are listed below:
+
+1) Send an IPI. This forces a guest mode exit.
+2) Waking a sleeping VCPU. Sleeping VCPUs are VCPU threads outside guest
+ mode that wait on waitqueues. Waking them removes the threads from
+ the waitqueues, allowing the threads to run again. This behavior
+ may be suppressed, see KVM_REQUEST_NO_WAKEUP below.
+3) Nothing. When the VCPU is not in guest mode and the VCPU thread is not
+ sleeping, then there is nothing to do.
+
+VCPU Mode
+---------
+
+VCPUs have a mode state, ``vcpu->mode``, that is used to track whether the
+guest is running in guest mode or not, as well as some specific
+outside guest mode states. The architecture may use ``vcpu->mode`` to
+ensure VCPU requests are seen by VCPUs (see "Ensuring Requests Are Seen"),
+as well as to avoid sending unnecessary IPIs (see "IPI Reduction"), and
+even to ensure IPI acknowledgements are waited upon (see "Waiting for
+Acknowledgements"). The following modes are defined:
+
+OUTSIDE_GUEST_MODE
+
+ The VCPU thread is outside guest mode.
+
+IN_GUEST_MODE
+
+ The VCPU thread is in guest mode.
+
+EXITING_GUEST_MODE
+
+ The VCPU thread is transitioning from IN_GUEST_MODE to
+ OUTSIDE_GUEST_MODE.
+
+READING_SHADOW_PAGE_TABLES
+
+ The VCPU thread is outside guest mode, but it wants the sender of
+ certain VCPU requests, namely KVM_REQ_TLB_FLUSH, to wait until the VCPU
+ thread is done reading the page tables.
+
+VCPU Request Internals
+======================
+
+VCPU requests are simply bit indices of the ``vcpu->requests`` bitmap.
+This means general bitops, like those documented in [atomic-ops]_ could
+also be used, e.g. ::
+
+ clear_bit(KVM_REQ_UNHALT & KVM_REQUEST_MASK, &vcpu->requests);
+
+However, VCPU request users should refrain from doing so, as it would
+break the abstraction. The first 8 bits are reserved for architecture
+independent requests, all additional bits are available for architecture
+dependent requests.
+
+Architecture Independent Requests
+---------------------------------
+
+KVM_REQ_TLB_FLUSH
+
+ KVM's common MMU notifier may need to flush all of a guest's TLB
+ entries, calling kvm_flush_remote_tlbs() to do so. Architectures that
+ choose to use the common kvm_flush_remote_tlbs() implementation will
+ need to handle this VCPU request.
+
+KVM_REQ_MMU_RELOAD
+
+ When shadow page tables are used and memory slots are removed it's
+ necessary to inform each VCPU to completely refresh the tables. This
+ request is used for that.
+
+KVM_REQ_PENDING_TIMER
+
+ This request may be made from a timer handler run on the host on behalf
+ of a VCPU. It informs the VCPU thread to inject a timer interrupt.
+
+KVM_REQ_UNHALT
+
+ This request may be made from the KVM common function kvm_vcpu_block(),
+ which is used to emulate an instruction that causes a CPU to halt until
+ one of an architectural specific set of events and/or interrupts is
+ received (determined by checking kvm_arch_vcpu_runnable()). When that
+ event or interrupt arrives kvm_vcpu_block() makes the request. This is
+ in contrast to when kvm_vcpu_block() returns due to any other reason,
+ such as a pending signal, which does not indicate the VCPU's halt
+ emulation should stop, and therefore does not make the request.
+
+KVM_REQUEST_MASK
+----------------
+
+VCPU requests should be masked by KVM_REQUEST_MASK before using them with
+bitops. This is because only the lower 8 bits are used to represent the
+request's number. The upper bits are used as flags. Currently only two
+flags are defined.
+
+VCPU Request Flags
+------------------
+
+KVM_REQUEST_NO_WAKEUP
+
+ This flag is applied to requests that only need immediate attention
+ from VCPUs running in guest mode. That is, sleeping VCPUs do not need
+ to be awaken for these requests. Sleeping VCPUs will handle the
+ requests when they are awaken later for some other reason.
+
+KVM_REQUEST_WAIT
+
+ When requests with this flag are made with kvm_make_all_cpus_request(),
+ then the caller will wait for each VCPU to acknowledge its IPI before
+ proceeding. This flag only applies to VCPUs that would receive IPIs.
+ If, for example, the VCPU is sleeping, so no IPI is necessary, then
+ the requesting thread does not wait. This means that this flag may be
+ safely combined with KVM_REQUEST_NO_WAKEUP. See "Waiting for
+ Acknowledgements" for more information about requests with
+ KVM_REQUEST_WAIT.
+
+VCPU Requests with Associated State
+===================================
+
+Requesters that want the receiving VCPU to handle new state need to ensure
+the newly written state is observable to the receiving VCPU thread's CPU
+by the time it observes the request. This means a write memory barrier
+must be inserted after writing the new state and before setting the VCPU
+request bit. Additionally, on the receiving VCPU thread's side, a
+corresponding read barrier must be inserted after reading the request bit
+and before proceeding to read the new state associated with it. See
+scenario 3, Message and Flag, of [lwn-mb]_ and the kernel documentation
+[memory-barriers]_.
+
+The pair of functions, kvm_check_request() and kvm_make_request(), provide
+the memory barriers, allowing this requirement to be handled internally by
+the API.
+
+Ensuring Requests Are Seen
+==========================
+
+When making requests to VCPUs, we want to avoid the receiving VCPU
+executing in guest mode for an arbitrary long time without handling the
+request. We can be sure this won't happen as long as we ensure the VCPU
+thread checks kvm_request_pending() before entering guest mode and that a
+kick will send an IPI to force an exit from guest mode when necessary.
+Extra care must be taken to cover the period after the VCPU thread's last
+kvm_request_pending() check and before it has entered guest mode, as kick
+IPIs will only trigger guest mode exits for VCPU threads that are in guest
+mode or at least have already disabled interrupts in order to prepare to
+enter guest mode. This means that an optimized implementation (see "IPI
+Reduction") must be certain when it's safe to not send the IPI. One
+solution, which all architectures except s390 apply, is to:
+
+- set ``vcpu->mode`` to IN_GUEST_MODE between disabling the interrupts and
+ the last kvm_request_pending() check;
+- enable interrupts atomically when entering the guest.
+
+This solution also requires memory barriers to be placed carefully in both
+the requesting thread and the receiving VCPU. With the memory barriers we
+can exclude the possibility of a VCPU thread observing
+!kvm_request_pending() on its last check and then not receiving an IPI for
+the next request made of it, even if the request is made immediately after
+the check. This is done by way of the Dekker memory barrier pattern
+(scenario 10 of [lwn-mb]_). As the Dekker pattern requires two variables,
+this solution pairs ``vcpu->mode`` with ``vcpu->requests``. Substituting
+them into the pattern gives::
+
+ CPU1 CPU2
+ ================= =================
+ local_irq_disable();
+ WRITE_ONCE(vcpu->mode, IN_GUEST_MODE); kvm_make_request(REQ, vcpu);
+ smp_mb(); smp_mb();
+ if (kvm_request_pending(vcpu)) { if (READ_ONCE(vcpu->mode) ==
+ IN_GUEST_MODE) {
+ ...abort guest entry... ...send IPI...
+ } }
+
+As stated above, the IPI is only useful for VCPU threads in guest mode or
+that have already disabled interrupts. This is why this specific case of
+the Dekker pattern has been extended to disable interrupts before setting
+``vcpu->mode`` to IN_GUEST_MODE. WRITE_ONCE() and READ_ONCE() are used to
+pedantically implement the memory barrier pattern, guaranteeing the
+compiler doesn't interfere with ``vcpu->mode``'s carefully planned
+accesses.
+
+IPI Reduction
+-------------
+
+As only one IPI is needed to get a VCPU to check for any/all requests,
+then they may be coalesced. This is easily done by having the first IPI
+sending kick also change the VCPU mode to something !IN_GUEST_MODE. The
+transitional state, EXITING_GUEST_MODE, is used for this purpose.
+
+Waiting for Acknowledgements
+----------------------------
+
+Some requests, those with the KVM_REQUEST_WAIT flag set, require IPIs to
+be sent, and the acknowledgements to be waited upon, even when the target
+VCPU threads are in modes other than IN_GUEST_MODE. For example, one case
+is when a target VCPU thread is in READING_SHADOW_PAGE_TABLES mode, which
+is set after disabling interrupts. To support these cases, the
+KVM_REQUEST_WAIT flag changes the condition for sending an IPI from
+checking that the VCPU is IN_GUEST_MODE to checking that it is not
+OUTSIDE_GUEST_MODE.
+
+Request-less VCPU Kicks
+-----------------------
+
+As the determination of whether or not to send an IPI depends on the
+two-variable Dekker memory barrier pattern, then it's clear that
+request-less VCPU kicks are almost never correct. Without the assurance
+that a non-IPI generating kick will still result in an action by the
+receiving VCPU, as the final kvm_request_pending() check does for
+request-accompanying kicks, then the kick may not do anything useful at
+all. If, for instance, a request-less kick was made to a VCPU that was
+just about to set its mode to IN_GUEST_MODE, meaning no IPI is sent, then
+the VCPU thread may continue its entry without actually having done
+whatever it was the kick was meant to initiate.
+
+One exception is x86's posted interrupt mechanism. In this case, however,
+even the request-less VCPU kick is coupled with the same
+local_irq_disable() + smp_mb() pattern described above; the ON bit
+(Outstanding Notification) in the posted interrupt descriptor takes the
+role of ``vcpu->requests``. When sending a posted interrupt, PIR.ON is
+set before reading ``vcpu->mode``; dually, in the VCPU thread,
+vmx_sync_pir_to_irr() reads PIR after setting ``vcpu->mode`` to
+IN_GUEST_MODE.
+
+Additional Considerations
+=========================
+
+Sleeping VCPUs
+--------------
+
+VCPU threads may need to consider requests before and/or after calling
+functions that may put them to sleep, e.g. kvm_vcpu_block(). Whether they
+do or not, and, if they do, which requests need consideration, is
+architecture dependent. kvm_vcpu_block() calls kvm_arch_vcpu_runnable()
+to check if it should awaken. One reason to do so is to provide
+architectures a function where requests may be checked if necessary.
+
+Clearing Requests
+-----------------
+
+Generally it only makes sense for the receiving VCPU thread to clear a
+request. However, in some circumstances, such as when the requesting
+thread and the receiving VCPU thread are executed serially, such as when
+they are the same thread, or when they are using some form of concurrency
+control to temporarily execute synchronously, then it's possible to know
+that the request may be cleared immediately, rather than waiting for the
+receiving VCPU thread to handle the request in VCPU RUN. The only current
+examples of this are kvm_vcpu_block() calls made by VCPUs to block
+themselves. A possible side-effect of that call is to make the
+KVM_REQ_UNHALT request, which may then be cleared immediately when the
+VCPU returns from the call.
+
+References
+==========
+
+.. [atomic-ops] Documentation/core-api/atomic_ops.rst
+.. [memory-barriers] Documentation/memory-barriers.txt
+.. [lwn-mb] https://lwn.net/Articles/573436/
--- /dev/null
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+Paravirt_ops
+============
+
+Linux provides support for different hypervisor virtualization technologies.
+Historically different binary kernels would be required in order to support
+different hypervisors, this restriction was removed with pv_ops.
+Linux pv_ops is a virtualization API which enables support for different
+hypervisors. It allows each hypervisor to override critical operations and
+allows a single kernel binary to run on all supported execution environments
+including native machine -- without any hypervisors.
+
+pv_ops provides a set of function pointers which represent operations
+corresponding to low level critical instructions and high level
+functionalities in various areas. pv-ops allows for optimizations at run
+time by enabling binary patching of the low-ops critical operations
+at boot time.
+
+pv_ops operations are classified into three categories:
+
+- simple indirect call
+ These operations correspond to high level functionality where it is
+ known that the overhead of indirect call isn't very important.
+
+- indirect call which allows optimization with binary patch
+ Usually these operations correspond to low level critical instructions. They
+ are called frequently and are performance critical. The overhead is
+ very important.
+
+- a set of macros for hand written assembly code
+ Hand written assembly codes (.S files) also need paravirtualization
+ because they include sensitive instructions or some of code paths in
+ them are very performance critical.
--- /dev/null
+ User Mode Linux HOWTO
+ User Mode Linux Core Team
+ Mon Nov 18 14:16:16 EST 2002
+
+ This document describes the use and abuse of Jeff Dike's User Mode
+ Linux: a port of the Linux kernel as a normal Intel Linux process.
+ ______________________________________________________________________
+
+ Table of Contents
+
+ 1. Introduction
+
+ 1.1 How is User Mode Linux Different?
+ 1.2 Why Would I Want User Mode Linux?
+
+ 2. Compiling the kernel and modules
+
+ 2.1 Compiling the kernel
+ 2.2 Compiling and installing kernel modules
+ 2.3 Compiling and installing uml_utilities
+
+ 3. Running UML and logging in
+
+ 3.1 Running UML
+ 3.2 Logging in
+ 3.3 Examples
+
+ 4. UML on 2G/2G hosts
+
+ 4.1 Introduction
+ 4.2 The problem
+ 4.3 The solution
+
+ 5. Setting up serial lines and consoles
+
+ 5.1 Specifying the device
+ 5.2 Specifying the channel
+ 5.3 Examples
+
+ 6. Setting up the network
+
+ 6.1 General setup
+ 6.2 Userspace daemons
+ 6.3 Specifying ethernet addresses
+ 6.4 UML interface setup
+ 6.5 Multicast
+ 6.6 TUN/TAP with the uml_net helper
+ 6.7 TUN/TAP with a preconfigured tap device
+ 6.8 Ethertap
+ 6.9 The switch daemon
+ 6.10 Slip
+ 6.11 Slirp
+ 6.12 pcap
+ 6.13 Setting up the host yourself
+
+ 7. Sharing Filesystems between Virtual Machines
+
+ 7.1 A warning
+ 7.2 Using layered block devices
+ 7.3 Note!
+ 7.4 Another warning
+ 7.5 uml_moo : Merging a COW file with its backing file
+
+ 8. Creating filesystems
+
+ 8.1 Create the filesystem file
+ 8.2 Assign the file to a UML device
+ 8.3 Creating and mounting the filesystem
+
+ 9. Host file access
+
+ 9.1 Using hostfs
+ 9.2 hostfs as the root filesystem
+ 9.3 Building hostfs
+
+ 10. The Management Console
+ 10.1 version
+ 10.2 halt and reboot
+ 10.3 config
+ 10.4 remove
+ 10.5 sysrq
+ 10.6 help
+ 10.7 cad
+ 10.8 stop
+ 10.9 go
+
+ 11. Kernel debugging
+
+ 11.1 Starting the kernel under gdb
+ 11.2 Examining sleeping processes
+ 11.3 Running ddd on UML
+ 11.4 Debugging modules
+ 11.5 Attaching gdb to the kernel
+ 11.6 Using alternate debuggers
+
+ 12. Kernel debugging examples
+
+ 12.1 The case of the hung fsck
+ 12.2 Episode 2: The case of the hung fsck
+
+ 13. What to do when UML doesn't work
+
+ 13.1 Strange compilation errors when you build from source
+ 13.2 (obsolete)
+ 13.3 A variety of panics and hangs with /tmp on a reiserfs filesystem
+ 13.4 The compile fails with errors about conflicting types for 'open', 'dup', and 'waitpid'
+ 13.5 UML doesn't work when /tmp is an NFS filesystem
+ 13.6 UML hangs on boot when compiled with gprof support
+ 13.7 syslogd dies with a SIGTERM on startup
+ 13.8 TUN/TAP networking doesn't work on a 2.4 host
+ 13.9 You can network to the host but not to other machines on the net
+ 13.10 I have no root and I want to scream
+ 13.11 UML build conflict between ptrace.h and ucontext.h
+ 13.12 The UML BogoMips is exactly half the host's BogoMips
+ 13.13 When you run UML, it immediately segfaults
+ 13.14 xterms appear, then immediately disappear
+ 13.15 Any other panic, hang, or strange behavior
+
+ 14. Diagnosing Problems
+
+ 14.1 Case 1 : Normal kernel panics
+ 14.2 Case 2 : Tracing thread panics
+ 14.3 Case 3 : Tracing thread panics caused by other threads
+ 14.4 Case 4 : Hangs
+
+ 15. Thanks
+
+ 15.1 Code and Documentation
+ 15.2 Flushing out bugs
+ 15.3 Buglets and clean-ups
+ 15.4 Case Studies
+ 15.5 Other contributions
+
+
+ ______________________________________________________________________
+
+ 1. Introduction
+
+ Welcome to User Mode Linux. It's going to be fun.
+
+
+
+ 1.1. How is User Mode Linux Different?
+
+ Normally, the Linux Kernel talks straight to your hardware (video
+ card, keyboard, hard drives, etc), and any programs which run ask the
+ kernel to operate the hardware, like so:
+
+
+
+ +-----------+-----------+----+
+ | Process 1 | Process 2 | ...|
+ +-----------+-----------+----+
+ | Linux Kernel |
+ +----------------------------+
+ | Hardware |
+ +----------------------------+
+
+
+
+
+ The User Mode Linux Kernel is different; instead of talking to the
+ hardware, it talks to a `real' Linux kernel (called the `host kernel'
+ from now on), like any other program. Programs can then run inside
+ User-Mode Linux as if they were running under a normal kernel, like
+ so:
+
+
+
+ +----------------+
+ | Process 2 | ...|
+ +-----------+----------------+
+ | Process 1 | User-Mode Linux|
+ +----------------------------+
+ | Linux Kernel |
+ +----------------------------+
+ | Hardware |
+ +----------------------------+
+
+
+
+
+
+ 1.2. Why Would I Want User Mode Linux?
+
+
+ 1. If User Mode Linux crashes, your host kernel is still fine.
+
+ 2. You can run a usermode kernel as a non-root user.
+
+ 3. You can debug the User Mode Linux like any normal process.
+
+ 4. You can run gprof (profiling) and gcov (coverage testing).
+
+ 5. You can play with your kernel without breaking things.
+
+ 6. You can use it as a sandbox for testing new apps.
+
+ 7. You can try new development kernels safely.
+
+ 8. You can run different distributions simultaneously.
+
+ 9. It's extremely fun.
+
+
+
+
+
+ 2. Compiling the kernel and modules
+
+
+
+
+ 2.1. Compiling the kernel
+
+
+ Compiling the user mode kernel is just like compiling any other
+ kernel. Let's go through the steps, using 2.4.0-prerelease (current
+ as of this writing) as an example:
+
+
+ 1. Download the latest UML patch from
+
+ the download page <http://user-mode-linux.sourceforge.net/
+
+ In this example, the file is uml-patch-2.4.0-prerelease.bz2.
+
+
+ 2. Download the matching kernel from your favourite kernel mirror,
+ such as:
+
+ ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2
+ <ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2>
+ .
+
+
+ 3. Make a directory and unpack the kernel into it.
+
+
+
+ host%
+ mkdir ~/uml
+
+
+
+
+
+
+ host%
+ cd ~/uml
+
+
+
+
+
+
+ host%
+ tar -xzvf linux-2.4.0-prerelease.tar.bz2
+
+
+
+
+
+
+ 4. Apply the patch using
+
+
+
+ host%
+ cd ~/uml/linux
+
+
+
+ host%
+ bzcat uml-patch-2.4.0-prerelease.bz2 | patch -p1
+
+
+
+
+
+
+ 5. Run your favorite config; `make xconfig ARCH=um' is the most
+ convenient. `make config ARCH=um' and 'make menuconfig ARCH=um'
+ will work as well. The defaults will give you a useful kernel. If
+ you want to change something, go ahead, it probably won't hurt
+ anything.
+
+
+ Note: If the host is configured with a 2G/2G address space split
+ rather than the usual 3G/1G split, then the packaged UML binaries
+ will not run. They will immediately segfault. See ``UML on 2G/2G
+ hosts'' for the scoop on running UML on your system.
+
+
+
+ 6. Finish with `make linux ARCH=um': the result is a file called
+ `linux' in the top directory of your source tree.
+
+ Make sure that you don't build this kernel in /usr/src/linux. On some
+ distributions, /usr/include/asm is a link into this pool. The user-
+ mode build changes the other end of that link, and things that include
+ <asm/anything.h> stop compiling.
+
+ The sources are also available from cvs at the project's cvs page,
+ which has directions on getting the sources. You can also browse the
+ CVS pool from there.
+
+ If you get the CVS sources, you will have to check them out into an
+ empty directory. You will then have to copy each file into the
+ corresponding directory in the appropriate kernel pool.
+
+ If you don't have the latest kernel pool, you can get the
+ corresponding user-mode sources with
+
+
+ host% cvs co -r v_2_3_x linux
+
+
+
+
+ where 'x' is the version in your pool. Note that you will not get the
+ bug fixes and enhancements that have gone into subsequent releases.
+
+
+ 2.2. Compiling and installing kernel modules
+
+ UML modules are built in the same way as the native kernel (with the
+ exception of the 'ARCH=um' that you always need for UML):
+
+
+ host% make modules ARCH=um
+
+
+
+
+ Any modules that you want to load into this kernel need to be built in
+ the user-mode pool. Modules from the native kernel won't work.
+
+ You can install them by using ftp or something to copy them into the
+ virtual machine and dropping them into /lib/modules/`uname -r`.
+
+ You can also get the kernel build process to install them as follows:
+
+ 1. with the kernel not booted, mount the root filesystem in the top
+ level of the kernel pool:
+
+
+ host% mount root_fs mnt -o loop
+
+
+
+
+
+
+ 2. run
+
+
+ host%
+ make modules_install INSTALL_MOD_PATH=`pwd`/mnt ARCH=um
+
+
+
+
+
+
+ 3. unmount the filesystem
+
+
+ host% umount mnt
+
+
+
+
+
+
+ 4. boot the kernel on it
+
+
+ When the system is booted, you can use insmod as usual to get the
+ modules into the kernel. A number of things have been loaded into UML
+ as modules, especially filesystems and network protocols and filters,
+ so most symbols which need to be exported probably already are.
+ However, if you do find symbols that need exporting, let us
+ <http://user-mode-linux.sourceforge.net/> know, and
+ they'll be "taken care of".
+
+
+
+ 2.3. Compiling and installing uml_utilities
+
+ Many features of the UML kernel require a user-space helper program,
+ so a uml_utilities package is distributed separately from the kernel
+ patch which provides these helpers. Included within this is:
+
+ o port-helper - Used by consoles which connect to xterms or ports
+
+ o tunctl - Configuration tool to create and delete tap devices
+
+ o uml_net - Setuid binary for automatic tap device configuration
+
+ o uml_switch - User-space virtual switch required for daemon
+ transport
+
+ The uml_utilities tree is compiled with:
+
+
+ host#
+ make && make install
+
+
+
+
+ Note that UML kernel patches may require a specific version of the
+ uml_utilities distribution. If you don't keep up with the mailing
+ lists, ensure that you have the latest release of uml_utilities if you
+ are experiencing problems with your UML kernel, particularly when
+ dealing with consoles or command-line switches to the helper programs
+
+
+
+
+
+
+
+
+ 3. Running UML and logging in
+
+
+
+ 3.1. Running UML
+
+ It runs on 2.2.15 or later, and all 2.4 kernels.
+
+
+ Booting UML is straightforward. Simply run 'linux': it will try to
+ mount the file `root_fs' in the current directory. You do not need to
+ run it as root. If your root filesystem is not named `root_fs', then
+ you need to put a `ubd0=root_fs_whatever' switch on the linux command
+ line.
+
+
+ You will need a filesystem to boot UML from. There are a number
+ available for download from here <http://user-mode-
+ linux.sourceforge.net/> . There are also several tools
+ <http://user-mode-linux.sourceforge.net/> which can be
+ used to generate UML-compatible filesystem images from media.
+ The kernel will boot up and present you with a login prompt.
+
+
+ Note: If the host is configured with a 2G/2G address space split
+ rather than the usual 3G/1G split, then the packaged UML binaries will
+ not run. They will immediately segfault. See ``UML on 2G/2G hosts''
+ for the scoop on running UML on your system.
+
+
+
+ 3.2. Logging in
+
+
+
+ The prepackaged filesystems have a root account with password 'root'
+ and a user account with password 'user'. The login banner will
+ generally tell you how to log in. So, you log in and you will find
+ yourself inside a little virtual machine. Our filesystems have a
+ variety of commands and utilities installed (and it is fairly easy to
+ add more), so you will have a lot of tools with which to poke around
+ the system.
+
+ There are a couple of other ways to log in:
+
+ o On a virtual console
+
+
+
+ Each virtual console that is configured (i.e. the device exists in
+ /dev and /etc/inittab runs a getty on it) will come up in its own
+ xterm. If you get tired of the xterms, read ``Setting up serial
+ lines and consoles'' to see how to attach the consoles to
+ something else, like host ptys.
+
+
+
+ o Over the serial line
+
+
+ In the boot output, find a line that looks like:
+
+
+
+ serial line 0 assigned pty /dev/ptyp1
+
+
+
+
+ Attach your favorite terminal program to the corresponding tty. I.e.
+ for minicom, the command would be
+
+
+ host% minicom -o -p /dev/ttyp1
+
+
+
+
+
+
+ o Over the net
+
+
+ If the network is running, then you can telnet to the virtual
+ machine and log in to it. See ``Setting up the network'' to learn
+ about setting up a virtual network.
+
+ When you're done using it, run halt, and the kernel will bring itself
+ down and the process will exit.
+
+
+ 3.3. Examples
+
+ Here are some examples of UML in action:
+
+ o A login session <http://user-mode-linux.sourceforge.net/login.html>
+
+ o A virtual network <http://user-mode-linux.sourceforge.net/net.html>
+
+
+
+
+
+
+
+ 4. UML on 2G/2G hosts
+
+
+
+
+ 4.1. Introduction
+
+
+ Most Linux machines are configured so that the kernel occupies the
+ upper 1G (0xc0000000 - 0xffffffff) of the 4G address space and
+ processes use the lower 3G (0x00000000 - 0xbfffffff). However, some
+ machine are configured with a 2G/2G split, with the kernel occupying
+ the upper 2G (0x80000000 - 0xffffffff) and processes using the lower
+ 2G (0x00000000 - 0x7fffffff).
+
+
+
+
+ 4.2. The problem
+
+
+ The prebuilt UML binaries on this site will not run on 2G/2G hosts
+ because UML occupies the upper .5G of the 3G process address space
+ (0xa0000000 - 0xbfffffff). Obviously, on 2G/2G hosts, this is right
+ in the middle of the kernel address space, so UML won't even load - it
+ will immediately segfault.
+
+
+
+
+ 4.3. The solution
+
+
+ The fix for this is to rebuild UML from source after enabling
+ CONFIG_HOST_2G_2G (under 'General Setup'). This will cause UML to
+ load itself in the top .5G of that smaller process address space,
+ where it will run fine. See ``Compiling the kernel and modules'' if
+ you need help building UML from source.
+
+
+
+
+
+
+
+
+
+
+ 5. Setting up serial lines and consoles
+
+
+ It is possible to attach UML serial lines and consoles to many types
+ of host I/O channels by specifying them on the command line.
+
+
+ You can attach them to host ptys, ttys, file descriptors, and ports.
+ This allows you to do things like
+
+ o have a UML console appear on an unused host console,
+
+ o hook two virtual machines together by having one attach to a pty
+ and having the other attach to the corresponding tty
+
+ o make a virtual machine accessible from the net by attaching a
+ console to a port on the host.
+
+
+ The general format of the command line option is device=channel.
+
+
+
+ 5.1. Specifying the device
+
+ Devices are specified with "con" or "ssl" (console or serial line,
+ respectively), optionally with a device number if you are talking
+ about a specific device.
+
+
+ Using just "con" or "ssl" describes all of the consoles or serial
+ lines. If you want to talk about console #3 or serial line #10, they
+ would be "con3" and "ssl10", respectively.
+
+
+ A specific device name will override a less general "con=" or "ssl=".
+ So, for example, you can assign a pty to each of the serial lines
+ except for the first two like this:
+
+
+ ssl=pty ssl0=tty:/dev/tty0 ssl1=tty:/dev/tty1
+
+
+
+
+ The specificity of the device name is all that matters; order on the
+ command line is irrelevant.
+
+
+
+ 5.2. Specifying the channel
+
+ There are a number of different types of channels to attach a UML
+ device to, each with a different way of specifying exactly what to
+ attach to.
+
+ o pseudo-terminals - device=pty pts terminals - device=pts
+
+
+ This will cause UML to allocate a free host pseudo-terminal for the
+ device. The terminal that it got will be announced in the boot
+ log. You access it by attaching a terminal program to the
+ corresponding tty:
+
+ o screen /dev/pts/n
+
+ o screen /dev/ttyxx
+
+ o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
+ devices
+
+ o kermit - start it up, 'open' the device, then 'connect'
+
+
+
+
+
+ o terminals - device=tty:tty device file
+
+
+ This will make UML attach the device to the specified tty (i.e
+
+
+ con1=tty:/dev/tty3
+
+
+
+
+ will attach UML's console 1 to the host's /dev/tty3). If the tty that
+ you specify is the slave end of a tty/pty pair, something else must
+ have already opened the corresponding pty in order for this to work.
+
+
+
+
+
+ o xterms - device=xterm
+
+
+ UML will run an xterm and the device will be attached to it.
+
+
+
+
+
+ o Port - device=port:port number
+
+
+ This will attach the UML devices to the specified host port.
+ Attaching console 1 to the host's port 9000 would be done like
+ this:
+
+
+ con1=port:9000
+
+
+
+
+ Attaching all the serial lines to that port would be done similarly:
+
+
+ ssl=port:9000
+
+
+
+
+ You access these devices by telnetting to that port. Each active tel-
+ net session gets a different device. If there are more telnets to a
+ port than UML devices attached to it, then the extra telnet sessions
+ will block until an existing telnet detaches, or until another device
+ becomes active (i.e. by being activated in /etc/inittab).
+
+ This channel has the advantage that you can both attach multiple UML
+ devices to it and know how to access them without reading the UML boot
+ log. It is also unique in allowing access to a UML from remote
+ machines without requiring that the UML be networked. This could be
+ useful in allowing public access to UMLs because they would be
+ accessible from the net, but wouldn't need any kind of network
+ filtering or access control because they would have no network access.
+
+
+ If you attach the main console to a portal, then the UML boot will
+ appear to hang. In reality, it's waiting for a telnet to connect, at
+ which point the boot will proceed.
+
+
+
+
+
+ o already-existing file descriptors - device=file descriptor
+
+
+ If you set up a file descriptor on the UML command line, you can
+ attach a UML device to it. This is most commonly used to put the
+ main console back on stdin and stdout after assigning all the other
+ consoles to something else:
+
+
+ con0=fd:0,fd:1 con=pts
+
+
+
+
+
+
+
+
+ o Nothing - device=null
+
+
+ This allows the device to be opened, in contrast to 'none', but
+ reads will block, and writes will succeed and the data will be
+ thrown out.
+
+
+
+
+
+ o None - device=none
+
+
+ This causes the device to disappear.
+
+
+
+ You can also specify different input and output channels for a device
+ by putting a comma between them:
+
+
+ ssl3=tty:/dev/tty2,xterm
+
+
+
+
+ will cause serial line 3 to accept input on the host's /dev/tty2 and
+ display output on an xterm. That's a silly example - the most common
+ use of this syntax is to reattach the main console to stdin and stdout
+ as shown above.
+
+
+ If you decide to move the main console away from stdin/stdout, the
+ initial boot output will appear in the terminal that you're running
+ UML in. However, once the console driver has been officially
+ initialized, then the boot output will start appearing wherever you
+ specified that console 0 should be. That device will receive all
+ subsequent output.
+
+
+
+ 5.3. Examples
+
+ There are a number of interesting things you can do with this
+ capability.
+
+
+ First, this is how you get rid of those bleeding console xterms by
+ attaching them to host ptys:
+
+
+ con=pty con0=fd:0,fd:1
+
+
+
+
+ This will make a UML console take over an unused host virtual console,
+ so that when you switch to it, you will see the UML login prompt
+ rather than the host login prompt:
+
+
+ con1=tty:/dev/tty6
+
+
+
+
+ You can attach two virtual machines together with what amounts to a
+ serial line as follows:
+
+ Run one UML with a serial line attached to a pty -
+
+
+ ssl1=pty
+
+
+
+
+ Look at the boot log to see what pty it got (this example will assume
+ that it got /dev/ptyp1).
+
+ Boot the other UML with a serial line attached to the corresponding
+ tty -
+
+
+ ssl1=tty:/dev/ttyp1
+
+
+
+
+ Log in, make sure that it has no getty on that serial line, attach a
+ terminal program like minicom to it, and you should see the login
+ prompt of the other virtual machine.
+
+
+ 6. Setting up the network
+
+
+
+ This page describes how to set up the various transports and to
+ provide a UML instance with network access to the host, other machines
+ on the local net, and the rest of the net.
+
+
+ As of 2.4.5, UML networking has been completely redone to make it much
+ easier to set up, fix bugs, and add new features.
+
+
+ There is a new helper, uml_net, which does the host setup that
+ requires root privileges.
+
+
+ There are currently five transport types available for a UML virtual
+ machine to exchange packets with other hosts:
+
+ o ethertap
+
+ o TUN/TAP
+
+ o Multicast
+
+ o a switch daemon
+
+ o slip
+
+ o slirp
+
+ o pcap
+
+ The TUN/TAP, ethertap, slip, and slirp transports allow a UML
+ instance to exchange packets with the host. They may be directed
+ to the host or the host may just act as a router to provide access
+ to other physical or virtual machines.
+
+
+ The pcap transport is a synthetic read-only interface, using the
+ libpcap binary to collect packets from interfaces on the host and
+ filter them. This is useful for building preconfigured traffic
+ monitors or sniffers.
+
+
+ The daemon and multicast transports provide a completely virtual
+ network to other virtual machines. This network is completely
+ disconnected from the physical network unless one of the virtual
+ machines on it is acting as a gateway.
+
+
+ With so many host transports, which one should you use? Here's when
+ you should use each one:
+
+ o ethertap - if you want access to the host networking and it is
+ running 2.2
+
+ o TUN/TAP - if you want access to the host networking and it is
+ running 2.4. Also, the TUN/TAP transport is able to use a
+ preconfigured device, allowing it to avoid using the setuid uml_net
+ helper, which is a security advantage.
+
+ o Multicast - if you want a purely virtual network and you don't want
+ to set up anything but the UML
+
+ o a switch daemon - if you want a purely virtual network and you
+ don't mind running the daemon in order to get somewhat better
+ performance
+
+ o slip - there is no particular reason to run the slip backend unless
+ ethertap and TUN/TAP are just not available for some reason
+
+ o slirp - if you don't have root access on the host to setup
+ networking, or if you don't want to allocate an IP to your UML
+
+ o pcap - not much use for actual network connectivity, but great for
+ monitoring traffic on the host
+
+ Ethertap is available on 2.4 and works fine. TUN/TAP is preferred
+ to it because it has better performance and ethertap is officially
+ considered obsolete in 2.4. Also, the root helper only needs to
+ run occasionally for TUN/TAP, rather than handling every packet, as
+ it does with ethertap. This is a slight security advantage since
+ it provides fewer opportunities for a nasty UML user to somehow
+ exploit the helper's root privileges.
+
+
+ 6.1. General setup
+
+ First, you must have the virtual network enabled in your UML. If are
+ running a prebuilt kernel from this site, everything is already
+ enabled. If you build the kernel yourself, under the "Network device
+ support" menu, enable "Network device support", and then the three
+ transports.
+
+
+ The next step is to provide a network device to the virtual machine.
+ This is done by describing it on the kernel command line.
+
+ The general format is
+
+
+ eth <n> = <transport> , <transport args>
+
+
+
+
+ For example, a virtual ethernet device may be attached to a host
+ ethertap device as follows:
+
+
+ eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254
+
+
+
+
+ This sets up eth0 inside the virtual machine to attach itself to the
+ host /dev/tap0, assigns it an ethernet address, and assigns the host
+ tap0 interface an IP address.
+
+
+
+ Note that the IP address you assign to the host end of the tap device
+ must be different than the IP you assign to the eth device inside UML.
+ If you are short on IPs and don't want to consume two per UML, then
+ you can reuse the host's eth IP address for the host ends of the tap
+ devices. Internally, the UMLs must still get unique IPs for their eth
+ devices. You can also give the UMLs non-routable IPs (192.168.x.x or
+ 10.x.x.x) and have the host masquerade them. This will let outgoing
+ connections work, but incoming connections won't without more work,
+ such as port forwarding from the host.
+ Also note that when you configure the host side of an interface, it is
+ only acting as a gateway. It will respond to pings sent to it
+ locally, but is not useful to do that since it's a host interface.
+ You are not talking to the UML when you ping that interface and get a
+ response.
+
+
+ You can also add devices to a UML and remove them at runtime. See the
+ ``The Management Console'' page for details.
+
+
+ The sections below describe this in more detail.
+
+
+ Once you've decided how you're going to set up the devices, you boot
+ UML, log in, configure the UML side of the devices, and set up routes
+ to the outside world. At that point, you will be able to talk to any
+ other machines, physical or virtual, on the net.
+
+
+ If ifconfig inside UML fails and the network refuses to come up, run
+ tell you what went wrong.
+
+
+
+ 6.2. Userspace daemons
+
+ You will likely need the setuid helper, or the switch daemon, or both.
+ They are both installed with the RPM and deb, so if you've installed
+ either, you can skip the rest of this section.
+
+
+ If not, then you need to check them out of CVS, build them, and
+ install them. The helper is uml_net, in CVS /tools/uml_net, and the
+ daemon is uml_switch, in CVS /tools/uml_router. They are both built
+ with a plain 'make'. Both need to be installed in a directory that's
+ in your path - /usr/bin is recommend. On top of that, uml_net needs
+ to be setuid root.
+
+
+
+ 6.3. Specifying ethernet addresses
+
+ Below, you will see that the TUN/TAP, ethertap, and daemon interfaces
+ allow you to specify hardware addresses for the virtual ethernet
+ devices. This is generally not necessary. If you don't have a
+ specific reason to do it, you probably shouldn't. If one is not
+ specified on the command line, the driver will assign one based on the
+ device IP address. It will provide the address fe:fd:nn:nn:nn:nn
+ where nn.nn.nn.nn is the device IP address. This is nearly always
+ sufficient to guarantee a unique hardware address for the device. A
+ couple of exceptions are:
+
+ o Another set of virtual ethernet devices are on the same network and
+ they are assigned hardware addresses using a different scheme which
+ may conflict with the UML IP address-based scheme
+
+ o You aren't going to use the device for IP networking, so you don't
+ assign the device an IP address
+
+ If you let the driver provide the hardware address, you should make
+ sure that the device IP address is known before the interface is
+ brought up. So, inside UML, this will guarantee that:
+
+
+
+ UML#
+ ifconfig eth0 192.168.0.250 up
+
+
+
+
+ If you decide to assign the hardware address yourself, make sure that
+ the first byte of the address is even. Addresses with an odd first
+ byte are broadcast addresses, which you don't want assigned to a
+ device.
+
+
+
+ 6.4. UML interface setup
+
+ Once the network devices have been described on the command line, you
+ should boot UML and log in.
+
+
+ The first thing to do is bring the interface up:
+
+
+ UML# ifconfig ethn ip-address up
+
+
+
+
+ You should be able to ping the host at this point.
+
+
+ To reach the rest of the world, you should set a default route to the
+ host:
+
+
+ UML# route add default gw host ip
+
+
+
+
+ Again, with host ip of 192.168.0.4:
+
+
+ UML# route add default gw 192.168.0.4
+
+
+
+
+ This page used to recommend setting a network route to your local net.
+ This is wrong, because it will cause UML to try to figure out hardware
+ addresses of the local machines by arping on the interface to the
+ host. Since that interface is basically a single strand of ethernet
+ with two nodes on it (UML and the host) and arp requests don't cross
+ networks, they will fail to elicit any responses. So, what you want
+ is for UML to just blindly throw all packets at the host and let it
+ figure out what to do with them, which is what leaving out the network
+ route and adding the default route does.
+
+
+ Note: If you can't communicate with other hosts on your physical
+ ethernet, it's probably because of a network route that's
+ automatically set up. If you run 'route -n' and see a route that
+ looks like this:
+
+
+
+
+ Destination Gateway Genmask Flags Metric Ref Use Iface
+ 192.168.0.0 0.0.0.0 255.255.255.0 U 0 0 0 eth0
+
+
+
+
+ with a mask that's not 255.255.255.255, then replace it with a route
+ to your host:
+
+
+ UML#
+ route del -net 192.168.0.0 dev eth0 netmask 255.255.255.0
+
+
+
+
+
+
+ UML#
+ route add -host 192.168.0.4 dev eth0
+
+
+
+
+ This, plus the default route to the host, will allow UML to exchange
+ packets with any machine on your ethernet.
+
+
+
+ 6.5. Multicast
+
+ The simplest way to set up a virtual network between multiple UMLs is
+ to use the mcast transport. This was written by Harald Welte and is
+ present in UML version 2.4.5-5um and later. Your system must have
+ multicast enabled in the kernel and there must be a multicast-capable
+ network device on the host. Normally, this is eth0, but if there is
+ no ethernet card on the host, then you will likely get strange error
+ messages when you bring the device up inside UML.
+
+
+ To use it, run two UMLs with
+
+
+ eth0=mcast
+
+
+
+
+ on their command lines. Log in, configure the ethernet device in each
+ machine with different IP addresses:
+
+
+ UML1# ifconfig eth0 192.168.0.254
+
+
+
+
+
+
+ UML2# ifconfig eth0 192.168.0.253
+
+
+
+
+ and they should be able to talk to each other.
+
+ The full set of command line options for this transport are
+
+
+
+ ethn=mcast,ethernet address,multicast
+ address,multicast port,ttl
+
+
+
+
+ Harald's original README is here <http://user-mode-linux.source-
+ forge.net/> and explains these in detail, as well as
+ some other issues.
+
+ There is also a related point-to-point only "ucast" transport.
+ This is useful when your network does not support multicast, and
+ all network connections are simple point to point links.
+
+ The full set of command line options for this transport are
+
+
+ ethn=ucast,ethernet address,remote address,listen port,remote port
+
+
+
+
+ 6.6. TUN/TAP with the uml_net helper
+
+ TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the
+ host. The TUN/TAP backend has been in UML since 2.4.9-3um.
+
+
+ The easiest way to get up and running is to let the setuid uml_net
+ helper do the host setup for you. This involves insmod-ing the tun.o
+ module if necessary, configuring the device, and setting up IP
+ forwarding, routing, and proxy arp. If you are new to UML networking,
+ do this first. If you're concerned about the security implications of
+ the setuid helper, use it to get up and running, then read the next
+ section to see how to have UML use a preconfigured tap device, which
+ avoids the use of uml_net.
+
+
+ If you specify an IP address for the host side of the device, the
+ uml_net helper will do all necessary setup on the host - the only
+ requirement is that TUN/TAP be available, either built in to the host
+ kernel or as the tun.o module.
+
+ The format of the command line switch to attach a device to a TUN/TAP
+ device is
+
+
+ eth <n> =tuntap,,, <IP address>
+
+
+
+
+ For example, this argument will attach the UML's eth0 to the next
+ available tap device and assign an ethernet address to it based on its
+ IP address
+
+
+ eth0=tuntap,,,192.168.0.254
+
+
+
+
+
+
+ Note that the IP address that must be used for the eth device inside
+ UML is fixed by the routing and proxy arp that is set up on the
+ TUN/TAP device on the host. You can use a different one, but it won't
+ work because reply packets won't reach the UML. This is a feature.
+ It prevents a nasty UML user from doing things like setting the UML IP
+ to the same as the network's nameserver or mail server.
+
+
+ There are a couple potential problems with running the TUN/TAP
+ transport on a 2.4 host kernel
+
+ o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host
+ kernel or use the ethertap transport.
+
+ o With an upgraded kernel, TUN/TAP may fail with
+
+
+ File descriptor in bad state
+
+
+
+
+ This is due to a header mismatch between the upgraded kernel and the
+ kernel that was originally installed on the machine. The fix is to
+ make sure that /usr/src/linux points to the headers for the running
+ kernel.
+
+ These were pointed out by Tim Robinson <timro at trkr dot net> in
+ <http://www.geocrawler.com/> name="this uml-
+ user post"> .
+
+
+
+ 6.7. TUN/TAP with a preconfigured tap device
+
+ If you prefer not to have UML use uml_net (which is somewhat
+ insecure), with UML 2.4.17-11, you can set up a TUN/TAP device
+ beforehand. The setup needs to be done as root, but once that's done,
+ there is no need for root assistance. Setting up the device is done
+ as follows:
+
+ o Create the device with tunctl (available from the UML utilities
+ tarball)
+
+
+
+
+ host# tunctl -u uid
+
+
+
+
+ where uid is the user id or username that UML will be run as. This
+ will tell you what device was created.
+
+ o Configure the device IP (change IP addresses and device name to
+ suit)
+
+
+
+
+ host# ifconfig tap0 192.168.0.254 up
+
+
+
+
+
+ o Set up routing and arping if desired - this is my recipe, there are
+ other ways of doing the same thing
+
+
+ host#
+ bash -c 'echo 1 > /proc/sys/net/ipv4/ip_forward'
+
+ host#
+ route add -host 192.168.0.253 dev tap0
+
+
+
+
+
+
+ host#
+ bash -c 'echo 1 > /proc/sys/net/ipv4/conf/tap0/proxy_arp'
+
+
+
+
+
+
+ host#
+ arp -Ds 192.168.0.253 eth0 pub
+
+
+
+
+ Note that this must be done every time the host boots - this configu-
+ ration is not stored across host reboots. So, it's probably a good
+ idea to stick it in an rc file. An even better idea would be a little
+ utility which reads the information from a config file and sets up
+ devices at boot time.
+
+ o Rather than using up two IPs and ARPing for one of them, you can
+ also provide direct access to your LAN by the UML by using a
+ bridge.
+
+
+ host#
+ brctl addbr br0
+
+
+
+
+
+
+ host#
+ ifconfig eth0 0.0.0.0 promisc up
+
+
+
+
+
+
+ host#
+ ifconfig tap0 0.0.0.0 promisc up
+
+
+
+
+
+
+ host#
+ ifconfig br0 192.168.0.1 netmask 255.255.255.0 up
+
+
+
+
+
+
+
+ host#
+ brctl stp br0 off
+
+
+
+
+
+
+ host#
+ brctl setfd br0 1
+
+
+
+
+
+
+ host#
+ brctl sethello br0 1
+
+
+
+
+
+
+ host#
+ brctl addif br0 eth0
+
+
+
+
+
+
+ host#
+ brctl addif br0 tap0
+
+
+
+
+ Note that 'br0' should be setup using ifconfig with the existing IP
+ address of eth0, as eth0 no longer has its own IP.
+
+ o
+
+
+ Also, the /dev/net/tun device must be writable by the user running
+ UML in order for the UML to use the device that's been configured
+ for it. The simplest thing to do is
+
+
+ host# chmod 666 /dev/net/tun
+
+
+
+
+ Making it world-writable looks bad, but it seems not to be
+ exploitable as a security hole. However, it does allow anyone to cre-
+ ate useless tap devices (useless because they can't configure them),
+ which is a DOS attack. A somewhat more secure alternative would to be
+ to create a group containing all the users who have preconfigured tap
+ devices and chgrp /dev/net/tun to that group with mode 664 or 660.
+
+
+ o Once the device is set up, run UML with 'eth0=tuntap,device name'
+ (i.e. 'eth0=tuntap,tap0') on the command line (or do it with the
+ mconsole config command).
+
+ o Bring the eth device up in UML and you're in business.
+
+ If you don't want that tap device any more, you can make it non-
+ persistent with
+
+
+ host# tunctl -d tap device
+
+
+
+
+ Finally, tunctl has a -b (for brief mode) switch which causes it to
+ output only the name of the tap device it created. This makes it
+ suitable for capture by a script:
+
+
+ host# TAP=`tunctl -u 1000 -b`
+
+
+
+
+
+
+ 6.8. Ethertap
+
+ Ethertap is the general mechanism on 2.2 for userspace processes to
+ exchange packets with the kernel.
+
+
+
+ To use this transport, you need to describe the virtual network device
+ on the UML command line. The general format for this is
+
+
+ eth <n> =ethertap, <device> , <ethernet address> , <tap IP address>
+
+
+
+
+ So, the previous example
+
+
+ eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254
+
+
+
+
+ attaches the UML eth0 device to the host /dev/tap0, assigns it the
+ ethernet address fe:fd:0:0:0:1, and assigns the IP address
+ 192.168.0.254 to the tap device.
+
+
+
+ The tap device is mandatory, but the others are optional. If the
+ ethernet address is omitted, one will be assigned to it.
+
+
+ The presence of the tap IP address will cause the helper to run and do
+ whatever host setup is needed to allow the virtual machine to
+ communicate with the outside world. If you're not sure you know what
+ you're doing, this is the way to go.
+
+
+ If it is absent, then you must configure the tap device and whatever
+ arping and routing you will need on the host. However, even in this
+ case, the uml_net helper still needs to be in your path and it must be
+ setuid root if you're not running UML as root. This is because the
+ tap device doesn't support SIGIO, which UML needs in order to use
+ something as a source of input. So, the helper is used as a
+ convenient asynchronous IO thread.
+
+ If you're using the uml_net helper, you can ignore the following host
+ setup - uml_net will do it for you. You just need to make sure you
+ have ethertap available, either built in to the host kernel or
+ available as a module.
+
+
+ If you want to set things up yourself, you need to make sure that the
+ appropriate /dev entry exists. If it doesn't, become root and create
+ it as follows:
+
+
+ mknod /dev/tap <minor> c 36 <minor> + 16
+
+
+
+
+ For example, this is how to create /dev/tap0:
+
+
+ mknod /dev/tap0 c 36 0 + 16
+
+
+
+
+ You also need to make sure that the host kernel has ethertap support.
+ If ethertap is enabled as a module, you apparently need to insmod
+ ethertap once for each ethertap device you want to enable. So,
+
+
+ host#
+ insmod ethertap
+
+
+
+
+ will give you the tap0 interface. To get the tap1 interface, you need
+ to run
+
+
+ host#
+ insmod ethertap unit=1 -o ethertap1
+
+
+
+
+
+
+
+ 6.9. The switch daemon
+
+ Note: This is the daemon formerly known as uml_router, but which was
+ renamed so the network weenies of the world would stop growling at me.
+
+
+ The switch daemon, uml_switch, provides a mechanism for creating a
+ totally virtual network. By default, it provides no connection to the
+ host network (but see -tap, below).
+
+
+ The first thing you need to do is run the daemon. Running it with no
+ arguments will make it listen on a default pair of unix domain
+ sockets.
+
+
+ If you want it to listen on a different pair of sockets, use
+
+
+ -unix control socket data socket
+
+
+
+
+
+ If you want it to act as a hub rather than a switch, use
+
+
+ -hub
+
+
+
+
+
+ If you want the switch to be connected to host networking (allowing
+ the umls to get access to the outside world through the host), use
+
+
+ -tap tap0
+
+
+
+
+
+ Note that the tap device must be preconfigured (see "TUN/TAP with a
+ preconfigured tap device", above). If you're using a different tap
+ device than tap0, specify that instead of tap0.
+
+
+ uml_switch can be backgrounded as follows
+
+
+ host%
+ uml_switch [ options ] < /dev/null > /dev/null
+
+
+
+
+ The reason it doesn't background by default is that it listens to
+ stdin for EOF. When it sees that, it exits.
+
+
+ The general format of the kernel command line switch is
+
+
+
+ ethn=daemon,ethernet address,socket
+ type,control socket,data socket
+
+
+
+
+ You can leave off everything except the 'daemon'. You only need to
+ specify the ethernet address if the one that will be assigned to it
+ isn't acceptable for some reason. The rest of the arguments describe
+ how to communicate with the daemon. You should only specify them if
+ you told the daemon to use different sockets than the default. So, if
+ you ran the daemon with no arguments, running the UML on the same
+ machine with
+ eth0=daemon
+
+
+
+
+ will cause the eth0 driver to attach itself to the daemon correctly.
+
+
+
+ 6.10. Slip
+
+ Slip is another, less general, mechanism for a process to communicate
+ with the host networking. In contrast to the ethertap interface,
+ which exchanges ethernet frames with the host and can be used to
+ transport any higher-level protocol, it can only be used to transport
+ IP.
+
+
+ The general format of the command line switch is
+
+
+
+ ethn=slip,slip IP
+
+
+
+
+ The slip IP argument is the IP address that will be assigned to the
+ host end of the slip device. If it is specified, the helper will run
+ and will set up the host so that the virtual machine can reach it and
+ the rest of the network.
+
+
+ There are some oddities with this interface that you should be aware
+ of. You should only specify one slip device on a given virtual
+ machine, and its name inside UML will be 'umn', not 'eth0' or whatever
+ you specified on the command line. These problems will be fixed at
+ some point.
+
+
+
+ 6.11. Slirp
+
+ slirp uses an external program, usually /usr/bin/slirp, to provide IP
+ only networking connectivity through the host. This is similar to IP
+ masquerading with a firewall, although the translation is performed in
+ user-space, rather than by the kernel. As slirp does not set up any
+ interfaces on the host, or changes routing, slirp does not require
+ root access or setuid binaries on the host.
+
+
+ The general format of the command line switch for slirp is:
+
+
+
+ ethn=slirp,ethernet address,slirp path
+
+
+
+
+ The ethernet address is optional, as UML will set up the interface
+ with an ethernet address based upon the initial IP address of the
+ interface. The slirp path is generally /usr/bin/slirp, although it
+ will depend on distribution.
+
+
+ The slirp program can have a number of options passed to the command
+ line and we can't add them to the UML command line, as they will be
+ parsed incorrectly. Instead, a wrapper shell script can be written or
+ the options inserted into the /.slirprc file. More information on
+ all of the slirp options can be found in its man pages.
+
+
+ The eth0 interface on UML should be set up with the IP 10.2.0.15,
+ although you can use anything as long as it is not used by a network
+ you will be connecting to. The default route on UML should be set to
+ use
+
+
+ UML#
+ route add default dev eth0
+
+
+
+
+ slirp provides a number of useful IP addresses which can be used by
+ UML, such as 10.0.2.3 which is an alias for the DNS server specified
+ in /etc/resolv.conf on the host or the IP given in the 'dns' option
+ for slirp.
+
+
+ Even with a baudrate setting higher than 115200, the slirp connection
+ is limited to 115200. If you need it to go faster, the slirp binary
+ needs to be compiled with FULL_BOLT defined in config.h.
+
+
+
+ 6.12. pcap
+
+ The pcap transport is attached to a UML ethernet device on the command
+ line or with uml_mconsole with the following syntax:
+
+
+
+ ethn=pcap,host interface,filter
+ expression,option1,option2
+
+
+
+
+ The expression and options are optional.
+
+
+ The interface is whatever network device on the host you want to
+ sniff. The expression is a pcap filter expression, which is also what
+ tcpdump uses, so if you know how to specify tcpdump filters, you will
+ use the same expressions here. The options are up to two of
+ 'promisc', control whether pcap puts the host interface into
+ promiscuous mode. 'optimize' and 'nooptimize' control whether the pcap
+ expression optimizer is used.
+
+
+ Example:
+
+
+
+ eth0=pcap,eth0,tcp
+
+ eth1=pcap,eth0,!tcp
+
+
+
+ will cause the UML eth0 to emit all tcp packets on the host eth0 and
+ the UML eth1 to emit all non-tcp packets on the host eth0.
+
+
+
+ 6.13. Setting up the host yourself
+
+ If you don't specify an address for the host side of the ethertap or
+ slip device, UML won't do any setup on the host. So this is what is
+ needed to get things working (the examples use a host-side IP of
+ 192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your
+ own network):
+
+ o The device needs to be configured with its IP address. Tap devices
+ are also configured with an mtu of 1484. Slip devices are
+ configured with a point-to-point address pointing at the UML ip
+ address.
+
+
+ host# ifconfig tap0 arp mtu 1484 192.168.0.251 up
+
+
+
+
+
+
+ host#
+ ifconfig sl0 192.168.0.251 pointopoint 192.168.0.250 up
+
+
+
+
+
+ o If a tap device is being set up, a route is set to the UML IP.
+
+
+ UML# route add -host 192.168.0.250 gw 192.168.0.251
+
+
+
+
+
+ o To allow other hosts on your network to see the virtual machine,
+ proxy arp is set up for it.
+
+
+ host# arp -Ds 192.168.0.250 eth0 pub
+
+
+
+
+
+ o Finally, the host is set up to route packets.
+
+
+ host# echo 1 > /proc/sys/net/ipv4/ip_forward
+
+
+
+
+
+
+
+
+
+
+ 7. Sharing Filesystems between Virtual Machines
+
+
+
+
+ 7.1. A warning
+
+ Don't attempt to share filesystems simply by booting two UMLs from the
+ same file. That's the same thing as booting two physical machines
+ from a shared disk. It will result in filesystem corruption.
+
+
+
+ 7.2. Using layered block devices
+
+ The way to share a filesystem between two virtual machines is to use
+ the copy-on-write (COW) layering capability of the ubd block driver.
+ As of 2.4.6-2um, the driver supports layering a read-write private
+ device over a read-only shared device. A machine's writes are stored
+ in the private device, while reads come from either device - the
+ private one if the requested block is valid in it, the shared one if
+ not. Using this scheme, the majority of data which is unchanged is
+ shared between an arbitrary number of virtual machines, each of which
+ has a much smaller file containing the changes that it has made. With
+ a large number of UMLs booting from a large root filesystem, this
+ leads to a huge disk space saving. It will also help performance,
+ since the host will be able to cache the shared data using a much
+ smaller amount of memory, so UML disk requests will be served from the
+ host's memory rather than its disks.
+
+
+
+
+ To add a copy-on-write layer to an existing block device file, simply
+ add the name of the COW file to the appropriate ubd switch:
+
+
+ ubd0=root_fs_cow,root_fs_debian_22
+
+
+
+
+ where 'root_fs_cow' is the private COW file and 'root_fs_debian_22' is
+ the existing shared filesystem. The COW file need not exist. If it
+ doesn't, the driver will create and initialize it. Once the COW file
+ has been initialized, it can be used on its own on the command line:
+
+
+ ubd0=root_fs_cow
+
+
+
+
+ The name of the backing file is stored in the COW file header, so it
+ would be redundant to continue specifying it on the command line.
+
+
+
+ 7.3. Note!
+
+ When checking the size of the COW file in order to see the gobs of
+ space that you're saving, make sure you use 'ls -ls' to see the actual
+ disk consumption rather than the length of the file. The COW file is
+ sparse, so the length will be very different from the disk usage.
+ Here is a 'ls -l' of a COW file and backing file from one boot and
+ shutdown:
+ host% ls -l cow.debian debian2.2
+ -rw-r--r-- 1 jdike jdike 492504064 Aug 6 21:16 cow.debian
+ -rwxrw-rw- 1 jdike jdike 537919488 Aug 6 20:42 debian2.2
+
+
+
+
+ Doesn't look like much saved space, does it? Well, here's 'ls -ls':
+
+
+ host% ls -ls cow.debian debian2.2
+ 880 -rw-r--r-- 1 jdike jdike 492504064 Aug 6 21:16 cow.debian
+ 525832 -rwxrw-rw- 1 jdike jdike 537919488 Aug 6 20:42 debian2.2
+
+
+
+
+ Now, you can see that the COW file has less than a meg of disk, rather
+ than 492 meg.
+
+
+
+ 7.4. Another warning
+
+ Once a filesystem is being used as a readonly backing file for a COW
+ file, do not boot directly from it or modify it in any way. Doing so
+ will invalidate any COW files that are using it. The mtime and size
+ of the backing file are stored in the COW file header at its creation,
+ and they must continue to match. If they don't, the driver will
+ refuse to use the COW file.
+
+
+
+
+ If you attempt to evade this restriction by changing either the
+ backing file or the COW header by hand, you will get a corrupted
+ filesystem.
+
+
+
+
+ Among other things, this means that upgrading the distribution in a
+ backing file and expecting that all of the COW files using it will see
+ the upgrade will not work.
+
+
+
+
+ 7.5. uml_moo : Merging a COW file with its backing file
+
+ Depending on how you use UML and COW devices, it may be advisable to
+ merge the changes in the COW file into the backing file every once in
+ a while.
+
+
+
+
+ The utility that does this is uml_moo. Its usage is
+
+
+ host% uml_moo COW file new backing file
+
+
+
+
+ There's no need to specify the backing file since that information is
+ already in the COW file header. If you're paranoid, boot the new
+ merged file, and if you're happy with it, move it over the old backing
+ file.
+
+
+
+
+ uml_moo creates a new backing file by default as a safety measure. It
+ also has a destructive merge option which will merge the COW file
+ directly into its current backing file. This is really only usable
+ when the backing file only has one COW file associated with it. If
+ there are multiple COWs associated with a backing file, a -d merge of
+ one of them will invalidate all of the others. However, it is
+ convenient if you're short of disk space, and it should also be
+ noticeably faster than a non-destructive merge.
+
+
+
+
+ uml_moo is installed with the UML deb and RPM. If you didn't install
+ UML from one of those packages, you can also get it from the UML
+ utilities <http://user-mode-linux.sourceforge.net/
+ utilities> tar file in tools/moo.
+
+
+
+
+
+
+
+
+ 8. Creating filesystems
+
+
+ You may want to create and mount new UML filesystems, either because
+ your root filesystem isn't large enough or because you want to use a
+ filesystem other than ext2.
+
+
+ This was written on the occasion of reiserfs being included in the
+ 2.4.1 kernel pool, and therefore the 2.4.1 UML, so the examples will
+ talk about reiserfs. This information is generic, and the examples
+ should be easy to translate to the filesystem of your choice.
+
+
+ 8.1. Create the filesystem file
+
+ dd is your friend. All you need to do is tell dd to create an empty
+ file of the appropriate size. I usually make it sparse to save time
+ and to avoid allocating disk space until it's actually used. For
+ example, the following command will create a sparse 100 meg file full
+ of zeroes.
+
+
+ host%
+ dd if=/dev/zero of=new_filesystem seek=100 count=1 bs=1M
+
+
+
+
+
+
+ 8.2. Assign the file to a UML device
+
+ Add an argument like the following to the UML command line:
+
+ ubd4=new_filesystem
+
+
+
+
+ making sure that you use an unassigned ubd device number.
+
+
+
+ 8.3. Creating and mounting the filesystem
+
+ Make sure that the filesystem is available, either by being built into
+ the kernel, or available as a module, then boot up UML and log in. If
+ the root filesystem doesn't have the filesystem utilities (mkfs, fsck,
+ etc), then get them into UML by way of the net or hostfs.
+
+
+ Make the new filesystem on the device assigned to the new file:
+
+
+ host# mkreiserfs /dev/ubd/4
+
+
+ <----------- MKREISERFSv2 ----------->
+
+ ReiserFS version 3.6.25
+ Block size 4096 bytes
+ Block count 25856
+ Used blocks 8212
+ Journal - 8192 blocks (18-8209), journal header is in block 8210
+ Bitmaps: 17
+ Root block 8211
+ Hash function "r5"
+ ATTENTION: ALL DATA WILL BE LOST ON '/dev/ubd/4'! (y/n)y
+ journal size 8192 (from 18)
+ Initializing journal - 0%....20%....40%....60%....80%....100%
+ Syncing..done.
+
+
+
+
+ Now, mount it:
+
+
+ UML#
+ mount /dev/ubd/4 /mnt
+
+
+
+
+ and you're in business.
+
+
+
+
+
+
+
+
+
+ 9. Host file access
+
+
+ If you want to access files on the host machine from inside UML, you
+ can treat it as a separate machine and either nfs mount directories
+ from the host or copy files into the virtual machine with scp or rcp.
+ However, since UML is running on the host, it can access those
+ files just like any other process and make them available inside the
+ virtual machine without needing to use the network.
+
+
+ This is now possible with the hostfs virtual filesystem. With it, you
+ can mount a host directory into the UML filesystem and access the
+ files contained in it just as you would on the host.
+
+
+ 9.1. Using hostfs
+
+ To begin with, make sure that hostfs is available inside the virtual
+ machine with
+
+
+ UML# cat /proc/filesystems
+
+
+
+ . hostfs should be listed. If it's not, either rebuild the kernel
+ with hostfs configured into it or make sure that hostfs is built as a
+ module and available inside the virtual machine, and insmod it.
+
+
+ Now all you need to do is run mount:
+
+
+ UML# mount none /mnt/host -t hostfs
+
+
+
+
+ will mount the host's / on the virtual machine's /mnt/host.
+
+
+ If you don't want to mount the host root directory, then you can
+ specify a subdirectory to mount with the -o switch to mount:
+
+
+ UML# mount none /mnt/home -t hostfs -o /home
+
+
+
+
+ will mount the hosts's /home on the virtual machine's /mnt/home.
+
+
+
+ 9.2. hostfs as the root filesystem
+
+ It's possible to boot from a directory hierarchy on the host using
+ hostfs rather than using the standard filesystem in a file.
+
+ To start, you need that hierarchy. The easiest way is to loop mount
+ an existing root_fs file:
+
+
+ host# mount root_fs uml_root_dir -o loop
+
+
+
+
+ You need to change the filesystem type of / in etc/fstab to be
+ 'hostfs', so that line looks like this:
+
+ /dev/ubd/0 / hostfs defaults 1 1
+
+
+
+
+ Then you need to chown to yourself all the files in that directory
+ that are owned by root. This worked for me:
+
+
+ host# find . -uid 0 -exec chown jdike {} \;
+
+
+
+
+ Next, make sure that your UML kernel has hostfs compiled in, not as a
+ module. Then run UML with the boot device pointing at that directory:
+
+
+ ubd0=/path/to/uml/root/directory
+
+
+
+
+ UML should then boot as it does normally.
+
+
+ 9.3. Building hostfs
+
+ If you need to build hostfs because it's not in your kernel, you have
+ two choices:
+
+
+
+ o Compiling hostfs into the kernel:
+
+
+ Reconfigure the kernel and set the 'Host filesystem' option under
+
+
+ o Compiling hostfs as a module:
+
+
+ Reconfigure the kernel and set the 'Host filesystem' option under
+ be in arch/um/fs/hostfs/hostfs.o. Install that in
+ /lib/modules/`uname -r`/fs in the virtual machine, boot it up, and
+
+
+ UML# insmod hostfs
+
+
+
+
+
+
+
+
+
+
+
+
+ 10. The Management Console
+
+
+
+ The UML management console is a low-level interface to the kernel,
+ somewhat like the i386 SysRq interface. Since there is a full-blown
+ operating system under UML, there is much greater flexibility possible
+ than with the SysRq mechanism.
+
+
+ There are a number of things you can do with the mconsole interface:
+
+ o get the kernel version
+
+ o add and remove devices
+
+ o halt or reboot the machine
+
+ o Send SysRq commands
+
+ o Pause and resume the UML
+
+
+ You need the mconsole client (uml_mconsole) which is present in CVS
+ (/tools/mconsole) in 2.4.5-9um and later, and will be in the RPM in
+ 2.4.6.
+
+
+ You also need CONFIG_MCONSOLE (under 'General Setup') enabled in UML.
+ When you boot UML, you'll see a line like:
+
+
+ mconsole initialized on /home/jdike/.uml/umlNJ32yL/mconsole
+
+
+
+
+ If you specify a unique machine id one the UML command line, i.e.
+
+
+ umid=debian
+
+
+
+
+ you'll see this
+
+
+ mconsole initialized on /home/jdike/.uml/debian/mconsole
+
+
+
+
+ That file is the socket that uml_mconsole will use to communicate with
+ UML. Run it with either the umid or the full path as its argument:
+
+
+ host% uml_mconsole debian
+
+
+
+
+ or
+
+
+ host% uml_mconsole /home/jdike/.uml/debian/mconsole
+
+
+
+
+ You'll get a prompt, at which you can run one of these commands:
+
+ o version
+
+ o halt
+
+ o reboot
+
+ o config
+
+ o remove
+
+ o sysrq
+
+ o help
+
+ o cad
+
+ o stop
+
+ o go
+
+
+ 10.1. version
+
+ This takes no arguments. It prints the UML version.
+
+
+ (mconsole) version
+ OK Linux usermode 2.4.5-9um #1 Wed Jun 20 22:47:08 EDT 2001 i686
+
+
+
+
+ There are a couple actual uses for this. It's a simple no-op which
+ can be used to check that a UML is running. It's also a way of
+ sending an interrupt to the UML. This is sometimes useful on SMP
+ hosts, where there's a bug which causes signals to UML to be lost,
+ often causing it to appear to hang. Sending such a UML the mconsole
+ version command is a good way to 'wake it up' before networking has
+ been enabled, as it does not do anything to the function of the UML.
+
+
+
+ 10.2. halt and reboot
+
+ These take no arguments. They shut the machine down immediately, with
+ no syncing of disks and no clean shutdown of userspace. So, they are
+ pretty close to crashing the machine.
+
+
+ (mconsole) halt
+ OK
+
+
+
+
+
+
+ 10.3. config
+
+ "config" adds a new device to the virtual machine. Currently the ubd
+ and network drivers support this. It takes one argument, which is the
+ device to add, with the same syntax as the kernel command line.
+
+
+
+
+ (mconsole)
+ config ubd3=/home/jdike/incoming/roots/root_fs_debian22
+
+ OK
+ (mconsole) config eth1=mcast
+ OK
+
+
+
+
+
+
+ 10.4. remove
+
+ "remove" deletes a device from the system. Its argument is just the
+ name of the device to be removed. The device must be idle in whatever
+ sense the driver considers necessary. In the case of the ubd driver,
+ the removed block device must not be mounted, swapped on, or otherwise
+ open, and in the case of the network driver, the device must be down.
+
+
+ (mconsole) remove ubd3
+ OK
+ (mconsole) remove eth1
+ OK
+
+
+
+
+
+
+ 10.5. sysrq
+
+ This takes one argument, which is a single letter. It calls the
+ generic kernel's SysRq driver, which does whatever is called for by
+ that argument. See the SysRq documentation in
+ Documentation/admin-guide/sysrq.rst in your favorite kernel tree to
+ see what letters are valid and what they do.
+
+
+
+ 10.6. help
+
+ "help" returns a string listing the valid commands and what each one
+ does.
+
+
+
+ 10.7. cad
+
+ This invokes the Ctl-Alt-Del action on init. What exactly this ends
+ up doing is up to /etc/inittab. Normally, it reboots the machine.
+ With UML, this is usually not desired, so if a halt would be better,
+ then find the section of inittab that looks like this
+
+
+ # What to do when CTRL-ALT-DEL is pressed.
+ ca:12345:ctrlaltdel:/sbin/shutdown -t1 -a -r now
+
+
+
+
+ and change the command to halt.
+
+
+
+ 10.8. stop
+
+ This puts the UML in a loop reading mconsole requests until a 'go'
+ mconsole command is received. This is very useful for making backups
+ of UML filesystems, as the UML can be stopped, then synced via 'sysrq
+ s', so that everything is written to the filesystem. You can then copy
+ the filesystem and then send the UML 'go' via mconsole.
+
+
+ Note that a UML running with more than one CPU will have problems
+ after you send the 'stop' command, as only one CPU will be held in a
+ mconsole loop and all others will continue as normal. This is a bug,
+ and will be fixed.
+
+
+
+ 10.9. go
+
+ This resumes a UML after being paused by a 'stop' command. Note that
+ when the UML has resumed, TCP connections may have timed out and if
+ the UML is paused for a long period of time, crond might go a little
+ crazy, running all the jobs it didn't do earlier.
+
+
+
+
+
+
+
+
+ 11. Kernel debugging
+
+
+ Note: The interface that makes debugging, as described here, possible
+ is present in 2.4.0-test6 kernels and later.
+
+
+ Since the user-mode kernel runs as a normal Linux process, it is
+ possible to debug it with gdb almost like any other process. It is
+ slightly different because the kernel's threads are already being
+ ptraced for system call interception, so gdb can't ptrace them.
+ However, a mechanism has been added to work around that problem.
+
+
+ In order to debug the kernel, you need build it from source. See
+ ``Compiling the kernel and modules'' for information on doing that.
+ Make sure that you enable CONFIG_DEBUGSYM and CONFIG_PT_PROXY during
+ the config. These will compile the kernel with -g, and enable the
+ ptrace proxy so that gdb works with UML, respectively.
+
+
+
+
+ 11.1. Starting the kernel under gdb
+
+ You can have the kernel running under the control of gdb from the
+ beginning by putting 'debug' on the command line. You will get an
+ xterm with gdb running inside it. The kernel will send some commands
+ to gdb which will leave it stopped at the beginning of start_kernel.
+ At this point, you can get things going with 'next', 'step', or
+ 'cont'.
+
+
+ There is a transcript of a debugging session here <debug-
+ session.html> , with breakpoints being set in the scheduler and in an
+ interrupt handler.
+ 11.2. Examining sleeping processes
+
+ Not every bug is evident in the currently running process. Sometimes,
+ processes hang in the kernel when they shouldn't because they've
+ deadlocked on a semaphore or something similar. In this case, when
+ you ^C gdb and get a backtrace, you will see the idle thread, which
+ isn't very relevant.
+
+
+ What you want is the stack of whatever process is sleeping when it
+ shouldn't be. You need to figure out which process that is, which is
+ generally fairly easy. Then you need to get its host process id,
+ which you can do either by looking at ps on the host or at
+ task.thread.extern_pid in gdb.
+
+
+ Now what you do is this:
+
+ o detach from the current thread
+
+
+ (UML gdb) det
+
+
+
+
+
+ o attach to the thread you are interested in
+
+
+ (UML gdb) att <host pid>
+
+
+
+
+
+ o look at its stack and anything else of interest
+
+
+ (UML gdb) bt
+
+
+
+
+ Note that you can't do anything at this point that requires that a
+ process execute, e.g. calling a function
+
+ o when you're done looking at that process, reattach to the current
+ thread and continue it
+
+
+ (UML gdb)
+ att 1
+
+
+
+
+
+
+ (UML gdb)
+ c
+
+
+
+
+ Here, specifying any pid which is not the process id of a UML thread
+ will cause gdb to reattach to the current thread. I commonly use 1,
+ but any other invalid pid would work.
+
+
+
+ 11.3. Running ddd on UML
+
+ ddd works on UML, but requires a special kludge. The process goes
+ like this:
+
+ o Start ddd
+
+
+ host% ddd linux
+
+
+
+
+
+ o With ps, get the pid of the gdb that ddd started. You can ask the
+ gdb to tell you, but for some reason that confuses things and
+ causes a hang.
+
+ o run UML with 'debug=parent gdb-pid=<pid>' added to the command line
+ - it will just sit there after you hit return
+
+ o type 'att 1' to the ddd gdb and you will see something like
+
+
+ 0xa013dc51 in __kill ()
+
+
+ (gdb)
+
+
+
+
+
+ o At this point, type 'c', UML will boot up, and you can use ddd just
+ as you do on any other process.
+
+
+
+ 11.4. Debugging modules
+
+ gdb has support for debugging code which is dynamically loaded into
+ the process. This support is what is needed to debug kernel modules
+ under UML.
+
+
+ Using that support is somewhat complicated. You have to tell gdb what
+ object file you just loaded into UML and where in memory it is. Then,
+ it can read the symbol table, and figure out where all the symbols are
+ from the load address that you provided. It gets more interesting
+ when you load the module again (i.e. after an rmmod). You have to
+ tell gdb to forget about all its symbols, including the main UML ones
+ for some reason, then load then all back in again.
+
+
+ There's an easy way and a hard way to do this. The easy way is to use
+ the umlgdb expect script written by Chandan Kudige. It basically
+ automates the process for you.
+
+
+ First, you must tell it where your modules are. There is a list in
+ the script that looks like this:
+ set MODULE_PATHS {
+ "fat" "/usr/src/uml/linux-2.4.18/fs/fat/fat.o"
+ "isofs" "/usr/src/uml/linux-2.4.18/fs/isofs/isofs.o"
+ "minix" "/usr/src/uml/linux-2.4.18/fs/minix/minix.o"
+ }
+
+
+
+
+ You change that to list the names and paths of the modules that you
+ are going to debug. Then you run it from the toplevel directory of
+ your UML pool and it basically tells you what to do:
+
+
+
+
+ ******** GDB pid is 21903 ********
+ Start UML as: ./linux <kernel switches> debug gdb-pid=21903
+
+
+
+ GNU gdb 5.0rh-5 Red Hat Linux 7.1
+ Copyright 2001 Free Software Foundation, Inc.
+ GDB is free software, covered by the GNU General Public License, and you are
+ welcome to change it and/or distribute copies of it under certain conditions.
+ Type "show copying" to see the conditions.
+ There is absolutely no warranty for GDB. Type "show warranty" for details.
+ This GDB was configured as "i386-redhat-linux"...
+ (gdb) b sys_init_module
+ Breakpoint 1 at 0xa0011923: file module.c, line 349.
+ (gdb) att 1
+
+
+
+
+ After you run UML and it sits there doing nothing, you hit return at
+ the 'att 1' and continue it:
+
+
+ Attaching to program: /home/jdike/linux/2.4/um/./linux, process 1
+ 0xa00f4221 in __kill ()
+ (UML gdb) c
+ Continuing.
+
+
+
+
+ At this point, you debug normally. When you insmod something, the
+ expect magic will kick in and you'll see something like:
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ *** Module hostfs loaded ***
+ Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs",
+ mod_user=0x8070e00) at module.c:349
+ 349 char *name, *n_name, *name_tmp = NULL;
+ (UML gdb) finish
+ Run till exit from #0 sys_init_module (name_user=0x805abb0 "hostfs",
+ mod_user=0x8070e00) at module.c:349
+ 0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411
+ 411 else res = EXECUTE_SYSCALL(syscall, regs);
+ Value returned is $1 = 0
+ (UML gdb)
+ p/x (int)module_list + module_list->size_of_struct
+
+ $2 = 0xa9021054
+ (UML gdb) symbol-file ./linux
+ Load new symbol table from "./linux"? (y or n) y
+ Reading symbols from ./linux...
+ done.
+ (UML gdb)
+ add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054
+
+ add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at
+ .text_addr = 0xa9021054
+ (y or n) y
+
+ Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o...
+ done.
+ (UML gdb) p *module_list
+ $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs",
+ size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1,
+ nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0,
+ init = 0xa90221f0 <init_hostfs>, cleanup = 0xa902222c <exit_hostfs>,
+ ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0,
+ persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0,
+ kallsyms_end = 0x0,
+ archdata_start = 0x1b855 <Address 0x1b855 out of bounds>,
+ archdata_end = 0xe5890000 <Address 0xe5890000 out of bounds>,
+ kernel_data = 0xf689c35d <Address 0xf689c35d out of bounds>}
+ >> Finished loading symbols for hostfs ...
+
+
+
+
+ That's the easy way. It's highly recommended. The hard way is
+ described below in case you're interested in what's going on.
+
+
+ Boot the kernel under the debugger and load the module with insmod or
+ modprobe. With gdb, do:
+
+
+ (UML gdb) p module_list
+
+
+
+
+ This is a list of modules that have been loaded into the kernel, with
+ the most recently loaded module first. Normally, the module you want
+ is at module_list. If it's not, walk down the next links, looking at
+ the name fields until find the module you want to debug. Take the
+ address of that structure, and add module.size_of_struct (which in
+ 2.4.10 kernels is 96 (0x60)) to it. Gdb can make this hard addition
+ for you :-):
+
+
+
+ (UML gdb)
+ printf "%#x\n", (int)module_list module_list->size_of_struct
+
+
+
+
+ The offset from the module start occasionally changes (before 2.4.0,
+ it was module.size_of_struct + 4), so it's a good idea to check the
+ init and cleanup addresses once in a while, as describe below. Now
+ do:
+
+
+ (UML gdb)
+ add-symbol-file /path/to/module/on/host that_address
+
+
+
+
+ Tell gdb you really want to do it, and you're in business.
+
+
+ If there's any doubt that you got the offset right, like breakpoints
+ appear not to work, or they're appearing in the wrong place, you can
+ check it by looking at the module structure. The init and cleanup
+ fields should look like:
+
+
+ init = 0x588066b0 <init_hostfs>, cleanup = 0x588066c0 <exit_hostfs>
+
+
+
+
+ with no offsets on the symbol names. If the names are right, but they
+ are offset, then the offset tells you how much you need to add to the
+ address you gave to add-symbol-file.
+
+
+ When you want to load in a new version of the module, you need to get
+ gdb to forget about the old one. The only way I've found to do that
+ is to tell gdb to forget about all symbols that it knows about:
+
+
+ (UML gdb) symbol-file
+
+
+
+
+ Then reload the symbols from the kernel binary:
+
+
+ (UML gdb) symbol-file /path/to/kernel
+
+
+
+
+ and repeat the process above. You'll also need to re-enable break-
+ points. They were disabled when you dumped all the symbols because
+ gdb couldn't figure out where they should go.
+
+
+
+ 11.5. Attaching gdb to the kernel
+
+ If you don't have the kernel running under gdb, you can attach gdb to
+ it later by sending the tracing thread a SIGUSR1. The first line of
+ the console output identifies its pid:
+ tracing thread pid = 20093
+
+
+
+
+ When you send it the signal:
+
+
+ host% kill -USR1 20093
+
+
+
+
+ you will get an xterm with gdb running in it.
+
+
+ If you have the mconsole compiled into UML, then the mconsole client
+ can be used to start gdb:
+
+
+ (mconsole) (mconsole) config gdb=xterm
+
+
+
+
+ will fire up an xterm with gdb running in it.
+
+
+
+ 11.6. Using alternate debuggers
+
+ UML has support for attaching to an already running debugger rather
+ than starting gdb itself. This is present in CVS as of 17 Apr 2001.
+ I sent it to Alan for inclusion in the ac tree, and it will be in my
+ 2.4.4 release.
+
+
+ This is useful when gdb is a subprocess of some UI, such as emacs or
+ ddd. It can also be used to run debuggers other than gdb on UML.
+ Below is an example of using strace as an alternate debugger.
+
+
+ To do this, you need to get the pid of the debugger and pass it in
+ with the
+
+
+ If you are using gdb under some UI, then tell it to 'att 1', and
+ you'll find yourself attached to UML.
+
+
+ If you are using something other than gdb as your debugger, then
+ you'll need to get it to do the equivalent of 'att 1' if it doesn't do
+ it automatically.
+
+
+ An example of an alternate debugger is strace. You can strace the
+ actual kernel as follows:
+
+ o Run the following in a shell
+
+
+ host%
+ sh -c 'echo pid=$$; echo -n hit return; read x; exec strace -p 1 -o strace.out'
+
+
+
+ o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
+ by the previous command
+
+ o Hit return in the shell, and UML will start running, and strace
+ output will start accumulating in the output file.
+
+ Note that this is different from running
+
+
+ host% strace ./linux
+
+
+
+
+ That will strace only the main UML thread, the tracing thread, which
+ doesn't do any of the actual kernel work. It just oversees the vir-
+ tual machine. In contrast, using strace as described above will show
+ you the low-level activity of the virtual machine.
+
+
+
+
+
+ 12. Kernel debugging examples
+
+ 12.1. The case of the hung fsck
+
+ When booting up the kernel, fsck failed, and dropped me into a shell
+ to fix things up. I ran fsck -y, which hung:
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Setting hostname uml [ OK ]
+ Checking root filesystem
+ /dev/fhd0 was not cleanly unmounted, check forced.
+ Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
+
+ /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
+ (i.e., without -a or -p options)
+ [ FAILED ]
+
+ *** An error occurred during the file system check.
+ *** Dropping you to a shell; the system will reboot
+ *** when you leave the shell.
+ Give root password for maintenance
+ (or type Control-D for normal startup):
+
+ [root@uml /root]# fsck -y /dev/fhd0
+ fsck -y /dev/fhd0
+ Parallelizing fsck version 1.14 (9-Jan-1999)
+ e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
+ /dev/fhd0 contains a file system with errors, check forced.
+ Pass 1: Checking inodes, blocks, and sizes
+ Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes
+
+ Inode 19780, i_blocks is 1548, should be 540. Fix? yes
+
+ Pass 2: Checking directory structure
+ Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes
+
+ Directory inode 11858, block 0, offset 0: directory corrupted
+ Salvage? yes
+
+ Missing '.' in directory inode 11858.
+ Fix? yes
+
+ Missing '..' in directory inode 11858.
+ Fix? yes
+
+
+
+
+
+ The standard drill in this sort of situation is to fire up gdb on the
+ signal thread, which, in this case, was pid 1935. In another window,
+ I run gdb and attach pid 1935.
+
+
+
+
+ ~/linux/2.3.26/um 1016: gdb linux
+ GNU gdb 4.17.0.11 with Linux support
+ Copyright 1998 Free Software Foundation, Inc.
+ GDB is free software, covered by the GNU General Public License, and you are
+ welcome to change it and/or distribute copies of it under certain conditions.
+ Type "show copying" to see the conditions.
+ There is absolutely no warranty for GDB. Type "show warranty" for details.
+ This GDB was configured as "i386-redhat-linux"...
+
+ (gdb) att 1935
+ Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 1935
+ 0x100756d9 in __wait4 ()
+
+
+
+
+
+
+ Let's see what's currently running:
+
+
+
+ (gdb) p current_task.pid
+ $1 = 0
+
+
+
+
+
+ It's the idle thread, which means that fsck went to sleep for some
+ reason and never woke up.
+
+
+ Let's guess that the last process in the process list is fsck:
+
+
+
+ (gdb) p current_task.prev_task.comm
+ $13 = "fsck.ext2\000\000\000\000\000\000"
+
+
+
+
+
+ It is, so let's see what it thinks it's up to:
+
+
+
+ (gdb) p current_task.prev_task.thread
+ $14 = {extern_pid = 1980, tracing = 0, want_tracing = 0, forking = 0,
+ kernel_stack_page = 0, signal_stack = 1342627840, syscall = {id = 4, args = {
+ 3, 134973440, 1024, 0, 1024}, have_result = 0, result = 50590720},
+ request = {op = 2, u = {exec = {ip = 1350467584, sp = 2952789424}, fork = {
+ regs = {1350467584, 2952789424, 0 <repeats 15 times>}, sigstack = 0,
+ pid = 0}, switch_to = 0x507e8000, thread = {proc = 0x507e8000,
+ arg = 0xaffffdb0, flags = 0, new_pid = 0}, input_request = {
+ op = 1350467584, fd = -1342177872, proc = 0, pid = 0}}}}
+
+
+
+
+
+ The interesting things here are the fact that its .thread.syscall.id
+ is __NR_write (see the big switch in arch/um/kernel/syscall_kern.c or
+ the defines in include/asm-um/arch/unistd.h), and that it never
+ returned. Also, its .request.op is OP_SWITCH (see
+ arch/um/include/user_util.h). These mean that it went into a write,
+ and, for some reason, called schedule().
+
+
+ The fact that it never returned from write means that its stack should
+ be fairly interesting. Its pid is 1980 (.thread.extern_pid). That
+ process is being ptraced by the signal thread, so it must be detached
+ before gdb can attach it:
+
+
+
+
+
+
+
+
+
+
+ (gdb) call detach(1980)
+
+ Program received signal SIGSEGV, Segmentation fault.
+ <function called from gdb>
+ The program being debugged stopped while in a function called from GDB.
+ When the function (detach) is done executing, GDB will silently
+ stop (instead of continuing to evaluate the expression containing
+ the function call).
+ (gdb) call detach(1980)
+ $15 = 0
+
+
+
+
+
+ The first detach segfaults for some reason, and the second one
+ succeeds.
+
+
+ Now I detach from the signal thread, attach to the fsck thread, and
+ look at its stack:
+
+
+ (gdb) det
+ Detaching from program: /home/dike/linux/2.3.26/um/linux Pid 1935
+ (gdb) att 1980
+ Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 1980
+ 0x10070451 in __kill ()
+ (gdb) bt
+ #0 0x10070451 in __kill ()
+ #1 0x10068ccd in usr1_pid (pid=1980) at process.c:30
+ #2 0x1006a03f in _switch_to (prev=0x50072000, next=0x507e8000)
+ at process_kern.c:156
+ #3 0x1006a052 in switch_to (prev=0x50072000, next=0x507e8000, last=0x50072000)
+ at process_kern.c:161
+ #4 0x10001d12 in schedule () at core.c:777
+ #5 0x1006a744 in __down (sem=0x507d241c) at semaphore.c:71
+ #6 0x1006aa10 in __down_failed () at semaphore.c:157
+ #7 0x1006c5d8 in segv_handler (sc=0x5006e940) at trap_user.c:174
+ #8 0x1006c5ec in kern_segv_handler (sig=11) at trap_user.c:182
+ #9 <signal handler called>
+ #10 0x10155404 in errno ()
+ #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50
+ #12 0x1006c5d8 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
+ #13 0x1006c5ec in kern_segv_handler (sig=11) at trap_user.c:182
+ #14 <signal handler called>
+ #15 0xc0fd in ?? ()
+ #16 0x10016647 in sys_write (fd=3,
+ buf=0x80b8800 <Address 0x80b8800 out of bounds>, count=1024)
+ at read_write.c:159
+ #17 0x1006d5b3 in execute_syscall (syscall=4, args=0x5006ef08)
+ at syscall_kern.c:254
+ #18 0x1006af87 in really_do_syscall (sig=12) at syscall_user.c:35
+ #19 <signal handler called>
+ #20 0x400dc8b0 in ?? ()
+
+
+
+
+
+ The interesting things here are :
+
+ o There are two segfaults on this stack (frames 9 and 14)
+
+ o The first faulting address (frame 11) is 0x50000800
+
+ (gdb) p (void *)1342179328
+ $16 = (void *) 0x50000800
+
+
+
+
+
+ The initial faulting address is interesting because it is on the idle
+ thread's stack. I had been seeing the idle thread segfault for no
+ apparent reason, and the cause looked like stack corruption. In hopes
+ of catching the culprit in the act, I had turned off all protections
+ to that stack while the idle thread wasn't running. This apparently
+ tripped that trap.
+
+
+ However, the more immediate problem is that second segfault and I'm
+ going to concentrate on that. First, I want to see where the fault
+ happened, so I have to go look at the sigcontent struct in frame 8:
+
+
+
+ (gdb) up
+ #1 0x10068ccd in usr1_pid (pid=1980) at process.c:30
+ 30 kill(pid, SIGUSR1);
+ (gdb)
+ #2 0x1006a03f in _switch_to (prev=0x50072000, next=0x507e8000)
+ at process_kern.c:156
+ 156 usr1_pid(getpid());
+ (gdb)
+ #3 0x1006a052 in switch_to (prev=0x50072000, next=0x507e8000, last=0x50072000)
+ at process_kern.c:161
+ 161 _switch_to(prev, next);
+ (gdb)
+ #4 0x10001d12 in schedule () at core.c:777
+ 777 switch_to(prev, next, prev);
+ (gdb)
+ #5 0x1006a744 in __down (sem=0x507d241c) at semaphore.c:71
+ 71 schedule();
+ (gdb)
+ #6 0x1006aa10 in __down_failed () at semaphore.c:157
+ 157 }
+ (gdb)
+ #7 0x1006c5d8 in segv_handler (sc=0x5006e940) at trap_user.c:174
+ 174 segv(sc->cr2, sc->err & 2);
+ (gdb)
+ #8 0x1006c5ec in kern_segv_handler (sig=11) at trap_user.c:182
+ 182 segv_handler(sc);
+ (gdb) p *sc
+ Cannot access memory at address 0x0.
+
+
+
+
+ That's not very useful, so I'll try a more manual method:
+
+
+ (gdb) p *((struct sigcontext *) (&sig + 1))
+ $19 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43,
+ __dsh = 0, edi = 1342179328, esi = 1350378548, ebp = 1342630440,
+ esp = 1342630420, ebx = 1348150624, edx = 1280, ecx = 0, eax = 0,
+ trapno = 14, err = 4, eip = 268480945, cs = 35, __csh = 0, eflags = 66118,
+ esp_at_signal = 1342630420, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0,
+ cr2 = 1280}
+
+
+
+ The ip is in handle_mm_fault:
+
+
+ (gdb) p (void *)268480945
+ $20 = (void *) 0x1000b1b1
+ (gdb) i sym $20
+ handle_mm_fault + 57 in section .text
+
+
+
+
+
+ Specifically, it's in pte_alloc:
+
+
+ (gdb) i line *$20
+ Line 124 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b1b1 <handle_mm_fault+57>
+ and ends at 0x1000b1b7 <handle_mm_fault+63>.
+
+
+
+
+
+ To find where in handle_mm_fault this is, I'll jump forward in the
+ code until I see an address in that procedure:
+
+
+
+ (gdb) i line *0x1000b1c0
+ Line 126 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b1b7 <handle_mm_fault+63>
+ and ends at 0x1000b1c3 <handle_mm_fault+75>.
+ (gdb) i line *0x1000b1d0
+ Line 131 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b1d0 <handle_mm_fault+88>
+ and ends at 0x1000b1da <handle_mm_fault+98>.
+ (gdb) i line *0x1000b1e0
+ Line 61 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b1da <handle_mm_fault+98>
+ and ends at 0x1000b1e1 <handle_mm_fault+105>.
+ (gdb) i line *0x1000b1f0
+ Line 134 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b1f0 <handle_mm_fault+120>
+ and ends at 0x1000b200 <handle_mm_fault+136>.
+ (gdb) i line *0x1000b200
+ Line 135 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b200 <handle_mm_fault+136>
+ and ends at 0x1000b208 <handle_mm_fault+144>.
+ (gdb) i line *0x1000b210
+ Line 139 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
+ starts at address 0x1000b210 <handle_mm_fault+152>
+ and ends at 0x1000b219 <handle_mm_fault+161>.
+ (gdb) i line *0x1000b220
+ Line 1168 of "memory.c" starts at address 0x1000b21e <handle_mm_fault+166>
+ and ends at 0x1000b222 <handle_mm_fault+170>.
+
+
+
+
+
+ Something is apparently wrong with the page tables or vma_structs, so
+ lets go back to frame 11 and have a look at them:
+
+
+
+ #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50
+ 50 handle_mm_fault(current, vma, address, is_write);
+ (gdb) call pgd_offset_proc(vma->vm_mm, address)
+ $22 = (pgd_t *) 0x80a548c
+
+
+
+
+
+ That's pretty bogus. Page tables aren't supposed to be in process
+ text or data areas. Let's see what's in the vma:
+
+
+ (gdb) p *vma
+ $23 = {vm_mm = 0x507d2434, vm_start = 0, vm_end = 134512640,
+ vm_next = 0x80a4f8c, vm_page_prot = {pgprot = 0}, vm_flags = 31200,
+ vm_avl_height = 2058, vm_avl_left = 0x80a8c94, vm_avl_right = 0x80d1000,
+ vm_next_share = 0xaffffdb0, vm_pprev_share = 0xaffffe63,
+ vm_ops = 0xaffffe7a, vm_pgoff = 2952789626, vm_file = 0xafffffec,
+ vm_private_data = 0x62}
+ (gdb) p *vma.vm_mm
+ $24 = {mmap = 0x507d2434, mmap_avl = 0x0, mmap_cache = 0x8048000,
+ pgd = 0x80a4f8c, mm_users = {counter = 0}, mm_count = {counter = 134904288},
+ map_count = 134909076, mmap_sem = {count = {counter = 135073792},
+ sleepers = -1342177872, wait = {lock = <optimized out or zero length>,
+ task_list = {next = 0xaffffe63, prev = 0xaffffe7a},
+ __magic = -1342177670, __creator = -1342177300}, __magic = 98},
+ page_table_lock = {}, context = 138, start_code = 0, end_code = 0,
+ start_data = 0, end_data = 0, start_brk = 0, brk = 0, start_stack = 0,
+ arg_start = 0, arg_end = 0, env_start = 0, env_end = 0, rss = 1350381536,
+ total_vm = 0, locked_vm = 0, def_flags = 0, cpu_vm_mask = 0, swap_cnt = 0,
+ swap_address = 0, segments = 0x0}
+
+
+
+
+
+ This also pretty bogus. With all of the 0x80xxxxx and 0xaffffxxx
+ addresses, this is looking like a stack was plonked down on top of
+ these structures. Maybe it's a stack overflow from the next page:
+
+
+
+ (gdb) p vma
+ $25 = (struct vm_area_struct *) 0x507d2434
+
+
+
+
+
+ That's towards the lower quarter of the page, so that would have to
+ have been pretty heavy stack overflow:
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (gdb) x/100x $25
+ 0x507d2434: 0x507d2434 0x00000000 0x08048000 0x080a4f8c
+ 0x507d2444: 0x00000000 0x080a79e0 0x080a8c94 0x080d1000
+ 0x507d2454: 0xaffffdb0 0xaffffe63 0xaffffe7a 0xaffffe7a
+ 0x507d2464: 0xafffffec 0x00000062 0x0000008a 0x00000000
+ 0x507d2474: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2484: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2494: 0x00000000 0x00000000 0x507d2fe0 0x00000000
+ 0x507d24a4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d24b4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d24c4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d24d4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d24e4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d24f4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2504: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2514: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2524: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2534: 0x00000000 0x00000000 0x507d25dc 0x00000000
+ 0x507d2544: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2554: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2564: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2574: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2584: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d2594: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d25a4: 0x00000000 0x00000000 0x00000000 0x00000000
+ 0x507d25b4: 0x00000000 0x00000000 0x00000000 0x00000000
+
+
+
+
+
+ It's not stack overflow. The only "stack-like" piece of this data is
+ the vma_struct itself.
+
+
+ At this point, I don't see any avenues to pursue, so I just have to
+ admit that I have no idea what's going on. What I will do, though, is
+ stick a trap on the segfault handler which will stop if it sees any
+ writes to the idle thread's stack. That was the thing that happened
+ first, and it may be that if I can catch it immediately, what's going
+ on will be somewhat clearer.
+
+
+ 12.2. Episode 2: The case of the hung fsck
+
+ After setting a trap in the SEGV handler for accesses to the signal
+ thread's stack, I reran the kernel.
+
+
+ fsck hung again, this time by hitting the trap:
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Setting hostname uml [ OK ]
+ Checking root filesystem
+ /dev/fhd0 contains a file system with errors, check forced.
+ Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
+
+ /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
+ (i.e., without -a or -p options)
+ [ FAILED ]
+
+ *** An error occurred during the file system check.
+ *** Dropping you to a shell; the system will reboot
+ *** when you leave the shell.
+ Give root password for maintenance
+ (or type Control-D for normal startup):
+
+ [root@uml /root]# fsck -y /dev/fhd0
+ fsck -y /dev/fhd0
+ Parallelizing fsck version 1.14 (9-Jan-1999)
+ e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
+ /dev/fhd0 contains a file system with errors, check forced.
+ Pass 1: Checking inodes, blocks, and sizes
+ Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes
+
+ Pass 2: Checking directory structure
+ Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes
+
+ Directory inode 11858, block 0, offset 0: directory corrupted
+ Salvage? yes
+
+ Missing '.' in directory inode 11858.
+ Fix? yes
+
+ Missing '..' in directory inode 11858.
+ Fix? yes
+
+ Untested (4127) [100fe44c]: trap_kern.c line 31
+
+
+
+
+
+ I need to get the signal thread to detach from pid 4127 so that I can
+ attach to it with gdb. This is done by sending it a SIGUSR1, which is
+ caught by the signal thread, which detaches the process:
+
+
+ kill -USR1 4127
+
+
+
+
+
+ Now I can run gdb on it:
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ~/linux/2.3.26/um 1034: gdb linux
+ GNU gdb 4.17.0.11 with Linux support
+ Copyright 1998 Free Software Foundation, Inc.
+ GDB is free software, covered by the GNU General Public License, and you are
+ welcome to change it and/or distribute copies of it under certain conditions.
+ Type "show copying" to see the conditions.
+ There is absolutely no warranty for GDB. Type "show warranty" for details.
+ This GDB was configured as "i386-redhat-linux"...
+ (gdb) att 4127
+ Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127
+ 0x10075891 in __libc_nanosleep ()
+
+
+
+
+
+ The backtrace shows that it was in a write and that the fault address
+ (address in frame 3) is 0x50000800, which is right in the middle of
+ the signal thread's stack page:
+
+
+ (gdb) bt
+ #0 0x10075891 in __libc_nanosleep ()
+ #1 0x1007584d in __sleep (seconds=1000000)
+ at ../sysdeps/unix/sysv/linux/sleep.c:78
+ #2 0x1006ce9a in stop () at user_util.c:191
+ #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31
+ #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
+ #5 0x1006c63c in kern_segv_handler (sig=11) at trap_user.c:182
+ #6 <signal handler called>
+ #7 0xc0fd in ?? ()
+ #8 0x10016647 in sys_write (fd=3, buf=0x80b8800 "R.", count=1024)
+ at read_write.c:159
+ #9 0x1006d603 in execute_syscall (syscall=4, args=0x5006ef08)
+ at syscall_kern.c:254
+ #10 0x1006af87 in really_do_syscall (sig=12) at syscall_user.c:35
+ #11 <signal handler called>
+ #12 0x400dc8b0 in ?? ()
+ #13 <signal handler called>
+ #14 0x400dc8b0 in ?? ()
+ #15 0x80545fd in ?? ()
+ #16 0x804daae in ?? ()
+ #17 0x8054334 in ?? ()
+ #18 0x804d23e in ?? ()
+ #19 0x8049632 in ?? ()
+ #20 0x80491d2 in ?? ()
+ #21 0x80596b5 in ?? ()
+ (gdb) p (void *)1342179328
+ $3 = (void *) 0x50000800
+
+
+
+
+
+ Going up the stack to the segv_handler frame and looking at where in
+ the code the access happened shows that it happened near line 110 of
+ block_dev.c:
+
+
+
+
+
+
+
+
+
+ (gdb) up
+ #1 0x1007584d in __sleep (seconds=1000000)
+ at ../sysdeps/unix/sysv/linux/sleep.c:78
+ ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory.
+ (gdb)
+ #2 0x1006ce9a in stop () at user_util.c:191
+ 191 while(1) sleep(1000000);
+ (gdb)
+ #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31
+ 31 KERN_UNTESTED();
+ (gdb)
+ #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
+ 174 segv(sc->cr2, sc->err & 2);
+ (gdb) p *sc
+ $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43,
+ __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484,
+ esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14,
+ err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070,
+ esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0,
+ cr2 = 1342179328}
+ (gdb) p (void *)268550834
+ $2 = (void *) 0x1001c2b2
+ (gdb) i sym $2
+ block_write + 1090 in section .text
+ (gdb) i line *$2
+ Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h"
+ starts at address 0x1001c2a1 <block_write+1073>
+ and ends at 0x1001c2bf <block_write+1103>.
+ (gdb) i line *0x1001c2c0
+ Line 110 of "block_dev.c" starts at address 0x1001c2bf <block_write+1103>
+ and ends at 0x1001c2e3 <block_write+1139>.
+
+
+
+
+
+ Looking at the source shows that the fault happened during a call to
+ copy_from_user to copy the data into the kernel:
+
+
+ 107 count -= chars;
+ 108 copy_from_user(p,buf,chars);
+ 109 p += chars;
+ 110 buf += chars;
+
+
+
+
+
+ p is the pointer which must contain 0x50000800, since buf contains
+ 0x80b8800 (frame 8 above). It is defined as:
+
+
+ p = offset + bh->b_data;
+
+
+
+
+
+ I need to figure out what bh is, and it just so happens that bh is
+ passed as an argument to mark_buffer_uptodate and mark_buffer_dirty a
+ few lines later, so I do a little disassembly:
+
+
+
+
+ (gdb) disas 0x1001c2bf 0x1001c2e0
+ Dump of assembler code from 0x1001c2bf to 0x1001c2d0:
+ 0x1001c2bf <block_write+1103>: addl %eax,0xc(%ebp)
+ 0x1001c2c2 <block_write+1106>: movl 0xfffffdd4(%ebp),%edx
+ 0x1001c2c8 <block_write+1112>: btsl $0x0,0x18(%edx)
+ 0x1001c2cd <block_write+1117>: btsl $0x1,0x18(%edx)
+ 0x1001c2d2 <block_write+1122>: sbbl %ecx,%ecx
+ 0x1001c2d4 <block_write+1124>: testl %ecx,%ecx
+ 0x1001c2d6 <block_write+1126>: jne 0x1001c2e3 <block_write+1139>
+ 0x1001c2d8 <block_write+1128>: pushl $0x0
+ 0x1001c2da <block_write+1130>: pushl %edx
+ 0x1001c2db <block_write+1131>: call 0x1001819c <__mark_buffer_dirty>
+ End of assembler dump.
+
+
+
+
+
+ At that point, bh is in %edx (address 0x1001c2da), which is calculated
+ at 0x1001c2c2 as %ebp + 0xfffffdd4, so I figure exactly what that is,
+ taking %ebp from the sigcontext_struct above:
+
+
+ (gdb) p (void *)1342631484
+ $5 = (void *) 0x5006ee3c
+ (gdb) p 0x5006ee3c+0xfffffdd4
+ $6 = 1342630928
+ (gdb) p (void *)$6
+ $7 = (void *) 0x5006ec10
+ (gdb) p *((void **)$7)
+ $8 = (void *) 0x50100200
+
+
+
+
+
+ Now, I look at the structure to see what's in it, and particularly,
+ what its b_data field contains:
+
+
+ (gdb) p *((struct buffer_head *)0x50100200)
+ $13 = {b_next = 0x50289380, b_blocknr = 49405, b_size = 1024, b_list = 0,
+ b_dev = 15872, b_count = {counter = 1}, b_rdev = 15872, b_state = 24,
+ b_flushtime = 0, b_next_free = 0x501001a0, b_prev_free = 0x50100260,
+ b_this_page = 0x501001a0, b_reqnext = 0x0, b_pprev = 0x507fcf58,
+ b_data = 0x50000800 "", b_page = 0x50004000,
+ b_end_io = 0x10017f60 <end_buffer_io_sync>, b_dev_id = 0x0,
+ b_rsector = 98810, b_wait = {lock = <optimized out or zero length>,
+ task_list = {next = 0x50100248, prev = 0x50100248}, __magic = 1343226448,
+ __creator = 0}, b_kiobuf = 0x0}
+
+
+
+
+
+ The b_data field is indeed 0x50000800, so the question becomes how
+ that happened. The rest of the structure looks fine, so this probably
+ is not a case of data corruption. It happened on purpose somehow.
+
+
+ The b_page field is a pointer to the page_struct representing the
+ 0x50000000 page. Looking at it shows the kernel's idea of the state
+ of that page:
+
+
+
+ (gdb) p *$13.b_page
+ $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0,
+ index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = {
+ next = 0x50008460, prev = 0x50019350}, wait = {
+ lock = <optimized out or zero length>, task_list = {next = 0x50004024,
+ prev = 0x50004024}, __magic = 1342193708, __creator = 0},
+ pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280,
+ zone = 0x100c5160}
+
+
+
+
+
+ Some sanity-checking: the virtual field shows the "virtual" address of
+ this page, which in this kernel is the same as its "physical" address,
+ and the page_struct itself should be mem_map[0], since it represents
+ the first page of memory:
+
+
+
+ (gdb) p (void *)1342177280
+ $18 = (void *) 0x50000000
+ (gdb) p mem_map
+ $19 = (mem_map_t *) 0x50004000
+
+
+
+
+
+ These check out fine.
+
+
+ Now to check out the page_struct itself. In particular, the flags
+ field shows whether the page is considered free or not:
+
+
+ (gdb) p (void *)132
+ $21 = (void *) 0x84
+
+
+
+
+
+ The "reserved" bit is the high bit, which is definitely not set, so
+ the kernel considers the signal stack page to be free and available to
+ be used.
+
+
+ At this point, I jump to conclusions and start looking at my early
+ boot code, because that's where that page is supposed to be reserved.
+
+
+ In my setup_arch procedure, I have the following code which looks just
+ fine:
+
+
+
+ bootmap_size = init_bootmem(start_pfn, end_pfn - start_pfn);
+ free_bootmem(__pa(low_physmem) + bootmap_size, high_physmem - low_physmem);
+
+
+
+
+
+ Two stack pages have already been allocated, and low_physmem points to
+ the third page, which is the beginning of free memory.
+ The init_bootmem call declares the entire memory to the boot memory
+ manager, which marks it all reserved. The free_bootmem call frees up
+ all of it, except for the first two pages. This looks correct to me.
+
+
+ So, I decide to see init_bootmem run and make sure that it is marking
+ those first two pages as reserved. I never get that far.
+
+
+ Stepping into init_bootmem, and looking at bootmem_map before looking
+ at what it contains shows the following:
+
+
+
+ (gdb) p bootmem_map
+ $3 = (void *) 0x50000000
+
+
+
+
+
+ Aha! The light dawns. That first page is doing double duty as a
+ stack and as the boot memory map. The last thing that the boot memory
+ manager does is to free the pages used by its memory map, so this page
+ is getting freed even its marked as reserved.
+
+
+ The fix was to initialize the boot memory manager before allocating
+ those two stack pages, and then allocate them through the boot memory
+ manager. After doing this, and fixing a couple of subsequent buglets,
+ the stack corruption problem disappeared.
+
+
+
+
+
+ 13. What to do when UML doesn't work
+
+
+
+
+ 13.1. Strange compilation errors when you build from source
+
+ As of test11, it is necessary to have "ARCH=um" in the environment or
+ on the make command line for all steps in building UML, including
+ clean, distclean, or mrproper, config, menuconfig, or xconfig, dep,
+ and linux. If you forget for any of them, the i386 build seems to
+ contaminate the UML build. If this happens, start from scratch with
+
+
+ host%
+ make mrproper ARCH=um
+
+
+
+
+ and repeat the build process with ARCH=um on all the steps.
+
+
+ See ``Compiling the kernel and modules'' for more details.
+
+
+ Another cause of strange compilation errors is building UML in
+ /usr/src/linux. If you do this, the first thing you need to do is
+ clean up the mess you made. The /usr/src/linux/asm link will now
+ point to /usr/src/linux/asm-um. Make it point back to
+ /usr/src/linux/asm-i386. Then, move your UML pool someplace else and
+ build it there. Also see below, where a more specific set of symptoms
+ is described.
+
+
+
+ 13.3. A variety of panics and hangs with /tmp on a reiserfs filesys-
+ tem
+
+ I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27.
+ Panics preceded by
+
+
+ Detaching pid nnnn
+
+
+
+ are diagnostic of this problem. This is a reiserfs bug which causes a
+ thread to occasionally read stale data from a mmapped page shared with
+ another thread. The fix is to upgrade the filesystem or to have /tmp
+ be an ext2 filesystem.
+
+
+
+ 13.4. The compile fails with errors about conflicting types for
+ 'open', 'dup', and 'waitpid'
+
+ This happens when you build in /usr/src/linux. The UML build makes
+ the include/asm link point to include/asm-um. /usr/include/asm points
+ to /usr/src/linux/include/asm, so when that link gets moved, files
+ which need to include the asm-i386 versions of headers get the
+ incompatible asm-um versions. The fix is to move the include/asm link
+ back to include/asm-i386 and to do UML builds someplace else.
+
+
+
+ 13.5. UML doesn't work when /tmp is an NFS filesystem
+
+ This seems to be a similar situation with the ReiserFS problem above.
+ Some versions of NFS seems not to handle mmap correctly, which UML
+ depends on. The workaround is have /tmp be a non-NFS directory.
+
+
+ 13.6. UML hangs on boot when compiled with gprof support
+
+ If you build UML with gprof support and, early in the boot, it does
+ this
+
+
+ kernel BUG at page_alloc.c:100!
+
+
+
+
+ you have a buggy gcc. You can work around the problem by removing
+ UM_FASTCALL from CFLAGS in arch/um/Makefile-i386. This will open up
+ another bug, but that one is fairly hard to reproduce.
+
+
+
+ 13.7. syslogd dies with a SIGTERM on startup
+
+ The exact boot error depends on the distribution that you're booting,
+ but Debian produces this:
+
+
+ /etc/rc2.d/S10sysklogd: line 49: 93 Terminated
+ start-stop-daemon --start --quiet --exec /sbin/syslogd -- $SYSLOGD
+
+
+
+
+ This is a syslogd bug. There's a race between a parent process
+ installing a signal handler and its child sending the signal. See
+ this uml-devel post <http://www.geocrawler.com/lists/3/Source-
+ Forge/709/0/6612801> for the details.
+
+
+
+ 13.8. TUN/TAP networking doesn't work on a 2.4 host
+
+ There are a couple of problems which were
+ <http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed
+ out"> by Tim Robinson <timro at trkr dot net>
+
+ o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
+ The fix is to upgrade to something more recent and then read the
+ next item.
+
+ o If you see
+
+
+ File descriptor in bad state
+
+
+
+ when you bring up the device inside UML, you have a header mismatch
+ between the original kernel and the upgraded one. Make /usr/src/linux
+ point at the new headers. This will only be a problem if you build
+ uml_net yourself.
+
+
+
+ 13.9. You can network to the host but not to other machines on the
+ net
+
+ If you can connect to the host, and the host can connect to UML, but
+ you cannot connect to any other machines, then you may need to enable
+ IP Masquerading on the host. Usually this is only experienced when
+ using private IP addresses (192.168.x.x or 10.x.x.x) for host/UML
+ networking, rather than the public address space that your host is
+ connected to. UML does not enable IP Masquerading, so you will need
+ to create a static rule to enable it:
+
+
+ host%
+ iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE
+
+
+
+
+ Replace eth0 with the interface that you use to talk to the rest of
+ the world.
+
+
+ Documentation on IP Masquerading, and SNAT, can be found at
+ www.netfilter.org <http://www.netfilter.org> .
+
+
+ If you can reach the local net, but not the outside Internet, then
+ that is usually a routing problem. The UML needs a default route:
+
+
+ UML#
+ route add default gw gateway IP
+
+
+
+
+ The gateway IP can be any machine on the local net that knows how to
+ reach the outside world. Usually, this is the host or the local net-
+ work's gateway.
+
+
+ Occasionally, we hear from someone who can reach some machines, but
+ not others on the same net, or who can reach some ports on other
+ machines, but not others. These are usually caused by strange
+ firewalling somewhere between the UML and the other box. You track
+ this down by running tcpdump on every interface the packets travel
+ over and see where they disappear. When you find a machine that takes
+ the packets in, but does not send them onward, that's the culprit.
+
+
+
+ 13.10. I have no root and I want to scream
+
+ Thanks to Birgit Wahlich for telling me about this strange one. It
+ turns out that there's a limit of six environment variables on the
+ kernel command line. When that limit is reached or exceeded, argument
+ processing stops, which means that the 'root=' argument that UML
+ usually adds is not seen. So, the filesystem has no idea what the
+ root device is, so it panics.
+
+
+ The fix is to put less stuff on the command line. Glomming all your
+ setup variables into one is probably the best way to go.
+
+
+
+ 13.11. UML build conflict between ptrace.h and ucontext.h
+
+ On some older systems, /usr/include/asm/ptrace.h and
+ /usr/include/sys/ucontext.h define the same names. So, when they're
+ included together, the defines from one completely mess up the parsing
+ of the other, producing errors like:
+ /usr/include/sys/ucontext.h:47: parse error before
+ `10'
+
+
+
+
+ plus a pile of warnings.
+
+
+ This is a libc botch, which has since been fixed, and I don't see any
+ way around it besides upgrading.
+
+
+
+ 13.12. The UML BogoMips is exactly half the host's BogoMips
+
+ On i386 kernels, there are two ways of running the loop that is used
+ to calculate the BogoMips rating, using the TSC if it's there or using
+ a one-instruction loop. The TSC produces twice the BogoMips as the
+ loop. UML uses the loop, since it has nothing resembling a TSC, and
+ will get almost exactly the same BogoMips as a host using the loop.
+ However, on a host with a TSC, its BogoMips will be double the loop
+ BogoMips, and therefore double the UML BogoMips.
+
+
+
+ 13.13. When you run UML, it immediately segfaults
+
+ If the host is configured with the 2G/2G address space split, that's
+ why. See ``UML on 2G/2G hosts'' for the details on getting UML to
+ run on your host.
+
+
+
+ 13.14. xterms appear, then immediately disappear
+
+ If you're running an up to date kernel with an old release of
+ uml_utilities, the port-helper program will not work properly, so
+ xterms will exit straight after they appear. The solution is to
+ upgrade to the latest release of uml_utilities. Usually this problem
+ occurs when you have installed a packaged release of UML then compiled
+ your own development kernel without upgrading the uml_utilities from
+ the source distribution.
+
+
+
+ 13.15. Any other panic, hang, or strange behavior
+
+ If you're seeing truly strange behavior, such as hangs or panics that
+ happen in random places, or you try running the debugger to see what's
+ happening and it acts strangely, then it could be a problem in the
+ host kernel. If you're not running a stock Linus or -ac kernel, then
+ try that. An early version of the preemption patch and a 2.4.10 SuSE
+ kernel have caused very strange problems in UML.
+
+
+ Otherwise, let me know about it. Send a message to one of the UML
+ mailing lists - either the developer list - user-mode-linux-devel at
+ lists dot sourceforge dot net (subscription info) or the user list -
+ user-mode-linux-user at lists dot sourceforge do net (subscription
+ info), whichever you prefer. Don't assume that everyone knows about
+ it and that a fix is imminent.
+
+
+ If you want to be super-helpful, read ``Diagnosing Problems'' and
+ follow the instructions contained therein.
+ 14. Diagnosing Problems
+
+
+ If you get UML to crash, hang, or otherwise misbehave, you should
+ report this on one of the project mailing lists, either the developer
+ list - user-mode-linux-devel at lists dot sourceforge dot net
+ (subscription info) or the user list - user-mode-linux-user at lists
+ dot sourceforge dot net (subscription info). When you do, it is
+ likely that I will want more information. So, it would be helpful to
+ read the stuff below, do whatever is applicable in your case, and
+ report the results to the list.
+
+
+ For any diagnosis, you're going to need to build a debugging kernel.
+ The binaries from this site aren't debuggable. If you haven't done
+ this before, read about ``Compiling the kernel and modules'' and
+ ``Kernel debugging'' UML first.
+
+
+ 14.1. Case 1 : Normal kernel panics
+
+ The most common case is for a normal thread to panic. To debug this,
+ you will need to run it under the debugger (add 'debug' to the command
+ line). An xterm will start up with gdb running inside it. Continue
+ it when it stops in start_kernel and make it crash. Now ^C gdb and
+
+
+ If the panic was a "Kernel mode fault", then there will be a segv
+ frame on the stack and I'm going to want some more information. The
+ stack might look something like this:
+
+
+ (UML gdb) backtrace
+ #0 0x1009bf76 in __sigprocmask (how=1, set=0x5f347940, oset=0x0)
+ at ../sysdeps/unix/sysv/linux/sigprocmask.c:49
+ #1 0x10091411 in change_sig (signal=10, on=1) at process.c:218
+ #2 0x10094785 in timer_handler (sig=26) at time_kern.c:32
+ #3 0x1009bf38 in __restore ()
+ at ../sysdeps/unix/sysv/linux/i386/sigaction.c:125
+ #4 0x1009534c in segv (address=8, ip=268849158, is_write=2, is_user=0)
+ at trap_kern.c:66
+ #5 0x10095c04 in segv_handler (sig=11) at trap_user.c:285
+ #6 0x1009bf38 in __restore ()
+
+
+
+
+ I'm going to want to see the symbol and line information for the value
+ of ip in the segv frame. In this case, you would do the following:
+
+
+ (UML gdb) i sym 268849158
+
+
+
+
+ and
+
+
+ (UML gdb) i line *268849158
+
+
+
+
+ The reason for this is the __restore frame right above the segv_han-
+ dler frame is hiding the frame that actually segfaulted. So, I have
+ to get that information from the faulting ip.
+
+
+ 14.2. Case 2 : Tracing thread panics
+
+ The less common and more painful case is when the tracing thread
+ panics. In this case, the kernel debugger will be useless because it
+ needs a healthy tracing thread in order to work. The first thing to
+ do is get a backtrace from the tracing thread. This is done by
+ figuring out what its pid is, firing up gdb, and attaching it to that
+ pid. You can figure out the tracing thread pid by looking at the
+ first line of the console output, which will look like this:
+
+
+ tracing thread pid = 15851
+
+
+
+
+ or by running ps on the host and finding the line that looks like
+ this:
+
+
+ jdike 15851 4.5 0.4 132568 1104 pts/0 S 21:34 0:05 ./linux [(tracing thread)]
+
+
+
+
+ If the panic was 'segfault in signals', then follow the instructions
+ above for collecting information about the location of the seg fault.
+
+
+ If the tracing thread flaked out all by itself, then send that
+ backtrace in and wait for our crack debugging team to fix the problem.
+
+
+ 14.3. Case 3 : Tracing thread panics caused by other threads
+
+ However, there are cases where the misbehavior of another thread
+ caused the problem. The most common panic of this type is:
+
+
+ wait_for_stop failed to wait for <pid> to stop with <signal number>
+
+
+
+
+ In this case, you'll need to get a backtrace from the process men-
+ tioned in the panic, which is complicated by the fact that the kernel
+ debugger is defunct and without some fancy footwork, another gdb can't
+ attach to it. So, this is how the fancy footwork goes:
+
+ In a shell:
+
+
+ host% kill -STOP pid
+
+
+
+
+ Run gdb on the tracing thread as described in case 2 and do:
+
+
+ (host gdb) call detach(pid)
+
+
+ If you get a segfault, do it again. It always works the second time.
+
+ Detach from the tracing thread and attach to that other thread:
+
+
+ (host gdb) detach
+
+
+
+
+
+
+ (host gdb) attach pid
+
+
+
+
+ If gdb hangs when attaching to that process, go back to a shell and
+ do:
+
+
+ host%
+ kill -CONT pid
+
+
+
+
+ And then get the backtrace:
+
+
+ (host gdb) backtrace
+
+
+
+
+
+ 14.4. Case 4 : Hangs
+
+ Hangs seem to be fairly rare, but they sometimes happen. When a hang
+ happens, we need a backtrace from the offending process. Run the
+ kernel debugger as described in case 1 and get a backtrace. If the
+ current process is not the idle thread, then send in the backtrace.
+ You can tell that it's the idle thread if the stack looks like this:
+
+
+ #0 0x100b1401 in __libc_nanosleep ()
+ #1 0x100a2885 in idle_sleep (secs=10) at time.c:122
+ #2 0x100a546f in do_idle () at process_kern.c:445
+ #3 0x100a5508 in cpu_idle () at process_kern.c:471
+ #4 0x100ec18f in start_kernel () at init/main.c:592
+ #5 0x100a3e10 in start_kernel_proc (unused=0x0) at um_arch.c:71
+ #6 0x100a383f in signal_tramp (arg=0x100a3dd8) at trap_user.c:50
+
+
+
+
+ If this is the case, then some other process is at fault, and went to
+ sleep when it shouldn't have. Run ps on the host and figure out which
+ process should not have gone to sleep and stayed asleep. Then attach
+ to it with gdb and get a backtrace as described in case 3.
+
+
+
+
+
+
+ 15. Thanks
+
+
+ A number of people have helped this project in various ways, and this
+ page gives recognition where recognition is due.
+
+
+ If you're listed here and you would prefer a real link on your name,
+ or no link at all, instead of the despammed email address pseudo-link,
+ let me know.
+
+
+ If you're not listed here and you think maybe you should be, please
+ let me know that as well. I try to get everyone, but sometimes my
+ bookkeeping lapses and I forget about contributions.
+
+
+ 15.1. Code and Documentation
+
+ Rusty Russell <rusty at linuxcare.com.au> -
+
+ o wrote the HOWTO <http://user-mode-
+ linux.sourceforge.net/UserModeLinux-HOWTO.html>
+
+ o prodded me into making this project official and putting it on
+ SourceForge
+
+ o came up with the way cool UML logo <http://user-mode-
+ linux.sourceforge.net/uml-small.png>
+
+ o redid the config process
+
+
+ Peter Moulder <reiter at netspace.net.au> - Fixed my config and build
+ processes, and added some useful code to the block driver
+
+
+ Bill Stearns <wstearns at pobox.com> -
+
+ o HOWTO updates
+
+ o lots of bug reports
+
+ o lots of testing
+
+ o dedicated a box (uml.ists.dartmouth.edu) to support UML development
+
+ o wrote the mkrootfs script, which allows bootable filesystems of
+ RPM-based distributions to be cranked out
+
+ o cranked out a large number of filesystems with said script
+
+
+ Jim Leu <jleu at mindspring.com> - Wrote the virtual ethernet driver
+ and associated usermode tools
+
+ Lars Brinkhoff <http://lars.nocrew.org/> - Contributed the ptrace
+ proxy from his own project <http://a386.nocrew.org/> to allow easier
+ kernel debugging
+
+
+ Andrea Arcangeli <andrea at suse.de> - Redid some of the early boot
+ code so that it would work on machines with Large File Support
+
+
+ Chris Emerson <http://www.chiark.greenend.org.uk/~cemerson/> - Did
+ the first UML port to Linux/ppc
+
+
+ Harald Welte <laforge at gnumonks.org> - Wrote the multicast
+ transport for the network driver
+
+
+ Jorgen Cederlof - Added special file support to hostfs
+
+
+ Greg Lonnon <glonnon at ridgerun dot com> - Changed the ubd driver
+ to allow it to layer a COW file on a shared read-only filesystem and
+ wrote the iomem emulation support
+
+
+ Henrik Nordstrom <http://hem.passagen.se/hno/> - Provided a variety
+ of patches, fixes, and clues
+
+
+ Lennert Buytenhek - Contributed various patches, a rewrite of the
+ network driver, the first implementation of the mconsole driver, and
+ did the bulk of the work needed to get SMP working again.
+
+
+ Yon Uriarte - Fixed the TUN/TAP network backend while I slept.
+
+
+ Adam Heath - Made a bunch of nice cleanups to the initialization code,
+ plus various other small patches.
+
+
+ Matt Zimmerman - Matt volunteered to be the UML Debian maintainer and
+ is doing a real nice job of it. He also noticed and fixed a number of
+ actually and potentially exploitable security holes in uml_net. Plus
+ the occasional patch. I like patches.
+
+
+ James McMechan - James seems to have taken over maintenance of the ubd
+ driver and is doing a nice job of it.
+
+
+ Chandan Kudige - wrote the umlgdb script which automates the reloading
+ of module symbols.
+
+
+ Steve Schmidtke - wrote the UML slirp transport and hostaudio drivers,
+ enabling UML processes to access audio devices on the host. He also
+ submitted patches for the slip transport and lots of other things.
+
+
+ David Coulson <http://davidcoulson.net> -
+
+ o Set up the usermodelinux.org <http://usermodelinux.org> site,
+ which is a great way of keeping the UML user community on top of
+ UML goings-on.
+
+ o Site documentation and updates
+
+ o Nifty little UML management daemon UMLd
+ <http://uml.openconsultancy.com/umld/>
+
+ o Lots of testing and bug reports
+
+
+
+
+ 15.2. Flushing out bugs
+
+
+
+ o Yuri Pudgorodsky
+
+ o Gerald Britton
+
+ o Ian Wehrman
+
+ o Gord Lamb
+
+ o Eugene Koontz
+
+ o John H. Hartman
+
+ o Anders Karlsson
+
+ o Daniel Phillips
+
+ o John Fremlin
+
+ o Rainer Burgstaller
+
+ o James Stevenson
+
+ o Matt Clay
+
+ o Cliff Jefferies
+
+ o Geoff Hoff
+
+ o Lennert Buytenhek
+
+ o Al Viro
+
+ o Frank Klingenhoefer
+
+ o Livio Baldini Soares
+
+ o Jon Burgess
+
+ o Petru Paler
+
+ o Paul
+
+ o Chris Reahard
+
+ o Sverker Nilsson
+
+ o Gong Su
+
+ o johan verrept
+
+ o Bjorn Eriksson
+
+ o Lorenzo Allegrucci
+
+ o Muli Ben-Yehuda
+
+ o David Mansfield
+
+ o Howard Goff
+
+ o Mike Anderson
+
+ o John Byrne
+
+ o Sapan J. Batia
+
+ o Iris Huang
+
+ o Jan Hudec
+
+ o Voluspa
+
+
+
+
+ 15.3. Buglets and clean-ups
+
+
+
+ o Dave Zarzycki
+
+ o Adam Lazur
+
+ o Boria Feigin
+
+ o Brian J. Murrell
+
+ o JS
+
+ o Roman Zippel
+
+ o Wil Cooley
+
+ o Ayelet Shemesh
+
+ o Will Dyson
+
+ o Sverker Nilsson
+
+ o dvorak
+
+ o v.naga srinivas
+
+ o Shlomi Fish
+
+ o Roger Binns
+
+ o johan verrept
+
+ o MrChuoi
+
+ o Peter Cleve
+
+ o Vincent Guffens
+
+ o Nathan Scott
+
+ o Patrick Caulfield
+
+ o jbearce
+
+ o Catalin Marinas
+
+ o Shane Spencer
+
+ o Zou Min
+
+
+ o Ryan Boder
+
+ o Lorenzo Colitti
+
+ o Gwendal Grignou
+
+ o Andre' Breiler
+
+ o Tsutomu Yasuda
+
+
+
+ 15.4. Case Studies
+
+
+ o Jon Wright
+
+ o William McEwan
+
+ o Michael Richardson
+
+
+
+ 15.5. Other contributions
+
+
+ Bill Carr <Bill.Carr at compaq.com> made the Red Hat mkrootfs script
+ work with RH 6.2.
+
+ Michael Jennings <mikejen at hevanet.com> sent in some material which
+ is now gracing the top of the index page <http://user-mode-
+ linux.sourceforge.net/> of this site.
+
+ SGI <http://www.sgi.com> (and more specifically Ralf Baechle <ralf at
+ uni-koblenz.de> ) gave me an account on oss.sgi.com
+ <http://www.oss.sgi.com> . The bandwidth there made it possible to
+ produce most of the filesystems available on the project download
+ page.
+
+ Laurent Bonnaud <Laurent.Bonnaud at inpg.fr> took the old grotty
+ Debian filesystem that I've been distributing and updated it to 2.2.
+ It is now available by itself here.
+
+ Rik van Riel gave me some ftp space on ftp.nl.linux.org so I can make
+ releases even when Sourceforge is broken.
+
+ Rodrigo de Castro looked at my broken pte code and told me what was
+ wrong with it, letting me fix a long-standing (several weeks) and
+ serious set of bugs.
+
+ Chris Reahard built a specialized root filesystem for running a DNS
+ server jailed inside UML. It's available from the download
+ <http://user-mode-linux.sourceforge.net/dl-sf.html> page in the Jail
+ Filesystems section.
+
+
+
+
+
+
+
+
+
+
+
+
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-
-============================
-Linux Virtualization Support
-============================
-
-.. toctree::
- :maxdepth: 2
-
- kvm/index
- paravirt_ops
-
-.. only:: html and subproject
-
- Indices
- =======
-
- * :ref:`genindex`
+++ /dev/null
-======================================
-Secure Encrypted Virtualization (SEV)
-======================================
-
-Overview
-========
-
-Secure Encrypted Virtualization (SEV) is a feature found on AMD processors.
-
-SEV is an extension to the AMD-V architecture which supports running
-virtual machines (VMs) under the control of a hypervisor. When enabled,
-the memory contents of a VM will be transparently encrypted with a key
-unique to that VM.
-
-The hypervisor can determine the SEV support through the CPUID
-instruction. The CPUID function 0x8000001f reports information related
-to SEV::
-
- 0x8000001f[eax]:
- Bit[1] indicates support for SEV
- ...
- [ecx]:
- Bits[31:0] Number of encrypted guests supported simultaneously
-
-If support for SEV is present, MSR 0xc001_0010 (MSR_K8_SYSCFG) and MSR 0xc001_0015
-(MSR_K7_HWCR) can be used to determine if it can be enabled::
-
- 0xc001_0010:
- Bit[23] 1 = memory encryption can be enabled
- 0 = memory encryption can not be enabled
-
- 0xc001_0015:
- Bit[0] 1 = memory encryption can be enabled
- 0 = memory encryption can not be enabled
-
-When SEV support is available, it can be enabled in a specific VM by
-setting the SEV bit before executing VMRUN.::
-
- VMCB[0x90]:
- Bit[1] 1 = SEV is enabled
- 0 = SEV is disabled
-
-SEV hardware uses ASIDs to associate a memory encryption key with a VM.
-Hence, the ASID for the SEV-enabled guests must be from 1 to a maximum value
-defined in the CPUID 0x8000001f[ecx] field.
-
-SEV Key Management
-==================
-
-The SEV guest key management is handled by a separate processor called the AMD
-Secure Processor (AMD-SP). Firmware running inside the AMD-SP provides a secure
-key management interface to perform common hypervisor activities such as
-encrypting bootstrap code, snapshot, migrating and debugging the guest. For more
-information, see the SEV Key Management spec [api-spec]_
-
-KVM implements the following commands to support common lifecycle events of SEV
-guests, such as launching, running, snapshotting, migrating and decommissioning.
-
-1. KVM_SEV_INIT
----------------
-
-The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform
-context. In a typical workflow, this command should be the first command issued.
-
-Returns: 0 on success, -negative on error
-
-2. KVM_SEV_LAUNCH_START
------------------------
-
-The KVM_SEV_LAUNCH_START command is used for creating the memory encryption
-context. To create the encryption context, user must provide a guest policy,
-the owner's public Diffie-Hellman (PDH) key and session information.
-
-Parameters: struct kvm_sev_launch_start (in/out)
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_launch_start {
- __u32 handle; /* if zero then firmware creates a new handle */
- __u32 policy; /* guest's policy */
-
- __u64 dh_uaddr; /* userspace address pointing to the guest owner's PDH key */
- __u32 dh_len;
-
- __u64 session_addr; /* userspace address which points to the guest session information */
- __u32 session_len;
- };
-
-On success, the 'handle' field contains a new handle and on error, a negative value.
-
-For more details, see SEV spec Section 6.2.
-
-3. KVM_SEV_LAUNCH_UPDATE_DATA
------------------------------
-
-The KVM_SEV_LAUNCH_UPDATE_DATA is used for encrypting a memory region. It also
-calculates a measurement of the memory contents. The measurement is a signature
-of the memory contents that can be sent to the guest owner as an attestation
-that the memory was encrypted correctly by the firmware.
-
-Parameters (in): struct kvm_sev_launch_update_data
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_launch_update {
- __u64 uaddr; /* userspace address to be encrypted (must be 16-byte aligned) */
- __u32 len; /* length of the data to be encrypted (must be 16-byte aligned) */
- };
-
-For more details, see SEV spec Section 6.3.
-
-4. KVM_SEV_LAUNCH_MEASURE
--------------------------
-
-The KVM_SEV_LAUNCH_MEASURE command is used to retrieve the measurement of the
-data encrypted by the KVM_SEV_LAUNCH_UPDATE_DATA command. The guest owner may
-wait to provide the guest with confidential information until it can verify the
-measurement. Since the guest owner knows the initial contents of the guest at
-boot, the measurement can be verified by comparing it to what the guest owner
-expects.
-
-Parameters (in): struct kvm_sev_launch_measure
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_launch_measure {
- __u64 uaddr; /* where to copy the measurement */
- __u32 len; /* length of measurement blob */
- };
-
-For more details on the measurement verification flow, see SEV spec Section 6.4.
-
-5. KVM_SEV_LAUNCH_FINISH
-------------------------
-
-After completion of the launch flow, the KVM_SEV_LAUNCH_FINISH command can be
-issued to make the guest ready for the execution.
-
-Returns: 0 on success, -negative on error
-
-6. KVM_SEV_GUEST_STATUS
------------------------
-
-The KVM_SEV_GUEST_STATUS command is used to retrieve status information about a
-SEV-enabled guest.
-
-Parameters (out): struct kvm_sev_guest_status
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_guest_status {
- __u32 handle; /* guest handle */
- __u32 policy; /* guest policy */
- __u8 state; /* guest state (see enum below) */
- };
-
-SEV guest state:
-
-::
-
- enum {
- SEV_STATE_INVALID = 0;
- SEV_STATE_LAUNCHING, /* guest is currently being launched */
- SEV_STATE_SECRET, /* guest is being launched and ready to accept the ciphertext data */
- SEV_STATE_RUNNING, /* guest is fully launched and running */
- SEV_STATE_RECEIVING, /* guest is being migrated in from another SEV machine */
- SEV_STATE_SENDING /* guest is getting migrated out to another SEV machine */
- };
-
-7. KVM_SEV_DBG_DECRYPT
-----------------------
-
-The KVM_SEV_DEBUG_DECRYPT command can be used by the hypervisor to request the
-firmware to decrypt the data at the given memory region.
-
-Parameters (in): struct kvm_sev_dbg
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_dbg {
- __u64 src_uaddr; /* userspace address of data to decrypt */
- __u64 dst_uaddr; /* userspace address of destination */
- __u32 len; /* length of memory region to decrypt */
- };
-
-The command returns an error if the guest policy does not allow debugging.
-
-8. KVM_SEV_DBG_ENCRYPT
-----------------------
-
-The KVM_SEV_DEBUG_ENCRYPT command can be used by the hypervisor to request the
-firmware to encrypt the data at the given memory region.
-
-Parameters (in): struct kvm_sev_dbg
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_dbg {
- __u64 src_uaddr; /* userspace address of data to encrypt */
- __u64 dst_uaddr; /* userspace address of destination */
- __u32 len; /* length of memory region to encrypt */
- };
-
-The command returns an error if the guest policy does not allow debugging.
-
-9. KVM_SEV_LAUNCH_SECRET
-------------------------
-
-The KVM_SEV_LAUNCH_SECRET command can be used by the hypervisor to inject secret
-data after the measurement has been validated by the guest owner.
-
-Parameters (in): struct kvm_sev_launch_secret
-
-Returns: 0 on success, -negative on error
-
-::
-
- struct kvm_sev_launch_secret {
- __u64 hdr_uaddr; /* userspace address containing the packet header */
- __u32 hdr_len;
-
- __u64 guest_uaddr; /* the guest memory region where the secret should be injected */
- __u32 guest_len;
-
- __u64 trans_uaddr; /* the hypervisor memory region which contains the secret */
- __u32 trans_len;
- };
-
-References
-==========
-
-
-See [white-paper]_, [api-spec]_, [amd-apm]_ and [kvm-forum]_ for more info.
-
-.. [white-paper] http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf
-.. [api-spec] http://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf
-.. [amd-apm] http://support.amd.com/TechDocs/24593.pdf (section 15.34)
-.. [kvm-forum] http://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf
+++ /dev/null
-The Definitive KVM (Kernel-based Virtual Machine) API Documentation
-===================================================================
-
-1. General description
-----------------------
-
-The kvm API is a set of ioctls that are issued to control various aspects
-of a virtual machine. The ioctls belong to three classes:
-
- - System ioctls: These query and set global attributes which affect the
- whole kvm subsystem. In addition a system ioctl is used to create
- virtual machines.
-
- - VM ioctls: These query and set attributes that affect an entire virtual
- machine, for example memory layout. In addition a VM ioctl is used to
- create virtual cpus (vcpus) and devices.
-
- VM ioctls must be issued from the same process (address space) that was
- used to create the VM.
-
- - vcpu ioctls: These query and set attributes that control the operation
- of a single virtual cpu.
-
- vcpu ioctls should be issued from the same thread that was used to create
- the vcpu, except for asynchronous vcpu ioctl that are marked as such in
- the documentation. Otherwise, the first ioctl after switching threads
- could see a performance impact.
-
- - device ioctls: These query and set attributes that control the operation
- of a single device.
-
- device ioctls must be issued from the same process (address space) that
- was used to create the VM.
-
-2. File descriptors
--------------------
-
-The kvm API is centered around file descriptors. An initial
-open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
-can be used to issue system ioctls. A KVM_CREATE_VM ioctl on this
-handle will create a VM file descriptor which can be used to issue VM
-ioctls. A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will
-create a virtual cpu or device and return a file descriptor pointing to
-the new resource. Finally, ioctls on a vcpu or device fd can be used
-to control the vcpu or device. For vcpus, this includes the important
-task of actually running guest code.
-
-In general file descriptors can be migrated among processes by means
-of fork() and the SCM_RIGHTS facility of unix domain socket. These
-kinds of tricks are explicitly not supported by kvm. While they will
-not cause harm to the host, their actual behavior is not guaranteed by
-the API. See "General description" for details on the ioctl usage
-model that is supported by KVM.
-
-It is important to note that althought VM ioctls may only be issued from
-the process that created the VM, a VM's lifecycle is associated with its
-file descriptor, not its creator (process). In other words, the VM and
-its resources, *including the associated address space*, are not freed
-until the last reference to the VM's file descriptor has been released.
-For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will
-not be freed until both the parent (original) process and its child have
-put their references to the VM's file descriptor.
-
-Because a VM's resources are not freed until the last reference to its
-file descriptor is released, creating additional references to a VM via
-via fork(), dup(), etc... without careful consideration is strongly
-discouraged and may have unwanted side effects, e.g. memory allocated
-by and on behalf of the VM's process may not be freed/unaccounted when
-the VM is shut down.
-
-
-3. Extensions
--------------
-
-As of Linux 2.6.22, the KVM ABI has been stabilized: no backward
-incompatible change are allowed. However, there is an extension
-facility that allows backward-compatible extensions to the API to be
-queried and used.
-
-The extension mechanism is not based on the Linux version number.
-Instead, kvm defines extension identifiers and a facility to query
-whether a particular extension identifier is available. If it is, a
-set of ioctls is available for application use.
-
-
-4. API description
-------------------
-
-This section describes ioctls that can be used to control kvm guests.
-For each ioctl, the following information is provided along with a
-description:
-
- Capability: which KVM extension provides this ioctl. Can be 'basic',
- which means that is will be provided by any kernel that supports
- API version 12 (see section 4.1), a KVM_CAP_xyz constant, which
- means availability needs to be checked with KVM_CHECK_EXTENSION
- (see section 4.4), or 'none' which means that while not all kernels
- support this ioctl, there's no capability bit to check its
- availability: for kernels that don't support the ioctl,
- the ioctl returns -ENOTTY.
-
- Architectures: which instruction set architectures provide this ioctl.
- x86 includes both i386 and x86_64.
-
- Type: system, vm, or vcpu.
-
- Parameters: what parameters are accepted by the ioctl.
-
- Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
- are not detailed, but errors with specific meanings are.
-
-
-4.1 KVM_GET_API_VERSION
-
-Capability: basic
-Architectures: all
-Type: system ioctl
-Parameters: none
-Returns: the constant KVM_API_VERSION (=12)
-
-This identifies the API version as the stable kvm API. It is not
-expected that this number will change. However, Linux 2.6.20 and
-2.6.21 report earlier versions; these are not documented and not
-supported. Applications should refuse to run if KVM_GET_API_VERSION
-returns a value other than 12. If this check passes, all ioctls
-described as 'basic' will be available.
-
-
-4.2 KVM_CREATE_VM
-
-Capability: basic
-Architectures: all
-Type: system ioctl
-Parameters: machine type identifier (KVM_VM_*)
-Returns: a VM fd that can be used to control the new virtual machine.
-
-The new VM has no virtual cpus and no memory.
-You probably want to use 0 as machine type.
-
-In order to create user controlled virtual machines on S390, check
-KVM_CAP_S390_UCONTROL and use the flag KVM_VM_S390_UCONTROL as
-privileged user (CAP_SYS_ADMIN).
-
-To use hardware assisted virtualization on MIPS (VZ ASE) rather than
-the default trap & emulate implementation (which changes the virtual
-memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
-flag KVM_VM_MIPS_VZ.
-
-
-On arm64, the physical address size for a VM (IPA Size limit) is limited
-to 40bits by default. The limit can be configured if the host supports the
-extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
-KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type
-identifier, where IPA_Bits is the maximum width of any physical
-address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
-machine type identifier.
-
-e.g, to configure a guest to use 48bit physical address size :
-
- vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48));
-
-The requested size (IPA_Bits) must be :
- 0 - Implies default size, 40bits (for backward compatibility)
-
- or
-
- N - Implies N bits, where N is a positive integer such that,
- 32 <= N <= Host_IPA_Limit
-
-Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and
-is dependent on the CPU capability and the kernel configuration. The limit can
-be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
-ioctl() at run-time.
-
-Please note that configuring the IPA size does not affect the capability
-exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
-size of the address translated by the stage2 level (guest physical to
-host physical address translations).
-
-
-4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
-
-Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
-Architectures: x86
-Type: system ioctl
-Parameters: struct kvm_msr_list (in/out)
-Returns: 0 on success; -1 on error
-Errors:
- EFAULT: the msr index list cannot be read from or written to
- E2BIG: the msr index list is to be to fit in the array specified by
- the user.
-
-struct kvm_msr_list {
- __u32 nmsrs; /* number of msrs in entries */
- __u32 indices[0];
-};
-
-The user fills in the size of the indices array in nmsrs, and in return
-kvm adjusts nmsrs to reflect the actual number of msrs and fills in the
-indices array with their numbers.
-
-KVM_GET_MSR_INDEX_LIST returns the guest msrs that are supported. The list
-varies by kvm version and host processor, but does not change otherwise.
-
-Note: if kvm indicates supports MCE (KVM_CAP_MCE), then the MCE bank MSRs are
-not returned in the MSR list, as different vcpus can have a different number
-of banks, as set via the KVM_X86_SETUP_MCE ioctl.
-
-KVM_GET_MSR_FEATURE_INDEX_LIST returns the list of MSRs that can be passed
-to the KVM_GET_MSRS system ioctl. This lets userspace probe host capabilities
-and processor features that are exposed via MSRs (e.g., VMX capabilities).
-This list also varies by kvm version and host processor, but does not change
-otherwise.
-
-
-4.4 KVM_CHECK_EXTENSION
-
-Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
-Architectures: all
-Type: system ioctl, vm ioctl
-Parameters: extension identifier (KVM_CAP_*)
-Returns: 0 if unsupported; 1 (or some other positive integer) if supported
-
-The API allows the application to query about extensions to the core
-kvm API. Userspace passes an extension identifier (an integer) and
-receives an integer that describes the extension availability.
-Generally 0 means no and 1 means yes, but some extensions may report
-additional information in the integer return value.
-
-Based on their initialization different VMs may have different capabilities.
-It is thus encouraged to use the vm ioctl to query for capabilities (available
-with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
-
-4.5 KVM_GET_VCPU_MMAP_SIZE
-
-Capability: basic
-Architectures: all
-Type: system ioctl
-Parameters: none
-Returns: size of vcpu mmap area, in bytes
-
-The KVM_RUN ioctl (cf.) communicates with userspace via a shared
-memory region. This ioctl returns the size of that region. See the
-KVM_RUN documentation for details.
-
-
-4.6 KVM_SET_MEMORY_REGION
-
-Capability: basic
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_memory_region (in)
-Returns: 0 on success, -1 on error
-
-This ioctl is obsolete and has been removed.
-
-
-4.7 KVM_CREATE_VCPU
-
-Capability: basic
-Architectures: all
-Type: vm ioctl
-Parameters: vcpu id (apic id on x86)
-Returns: vcpu fd on success, -1 on error
-
-This API adds a vcpu to a virtual machine. No more than max_vcpus may be added.
-The vcpu id is an integer in the range [0, max_vcpu_id).
-
-The recommended max_vcpus value can be retrieved using the KVM_CAP_NR_VCPUS of
-the KVM_CHECK_EXTENSION ioctl() at run-time.
-The maximum possible value for max_vcpus can be retrieved using the
-KVM_CAP_MAX_VCPUS of the KVM_CHECK_EXTENSION ioctl() at run-time.
-
-If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
-cpus max.
-If the KVM_CAP_MAX_VCPUS does not exist, you should assume that max_vcpus is
-same as the value returned from KVM_CAP_NR_VCPUS.
-
-The maximum possible value for max_vcpu_id can be retrieved using the
-KVM_CAP_MAX_VCPU_ID of the KVM_CHECK_EXTENSION ioctl() at run-time.
-
-If the KVM_CAP_MAX_VCPU_ID does not exist, you should assume that max_vcpu_id
-is the same as the value returned from KVM_CAP_MAX_VCPUS.
-
-On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
-threads in one or more virtual CPU cores. (This is because the
-hardware requires all the hardware threads in a CPU core to be in the
-same partition.) The KVM_CAP_PPC_SMT capability indicates the number
-of vcpus per virtual core (vcore). The vcore id is obtained by
-dividing the vcpu id by the number of vcpus per vcore. The vcpus in a
-given vcore will always be in the same physical core as each other
-(though that might be a different physical core from time to time).
-Userspace can control the threading (SMT) mode of the guest by its
-allocation of vcpu ids. For example, if userspace wants
-single-threaded guest vcpus, it should make all vcpu ids be a multiple
-of the number of vcpus per vcore.
-
-For virtual cpus that have been created with S390 user controlled virtual
-machines, the resulting vcpu fd can be memory mapped at page offset
-KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
-cpu's hardware control block.
-
-
-4.8 KVM_GET_DIRTY_LOG (vm ioctl)
-
-Capability: basic
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_dirty_log (in/out)
-Returns: 0 on success, -1 on error
-
-/* for KVM_GET_DIRTY_LOG */
-struct kvm_dirty_log {
- __u32 slot;
- __u32 padding;
- union {
- void __user *dirty_bitmap; /* one bit per page */
- __u64 padding;
- };
-};
-
-Given a memory slot, return a bitmap containing any pages dirtied
-since the last call to this ioctl. Bit 0 is the first page in the
-memory slot. Ensure the entire structure is cleared to avoid padding
-issues.
-
-If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
-the address space for which you want to return the dirty bitmap.
-They must be less than the value that KVM_CHECK_EXTENSION returns for
-the KVM_CAP_MULTI_ADDRESS_SPACE capability.
-
-The bits in the dirty bitmap are cleared before the ioctl returns, unless
-KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is enabled. For more information,
-see the description of the capability.
-
-4.9 KVM_SET_MEMORY_ALIAS
-
-Capability: basic
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_memory_alias (in)
-Returns: 0 (success), -1 (error)
-
-This ioctl is obsolete and has been removed.
-
-
-4.10 KVM_RUN
-
-Capability: basic
-Architectures: all
-Type: vcpu ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
-Errors:
- EINTR: an unmasked signal is pending
-
-This ioctl is used to run a guest virtual cpu. While there are no
-explicit parameters, there is an implicit parameter block that can be
-obtained by mmap()ing the vcpu fd at offset 0, with the size given by
-KVM_GET_VCPU_MMAP_SIZE. The parameter block is formatted as a 'struct
-kvm_run' (see below).
-
-
-4.11 KVM_GET_REGS
-
-Capability: basic
-Architectures: all except ARM, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_regs (out)
-Returns: 0 on success, -1 on error
-
-Reads the general purpose registers from the vcpu.
-
-/* x86 */
-struct kvm_regs {
- /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
- __u64 rax, rbx, rcx, rdx;
- __u64 rsi, rdi, rsp, rbp;
- __u64 r8, r9, r10, r11;
- __u64 r12, r13, r14, r15;
- __u64 rip, rflags;
-};
-
-/* mips */
-struct kvm_regs {
- /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
- __u64 gpr[32];
- __u64 hi;
- __u64 lo;
- __u64 pc;
-};
-
-
-4.12 KVM_SET_REGS
-
-Capability: basic
-Architectures: all except ARM, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_regs (in)
-Returns: 0 on success, -1 on error
-
-Writes the general purpose registers into the vcpu.
-
-See KVM_GET_REGS for the data structure.
-
-
-4.13 KVM_GET_SREGS
-
-Capability: basic
-Architectures: x86, ppc
-Type: vcpu ioctl
-Parameters: struct kvm_sregs (out)
-Returns: 0 on success, -1 on error
-
-Reads special registers from the vcpu.
-
-/* x86 */
-struct kvm_sregs {
- struct kvm_segment cs, ds, es, fs, gs, ss;
- struct kvm_segment tr, ldt;
- struct kvm_dtable gdt, idt;
- __u64 cr0, cr2, cr3, cr4, cr8;
- __u64 efer;
- __u64 apic_base;
- __u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
-};
-
-/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
-
-interrupt_bitmap is a bitmap of pending external interrupts. At most
-one bit may be set. This interrupt has been acknowledged by the APIC
-but not yet injected into the cpu core.
-
-
-4.14 KVM_SET_SREGS
-
-Capability: basic
-Architectures: x86, ppc
-Type: vcpu ioctl
-Parameters: struct kvm_sregs (in)
-Returns: 0 on success, -1 on error
-
-Writes special registers into the vcpu. See KVM_GET_SREGS for the
-data structures.
-
-
-4.15 KVM_TRANSLATE
-
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_translation (in/out)
-Returns: 0 on success, -1 on error
-
-Translates a virtual address according to the vcpu's current address
-translation mode.
-
-struct kvm_translation {
- /* in */
- __u64 linear_address;
-
- /* out */
- __u64 physical_address;
- __u8 valid;
- __u8 writeable;
- __u8 usermode;
- __u8 pad[5];
-};
-
-
-4.16 KVM_INTERRUPT
-
-Capability: basic
-Architectures: x86, ppc, mips
-Type: vcpu ioctl
-Parameters: struct kvm_interrupt (in)
-Returns: 0 on success, negative on failure.
-
-Queues a hardware interrupt vector to be injected.
-
-/* for KVM_INTERRUPT */
-struct kvm_interrupt {
- /* in */
- __u32 irq;
-};
-
-X86:
-
-Returns: 0 on success,
- -EEXIST if an interrupt is already enqueued
- -EINVAL the the irq number is invalid
- -ENXIO if the PIC is in the kernel
- -EFAULT if the pointer is invalid
-
-Note 'irq' is an interrupt vector, not an interrupt pin or line. This
-ioctl is useful if the in-kernel PIC is not used.
-
-PPC:
-
-Queues an external interrupt to be injected. This ioctl is overleaded
-with 3 different irq values:
-
-a) KVM_INTERRUPT_SET
-
- This injects an edge type external interrupt into the guest once it's ready
- to receive interrupts. When injected, the interrupt is done.
-
-b) KVM_INTERRUPT_UNSET
-
- This unsets any pending interrupt.
-
- Only available with KVM_CAP_PPC_UNSET_IRQ.
-
-c) KVM_INTERRUPT_SET_LEVEL
-
- This injects a level type external interrupt into the guest context. The
- interrupt stays pending until a specific ioctl with KVM_INTERRUPT_UNSET
- is triggered.
-
- Only available with KVM_CAP_PPC_IRQ_LEVEL.
-
-Note that any value for 'irq' other than the ones stated above is invalid
-and incurs unexpected behavior.
-
-This is an asynchronous vcpu ioctl and can be invoked from any thread.
-
-MIPS:
-
-Queues an external interrupt to be injected into the virtual CPU. A negative
-interrupt number dequeues the interrupt.
-
-This is an asynchronous vcpu ioctl and can be invoked from any thread.
-
-
-4.17 KVM_DEBUG_GUEST
-
-Capability: basic
-Architectures: none
-Type: vcpu ioctl
-Parameters: none)
-Returns: -1 on error
-
-Support for this has been removed. Use KVM_SET_GUEST_DEBUG instead.
-
-
-4.18 KVM_GET_MSRS
-
-Capability: basic (vcpu), KVM_CAP_GET_MSR_FEATURES (system)
-Architectures: x86
-Type: system ioctl, vcpu ioctl
-Parameters: struct kvm_msrs (in/out)
-Returns: number of msrs successfully returned;
- -1 on error
-
-When used as a system ioctl:
-Reads the values of MSR-based features that are available for the VM. This
-is similar to KVM_GET_SUPPORTED_CPUID, but it returns MSR indices and values.
-The list of msr-based features can be obtained using KVM_GET_MSR_FEATURE_INDEX_LIST
-in a system ioctl.
-
-When used as a vcpu ioctl:
-Reads model-specific registers from the vcpu. Supported msr indices can
-be obtained using KVM_GET_MSR_INDEX_LIST in a system ioctl.
-
-struct kvm_msrs {
- __u32 nmsrs; /* number of msrs in entries */
- __u32 pad;
-
- struct kvm_msr_entry entries[0];
-};
-
-struct kvm_msr_entry {
- __u32 index;
- __u32 reserved;
- __u64 data;
-};
-
-Application code should set the 'nmsrs' member (which indicates the
-size of the entries array) and the 'index' member of each array entry.
-kvm will fill in the 'data' member.
-
-
-4.19 KVM_SET_MSRS
-
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_msrs (in)
-Returns: 0 on success, -1 on error
-
-Writes model-specific registers to the vcpu. See KVM_GET_MSRS for the
-data structures.
-
-Application code should set the 'nmsrs' member (which indicates the
-size of the entries array), and the 'index' and 'data' members of each
-array entry.
-
-
-4.20 KVM_SET_CPUID
-
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_cpuid (in)
-Returns: 0 on success, -1 on error
-
-Defines the vcpu responses to the cpuid instruction. Applications
-should use the KVM_SET_CPUID2 ioctl if available.
-
-
-struct kvm_cpuid_entry {
- __u32 function;
- __u32 eax;
- __u32 ebx;
- __u32 ecx;
- __u32 edx;
- __u32 padding;
-};
-
-/* for KVM_SET_CPUID */
-struct kvm_cpuid {
- __u32 nent;
- __u32 padding;
- struct kvm_cpuid_entry entries[0];
-};
-
-
-4.21 KVM_SET_SIGNAL_MASK
-
-Capability: basic
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_signal_mask (in)
-Returns: 0 on success, -1 on error
-
-Defines which signals are blocked during execution of KVM_RUN. This
-signal mask temporarily overrides the threads signal mask. Any
-unblocked signal received (except SIGKILL and SIGSTOP, which retain
-their traditional behaviour) will cause KVM_RUN to return with -EINTR.
-
-Note the signal will only be delivered if not blocked by the original
-signal mask.
-
-/* for KVM_SET_SIGNAL_MASK */
-struct kvm_signal_mask {
- __u32 len;
- __u8 sigset[0];
-};
-
-
-4.22 KVM_GET_FPU
-
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_fpu (out)
-Returns: 0 on success, -1 on error
-
-Reads the floating point state from the vcpu.
-
-/* for KVM_GET_FPU and KVM_SET_FPU */
-struct kvm_fpu {
- __u8 fpr[8][16];
- __u16 fcw;
- __u16 fsw;
- __u8 ftwx; /* in fxsave format */
- __u8 pad1;
- __u16 last_opcode;
- __u64 last_ip;
- __u64 last_dp;
- __u8 xmm[16][16];
- __u32 mxcsr;
- __u32 pad2;
-};
-
-
-4.23 KVM_SET_FPU
-
-Capability: basic
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_fpu (in)
-Returns: 0 on success, -1 on error
-
-Writes the floating point state to the vcpu.
-
-/* for KVM_GET_FPU and KVM_SET_FPU */
-struct kvm_fpu {
- __u8 fpr[8][16];
- __u16 fcw;
- __u16 fsw;
- __u8 ftwx; /* in fxsave format */
- __u8 pad1;
- __u16 last_opcode;
- __u64 last_ip;
- __u64 last_dp;
- __u8 xmm[16][16];
- __u32 mxcsr;
- __u32 pad2;
-};
-
-
-4.24 KVM_CREATE_IRQCHIP
-
-Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
-Architectures: x86, ARM, arm64, s390
-Type: vm ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
-
-Creates an interrupt controller model in the kernel.
-On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up
-future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both
-PIC and IOAPIC; GSI 16-23 only go to the IOAPIC.
-On ARM/arm64, a GICv2 is created. Any other GIC versions require the usage of
-KVM_CREATE_DEVICE, which also supports creating a GICv2. Using
-KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2.
-On s390, a dummy irq routing table is created.
-
-Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
-before KVM_CREATE_IRQCHIP can be used.
-
-
-4.25 KVM_IRQ_LINE
-
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86, arm, arm64
-Type: vm ioctl
-Parameters: struct kvm_irq_level
-Returns: 0 on success, -1 on error
-
-Sets the level of a GSI input to the interrupt controller model in the kernel.
-On some architectures it is required that an interrupt controller model has
-been previously created with KVM_CREATE_IRQCHIP. Note that edge-triggered
-interrupts require the level to be set to 1 and then back to 0.
-
-On real hardware, interrupt pins can be active-low or active-high. This
-does not matter for the level field of struct kvm_irq_level: 1 always
-means active (asserted), 0 means inactive (deasserted).
-
-x86 allows the operating system to program the interrupt polarity
-(active-low/active-high) for level-triggered interrupts, and KVM used
-to consider the polarity. However, due to bitrot in the handling of
-active-low interrupts, the above convention is now valid on x86 too.
-This is signaled by KVM_CAP_X86_IOAPIC_POLARITY_IGNORED. Userspace
-should not present interrupts to the guest as active-low unless this
-capability is present (or unless it is not using the in-kernel irqchip,
-of course).
-
-
-ARM/arm64 can signal an interrupt either at the CPU level, or at the
-in-kernel irqchip (GIC), and for in-kernel irqchip can tell the GIC to
-use PPIs designated for specific cpus. The irq field is interpreted
-like this:
-
- bits: | 31 ... 24 | 23 ... 16 | 15 ... 0 |
- field: | irq_type | vcpu_index | irq_id |
-
-The irq_type field has the following values:
-- irq_type[0]: out-of-kernel GIC: irq_id 0 is IRQ, irq_id 1 is FIQ
-- irq_type[1]: in-kernel GIC: SPI, irq_id between 32 and 1019 (incl.)
- (the vcpu_index field is ignored)
-- irq_type[2]: in-kernel GIC: PPI, irq_id between 16 and 31 (incl.)
-
-(The irq_id field thus corresponds nicely to the IRQ ID in the ARM GIC specs)
-
-In both cases, level is used to assert/deassert the line.
-
-struct kvm_irq_level {
- union {
- __u32 irq; /* GSI */
- __s32 status; /* not used for KVM_IRQ_LEVEL */
- };
- __u32 level; /* 0 or 1 */
-};
-
-
-4.26 KVM_GET_IRQCHIP
-
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_irqchip (in/out)
-Returns: 0 on success, -1 on error
-
-Reads the state of a kernel interrupt controller created with
-KVM_CREATE_IRQCHIP into a buffer provided by the caller.
-
-struct kvm_irqchip {
- __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
- __u32 pad;
- union {
- char dummy[512]; /* reserving space */
- struct kvm_pic_state pic;
- struct kvm_ioapic_state ioapic;
- } chip;
-};
-
-
-4.27 KVM_SET_IRQCHIP
-
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_irqchip (in)
-Returns: 0 on success, -1 on error
-
-Sets the state of a kernel interrupt controller created with
-KVM_CREATE_IRQCHIP from a buffer provided by the caller.
-
-struct kvm_irqchip {
- __u32 chip_id; /* 0 = PIC1, 1 = PIC2, 2 = IOAPIC */
- __u32 pad;
- union {
- char dummy[512]; /* reserving space */
- struct kvm_pic_state pic;
- struct kvm_ioapic_state ioapic;
- } chip;
-};
-
-
-4.28 KVM_XEN_HVM_CONFIG
-
-Capability: KVM_CAP_XEN_HVM
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_xen_hvm_config (in)
-Returns: 0 on success, -1 on error
-
-Sets the MSR that the Xen HVM guest uses to initialize its hypercall
-page, and provides the starting address and size of the hypercall
-blobs in userspace. When the guest writes the MSR, kvm copies one
-page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
-memory.
-
-struct kvm_xen_hvm_config {
- __u32 flags;
- __u32 msr;
- __u64 blob_addr_32;
- __u64 blob_addr_64;
- __u8 blob_size_32;
- __u8 blob_size_64;
- __u8 pad2[30];
-};
-
-
-4.29 KVM_GET_CLOCK
-
-Capability: KVM_CAP_ADJUST_CLOCK
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_clock_data (out)
-Returns: 0 on success, -1 on error
-
-Gets the current timestamp of kvmclock as seen by the current guest. In
-conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
-such as migration.
-
-When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the
-set of bits that KVM can return in struct kvm_clock_data's flag member.
-
-The only flag defined now is KVM_CLOCK_TSC_STABLE. If set, the returned
-value is the exact kvmclock value seen by all VCPUs at the instant
-when KVM_GET_CLOCK was called. If clear, the returned value is simply
-CLOCK_MONOTONIC plus a constant offset; the offset can be modified
-with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock,
-but the exact value read by each VCPU could differ, because the host
-TSC is not stable.
-
-struct kvm_clock_data {
- __u64 clock; /* kvmclock current value */
- __u32 flags;
- __u32 pad[9];
-};
-
-
-4.30 KVM_SET_CLOCK
-
-Capability: KVM_CAP_ADJUST_CLOCK
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_clock_data (in)
-Returns: 0 on success, -1 on error
-
-Sets the current timestamp of kvmclock to the value specified in its parameter.
-In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
-such as migration.
-
-struct kvm_clock_data {
- __u64 clock; /* kvmclock current value */
- __u32 flags;
- __u32 pad[9];
-};
-
-
-4.31 KVM_GET_VCPU_EVENTS
-
-Capability: KVM_CAP_VCPU_EVENTS
-Extended by: KVM_CAP_INTR_SHADOW
-Architectures: x86, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_vcpu_event (out)
-Returns: 0 on success, -1 on error
-
-X86:
-
-Gets currently pending exceptions, interrupts, and NMIs as well as related
-states of the vcpu.
-
-struct kvm_vcpu_events {
- struct {
- __u8 injected;
- __u8 nr;
- __u8 has_error_code;
- __u8 pending;
- __u32 error_code;
- } exception;
- struct {
- __u8 injected;
- __u8 nr;
- __u8 soft;
- __u8 shadow;
- } interrupt;
- struct {
- __u8 injected;
- __u8 pending;
- __u8 masked;
- __u8 pad;
- } nmi;
- __u32 sipi_vector;
- __u32 flags;
- struct {
- __u8 smm;
- __u8 pending;
- __u8 smm_inside_nmi;
- __u8 latched_init;
- } smi;
- __u8 reserved[27];
- __u8 exception_has_payload;
- __u64 exception_payload;
-};
-
-The following bits are defined in the flags field:
-
-- KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
- interrupt.shadow contains a valid state.
-
-- KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
- valid state.
-
-- KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
- exception_has_payload, exception_payload, and exception.pending
- fields contain a valid state. This bit will be set whenever
- KVM_CAP_EXCEPTION_PAYLOAD is enabled.
-
-ARM/ARM64:
-
-If the guest accesses a device that is being emulated by the host kernel in
-such a way that a real device would generate a physical SError, KVM may make
-a virtual SError pending for that VCPU. This system error interrupt remains
-pending until the guest takes the exception by unmasking PSTATE.A.
-
-Running the VCPU may cause it to take a pending SError, or make an access that
-causes an SError to become pending. The event's description is only valid while
-the VPCU is not running.
-
-This API provides a way to read and write the pending 'event' state that is not
-visible to the guest. To save, restore or migrate a VCPU the struct representing
-the state can be read then written using this GET/SET API, along with the other
-guest-visible registers. It is not possible to 'cancel' an SError that has been
-made pending.
-
-A device being emulated in user-space may also wish to generate an SError. To do
-this the events structure can be populated by user-space. The current state
-should be read first, to ensure no existing SError is pending. If an existing
-SError is pending, the architecture's 'Multiple SError interrupts' rules should
-be followed. (2.5.3 of DDI0587.a "ARM Reliability, Availability, and
-Serviceability (RAS) Specification").
-
-SError exceptions always have an ESR value. Some CPUs have the ability to
-specify what the virtual SError's ESR value should be. These systems will
-advertise KVM_CAP_ARM_INJECT_SERROR_ESR. In this case exception.has_esr will
-always have a non-zero value when read, and the agent making an SError pending
-should specify the ISS field in the lower 24 bits of exception.serror_esr. If
-the system supports KVM_CAP_ARM_INJECT_SERROR_ESR, but user-space sets the events
-with exception.has_esr as zero, KVM will choose an ESR.
-
-Specifying exception.has_esr on a system that does not support it will return
--EINVAL. Setting anything other than the lower 24bits of exception.serror_esr
-will return -EINVAL.
-
-struct kvm_vcpu_events {
- struct {
- __u8 serror_pending;
- __u8 serror_has_esr;
- /* Align it to 8 bytes */
- __u8 pad[6];
- __u64 serror_esr;
- } exception;
- __u32 reserved[12];
-};
-
-4.32 KVM_SET_VCPU_EVENTS
-
-Capability: KVM_CAP_VCPU_EVENTS
-Extended by: KVM_CAP_INTR_SHADOW
-Architectures: x86, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_vcpu_event (in)
-Returns: 0 on success, -1 on error
-
-X86:
-
-Set pending exceptions, interrupts, and NMIs as well as related states of the
-vcpu.
-
-See KVM_GET_VCPU_EVENTS for the data structure.
-
-Fields that may be modified asynchronously by running VCPUs can be excluded
-from the update. These fields are nmi.pending, sipi_vector, smi.smm,
-smi.pending. Keep the corresponding bits in the flags field cleared to
-suppress overwriting the current in-kernel state. The bits are:
-
-KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
-KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
-KVM_VCPUEVENT_VALID_SMM - transfer the smi sub-struct.
-
-If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
-the flags field to signal that interrupt.shadow contains a valid state and
-shall be written into the VCPU.
-
-KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
-
-If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD
-can be set in the flags field to signal that the
-exception_has_payload, exception_payload, and exception.pending fields
-contain a valid state and shall be written into the VCPU.
-
-ARM/ARM64:
-
-Set the pending SError exception state for this VCPU. It is not possible to
-'cancel' an Serror that has been made pending.
-
-See KVM_GET_VCPU_EVENTS for the data structure.
-
-
-4.33 KVM_GET_DEBUGREGS
-
-Capability: KVM_CAP_DEBUGREGS
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_debugregs (out)
-Returns: 0 on success, -1 on error
-
-Reads debug registers from the vcpu.
-
-struct kvm_debugregs {
- __u64 db[4];
- __u64 dr6;
- __u64 dr7;
- __u64 flags;
- __u64 reserved[9];
-};
-
-
-4.34 KVM_SET_DEBUGREGS
-
-Capability: KVM_CAP_DEBUGREGS
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_debugregs (in)
-Returns: 0 on success, -1 on error
-
-Writes debug registers into the vcpu.
-
-See KVM_GET_DEBUGREGS for the data structure. The flags field is unused
-yet and must be cleared on entry.
-
-
-4.35 KVM_SET_USER_MEMORY_REGION
-
-Capability: KVM_CAP_USER_MEMORY
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_userspace_memory_region (in)
-Returns: 0 on success, -1 on error
-
-struct kvm_userspace_memory_region {
- __u32 slot;
- __u32 flags;
- __u64 guest_phys_addr;
- __u64 memory_size; /* bytes */
- __u64 userspace_addr; /* start of the userspace allocated memory */
-};
-
-/* for kvm_memory_region::flags */
-#define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0)
-#define KVM_MEM_READONLY (1UL << 1)
-
-This ioctl allows the user to create, modify or delete a guest physical
-memory slot. Bits 0-15 of "slot" specify the slot id and this value
-should be less than the maximum number of user memory slots supported per
-VM. The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS.
-Slots may not overlap in guest physical address space.
-
-If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
-specifies the address space which is being modified. They must be
-less than the value that KVM_CHECK_EXTENSION returns for the
-KVM_CAP_MULTI_ADDRESS_SPACE capability. Slots in separate address spaces
-are unrelated; the restriction on overlapping slots only applies within
-each address space.
-
-Deleting a slot is done by passing zero for memory_size. When changing
-an existing slot, it may be moved in the guest physical memory space,
-or its flags may be modified, but it may not be resized.
-
-Memory for the region is taken starting at the address denoted by the
-field userspace_addr, which must point at user addressable memory for
-the entire memory slot size. Any object may back this memory, including
-anonymous memory, ordinary files, and hugetlbfs.
-
-It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
-be identical. This allows large pages in the guest to be backed by large
-pages in the host.
-
-The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
-KVM_MEM_READONLY. The former can be set to instruct KVM to keep track of
-writes to memory within the slot. See KVM_GET_DIRTY_LOG ioctl to know how to
-use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
-to make a new slot read-only. In this case, writes to this memory will be
-posted to userspace as KVM_EXIT_MMIO exits.
-
-When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
-the memory region are automatically reflected into the guest. For example, an
-mmap() that affects the region will be made visible immediately. Another
-example is madvise(MADV_DROP).
-
-It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
-The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
-allocation and is deprecated.
-
-
-4.36 KVM_SET_TSS_ADDR
-
-Capability: KVM_CAP_SET_TSS_ADDR
-Architectures: x86
-Type: vm ioctl
-Parameters: unsigned long tss_address (in)
-Returns: 0 on success, -1 on error
-
-This ioctl defines the physical address of a three-page region in the guest
-physical address space. The region must be within the first 4GB of the
-guest physical address space and must not conflict with any memory slot
-or any mmio address. The guest may malfunction if it accesses this memory
-region.
-
-This ioctl is required on Intel-based hosts. This is needed on Intel hardware
-because of a quirk in the virtualization implementation (see the internals
-documentation when it pops into existence).
-
-
-4.37 KVM_ENABLE_CAP
-
-Capability: KVM_CAP_ENABLE_CAP
-Architectures: mips, ppc, s390
-Type: vcpu ioctl
-Parameters: struct kvm_enable_cap (in)
-Returns: 0 on success; -1 on error
-
-Capability: KVM_CAP_ENABLE_CAP_VM
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_enable_cap (in)
-Returns: 0 on success; -1 on error
-
-+Not all extensions are enabled by default. Using this ioctl the application
-can enable an extension, making it available to the guest.
-
-On systems that do not support this ioctl, it always fails. On systems that
-do support it, it only works for extensions that are supported for enablement.
-
-To check if a capability can be enabled, the KVM_CHECK_EXTENSION ioctl should
-be used.
-
-struct kvm_enable_cap {
- /* in */
- __u32 cap;
-
-The capability that is supposed to get enabled.
-
- __u32 flags;
-
-A bitfield indicating future enhancements. Has to be 0 for now.
-
- __u64 args[4];
-
-Arguments for enabling a feature. If a feature needs initial values to
-function properly, this is the place to put them.
-
- __u8 pad[64];
-};
-
-The vcpu ioctl should be used for vcpu-specific capabilities, the vm ioctl
-for vm-wide capabilities.
-
-4.38 KVM_GET_MP_STATE
-
-Capability: KVM_CAP_MP_STATE
-Architectures: x86, s390, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_mp_state (out)
-Returns: 0 on success; -1 on error
-
-struct kvm_mp_state {
- __u32 mp_state;
-};
-
-Returns the vcpu's current "multiprocessing state" (though also valid on
-uniprocessor guests).
-
-Possible values are:
-
- - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64]
- - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP)
- which has not yet received an INIT signal [x86]
- - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is
- now ready for a SIPI [x86]
- - KVM_MP_STATE_HALTED: the vcpu has executed a HLT instruction and
- is waiting for an interrupt [x86]
- - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector
- accessible via KVM_GET_VCPU_EVENTS) [x86]
- - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64]
- - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390]
- - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted)
- [s390]
- - KVM_MP_STATE_LOAD: the vcpu is in a special load/startup state
- [s390]
-
-On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
-in-kernel irqchip, the multiprocessing state must be maintained by userspace on
-these architectures.
-
-For arm/arm64:
-
-The only states that are valid are KVM_MP_STATE_STOPPED and
-KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
-
-4.39 KVM_SET_MP_STATE
-
-Capability: KVM_CAP_MP_STATE
-Architectures: x86, s390, arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_mp_state (in)
-Returns: 0 on success; -1 on error
-
-Sets the vcpu's current "multiprocessing state"; see KVM_GET_MP_STATE for
-arguments.
-
-On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an
-in-kernel irqchip, the multiprocessing state must be maintained by userspace on
-these architectures.
-
-For arm/arm64:
-
-The only states that are valid are KVM_MP_STATE_STOPPED and
-KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
-
-4.40 KVM_SET_IDENTITY_MAP_ADDR
-
-Capability: KVM_CAP_SET_IDENTITY_MAP_ADDR
-Architectures: x86
-Type: vm ioctl
-Parameters: unsigned long identity (in)
-Returns: 0 on success, -1 on error
-
-This ioctl defines the physical address of a one-page region in the guest
-physical address space. The region must be within the first 4GB of the
-guest physical address space and must not conflict with any memory slot
-or any mmio address. The guest may malfunction if it accesses this memory
-region.
-
-Setting the address to 0 will result in resetting the address to its default
-(0xfffbc000).
-
-This ioctl is required on Intel-based hosts. This is needed on Intel hardware
-because of a quirk in the virtualization implementation (see the internals
-documentation when it pops into existence).
-
-Fails if any VCPU has already been created.
-
-4.41 KVM_SET_BOOT_CPU_ID
-
-Capability: KVM_CAP_SET_BOOT_CPU_ID
-Architectures: x86
-Type: vm ioctl
-Parameters: unsigned long vcpu_id
-Returns: 0 on success, -1 on error
-
-Define which vcpu is the Bootstrap Processor (BSP). Values are the same
-as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default
-is vcpu 0.
-
-
-4.42 KVM_GET_XSAVE
-
-Capability: KVM_CAP_XSAVE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xsave (out)
-Returns: 0 on success, -1 on error
-
-struct kvm_xsave {
- __u32 region[1024];
-};
-
-This ioctl would copy current vcpu's xsave struct to the userspace.
-
-
-4.43 KVM_SET_XSAVE
-
-Capability: KVM_CAP_XSAVE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xsave (in)
-Returns: 0 on success, -1 on error
-
-struct kvm_xsave {
- __u32 region[1024];
-};
-
-This ioctl would copy userspace's xsave struct to the kernel.
-
-
-4.44 KVM_GET_XCRS
-
-Capability: KVM_CAP_XCRS
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xcrs (out)
-Returns: 0 on success, -1 on error
-
-struct kvm_xcr {
- __u32 xcr;
- __u32 reserved;
- __u64 value;
-};
-
-struct kvm_xcrs {
- __u32 nr_xcrs;
- __u32 flags;
- struct kvm_xcr xcrs[KVM_MAX_XCRS];
- __u64 padding[16];
-};
-
-This ioctl would copy current vcpu's xcrs to the userspace.
-
-
-4.45 KVM_SET_XCRS
-
-Capability: KVM_CAP_XCRS
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_xcrs (in)
-Returns: 0 on success, -1 on error
-
-struct kvm_xcr {
- __u32 xcr;
- __u32 reserved;
- __u64 value;
-};
-
-struct kvm_xcrs {
- __u32 nr_xcrs;
- __u32 flags;
- struct kvm_xcr xcrs[KVM_MAX_XCRS];
- __u64 padding[16];
-};
-
-This ioctl would set vcpu's xcr to the value userspace specified.
-
-
-4.46 KVM_GET_SUPPORTED_CPUID
-
-Capability: KVM_CAP_EXT_CPUID
-Architectures: x86
-Type: system ioctl
-Parameters: struct kvm_cpuid2 (in/out)
-Returns: 0 on success, -1 on error
-
-struct kvm_cpuid2 {
- __u32 nent;
- __u32 padding;
- struct kvm_cpuid_entry2 entries[0];
-};
-
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
-#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
-#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
-
-struct kvm_cpuid_entry2 {
- __u32 function;
- __u32 index;
- __u32 flags;
- __u32 eax;
- __u32 ebx;
- __u32 ecx;
- __u32 edx;
- __u32 padding[3];
-};
-
-This ioctl returns x86 cpuid features which are supported by both the
-hardware and kvm in its default configuration. Userspace can use the
-information returned by this ioctl to construct cpuid information (for
-KVM_SET_CPUID2) that is consistent with hardware, kernel, and
-userspace capabilities, and with user requirements (for example, the
-user may wish to constrain cpuid to emulate older hardware, or for
-feature consistency across a cluster).
-
-Note that certain capabilities, such as KVM_CAP_X86_DISABLE_EXITS, may
-expose cpuid features (e.g. MONITOR) which are not supported by kvm in
-its default configuration. If userspace enables such capabilities, it
-is responsible for modifying the results of this ioctl appropriately.
-
-Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
-with the 'nent' field indicating the number of entries in the variable-size
-array 'entries'. If the number of entries is too low to describe the cpu
-capabilities, an error (E2BIG) is returned. If the number is too high,
-the 'nent' field is adjusted and an error (ENOMEM) is returned. If the
-number is just right, the 'nent' field is adjusted to the number of valid
-entries in the 'entries' array, which is then filled.
-
-The entries returned are the host cpuid as returned by the cpuid instruction,
-with unknown or unsupported features masked out. Some features (for example,
-x2apic), may not be present in the host cpu, but are exposed by kvm if it can
-emulate them efficiently. The fields in each entry are defined as follows:
-
- function: the eax value used to obtain the entry
- index: the ecx value used to obtain the entry (for entries that are
- affected by ecx)
- flags: an OR of zero or more of the following:
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
- if the index field is valid
- KVM_CPUID_FLAG_STATEFUL_FUNC:
- if cpuid for this function returns different values for successive
- invocations; there will be several entries with the same function,
- all with this flag set
- KVM_CPUID_FLAG_STATE_READ_NEXT:
- for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
- the first entry to be read by a cpu
- eax, ebx, ecx, edx: the values returned by the cpuid instruction for
- this function/index combination
-
-The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned
-as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC
-support. Instead it is reported via
-
- ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER)
-
-if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the
-feature in userspace, then you can enable the feature for KVM_SET_CPUID2.
-
-
-4.47 KVM_PPC_GET_PVINFO
-
-Capability: KVM_CAP_PPC_GET_PVINFO
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_ppc_pvinfo (out)
-Returns: 0 on success, !0 on error
-
-struct kvm_ppc_pvinfo {
- __u32 flags;
- __u32 hcall[4];
- __u8 pad[108];
-};
-
-This ioctl fetches PV specific information that need to be passed to the guest
-using the device tree or other means from vm context.
-
-The hcall array defines 4 instructions that make up a hypercall.
-
-If any additional field gets added to this structure later on, a bit for that
-additional piece of information will be set in the flags bitmap.
-
-The flags bitmap is defined as:
-
- /* the host supports the ePAPR idle hcall
- #define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
-
-4.52 KVM_SET_GSI_ROUTING
-
-Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 s390 arm arm64
-Type: vm ioctl
-Parameters: struct kvm_irq_routing (in)
-Returns: 0 on success, -1 on error
-
-Sets the GSI routing table entries, overwriting any previously set entries.
-
-On arm/arm64, GSI routing has the following limitation:
-- GSI routing does not apply to KVM_IRQ_LINE but only to KVM_IRQFD.
-
-struct kvm_irq_routing {
- __u32 nr;
- __u32 flags;
- struct kvm_irq_routing_entry entries[0];
-};
-
-No flags are specified so far, the corresponding field must be set to zero.
-
-struct kvm_irq_routing_entry {
- __u32 gsi;
- __u32 type;
- __u32 flags;
- __u32 pad;
- union {
- struct kvm_irq_routing_irqchip irqchip;
- struct kvm_irq_routing_msi msi;
- struct kvm_irq_routing_s390_adapter adapter;
- struct kvm_irq_routing_hv_sint hv_sint;
- __u32 pad[8];
- } u;
-};
-
-/* gsi routing entry types */
-#define KVM_IRQ_ROUTING_IRQCHIP 1
-#define KVM_IRQ_ROUTING_MSI 2
-#define KVM_IRQ_ROUTING_S390_ADAPTER 3
-#define KVM_IRQ_ROUTING_HV_SINT 4
-
-flags:
-- KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry
- type, specifies that the devid field contains a valid value. The per-VM
- KVM_CAP_MSI_DEVID capability advertises the requirement to provide
- the device ID. If this capability is not available, userspace should
- never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
-- zero otherwise
-
-struct kvm_irq_routing_irqchip {
- __u32 irqchip;
- __u32 pin;
-};
-
-struct kvm_irq_routing_msi {
- __u32 address_lo;
- __u32 address_hi;
- __u32 data;
- union {
- __u32 pad;
- __u32 devid;
- };
-};
-
-If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
-for the device that wrote the MSI message. For PCI, this is usually a
-BFD identifier in the lower 16 bits.
-
-On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
-feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
-address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
-address_hi must be zero.
-
-struct kvm_irq_routing_s390_adapter {
- __u64 ind_addr;
- __u64 summary_addr;
- __u64 ind_offset;
- __u32 summary_offset;
- __u32 adapter_id;
-};
-
-struct kvm_irq_routing_hv_sint {
- __u32 vcpu;
- __u32 sint;
-};
-
-
-4.55 KVM_SET_TSC_KHZ
-
-Capability: KVM_CAP_TSC_CONTROL
-Architectures: x86
-Type: vcpu ioctl
-Parameters: virtual tsc_khz
-Returns: 0 on success, -1 on error
-
-Specifies the tsc frequency for the virtual machine. The unit of the
-frequency is KHz.
-
-
-4.56 KVM_GET_TSC_KHZ
-
-Capability: KVM_CAP_GET_TSC_KHZ
-Architectures: x86
-Type: vcpu ioctl
-Parameters: none
-Returns: virtual tsc-khz on success, negative value on error
-
-Returns the tsc frequency of the guest. The unit of the return value is
-KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
-error.
-
-
-4.57 KVM_GET_LAPIC
-
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_lapic_state (out)
-Returns: 0 on success, -1 on error
-
-#define KVM_APIC_REG_SIZE 0x400
-struct kvm_lapic_state {
- char regs[KVM_APIC_REG_SIZE];
-};
-
-Reads the Local APIC registers and copies them into the input argument. The
-data format and layout are the same as documented in the architecture manual.
-
-If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
-enabled, then the format of APIC_ID register depends on the APIC mode
-(reported by MSR_IA32_APICBASE) of its VCPU. x2APIC stores APIC ID in
-the APIC_ID register (bytes 32-35). xAPIC only allows an 8-bit APIC ID
-which is stored in bits 31-24 of the APIC register, or equivalently in
-byte 35 of struct kvm_lapic_state's regs field. KVM_GET_LAPIC must then
-be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.
-
-If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
-always uses xAPIC format.
-
-
-4.58 KVM_SET_LAPIC
-
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_lapic_state (in)
-Returns: 0 on success, -1 on error
-
-#define KVM_APIC_REG_SIZE 0x400
-struct kvm_lapic_state {
- char regs[KVM_APIC_REG_SIZE];
-};
-
-Copies the input argument into the Local APIC registers. The data format
-and layout are the same as documented in the architecture manual.
-
-The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
-regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
-See the note in KVM_GET_LAPIC.
-
-
-4.59 KVM_IOEVENTFD
-
-Capability: KVM_CAP_IOEVENTFD
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_ioeventfd (in)
-Returns: 0 on success, !0 on error
-
-This ioctl attaches or detaches an ioeventfd to a legal pio/mmio address
-within the guest. A guest write in the registered address will signal the
-provided event instead of triggering an exit.
-
-struct kvm_ioeventfd {
- __u64 datamatch;
- __u64 addr; /* legal pio/mmio address */
- __u32 len; /* 0, 1, 2, 4, or 8 bytes */
- __s32 fd;
- __u32 flags;
- __u8 pad[36];
-};
-
-For the special case of virtio-ccw devices on s390, the ioevent is matched
-to a subchannel/virtqueue tuple instead.
-
-The following flags are defined:
-
-#define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
-#define KVM_IOEVENTFD_FLAG_PIO (1 << kvm_ioeventfd_flag_nr_pio)
-#define KVM_IOEVENTFD_FLAG_DEASSIGN (1 << kvm_ioeventfd_flag_nr_deassign)
-#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
- (1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)
-
-If datamatch flag is set, the event will be signaled only if the written value
-to the registered address is equal to datamatch in struct kvm_ioeventfd.
-
-For virtio-ccw devices, addr contains the subchannel id and datamatch the
-virtqueue index.
-
-With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and
-the kernel will ignore the length of guest write and may get a faster vmexit.
-The speedup may only apply to specific architectures, but the ioeventfd will
-work anyway.
-
-4.60 KVM_DIRTY_TLB
-
-Capability: KVM_CAP_SW_TLB
-Architectures: ppc
-Type: vcpu ioctl
-Parameters: struct kvm_dirty_tlb (in)
-Returns: 0 on success, -1 on error
-
-struct kvm_dirty_tlb {
- __u64 bitmap;
- __u32 num_dirty;
-};
-
-This must be called whenever userspace has changed an entry in the shared
-TLB, prior to calling KVM_RUN on the associated vcpu.
-
-The "bitmap" field is the userspace address of an array. This array
-consists of a number of bits, equal to the total number of TLB entries as
-determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
-nearest multiple of 64.
-
-Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
-array.
-
-The array is little-endian: the bit 0 is the least significant bit of the
-first byte, bit 8 is the least significant bit of the second byte, etc.
-This avoids any complications with differing word sizes.
-
-The "num_dirty" field is a performance hint for KVM to determine whether it
-should skip processing the bitmap and just invalidate everything. It must
-be set to the number of set bits in the bitmap.
-
-
-4.62 KVM_CREATE_SPAPR_TCE
-
-Capability: KVM_CAP_SPAPR_TCE
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_create_spapr_tce (in)
-Returns: file descriptor for manipulating the created TCE table
-
-This creates a virtual TCE (translation control entry) table, which
-is an IOMMU for PAPR-style virtual I/O. It is used to translate
-logical addresses used in virtual I/O into guest physical addresses,
-and provides a scatter/gather capability for PAPR virtual I/O.
-
-/* for KVM_CAP_SPAPR_TCE */
-struct kvm_create_spapr_tce {
- __u64 liobn;
- __u32 window_size;
-};
-
-The liobn field gives the logical IO bus number for which to create a
-TCE table. The window_size field specifies the size of the DMA window
-which this TCE table will translate - the table will contain one 64
-bit TCE entry for every 4kiB of the DMA window.
-
-When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
-table has been created using this ioctl(), the kernel will handle it
-in real mode, updating the TCE table. H_PUT_TCE calls for other
-liobns will cause a vm exit and must be handled by userspace.
-
-The return value is a file descriptor which can be passed to mmap(2)
-to map the created TCE table into userspace. This lets userspace read
-the entries written by kernel-handled H_PUT_TCE calls, and also lets
-userspace update the TCE table directly which is useful in some
-circumstances.
-
-
-4.63 KVM_ALLOCATE_RMA
-
-Capability: KVM_CAP_PPC_RMA
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_allocate_rma (out)
-Returns: file descriptor for mapping the allocated RMA
-
-This allocates a Real Mode Area (RMA) from the pool allocated at boot
-time by the kernel. An RMA is a physically-contiguous, aligned region
-of memory used on older POWER processors to provide the memory which
-will be accessed by real-mode (MMU off) accesses in a KVM guest.
-POWER processors support a set of sizes for the RMA that usually
-includes 64MB, 128MB, 256MB and some larger powers of two.
-
-/* for KVM_ALLOCATE_RMA */
-struct kvm_allocate_rma {
- __u64 rma_size;
-};
-
-The return value is a file descriptor which can be passed to mmap(2)
-to map the allocated RMA into userspace. The mapped area can then be
-passed to the KVM_SET_USER_MEMORY_REGION ioctl to establish it as the
-RMA for a virtual machine. The size of the RMA in bytes (which is
-fixed at host kernel boot time) is returned in the rma_size field of
-the argument structure.
-
-The KVM_CAP_PPC_RMA capability is 1 or 2 if the KVM_ALLOCATE_RMA ioctl
-is supported; 2 if the processor requires all virtual machines to have
-an RMA, or 1 if the processor can use an RMA but doesn't require it,
-because it supports the Virtual RMA (VRMA) facility.
-
-
-4.64 KVM_NMI
-
-Capability: KVM_CAP_USER_NMI
-Architectures: x86
-Type: vcpu ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
-
-Queues an NMI on the thread's vcpu. Note this is well defined only
-when KVM_CREATE_IRQCHIP has not been called, since this is an interface
-between the virtual cpu core and virtual local APIC. After KVM_CREATE_IRQCHIP
-has been called, this interface is completely emulated within the kernel.
-
-To use this to emulate the LINT1 input with KVM_CREATE_IRQCHIP, use the
-following algorithm:
-
- - pause the vcpu
- - read the local APIC's state (KVM_GET_LAPIC)
- - check whether changing LINT1 will queue an NMI (see the LVT entry for LINT1)
- - if so, issue KVM_NMI
- - resume the vcpu
-
-Some guests configure the LINT1 NMI input to cause a panic, aiding in
-debugging.
-
-
-4.65 KVM_S390_UCAS_MAP
-
-Capability: KVM_CAP_S390_UCONTROL
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_ucas_mapping (in)
-Returns: 0 in case of success
-
-The parameter is defined like this:
- struct kvm_s390_ucas_mapping {
- __u64 user_addr;
- __u64 vcpu_addr;
- __u64 length;
- };
-
-This ioctl maps the memory at "user_addr" with the length "length" to
-the vcpu's address space starting at "vcpu_addr". All parameters need to
-be aligned by 1 megabyte.
-
-
-4.66 KVM_S390_UCAS_UNMAP
-
-Capability: KVM_CAP_S390_UCONTROL
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_ucas_mapping (in)
-Returns: 0 in case of success
-
-The parameter is defined like this:
- struct kvm_s390_ucas_mapping {
- __u64 user_addr;
- __u64 vcpu_addr;
- __u64 length;
- };
-
-This ioctl unmaps the memory in the vcpu's address space starting at
-"vcpu_addr" with the length "length". The field "user_addr" is ignored.
-All parameters need to be aligned by 1 megabyte.
-
-
-4.67 KVM_S390_VCPU_FAULT
-
-Capability: KVM_CAP_S390_UCONTROL
-Architectures: s390
-Type: vcpu ioctl
-Parameters: vcpu absolute address (in)
-Returns: 0 in case of success
-
-This call creates a page table entry on the virtual cpu's address space
-(for user controlled virtual machines) or the virtual machine's address
-space (for regular virtual machines). This only works for minor faults,
-thus it's recommended to access subject memory page via the user page
-table upfront. This is useful to handle validity intercepts for user
-controlled virtual machines to fault in the virtual cpu's lowcore pages
-prior to calling the KVM_RUN ioctl.
-
-
-4.68 KVM_SET_ONE_REG
-
-Capability: KVM_CAP_ONE_REG
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_one_reg (in)
-Returns: 0 on success, negative value on failure
-Errors:
- ENOENT: no such register
- EINVAL: invalid register ID, or no such register
- EPERM: (arm64) register access not allowed before vcpu finalization
-(These error codes are indicative only: do not rely on a specific error
-code being returned in a specific situation.)
-
-struct kvm_one_reg {
- __u64 id;
- __u64 addr;
-};
-
-Using this ioctl, a single vcpu register can be set to a specific value
-defined by user space with the passed in struct kvm_one_reg, where id
-refers to the register identifier as described below and addr is a pointer
-to a variable with the respective size. There can be architecture agnostic
-and architecture specific registers. Each have their own range of operation
-and their own constants and width. To keep track of the implemented
-registers, find a list below:
-
- Arch | Register | Width (bits)
- | |
- PPC | KVM_REG_PPC_HIOR | 64
- PPC | KVM_REG_PPC_IAC1 | 64
- PPC | KVM_REG_PPC_IAC2 | 64
- PPC | KVM_REG_PPC_IAC3 | 64
- PPC | KVM_REG_PPC_IAC4 | 64
- PPC | KVM_REG_PPC_DAC1 | 64
- PPC | KVM_REG_PPC_DAC2 | 64
- PPC | KVM_REG_PPC_DABR | 64
- PPC | KVM_REG_PPC_DSCR | 64
- PPC | KVM_REG_PPC_PURR | 64
- PPC | KVM_REG_PPC_SPURR | 64
- PPC | KVM_REG_PPC_DAR | 64
- PPC | KVM_REG_PPC_DSISR | 32
- PPC | KVM_REG_PPC_AMR | 64
- PPC | KVM_REG_PPC_UAMOR | 64
- PPC | KVM_REG_PPC_MMCR0 | 64
- PPC | KVM_REG_PPC_MMCR1 | 64
- PPC | KVM_REG_PPC_MMCRA | 64
- PPC | KVM_REG_PPC_MMCR2 | 64
- PPC | KVM_REG_PPC_MMCRS | 64
- PPC | KVM_REG_PPC_SIAR | 64
- PPC | KVM_REG_PPC_SDAR | 64
- PPC | KVM_REG_PPC_SIER | 64
- PPC | KVM_REG_PPC_PMC1 | 32
- PPC | KVM_REG_PPC_PMC2 | 32
- PPC | KVM_REG_PPC_PMC3 | 32
- PPC | KVM_REG_PPC_PMC4 | 32
- PPC | KVM_REG_PPC_PMC5 | 32
- PPC | KVM_REG_PPC_PMC6 | 32
- PPC | KVM_REG_PPC_PMC7 | 32
- PPC | KVM_REG_PPC_PMC8 | 32
- PPC | KVM_REG_PPC_FPR0 | 64
- ...
- PPC | KVM_REG_PPC_FPR31 | 64
- PPC | KVM_REG_PPC_VR0 | 128
- ...
- PPC | KVM_REG_PPC_VR31 | 128
- PPC | KVM_REG_PPC_VSR0 | 128
- ...
- PPC | KVM_REG_PPC_VSR31 | 128
- PPC | KVM_REG_PPC_FPSCR | 64
- PPC | KVM_REG_PPC_VSCR | 32
- PPC | KVM_REG_PPC_VPA_ADDR | 64
- PPC | KVM_REG_PPC_VPA_SLB | 128
- PPC | KVM_REG_PPC_VPA_DTL | 128
- PPC | KVM_REG_PPC_EPCR | 32
- PPC | KVM_REG_PPC_EPR | 32
- PPC | KVM_REG_PPC_TCR | 32
- PPC | KVM_REG_PPC_TSR | 32
- PPC | KVM_REG_PPC_OR_TSR | 32
- PPC | KVM_REG_PPC_CLEAR_TSR | 32
- PPC | KVM_REG_PPC_MAS0 | 32
- PPC | KVM_REG_PPC_MAS1 | 32
- PPC | KVM_REG_PPC_MAS2 | 64
- PPC | KVM_REG_PPC_MAS7_3 | 64
- PPC | KVM_REG_PPC_MAS4 | 32
- PPC | KVM_REG_PPC_MAS6 | 32
- PPC | KVM_REG_PPC_MMUCFG | 32
- PPC | KVM_REG_PPC_TLB0CFG | 32
- PPC | KVM_REG_PPC_TLB1CFG | 32
- PPC | KVM_REG_PPC_TLB2CFG | 32
- PPC | KVM_REG_PPC_TLB3CFG | 32
- PPC | KVM_REG_PPC_TLB0PS | 32
- PPC | KVM_REG_PPC_TLB1PS | 32
- PPC | KVM_REG_PPC_TLB2PS | 32
- PPC | KVM_REG_PPC_TLB3PS | 32
- PPC | KVM_REG_PPC_EPTCFG | 32
- PPC | KVM_REG_PPC_ICP_STATE | 64
- PPC | KVM_REG_PPC_VP_STATE | 128
- PPC | KVM_REG_PPC_TB_OFFSET | 64
- PPC | KVM_REG_PPC_SPMC1 | 32
- PPC | KVM_REG_PPC_SPMC2 | 32
- PPC | KVM_REG_PPC_IAMR | 64
- PPC | KVM_REG_PPC_TFHAR | 64
- PPC | KVM_REG_PPC_TFIAR | 64
- PPC | KVM_REG_PPC_TEXASR | 64
- PPC | KVM_REG_PPC_FSCR | 64
- PPC | KVM_REG_PPC_PSPB | 32
- PPC | KVM_REG_PPC_EBBHR | 64
- PPC | KVM_REG_PPC_EBBRR | 64
- PPC | KVM_REG_PPC_BESCR | 64
- PPC | KVM_REG_PPC_TAR | 64
- PPC | KVM_REG_PPC_DPDES | 64
- PPC | KVM_REG_PPC_DAWR | 64
- PPC | KVM_REG_PPC_DAWRX | 64
- PPC | KVM_REG_PPC_CIABR | 64
- PPC | KVM_REG_PPC_IC | 64
- PPC | KVM_REG_PPC_VTB | 64
- PPC | KVM_REG_PPC_CSIGR | 64
- PPC | KVM_REG_PPC_TACR | 64
- PPC | KVM_REG_PPC_TCSCR | 64
- PPC | KVM_REG_PPC_PID | 64
- PPC | KVM_REG_PPC_ACOP | 64
- PPC | KVM_REG_PPC_VRSAVE | 32
- PPC | KVM_REG_PPC_LPCR | 32
- PPC | KVM_REG_PPC_LPCR_64 | 64
- PPC | KVM_REG_PPC_PPR | 64
- PPC | KVM_REG_PPC_ARCH_COMPAT | 32
- PPC | KVM_REG_PPC_DABRX | 32
- PPC | KVM_REG_PPC_WORT | 64
- PPC | KVM_REG_PPC_SPRG9 | 64
- PPC | KVM_REG_PPC_DBSR | 32
- PPC | KVM_REG_PPC_TIDR | 64
- PPC | KVM_REG_PPC_PSSCR | 64
- PPC | KVM_REG_PPC_DEC_EXPIRY | 64
- PPC | KVM_REG_PPC_PTCR | 64
- PPC | KVM_REG_PPC_TM_GPR0 | 64
- ...
- PPC | KVM_REG_PPC_TM_GPR31 | 64
- PPC | KVM_REG_PPC_TM_VSR0 | 128
- ...
- PPC | KVM_REG_PPC_TM_VSR63 | 128
- PPC | KVM_REG_PPC_TM_CR | 64
- PPC | KVM_REG_PPC_TM_LR | 64
- PPC | KVM_REG_PPC_TM_CTR | 64
- PPC | KVM_REG_PPC_TM_FPSCR | 64
- PPC | KVM_REG_PPC_TM_AMR | 64
- PPC | KVM_REG_PPC_TM_PPR | 64
- PPC | KVM_REG_PPC_TM_VRSAVE | 64
- PPC | KVM_REG_PPC_TM_VSCR | 32
- PPC | KVM_REG_PPC_TM_DSCR | 64
- PPC | KVM_REG_PPC_TM_TAR | 64
- PPC | KVM_REG_PPC_TM_XER | 64
- | |
- MIPS | KVM_REG_MIPS_R0 | 64
- ...
- MIPS | KVM_REG_MIPS_R31 | 64
- MIPS | KVM_REG_MIPS_HI | 64
- MIPS | KVM_REG_MIPS_LO | 64
- MIPS | KVM_REG_MIPS_PC | 64
- MIPS | KVM_REG_MIPS_CP0_INDEX | 32
- MIPS | KVM_REG_MIPS_CP0_ENTRYLO0 | 64
- MIPS | KVM_REG_MIPS_CP0_ENTRYLO1 | 64
- MIPS | KVM_REG_MIPS_CP0_CONTEXT | 64
- MIPS | KVM_REG_MIPS_CP0_CONTEXTCONFIG| 32
- MIPS | KVM_REG_MIPS_CP0_USERLOCAL | 64
- MIPS | KVM_REG_MIPS_CP0_XCONTEXTCONFIG| 64
- MIPS | KVM_REG_MIPS_CP0_PAGEMASK | 32
- MIPS | KVM_REG_MIPS_CP0_PAGEGRAIN | 32
- MIPS | KVM_REG_MIPS_CP0_SEGCTL0 | 64
- MIPS | KVM_REG_MIPS_CP0_SEGCTL1 | 64
- MIPS | KVM_REG_MIPS_CP0_SEGCTL2 | 64
- MIPS | KVM_REG_MIPS_CP0_PWBASE | 64
- MIPS | KVM_REG_MIPS_CP0_PWFIELD | 64
- MIPS | KVM_REG_MIPS_CP0_PWSIZE | 64
- MIPS | KVM_REG_MIPS_CP0_WIRED | 32
- MIPS | KVM_REG_MIPS_CP0_PWCTL | 32
- MIPS | KVM_REG_MIPS_CP0_HWRENA | 32
- MIPS | KVM_REG_MIPS_CP0_BADVADDR | 64
- MIPS | KVM_REG_MIPS_CP0_BADINSTR | 32
- MIPS | KVM_REG_MIPS_CP0_BADINSTRP | 32
- MIPS | KVM_REG_MIPS_CP0_COUNT | 32
- MIPS | KVM_REG_MIPS_CP0_ENTRYHI | 64
- MIPS | KVM_REG_MIPS_CP0_COMPARE | 32
- MIPS | KVM_REG_MIPS_CP0_STATUS | 32
- MIPS | KVM_REG_MIPS_CP0_INTCTL | 32
- MIPS | KVM_REG_MIPS_CP0_CAUSE | 32
- MIPS | KVM_REG_MIPS_CP0_EPC | 64
- MIPS | KVM_REG_MIPS_CP0_PRID | 32
- MIPS | KVM_REG_MIPS_CP0_EBASE | 64
- MIPS | KVM_REG_MIPS_CP0_CONFIG | 32
- MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32
- MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32
- MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32
- MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32
- MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32
- MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32
- MIPS | KVM_REG_MIPS_CP0_XCONTEXT | 64
- MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64
- MIPS | KVM_REG_MIPS_CP0_KSCRATCH1 | 64
- MIPS | KVM_REG_MIPS_CP0_KSCRATCH2 | 64
- MIPS | KVM_REG_MIPS_CP0_KSCRATCH3 | 64
- MIPS | KVM_REG_MIPS_CP0_KSCRATCH4 | 64
- MIPS | KVM_REG_MIPS_CP0_KSCRATCH5 | 64
- MIPS | KVM_REG_MIPS_CP0_KSCRATCH6 | 64
- MIPS | KVM_REG_MIPS_CP0_MAAR(0..63) | 64
- MIPS | KVM_REG_MIPS_COUNT_CTL | 64
- MIPS | KVM_REG_MIPS_COUNT_RESUME | 64
- MIPS | KVM_REG_MIPS_COUNT_HZ | 64
- MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32
- MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64
- MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128
- MIPS | KVM_REG_MIPS_FCR_IR | 32
- MIPS | KVM_REG_MIPS_FCR_CSR | 32
- MIPS | KVM_REG_MIPS_MSA_IR | 32
- MIPS | KVM_REG_MIPS_MSA_CSR | 32
-
-ARM registers are mapped using the lower 32 bits. The upper 16 of that
-is the register group type, or coprocessor number:
-
-ARM core registers have the following id bit patterns:
- 0x4020 0000 0010 <index into the kvm_regs struct:16>
-
-ARM 32-bit CP15 registers have the following id bit patterns:
- 0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
-
-ARM 64-bit CP15 registers have the following id bit patterns:
- 0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
-
-ARM CCSIDR registers are demultiplexed by CSSELR value:
- 0x4020 0000 0011 00 <csselr:8>
-
-ARM 32-bit VFP control registers have the following id bit patterns:
- 0x4020 0000 0012 1 <regno:12>
-
-ARM 64-bit FP registers have the following id bit patterns:
- 0x4030 0000 0012 0 <regno:12>
-
-ARM firmware pseudo-registers have the following bit pattern:
- 0x4030 0000 0014 <regno:16>
-
-
-arm64 registers are mapped using the lower 32 bits. The upper 16 of
-that is the register group type, or coprocessor number:
-
-arm64 core/FP-SIMD registers have the following id bit patterns. Note
-that the size of the access is variable, as the kvm_regs structure
-contains elements ranging from 32 to 128 bits. The index is a 32bit
-value in the kvm_regs structure seen as a 32bit array.
- 0x60x0 0000 0010 <index into the kvm_regs struct:16>
-
-Specifically:
- Encoding Register Bits kvm_regs member
-----------------------------------------------------------------
- 0x6030 0000 0010 0000 X0 64 regs.regs[0]
- 0x6030 0000 0010 0002 X1 64 regs.regs[1]
- ...
- 0x6030 0000 0010 003c X30 64 regs.regs[30]
- 0x6030 0000 0010 003e SP 64 regs.sp
- 0x6030 0000 0010 0040 PC 64 regs.pc
- 0x6030 0000 0010 0042 PSTATE 64 regs.pstate
- 0x6030 0000 0010 0044 SP_EL1 64 sp_el1
- 0x6030 0000 0010 0046 ELR_EL1 64 elr_el1
- 0x6030 0000 0010 0048 SPSR_EL1 64 spsr[KVM_SPSR_EL1] (alias SPSR_SVC)
- 0x6030 0000 0010 004a SPSR_ABT 64 spsr[KVM_SPSR_ABT]
- 0x6030 0000 0010 004c SPSR_UND 64 spsr[KVM_SPSR_UND]
- 0x6030 0000 0010 004e SPSR_IRQ 64 spsr[KVM_SPSR_IRQ]
- 0x6060 0000 0010 0050 SPSR_FIQ 64 spsr[KVM_SPSR_FIQ]
- 0x6040 0000 0010 0054 V0 128 fp_regs.vregs[0] (*)
- 0x6040 0000 0010 0058 V1 128 fp_regs.vregs[1] (*)
- ...
- 0x6040 0000 0010 00d0 V31 128 fp_regs.vregs[31] (*)
- 0x6020 0000 0010 00d4 FPSR 32 fp_regs.fpsr
- 0x6020 0000 0010 00d5 FPCR 32 fp_regs.fpcr
-
-(*) These encodings are not accepted for SVE-enabled vcpus. See
- KVM_ARM_VCPU_INIT.
-
- The equivalent register content can be accessed via bits [127:0] of
- the corresponding SVE Zn registers instead for vcpus that have SVE
- enabled (see below).
-
-arm64 CCSIDR registers are demultiplexed by CSSELR value:
- 0x6020 0000 0011 00 <csselr:8>
-
-arm64 system registers have the following id bit patterns:
- 0x6030 0000 0013 <op0:2> <op1:3> <crn:4> <crm:4> <op2:3>
-
-arm64 firmware pseudo-registers have the following bit pattern:
- 0x6030 0000 0014 <regno:16>
-
-arm64 SVE registers have the following bit patterns:
- 0x6080 0000 0015 00 <n:5> <slice:5> Zn bits[2048*slice + 2047 : 2048*slice]
- 0x6050 0000 0015 04 <n:4> <slice:5> Pn bits[256*slice + 255 : 256*slice]
- 0x6050 0000 0015 060 <slice:5> FFR bits[256*slice + 255 : 256*slice]
- 0x6060 0000 0015 ffff KVM_REG_ARM64_SVE_VLS pseudo-register
-
-Access to register IDs where 2048 * slice >= 128 * max_vq will fail with
-ENOENT. max_vq is the vcpu's maximum supported vector length in 128-bit
-quadwords: see (**) below.
-
-These registers are only accessible on vcpus for which SVE is enabled.
-See KVM_ARM_VCPU_INIT for details.
-
-In addition, except for KVM_REG_ARM64_SVE_VLS, these registers are not
-accessible until the vcpu's SVE configuration has been finalized
-using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE). See KVM_ARM_VCPU_INIT
-and KVM_ARM_VCPU_FINALIZE for more information about this procedure.
-
-KVM_REG_ARM64_SVE_VLS is a pseudo-register that allows the set of vector
-lengths supported by the vcpu to be discovered and configured by
-userspace. When transferred to or from user memory via KVM_GET_ONE_REG
-or KVM_SET_ONE_REG, the value of this register is of type
-__u64[KVM_ARM64_SVE_VLS_WORDS], and encodes the set of vector lengths as
-follows:
-
-__u64 vector_lengths[KVM_ARM64_SVE_VLS_WORDS];
-
-if (vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX &&
- ((vector_lengths[(vq - KVM_ARM64_SVE_VQ_MIN) / 64] >>
- ((vq - KVM_ARM64_SVE_VQ_MIN) % 64)) & 1))
- /* Vector length vq * 16 bytes supported */
-else
- /* Vector length vq * 16 bytes not supported */
-
-(**) The maximum value vq for which the above condition is true is
-max_vq. This is the maximum vector length available to the guest on
-this vcpu, and determines which register slices are visible through
-this ioctl interface.
-
-(See Documentation/arm64/sve.rst for an explanation of the "vq"
-nomenclature.)
-
-KVM_REG_ARM64_SVE_VLS is only accessible after KVM_ARM_VCPU_INIT.
-KVM_ARM_VCPU_INIT initialises it to the best set of vector lengths that
-the host supports.
-
-Userspace may subsequently modify it if desired until the vcpu's SVE
-configuration is finalized using KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE).
-
-Apart from simply removing all vector lengths from the host set that
-exceed some value, support for arbitrarily chosen sets of vector lengths
-is hardware-dependent and may not be available. Attempting to configure
-an invalid set of vector lengths via KVM_SET_ONE_REG will fail with
-EINVAL.
-
-After the vcpu's SVE configuration is finalized, further attempts to
-write this register will fail with EPERM.
-
-
-MIPS registers are mapped using the lower 32 bits. The upper 16 of that is
-the register group type:
-
-MIPS core registers (see above) have the following id bit patterns:
- 0x7030 0000 0000 <reg:16>
-
-MIPS CP0 registers (see KVM_REG_MIPS_CP0_* above) have the following id bit
-patterns depending on whether they're 32-bit or 64-bit registers:
- 0x7020 0000 0001 00 <reg:5> <sel:3> (32-bit)
- 0x7030 0000 0001 00 <reg:5> <sel:3> (64-bit)
-
-Note: KVM_REG_MIPS_CP0_ENTRYLO0 and KVM_REG_MIPS_CP0_ENTRYLO1 are the MIPS64
-versions of the EntryLo registers regardless of the word size of the host
-hardware, host kernel, guest, and whether XPA is present in the guest, i.e.
-with the RI and XI bits (if they exist) in bits 63 and 62 respectively, and
-the PFNX field starting at bit 30.
-
-MIPS MAARs (see KVM_REG_MIPS_CP0_MAAR(*) above) have the following id bit
-patterns:
- 0x7030 0000 0001 01 <reg:8>
-
-MIPS KVM control registers (see above) have the following id bit patterns:
- 0x7030 0000 0002 <reg:16>
-
-MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following
-id bit patterns depending on the size of the register being accessed. They are
-always accessed according to the current guest FPU mode (Status.FR and
-Config5.FRE), i.e. as the guest would see them, and they become unpredictable
-if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector
-registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they
-overlap the FPU registers:
- 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers)
- 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers)
- 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers)
-
-MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the
-following id bit patterns:
- 0x7020 0000 0003 01 <0:3> <reg:5>
-
-MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the
-following id bit patterns:
- 0x7020 0000 0003 02 <0:3> <reg:5>
-
-
-4.69 KVM_GET_ONE_REG
-
-Capability: KVM_CAP_ONE_REG
-Architectures: all
-Type: vcpu ioctl
-Parameters: struct kvm_one_reg (in and out)
-Returns: 0 on success, negative value on failure
-Errors include:
- ENOENT: no such register
- EINVAL: invalid register ID, or no such register
- EPERM: (arm64) register access not allowed before vcpu finalization
-(These error codes are indicative only: do not rely on a specific error
-code being returned in a specific situation.)
-
-This ioctl allows to receive the value of a single register implemented
-in a vcpu. The register to read is indicated by the "id" field of the
-kvm_one_reg struct passed in. On success, the register value can be found
-at the memory location pointed to by "addr".
-
-The list of registers accessible using this interface is identical to the
-list in 4.68.
-
-
-4.70 KVM_KVMCLOCK_CTRL
-
-Capability: KVM_CAP_KVMCLOCK_CTRL
-Architectures: Any that implement pvclocks (currently x86 only)
-Type: vcpu ioctl
-Parameters: None
-Returns: 0 on success, -1 on error
-
-This signals to the host kernel that the specified guest is being paused by
-userspace. The host will set a flag in the pvclock structure that is checked
-from the soft lockup watchdog. The flag is part of the pvclock structure that
-is shared between guest and host, specifically the second bit of the flags
-field of the pvclock_vcpu_time_info structure. It will be set exclusively by
-the host and read/cleared exclusively by the guest. The guest operation of
-checking and clearing the flag must an atomic operation so
-load-link/store-conditional, or equivalent must be used. There are two cases
-where the guest will clear the flag: when the soft lockup watchdog timer resets
-itself or when a soft lockup is detected. This ioctl can be called any time
-after pausing the vcpu, but before it is resumed.
-
-
-4.71 KVM_SIGNAL_MSI
-
-Capability: KVM_CAP_SIGNAL_MSI
-Architectures: x86 arm arm64
-Type: vm ioctl
-Parameters: struct kvm_msi (in)
-Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
-
-Directly inject a MSI message. Only valid with in-kernel irqchip that handles
-MSI messages.
-
-struct kvm_msi {
- __u32 address_lo;
- __u32 address_hi;
- __u32 data;
- __u32 flags;
- __u32 devid;
- __u8 pad[12];
-};
-
-flags: KVM_MSI_VALID_DEVID: devid contains a valid value. The per-VM
- KVM_CAP_MSI_DEVID capability advertises the requirement to provide
- the device ID. If this capability is not available, userspace
- should never set the KVM_MSI_VALID_DEVID flag as the ioctl might fail.
-
-If KVM_MSI_VALID_DEVID is set, devid contains a unique device identifier
-for the device that wrote the MSI message. For PCI, this is usually a
-BFD identifier in the lower 16 bits.
-
-On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
-feature of KVM_CAP_X2APIC_API capability is enabled. If it is enabled,
-address_hi bits 31-8 provide bits 31-8 of the destination id. Bits 7-0 of
-address_hi must be zero.
-
-
-4.71 KVM_CREATE_PIT2
-
-Capability: KVM_CAP_PIT2
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pit_config (in)
-Returns: 0 on success, -1 on error
-
-Creates an in-kernel device model for the i8254 PIT. This call is only valid
-after enabling in-kernel irqchip support via KVM_CREATE_IRQCHIP. The following
-parameters have to be passed:
-
-struct kvm_pit_config {
- __u32 flags;
- __u32 pad[15];
-};
-
-Valid flags are:
-
-#define KVM_PIT_SPEAKER_DUMMY 1 /* emulate speaker port stub */
-
-PIT timer interrupts may use a per-VM kernel thread for injection. If it
-exists, this thread will have a name of the following pattern:
-
-kvm-pit/<owner-process-pid>
-
-When running a guest with elevated priorities, the scheduling parameters of
-this thread may have to be adjusted accordingly.
-
-This IOCTL replaces the obsolete KVM_CREATE_PIT.
-
-
-4.72 KVM_GET_PIT2
-
-Capability: KVM_CAP_PIT_STATE2
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pit_state2 (out)
-Returns: 0 on success, -1 on error
-
-Retrieves the state of the in-kernel PIT model. Only valid after
-KVM_CREATE_PIT2. The state is returned in the following structure:
-
-struct kvm_pit_state2 {
- struct kvm_pit_channel_state channels[3];
- __u32 flags;
- __u32 reserved[9];
-};
-
-Valid flags are:
-
-/* disable PIT in HPET legacy mode */
-#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
-
-This IOCTL replaces the obsolete KVM_GET_PIT.
-
-
-4.73 KVM_SET_PIT2
-
-Capability: KVM_CAP_PIT_STATE2
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pit_state2 (in)
-Returns: 0 on success, -1 on error
-
-Sets the state of the in-kernel PIT model. Only valid after KVM_CREATE_PIT2.
-See KVM_GET_PIT2 for details on struct kvm_pit_state2.
-
-This IOCTL replaces the obsolete KVM_SET_PIT.
-
-
-4.74 KVM_PPC_GET_SMMU_INFO
-
-Capability: KVM_CAP_PPC_GET_SMMU_INFO
-Architectures: powerpc
-Type: vm ioctl
-Parameters: None
-Returns: 0 on success, -1 on error
-
-This populates and returns a structure describing the features of
-the "Server" class MMU emulation supported by KVM.
-This can in turn be used by userspace to generate the appropriate
-device-tree properties for the guest operating system.
-
-The structure contains some global information, followed by an
-array of supported segment page sizes:
-
- struct kvm_ppc_smmu_info {
- __u64 flags;
- __u32 slb_size;
- __u32 pad;
- struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
- };
-
-The supported flags are:
-
- - KVM_PPC_PAGE_SIZES_REAL:
- When that flag is set, guest page sizes must "fit" the backing
- store page sizes. When not set, any page size in the list can
- be used regardless of how they are backed by userspace.
-
- - KVM_PPC_1T_SEGMENTS
- The emulated MMU supports 1T segments in addition to the
- standard 256M ones.
-
- - KVM_PPC_NO_HASH
- This flag indicates that HPT guests are not supported by KVM,
- thus all guests must use radix MMU mode.
-
-The "slb_size" field indicates how many SLB entries are supported
-
-The "sps" array contains 8 entries indicating the supported base
-page sizes for a segment in increasing order. Each entry is defined
-as follow:
-
- struct kvm_ppc_one_seg_page_size {
- __u32 page_shift; /* Base page shift of segment (or 0) */
- __u32 slb_enc; /* SLB encoding for BookS */
- struct kvm_ppc_one_page_size enc[KVM_PPC_PAGE_SIZES_MAX_SZ];
- };
-
-An entry with a "page_shift" of 0 is unused. Because the array is
-organized in increasing order, a lookup can stop when encoutering
-such an entry.
-
-The "slb_enc" field provides the encoding to use in the SLB for the
-page size. The bits are in positions such as the value can directly
-be OR'ed into the "vsid" argument of the slbmte instruction.
-
-The "enc" array is a list which for each of those segment base page
-size provides the list of supported actual page sizes (which can be
-only larger or equal to the base page size), along with the
-corresponding encoding in the hash PTE. Similarly, the array is
-8 entries sorted by increasing sizes and an entry with a "0" shift
-is an empty entry and a terminator:
-
- struct kvm_ppc_one_page_size {
- __u32 page_shift; /* Page shift (or 0) */
- __u32 pte_enc; /* Encoding in the HPTE (>>12) */
- };
-
-The "pte_enc" field provides a value that can OR'ed into the hash
-PTE's RPN field (ie, it needs to be shifted left by 12 to OR it
-into the hash PTE second double word).
-
-4.75 KVM_IRQFD
-
-Capability: KVM_CAP_IRQFD
-Architectures: x86 s390 arm arm64
-Type: vm ioctl
-Parameters: struct kvm_irqfd (in)
-Returns: 0 on success, -1 on error
-
-Allows setting an eventfd to directly trigger a guest interrupt.
-kvm_irqfd.fd specifies the file descriptor to use as the eventfd and
-kvm_irqfd.gsi specifies the irqchip pin toggled by this event. When
-an event is triggered on the eventfd, an interrupt is injected into
-the guest using the specified gsi pin. The irqfd is removed using
-the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
-and kvm_irqfd.gsi.
-
-With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
-mechanism allowing emulation of level-triggered, irqfd-based
-interrupts. When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
-additional eventfd in the kvm_irqfd.resamplefd field. When operating
-in resample mode, posting of an interrupt through kvm_irq.fd asserts
-the specified gsi in the irqchip. When the irqchip is resampled, such
-as from an EOI, the gsi is de-asserted and the user is notified via
-kvm_irqfd.resamplefd. It is the user's responsibility to re-queue
-the interrupt if the device making use of it still requires service.
-Note that closing the resamplefd is not sufficient to disable the
-irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
-and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
-
-On arm/arm64, gsi routing being supported, the following can happen:
-- in case no routing entry is associated to this gsi, injection fails
-- in case the gsi is associated to an irqchip routing entry,
- irqchip.pin + 32 corresponds to the injected SPI ID.
-- in case the gsi is associated to an MSI routing entry, the MSI
- message and device ID are translated into an LPI (support restricted
- to GICv3 ITS in-kernel emulation).
-
-4.76 KVM_PPC_ALLOCATE_HTAB
-
-Capability: KVM_CAP_PPC_ALLOC_HTAB
-Architectures: powerpc
-Type: vm ioctl
-Parameters: Pointer to u32 containing hash table order (in/out)
-Returns: 0 on success, -1 on error
-
-This requests the host kernel to allocate an MMU hash table for a
-guest using the PAPR paravirtualization interface. This only does
-anything if the kernel is configured to use the Book 3S HV style of
-virtualization. Otherwise the capability doesn't exist and the ioctl
-returns an ENOTTY error. The rest of this description assumes Book 3S
-HV.
-
-There must be no vcpus running when this ioctl is called; if there
-are, it will do nothing and return an EBUSY error.
-
-The parameter is a pointer to a 32-bit unsigned integer variable
-containing the order (log base 2) of the desired size of the hash
-table, which must be between 18 and 46. On successful return from the
-ioctl, the value will not be changed by the kernel.
-
-If no hash table has been allocated when any vcpu is asked to run
-(with the KVM_RUN ioctl), the host kernel will allocate a
-default-sized hash table (16 MB).
-
-If this ioctl is called when a hash table has already been allocated,
-with a different order from the existing hash table, the existing hash
-table will be freed and a new one allocated. If this is ioctl is
-called when a hash table has already been allocated of the same order
-as specified, the kernel will clear out the existing hash table (zero
-all HPTEs). In either case, if the guest is using the virtualized
-real-mode area (VRMA) facility, the kernel will re-create the VMRA
-HPTEs on the next KVM_RUN of any vcpu.
-
-4.77 KVM_S390_INTERRUPT
-
-Capability: basic
-Architectures: s390
-Type: vm ioctl, vcpu ioctl
-Parameters: struct kvm_s390_interrupt (in)
-Returns: 0 on success, -1 on error
-
-Allows to inject an interrupt to the guest. Interrupts can be floating
-(vm ioctl) or per cpu (vcpu ioctl), depending on the interrupt type.
-
-Interrupt parameters are passed via kvm_s390_interrupt:
-
-struct kvm_s390_interrupt {
- __u32 type;
- __u32 parm;
- __u64 parm64;
-};
-
-type can be one of the following:
-
-KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm
-KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm
-KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm
-KVM_S390_RESTART (vcpu) - restart
-KVM_S390_INT_CLOCK_COMP (vcpu) - clock comparator interrupt
-KVM_S390_INT_CPU_TIMER (vcpu) - CPU timer interrupt
-KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
- parameters in parm and parm64
-KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
-KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
-KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
-KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
- I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
- I/O interruption parameters in parm (subchannel) and parm64 (intparm,
- interruption subclass)
-KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
- machine check interrupt code in parm64 (note that
- machine checks needing further payload are not
- supported by this ioctl)
-
-This is an asynchronous vcpu ioctl and can be invoked from any thread.
-
-4.78 KVM_PPC_GET_HTAB_FD
-
-Capability: KVM_CAP_PPC_HTAB_FD
-Architectures: powerpc
-Type: vm ioctl
-Parameters: Pointer to struct kvm_get_htab_fd (in)
-Returns: file descriptor number (>= 0) on success, -1 on error
-
-This returns a file descriptor that can be used either to read out the
-entries in the guest's hashed page table (HPT), or to write entries to
-initialize the HPT. The returned fd can only be written to if the
-KVM_GET_HTAB_WRITE bit is set in the flags field of the argument, and
-can only be read if that bit is clear. The argument struct looks like
-this:
-
-/* For KVM_PPC_GET_HTAB_FD */
-struct kvm_get_htab_fd {
- __u64 flags;
- __u64 start_index;
- __u64 reserved[2];
-};
-
-/* Values for kvm_get_htab_fd.flags */
-#define KVM_GET_HTAB_BOLTED_ONLY ((__u64)0x1)
-#define KVM_GET_HTAB_WRITE ((__u64)0x2)
-
-The `start_index' field gives the index in the HPT of the entry at
-which to start reading. It is ignored when writing.
-
-Reads on the fd will initially supply information about all
-"interesting" HPT entries. Interesting entries are those with the
-bolted bit set, if the KVM_GET_HTAB_BOLTED_ONLY bit is set, otherwise
-all entries. When the end of the HPT is reached, the read() will
-return. If read() is called again on the fd, it will start again from
-the beginning of the HPT, but will only return HPT entries that have
-changed since they were last read.
-
-Data read or written is structured as a header (8 bytes) followed by a
-series of valid HPT entries (16 bytes) each. The header indicates how
-many valid HPT entries there are and how many invalid entries follow
-the valid entries. The invalid entries are not represented explicitly
-in the stream. The header format is:
-
-struct kvm_get_htab_header {
- __u32 index;
- __u16 n_valid;
- __u16 n_invalid;
-};
-
-Writes to the fd create HPT entries starting at the index given in the
-header; first `n_valid' valid entries with contents from the data
-written, then `n_invalid' invalid entries, invalidating any previously
-valid entries found.
-
-4.79 KVM_CREATE_DEVICE
-
-Capability: KVM_CAP_DEVICE_CTRL
-Type: vm ioctl
-Parameters: struct kvm_create_device (in/out)
-Returns: 0 on success, -1 on error
-Errors:
- ENODEV: The device type is unknown or unsupported
- EEXIST: Device already created, and this type of device may not
- be instantiated multiple times
-
- Other error conditions may be defined by individual device types or
- have their standard meanings.
-
-Creates an emulated device in the kernel. The file descriptor returned
-in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
-
-If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
-device type is supported (not necessarily whether it can be created
-in the current vm).
-
-Individual devices should not define flags. Attributes should be used
-for specifying any behavior that is not implied by the device type
-number.
-
-struct kvm_create_device {
- __u32 type; /* in: KVM_DEV_TYPE_xxx */
- __u32 fd; /* out: device handle */
- __u32 flags; /* in: KVM_CREATE_DEVICE_xxx */
-};
-
-4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
-
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
- KVM_CAP_VCPU_ATTRIBUTES for vcpu device
-Type: device ioctl, vm ioctl, vcpu ioctl
-Parameters: struct kvm_device_attr
-Returns: 0 on success, -1 on error
-Errors:
- ENXIO: The group or attribute is unknown/unsupported for this device
- or hardware support is missing.
- EPERM: The attribute cannot (currently) be accessed this way
- (e.g. read-only attribute, or attribute that only makes
- sense when the device is in a different state)
-
- Other error conditions may be defined by individual device types.
-
-Gets/sets a specified piece of device configuration and/or state. The
-semantics are device-specific. See individual device documentation in
-the "devices" directory. As with ONE_REG, the size of the data
-transferred is defined by the particular attribute.
-
-struct kvm_device_attr {
- __u32 flags; /* no flags currently defined */
- __u32 group; /* device-defined */
- __u64 attr; /* group-defined */
- __u64 addr; /* userspace address of attr data */
-};
-
-4.81 KVM_HAS_DEVICE_ATTR
-
-Capability: KVM_CAP_DEVICE_CTRL, KVM_CAP_VM_ATTRIBUTES for vm device,
- KVM_CAP_VCPU_ATTRIBUTES for vcpu device
-Type: device ioctl, vm ioctl, vcpu ioctl
-Parameters: struct kvm_device_attr
-Returns: 0 on success, -1 on error
-Errors:
- ENXIO: The group or attribute is unknown/unsupported for this device
- or hardware support is missing.
-
-Tests whether a device supports a particular attribute. A successful
-return indicates the attribute is implemented. It does not necessarily
-indicate that the attribute can be read or written in the device's
-current state. "addr" is ignored.
-
-4.82 KVM_ARM_VCPU_INIT
-
-Capability: basic
-Architectures: arm, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_vcpu_init (in)
-Returns: 0 on success; -1 on error
-Errors:
- EINVAL: the target is unknown, or the combination of features is invalid.
- ENOENT: a features bit specified is unknown.
-
-This tells KVM what type of CPU to present to the guest, and what
-optional features it should have. This will cause a reset of the cpu
-registers to their initial values. If this is not called, KVM_RUN will
-return ENOEXEC for that vcpu.
-
-Note that because some registers reflect machine topology, all vcpus
-should be created before this ioctl is invoked.
-
-Userspace can call this function multiple times for a given vcpu, including
-after the vcpu has been run. This will reset the vcpu to its initial
-state. All calls to this function after the initial call must use the same
-target and same set of feature flags, otherwise EINVAL will be returned.
-
-Possible features:
- - KVM_ARM_VCPU_POWER_OFF: Starts the CPU in a power-off state.
- Depends on KVM_CAP_ARM_PSCI. If not set, the CPU will be powered on
- and execute guest code when KVM_RUN is called.
- - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode.
- Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
- - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision
- backward compatible with v0.2) for the CPU.
- Depends on KVM_CAP_ARM_PSCI_0_2.
- - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU.
- Depends on KVM_CAP_ARM_PMU_V3.
-
- - KVM_ARM_VCPU_PTRAUTH_ADDRESS: Enables Address Pointer authentication
- for arm64 only.
- Depends on KVM_CAP_ARM_PTRAUTH_ADDRESS.
- If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
- both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
- KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
- requested.
-
- - KVM_ARM_VCPU_PTRAUTH_GENERIC: Enables Generic Pointer authentication
- for arm64 only.
- Depends on KVM_CAP_ARM_PTRAUTH_GENERIC.
- If KVM_CAP_ARM_PTRAUTH_ADDRESS and KVM_CAP_ARM_PTRAUTH_GENERIC are
- both present, then both KVM_ARM_VCPU_PTRAUTH_ADDRESS and
- KVM_ARM_VCPU_PTRAUTH_GENERIC must be requested or neither must be
- requested.
-
- - KVM_ARM_VCPU_SVE: Enables SVE for the CPU (arm64 only).
- Depends on KVM_CAP_ARM_SVE.
- Requires KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
-
- * After KVM_ARM_VCPU_INIT:
-
- - KVM_REG_ARM64_SVE_VLS may be read using KVM_GET_ONE_REG: the
- initial value of this pseudo-register indicates the best set of
- vector lengths possible for a vcpu on this host.
-
- * Before KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
-
- - KVM_RUN and KVM_GET_REG_LIST are not available;
-
- - KVM_GET_ONE_REG and KVM_SET_ONE_REG cannot be used to access
- the scalable archietctural SVE registers
- KVM_REG_ARM64_SVE_ZREG(), KVM_REG_ARM64_SVE_PREG() or
- KVM_REG_ARM64_SVE_FFR;
-
- - KVM_REG_ARM64_SVE_VLS may optionally be written using
- KVM_SET_ONE_REG, to modify the set of vector lengths available
- for the vcpu.
-
- * After KVM_ARM_VCPU_FINALIZE(KVM_ARM_VCPU_SVE):
-
- - the KVM_REG_ARM64_SVE_VLS pseudo-register is immutable, and can
- no longer be written using KVM_SET_ONE_REG.
-
-4.83 KVM_ARM_PREFERRED_TARGET
-
-Capability: basic
-Architectures: arm, arm64
-Type: vm ioctl
-Parameters: struct struct kvm_vcpu_init (out)
-Returns: 0 on success; -1 on error
-Errors:
- ENODEV: no preferred target available for the host
-
-This queries KVM for preferred CPU target type which can be emulated
-by KVM on underlying host.
-
-The ioctl returns struct kvm_vcpu_init instance containing information
-about preferred CPU target type and recommended features for it. The
-kvm_vcpu_init->features bitmap returned will have feature bits set if
-the preferred target recommends setting these features, but this is
-not mandatory.
-
-The information returned by this ioctl can be used to prepare an instance
-of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
-in VCPU matching underlying host.
-
-
-4.84 KVM_GET_REG_LIST
-
-Capability: basic
-Architectures: arm, arm64, mips
-Type: vcpu ioctl
-Parameters: struct kvm_reg_list (in/out)
-Returns: 0 on success; -1 on error
-Errors:
- E2BIG: the reg index list is too big to fit in the array specified by
- the user (the number required will be written into n).
-
-struct kvm_reg_list {
- __u64 n; /* number of registers in reg[] */
- __u64 reg[0];
-};
-
-This ioctl returns the guest registers that are supported for the
-KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
-
-
-4.85 KVM_ARM_SET_DEVICE_ADDR (deprecated)
-
-Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
-Architectures: arm, arm64
-Type: vm ioctl
-Parameters: struct kvm_arm_device_address (in)
-Returns: 0 on success, -1 on error
-Errors:
- ENODEV: The device id is unknown
- ENXIO: Device not supported on current system
- EEXIST: Address already set
- E2BIG: Address outside guest physical address space
- EBUSY: Address overlaps with other device range
-
-struct kvm_arm_device_addr {
- __u64 id;
- __u64 addr;
-};
-
-Specify a device address in the guest's physical address space where guests
-can access emulated or directly exposed devices, which the host kernel needs
-to know about. The id field is an architecture specific identifier for a
-specific device.
-
-ARM/arm64 divides the id field into two parts, a device id and an
-address type id specific to the individual device.
-
- bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
- field: | 0x00000000 | device id | addr type id |
-
-ARM/arm64 currently only require this when using the in-kernel GIC
-support for the hardware VGIC features, using KVM_ARM_DEVICE_VGIC_V2
-as the device id. When setting the base address for the guest's
-mapping of the VGIC virtual CPU and distributor interface, the ioctl
-must be called after calling KVM_CREATE_IRQCHIP, but before calling
-KVM_RUN on any of the VCPUs. Calling this ioctl twice for any of the
-base addresses will return -EEXIST.
-
-Note, this IOCTL is deprecated and the more flexible SET/GET_DEVICE_ATTR API
-should be used instead.
-
-
-4.86 KVM_PPC_RTAS_DEFINE_TOKEN
-
-Capability: KVM_CAP_PPC_RTAS
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_rtas_token_args
-Returns: 0 on success, -1 on error
-
-Defines a token value for a RTAS (Run Time Abstraction Services)
-service in order to allow it to be handled in the kernel. The
-argument struct gives the name of the service, which must be the name
-of a service that has a kernel-side implementation. If the token
-value is non-zero, it will be associated with that service, and
-subsequent RTAS calls by the guest specifying that token will be
-handled by the kernel. If the token value is 0, then any token
-associated with the service will be forgotten, and subsequent RTAS
-calls by the guest for that service will be passed to userspace to be
-handled.
-
-4.87 KVM_SET_GUEST_DEBUG
-
-Capability: KVM_CAP_SET_GUEST_DEBUG
-Architectures: x86, s390, ppc, arm64
-Type: vcpu ioctl
-Parameters: struct kvm_guest_debug (in)
-Returns: 0 on success; -1 on error
-
-struct kvm_guest_debug {
- __u32 control;
- __u32 pad;
- struct kvm_guest_debug_arch arch;
-};
-
-Set up the processor specific debug registers and configure vcpu for
-handling guest debug events. There are two parts to the structure, the
-first a control bitfield indicates the type of debug events to handle
-when running. Common control bits are:
-
- - KVM_GUESTDBG_ENABLE: guest debugging is enabled
- - KVM_GUESTDBG_SINGLESTEP: the next run should single-step
-
-The top 16 bits of the control field are architecture specific control
-flags which can include the following:
-
- - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64]
- - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390, arm64]
- - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86]
- - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86]
- - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390]
-
-For example KVM_GUESTDBG_USE_SW_BP indicates that software breakpoints
-are enabled in memory so we need to ensure breakpoint exceptions are
-correctly trapped and the KVM run loop exits at the breakpoint and not
-running off into the normal guest vector. For KVM_GUESTDBG_USE_HW_BP
-we need to ensure the guest vCPUs architecture specific registers are
-updated to the correct (supplied) values.
-
-The second part of the structure is architecture specific and
-typically contains a set of debug registers.
-
-For arm64 the number of debug registers is implementation defined and
-can be determined by querying the KVM_CAP_GUEST_DEBUG_HW_BPS and
-KVM_CAP_GUEST_DEBUG_HW_WPS capabilities which return a positive number
-indicating the number of supported registers.
-
-When debug events exit the main run loop with the reason
-KVM_EXIT_DEBUG with the kvm_debug_exit_arch part of the kvm_run
-structure containing architecture specific debug information.
-
-4.88 KVM_GET_EMULATED_CPUID
-
-Capability: KVM_CAP_EXT_EMUL_CPUID
-Architectures: x86
-Type: system ioctl
-Parameters: struct kvm_cpuid2 (in/out)
-Returns: 0 on success, -1 on error
-
-struct kvm_cpuid2 {
- __u32 nent;
- __u32 flags;
- struct kvm_cpuid_entry2 entries[0];
-};
-
-The member 'flags' is used for passing flags from userspace.
-
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0)
-#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1)
-#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2)
-
-struct kvm_cpuid_entry2 {
- __u32 function;
- __u32 index;
- __u32 flags;
- __u32 eax;
- __u32 ebx;
- __u32 ecx;
- __u32 edx;
- __u32 padding[3];
-};
-
-This ioctl returns x86 cpuid features which are emulated by
-kvm.Userspace can use the information returned by this ioctl to query
-which features are emulated by kvm instead of being present natively.
-
-Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
-structure with the 'nent' field indicating the number of entries in
-the variable-size array 'entries'. If the number of entries is too low
-to describe the cpu capabilities, an error (E2BIG) is returned. If the
-number is too high, the 'nent' field is adjusted and an error (ENOMEM)
-is returned. If the number is just right, the 'nent' field is adjusted
-to the number of valid entries in the 'entries' array, which is then
-filled.
-
-The entries returned are the set CPUID bits of the respective features
-which kvm emulates, as returned by the CPUID instruction, with unknown
-or unsupported feature bits cleared.
-
-Features like x2apic, for example, may not be present in the host cpu
-but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
-emulated efficiently and thus not included here.
-
-The fields in each entry are defined as follows:
-
- function: the eax value used to obtain the entry
- index: the ecx value used to obtain the entry (for entries that are
- affected by ecx)
- flags: an OR of zero or more of the following:
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
- if the index field is valid
- KVM_CPUID_FLAG_STATEFUL_FUNC:
- if cpuid for this function returns different values for successive
- invocations; there will be several entries with the same function,
- all with this flag set
- KVM_CPUID_FLAG_STATE_READ_NEXT:
- for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
- the first entry to be read by a cpu
- eax, ebx, ecx, edx: the values returned by the cpuid instruction for
- this function/index combination
-
-4.89 KVM_S390_MEM_OP
-
-Capability: KVM_CAP_S390_MEM_OP
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_mem_op (in)
-Returns: = 0 on success,
- < 0 on generic error (e.g. -EFAULT or -ENOMEM),
- > 0 if an exception occurred while walking the page tables
-
-Read or write data from/to the logical (virtual) memory of a VCPU.
-
-Parameters are specified via the following structure:
-
-struct kvm_s390_mem_op {
- __u64 gaddr; /* the guest address */
- __u64 flags; /* flags */
- __u32 size; /* amount of bytes */
- __u32 op; /* type of operation */
- __u64 buf; /* buffer in userspace */
- __u8 ar; /* the access register number */
- __u8 reserved[31]; /* should be set to 0 */
-};
-
-The type of operation is specified in the "op" field. It is either
-KVM_S390_MEMOP_LOGICAL_READ for reading from logical memory space or
-KVM_S390_MEMOP_LOGICAL_WRITE for writing to logical memory space. The
-KVM_S390_MEMOP_F_CHECK_ONLY flag can be set in the "flags" field to check
-whether the corresponding memory access would create an access exception
-(without touching the data in the memory at the destination). In case an
-access exception occurred while walking the MMU tables of the guest, the
-ioctl returns a positive error number to indicate the type of exception.
-This exception is also raised directly at the corresponding VCPU if the
-flag KVM_S390_MEMOP_F_INJECT_EXCEPTION is set in the "flags" field.
-
-The start address of the memory region has to be specified in the "gaddr"
-field, and the length of the region in the "size" field. "buf" is the buffer
-supplied by the userspace application where the read data should be written
-to for KVM_S390_MEMOP_LOGICAL_READ, or where the data that should be written
-is stored for a KVM_S390_MEMOP_LOGICAL_WRITE. "buf" is unused and can be NULL
-when KVM_S390_MEMOP_F_CHECK_ONLY is specified. "ar" designates the access
-register number to be used.
-
-The "reserved" field is meant for future extensions. It is not used by
-KVM with the currently defined set of flags.
-
-4.90 KVM_S390_GET_SKEYS
-
-Capability: KVM_CAP_S390_SKEYS
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_skeys
-Returns: 0 on success, KVM_S390_GET_KEYS_NONE if guest is not using storage
- keys, negative value on error
-
-This ioctl is used to get guest storage key values on the s390
-architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
-
-struct kvm_s390_skeys {
- __u64 start_gfn;
- __u64 count;
- __u64 skeydata_addr;
- __u32 flags;
- __u32 reserved[9];
-};
-
-The start_gfn field is the number of the first guest frame whose storage keys
-you want to get.
-
-The count field is the number of consecutive frames (starting from start_gfn)
-whose storage keys to get. The count field must be at least 1 and the maximum
-allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
-will cause the ioctl to return -EINVAL.
-
-The skeydata_addr field is the address to a buffer large enough to hold count
-bytes. This buffer will be filled with storage key data by the ioctl.
-
-4.91 KVM_S390_SET_SKEYS
-
-Capability: KVM_CAP_S390_SKEYS
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_skeys
-Returns: 0 on success, negative value on error
-
-This ioctl is used to set guest storage key values on the s390
-architecture. The ioctl takes parameters via the kvm_s390_skeys struct.
-See section on KVM_S390_GET_SKEYS for struct definition.
-
-The start_gfn field is the number of the first guest frame whose storage keys
-you want to set.
-
-The count field is the number of consecutive frames (starting from start_gfn)
-whose storage keys to get. The count field must be at least 1 and the maximum
-allowed value is defined as KVM_S390_SKEYS_ALLOC_MAX. Values outside this range
-will cause the ioctl to return -EINVAL.
-
-The skeydata_addr field is the address to a buffer containing count bytes of
-storage keys. Each byte in the buffer will be set as the storage key for a
-single frame starting at start_gfn for count frames.
-
-Note: If any architecturally invalid key value is found in the given data then
-the ioctl will return -EINVAL.
-
-4.92 KVM_S390_IRQ
-
-Capability: KVM_CAP_S390_INJECT_IRQ
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_irq (in)
-Returns: 0 on success, -1 on error
-Errors:
- EINVAL: interrupt type is invalid
- type is KVM_S390_SIGP_STOP and flag parameter is invalid value
- type is KVM_S390_INT_EXTERNAL_CALL and code is bigger
- than the maximum of VCPUs
- EBUSY: type is KVM_S390_SIGP_SET_PREFIX and vcpu is not stopped
- type is KVM_S390_SIGP_STOP and a stop irq is already pending
- type is KVM_S390_INT_EXTERNAL_CALL and an external call interrupt
- is already pending
-
-Allows to inject an interrupt to the guest.
-
-Using struct kvm_s390_irq as a parameter allows
-to inject additional payload which is not
-possible via KVM_S390_INTERRUPT.
-
-Interrupt parameters are passed via kvm_s390_irq:
-
-struct kvm_s390_irq {
- __u64 type;
- union {
- struct kvm_s390_io_info io;
- struct kvm_s390_ext_info ext;
- struct kvm_s390_pgm_info pgm;
- struct kvm_s390_emerg_info emerg;
- struct kvm_s390_extcall_info extcall;
- struct kvm_s390_prefix_info prefix;
- struct kvm_s390_stop_info stop;
- struct kvm_s390_mchk_info mchk;
- char reserved[64];
- } u;
-};
-
-type can be one of the following:
-
-KVM_S390_SIGP_STOP - sigp stop; parameter in .stop
-KVM_S390_PROGRAM_INT - program check; parameters in .pgm
-KVM_S390_SIGP_SET_PREFIX - sigp set prefix; parameters in .prefix
-KVM_S390_RESTART - restart; no parameters
-KVM_S390_INT_CLOCK_COMP - clock comparator interrupt; no parameters
-KVM_S390_INT_CPU_TIMER - CPU timer interrupt; no parameters
-KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
-KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
-KVM_S390_MCHK - machine check interrupt; parameters in .mchk
-
-This is an asynchronous vcpu ioctl and can be invoked from any thread.
-
-4.94 KVM_S390_GET_IRQ_STATE
-
-Capability: KVM_CAP_S390_IRQ_STATE
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_irq_state (out)
-Returns: >= number of bytes copied into buffer,
- -EINVAL if buffer size is 0,
- -ENOBUFS if buffer size is too small to fit all pending interrupts,
- -EFAULT if the buffer address was invalid
-
-This ioctl allows userspace to retrieve the complete state of all currently
-pending interrupts in a single buffer. Use cases include migration
-and introspection. The parameter structure contains the address of a
-userspace buffer and its length:
-
-struct kvm_s390_irq_state {
- __u64 buf;
- __u32 flags; /* will stay unused for compatibility reasons */
- __u32 len;
- __u32 reserved[4]; /* will stay unused for compatibility reasons */
-};
-
-Userspace passes in the above struct and for each pending interrupt a
-struct kvm_s390_irq is copied to the provided buffer.
-
-The structure contains a flags and a reserved field for future extensions. As
-the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and
-reserved, these fields can not be used in the future without breaking
-compatibility.
-
-If -ENOBUFS is returned the buffer provided was too small and userspace
-may retry with a bigger buffer.
-
-4.95 KVM_S390_SET_IRQ_STATE
-
-Capability: KVM_CAP_S390_IRQ_STATE
-Architectures: s390
-Type: vcpu ioctl
-Parameters: struct kvm_s390_irq_state (in)
-Returns: 0 on success,
- -EFAULT if the buffer address was invalid,
- -EINVAL for an invalid buffer length (see below),
- -EBUSY if there were already interrupts pending,
- errors occurring when actually injecting the
- interrupt. See KVM_S390_IRQ.
-
-This ioctl allows userspace to set the complete state of all cpu-local
-interrupts currently pending for the vcpu. It is intended for restoring
-interrupt state after a migration. The input parameter is a userspace buffer
-containing a struct kvm_s390_irq_state:
-
-struct kvm_s390_irq_state {
- __u64 buf;
- __u32 flags; /* will stay unused for compatibility reasons */
- __u32 len;
- __u32 reserved[4]; /* will stay unused for compatibility reasons */
-};
-
-The restrictions for flags and reserved apply as well.
-(see KVM_S390_GET_IRQ_STATE)
-
-The userspace memory referenced by buf contains a struct kvm_s390_irq
-for each interrupt to be injected into the guest.
-If one of the interrupts could not be injected for some reason the
-ioctl aborts.
-
-len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
-and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
-which is the maximum number of possibly pending cpu-local interrupts.
-
-4.96 KVM_SMI
-
-Capability: KVM_CAP_X86_SMM
-Architectures: x86
-Type: vcpu ioctl
-Parameters: none
-Returns: 0 on success, -1 on error
-
-Queues an SMI on the thread's vcpu.
-
-4.97 KVM_CAP_PPC_MULTITCE
-
-Capability: KVM_CAP_PPC_MULTITCE
-Architectures: ppc
-Type: vm
-
-This capability means the kernel is capable of handling hypercalls
-H_PUT_TCE_INDIRECT and H_STUFF_TCE without passing those into the user
-space. This significantly accelerates DMA operations for PPC KVM guests.
-User space should expect that its handlers for these hypercalls
-are not going to be called if user space previously registered LIOBN
-in KVM (via KVM_CREATE_SPAPR_TCE or similar calls).
-
-In order to enable H_PUT_TCE_INDIRECT and H_STUFF_TCE use in the guest,
-user space might have to advertise it for the guest. For example,
-IBM pSeries (sPAPR) guest starts using them if "hcall-multi-tce" is
-present in the "ibm,hypertas-functions" device-tree property.
-
-The hypercalls mentioned above may or may not be processed successfully
-in the kernel based fast path. If they can not be handled by the kernel,
-they will get passed on to user space. So user space still has to have
-an implementation for these despite the in kernel acceleration.
-
-This capability is always enabled.
-
-4.98 KVM_CREATE_SPAPR_TCE_64
-
-Capability: KVM_CAP_SPAPR_TCE_64
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_create_spapr_tce_64 (in)
-Returns: file descriptor for manipulating the created TCE table
-
-This is an extension for KVM_CAP_SPAPR_TCE which only supports 32bit
-windows, described in 4.62 KVM_CREATE_SPAPR_TCE
-
-This capability uses extended struct in ioctl interface:
-
-/* for KVM_CAP_SPAPR_TCE_64 */
-struct kvm_create_spapr_tce_64 {
- __u64 liobn;
- __u32 page_shift;
- __u32 flags;
- __u64 offset; /* in pages */
- __u64 size; /* in pages */
-};
-
-The aim of extension is to support an additional bigger DMA window with
-a variable page size.
-KVM_CREATE_SPAPR_TCE_64 receives a 64bit window size, an IOMMU page shift and
-a bus offset of the corresponding DMA window, @size and @offset are numbers
-of IOMMU pages.
-
-@flags are not used at the moment.
-
-The rest of functionality is identical to KVM_CREATE_SPAPR_TCE.
-
-4.99 KVM_REINJECT_CONTROL
-
-Capability: KVM_CAP_REINJECT_CONTROL
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_reinject_control (in)
-Returns: 0 on success,
- -EFAULT if struct kvm_reinject_control cannot be read,
- -ENXIO if KVM_CREATE_PIT or KVM_CREATE_PIT2 didn't succeed earlier.
-
-i8254 (PIT) has two modes, reinject and !reinject. The default is reinject,
-where KVM queues elapsed i8254 ticks and monitors completion of interrupt from
-vector(s) that i8254 injects. Reinject mode dequeues a tick and injects its
-interrupt whenever there isn't a pending interrupt from i8254.
-!reinject mode injects an interrupt as soon as a tick arrives.
-
-struct kvm_reinject_control {
- __u8 pit_reinject;
- __u8 reserved[31];
-};
-
-pit_reinject = 0 (!reinject mode) is recommended, unless running an old
-operating system that uses the PIT for timing (e.g. Linux 2.4.x).
-
-4.100 KVM_PPC_CONFIGURE_V3_MMU
-
-Capability: KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_ppc_mmuv3_cfg (in)
-Returns: 0 on success,
- -EFAULT if struct kvm_ppc_mmuv3_cfg cannot be read,
- -EINVAL if the configuration is invalid
-
-This ioctl controls whether the guest will use radix or HPT (hashed
-page table) translation, and sets the pointer to the process table for
-the guest.
-
-struct kvm_ppc_mmuv3_cfg {
- __u64 flags;
- __u64 process_table;
-};
-
-There are two bits that can be set in flags; KVM_PPC_MMUV3_RADIX and
-KVM_PPC_MMUV3_GTSE. KVM_PPC_MMUV3_RADIX, if set, configures the guest
-to use radix tree translation, and if clear, to use HPT translation.
-KVM_PPC_MMUV3_GTSE, if set and if KVM permits it, configures the guest
-to be able to use the global TLB and SLB invalidation instructions;
-if clear, the guest may not use these instructions.
-
-The process_table field specifies the address and size of the guest
-process table, which is in the guest's space. This field is formatted
-as the second doubleword of the partition table entry, as defined in
-the Power ISA V3.00, Book III section 5.7.6.1.
-
-4.101 KVM_PPC_GET_RMMU_INFO
-
-Capability: KVM_CAP_PPC_RADIX_MMU
-Architectures: ppc
-Type: vm ioctl
-Parameters: struct kvm_ppc_rmmu_info (out)
-Returns: 0 on success,
- -EFAULT if struct kvm_ppc_rmmu_info cannot be written,
- -EINVAL if no useful information can be returned
-
-This ioctl returns a structure containing two things: (a) a list
-containing supported radix tree geometries, and (b) a list that maps
-page sizes to put in the "AP" (actual page size) field for the tlbie
-(TLB invalidate entry) instruction.
-
-struct kvm_ppc_rmmu_info {
- struct kvm_ppc_radix_geom {
- __u8 page_shift;
- __u8 level_bits[4];
- __u8 pad[3];
- } geometries[8];
- __u32 ap_encodings[8];
-};
-
-The geometries[] field gives up to 8 supported geometries for the
-radix page table, in terms of the log base 2 of the smallest page
-size, and the number of bits indexed at each level of the tree, from
-the PTE level up to the PGD level in that order. Any unused entries
-will have 0 in the page_shift field.
-
-The ap_encodings gives the supported page sizes and their AP field
-encodings, encoded with the AP value in the top 3 bits and the log
-base 2 of the page size in the bottom 6 bits.
-
-4.102 KVM_PPC_RESIZE_HPT_PREPARE
-
-Capability: KVM_CAP_SPAPR_RESIZE_HPT
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_ppc_resize_hpt (in)
-Returns: 0 on successful completion,
- >0 if a new HPT is being prepared, the value is an estimated
- number of milliseconds until preparation is complete
- -EFAULT if struct kvm_reinject_control cannot be read,
- -EINVAL if the supplied shift or flags are invalid
- -ENOMEM if unable to allocate the new HPT
- -ENOSPC if there was a hash collision when moving existing
- HPT entries to the new HPT
- -EIO on other error conditions
-
-Used to implement the PAPR extension for runtime resizing of a guest's
-Hashed Page Table (HPT). Specifically this starts, stops or monitors
-the preparation of a new potential HPT for the guest, essentially
-implementing the H_RESIZE_HPT_PREPARE hypercall.
-
-If called with shift > 0 when there is no pending HPT for the guest,
-this begins preparation of a new pending HPT of size 2^(shift) bytes.
-It then returns a positive integer with the estimated number of
-milliseconds until preparation is complete.
-
-If called when there is a pending HPT whose size does not match that
-requested in the parameters, discards the existing pending HPT and
-creates a new one as above.
-
-If called when there is a pending HPT of the size requested, will:
- * If preparation of the pending HPT is already complete, return 0
- * If preparation of the pending HPT has failed, return an error
- code, then discard the pending HPT.
- * If preparation of the pending HPT is still in progress, return an
- estimated number of milliseconds until preparation is complete.
-
-If called with shift == 0, discards any currently pending HPT and
-returns 0 (i.e. cancels any in-progress preparation).
-
-flags is reserved for future expansion, currently setting any bits in
-flags will result in an -EINVAL.
-
-Normally this will be called repeatedly with the same parameters until
-it returns <= 0. The first call will initiate preparation, subsequent
-ones will monitor preparation until it completes or fails.
-
-struct kvm_ppc_resize_hpt {
- __u64 flags;
- __u32 shift;
- __u32 pad;
-};
-
-4.103 KVM_PPC_RESIZE_HPT_COMMIT
-
-Capability: KVM_CAP_SPAPR_RESIZE_HPT
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_ppc_resize_hpt (in)
-Returns: 0 on successful completion,
- -EFAULT if struct kvm_reinject_control cannot be read,
- -EINVAL if the supplied shift or flags are invalid
- -ENXIO is there is no pending HPT, or the pending HPT doesn't
- have the requested size
- -EBUSY if the pending HPT is not fully prepared
- -ENOSPC if there was a hash collision when moving existing
- HPT entries to the new HPT
- -EIO on other error conditions
-
-Used to implement the PAPR extension for runtime resizing of a guest's
-Hashed Page Table (HPT). Specifically this requests that the guest be
-transferred to working with the new HPT, essentially implementing the
-H_RESIZE_HPT_COMMIT hypercall.
-
-This should only be called after KVM_PPC_RESIZE_HPT_PREPARE has
-returned 0 with the same parameters. In other cases
-KVM_PPC_RESIZE_HPT_COMMIT will return an error (usually -ENXIO or
--EBUSY, though others may be possible if the preparation was started,
-but failed).
-
-This will have undefined effects on the guest if it has not already
-placed itself in a quiescent state where no vcpu will make MMU enabled
-memory accesses.
-
-On succsful completion, the pending HPT will become the guest's active
-HPT and the previous HPT will be discarded.
-
-On failure, the guest will still be operating on its previous HPT.
-
-struct kvm_ppc_resize_hpt {
- __u64 flags;
- __u32 shift;
- __u32 pad;
-};
-
-4.104 KVM_X86_GET_MCE_CAP_SUPPORTED
-
-Capability: KVM_CAP_MCE
-Architectures: x86
-Type: system ioctl
-Parameters: u64 mce_cap (out)
-Returns: 0 on success, -1 on error
-
-Returns supported MCE capabilities. The u64 mce_cap parameter
-has the same format as the MSR_IA32_MCG_CAP register. Supported
-capabilities will have the corresponding bits set.
-
-4.105 KVM_X86_SETUP_MCE
-
-Capability: KVM_CAP_MCE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: u64 mcg_cap (in)
-Returns: 0 on success,
- -EFAULT if u64 mcg_cap cannot be read,
- -EINVAL if the requested number of banks is invalid,
- -EINVAL if requested MCE capability is not supported.
-
-Initializes MCE support for use. The u64 mcg_cap parameter
-has the same format as the MSR_IA32_MCG_CAP register and
-specifies which capabilities should be enabled. The maximum
-supported number of error-reporting banks can be retrieved when
-checking for KVM_CAP_MCE. The supported capabilities can be
-retrieved with KVM_X86_GET_MCE_CAP_SUPPORTED.
-
-4.106 KVM_X86_SET_MCE
-
-Capability: KVM_CAP_MCE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_x86_mce (in)
-Returns: 0 on success,
- -EFAULT if struct kvm_x86_mce cannot be read,
- -EINVAL if the bank number is invalid,
- -EINVAL if VAL bit is not set in status field.
-
-Inject a machine check error (MCE) into the guest. The input
-parameter is:
-
-struct kvm_x86_mce {
- __u64 status;
- __u64 addr;
- __u64 misc;
- __u64 mcg_status;
- __u8 bank;
- __u8 pad1[7];
- __u64 pad2[3];
-};
-
-If the MCE being reported is an uncorrected error, KVM will
-inject it as an MCE exception into the guest. If the guest
-MCG_STATUS register reports that an MCE is in progress, KVM
-causes an KVM_EXIT_SHUTDOWN vmexit.
-
-Otherwise, if the MCE is a corrected error, KVM will just
-store it in the corresponding bank (provided this bank is
-not holding a previously reported uncorrected error).
-
-4.107 KVM_S390_GET_CMMA_BITS
-
-Capability: KVM_CAP_S390_CMMA_MIGRATION
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_cmma_log (in, out)
-Returns: 0 on success, a negative value on error
-
-This ioctl is used to get the values of the CMMA bits on the s390
-architecture. It is meant to be used in two scenarios:
-- During live migration to save the CMMA values. Live migration needs
- to be enabled via the KVM_REQ_START_MIGRATION VM property.
-- To non-destructively peek at the CMMA values, with the flag
- KVM_S390_CMMA_PEEK set.
-
-The ioctl takes parameters via the kvm_s390_cmma_log struct. The desired
-values are written to a buffer whose location is indicated via the "values"
-member in the kvm_s390_cmma_log struct. The values in the input struct are
-also updated as needed.
-Each CMMA value takes up one byte.
-
-struct kvm_s390_cmma_log {
- __u64 start_gfn;
- __u32 count;
- __u32 flags;
- union {
- __u64 remaining;
- __u64 mask;
- };
- __u64 values;
-};
-
-start_gfn is the number of the first guest frame whose CMMA values are
-to be retrieved,
-
-count is the length of the buffer in bytes,
-
-values points to the buffer where the result will be written to.
-
-If count is greater than KVM_S390_SKEYS_MAX, then it is considered to be
-KVM_S390_SKEYS_MAX. KVM_S390_SKEYS_MAX is re-used for consistency with
-other ioctls.
-
-The result is written in the buffer pointed to by the field values, and
-the values of the input parameter are updated as follows.
-
-Depending on the flags, different actions are performed. The only
-supported flag so far is KVM_S390_CMMA_PEEK.
-
-The default behaviour if KVM_S390_CMMA_PEEK is not set is:
-start_gfn will indicate the first page frame whose CMMA bits were dirty.
-It is not necessarily the same as the one passed as input, as clean pages
-are skipped.
-
-count will indicate the number of bytes actually written in the buffer.
-It can (and very often will) be smaller than the input value, since the
-buffer is only filled until 16 bytes of clean values are found (which
-are then not copied in the buffer). Since a CMMA migration block needs
-the base address and the length, for a total of 16 bytes, we will send
-back some clean data if there is some dirty data afterwards, as long as
-the size of the clean data does not exceed the size of the header. This
-allows to minimize the amount of data to be saved or transferred over
-the network at the expense of more roundtrips to userspace. The next
-invocation of the ioctl will skip over all the clean values, saving
-potentially more than just the 16 bytes we found.
-
-If KVM_S390_CMMA_PEEK is set:
-the existing storage attributes are read even when not in migration
-mode, and no other action is performed;
-
-the output start_gfn will be equal to the input start_gfn,
-
-the output count will be equal to the input count, except if the end of
-memory has been reached.
-
-In both cases:
-the field "remaining" will indicate the total number of dirty CMMA values
-still remaining, or 0 if KVM_S390_CMMA_PEEK is set and migration mode is
-not enabled.
-
-mask is unused.
-
-values points to the userspace buffer where the result will be stored.
-
-This ioctl can fail with -ENOMEM if not enough memory can be allocated to
-complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
-KVM_S390_CMMA_PEEK is not set but migration mode was not enabled, with
--EFAULT if the userspace address is invalid or if no page table is
-present for the addresses (e.g. when using hugepages).
-
-4.108 KVM_S390_SET_CMMA_BITS
-
-Capability: KVM_CAP_S390_CMMA_MIGRATION
-Architectures: s390
-Type: vm ioctl
-Parameters: struct kvm_s390_cmma_log (in)
-Returns: 0 on success, a negative value on error
-
-This ioctl is used to set the values of the CMMA bits on the s390
-architecture. It is meant to be used during live migration to restore
-the CMMA values, but there are no restrictions on its use.
-The ioctl takes parameters via the kvm_s390_cmma_values struct.
-Each CMMA value takes up one byte.
-
-struct kvm_s390_cmma_log {
- __u64 start_gfn;
- __u32 count;
- __u32 flags;
- union {
- __u64 remaining;
- __u64 mask;
- };
- __u64 values;
-};
-
-start_gfn indicates the starting guest frame number,
-
-count indicates how many values are to be considered in the buffer,
-
-flags is not used and must be 0.
-
-mask indicates which PGSTE bits are to be considered.
-
-remaining is not used.
-
-values points to the buffer in userspace where to store the values.
-
-This ioctl can fail with -ENOMEM if not enough memory can be allocated to
-complete the task, with -ENXIO if CMMA is not enabled, with -EINVAL if
-the count field is too large (e.g. more than KVM_S390_CMMA_SIZE_MAX) or
-if the flags field was not 0, with -EFAULT if the userspace address is
-invalid, if invalid pages are written to (e.g. after the end of memory)
-or if no page table is present for the addresses (e.g. when using
-hugepages).
-
-4.109 KVM_PPC_GET_CPU_CHAR
-
-Capability: KVM_CAP_PPC_GET_CPU_CHAR
-Architectures: powerpc
-Type: vm ioctl
-Parameters: struct kvm_ppc_cpu_char (out)
-Returns: 0 on successful completion
- -EFAULT if struct kvm_ppc_cpu_char cannot be written
-
-This ioctl gives userspace information about certain characteristics
-of the CPU relating to speculative execution of instructions and
-possible information leakage resulting from speculative execution (see
-CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754). The information is
-returned in struct kvm_ppc_cpu_char, which looks like this:
-
-struct kvm_ppc_cpu_char {
- __u64 character; /* characteristics of the CPU */
- __u64 behaviour; /* recommended software behaviour */
- __u64 character_mask; /* valid bits in character */
- __u64 behaviour_mask; /* valid bits in behaviour */
-};
-
-For extensibility, the character_mask and behaviour_mask fields
-indicate which bits of character and behaviour have been filled in by
-the kernel. If the set of defined bits is extended in future then
-userspace will be able to tell whether it is running on a kernel that
-knows about the new bits.
-
-The character field describes attributes of the CPU which can help
-with preventing inadvertent information disclosure - specifically,
-whether there is an instruction to flash-invalidate the L1 data cache
-(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
-to a mode where entries can only be used by the thread that created
-them, whether the bcctr[l] instruction prevents speculation, and
-whether a speculation barrier instruction (ori 31,31,0) is provided.
-
-The behaviour field describes actions that software should take to
-prevent inadvertent information disclosure, and thus describes which
-vulnerabilities the hardware is subject to; specifically whether the
-L1 data cache should be flushed when returning to user mode from the
-kernel, and whether a speculation barrier should be placed between an
-array bounds check and the array access.
-
-These fields use the same bit definitions as the new
-H_GET_CPU_CHARACTERISTICS hypercall.
-
-4.110 KVM_MEMORY_ENCRYPT_OP
-
-Capability: basic
-Architectures: x86
-Type: system
-Parameters: an opaque platform specific structure (in/out)
-Returns: 0 on success; -1 on error
-
-If the platform supports creating encrypted VMs then this ioctl can be used
-for issuing platform-specific memory encryption commands to manage those
-encrypted VMs.
-
-Currently, this ioctl is used for issuing Secure Encrypted Virtualization
-(SEV) commands on AMD Processors. The SEV commands are defined in
-Documentation/virtual/kvm/amd-memory-encryption.rst.
-
-4.111 KVM_MEMORY_ENCRYPT_REG_REGION
-
-Capability: basic
-Architectures: x86
-Type: system
-Parameters: struct kvm_enc_region (in)
-Returns: 0 on success; -1 on error
-
-This ioctl can be used to register a guest memory region which may
-contain encrypted data (e.g. guest RAM, SMRAM etc).
-
-It is used in the SEV-enabled guest. When encryption is enabled, a guest
-memory region may contain encrypted data. The SEV memory encryption
-engine uses a tweak such that two identical plaintext pages, each at
-different locations will have differing ciphertexts. So swapping or
-moving ciphertext of those pages will not result in plaintext being
-swapped. So relocating (or migrating) physical backing pages for the SEV
-guest will require some additional steps.
-
-Note: The current SEV key management spec does not provide commands to
-swap or migrate (move) ciphertext pages. Hence, for now we pin the guest
-memory region registered with the ioctl.
-
-4.112 KVM_MEMORY_ENCRYPT_UNREG_REGION
-
-Capability: basic
-Architectures: x86
-Type: system
-Parameters: struct kvm_enc_region (in)
-Returns: 0 on success; -1 on error
-
-This ioctl can be used to unregister the guest memory region registered
-with KVM_MEMORY_ENCRYPT_REG_REGION ioctl above.
-
-4.113 KVM_HYPERV_EVENTFD
-
-Capability: KVM_CAP_HYPERV_EVENTFD
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_hyperv_eventfd (in)
-
-This ioctl (un)registers an eventfd to receive notifications from the guest on
-the specified Hyper-V connection id through the SIGNAL_EVENT hypercall, without
-causing a user exit. SIGNAL_EVENT hypercall with non-zero event flag number
-(bits 24-31) still triggers a KVM_EXIT_HYPERV_HCALL user exit.
-
-struct kvm_hyperv_eventfd {
- __u32 conn_id;
- __s32 fd;
- __u32 flags;
- __u32 padding[3];
-};
-
-The conn_id field should fit within 24 bits:
-
-#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff
-
-The acceptable values for the flags field are:
-
-#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0)
-
-Returns: 0 on success,
- -EINVAL if conn_id or flags is outside the allowed range
- -ENOENT on deassign if the conn_id isn't registered
- -EEXIST on assign if the conn_id is already registered
-
-4.114 KVM_GET_NESTED_STATE
-
-Capability: KVM_CAP_NESTED_STATE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_nested_state (in/out)
-Returns: 0 on success, -1 on error
-Errors:
- E2BIG: the total state size exceeds the value of 'size' specified by
- the user; the size required will be written into size.
-
-struct kvm_nested_state {
- __u16 flags;
- __u16 format;
- __u32 size;
-
- union {
- struct kvm_vmx_nested_state_hdr vmx;
- struct kvm_svm_nested_state_hdr svm;
-
- /* Pad the header to 128 bytes. */
- __u8 pad[120];
- } hdr;
-
- union {
- struct kvm_vmx_nested_state_data vmx[0];
- struct kvm_svm_nested_state_data svm[0];
- } data;
-};
-
-#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
-#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
-#define KVM_STATE_NESTED_EVMCS 0x00000004
-
-#define KVM_STATE_NESTED_FORMAT_VMX 0
-#define KVM_STATE_NESTED_FORMAT_SVM 1
-
-#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
-
-#define KVM_STATE_NESTED_VMX_SMM_GUEST_MODE 0x00000001
-#define KVM_STATE_NESTED_VMX_SMM_VMXON 0x00000002
-
-struct kvm_vmx_nested_state_hdr {
- __u64 vmxon_pa;
- __u64 vmcs12_pa;
-
- struct {
- __u16 flags;
- } smm;
-};
-
-struct kvm_vmx_nested_state_data {
- __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
- __u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
-};
-
-This ioctl copies the vcpu's nested virtualization state from the kernel to
-userspace.
-
-The maximum size of the state can be retrieved by passing KVM_CAP_NESTED_STATE
-to the KVM_CHECK_EXTENSION ioctl().
-
-4.115 KVM_SET_NESTED_STATE
-
-Capability: KVM_CAP_NESTED_STATE
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_nested_state (in)
-Returns: 0 on success, -1 on error
-
-This copies the vcpu's kvm_nested_state struct from userspace to the kernel.
-For the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
-
-4.116 KVM_(UN)REGISTER_COALESCED_MMIO
-
-Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
- KVM_CAP_COALESCED_PIO (for coalesced pio)
-Architectures: all
-Type: vm ioctl
-Parameters: struct kvm_coalesced_mmio_zone
-Returns: 0 on success, < 0 on error
-
-Coalesced I/O is a performance optimization that defers hardware
-register write emulation so that userspace exits are avoided. It is
-typically used to reduce the overhead of emulating frequently accessed
-hardware registers.
-
-When a hardware register is configured for coalesced I/O, write accesses
-do not exit to userspace and their value is recorded in a ring buffer
-that is shared between kernel and userspace.
-
-Coalesced I/O is used if one or more write accesses to a hardware
-register can be deferred until a read or a write to another hardware
-register on the same device. This last access will cause a vmexit and
-userspace will process accesses from the ring buffer before emulating
-it. That will avoid exiting to userspace on repeated writes.
-
-Coalesced pio is based on coalesced mmio. There is little difference
-between coalesced mmio and pio except that coalesced pio records accesses
-to I/O ports.
-
-4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
-
-Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
-Architectures: x86, arm, arm64, mips
-Type: vm ioctl
-Parameters: struct kvm_dirty_log (in)
-Returns: 0 on success, -1 on error
-
-/* for KVM_CLEAR_DIRTY_LOG */
-struct kvm_clear_dirty_log {
- __u32 slot;
- __u32 num_pages;
- __u64 first_page;
- union {
- void __user *dirty_bitmap; /* one bit per page */
- __u64 padding;
- };
-};
-
-The ioctl clears the dirty status of pages in a memory slot, according to
-the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
-field. Bit 0 of the bitmap corresponds to page "first_page" in the
-memory slot, and num_pages is the size in bits of the input bitmap.
-first_page must be a multiple of 64; num_pages must also be a multiple of
-64 unless first_page + num_pages is the size of the memory slot. For each
-bit that is set in the input bitmap, the corresponding page is marked "clean"
-in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
-(for example via write-protection, or by clearing the dirty bit in
-a page table entry).
-
-If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 specifies
-the address space for which you want to return the dirty bitmap.
-They must be less than the value that KVM_CHECK_EXTENSION returns for
-the KVM_CAP_MULTI_ADDRESS_SPACE capability.
-
-This ioctl is mostly useful when KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
-is enabled; for more information, see the description of the capability.
-However, it can always be used as long as KVM_CHECK_EXTENSION confirms
-that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present.
-
-4.118 KVM_GET_SUPPORTED_HV_CPUID
-
-Capability: KVM_CAP_HYPERV_CPUID
-Architectures: x86
-Type: vcpu ioctl
-Parameters: struct kvm_cpuid2 (in/out)
-Returns: 0 on success, -1 on error
-
-struct kvm_cpuid2 {
- __u32 nent;
- __u32 padding;
- struct kvm_cpuid_entry2 entries[0];
-};
-
-struct kvm_cpuid_entry2 {
- __u32 function;
- __u32 index;
- __u32 flags;
- __u32 eax;
- __u32 ebx;
- __u32 ecx;
- __u32 edx;
- __u32 padding[3];
-};
-
-This ioctl returns x86 cpuid features leaves related to Hyper-V emulation in
-KVM. Userspace can use the information returned by this ioctl to construct
-cpuid information presented to guests consuming Hyper-V enlightenments (e.g.
-Windows or Hyper-V guests).
-
-CPUID feature leaves returned by this ioctl are defined by Hyper-V Top Level
-Functional Specification (TLFS). These leaves can't be obtained with
-KVM_GET_SUPPORTED_CPUID ioctl because some of them intersect with KVM feature
-leaves (0x40000000, 0x40000001).
-
-Currently, the following list of CPUID leaves are returned:
- HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS
- HYPERV_CPUID_INTERFACE
- HYPERV_CPUID_VERSION
- HYPERV_CPUID_FEATURES
- HYPERV_CPUID_ENLIGHTMENT_INFO
- HYPERV_CPUID_IMPLEMENT_LIMITS
- HYPERV_CPUID_NESTED_FEATURES
-
-HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
-enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
-
-Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
-with the 'nent' field indicating the number of entries in the variable-size
-array 'entries'. If the number of entries is too low to describe all Hyper-V
-feature leaves, an error (E2BIG) is returned. If the number is more or equal
-to the number of Hyper-V feature leaves, the 'nent' field is adjusted to the
-number of valid entries in the 'entries' array, which is then filled.
-
-'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
-userspace should not expect to get any particular value there.
-
-4.119 KVM_ARM_VCPU_FINALIZE
-
-Architectures: arm, arm64
-Type: vcpu ioctl
-Parameters: int feature (in)
-Returns: 0 on success, -1 on error
-Errors:
- EPERM: feature not enabled, needs configuration, or already finalized
- EINVAL: feature unknown or not present
-
-Recognised values for feature:
- arm64 KVM_ARM_VCPU_SVE (requires KVM_CAP_ARM_SVE)
-
-Finalizes the configuration of the specified vcpu feature.
-
-The vcpu must already have been initialised, enabling the affected feature, by
-means of a successful KVM_ARM_VCPU_INIT call with the appropriate flag set in
-features[].
-
-For affected vcpu features, this is a mandatory step that must be performed
-before the vcpu is fully usable.
-
-Between KVM_ARM_VCPU_INIT and KVM_ARM_VCPU_FINALIZE, the feature may be
-configured by use of ioctls such as KVM_SET_ONE_REG. The exact configuration
-that should be performaned and how to do it are feature-dependent.
-
-Other calls that depend on a particular feature being finalized, such as
-KVM_RUN, KVM_GET_REG_LIST, KVM_GET_ONE_REG and KVM_SET_ONE_REG, will fail with
--EPERM unless the feature has already been finalized by means of a
-KVM_ARM_VCPU_FINALIZE call.
-
-See KVM_ARM_VCPU_INIT for details of vcpu features that require finalization
-using this ioctl.
-
-4.120 KVM_SET_PMU_EVENT_FILTER
-
-Capability: KVM_CAP_PMU_EVENT_FILTER
-Architectures: x86
-Type: vm ioctl
-Parameters: struct kvm_pmu_event_filter (in)
-Returns: 0 on success, -1 on error
-
-struct kvm_pmu_event_filter {
- __u32 action;
- __u32 nevents;
- __u32 fixed_counter_bitmap;
- __u32 flags;
- __u32 pad[4];
- __u64 events[0];
-};
-
-This ioctl restricts the set of PMU events that the guest can program.
-The argument holds a list of events which will be allowed or denied.
-The eventsel+umask of each event the guest attempts to program is compared
-against the events field to determine whether the guest should have access.
-The events field only controls general purpose counters; fixed purpose
-counters are controlled by the fixed_counter_bitmap.
-
-No flags are defined yet, the field must be zero.
-
-Valid values for 'action':
-#define KVM_PMU_EVENT_ALLOW 0
-#define KVM_PMU_EVENT_DENY 1
-
-
-5. The kvm_run structure
-------------------------
-
-Application code obtains a pointer to the kvm_run structure by
-mmap()ing a vcpu fd. From that point, application code can control
-execution by changing fields in kvm_run prior to calling the KVM_RUN
-ioctl, and obtain information about the reason KVM_RUN returned by
-looking up structure members.
-
-struct kvm_run {
- /* in */
- __u8 request_interrupt_window;
-
-Request that KVM_RUN return when it becomes possible to inject external
-interrupts into the guest. Useful in conjunction with KVM_INTERRUPT.
-
- __u8 immediate_exit;
-
-This field is polled once when KVM_RUN starts; if non-zero, KVM_RUN
-exits immediately, returning -EINTR. In the common scenario where a
-signal is used to "kick" a VCPU out of KVM_RUN, this field can be used
-to avoid usage of KVM_SET_SIGNAL_MASK, which has worse scalability.
-Rather than blocking the signal outside KVM_RUN, userspace can set up
-a signal handler that sets run->immediate_exit to a non-zero value.
-
-This field is ignored if KVM_CAP_IMMEDIATE_EXIT is not available.
-
- __u8 padding1[6];
-
- /* out */
- __u32 exit_reason;
-
-When KVM_RUN has returned successfully (return value 0), this informs
-application code why KVM_RUN has returned. Allowable values for this
-field are detailed below.
-
- __u8 ready_for_interrupt_injection;
-
-If request_interrupt_window has been specified, this field indicates
-an interrupt can be injected now with KVM_INTERRUPT.
-
- __u8 if_flag;
-
-The value of the current interrupt flag. Only valid if in-kernel
-local APIC is not used.
-
- __u16 flags;
-
-More architecture-specific flags detailing state of the VCPU that may
-affect the device's behavior. The only currently defined flag is
-KVM_RUN_X86_SMM, which is valid on x86 machines and is set if the
-VCPU is in system management mode.
-
- /* in (pre_kvm_run), out (post_kvm_run) */
- __u64 cr8;
-
-The value of the cr8 register. Only valid if in-kernel local APIC is
-not used. Both input and output.
-
- __u64 apic_base;
-
-The value of the APIC BASE msr. Only valid if in-kernel local
-APIC is not used. Both input and output.
-
- union {
- /* KVM_EXIT_UNKNOWN */
- struct {
- __u64 hardware_exit_reason;
- } hw;
-
-If exit_reason is KVM_EXIT_UNKNOWN, the vcpu has exited due to unknown
-reasons. Further architecture-specific information is available in
-hardware_exit_reason.
-
- /* KVM_EXIT_FAIL_ENTRY */
- struct {
- __u64 hardware_entry_failure_reason;
- } fail_entry;
-
-If exit_reason is KVM_EXIT_FAIL_ENTRY, the vcpu could not be run due
-to unknown reasons. Further architecture-specific information is
-available in hardware_entry_failure_reason.
-
- /* KVM_EXIT_EXCEPTION */
- struct {
- __u32 exception;
- __u32 error_code;
- } ex;
-
-Unused.
-
- /* KVM_EXIT_IO */
- struct {
-#define KVM_EXIT_IO_IN 0
-#define KVM_EXIT_IO_OUT 1
- __u8 direction;
- __u8 size; /* bytes */
- __u16 port;
- __u32 count;
- __u64 data_offset; /* relative to kvm_run start */
- } io;
-
-If exit_reason is KVM_EXIT_IO, then the vcpu has
-executed a port I/O instruction which could not be satisfied by kvm.
-data_offset describes where the data is located (KVM_EXIT_IO_OUT) or
-where kvm expects application code to place the data for the next
-KVM_RUN invocation (KVM_EXIT_IO_IN). Data format is a packed array.
-
- /* KVM_EXIT_DEBUG */
- struct {
- struct kvm_debug_exit_arch arch;
- } debug;
-
-If the exit_reason is KVM_EXIT_DEBUG, then a vcpu is processing a debug event
-for which architecture specific information is returned.
-
- /* KVM_EXIT_MMIO */
- struct {
- __u64 phys_addr;
- __u8 data[8];
- __u32 len;
- __u8 is_write;
- } mmio;
-
-If exit_reason is KVM_EXIT_MMIO, then the vcpu has
-executed a memory-mapped I/O instruction which could not be satisfied
-by kvm. The 'data' member contains the written data if 'is_write' is
-true, and should be filled by application code otherwise.
-
-The 'data' member contains, in its first 'len' bytes, the value as it would
-appear if the VCPU performed a load or store of the appropriate width directly
-to the byte array.
-
-NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
- KVM_EXIT_EPR the corresponding
-operations are complete (and guest state is consistent) only after userspace
-has re-entered the kernel with KVM_RUN. The kernel side will first finish
-incomplete operations and then check for pending signals. Userspace
-can re-enter the guest with an unmasked signal pending to complete
-pending operations.
-
- /* KVM_EXIT_HYPERCALL */
- struct {
- __u64 nr;
- __u64 args[6];
- __u64 ret;
- __u32 longmode;
- __u32 pad;
- } hypercall;
-
-Unused. This was once used for 'hypercall to userspace'. To implement
-such functionality, use KVM_EXIT_IO (x86) or KVM_EXIT_MMIO (all except s390).
-Note KVM_EXIT_IO is significantly faster than KVM_EXIT_MMIO.
-
- /* KVM_EXIT_TPR_ACCESS */
- struct {
- __u64 rip;
- __u32 is_write;
- __u32 pad;
- } tpr_access;
-
-To be documented (KVM_TPR_ACCESS_REPORTING).
-
- /* KVM_EXIT_S390_SIEIC */
- struct {
- __u8 icptcode;
- __u64 mask; /* psw upper half */
- __u64 addr; /* psw lower half */
- __u16 ipa;
- __u32 ipb;
- } s390_sieic;
-
-s390 specific.
-
- /* KVM_EXIT_S390_RESET */
-#define KVM_S390_RESET_POR 1
-#define KVM_S390_RESET_CLEAR 2
-#define KVM_S390_RESET_SUBSYSTEM 4
-#define KVM_S390_RESET_CPU_INIT 8
-#define KVM_S390_RESET_IPL 16
- __u64 s390_reset_flags;
-
-s390 specific.
-
- /* KVM_EXIT_S390_UCONTROL */
- struct {
- __u64 trans_exc_code;
- __u32 pgm_code;
- } s390_ucontrol;
-
-s390 specific. A page fault has occurred for a user controlled virtual
-machine (KVM_VM_S390_UNCONTROL) on it's host page table that cannot be
-resolved by the kernel.
-The program code and the translation exception code that were placed
-in the cpu's lowcore are presented here as defined by the z Architecture
-Principles of Operation Book in the Chapter for Dynamic Address Translation
-(DAT)
-
- /* KVM_EXIT_DCR */
- struct {
- __u32 dcrn;
- __u32 data;
- __u8 is_write;
- } dcr;
-
-Deprecated - was used for 440 KVM.
-
- /* KVM_EXIT_OSI */
- struct {
- __u64 gprs[32];
- } osi;
-
-MOL uses a special hypercall interface it calls 'OSI'. To enable it, we catch
-hypercalls and exit with this exit struct that contains all the guest gprs.
-
-If exit_reason is KVM_EXIT_OSI, then the vcpu has triggered such a hypercall.
-Userspace can now handle the hypercall and when it's done modify the gprs as
-necessary. Upon guest entry all guest GPRs will then be replaced by the values
-in this struct.
-
- /* KVM_EXIT_PAPR_HCALL */
- struct {
- __u64 nr;
- __u64 ret;
- __u64 args[9];
- } papr_hcall;
-
-This is used on 64-bit PowerPC when emulating a pSeries partition,
-e.g. with the 'pseries' machine type in qemu. It occurs when the
-guest does a hypercall using the 'sc 1' instruction. The 'nr' field
-contains the hypercall number (from the guest R3), and 'args' contains
-the arguments (from the guest R4 - R12). Userspace should put the
-return code in 'ret' and any extra returned values in args[].
-The possible hypercalls are defined in the Power Architecture Platform
-Requirements (PAPR) document available from www.power.org (free
-developer registration required to access it).
-
- /* KVM_EXIT_S390_TSCH */
- struct {
- __u16 subchannel_id;
- __u16 subchannel_nr;
- __u32 io_int_parm;
- __u32 io_int_word;
- __u32 ipb;
- __u8 dequeued;
- } s390_tsch;
-
-s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
-and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
-interrupt for the target subchannel has been dequeued and subchannel_id,
-subchannel_nr, io_int_parm and io_int_word contain the parameters for that
-interrupt. ipb is needed for instruction parameter decoding.
-
- /* KVM_EXIT_EPR */
- struct {
- __u32 epr;
- } epr;
-
-On FSL BookE PowerPC chips, the interrupt controller has a fast patch
-interrupt acknowledge path to the core. When the core successfully
-delivers an interrupt, it automatically populates the EPR register with
-the interrupt vector number and acknowledges the interrupt inside
-the interrupt controller.
-
-In case the interrupt controller lives in user space, we need to do
-the interrupt acknowledge cycle through it to fetch the next to be
-delivered interrupt vector using this exit.
-
-It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
-external interrupt has just been delivered into the guest. User space
-should put the acknowledged interrupt vector into the 'epr' field.
-
- /* KVM_EXIT_SYSTEM_EVENT */
- struct {
-#define KVM_SYSTEM_EVENT_SHUTDOWN 1
-#define KVM_SYSTEM_EVENT_RESET 2
-#define KVM_SYSTEM_EVENT_CRASH 3
- __u32 type;
- __u64 flags;
- } system_event;
-
-If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
-a system-level event using some architecture specific mechanism (hypercall
-or some special instruction). In case of ARM/ARM64, this is triggered using
-HVC instruction based PSCI call from the vcpu. The 'type' field describes
-the system-level event type. The 'flags' field describes architecture
-specific flags for the system-level event.
-
-Valid values for 'type' are:
- KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
- VM. Userspace is not obliged to honour this, and if it does honour
- this does not need to destroy the VM synchronously (ie it may call
- KVM_RUN again before shutdown finally occurs).
- KVM_SYSTEM_EVENT_RESET -- the guest has requested a reset of the VM.
- As with SHUTDOWN, userspace can choose to ignore the request, or
- to schedule the reset to occur in the future and may call KVM_RUN again.
- KVM_SYSTEM_EVENT_CRASH -- the guest crash occurred and the guest
- has requested a crash condition maintenance. Userspace can choose
- to ignore the request, or to gather VM memory core dump and/or
- reset/shutdown of the VM.
-
- /* KVM_EXIT_IOAPIC_EOI */
- struct {
- __u8 vector;
- } eoi;
-
-Indicates that the VCPU's in-kernel local APIC received an EOI for a
-level-triggered IOAPIC interrupt. This exit only triggers when the
-IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled);
-the userspace IOAPIC should process the EOI and retrigger the interrupt if
-it is still asserted. Vector is the LAPIC interrupt vector for which the
-EOI was received.
-
- struct kvm_hyperv_exit {
-#define KVM_EXIT_HYPERV_SYNIC 1
-#define KVM_EXIT_HYPERV_HCALL 2
- __u32 type;
- union {
- struct {
- __u32 msr;
- __u64 control;
- __u64 evt_page;
- __u64 msg_page;
- } synic;
- struct {
- __u64 input;
- __u64 result;
- __u64 params[2];
- } hcall;
- } u;
- };
- /* KVM_EXIT_HYPERV */
- struct kvm_hyperv_exit hyperv;
-Indicates that the VCPU exits into userspace to process some tasks
-related to Hyper-V emulation.
-Valid values for 'type' are:
- KVM_EXIT_HYPERV_SYNIC -- synchronously notify user-space about
-Hyper-V SynIC state change. Notification is used to remap SynIC
-event/message pages and to enable/disable SynIC messages/events processing
-in userspace.
-
- /* Fix the size of the union. */
- char padding[256];
- };
-
- /*
- * shared registers between kvm and userspace.
- * kvm_valid_regs specifies the register classes set by the host
- * kvm_dirty_regs specified the register classes dirtied by userspace
- * struct kvm_sync_regs is architecture specific, as well as the
- * bits for kvm_valid_regs and kvm_dirty_regs
- */
- __u64 kvm_valid_regs;
- __u64 kvm_dirty_regs;
- union {
- struct kvm_sync_regs regs;
- char padding[SYNC_REGS_SIZE_BYTES];
- } s;
-
-If KVM_CAP_SYNC_REGS is defined, these fields allow userspace to access
-certain guest registers without having to call SET/GET_*REGS. Thus we can
-avoid some system call overhead if userspace has to handle the exit.
-Userspace can query the validity of the structure by checking
-kvm_valid_regs for specific bits. These bits are architecture specific
-and usually define the validity of a groups of registers. (e.g. one bit
- for general purpose registers)
-
-Please note that the kernel is allowed to use the kvm_run structure as the
-primary storage for certain register types. Therefore, the kernel may use the
-values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
-
-};
-
-
-
-6. Capabilities that can be enabled on vCPUs
---------------------------------------------
-
-There are certain capabilities that change the behavior of the virtual CPU or
-the virtual machine when enabled. To enable them, please see section 4.37.
-Below you can find a list of capabilities and what their effect on the vCPU or
-the virtual machine is when enabling them.
-
-The following information is provided along with the description:
-
- Architectures: which instruction set architectures provide this ioctl.
- x86 includes both i386 and x86_64.
-
- Target: whether this is a per-vcpu or per-vm capability.
-
- Parameters: what parameters are accepted by the capability.
-
- Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
- are not detailed, but errors with specific meanings are.
-
-
-6.1 KVM_CAP_PPC_OSI
-
-Architectures: ppc
-Target: vcpu
-Parameters: none
-Returns: 0 on success; -1 on error
-
-This capability enables interception of OSI hypercalls that otherwise would
-be treated as normal system calls to be injected into the guest. OSI hypercalls
-were invented by Mac-on-Linux to have a standardized communication mechanism
-between the guest and the host.
-
-When this capability is enabled, KVM_EXIT_OSI can occur.
-
-
-6.2 KVM_CAP_PPC_PAPR
-
-Architectures: ppc
-Target: vcpu
-Parameters: none
-Returns: 0 on success; -1 on error
-
-This capability enables interception of PAPR hypercalls. PAPR hypercalls are
-done using the hypercall instruction "sc 1".
-
-It also sets the guest privilege level to "supervisor" mode. Usually the guest
-runs in "hypervisor" privilege mode with a few missing features.
-
-In addition to the above, it changes the semantics of SDR1. In this mode, the
-HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
-HTAB invisible to the guest.
-
-When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
-
-
-6.3 KVM_CAP_SW_TLB
-
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] is the address of a struct kvm_config_tlb
-Returns: 0 on success; -1 on error
-
-struct kvm_config_tlb {
- __u64 params;
- __u64 array;
- __u32 mmu_type;
- __u32 array_len;
-};
-
-Configures the virtual CPU's TLB array, establishing a shared memory area
-between userspace and KVM. The "params" and "array" fields are userspace
-addresses of mmu-type-specific data structures. The "array_len" field is an
-safety mechanism, and should be set to the size in bytes of the memory that
-userspace has reserved for the array. It must be at least the size dictated
-by "mmu_type" and "params".
-
-While KVM_RUN is active, the shared region is under control of KVM. Its
-contents are undefined, and any modification by userspace results in
-boundedly undefined behavior.
-
-On return from KVM_RUN, the shared region will reflect the current state of
-the guest's TLB. If userspace makes any changes, it must call KVM_DIRTY_TLB
-to tell KVM which entries have been changed, prior to calling KVM_RUN again
-on this vcpu.
-
-For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
- - The "params" field is of type "struct kvm_book3e_206_tlb_params".
- - The "array" field points to an array of type "struct
- kvm_book3e_206_tlb_entry".
- - The array consists of all entries in the first TLB, followed by all
- entries in the second TLB.
- - Within a TLB, entries are ordered first by increasing set number. Within a
- set, entries are ordered by way (increasing ESEL).
- - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
- where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
- - The tsize field of mas1 shall be set to 4K on TLB0, even though the
- hardware ignores this value for TLB0.
-
-6.4 KVM_CAP_S390_CSS_SUPPORT
-
-Architectures: s390
-Target: vcpu
-Parameters: none
-Returns: 0 on success; -1 on error
-
-This capability enables support for handling of channel I/O instructions.
-
-TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
-handled in-kernel, while the other I/O instructions are passed to userspace.
-
-When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
-SUBCHANNEL intercepts.
-
-Note that even though this capability is enabled per-vcpu, the complete
-virtual machine is affected.
-
-6.5 KVM_CAP_PPC_EPR
-
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] defines whether the proxy facility is active
-Returns: 0 on success; -1 on error
-
-This capability enables or disables the delivery of interrupts through the
-external proxy facility.
-
-When enabled (args[0] != 0), every time the guest gets an external interrupt
-delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
-to receive the topmost interrupt vector.
-
-When disabled (args[0] == 0), behavior is as if this facility is unsupported.
-
-When this capability is enabled, KVM_EXIT_EPR can occur.
-
-6.6 KVM_CAP_IRQ_MPIC
-
-Architectures: ppc
-Parameters: args[0] is the MPIC device fd
- args[1] is the MPIC CPU number for this vcpu
-
-This capability connects the vcpu to an in-kernel MPIC device.
-
-6.7 KVM_CAP_IRQ_XICS
-
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] is the XICS device fd
- args[1] is the XICS CPU number (server ID) for this vcpu
-
-This capability connects the vcpu to an in-kernel XICS device.
-
-6.8 KVM_CAP_S390_IRQCHIP
-
-Architectures: s390
-Target: vm
-Parameters: none
-
-This capability enables the in-kernel irqchip for s390. Please refer to
-"4.24 KVM_CREATE_IRQCHIP" for details.
-
-6.9 KVM_CAP_MIPS_FPU
-
-Architectures: mips
-Target: vcpu
-Parameters: args[0] is reserved for future use (should be 0).
-
-This capability allows the use of the host Floating Point Unit by the guest. It
-allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is
-done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed
-(depending on the current guest FPU register mode), and the Status.FR,
-Config5.FRE bits are accessible via the KVM API and also from the guest,
-depending on them being supported by the FPU.
-
-6.10 KVM_CAP_MIPS_MSA
-
-Architectures: mips
-Target: vcpu
-Parameters: args[0] is reserved for future use (should be 0).
-
-This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest.
-It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest.
-Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be
-accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from
-the guest.
-
-6.74 KVM_CAP_SYNC_REGS
-Architectures: s390, x86
-Target: s390: always enabled, x86: vcpu
-Parameters: none
-Returns: x86: KVM_CHECK_EXTENSION returns a bit-array indicating which register
-sets are supported (bitfields defined in arch/x86/include/uapi/asm/kvm.h).
-
-As described above in the kvm_sync_regs struct info in section 5 (kvm_run):
-KVM_CAP_SYNC_REGS "allow[s] userspace to access certain guest registers
-without having to call SET/GET_*REGS". This reduces overhead by eliminating
-repeated ioctl calls for setting and/or getting register values. This is
-particularly important when userspace is making synchronous guest state
-modifications, e.g. when emulating and/or intercepting instructions in
-userspace.
-
-For s390 specifics, please refer to the source code.
-
-For x86:
-- the register sets to be copied out to kvm_run are selectable
- by userspace (rather that all sets being copied out for every exit).
-- vcpu_events are available in addition to regs and sregs.
-
-For x86, the 'kvm_valid_regs' field of struct kvm_run is overloaded to
-function as an input bit-array field set by userspace to indicate the
-specific register sets to be copied out on the next exit.
-
-To indicate when userspace has modified values that should be copied into
-the vCPU, the all architecture bitarray field, 'kvm_dirty_regs' must be set.
-This is done using the same bitflags as for the 'kvm_valid_regs' field.
-If the dirty bit is not set, then the register set values will not be copied
-into the vCPU even if they've been modified.
-
-Unused bitfields in the bitarrays must be set to zero.
-
-struct kvm_sync_regs {
- struct kvm_regs regs;
- struct kvm_sregs sregs;
- struct kvm_vcpu_events events;
-};
-
-6.75 KVM_CAP_PPC_IRQ_XIVE
-
-Architectures: ppc
-Target: vcpu
-Parameters: args[0] is the XIVE device fd
- args[1] is the XIVE CPU number (server ID) for this vcpu
-
-This capability connects the vcpu to an in-kernel XIVE device.
-
-7. Capabilities that can be enabled on VMs
-------------------------------------------
-
-There are certain capabilities that change the behavior of the virtual
-machine when enabled. To enable them, please see section 4.37. Below
-you can find a list of capabilities and what their effect on the VM
-is when enabling them.
-
-The following information is provided along with the description:
-
- Architectures: which instruction set architectures provide this ioctl.
- x86 includes both i386 and x86_64.
-
- Parameters: what parameters are accepted by the capability.
-
- Returns: the return value. General error numbers (EBADF, ENOMEM, EINVAL)
- are not detailed, but errors with specific meanings are.
-
-
-7.1 KVM_CAP_PPC_ENABLE_HCALL
-
-Architectures: ppc
-Parameters: args[0] is the sPAPR hcall number
- args[1] is 0 to disable, 1 to enable in-kernel handling
-
-This capability controls whether individual sPAPR hypercalls (hcalls)
-get handled by the kernel or not. Enabling or disabling in-kernel
-handling of an hcall is effective across the VM. On creation, an
-initial set of hcalls are enabled for in-kernel handling, which
-consists of those hcalls for which in-kernel handlers were implemented
-before this capability was implemented. If disabled, the kernel will
-not to attempt to handle the hcall, but will always exit to userspace
-to handle it. Note that it may not make sense to enable some and
-disable others of a group of related hcalls, but KVM does not prevent
-userspace from doing that.
-
-If the hcall number specified is not one that has an in-kernel
-implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
-error.
-
-7.2 KVM_CAP_S390_USER_SIGP
-
-Architectures: s390
-Parameters: none
-
-This capability controls which SIGP orders will be handled completely in user
-space. With this capability enabled, all fast orders will be handled completely
-in the kernel:
-- SENSE
-- SENSE RUNNING
-- EXTERNAL CALL
-- EMERGENCY SIGNAL
-- CONDITIONAL EMERGENCY SIGNAL
-
-All other orders will be handled completely in user space.
-
-Only privileged operation exceptions will be checked for in the kernel (or even
-in the hardware prior to interception). If this capability is not enabled, the
-old way of handling SIGP orders is used (partially in kernel and user space).
-
-7.3 KVM_CAP_S390_VECTOR_REGISTERS
-
-Architectures: s390
-Parameters: none
-Returns: 0 on success, negative value on error
-
-Allows use of the vector registers introduced with z13 processor, and
-provides for the synchronization between host and user space. Will
-return -EINVAL if the machine does not support vectors.
-
-7.4 KVM_CAP_S390_USER_STSI
-
-Architectures: s390
-Parameters: none
-
-This capability allows post-handlers for the STSI instruction. After
-initial handling in the kernel, KVM exits to user space with
-KVM_EXIT_S390_STSI to allow user space to insert further data.
-
-Before exiting to userspace, kvm handlers should fill in s390_stsi field of
-vcpu->run:
-struct {
- __u64 addr;
- __u8 ar;
- __u8 reserved;
- __u8 fc;
- __u8 sel1;
- __u16 sel2;
-} s390_stsi;
-
-@addr - guest address of STSI SYSIB
-@fc - function code
-@sel1 - selector 1
-@sel2 - selector 2
-@ar - access register number
-
-KVM handlers should exit to userspace with rc = -EREMOTE.
-
-7.5 KVM_CAP_SPLIT_IRQCHIP
-
-Architectures: x86
-Parameters: args[0] - number of routes reserved for userspace IOAPICs
-Returns: 0 on success, -1 on error
-
-Create a local apic for each processor in the kernel. This can be used
-instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the
-IOAPIC and PIC (and also the PIT, even though this has to be enabled
-separately).
-
-This capability also enables in kernel routing of interrupt requests;
-when KVM_CAP_SPLIT_IRQCHIP only routes of KVM_IRQ_ROUTING_MSI type are
-used in the IRQ routing table. The first args[0] MSI routes are reserved
-for the IOAPIC pins. Whenever the LAPIC receives an EOI for these routes,
-a KVM_EXIT_IOAPIC_EOI vmexit will be reported to userspace.
-
-Fails if VCPU has already been created, or if the irqchip is already in the
-kernel (i.e. KVM_CREATE_IRQCHIP has already been called).
-
-7.6 KVM_CAP_S390_RI
-
-Architectures: s390
-Parameters: none
-
-Allows use of runtime-instrumentation introduced with zEC12 processor.
-Will return -EINVAL if the machine does not support runtime-instrumentation.
-Will return -EBUSY if a VCPU has already been created.
-
-7.7 KVM_CAP_X2APIC_API
-
-Architectures: x86
-Parameters: args[0] - features that should be enabled
-Returns: 0 on success, -EINVAL when args[0] contains invalid features
-
-Valid feature flags in args[0] are
-
-#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0)
-#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1)
-
-Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
-KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
-allowing the use of 32-bit APIC IDs. See KVM_CAP_X2APIC_API in their
-respective sections.
-
-KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
-in logical mode or with more than 255 VCPUs. Otherwise, KVM treats 0xff
-as a broadcast even in x2APIC mode in order to support physical x2APIC
-without interrupt remapping. This is undesirable in logical mode,
-where 0xff represents CPUs 0-7 in cluster 0.
-
-7.8 KVM_CAP_S390_USER_INSTR0
-
-Architectures: s390
-Parameters: none
-
-With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
-be intercepted and forwarded to user space. User space can use this
-mechanism e.g. to realize 2-byte software breakpoints. The kernel will
-not inject an operating exception for these instructions, user space has
-to take care of that.
-
-This capability can be enabled dynamically even if VCPUs were already
-created and are running.
-
-7.9 KVM_CAP_S390_GS
-
-Architectures: s390
-Parameters: none
-Returns: 0 on success; -EINVAL if the machine does not support
- guarded storage; -EBUSY if a VCPU has already been created.
-
-Allows use of guarded storage for the KVM guest.
-
-7.10 KVM_CAP_S390_AIS
-
-Architectures: s390
-Parameters: none
-
-Allow use of adapter-interruption suppression.
-Returns: 0 on success; -EBUSY if a VCPU has already been created.
-
-7.11 KVM_CAP_PPC_SMT
-
-Architectures: ppc
-Parameters: vsmt_mode, flags
-
-Enabling this capability on a VM provides userspace with a way to set
-the desired virtual SMT mode (i.e. the number of virtual CPUs per
-virtual core). The virtual SMT mode, vsmt_mode, must be a power of 2
-between 1 and 8. On POWER8, vsmt_mode must also be no greater than
-the number of threads per subcore for the host. Currently flags must
-be 0. A successful call to enable this capability will result in
-vsmt_mode being returned when the KVM_CAP_PPC_SMT capability is
-subsequently queried for the VM. This capability is only supported by
-HV KVM, and can only be set before any VCPUs have been created.
-The KVM_CAP_PPC_SMT_POSSIBLE capability indicates which virtual SMT
-modes are available.
-
-7.12 KVM_CAP_PPC_FWNMI
-
-Architectures: ppc
-Parameters: none
-
-With this capability a machine check exception in the guest address
-space will cause KVM to exit the guest with NMI exit reason. This
-enables QEMU to build error log and branch to guest kernel registered
-machine check handling routine. Without this capability KVM will
-branch to guests' 0x200 interrupt vector.
-
-7.13 KVM_CAP_X86_DISABLE_EXITS
-
-Architectures: x86
-Parameters: args[0] defines which exits are disabled
-Returns: 0 on success, -EINVAL when args[0] contains invalid exits
-
-Valid bits in args[0] are
-
-#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0)
-#define KVM_X86_DISABLE_EXITS_HLT (1 << 1)
-#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2)
-#define KVM_X86_DISABLE_EXITS_CSTATE (1 << 3)
-
-Enabling this capability on a VM provides userspace with a way to no
-longer intercept some instructions for improved latency in some
-workloads, and is suggested when vCPUs are associated to dedicated
-physical CPUs. More bits can be added in the future; userspace can
-just pass the KVM_CHECK_EXTENSION result to KVM_ENABLE_CAP to disable
-all such vmexits.
-
-Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
-
-7.14 KVM_CAP_S390_HPAGE_1M
-
-Architectures: s390
-Parameters: none
-Returns: 0 on success, -EINVAL if hpage module parameter was not set
- or cmma is enabled, or the VM has the KVM_VM_S390_UCONTROL
- flag set
-
-With this capability the KVM support for memory backing with 1m pages
-through hugetlbfs can be enabled for a VM. After the capability is
-enabled, cmma can't be enabled anymore and pfmfi and the storage key
-interpretation are disabled. If cmma has already been enabled or the
-hpage module parameter is not set to 1, -EINVAL is returned.
-
-While it is generally possible to create a huge page backed VM without
-this capability, the VM will not be able to run.
-
-7.15 KVM_CAP_MSR_PLATFORM_INFO
-
-Architectures: x86
-Parameters: args[0] whether feature should be enabled or not
-
-With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
-a #GP would be raised when the guest tries to access. Currently, this
-capability does not enable write permissions of this MSR for the guest.
-
-7.16 KVM_CAP_PPC_NESTED_HV
-
-Architectures: ppc
-Parameters: none
-Returns: 0 on success, -EINVAL when the implementation doesn't support
- nested-HV virtualization.
-
-HV-KVM on POWER9 and later systems allows for "nested-HV"
-virtualization, which provides a way for a guest VM to run guests that
-can run using the CPU's supervisor mode (privileged non-hypervisor
-state). Enabling this capability on a VM depends on the CPU having
-the necessary functionality and on the facility being enabled with a
-kvm-hv module parameter.
-
-7.17 KVM_CAP_EXCEPTION_PAYLOAD
-
-Architectures: x86
-Parameters: args[0] whether feature should be enabled or not
-
-With this capability enabled, CR2 will not be modified prior to the
-emulated VM-exit when L1 intercepts a #PF exception that occurs in
-L2. Similarly, for kvm-intel only, DR6 will not be modified prior to
-the emulated VM-exit when L1 intercepts a #DB exception that occurs in
-L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or
-#DB) exception for L2, exception.has_payload will be set and the
-faulting address (or the new DR6 bits*) will be reported in the
-exception_payload field. Similarly, when userspace injects a #PF (or
-#DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set
-exception.has_payload and to put the faulting address (or the new DR6
-bits*) in the exception_payload field.
-
-This capability also enables exception.pending in struct
-kvm_vcpu_events, which allows userspace to distinguish between pending
-and injected exceptions.
-
-
-* For the new DR6 bits, note that bit 16 is set iff the #DB exception
- will clear DR6.RTM.
-
-7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2
-
-Architectures: x86, arm, arm64, mips
-Parameters: args[0] whether feature should be enabled or not
-
-With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
-clear and write-protect all pages that are returned as dirty.
-Rather, userspace will have to do this operation separately using
-KVM_CLEAR_DIRTY_LOG.
-
-At the cost of a slightly more complicated operation, this provides better
-scalability and responsiveness for two reasons. First,
-KVM_CLEAR_DIRTY_LOG ioctl can operate on a 64-page granularity rather
-than requiring to sync a full memslot; this ensures that KVM does not
-take spinlocks for an extended period of time. Second, in some cases a
-large amount of time can pass between a call to KVM_GET_DIRTY_LOG and
-userspace actually using the data in the page. Pages can be modified
-during this time, which is inefficint for both the guest and userspace:
-the guest will incur a higher penalty due to write protection faults,
-while userspace can see false reports of dirty pages. Manual reprotection
-helps reducing this time, improving guest performance and reducing the
-number of dirty log false positives.
-
-KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 was previously available under the name
-KVM_CAP_MANUAL_DIRTY_LOG_PROTECT, but the implementation had bugs that make
-it hard or impossible to use it correctly. The availability of
-KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed.
-Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT.
-
-8. Other capabilities.
-----------------------
-
-This section lists capabilities that give information about other
-features of the KVM implementation.
-
-8.1 KVM_CAP_PPC_HWRNG
-
-Architectures: ppc
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that that the kernel has an implementation of the
-H_RANDOM hypercall backed by a hardware random-number generator.
-If present, the kernel H_RANDOM handler can be enabled for guest use
-with the KVM_CAP_PPC_ENABLE_HCALL capability.
-
-8.2 KVM_CAP_HYPERV_SYNIC
-
-Architectures: x86
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that that the kernel has an implementation of the
-Hyper-V Synthetic interrupt controller(SynIC). Hyper-V SynIC is
-used to support Windows Hyper-V based guest paravirt drivers(VMBus).
-
-In order to use SynIC, it has to be activated by setting this
-capability via KVM_ENABLE_CAP ioctl on the vcpu fd. Note that this
-will disable the use of APIC hardware virtualization even if supported
-by the CPU, as it's incompatible with SynIC auto-EOI behavior.
-
-8.3 KVM_CAP_PPC_RADIX_MMU
-
-Architectures: ppc
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that that the kernel can support guests using the
-radix MMU defined in Power ISA V3.00 (as implemented in the POWER9
-processor).
-
-8.4 KVM_CAP_PPC_HASH_MMU_V3
-
-Architectures: ppc
-
-This capability, if KVM_CHECK_EXTENSION indicates that it is
-available, means that that the kernel can support guests using the
-hashed page table MMU defined in Power ISA V3.00 (as implemented in
-the POWER9 processor), including in-memory segment tables.
-
-8.5 KVM_CAP_MIPS_VZ
-
-Architectures: mips
-
-This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
-it is available, means that full hardware assisted virtualization capabilities
-of the hardware are available for use through KVM. An appropriate
-KVM_VM_MIPS_* type must be passed to KVM_CREATE_VM to create a VM which
-utilises it.
-
-If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
-available, it means that the VM is using full hardware assisted virtualization
-capabilities of the hardware. This is useful to check after creating a VM with
-KVM_VM_MIPS_DEFAULT.
-
-The value returned by KVM_CHECK_EXTENSION should be compared against known
-values (see below). All other values are reserved. This is to allow for the
-possibility of other hardware assisted virtualization implementations which
-may be incompatible with the MIPS VZ ASE.
-
- 0: The trap & emulate implementation is in use to run guest code in user
- mode. Guest virtual memory segments are rearranged to fit the guest in the
- user mode address space.
-
- 1: The MIPS VZ ASE is in use, providing full hardware assisted
- virtualization, including standard guest virtual memory segments.
-
-8.6 KVM_CAP_MIPS_TE
-
-Architectures: mips
-
-This capability, if KVM_CHECK_EXTENSION on the main kvm handle indicates that
-it is available, means that the trap & emulate implementation is available to
-run guest code in user mode, even if KVM_CAP_MIPS_VZ indicates that hardware
-assisted virtualisation is also available. KVM_VM_MIPS_TE (0) must be passed
-to KVM_CREATE_VM to create a VM which utilises it.
-
-If KVM_CHECK_EXTENSION on a kvm VM handle indicates that this capability is
-available, it means that the VM is using trap & emulate.
-
-8.7 KVM_CAP_MIPS_64BIT
-
-Architectures: mips
-
-This capability indicates the supported architecture type of the guest, i.e. the
-supported register and address width.
-
-The values returned when this capability is checked by KVM_CHECK_EXTENSION on a
-kvm VM handle correspond roughly to the CP0_Config.AT register field, and should
-be checked specifically against known values (see below). All other values are
-reserved.
-
- 0: MIPS32 or microMIPS32.
- Both registers and addresses are 32-bits wide.
- It will only be possible to run 32-bit guest code.
-
- 1: MIPS64 or microMIPS64 with access only to 32-bit compatibility segments.
- Registers are 64-bits wide, but addresses are 32-bits wide.
- 64-bit guest code may run but cannot access MIPS64 memory segments.
- It will also be possible to run 32-bit guest code.
-
- 2: MIPS64 or microMIPS64 with access to all address segments.
- Both registers and addresses are 64-bits wide.
- It will be possible to run 64-bit or 32-bit guest code.
-
-8.9 KVM_CAP_ARM_USER_IRQ
-
-Architectures: arm, arm64
-This capability, if KVM_CHECK_EXTENSION indicates that it is available, means
-that if userspace creates a VM without an in-kernel interrupt controller, it
-will be notified of changes to the output level of in-kernel emulated devices,
-which can generate virtual interrupts, presented to the VM.
-For such VMs, on every return to userspace, the kernel
-updates the vcpu's run->s.regs.device_irq_level field to represent the actual
-output level of the device.
-
-Whenever kvm detects a change in the device output level, kvm guarantees at
-least one return to userspace before running the VM. This exit could either
-be a KVM_EXIT_INTR or any other exit event, like KVM_EXIT_MMIO. This way,
-userspace can always sample the device output level and re-compute the state of
-the userspace interrupt controller. Userspace should always check the state
-of run->s.regs.device_irq_level on every kvm exit.
-The value in run->s.regs.device_irq_level can represent both level and edge
-triggered interrupt signals, depending on the device. Edge triggered interrupt
-signals will exit to userspace with the bit in run->s.regs.device_irq_level
-set exactly once per edge signal.
-
-The field run->s.regs.device_irq_level is available independent of
-run->kvm_valid_regs or run->kvm_dirty_regs bits.
-
-If KVM_CAP_ARM_USER_IRQ is supported, the KVM_CHECK_EXTENSION ioctl returns a
-number larger than 0 indicating the version of this capability is implemented
-and thereby which bits in in run->s.regs.device_irq_level can signal values.
-
-Currently the following bits are defined for the device_irq_level bitmap:
-
- KVM_CAP_ARM_USER_IRQ >= 1:
-
- KVM_ARM_DEV_EL1_VTIMER - EL1 virtual timer
- KVM_ARM_DEV_EL1_PTIMER - EL1 physical timer
- KVM_ARM_DEV_PMU - ARM PMU overflow interrupt signal
-
-Future versions of kvm may implement additional events. These will get
-indicated by returning a higher number from KVM_CHECK_EXTENSION and will be
-listed above.
-
-8.10 KVM_CAP_PPC_SMT_POSSIBLE
-
-Architectures: ppc
-
-Querying this capability returns a bitmap indicating the possible
-virtual SMT modes that can be set using KVM_CAP_PPC_SMT. If bit N
-(counting from the right) is set, then a virtual SMT mode of 2^N is
-available.
-
-8.11 KVM_CAP_HYPERV_SYNIC2
-
-Architectures: x86
-
-This capability enables a newer version of Hyper-V Synthetic interrupt
-controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
-doesn't clear SynIC message and event flags pages when they are enabled by
-writing to the respective MSRs.
-
-8.12 KVM_CAP_HYPERV_VP_INDEX
-
-Architectures: x86
-
-This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its
-value is used to denote the target vcpu for a SynIC interrupt. For
-compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this
-capability is absent, userspace can still query this msr's value.
-
-8.13 KVM_CAP_S390_AIS_MIGRATION
-
-Architectures: s390
-Parameters: none
-
-This capability indicates if the flic device will be able to get/set the
-AIS states for migration via the KVM_DEV_FLIC_AISM_ALL attribute and allows
-to discover this without having to create a flic device.
-
-8.14 KVM_CAP_S390_PSW
-
-Architectures: s390
-
-This capability indicates that the PSW is exposed via the kvm_run structure.
-
-8.15 KVM_CAP_S390_GMAP
-
-Architectures: s390
-
-This capability indicates that the user space memory used as guest mapping can
-be anywhere in the user memory address space, as long as the memory slots are
-aligned and sized to a segment (1MB) boundary.
-
-8.16 KVM_CAP_S390_COW
-
-Architectures: s390
-
-This capability indicates that the user space memory used as guest mapping can
-use copy-on-write semantics as well as dirty pages tracking via read-only page
-tables.
-
-8.17 KVM_CAP_S390_BPB
-
-Architectures: s390
-
-This capability indicates that kvm will implement the interfaces to handle
-reset, migration and nested KVM for branch prediction blocking. The stfle
-facility 82 should not be provided to the guest without this capability.
-
-8.18 KVM_CAP_HYPERV_TLBFLUSH
-
-Architectures: x86
-
-This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush
-hypercalls:
-HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx,
-HvFlushVirtualAddressList, HvFlushVirtualAddressListEx.
-
-8.19 KVM_CAP_ARM_INJECT_SERROR_ESR
-
-Architectures: arm, arm64
-
-This capability indicates that userspace can specify (via the
-KVM_SET_VCPU_EVENTS ioctl) the syndrome value reported to the guest when it
-takes a virtual SError interrupt exception.
-If KVM advertises this capability, userspace can only specify the ISS field for
-the ESR syndrome. Other parts of the ESR, such as the EC are generated by the
-CPU when the exception is taken. If this virtual SError is taken to EL1 using
-AArch64, this value will be reported in the ISS field of ESR_ELx.
-
-See KVM_CAP_VCPU_EVENTS for more details.
-8.20 KVM_CAP_HYPERV_SEND_IPI
-
-Architectures: x86
-
-This capability indicates that KVM supports paravirtualized Hyper-V IPI send
-hypercalls:
-HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
+++ /dev/null
-* Internal ABI between the kernel and HYP
-
-This file documents the interaction between the Linux kernel and the
-hypervisor layer when running Linux as a hypervisor (for example
-KVM). It doesn't cover the interaction of the kernel with the
-hypervisor when running as a guest (under Xen, KVM or any other
-hypervisor), or any hypervisor-specific interaction when the kernel is
-used as a host.
-
-On arm and arm64 (without VHE), the kernel doesn't run in hypervisor
-mode, but still needs to interact with it, allowing a built-in
-hypervisor to be either installed or torn down.
-
-In order to achieve this, the kernel must be booted at HYP (arm) or
-EL2 (arm64), allowing it to install a set of stubs before dropping to
-SVC/EL1. These stubs are accessible by using a 'hvc #0' instruction,
-and only act on individual CPUs.
-
-Unless specified otherwise, any built-in hypervisor must implement
-these functions (see arch/arm{,64}/include/asm/virt.h):
-
-* r0/x0 = HVC_SET_VECTORS
- r1/x1 = vectors
-
- Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors'
- must be a physical address, and respect the alignment requirements
- of the architecture. Only implemented by the initial stubs, not by
- Linux hypervisors.
-
-* r0/x0 = HVC_RESET_VECTORS
-
- Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials
- stubs' exception vector value. This effectively disables an existing
- hypervisor.
-
-* r0/x0 = HVC_SOFT_RESTART
- r1/x1 = restart address
- x2 = x0's value when entering the next payload (arm64)
- x3 = x1's value when entering the next payload (arm64)
- x4 = x2's value when entering the next payload (arm64)
-
- Mask all exceptions, disable the MMU, move the arguments into place
- (arm64 only), and jump to the restart address while at HYP/EL2. This
- hypercall is not expected to return to its caller.
-
-Any other value of r0/x0 triggers a hypervisor-specific handling,
-which is not documented here.
-
-The return value of a stub hypercall is held by r0/x0, and is 0 on
-success, and HVC_STUB_ERR on error. A stub hypercall is allowed to
-clobber any of the caller-saved registers (x0-x18 on arm64, r0-r3 and
-ip on arm). It is thus recommended to use a function call to perform
-the hypercall.
+++ /dev/null
-KVM implements the PSCI (Power State Coordination Interface)
-specification in order to provide services such as CPU on/off, reset
-and power-off to the guest.
-
-The PSCI specification is regularly updated to provide new features,
-and KVM implements these updates if they make sense from a virtualization
-point of view.
-
-This means that a guest booted on two different versions of KVM can
-observe two different "firmware" revisions. This could cause issues if
-a given guest is tied to a particular PSCI revision (unlikely), or if
-a migration causes a different PSCI version to be exposed out of the
-blue to an unsuspecting guest.
-
-In order to remedy this situation, KVM exposes a set of "firmware
-pseudo-registers" that can be manipulated using the GET/SET_ONE_REG
-interface. These registers can be saved/restored by userspace, and set
-to a convenient value if required.
-
-The following register is defined:
-
-* KVM_REG_ARM_PSCI_VERSION:
-
- - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set
- (and thus has already been initialized)
- - Returns the current PSCI version on GET_ONE_REG (defaulting to the
- highest PSCI version implemented by KVM and compatible with v0.2)
- - Allows any PSCI version implemented by KVM and compatible with
- v0.2 to be set with SET_ONE_REG
- - Affects the whole VM (even if the register view is per-vcpu)
-
-* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
- Holds the state of the firmware support to mitigate CVE-2017-5715, as
- offered by KVM to the guest via a HVC call. The workaround is described
- under SMCCC_ARCH_WORKAROUND_1 in [1].
- Accepted values are:
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL: KVM does not offer
- firmware support for the workaround. The mitigation status for the
- guest is unknown.
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL: The workaround HVC call is
- available to the guest and required for the mitigation.
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED: The workaround HVC call
- is available to the guest, but it is not needed on this VCPU.
-
-* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
- Holds the state of the firmware support to mitigate CVE-2018-3639, as
- offered by KVM to the guest via a HVC call. The workaround is described
- under SMCCC_ARCH_WORKAROUND_2 in [1].
- Accepted values are:
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: A workaround is not
- available. KVM does not offer firmware support for the workaround.
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: The workaround state is
- unknown. KVM does not offer firmware support for the workaround.
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: The workaround is available,
- and can be disabled by a vCPU. If
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED is set, it is active for
- this vCPU.
- KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: The workaround is
- always active on this vCPU or it is not needed.
-
-[1] https://developer.arm.com/-/media/developer/pdf/ARM_DEN_0070A_Firmware_interfaces_for_mitigating_CVE-2017-5715.pdf
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-
-==============
-KVM CPUID bits
-==============
-
-:Author: Glauber Costa <glommer@gmail.com>
-
-A guest running on a kvm host, can check some of its features using
-cpuid. This is not always guaranteed to work, since userspace can
-mask-out some, or even all KVM-related cpuid features before launching
-a guest.
-
-KVM cpuid functions are:
-
-function: KVM_CPUID_SIGNATURE (0x40000000)
-
-returns::
-
- eax = 0x40000001
- ebx = 0x4b4d564b
- ecx = 0x564b4d56
- edx = 0x4d
-
-Note that this value in ebx, ecx and edx corresponds to the string "KVMKVMKVM".
-The value in eax corresponds to the maximum cpuid function present in this leaf,
-and will be updated if more functions are added in the future.
-Note also that old hosts set eax value to 0x0. This should
-be interpreted as if the value was 0x40000001.
-This function queries the presence of KVM cpuid leafs.
-
-function: define KVM_CPUID_FEATURES (0x40000001)
-
-returns::
-
- ebx, ecx
- eax = an OR'ed group of (1 << flag)
-
-where ``flag`` is defined as below:
-
-================================= =========== ================================
-flag value meaning
-================================= =========== ================================
-KVM_FEATURE_CLOCKSOURCE 0 kvmclock available at msrs
- 0x11 and 0x12
-
-KVM_FEATURE_NOP_IO_DELAY 1 not necessary to perform delays
- on PIO operations
-
-KVM_FEATURE_MMU_OP 2 deprecated
-
-KVM_FEATURE_CLOCKSOURCE2 3 kvmclock available at msrs
-
- 0x4b564d00 and 0x4b564d01
-KVM_FEATURE_ASYNC_PF 4 async pf can be enabled by
- writing to msr 0x4b564d02
-
-KVM_FEATURE_STEAL_TIME 5 steal time can be enabled by
- writing to msr 0x4b564d03
-
-KVM_FEATURE_PV_EOI 6 paravirtualized end of interrupt
- handler can be enabled by
- writing to msr 0x4b564d04
-
-KVM_FEATURE_PV_UNHAULT 7 guest checks this feature bit
- before enabling paravirtualized
- spinlock support
-
-KVM_FEATURE_PV_TLB_FLUSH 9 guest checks this feature bit
- before enabling paravirtualized
- tlb flush
-
-KVM_FEATURE_ASYNC_PF_VMEXIT 10 paravirtualized async PF VM EXIT
- can be enabled by setting bit 2
- when writing to msr 0x4b564d02
-
-KVM_FEATURE_PV_SEND_IPI 11 guest checks this feature bit
- before enabling paravirtualized
- sebd IPIs
-
-KVM_FEATURE_PV_POLL_CONTROL 12 host-side polling on HLT can
- be disabled by writing
- to msr 0x4b564d05.
-
-KVM_FEATURE_PV_SCHED_YIELD 13 guest checks this feature bit
- before using paravirtualized
- sched yield.
-
-KVM_FEATURE_CLOCSOURCE_STABLE_BIT 24 host will warn if no guest-side
- per-cpu warps are expeced in
- kvmclock
-================================= =========== ================================
-
-::
-
- edx = an OR'ed group of (1 << flag)
-
-Where ``flag`` here is defined as below:
-
-================== ============ =================================
-flag value meaning
-================== ============ =================================
-KVM_HINTS_REALTIME 0 guest checks this feature bit to
- determine that vCPUs are never
- preempted for an unlimited time
- allowing optimizations
-================== ============ =================================
+++ /dev/null
-This directory contains specific device bindings for KVM_CAP_DEVICE_CTRL.
+++ /dev/null
-ARM Virtual Interrupt Translation Service (ITS)
-===============================================
-
-Device types supported:
- KVM_DEV_TYPE_ARM_VGIC_ITS ARM Interrupt Translation Service Controller
-
-The ITS allows MSI(-X) interrupts to be injected into guests. This extension is
-optional. Creating a virtual ITS controller also requires a host GICv3 (see
-arm-vgic-v3.txt), but does not depend on having physical ITS controllers.
-
-There can be multiple ITS controllers per guest, each of them has to have
-a separate, non-overlapping MMIO region.
-
-
-Groups:
- KVM_DEV_ARM_VGIC_GRP_ADDR
- Attributes:
- KVM_VGIC_ITS_ADDR_TYPE (rw, 64-bit)
- Base address in the guest physical address space of the GICv3 ITS
- control register frame.
- This address needs to be 64K aligned and the region covers 128K.
- Errors:
- -E2BIG: Address outside of addressable IPA range
- -EINVAL: Incorrectly aligned address
- -EEXIST: Address already configured
- -EFAULT: Invalid user pointer for attr->addr.
- -ENODEV: Incorrect attribute or the ITS is not supported.
-
-
- KVM_DEV_ARM_VGIC_GRP_CTRL
- Attributes:
- KVM_DEV_ARM_VGIC_CTRL_INIT
- request the initialization of the ITS, no additional parameter in
- kvm_device_attr.addr.
-
- KVM_DEV_ARM_ITS_CTRL_RESET
- reset the ITS, no additional parameter in kvm_device_attr.addr.
- See "ITS Reset State" section.
-
- KVM_DEV_ARM_ITS_SAVE_TABLES
- save the ITS table data into guest RAM, at the location provisioned
- by the guest in corresponding registers/table entries.
-
- The layout of the tables in guest memory defines an ABI. The entries
- are laid out in little endian format as described in the last paragraph.
-
- KVM_DEV_ARM_ITS_RESTORE_TABLES
- restore the ITS tables from guest RAM to ITS internal structures.
-
- The GICV3 must be restored before the ITS and all ITS registers but
- the GITS_CTLR must be restored before restoring the ITS tables.
-
- The GITS_IIDR read-only register must also be restored before
- calling KVM_DEV_ARM_ITS_RESTORE_TABLES as the IIDR revision field
- encodes the ABI revision.
-
- The expected ordering when restoring the GICv3/ITS is described in section
- "ITS Restore Sequence".
-
- Errors:
- -ENXIO: ITS not properly configured as required prior to setting
- this attribute
- -ENOMEM: Memory shortage when allocating ITS internal data
- -EINVAL: Inconsistent restored data
- -EFAULT: Invalid guest ram access
- -EBUSY: One or more VCPUS are running
- -EACCES: The virtual ITS is backed by a physical GICv4 ITS, and the
- state is not available
-
- KVM_DEV_ARM_VGIC_GRP_ITS_REGS
- Attributes:
- The attr field of kvm_device_attr encodes the offset of the
- ITS register, relative to the ITS control frame base address
- (ITS_base).
-
- kvm_device_attr.addr points to a __u64 value whatever the width
- of the addressed register (32/64 bits). 64 bit registers can only
- be accessed with full length.
-
- Writes to read-only registers are ignored by the kernel except for:
- - GITS_CREADR. It must be restored otherwise commands in the queue
- will be re-executed after restoring CWRITER. GITS_CREADR must be
- restored before restoring the GITS_CTLR which is likely to enable the
- ITS. Also it must be restored after GITS_CBASER since a write to
- GITS_CBASER resets GITS_CREADR.
- - GITS_IIDR. The Revision field encodes the table layout ABI revision.
- In the future we might implement direct injection of virtual LPIs.
- This will require an upgrade of the table layout and an evolution of
- the ABI. GITS_IIDR must be restored before calling
- KVM_DEV_ARM_ITS_RESTORE_TABLES.
-
- For other registers, getting or setting a register has the same
- effect as reading/writing the register on real hardware.
- Errors:
- -ENXIO: Offset does not correspond to any supported register
- -EFAULT: Invalid user pointer for attr->addr
- -EINVAL: Offset is not 64-bit aligned
- -EBUSY: one or more VCPUS are running
-
- ITS Restore Sequence:
- -------------------------
-
-The following ordering must be followed when restoring the GIC and the ITS:
-a) restore all guest memory and create vcpus
-b) restore all redistributors
-c) provide the ITS base address
- (KVM_DEV_ARM_VGIC_GRP_ADDR)
-d) restore the ITS in the following order:
- 1. Restore GITS_CBASER
- 2. Restore all other GITS_ registers, except GITS_CTLR!
- 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES)
- 4. Restore GITS_CTLR
-
-Then vcpus can be started.
-
- ITS Table ABI REV0:
- -------------------
-
- Revision 0 of the ABI only supports the features of a virtual GICv3, and does
- not support a virtual GICv4 with support for direct injection of virtual
- interrupts for nested hypervisors.
-
- The device table and ITT are indexed by the DeviceID and EventID,
- respectively. The collection table is not indexed by CollectionID, and the
- entries in the collection are listed in no particular order.
- All entries are 8 bytes.
-
- Device Table Entry (DTE):
-
- bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 |
- values: | V | next | ITT_addr | Size |
-
- where;
- - V indicates whether the entry is valid. If not, other fields
- are not meaningful.
- - next: equals to 0 if this entry is the last one; otherwise it
- corresponds to the DeviceID offset to the next DTE, capped by
- 2^14 -1.
- - ITT_addr matches bits [51:8] of the ITT address (256 Byte aligned).
- - Size specifies the supported number of bits for the EventID,
- minus one
-
- Collection Table Entry (CTE):
-
- bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 |
- values: | V | RES0 | RDBase | ICID |
-
- where:
- - V indicates whether the entry is valid. If not, other fields are
- not meaningful.
- - RES0: reserved field with Should-Be-Zero-or-Preserved behavior.
- - RDBase is the PE number (GICR_TYPER.Processor_Number semantic),
- - ICID is the collection ID
-
- Interrupt Translation Entry (ITE):
-
- bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 |
- values: | next | pINTID | ICID |
-
- where:
- - next: equals to 0 if this entry is the last one; otherwise it corresponds
- to the EventID offset to the next ITE capped by 2^16 -1.
- - pINTID is the physical LPI ID; if zero, it means the entry is not valid
- and other fields are not meaningful.
- - ICID is the collection ID
-
- ITS Reset State:
- ----------------
-
-RESET returns the ITS to the same state that it was when first created and
-initialized. When the RESET command returns, the following things are
-guaranteed:
-
-- The ITS is not enabled and quiescent
- GITS_CTLR.Enabled = 0 .Quiescent=1
-- There is no internally cached state
-- No collection or device table are used
- GITS_BASER<n>.Valid = 0
-- GITS_CBASER = 0, GITS_CREADR = 0, GITS_CWRITER = 0
-- The ABI version is unchanged and remains the one set when the ITS
- device was first created.
+++ /dev/null
-ARM Virtual Generic Interrupt Controller v3 and later (VGICv3)
-==============================================================
-
-
-Device types supported:
- KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0
-
-Only one VGIC instance may be instantiated through this API. The created VGIC
-will act as the VM interrupt controller, requiring emulated user-space devices
-to inject interrupts to the VGIC instead of directly to CPUs. It is not
-possible to create both a GICv3 and GICv2 on the same VM.
-
-Creating a guest GICv3 device requires a host GICv3 as well.
-
-
-Groups:
- KVM_DEV_ARM_VGIC_GRP_ADDR
- Attributes:
- KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit)
- Base address in the guest physical address space of the GICv3 distributor
- register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
- This address needs to be 64K aligned and the region covers 64 KByte.
-
- KVM_VGIC_V3_ADDR_TYPE_REDIST (rw, 64-bit)
- Base address in the guest physical address space of the GICv3
- redistributor register mappings. There are two 64K pages for each
- VCPU and all of the redistributor pages are contiguous.
- Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
- This address needs to be 64K aligned.
-
- KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION (rw, 64-bit)
- The attribute data pointed to by kvm_device_attr.addr is a __u64 value:
- bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0
- values: | count | base | flags | index
- - index encodes the unique redistributor region index
- - flags: reserved for future use, currently 0
- - base field encodes bits [51:16] of the guest physical base address
- of the first redistributor in the region.
- - count encodes the number of redistributors in the region. Must be
- greater than 0.
- There are two 64K pages for each redistributor in the region and
- redistributors are laid out contiguously within the region. Regions
- are filled with redistributors in the index order. The sum of all
- region count fields must be greater than or equal to the number of
- VCPUs. Redistributor regions must be registered in the incremental
- index order, starting from index 0.
- The characteristics of a specific redistributor region can be read
- by presetting the index field in the attr data.
- Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
-
- It is invalid to mix calls with KVM_VGIC_V3_ADDR_TYPE_REDIST and
- KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes.
-
- Errors:
- -E2BIG: Address outside of addressable IPA range
- -EINVAL: Incorrectly aligned address, bad redistributor region
- count/index, mixed redistributor region attribute usage
- -EEXIST: Address already configured
- -ENOENT: Attempt to read the characteristics of a non existing
- redistributor region
- -ENXIO: The group or attribute is unknown/unsupported for this device
- or hardware support is missing.
- -EFAULT: Invalid user pointer for attr->addr.
-
-
- KVM_DEV_ARM_VGIC_GRP_DIST_REGS
- KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
- Attributes:
- The attr field of kvm_device_attr encodes two values:
- bits: | 63 .... 32 | 31 .... 0 |
- values: | mpidr | offset |
-
- All distributor regs are (rw, 32-bit) and kvm_device_attr.addr points to a
- __u32 value. 64-bit registers must be accessed by separately accessing the
- lower and higher word.
-
- Writes to read-only registers are ignored by the kernel.
-
- KVM_DEV_ARM_VGIC_GRP_DIST_REGS accesses the main distributor registers.
- KVM_DEV_ARM_VGIC_GRP_REDIST_REGS accesses the redistributor of the CPU
- specified by the mpidr.
-
- The offset is relative to the "[Re]Distributor base address" as defined
- in the GICv3/4 specs. Getting or setting such a register has the same
- effect as reading or writing the register on real hardware, except for the
- following registers: GICD_STATUSR, GICR_STATUSR, GICD_ISPENDR,
- GICR_ISPENDR0, GICD_ICPENDR, and GICR_ICPENDR0. These registers behave
- differently when accessed via this interface compared to their
- architecturally defined behavior to allow software a full view of the
- VGIC's internal state.
-
- The mpidr field is used to specify which
- redistributor is accessed. The mpidr is ignored for the distributor.
-
- The mpidr encoding is based on the affinity information in the
- architecture defined MPIDR, and the field is encoded as follows:
- | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
- | Aff3 | Aff2 | Aff1 | Aff0 |
-
- Note that distributor fields are not banked, but return the same value
- regardless of the mpidr used to access the register.
-
- GICD_IIDR.Revision is updated when the KVM implementation is changed in a
- way directly observable by the guest or userspace. Userspace should read
- GICD_IIDR from KVM and write back the read value to confirm its expected
- behavior is aligned with the KVM implementation. Userspace should set
- GICD_IIDR before setting any other registers to ensure the expected
- behavior.
-
-
- The GICD_STATUSR and GICR_STATUSR registers are architecturally defined such
- that a write of a clear bit has no effect, whereas a write with a set bit
- clears that value. To allow userspace to freely set the values of these two
- registers, setting the attributes with the register offsets for these two
- registers simply sets the non-reserved bits to the value written.
-
-
- Accesses (reads and writes) to the GICD_ISPENDR register region and
- GICR_ISPENDR0 registers get/set the value of the latched pending state for
- the interrupts.
-
- This is identical to the value returned by a guest read from ISPENDR for an
- edge triggered interrupt, but may differ for level triggered interrupts.
- For edge triggered interrupts, once an interrupt becomes pending (whether
- because of an edge detected on the input line or because of a guest write
- to ISPENDR) this state is "latched", and only cleared when either the
- interrupt is activated or when the guest writes to ICPENDR. A level
- triggered interrupt may be pending either because the level input is held
- high by a device, or because of a guest write to the ISPENDR register. Only
- ISPENDR writes are latched; if the device lowers the line level then the
- interrupt is no longer pending unless the guest also wrote to ISPENDR, and
- conversely writes to ICPENDR or activations of the interrupt do not clear
- the pending status if the line level is still being held high. (These
- rules are documented in the GICv3 specification descriptions of the ICPENDR
- and ISPENDR registers.) For a level triggered interrupt the value accessed
- here is that of the latch which is set by ISPENDR and cleared by ICPENDR or
- interrupt activation, whereas the value returned by a guest read from
- ISPENDR is the logical OR of the latch value and the input line level.
-
- Raw access to the latch state is provided to userspace so that it can save
- and restore the entire GIC internal state (which is defined by the
- combination of the current input line level and the latch state, and cannot
- be deduced from purely the line level and the value of the ISPENDR
- registers).
-
- Accesses to GICD_ICPENDR register region and GICR_ICPENDR0 registers have
- RAZ/WI semantics, meaning that reads always return 0 and writes are always
- ignored.
-
- Errors:
- -ENXIO: Getting or setting this register is not yet supported
- -EBUSY: One or more VCPUs are running
-
-
- KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS
- Attributes:
- The attr field of kvm_device_attr encodes two values:
- bits: | 63 .... 32 | 31 .... 16 | 15 .... 0 |
- values: | mpidr | RES | instr |
-
- The mpidr field encodes the CPU ID based on the affinity information in the
- architecture defined MPIDR, and the field is encoded as follows:
- | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
- | Aff3 | Aff2 | Aff1 | Aff0 |
-
- The instr field encodes the system register to access based on the fields
- defined in the A64 instruction set encoding for system register access
- (RES means the bits are reserved for future use and should be zero):
-
- | 15 ... 14 | 13 ... 11 | 10 ... 7 | 6 ... 3 | 2 ... 0 |
- | Op 0 | Op1 | CRn | CRm | Op2 |
-
- All system regs accessed through this API are (rw, 64-bit) and
- kvm_device_attr.addr points to a __u64 value.
-
- KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS accesses the CPU interface registers for the
- CPU specified by the mpidr field.
-
- CPU interface registers access is not implemented for AArch32 mode.
- Error -ENXIO is returned when accessed in AArch32 mode.
- Errors:
- -ENXIO: Getting or setting this register is not yet supported
- -EBUSY: VCPU is running
- -EINVAL: Invalid mpidr or register value supplied
-
-
- KVM_DEV_ARM_VGIC_GRP_NR_IRQS
- Attributes:
- A value describing the number of interrupts (SGI, PPI and SPI) for
- this GIC instance, ranging from 64 to 1024, in increments of 32.
-
- kvm_device_attr.addr points to a __u32 value.
-
- Errors:
- -EINVAL: Value set is out of the expected range
- -EBUSY: Value has already be set.
-
-
- KVM_DEV_ARM_VGIC_GRP_CTRL
- Attributes:
- KVM_DEV_ARM_VGIC_CTRL_INIT
- request the initialization of the VGIC, no additional parameter in
- kvm_device_attr.addr.
- KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES
- save all LPI pending bits into guest RAM pending tables.
-
- The first kB of the pending table is not altered by this operation.
- Errors:
- -ENXIO: VGIC not properly configured as required prior to calling
- this attribute
- -ENODEV: no online VCPU
- -ENOMEM: memory shortage when allocating vgic internal data
- -EFAULT: Invalid guest ram access
- -EBUSY: One or more VCPUS are running
-
-
- KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO
- Attributes:
- The attr field of kvm_device_attr encodes the following values:
- bits: | 63 .... 32 | 31 .... 10 | 9 .... 0 |
- values: | mpidr | info | vINTID |
-
- The vINTID specifies which set of IRQs is reported on.
-
- The info field specifies which information userspace wants to get or set
- using this interface. Currently we support the following info values:
-
- VGIC_LEVEL_INFO_LINE_LEVEL:
- Get/Set the input level of the IRQ line for a set of 32 contiguously
- numbered interrupts.
- vINTID must be a multiple of 32.
-
- kvm_device_attr.addr points to a __u32 value which will contain a
- bitmap where a set bit means the interrupt level is asserted.
-
- Bit[n] indicates the status for interrupt vINTID + n.
-
- SGIs and any interrupt with a higher ID than the number of interrupts
- supported, will be RAZ/WI. LPIs are always edge-triggered and are
- therefore not supported by this interface.
-
- PPIs are reported per VCPU as specified in the mpidr field, and SPIs are
- reported with the same value regardless of the mpidr specified.
-
- The mpidr field encodes the CPU ID based on the affinity information in the
- architecture defined MPIDR, and the field is encoded as follows:
- | 63 .... 56 | 55 .... 48 | 47 .... 40 | 39 .... 32 |
- | Aff3 | Aff2 | Aff1 | Aff0 |
- Errors:
- -EINVAL: vINTID is not multiple of 32 or
- info field is not VGIC_LEVEL_INFO_LINE_LEVEL
+++ /dev/null
-ARM Virtual Generic Interrupt Controller v2 (VGIC)
-==================================================
-
-Device types supported:
- KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0
-
-Only one VGIC instance may be instantiated through either this API or the
-legacy KVM_CREATE_IRQCHIP API. The created VGIC will act as the VM interrupt
-controller, requiring emulated user-space devices to inject interrupts to the
-VGIC instead of directly to CPUs.
-
-GICv3 implementations with hardware compatibility support allow creating a
-guest GICv2 through this interface. For information on creating a guest GICv3
-device and guest ITS devices, see arm-vgic-v3.txt. It is not possible to
-create both a GICv3 and GICv2 device on the same VM.
-
-
-Groups:
- KVM_DEV_ARM_VGIC_GRP_ADDR
- Attributes:
- KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit)
- Base address in the guest physical address space of the GIC distributor
- register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
- This address needs to be 4K aligned and the region covers 4 KByte.
-
- KVM_VGIC_V2_ADDR_TYPE_CPU (rw, 64-bit)
- Base address in the guest physical address space of the GIC virtual cpu
- interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2.
- This address needs to be 4K aligned and the region covers 4 KByte.
- Errors:
- -E2BIG: Address outside of addressable IPA range
- -EINVAL: Incorrectly aligned address
- -EEXIST: Address already configured
- -ENXIO: The group or attribute is unknown/unsupported for this device
- or hardware support is missing.
- -EFAULT: Invalid user pointer for attr->addr.
-
- KVM_DEV_ARM_VGIC_GRP_DIST_REGS
- Attributes:
- The attr field of kvm_device_attr encodes two values:
- bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
- values: | reserved | vcpu_index | offset |
-
- All distributor regs are (rw, 32-bit)
-
- The offset is relative to the "Distributor base address" as defined in the
- GICv2 specs. Getting or setting such a register has the same effect as
- reading or writing the register on the actual hardware from the cpu whose
- index is specified with the vcpu_index field. Note that most distributor
- fields are not banked, but return the same value regardless of the
- vcpu_index used to access the register.
-
- GICD_IIDR.Revision is updated when the KVM implementation of an emulated
- GICv2 is changed in a way directly observable by the guest or userspace.
- Userspace should read GICD_IIDR from KVM and write back the read value to
- confirm its expected behavior is aligned with the KVM implementation.
- Userspace should set GICD_IIDR before setting any other registers (both
- KVM_DEV_ARM_VGIC_GRP_DIST_REGS and KVM_DEV_ARM_VGIC_GRP_CPU_REGS) to ensure
- the expected behavior. Unless GICD_IIDR has been set from userspace, writes
- to the interrupt group registers (GICD_IGROUPR) are ignored.
- Errors:
- -ENXIO: Getting or setting this register is not yet supported
- -EBUSY: One or more VCPUs are running
- -EINVAL: Invalid vcpu_index supplied
-
- KVM_DEV_ARM_VGIC_GRP_CPU_REGS
- Attributes:
- The attr field of kvm_device_attr encodes two values:
- bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
- values: | reserved | vcpu_index | offset |
-
- All CPU interface regs are (rw, 32-bit)
-
- The offset specifies the offset from the "CPU interface base address" as
- defined in the GICv2 specs. Getting or setting such a register has the
- same effect as reading or writing the register on the actual hardware.
-
- The Active Priorities Registers APRn are implementation defined, so we set a
- fixed format for our implementation that fits with the model of a "GICv2
- implementation without the security extensions" which we present to the
- guest. This interface always exposes four register APR[0-3] describing the
- maximum possible 128 preemption levels. The semantics of the register
- indicate if any interrupts in a given preemption level are in the active
- state by setting the corresponding bit.
-
- Thus, preemption level X has one or more active interrupts if and only if:
-
- APRn[X mod 32] == 0b1, where n = X / 32
-
- Bits for undefined preemption levels are RAZ/WI.
-
- Note that this differs from a CPU's view of the APRs on hardware in which
- a GIC without the security extensions expose group 0 and group 1 active
- priorities in separate register groups, whereas we show a combined view
- similar to GICv2's GICH_APR.
-
- For historical reasons and to provide ABI compatibility with userspace we
- export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
- field in the lower 5 bits of a word, meaning that userspace must always
- use the lower 5 bits to communicate with the KVM device and must shift the
- value left by 3 places to obtain the actual priority mask level.
-
- Errors:
- -ENXIO: Getting or setting this register is not yet supported
- -EBUSY: One or more VCPUs are running
- -EINVAL: Invalid vcpu_index supplied
-
- KVM_DEV_ARM_VGIC_GRP_NR_IRQS
- Attributes:
- A value describing the number of interrupts (SGI, PPI and SPI) for
- this GIC instance, ranging from 64 to 1024, in increments of 32.
-
- Errors:
- -EINVAL: Value set is out of the expected range
- -EBUSY: Value has already be set, or GIC has already been initialized
- with default values.
-
- KVM_DEV_ARM_VGIC_GRP_CTRL
- Attributes:
- KVM_DEV_ARM_VGIC_CTRL_INIT
- request the initialization of the VGIC or ITS, no additional parameter
- in kvm_device_attr.addr.
- Errors:
- -ENXIO: VGIC not properly configured as required prior to calling
- this attribute
- -ENODEV: no online VCPU
- -ENOMEM: memory shortage when allocating vgic internal data
+++ /dev/null
-MPIC interrupt controller
-=========================
-
-Device types supported:
- KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0
- KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2
-
-Only one MPIC instance, of any type, may be instantiated. The created
-MPIC will act as the system interrupt controller, connecting to each
-vcpu's interrupt inputs.
-
-Groups:
- KVM_DEV_MPIC_GRP_MISC
- Attributes:
- KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit)
- Base address of the 256 KiB MPIC register space. Must be
- naturally aligned. A value of zero disables the mapping.
- Reset value is zero.
-
- KVM_DEV_MPIC_GRP_REGISTER (rw, 32-bit)
- Access an MPIC register, as if the access were made from the guest.
- "attr" is the byte offset into the MPIC register space. Accesses
- must be 4-byte aligned.
-
- MSIs may be signaled by using this attribute group to write
- to the relevant MSIIR.
-
- KVM_DEV_MPIC_GRP_IRQ_ACTIVE (rw, 32-bit)
- IRQ input line for each standard openpic source. 0 is inactive and 1
- is active, regardless of interrupt sense.
-
- For edge-triggered interrupts: Writing 1 is considered an activating
- edge, and writing 0 is ignored. Reading returns 1 if a previously
- signaled edge has not been acknowledged, and 0 otherwise.
-
- "attr" is the IRQ number. IRQ numbers for standard sources are the
- byte offset of the relevant IVPR from EIVPR0, divided by 32.
-
-IRQ Routing:
-
- The MPIC emulation supports IRQ routing. Only a single MPIC device can
- be instantiated. Once that device has been created, it's available as
- irqchip id 0.
-
- This irqchip 0 has 256 interrupt pins, which expose the interrupts in
- the main array of interrupt sources (a.k.a. "SRC" interrupts).
-
- The numbering is the same as the MPIC device tree binding -- based on
- the register offset from the beginning of the sources array, without
- regard to any subdivisions in chip documentation such as "internal"
- or "external" interrupts.
-
- Access to non-SRC interrupts is not implemented through IRQ routing mechanisms.
+++ /dev/null
-FLIC (floating interrupt controller)
-====================================
-
-FLIC handles floating (non per-cpu) interrupts, i.e. I/O, service and some
-machine check interruptions. All interrupts are stored in a per-vm list of
-pending interrupts. FLIC performs operations on this list.
-
-Only one FLIC instance may be instantiated.
-
-FLIC provides support to
-- add interrupts (KVM_DEV_FLIC_ENQUEUE)
-- inspect currently pending interrupts (KVM_FLIC_GET_ALL_IRQS)
-- purge all pending floating interrupts (KVM_DEV_FLIC_CLEAR_IRQS)
-- purge one pending floating I/O interrupt (KVM_DEV_FLIC_CLEAR_IO_IRQ)
-- enable/disable for the guest transparent async page faults
-- register and modify adapter interrupt sources (KVM_DEV_FLIC_ADAPTER_*)
-- modify AIS (adapter-interruption-suppression) mode state (KVM_DEV_FLIC_AISM)
-- inject adapter interrupts on a specified adapter (KVM_DEV_FLIC_AIRQ_INJECT)
-- get/set all AIS mode states (KVM_DEV_FLIC_AISM_ALL)
-
-Groups:
- KVM_DEV_FLIC_ENQUEUE
- Passes a buffer and length into the kernel which are then injected into
- the list of pending interrupts.
- attr->addr contains the pointer to the buffer and attr->attr contains
- the length of the buffer.
- The format of the data structure kvm_s390_irq as it is copied from userspace
- is defined in usr/include/linux/kvm.h.
-
- KVM_DEV_FLIC_GET_ALL_IRQS
- Copies all floating interrupts into a buffer provided by userspace.
- When the buffer is too small it returns -ENOMEM, which is the indication
- for userspace to try again with a bigger buffer.
- -ENOBUFS is returned when the allocation of a kernelspace buffer has
- failed.
- -EFAULT is returned when copying data to userspace failed.
- All interrupts remain pending, i.e. are not deleted from the list of
- currently pending interrupts.
- attr->addr contains the userspace address of the buffer into which all
- interrupt data will be copied.
- attr->attr contains the size of the buffer in bytes.
-
- KVM_DEV_FLIC_CLEAR_IRQS
- Simply deletes all elements from the list of currently pending floating
- interrupts. No interrupts are injected into the guest.
-
- KVM_DEV_FLIC_CLEAR_IO_IRQ
- Deletes one (if any) I/O interrupt for a subchannel identified by the
- subsystem identification word passed via the buffer specified by
- attr->addr (address) and attr->attr (length).
-
- KVM_DEV_FLIC_APF_ENABLE
- Enables async page faults for the guest. So in case of a major page fault
- the host is allowed to handle this async and continues the guest.
-
- KVM_DEV_FLIC_APF_DISABLE_WAIT
- Disables async page faults for the guest and waits until already pending
- async page faults are done. This is necessary to trigger a completion interrupt
- for every init interrupt before migrating the interrupt list.
-
- KVM_DEV_FLIC_ADAPTER_REGISTER
- Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter
- describing the adapter to register:
-
-struct kvm_s390_io_adapter {
- __u32 id;
- __u8 isc;
- __u8 maskable;
- __u8 swap;
- __u8 flags;
-};
-
- id contains the unique id for the adapter, isc the I/O interruption subclass
- to use, maskable whether this adapter may be masked (interrupts turned off),
- swap whether the indicators need to be byte swapped, and flags contains
- further characteristics of the adapter.
- Currently defined values for 'flags' are:
- - KVM_S390_ADAPTER_SUPPRESSIBLE: adapter is subject to AIS
- (adapter-interrupt-suppression) facility. This flag only has an effect if
- the AIS capability is enabled.
- Unknown flag values are ignored.
-
-
- KVM_DEV_FLIC_ADAPTER_MODIFY
- Modifies attributes of an existing I/O adapter interrupt source. Takes
- a kvm_s390_io_adapter_req specifying the adapter and the operation:
-
-struct kvm_s390_io_adapter_req {
- __u32 id;
- __u8 type;
- __u8 mask;
- __u16 pad0;
- __u64 addr;
-};
-
- id specifies the adapter and type the operation. The supported operations
- are:
-
- KVM_S390_IO_ADAPTER_MASK
- mask or unmask the adapter, as specified in mask
-
- KVM_S390_IO_ADAPTER_MAP
- perform a gmap translation for the guest address provided in addr,
- pin a userspace page for the translated address and add it to the
- list of mappings
- Note: A new mapping will be created unconditionally; therefore,
- the calling code should avoid making duplicate mappings.
-
- KVM_S390_IO_ADAPTER_UNMAP
- release a userspace page for the translated address specified in addr
- from the list of mappings
-
- KVM_DEV_FLIC_AISM
- modify the adapter-interruption-suppression mode for a given isc if the
- AIS capability is enabled. Takes a kvm_s390_ais_req describing:
-
-struct kvm_s390_ais_req {
- __u8 isc;
- __u16 mode;
-};
-
- isc contains the target I/O interruption subclass, mode the target
- adapter-interruption-suppression mode. The following modes are
- currently supported:
- - KVM_S390_AIS_MODE_ALL: ALL-Interruptions Mode, i.e. airq injection
- is always allowed;
- - KVM_S390_AIS_MODE_SINGLE: SINGLE-Interruption Mode, i.e. airq
- injection is only allowed once and the following adapter interrupts
- will be suppressed until the mode is set again to ALL-Interruptions
- or SINGLE-Interruption mode.
-
- KVM_DEV_FLIC_AIRQ_INJECT
- Inject adapter interrupts on a specified adapter.
- attr->attr contains the unique id for the adapter, which allows for
- adapter-specific checks and actions.
- For adapters subject to AIS, handle the airq injection suppression for
- an isc according to the adapter-interruption-suppression mode on condition
- that the AIS capability is enabled.
-
- KVM_DEV_FLIC_AISM_ALL
- Gets or sets the adapter-interruption-suppression mode for all ISCs. Takes
- a kvm_s390_ais_all describing:
-
-struct kvm_s390_ais_all {
- __u8 simm; /* Single-Interruption-Mode mask */
- __u8 nimm; /* No-Interruption-Mode mask *
-};
-
- simm contains Single-Interruption-Mode mask for all ISCs, nimm contains
- No-Interruption-Mode mask for all ISCs. Each bit in simm and nimm corresponds
- to an ISC (MSB0 bit 0 to ISC 0 and so on). The combination of simm bit and
- nimm bit presents AIS mode for a ISC.
-
- KVM_DEV_FLIC_AISM_ALL is indicated by KVM_CAP_S390_AIS_MIGRATION.
-
-Note: The KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR device ioctls executed on
-FLIC with an unknown group or attribute gives the error code EINVAL (instead of
-ENXIO, as specified in the API documentation). It is not possible to conclude
-that a FLIC operation is unavailable based on the error code resulting from a
-usage attempt.
-
-Note: The KVM_DEV_FLIC_CLEAR_IO_IRQ ioctl will return EINVAL in case a zero
-schid is specified.
+++ /dev/null
-Generic vcpu interface
-====================================
-
-The virtual cpu "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
-KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same struct
-kvm_device_attr as other devices, but targets VCPU-wide settings and controls.
-
-The groups and attributes per virtual cpu, if any, are architecture specific.
-
-1. GROUP: KVM_ARM_VCPU_PMU_V3_CTRL
-Architectures: ARM64
-
-1.1. ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_IRQ
-Parameters: in kvm_device_attr.addr the address for PMU overflow interrupt is a
- pointer to an int
-Returns: -EBUSY: The PMU overflow interrupt is already set
- -ENXIO: The overflow interrupt not set when attempting to get it
- -ENODEV: PMUv3 not supported
- -EINVAL: Invalid PMU overflow interrupt number supplied or
- trying to set the IRQ number without using an in-kernel
- irqchip.
-
-A value describing the PMUv3 (Performance Monitor Unit v3) overflow interrupt
-number for this vcpu. This interrupt could be a PPI or SPI, but the interrupt
-type must be same for each vcpu. As a PPI, the interrupt number is the same for
-all vcpus, while as an SPI it must be a separate number per vcpu.
-
-1.2 ATTRIBUTE: KVM_ARM_VCPU_PMU_V3_INIT
-Parameters: no additional parameter in kvm_device_attr.addr
-Returns: -ENODEV: PMUv3 not supported or GIC not initialized
- -ENXIO: PMUv3 not properly configured or in-kernel irqchip not
- configured as required prior to calling this attribute
- -EBUSY: PMUv3 already initialized
-
-Request the initialization of the PMUv3. If using the PMUv3 with an in-kernel
-virtual GIC implementation, this must be done after initializing the in-kernel
-irqchip.
-
-
-2. GROUP: KVM_ARM_VCPU_TIMER_CTRL
-Architectures: ARM,ARM64
-
-2.1. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_VTIMER
-2.2. ATTRIBUTE: KVM_ARM_VCPU_TIMER_IRQ_PTIMER
-Parameters: in kvm_device_attr.addr the address for the timer interrupt is a
- pointer to an int
-Returns: -EINVAL: Invalid timer interrupt number
- -EBUSY: One or more VCPUs has already run
-
-A value describing the architected timer interrupt number when connected to an
-in-kernel virtual GIC. These must be a PPI (16 <= intid < 32). Setting the
-attribute overrides the default values (see below).
-
-KVM_ARM_VCPU_TIMER_IRQ_VTIMER: The EL1 virtual timer intid (default: 27)
-KVM_ARM_VCPU_TIMER_IRQ_PTIMER: The EL1 physical timer intid (default: 30)
-
-Setting the same PPI for different timers will prevent the VCPUs from running.
-Setting the interrupt number on a VCPU configures all VCPUs created at that
-time to use the number provided for a given timer, overwriting any previously
-configured values on other VCPUs. Userspace should configure the interrupt
-numbers on at least one VCPU after creating all VCPUs and before running any
-VCPUs.
+++ /dev/null
-VFIO virtual device
-===================
-
-Device types supported:
- KVM_DEV_TYPE_VFIO
-
-Only one VFIO instance may be created per VM. The created device
-tracks VFIO groups in use by the VM and features of those groups
-important to the correctness and acceleration of the VM. As groups
-are enabled and disabled for use by the VM, KVM should be updated
-about their presence. When registered with KVM, a reference to the
-VFIO-group is held by KVM.
-
-Groups:
- KVM_DEV_VFIO_GROUP
-
-KVM_DEV_VFIO_GROUP attributes:
- KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
- kvm_device_attr.addr points to an int32_t file descriptor
- for the VFIO group.
- KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
- kvm_device_attr.addr points to an int32_t file descriptor
- for the VFIO group.
- KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
- allocated by sPAPR KVM.
- kvm_device_attr.addr points to a struct:
-
- struct kvm_vfio_spapr_tce {
- __s32 groupfd;
- __s32 tablefd;
- };
-
- where
- @groupfd is a file descriptor for a VFIO group;
- @tablefd is a file descriptor for a TCE table allocated via
- KVM_CREATE_SPAPR_TCE.
+++ /dev/null
-Generic vm interface
-====================================
-
-The virtual machine "device" also accepts the ioctls KVM_SET_DEVICE_ATTR,
-KVM_GET_DEVICE_ATTR, and KVM_HAS_DEVICE_ATTR. The interface uses the same
-struct kvm_device_attr as other devices, but targets VM-wide settings
-and controls.
-
-The groups and attributes per virtual machine, if any, are architecture
-specific.
-
-1. GROUP: KVM_S390_VM_MEM_CTRL
-Architectures: s390
-
-1.1. ATTRIBUTE: KVM_S390_VM_MEM_ENABLE_CMMA
-Parameters: none
-Returns: -EBUSY if a vcpu is already defined, otherwise 0
-
-Enables Collaborative Memory Management Assist (CMMA) for the virtual machine.
-
-1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA
-Parameters: none
-Returns: -EINVAL if CMMA was not enabled
- 0 otherwise
-
-Clear the CMMA status for all guest pages, so any pages the guest marked
-as unused are again used any may not be reclaimed by the host.
-
-1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE
-Parameters: in attr->addr the address for the new limit of guest memory
-Returns: -EFAULT if the given address is not accessible
- -EINVAL if the virtual machine is of type UCONTROL
- -E2BIG if the given guest memory is to big for that machine
- -EBUSY if a vcpu is already defined
- -ENOMEM if not enough memory is available for a new shadow guest mapping
- 0 otherwise
-
-Allows userspace to query the actual limit and set a new limit for
-the maximum guest memory size. The limit will be rounded up to
-2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by
-the number of page table levels. In the case that there is no limit we will set
-the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX).
-
-2. GROUP: KVM_S390_VM_CPU_MODEL
-Architectures: s390
-
-2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o)
-
-Allows user space to retrieve machine and kvm specific cpu related information:
-
-struct kvm_s390_vm_cpu_machine {
- __u64 cpuid; # CPUID of host
- __u32 ibc; # IBC level range offered by host
- __u8 pad[4];
- __u64 fac_mask[256]; # set of cpu facilities enabled by KVM
- __u64 fac_list[256]; # set of cpu facilities offered by host
-}
-
-Parameters: address of buffer to store the machine related cpu data
- of type struct kvm_s390_vm_cpu_machine*
-Returns: -EFAULT if the given address is not accessible from kernel space
- -ENOMEM if not enough memory is available to process the ioctl
- 0 in case of success
-
-2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w)
-
-Allows user space to retrieve or request to change cpu related information for a vcpu:
-
-struct kvm_s390_vm_cpu_processor {
- __u64 cpuid; # CPUID currently (to be) used by this vcpu
- __u16 ibc; # IBC level currently (to be) used by this vcpu
- __u8 pad[6];
- __u64 fac_list[256]; # set of cpu facilities currently (to be) used
- # by this vcpu
-}
-
-KVM does not enforce or limit the cpu model data in any form. Take the information
-retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration
-setups. Instruction interceptions triggered by additionally set facility bits that
-are not handled by KVM need to by imlemented in the VM driver code.
-
-Parameters: address of buffer to store/set the processor related cpu
- data of type struct kvm_s390_vm_cpu_processor*.
-Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case)
- -EFAULT if the given address is not accessible from kernel space
- -ENOMEM if not enough memory is available to process the ioctl
- 0 in case of success
-
-2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o)
-
-Allows user space to retrieve available cpu features. A feature is available if
-provided by the hardware and supported by kvm. In theory, cpu features could
-even be completely emulated by kvm.
-
-struct kvm_s390_vm_cpu_feat {
- __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering
-};
-
-Parameters: address of a buffer to load the feature list from.
-Returns: -EFAULT if the given address is not accessible from kernel space.
- 0 in case of success.
-
-2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w)
-
-Allows user space to retrieve or change enabled cpu features for all VCPUs of a
-VM. Features that are not available cannot be enabled.
-
-See 2.3. for a description of the parameter struct.
-
-Parameters: address of a buffer to store/load the feature list from.
-Returns: -EFAULT if the given address is not accessible from kernel space.
- -EINVAL if a cpu feature that is not available is to be enabled.
- -EBUSY if at least one VCPU has already been defined.
- 0 in case of success.
-
-2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o)
-
-Allows user space to retrieve available cpu subfunctions without any filtering
-done by a set IBC. These subfunctions are indicated to the guest VCPU via
-query or "test bit" subfunctions and used e.g. by cpacf functions, plo and ptff.
-
-A subfunction block is only valid if KVM_S390_VM_CPU_MACHINE contains the
-STFL(E) bit introducing the affected instruction. If the affected instruction
-indicates subfunctions via a "query subfunction", the response block is
-contained in the returned struct. If the affected instruction
-indicates subfunctions via a "test bit" mechanism, the subfunction codes are
-contained in the returned struct in MSB 0 bit numbering.
-
-struct kvm_s390_vm_cpu_subfunc {
- u8 plo[32]; # always valid (ESA/390 feature)
- u8 ptff[16]; # valid with TOD-clock steering
- u8 kmac[16]; # valid with Message-Security-Assist
- u8 kmc[16]; # valid with Message-Security-Assist
- u8 km[16]; # valid with Message-Security-Assist
- u8 kimd[16]; # valid with Message-Security-Assist
- u8 klmd[16]; # valid with Message-Security-Assist
- u8 pckmo[16]; # valid with Message-Security-Assist-Extension 3
- u8 kmctr[16]; # valid with Message-Security-Assist-Extension 4
- u8 kmf[16]; # valid with Message-Security-Assist-Extension 4
- u8 kmo[16]; # valid with Message-Security-Assist-Extension 4
- u8 pcc[16]; # valid with Message-Security-Assist-Extension 4
- u8 ppno[16]; # valid with Message-Security-Assist-Extension 5
- u8 kma[16]; # valid with Message-Security-Assist-Extension 8
- u8 kdsa[16]; # valid with Message-Security-Assist-Extension 9
- u8 reserved[1792]; # reserved for future instructions
-};
-
-Parameters: address of a buffer to load the subfunction blocks from.
-Returns: -EFAULT if the given address is not accessible from kernel space.
- 0 in case of success.
-
-2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w)
-
-Allows user space to retrieve or change cpu subfunctions to be indicated for
-all VCPUs of a VM. This attribute will only be available if kernel and
-hardware support are in place.
-
-The kernel uses the configured subfunction blocks for indication to
-the guest. A subfunction block will only be used if the associated STFL(E) bit
-has not been disabled by user space (so the instruction to be queried is
-actually available for the guest).
-
-As long as no data has been written, a read will fail. The IBC will be used
-to determine available subfunctions in this case, this will guarantee backward
-compatibility.
-
-See 2.5. for a description of the parameter struct.
-
-Parameters: address of a buffer to store/load the subfunction blocks from.
-Returns: -EFAULT if the given address is not accessible from kernel space.
- -EINVAL when reading, if there was no write yet.
- -EBUSY if at least one VCPU has already been defined.
- 0 in case of success.
-
-3. GROUP: KVM_S390_VM_TOD
-Architectures: s390
-
-3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
-
-Allows user space to set/get the TOD clock extension (u8) (superseded by
-KVM_S390_VM_TOD_EXT).
-
-Parameters: address of a buffer in user space to store the data (u8) to
-Returns: -EFAULT if the given address is not accessible from kernel space
- -EINVAL if setting the TOD clock extension to != 0 is not supported
-
-3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
-
-Allows user space to set/get bits 0-63 of the TOD clock register as defined in
-the POP (u64).
-
-Parameters: address of a buffer in user space to store the data (u64) to
-Returns: -EFAULT if the given address is not accessible from kernel space
-
-3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
-Allows user space to set/get bits 0-63 of the TOD clock register as defined in
-the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
-also allows user space to get/set it. If the guest CPU model does not support
-it, it is stored as 0 and not allowed to be set to a value != 0.
-
-Parameters: address of a buffer in user space to store the data
- (kvm_s390_vm_tod_clock) to
-Returns: -EFAULT if the given address is not accessible from kernel space
- -EINVAL if setting the TOD clock extension to != 0 is not supported
-
-4. GROUP: KVM_S390_VM_CRYPTO
-Architectures: s390
-
-4.1. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_AES_KW (w/o)
-
-Allows user space to enable aes key wrapping, including generating a new
-wrapping key.
-
-Parameters: none
-Returns: 0
-
-4.2. ATTRIBUTE: KVM_S390_VM_CRYPTO_ENABLE_DEA_KW (w/o)
-
-Allows user space to enable dea key wrapping, including generating a new
-wrapping key.
-
-Parameters: none
-Returns: 0
-
-4.3. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_AES_KW (w/o)
-
-Allows user space to disable aes key wrapping, clearing the wrapping key.
-
-Parameters: none
-Returns: 0
-
-4.4. ATTRIBUTE: KVM_S390_VM_CRYPTO_DISABLE_DEA_KW (w/o)
-
-Allows user space to disable dea key wrapping, clearing the wrapping key.
-
-Parameters: none
-Returns: 0
-
-5. GROUP: KVM_S390_VM_MIGRATION
-Architectures: s390
-
-5.1. ATTRIBUTE: KVM_S390_VM_MIGRATION_STOP (w/o)
-
-Allows userspace to stop migration mode, needed for PGSTE migration.
-Setting this attribute when migration mode is not active will have no
-effects.
-
-Parameters: none
-Returns: 0
-
-5.2. ATTRIBUTE: KVM_S390_VM_MIGRATION_START (w/o)
-
-Allows userspace to start migration mode, needed for PGSTE migration.
-Setting this attribute when migration mode is already active will have
-no effects.
-
-Parameters: none
-Returns: -ENOMEM if there is not enough free memory to start migration mode
- -EINVAL if the state of the VM is invalid (e.g. no memory defined)
- 0 in case of success.
-
-5.3. ATTRIBUTE: KVM_S390_VM_MIGRATION_STATUS (r/o)
-
-Allows userspace to query the status of migration mode.
-
-Parameters: address of a buffer in user space to store the data (u64) to;
- the data itself is either 0 if migration mode is disabled or 1
- if it is enabled
-Returns: -EFAULT if the given address is not accessible from kernel space
- 0 in case of success.
+++ /dev/null
-XICS interrupt controller
-
-Device type supported: KVM_DEV_TYPE_XICS
-
-Groups:
- KVM_DEV_XICS_SOURCES
- Attributes: One per interrupt source, indexed by the source number.
-
-This device emulates the XICS (eXternal Interrupt Controller
-Specification) defined in PAPR. The XICS has a set of interrupt
-sources, each identified by a 20-bit source number, and a set of
-Interrupt Control Presentation (ICP) entities, also called "servers",
-each associated with a virtual CPU.
-
-The ICP entities are created by enabling the KVM_CAP_IRQ_ARCH
-capability for each vcpu, specifying KVM_CAP_IRQ_XICS in args[0] and
-the interrupt server number (i.e. the vcpu number from the XICS's
-point of view) in args[1] of the kvm_enable_cap struct. Each ICP has
-64 bits of state which can be read and written using the
-KVM_GET_ONE_REG and KVM_SET_ONE_REG ioctls on the vcpu. The 64 bit
-state word has the following bitfields, starting at the
-least-significant end of the word:
-
-* Unused, 16 bits
-
-* Pending interrupt priority, 8 bits
- Zero is the highest priority, 255 means no interrupt is pending.
-
-* Pending IPI (inter-processor interrupt) priority, 8 bits
- Zero is the highest priority, 255 means no IPI is pending.
-
-* Pending interrupt source number, 24 bits
- Zero means no interrupt pending, 2 means an IPI is pending
-
-* Current processor priority, 8 bits
- Zero is the highest priority, meaning no interrupts can be
- delivered, and 255 is the lowest priority.
-
-Each source has 64 bits of state that can be read and written using
-the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the
-KVM_DEV_XICS_SOURCES attribute group, with the attribute number being
-the interrupt source number. The 64 bit state word has the following
-bitfields, starting from the least-significant end of the word:
-
-* Destination (server number), 32 bits
- This specifies where the interrupt should be sent, and is the
- interrupt server number specified for the destination vcpu.
-
-* Priority, 8 bits
- This is the priority specified for this interrupt source, where 0 is
- the highest priority and 255 is the lowest. An interrupt with a
- priority of 255 will never be delivered.
-
-* Level sensitive flag, 1 bit
- This bit is 1 for a level-sensitive interrupt source, or 0 for
- edge-sensitive (or MSI).
-
-* Masked flag, 1 bit
- This bit is set to 1 if the interrupt is masked (cannot be delivered
- regardless of its priority), for example by the ibm,int-off RTAS
- call, or 0 if it is not masked.
-
-* Pending flag, 1 bit
- This bit is 1 if the source has a pending interrupt, otherwise 0.
-
-Only one XICS instance may be created per VM.
+++ /dev/null
-POWER9 eXternal Interrupt Virtualization Engine (XIVE Gen1)
-==========================================================
-
-Device types supported:
- KVM_DEV_TYPE_XIVE POWER9 XIVE Interrupt Controller generation 1
-
-This device acts as a VM interrupt controller. It provides the KVM
-interface to configure the interrupt sources of a VM in the underlying
-POWER9 XIVE interrupt controller.
-
-Only one XIVE instance may be instantiated. A guest XIVE device
-requires a POWER9 host and the guest OS should have support for the
-XIVE native exploitation interrupt mode. If not, it should run using
-the legacy interrupt mode, referred as XICS (POWER7/8).
-
-* Device Mappings
-
- The KVM device exposes different MMIO ranges of the XIVE HW which
- are required for interrupt management. These are exposed to the
- guest in VMAs populated with a custom VM fault handler.
-
- 1. Thread Interrupt Management Area (TIMA)
-
- Each thread has an associated Thread Interrupt Management context
- composed of a set of registers. These registers let the thread
- handle priority management and interrupt acknowledgment. The most
- important are :
-
- - Interrupt Pending Buffer (IPB)
- - Current Processor Priority (CPPR)
- - Notification Source Register (NSR)
-
- They are exposed to software in four different pages each proposing
- a view with a different privilege. The first page is for the
- physical thread context and the second for the hypervisor. Only the
- third (operating system) and the fourth (user level) are exposed the
- guest.
-
- 2. Event State Buffer (ESB)
-
- Each source is associated with an Event State Buffer (ESB) with
- either a pair of even/odd pair of pages which provides commands to
- manage the source: to trigger, to EOI, to turn off the source for
- instance.
-
- 3. Device pass-through
-
- When a device is passed-through into the guest, the source
- interrupts are from a different HW controller (PHB4) and the ESB
- pages exposed to the guest should accommadate this change.
-
- The passthru_irq helpers, kvmppc_xive_set_mapped() and
- kvmppc_xive_clr_mapped() are called when the device HW irqs are
- mapped into or unmapped from the guest IRQ number space. The KVM
- device extends these helpers to clear the ESB pages of the guest IRQ
- number being mapped and then lets the VM fault handler repopulate.
- The handler will insert the ESB page corresponding to the HW
- interrupt of the device being passed-through or the initial IPI ESB
- page if the device has being removed.
-
- The ESB remapping is fully transparent to the guest and the OS
- device driver. All handling is done within VFIO and the above
- helpers in KVM-PPC.
-
-* Groups:
-
- 1. KVM_DEV_XIVE_GRP_CTRL
- Provides global controls on the device
- Attributes:
- 1.1 KVM_DEV_XIVE_RESET (write only)
- Resets the interrupt controller configuration for sources and event
- queues. To be used by kexec and kdump.
- Errors: none
-
- 1.2 KVM_DEV_XIVE_EQ_SYNC (write only)
- Sync all the sources and queues and mark the EQ pages dirty. This
- to make sure that a consistent memory state is captured when
- migrating the VM.
- Errors: none
-
- 2. KVM_DEV_XIVE_GRP_SOURCE (write only)
- Initializes a new source in the XIVE device and mask it.
- Attributes:
- Interrupt source number (64-bit)
- The kvm_device_attr.addr points to a __u64 value:
- bits: | 63 .... 2 | 1 | 0
- values: | unused | level | type
- - type: 0:MSI 1:LSI
- - level: assertion level in case of an LSI.
- Errors:
- -E2BIG: Interrupt source number is out of range
- -ENOMEM: Could not create a new source block
- -EFAULT: Invalid user pointer for attr->addr.
- -ENXIO: Could not allocate underlying HW interrupt
-
- 3. KVM_DEV_XIVE_GRP_SOURCE_CONFIG (write only)
- Configures source targeting
- Attributes:
- Interrupt source number (64-bit)
- The kvm_device_attr.addr points to a __u64 value:
- bits: | 63 .... 33 | 32 | 31 .. 3 | 2 .. 0
- values: | eisn | mask | server | priority
- - priority: 0-7 interrupt priority level
- - server: CPU number chosen to handle the interrupt
- - mask: mask flag (unused)
- - eisn: Effective Interrupt Source Number
- Errors:
- -ENOENT: Unknown source number
- -EINVAL: Not initialized source number
- -EINVAL: Invalid priority
- -EINVAL: Invalid CPU number.
- -EFAULT: Invalid user pointer for attr->addr.
- -ENXIO: CPU event queues not configured or configuration of the
- underlying HW interrupt failed
- -EBUSY: No CPU available to serve interrupt
-
- 4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
- Configures an event queue of a CPU
- Attributes:
- EQ descriptor identifier (64-bit)
- The EQ descriptor identifier is a tuple (server, priority) :
- bits: | 63 .... 32 | 31 .. 3 | 2 .. 0
- values: | unused | server | priority
- The kvm_device_attr.addr points to :
- struct kvm_ppc_xive_eq {
- __u32 flags;
- __u32 qshift;
- __u64 qaddr;
- __u32 qtoggle;
- __u32 qindex;
- __u8 pad[40];
- };
- - flags: queue flags
- KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
- forces notification without using the coalescing mechanism
- provided by the XIVE END ESBs.
- - qshift: queue size (power of 2)
- - qaddr: real address of queue
- - qtoggle: current queue toggle bit
- - qindex: current queue index
- - pad: reserved for future use
- Errors:
- -ENOENT: Invalid CPU number
- -EINVAL: Invalid priority
- -EINVAL: Invalid flags
- -EINVAL: Invalid queue size
- -EINVAL: Invalid queue address
- -EFAULT: Invalid user pointer for attr->addr.
- -EIO: Configuration of the underlying HW failed
-
- 5. KVM_DEV_XIVE_GRP_SOURCE_SYNC (write only)
- Synchronize the source to flush event notifications
- Attributes:
- Interrupt source number (64-bit)
- Errors:
- -ENOENT: Unknown source number
- -EINVAL: Not initialized source number
-
-* VCPU state
-
- The XIVE IC maintains VP interrupt state in an internal structure
- called the NVT. When a VP is not dispatched on a HW processor
- thread, this structure can be updated by HW if the VP is the target
- of an event notification.
-
- It is important for migration to capture the cached IPB from the NVT
- as it synthesizes the priorities of the pending interrupts. We
- capture a bit more to report debug information.
-
- KVM_REG_PPC_VP_STATE (2 * 64bits)
- bits: | 63 .... 32 | 31 .... 0 |
- values: | TIMA word0 | TIMA word1 |
- bits: | 127 .......... 64 |
- values: | unused |
-
-* Migration:
-
- Saving the state of a VM using the XIVE native exploitation mode
- should follow a specific sequence. When the VM is stopped :
-
- 1. Mask all sources (PQ=01) to stop the flow of events.
-
- 2. Sync the XIVE device with the KVM control KVM_DEV_XIVE_EQ_SYNC to
- flush any in-flight event notification and to stabilize the EQs. At
- this stage, the EQ pages are marked dirty to make sure they are
- transferred in the migration sequence.
-
- 3. Capture the state of the source targeting, the EQs configuration
- and the state of thread interrupt context registers.
-
- Restore is similar :
-
- 1. Restore the EQ configuration. As targeting depends on it.
- 2. Restore targeting
- 3. Restore the thread interrupt contexts
- 4. Restore the source states
- 5. Let the vCPU run
+++ /dev/null
-The KVM halt polling system
-===========================
-
-The KVM halt polling system provides a feature within KVM whereby the latency
-of a guest can, under some circumstances, be reduced by polling in the host
-for some time period after the guest has elected to no longer run by cedeing.
-That is, when a guest vcpu has ceded, or in the case of powerpc when all of the
-vcpus of a single vcore have ceded, the host kernel polls for wakeup conditions
-before giving up the cpu to the scheduler in order to let something else run.
-
-Polling provides a latency advantage in cases where the guest can be run again
-very quickly by at least saving us a trip through the scheduler, normally on
-the order of a few micro-seconds, although performance benefits are workload
-dependant. In the event that no wakeup source arrives during the polling
-interval or some other task on the runqueue is runnable the scheduler is
-invoked. Thus halt polling is especially useful on workloads with very short
-wakeup periods where the time spent halt polling is minimised and the time
-savings of not invoking the scheduler are distinguishable.
-
-The generic halt polling code is implemented in:
-
- virt/kvm/kvm_main.c: kvm_vcpu_block()
-
-The powerpc kvm-hv specific case is implemented in:
-
- arch/powerpc/kvm/book3s_hv.c: kvmppc_vcore_blocked()
-
-Halt Polling Interval
-=====================
-
-The maximum time for which to poll before invoking the scheduler, referred to
-as the halt polling interval, is increased and decreased based on the perceived
-effectiveness of the polling in an attempt to limit pointless polling.
-This value is stored in either the vcpu struct:
-
- kvm_vcpu->halt_poll_ns
-
-or in the case of powerpc kvm-hv, in the vcore struct:
-
- kvmppc_vcore->halt_poll_ns
-
-Thus this is a per vcpu (or vcore) value.
-
-During polling if a wakeup source is received within the halt polling interval,
-the interval is left unchanged. In the event that a wakeup source isn't
-received during the polling interval (and thus schedule is invoked) there are
-two options, either the polling interval and total block time[0] were less than
-the global max polling interval (see module params below), or the total block
-time was greater than the global max polling interval.
-
-In the event that both the polling interval and total block time were less than
-the global max polling interval then the polling interval can be increased in
-the hope that next time during the longer polling interval the wake up source
-will be received while the host is polling and the latency benefits will be
-received. The polling interval is grown in the function grow_halt_poll_ns() and
-is multiplied by the module parameters halt_poll_ns_grow and
-halt_poll_ns_grow_start.
-
-In the event that the total block time was greater than the global max polling
-interval then the host will never poll for long enough (limited by the global
-max) to wakeup during the polling interval so it may as well be shrunk in order
-to avoid pointless polling. The polling interval is shrunk in the function
-shrink_halt_poll_ns() and is divided by the module parameter
-halt_poll_ns_shrink, or set to 0 iff halt_poll_ns_shrink == 0.
-
-It is worth noting that this adjustment process attempts to hone in on some
-steady state polling interval but will only really do a good job for wakeups
-which come at an approximately constant rate, otherwise there will be constant
-adjustment of the polling interval.
-
-[0] total block time: the time between when the halt polling function is
- invoked and a wakeup source received (irrespective of
- whether the scheduler is invoked within that function).
-
-Module Parameters
-=================
-
-The kvm module has 3 tuneable module parameters to adjust the global max
-polling interval as well as the rate at which the polling interval is grown and
-shrunk. These variables are defined in include/linux/kvm_host.h and as module
-parameters in virt/kvm/kvm_main.c, or arch/powerpc/kvm/book3s_hv.c in the
-powerpc kvm-hv case.
-
-Module Parameter | Description | Default Value
---------------------------------------------------------------------------------
-halt_poll_ns | The global max polling | KVM_HALT_POLL_NS_DEFAULT
- | interval which defines |
- | the ceiling value of the |
- | polling interval for | (per arch value)
- | each vcpu. |
---------------------------------------------------------------------------------
-halt_poll_ns_grow | The value by which the | 2
- | halt polling interval is |
- | multiplied in the |
- | grow_halt_poll_ns() |
- | function. |
---------------------------------------------------------------------------------
-halt_poll_ns_grow_start | The initial value to grow | 10000
- | to from zero in the |
- | grow_halt_poll_ns() |
- | function. |
---------------------------------------------------------------------------------
-halt_poll_ns_shrink | The value by which the | 0
- | halt polling interval is |
- | divided in the |
- | shrink_halt_poll_ns() |
- | function. |
---------------------------------------------------------------------------------
-
-These module parameters can be set from the debugfs files in:
-
- /sys/module/kvm/parameters/
-
-Note: that these module parameters are system wide values and are not able to
- be tuned on a per vm basis.
-
-Further Notes
-=============
-
-- Care should be taken when setting the halt_poll_ns module parameter as a
-large value has the potential to drive the cpu usage to 100% on a machine which
-would be almost entirely idle otherwise. This is because even if a guest has
-wakeups during which very little work is done and which are quite far apart, if
-the period is shorter than the global max polling interval (halt_poll_ns) then
-the host will always poll for the entire block time and thus cpu utilisation
-will go to 100%.
-
-- Halt polling essentially presents a trade off between power usage and latency
-and the module parameters should be used to tune the affinity for this. Idle
-cpu time is essentially converted to host kernel time with the aim of decreasing
-latency when entering the guest.
-
-- Halt polling will only be conducted by the host when no other tasks are
-runnable on that cpu, otherwise the polling will cease immediately and
-schedule will be invoked to allow that other task to run. Thus this doesn't
-allow a guest to denial of service the cpu.
+++ /dev/null
-Linux KVM Hypercall:
-===================
-X86:
- KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall
- instruction. The hypervisor can replace it with instructions that are
- guaranteed to be supported.
-
- Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
- The hypercall number should be placed in rax and the return value will be
- placed in rax. No other registers will be clobbered unless explicitly stated
- by the particular hypercall.
-
-S390:
- R2-R7 are used for parameters 1-6. In addition, R1 is used for hypercall
- number. The return value is written to R2.
-
- S390 uses diagnose instruction as hypercall (0x500) along with hypercall
- number in R1.
-
- For further information on the S390 diagnose call as supported by KVM,
- refer to Documentation/virtual/kvm/s390-diag.txt.
-
- PowerPC:
- It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
- Return value is placed in R3.
-
- KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
- property inside the device tree's /hypervisor node.
- For more information refer to Documentation/virtual/kvm/ppc-pv.txt
-
-MIPS:
- KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall
- number in $2 (v0). Up to four arguments may be placed in $4-$7 (a0-a3) and
- the return value is placed in $2 (v0).
-
-KVM Hypercalls Documentation
-===========================
-The template for each hypercall is:
-1. Hypercall name.
-2. Architecture(s)
-3. Status (deprecated, obsolete, active)
-4. Purpose
-
-1. KVM_HC_VAPIC_POLL_IRQ
-------------------------
-Architecture: x86
-Status: active
-Purpose: Trigger guest exit so that the host can check for pending
-interrupts on reentry.
-
-2. KVM_HC_MMU_OP
-------------------------
-Architecture: x86
-Status: deprecated.
-Purpose: Support MMU operations such as writing to PTE,
-flushing TLB, release PT.
-
-3. KVM_HC_FEATURES
-------------------------
-Architecture: PPC
-Status: active
-Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid
-used to enumerate which hypercalls are available. On PPC, either device tree
-based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration
-mechanism (which is this hypercall) can be used.
-
-4. KVM_HC_PPC_MAP_MAGIC_PAGE
-------------------------
-Architecture: PPC
-Status: active
-Purpose: To enable communication between the hypervisor and guest there is a
-shared page that contains parts of supervisor visible register state.
-The guest can map this shared page to access its supervisor register through
-memory using this hypercall.
-
-5. KVM_HC_KICK_CPU
-------------------------
-Architecture: x86
-Status: active
-Purpose: Hypercall used to wakeup a vcpu from HLT state
-Usage example : A vcpu of a paravirtualized guest that is busywaiting in guest
-kernel mode for an event to occur (ex: a spinlock to become available) can
-execute HLT instruction once it has busy-waited for more than a threshold
-time-interval. Execution of HLT instruction would cause the hypervisor to put
-the vcpu to sleep until occurrence of an appropriate event. Another vcpu of the
-same guest can wakeup the sleeping vcpu by issuing KVM_HC_KICK_CPU hypercall,
-specifying APIC ID (a1) of the vcpu to be woken up. An additional argument (a0)
-is used in the hypercall for future use.
-
-
-6. KVM_HC_CLOCK_PAIRING
-------------------------
-Architecture: x86
-Status: active
-Purpose: Hypercall used to synchronize host and guest clocks.
-Usage:
-
-a0: guest physical address where host copies
-"struct kvm_clock_offset" structure.
-
-a1: clock_type, ATM only KVM_CLOCK_PAIRING_WALLCLOCK (0)
-is supported (corresponding to the host's CLOCK_REALTIME clock).
-
- struct kvm_clock_pairing {
- __s64 sec;
- __s64 nsec;
- __u64 tsc;
- __u32 flags;
- __u32 pad[9];
- };
-
- Where:
- * sec: seconds from clock_type clock.
- * nsec: nanoseconds from clock_type clock.
- * tsc: guest TSC value used to calculate sec/nsec pair
- * flags: flags, unused (0) at the moment.
-
-The hypercall lets a guest compute a precise timestamp across
-host and guest. The guest can use the returned TSC value to
-compute the CLOCK_REALTIME for its clock, at the same instant.
-
-Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,
-or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.
-
-6. KVM_HC_SEND_IPI
-------------------------
-Architecture: x86
-Status: active
-Purpose: Send IPIs to multiple vCPUs.
-
-a0: lower part of the bitmap of destination APIC IDs
-a1: higher part of the bitmap of destination APIC IDs
-a2: the lowest APIC ID in bitmap
-a3: APIC ICR
-
-The hypercall lets a guest send multicast IPIs, with at most 128
-128 destinations per hypercall in 64-bit mode and 64 vCPUs per
-hypercall in 32-bit mode. The destinations are represented by a
-bitmap contained in the first two arguments (a0 and a1). Bit 0 of
-a0 corresponds to the APIC ID in the third argument (a2), bit 1
-corresponds to the APIC ID a2+1, and so on.
-
-Returns the number of CPUs to which the IPIs were delivered successfully.
-
-7. KVM_HC_SCHED_YIELD
-------------------------
-Architecture: x86
-Status: active
-Purpose: Hypercall used to yield if the IPI target vCPU is preempted
-
-a0: destination APIC ID
-
-Usage example: When sending a call-function IPI-many to vCPUs, yield if
-any of the IPI target vCPUs was preempted.
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-
-===
-KVM
-===
-
-.. toctree::
- :maxdepth: 2
-
- amd-memory-encryption
- cpuid
+++ /dev/null
-KVM Lock Overview
-=================
-
-1. Acquisition Orders
----------------------
-
-The acquisition orders for mutexes are as follows:
-
-- kvm->lock is taken outside vcpu->mutex
-
-- kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock
-
-- kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
- them together is quite rare.
-
-On x86, vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock.
-
-Everything else is a leaf: no other lock is taken inside the critical
-sections.
-
-2: Exception
-------------
-
-Fast page fault:
-
-Fast page fault is the fast path which fixes the guest page fault out of
-the mmu-lock on x86. Currently, the page fault can be fast in one of the
-following two cases:
-
-1. Access Tracking: The SPTE is not present, but it is marked for access
-tracking i.e. the SPTE_SPECIAL_MASK is set. That means we need to
-restore the saved R/X bits. This is described in more detail later below.
-
-2. Write-Protection: The SPTE is present and the fault is
-caused by write-protect. That means we just need to change the W bit of the
-spte.
-
-What we use to avoid all the race is the SPTE_HOST_WRITEABLE bit and
-SPTE_MMU_WRITEABLE bit on the spte:
-- SPTE_HOST_WRITEABLE means the gfn is writable on host.
-- SPTE_MMU_WRITEABLE means the gfn is writable on mmu. The bit is set when
- the gfn is writable on guest mmu and it is not write-protected by shadow
- page write-protection.
-
-On fast page fault path, we will use cmpxchg to atomically set the spte W
-bit if spte.SPTE_HOST_WRITEABLE = 1 and spte.SPTE_WRITE_PROTECT = 1, or
-restore the saved R/X bits if VMX_EPT_TRACK_ACCESS mask is set, or both. This
-is safe because whenever changing these bits can be detected by cmpxchg.
-
-But we need carefully check these cases:
-1): The mapping from gfn to pfn
-The mapping from gfn to pfn may be changed since we can only ensure the pfn
-is not changed during cmpxchg. This is a ABA problem, for example, below case
-will happen:
-
-At the beginning:
-gpte = gfn1
-gfn1 is mapped to pfn1 on host
-spte is the shadow page table entry corresponding with gpte and
-spte = pfn1
-
- VCPU 0 VCPU0
-on fast page fault path:
-
- old_spte = *spte;
- pfn1 is swapped out:
- spte = 0;
-
- pfn1 is re-alloced for gfn2.
-
- gpte is changed to point to
- gfn2 by the guest:
- spte = pfn1;
-
- if (cmpxchg(spte, old_spte, old_spte+W)
- mark_page_dirty(vcpu->kvm, gfn1)
- OOPS!!!
-
-We dirty-log for gfn1, that means gfn2 is lost in dirty-bitmap.
-
-For direct sp, we can easily avoid it since the spte of direct sp is fixed
-to gfn. For indirect sp, before we do cmpxchg, we call gfn_to_pfn_atomic()
-to pin gfn to pfn, because after gfn_to_pfn_atomic():
-- We have held the refcount of pfn that means the pfn can not be freed and
- be reused for another gfn.
-- The pfn is writable that means it can not be shared between different gfns
- by KSM.
-
-Then, we can ensure the dirty bitmaps is correctly set for a gfn.
-
-Currently, to simplify the whole things, we disable fast page fault for
-indirect shadow page.
-
-2): Dirty bit tracking
-In the origin code, the spte can be fast updated (non-atomically) if the
-spte is read-only and the Accessed bit has already been set since the
-Accessed bit and Dirty bit can not be lost.
-
-But it is not true after fast page fault since the spte can be marked
-writable between reading spte and updating spte. Like below case:
-
-At the beginning:
-spte.W = 0
-spte.Accessed = 1
-
- VCPU 0 VCPU0
-In mmu_spte_clear_track_bits():
-
- old_spte = *spte;
-
- /* 'if' condition is satisfied. */
- if (old_spte.Accessed == 1 &&
- old_spte.W == 0)
- spte = 0ull;
- on fast page fault path:
- spte.W = 1
- memory write on the spte:
- spte.Dirty = 1
-
-
- else
- old_spte = xchg(spte, 0ull)
-
-
- if (old_spte.Accessed == 1)
- kvm_set_pfn_accessed(spte.pfn);
- if (old_spte.Dirty == 1)
- kvm_set_pfn_dirty(spte.pfn);
- OOPS!!!
-
-The Dirty bit is lost in this case.
-
-In order to avoid this kind of issue, we always treat the spte as "volatile"
-if it can be updated out of mmu-lock, see spte_has_volatile_bits(), it means,
-the spte is always atomically updated in this case.
-
-3): flush tlbs due to spte updated
-If the spte is updated from writable to readonly, we should flush all TLBs,
-otherwise rmap_write_protect will find a read-only spte, even though the
-writable spte might be cached on a CPU's TLB.
-
-As mentioned before, the spte can be updated to writable out of mmu-lock on
-fast page fault path, in order to easily audit the path, we see if TLBs need
-be flushed caused by this reason in mmu_spte_update() since this is a common
-function to update spte (present -> present).
-
-Since the spte is "volatile" if it can be updated out of mmu-lock, we always
-atomically update the spte, the race caused by fast page fault can be avoided,
-See the comments in spte_has_volatile_bits() and mmu_spte_update().
-
-Lockless Access Tracking:
-
-This is used for Intel CPUs that are using EPT but do not support the EPT A/D
-bits. In this case, when the KVM MMU notifier is called to track accesses to a
-page (via kvm_mmu_notifier_clear_flush_young), it marks the PTE as not-present
-by clearing the RWX bits in the PTE and storing the original R & X bits in
-some unused/ignored bits. In addition, the SPTE_SPECIAL_MASK is also set on the
-PTE (using the ignored bit 62). When the VM tries to access the page later on,
-a fault is generated and the fast page fault mechanism described above is used
-to atomically restore the PTE to a Present state. The W bit is not saved when
-the PTE is marked for access tracking and during restoration to the Present
-state, the W bit is set depending on whether or not it was a write access. If
-it wasn't, then the W bit will remain clear until a write access happens, at
-which time it will be set using the Dirty tracking mechanism described above.
-
-3. Reference
-------------
-
-Name: kvm_lock
-Type: mutex
-Arch: any
-Protects: - vm_list
-
-Name: kvm_count_lock
-Type: raw_spinlock_t
-Arch: any
-Protects: - hardware virtualization enable/disable
-Comment: 'raw' because hardware enabling/disabling must be atomic /wrt
- migration.
-
-Name: kvm_arch::tsc_write_lock
-Type: raw_spinlock
-Arch: x86
-Protects: - kvm_arch::{last_tsc_write,last_tsc_nsec,last_tsc_offset}
- - tsc offset in vmcb
-Comment: 'raw' because updating the tsc offsets must not be preempted.
-
-Name: kvm->mmu_lock
-Type: spinlock_t
-Arch: any
-Protects: -shadow page/shadow tlb entry
-Comment: it is a spinlock since it is used in mmu notifier.
-
-Name: kvm->srcu
-Type: srcu lock
-Arch: any
-Protects: - kvm->memslots
- - kvm->buses
-Comment: The srcu read lock must be held while accessing memslots (e.g.
- when using gfn_to_* functions) and while accessing in-kernel
- MMIO/PIO address->device structure mapping (kvm->buses).
- The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu
- if it is needed by multiple functions.
-
-Name: blocked_vcpu_on_cpu_lock
-Type: spinlock_t
-Arch: x86
-Protects: blocked_vcpu_on_cpu
-Comment: This is a per-CPU lock and it is used for VT-d posted-interrupts.
- When VT-d posted-interrupts is supported and the VM has assigned
- devices, we put the blocked vCPU on the list blocked_vcpu_on_cpu
- protected by blocked_vcpu_on_cpu_lock, when VT-d hardware issues
- wakeup notification event since external interrupts from the
- assigned devices happens, we will find the vCPU on the list to
- wakeup.
+++ /dev/null
-The x86 kvm shadow mmu
-======================
-
-The mmu (in arch/x86/kvm, files mmu.[ch] and paging_tmpl.h) is responsible
-for presenting a standard x86 mmu to the guest, while translating guest
-physical addresses to host physical addresses.
-
-The mmu code attempts to satisfy the following requirements:
-
-- correctness: the guest should not be able to determine that it is running
- on an emulated mmu except for timing (we attempt to comply
- with the specification, not emulate the characteristics of
- a particular implementation such as tlb size)
-- security: the guest must not be able to touch host memory not assigned
- to it
-- performance: minimize the performance penalty imposed by the mmu
-- scaling: need to scale to large memory and large vcpu guests
-- hardware: support the full range of x86 virtualization hardware
-- integration: Linux memory management code must be in control of guest memory
- so that swapping, page migration, page merging, transparent
- hugepages, and similar features work without change
-- dirty tracking: report writes to guest memory to enable live migration
- and framebuffer-based displays
-- footprint: keep the amount of pinned kernel memory low (most memory
- should be shrinkable)
-- reliability: avoid multipage or GFP_ATOMIC allocations
-
-Acronyms
-========
-
-pfn host page frame number
-hpa host physical address
-hva host virtual address
-gfn guest frame number
-gpa guest physical address
-gva guest virtual address
-ngpa nested guest physical address
-ngva nested guest virtual address
-pte page table entry (used also to refer generically to paging structure
- entries)
-gpte guest pte (referring to gfns)
-spte shadow pte (referring to pfns)
-tdp two dimensional paging (vendor neutral term for NPT and EPT)
-
-Virtual and real hardware supported
-===================================
-
-The mmu supports first-generation mmu hardware, which allows an atomic switch
-of the current paging mode and cr3 during guest entry, as well as
-two-dimensional paging (AMD's NPT and Intel's EPT). The emulated hardware
-it exposes is the traditional 2/3/4 level x86 mmu, with support for global
-pages, pae, pse, pse36, cr0.wp, and 1GB pages. Emulated hardware also
-able to expose NPT capable hardware on NPT capable hosts.
-
-Translation
-===========
-
-The primary job of the mmu is to program the processor's mmu to translate
-addresses for the guest. Different translations are required at different
-times:
-
-- when guest paging is disabled, we translate guest physical addresses to
- host physical addresses (gpa->hpa)
-- when guest paging is enabled, we translate guest virtual addresses, to
- guest physical addresses, to host physical addresses (gva->gpa->hpa)
-- when the guest launches a guest of its own, we translate nested guest
- virtual addresses, to nested guest physical addresses, to guest physical
- addresses, to host physical addresses (ngva->ngpa->gpa->hpa)
-
-The primary challenge is to encode between 1 and 3 translations into hardware
-that support only 1 (traditional) and 2 (tdp) translations. When the
-number of required translations matches the hardware, the mmu operates in
-direct mode; otherwise it operates in shadow mode (see below).
-
-Memory
-======
-
-Guest memory (gpa) is part of the user address space of the process that is
-using kvm. Userspace defines the translation between guest addresses and user
-addresses (gpa->hva); note that two gpas may alias to the same hva, but not
-vice versa.
-
-These hvas may be backed using any method available to the host: anonymous
-memory, file backed memory, and device memory. Memory might be paged by the
-host at any time.
-
-Events
-======
-
-The mmu is driven by events, some from the guest, some from the host.
-
-Guest generated events:
-- writes to control registers (especially cr3)
-- invlpg/invlpga instruction execution
-- access to missing or protected translations
-
-Host generated events:
-- changes in the gpa->hpa translation (either through gpa->hva changes or
- through hva->hpa changes)
-- memory pressure (the shrinker)
-
-Shadow pages
-============
-
-The principal data structure is the shadow page, 'struct kvm_mmu_page'. A
-shadow page contains 512 sptes, which can be either leaf or nonleaf sptes. A
-shadow page may contain a mix of leaf and nonleaf sptes.
-
-A nonleaf spte allows the hardware mmu to reach the leaf pages and
-is not related to a translation directly. It points to other shadow pages.
-
-A leaf spte corresponds to either one or two translations encoded into
-one paging structure entry. These are always the lowest level of the
-translation stack, with optional higher level translations left to NPT/EPT.
-Leaf ptes point at guest pages.
-
-The following table shows translations encoded by leaf ptes, with higher-level
-translations in parentheses:
-
- Non-nested guests:
- nonpaging: gpa->hpa
- paging: gva->gpa->hpa
- paging, tdp: (gva->)gpa->hpa
- Nested guests:
- non-tdp: ngva->gpa->hpa (*)
- tdp: (ngva->)ngpa->gpa->hpa
-
-(*) the guest hypervisor will encode the ngva->gpa translation into its page
- tables if npt is not present
-
-Shadow pages contain the following information:
- role.level:
- The level in the shadow paging hierarchy that this shadow page belongs to.
- 1=4k sptes, 2=2M sptes, 3=1G sptes, etc.
- role.direct:
- If set, leaf sptes reachable from this page are for a linear range.
- Examples include real mode translation, large guest pages backed by small
- host pages, and gpa->hpa translations when NPT or EPT is active.
- The linear range starts at (gfn << PAGE_SHIFT) and its size is determined
- by role.level (2MB for first level, 1GB for second level, 0.5TB for third
- level, 256TB for fourth level)
- If clear, this page corresponds to a guest page table denoted by the gfn
- field.
- role.quadrant:
- When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit
- sptes. That means a guest page table contains more ptes than the host,
- so multiple shadow pages are needed to shadow one guest page.
- For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the
- first or second 512-gpte block in the guest page table. For second-level
- page tables, each 32-bit gpte is converted to two 64-bit sptes
- (since each first-level guest page is shadowed by two first-level
- shadow pages) so role.quadrant takes values in the range 0..3. Each
- quadrant maps 1GB virtual address space.
- role.access:
- Inherited guest access permissions in the form uwx. Note execute
- permission is positive, not negative.
- role.invalid:
- The page is invalid and should not be used. It is a root page that is
- currently pinned (by a cpu hardware register pointing to it); once it is
- unpinned it will be destroyed.
- role.gpte_is_8_bytes:
- Reflects the size of the guest PTE for which the page is valid, i.e. '1'
- if 64-bit gptes are in use, '0' if 32-bit gptes are in use.
- role.nxe:
- Contains the value of efer.nxe for which the page is valid.
- role.cr0_wp:
- Contains the value of cr0.wp for which the page is valid.
- role.smep_andnot_wp:
- Contains the value of cr4.smep && !cr0.wp for which the page is valid
- (pages for which this is true are different from other pages; see the
- treatment of cr0.wp=0 below).
- role.smap_andnot_wp:
- Contains the value of cr4.smap && !cr0.wp for which the page is valid
- (pages for which this is true are different from other pages; see the
- treatment of cr0.wp=0 below).
- role.ept_sp:
- This is a virtual flag to denote a shadowed nested EPT page. ept_sp
- is true if "cr0_wp && smap_andnot_wp", an otherwise invalid combination.
- role.smm:
- Is 1 if the page is valid in system management mode. This field
- determines which of the kvm_memslots array was used to build this
- shadow page; it is also used to go back from a struct kvm_mmu_page
- to a memslot, through the kvm_memslots_for_spte_role macro and
- __gfn_to_memslot.
- role.ad_disabled:
- Is 1 if the MMU instance cannot use A/D bits. EPT did not have A/D
- bits before Haswell; shadow EPT page tables also cannot use A/D bits
- if the L1 hypervisor does not enable them.
- gfn:
- Either the guest page table containing the translations shadowed by this
- page, or the base page frame for linear translations. See role.direct.
- spt:
- A pageful of 64-bit sptes containing the translations for this page.
- Accessed by both kvm and hardware.
- The page pointed to by spt will have its page->private pointing back
- at the shadow page structure.
- sptes in spt point either at guest pages, or at lower-level shadow pages.
- Specifically, if sp1 and sp2 are shadow pages, then sp1->spt[n] may point
- at __pa(sp2->spt). sp2 will point back at sp1 through parent_pte.
- The spt array forms a DAG structure with the shadow page as a node, and
- guest pages as leaves.
- gfns:
- An array of 512 guest frame numbers, one for each present pte. Used to
- perform a reverse map from a pte to a gfn. When role.direct is set, any
- element of this array can be calculated from the gfn field when used, in
- this case, the array of gfns is not allocated. See role.direct and gfn.
- root_count:
- A counter keeping track of how many hardware registers (guest cr3 or
- pdptrs) are now pointing at the page. While this counter is nonzero, the
- page cannot be destroyed. See role.invalid.
- parent_ptes:
- The reverse mapping for the pte/ptes pointing at this page's spt. If
- parent_ptes bit 0 is zero, only one spte points at this page and
- parent_ptes points at this single spte, otherwise, there exists multiple
- sptes pointing at this page and (parent_ptes & ~0x1) points at a data
- structure with a list of parent sptes.
- unsync:
- If true, then the translations in this page may not match the guest's
- translation. This is equivalent to the state of the tlb when a pte is
- changed but before the tlb entry is flushed. Accordingly, unsync ptes
- are synchronized when the guest executes invlpg or flushes its tlb by
- other means. Valid for leaf pages.
- unsync_children:
- How many sptes in the page point at pages that are unsync (or have
- unsynchronized children).
- unsync_child_bitmap:
- A bitmap indicating which sptes in spt point (directly or indirectly) at
- pages that may be unsynchronized. Used to quickly locate all unsychronized
- pages reachable from a given page.
- clear_spte_count:
- Only present on 32-bit hosts, where a 64-bit spte cannot be written
- atomically. The reader uses this while running out of the MMU lock
- to detect in-progress updates and retry them until the writer has
- finished the write.
- write_flooding_count:
- A guest may write to a page table many times, causing a lot of
- emulations if the page needs to be write-protected (see "Synchronized
- and unsynchronized pages" below). Leaf pages can be unsynchronized
- so that they do not trigger frequent emulation, but this is not
- possible for non-leafs. This field counts the number of emulations
- since the last time the page table was actually used; if emulation
- is triggered too frequently on this page, KVM will unmap the page
- to avoid emulation in the future.
-
-Reverse map
-===========
-
-The mmu maintains a reverse mapping whereby all ptes mapping a page can be
-reached given its gfn. This is used, for example, when swapping out a page.
-
-Synchronized and unsynchronized pages
-=====================================
-
-The guest uses two events to synchronize its tlb and page tables: tlb flushes
-and page invalidations (invlpg).
-
-A tlb flush means that we need to synchronize all sptes reachable from the
-guest's cr3. This is expensive, so we keep all guest page tables write
-protected, and synchronize sptes to gptes when a gpte is written.
-
-A special case is when a guest page table is reachable from the current
-guest cr3. In this case, the guest is obliged to issue an invlpg instruction
-before using the translation. We take advantage of that by removing write
-protection from the guest page, and allowing the guest to modify it freely.
-We synchronize modified gptes when the guest invokes invlpg. This reduces
-the amount of emulation we have to do when the guest modifies multiple gptes,
-or when the a guest page is no longer used as a page table and is used for
-random guest data.
-
-As a side effect we have to resynchronize all reachable unsynchronized shadow
-pages on a tlb flush.
-
-
-Reaction to events
-==================
-
-- guest page fault (or npt page fault, or ept violation)
-
-This is the most complicated event. The cause of a page fault can be:
-
- - a true guest fault (the guest translation won't allow the access) (*)
- - access to a missing translation
- - access to a protected translation
- - when logging dirty pages, memory is write protected
- - synchronized shadow pages are write protected (*)
- - access to untranslatable memory (mmio)
-
- (*) not applicable in direct mode
-
-Handling a page fault is performed as follows:
-
- - if the RSV bit of the error code is set, the page fault is caused by guest
- accessing MMIO and cached MMIO information is available.
- - walk shadow page table
- - check for valid generation number in the spte (see "Fast invalidation of
- MMIO sptes" below)
- - cache the information to vcpu->arch.mmio_gva, vcpu->arch.access and
- vcpu->arch.mmio_gfn, and call the emulator
- - If both P bit and R/W bit of error code are set, this could possibly
- be handled as a "fast page fault" (fixed without taking the MMU lock). See
- the description in Documentation/virtual/kvm/locking.txt.
- - if needed, walk the guest page tables to determine the guest translation
- (gva->gpa or ngpa->gpa)
- - if permissions are insufficient, reflect the fault back to the guest
- - determine the host page
- - if this is an mmio request, there is no host page; cache the info to
- vcpu->arch.mmio_gva, vcpu->arch.access and vcpu->arch.mmio_gfn
- - walk the shadow page table to find the spte for the translation,
- instantiating missing intermediate page tables as necessary
- - If this is an mmio request, cache the mmio info to the spte and set some
- reserved bit on the spte (see callers of kvm_mmu_set_mmio_spte_mask)
- - try to unsynchronize the page
- - if successful, we can let the guest continue and modify the gpte
- - emulate the instruction
- - if failed, unshadow the page and let the guest continue
- - update any translations that were modified by the instruction
-
-invlpg handling:
-
- - walk the shadow page hierarchy and drop affected translations
- - try to reinstantiate the indicated translation in the hope that the
- guest will use it in the near future
-
-Guest control register updates:
-
-- mov to cr3
- - look up new shadow roots
- - synchronize newly reachable shadow pages
-
-- mov to cr0/cr4/efer
- - set up mmu context for new paging mode
- - look up new shadow roots
- - synchronize newly reachable shadow pages
-
-Host translation updates:
-
- - mmu notifier called with updated hva
- - look up affected sptes through reverse map
- - drop (or update) translations
-
-Emulating cr0.wp
-================
-
-If tdp is not enabled, the host must keep cr0.wp=1 so page write protection
-works for the guest kernel, not guest guest userspace. When the guest
-cr0.wp=1, this does not present a problem. However when the guest cr0.wp=0,
-we cannot map the permissions for gpte.u=1, gpte.w=0 to any spte (the
-semantics require allowing any guest kernel access plus user read access).
-
-We handle this by mapping the permissions to two possible sptes, depending
-on fault type:
-
-- kernel write fault: spte.u=0, spte.w=1 (allows full kernel access,
- disallows user access)
-- read fault: spte.u=1, spte.w=0 (allows full read access, disallows kernel
- write access)
-
-(user write faults generate a #PF)
-
-In the first case there are two additional complications:
-- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
- the kernel may now execute it. We handle this by also setting spte.nx.
- If we get a user fetch or read fault, we'll change spte.u=1 and
- spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when
- shadow paging is in use.
-- if CR4.SMAP is disabled: since the page has been changed to a kernel
- page, it can not be reused when CR4.SMAP is enabled. We set
- CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
- here we do not care the case that CR4.SMAP is enabled since KVM will
- directly inject #PF to guest due to failed permission check.
-
-To prevent an spte that was converted into a kernel page with cr0.wp=0
-from being written by the kernel after cr0.wp has changed to 1, we make
-the value of cr0.wp part of the page role. This means that an spte created
-with one value of cr0.wp cannot be used when cr0.wp has a different value -
-it will simply be missed by the shadow page lookup code. A similar issue
-exists when an spte created with cr0.wp=0 and cr4.smep=0 is used after
-changing cr4.smep to 1. To avoid this, the value of !cr0.wp && cr4.smep
-is also made a part of the page role.
-
-Large pages
-===========
-
-The mmu supports all combinations of large and small guest and host pages.
-Supported page sizes include 4k, 2M, 4M, and 1G. 4M pages are treated as
-two separate 2M pages, on both guest and host, since the mmu always uses PAE
-paging.
-
-To instantiate a large spte, four constraints must be satisfied:
-
-- the spte must point to a large host page
-- the guest pte must be a large pte of at least equivalent size (if tdp is
- enabled, there is no guest pte and this condition is satisfied)
-- if the spte will be writeable, the large page frame may not overlap any
- write-protected pages
-- the guest page must be wholly contained by a single memory slot
-
-To check the last two conditions, the mmu maintains a ->disallow_lpage set of
-arrays for each memory slot and large page size. Every write protected page
-causes its disallow_lpage to be incremented, thus preventing instantiation of
-a large spte. The frames at the end of an unaligned memory slot have
-artificially inflated ->disallow_lpages so they can never be instantiated.
-
-Fast invalidation of MMIO sptes
-===============================
-
-As mentioned in "Reaction to events" above, kvm will cache MMIO
-information in leaf sptes. When a new memslot is added or an existing
-memslot is changed, this information may become stale and needs to be
-invalidated. This also needs to hold the MMU lock while walking all
-shadow pages, and is made more scalable with a similar technique.
-
-MMIO sptes have a few spare bits, which are used to store a
-generation number. The global generation number is stored in
-kvm_memslots(kvm)->generation, and increased whenever guest memory info
-changes.
-
-When KVM finds an MMIO spte, it checks the generation number of the spte.
-If the generation number of the spte does not equal the global generation
-number, it will ignore the cached MMIO information and handle the page
-fault through the slow path.
-
-Since only 19 bits are used to store generation-number on mmio spte, all
-pages are zapped when there is an overflow.
-
-Unfortunately, a single memory access might access kvm_memslots(kvm) multiple
-times, the last one happening when the generation number is retrieved and
-stored into the MMIO spte. Thus, the MMIO spte might be created based on
-out-of-date information, but with an up-to-date generation number.
-
-To avoid this, the generation number is incremented again after synchronize_srcu
-returns; thus, bit 63 of kvm_memslots(kvm)->generation set to 1 only during a
-memslot update, while some SRCU readers might be using the old copy. We do not
-want to use an MMIO sptes created with an odd generation number, and we can do
-this without losing a bit in the MMIO spte. The "update in-progress" bit of the
-generation is not stored in MMIO spte, and is so is implicitly zero when the
-generation is extracted out of the spte. If KVM is unlucky and creates an MMIO
-spte while an update is in-progress, the next access to the spte will always be
-a cache miss. For example, a subsequent access during the update window will
-miss due to the in-progress flag diverging, while an access after the update
-window closes will have a higher generation number (as compared to the spte).
-
-
-Further reading
-===============
-
-- NPT presentation from KVM Forum 2008
- http://www.linux-kvm.org/images/c/c8/KvmForum2008%24kdf2008_21.pdf
-
+++ /dev/null
-KVM-specific MSRs.
-Glauber Costa <glommer@redhat.com>, Red Hat Inc, 2010
-=====================================================
-
-KVM makes use of some custom MSRs to service some requests.
-
-Custom MSRs have a range reserved for them, that goes from
-0x4b564d00 to 0x4b564dff. There are MSRs outside this area,
-but they are deprecated and their use is discouraged.
-
-Custom MSR list
---------
-
-The current supported Custom MSR list is:
-
-MSR_KVM_WALL_CLOCK_NEW: 0x4b564d00
-
- data: 4-byte alignment physical address of a memory area which must be
- in guest RAM. This memory is expected to hold a copy of the following
- structure:
-
- struct pvclock_wall_clock {
- u32 version;
- u32 sec;
- u32 nsec;
- } __attribute__((__packed__));
-
- whose data will be filled in by the hypervisor. The hypervisor is only
- guaranteed to update this data at the moment of MSR write.
- Users that want to reliably query this information more than once have
- to write more than once to this MSR. Fields have the following meanings:
-
- version: guest has to check version before and after grabbing
- time information and check that they are both equal and even.
- An odd version indicates an in-progress update.
-
- sec: number of seconds for wallclock at time of boot.
-
- nsec: number of nanoseconds for wallclock at time of boot.
-
- In order to get the current wallclock time, the system_time from
- MSR_KVM_SYSTEM_TIME_NEW needs to be added.
-
- Note that although MSRs are per-CPU entities, the effect of this
- particular MSR is global.
-
- Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
- leaf prior to usage.
-
-MSR_KVM_SYSTEM_TIME_NEW: 0x4b564d01
-
- data: 4-byte aligned physical address of a memory area which must be in
- guest RAM, plus an enable bit in bit 0. This memory is expected to hold
- a copy of the following structure:
-
- struct pvclock_vcpu_time_info {
- u32 version;
- u32 pad0;
- u64 tsc_timestamp;
- u64 system_time;
- u32 tsc_to_system_mul;
- s8 tsc_shift;
- u8 flags;
- u8 pad[2];
- } __attribute__((__packed__)); /* 32 bytes */
-
- whose data will be filled in by the hypervisor periodically. Only one
- write, or registration, is needed for each VCPU. The interval between
- updates of this structure is arbitrary and implementation-dependent.
- The hypervisor may update this structure at any time it sees fit until
- anything with bit0 == 0 is written to it.
-
- Fields have the following meanings:
-
- version: guest has to check version before and after grabbing
- time information and check that they are both equal and even.
- An odd version indicates an in-progress update.
-
- tsc_timestamp: the tsc value at the current VCPU at the time
- of the update of this structure. Guests can subtract this value
- from current tsc to derive a notion of elapsed time since the
- structure update.
-
- system_time: a host notion of monotonic time, including sleep
- time at the time this structure was last updated. Unit is
- nanoseconds.
-
- tsc_to_system_mul: multiplier to be used when converting
- tsc-related quantity to nanoseconds
-
- tsc_shift: shift to be used when converting tsc-related
- quantity to nanoseconds. This shift will ensure that
- multiplication with tsc_to_system_mul does not overflow.
- A positive value denotes a left shift, a negative value
- a right shift.
-
- The conversion from tsc to nanoseconds involves an additional
- right shift by 32 bits. With this information, guests can
- derive per-CPU time by doing:
-
- time = (current_tsc - tsc_timestamp)
- if (tsc_shift >= 0)
- time <<= tsc_shift;
- else
- time >>= -tsc_shift;
- time = (time * tsc_to_system_mul) >> 32
- time = time + system_time
-
- flags: bits in this field indicate extended capabilities
- coordinated between the guest and the hypervisor. Availability
- of specific flags has to be checked in 0x40000001 cpuid leaf.
- Current flags are:
-
- flag bit | cpuid bit | meaning
- -------------------------------------------------------------
- | | time measures taken across
- 0 | 24 | multiple cpus are guaranteed to
- | | be monotonic
- -------------------------------------------------------------
- | | guest vcpu has been paused by
- 1 | N/A | the host
- | | See 4.70 in api.txt
- -------------------------------------------------------------
-
- Availability of this MSR must be checked via bit 3 in 0x4000001 cpuid
- leaf prior to usage.
-
-
-MSR_KVM_WALL_CLOCK: 0x11
-
- data and functioning: same as MSR_KVM_WALL_CLOCK_NEW. Use that instead.
-
- This MSR falls outside the reserved KVM range and may be removed in the
- future. Its usage is deprecated.
-
- Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid
- leaf prior to usage.
-
-MSR_KVM_SYSTEM_TIME: 0x12
-
- data and functioning: same as MSR_KVM_SYSTEM_TIME_NEW. Use that instead.
-
- This MSR falls outside the reserved KVM range and may be removed in the
- future. Its usage is deprecated.
-
- Availability of this MSR must be checked via bit 0 in 0x4000001 cpuid
- leaf prior to usage.
-
- The suggested algorithm for detecting kvmclock presence is then:
-
- if (!kvm_para_available()) /* refer to cpuid.txt */
- return NON_PRESENT;
-
- flags = cpuid_eax(0x40000001);
- if (flags & 3) {
- msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
- msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
- return PRESENT;
- } else if (flags & 0) {
- msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
- msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
- return PRESENT;
- } else
- return NON_PRESENT;
-
-MSR_KVM_ASYNC_PF_EN: 0x4b564d02
- data: Bits 63-6 hold 64-byte aligned physical address of a
- 64 byte memory area which must be in guest RAM and must be
- zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
- when asynchronous page faults are enabled on the vcpu 0 when
- disabled. Bit 1 is 1 if asynchronous page faults can be injected
- when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
- are delivered to L1 as #PF vmexits. Bit 2 can be set only if
- KVM_FEATURE_ASYNC_PF_VMEXIT is present in CPUID.
-
- First 4 byte of 64 byte memory location will be written to by
- the hypervisor at the time of asynchronous page fault (APF)
- injection to indicate type of asynchronous page fault. Value
- of 1 means that the page referred to by the page fault is not
- present. Value 2 means that the page is now available. Disabling
- interrupt inhibits APFs. Guest must not enable interrupt
- before the reason is read, or it may be overwritten by another
- APF. Since APF uses the same exception vector as regular page
- fault guest must reset the reason to 0 before it does
- something that can generate normal page fault. If during page
- fault APF reason is 0 it means that this is regular page
- fault.
-
- During delivery of type 1 APF cr2 contains a token that will
- be used to notify a guest when missing page becomes
- available. When page becomes available type 2 APF is sent with
- cr2 set to the token associated with the page. There is special
- kind of token 0xffffffff which tells vcpu that it should wake
- up all processes waiting for APFs and no individual type 2 APFs
- will be sent.
-
- If APF is disabled while there are outstanding APFs, they will
- not be delivered.
-
- Currently type 2 APF will be always delivered on the same vcpu as
- type 1 was, but guest should not rely on that.
-
-MSR_KVM_STEAL_TIME: 0x4b564d03
-
- data: 64-byte alignment physical address of a memory area which must be
- in guest RAM, plus an enable bit in bit 0. This memory is expected to
- hold a copy of the following structure:
-
- struct kvm_steal_time {
- __u64 steal;
- __u32 version;
- __u32 flags;
- __u8 preempted;
- __u8 u8_pad[3];
- __u32 pad[11];
- }
-
- whose data will be filled in by the hypervisor periodically. Only one
- write, or registration, is needed for each VCPU. The interval between
- updates of this structure is arbitrary and implementation-dependent.
- The hypervisor may update this structure at any time it sees fit until
- anything with bit0 == 0 is written to it. Guest is required to make sure
- this structure is initialized to zero.
-
- Fields have the following meanings:
-
- version: a sequence counter. In other words, guest has to check
- this field before and after grabbing time information and make
- sure they are both equal and even. An odd version indicates an
- in-progress update.
-
- flags: At this point, always zero. May be used to indicate
- changes in this structure in the future.
-
- steal: the amount of time in which this vCPU did not run, in
- nanoseconds. Time during which the vcpu is idle, will not be
- reported as steal time.
-
- preempted: indicate the vCPU who owns this struct is running or
- not. Non-zero values mean the vCPU has been preempted. Zero
- means the vCPU is not preempted. NOTE, it is always zero if the
- the hypervisor doesn't support this field.
-
-MSR_KVM_EOI_EN: 0x4b564d04
- data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0
- when disabled. Bit 1 is reserved and must be zero. When PV end of
- interrupt is enabled (bit 0 set), bits 63-2 hold a 4-byte aligned
- physical address of a 4 byte memory area which must be in guest RAM and
- must be zeroed.
-
- The first, least significant bit of 4 byte memory location will be
- written to by the hypervisor, typically at the time of interrupt
- injection. Value of 1 means that guest can skip writing EOI to the apic
- (using MSR or MMIO write); instead, it is sufficient to signal
- EOI by clearing the bit in guest memory - this location will
- later be polled by the hypervisor.
- Value of 0 means that the EOI write is required.
-
- It is always safe for the guest to ignore the optimization and perform
- the APIC EOI write anyway.
-
- Hypervisor is guaranteed to only modify this least
- significant bit while in the current VCPU context, this means that
- guest does not need to use either lock prefix or memory ordering
- primitives to synchronise with the hypervisor.
-
- However, hypervisor can set and clear this memory bit at any time:
- therefore to make sure hypervisor does not interrupt the
- guest and clear the least significant bit in the memory area
- in the window between guest testing it to detect
- whether it can skip EOI apic write and between guest
- clearing it to signal EOI to the hypervisor,
- guest must both read the least significant bit in the memory area and
- clear it using a single CPU instruction, such as test and clear, or
- compare and exchange.
-
-MSR_KVM_POLL_CONTROL: 0x4b564d05
- Control host-side polling.
-
- data: Bit 0 enables (1) or disables (0) host-side HLT polling logic.
-
- KVM guests can request the host not to poll on HLT, for example if
- they are performing polling themselves.
-
+++ /dev/null
-Nested VMX
-==========
-
-Overview
----------
-
-On Intel processors, KVM uses Intel's VMX (Virtual-Machine eXtensions)
-to easily and efficiently run guest operating systems. Normally, these guests
-*cannot* themselves be hypervisors running their own guests, because in VMX,
-guests cannot use VMX instructions.
-
-The "Nested VMX" feature adds this missing capability - of running guest
-hypervisors (which use VMX) with their own nested guests. It does so by
-allowing a guest to use VMX instructions, and correctly and efficiently
-emulating them using the single level of VMX available in the hardware.
-
-We describe in much greater detail the theory behind the nested VMX feature,
-its implementation and its performance characteristics, in the OSDI 2010 paper
-"The Turtles Project: Design and Implementation of Nested Virtualization",
-available at:
-
- http://www.usenix.org/events/osdi10/tech/full_papers/Ben-Yehuda.pdf
-
-
-Terminology
------------
-
-Single-level virtualization has two levels - the host (KVM) and the guests.
-In nested virtualization, we have three levels: The host (KVM), which we call
-L0, the guest hypervisor, which we call L1, and its nested guest, which we
-call L2.
-
-
-Running nested VMX
-------------------
-
-The nested VMX feature is disabled by default. It can be enabled by giving
-the "nested=1" option to the kvm-intel module.
-
-No modifications are required to user space (qemu). However, qemu's default
-emulated CPU type (qemu64) does not list the "VMX" CPU feature, so it must be
-explicitly enabled, by giving qemu one of the following options:
-
- -cpu host (emulated CPU has all features of the real CPU)
-
- -cpu qemu64,+vmx (add just the vmx feature to a named CPU type)
-
-
-ABIs
-----
-
-Nested VMX aims to present a standard and (eventually) fully-functional VMX
-implementation for the a guest hypervisor to use. As such, the official
-specification of the ABI that it provides is Intel's VMX specification,
-namely volume 3B of their "Intel 64 and IA-32 Architectures Software
-Developer's Manual". Not all of VMX's features are currently fully supported,
-but the goal is to eventually support them all, starting with the VMX features
-which are used in practice by popular hypervisors (KVM and others).
-
-As a VMX implementation, nested VMX presents a VMCS structure to L1.
-As mandated by the spec, other than the two fields revision_id and abort,
-this structure is *opaque* to its user, who is not supposed to know or care
-about its internal structure. Rather, the structure is accessed through the
-VMREAD and VMWRITE instructions.
-Still, for debugging purposes, KVM developers might be interested to know the
-internals of this structure; This is struct vmcs12 from arch/x86/kvm/vmx.c.
-
-The name "vmcs12" refers to the VMCS that L1 builds for L2. In the code we
-also have "vmcs01", the VMCS that L0 built for L1, and "vmcs02" is the VMCS
-which L0 builds to actually run L2 - how this is done is explained in the
-aforementioned paper.
-
-For convenience, we repeat the content of struct vmcs12 here. If the internals
-of this structure changes, this can break live migration across KVM versions.
-VMCS12_REVISION (from vmx.c) should be changed if struct vmcs12 or its inner
-struct shadow_vmcs is ever changed.
-
- typedef u64 natural_width;
- struct __packed vmcs12 {
- /* According to the Intel spec, a VMCS region must start with
- * these two user-visible fields */
- u32 revision_id;
- u32 abort;
-
- u32 launch_state; /* set to 0 by VMCLEAR, to 1 by VMLAUNCH */
- u32 padding[7]; /* room for future expansion */
-
- u64 io_bitmap_a;
- u64 io_bitmap_b;
- u64 msr_bitmap;
- u64 vm_exit_msr_store_addr;
- u64 vm_exit_msr_load_addr;
- u64 vm_entry_msr_load_addr;
- u64 tsc_offset;
- u64 virtual_apic_page_addr;
- u64 apic_access_addr;
- u64 ept_pointer;
- u64 guest_physical_address;
- u64 vmcs_link_pointer;
- u64 guest_ia32_debugctl;
- u64 guest_ia32_pat;
- u64 guest_ia32_efer;
- u64 guest_pdptr0;
- u64 guest_pdptr1;
- u64 guest_pdptr2;
- u64 guest_pdptr3;
- u64 host_ia32_pat;
- u64 host_ia32_efer;
- u64 padding64[8]; /* room for future expansion */
- natural_width cr0_guest_host_mask;
- natural_width cr4_guest_host_mask;
- natural_width cr0_read_shadow;
- natural_width cr4_read_shadow;
- natural_width cr3_target_value0;
- natural_width cr3_target_value1;
- natural_width cr3_target_value2;
- natural_width cr3_target_value3;
- natural_width exit_qualification;
- natural_width guest_linear_address;
- natural_width guest_cr0;
- natural_width guest_cr3;
- natural_width guest_cr4;
- natural_width guest_es_base;
- natural_width guest_cs_base;
- natural_width guest_ss_base;
- natural_width guest_ds_base;
- natural_width guest_fs_base;
- natural_width guest_gs_base;
- natural_width guest_ldtr_base;
- natural_width guest_tr_base;
- natural_width guest_gdtr_base;
- natural_width guest_idtr_base;
- natural_width guest_dr7;
- natural_width guest_rsp;
- natural_width guest_rip;
- natural_width guest_rflags;
- natural_width guest_pending_dbg_exceptions;
- natural_width guest_sysenter_esp;
- natural_width guest_sysenter_eip;
- natural_width host_cr0;
- natural_width host_cr3;
- natural_width host_cr4;
- natural_width host_fs_base;
- natural_width host_gs_base;
- natural_width host_tr_base;
- natural_width host_gdtr_base;
- natural_width host_idtr_base;
- natural_width host_ia32_sysenter_esp;
- natural_width host_ia32_sysenter_eip;
- natural_width host_rsp;
- natural_width host_rip;
- natural_width paddingl[8]; /* room for future expansion */
- u32 pin_based_vm_exec_control;
- u32 cpu_based_vm_exec_control;
- u32 exception_bitmap;
- u32 page_fault_error_code_mask;
- u32 page_fault_error_code_match;
- u32 cr3_target_count;
- u32 vm_exit_controls;
- u32 vm_exit_msr_store_count;
- u32 vm_exit_msr_load_count;
- u32 vm_entry_controls;
- u32 vm_entry_msr_load_count;
- u32 vm_entry_intr_info_field;
- u32 vm_entry_exception_error_code;
- u32 vm_entry_instruction_len;
- u32 tpr_threshold;
- u32 secondary_vm_exec_control;
- u32 vm_instruction_error;
- u32 vm_exit_reason;
- u32 vm_exit_intr_info;
- u32 vm_exit_intr_error_code;
- u32 idt_vectoring_info_field;
- u32 idt_vectoring_error_code;
- u32 vm_exit_instruction_len;
- u32 vmx_instruction_info;
- u32 guest_es_limit;
- u32 guest_cs_limit;
- u32 guest_ss_limit;
- u32 guest_ds_limit;
- u32 guest_fs_limit;
- u32 guest_gs_limit;
- u32 guest_ldtr_limit;
- u32 guest_tr_limit;
- u32 guest_gdtr_limit;
- u32 guest_idtr_limit;
- u32 guest_es_ar_bytes;
- u32 guest_cs_ar_bytes;
- u32 guest_ss_ar_bytes;
- u32 guest_ds_ar_bytes;
- u32 guest_fs_ar_bytes;
- u32 guest_gs_ar_bytes;
- u32 guest_ldtr_ar_bytes;
- u32 guest_tr_ar_bytes;
- u32 guest_interruptibility_info;
- u32 guest_activity_state;
- u32 guest_sysenter_cs;
- u32 host_ia32_sysenter_cs;
- u32 padding32[8]; /* room for future expansion */
- u16 virtual_processor_id;
- u16 guest_es_selector;
- u16 guest_cs_selector;
- u16 guest_ss_selector;
- u16 guest_ds_selector;
- u16 guest_fs_selector;
- u16 guest_gs_selector;
- u16 guest_ldtr_selector;
- u16 guest_tr_selector;
- u16 host_es_selector;
- u16 host_cs_selector;
- u16 host_ss_selector;
- u16 host_ds_selector;
- u16 host_fs_selector;
- u16 host_gs_selector;
- u16 host_tr_selector;
- };
-
-
-Authors
--------
-
-These patches were written by:
- Abel Gordon, abelg <at> il.ibm.com
- Nadav Har'El, nyh <at> il.ibm.com
- Orit Wasserman, oritw <at> il.ibm.com
- Ben-Ami Yassor, benami <at> il.ibm.com
- Muli Ben-Yehuda, muli <at> il.ibm.com
-
-With contributions by:
- Anthony Liguori, aliguori <at> us.ibm.com
- Mike Day, mdday <at> us.ibm.com
- Michael Factor, factor <at> il.ibm.com
- Zvi Dubitzky, dubi <at> il.ibm.com
-
-And valuable reviews by:
- Avi Kivity, avi <at> redhat.com
- Gleb Natapov, gleb <at> redhat.com
- Marcelo Tosatti, mtosatti <at> redhat.com
- Kevin Tian, kevin.tian <at> intel.com
- and others.
+++ /dev/null
-The PPC KVM paravirtual interface
-=================================
-
-The basic execution principle by which KVM on PowerPC works is to run all kernel
-space code in PR=1 which is user space. This way we trap all privileged
-instructions and can emulate them accordingly.
-
-Unfortunately that is also the downfall. There are quite some privileged
-instructions that needlessly return us to the hypervisor even though they
-could be handled differently.
-
-This is what the PPC PV interface helps with. It takes privileged instructions
-and transforms them into unprivileged ones with some help from the hypervisor.
-This cuts down virtualization costs by about 50% on some of my benchmarks.
-
-The code for that interface can be found in arch/powerpc/kernel/kvm*
-
-Querying for existence
-======================
-
-To find out if we're running on KVM or not, we leverage the device tree. When
-Linux is running on KVM, a node /hypervisor exists. That node contains a
-compatible property with the value "linux,kvm".
-
-Once you determined you're running under a PV capable KVM, you can now use
-hypercalls as described below.
-
-KVM hypercalls
-==============
-
-Inside the device tree's /hypervisor node there's a property called
-'hypercall-instructions'. This property contains at most 4 opcodes that make
-up the hypercall. To call a hypercall, just call these instructions.
-
-The parameters are as follows:
-
- Register IN OUT
-
- r0 - volatile
- r3 1st parameter Return code
- r4 2nd parameter 1st output value
- r5 3rd parameter 2nd output value
- r6 4th parameter 3rd output value
- r7 5th parameter 4th output value
- r8 6th parameter 5th output value
- r9 7th parameter 6th output value
- r10 8th parameter 7th output value
- r11 hypercall number 8th output value
- r12 - volatile
-
-Hypercall definitions are shared in generic code, so the same hypercall numbers
-apply for x86 and powerpc alike with the exception that each KVM hypercall
-also needs to be ORed with the KVM vendor code which is (42 << 16).
-
-Return codes can be as follows:
-
- Code Meaning
-
- 0 Success
- 12 Hypercall not implemented
- <0 Error
-
-The magic page
-==============
-
-To enable communication between the hypervisor and guest there is a new shared
-page that contains parts of supervisor visible register state. The guest can
-map this shared page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE.
-
-With this hypercall issued the guest always gets the magic page mapped at the
-desired location. The first parameter indicates the effective address when the
-MMU is enabled. The second parameter indicates the address in real mode, if
-applicable to the target. For now, we always map the page to -4096. This way we
-can access it using absolute load and store functions. The following
-instruction reads the first field of the magic page:
-
- ld rX, -4096(0)
-
-The interface is designed to be extensible should there be need later to add
-additional registers to the magic page. If you add fields to the magic page,
-also define a new hypercall feature to indicate that the host can give you more
-registers. Only if the host supports the additional features, make use of them.
-
-The magic page layout is described by struct kvm_vcpu_arch_shared
-in arch/powerpc/include/asm/kvm_para.h.
-
-Magic page features
-===================
-
-When mapping the magic page using the KVM hypercall KVM_HC_PPC_MAP_MAGIC_PAGE,
-a second return value is passed to the guest. This second return value contains
-a bitmap of available features inside the magic page.
-
-The following enhancements to the magic page are currently available:
-
- KVM_MAGIC_FEAT_SR Maps SR registers r/w in the magic page
- KVM_MAGIC_FEAT_MAS0_TO_SPRG7 Maps MASn, ESR, PIR and high SPRGs
-
-For enhanced features in the magic page, please check for the existence of the
-feature before using them!
-
-Magic page flags
-================
-
-In addition to features that indicate whether a host is capable of a particular
-feature we also have a channel for a guest to tell the guest whether it's capable
-of something. This is what we call "flags".
-
-Flags are passed to the host in the low 12 bits of the Effective Address.
-
-The following flags are currently available for a guest to expose:
-
- MAGIC_PAGE_FLAG_NOT_MAPPED_NX Guest handles NX bits correctly wrt magic page
-
-MSR bits
-========
-
-The MSR contains bits that require hypervisor intervention and bits that do
-not require direct hypervisor intervention because they only get interpreted
-when entering the guest or don't have any impact on the hypervisor's behavior.
-
-The following bits are safe to be set inside the guest:
-
- MSR_EE
- MSR_RI
-
-If any other bit changes in the MSR, please still use mtmsr(d).
-
-Patched instructions
-====================
-
-The "ld" and "std" instructions are transformed to "lwz" and "stw" instructions
-respectively on 32 bit systems with an added offset of 4 to accommodate for big
-endianness.
-
-The following is a list of mapping the Linux kernel performs when running as
-guest. Implementing any of those mappings is optional, as the instruction traps
-also act on the shared page. So calling privileged instructions still works as
-before.
-
-From To
-==== ==
-
-mfmsr rX ld rX, magic_page->msr
-mfsprg rX, 0 ld rX, magic_page->sprg0
-mfsprg rX, 1 ld rX, magic_page->sprg1
-mfsprg rX, 2 ld rX, magic_page->sprg2
-mfsprg rX, 3 ld rX, magic_page->sprg3
-mfsrr0 rX ld rX, magic_page->srr0
-mfsrr1 rX ld rX, magic_page->srr1
-mfdar rX ld rX, magic_page->dar
-mfdsisr rX lwz rX, magic_page->dsisr
-
-mtmsr rX std rX, magic_page->msr
-mtsprg 0, rX std rX, magic_page->sprg0
-mtsprg 1, rX std rX, magic_page->sprg1
-mtsprg 2, rX std rX, magic_page->sprg2
-mtsprg 3, rX std rX, magic_page->sprg3
-mtsrr0 rX std rX, magic_page->srr0
-mtsrr1 rX std rX, magic_page->srr1
-mtdar rX std rX, magic_page->dar
-mtdsisr rX stw rX, magic_page->dsisr
-
-tlbsync nop
-
-mtmsrd rX, 0 b <special mtmsr section>
-mtmsr rX b <special mtmsr section>
-
-mtmsrd rX, 1 b <special mtmsrd section>
-
-[Book3S only]
-mtsrin rX, rY b <special mtsrin section>
-
-[BookE only]
-wrteei [0|1] b <special wrteei section>
-
-
-Some instructions require more logic to determine what's going on than a load
-or store instruction can deliver. To enable patching of those, we keep some
-RAM around where we can live translate instructions to. What happens is the
-following:
-
- 1) copy emulation code to memory
- 2) patch that code to fit the emulated instruction
- 3) patch that code to return to the original pc + 4
- 4) patch the original instruction to branch to the new code
-
-That way we can inject an arbitrary amount of code as replacement for a single
-instruction. This allows us to check for pending interrupts when setting EE=1
-for example.
-
-Hypercall ABIs in KVM on PowerPC
-=================================
-1) KVM hypercalls (ePAPR)
-
-These are ePAPR compliant hypercall implementation (mentioned above). Even
-generic hypercalls are implemented here, like the ePAPR idle hcall. These are
-available on all targets.
-
-2) PAPR hypercalls
-
-PAPR hypercalls are needed to run server PowerPC PAPR guests (-M pseries in QEMU).
-These are the same hypercalls that pHyp, the POWER hypervisor implements. Some of
-them are handled in the kernel, some are handled in user space. This is only
-available on book3s_64.
-
-3) OSI hypercalls
-
-Mac-on-Linux is another user of KVM on PowerPC, which has its own hypercall (long
-before KVM). This is supported to maintain compatibility. All these hypercalls get
-forwarded to user space. This is only useful on book3s_32, but can be used with
-book3s_64 as well.
+++ /dev/null
-Review checklist for kvm patches
-================================
-
-1. The patch must follow Documentation/process/coding-style.rst and
- Documentation/process/submitting-patches.rst.
-
-2. Patches should be against kvm.git master branch.
-
-3. If the patch introduces or modifies a new userspace API:
- - the API must be documented in Documentation/virtual/kvm/api.txt
- - the API must be discoverable using KVM_CHECK_EXTENSION
-
-4. New state must include support for save/restore.
-
-5. New features must default to off (userspace should explicitly request them).
- Performance improvements can and should default to on.
-
-6. New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2
-
-7. Emulator changes should be accompanied by unit tests for qemu-kvm.git
- kvm/test directory.
-
-8. Changes should be vendor neutral when possible. Changes to common code
- are better than duplicating changes to vendor code.
-
-9. Similarly, prefer changes to arch independent code than to arch dependent
- code.
-
-10. User/kernel interfaces and guest/host interfaces must be 64-bit clean
- (all variables and sizes naturally aligned on 64-bit; use specific types
- only - u64 rather than ulong).
-
-11. New guest visible features must either be documented in a hardware manual
- or be accompanied by documentation.
-
-12. Features must be robust against reset and kexec - for example, shared
- host/guest memory must be unshared to prevent the host from writing to
- guest memory that the guest has not reserved for this purpose.
+++ /dev/null
-The s390 DIAGNOSE call on KVM
-=============================
-
-KVM on s390 supports the DIAGNOSE call for making hypercalls, both for
-native hypercalls and for selected hypercalls found on other s390
-hypervisors.
-
-Note that bits are numbered as by the usual s390 convention (most significant
-bit on the left).
-
-
-General remarks
----------------
-
-DIAGNOSE calls by the guest cause a mandatory intercept. This implies
-all supported DIAGNOSE calls need to be handled by either KVM or its
-userspace.
-
-All DIAGNOSE calls supported by KVM use the RS-a format:
-
---------------------------------------
-| '83' | R1 | R3 | B2 | D2 |
---------------------------------------
-0 8 12 16 20 31
-
-The second-operand address (obtained by the base/displacement calculation)
-is not used to address data. Instead, bits 48-63 of this address specify
-the function code, and bits 0-47 are ignored.
-
-The supported DIAGNOSE function codes vary by the userspace used. For
-DIAGNOSE function codes not specific to KVM, please refer to the
-documentation for the s390 hypervisors defining them.
-
-
-DIAGNOSE function code 'X'500' - KVM virtio functions
------------------------------------------------------
-
-If the function code specifies 0x500, various virtio-related functions
-are performed.
-
-General register 1 contains the virtio subfunction code. Supported
-virtio subfunctions depend on KVM's userspace. Generally, userspace
-provides either s390-virtio (subcodes 0-2) or virtio-ccw (subcode 3).
-
-Upon completion of the DIAGNOSE instruction, general register 2 contains
-the function's return code, which is either a return code or a subcode
-specific value.
-
-Subcode 0 - s390-virtio notification and early console printk
- Handled by userspace.
-
-Subcode 1 - s390-virtio reset
- Handled by userspace.
-
-Subcode 2 - s390-virtio set status
- Handled by userspace.
-
-Subcode 3 - virtio-ccw notification
- Handled by either userspace or KVM (ioeventfd case).
-
- General register 2 contains a subchannel-identification word denoting
- the subchannel of the virtio-ccw proxy device to be notified.
-
- General register 3 contains the number of the virtqueue to be notified.
-
- General register 4 contains a 64bit identifier for KVM usage (the
- kvm_io_bus cookie). If general register 4 does not contain a valid
- identifier, it is ignored.
-
- After completion of the DIAGNOSE call, general register 2 may contain
- a 64bit identifier (in the kvm_io_bus cookie case), or a negative
- error value, if an internal error occurred.
-
- See also the virtio standard for a discussion of this hypercall.
-
-
-DIAGNOSE function code 'X'501 - KVM breakpoint
-----------------------------------------------
-
-If the function code specifies 0x501, breakpoint functions may be performed.
-This function code is handled by userspace.
-
-This diagnose function code has no subfunctions and uses no parameters.
+++ /dev/null
-
- Timekeeping Virtualization for X86-Based Architectures
-
- Zachary Amsden <zamsden@redhat.com>
- Copyright (c) 2010, Red Hat. All rights reserved.
-
-1) Overview
-2) Timing Devices
-3) TSC Hardware
-4) Virtualization Problems
-
-=========================================================================
-
-1) Overview
-
-One of the most complicated parts of the X86 platform, and specifically,
-the virtualization of this platform is the plethora of timing devices available
-and the complexity of emulating those devices. In addition, virtualization of
-time introduces a new set of challenges because it introduces a multiplexed
-division of time beyond the control of the guest CPU.
-
-First, we will describe the various timekeeping hardware available, then
-present some of the problems which arise and solutions available, giving
-specific recommendations for certain classes of KVM guests.
-
-The purpose of this document is to collect data and information relevant to
-timekeeping which may be difficult to find elsewhere, specifically,
-information relevant to KVM and hardware-based virtualization.
-
-=========================================================================
-
-2) Timing Devices
-
-First we discuss the basic hardware devices available. TSC and the related
-KVM clock are special enough to warrant a full exposition and are described in
-the following section.
-
-2.1) i8254 - PIT
-
-One of the first timer devices available is the programmable interrupt timer,
-or PIT. The PIT has a fixed frequency 1.193182 MHz base clock and three
-channels which can be programmed to deliver periodic or one-shot interrupts.
-These three channels can be configured in different modes and have individual
-counters. Channel 1 and 2 were not available for general use in the original
-IBM PC, and historically were connected to control RAM refresh and the PC
-speaker. Now the PIT is typically integrated as part of an emulated chipset
-and a separate physical PIT is not used.
-
-The PIT uses I/O ports 0x40 - 0x43. Access to the 16-bit counters is done
-using single or multiple byte access to the I/O ports. There are 6 modes
-available, but not all modes are available to all timers, as only timer 2
-has a connected gate input, required for modes 1 and 5. The gate line is
-controlled by port 61h, bit 0, as illustrated in the following diagram.
-
- -------------- ----------------
-| | | |
-| 1.1932 MHz |---------->| CLOCK OUT | ---------> IRQ 0
-| Clock | | | |
- -------------- | +->| GATE TIMER 0 |
- | ----------------
- |
- | ----------------
- | | |
- |------>| CLOCK OUT | ---------> 66.3 KHZ DRAM
- | | | (aka /dev/null)
- | +->| GATE TIMER 1 |
- | ----------------
- |
- | ----------------
- | | |
- |------>| CLOCK OUT | ---------> Port 61h, bit 5
- | | |
-Port 61h, bit 0 ---------->| GATE TIMER 2 | \_.---- ____
- ---------------- _| )--|LPF|---Speaker
- / *---- \___/
-Port 61h, bit 1 -----------------------------------/
-
-The timer modes are now described.
-
-Mode 0: Single Timeout. This is a one-shot software timeout that counts down
- when the gate is high (always true for timers 0 and 1). When the count
- reaches zero, the output goes high.
-
-Mode 1: Triggered One-shot. The output is initially set high. When the gate
- line is set high, a countdown is initiated (which does not stop if the gate is
- lowered), during which the output is set low. When the count reaches zero,
- the output goes high.
-
-Mode 2: Rate Generator. The output is initially set high. When the countdown
- reaches 1, the output goes low for one count and then returns high. The value
- is reloaded and the countdown automatically resumes. If the gate line goes
- low, the count is halted. If the output is low when the gate is lowered, the
- output automatically goes high (this only affects timer 2).
-
-Mode 3: Square Wave. This generates a high / low square wave. The count
- determines the length of the pulse, which alternates between high and low
- when zero is reached. The count only proceeds when gate is high and is
- automatically reloaded on reaching zero. The count is decremented twice at
- each clock to generate a full high / low cycle at the full periodic rate.
- If the count is even, the clock remains high for N/2 counts and low for N/2
- counts; if the clock is odd, the clock is high for (N+1)/2 counts and low
- for (N-1)/2 counts. Only even values are latched by the counter, so odd
- values are not observed when reading. This is the intended mode for timer 2,
- which generates sine-like tones by low-pass filtering the square wave output.
-
-Mode 4: Software Strobe. After programming this mode and loading the counter,
- the output remains high until the counter reaches zero. Then the output
- goes low for 1 clock cycle and returns high. The counter is not reloaded.
- Counting only occurs when gate is high.
-
-Mode 5: Hardware Strobe. After programming and loading the counter, the
- output remains high. When the gate is raised, a countdown is initiated
- (which does not stop if the gate is lowered). When the counter reaches zero,
- the output goes low for 1 clock cycle and then returns high. The counter is
- not reloaded.
-
-In addition to normal binary counting, the PIT supports BCD counting. The
-command port, 0x43 is used to set the counter and mode for each of the three
-timers.
-
-PIT commands, issued to port 0x43, using the following bit encoding:
-
-Bit 7-4: Command (See table below)
-Bit 3-1: Mode (000 = Mode 0, 101 = Mode 5, 11X = undefined)
-Bit 0 : Binary (0) / BCD (1)
-
-Command table:
-
-0000 - Latch Timer 0 count for port 0x40
- sample and hold the count to be read in port 0x40;
- additional commands ignored until counter is read;
- mode bits ignored.
-
-0001 - Set Timer 0 LSB mode for port 0x40
- set timer to read LSB only and force MSB to zero;
- mode bits set timer mode
-
-0010 - Set Timer 0 MSB mode for port 0x40
- set timer to read MSB only and force LSB to zero;
- mode bits set timer mode
-
-0011 - Set Timer 0 16-bit mode for port 0x40
- set timer to read / write LSB first, then MSB;
- mode bits set timer mode
-
-0100 - Latch Timer 1 count for port 0x41 - as described above
-0101 - Set Timer 1 LSB mode for port 0x41 - as described above
-0110 - Set Timer 1 MSB mode for port 0x41 - as described above
-0111 - Set Timer 1 16-bit mode for port 0x41 - as described above
-
-1000 - Latch Timer 2 count for port 0x42 - as described above
-1001 - Set Timer 2 LSB mode for port 0x42 - as described above
-1010 - Set Timer 2 MSB mode for port 0x42 - as described above
-1011 - Set Timer 2 16-bit mode for port 0x42 as described above
-
-1101 - General counter latch
- Latch combination of counters into corresponding ports
- Bit 3 = Counter 2
- Bit 2 = Counter 1
- Bit 1 = Counter 0
- Bit 0 = Unused
-
-1110 - Latch timer status
- Latch combination of counter mode into corresponding ports
- Bit 3 = Counter 2
- Bit 2 = Counter 1
- Bit 1 = Counter 0
-
- The output of ports 0x40-0x42 following this command will be:
-
- Bit 7 = Output pin
- Bit 6 = Count loaded (0 if timer has expired)
- Bit 5-4 = Read / Write mode
- 01 = MSB only
- 10 = LSB only
- 11 = LSB / MSB (16-bit)
- Bit 3-1 = Mode
- Bit 0 = Binary (0) / BCD mode (1)
-
-2.2) RTC
-
-The second device which was available in the original PC was the MC146818 real
-time clock. The original device is now obsolete, and usually emulated by the
-system chipset, sometimes by an HPET and some frankenstein IRQ routing.
-
-The RTC is accessed through CMOS variables, which uses an index register to
-control which bytes are read. Since there is only one index register, read
-of the CMOS and read of the RTC require lock protection (in addition, it is
-dangerous to allow userspace utilities such as hwclock to have direct RTC
-access, as they could corrupt kernel reads and writes of CMOS memory).
-
-The RTC generates an interrupt which is usually routed to IRQ 8. The interrupt
-can function as a periodic timer, an additional once a day alarm, and can issue
-interrupts after an update of the CMOS registers by the MC146818 is complete.
-The type of interrupt is signalled in the RTC status registers.
-
-The RTC will update the current time fields by battery power even while the
-system is off. The current time fields should not be read while an update is
-in progress, as indicated in the status register.
-
-The clock uses a 32.768kHz crystal, so bits 6-4 of register A should be
-programmed to a 32kHz divider if the RTC is to count seconds.
-
-This is the RAM map originally used for the RTC/CMOS:
-
-Location Size Description
-------------------------------------------
-00h byte Current second (BCD)
-01h byte Seconds alarm (BCD)
-02h byte Current minute (BCD)
-03h byte Minutes alarm (BCD)
-04h byte Current hour (BCD)
-05h byte Hours alarm (BCD)
-06h byte Current day of week (BCD)
-07h byte Current day of month (BCD)
-08h byte Current month (BCD)
-09h byte Current year (BCD)
-0Ah byte Register A
- bit 7 = Update in progress
- bit 6-4 = Divider for clock
- 000 = 4.194 MHz
- 001 = 1.049 MHz
- 010 = 32 kHz
- 10X = test modes
- 110 = reset / disable
- 111 = reset / disable
- bit 3-0 = Rate selection for periodic interrupt
- 000 = periodic timer disabled
- 001 = 3.90625 uS
- 010 = 7.8125 uS
- 011 = .122070 mS
- 100 = .244141 mS
- ...
- 1101 = 125 mS
- 1110 = 250 mS
- 1111 = 500 mS
-0Bh byte Register B
- bit 7 = Run (0) / Halt (1)
- bit 6 = Periodic interrupt enable
- bit 5 = Alarm interrupt enable
- bit 4 = Update-ended interrupt enable
- bit 3 = Square wave interrupt enable
- bit 2 = BCD calendar (0) / Binary (1)
- bit 1 = 12-hour mode (0) / 24-hour mode (1)
- bit 0 = 0 (DST off) / 1 (DST enabled)
-OCh byte Register C (read only)
- bit 7 = interrupt request flag (IRQF)
- bit 6 = periodic interrupt flag (PF)
- bit 5 = alarm interrupt flag (AF)
- bit 4 = update interrupt flag (UF)
- bit 3-0 = reserved
-ODh byte Register D (read only)
- bit 7 = RTC has power
- bit 6-0 = reserved
-32h byte Current century BCD (*)
- (*) location vendor specific and now determined from ACPI global tables
-
-2.3) APIC
-
-On Pentium and later processors, an on-board timer is available to each CPU
-as part of the Advanced Programmable Interrupt Controller. The APIC is
-accessed through memory-mapped registers and provides interrupt service to each
-CPU, used for IPIs and local timer interrupts.
-
-Although in theory the APIC is a safe and stable source for local interrupts,
-in practice, many bugs and glitches have occurred due to the special nature of
-the APIC CPU-local memory-mapped hardware. Beware that CPU errata may affect
-the use of the APIC and that workarounds may be required. In addition, some of
-these workarounds pose unique constraints for virtualization - requiring either
-extra overhead incurred from extra reads of memory-mapped I/O or additional
-functionality that may be more computationally expensive to implement.
-
-Since the APIC is documented quite well in the Intel and AMD manuals, we will
-avoid repetition of the detail here. It should be pointed out that the APIC
-timer is programmed through the LVT (local vector timer) register, is capable
-of one-shot or periodic operation, and is based on the bus clock divided down
-by the programmable divider register.
-
-2.4) HPET
-
-HPET is quite complex, and was originally intended to replace the PIT / RTC
-support of the X86 PC. It remains to be seen whether that will be the case, as
-the de facto standard of PC hardware is to emulate these older devices. Some
-systems designated as legacy free may support only the HPET as a hardware timer
-device.
-
-The HPET spec is rather loose and vague, requiring at least 3 hardware timers,
-but allowing implementation freedom to support many more. It also imposes no
-fixed rate on the timer frequency, but does impose some extremal values on
-frequency, error and slew.
-
-In general, the HPET is recommended as a high precision (compared to PIT /RTC)
-time source which is independent of local variation (as there is only one HPET
-in any given system). The HPET is also memory-mapped, and its presence is
-indicated through ACPI tables by the BIOS.
-
-Detailed specification of the HPET is beyond the current scope of this
-document, as it is also very well documented elsewhere.
-
-2.5) Offboard Timers
-
-Several cards, both proprietary (watchdog boards) and commonplace (e1000) have
-timing chips built into the cards which may have registers which are accessible
-to kernel or user drivers. To the author's knowledge, using these to generate
-a clocksource for a Linux or other kernel has not yet been attempted and is in
-general frowned upon as not playing by the agreed rules of the game. Such a
-timer device would require additional support to be virtualized properly and is
-not considered important at this time as no known operating system does this.
-
-=========================================================================
-
-3) TSC Hardware
-
-The TSC or time stamp counter is relatively simple in theory; it counts
-instruction cycles issued by the processor, which can be used as a measure of
-time. In practice, due to a number of problems, it is the most complicated
-timekeeping device to use.
-
-The TSC is represented internally as a 64-bit MSR which can be read with the
-RDMSR, RDTSC, or RDTSCP (when available) instructions. In the past, hardware
-limitations made it possible to write the TSC, but generally on old hardware it
-was only possible to write the low 32-bits of the 64-bit counter, and the upper
-32-bits of the counter were cleared. Now, however, on Intel processors family
-0Fh, for models 3, 4 and 6, and family 06h, models e and f, this restriction
-has been lifted and all 64-bits are writable. On AMD systems, the ability to
-write the TSC MSR is not an architectural guarantee.
-
-The TSC is accessible from CPL-0 and conditionally, for CPL > 0 software by
-means of the CR4.TSD bit, which when enabled, disables CPL > 0 TSC access.
-
-Some vendors have implemented an additional instruction, RDTSCP, which returns
-atomically not just the TSC, but an indicator which corresponds to the
-processor number. This can be used to index into an array of TSC variables to
-determine offset information in SMP systems where TSCs are not synchronized.
-The presence of this instruction must be determined by consulting CPUID feature
-bits.
-
-Both VMX and SVM provide extension fields in the virtualization hardware which
-allows the guest visible TSC to be offset by a constant. Newer implementations
-promise to allow the TSC to additionally be scaled, but this hardware is not
-yet widely available.
-
-3.1) TSC synchronization
-
-The TSC is a CPU-local clock in most implementations. This means, on SMP
-platforms, the TSCs of different CPUs may start at different times depending
-on when the CPUs are powered on. Generally, CPUs on the same die will share
-the same clock, however, this is not always the case.
-
-The BIOS may attempt to resynchronize the TSCs during the poweron process and
-the operating system or other system software may attempt to do this as well.
-Several hardware limitations make the problem worse - if it is not possible to
-write the full 64-bits of the TSC, it may be impossible to match the TSC in
-newly arriving CPUs to that of the rest of the system, resulting in
-unsynchronized TSCs. This may be done by BIOS or system software, but in
-practice, getting a perfectly synchronized TSC will not be possible unless all
-values are read from the same clock, which generally only is possible on single
-socket systems or those with special hardware support.
-
-3.2) TSC and CPU hotplug
-
-As touched on already, CPUs which arrive later than the boot time of the system
-may not have a TSC value that is synchronized with the rest of the system.
-Either system software, BIOS, or SMM code may actually try to establish the TSC
-to a value matching the rest of the system, but a perfect match is usually not
-a guarantee. This can have the effect of bringing a system from a state where
-TSC is synchronized back to a state where TSC synchronization flaws, however
-small, may be exposed to the OS and any virtualization environment.
-
-3.3) TSC and multi-socket / NUMA
-
-Multi-socket systems, especially large multi-socket systems are likely to have
-individual clocksources rather than a single, universally distributed clock.
-Since these clocks are driven by different crystals, they will not have
-perfectly matched frequency, and temperature and electrical variations will
-cause the CPU clocks, and thus the TSCs to drift over time. Depending on the
-exact clock and bus design, the drift may or may not be fixed in absolute
-error, and may accumulate over time.
-
-In addition, very large systems may deliberately slew the clocks of individual
-cores. This technique, known as spread-spectrum clocking, reduces EMI at the
-clock frequency and harmonics of it, which may be required to pass FCC
-standards for telecommunications and computer equipment.
-
-It is recommended not to trust the TSCs to remain synchronized on NUMA or
-multiple socket systems for these reasons.
-
-3.4) TSC and C-states
-
-C-states, or idling states of the processor, especially C1E and deeper sleep
-states may be problematic for TSC as well. The TSC may stop advancing in such
-a state, resulting in a TSC which is behind that of other CPUs when execution
-is resumed. Such CPUs must be detected and flagged by the operating system
-based on CPU and chipset identifications.
-
-The TSC in such a case may be corrected by catching it up to a known external
-clocksource.
-
-3.5) TSC frequency change / P-states
-
-To make things slightly more interesting, some CPUs may change frequency. They
-may or may not run the TSC at the same rate, and because the frequency change
-may be staggered or slewed, at some points in time, the TSC rate may not be
-known other than falling within a range of values. In this case, the TSC will
-not be a stable time source, and must be calibrated against a known, stable,
-external clock to be a usable source of time.
-
-Whether the TSC runs at a constant rate or scales with the P-state is model
-dependent and must be determined by inspecting CPUID, chipset or vendor
-specific MSR fields.
-
-In addition, some vendors have known bugs where the P-state is actually
-compensated for properly during normal operation, but when the processor is
-inactive, the P-state may be raised temporarily to service cache misses from
-other processors. In such cases, the TSC on halted CPUs could advance faster
-than that of non-halted processors. AMD Turion processors are known to have
-this problem.
-
-3.6) TSC and STPCLK / T-states
-
-External signals given to the processor may also have the effect of stopping
-the TSC. This is typically done for thermal emergency power control to prevent
-an overheating condition, and typically, there is no way to detect that this
-condition has happened.
-
-3.7) TSC virtualization - VMX
-
-VMX provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
-instructions, which is enough for full virtualization of TSC in any manner. In
-addition, VMX allows passing through the host TSC plus an additional TSC_OFFSET
-field specified in the VMCS. Special instructions must be used to read and
-write the VMCS field.
-
-3.8) TSC virtualization - SVM
-
-SVM provides conditional trapping of RDTSC, RDMSR, WRMSR and RDTSCP
-instructions, which is enough for full virtualization of TSC in any manner. In
-addition, SVM allows passing through the host TSC plus an additional offset
-field specified in the SVM control block.
-
-3.9) TSC feature bits in Linux
-
-In summary, there is no way to guarantee the TSC remains in perfect
-synchronization unless it is explicitly guaranteed by the architecture. Even
-if so, the TSCs in multi-sockets or NUMA systems may still run independently
-despite being locally consistent.
-
-The following feature bits are used by Linux to signal various TSC attributes,
-but they can only be taken to be meaningful for UP or single node systems.
-
-X86_FEATURE_TSC : The TSC is available in hardware
-X86_FEATURE_RDTSCP : The RDTSCP instruction is available
-X86_FEATURE_CONSTANT_TSC : The TSC rate is unchanged with P-states
-X86_FEATURE_NONSTOP_TSC : The TSC does not stop in C-states
-X86_FEATURE_TSC_RELIABLE : TSC sync checks are skipped (VMware)
-
-4) Virtualization Problems
-
-Timekeeping is especially problematic for virtualization because a number of
-challenges arise. The most obvious problem is that time is now shared between
-the host and, potentially, a number of virtual machines. Thus the virtual
-operating system does not run with 100% usage of the CPU, despite the fact that
-it may very well make that assumption. It may expect it to remain true to very
-exacting bounds when interrupt sources are disabled, but in reality only its
-virtual interrupt sources are disabled, and the machine may still be preempted
-at any time. This causes problems as the passage of real time, the injection
-of machine interrupts and the associated clock sources are no longer completely
-synchronized with real time.
-
-This same problem can occur on native hardware to a degree, as SMM mode may
-steal cycles from the naturally on X86 systems when SMM mode is used by the
-BIOS, but not in such an extreme fashion. However, the fact that SMM mode may
-cause similar problems to virtualization makes it a good justification for
-solving many of these problems on bare metal.
-
-4.1) Interrupt clocking
-
-One of the most immediate problems that occurs with legacy operating systems
-is that the system timekeeping routines are often designed to keep track of
-time by counting periodic interrupts. These interrupts may come from the PIT
-or the RTC, but the problem is the same: the host virtualization engine may not
-be able to deliver the proper number of interrupts per second, and so guest
-time may fall behind. This is especially problematic if a high interrupt rate
-is selected, such as 1000 HZ, which is unfortunately the default for many Linux
-guests.
-
-There are three approaches to solving this problem; first, it may be possible
-to simply ignore it. Guests which have a separate time source for tracking
-'wall clock' or 'real time' may not need any adjustment of their interrupts to
-maintain proper time. If this is not sufficient, it may be necessary to inject
-additional interrupts into the guest in order to increase the effective
-interrupt rate. This approach leads to complications in extreme conditions,
-where host load or guest lag is too much to compensate for, and thus another
-solution to the problem has risen: the guest may need to become aware of lost
-ticks and compensate for them internally. Although promising in theory, the
-implementation of this policy in Linux has been extremely error prone, and a
-number of buggy variants of lost tick compensation are distributed across
-commonly used Linux systems.
-
-Windows uses periodic RTC clocking as a means of keeping time internally, and
-thus requires interrupt slewing to keep proper time. It does use a low enough
-rate (ed: is it 18.2 Hz?) however that it has not yet been a problem in
-practice.
-
-4.2) TSC sampling and serialization
-
-As the highest precision time source available, the cycle counter of the CPU
-has aroused much interest from developers. As explained above, this timer has
-many problems unique to its nature as a local, potentially unstable and
-potentially unsynchronized source. One issue which is not unique to the TSC,
-but is highlighted because of its very precise nature is sampling delay. By
-definition, the counter, once read is already old. However, it is also
-possible for the counter to be read ahead of the actual use of the result.
-This is a consequence of the superscalar execution of the instruction stream,
-which may execute instructions out of order. Such execution is called
-non-serialized. Forcing serialized execution is necessary for precise
-measurement with the TSC, and requires a serializing instruction, such as CPUID
-or an MSR read.
-
-Since CPUID may actually be virtualized by a trap and emulate mechanism, this
-serialization can pose a performance issue for hardware virtualization. An
-accurate time stamp counter reading may therefore not always be available, and
-it may be necessary for an implementation to guard against "backwards" reads of
-the TSC as seen from other CPUs, even in an otherwise perfectly synchronized
-system.
-
-4.3) Timespec aliasing
-
-Additionally, this lack of serialization from the TSC poses another challenge
-when using results of the TSC when measured against another time source. As
-the TSC is much higher precision, many possible values of the TSC may be read
-while another clock is still expressing the same value.
-
-That is, you may read (T,T+10) while external clock C maintains the same value.
-Due to non-serialized reads, you may actually end up with a range which
-fluctuates - from (T-1.. T+10). Thus, any time calculated from a TSC, but
-calibrated against an external value may have a range of valid values.
-Re-calibrating this computation may actually cause time, as computed after the
-calibration, to go backwards, compared with time computed before the
-calibration.
-
-This problem is particularly pronounced with an internal time source in Linux,
-the kernel time, which is expressed in the theoretically high resolution
-timespec - but which advances in much larger granularity intervals, sometimes
-at the rate of jiffies, and possibly in catchup modes, at a much larger step.
-
-This aliasing requires care in the computation and recalibration of kvmclock
-and any other values derived from TSC computation (such as TSC virtualization
-itself).
-
-4.4) Migration
-
-Migration of a virtual machine raises problems for timekeeping in two ways.
-First, the migration itself may take time, during which interrupts cannot be
-delivered, and after which, the guest time may need to be caught up. NTP may
-be able to help to some degree here, as the clock correction required is
-typically small enough to fall in the NTP-correctable window.
-
-An additional concern is that timers based off the TSC (or HPET, if the raw bus
-clock is exposed) may now be running at different rates, requiring compensation
-in some way in the hypervisor by virtualizing these timers. In addition,
-migrating to a faster machine may preclude the use of a passthrough TSC, as a
-faster clock cannot be made visible to a guest without the potential of time
-advancing faster than usual. A slower clock is less of a problem, as it can
-always be caught up to the original rate. KVM clock avoids these problems by
-simply storing multipliers and offsets against the TSC for the guest to convert
-back into nanosecond resolution values.
-
-4.5) Scheduling
-
-Since scheduling may be based on precise timing and firing of interrupts, the
-scheduling algorithms of an operating system may be adversely affected by
-virtualization. In theory, the effect is random and should be universally
-distributed, but in contrived as well as real scenarios (guest device access,
-causes of virtualization exits, possible context switch), this may not always
-be the case. The effect of this has not been well studied.
-
-In an attempt to work around this, several implementations have provided a
-paravirtualized scheduler clock, which reveals the true amount of CPU time for
-which a virtual machine has been running.
-
-4.6) Watchdogs
-
-Watchdog timers, such as the lock detector in Linux may fire accidentally when
-running under hardware virtualization due to timer interrupts being delayed or
-misinterpretation of the passage of real time. Usually, these warnings are
-spurious and can be ignored, but in some circumstances it may be necessary to
-disable such detection.
-
-4.7) Delays and precision timing
-
-Precise timing and delays may not be possible in a virtualized system. This
-can happen if the system is controlling physical hardware, or issues delays to
-compensate for slower I/O to and from devices. The first issue is not solvable
-in general for a virtualized system; hardware control software can't be
-adequately virtualized without a full real-time operating system, which would
-require an RT aware virtualization platform.
-
-The second issue may cause performance problems, but this is unlikely to be a
-significant issue. In many cases these delays may be eliminated through
-configuration or paravirtualization.
-
-4.8) Covert channels and leaks
-
-In addition to the above problems, time information will inevitably leak to the
-guest about the host in anything but a perfect implementation of virtualized
-time. This may allow the guest to infer the presence of a hypervisor (as in a
-red-pill type detection), and it may allow information to leak between guests
-by using CPU utilization itself as a signalling channel. Preventing such
-problems would require completely isolated virtual time which may not track
-real time any longer. This may be useful in certain security or QA contexts,
-but in general isn't recommended for real-world deployment scenarios.
+++ /dev/null
-=================
-KVM VCPU Requests
-=================
-
-Overview
-========
-
-KVM supports an internal API enabling threads to request a VCPU thread to
-perform some activity. For example, a thread may request a VCPU to flush
-its TLB with a VCPU request. The API consists of the following functions::
-
- /* Check if any requests are pending for VCPU @vcpu. */
- bool kvm_request_pending(struct kvm_vcpu *vcpu);
-
- /* Check if VCPU @vcpu has request @req pending. */
- bool kvm_test_request(int req, struct kvm_vcpu *vcpu);
-
- /* Clear request @req for VCPU @vcpu. */
- void kvm_clear_request(int req, struct kvm_vcpu *vcpu);
-
- /*
- * Check if VCPU @vcpu has request @req pending. When the request is
- * pending it will be cleared and a memory barrier, which pairs with
- * another in kvm_make_request(), will be issued.
- */
- bool kvm_check_request(int req, struct kvm_vcpu *vcpu);
-
- /*
- * Make request @req of VCPU @vcpu. Issues a memory barrier, which pairs
- * with another in kvm_check_request(), prior to setting the request.
- */
- void kvm_make_request(int req, struct kvm_vcpu *vcpu);
-
- /* Make request @req of all VCPUs of the VM with struct kvm @kvm. */
- bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
-
-Typically a requester wants the VCPU to perform the activity as soon
-as possible after making the request. This means most requests
-(kvm_make_request() calls) are followed by a call to kvm_vcpu_kick(),
-and kvm_make_all_cpus_request() has the kicking of all VCPUs built
-into it.
-
-VCPU Kicks
-----------
-
-The goal of a VCPU kick is to bring a VCPU thread out of guest mode in
-order to perform some KVM maintenance. To do so, an IPI is sent, forcing
-a guest mode exit. However, a VCPU thread may not be in guest mode at the
-time of the kick. Therefore, depending on the mode and state of the VCPU
-thread, there are two other actions a kick may take. All three actions
-are listed below:
-
-1) Send an IPI. This forces a guest mode exit.
-2) Waking a sleeping VCPU. Sleeping VCPUs are VCPU threads outside guest
- mode that wait on waitqueues. Waking them removes the threads from
- the waitqueues, allowing the threads to run again. This behavior
- may be suppressed, see KVM_REQUEST_NO_WAKEUP below.
-3) Nothing. When the VCPU is not in guest mode and the VCPU thread is not
- sleeping, then there is nothing to do.
-
-VCPU Mode
----------
-
-VCPUs have a mode state, ``vcpu->mode``, that is used to track whether the
-guest is running in guest mode or not, as well as some specific
-outside guest mode states. The architecture may use ``vcpu->mode`` to
-ensure VCPU requests are seen by VCPUs (see "Ensuring Requests Are Seen"),
-as well as to avoid sending unnecessary IPIs (see "IPI Reduction"), and
-even to ensure IPI acknowledgements are waited upon (see "Waiting for
-Acknowledgements"). The following modes are defined:
-
-OUTSIDE_GUEST_MODE
-
- The VCPU thread is outside guest mode.
-
-IN_GUEST_MODE
-
- The VCPU thread is in guest mode.
-
-EXITING_GUEST_MODE
-
- The VCPU thread is transitioning from IN_GUEST_MODE to
- OUTSIDE_GUEST_MODE.
-
-READING_SHADOW_PAGE_TABLES
-
- The VCPU thread is outside guest mode, but it wants the sender of
- certain VCPU requests, namely KVM_REQ_TLB_FLUSH, to wait until the VCPU
- thread is done reading the page tables.
-
-VCPU Request Internals
-======================
-
-VCPU requests are simply bit indices of the ``vcpu->requests`` bitmap.
-This means general bitops, like those documented in [atomic-ops]_ could
-also be used, e.g. ::
-
- clear_bit(KVM_REQ_UNHALT & KVM_REQUEST_MASK, &vcpu->requests);
-
-However, VCPU request users should refrain from doing so, as it would
-break the abstraction. The first 8 bits are reserved for architecture
-independent requests, all additional bits are available for architecture
-dependent requests.
-
-Architecture Independent Requests
----------------------------------
-
-KVM_REQ_TLB_FLUSH
-
- KVM's common MMU notifier may need to flush all of a guest's TLB
- entries, calling kvm_flush_remote_tlbs() to do so. Architectures that
- choose to use the common kvm_flush_remote_tlbs() implementation will
- need to handle this VCPU request.
-
-KVM_REQ_MMU_RELOAD
-
- When shadow page tables are used and memory slots are removed it's
- necessary to inform each VCPU to completely refresh the tables. This
- request is used for that.
-
-KVM_REQ_PENDING_TIMER
-
- This request may be made from a timer handler run on the host on behalf
- of a VCPU. It informs the VCPU thread to inject a timer interrupt.
-
-KVM_REQ_UNHALT
-
- This request may be made from the KVM common function kvm_vcpu_block(),
- which is used to emulate an instruction that causes a CPU to halt until
- one of an architectural specific set of events and/or interrupts is
- received (determined by checking kvm_arch_vcpu_runnable()). When that
- event or interrupt arrives kvm_vcpu_block() makes the request. This is
- in contrast to when kvm_vcpu_block() returns due to any other reason,
- such as a pending signal, which does not indicate the VCPU's halt
- emulation should stop, and therefore does not make the request.
-
-KVM_REQUEST_MASK
-----------------
-
-VCPU requests should be masked by KVM_REQUEST_MASK before using them with
-bitops. This is because only the lower 8 bits are used to represent the
-request's number. The upper bits are used as flags. Currently only two
-flags are defined.
-
-VCPU Request Flags
-------------------
-
-KVM_REQUEST_NO_WAKEUP
-
- This flag is applied to requests that only need immediate attention
- from VCPUs running in guest mode. That is, sleeping VCPUs do not need
- to be awaken for these requests. Sleeping VCPUs will handle the
- requests when they are awaken later for some other reason.
-
-KVM_REQUEST_WAIT
-
- When requests with this flag are made with kvm_make_all_cpus_request(),
- then the caller will wait for each VCPU to acknowledge its IPI before
- proceeding. This flag only applies to VCPUs that would receive IPIs.
- If, for example, the VCPU is sleeping, so no IPI is necessary, then
- the requesting thread does not wait. This means that this flag may be
- safely combined with KVM_REQUEST_NO_WAKEUP. See "Waiting for
- Acknowledgements" for more information about requests with
- KVM_REQUEST_WAIT.
-
-VCPU Requests with Associated State
-===================================
-
-Requesters that want the receiving VCPU to handle new state need to ensure
-the newly written state is observable to the receiving VCPU thread's CPU
-by the time it observes the request. This means a write memory barrier
-must be inserted after writing the new state and before setting the VCPU
-request bit. Additionally, on the receiving VCPU thread's side, a
-corresponding read barrier must be inserted after reading the request bit
-and before proceeding to read the new state associated with it. See
-scenario 3, Message and Flag, of [lwn-mb]_ and the kernel documentation
-[memory-barriers]_.
-
-The pair of functions, kvm_check_request() and kvm_make_request(), provide
-the memory barriers, allowing this requirement to be handled internally by
-the API.
-
-Ensuring Requests Are Seen
-==========================
-
-When making requests to VCPUs, we want to avoid the receiving VCPU
-executing in guest mode for an arbitrary long time without handling the
-request. We can be sure this won't happen as long as we ensure the VCPU
-thread checks kvm_request_pending() before entering guest mode and that a
-kick will send an IPI to force an exit from guest mode when necessary.
-Extra care must be taken to cover the period after the VCPU thread's last
-kvm_request_pending() check and before it has entered guest mode, as kick
-IPIs will only trigger guest mode exits for VCPU threads that are in guest
-mode or at least have already disabled interrupts in order to prepare to
-enter guest mode. This means that an optimized implementation (see "IPI
-Reduction") must be certain when it's safe to not send the IPI. One
-solution, which all architectures except s390 apply, is to:
-
-- set ``vcpu->mode`` to IN_GUEST_MODE between disabling the interrupts and
- the last kvm_request_pending() check;
-- enable interrupts atomically when entering the guest.
-
-This solution also requires memory barriers to be placed carefully in both
-the requesting thread and the receiving VCPU. With the memory barriers we
-can exclude the possibility of a VCPU thread observing
-!kvm_request_pending() on its last check and then not receiving an IPI for
-the next request made of it, even if the request is made immediately after
-the check. This is done by way of the Dekker memory barrier pattern
-(scenario 10 of [lwn-mb]_). As the Dekker pattern requires two variables,
-this solution pairs ``vcpu->mode`` with ``vcpu->requests``. Substituting
-them into the pattern gives::
-
- CPU1 CPU2
- ================= =================
- local_irq_disable();
- WRITE_ONCE(vcpu->mode, IN_GUEST_MODE); kvm_make_request(REQ, vcpu);
- smp_mb(); smp_mb();
- if (kvm_request_pending(vcpu)) { if (READ_ONCE(vcpu->mode) ==
- IN_GUEST_MODE) {
- ...abort guest entry... ...send IPI...
- } }
-
-As stated above, the IPI is only useful for VCPU threads in guest mode or
-that have already disabled interrupts. This is why this specific case of
-the Dekker pattern has been extended to disable interrupts before setting
-``vcpu->mode`` to IN_GUEST_MODE. WRITE_ONCE() and READ_ONCE() are used to
-pedantically implement the memory barrier pattern, guaranteeing the
-compiler doesn't interfere with ``vcpu->mode``'s carefully planned
-accesses.
-
-IPI Reduction
--------------
-
-As only one IPI is needed to get a VCPU to check for any/all requests,
-then they may be coalesced. This is easily done by having the first IPI
-sending kick also change the VCPU mode to something !IN_GUEST_MODE. The
-transitional state, EXITING_GUEST_MODE, is used for this purpose.
-
-Waiting for Acknowledgements
-----------------------------
-
-Some requests, those with the KVM_REQUEST_WAIT flag set, require IPIs to
-be sent, and the acknowledgements to be waited upon, even when the target
-VCPU threads are in modes other than IN_GUEST_MODE. For example, one case
-is when a target VCPU thread is in READING_SHADOW_PAGE_TABLES mode, which
-is set after disabling interrupts. To support these cases, the
-KVM_REQUEST_WAIT flag changes the condition for sending an IPI from
-checking that the VCPU is IN_GUEST_MODE to checking that it is not
-OUTSIDE_GUEST_MODE.
-
-Request-less VCPU Kicks
------------------------
-
-As the determination of whether or not to send an IPI depends on the
-two-variable Dekker memory barrier pattern, then it's clear that
-request-less VCPU kicks are almost never correct. Without the assurance
-that a non-IPI generating kick will still result in an action by the
-receiving VCPU, as the final kvm_request_pending() check does for
-request-accompanying kicks, then the kick may not do anything useful at
-all. If, for instance, a request-less kick was made to a VCPU that was
-just about to set its mode to IN_GUEST_MODE, meaning no IPI is sent, then
-the VCPU thread may continue its entry without actually having done
-whatever it was the kick was meant to initiate.
-
-One exception is x86's posted interrupt mechanism. In this case, however,
-even the request-less VCPU kick is coupled with the same
-local_irq_disable() + smp_mb() pattern described above; the ON bit
-(Outstanding Notification) in the posted interrupt descriptor takes the
-role of ``vcpu->requests``. When sending a posted interrupt, PIR.ON is
-set before reading ``vcpu->mode``; dually, in the VCPU thread,
-vmx_sync_pir_to_irr() reads PIR after setting ``vcpu->mode`` to
-IN_GUEST_MODE.
-
-Additional Considerations
-=========================
-
-Sleeping VCPUs
---------------
-
-VCPU threads may need to consider requests before and/or after calling
-functions that may put them to sleep, e.g. kvm_vcpu_block(). Whether they
-do or not, and, if they do, which requests need consideration, is
-architecture dependent. kvm_vcpu_block() calls kvm_arch_vcpu_runnable()
-to check if it should awaken. One reason to do so is to provide
-architectures a function where requests may be checked if necessary.
-
-Clearing Requests
------------------
-
-Generally it only makes sense for the receiving VCPU thread to clear a
-request. However, in some circumstances, such as when the requesting
-thread and the receiving VCPU thread are executed serially, such as when
-they are the same thread, or when they are using some form of concurrency
-control to temporarily execute synchronously, then it's possible to know
-that the request may be cleared immediately, rather than waiting for the
-receiving VCPU thread to handle the request in VCPU RUN. The only current
-examples of this are kvm_vcpu_block() calls made by VCPUs to block
-themselves. A possible side-effect of that call is to make the
-KVM_REQ_UNHALT request, which may then be cleared immediately when the
-VCPU returns from the call.
-
-References
-==========
-
-.. [atomic-ops] Documentation/core-api/atomic_ops.rst
-.. [memory-barriers] Documentation/memory-barriers.txt
-.. [lwn-mb] https://lwn.net/Articles/573436/
+++ /dev/null
-.. SPDX-License-Identifier: GPL-2.0
-
-============
-Paravirt_ops
-============
-
-Linux provides support for different hypervisor virtualization technologies.
-Historically different binary kernels would be required in order to support
-different hypervisors, this restriction was removed with pv_ops.
-Linux pv_ops is a virtualization API which enables support for different
-hypervisors. It allows each hypervisor to override critical operations and
-allows a single kernel binary to run on all supported execution environments
-including native machine -- without any hypervisors.
-
-pv_ops provides a set of function pointers which represent operations
-corresponding to low level critical instructions and high level
-functionalities in various areas. pv-ops allows for optimizations at run
-time by enabling binary patching of the low-ops critical operations
-at boot time.
-
-pv_ops operations are classified into three categories:
-
-- simple indirect call
- These operations correspond to high level functionality where it is
- known that the overhead of indirect call isn't very important.
-
-- indirect call which allows optimization with binary patch
- Usually these operations correspond to low level critical instructions. They
- are called frequently and are performance critical. The overhead is
- very important.
-
-- a set of macros for hand written assembly code
- Hand written assembly codes (.S files) also need paravirtualization
- because they include sensitive instructions or some of code paths in
- them are very performance critical.
+++ /dev/null
- User Mode Linux HOWTO
- User Mode Linux Core Team
- Mon Nov 18 14:16:16 EST 2002
-
- This document describes the use and abuse of Jeff Dike's User Mode
- Linux: a port of the Linux kernel as a normal Intel Linux process.
- ______________________________________________________________________
-
- Table of Contents
-
- 1. Introduction
-
- 1.1 How is User Mode Linux Different?
- 1.2 Why Would I Want User Mode Linux?
-
- 2. Compiling the kernel and modules
-
- 2.1 Compiling the kernel
- 2.2 Compiling and installing kernel modules
- 2.3 Compiling and installing uml_utilities
-
- 3. Running UML and logging in
-
- 3.1 Running UML
- 3.2 Logging in
- 3.3 Examples
-
- 4. UML on 2G/2G hosts
-
- 4.1 Introduction
- 4.2 The problem
- 4.3 The solution
-
- 5. Setting up serial lines and consoles
-
- 5.1 Specifying the device
- 5.2 Specifying the channel
- 5.3 Examples
-
- 6. Setting up the network
-
- 6.1 General setup
- 6.2 Userspace daemons
- 6.3 Specifying ethernet addresses
- 6.4 UML interface setup
- 6.5 Multicast
- 6.6 TUN/TAP with the uml_net helper
- 6.7 TUN/TAP with a preconfigured tap device
- 6.8 Ethertap
- 6.9 The switch daemon
- 6.10 Slip
- 6.11 Slirp
- 6.12 pcap
- 6.13 Setting up the host yourself
-
- 7. Sharing Filesystems between Virtual Machines
-
- 7.1 A warning
- 7.2 Using layered block devices
- 7.3 Note!
- 7.4 Another warning
- 7.5 uml_moo : Merging a COW file with its backing file
-
- 8. Creating filesystems
-
- 8.1 Create the filesystem file
- 8.2 Assign the file to a UML device
- 8.3 Creating and mounting the filesystem
-
- 9. Host file access
-
- 9.1 Using hostfs
- 9.2 hostfs as the root filesystem
- 9.3 Building hostfs
-
- 10. The Management Console
- 10.1 version
- 10.2 halt and reboot
- 10.3 config
- 10.4 remove
- 10.5 sysrq
- 10.6 help
- 10.7 cad
- 10.8 stop
- 10.9 go
-
- 11. Kernel debugging
-
- 11.1 Starting the kernel under gdb
- 11.2 Examining sleeping processes
- 11.3 Running ddd on UML
- 11.4 Debugging modules
- 11.5 Attaching gdb to the kernel
- 11.6 Using alternate debuggers
-
- 12. Kernel debugging examples
-
- 12.1 The case of the hung fsck
- 12.2 Episode 2: The case of the hung fsck
-
- 13. What to do when UML doesn't work
-
- 13.1 Strange compilation errors when you build from source
- 13.2 (obsolete)
- 13.3 A variety of panics and hangs with /tmp on a reiserfs filesystem
- 13.4 The compile fails with errors about conflicting types for 'open', 'dup', and 'waitpid'
- 13.5 UML doesn't work when /tmp is an NFS filesystem
- 13.6 UML hangs on boot when compiled with gprof support
- 13.7 syslogd dies with a SIGTERM on startup
- 13.8 TUN/TAP networking doesn't work on a 2.4 host
- 13.9 You can network to the host but not to other machines on the net
- 13.10 I have no root and I want to scream
- 13.11 UML build conflict between ptrace.h and ucontext.h
- 13.12 The UML BogoMips is exactly half the host's BogoMips
- 13.13 When you run UML, it immediately segfaults
- 13.14 xterms appear, then immediately disappear
- 13.15 Any other panic, hang, or strange behavior
-
- 14. Diagnosing Problems
-
- 14.1 Case 1 : Normal kernel panics
- 14.2 Case 2 : Tracing thread panics
- 14.3 Case 3 : Tracing thread panics caused by other threads
- 14.4 Case 4 : Hangs
-
- 15. Thanks
-
- 15.1 Code and Documentation
- 15.2 Flushing out bugs
- 15.3 Buglets and clean-ups
- 15.4 Case Studies
- 15.5 Other contributions
-
-
- ______________________________________________________________________
-
- 1. Introduction
-
- Welcome to User Mode Linux. It's going to be fun.
-
-
-
- 1.1. How is User Mode Linux Different?
-
- Normally, the Linux Kernel talks straight to your hardware (video
- card, keyboard, hard drives, etc), and any programs which run ask the
- kernel to operate the hardware, like so:
-
-
-
- +-----------+-----------+----+
- | Process 1 | Process 2 | ...|
- +-----------+-----------+----+
- | Linux Kernel |
- +----------------------------+
- | Hardware |
- +----------------------------+
-
-
-
-
- The User Mode Linux Kernel is different; instead of talking to the
- hardware, it talks to a `real' Linux kernel (called the `host kernel'
- from now on), like any other program. Programs can then run inside
- User-Mode Linux as if they were running under a normal kernel, like
- so:
-
-
-
- +----------------+
- | Process 2 | ...|
- +-----------+----------------+
- | Process 1 | User-Mode Linux|
- +----------------------------+
- | Linux Kernel |
- +----------------------------+
- | Hardware |
- +----------------------------+
-
-
-
-
-
- 1.2. Why Would I Want User Mode Linux?
-
-
- 1. If User Mode Linux crashes, your host kernel is still fine.
-
- 2. You can run a usermode kernel as a non-root user.
-
- 3. You can debug the User Mode Linux like any normal process.
-
- 4. You can run gprof (profiling) and gcov (coverage testing).
-
- 5. You can play with your kernel without breaking things.
-
- 6. You can use it as a sandbox for testing new apps.
-
- 7. You can try new development kernels safely.
-
- 8. You can run different distributions simultaneously.
-
- 9. It's extremely fun.
-
-
-
-
-
- 2. Compiling the kernel and modules
-
-
-
-
- 2.1. Compiling the kernel
-
-
- Compiling the user mode kernel is just like compiling any other
- kernel. Let's go through the steps, using 2.4.0-prerelease (current
- as of this writing) as an example:
-
-
- 1. Download the latest UML patch from
-
- the download page <http://user-mode-linux.sourceforge.net/
-
- In this example, the file is uml-patch-2.4.0-prerelease.bz2.
-
-
- 2. Download the matching kernel from your favourite kernel mirror,
- such as:
-
- ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2
- <ftp://ftp.ca.kernel.org/pub/kernel/v2.4/linux-2.4.0-prerelease.tar.bz2>
- .
-
-
- 3. Make a directory and unpack the kernel into it.
-
-
-
- host%
- mkdir ~/uml
-
-
-
-
-
-
- host%
- cd ~/uml
-
-
-
-
-
-
- host%
- tar -xzvf linux-2.4.0-prerelease.tar.bz2
-
-
-
-
-
-
- 4. Apply the patch using
-
-
-
- host%
- cd ~/uml/linux
-
-
-
- host%
- bzcat uml-patch-2.4.0-prerelease.bz2 | patch -p1
-
-
-
-
-
-
- 5. Run your favorite config; `make xconfig ARCH=um' is the most
- convenient. `make config ARCH=um' and 'make menuconfig ARCH=um'
- will work as well. The defaults will give you a useful kernel. If
- you want to change something, go ahead, it probably won't hurt
- anything.
-
-
- Note: If the host is configured with a 2G/2G address space split
- rather than the usual 3G/1G split, then the packaged UML binaries
- will not run. They will immediately segfault. See ``UML on 2G/2G
- hosts'' for the scoop on running UML on your system.
-
-
-
- 6. Finish with `make linux ARCH=um': the result is a file called
- `linux' in the top directory of your source tree.
-
- Make sure that you don't build this kernel in /usr/src/linux. On some
- distributions, /usr/include/asm is a link into this pool. The user-
- mode build changes the other end of that link, and things that include
- <asm/anything.h> stop compiling.
-
- The sources are also available from cvs at the project's cvs page,
- which has directions on getting the sources. You can also browse the
- CVS pool from there.
-
- If you get the CVS sources, you will have to check them out into an
- empty directory. You will then have to copy each file into the
- corresponding directory in the appropriate kernel pool.
-
- If you don't have the latest kernel pool, you can get the
- corresponding user-mode sources with
-
-
- host% cvs co -r v_2_3_x linux
-
-
-
-
- where 'x' is the version in your pool. Note that you will not get the
- bug fixes and enhancements that have gone into subsequent releases.
-
-
- 2.2. Compiling and installing kernel modules
-
- UML modules are built in the same way as the native kernel (with the
- exception of the 'ARCH=um' that you always need for UML):
-
-
- host% make modules ARCH=um
-
-
-
-
- Any modules that you want to load into this kernel need to be built in
- the user-mode pool. Modules from the native kernel won't work.
-
- You can install them by using ftp or something to copy them into the
- virtual machine and dropping them into /lib/modules/`uname -r`.
-
- You can also get the kernel build process to install them as follows:
-
- 1. with the kernel not booted, mount the root filesystem in the top
- level of the kernel pool:
-
-
- host% mount root_fs mnt -o loop
-
-
-
-
-
-
- 2. run
-
-
- host%
- make modules_install INSTALL_MOD_PATH=`pwd`/mnt ARCH=um
-
-
-
-
-
-
- 3. unmount the filesystem
-
-
- host% umount mnt
-
-
-
-
-
-
- 4. boot the kernel on it
-
-
- When the system is booted, you can use insmod as usual to get the
- modules into the kernel. A number of things have been loaded into UML
- as modules, especially filesystems and network protocols and filters,
- so most symbols which need to be exported probably already are.
- However, if you do find symbols that need exporting, let us
- <http://user-mode-linux.sourceforge.net/> know, and
- they'll be "taken care of".
-
-
-
- 2.3. Compiling and installing uml_utilities
-
- Many features of the UML kernel require a user-space helper program,
- so a uml_utilities package is distributed separately from the kernel
- patch which provides these helpers. Included within this is:
-
- o port-helper - Used by consoles which connect to xterms or ports
-
- o tunctl - Configuration tool to create and delete tap devices
-
- o uml_net - Setuid binary for automatic tap device configuration
-
- o uml_switch - User-space virtual switch required for daemon
- transport
-
- The uml_utilities tree is compiled with:
-
-
- host#
- make && make install
-
-
-
-
- Note that UML kernel patches may require a specific version of the
- uml_utilities distribution. If you don't keep up with the mailing
- lists, ensure that you have the latest release of uml_utilities if you
- are experiencing problems with your UML kernel, particularly when
- dealing with consoles or command-line switches to the helper programs
-
-
-
-
-
-
-
-
- 3. Running UML and logging in
-
-
-
- 3.1. Running UML
-
- It runs on 2.2.15 or later, and all 2.4 kernels.
-
-
- Booting UML is straightforward. Simply run 'linux': it will try to
- mount the file `root_fs' in the current directory. You do not need to
- run it as root. If your root filesystem is not named `root_fs', then
- you need to put a `ubd0=root_fs_whatever' switch on the linux command
- line.
-
-
- You will need a filesystem to boot UML from. There are a number
- available for download from here <http://user-mode-
- linux.sourceforge.net/> . There are also several tools
- <http://user-mode-linux.sourceforge.net/> which can be
- used to generate UML-compatible filesystem images from media.
- The kernel will boot up and present you with a login prompt.
-
-
- Note: If the host is configured with a 2G/2G address space split
- rather than the usual 3G/1G split, then the packaged UML binaries will
- not run. They will immediately segfault. See ``UML on 2G/2G hosts''
- for the scoop on running UML on your system.
-
-
-
- 3.2. Logging in
-
-
-
- The prepackaged filesystems have a root account with password 'root'
- and a user account with password 'user'. The login banner will
- generally tell you how to log in. So, you log in and you will find
- yourself inside a little virtual machine. Our filesystems have a
- variety of commands and utilities installed (and it is fairly easy to
- add more), so you will have a lot of tools with which to poke around
- the system.
-
- There are a couple of other ways to log in:
-
- o On a virtual console
-
-
-
- Each virtual console that is configured (i.e. the device exists in
- /dev and /etc/inittab runs a getty on it) will come up in its own
- xterm. If you get tired of the xterms, read ``Setting up serial
- lines and consoles'' to see how to attach the consoles to
- something else, like host ptys.
-
-
-
- o Over the serial line
-
-
- In the boot output, find a line that looks like:
-
-
-
- serial line 0 assigned pty /dev/ptyp1
-
-
-
-
- Attach your favorite terminal program to the corresponding tty. I.e.
- for minicom, the command would be
-
-
- host% minicom -o -p /dev/ttyp1
-
-
-
-
-
-
- o Over the net
-
-
- If the network is running, then you can telnet to the virtual
- machine and log in to it. See ``Setting up the network'' to learn
- about setting up a virtual network.
-
- When you're done using it, run halt, and the kernel will bring itself
- down and the process will exit.
-
-
- 3.3. Examples
-
- Here are some examples of UML in action:
-
- o A login session <http://user-mode-linux.sourceforge.net/login.html>
-
- o A virtual network <http://user-mode-linux.sourceforge.net/net.html>
-
-
-
-
-
-
-
- 4. UML on 2G/2G hosts
-
-
-
-
- 4.1. Introduction
-
-
- Most Linux machines are configured so that the kernel occupies the
- upper 1G (0xc0000000 - 0xffffffff) of the 4G address space and
- processes use the lower 3G (0x00000000 - 0xbfffffff). However, some
- machine are configured with a 2G/2G split, with the kernel occupying
- the upper 2G (0x80000000 - 0xffffffff) and processes using the lower
- 2G (0x00000000 - 0x7fffffff).
-
-
-
-
- 4.2. The problem
-
-
- The prebuilt UML binaries on this site will not run on 2G/2G hosts
- because UML occupies the upper .5G of the 3G process address space
- (0xa0000000 - 0xbfffffff). Obviously, on 2G/2G hosts, this is right
- in the middle of the kernel address space, so UML won't even load - it
- will immediately segfault.
-
-
-
-
- 4.3. The solution
-
-
- The fix for this is to rebuild UML from source after enabling
- CONFIG_HOST_2G_2G (under 'General Setup'). This will cause UML to
- load itself in the top .5G of that smaller process address space,
- where it will run fine. See ``Compiling the kernel and modules'' if
- you need help building UML from source.
-
-
-
-
-
-
-
-
-
-
- 5. Setting up serial lines and consoles
-
-
- It is possible to attach UML serial lines and consoles to many types
- of host I/O channels by specifying them on the command line.
-
-
- You can attach them to host ptys, ttys, file descriptors, and ports.
- This allows you to do things like
-
- o have a UML console appear on an unused host console,
-
- o hook two virtual machines together by having one attach to a pty
- and having the other attach to the corresponding tty
-
- o make a virtual machine accessible from the net by attaching a
- console to a port on the host.
-
-
- The general format of the command line option is device=channel.
-
-
-
- 5.1. Specifying the device
-
- Devices are specified with "con" or "ssl" (console or serial line,
- respectively), optionally with a device number if you are talking
- about a specific device.
-
-
- Using just "con" or "ssl" describes all of the consoles or serial
- lines. If you want to talk about console #3 or serial line #10, they
- would be "con3" and "ssl10", respectively.
-
-
- A specific device name will override a less general "con=" or "ssl=".
- So, for example, you can assign a pty to each of the serial lines
- except for the first two like this:
-
-
- ssl=pty ssl0=tty:/dev/tty0 ssl1=tty:/dev/tty1
-
-
-
-
- The specificity of the device name is all that matters; order on the
- command line is irrelevant.
-
-
-
- 5.2. Specifying the channel
-
- There are a number of different types of channels to attach a UML
- device to, each with a different way of specifying exactly what to
- attach to.
-
- o pseudo-terminals - device=pty pts terminals - device=pts
-
-
- This will cause UML to allocate a free host pseudo-terminal for the
- device. The terminal that it got will be announced in the boot
- log. You access it by attaching a terminal program to the
- corresponding tty:
-
- o screen /dev/pts/n
-
- o screen /dev/ttyxx
-
- o minicom -o -p /dev/ttyxx - minicom seems not able to handle pts
- devices
-
- o kermit - start it up, 'open' the device, then 'connect'
-
-
-
-
-
- o terminals - device=tty:tty device file
-
-
- This will make UML attach the device to the specified tty (i.e
-
-
- con1=tty:/dev/tty3
-
-
-
-
- will attach UML's console 1 to the host's /dev/tty3). If the tty that
- you specify is the slave end of a tty/pty pair, something else must
- have already opened the corresponding pty in order for this to work.
-
-
-
-
-
- o xterms - device=xterm
-
-
- UML will run an xterm and the device will be attached to it.
-
-
-
-
-
- o Port - device=port:port number
-
-
- This will attach the UML devices to the specified host port.
- Attaching console 1 to the host's port 9000 would be done like
- this:
-
-
- con1=port:9000
-
-
-
-
- Attaching all the serial lines to that port would be done similarly:
-
-
- ssl=port:9000
-
-
-
-
- You access these devices by telnetting to that port. Each active tel-
- net session gets a different device. If there are more telnets to a
- port than UML devices attached to it, then the extra telnet sessions
- will block until an existing telnet detaches, or until another device
- becomes active (i.e. by being activated in /etc/inittab).
-
- This channel has the advantage that you can both attach multiple UML
- devices to it and know how to access them without reading the UML boot
- log. It is also unique in allowing access to a UML from remote
- machines without requiring that the UML be networked. This could be
- useful in allowing public access to UMLs because they would be
- accessible from the net, but wouldn't need any kind of network
- filtering or access control because they would have no network access.
-
-
- If you attach the main console to a portal, then the UML boot will
- appear to hang. In reality, it's waiting for a telnet to connect, at
- which point the boot will proceed.
-
-
-
-
-
- o already-existing file descriptors - device=file descriptor
-
-
- If you set up a file descriptor on the UML command line, you can
- attach a UML device to it. This is most commonly used to put the
- main console back on stdin and stdout after assigning all the other
- consoles to something else:
-
-
- con0=fd:0,fd:1 con=pts
-
-
-
-
-
-
-
-
- o Nothing - device=null
-
-
- This allows the device to be opened, in contrast to 'none', but
- reads will block, and writes will succeed and the data will be
- thrown out.
-
-
-
-
-
- o None - device=none
-
-
- This causes the device to disappear.
-
-
-
- You can also specify different input and output channels for a device
- by putting a comma between them:
-
-
- ssl3=tty:/dev/tty2,xterm
-
-
-
-
- will cause serial line 3 to accept input on the host's /dev/tty2 and
- display output on an xterm. That's a silly example - the most common
- use of this syntax is to reattach the main console to stdin and stdout
- as shown above.
-
-
- If you decide to move the main console away from stdin/stdout, the
- initial boot output will appear in the terminal that you're running
- UML in. However, once the console driver has been officially
- initialized, then the boot output will start appearing wherever you
- specified that console 0 should be. That device will receive all
- subsequent output.
-
-
-
- 5.3. Examples
-
- There are a number of interesting things you can do with this
- capability.
-
-
- First, this is how you get rid of those bleeding console xterms by
- attaching them to host ptys:
-
-
- con=pty con0=fd:0,fd:1
-
-
-
-
- This will make a UML console take over an unused host virtual console,
- so that when you switch to it, you will see the UML login prompt
- rather than the host login prompt:
-
-
- con1=tty:/dev/tty6
-
-
-
-
- You can attach two virtual machines together with what amounts to a
- serial line as follows:
-
- Run one UML with a serial line attached to a pty -
-
-
- ssl1=pty
-
-
-
-
- Look at the boot log to see what pty it got (this example will assume
- that it got /dev/ptyp1).
-
- Boot the other UML with a serial line attached to the corresponding
- tty -
-
-
- ssl1=tty:/dev/ttyp1
-
-
-
-
- Log in, make sure that it has no getty on that serial line, attach a
- terminal program like minicom to it, and you should see the login
- prompt of the other virtual machine.
-
-
- 6. Setting up the network
-
-
-
- This page describes how to set up the various transports and to
- provide a UML instance with network access to the host, other machines
- on the local net, and the rest of the net.
-
-
- As of 2.4.5, UML networking has been completely redone to make it much
- easier to set up, fix bugs, and add new features.
-
-
- There is a new helper, uml_net, which does the host setup that
- requires root privileges.
-
-
- There are currently five transport types available for a UML virtual
- machine to exchange packets with other hosts:
-
- o ethertap
-
- o TUN/TAP
-
- o Multicast
-
- o a switch daemon
-
- o slip
-
- o slirp
-
- o pcap
-
- The TUN/TAP, ethertap, slip, and slirp transports allow a UML
- instance to exchange packets with the host. They may be directed
- to the host or the host may just act as a router to provide access
- to other physical or virtual machines.
-
-
- The pcap transport is a synthetic read-only interface, using the
- libpcap binary to collect packets from interfaces on the host and
- filter them. This is useful for building preconfigured traffic
- monitors or sniffers.
-
-
- The daemon and multicast transports provide a completely virtual
- network to other virtual machines. This network is completely
- disconnected from the physical network unless one of the virtual
- machines on it is acting as a gateway.
-
-
- With so many host transports, which one should you use? Here's when
- you should use each one:
-
- o ethertap - if you want access to the host networking and it is
- running 2.2
-
- o TUN/TAP - if you want access to the host networking and it is
- running 2.4. Also, the TUN/TAP transport is able to use a
- preconfigured device, allowing it to avoid using the setuid uml_net
- helper, which is a security advantage.
-
- o Multicast - if you want a purely virtual network and you don't want
- to set up anything but the UML
-
- o a switch daemon - if you want a purely virtual network and you
- don't mind running the daemon in order to get somewhat better
- performance
-
- o slip - there is no particular reason to run the slip backend unless
- ethertap and TUN/TAP are just not available for some reason
-
- o slirp - if you don't have root access on the host to setup
- networking, or if you don't want to allocate an IP to your UML
-
- o pcap - not much use for actual network connectivity, but great for
- monitoring traffic on the host
-
- Ethertap is available on 2.4 and works fine. TUN/TAP is preferred
- to it because it has better performance and ethertap is officially
- considered obsolete in 2.4. Also, the root helper only needs to
- run occasionally for TUN/TAP, rather than handling every packet, as
- it does with ethertap. This is a slight security advantage since
- it provides fewer opportunities for a nasty UML user to somehow
- exploit the helper's root privileges.
-
-
- 6.1. General setup
-
- First, you must have the virtual network enabled in your UML. If are
- running a prebuilt kernel from this site, everything is already
- enabled. If you build the kernel yourself, under the "Network device
- support" menu, enable "Network device support", and then the three
- transports.
-
-
- The next step is to provide a network device to the virtual machine.
- This is done by describing it on the kernel command line.
-
- The general format is
-
-
- eth <n> = <transport> , <transport args>
-
-
-
-
- For example, a virtual ethernet device may be attached to a host
- ethertap device as follows:
-
-
- eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254
-
-
-
-
- This sets up eth0 inside the virtual machine to attach itself to the
- host /dev/tap0, assigns it an ethernet address, and assigns the host
- tap0 interface an IP address.
-
-
-
- Note that the IP address you assign to the host end of the tap device
- must be different than the IP you assign to the eth device inside UML.
- If you are short on IPs and don't want to consume two per UML, then
- you can reuse the host's eth IP address for the host ends of the tap
- devices. Internally, the UMLs must still get unique IPs for their eth
- devices. You can also give the UMLs non-routable IPs (192.168.x.x or
- 10.x.x.x) and have the host masquerade them. This will let outgoing
- connections work, but incoming connections won't without more work,
- such as port forwarding from the host.
- Also note that when you configure the host side of an interface, it is
- only acting as a gateway. It will respond to pings sent to it
- locally, but is not useful to do that since it's a host interface.
- You are not talking to the UML when you ping that interface and get a
- response.
-
-
- You can also add devices to a UML and remove them at runtime. See the
- ``The Management Console'' page for details.
-
-
- The sections below describe this in more detail.
-
-
- Once you've decided how you're going to set up the devices, you boot
- UML, log in, configure the UML side of the devices, and set up routes
- to the outside world. At that point, you will be able to talk to any
- other machines, physical or virtual, on the net.
-
-
- If ifconfig inside UML fails and the network refuses to come up, run
- tell you what went wrong.
-
-
-
- 6.2. Userspace daemons
-
- You will likely need the setuid helper, or the switch daemon, or both.
- They are both installed with the RPM and deb, so if you've installed
- either, you can skip the rest of this section.
-
-
- If not, then you need to check them out of CVS, build them, and
- install them. The helper is uml_net, in CVS /tools/uml_net, and the
- daemon is uml_switch, in CVS /tools/uml_router. They are both built
- with a plain 'make'. Both need to be installed in a directory that's
- in your path - /usr/bin is recommend. On top of that, uml_net needs
- to be setuid root.
-
-
-
- 6.3. Specifying ethernet addresses
-
- Below, you will see that the TUN/TAP, ethertap, and daemon interfaces
- allow you to specify hardware addresses for the virtual ethernet
- devices. This is generally not necessary. If you don't have a
- specific reason to do it, you probably shouldn't. If one is not
- specified on the command line, the driver will assign one based on the
- device IP address. It will provide the address fe:fd:nn:nn:nn:nn
- where nn.nn.nn.nn is the device IP address. This is nearly always
- sufficient to guarantee a unique hardware address for the device. A
- couple of exceptions are:
-
- o Another set of virtual ethernet devices are on the same network and
- they are assigned hardware addresses using a different scheme which
- may conflict with the UML IP address-based scheme
-
- o You aren't going to use the device for IP networking, so you don't
- assign the device an IP address
-
- If you let the driver provide the hardware address, you should make
- sure that the device IP address is known before the interface is
- brought up. So, inside UML, this will guarantee that:
-
-
-
- UML#
- ifconfig eth0 192.168.0.250 up
-
-
-
-
- If you decide to assign the hardware address yourself, make sure that
- the first byte of the address is even. Addresses with an odd first
- byte are broadcast addresses, which you don't want assigned to a
- device.
-
-
-
- 6.4. UML interface setup
-
- Once the network devices have been described on the command line, you
- should boot UML and log in.
-
-
- The first thing to do is bring the interface up:
-
-
- UML# ifconfig ethn ip-address up
-
-
-
-
- You should be able to ping the host at this point.
-
-
- To reach the rest of the world, you should set a default route to the
- host:
-
-
- UML# route add default gw host ip
-
-
-
-
- Again, with host ip of 192.168.0.4:
-
-
- UML# route add default gw 192.168.0.4
-
-
-
-
- This page used to recommend setting a network route to your local net.
- This is wrong, because it will cause UML to try to figure out hardware
- addresses of the local machines by arping on the interface to the
- host. Since that interface is basically a single strand of ethernet
- with two nodes on it (UML and the host) and arp requests don't cross
- networks, they will fail to elicit any responses. So, what you want
- is for UML to just blindly throw all packets at the host and let it
- figure out what to do with them, which is what leaving out the network
- route and adding the default route does.
-
-
- Note: If you can't communicate with other hosts on your physical
- ethernet, it's probably because of a network route that's
- automatically set up. If you run 'route -n' and see a route that
- looks like this:
-
-
-
-
- Destination Gateway Genmask Flags Metric Ref Use Iface
- 192.168.0.0 0.0.0.0 255.255.255.0 U 0 0 0 eth0
-
-
-
-
- with a mask that's not 255.255.255.255, then replace it with a route
- to your host:
-
-
- UML#
- route del -net 192.168.0.0 dev eth0 netmask 255.255.255.0
-
-
-
-
-
-
- UML#
- route add -host 192.168.0.4 dev eth0
-
-
-
-
- This, plus the default route to the host, will allow UML to exchange
- packets with any machine on your ethernet.
-
-
-
- 6.5. Multicast
-
- The simplest way to set up a virtual network between multiple UMLs is
- to use the mcast transport. This was written by Harald Welte and is
- present in UML version 2.4.5-5um and later. Your system must have
- multicast enabled in the kernel and there must be a multicast-capable
- network device on the host. Normally, this is eth0, but if there is
- no ethernet card on the host, then you will likely get strange error
- messages when you bring the device up inside UML.
-
-
- To use it, run two UMLs with
-
-
- eth0=mcast
-
-
-
-
- on their command lines. Log in, configure the ethernet device in each
- machine with different IP addresses:
-
-
- UML1# ifconfig eth0 192.168.0.254
-
-
-
-
-
-
- UML2# ifconfig eth0 192.168.0.253
-
-
-
-
- and they should be able to talk to each other.
-
- The full set of command line options for this transport are
-
-
-
- ethn=mcast,ethernet address,multicast
- address,multicast port,ttl
-
-
-
-
- Harald's original README is here <http://user-mode-linux.source-
- forge.net/> and explains these in detail, as well as
- some other issues.
-
- There is also a related point-to-point only "ucast" transport.
- This is useful when your network does not support multicast, and
- all network connections are simple point to point links.
-
- The full set of command line options for this transport are
-
-
- ethn=ucast,ethernet address,remote address,listen port,remote port
-
-
-
-
- 6.6. TUN/TAP with the uml_net helper
-
- TUN/TAP is the preferred mechanism on 2.4 to exchange packets with the
- host. The TUN/TAP backend has been in UML since 2.4.9-3um.
-
-
- The easiest way to get up and running is to let the setuid uml_net
- helper do the host setup for you. This involves insmod-ing the tun.o
- module if necessary, configuring the device, and setting up IP
- forwarding, routing, and proxy arp. If you are new to UML networking,
- do this first. If you're concerned about the security implications of
- the setuid helper, use it to get up and running, then read the next
- section to see how to have UML use a preconfigured tap device, which
- avoids the use of uml_net.
-
-
- If you specify an IP address for the host side of the device, the
- uml_net helper will do all necessary setup on the host - the only
- requirement is that TUN/TAP be available, either built in to the host
- kernel or as the tun.o module.
-
- The format of the command line switch to attach a device to a TUN/TAP
- device is
-
-
- eth <n> =tuntap,,, <IP address>
-
-
-
-
- For example, this argument will attach the UML's eth0 to the next
- available tap device and assign an ethernet address to it based on its
- IP address
-
-
- eth0=tuntap,,,192.168.0.254
-
-
-
-
-
-
- Note that the IP address that must be used for the eth device inside
- UML is fixed by the routing and proxy arp that is set up on the
- TUN/TAP device on the host. You can use a different one, but it won't
- work because reply packets won't reach the UML. This is a feature.
- It prevents a nasty UML user from doing things like setting the UML IP
- to the same as the network's nameserver or mail server.
-
-
- There are a couple potential problems with running the TUN/TAP
- transport on a 2.4 host kernel
-
- o TUN/TAP seems not to work on 2.4.3 and earlier. Upgrade the host
- kernel or use the ethertap transport.
-
- o With an upgraded kernel, TUN/TAP may fail with
-
-
- File descriptor in bad state
-
-
-
-
- This is due to a header mismatch between the upgraded kernel and the
- kernel that was originally installed on the machine. The fix is to
- make sure that /usr/src/linux points to the headers for the running
- kernel.
-
- These were pointed out by Tim Robinson <timro at trkr dot net> in
- <http://www.geocrawler.com/> name="this uml-
- user post"> .
-
-
-
- 6.7. TUN/TAP with a preconfigured tap device
-
- If you prefer not to have UML use uml_net (which is somewhat
- insecure), with UML 2.4.17-11, you can set up a TUN/TAP device
- beforehand. The setup needs to be done as root, but once that's done,
- there is no need for root assistance. Setting up the device is done
- as follows:
-
- o Create the device with tunctl (available from the UML utilities
- tarball)
-
-
-
-
- host# tunctl -u uid
-
-
-
-
- where uid is the user id or username that UML will be run as. This
- will tell you what device was created.
-
- o Configure the device IP (change IP addresses and device name to
- suit)
-
-
-
-
- host# ifconfig tap0 192.168.0.254 up
-
-
-
-
-
- o Set up routing and arping if desired - this is my recipe, there are
- other ways of doing the same thing
-
-
- host#
- bash -c 'echo 1 > /proc/sys/net/ipv4/ip_forward'
-
- host#
- route add -host 192.168.0.253 dev tap0
-
-
-
-
-
-
- host#
- bash -c 'echo 1 > /proc/sys/net/ipv4/conf/tap0/proxy_arp'
-
-
-
-
-
-
- host#
- arp -Ds 192.168.0.253 eth0 pub
-
-
-
-
- Note that this must be done every time the host boots - this configu-
- ration is not stored across host reboots. So, it's probably a good
- idea to stick it in an rc file. An even better idea would be a little
- utility which reads the information from a config file and sets up
- devices at boot time.
-
- o Rather than using up two IPs and ARPing for one of them, you can
- also provide direct access to your LAN by the UML by using a
- bridge.
-
-
- host#
- brctl addbr br0
-
-
-
-
-
-
- host#
- ifconfig eth0 0.0.0.0 promisc up
-
-
-
-
-
-
- host#
- ifconfig tap0 0.0.0.0 promisc up
-
-
-
-
-
-
- host#
- ifconfig br0 192.168.0.1 netmask 255.255.255.0 up
-
-
-
-
-
-
-
- host#
- brctl stp br0 off
-
-
-
-
-
-
- host#
- brctl setfd br0 1
-
-
-
-
-
-
- host#
- brctl sethello br0 1
-
-
-
-
-
-
- host#
- brctl addif br0 eth0
-
-
-
-
-
-
- host#
- brctl addif br0 tap0
-
-
-
-
- Note that 'br0' should be setup using ifconfig with the existing IP
- address of eth0, as eth0 no longer has its own IP.
-
- o
-
-
- Also, the /dev/net/tun device must be writable by the user running
- UML in order for the UML to use the device that's been configured
- for it. The simplest thing to do is
-
-
- host# chmod 666 /dev/net/tun
-
-
-
-
- Making it world-writable looks bad, but it seems not to be
- exploitable as a security hole. However, it does allow anyone to cre-
- ate useless tap devices (useless because they can't configure them),
- which is a DOS attack. A somewhat more secure alternative would to be
- to create a group containing all the users who have preconfigured tap
- devices and chgrp /dev/net/tun to that group with mode 664 or 660.
-
-
- o Once the device is set up, run UML with 'eth0=tuntap,device name'
- (i.e. 'eth0=tuntap,tap0') on the command line (or do it with the
- mconsole config command).
-
- o Bring the eth device up in UML and you're in business.
-
- If you don't want that tap device any more, you can make it non-
- persistent with
-
-
- host# tunctl -d tap device
-
-
-
-
- Finally, tunctl has a -b (for brief mode) switch which causes it to
- output only the name of the tap device it created. This makes it
- suitable for capture by a script:
-
-
- host# TAP=`tunctl -u 1000 -b`
-
-
-
-
-
-
- 6.8. Ethertap
-
- Ethertap is the general mechanism on 2.2 for userspace processes to
- exchange packets with the kernel.
-
-
-
- To use this transport, you need to describe the virtual network device
- on the UML command line. The general format for this is
-
-
- eth <n> =ethertap, <device> , <ethernet address> , <tap IP address>
-
-
-
-
- So, the previous example
-
-
- eth0=ethertap,tap0,fe:fd:0:0:0:1,192.168.0.254
-
-
-
-
- attaches the UML eth0 device to the host /dev/tap0, assigns it the
- ethernet address fe:fd:0:0:0:1, and assigns the IP address
- 192.168.0.254 to the tap device.
-
-
-
- The tap device is mandatory, but the others are optional. If the
- ethernet address is omitted, one will be assigned to it.
-
-
- The presence of the tap IP address will cause the helper to run and do
- whatever host setup is needed to allow the virtual machine to
- communicate with the outside world. If you're not sure you know what
- you're doing, this is the way to go.
-
-
- If it is absent, then you must configure the tap device and whatever
- arping and routing you will need on the host. However, even in this
- case, the uml_net helper still needs to be in your path and it must be
- setuid root if you're not running UML as root. This is because the
- tap device doesn't support SIGIO, which UML needs in order to use
- something as a source of input. So, the helper is used as a
- convenient asynchronous IO thread.
-
- If you're using the uml_net helper, you can ignore the following host
- setup - uml_net will do it for you. You just need to make sure you
- have ethertap available, either built in to the host kernel or
- available as a module.
-
-
- If you want to set things up yourself, you need to make sure that the
- appropriate /dev entry exists. If it doesn't, become root and create
- it as follows:
-
-
- mknod /dev/tap <minor> c 36 <minor> + 16
-
-
-
-
- For example, this is how to create /dev/tap0:
-
-
- mknod /dev/tap0 c 36 0 + 16
-
-
-
-
- You also need to make sure that the host kernel has ethertap support.
- If ethertap is enabled as a module, you apparently need to insmod
- ethertap once for each ethertap device you want to enable. So,
-
-
- host#
- insmod ethertap
-
-
-
-
- will give you the tap0 interface. To get the tap1 interface, you need
- to run
-
-
- host#
- insmod ethertap unit=1 -o ethertap1
-
-
-
-
-
-
-
- 6.9. The switch daemon
-
- Note: This is the daemon formerly known as uml_router, but which was
- renamed so the network weenies of the world would stop growling at me.
-
-
- The switch daemon, uml_switch, provides a mechanism for creating a
- totally virtual network. By default, it provides no connection to the
- host network (but see -tap, below).
-
-
- The first thing you need to do is run the daemon. Running it with no
- arguments will make it listen on a default pair of unix domain
- sockets.
-
-
- If you want it to listen on a different pair of sockets, use
-
-
- -unix control socket data socket
-
-
-
-
-
- If you want it to act as a hub rather than a switch, use
-
-
- -hub
-
-
-
-
-
- If you want the switch to be connected to host networking (allowing
- the umls to get access to the outside world through the host), use
-
-
- -tap tap0
-
-
-
-
-
- Note that the tap device must be preconfigured (see "TUN/TAP with a
- preconfigured tap device", above). If you're using a different tap
- device than tap0, specify that instead of tap0.
-
-
- uml_switch can be backgrounded as follows
-
-
- host%
- uml_switch [ options ] < /dev/null > /dev/null
-
-
-
-
- The reason it doesn't background by default is that it listens to
- stdin for EOF. When it sees that, it exits.
-
-
- The general format of the kernel command line switch is
-
-
-
- ethn=daemon,ethernet address,socket
- type,control socket,data socket
-
-
-
-
- You can leave off everything except the 'daemon'. You only need to
- specify the ethernet address if the one that will be assigned to it
- isn't acceptable for some reason. The rest of the arguments describe
- how to communicate with the daemon. You should only specify them if
- you told the daemon to use different sockets than the default. So, if
- you ran the daemon with no arguments, running the UML on the same
- machine with
- eth0=daemon
-
-
-
-
- will cause the eth0 driver to attach itself to the daemon correctly.
-
-
-
- 6.10. Slip
-
- Slip is another, less general, mechanism for a process to communicate
- with the host networking. In contrast to the ethertap interface,
- which exchanges ethernet frames with the host and can be used to
- transport any higher-level protocol, it can only be used to transport
- IP.
-
-
- The general format of the command line switch is
-
-
-
- ethn=slip,slip IP
-
-
-
-
- The slip IP argument is the IP address that will be assigned to the
- host end of the slip device. If it is specified, the helper will run
- and will set up the host so that the virtual machine can reach it and
- the rest of the network.
-
-
- There are some oddities with this interface that you should be aware
- of. You should only specify one slip device on a given virtual
- machine, and its name inside UML will be 'umn', not 'eth0' or whatever
- you specified on the command line. These problems will be fixed at
- some point.
-
-
-
- 6.11. Slirp
-
- slirp uses an external program, usually /usr/bin/slirp, to provide IP
- only networking connectivity through the host. This is similar to IP
- masquerading with a firewall, although the translation is performed in
- user-space, rather than by the kernel. As slirp does not set up any
- interfaces on the host, or changes routing, slirp does not require
- root access or setuid binaries on the host.
-
-
- The general format of the command line switch for slirp is:
-
-
-
- ethn=slirp,ethernet address,slirp path
-
-
-
-
- The ethernet address is optional, as UML will set up the interface
- with an ethernet address based upon the initial IP address of the
- interface. The slirp path is generally /usr/bin/slirp, although it
- will depend on distribution.
-
-
- The slirp program can have a number of options passed to the command
- line and we can't add them to the UML command line, as they will be
- parsed incorrectly. Instead, a wrapper shell script can be written or
- the options inserted into the /.slirprc file. More information on
- all of the slirp options can be found in its man pages.
-
-
- The eth0 interface on UML should be set up with the IP 10.2.0.15,
- although you can use anything as long as it is not used by a network
- you will be connecting to. The default route on UML should be set to
- use
-
-
- UML#
- route add default dev eth0
-
-
-
-
- slirp provides a number of useful IP addresses which can be used by
- UML, such as 10.0.2.3 which is an alias for the DNS server specified
- in /etc/resolv.conf on the host or the IP given in the 'dns' option
- for slirp.
-
-
- Even with a baudrate setting higher than 115200, the slirp connection
- is limited to 115200. If you need it to go faster, the slirp binary
- needs to be compiled with FULL_BOLT defined in config.h.
-
-
-
- 6.12. pcap
-
- The pcap transport is attached to a UML ethernet device on the command
- line or with uml_mconsole with the following syntax:
-
-
-
- ethn=pcap,host interface,filter
- expression,option1,option2
-
-
-
-
- The expression and options are optional.
-
-
- The interface is whatever network device on the host you want to
- sniff. The expression is a pcap filter expression, which is also what
- tcpdump uses, so if you know how to specify tcpdump filters, you will
- use the same expressions here. The options are up to two of
- 'promisc', control whether pcap puts the host interface into
- promiscuous mode. 'optimize' and 'nooptimize' control whether the pcap
- expression optimizer is used.
-
-
- Example:
-
-
-
- eth0=pcap,eth0,tcp
-
- eth1=pcap,eth0,!tcp
-
-
-
- will cause the UML eth0 to emit all tcp packets on the host eth0 and
- the UML eth1 to emit all non-tcp packets on the host eth0.
-
-
-
- 6.13. Setting up the host yourself
-
- If you don't specify an address for the host side of the ethertap or
- slip device, UML won't do any setup on the host. So this is what is
- needed to get things working (the examples use a host-side IP of
- 192.168.0.251 and a UML-side IP of 192.168.0.250 - adjust to suit your
- own network):
-
- o The device needs to be configured with its IP address. Tap devices
- are also configured with an mtu of 1484. Slip devices are
- configured with a point-to-point address pointing at the UML ip
- address.
-
-
- host# ifconfig tap0 arp mtu 1484 192.168.0.251 up
-
-
-
-
-
-
- host#
- ifconfig sl0 192.168.0.251 pointopoint 192.168.0.250 up
-
-
-
-
-
- o If a tap device is being set up, a route is set to the UML IP.
-
-
- UML# route add -host 192.168.0.250 gw 192.168.0.251
-
-
-
-
-
- o To allow other hosts on your network to see the virtual machine,
- proxy arp is set up for it.
-
-
- host# arp -Ds 192.168.0.250 eth0 pub
-
-
-
-
-
- o Finally, the host is set up to route packets.
-
-
- host# echo 1 > /proc/sys/net/ipv4/ip_forward
-
-
-
-
-
-
-
-
-
-
- 7. Sharing Filesystems between Virtual Machines
-
-
-
-
- 7.1. A warning
-
- Don't attempt to share filesystems simply by booting two UMLs from the
- same file. That's the same thing as booting two physical machines
- from a shared disk. It will result in filesystem corruption.
-
-
-
- 7.2. Using layered block devices
-
- The way to share a filesystem between two virtual machines is to use
- the copy-on-write (COW) layering capability of the ubd block driver.
- As of 2.4.6-2um, the driver supports layering a read-write private
- device over a read-only shared device. A machine's writes are stored
- in the private device, while reads come from either device - the
- private one if the requested block is valid in it, the shared one if
- not. Using this scheme, the majority of data which is unchanged is
- shared between an arbitrary number of virtual machines, each of which
- has a much smaller file containing the changes that it has made. With
- a large number of UMLs booting from a large root filesystem, this
- leads to a huge disk space saving. It will also help performance,
- since the host will be able to cache the shared data using a much
- smaller amount of memory, so UML disk requests will be served from the
- host's memory rather than its disks.
-
-
-
-
- To add a copy-on-write layer to an existing block device file, simply
- add the name of the COW file to the appropriate ubd switch:
-
-
- ubd0=root_fs_cow,root_fs_debian_22
-
-
-
-
- where 'root_fs_cow' is the private COW file and 'root_fs_debian_22' is
- the existing shared filesystem. The COW file need not exist. If it
- doesn't, the driver will create and initialize it. Once the COW file
- has been initialized, it can be used on its own on the command line:
-
-
- ubd0=root_fs_cow
-
-
-
-
- The name of the backing file is stored in the COW file header, so it
- would be redundant to continue specifying it on the command line.
-
-
-
- 7.3. Note!
-
- When checking the size of the COW file in order to see the gobs of
- space that you're saving, make sure you use 'ls -ls' to see the actual
- disk consumption rather than the length of the file. The COW file is
- sparse, so the length will be very different from the disk usage.
- Here is a 'ls -l' of a COW file and backing file from one boot and
- shutdown:
- host% ls -l cow.debian debian2.2
- -rw-r--r-- 1 jdike jdike 492504064 Aug 6 21:16 cow.debian
- -rwxrw-rw- 1 jdike jdike 537919488 Aug 6 20:42 debian2.2
-
-
-
-
- Doesn't look like much saved space, does it? Well, here's 'ls -ls':
-
-
- host% ls -ls cow.debian debian2.2
- 880 -rw-r--r-- 1 jdike jdike 492504064 Aug 6 21:16 cow.debian
- 525832 -rwxrw-rw- 1 jdike jdike 537919488 Aug 6 20:42 debian2.2
-
-
-
-
- Now, you can see that the COW file has less than a meg of disk, rather
- than 492 meg.
-
-
-
- 7.4. Another warning
-
- Once a filesystem is being used as a readonly backing file for a COW
- file, do not boot directly from it or modify it in any way. Doing so
- will invalidate any COW files that are using it. The mtime and size
- of the backing file are stored in the COW file header at its creation,
- and they must continue to match. If they don't, the driver will
- refuse to use the COW file.
-
-
-
-
- If you attempt to evade this restriction by changing either the
- backing file or the COW header by hand, you will get a corrupted
- filesystem.
-
-
-
-
- Among other things, this means that upgrading the distribution in a
- backing file and expecting that all of the COW files using it will see
- the upgrade will not work.
-
-
-
-
- 7.5. uml_moo : Merging a COW file with its backing file
-
- Depending on how you use UML and COW devices, it may be advisable to
- merge the changes in the COW file into the backing file every once in
- a while.
-
-
-
-
- The utility that does this is uml_moo. Its usage is
-
-
- host% uml_moo COW file new backing file
-
-
-
-
- There's no need to specify the backing file since that information is
- already in the COW file header. If you're paranoid, boot the new
- merged file, and if you're happy with it, move it over the old backing
- file.
-
-
-
-
- uml_moo creates a new backing file by default as a safety measure. It
- also has a destructive merge option which will merge the COW file
- directly into its current backing file. This is really only usable
- when the backing file only has one COW file associated with it. If
- there are multiple COWs associated with a backing file, a -d merge of
- one of them will invalidate all of the others. However, it is
- convenient if you're short of disk space, and it should also be
- noticeably faster than a non-destructive merge.
-
-
-
-
- uml_moo is installed with the UML deb and RPM. If you didn't install
- UML from one of those packages, you can also get it from the UML
- utilities <http://user-mode-linux.sourceforge.net/
- utilities> tar file in tools/moo.
-
-
-
-
-
-
-
-
- 8. Creating filesystems
-
-
- You may want to create and mount new UML filesystems, either because
- your root filesystem isn't large enough or because you want to use a
- filesystem other than ext2.
-
-
- This was written on the occasion of reiserfs being included in the
- 2.4.1 kernel pool, and therefore the 2.4.1 UML, so the examples will
- talk about reiserfs. This information is generic, and the examples
- should be easy to translate to the filesystem of your choice.
-
-
- 8.1. Create the filesystem file
-
- dd is your friend. All you need to do is tell dd to create an empty
- file of the appropriate size. I usually make it sparse to save time
- and to avoid allocating disk space until it's actually used. For
- example, the following command will create a sparse 100 meg file full
- of zeroes.
-
-
- host%
- dd if=/dev/zero of=new_filesystem seek=100 count=1 bs=1M
-
-
-
-
-
-
- 8.2. Assign the file to a UML device
-
- Add an argument like the following to the UML command line:
-
- ubd4=new_filesystem
-
-
-
-
- making sure that you use an unassigned ubd device number.
-
-
-
- 8.3. Creating and mounting the filesystem
-
- Make sure that the filesystem is available, either by being built into
- the kernel, or available as a module, then boot up UML and log in. If
- the root filesystem doesn't have the filesystem utilities (mkfs, fsck,
- etc), then get them into UML by way of the net or hostfs.
-
-
- Make the new filesystem on the device assigned to the new file:
-
-
- host# mkreiserfs /dev/ubd/4
-
-
- <----------- MKREISERFSv2 ----------->
-
- ReiserFS version 3.6.25
- Block size 4096 bytes
- Block count 25856
- Used blocks 8212
- Journal - 8192 blocks (18-8209), journal header is in block 8210
- Bitmaps: 17
- Root block 8211
- Hash function "r5"
- ATTENTION: ALL DATA WILL BE LOST ON '/dev/ubd/4'! (y/n)y
- journal size 8192 (from 18)
- Initializing journal - 0%....20%....40%....60%....80%....100%
- Syncing..done.
-
-
-
-
- Now, mount it:
-
-
- UML#
- mount /dev/ubd/4 /mnt
-
-
-
-
- and you're in business.
-
-
-
-
-
-
-
-
-
- 9. Host file access
-
-
- If you want to access files on the host machine from inside UML, you
- can treat it as a separate machine and either nfs mount directories
- from the host or copy files into the virtual machine with scp or rcp.
- However, since UML is running on the host, it can access those
- files just like any other process and make them available inside the
- virtual machine without needing to use the network.
-
-
- This is now possible with the hostfs virtual filesystem. With it, you
- can mount a host directory into the UML filesystem and access the
- files contained in it just as you would on the host.
-
-
- 9.1. Using hostfs
-
- To begin with, make sure that hostfs is available inside the virtual
- machine with
-
-
- UML# cat /proc/filesystems
-
-
-
- . hostfs should be listed. If it's not, either rebuild the kernel
- with hostfs configured into it or make sure that hostfs is built as a
- module and available inside the virtual machine, and insmod it.
-
-
- Now all you need to do is run mount:
-
-
- UML# mount none /mnt/host -t hostfs
-
-
-
-
- will mount the host's / on the virtual machine's /mnt/host.
-
-
- If you don't want to mount the host root directory, then you can
- specify a subdirectory to mount with the -o switch to mount:
-
-
- UML# mount none /mnt/home -t hostfs -o /home
-
-
-
-
- will mount the hosts's /home on the virtual machine's /mnt/home.
-
-
-
- 9.2. hostfs as the root filesystem
-
- It's possible to boot from a directory hierarchy on the host using
- hostfs rather than using the standard filesystem in a file.
-
- To start, you need that hierarchy. The easiest way is to loop mount
- an existing root_fs file:
-
-
- host# mount root_fs uml_root_dir -o loop
-
-
-
-
- You need to change the filesystem type of / in etc/fstab to be
- 'hostfs', so that line looks like this:
-
- /dev/ubd/0 / hostfs defaults 1 1
-
-
-
-
- Then you need to chown to yourself all the files in that directory
- that are owned by root. This worked for me:
-
-
- host# find . -uid 0 -exec chown jdike {} \;
-
-
-
-
- Next, make sure that your UML kernel has hostfs compiled in, not as a
- module. Then run UML with the boot device pointing at that directory:
-
-
- ubd0=/path/to/uml/root/directory
-
-
-
-
- UML should then boot as it does normally.
-
-
- 9.3. Building hostfs
-
- If you need to build hostfs because it's not in your kernel, you have
- two choices:
-
-
-
- o Compiling hostfs into the kernel:
-
-
- Reconfigure the kernel and set the 'Host filesystem' option under
-
-
- o Compiling hostfs as a module:
-
-
- Reconfigure the kernel and set the 'Host filesystem' option under
- be in arch/um/fs/hostfs/hostfs.o. Install that in
- /lib/modules/`uname -r`/fs in the virtual machine, boot it up, and
-
-
- UML# insmod hostfs
-
-
-
-
-
-
-
-
-
-
-
-
- 10. The Management Console
-
-
-
- The UML management console is a low-level interface to the kernel,
- somewhat like the i386 SysRq interface. Since there is a full-blown
- operating system under UML, there is much greater flexibility possible
- than with the SysRq mechanism.
-
-
- There are a number of things you can do with the mconsole interface:
-
- o get the kernel version
-
- o add and remove devices
-
- o halt or reboot the machine
-
- o Send SysRq commands
-
- o Pause and resume the UML
-
-
- You need the mconsole client (uml_mconsole) which is present in CVS
- (/tools/mconsole) in 2.4.5-9um and later, and will be in the RPM in
- 2.4.6.
-
-
- You also need CONFIG_MCONSOLE (under 'General Setup') enabled in UML.
- When you boot UML, you'll see a line like:
-
-
- mconsole initialized on /home/jdike/.uml/umlNJ32yL/mconsole
-
-
-
-
- If you specify a unique machine id one the UML command line, i.e.
-
-
- umid=debian
-
-
-
-
- you'll see this
-
-
- mconsole initialized on /home/jdike/.uml/debian/mconsole
-
-
-
-
- That file is the socket that uml_mconsole will use to communicate with
- UML. Run it with either the umid or the full path as its argument:
-
-
- host% uml_mconsole debian
-
-
-
-
- or
-
-
- host% uml_mconsole /home/jdike/.uml/debian/mconsole
-
-
-
-
- You'll get a prompt, at which you can run one of these commands:
-
- o version
-
- o halt
-
- o reboot
-
- o config
-
- o remove
-
- o sysrq
-
- o help
-
- o cad
-
- o stop
-
- o go
-
-
- 10.1. version
-
- This takes no arguments. It prints the UML version.
-
-
- (mconsole) version
- OK Linux usermode 2.4.5-9um #1 Wed Jun 20 22:47:08 EDT 2001 i686
-
-
-
-
- There are a couple actual uses for this. It's a simple no-op which
- can be used to check that a UML is running. It's also a way of
- sending an interrupt to the UML. This is sometimes useful on SMP
- hosts, where there's a bug which causes signals to UML to be lost,
- often causing it to appear to hang. Sending such a UML the mconsole
- version command is a good way to 'wake it up' before networking has
- been enabled, as it does not do anything to the function of the UML.
-
-
-
- 10.2. halt and reboot
-
- These take no arguments. They shut the machine down immediately, with
- no syncing of disks and no clean shutdown of userspace. So, they are
- pretty close to crashing the machine.
-
-
- (mconsole) halt
- OK
-
-
-
-
-
-
- 10.3. config
-
- "config" adds a new device to the virtual machine. Currently the ubd
- and network drivers support this. It takes one argument, which is the
- device to add, with the same syntax as the kernel command line.
-
-
-
-
- (mconsole)
- config ubd3=/home/jdike/incoming/roots/root_fs_debian22
-
- OK
- (mconsole) config eth1=mcast
- OK
-
-
-
-
-
-
- 10.4. remove
-
- "remove" deletes a device from the system. Its argument is just the
- name of the device to be removed. The device must be idle in whatever
- sense the driver considers necessary. In the case of the ubd driver,
- the removed block device must not be mounted, swapped on, or otherwise
- open, and in the case of the network driver, the device must be down.
-
-
- (mconsole) remove ubd3
- OK
- (mconsole) remove eth1
- OK
-
-
-
-
-
-
- 10.5. sysrq
-
- This takes one argument, which is a single letter. It calls the
- generic kernel's SysRq driver, which does whatever is called for by
- that argument. See the SysRq documentation in
- Documentation/admin-guide/sysrq.rst in your favorite kernel tree to
- see what letters are valid and what they do.
-
-
-
- 10.6. help
-
- "help" returns a string listing the valid commands and what each one
- does.
-
-
-
- 10.7. cad
-
- This invokes the Ctl-Alt-Del action on init. What exactly this ends
- up doing is up to /etc/inittab. Normally, it reboots the machine.
- With UML, this is usually not desired, so if a halt would be better,
- then find the section of inittab that looks like this
-
-
- # What to do when CTRL-ALT-DEL is pressed.
- ca:12345:ctrlaltdel:/sbin/shutdown -t1 -a -r now
-
-
-
-
- and change the command to halt.
-
-
-
- 10.8. stop
-
- This puts the UML in a loop reading mconsole requests until a 'go'
- mconsole command is received. This is very useful for making backups
- of UML filesystems, as the UML can be stopped, then synced via 'sysrq
- s', so that everything is written to the filesystem. You can then copy
- the filesystem and then send the UML 'go' via mconsole.
-
-
- Note that a UML running with more than one CPU will have problems
- after you send the 'stop' command, as only one CPU will be held in a
- mconsole loop and all others will continue as normal. This is a bug,
- and will be fixed.
-
-
-
- 10.9. go
-
- This resumes a UML after being paused by a 'stop' command. Note that
- when the UML has resumed, TCP connections may have timed out and if
- the UML is paused for a long period of time, crond might go a little
- crazy, running all the jobs it didn't do earlier.
-
-
-
-
-
-
-
-
- 11. Kernel debugging
-
-
- Note: The interface that makes debugging, as described here, possible
- is present in 2.4.0-test6 kernels and later.
-
-
- Since the user-mode kernel runs as a normal Linux process, it is
- possible to debug it with gdb almost like any other process. It is
- slightly different because the kernel's threads are already being
- ptraced for system call interception, so gdb can't ptrace them.
- However, a mechanism has been added to work around that problem.
-
-
- In order to debug the kernel, you need build it from source. See
- ``Compiling the kernel and modules'' for information on doing that.
- Make sure that you enable CONFIG_DEBUGSYM and CONFIG_PT_PROXY during
- the config. These will compile the kernel with -g, and enable the
- ptrace proxy so that gdb works with UML, respectively.
-
-
-
-
- 11.1. Starting the kernel under gdb
-
- You can have the kernel running under the control of gdb from the
- beginning by putting 'debug' on the command line. You will get an
- xterm with gdb running inside it. The kernel will send some commands
- to gdb which will leave it stopped at the beginning of start_kernel.
- At this point, you can get things going with 'next', 'step', or
- 'cont'.
-
-
- There is a transcript of a debugging session here <debug-
- session.html> , with breakpoints being set in the scheduler and in an
- interrupt handler.
- 11.2. Examining sleeping processes
-
- Not every bug is evident in the currently running process. Sometimes,
- processes hang in the kernel when they shouldn't because they've
- deadlocked on a semaphore or something similar. In this case, when
- you ^C gdb and get a backtrace, you will see the idle thread, which
- isn't very relevant.
-
-
- What you want is the stack of whatever process is sleeping when it
- shouldn't be. You need to figure out which process that is, which is
- generally fairly easy. Then you need to get its host process id,
- which you can do either by looking at ps on the host or at
- task.thread.extern_pid in gdb.
-
-
- Now what you do is this:
-
- o detach from the current thread
-
-
- (UML gdb) det
-
-
-
-
-
- o attach to the thread you are interested in
-
-
- (UML gdb) att <host pid>
-
-
-
-
-
- o look at its stack and anything else of interest
-
-
- (UML gdb) bt
-
-
-
-
- Note that you can't do anything at this point that requires that a
- process execute, e.g. calling a function
-
- o when you're done looking at that process, reattach to the current
- thread and continue it
-
-
- (UML gdb)
- att 1
-
-
-
-
-
-
- (UML gdb)
- c
-
-
-
-
- Here, specifying any pid which is not the process id of a UML thread
- will cause gdb to reattach to the current thread. I commonly use 1,
- but any other invalid pid would work.
-
-
-
- 11.3. Running ddd on UML
-
- ddd works on UML, but requires a special kludge. The process goes
- like this:
-
- o Start ddd
-
-
- host% ddd linux
-
-
-
-
-
- o With ps, get the pid of the gdb that ddd started. You can ask the
- gdb to tell you, but for some reason that confuses things and
- causes a hang.
-
- o run UML with 'debug=parent gdb-pid=<pid>' added to the command line
- - it will just sit there after you hit return
-
- o type 'att 1' to the ddd gdb and you will see something like
-
-
- 0xa013dc51 in __kill ()
-
-
- (gdb)
-
-
-
-
-
- o At this point, type 'c', UML will boot up, and you can use ddd just
- as you do on any other process.
-
-
-
- 11.4. Debugging modules
-
- gdb has support for debugging code which is dynamically loaded into
- the process. This support is what is needed to debug kernel modules
- under UML.
-
-
- Using that support is somewhat complicated. You have to tell gdb what
- object file you just loaded into UML and where in memory it is. Then,
- it can read the symbol table, and figure out where all the symbols are
- from the load address that you provided. It gets more interesting
- when you load the module again (i.e. after an rmmod). You have to
- tell gdb to forget about all its symbols, including the main UML ones
- for some reason, then load then all back in again.
-
-
- There's an easy way and a hard way to do this. The easy way is to use
- the umlgdb expect script written by Chandan Kudige. It basically
- automates the process for you.
-
-
- First, you must tell it where your modules are. There is a list in
- the script that looks like this:
- set MODULE_PATHS {
- "fat" "/usr/src/uml/linux-2.4.18/fs/fat/fat.o"
- "isofs" "/usr/src/uml/linux-2.4.18/fs/isofs/isofs.o"
- "minix" "/usr/src/uml/linux-2.4.18/fs/minix/minix.o"
- }
-
-
-
-
- You change that to list the names and paths of the modules that you
- are going to debug. Then you run it from the toplevel directory of
- your UML pool and it basically tells you what to do:
-
-
-
-
- ******** GDB pid is 21903 ********
- Start UML as: ./linux <kernel switches> debug gdb-pid=21903
-
-
-
- GNU gdb 5.0rh-5 Red Hat Linux 7.1
- Copyright 2001 Free Software Foundation, Inc.
- GDB is free software, covered by the GNU General Public License, and you are
- welcome to change it and/or distribute copies of it under certain conditions.
- Type "show copying" to see the conditions.
- There is absolutely no warranty for GDB. Type "show warranty" for details.
- This GDB was configured as "i386-redhat-linux"...
- (gdb) b sys_init_module
- Breakpoint 1 at 0xa0011923: file module.c, line 349.
- (gdb) att 1
-
-
-
-
- After you run UML and it sits there doing nothing, you hit return at
- the 'att 1' and continue it:
-
-
- Attaching to program: /home/jdike/linux/2.4/um/./linux, process 1
- 0xa00f4221 in __kill ()
- (UML gdb) c
- Continuing.
-
-
-
-
- At this point, you debug normally. When you insmod something, the
- expect magic will kick in and you'll see something like:
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- *** Module hostfs loaded ***
- Breakpoint 1, sys_init_module (name_user=0x805abb0 "hostfs",
- mod_user=0x8070e00) at module.c:349
- 349 char *name, *n_name, *name_tmp = NULL;
- (UML gdb) finish
- Run till exit from #0 sys_init_module (name_user=0x805abb0 "hostfs",
- mod_user=0x8070e00) at module.c:349
- 0xa00e2e23 in execute_syscall (r=0xa8140284) at syscall_kern.c:411
- 411 else res = EXECUTE_SYSCALL(syscall, regs);
- Value returned is $1 = 0
- (UML gdb)
- p/x (int)module_list + module_list->size_of_struct
-
- $2 = 0xa9021054
- (UML gdb) symbol-file ./linux
- Load new symbol table from "./linux"? (y or n) y
- Reading symbols from ./linux...
- done.
- (UML gdb)
- add-symbol-file /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o 0xa9021054
-
- add symbol table from file "/home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o" at
- .text_addr = 0xa9021054
- (y or n) y
-
- Reading symbols from /home/jdike/linux/2.4/um/arch/um/fs/hostfs/hostfs.o...
- done.
- (UML gdb) p *module_list
- $1 = {size_of_struct = 84, next = 0xa0178720, name = 0xa9022de0 "hostfs",
- size = 9016, uc = {usecount = {counter = 0}, pad = 0}, flags = 1,
- nsyms = 57, ndeps = 0, syms = 0xa9023170, deps = 0x0, refs = 0x0,
- init = 0xa90221f0 <init_hostfs>, cleanup = 0xa902222c <exit_hostfs>,
- ex_table_start = 0x0, ex_table_end = 0x0, persist_start = 0x0,
- persist_end = 0x0, can_unload = 0, runsize = 0, kallsyms_start = 0x0,
- kallsyms_end = 0x0,
- archdata_start = 0x1b855 <Address 0x1b855 out of bounds>,
- archdata_end = 0xe5890000 <Address 0xe5890000 out of bounds>,
- kernel_data = 0xf689c35d <Address 0xf689c35d out of bounds>}
- >> Finished loading symbols for hostfs ...
-
-
-
-
- That's the easy way. It's highly recommended. The hard way is
- described below in case you're interested in what's going on.
-
-
- Boot the kernel under the debugger and load the module with insmod or
- modprobe. With gdb, do:
-
-
- (UML gdb) p module_list
-
-
-
-
- This is a list of modules that have been loaded into the kernel, with
- the most recently loaded module first. Normally, the module you want
- is at module_list. If it's not, walk down the next links, looking at
- the name fields until find the module you want to debug. Take the
- address of that structure, and add module.size_of_struct (which in
- 2.4.10 kernels is 96 (0x60)) to it. Gdb can make this hard addition
- for you :-):
-
-
-
- (UML gdb)
- printf "%#x\n", (int)module_list module_list->size_of_struct
-
-
-
-
- The offset from the module start occasionally changes (before 2.4.0,
- it was module.size_of_struct + 4), so it's a good idea to check the
- init and cleanup addresses once in a while, as describe below. Now
- do:
-
-
- (UML gdb)
- add-symbol-file /path/to/module/on/host that_address
-
-
-
-
- Tell gdb you really want to do it, and you're in business.
-
-
- If there's any doubt that you got the offset right, like breakpoints
- appear not to work, or they're appearing in the wrong place, you can
- check it by looking at the module structure. The init and cleanup
- fields should look like:
-
-
- init = 0x588066b0 <init_hostfs>, cleanup = 0x588066c0 <exit_hostfs>
-
-
-
-
- with no offsets on the symbol names. If the names are right, but they
- are offset, then the offset tells you how much you need to add to the
- address you gave to add-symbol-file.
-
-
- When you want to load in a new version of the module, you need to get
- gdb to forget about the old one. The only way I've found to do that
- is to tell gdb to forget about all symbols that it knows about:
-
-
- (UML gdb) symbol-file
-
-
-
-
- Then reload the symbols from the kernel binary:
-
-
- (UML gdb) symbol-file /path/to/kernel
-
-
-
-
- and repeat the process above. You'll also need to re-enable break-
- points. They were disabled when you dumped all the symbols because
- gdb couldn't figure out where they should go.
-
-
-
- 11.5. Attaching gdb to the kernel
-
- If you don't have the kernel running under gdb, you can attach gdb to
- it later by sending the tracing thread a SIGUSR1. The first line of
- the console output identifies its pid:
- tracing thread pid = 20093
-
-
-
-
- When you send it the signal:
-
-
- host% kill -USR1 20093
-
-
-
-
- you will get an xterm with gdb running in it.
-
-
- If you have the mconsole compiled into UML, then the mconsole client
- can be used to start gdb:
-
-
- (mconsole) (mconsole) config gdb=xterm
-
-
-
-
- will fire up an xterm with gdb running in it.
-
-
-
- 11.6. Using alternate debuggers
-
- UML has support for attaching to an already running debugger rather
- than starting gdb itself. This is present in CVS as of 17 Apr 2001.
- I sent it to Alan for inclusion in the ac tree, and it will be in my
- 2.4.4 release.
-
-
- This is useful when gdb is a subprocess of some UI, such as emacs or
- ddd. It can also be used to run debuggers other than gdb on UML.
- Below is an example of using strace as an alternate debugger.
-
-
- To do this, you need to get the pid of the debugger and pass it in
- with the
-
-
- If you are using gdb under some UI, then tell it to 'att 1', and
- you'll find yourself attached to UML.
-
-
- If you are using something other than gdb as your debugger, then
- you'll need to get it to do the equivalent of 'att 1' if it doesn't do
- it automatically.
-
-
- An example of an alternate debugger is strace. You can strace the
- actual kernel as follows:
-
- o Run the following in a shell
-
-
- host%
- sh -c 'echo pid=$$; echo -n hit return; read x; exec strace -p 1 -o strace.out'
-
-
-
- o Run UML with 'debug' and 'gdb-pid=<pid>' with the pid printed out
- by the previous command
-
- o Hit return in the shell, and UML will start running, and strace
- output will start accumulating in the output file.
-
- Note that this is different from running
-
-
- host% strace ./linux
-
-
-
-
- That will strace only the main UML thread, the tracing thread, which
- doesn't do any of the actual kernel work. It just oversees the vir-
- tual machine. In contrast, using strace as described above will show
- you the low-level activity of the virtual machine.
-
-
-
-
-
- 12. Kernel debugging examples
-
- 12.1. The case of the hung fsck
-
- When booting up the kernel, fsck failed, and dropped me into a shell
- to fix things up. I ran fsck -y, which hung:
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- Setting hostname uml [ OK ]
- Checking root filesystem
- /dev/fhd0 was not cleanly unmounted, check forced.
- Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
-
- /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
- (i.e., without -a or -p options)
- [ FAILED ]
-
- *** An error occurred during the file system check.
- *** Dropping you to a shell; the system will reboot
- *** when you leave the shell.
- Give root password for maintenance
- (or type Control-D for normal startup):
-
- [root@uml /root]# fsck -y /dev/fhd0
- fsck -y /dev/fhd0
- Parallelizing fsck version 1.14 (9-Jan-1999)
- e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
- /dev/fhd0 contains a file system with errors, check forced.
- Pass 1: Checking inodes, blocks, and sizes
- Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes
-
- Inode 19780, i_blocks is 1548, should be 540. Fix? yes
-
- Pass 2: Checking directory structure
- Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes
-
- Directory inode 11858, block 0, offset 0: directory corrupted
- Salvage? yes
-
- Missing '.' in directory inode 11858.
- Fix? yes
-
- Missing '..' in directory inode 11858.
- Fix? yes
-
-
-
-
-
- The standard drill in this sort of situation is to fire up gdb on the
- signal thread, which, in this case, was pid 1935. In another window,
- I run gdb and attach pid 1935.
-
-
-
-
- ~/linux/2.3.26/um 1016: gdb linux
- GNU gdb 4.17.0.11 with Linux support
- Copyright 1998 Free Software Foundation, Inc.
- GDB is free software, covered by the GNU General Public License, and you are
- welcome to change it and/or distribute copies of it under certain conditions.
- Type "show copying" to see the conditions.
- There is absolutely no warranty for GDB. Type "show warranty" for details.
- This GDB was configured as "i386-redhat-linux"...
-
- (gdb) att 1935
- Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 1935
- 0x100756d9 in __wait4 ()
-
-
-
-
-
-
- Let's see what's currently running:
-
-
-
- (gdb) p current_task.pid
- $1 = 0
-
-
-
-
-
- It's the idle thread, which means that fsck went to sleep for some
- reason and never woke up.
-
-
- Let's guess that the last process in the process list is fsck:
-
-
-
- (gdb) p current_task.prev_task.comm
- $13 = "fsck.ext2\000\000\000\000\000\000"
-
-
-
-
-
- It is, so let's see what it thinks it's up to:
-
-
-
- (gdb) p current_task.prev_task.thread
- $14 = {extern_pid = 1980, tracing = 0, want_tracing = 0, forking = 0,
- kernel_stack_page = 0, signal_stack = 1342627840, syscall = {id = 4, args = {
- 3, 134973440, 1024, 0, 1024}, have_result = 0, result = 50590720},
- request = {op = 2, u = {exec = {ip = 1350467584, sp = 2952789424}, fork = {
- regs = {1350467584, 2952789424, 0 <repeats 15 times>}, sigstack = 0,
- pid = 0}, switch_to = 0x507e8000, thread = {proc = 0x507e8000,
- arg = 0xaffffdb0, flags = 0, new_pid = 0}, input_request = {
- op = 1350467584, fd = -1342177872, proc = 0, pid = 0}}}}
-
-
-
-
-
- The interesting things here are the fact that its .thread.syscall.id
- is __NR_write (see the big switch in arch/um/kernel/syscall_kern.c or
- the defines in include/asm-um/arch/unistd.h), and that it never
- returned. Also, its .request.op is OP_SWITCH (see
- arch/um/include/user_util.h). These mean that it went into a write,
- and, for some reason, called schedule().
-
-
- The fact that it never returned from write means that its stack should
- be fairly interesting. Its pid is 1980 (.thread.extern_pid). That
- process is being ptraced by the signal thread, so it must be detached
- before gdb can attach it:
-
-
-
-
-
-
-
-
-
-
- (gdb) call detach(1980)
-
- Program received signal SIGSEGV, Segmentation fault.
- <function called from gdb>
- The program being debugged stopped while in a function called from GDB.
- When the function (detach) is done executing, GDB will silently
- stop (instead of continuing to evaluate the expression containing
- the function call).
- (gdb) call detach(1980)
- $15 = 0
-
-
-
-
-
- The first detach segfaults for some reason, and the second one
- succeeds.
-
-
- Now I detach from the signal thread, attach to the fsck thread, and
- look at its stack:
-
-
- (gdb) det
- Detaching from program: /home/dike/linux/2.3.26/um/linux Pid 1935
- (gdb) att 1980
- Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 1980
- 0x10070451 in __kill ()
- (gdb) bt
- #0 0x10070451 in __kill ()
- #1 0x10068ccd in usr1_pid (pid=1980) at process.c:30
- #2 0x1006a03f in _switch_to (prev=0x50072000, next=0x507e8000)
- at process_kern.c:156
- #3 0x1006a052 in switch_to (prev=0x50072000, next=0x507e8000, last=0x50072000)
- at process_kern.c:161
- #4 0x10001d12 in schedule () at core.c:777
- #5 0x1006a744 in __down (sem=0x507d241c) at semaphore.c:71
- #6 0x1006aa10 in __down_failed () at semaphore.c:157
- #7 0x1006c5d8 in segv_handler (sc=0x5006e940) at trap_user.c:174
- #8 0x1006c5ec in kern_segv_handler (sig=11) at trap_user.c:182
- #9 <signal handler called>
- #10 0x10155404 in errno ()
- #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50
- #12 0x1006c5d8 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
- #13 0x1006c5ec in kern_segv_handler (sig=11) at trap_user.c:182
- #14 <signal handler called>
- #15 0xc0fd in ?? ()
- #16 0x10016647 in sys_write (fd=3,
- buf=0x80b8800 <Address 0x80b8800 out of bounds>, count=1024)
- at read_write.c:159
- #17 0x1006d5b3 in execute_syscall (syscall=4, args=0x5006ef08)
- at syscall_kern.c:254
- #18 0x1006af87 in really_do_syscall (sig=12) at syscall_user.c:35
- #19 <signal handler called>
- #20 0x400dc8b0 in ?? ()
-
-
-
-
-
- The interesting things here are :
-
- o There are two segfaults on this stack (frames 9 and 14)
-
- o The first faulting address (frame 11) is 0x50000800
-
- (gdb) p (void *)1342179328
- $16 = (void *) 0x50000800
-
-
-
-
-
- The initial faulting address is interesting because it is on the idle
- thread's stack. I had been seeing the idle thread segfault for no
- apparent reason, and the cause looked like stack corruption. In hopes
- of catching the culprit in the act, I had turned off all protections
- to that stack while the idle thread wasn't running. This apparently
- tripped that trap.
-
-
- However, the more immediate problem is that second segfault and I'm
- going to concentrate on that. First, I want to see where the fault
- happened, so I have to go look at the sigcontent struct in frame 8:
-
-
-
- (gdb) up
- #1 0x10068ccd in usr1_pid (pid=1980) at process.c:30
- 30 kill(pid, SIGUSR1);
- (gdb)
- #2 0x1006a03f in _switch_to (prev=0x50072000, next=0x507e8000)
- at process_kern.c:156
- 156 usr1_pid(getpid());
- (gdb)
- #3 0x1006a052 in switch_to (prev=0x50072000, next=0x507e8000, last=0x50072000)
- at process_kern.c:161
- 161 _switch_to(prev, next);
- (gdb)
- #4 0x10001d12 in schedule () at core.c:777
- 777 switch_to(prev, next, prev);
- (gdb)
- #5 0x1006a744 in __down (sem=0x507d241c) at semaphore.c:71
- 71 schedule();
- (gdb)
- #6 0x1006aa10 in __down_failed () at semaphore.c:157
- 157 }
- (gdb)
- #7 0x1006c5d8 in segv_handler (sc=0x5006e940) at trap_user.c:174
- 174 segv(sc->cr2, sc->err & 2);
- (gdb)
- #8 0x1006c5ec in kern_segv_handler (sig=11) at trap_user.c:182
- 182 segv_handler(sc);
- (gdb) p *sc
- Cannot access memory at address 0x0.
-
-
-
-
- That's not very useful, so I'll try a more manual method:
-
-
- (gdb) p *((struct sigcontext *) (&sig + 1))
- $19 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43,
- __dsh = 0, edi = 1342179328, esi = 1350378548, ebp = 1342630440,
- esp = 1342630420, ebx = 1348150624, edx = 1280, ecx = 0, eax = 0,
- trapno = 14, err = 4, eip = 268480945, cs = 35, __csh = 0, eflags = 66118,
- esp_at_signal = 1342630420, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0,
- cr2 = 1280}
-
-
-
- The ip is in handle_mm_fault:
-
-
- (gdb) p (void *)268480945
- $20 = (void *) 0x1000b1b1
- (gdb) i sym $20
- handle_mm_fault + 57 in section .text
-
-
-
-
-
- Specifically, it's in pte_alloc:
-
-
- (gdb) i line *$20
- Line 124 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b1b1 <handle_mm_fault+57>
- and ends at 0x1000b1b7 <handle_mm_fault+63>.
-
-
-
-
-
- To find where in handle_mm_fault this is, I'll jump forward in the
- code until I see an address in that procedure:
-
-
-
- (gdb) i line *0x1000b1c0
- Line 126 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b1b7 <handle_mm_fault+63>
- and ends at 0x1000b1c3 <handle_mm_fault+75>.
- (gdb) i line *0x1000b1d0
- Line 131 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b1d0 <handle_mm_fault+88>
- and ends at 0x1000b1da <handle_mm_fault+98>.
- (gdb) i line *0x1000b1e0
- Line 61 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b1da <handle_mm_fault+98>
- and ends at 0x1000b1e1 <handle_mm_fault+105>.
- (gdb) i line *0x1000b1f0
- Line 134 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b1f0 <handle_mm_fault+120>
- and ends at 0x1000b200 <handle_mm_fault+136>.
- (gdb) i line *0x1000b200
- Line 135 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b200 <handle_mm_fault+136>
- and ends at 0x1000b208 <handle_mm_fault+144>.
- (gdb) i line *0x1000b210
- Line 139 of "/home/dike/linux/2.3.26/um/include/asm/pgalloc.h"
- starts at address 0x1000b210 <handle_mm_fault+152>
- and ends at 0x1000b219 <handle_mm_fault+161>.
- (gdb) i line *0x1000b220
- Line 1168 of "memory.c" starts at address 0x1000b21e <handle_mm_fault+166>
- and ends at 0x1000b222 <handle_mm_fault+170>.
-
-
-
-
-
- Something is apparently wrong with the page tables or vma_structs, so
- lets go back to frame 11 and have a look at them:
-
-
-
- #11 0x1006c0aa in segv (address=1342179328, is_write=2) at trap_kern.c:50
- 50 handle_mm_fault(current, vma, address, is_write);
- (gdb) call pgd_offset_proc(vma->vm_mm, address)
- $22 = (pgd_t *) 0x80a548c
-
-
-
-
-
- That's pretty bogus. Page tables aren't supposed to be in process
- text or data areas. Let's see what's in the vma:
-
-
- (gdb) p *vma
- $23 = {vm_mm = 0x507d2434, vm_start = 0, vm_end = 134512640,
- vm_next = 0x80a4f8c, vm_page_prot = {pgprot = 0}, vm_flags = 31200,
- vm_avl_height = 2058, vm_avl_left = 0x80a8c94, vm_avl_right = 0x80d1000,
- vm_next_share = 0xaffffdb0, vm_pprev_share = 0xaffffe63,
- vm_ops = 0xaffffe7a, vm_pgoff = 2952789626, vm_file = 0xafffffec,
- vm_private_data = 0x62}
- (gdb) p *vma.vm_mm
- $24 = {mmap = 0x507d2434, mmap_avl = 0x0, mmap_cache = 0x8048000,
- pgd = 0x80a4f8c, mm_users = {counter = 0}, mm_count = {counter = 134904288},
- map_count = 134909076, mmap_sem = {count = {counter = 135073792},
- sleepers = -1342177872, wait = {lock = <optimized out or zero length>,
- task_list = {next = 0xaffffe63, prev = 0xaffffe7a},
- __magic = -1342177670, __creator = -1342177300}, __magic = 98},
- page_table_lock = {}, context = 138, start_code = 0, end_code = 0,
- start_data = 0, end_data = 0, start_brk = 0, brk = 0, start_stack = 0,
- arg_start = 0, arg_end = 0, env_start = 0, env_end = 0, rss = 1350381536,
- total_vm = 0, locked_vm = 0, def_flags = 0, cpu_vm_mask = 0, swap_cnt = 0,
- swap_address = 0, segments = 0x0}
-
-
-
-
-
- This also pretty bogus. With all of the 0x80xxxxx and 0xaffffxxx
- addresses, this is looking like a stack was plonked down on top of
- these structures. Maybe it's a stack overflow from the next page:
-
-
-
- (gdb) p vma
- $25 = (struct vm_area_struct *) 0x507d2434
-
-
-
-
-
- That's towards the lower quarter of the page, so that would have to
- have been pretty heavy stack overflow:
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- (gdb) x/100x $25
- 0x507d2434: 0x507d2434 0x00000000 0x08048000 0x080a4f8c
- 0x507d2444: 0x00000000 0x080a79e0 0x080a8c94 0x080d1000
- 0x507d2454: 0xaffffdb0 0xaffffe63 0xaffffe7a 0xaffffe7a
- 0x507d2464: 0xafffffec 0x00000062 0x0000008a 0x00000000
- 0x507d2474: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2484: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2494: 0x00000000 0x00000000 0x507d2fe0 0x00000000
- 0x507d24a4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d24b4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d24c4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d24d4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d24e4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d24f4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2504: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2514: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2524: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2534: 0x00000000 0x00000000 0x507d25dc 0x00000000
- 0x507d2544: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2554: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2564: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2574: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2584: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d2594: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d25a4: 0x00000000 0x00000000 0x00000000 0x00000000
- 0x507d25b4: 0x00000000 0x00000000 0x00000000 0x00000000
-
-
-
-
-
- It's not stack overflow. The only "stack-like" piece of this data is
- the vma_struct itself.
-
-
- At this point, I don't see any avenues to pursue, so I just have to
- admit that I have no idea what's going on. What I will do, though, is
- stick a trap on the segfault handler which will stop if it sees any
- writes to the idle thread's stack. That was the thing that happened
- first, and it may be that if I can catch it immediately, what's going
- on will be somewhat clearer.
-
-
- 12.2. Episode 2: The case of the hung fsck
-
- After setting a trap in the SEGV handler for accesses to the signal
- thread's stack, I reran the kernel.
-
-
- fsck hung again, this time by hitting the trap:
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- Setting hostname uml [ OK ]
- Checking root filesystem
- /dev/fhd0 contains a file system with errors, check forced.
- Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780.
-
- /dev/fhd0: UNEXPECTED INCONSISTENCY; RUN fsck MANUALLY.
- (i.e., without -a or -p options)
- [ FAILED ]
-
- *** An error occurred during the file system check.
- *** Dropping you to a shell; the system will reboot
- *** when you leave the shell.
- Give root password for maintenance
- (or type Control-D for normal startup):
-
- [root@uml /root]# fsck -y /dev/fhd0
- fsck -y /dev/fhd0
- Parallelizing fsck version 1.14 (9-Jan-1999)
- e2fsck 1.14, 9-Jan-1999 for EXT2 FS 0.5b, 95/08/09
- /dev/fhd0 contains a file system with errors, check forced.
- Pass 1: Checking inodes, blocks, and sizes
- Error reading block 86894 (Attempt to read block from filesystem resulted in short read) while reading indirect blocks of inode 19780. Ignore error? yes
-
- Pass 2: Checking directory structure
- Error reading block 49405 (Attempt to read block from filesystem resulted in short read). Ignore error? yes
-
- Directory inode 11858, block 0, offset 0: directory corrupted
- Salvage? yes
-
- Missing '.' in directory inode 11858.
- Fix? yes
-
- Missing '..' in directory inode 11858.
- Fix? yes
-
- Untested (4127) [100fe44c]: trap_kern.c line 31
-
-
-
-
-
- I need to get the signal thread to detach from pid 4127 so that I can
- attach to it with gdb. This is done by sending it a SIGUSR1, which is
- caught by the signal thread, which detaches the process:
-
-
- kill -USR1 4127
-
-
-
-
-
- Now I can run gdb on it:
-
-
-
-
-
-
-
-
-
-
-
-
-
- ~/linux/2.3.26/um 1034: gdb linux
- GNU gdb 4.17.0.11 with Linux support
- Copyright 1998 Free Software Foundation, Inc.
- GDB is free software, covered by the GNU General Public License, and you are
- welcome to change it and/or distribute copies of it under certain conditions.
- Type "show copying" to see the conditions.
- There is absolutely no warranty for GDB. Type "show warranty" for details.
- This GDB was configured as "i386-redhat-linux"...
- (gdb) att 4127
- Attaching to program `/home/dike/linux/2.3.26/um/linux', Pid 4127
- 0x10075891 in __libc_nanosleep ()
-
-
-
-
-
- The backtrace shows that it was in a write and that the fault address
- (address in frame 3) is 0x50000800, which is right in the middle of
- the signal thread's stack page:
-
-
- (gdb) bt
- #0 0x10075891 in __libc_nanosleep ()
- #1 0x1007584d in __sleep (seconds=1000000)
- at ../sysdeps/unix/sysv/linux/sleep.c:78
- #2 0x1006ce9a in stop () at user_util.c:191
- #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31
- #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
- #5 0x1006c63c in kern_segv_handler (sig=11) at trap_user.c:182
- #6 <signal handler called>
- #7 0xc0fd in ?? ()
- #8 0x10016647 in sys_write (fd=3, buf=0x80b8800 "R.", count=1024)
- at read_write.c:159
- #9 0x1006d603 in execute_syscall (syscall=4, args=0x5006ef08)
- at syscall_kern.c:254
- #10 0x1006af87 in really_do_syscall (sig=12) at syscall_user.c:35
- #11 <signal handler called>
- #12 0x400dc8b0 in ?? ()
- #13 <signal handler called>
- #14 0x400dc8b0 in ?? ()
- #15 0x80545fd in ?? ()
- #16 0x804daae in ?? ()
- #17 0x8054334 in ?? ()
- #18 0x804d23e in ?? ()
- #19 0x8049632 in ?? ()
- #20 0x80491d2 in ?? ()
- #21 0x80596b5 in ?? ()
- (gdb) p (void *)1342179328
- $3 = (void *) 0x50000800
-
-
-
-
-
- Going up the stack to the segv_handler frame and looking at where in
- the code the access happened shows that it happened near line 110 of
- block_dev.c:
-
-
-
-
-
-
-
-
-
- (gdb) up
- #1 0x1007584d in __sleep (seconds=1000000)
- at ../sysdeps/unix/sysv/linux/sleep.c:78
- ../sysdeps/unix/sysv/linux/sleep.c:78: No such file or directory.
- (gdb)
- #2 0x1006ce9a in stop () at user_util.c:191
- 191 while(1) sleep(1000000);
- (gdb)
- #3 0x1006bf88 in segv (address=1342179328, is_write=2) at trap_kern.c:31
- 31 KERN_UNTESTED();
- (gdb)
- #4 0x1006c628 in segv_handler (sc=0x5006eaf8) at trap_user.c:174
- 174 segv(sc->cr2, sc->err & 2);
- (gdb) p *sc
- $1 = {gs = 0, __gsh = 0, fs = 0, __fsh = 0, es = 43, __esh = 0, ds = 43,
- __dsh = 0, edi = 1342179328, esi = 134973440, ebp = 1342631484,
- esp = 1342630864, ebx = 256, edx = 0, ecx = 256, eax = 1024, trapno = 14,
- err = 6, eip = 268550834, cs = 35, __csh = 0, eflags = 66070,
- esp_at_signal = 1342630864, ss = 43, __ssh = 0, fpstate = 0x0, oldmask = 0,
- cr2 = 1342179328}
- (gdb) p (void *)268550834
- $2 = (void *) 0x1001c2b2
- (gdb) i sym $2
- block_write + 1090 in section .text
- (gdb) i line *$2
- Line 209 of "/home/dike/linux/2.3.26/um/include/asm/arch/string.h"
- starts at address 0x1001c2a1 <block_write+1073>
- and ends at 0x1001c2bf <block_write+1103>.
- (gdb) i line *0x1001c2c0
- Line 110 of "block_dev.c" starts at address 0x1001c2bf <block_write+1103>
- and ends at 0x1001c2e3 <block_write+1139>.
-
-
-
-
-
- Looking at the source shows that the fault happened during a call to
- copy_from_user to copy the data into the kernel:
-
-
- 107 count -= chars;
- 108 copy_from_user(p,buf,chars);
- 109 p += chars;
- 110 buf += chars;
-
-
-
-
-
- p is the pointer which must contain 0x50000800, since buf contains
- 0x80b8800 (frame 8 above). It is defined as:
-
-
- p = offset + bh->b_data;
-
-
-
-
-
- I need to figure out what bh is, and it just so happens that bh is
- passed as an argument to mark_buffer_uptodate and mark_buffer_dirty a
- few lines later, so I do a little disassembly:
-
-
-
-
- (gdb) disas 0x1001c2bf 0x1001c2e0
- Dump of assembler code from 0x1001c2bf to 0x1001c2d0:
- 0x1001c2bf <block_write+1103>: addl %eax,0xc(%ebp)
- 0x1001c2c2 <block_write+1106>: movl 0xfffffdd4(%ebp),%edx
- 0x1001c2c8 <block_write+1112>: btsl $0x0,0x18(%edx)
- 0x1001c2cd <block_write+1117>: btsl $0x1,0x18(%edx)
- 0x1001c2d2 <block_write+1122>: sbbl %ecx,%ecx
- 0x1001c2d4 <block_write+1124>: testl %ecx,%ecx
- 0x1001c2d6 <block_write+1126>: jne 0x1001c2e3 <block_write+1139>
- 0x1001c2d8 <block_write+1128>: pushl $0x0
- 0x1001c2da <block_write+1130>: pushl %edx
- 0x1001c2db <block_write+1131>: call 0x1001819c <__mark_buffer_dirty>
- End of assembler dump.
-
-
-
-
-
- At that point, bh is in %edx (address 0x1001c2da), which is calculated
- at 0x1001c2c2 as %ebp + 0xfffffdd4, so I figure exactly what that is,
- taking %ebp from the sigcontext_struct above:
-
-
- (gdb) p (void *)1342631484
- $5 = (void *) 0x5006ee3c
- (gdb) p 0x5006ee3c+0xfffffdd4
- $6 = 1342630928
- (gdb) p (void *)$6
- $7 = (void *) 0x5006ec10
- (gdb) p *((void **)$7)
- $8 = (void *) 0x50100200
-
-
-
-
-
- Now, I look at the structure to see what's in it, and particularly,
- what its b_data field contains:
-
-
- (gdb) p *((struct buffer_head *)0x50100200)
- $13 = {b_next = 0x50289380, b_blocknr = 49405, b_size = 1024, b_list = 0,
- b_dev = 15872, b_count = {counter = 1}, b_rdev = 15872, b_state = 24,
- b_flushtime = 0, b_next_free = 0x501001a0, b_prev_free = 0x50100260,
- b_this_page = 0x501001a0, b_reqnext = 0x0, b_pprev = 0x507fcf58,
- b_data = 0x50000800 "", b_page = 0x50004000,
- b_end_io = 0x10017f60 <end_buffer_io_sync>, b_dev_id = 0x0,
- b_rsector = 98810, b_wait = {lock = <optimized out or zero length>,
- task_list = {next = 0x50100248, prev = 0x50100248}, __magic = 1343226448,
- __creator = 0}, b_kiobuf = 0x0}
-
-
-
-
-
- The b_data field is indeed 0x50000800, so the question becomes how
- that happened. The rest of the structure looks fine, so this probably
- is not a case of data corruption. It happened on purpose somehow.
-
-
- The b_page field is a pointer to the page_struct representing the
- 0x50000000 page. Looking at it shows the kernel's idea of the state
- of that page:
-
-
-
- (gdb) p *$13.b_page
- $17 = {list = {next = 0x50004a5c, prev = 0x100c5174}, mapping = 0x0,
- index = 0, next_hash = 0x0, count = {counter = 1}, flags = 132, lru = {
- next = 0x50008460, prev = 0x50019350}, wait = {
- lock = <optimized out or zero length>, task_list = {next = 0x50004024,
- prev = 0x50004024}, __magic = 1342193708, __creator = 0},
- pprev_hash = 0x0, buffers = 0x501002c0, virtual = 1342177280,
- zone = 0x100c5160}
-
-
-
-
-
- Some sanity-checking: the virtual field shows the "virtual" address of
- this page, which in this kernel is the same as its "physical" address,
- and the page_struct itself should be mem_map[0], since it represents
- the first page of memory:
-
-
-
- (gdb) p (void *)1342177280
- $18 = (void *) 0x50000000
- (gdb) p mem_map
- $19 = (mem_map_t *) 0x50004000
-
-
-
-
-
- These check out fine.
-
-
- Now to check out the page_struct itself. In particular, the flags
- field shows whether the page is considered free or not:
-
-
- (gdb) p (void *)132
- $21 = (void *) 0x84
-
-
-
-
-
- The "reserved" bit is the high bit, which is definitely not set, so
- the kernel considers the signal stack page to be free and available to
- be used.
-
-
- At this point, I jump to conclusions and start looking at my early
- boot code, because that's where that page is supposed to be reserved.
-
-
- In my setup_arch procedure, I have the following code which looks just
- fine:
-
-
-
- bootmap_size = init_bootmem(start_pfn, end_pfn - start_pfn);
- free_bootmem(__pa(low_physmem) + bootmap_size, high_physmem - low_physmem);
-
-
-
-
-
- Two stack pages have already been allocated, and low_physmem points to
- the third page, which is the beginning of free memory.
- The init_bootmem call declares the entire memory to the boot memory
- manager, which marks it all reserved. The free_bootmem call frees up
- all of it, except for the first two pages. This looks correct to me.
-
-
- So, I decide to see init_bootmem run and make sure that it is marking
- those first two pages as reserved. I never get that far.
-
-
- Stepping into init_bootmem, and looking at bootmem_map before looking
- at what it contains shows the following:
-
-
-
- (gdb) p bootmem_map
- $3 = (void *) 0x50000000
-
-
-
-
-
- Aha! The light dawns. That first page is doing double duty as a
- stack and as the boot memory map. The last thing that the boot memory
- manager does is to free the pages used by its memory map, so this page
- is getting freed even its marked as reserved.
-
-
- The fix was to initialize the boot memory manager before allocating
- those two stack pages, and then allocate them through the boot memory
- manager. After doing this, and fixing a couple of subsequent buglets,
- the stack corruption problem disappeared.
-
-
-
-
-
- 13. What to do when UML doesn't work
-
-
-
-
- 13.1. Strange compilation errors when you build from source
-
- As of test11, it is necessary to have "ARCH=um" in the environment or
- on the make command line for all steps in building UML, including
- clean, distclean, or mrproper, config, menuconfig, or xconfig, dep,
- and linux. If you forget for any of them, the i386 build seems to
- contaminate the UML build. If this happens, start from scratch with
-
-
- host%
- make mrproper ARCH=um
-
-
-
-
- and repeat the build process with ARCH=um on all the steps.
-
-
- See ``Compiling the kernel and modules'' for more details.
-
-
- Another cause of strange compilation errors is building UML in
- /usr/src/linux. If you do this, the first thing you need to do is
- clean up the mess you made. The /usr/src/linux/asm link will now
- point to /usr/src/linux/asm-um. Make it point back to
- /usr/src/linux/asm-i386. Then, move your UML pool someplace else and
- build it there. Also see below, where a more specific set of symptoms
- is described.
-
-
-
- 13.3. A variety of panics and hangs with /tmp on a reiserfs filesys-
- tem
-
- I saw this on reiserfs 3.5.21 and it seems to be fixed in 3.5.27.
- Panics preceded by
-
-
- Detaching pid nnnn
-
-
-
- are diagnostic of this problem. This is a reiserfs bug which causes a
- thread to occasionally read stale data from a mmapped page shared with
- another thread. The fix is to upgrade the filesystem or to have /tmp
- be an ext2 filesystem.
-
-
-
- 13.4. The compile fails with errors about conflicting types for
- 'open', 'dup', and 'waitpid'
-
- This happens when you build in /usr/src/linux. The UML build makes
- the include/asm link point to include/asm-um. /usr/include/asm points
- to /usr/src/linux/include/asm, so when that link gets moved, files
- which need to include the asm-i386 versions of headers get the
- incompatible asm-um versions. The fix is to move the include/asm link
- back to include/asm-i386 and to do UML builds someplace else.
-
-
-
- 13.5. UML doesn't work when /tmp is an NFS filesystem
-
- This seems to be a similar situation with the ReiserFS problem above.
- Some versions of NFS seems not to handle mmap correctly, which UML
- depends on. The workaround is have /tmp be a non-NFS directory.
-
-
- 13.6. UML hangs on boot when compiled with gprof support
-
- If you build UML with gprof support and, early in the boot, it does
- this
-
-
- kernel BUG at page_alloc.c:100!
-
-
-
-
- you have a buggy gcc. You can work around the problem by removing
- UM_FASTCALL from CFLAGS in arch/um/Makefile-i386. This will open up
- another bug, but that one is fairly hard to reproduce.
-
-
-
- 13.7. syslogd dies with a SIGTERM on startup
-
- The exact boot error depends on the distribution that you're booting,
- but Debian produces this:
-
-
- /etc/rc2.d/S10sysklogd: line 49: 93 Terminated
- start-stop-daemon --start --quiet --exec /sbin/syslogd -- $SYSLOGD
-
-
-
-
- This is a syslogd bug. There's a race between a parent process
- installing a signal handler and its child sending the signal. See
- this uml-devel post <http://www.geocrawler.com/lists/3/Source-
- Forge/709/0/6612801> for the details.
-
-
-
- 13.8. TUN/TAP networking doesn't work on a 2.4 host
-
- There are a couple of problems which were
- <http://www.geocrawler.com/lists/3/SourceForge/597/0/> name="pointed
- out"> by Tim Robinson <timro at trkr dot net>
-
- o It doesn't work on hosts running 2.4.7 (or thereabouts) or earlier.
- The fix is to upgrade to something more recent and then read the
- next item.
-
- o If you see
-
-
- File descriptor in bad state
-
-
-
- when you bring up the device inside UML, you have a header mismatch
- between the original kernel and the upgraded one. Make /usr/src/linux
- point at the new headers. This will only be a problem if you build
- uml_net yourself.
-
-
-
- 13.9. You can network to the host but not to other machines on the
- net
-
- If you can connect to the host, and the host can connect to UML, but
- you cannot connect to any other machines, then you may need to enable
- IP Masquerading on the host. Usually this is only experienced when
- using private IP addresses (192.168.x.x or 10.x.x.x) for host/UML
- networking, rather than the public address space that your host is
- connected to. UML does not enable IP Masquerading, so you will need
- to create a static rule to enable it:
-
-
- host%
- iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE
-
-
-
-
- Replace eth0 with the interface that you use to talk to the rest of
- the world.
-
-
- Documentation on IP Masquerading, and SNAT, can be found at
- www.netfilter.org <http://www.netfilter.org> .
-
-
- If you can reach the local net, but not the outside Internet, then
- that is usually a routing problem. The UML needs a default route:
-
-
- UML#
- route add default gw gateway IP
-
-
-
-
- The gateway IP can be any machine on the local net that knows how to
- reach the outside world. Usually, this is the host or the local net-
- work's gateway.
-
-
- Occasionally, we hear from someone who can reach some machines, but
- not others on the same net, or who can reach some ports on other
- machines, but not others. These are usually caused by strange
- firewalling somewhere between the UML and the other box. You track
- this down by running tcpdump on every interface the packets travel
- over and see where they disappear. When you find a machine that takes
- the packets in, but does not send them onward, that's the culprit.
-
-
-
- 13.10. I have no root and I want to scream
-
- Thanks to Birgit Wahlich for telling me about this strange one. It
- turns out that there's a limit of six environment variables on the
- kernel command line. When that limit is reached or exceeded, argument
- processing stops, which means that the 'root=' argument that UML
- usually adds is not seen. So, the filesystem has no idea what the
- root device is, so it panics.
-
-
- The fix is to put less stuff on the command line. Glomming all your
- setup variables into one is probably the best way to go.
-
-
-
- 13.11. UML build conflict between ptrace.h and ucontext.h
-
- On some older systems, /usr/include/asm/ptrace.h and
- /usr/include/sys/ucontext.h define the same names. So, when they're
- included together, the defines from one completely mess up the parsing
- of the other, producing errors like:
- /usr/include/sys/ucontext.h:47: parse error before
- `10'
-
-
-
-
- plus a pile of warnings.
-
-
- This is a libc botch, which has since been fixed, and I don't see any
- way around it besides upgrading.
-
-
-
- 13.12. The UML BogoMips is exactly half the host's BogoMips
-
- On i386 kernels, there are two ways of running the loop that is used
- to calculate the BogoMips rating, using the TSC if it's there or using
- a one-instruction loop. The TSC produces twice the BogoMips as the
- loop. UML uses the loop, since it has nothing resembling a TSC, and
- will get almost exactly the same BogoMips as a host using the loop.
- However, on a host with a TSC, its BogoMips will be double the loop
- BogoMips, and therefore double the UML BogoMips.
-
-
-
- 13.13. When you run UML, it immediately segfaults
-
- If the host is configured with the 2G/2G address space split, that's
- why. See ``UML on 2G/2G hosts'' for the details on getting UML to
- run on your host.
-
-
-
- 13.14. xterms appear, then immediately disappear
-
- If you're running an up to date kernel with an old release of
- uml_utilities, the port-helper program will not work properly, so
- xterms will exit straight after they appear. The solution is to
- upgrade to the latest release of uml_utilities. Usually this problem
- occurs when you have installed a packaged release of UML then compiled
- your own development kernel without upgrading the uml_utilities from
- the source distribution.
-
-
-
- 13.15. Any other panic, hang, or strange behavior
-
- If you're seeing truly strange behavior, such as hangs or panics that
- happen in random places, or you try running the debugger to see what's
- happening and it acts strangely, then it could be a problem in the
- host kernel. If you're not running a stock Linus or -ac kernel, then
- try that. An early version of the preemption patch and a 2.4.10 SuSE
- kernel have caused very strange problems in UML.
-
-
- Otherwise, let me know about it. Send a message to one of the UML
- mailing lists - either the developer list - user-mode-linux-devel at
- lists dot sourceforge dot net (subscription info) or the user list -
- user-mode-linux-user at lists dot sourceforge do net (subscription
- info), whichever you prefer. Don't assume that everyone knows about
- it and that a fix is imminent.
-
-
- If you want to be super-helpful, read ``Diagnosing Problems'' and
- follow the instructions contained therein.
- 14. Diagnosing Problems
-
-
- If you get UML to crash, hang, or otherwise misbehave, you should
- report this on one of the project mailing lists, either the developer
- list - user-mode-linux-devel at lists dot sourceforge dot net
- (subscription info) or the user list - user-mode-linux-user at lists
- dot sourceforge dot net (subscription info). When you do, it is
- likely that I will want more information. So, it would be helpful to
- read the stuff below, do whatever is applicable in your case, and
- report the results to the list.
-
-
- For any diagnosis, you're going to need to build a debugging kernel.
- The binaries from this site aren't debuggable. If you haven't done
- this before, read about ``Compiling the kernel and modules'' and
- ``Kernel debugging'' UML first.
-
-
- 14.1. Case 1 : Normal kernel panics
-
- The most common case is for a normal thread to panic. To debug this,
- you will need to run it under the debugger (add 'debug' to the command
- line). An xterm will start up with gdb running inside it. Continue
- it when it stops in start_kernel and make it crash. Now ^C gdb and
-
-
- If the panic was a "Kernel mode fault", then there will be a segv
- frame on the stack and I'm going to want some more information. The
- stack might look something like this:
-
-
- (UML gdb) backtrace
- #0 0x1009bf76 in __sigprocmask (how=1, set=0x5f347940, oset=0x0)
- at ../sysdeps/unix/sysv/linux/sigprocmask.c:49
- #1 0x10091411 in change_sig (signal=10, on=1) at process.c:218
- #2 0x10094785 in timer_handler (sig=26) at time_kern.c:32
- #3 0x1009bf38 in __restore ()
- at ../sysdeps/unix/sysv/linux/i386/sigaction.c:125
- #4 0x1009534c in segv (address=8, ip=268849158, is_write=2, is_user=0)
- at trap_kern.c:66
- #5 0x10095c04 in segv_handler (sig=11) at trap_user.c:285
- #6 0x1009bf38 in __restore ()
-
-
-
-
- I'm going to want to see the symbol and line information for the value
- of ip in the segv frame. In this case, you would do the following:
-
-
- (UML gdb) i sym 268849158
-
-
-
-
- and
-
-
- (UML gdb) i line *268849158
-
-
-
-
- The reason for this is the __restore frame right above the segv_han-
- dler frame is hiding the frame that actually segfaulted. So, I have
- to get that information from the faulting ip.
-
-
- 14.2. Case 2 : Tracing thread panics
-
- The less common and more painful case is when the tracing thread
- panics. In this case, the kernel debugger will be useless because it
- needs a healthy tracing thread in order to work. The first thing to
- do is get a backtrace from the tracing thread. This is done by
- figuring out what its pid is, firing up gdb, and attaching it to that
- pid. You can figure out the tracing thread pid by looking at the
- first line of the console output, which will look like this:
-
-
- tracing thread pid = 15851
-
-
-
-
- or by running ps on the host and finding the line that looks like
- this:
-
-
- jdike 15851 4.5 0.4 132568 1104 pts/0 S 21:34 0:05 ./linux [(tracing thread)]
-
-
-
-
- If the panic was 'segfault in signals', then follow the instructions
- above for collecting information about the location of the seg fault.
-
-
- If the tracing thread flaked out all by itself, then send that
- backtrace in and wait for our crack debugging team to fix the problem.
-
-
- 14.3. Case 3 : Tracing thread panics caused by other threads
-
- However, there are cases where the misbehavior of another thread
- caused the problem. The most common panic of this type is:
-
-
- wait_for_stop failed to wait for <pid> to stop with <signal number>
-
-
-
-
- In this case, you'll need to get a backtrace from the process men-
- tioned in the panic, which is complicated by the fact that the kernel
- debugger is defunct and without some fancy footwork, another gdb can't
- attach to it. So, this is how the fancy footwork goes:
-
- In a shell:
-
-
- host% kill -STOP pid
-
-
-
-
- Run gdb on the tracing thread as described in case 2 and do:
-
-
- (host gdb) call detach(pid)
-
-
- If you get a segfault, do it again. It always works the second time.
-
- Detach from the tracing thread and attach to that other thread:
-
-
- (host gdb) detach
-
-
-
-
-
-
- (host gdb) attach pid
-
-
-
-
- If gdb hangs when attaching to that process, go back to a shell and
- do:
-
-
- host%
- kill -CONT pid
-
-
-
-
- And then get the backtrace:
-
-
- (host gdb) backtrace
-
-
-
-
-
- 14.4. Case 4 : Hangs
-
- Hangs seem to be fairly rare, but they sometimes happen. When a hang
- happens, we need a backtrace from the offending process. Run the
- kernel debugger as described in case 1 and get a backtrace. If the
- current process is not the idle thread, then send in the backtrace.
- You can tell that it's the idle thread if the stack looks like this:
-
-
- #0 0x100b1401 in __libc_nanosleep ()
- #1 0x100a2885 in idle_sleep (secs=10) at time.c:122
- #2 0x100a546f in do_idle () at process_kern.c:445
- #3 0x100a5508 in cpu_idle () at process_kern.c:471
- #4 0x100ec18f in start_kernel () at init/main.c:592
- #5 0x100a3e10 in start_kernel_proc (unused=0x0) at um_arch.c:71
- #6 0x100a383f in signal_tramp (arg=0x100a3dd8) at trap_user.c:50
-
-
-
-
- If this is the case, then some other process is at fault, and went to
- sleep when it shouldn't have. Run ps on the host and figure out which
- process should not have gone to sleep and stayed asleep. Then attach
- to it with gdb and get a backtrace as described in case 3.
-
-
-
-
-
-
- 15. Thanks
-
-
- A number of people have helped this project in various ways, and this
- page gives recognition where recognition is due.
-
-
- If you're listed here and you would prefer a real link on your name,
- or no link at all, instead of the despammed email address pseudo-link,
- let me know.
-
-
- If you're not listed here and you think maybe you should be, please
- let me know that as well. I try to get everyone, but sometimes my
- bookkeeping lapses and I forget about contributions.
-
-
- 15.1. Code and Documentation
-
- Rusty Russell <rusty at linuxcare.com.au> -
-
- o wrote the HOWTO <http://user-mode-
- linux.sourceforge.net/UserModeLinux-HOWTO.html>
-
- o prodded me into making this project official and putting it on
- SourceForge
-
- o came up with the way cool UML logo <http://user-mode-
- linux.sourceforge.net/uml-small.png>
-
- o redid the config process
-
-
- Peter Moulder <reiter at netspace.net.au> - Fixed my config and build
- processes, and added some useful code to the block driver
-
-
- Bill Stearns <wstearns at pobox.com> -
-
- o HOWTO updates
-
- o lots of bug reports
-
- o lots of testing
-
- o dedicated a box (uml.ists.dartmouth.edu) to support UML development
-
- o wrote the mkrootfs script, which allows bootable filesystems of
- RPM-based distributions to be cranked out
-
- o cranked out a large number of filesystems with said script
-
-
- Jim Leu <jleu at mindspring.com> - Wrote the virtual ethernet driver
- and associated usermode tools
-
- Lars Brinkhoff <http://lars.nocrew.org/> - Contributed the ptrace
- proxy from his own project <http://a386.nocrew.org/> to allow easier
- kernel debugging
-
-
- Andrea Arcangeli <andrea at suse.de> - Redid some of the early boot
- code so that it would work on machines with Large File Support
-
-
- Chris Emerson <http://www.chiark.greenend.org.uk/~cemerson/> - Did
- the first UML port to Linux/ppc
-
-
- Harald Welte <laforge at gnumonks.org> - Wrote the multicast
- transport for the network driver
-
-
- Jorgen Cederlof - Added special file support to hostfs
-
-
- Greg Lonnon <glonnon at ridgerun dot com> - Changed the ubd driver
- to allow it to layer a COW file on a shared read-only filesystem and
- wrote the iomem emulation support
-
-
- Henrik Nordstrom <http://hem.passagen.se/hno/> - Provided a variety
- of patches, fixes, and clues
-
-
- Lennert Buytenhek - Contributed various patches, a rewrite of the
- network driver, the first implementation of the mconsole driver, and
- did the bulk of the work needed to get SMP working again.
-
-
- Yon Uriarte - Fixed the TUN/TAP network backend while I slept.
-
-
- Adam Heath - Made a bunch of nice cleanups to the initialization code,
- plus various other small patches.
-
-
- Matt Zimmerman - Matt volunteered to be the UML Debian maintainer and
- is doing a real nice job of it. He also noticed and fixed a number of
- actually and potentially exploitable security holes in uml_net. Plus
- the occasional patch. I like patches.
-
-
- James McMechan - James seems to have taken over maintenance of the ubd
- driver and is doing a nice job of it.
-
-
- Chandan Kudige - wrote the umlgdb script which automates the reloading
- of module symbols.
-
-
- Steve Schmidtke - wrote the UML slirp transport and hostaudio drivers,
- enabling UML processes to access audio devices on the host. He also
- submitted patches for the slip transport and lots of other things.
-
-
- David Coulson <http://davidcoulson.net> -
-
- o Set up the usermodelinux.org <http://usermodelinux.org> site,
- which is a great way of keeping the UML user community on top of
- UML goings-on.
-
- o Site documentation and updates
-
- o Nifty little UML management daemon UMLd
- <http://uml.openconsultancy.com/umld/>
-
- o Lots of testing and bug reports
-
-
-
-
- 15.2. Flushing out bugs
-
-
-
- o Yuri Pudgorodsky
-
- o Gerald Britton
-
- o Ian Wehrman
-
- o Gord Lamb
-
- o Eugene Koontz
-
- o John H. Hartman
-
- o Anders Karlsson
-
- o Daniel Phillips
-
- o John Fremlin
-
- o Rainer Burgstaller
-
- o James Stevenson
-
- o Matt Clay
-
- o Cliff Jefferies
-
- o Geoff Hoff
-
- o Lennert Buytenhek
-
- o Al Viro
-
- o Frank Klingenhoefer
-
- o Livio Baldini Soares
-
- o Jon Burgess
-
- o Petru Paler
-
- o Paul
-
- o Chris Reahard
-
- o Sverker Nilsson
-
- o Gong Su
-
- o johan verrept
-
- o Bjorn Eriksson
-
- o Lorenzo Allegrucci
-
- o Muli Ben-Yehuda
-
- o David Mansfield
-
- o Howard Goff
-
- o Mike Anderson
-
- o John Byrne
-
- o Sapan J. Batia
-
- o Iris Huang
-
- o Jan Hudec
-
- o Voluspa
-
-
-
-
- 15.3. Buglets and clean-ups
-
-
-
- o Dave Zarzycki
-
- o Adam Lazur
-
- o Boria Feigin
-
- o Brian J. Murrell
-
- o JS
-
- o Roman Zippel
-
- o Wil Cooley
-
- o Ayelet Shemesh
-
- o Will Dyson
-
- o Sverker Nilsson
-
- o dvorak
-
- o v.naga srinivas
-
- o Shlomi Fish
-
- o Roger Binns
-
- o johan verrept
-
- o MrChuoi
-
- o Peter Cleve
-
- o Vincent Guffens
-
- o Nathan Scott
-
- o Patrick Caulfield
-
- o jbearce
-
- o Catalin Marinas
-
- o Shane Spencer
-
- o Zou Min
-
-
- o Ryan Boder
-
- o Lorenzo Colitti
-
- o Gwendal Grignou
-
- o Andre' Breiler
-
- o Tsutomu Yasuda
-
-
-
- 15.4. Case Studies
-
-
- o Jon Wright
-
- o William McEwan
-
- o Michael Richardson
-
-
-
- 15.5. Other contributions
-
-
- Bill Carr <Bill.Carr at compaq.com> made the Red Hat mkrootfs script
- work with RH 6.2.
-
- Michael Jennings <mikejen at hevanet.com> sent in some material which
- is now gracing the top of the index page <http://user-mode-
- linux.sourceforge.net/> of this site.
-
- SGI <http://www.sgi.com> (and more specifically Ralf Baechle <ralf at
- uni-koblenz.de> ) gave me an account on oss.sgi.com
- <http://www.oss.sgi.com> . The bandwidth there made it possible to
- produce most of the filesystems available on the project download
- page.
-
- Laurent Bonnaud <Laurent.Bonnaud at inpg.fr> took the old grotty
- Debian filesystem that I've been distributing and updated it to 2.2.
- It is now available by itself here.
-
- Rik van Riel gave me some ftp space on ftp.nl.linux.org so I can make
- releases even when Sourceforge is broken.
-
- Rodrigo de Castro looked at my broken pte code and told me what was
- wrong with it, letting me fix a long-standing (several weeks) and
- serious set of bugs.
-
- Chris Reahard built a specialized root filesystem for running a DNS
- server jailed inside UML. It's available from the download
- <http://user-mode-linux.sourceforge.net/dl-sf.html> page in the Jail
- Filesystems section.
-
-
-
-
-
-
-
-
-
-
-
-
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "Linux Memory Management Documentation"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'memory-management.tex', project,
- 'The kernel development community', 'manual'),
-]
ret = hmm_range_snapshot(&range);
if (ret) {
up_read(&mm->mmap_sem);
- if (ret == -EAGAIN) {
+ if (ret == -EBUSY) {
/*
* No need to check hmm_range_wait_until_valid() return value
* on retry we will get proper error with hmm_range_snapshot()
and loop forever. This is generally not what a watchdog user wants.
For those wishing to learn more please see:
- Documentation/kdump/kdump.rst
+ Documentation/admin-guide/kdump/kdump.rst
Documentation/admin-guide/kernel-parameters.txt (panic=)
Your Linux Distribution specific documentation.
+++ /dev/null
-# -*- coding: utf-8; mode: python -*-
-
-project = "X86 architecture specific documentation"
-
-tags.add("subproject")
-
-latex_documents = [
- ('index', 'x86.tex', project,
- 'The kernel development community', 'manual'),
-]
M: Heiner Kallweit <hkallweit1@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
-F: drivers/net/ethernet/realtek/r8169.c
+F: drivers/net/ethernet/realtek/r8169*
8250/16?50 (AND CLONE UARTS) SERIAL DRIVER
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
F: drivers/crypto/sunxi-ss/
ALLWINNER VPU DRIVER
-M: Maxime Ripard <maxime.ripard@bootlin.com>
+M: Maxime Ripard <mripard@kernel.org>
M: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
L: linux-media@vger.kernel.org
S: Maintained
W: http://ez.analog.com/community/linux-device-drivers
S: Supported
F: drivers/iio/adc/ad7124.c
-F: Documentation/devicetree/bindings/iio/adc/adi,ad7124.txt
+F: Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml
ANALOG DEVICES INC AD7606 DRIVER
M: Stefan Popa <stefan.popa@analog.com>
ARM ARCHITECTED TIMER DRIVER
M: Mark Rutland <mark.rutland@arm.com>
-M: Marc Zyngier <marc.zyngier@arm.com>
+M: Marc Zyngier <maz@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/include/asm/arch_timer.h
F: drivers/clk/sunxi/
ARM/Allwinner sunXi SoC support
-M: Maxime Ripard <maxime.ripard@bootlin.com>
+M: Maxime Ripard <mripard@kernel.org>
M: Chen-Yu Tsai <wens@csie.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
ARM/RENESAS ARM64 ARCHITECTURE
M: Simon Horman <horms@verge.net.au>
+M: Geert Uytterhoeven <geert+renesas@glider.be>
M: Magnus Damm <magnus.damm@gmail.com>
L: linux-renesas-soc@vger.kernel.org
Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next
S: Supported
F: arch/arm64/boot/dts/renesas/
F: Documentation/devicetree/bindings/arm/renesas.yaml
ARM/SHMOBILE ARM ARCHITECTURE
M: Simon Horman <horms@verge.net.au>
+M: Geert Uytterhoeven <geert+renesas@glider.be>
M: Magnus Damm <magnus.damm@gmail.com>
L: linux-renesas-soc@vger.kernel.org
Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/horms/renesas.git next
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next
S: Supported
F: arch/arm/boot/dts/emev2*
F: arch/arm/boot/dts/gr-peach*
F: fs/cachefiles/
CADENCE MIPI-CSI2 BRIDGES
-M: Maxime Ripard <maxime.ripard@bootlin.com>
+M: Maxime Ripard <mripard@kernel.org>
L: linux-media@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/media/cdns,*.txt
L: cgroups@vger.kernel.org
L: linux-block@vger.kernel.org
T: git git://git.kernel.dk/linux-block
-F: Documentation/cgroup-v1/blkio-controller.rst
+F: Documentation/admin-guide/cgroup-v1/blkio-controller.rst
F: block/blk-cgroup.c
F: include/linux/blk-cgroup.h
F: block/blk-throttle.c
F: drivers/misc/cxl/
F: include/misc/cxl*
F: include/uapi/misc/cxl.h
-F: Documentation/powerpc/cxl.txt
+F: Documentation/powerpc/cxl.rst
F: Documentation/ABI/testing/sysfs-class-cxl
CXLFLASH (IBM Coherent Accelerator Processor Interface CAPI Flash) SCSI DRIVER
S: Supported
F: drivers/scsi/cxlflash/
F: include/uapi/scsi/cxlflash_ioctl.h
-F: Documentation/powerpc/cxlflash.txt
+F: Documentation/powerpc/cxlflash.rst
CYBERPRO FB DRIVER
M: Russell King <linux@armlinux.org.uk>
DRM DRIVERS AND MISC GPU PATCHES
M: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
-M: Maxime Ripard <maxime.ripard@bootlin.com>
+M: Maxime Ripard <mripard@kernel.org>
M: Sean Paul <sean@poorly.run>
W: https://01.org/linuxgraphics/gfx-docs/maintainer-tools/drm-misc.html
S: Maintained
F: include/linux/vga*
DRM DRIVERS FOR ALLWINNER A10
-M: Maxime Ripard <maxime.ripard@bootlin.com>
+M: Maxime Ripard <mripard@kernel.org>
L: dri-devel@lists.freedesktop.org
S: Supported
F: drivers/gpu/drm/sun4i/
M: Heiner Kallweit <hkallweit1@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
-F: Documentation/ABI/testing/sysfs-bus-mdio
+F: Documentation/ABI/testing/sysfs-class-net-phydev
F: Documentation/devicetree/bindings/net/ethernet-phy.yaml
F: Documentation/devicetree/bindings/net/mdio*
F: Documentation/networking/phy.rst
F: drivers/counter/ftm-quaddec.c
FLOPPY DRIVER
-S: Orphan
+M: Denis Efremov <efremov@linux.com>
+S: Odd Fixes
L: linux-block@vger.kernel.org
F: drivers/block/floppy.c
M: Moritz Fischer <mdf@kernel.org>
L: linux-fpga@vger.kernel.org
S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/atull/linux-fpga.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/mdf/linux-fpga.git
Q: http://patchwork.kernel.org/project/linux-fpga/list/
F: Documentation/fpga/
F: Documentation/driver-api/fpga/
M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: dri-devel@lists.freedesktop.org
L: linux-fbdev@vger.kernel.org
-T: git git://github.com/bzolnier/linux.git
+T: git git://anongit.freedesktop.org/drm/drm-misc
Q: http://patchwork.kernel.org/project/linux-fbdev/list/
S: Maintained
F: Documentation/fb/
F: drivers/perf/fsl_imx8_ddr_perf.c
F: Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt
+FREESCALE IMX I2C DRIVER
+M: Oleksij Rempel <o.rempel@pengutronix.de>
+R: Pengutronix Kernel Team <kernel@pengutronix.de>
+L: linux-i2c@vger.kernel.org
+S: Maintained
+F: drivers/i2c/busses/i2c-imx.c
+F: Documentation/devicetree/bindings/i2c/i2c-imx.txt
+
FREESCALE IMX LPI2C DRIVER
M: Dong Aisheng <aisheng.dong@nxp.com>
L: linux-i2c@vger.kernel.org
F: fs/gfs2/
F: include/uapi/linux/gfs2_ondisk.h
-GIGASET ISDN DRIVERS
-M: Paul Bolle <pebolle@tiscali.nl>
-L: gigaset307x-common@lists.sourceforge.net
-W: http://gigaset307x.sourceforge.net/
-S: Odd Fixes
-F: drivers/staging/isdn/gigaset/
-
GNSS SUBSYSTEM
M: Johan Hovold <johan@kernel.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/johan/gnss.git
R: Jon Olson <jonolson@google.com>
L: netdev@vger.kernel.org
S: Supported
-F: Documentation/networking/device_drivers/google/gve.txt
+F: Documentation/networking/device_drivers/google/gve.rst
F: drivers/net/ethernet/google
GPD POCKET FAN DRIVER
F: drivers/scsi/storvsc_drv.c
F: drivers/uio/uio_hv_generic.c
F: drivers/video/fbdev/hyperv_fb.c
-F: drivers/iommu/hyperv_iommu.c
+F: drivers/iommu/hyperv-iommu.c
F: net/vmw_vsock/hyperv_transport.c
F: include/clocksource/hyperv_timer.h
F: include/linux/hyperv.h
M: Gregory CLEMENT <gregory.clement@bootlin.com>
L: linux-i2c@vger.kernel.org
S: Maintained
-F: Documentation/devicetree/bindings/i2c/i2c-mv64xxx.txt
+F: Documentation/devicetree/bindings/i2c/marvell,mv64xxx-i2c.yaml
F: drivers/i2c/busses/i2c-mv64xxx.c
I2C OVER PARALLEL PORT
S: Supported
F: drivers/scsi/isci/
+INTEL CPU family model numbers
+M: Tony Luck <tony.luck@intel.com>
+M: x86@kernel.org
+L: linux-kernel@vger.kernel.org
+S: Supported
+F: arch/x86/include/asm/intel-family.h
+
INTEL DRM DRIVERS (excluding Poulsbo, Moorestown and derivative chipsets)
M: Jani Nikula <jani.nikula@linux.intel.com>
M: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
L: linux-fsdevel@vger.kernel.org
T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git
S: Supported
-F: fs/iomap.c
F: fs/iomap/
F: include/linux/iomap.h
F: fs/io_uring.c
F: include/uapi/linux/io_uring.h
-IP MASQUERADING
-M: Juanjo Ciarlante <jjciarla@raiz.uncu.edu.ar>
-S: Maintained
-F: net/ipv4/netfilter/ipt_MASQUERADE.c
-
IPMI SUBSYSTEM
M: Corey Minyard <minyard@acm.org>
L: openipmi-developer@lists.sourceforge.net (moderated for non-subscribers)
F: include/uapi/linux/ipx.h
IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
-M: Marc Zyngier <marc.zyngier@arm.com>
+M: Marc Zyngier <maz@kernel.org>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
F: Documentation/IRQ-domain.txt
IRQCHIP DRIVERS
M: Thomas Gleixner <tglx@linutronix.de>
M: Jason Cooper <jason@lakedaemon.net>
-M: Marc Zyngier <marc.zyngier@arm.com>
+M: Marc Zyngier <maz@kernel.org>
L: linux-kernel@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
W: http://www.linux-kvm.org
T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
S: Supported
-F: Documentation/virtual/kvm/
+F: Documentation/virt/kvm/
F: include/trace/events/kvm.h
F: include/uapi/asm-generic/kvm*
F: include/uapi/linux/kvm*
F: tools/kvm/
F: tools/testing/selftests/kvm/
-KERNEL VIRTUAL MACHINE FOR AMD-V (KVM/amd)
-M: Joerg Roedel <joro@8bytes.org>
-L: kvm@vger.kernel.org
-W: http://www.linux-kvm.org/
-S: Maintained
-F: arch/x86/include/asm/svm.h
-F: arch/x86/kvm/svm.c
-
KERNEL VIRTUAL MACHINE FOR ARM/ARM64 (KVM/arm, KVM/arm64)
-M: Marc Zyngier <marc.zyngier@arm.com>
+M: Marc Zyngier <maz@kernel.org>
R: James Morse <james.morse@arm.com>
-R: Julien Thierry <julien.thierry@arm.com>
-R: Suzuki K Pouloze <suzuki.poulose@arm.com>
+R: Julien Thierry <julien.thierry.kdev@gmail.com>
+R: Suzuki K Poulose <suzuki.poulose@arm.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: kvmarm@lists.cs.columbia.edu
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm.git
M: Janosch Frank <frankja@linux.ibm.com>
R: David Hildenbrand <david@redhat.com>
R: Cornelia Huck <cohuck@redhat.com>
-L: linux-s390@vger.kernel.org
+L: kvm@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
S: Supported
KERNEL VIRTUAL MACHINE FOR X86 (KVM/x86)
M: Paolo Bonzini <pbonzini@redhat.com>
M: Radim Krčmář <rkrcmar@redhat.com>
+R: Sean Christopherson <sean.j.christopherson@intel.com>
+R: Vitaly Kuznetsov <vkuznets@redhat.com>
+R: Wanpeng Li <wanpengli@tencent.com>
+R: Jim Mattson <jmattson@google.com>
+R: Joerg Roedel <joro@8bytes.org>
L: kvm@vger.kernel.org
W: http://www.linux-kvm.org
T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
F: arch/x86/kvm/
F: arch/x86/kvm/*/
F: arch/x86/include/uapi/asm/kvm*
+F: arch/x86/include/uapi/asm/vmx.h
+F: arch/x86/include/uapi/asm/svm.h
F: arch/x86/include/asm/kvm*
F: arch/x86/include/asm/pvclock-abi.h
+F: arch/x86/include/asm/svm.h
+F: arch/x86/include/asm/vmx.h
F: arch/x86/kernel/kvm.c
F: arch/x86/kernel/kvmclock.c
F: include/linux/libnvdimm.h
F: include/uapi/linux/ndctl.h
+LICENSES and SPDX stuff
+M: Thomas Gleixner <tglx@linutronix.de>
+M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+L: linux-spdx@vger.kernel.org
+S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/spdx.git
+F: COPYING
+F: Documentation/process/license-rules.rst
+F: LICENSES/
+F: scripts/spdxcheck-test.sh
+F: scripts/spdxcheck.py
+
LIGHTNVM PLATFORM SUPPORT
M: Matias Bjorling <mb@lightnvm.io>
W: http://github/OpenChannelSSD
M: Sridhar Samudrala <sridhar.samudrala@intel.com>
L: netdev@vger.kernel.org
S: Supported
-F: driver/net/net_failover.c
+F: drivers/net/net_failover.c
F: include/net/net_failover.h
F: Documentation/networking/net_failover.rst
S: Maintained
W: https://fedorahosted.org/dropwatch/
F: net/core/drop_monitor.c
+F: include/uapi/linux/net_dropmon.h
NETWORKING DRIVERS
M: "David S. Miller" <davem@davemloft.net>
M: Dave Watson <davejwatson@fb.com>
M: John Fastabend <john.fastabend@gmail.com>
M: Daniel Borkmann <daniel@iogearbox.net>
+M: Jakub Kicinski <jakub.kicinski@netronome.com>
L: netdev@vger.kernel.org
S: Maintained
F: net/tls/*
M: "VMware, Inc." <pv-drivers@vmware.com>
L: virtualization@lists.linux-foundation.org
S: Supported
-F: Documentation/virtual/paravirt_ops.txt
+F: Documentation/virt/paravirt_ops.rst
F: arch/*/kernel/paravirt*
F: arch/*/include/asm/paravirt*.h
F: include/linux/hypervisor.h
F: drivers/pci/pcie/aer.c
F: drivers/pci/pcie/dpc.c
F: drivers/pci/pcie/err.c
-F: Documentation/powerpc/eeh-pci-error-recovery.txt
+F: Documentation/powerpc/eeh-pci-error-recovery.rst
F: arch/powerpc/kernel/eeh*.c
F: arch/powerpc/platforms/*/eeh*.c
F: arch/powerpc/include/*/eeh*.h
F: drivers/mtd/nand/raw/r852.h
RISC-V ARCHITECTURE
+M: Paul Walmsley <paul.walmsley@sifive.com>
M: Palmer Dabbelt <palmer@sifive.com>
M: Albert Ou <aou@eecs.berkeley.edu>
L: linux-riscv@lists.infradead.org
S390 VFIO-CCW DRIVER
M: Cornelia Huck <cohuck@redhat.com>
-M: Farhan Ali <alifm@linux.ibm.com>
M: Eric Farman <farman@linux.ibm.com>
R: Halil Pasic <pasic@linux.ibm.com>
L: linux-s390@vger.kernel.org
F: drivers/media/pci/saa7146/
F: include/media/drv-intf/saa7146*
+SAFESETID SECURITY MODULE
+M: Micah Morton <mortonm@chromium.org>
+S: Supported
+F: security/safesetid/
+F: Documentation/admin-guide/LSM/SafeSetID.rst
+
SAMSUNG AUDIO (ASoC) DRIVERS
M: Krzysztof Kozlowski <krzk@kernel.org>
M: Sangbeom Kim <sbkim73@samsung.com>
F: drivers/net/phy/sfp*
F: include/linux/phylink.h
F: include/linux/sfp.h
+K: phylink
SGI GRU DRIVER
M: Dimitri Sivanich <sivanich@sgi.com>
F: include/uapi/linux/arm_sdei.h
SOFTWARE RAID (Multiple Disks) SUPPORT
-M: Shaohua Li <shli@kernel.org>
+M: Song Liu <song@kernel.org>
L: linux-raid@vger.kernel.org
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/shli/md.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/song/md.git
S: Supported
F: drivers/md/Makefile
F: drivers/md/Kconfig
Q: https://patchwork.ozlabs.org/project/linux-um/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git
S: Maintained
-F: Documentation/virtual/uml/
+F: Documentation/virt/uml/
F: arch/um/
F: arch/x86/um/
F: fs/hostfs/
F: include/uapi/linux/virtio_input.h
VIRTIO IOMMU DRIVER
-M: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
+M: Jean-Philippe Brucker <jean-philippe@linaro.org>
L: virtualization@lists.linux-foundation.org
S: Maintained
F: drivers/iommu/virtio-iommu.c
F: include/linux/vme*
VMWARE BALLOON DRIVER
-M: Julien Freche <jfreche@vmware.com>
M: Nadav Amit <namit@vmware.com>
M: "VMware, Inc." <pv-drivers@vmware.com>
L: linux-kernel@vger.kernel.org
M: Jesper Dangaard Brouer <hawk@kernel.org>
M: John Fastabend <john.fastabend@gmail.com>
L: netdev@vger.kernel.org
-L: xdp-newbies@vger.kernel.org
L: bpf@vger.kernel.org
S: Supported
F: net/core/xdp.c
VERSION = 5
PATCHLEVEL = 3
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc8
NAME = Bobtail Squid
# *DOCUMENTATION*
STRIP = $(CROSS_COMPILE)strip
OBJCOPY = $(CROSS_COMPILE)objcopy
OBJDUMP = $(CROSS_COMPILE)objdump
+OBJSIZE = $(CROSS_COMPILE)size
PAHOLE = pahole
LEX = flex
YACC = bison
KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds
KBUILD_LDFLAGS :=
GCC_PLUGINS_CFLAGS :=
+CLANG_FLAGS :=
export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP PAHOLE KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS
-export MAKE LEX YACC AWK INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
-export HOSTCXX KBUILD_HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
+export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE PAHOLE LEX YACC AWK INSTALLKERNEL
+export PERL PYTHON PYTHON2 PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
+export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS
export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE
ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
ifneq ($(CROSS_COMPILE),)
-CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%))
+CLANG_FLAGS += --target=$(notdir $(CROSS_COMPILE:%-=%))
GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
CLANG_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)
GCC_TOOLCHAIN := $(realpath $(GCC_TOOLCHAIN_DIR)/..)
# warn about C99 declaration after statement
KBUILD_CFLAGS += -Wdeclaration-after-statement
+# Warn about unmarked fall-throughs in switch statement.
+KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough,)
+
# Variable Length Arrays (VLAs) should not be used anywhere in the kernel
KBUILD_CFLAGS += -Wvla
PHONY += prepare0
+export MODORDER := $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/)modules.order
+
ifeq ($(KBUILD_EXTMOD),)
core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
$(Q)$(MAKE) $(build)=$(build-dir) $(build-target)
%.symtypes: prepare FORCE
$(Q)$(MAKE) $(build)=$(build-dir) $(build-target)
+ifeq ($(KBUILD_EXTMOD),)
+# For the single build of an in-tree module, use a temporary file to avoid
+# the situation of modules_install installing an invalid modules.order.
+%.ko: MODORDER := .modules.tmp
+endif
+%.ko: prepare FORCE
+ $(Q)$(MAKE) $(build)=$(build-dir) $(build-target:.ko=.mod)
+ $(Q)echo $(build-target) > $(MODORDER)
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
# Modules
PHONY += /
/: ./
%/: prepare FORCE
- $(Q)$(MAKE) KBUILD_MODULES=1 $(build)=$(build-dir)
+ $(Q)$(MAKE) KBUILD_MODULES=1 $(build)=$(build-dir) need-modorder=1
# FIXME Should go into a make.lib or something
# ===========================================================================
# for CONFIG_OF_ALL_DTBS test
dtstree := $(srctree)/$(src)
dtb- := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts))
+
+# board-specific dtc flags
+DTC_FLAGS_hsdk += --pad 20
.macro FAKE_RET_FROM_EXCPN
lr r9, [status32]
- bic r9, r9, (STATUS_U_MASK|STATUS_DE_MASK|STATUS_AE_MASK)
+ bic r9, r9, STATUS_AE_MASK
or r9, r9, STATUS_IE_MASK
kflag r9
.endm
#else /* !__ASSEMBLY__ */
#ifdef CONFIG_ARC_HAS_ICCM
-#define __arcfp_code __attribute__((__section__(".text.arcfp")))
+#define __arcfp_code __section(.text.arcfp)
#else
-#define __arcfp_code __attribute__((__section__(".text")))
+#define __arcfp_code __section(.text)
#endif
#ifdef CONFIG_ARC_HAS_DCCM
-#define __arcfp_data __attribute__((__section__(".data.arcfp")))
+#define __arcfp_data __section(.data.arcfp)
#else
-#define __arcfp_data __attribute__((__section__(".data")))
+#define __arcfp_data __section(.data)
#endif
#endif /* __ASSEMBLY__ */
*/
#define MACHINE_START(_type, _name) \
static const struct machine_desc __mach_desc_##_type \
-__used \
-__attribute__((__section__(".arch.info.init"))) = { \
+__used __section(.arch.info.init) = { \
.name = _name,
#define MACHINE_END \
__mcip_cmd_data(CMD_IDU_SET_DEST, cmn_irq, cpu_mask);
}
-static void idu_set_mode(unsigned int cmn_irq, unsigned int lvl,
- unsigned int distr)
+static void idu_set_mode(unsigned int cmn_irq, bool set_lvl, unsigned int lvl,
+ bool set_distr, unsigned int distr)
{
union {
unsigned int word;
};
} data;
- data.distr = distr;
- data.lvl = lvl;
+ data.word = __mcip_cmd_read(CMD_IDU_READ_MODE, cmn_irq);
+ if (set_distr)
+ data.distr = distr;
+ if (set_lvl)
+ data.lvl = lvl;
__mcip_cmd_data(CMD_IDU_SET_MODE, cmn_irq, data.word);
}
raw_spin_unlock_irqrestore(&mcip_lock, flags);
}
+static void idu_irq_ack(struct irq_data *data)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&mcip_lock, flags);
+ __mcip_cmd(CMD_IDU_ACK_CIRQ, data->hwirq);
+ raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
+static void idu_irq_mask_ack(struct irq_data *data)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&mcip_lock, flags);
+ __mcip_cmd_data(CMD_IDU_SET_MASK, data->hwirq, 1);
+ __mcip_cmd(CMD_IDU_ACK_CIRQ, data->hwirq);
+ raw_spin_unlock_irqrestore(&mcip_lock, flags);
+}
+
static int
idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
bool force)
else
distribution_mode = IDU_M_DISTRI_RR;
- idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, distribution_mode);
+ idu_set_mode(data->hwirq, false, 0, true, distribution_mode);
raw_spin_unlock_irqrestore(&mcip_lock, flags);
return IRQ_SET_MASK_OK;
}
+static int idu_irq_set_type(struct irq_data *data, u32 type)
+{
+ unsigned long flags;
+
+ /*
+ * ARCv2 IDU HW does not support inverse polarity, so these are the
+ * only interrupt types supported.
+ */
+ if (type & ~(IRQ_TYPE_EDGE_RISING | IRQ_TYPE_LEVEL_HIGH))
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&mcip_lock, flags);
+
+ idu_set_mode(data->hwirq, true,
+ type & IRQ_TYPE_EDGE_RISING ? IDU_M_TRIG_EDGE :
+ IDU_M_TRIG_LEVEL,
+ false, 0);
+
+ raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
+ return 0;
+}
+
static void idu_irq_enable(struct irq_data *data)
{
/*
.name = "MCIP IDU Intc",
.irq_mask = idu_irq_mask,
.irq_unmask = idu_irq_unmask,
+ .irq_ack = idu_irq_ack,
+ .irq_mask_ack = idu_irq_mask_ack,
.irq_enable = idu_irq_enable,
+ .irq_set_type = idu_irq_set_type,
#ifdef CONFIG_SMP
.irq_set_affinity = idu_irq_set_affinity,
#endif
}
static const struct irq_domain_ops idu_irq_ops = {
- .xlate = irq_domain_xlate_onecell,
+ .xlate = irq_domain_xlate_onetwocell,
.map = idu_irq_map,
};
#else
BUILD_BUG_ON(sizeof(u32) != sizeof(value));
#endif
+ /* Fall through */
case DW_EH_PE_native:
if (end < (const void *)(ptr.pul + 1))
return 0;
case DW_CFA_def_cfa:
state->cfa.reg = get_uleb128(&ptr.p8, end);
unw_debug("cfa_def_cfa: r%lu ", state->cfa.reg);
- /*nobreak*/
+ /* fall through */
case DW_CFA_def_cfa_offset:
state->cfa.offs = get_uleb128(&ptr.p8, end);
unw_debug("cfa_def_cfa_offset: 0x%lx ",
break;
case DW_CFA_def_cfa_sf:
state->cfa.reg = get_uleb128(&ptr.p8, end);
- /*nobreak */
+ /* fall through */
case DW_CFA_def_cfa_offset_sf:
state->cfa.offs = get_sleb128(&ptr.p8, end)
* state->dataAlign;
if (is_isa_arcv2() && ioc_enable && coherent)
dev->dma_coherent = true;
- dev_info(dev, "use %sncoherent DMA ops\n",
+ dev_info(dev, "use %scoherent DMA ops\n",
dev->dma_coherent ? "" : "non");
}
*/
#include <linux/init.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
#include <linux/smp.h>
#include <asm/arcregs.h>
#include <asm/io.h>
#include <asm/mach_desc.h>
+int arc_hsdk_axi_dmac_coherent __section(.data) = 0;
+
#define ARC_CCM_UNUSED_ADDR 0x60000000
static void __init hsdk_init_per_cpu(unsigned int cpu)
iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN);
}
+static int __init hsdk_tweak_node_coherency(const char *path, bool coherent)
+{
+ void *fdt = initial_boot_params;
+ const void *prop;
+ int node, ret;
+ bool dt_coh_set;
+
+ node = fdt_path_offset(fdt, path);
+ if (node < 0)
+ goto tweak_fail;
+
+ prop = fdt_getprop(fdt, node, "dma-coherent", &ret);
+ if (!prop && ret != -FDT_ERR_NOTFOUND)
+ goto tweak_fail;
+
+ dt_coh_set = ret != -FDT_ERR_NOTFOUND;
+ ret = 0;
+
+ /* need to remove "dma-coherent" property */
+ if (dt_coh_set && !coherent)
+ ret = fdt_delprop(fdt, node, "dma-coherent");
+
+ /* need to set "dma-coherent" property */
+ if (!dt_coh_set && coherent)
+ ret = fdt_setprop(fdt, node, "dma-coherent", NULL, 0);
+
+ if (ret < 0)
+ goto tweak_fail;
+
+ return 0;
+
+tweak_fail:
+ pr_err("failed to tweak %s to %scoherent\n", path, coherent ? "" : "non");
+ return -EFAULT;
+}
+
enum hsdk_axi_masters {
M_HS_CORE = 0,
M_HS_RTT,
#define CREG_PAE ((void __iomem *)(CREG_BASE + 0x180))
#define CREG_PAE_UPDT ((void __iomem *)(CREG_BASE + 0x194))
+static void __init hsdk_init_memory_bridge_axi_dmac(void)
+{
+ bool coherent = !!arc_hsdk_axi_dmac_coherent;
+ u32 axi_m_slv1, axi_m_oft1;
+
+ /*
+ * Don't tweak memory bridge configuration if we failed to tweak DTB
+ * as we will end up in a inconsistent state.
+ */
+ if (hsdk_tweak_node_coherency("/soc/dmac@80000", coherent))
+ return;
+
+ if (coherent) {
+ axi_m_slv1 = 0x77999999;
+ axi_m_oft1 = 0x76DCBA98;
+ } else {
+ axi_m_slv1 = 0x77777777;
+ axi_m_oft1 = 0x76543210;
+ }
+
+ writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_0));
+ writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_0));
+ writel(axi_m_slv1, CREG_AXI_M_SLV1(M_DMAC_0));
+ writel(axi_m_oft1, CREG_AXI_M_OFT1(M_DMAC_0));
+ writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_0));
+
+ writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_1));
+ writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_1));
+ writel(axi_m_slv1, CREG_AXI_M_SLV1(M_DMAC_1));
+ writel(axi_m_oft1, CREG_AXI_M_OFT1(M_DMAC_1));
+ writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_1));
+}
+
static void __init hsdk_init_memory_bridge(void)
{
u32 reg;
writel(0x76543210, CREG_AXI_M_OFT1(M_GPU));
writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_GPU));
- writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_0));
- writel(0x77777777, CREG_AXI_M_SLV1(M_DMAC_0));
- writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_0));
- writel(0x76543210, CREG_AXI_M_OFT1(M_DMAC_0));
- writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_0));
-
- writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_1));
- writel(0x77777777, CREG_AXI_M_SLV1(M_DMAC_1));
- writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_1));
- writel(0x76543210, CREG_AXI_M_OFT1(M_DMAC_1));
- writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_1));
-
writel(0x00000000, CREG_AXI_M_SLV0(M_DVFS));
writel(0x60000000, CREG_AXI_M_SLV1(M_DVFS));
writel(0x00000000, CREG_AXI_M_OFT0(M_DVFS));
writel(0x00000000, CREG_AXI_M_OFT1(M_DVFS));
writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DVFS));
+ hsdk_init_memory_bridge_axi_dmac();
+
/*
* PAE remapping for DMA clients does not work due to an RTL bug, so
* CREG_PAE register must be programmed to all zeroes, otherwise it
select ARCH_HAS_BINFMT_FLAT
select ARCH_HAS_DEBUG_VIRTUAL if MMU
select ARCH_HAS_DEVMEM_IS_ALLOWED
+ select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
+ select ARCH_HAS_DMA_MMAP_PGPROT if SWIOTLB
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_KEEPINITRD
select ARCH_HAS_SET_MEMORY
select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
select ARCH_HAS_STRICT_MODULE_RWX if MMU
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE if SWIOTLB
+ select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB
select ARCH_HAS_TEARDOWN_DMA_OPS if MMU
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_HAVE_CUSTOM_GPIO_H
DEBUG_IMX7D_UART
default "debug/ks8695.S" if DEBUG_KS8695_UART
default "debug/msm.S" if DEBUG_QCOM_UARTDM
- default "debug/netx.S" if DEBUG_NETX_UART
default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART
default "debug/renesas-scif.S" if DEBUG_R7S72100_SCIF2
default "debug/renesas-scif.S" if DEBUG_RCAR_GEN1_SCIF0
config DEBUG_UART_PHYS
hex "Physical base address of debug UART"
- default 0x00100a00 if DEBUG_NETX_UART
default 0x01c20000 if DEBUG_DAVINCI_DMx_UART0
default 0x01c28000 if DEBUG_SUNXI_UART0
default 0x01c28400 if DEBUG_SUNXI_UART1
DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
DEBUG_LL_UART_EFM32 || \
DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \
- DEBUG_NETX_UART || \
DEBUG_QCOM_UARTDM || DEBUG_R7S72100_SCIF2 || \
DEBUG_RCAR_GEN1_SCIF0 || DEBUG_RCAR_GEN1_SCIF2 || \
DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF1 || \
default 0xc881f000 if DEBUG_RV1108_UART2
default 0xc8821000 if DEBUG_RV1108_UART1
default 0xc8912000 if DEBUG_RV1108_UART0
- default 0xe0000a00 if DEBUG_NETX_UART
default 0xe0010fe0 if ARCH_RPC
default 0xf0000be0 if ARCH_EBSA110
default 0xf0010000 if DEBUG_ASM9260_UART
default DEBUG_UART_PHYS if !MMU
depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \
- DEBUG_NETX_UART || \
DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \
DEBUG_S3C64XX_UART || \
DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \
uart0: serial@0 {
compatible = "ti,am3352-uart", "ti,omap3-uart";
clock-frequency = <48000000>;
- reg = <0x0 0x2000>;
+ reg = <0x0 0x1000>;
interrupts = <72>;
status = "disabled";
dmas = <&edma 26 0>, <&edma 27 0>;
uart1: serial@0 {
compatible = "ti,am3352-uart", "ti,omap3-uart";
clock-frequency = <48000000>;
- reg = <0x0 0x2000>;
+ reg = <0x0 0x1000>;
interrupts = <73>;
status = "disabled";
dmas = <&edma 28 0>, <&edma 29 0>;
uart2: serial@0 {
compatible = "ti,am3352-uart", "ti,omap3-uart";
clock-frequency = <48000000>;
- reg = <0x0 0x2000>;
+ reg = <0x0 0x1000>;
interrupts = <74>;
status = "disabled";
dmas = <&edma 30 0>, <&edma 31 0>;
uart3: serial@0 {
compatible = "ti,am3352-uart", "ti,omap3-uart";
clock-frequency = <48000000>;
- reg = <0x0 0x2000>;
+ reg = <0x0 0x1000>;
interrupts = <44>;
status = "disabled";
};
uart4: serial@0 {
compatible = "ti,am3352-uart", "ti,omap3-uart";
clock-frequency = <48000000>;
- reg = <0x0 0x2000>;
+ reg = <0x0 0x1000>;
interrupts = <45>;
status = "disabled";
};
uart5: serial@0 {
compatible = "ti,am3352-uart", "ti,omap3-uart";
clock-frequency = <48000000>;
- reg = <0x0 0x2000>;
+ reg = <0x0 0x1000>;
interrupts = <46>;
status = "disabled";
};
target-module@cc000 { /* 0x481cc000, ap 60 46.0 */
compatible = "ti,sysc-omap4", "ti,sysc";
+ reg = <0xcc020 0x4>;
+ reg-names = "rev";
ti,hwmods = "d_can0";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN0_CLKCTRL 0>,
target-module@d0000 { /* 0x481d0000, ap 62 42.0 */
compatible = "ti,sysc-omap4", "ti,sysc";
+ reg = <0xd0020 0x4>;
+ reg-names = "rev";
ti,hwmods = "d_can1";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN1_CLKCTRL 0>,
interrupt-names = "edma3_tcerrint";
};
- mmc3: mmc@47810000 {
- compatible = "ti,omap4-hsmmc";
+ target-module@47810000 {
+ compatible = "ti,sysc-omap2", "ti,sysc";
ti,hwmods = "mmc3";
- ti,needs-special-reset;
- interrupts = <29>;
- reg = <0x47810000 0x1000>;
- status = "disabled";
+ reg = <0x478102fc 0x4>,
+ <0x47810110 0x4>,
+ <0x47810114 0x4>;
+ reg-names = "rev", "sysc", "syss";
+ ti,sysc-mask = <(SYSC_OMAP2_CLOCKACTIVITY |
+ SYSC_OMAP2_ENAWAKEUP |
+ SYSC_OMAP2_SOFTRESET |
+ SYSC_OMAP2_AUTOIDLE)>;
+ ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+ <SYSC_IDLE_NO>,
+ <SYSC_IDLE_SMART>;
+ ti,syss-mask = <1>;
+ clocks = <&l3s_clkctrl AM3_L3S_MMC3_CLKCTRL 0>;
+ clock-names = "fck";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0x0 0x47810000 0x1000>;
+
+ mmc3: mmc@0 {
+ compatible = "ti,omap4-hsmmc";
+ ti,needs-special-reset;
+ interrupts = <29>;
+ reg = <0x0 0x1000>;
+ };
};
usb: usb@47400000 {
interrupt-names = "edma3_tcerrint";
};
- mmc3: mmc@47810000 {
- compatible = "ti,omap4-hsmmc";
- reg = <0x47810000 0x1000>;
+ target-module@47810000 {
+ compatible = "ti,sysc-omap2", "ti,sysc";
ti,hwmods = "mmc3";
- ti,needs-special-reset;
- interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
- status = "disabled";
+ reg = <0x478102fc 0x4>,
+ <0x47810110 0x4>,
+ <0x47810114 0x4>;
+ reg-names = "rev", "sysc", "syss";
+ ti,sysc-mask = <(SYSC_OMAP2_CLOCKACTIVITY |
+ SYSC_OMAP2_ENAWAKEUP |
+ SYSC_OMAP2_SOFTRESET |
+ SYSC_OMAP2_AUTOIDLE)>;
+ ti,sysc-sidle = <SYSC_IDLE_FORCE>,
+ <SYSC_IDLE_NO>,
+ <SYSC_IDLE_SMART>;
+ ti,syss-mask = <1>;
+ clocks = <&l3s_clkctrl AM4_L3S_MMC3_CLKCTRL 0>;
+ clock-names = "fck";
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0x0 0x47810000 0x1000>;
+
+ mmc3: mmc@0 {
+ compatible = "ti,omap4-hsmmc";
+ ti,needs-special-reset;
+ interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
+ reg = <0x0 0x1000>;
+ };
};
sham: sham@53100000 {
target-module@cc000 { /* 0x481cc000, ap 50 46.0 */
compatible = "ti,sysc-omap4", "ti,sysc";
+ reg = <0xcc020 0x4>;
+ reg-names = "rev";
ti,hwmods = "d_can0";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>;
target-module@d0000 { /* 0x481d0000, ap 52 3a.0 */
compatible = "ti,sysc-omap4", "ti,sysc";
+ reg = <0xd0020 0x4>;
+ reg-names = "rev";
ti,hwmods = "d_can1";
/* Domains (P, C): per_pwrdm, l4ls_clkdm */
clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>;
};
&mmc1 {
- pinctrl-names = "default", "hs", "sdr12", "sdr25", "sdr50", "ddr50", "sdr104";
+ pinctrl-names = "default", "hs";
pinctrl-0 = <&mmc1_pins_default_no_clk_pu>;
pinctrl-1 = <&mmc1_pins_hs>;
- pinctrl-2 = <&mmc1_pins_sdr12>;
- pinctrl-3 = <&mmc1_pins_sdr25>;
- pinctrl-4 = <&mmc1_pins_sdr50>;
- pinctrl-5 = <&mmc1_pins_ddr50_rev20 &mmc1_iodelay_ddr50_conf>;
- pinctrl-6 = <&mmc1_pins_sdr104 &mmc1_iodelay_sdr104_rev20_conf>;
};
&mmc2 {
};
&mmc1 {
- pinctrl-names = "default", "hs", "sdr12", "sdr25", "sdr50", "ddr50", "sdr104";
+ pinctrl-names = "default", "hs";
pinctrl-0 = <&mmc1_pins_default_no_clk_pu>;
pinctrl-1 = <&mmc1_pins_hs>;
- pinctrl-2 = <&mmc1_pins_sdr12>;
- pinctrl-3 = <&mmc1_pins_sdr25>;
- pinctrl-4 = <&mmc1_pins_sdr50>;
- pinctrl-5 = <&mmc1_pins_ddr50 &mmc1_iodelay_ddr_rev20_conf>;
- pinctrl-6 = <&mmc1_pins_sdr104 &mmc1_iodelay_sdr104_rev20_conf>;
};
&mmc2 {
};
&mmc1 {
- pinctrl-names = "default", "hs", "sdr12", "sdr25", "sdr50", "ddr50", "sdr104";
+ pinctrl-names = "default", "hs";
pinctrl-0 = <&mmc1_pins_default_no_clk_pu>;
pinctrl-1 = <&mmc1_pins_hs>;
- pinctrl-2 = <&mmc1_pins_default>;
- pinctrl-3 = <&mmc1_pins_hs>;
- pinctrl-4 = <&mmc1_pins_sdr50>;
- pinctrl-5 = <&mmc1_pins_ddr50 &mmc1_iodelay_ddr_conf>;
- pinctrl-6 = <&mmc1_pins_ddr50 &mmc1_iodelay_sdr104_conf>;
};
&mmc2 {
};
};
-&gpio7 {
+&gpio7_target {
ti,no-reset-on-init;
ti,no-idle-on-init;
};
bus-width = <4>;
cd-gpios = <&gpio6 27 GPIO_ACTIVE_LOW>; /* gpio 219 */
+ no-1-8-v;
};
&mmc2 {
};
&mmc1 {
- pinctrl-names = "default", "hs", "sdr12", "sdr25", "sdr50", "ddr50", "sdr104";
+ pinctrl-names = "default", "hs";
pinctrl-0 = <&mmc1_pins_default>;
pinctrl-1 = <&mmc1_pins_hs>;
- pinctrl-2 = <&mmc1_pins_sdr12>;
- pinctrl-3 = <&mmc1_pins_sdr25>;
- pinctrl-4 = <&mmc1_pins_sdr50>;
- pinctrl-5 = <&mmc1_pins_ddr50 &mmc1_iodelay_ddr_rev11_conf>;
- pinctrl-6 = <&mmc1_pins_sdr104 &mmc1_iodelay_sdr104_rev11_conf>;
vmmc-supply = <&vdd_3v3>;
vqmmc-supply = <&ldo1_reg>;
};
};
&mmc1 {
- pinctrl-names = "default", "hs", "sdr12", "sdr25", "sdr50", "ddr50", "sdr104";
+ pinctrl-names = "default", "hs";
pinctrl-0 = <&mmc1_pins_default>;
pinctrl-1 = <&mmc1_pins_hs>;
- pinctrl-2 = <&mmc1_pins_sdr12>;
- pinctrl-3 = <&mmc1_pins_sdr25>;
- pinctrl-4 = <&mmc1_pins_sdr50>;
- pinctrl-5 = <&mmc1_pins_ddr50 &mmc1_iodelay_ddr_rev20_conf>;
- pinctrl-6 = <&mmc1_pins_sdr104 &mmc1_iodelay_sdr104_rev20_conf>;
vmmc-supply = <&vdd_3v3>;
vqmmc-supply = <&ldo1_reg>;
};
};
mdio-bus-mux {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
/* BIT(9) = 1 => external mdio */
mdio_ext: mdio@200 {
reg = <0x200>;
phy-supply = <&ldousb_reg>;
};
-&gpio7 {
+&gpio7_target {
ti,no-reset-on-init;
ti,no-idle-on-init;
};
};
};
- target-module@51000 { /* 0x48051000, ap 45 2e.0 */
+ gpio7_target: target-module@51000 { /* 0x48051000, ap 45 2e.0 */
compatible = "ti,sysc-omap2", "ti,sysc";
ti,hwmods = "gpio7";
reg = <0x51000 0x4>,
target-module@80000 { /* 0x48480000, ap 31 16.0 */
compatible = "ti,sysc-omap4", "ti,sysc";
- reg = <0x80000 0x4>;
+ reg = <0x80020 0x4>;
reg-names = "rev";
clocks = <&l4per2_clkctrl DRA7_L4PER2_DCAN2_CLKCTRL 0>;
clock-names = "fck";
target-module@c000 { /* 0x4ae3c000, ap 30 04.0 */
compatible = "ti,sysc-omap4", "ti,sysc";
- reg = <0xc000 0x4>;
+ reg = <0xc020 0x4>;
reg-names = "rev";
clocks = <&wkupaon_clkctrl DRA7_WKUPAON_DCAN1_CLKCTRL 0>;
clock-names = "fck";
*
* Datamanual Revisions:
*
- * AM572x Silicon Revision 2.0: SPRS953B, Revised November 2016
+ * AM572x Silicon Revision 2.0: SPRS953F, Revised May 2019
* AM572x Silicon Revision 1.1: SPRS915R, Revised November 2016
*
*/
mmc3_pins_default: mmc3_pins_default {
pinctrl-single,pins = <
- DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
- DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
- DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
- DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
- DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
- DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
+ DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
+ DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
+ DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
+ DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
+ DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
+ DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
>;
};
mmc3_pins_hs: mmc3_pins_hs {
pinctrl-single,pins = <
- DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
- DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
- DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
- DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
- DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
- DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
+ DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
+ DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
+ DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
+ DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
+ DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
+ DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
>;
};
mmc3_pins_sdr12: mmc3_pins_sdr12 {
pinctrl-single,pins = <
- DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
- DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
- DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
- DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
- DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
- DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
+ DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
+ DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
+ DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
+ DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
+ DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
+ DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
>;
};
mmc3_pins_sdr25: mmc3_pins_sdr25 {
pinctrl-single,pins = <
- DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
- DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
- DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
- DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
- DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
- DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
+ DRA7XX_CORE_IOPAD(0x377c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_clk.mmc3_clk */
+ DRA7XX_CORE_IOPAD(0x3780, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_cmd.mmc3_cmd */
+ DRA7XX_CORE_IOPAD(0x3784, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat0.mmc3_dat0 */
+ DRA7XX_CORE_IOPAD(0x3788, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat1.mmc3_dat1 */
+ DRA7XX_CORE_IOPAD(0x378c, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat2.mmc3_dat2 */
+ DRA7XX_CORE_IOPAD(0x3790, (PIN_INPUT_PULLUP | MODE_SELECT | MUX_MODE0)) /* mmc3_dat3.mmc3_dat3 */
>;
};
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
};
&i2c2 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c2>;
status = "okay";
};
&i2c3 {
- clock_frequency = <100000>;
+ clock-frequency = <100000>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_i2c3>;
status = "okay";
reg = <0x40330200 0x200>;
};
- usbphy1: usb-phy@0x40350000 {
+ usbphy1: usb-phy@40350000 {
compatible = "fsl,imx7ulp-usbphy", "fsl,imx6ul-usbphy";
reg = <0x40350000 0x1000>;
interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>;
reg = <0>;
};
- n25q128a13_2: flash@1 {
+ n25q128a13_2: flash@2 {
compatible = "n25q128a13", "jedec,spi-nor";
#address-cells = <1>;
#size-cells = <1>;
spi-max-frequency = <66000000>;
spi-rx-bus-width = <2>;
- reg = <1>;
+ reg = <2>;
};
};
CONFIG_HIGH_RES_TIMERS=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PARTITION_ADVANCED=y
CONFIG_ARCH_U8500=y
-CONFIG_MACH_HREFV60=y
-CONFIG_MACH_SNOWBALL=y
CONFIG_SMP=y
CONFIG_NR_CPUS=2
-CONFIG_PREEMPT=y
-CONFIG_AEABI=y
CONFIG_HIGHMEM=y
CONFIG_ARM_APPENDED_DTB=y
CONFIG_ARM_ATAG_DTB_COMPAT=y
CONFIG_ARM_U8500_CPUIDLE=y
CONFIG_VFP=y
CONFIG_NEON=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_CMA=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_SMSC_PHY=y
CONFIG_CW1200=y
CONFIG_CW1200_WLAN_SDIO=y
-# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_EVDEV=y
# CONFIG_KEYBOARD_ATKBD is not set
CONFIG_KEYBOARD_GPIO=y
CONFIG_RMI4_I2C=y
CONFIG_RMI4_F11=y
# CONFIG_SERIO is not set
-CONFIG_VT_HW_CONSOLE_BINDING=y
# CONFIG_LEGACY_PTYS is not set
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
CONFIG_SPI_PL022=y
CONFIG_GPIO_STMPE=y
CONFIG_GPIO_TC3589X=y
+CONFIG_SENSORS_IIO_HWMON=y
CONFIG_THERMAL=y
CONFIG_CPU_THERMAL=y
CONFIG_WATCHDOG=y
CONFIG_MFD_TC3589X=y
CONFIG_REGULATOR_AB8500=y
CONFIG_REGULATOR_GPIO=y
+CONFIG_DRM=y
+CONFIG_DRM_PANEL_SAMSUNG_S6D16D0=y
+CONFIG_DRM_LIMA=y
+CONFIG_DRM_MCDE=y
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+CONFIG_BACKLIGHT_GENERIC=m
+CONFIG_LOGO=y
CONFIG_SOUND=y
CONFIG_SND=y
CONFIG_SND_SOC=y
CONFIG_USB=y
CONFIG_USB_MUSB_HDRC=y
CONFIG_USB_MUSB_UX500=y
+CONFIG_MUSB_PIO_ONLY=y
CONFIG_AB8500_USB=y
CONFIG_USB_GADGET=y
CONFIG_USB_ETH=m
CONFIG_RTC_DRV_PL031=y
CONFIG_DMADEVICES=y
CONFIG_STE_DMA40=y
+CONFIG_HWSPINLOCK=y
CONFIG_HSEM_U8500=y
CONFIG_IIO=y
CONFIG_IIO_SW_TRIGGER=y
CONFIG_ROOT_NFS=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
+CONFIG_CRYPTO_DEV_UX500=y
+CONFIG_CRYPTO_DEV_UX500_CRYP=y
+CONFIG_CRYPTO_DEV_UX500_HASH=y
+CONFIG_CRYPTO_DEV_UX500_DEBUG=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_FS=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
# CONFIG_SCHED_DEBUG is not set
-# CONFIG_DEBUG_PREEMPT is not set
# CONFIG_FTRACE is not set
CONFIG_DEBUG_USER=y
CONFIG_CORESIGHT=y
CONFIG_CORESIGHT_SINK_TPIU=y
CONFIG_CORESIGHT_SINK_ETBV10=y
CONFIG_CORESIGHT_SOURCE_ETM3X=y
-CONFIG_CRYPTO_DEV_UX500=y
-CONFIG_CRYPTO_DEV_UX500_CRYP=y
-CONFIG_CRYPTO_DEV_UX500_HASH=y
-CONFIG_CRYPTO_DEV_UX500_DEBUG=y
static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
- return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL;
+ if (IS_ENABLED(CONFIG_MMU) && !IS_ENABLED(CONFIG_ARM_LPAE))
+ return &arm_dma_ops;
+ return NULL;
}
#ifdef __arch_page_to_dma
if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
&& max_watchpoint_len >= 8)
break;
+ /* Else, fall through */
default:
return -EINVAL;
}
/* Allow halfword watchpoints and breakpoints. */
if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
break;
+ /* Else, fall through */
case 3:
/* Allow single byte watchpoint. */
if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
break;
+ /* Else, fall through */
default:
ret = -EINVAL;
goto out;
break;
case ARM_ENTRY_ASYNC_WATCHPOINT:
WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
+ /* Fall through */
case ARM_ENTRY_SYNC_WATCHPOINT:
watchpoint_handler(addr, fsr, regs);
break;
ARM_DBG_READ(c1, c1, 4, oslsr);
if (oslsr & ARM_OSLSR_OSLM0)
return true;
+ /* Else, fall through */
default:
return false;
}
switch (retval) {
case -ERESTART_RESTARTBLOCK:
restart -= 2;
+ /* Fall through */
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
}
static void reset_coproc_regs(struct kvm_vcpu *vcpu,
- const struct coproc_reg *table, size_t num)
+ const struct coproc_reg *table, size_t num,
+ unsigned long *bmap)
{
unsigned long i;
for (i = 0; i < num; i++)
- if (table[i].reset)
+ if (table[i].reset) {
+ int reg = table[i].reg;
+
table[i].reset(vcpu, &table[i]);
+ if (reg > 0 && reg < NR_CP15_REGS) {
+ set_bit(reg, bmap);
+ if (table[i].is_64bit)
+ set_bit(reg + 1, bmap);
+ }
+ }
}
static struct coproc_params decode_32bit_hsr(struct kvm_vcpu *vcpu)
{
size_t num;
const struct coproc_reg *table;
-
- /* Catch someone adding a register without putting in reset entry. */
- memset(vcpu->arch.ctxt.cp15, 0x42, sizeof(vcpu->arch.ctxt.cp15));
+ DECLARE_BITMAP(bmap, NR_CP15_REGS) = { 0, };
/* Generic chip reset first (so target could override). */
- reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs));
+ reset_coproc_regs(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs), bmap);
table = get_target_table(vcpu->arch.target, &num);
- reset_coproc_regs(vcpu, table, num);
+ reset_coproc_regs(vcpu, table, num, bmap);
for (num = 1; num < NR_CP15_REGS; num++)
- WARN(vcpu_cp15(vcpu, num) == 0x42424242,
+ WARN(!test_bit(num, bmap),
"Didn't reset vcpu_cp15(vcpu, %zi)", num);
}
1003: ldr r2, [sv_pc, #-4] @ if stmfd sp!, {args} exists,
ldr r3, .Ldsi+4 @ adjust saved 'pc' back one
- teq r3, r2, lsr #10 @ instruction
+ teq r3, r2, lsr #11 @ instruction
subne r0, sv_pc, #4 @ allow for mov
subeq r0, sv_pc, #8 @ allow for mov + stmia
#define DEEPSLEEP_SLEEPENABLE_BIT BIT(31)
.text
+ .arch armv5te
/*
* Move DaVinci into deep sleep state
*
* FALLTHROUGH: Ensure we don't try to overwrite our newly
* initialised state information on the first fault.
*/
+ /* Fall through */
case THREAD_NOTIFY_EXIT:
crunch_task_release(thread);
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-menu "NetX Implementations"
- depends on ARCH_NETX
-
-config MACH_NXDKN
- bool "Enable Hilscher nxdkn Eval Board support"
- help
- Board support for the Hilscher NetX Eval Board
-
-config MACH_NXDB500
- bool "Enable Hilscher nxdb500 Eval Board support"
- select ARM_AMBA
- help
- Board support for the Hilscher nxdb500 Eval Board
-
-config MACH_NXEB500HMI
- bool "Enable Hilscher nxeb500hmi Eval Board support"
- select ARM_AMBA
- help
- Board support for the Hilscher nxeb500hmi Eval Board
-
-endmenu
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# Makefile for the linux kernel.
-#
-
-# Object file lists.
-
-obj-y += time.o generic.o pfifo.o xc.o
-
-# Specific board support
-obj-$(CONFIG_MACH_NXDKN) += nxdkn.o
-obj-$(CONFIG_MACH_NXDB500) += nxdb500.o fb.o
-obj-$(CONFIG_MACH_NXEB500HMI) += nxeb500hmi.o fb.o
+++ /dev/null
-# SPDX-License-Identifier: GPL-2.0-only
- zreladdr-y += 0x80008000
-
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/fb.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/device.h>
-#include <linux/init.h>
-#include <linux/dma-mapping.h>
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-#include <linux/err.h>
-#include <linux/gfp.h>
-
-#include <asm/irq.h>
-
-#include <mach/netx-regs.h>
-#include <mach/hardware.h>
-
-static struct clcd_panel *netx_panel;
-
-void netx_clcd_enable(struct clcd_fb *fb)
-{
-}
-
-int netx_clcd_setup(struct clcd_fb *fb)
-{
- dma_addr_t dma;
-
- fb->panel = netx_panel;
-
- fb->fb.screen_base = dma_alloc_wc(&fb->dev->dev, 1024 * 1024, &dma,
- GFP_KERNEL);
- if (!fb->fb.screen_base) {
- printk(KERN_ERR "CLCD: unable to map framebuffer\n");
- return -ENOMEM;
- }
-
- fb->fb.fix.smem_start = dma;
- fb->fb.fix.smem_len = 1024*1024;
-
- return 0;
-}
-
-int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma)
-{
- return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base,
- fb->fb.fix.smem_start, fb->fb.fix.smem_len);
-}
-
-void netx_clcd_remove(struct clcd_fb *fb)
-{
- dma_free_wc(&fb->dev->dev, fb->fb.fix.smem_len, fb->fb.screen_base,
- fb->fb.fix.smem_start);
-}
-
-static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL);
-
-int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel)
-{
- netx_panel = panel;
- fb_device.dev.platform_data = board;
- return amba_device_register(&fb_device, &iomem_resource);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/fb.h
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-void netx_clcd_enable(struct clcd_fb *fb);
-int netx_clcd_setup(struct clcd_fb *fb);
-int netx_clcd_mmap(struct clcd_fb *fb, struct vm_area_struct *vma);
-void netx_clcd_remove(struct clcd_fb *fb);
-int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/generic.c
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/device.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/io.h>
-#include <linux/irqchip/arm-vic.h>
-#include <linux/reboot.h>
-#include <mach/hardware.h>
-#include <asm/mach/map.h>
-#include <mach/netx-regs.h>
-#include <asm/mach/irq.h>
-
-static struct map_desc netx_io_desc[] __initdata = {
- {
- .virtual = NETX_IO_VIRT,
- .pfn = __phys_to_pfn(NETX_IO_PHYS),
- .length = NETX_IO_SIZE,
- .type = MT_DEVICE
- }
-};
-
-void __init netx_map_io(void)
-{
- iotable_init(netx_io_desc, ARRAY_SIZE(netx_io_desc));
-}
-
-static struct resource netx_rtc_resources[] = {
- [0] = {
- .start = 0x00101200,
- .end = 0x00101220,
- .flags = IORESOURCE_MEM,
- },
-};
-
-static struct platform_device netx_rtc_device = {
- .name = "netx-rtc",
- .id = 0,
- .num_resources = ARRAY_SIZE(netx_rtc_resources),
- .resource = netx_rtc_resources,
-};
-
-static struct platform_device *devices[] __initdata = {
- &netx_rtc_device,
-};
-
-#if 0
-#define DEBUG_IRQ(fmt...) printk(fmt)
-#else
-#define DEBUG_IRQ(fmt...) while (0) {}
-#endif
-
-static void netx_hif_demux_handler(struct irq_desc *desc)
-{
- unsigned int irq = NETX_IRQ_HIF_CHAINED(0);
- unsigned int stat;
-
- stat = ((readl(NETX_DPMAS_INT_EN) &
- readl(NETX_DPMAS_INT_STAT)) >> 24) & 0x1f;
-
- while (stat) {
- if (stat & 1) {
- DEBUG_IRQ("handling irq %d\n", irq);
- generic_handle_irq(irq);
- }
- irq++;
- stat >>= 1;
- }
-}
-
-static int
-netx_hif_irq_type(struct irq_data *d, unsigned int type)
-{
- unsigned int val, irq;
-
- val = readl(NETX_DPMAS_IF_CONF1);
-
- irq = d->irq - NETX_IRQ_HIF_CHAINED(0);
-
- if (type & IRQ_TYPE_EDGE_RISING) {
- DEBUG_IRQ("rising edges\n");
- val |= (1 << 26) << irq;
- }
- if (type & IRQ_TYPE_EDGE_FALLING) {
- DEBUG_IRQ("falling edges\n");
- val &= ~((1 << 26) << irq);
- }
- if (type & IRQ_TYPE_LEVEL_LOW) {
- DEBUG_IRQ("low level\n");
- val &= ~((1 << 26) << irq);
- }
- if (type & IRQ_TYPE_LEVEL_HIGH) {
- DEBUG_IRQ("high level\n");
- val |= (1 << 26) << irq;
- }
-
- writel(val, NETX_DPMAS_IF_CONF1);
-
- return 0;
-}
-
-static void
-netx_hif_ack_irq(struct irq_data *d)
-{
- unsigned int val, irq;
-
- irq = d->irq - NETX_IRQ_HIF_CHAINED(0);
- writel((1 << 24) << irq, NETX_DPMAS_INT_STAT);
-
- val = readl(NETX_DPMAS_INT_EN);
- val &= ~((1 << 24) << irq);
- writel(val, NETX_DPMAS_INT_EN);
-
- DEBUG_IRQ("%s: irq %d\n", __func__, d->irq);
-}
-
-static void
-netx_hif_mask_irq(struct irq_data *d)
-{
- unsigned int val, irq;
-
- irq = d->irq - NETX_IRQ_HIF_CHAINED(0);
- val = readl(NETX_DPMAS_INT_EN);
- val &= ~((1 << 24) << irq);
- writel(val, NETX_DPMAS_INT_EN);
- DEBUG_IRQ("%s: irq %d\n", __func__, d->irq);
-}
-
-static void
-netx_hif_unmask_irq(struct irq_data *d)
-{
- unsigned int val, irq;
-
- irq = d->irq - NETX_IRQ_HIF_CHAINED(0);
- val = readl(NETX_DPMAS_INT_EN);
- val |= (1 << 24) << irq;
- writel(val, NETX_DPMAS_INT_EN);
- DEBUG_IRQ("%s: irq %d\n", __func__, d->irq);
-}
-
-static struct irq_chip netx_hif_chip = {
- .irq_ack = netx_hif_ack_irq,
- .irq_mask = netx_hif_mask_irq,
- .irq_unmask = netx_hif_unmask_irq,
- .irq_set_type = netx_hif_irq_type,
-};
-
-void __init netx_init_irq(void)
-{
- int irq;
-
- vic_init(io_p2v(NETX_PA_VIC), NETX_IRQ_VIC_START, ~0, 0);
-
- for (irq = NETX_IRQ_HIF_CHAINED(0); irq <= NETX_IRQ_HIF_LAST; irq++) {
- irq_set_chip_and_handler(irq, &netx_hif_chip,
- handle_level_irq);
- irq_clear_status_flags(irq, IRQ_NOREQUEST);
- }
-
- writel(NETX_DPMAS_INT_EN_GLB_EN, NETX_DPMAS_INT_EN);
- irq_set_chained_handler(NETX_IRQ_HIF, netx_hif_demux_handler);
-}
-
-static int __init netx_init(void)
-{
- return platform_add_devices(devices, ARRAY_SIZE(devices));
-}
-
-subsys_initcall(netx_init);
-
-void netx_restart(enum reboot_mode mode, const char *cmd)
-{
- writel(NETX_SYSTEM_RES_CR_FIRMW_RES_EN | NETX_SYSTEM_RES_CR_FIRMW_RES,
- NETX_SYSTEM_RES_CR);
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/generic.h
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/reboot.h>
-
-extern void __init netx_map_io(void);
-extern void __init netx_init_irq(void);
-extern void netx_restart(enum reboot_mode, const char *);
-
-extern void netx_timer_init(void);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/include/mach/hardware.h
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-#ifndef __ASM_ARCH_HARDWARE_H
-#define __ASM_ARCH_HARDWARE_H
-
-#define NETX_IO_PHYS 0x00100000
-#define NETX_IO_VIRT 0xe0000000
-#define NETX_IO_SIZE 0x00100000
-
-#define SRAM_INTERNAL_PHYS_0 0x00000
-#define SRAM_INTERNAL_PHYS_1 0x08000
-#define SRAM_INTERNAL_PHYS_2 0x10000
-#define SRAM_INTERNAL_PHYS_3 0x18000
-#define SRAM_INTERNAL_PHYS(no) ((no) * 0x8000)
-
-#define XPEC_MEM_SIZE 0x4000
-#define XMAC_MEM_SIZE 0x1000
-#define SRAM_MEM_SIZE 0x8000
-
-#define io_p2v(x) IOMEM((x) - NETX_IO_PHYS + NETX_IO_VIRT)
-#define io_v2p(x) ((x) - NETX_IO_VIRT + NETX_IO_PHYS)
-
-#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/include/mach/irqs.h
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#define NETX_IRQ_VIC_START 64
-#define NETX_IRQ_SOFTINT (NETX_IRQ_VIC_START + 0)
-#define NETX_IRQ_TIMER0 (NETX_IRQ_VIC_START + 1)
-#define NETX_IRQ_TIMER1 (NETX_IRQ_VIC_START + 2)
-#define NETX_IRQ_TIMER2 (NETX_IRQ_VIC_START + 3)
-#define NETX_IRQ_SYSTIME_NS (NETX_IRQ_VIC_START + 4)
-#define NETX_IRQ_SYSTIME_S (NETX_IRQ_VIC_START + 5)
-#define NETX_IRQ_GPIO_15 (NETX_IRQ_VIC_START + 6)
-#define NETX_IRQ_WATCHDOG (NETX_IRQ_VIC_START + 7)
-#define NETX_IRQ_UART0 (NETX_IRQ_VIC_START + 8)
-#define NETX_IRQ_UART1 (NETX_IRQ_VIC_START + 9)
-#define NETX_IRQ_UART2 (NETX_IRQ_VIC_START + 10)
-#define NETX_IRQ_USB (NETX_IRQ_VIC_START + 11)
-#define NETX_IRQ_SPI (NETX_IRQ_VIC_START + 12)
-#define NETX_IRQ_I2C (NETX_IRQ_VIC_START + 13)
-#define NETX_IRQ_LCD (NETX_IRQ_VIC_START + 14)
-#define NETX_IRQ_HIF (NETX_IRQ_VIC_START + 15)
-#define NETX_IRQ_GPIO_0_14 (NETX_IRQ_VIC_START + 16)
-#define NETX_IRQ_XPEC0 (NETX_IRQ_VIC_START + 17)
-#define NETX_IRQ_XPEC1 (NETX_IRQ_VIC_START + 18)
-#define NETX_IRQ_XPEC2 (NETX_IRQ_VIC_START + 19)
-#define NETX_IRQ_XPEC3 (NETX_IRQ_VIC_START + 20)
-#define NETX_IRQ_XPEC(no) (NETX_IRQ_VIC_START + 17 + (no))
-#define NETX_IRQ_MSYNC0 (NETX_IRQ_VIC_START + 21)
-#define NETX_IRQ_MSYNC1 (NETX_IRQ_VIC_START + 22)
-#define NETX_IRQ_MSYNC2 (NETX_IRQ_VIC_START + 23)
-#define NETX_IRQ_MSYNC3 (NETX_IRQ_VIC_START + 24)
-#define NETX_IRQ_IRQ_PHY (NETX_IRQ_VIC_START + 25)
-#define NETX_IRQ_ISO_AREA (NETX_IRQ_VIC_START + 26)
-/* int 27 is reserved */
-/* int 28 is reserved */
-#define NETX_IRQ_TIMER3 (NETX_IRQ_VIC_START + 29)
-#define NETX_IRQ_TIMER4 (NETX_IRQ_VIC_START + 30)
-/* int 31 is reserved */
-
-#define NETX_IRQS (NETX_IRQ_VIC_START + 32)
-
-/* for multiplexed irqs on gpio 0..14 */
-#define NETX_IRQ_GPIO(x) (NETX_IRQS + (x))
-#define NETX_IRQ_GPIO_LAST NETX_IRQ_GPIO(14)
-
-/* Host interface interrupts */
-#define NETX_IRQ_HIF_CHAINED(x) (NETX_IRQ_GPIO_LAST + 1 + (x))
-#define NETX_IRQ_HIF_PIO35 NETX_IRQ_HIF_CHAINED(0)
-#define NETX_IRQ_HIF_PIO36 NETX_IRQ_HIF_CHAINED(1)
-#define NETX_IRQ_HIF_PIO40 NETX_IRQ_HIF_CHAINED(2)
-#define NETX_IRQ_HIF_PIO47 NETX_IRQ_HIF_CHAINED(3)
-#define NETX_IRQ_HIF_PIO72 NETX_IRQ_HIF_CHAINED(4)
-#define NETX_IRQ_HIF_LAST NETX_IRQ_HIF_CHAINED(4)
-
-#define NR_IRQS (NETX_IRQ_HIF_LAST + 1)
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/include/mach/netx-regs.h
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#ifndef __ASM_ARCH_NETX_REGS_H
-#define __ASM_ARCH_NETX_REGS_H
-
-/* offsets relative to the beginning of the io space */
-#define NETX_OFS_SYSTEM 0x00000
-#define NETX_OFS_MEMCR 0x00100
-#define NETX_OFS_DPMAS 0x03000
-#define NETX_OFS_GPIO 0x00800
-#define NETX_OFS_PIO 0x00900
-#define NETX_OFS_UART0 0x00a00
-#define NETX_OFS_UART1 0x00a40
-#define NETX_OFS_UART2 0x00a80
-#define NETX_OF_MIIMU 0x00b00
-#define NETX_OFS_SPI 0x00c00
-#define NETX_OFS_I2C 0x00d00
-#define NETX_OFS_SYSTIME 0x01100
-#define NETX_OFS_RTC 0x01200
-#define NETX_OFS_EXTBUS 0x03600
-#define NETX_OFS_LCD 0x04000
-#define NETX_OFS_USB 0x20000
-#define NETX_OFS_XMAC0 0x60000
-#define NETX_OFS_XMAC1 0x61000
-#define NETX_OFS_XMAC2 0x62000
-#define NETX_OFS_XMAC3 0x63000
-#define NETX_OFS_XMAC(no) (0x60000 + (no) * 0x1000)
-#define NETX_OFS_PFIFO 0x64000
-#define NETX_OFS_XPEC0 0x70000
-#define NETX_OFS_XPEC1 0x74000
-#define NETX_OFS_XPEC2 0x78000
-#define NETX_OFS_XPEC3 0x7c000
-#define NETX_OFS_XPEC(no) (0x70000 + (no) * 0x4000)
-#define NETX_OFS_VIC 0xff000
-
-/* physical addresses */
-#define NETX_PA_SYSTEM (NETX_IO_PHYS + NETX_OFS_SYSTEM)
-#define NETX_PA_MEMCR (NETX_IO_PHYS + NETX_OFS_MEMCR)
-#define NETX_PA_DPMAS (NETX_IO_PHYS + NETX_OFS_DPMAS)
-#define NETX_PA_GPIO (NETX_IO_PHYS + NETX_OFS_GPIO)
-#define NETX_PA_PIO (NETX_IO_PHYS + NETX_OFS_PIO)
-#define NETX_PA_UART0 (NETX_IO_PHYS + NETX_OFS_UART0)
-#define NETX_PA_UART1 (NETX_IO_PHYS + NETX_OFS_UART1)
-#define NETX_PA_UART2 (NETX_IO_PHYS + NETX_OFS_UART2)
-#define NETX_PA_MIIMU (NETX_IO_PHYS + NETX_OF_MIIMU)
-#define NETX_PA_SPI (NETX_IO_PHYS + NETX_OFS_SPI)
-#define NETX_PA_I2C (NETX_IO_PHYS + NETX_OFS_I2C)
-#define NETX_PA_SYSTIME (NETX_IO_PHYS + NETX_OFS_SYSTIME)
-#define NETX_PA_RTC (NETX_IO_PHYS + NETX_OFS_RTC)
-#define NETX_PA_EXTBUS (NETX_IO_PHYS + NETX_OFS_EXTBUS)
-#define NETX_PA_LCD (NETX_IO_PHYS + NETX_OFS_LCD)
-#define NETX_PA_USB (NETX_IO_PHYS + NETX_OFS_USB)
-#define NETX_PA_XMAC0 (NETX_IO_PHYS + NETX_OFS_XMAC0)
-#define NETX_PA_XMAC1 (NETX_IO_PHYS + NETX_OFS_XMAC1)
-#define NETX_PA_XMAC2 (NETX_IO_PHYS + NETX_OFS_XMAC2)
-#define NETX_PA_XMAC3 (NETX_IO_PHYS + NETX_OFS_XMAC3)
-#define NETX_PA_XMAC(no) (NETX_IO_PHYS + NETX_OFS_XMAC(no))
-#define NETX_PA_PFIFO (NETX_IO_PHYS + NETX_OFS_PFIFO)
-#define NETX_PA_XPEC0 (NETX_IO_PHYS + NETX_OFS_XPEC0)
-#define NETX_PA_XPEC1 (NETX_IO_PHYS + NETX_OFS_XPEC1)
-#define NETX_PA_XPEC2 (NETX_IO_PHYS + NETX_OFS_XPEC2)
-#define NETX_PA_XPEC3 (NETX_IO_PHYS + NETX_OFS_XPEC3)
-#define NETX_PA_XPEC(no) (NETX_IO_PHYS + NETX_OFS_XPEC(no))
-#define NETX_PA_VIC (NETX_IO_PHYS + NETX_OFS_VIC)
-
-/* virtual addresses */
-#define NETX_VA_SYSTEM (NETX_IO_VIRT + NETX_OFS_SYSTEM)
-#define NETX_VA_MEMCR (NETX_IO_VIRT + NETX_OFS_MEMCR)
-#define NETX_VA_DPMAS (NETX_IO_VIRT + NETX_OFS_DPMAS)
-#define NETX_VA_GPIO (NETX_IO_VIRT + NETX_OFS_GPIO)
-#define NETX_VA_PIO (NETX_IO_VIRT + NETX_OFS_PIO)
-#define NETX_VA_UART0 (NETX_IO_VIRT + NETX_OFS_UART0)
-#define NETX_VA_UART1 (NETX_IO_VIRT + NETX_OFS_UART1)
-#define NETX_VA_UART2 (NETX_IO_VIRT + NETX_OFS_UART2)
-#define NETX_VA_MIIMU (NETX_IO_VIRT + NETX_OF_MIIMU)
-#define NETX_VA_SPI (NETX_IO_VIRT + NETX_OFS_SPI)
-#define NETX_VA_I2C (NETX_IO_VIRT + NETX_OFS_I2C)
-#define NETX_VA_SYSTIME (NETX_IO_VIRT + NETX_OFS_SYSTIME)
-#define NETX_VA_RTC (NETX_IO_VIRT + NETX_OFS_RTC)
-#define NETX_VA_EXTBUS (NETX_IO_VIRT + NETX_OFS_EXTBUS)
-#define NETX_VA_LCD (NETX_IO_VIRT + NETX_OFS_LCD)
-#define NETX_VA_USB (NETX_IO_VIRT + NETX_OFS_USB)
-#define NETX_VA_XMAC0 (NETX_IO_VIRT + NETX_OFS_XMAC0)
-#define NETX_VA_XMAC1 (NETX_IO_VIRT + NETX_OFS_XMAC1)
-#define NETX_VA_XMAC2 (NETX_IO_VIRT + NETX_OFS_XMAC2)
-#define NETX_VA_XMAC3 (NETX_IO_VIRT + NETX_OFS_XMAC3)
-#define NETX_VA_XMAC(no) (NETX_IO_VIRT + NETX_OFS_XMAC(no))
-#define NETX_VA_PFIFO (NETX_IO_VIRT + NETX_OFS_PFIFO)
-#define NETX_VA_XPEC0 (NETX_IO_VIRT + NETX_OFS_XPEC0)
-#define NETX_VA_XPEC1 (NETX_IO_VIRT + NETX_OFS_XPEC1)
-#define NETX_VA_XPEC2 (NETX_IO_VIRT + NETX_OFS_XPEC2)
-#define NETX_VA_XPEC3 (NETX_IO_VIRT + NETX_OFS_XPEC3)
-#define NETX_VA_XPEC(no) (NETX_IO_VIRT + NETX_OFS_XPEC(no))
-#define NETX_VA_VIC (NETX_IO_VIRT + NETX_OFS_VIC)
-
-/*********************************
- * System functions *
- *********************************/
-
-/* Registers */
-#define NETX_SYSTEM_REG(ofs) IOMEM(NETX_VA_SYSTEM + (ofs))
-#define NETX_SYSTEM_BOO_SR NETX_SYSTEM_REG(0x00)
-#define NETX_SYSTEM_IOC_CR NETX_SYSTEM_REG(0x04)
-#define NETX_SYSTEM_IOC_MR NETX_SYSTEM_REG(0x08)
-
-/* FIXME: Docs are not consistent */
-/* #define NETX_SYSTEM_RES_CR NETX_SYSTEM_REG(0x08) */
-#define NETX_SYSTEM_RES_CR NETX_SYSTEM_REG(0x0c)
-
-#define NETX_SYSTEM_PHY_CONTROL NETX_SYSTEM_REG(0x10)
-#define NETX_SYSTEM_REV NETX_SYSTEM_REG(0x34)
-#define NETX_SYSTEM_IOC_ACCESS_KEY NETX_SYSTEM_REG(0x70)
-#define NETX_SYSTEM_WDG_TR NETX_SYSTEM_REG(0x200)
-#define NETX_SYSTEM_WDG_CTR NETX_SYSTEM_REG(0x204)
-#define NETX_SYSTEM_WDG_IRQ_TIMEOUT NETX_SYSTEM_REG(0x208)
-#define NETX_SYSTEM_WDG_RES_TIMEOUT NETX_SYSTEM_REG(0x20c)
-
-/* Bits */
-#define NETX_SYSTEM_RES_CR_RSTIN (1<<0)
-#define NETX_SYSTEM_RES_CR_WDG_RES (1<<1)
-#define NETX_SYSTEM_RES_CR_HOST_RES (1<<2)
-#define NETX_SYSTEM_RES_CR_FIRMW_RES (1<<3)
-#define NETX_SYSTEM_RES_CR_XPEC0_RES (1<<4)
-#define NETX_SYSTEM_RES_CR_XPEC1_RES (1<<5)
-#define NETX_SYSTEM_RES_CR_XPEC2_RES (1<<6)
-#define NETX_SYSTEM_RES_CR_XPEC3_RES (1<<7)
-#define NETX_SYSTEM_RES_CR_DIS_XPEC0_RES (1<<16)
-#define NETX_SYSTEM_RES_CR_DIS_XPEC1_RES (1<<17)
-#define NETX_SYSTEM_RES_CR_DIS_XPEC2_RES (1<<18)
-#define NETX_SYSTEM_RES_CR_DIS_XPEC3_RES (1<<19)
-#define NETX_SYSTEM_RES_CR_FIRMW_FLG0 (1<<20)
-#define NETX_SYSTEM_RES_CR_FIRMW_FLG1 (1<<21)
-#define NETX_SYSTEM_RES_CR_FIRMW_FLG2 (1<<22)
-#define NETX_SYSTEM_RES_CR_FIRMW_FLG3 (1<<23)
-#define NETX_SYSTEM_RES_CR_FIRMW_RES_EN (1<<24)
-#define NETX_SYSTEM_RES_CR_RSTOUT (1<<25)
-#define NETX_SYSTEM_RES_CR_EN_RSTOUT (1<<26)
-
-#define PHY_CONTROL_RESET (1<<31)
-#define PHY_CONTROL_SIM_BYP (1<<30)
-#define PHY_CONTROL_CLK_XLATIN (1<<29)
-#define PHY_CONTROL_PHY1_EN (1<<21)
-#define PHY_CONTROL_PHY1_NP_MSG_CODE
-#define PHY_CONTROL_PHY1_AUTOMDIX (1<<17)
-#define PHY_CONTROL_PHY1_FIXMODE (1<<16)
-#define PHY_CONTROL_PHY1_MODE(mode) (((mode) & 0x7) << 13)
-#define PHY_CONTROL_PHY0_EN (1<<12)
-#define PHY_CONTROL_PHY0_NP_MSG_CODE
-#define PHY_CONTROL_PHY0_AUTOMDIX (1<<8)
-#define PHY_CONTROL_PHY0_FIXMODE (1<<7)
-#define PHY_CONTROL_PHY0_MODE(mode) (((mode) & 0x7) << 4)
-#define PHY_CONTROL_PHY_ADDRESS(adr) ((adr) & 0xf)
-
-#define PHY_MODE_10BASE_T_HALF 0
-#define PHY_MODE_10BASE_T_FULL 1
-#define PHY_MODE_100BASE_TX_FX_FULL 2
-#define PHY_MODE_100BASE_TX_FX_HALF 3
-#define PHY_MODE_100BASE_TX_HALF 4
-#define PHY_MODE_REPEATER 5
-#define PHY_MODE_POWER_DOWN 6
-#define PHY_MODE_ALL 7
-
-/* Bits */
-#define VECT_CNTL_ENABLE (1 << 5)
-
-/*******************************
- * GPIO and timer module *
- *******************************/
-
-/* Registers */
-#define NETX_GPIO_REG(ofs) IOMEM(NETX_VA_GPIO + (ofs))
-#define NETX_GPIO_CFG(gpio) NETX_GPIO_REG(0x0 + ((gpio)<<2))
-#define NETX_GPIO_THRESHOLD_CAPTURE(gpio) NETX_GPIO_REG(0x40 + ((gpio)<<2))
-#define NETX_GPIO_COUNTER_CTRL(counter) NETX_GPIO_REG(0x80 + ((counter)<<2))
-#define NETX_GPIO_COUNTER_MAX(counter) NETX_GPIO_REG(0x94 + ((counter)<<2))
-#define NETX_GPIO_COUNTER_CURRENT(counter) NETX_GPIO_REG(0xa8 + ((counter)<<2))
-#define NETX_GPIO_IRQ_ENABLE NETX_GPIO_REG(0xbc)
-#define NETX_GPIO_IRQ_DISABLE NETX_GPIO_REG(0xc0)
-#define NETX_GPIO_SYSTIME_NS_CMP NETX_GPIO_REG(0xc4)
-#define NETX_GPIO_LINE NETX_GPIO_REG(0xc8)
-#define NETX_GPIO_IRQ NETX_GPIO_REG(0xd0)
-
-/* Bits */
-#define NETX_GPIO_CFG_IOCFG_GP_INPUT (0x0)
-#define NETX_GPIO_CFG_IOCFG_GP_OUTPUT (0x1)
-#define NETX_GPIO_CFG_IOCFG_GP_UART (0x2)
-#define NETX_GPIO_CFG_INV (1<<2)
-#define NETX_GPIO_CFG_MODE_INPUT_READ (0<<3)
-#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_CONT_RISING (1<<3)
-#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_ONCE_RISING (2<<3)
-#define NETX_GPIO_CFG_MODE_INPUT_CAPTURE_HIGH_LEVEL (3<<3)
-#define NETX_GPIO_CFG_COUNT_REF_COUNTER0 (0<<5)
-#define NETX_GPIO_CFG_COUNT_REF_COUNTER1 (1<<5)
-#define NETX_GPIO_CFG_COUNT_REF_COUNTER2 (2<<5)
-#define NETX_GPIO_CFG_COUNT_REF_COUNTER3 (3<<5)
-#define NETX_GPIO_CFG_COUNT_REF_COUNTER4 (4<<5)
-#define NETX_GPIO_CFG_COUNT_REF_SYSTIME (7<<5)
-
-#define NETX_GPIO_COUNTER_CTRL_RUN (1<<0)
-#define NETX_GPIO_COUNTER_CTRL_SYM (1<<1)
-#define NETX_GPIO_COUNTER_CTRL_ONCE (1<<2)
-#define NETX_GPIO_COUNTER_CTRL_IRQ_EN (1<<3)
-#define NETX_GPIO_COUNTER_CTRL_CNT_EVENT (1<<4)
-#define NETX_GPIO_COUNTER_CTRL_RST_EN (1<<5)
-#define NETX_GPIO_COUNTER_CTRL_SEL_EVENT (1<<6)
-#define NETX_GPIO_COUNTER_CTRL_GPIO_REF /* FIXME */
-
-#define GPIO_BIT(gpio) (1<<(gpio))
-#define COUNTER_BIT(counter) ((1<<16)<<(counter))
-
-/*******************************
- * PIO *
- *******************************/
-
-/* Registers */
-#define NETX_PIO_REG(ofs) IOMEM(NETX_VA_PIO + (ofs))
-#define NETX_PIO_INPIO NETX_PIO_REG(0x0)
-#define NETX_PIO_OUTPIO NETX_PIO_REG(0x4)
-#define NETX_PIO_OEPIO NETX_PIO_REG(0x8)
-
-/*******************************
- * MII Unit *
- *******************************/
-
-/* Registers */
-#define NETX_MIIMU IOMEM(NETX_VA_MIIMU)
-
-/* Bits */
-#define MIIMU_SNRDY (1<<0)
-#define MIIMU_PREAMBLE (1<<1)
-#define MIIMU_OPMODE_WRITE (1<<2)
-#define MIIMU_MDC_PERIOD (1<<3)
-#define MIIMU_PHY_NRES (1<<4)
-#define MIIMU_RTA (1<<5)
-#define MIIMU_REGADDR(adr) (((adr) & 0x1f) << 6)
-#define MIIMU_PHYADDR(adr) (((adr) & 0x1f) << 11)
-#define MIIMU_DATA(data) (((data) & 0xffff) << 16)
-
-/*******************************
- * xmac / xpec *
- *******************************/
-
-/* XPEC register offsets relative to NETX_VA_XPEC(no) */
-#define NETX_XPEC_R0_OFS 0x00
-#define NETX_XPEC_R1_OFS 0x04
-#define NETX_XPEC_R2_OFS 0x08
-#define NETX_XPEC_R3_OFS 0x0c
-#define NETX_XPEC_R4_OFS 0x10
-#define NETX_XPEC_R5_OFS 0x14
-#define NETX_XPEC_R6_OFS 0x18
-#define NETX_XPEC_R7_OFS 0x1c
-#define NETX_XPEC_RANGE01_OFS 0x20
-#define NETX_XPEC_RANGE23_OFS 0x24
-#define NETX_XPEC_RANGE45_OFS 0x28
-#define NETX_XPEC_RANGE67_OFS 0x2c
-#define NETX_XPEC_PC_OFS 0x48
-#define NETX_XPEC_TIMER_OFS(timer) (0x30 + ((timer)<<2))
-#define NETX_XPEC_IRQ_OFS 0x8c
-#define NETX_XPEC_SYSTIME_NS_OFS 0x90
-#define NETX_XPEC_FIFO_DATA_OFS 0x94
-#define NETX_XPEC_SYSTIME_S_OFS 0x98
-#define NETX_XPEC_ADC_OFS 0x9c
-#define NETX_XPEC_URX_COUNT_OFS 0x40
-#define NETX_XPEC_UTX_COUNT_OFS 0x44
-#define NETX_XPEC_PC_OFS 0x48
-#define NETX_XPEC_ZERO_OFS 0x4c
-#define NETX_XPEC_STATCFG_OFS 0x50
-#define NETX_XPEC_EC_MASKA_OFS 0x54
-#define NETX_XPEC_EC_MASKB_OFS 0x58
-#define NETX_XPEC_EC_MASK0_OFS 0x5c
-#define NETX_XPEC_EC_MASK8_OFS 0x7c
-#define NETX_XPEC_EC_MASK9_OFS 0x80
-#define NETX_XPEC_XPU_HOLD_PC_OFS 0x100
-#define NETX_XPEC_RAM_START_OFS 0x2000
-
-/* Bits */
-#define XPU_HOLD_PC (1<<0)
-
-/* XMAC register offsets relative to NETX_VA_XMAC(no) */
-#define NETX_XMAC_RPU_PROGRAM_START_OFS 0x000
-#define NETX_XMAC_RPU_PROGRAM_END_OFS 0x3ff
-#define NETX_XMAC_TPU_PROGRAM_START_OFS 0x400
-#define NETX_XMAC_TPU_PROGRAM_END_OFS 0x7ff
-#define NETX_XMAC_RPU_HOLD_PC_OFS 0xa00
-#define NETX_XMAC_TPU_HOLD_PC_OFS 0xa04
-#define NETX_XMAC_STATUS_SHARED0_OFS 0x840
-#define NETX_XMAC_CONFIG_SHARED0_OFS 0x844
-#define NETX_XMAC_STATUS_SHARED1_OFS 0x848
-#define NETX_XMAC_CONFIG_SHARED1_OFS 0x84c
-#define NETX_XMAC_STATUS_SHARED2_OFS 0x850
-#define NETX_XMAC_CONFIG_SHARED2_OFS 0x854
-#define NETX_XMAC_STATUS_SHARED3_OFS 0x858
-#define NETX_XMAC_CONFIG_SHARED3_OFS 0x85c
-
-#define RPU_HOLD_PC (1<<15)
-#define TPU_HOLD_PC (1<<15)
-
-/*******************************
- * Pointer FIFO *
- *******************************/
-
-/* Registers */
-#define NETX_PFIFO_REG(ofs) IOMEM(NETX_VA_PFIFO + (ofs))
-#define NETX_PFIFO_BASE(pfifo) NETX_PFIFO_REG(0x00 + ((pfifo)<<2))
-#define NETX_PFIFO_BORDER_BASE(pfifo) NETX_PFIFO_REG(0x80 + ((pfifo)<<2))
-#define NETX_PFIFO_RESET NETX_PFIFO_REG(0x100)
-#define NETX_PFIFO_FULL NETX_PFIFO_REG(0x104)
-#define NETX_PFIFO_EMPTY NETX_PFIFO_REG(0x108)
-#define NETX_PFIFO_OVEFLOW NETX_PFIFO_REG(0x10c)
-#define NETX_PFIFO_UNDERRUN NETX_PFIFO_REG(0x110)
-#define NETX_PFIFO_FILL_LEVEL(pfifo) NETX_PFIFO_REG(0x180 + ((pfifo)<<2))
-#define NETX_PFIFO_XPEC_ISR(xpec) NETX_PFIFO_REG(0x400 + ((xpec) << 2))
-
-
-/*******************************
- * Memory Controller *
- *******************************/
-
-/* Registers */
-#define NETX_MEMCR_REG(ofs) IOMEM(NETX_VA_MEMCR + (ofs))
-#define NETX_MEMCR_SRAM_CTRL(cs) NETX_MEMCR_REG(0x0 + 4 * (cs)) /* SRAM for CS 0..2 */
-#define NETX_MEMCR_SDRAM_CFG_CTRL NETX_MEMCR_REG(0x40)
-#define NETX_MEMCR_SDRAM_TIMING_CTRL NETX_MEMCR_REG(0x44)
-#define NETX_MEMCR_SDRAM_MODE NETX_MEMCR_REG(0x48)
-#define NETX_MEMCR_SDRAM_EXT_MODE NETX_MEMCR_REG(0x4c)
-#define NETX_MEMCR_PRIO_TIMESLOT_CTRL NETX_MEMCR_REG(0x80)
-#define NETX_MEMCR_PRIO_ACCESS_CTRL NETX_MEMCR_REG(0x84)
-
-/* Bits */
-#define NETX_MEMCR_SRAM_CTRL_WIDTHEXTMEM(x) (((x) & 0x3) << 24)
-#define NETX_MEMCR_SRAM_CTRL_WSPOSTPAUSEEXTMEM(x) (((x) & 0x3) << 16)
-#define NETX_MEMCR_SRAM_CTRL_WSPREPASEEXTMEM(x) (((x) & 0x3) << 8)
-#define NETX_MEMCR_SRAM_CTRL_WSEXTMEM(x) (((x) & 0x1f) << 0)
-
-
-/*******************************
- * Dual Port Memory *
- *******************************/
-
-/* Registers */
-#define NETX_DPMAS_REG(ofs) IOMEM(NETX_VA_DPMAS + (ofs))
-#define NETX_DPMAS_SYS_STAT NETX_DPMAS_REG(0x4d8)
-#define NETX_DPMAS_INT_STAT NETX_DPMAS_REG(0x4e0)
-#define NETX_DPMAS_INT_EN NETX_DPMAS_REG(0x4f0)
-#define NETX_DPMAS_IF_CONF0 NETX_DPMAS_REG(0x608)
-#define NETX_DPMAS_IF_CONF1 NETX_DPMAS_REG(0x60c)
-#define NETX_DPMAS_EXT_CONFIG(cs) NETX_DPMAS_REG(0x610 + 4 * (cs))
-#define NETX_DPMAS_IO_MODE0 NETX_DPMAS_REG(0x620) /* I/O 32..63 */
-#define NETX_DPMAS_DRV_EN0 NETX_DPMAS_REG(0x624)
-#define NETX_DPMAS_DATA0 NETX_DPMAS_REG(0x628)
-#define NETX_DPMAS_IO_MODE1 NETX_DPMAS_REG(0x630) /* I/O 64..84 */
-#define NETX_DPMAS_DRV_EN1 NETX_DPMAS_REG(0x634)
-#define NETX_DPMAS_DATA1 NETX_DPMAS_REG(0x638)
-
-/* Bits */
-#define NETX_DPMAS_INT_EN_GLB_EN (1<<31)
-#define NETX_DPMAS_INT_EN_MEM_LCK (1<<30)
-#define NETX_DPMAS_INT_EN_WDG (1<<29)
-#define NETX_DPMAS_INT_EN_PIO72 (1<<28)
-#define NETX_DPMAS_INT_EN_PIO47 (1<<27)
-#define NETX_DPMAS_INT_EN_PIO40 (1<<26)
-#define NETX_DPMAS_INT_EN_PIO36 (1<<25)
-#define NETX_DPMAS_INT_EN_PIO35 (1<<24)
-
-#define NETX_DPMAS_IF_CONF0_HIF_DISABLED (0<<28)
-#define NETX_DPMAS_IF_CONF0_HIF_EXT_BUS (1<<28)
-#define NETX_DPMAS_IF_CONF0_HIF_UP_8BIT (2<<28)
-#define NETX_DPMAS_IF_CONF0_HIF_UP_16BIT (3<<28)
-#define NETX_DPMAS_IF_CONF0_HIF_IO (4<<28)
-#define NETX_DPMAS_IF_CONF0_WAIT_DRV_PP (1<<14)
-#define NETX_DPMAS_IF_CONF0_WAIT_DRV_OD (2<<14)
-#define NETX_DPMAS_IF_CONF0_WAIT_DRV_TRI (3<<14)
-
-#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO35 (1<<26)
-#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO36 (1<<27)
-#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO40 (1<<28)
-#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO47 (1<<29)
-#define NETX_DPMAS_IF_CONF1_IRQ_POL_PIO72 (1<<30)
-
-#define NETX_EXT_CONFIG_TALEWIDTH(x) (((x) & 0x7) << 29)
-#define NETX_EXT_CONFIG_TADRHOLD(x) (((x) & 0x7) << 26)
-#define NETX_EXT_CONFIG_TCSON(x) (((x) & 0x7) << 23)
-#define NETX_EXT_CONFIG_TRDON(x) (((x) & 0x7) << 20)
-#define NETX_EXT_CONFIG_TWRON(x) (((x) & 0x7) << 17)
-#define NETX_EXT_CONFIG_TWROFF(x) (((x) & 0x1f) << 12)
-#define NETX_EXT_CONFIG_TRDWRCYC(x) (((x) & 0x1f) << 7)
-#define NETX_EXT_CONFIG_WAIT_POL (1<<6)
-#define NETX_EXT_CONFIG_WAIT_EN (1<<5)
-#define NETX_EXT_CONFIG_NRD_MODE (1<<4)
-#define NETX_EXT_CONFIG_DS_MODE (1<<3)
-#define NETX_EXT_CONFIG_NWR_MODE (1<<2)
-#define NETX_EXT_CONFIG_16BIT (1<<1)
-#define NETX_EXT_CONFIG_CS_ENABLE (1<<0)
-
-#define NETX_DPMAS_IO_MODE0_WRL (1<<13)
-#define NETX_DPMAS_IO_MODE0_WAIT (1<<14)
-#define NETX_DPMAS_IO_MODE0_READY (1<<15)
-#define NETX_DPMAS_IO_MODE0_CS0 (1<<19)
-#define NETX_DPMAS_IO_MODE0_EXTRD (1<<20)
-
-#define NETX_DPMAS_IO_MODE1_CS2 (1<<15)
-#define NETX_DPMAS_IO_MODE1_CS1 (1<<16)
-#define NETX_DPMAS_IO_MODE1_SAMPLE_NPOR (0<<30)
-#define NETX_DPMAS_IO_MODE1_SAMPLE_100MHZ (1<<30)
-#define NETX_DPMAS_IO_MODE1_SAMPLE_NPIO36 (2<<30)
-#define NETX_DPMAS_IO_MODE1_SAMPLE_PIO36 (3<<30)
-
-/*******************************
- * I2C *
- *******************************/
-#define NETX_I2C_REG(ofs) IOMEM(NETX_VA_I2C, (ofs))
-#define NETX_I2C_CTRL NETX_I2C_REG(0x0)
-#define NETX_I2C_DATA NETX_I2C_REG(0x4)
-
-#endif /* __ASM_ARCH_NETX_REGS_H */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/include/mach/pfifo.h
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-
-#ifndef ASM_ARCH_PFIFO_H
-#define ASM_ARCH_PFIFO_H
-
-static inline int pfifo_push(int no, unsigned int pointer)
-{
- writel(pointer, NETX_PFIFO_BASE(no));
- return 0;
-}
-
-static inline unsigned int pfifo_pop(int no)
-{
- return readl(NETX_PFIFO_BASE(no));
-}
-
-static inline int pfifo_fill_level(int no)
-{
-
- return readl(NETX_PFIFO_FILL_LEVEL(no));
-}
-
-static inline int pfifo_full(int no)
-{
- return readl(NETX_PFIFO_FULL) & (1<<no) ? 1 : 0;
-}
-
-static inline int pfifo_empty(int no)
-{
- return readl(NETX_PFIFO_EMPTY) & (1<<no) ? 1 : 0;
-}
-
-int pfifo_request(unsigned int pfifo_mask);
-void pfifo_free(unsigned int pfifo_mask);
-
-#endif /* ASM_ARCH_PFIFO_H */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/include/mach/uncompress.h
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-/*
- * The following code assumes the serial port has already been
- * initialized by the bootloader. We search for the first enabled
- * port in the most probable order. If you didn't setup a port in
- * your bootloader then nothing will appear (which might be desired).
- *
- * This does not append a newline
- */
-
-#define REG(x) (*(volatile unsigned long *)(x))
-
-#define UART1_BASE 0x100a00
-#define UART2_BASE 0x100a80
-
-#define UART_DR 0x0
-
-#define UART_CR 0x14
-#define CR_UART_EN (1<<0)
-
-#define UART_FR 0x18
-#define FR_BUSY (1<<3)
-#define FR_TXFF (1<<5)
-
-static inline void putc(char c)
-{
- unsigned long base;
-
- if (REG(UART1_BASE + UART_CR) & CR_UART_EN)
- base = UART1_BASE;
- else if (REG(UART2_BASE + UART_CR) & CR_UART_EN)
- base = UART2_BASE;
- else
- return;
-
- while (REG(base + UART_FR) & FR_TXFF);
- REG(base + UART_DR) = c;
-}
-
-static inline void flush(void)
-{
- unsigned long base;
-
- if (REG(UART1_BASE + UART_CR) & CR_UART_EN)
- base = UART1_BASE;
- else if (REG(UART2_BASE + UART_CR) & CR_UART_EN)
- base = UART2_BASE;
- else
- return;
-
- while (REG(base + UART_FR) & FR_BUSY);
-}
-
-/*
- * nothing to do
- */
-#define arch_decomp_setup()
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * arch/arm/mach-netx/include/mach/xc.h
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#ifndef __ASM_ARCH_XC_H
-#define __ASM_ARCH_XC_H
-
-struct xc {
- int no;
- unsigned int type;
- unsigned int version;
- void __iomem *xpec_base;
- void __iomem *xmac_base;
- void __iomem *sram_base;
- int irq;
- struct device *dev;
-};
-
-int xc_reset(struct xc *x);
-int xc_stop(struct xc* x);
-int xc_start(struct xc *x);
-int xc_running(struct xc *x);
-int xc_request_firmware(struct xc* x);
-struct xc* request_xc(int xcno, struct device *dev);
-void free_xc(struct xc *x);
-
-#endif /* __ASM_ARCH_XC_H */
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/nxdb500.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/mtd/plat-ram.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/netx-regs.h>
-#include <linux/platform_data/eth-netx.h>
-
-#include "generic.h"
-#include "fb.h"
-
-static struct clcd_panel qvga = {
- .mode = {
- .name = "QVGA",
- .refresh = 60,
- .xres = 240,
- .yres = 320,
- .pixclock = 187617,
- .left_margin = 6,
- .right_margin = 26,
- .upper_margin = 0,
- .lower_margin = 6,
- .hsync_len = 6,
- .vsync_len = 1,
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
- .width = -1,
- .height = -1,
- .tim2 = 16,
- .cntl = CNTL_LCDTFT | CNTL_BGR,
- .bpp = 16,
- .grayscale = 0,
-};
-
-static inline int nxdb500_check(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
- var->green.length = 5;
- var->green.msb_right = 0;
-
- return clcdfb_check(fb, var);
-}
-
-static int nxdb500_clcd_setup(struct clcd_fb *fb)
-{
- unsigned int val;
-
- fb->fb.var.green.length = 5;
- fb->fb.var.green.msb_right = 0;
-
- /* enable asic control */
- val = readl(NETX_SYSTEM_IOC_ACCESS_KEY);
- writel(val, NETX_SYSTEM_IOC_ACCESS_KEY);
-
- writel(3, NETX_SYSTEM_IOC_CR);
-
- val = readl(NETX_PIO_OUTPIO);
- writel(val | 1, NETX_PIO_OUTPIO);
-
- val = readl(NETX_PIO_OEPIO);
- writel(val | 1, NETX_PIO_OEPIO);
- return netx_clcd_setup(fb);
-}
-
-static struct clcd_board clcd_data = {
- .name = "netX",
- .check = nxdb500_check,
- .decode = clcdfb_decode,
- .enable = netx_clcd_enable,
- .setup = nxdb500_clcd_setup,
- .mmap = netx_clcd_mmap,
- .remove = netx_clcd_remove,
-};
-
-static struct netxeth_platform_data eth0_platform_data = {
- .xcno = 0,
-};
-
-static struct platform_device netx_eth0_device = {
- .name = "netx-eth",
- .id = 0,
- .num_resources = 0,
- .resource = NULL,
- .dev = {
- .platform_data = ð0_platform_data,
- }
-};
-
-static struct netxeth_platform_data eth1_platform_data = {
- .xcno = 1,
-};
-
-static struct platform_device netx_eth1_device = {
- .name = "netx-eth",
- .id = 1,
- .num_resources = 0,
- .resource = NULL,
- .dev = {
- .platform_data = ð1_platform_data,
- }
-};
-
-static struct resource netx_uart0_resources[] = {
- [0] = {
- .start = 0x00100A00,
- .end = 0x00100A3F,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = (NETX_IRQ_UART0),
- .end = (NETX_IRQ_UART0),
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device netx_uart0_device = {
- .name = "netx-uart",
- .id = 0,
- .num_resources = ARRAY_SIZE(netx_uart0_resources),
- .resource = netx_uart0_resources,
-};
-
-static struct resource netx_uart1_resources[] = {
- [0] = {
- .start = 0x00100A40,
- .end = 0x00100A7F,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = (NETX_IRQ_UART1),
- .end = (NETX_IRQ_UART1),
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device netx_uart1_device = {
- .name = "netx-uart",
- .id = 1,
- .num_resources = ARRAY_SIZE(netx_uart1_resources),
- .resource = netx_uart1_resources,
-};
-
-static struct resource netx_uart2_resources[] = {
- [0] = {
- .start = 0x00100A80,
- .end = 0x00100ABF,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = (NETX_IRQ_UART2),
- .end = (NETX_IRQ_UART2),
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device netx_uart2_device = {
- .name = "netx-uart",
- .id = 2,
- .num_resources = ARRAY_SIZE(netx_uart2_resources),
- .resource = netx_uart2_resources,
-};
-
-static struct platform_device *devices[] __initdata = {
- &netx_eth0_device,
- &netx_eth1_device,
- &netx_uart0_device,
- &netx_uart1_device,
- &netx_uart2_device,
-};
-
-static void __init nxdb500_init(void)
-{
- netx_fb_init(&clcd_data, &qvga);
- platform_add_devices(devices, ARRAY_SIZE(devices));
-}
-
-MACHINE_START(NXDB500, "Hilscher nxdb500")
- .atag_offset = 0x100,
- .map_io = netx_map_io,
- .init_irq = netx_init_irq,
- .init_time = netx_timer_init,
- .init_machine = nxdb500_init,
- .restart = netx_restart,
-MACHINE_END
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/nxdkn.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/mtd/plat-ram.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/netx-regs.h>
-#include <linux/platform_data/eth-netx.h>
-
-#include "generic.h"
-
-static struct netxeth_platform_data eth0_platform_data = {
- .xcno = 0,
-};
-
-static struct platform_device nxdkn_eth0_device = {
- .name = "netx-eth",
- .id = 0,
- .num_resources = 0,
- .resource = NULL,
- .dev = {
- .platform_data = ð0_platform_data,
- }
-};
-
-static struct netxeth_platform_data eth1_platform_data = {
- .xcno = 1,
-};
-
-static struct platform_device nxdkn_eth1_device = {
- .name = "netx-eth",
- .id = 1,
- .num_resources = 0,
- .resource = NULL,
- .dev = {
- .platform_data = ð1_platform_data,
- }
-};
-
-static struct resource netx_uart0_resources[] = {
- [0] = {
- .start = 0x00100A00,
- .end = 0x00100A3F,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = (NETX_IRQ_UART0),
- .end = (NETX_IRQ_UART0),
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device netx_uart0_device = {
- .name = "netx-uart",
- .id = 0,
- .num_resources = ARRAY_SIZE(netx_uart0_resources),
- .resource = netx_uart0_resources,
-};
-
-static struct platform_device *devices[] __initdata = {
- &nxdkn_eth0_device,
- &nxdkn_eth1_device,
- &netx_uart0_device,
-};
-
-static void __init nxdkn_init(void)
-{
- platform_add_devices(devices, ARRAY_SIZE(devices));
-}
-
-MACHINE_START(NXDKN, "Hilscher nxdkn")
- .atag_offset = 0x100,
- .map_io = netx_map_io,
- .init_irq = netx_init_irq,
- .init_time = netx_timer_init,
- .init_machine = nxdkn_init,
- .restart = netx_restart,
-MACHINE_END
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/nxeb500hmi.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/dma-mapping.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/mtd/plat-ram.h>
-#include <linux/platform_device.h>
-#include <linux/amba/bus.h>
-#include <linux/amba/clcd.h>
-
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
-#include <asm/mach/arch.h>
-#include <mach/netx-regs.h>
-#include <linux/platform_data/eth-netx.h>
-
-#include "generic.h"
-#include "fb.h"
-
-static struct clcd_panel qvga = {
- .mode = {
- .name = "QVGA",
- .refresh = 60,
- .xres = 240,
- .yres = 320,
- .pixclock = 187617,
- .left_margin = 6,
- .right_margin = 26,
- .upper_margin = 0,
- .lower_margin = 6,
- .hsync_len = 6,
- .vsync_len = 1,
- .sync = 0,
- .vmode = FB_VMODE_NONINTERLACED,
- },
- .width = -1,
- .height = -1,
- .tim2 = 16,
- .cntl = CNTL_LCDTFT | CNTL_BGR,
- .bpp = 16,
- .grayscale = 0,
-};
-
-static inline int nxeb500hmi_check(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
- var->green.length = 5;
- var->green.msb_right = 0;
-
- return clcdfb_check(fb, var);
-}
-
-static int nxeb500hmi_clcd_setup(struct clcd_fb *fb)
-{
- unsigned int val;
-
- fb->fb.var.green.length = 5;
- fb->fb.var.green.msb_right = 0;
-
- /* enable asic control */
- val = readl(NETX_SYSTEM_IOC_ACCESS_KEY);
- writel(val, NETX_SYSTEM_IOC_ACCESS_KEY);
-
- writel(3, NETX_SYSTEM_IOC_CR);
-
- /* GPIO 14 is used for display enable on newer boards */
- writel(9, NETX_GPIO_CFG(14));
-
- val = readl(NETX_PIO_OUTPIO);
- writel(val | 1, NETX_PIO_OUTPIO);
-
- val = readl(NETX_PIO_OEPIO);
- writel(val | 1, NETX_PIO_OEPIO);
- return netx_clcd_setup(fb);
-}
-
-static struct clcd_board clcd_data = {
- .name = "netX",
- .check = nxeb500hmi_check,
- .decode = clcdfb_decode,
- .enable = netx_clcd_enable,
- .setup = nxeb500hmi_clcd_setup,
- .mmap = netx_clcd_mmap,
- .remove = netx_clcd_remove,
-};
-
-static struct netxeth_platform_data eth0_platform_data = {
- .xcno = 0,
-};
-
-static struct platform_device netx_eth0_device = {
- .name = "netx-eth",
- .id = 0,
- .num_resources = 0,
- .resource = NULL,
- .dev = {
- .platform_data = ð0_platform_data,
- }
-};
-
-static struct netxeth_platform_data eth1_platform_data = {
- .xcno = 1,
-};
-
-static struct platform_device netx_eth1_device = {
- .name = "netx-eth",
- .id = 1,
- .num_resources = 0,
- .resource = NULL,
- .dev = {
- .platform_data = ð1_platform_data,
- }
-};
-
-static struct resource netx_cf_resources[] = {
- [0] = {
- .start = 0x20000000,
- .end = 0x25ffffff,
- .flags = IORESOURCE_MEM | IORESOURCE_MEM_8AND16BIT,
- },
-};
-
-static struct platform_device netx_cf_device = {
- .name = "netx-cf",
- .id = 0,
- .resource = netx_cf_resources,
- .num_resources = ARRAY_SIZE(netx_cf_resources),
-};
-
-static struct resource netx_uart0_resources[] = {
- [0] = {
- .start = 0x00100A00,
- .end = 0x00100A3F,
- .flags = IORESOURCE_MEM,
- },
- [1] = {
- .start = (NETX_IRQ_UART0),
- .end = (NETX_IRQ_UART0),
- .flags = IORESOURCE_IRQ,
- },
-};
-
-static struct platform_device netx_uart0_device = {
- .name = "netx-uart",
- .id = 0,
- .num_resources = ARRAY_SIZE(netx_uart0_resources),
- .resource = netx_uart0_resources,
-};
-
-static struct platform_device *devices[] __initdata = {
- &netx_eth0_device,
- &netx_eth1_device,
- &netx_cf_device,
- &netx_uart0_device,
-};
-
-static void __init nxeb500hmi_init(void)
-{
- netx_fb_init(&clcd_data, &qvga);
- platform_add_devices(devices, ARRAY_SIZE(devices));
-}
-
-MACHINE_START(NXEB500HMI, "Hilscher nxeb500hmi")
- .atag_offset = 0x100,
- .map_io = netx_map_io,
- .init_irq = netx_init_irq,
- .init_time = netx_timer_init,
- .init_machine = nxeb500hmi_init,
- .restart = netx_restart,
-MACHINE_END
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/pfifo.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/io.h>
-
-#include <mach/hardware.h>
-#include <mach/netx-regs.h>
-#include <mach/pfifo.h>
-
-static DEFINE_MUTEX(pfifo_lock);
-
-static unsigned int pfifo_used = 0;
-
-int pfifo_request(unsigned int pfifo_mask)
-{
- int err = 0;
- unsigned int val;
-
- mutex_lock(&pfifo_lock);
-
- if (pfifo_mask & pfifo_used) {
- err = -EBUSY;
- goto out;
- }
-
- pfifo_used |= pfifo_mask;
-
- val = readl(NETX_PFIFO_RESET);
- writel(val | pfifo_mask, NETX_PFIFO_RESET);
- writel(val, NETX_PFIFO_RESET);
-
-out:
- mutex_unlock(&pfifo_lock);
- return err;
-}
-
-void pfifo_free(unsigned int pfifo_mask)
-{
- mutex_lock(&pfifo_lock);
- pfifo_used &= ~pfifo_mask;
- mutex_unlock(&pfifo_lock);
-}
-
-EXPORT_SYMBOL(pfifo_push);
-EXPORT_SYMBOL(pfifo_pop);
-EXPORT_SYMBOL(pfifo_fill_level);
-EXPORT_SYMBOL(pfifo_empty);
-EXPORT_SYMBOL(pfifo_request);
-EXPORT_SYMBOL(pfifo_free);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/time.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/clocksource.h>
-#include <linux/clockchips.h>
-#include <linux/io.h>
-
-#include <mach/hardware.h>
-#include <asm/mach/time.h>
-#include <mach/netx-regs.h>
-
-#define NETX_CLOCK_FREQ 100000000
-#define NETX_LATCH DIV_ROUND_CLOSEST(NETX_CLOCK_FREQ, HZ)
-
-#define TIMER_CLOCKEVENT 0
-#define TIMER_CLOCKSOURCE 1
-
-static inline void timer_shutdown(struct clock_event_device *evt)
-{
- /* disable timer */
- writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT));
-}
-
-static int netx_shutdown(struct clock_event_device *evt)
-{
- timer_shutdown(evt);
-
- return 0;
-}
-
-static int netx_set_oneshot(struct clock_event_device *evt)
-{
- u32 tmode = NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN;
-
- timer_shutdown(evt);
- writel(0, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT));
- writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT));
-
- return 0;
-}
-
-static int netx_set_periodic(struct clock_event_device *evt)
-{
- u32 tmode = NETX_GPIO_COUNTER_CTRL_RST_EN |
- NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN;
-
- timer_shutdown(evt);
- writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKEVENT));
- writel(tmode, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKEVENT));
-
- return 0;
-}
-
-static int netx_set_next_event(unsigned long evt,
- struct clock_event_device *clk)
-{
- writel(0 - evt, NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKEVENT));
- return 0;
-}
-
-static struct clock_event_device netx_clockevent = {
- .name = "netx-timer" __stringify(TIMER_CLOCKEVENT),
- .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
- .set_next_event = netx_set_next_event,
- .set_state_shutdown = netx_shutdown,
- .set_state_periodic = netx_set_periodic,
- .set_state_oneshot = netx_set_oneshot,
- .tick_resume = netx_shutdown,
-};
-
-/*
- * IRQ handler for the timer
- */
-static irqreturn_t
-netx_timer_interrupt(int irq, void *dev_id)
-{
- struct clock_event_device *evt = &netx_clockevent;
-
- /* acknowledge interrupt */
- writel(COUNTER_BIT(0), NETX_GPIO_IRQ);
-
- evt->event_handler(evt);
-
- return IRQ_HANDLED;
-}
-
-static struct irqaction netx_timer_irq = {
- .name = "NetX Timer Tick",
- .flags = IRQF_TIMER | IRQF_IRQPOLL,
- .handler = netx_timer_interrupt,
-};
-
-/*
- * Set up timer interrupt
- */
-void __init netx_timer_init(void)
-{
- /* disable timer initially */
- writel(0, NETX_GPIO_COUNTER_CTRL(0));
-
- /* Reset the timer value to zero */
- writel(0, NETX_GPIO_COUNTER_CURRENT(0));
-
- writel(NETX_LATCH, NETX_GPIO_COUNTER_MAX(0));
-
- /* acknowledge interrupt */
- writel(COUNTER_BIT(0), NETX_GPIO_IRQ);
-
- /* Enable the interrupt in the specific timer
- * register and start timer
- */
- writel(COUNTER_BIT(0), NETX_GPIO_IRQ_ENABLE);
- writel(NETX_GPIO_COUNTER_CTRL_IRQ_EN | NETX_GPIO_COUNTER_CTRL_RUN,
- NETX_GPIO_COUNTER_CTRL(0));
-
- setup_irq(NETX_IRQ_TIMER0, &netx_timer_irq);
-
- /* Setup timer one for clocksource */
- writel(0, NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKSOURCE));
- writel(0, NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE));
- writel(0xffffffff, NETX_GPIO_COUNTER_MAX(TIMER_CLOCKSOURCE));
-
- writel(NETX_GPIO_COUNTER_CTRL_RUN,
- NETX_GPIO_COUNTER_CTRL(TIMER_CLOCKSOURCE));
-
- clocksource_mmio_init(NETX_GPIO_COUNTER_CURRENT(TIMER_CLOCKSOURCE),
- "netx_timer", NETX_CLOCK_FREQ, 200, 32, clocksource_mmio_readl_up);
-
- /* with max_delta_ns >= delta2ns(0x800) the system currently runs fine.
- * Adding some safety ... */
- netx_clockevent.cpumask = cpumask_of(0);
- clockevents_config_and_register(&netx_clockevent, NETX_CLOCK_FREQ,
- 0xa00, 0xfffffffe);
-}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mach-netx/xc.c
- *
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/firmware.h>
-#include <linux/mutex.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include <linux/export.h>
-
-#include <mach/hardware.h>
-#include <mach/irqs.h>
-#include <mach/netx-regs.h>
-
-#include <mach/xc.h>
-
-static DEFINE_MUTEX(xc_lock);
-
-static int xc_in_use = 0;
-
-struct fw_desc {
- unsigned int ofs;
- unsigned int size;
- unsigned int patch_ofs;
- unsigned int patch_entries;
-};
-
-struct fw_header {
- unsigned int magic;
- unsigned int type;
- unsigned int version;
- unsigned int reserved[5];
- struct fw_desc fw_desc[3];
-} __attribute__ ((packed));
-
-int xc_stop(struct xc *x)
-{
- writel(RPU_HOLD_PC, x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS);
- writel(TPU_HOLD_PC, x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS);
- writel(XPU_HOLD_PC, x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS);
- return 0;
-}
-
-int xc_start(struct xc *x)
-{
- writel(0, x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS);
- writel(0, x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS);
- writel(0, x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS);
- return 0;
-}
-
-int xc_running(struct xc *x)
-{
- return (readl(x->xmac_base + NETX_XMAC_RPU_HOLD_PC_OFS) & RPU_HOLD_PC)
- || (readl(x->xmac_base + NETX_XMAC_TPU_HOLD_PC_OFS) & TPU_HOLD_PC)
- || (readl(x->xpec_base + NETX_XPEC_XPU_HOLD_PC_OFS) & XPU_HOLD_PC) ?
- 0 : 1;
-}
-
-int xc_reset(struct xc *x)
-{
- writel(0, x->xpec_base + NETX_XPEC_PC_OFS);
- return 0;
-}
-
-static int xc_check_ptr(struct xc *x, unsigned long adr, unsigned int size)
-{
- if (adr >= NETX_PA_XMAC(x->no) &&
- adr + size < NETX_PA_XMAC(x->no) + XMAC_MEM_SIZE)
- return 0;
-
- if (adr >= NETX_PA_XPEC(x->no) &&
- adr + size < NETX_PA_XPEC(x->no) + XPEC_MEM_SIZE)
- return 0;
-
- dev_err(x->dev, "Illegal pointer in firmware found. aborting\n");
-
- return -1;
-}
-
-static int xc_patch(struct xc *x, const void *patch, int count)
-{
- unsigned int val, adr;
- const unsigned int *data = patch;
-
- int i;
- for (i = 0; i < count; i++) {
- adr = *data++;
- val = *data++;
- if (xc_check_ptr(x, adr, 4) < 0)
- return -EINVAL;
-
- writel(val, (void __iomem *)io_p2v(adr));
- }
- return 0;
-}
-
-int xc_request_firmware(struct xc *x)
-{
- int ret;
- char name[16];
- const struct firmware *fw;
- struct fw_header *head;
- unsigned int size;
- int i;
- const void *src;
- unsigned long dst;
-
- sprintf(name, "xc%d.bin", x->no);
-
- ret = request_firmware(&fw, name, x->dev);
-
- if (ret < 0) {
- dev_err(x->dev, "request_firmware failed\n");
- return ret;
- }
-
- head = (struct fw_header *)fw->data;
- if (head->magic != 0x4e657458) {
- if (head->magic == 0x5874654e) {
- dev_err(x->dev,
- "firmware magic is 'XteN'. Endianness problems?\n");
- ret = -ENODEV;
- goto exit_release_firmware;
- }
- dev_err(x->dev, "unrecognized firmware magic 0x%08x\n",
- head->magic);
- ret = -ENODEV;
- goto exit_release_firmware;
- }
-
- x->type = head->type;
- x->version = head->version;
-
- ret = -EINVAL;
-
- for (i = 0; i < 3; i++) {
- src = fw->data + head->fw_desc[i].ofs;
- dst = *(unsigned int *)src;
- src += sizeof (unsigned int);
- size = head->fw_desc[i].size - sizeof (unsigned int);
-
- if (xc_check_ptr(x, dst, size))
- goto exit_release_firmware;
-
- memcpy((void *)io_p2v(dst), src, size);
-
- src = fw->data + head->fw_desc[i].patch_ofs;
- size = head->fw_desc[i].patch_entries;
- ret = xc_patch(x, src, size);
- if (ret < 0)
- goto exit_release_firmware;
- }
-
- ret = 0;
-
- exit_release_firmware:
- release_firmware(fw);
-
- return ret;
-}
-
-struct xc *request_xc(int xcno, struct device *dev)
-{
- struct xc *x = NULL;
-
- mutex_lock(&xc_lock);
-
- if (xcno > 3)
- goto exit;
- if (xc_in_use & (1 << xcno))
- goto exit;
-
- x = kmalloc(sizeof (struct xc), GFP_KERNEL);
- if (!x)
- goto exit;
-
- if (!request_mem_region
- (NETX_PA_XPEC(xcno), XPEC_MEM_SIZE, kobject_name(&dev->kobj)))
- goto exit_free;
-
- if (!request_mem_region
- (NETX_PA_XMAC(xcno), XMAC_MEM_SIZE, kobject_name(&dev->kobj)))
- goto exit_release_1;
-
- if (!request_mem_region
- (SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE, kobject_name(&dev->kobj)))
- goto exit_release_2;
-
- x->xpec_base = (void * __iomem)io_p2v(NETX_PA_XPEC(xcno));
- x->xmac_base = (void * __iomem)io_p2v(NETX_PA_XMAC(xcno));
- x->sram_base = ioremap(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE);
- if (!x->sram_base)
- goto exit_release_3;
-
- x->irq = NETX_IRQ_XPEC(xcno);
-
- x->no = xcno;
- x->dev = dev;
-
- xc_in_use |= (1 << xcno);
-
- goto exit;
-
- exit_release_3:
- release_mem_region(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE);
- exit_release_2:
- release_mem_region(NETX_PA_XMAC(xcno), XMAC_MEM_SIZE);
- exit_release_1:
- release_mem_region(NETX_PA_XPEC(xcno), XPEC_MEM_SIZE);
- exit_free:
- kfree(x);
- x = NULL;
- exit:
- mutex_unlock(&xc_lock);
- return x;
-}
-
-void free_xc(struct xc *x)
-{
- int xcno = x->no;
-
- mutex_lock(&xc_lock);
-
- iounmap(x->sram_base);
- release_mem_region(SRAM_INTERNAL_PHYS(xcno), SRAM_MEM_SIZE);
- release_mem_region(NETX_PA_XMAC(xcno), XMAC_MEM_SIZE);
- release_mem_region(NETX_PA_XPEC(xcno), XPEC_MEM_SIZE);
- xc_in_use &= ~(1 << x->no);
- kfree(x);
-
- mutex_unlock(&xc_lock);
-}
-
-EXPORT_SYMBOL(free_xc);
-EXPORT_SYMBOL(request_xc);
-EXPORT_SYMBOL(xc_request_firmware);
-EXPORT_SYMBOL(xc_reset);
-EXPORT_SYMBOL(xc_running);
-EXPORT_SYMBOL(xc_start);
-EXPORT_SYMBOL(xc_stop);
orr r11, r11, r13 @ mask all requested interrupts
str r11, [r12, #OMAP1510_GPIO_INT_MASK]
+ str r13, [r12, #OMAP1510_GPIO_INT_STATUS] @ ack all requested interrupts
+
ands r10, r13, #KEYBRD_CLK_MASK @ extract keyboard status - set?
beq hksw @ no - try next source
@@@@@@@@@@@@@@@@@@@@@@
@ Keyboard clock FIQ mode interrupt handler
@ r10 now contains KEYBRD_CLK_MASK, use it
- str r10, [r12, #OMAP1510_GPIO_INT_STATUS] @ ack the interrupt
bic r11, r11, r10 @ unmask it
str r11, [r12, #OMAP1510_GPIO_INT_MASK]
* interrupts default to since commit 80ac93c27441
* requires interrupt already acked and unmasked.
*/
- if (irq_chip->irq_ack)
- irq_chip->irq_ack(d);
- if (irq_chip->irq_unmask)
+ if (!WARN_ON_ONCE(!irq_chip->irq_unmask))
irq_chip->irq_unmask(d);
}
for (; irq_counter[gpio] < fiq_count; irq_counter[gpio]++)
#define LATCH2_PIN_SCARD_CMDVCC 11
#define LATCH2_PIN_MODEM_NRESET 12
#define LATCH2_PIN_MODEM_CODEC 13
-#define LATCH2_PIN_AUDIO_MUTE 14
-#define LATCH2_PIN_HOOKFLASH 15
+#define LATCH2_PIN_HANDSFREE_MUTE 14
+#define LATCH2_PIN_HANDSET_MUTE 15
static struct regulator_consumer_supply modem_nreset_consumers[] = {
REGULATOR_SUPPLY("RESET#", "serial8250.1"),
"hook_switch", 0),
GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_MODEM_CODEC,
"modem_codec", 0),
+ GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_HANDSFREE_MUTE,
+ "handsfree_mute", 0),
+ GPIO_LOOKUP(LATCH2_LABEL, LATCH2_PIN_HANDSET_MUTE,
+ "handset_mute", 0),
{ },
},
};
static struct gpiod_hog ams_delta_gpio_hogs[] = {
GPIO_HOG(LATCH2_LABEL, LATCH2_PIN_KEYBRD_DATAOUT, "keybrd_dataout",
GPIO_ACTIVE_HIGH, GPIOD_OUT_LOW),
- GPIO_HOG(LATCH2_LABEL, LATCH2_PIN_AUDIO_MUTE, "audio_mute",
- GPIO_ACTIVE_HIGH, GPIOD_OUT_LOW),
{},
};
struct device_node *np;
struct gen_pool *sram_pool;
+ if (!soc_is_omap44xx() && !soc_is_omap54xx())
+ return 0;
+
np = of_find_compatible_node(NULL, NULL, "ti,omap4-mpu");
if (!np)
pr_warn("%s:Unable to allocate sram needed to handle errata I688\n",
static struct omap_hwmod_class_sysconfig dra7xx_epwmss_sysc = {
.rev_offs = 0x0,
.sysc_offs = 0x4,
- .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET,
+ .sysc_flags = SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+ SYSC_HAS_RESET_STATUS,
.idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
.sysc_fields = &omap_hwmod_sysc_type2,
};
switch (tag->u.acorn.vram_pages) {
case 512:
vram_size += PAGE_SIZE * 256;
+ /* Fall through - ??? */
case 256:
vram_size += PAGE_SIZE * 256;
default:
switch (err) {
case -ENOSYS:
tegra_cpu_reset_handler_set(reset_address);
- /* pass-through */
+ /* fall through */
case 0:
is_enabled = true;
break;
depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
!CPU_32v4 && !CPU_32v3
select PHYS_ADDR_T_64BIT
+ select SWIOTLB
help
Say Y if you have an ARMv7 processor supporting the LPAE page
table format and you would like to access memory beyond the
return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
(tinstr & 255); /* register_list */
}
- /* Else fall through for illegal instruction case */
+ /* Else, fall through - for illegal instruction case */
default:
return BAD_INSTR;
case 0xe8e0:
case 0xe9e0:
poffset->un = (tinst2 & 0xff) << 2;
+ /* Fall through */
+
case 0xe940:
case 0xe9c0:
return do_alignment_ldrdstrd;
#include <linux/init.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
#include <linux/dma-contiguous.h>
#include <linux/highmem.h>
#include <linux/memblock.h>
static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
{
+ /*
+ * When CONFIG_ARM_LPAE is set, physical address can extend above
+ * 32-bits, which then can't be addressed by devices that only support
+ * 32-bit DMA.
+ * Use the generic dma-direct / swiotlb ops code in that case, as that
+ * handles bounce buffering for us.
+ *
+ * Note: this checks CONFIG_ARM_LPAE instead of CONFIG_SWIOTLB as the
+ * latter is also selected by the Xen code, but that code for now relies
+ * on non-NULL dev_dma_ops. To be cleaned up later.
+ */
+ if (IS_ENABLED(CONFIG_ARM_LPAE))
+ return NULL;
return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
}
const struct dma_map_ops *dma_ops;
dev->archdata.dma_coherent = coherent;
+#ifdef CONFIG_SWIOTLB
+ dev->dma_coherent = coherent;
+#endif
/*
* Don't override the dma_ops if they have already been set. Ideally
/* Let arch_setup_dma_ops() start again from scratch upon re-probe */
set_dma_ops(dev, NULL);
}
+
+#ifdef CONFIG_SWIOTLB
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ __dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+ size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
+{
+ __dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+ size, dir);
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+ dma_addr_t dma_addr)
+{
+ return dma_to_pfn(dev, dma_addr);
+}
+
+pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
+ unsigned long attrs)
+{
+ return __get_dma_pgprot(attrs, prot);
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ return __dma_alloc(dev, size, dma_handle, gfp,
+ __get_dma_pgprot(attrs, PAGE_KERNEL), false,
+ attrs, __builtin_return_address(0));
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_handle, unsigned long attrs)
+{
+ __arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false);
+}
+#endif /* CONFIG_SWIOTLB */
#include <linux/dma-contiguous.h>
#include <linux/sizes.h>
#include <linux/stop_machine.h>
+#include <linux/swiotlb.h>
#include <asm/cp15.h>
#include <asm/mach-types.h>
#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
+ phys_addr_t addr = __pfn_to_phys(pfn);
+
+ if (__phys_to_pfn(addr) != pfn)
+ return 0;
+
return memblock_is_map_memory(__pfn_to_phys(pfn));
}
EXPORT_SYMBOL(pfn_valid);
*/
void __init mem_init(void)
{
+#ifdef CONFIG_ARM_LPAE
+ swiotlb_init(1);
+#endif
+
set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
/* this will put all unused low memory onto the freelists */
if (t->flags & PF_KTHREAD)
continue;
for_each_thread(t, s)
- set_section_perms(perms, n, true, s->mm);
+ if (s->mm)
+ set_section_perms(perms, n, true, s->mm);
}
set_section_perms(perms, n, true, current->active_mm);
set_section_perms(perms, n, true, &init_mm);
/*
* not supported by current hardware on OMAP1
* w |= (0x03 << 7);
- * fall through
*/
+ /* fall through */
case OMAP_DMA_DATA_BURST_16:
if (dma_omap2plus()) {
burst = 0x3;
break;
}
- /*
- * OMAP1 don't support burst 16
- * fall through
- */
+ /* OMAP1 don't support burst 16 */
+ /* fall through */
default:
BUG();
}
burst = 0x3;
break;
}
- /*
- * OMAP1 don't support burst 16
- * fall through
- */
+ /* OMAP1 don't support burst 16 */
+ /* fall through */
default:
printk(KERN_ERR "Invalid DMA burst mode\n");
BUG();
ifeq ($(CONFIG_CC_IS_CLANG), y)
$(warning CROSS_COMPILE_COMPAT is clang, the compat vDSO will not be built)
- else ifeq ($(CROSS_COMPILE_COMPAT),)
+ else ifeq ($(strip $(CROSS_COMPILE_COMPAT)),)
$(warning CROSS_COMPILE_COMPAT not defined or empty, the compat vDSO will not be built)
else ifeq ($(shell which $(CROSS_COMPILE_COMPAT)gcc 2> /dev/null),)
$(error $(CROSS_COMPILE_COMPAT)gcc not found, check CROSS_COMPILE_COMPAT)
pinctrl-names = "default";
};
+&ir {
+ status = "okay";
+ pinctrl-0 = <&remote_input_ao_pins>;
+ pinctrl-names = "default";
+};
+
&pwm_ef {
status = "okay";
pinctrl-0 = <&pwm_e_pins>;
clocks = <&clkc CLKID_USB1_DDR_BRIDGE>;
clock-names = "ddr";
phys = <&usb2_phy1>;
+ phy-names = "usb2-phy";
dr_mode = "peripheral";
g-rx-fifo-size = <192>;
g-np-tx-fifo-size = <128>;
gpio = <&gpio_ao GPIOAO_8 GPIO_ACTIVE_HIGH>;
enable-active-high;
+ regulator-always-on;
};
tf_io: gpio-regulator-tf_io {
#define MX8MM_IOMUXC_SAI3_RXFS_GPIO4_IO28 0x1CC 0x434 0x000 0x5 0x0
#define MX8MM_IOMUXC_SAI3_RXFS_TPSMP_HTRANS0 0x1CC 0x434 0x000 0x7 0x0
#define MX8MM_IOMUXC_SAI3_RXC_SAI3_RX_BCLK 0x1D0 0x438 0x000 0x0 0x0
-#define MX8MM_IOMUXC_SAI3_RXC_GPT1_CAPTURE2 0x1D0 0x438 0x000 0x1 0x0
+#define MX8MM_IOMUXC_SAI3_RXC_GPT1_CLK 0x1D0 0x438 0x000 0x1 0x0
#define MX8MM_IOMUXC_SAI3_RXC_SAI5_RX_BCLK 0x1D0 0x438 0x4D0 0x2 0x2
#define MX8MM_IOMUXC_SAI3_RXC_GPIO4_IO29 0x1D0 0x438 0x000 0x5 0x0
#define MX8MM_IOMUXC_SAI3_RXC_TPSMP_HTRANS1 0x1D0 0x438 0x000 0x7 0x0
#define MX8MM_IOMUXC_SAI3_RXD_GPIO4_IO30 0x1D4 0x43C 0x000 0x5 0x0
#define MX8MM_IOMUXC_SAI3_RXD_TPSMP_HDATA0 0x1D4 0x43C 0x000 0x7 0x0
#define MX8MM_IOMUXC_SAI3_TXFS_SAI3_TX_SYNC 0x1D8 0x440 0x000 0x0 0x0
-#define MX8MM_IOMUXC_SAI3_TXFS_GPT1_CLK 0x1D8 0x440 0x000 0x1 0x0
+#define MX8MM_IOMUXC_SAI3_TXFS_GPT1_CAPTURE2 0x1D8 0x440 0x000 0x1 0x0
#define MX8MM_IOMUXC_SAI3_TXFS_SAI5_RX_DATA1 0x1D8 0x440 0x4D8 0x2 0x2
#define MX8MM_IOMUXC_SAI3_TXFS_GPIO4_IO31 0x1D8 0x440 0x000 0x5 0x0
#define MX8MM_IOMUXC_SAI3_TXFS_TPSMP_HDATA1 0x1D8 0x440 0x000 0x7 0x0
sai2: sai@308b0000 {
#sound-dai-cells = <0>;
- compatible = "fsl,imx8mq-sai",
- "fsl,imx6sx-sai";
+ compatible = "fsl,imx8mq-sai";
reg = <0x308b0000 0x10000>;
interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MQ_CLK_SAI2_IPG>,
mmc-hs200-1_8v;
non-removable;
fixed-emmc-driver-type = <1>;
+ status = "okay";
};
&usb_extal_clk {
reg = <0x0 0x48000000 0x0 0x18000000>;
};
- reg_1p8v: regulator0 {
+ reg_1p8v: regulator-1p8v {
compatible = "regulator-fixed";
regulator-name = "fixed-1.8V";
regulator-min-microvolt = <1800000>;
regulator-always-on;
};
- reg_3p3v: regulator1 {
+ reg_3p3v: regulator-3p3v {
compatible = "regulator-fixed";
regulator-name = "fixed-3.3V";
regulator-min-microvolt = <3300000>;
regulator-always-on;
};
- reg_12p0v: regulator1 {
+ reg_12p0v: regulator-12p0v {
compatible = "regulator-fixed";
regulator-name = "D12.0V";
regulator-min-microvolt = <12000000>;
BUILD_BUG_ON(GICD_INT_DEF_PRI < (GIC_PRIO_IRQOFF |
GIC_PRIO_PSR_I_SET));
BUILD_BUG_ON(GICD_INT_DEF_PRI >= GIC_PRIO_IRQON);
+ /*
+ * Need to make sure IRQON allows IRQs when SCR_EL3.FIQ is cleared
+ * and non-secure PMR accesses are not subject to the shifts that
+ * are applied to IRQ priorities
+ */
+ BUILD_BUG_ON((0x80 | (GICD_INT_DEF_PRI >> 1)) >= GIC_PRIO_IRQON);
gic_write_pmr(GIC_PRIO_IRQOFF);
}
*/
enum ftr_type {
- FTR_EXACT, /* Use a predefined safe value */
- FTR_LOWER_SAFE, /* Smaller value is safe */
- FTR_HIGHER_SAFE,/* Bigger value is safe */
+ FTR_EXACT, /* Use a predefined safe value */
+ FTR_LOWER_SAFE, /* Smaller value is safe */
+ FTR_HIGHER_SAFE, /* Bigger value is safe */
+ FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */
};
#define FTR_STRICT true /* SANITY check strict matching required */
#define DAIF_PROCCTX 0
#define DAIF_PROCCTX_NOIRQ PSR_I_BIT
#define DAIF_ERRCTX (PSR_I_BIT | PSR_A_BIT)
+#define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
+
/* mask/save/unmask/restore all exceptions, including interrupts. */
static inline void local_daif_mask(void)
((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
#define alloc_screen_info(x...) &screen_info
-#define free_screen_info(x...)
+
+static inline void free_screen_info(efi_system_table_t *sys_table_arg,
+ struct screen_info *si)
+{
+}
/* redeclare as 'hidden' so the compiler will generate relative references */
extern struct screen_info screen_info __attribute__((__visibility__("hidden")));
({ \
set_thread_flag(TIF_32BIT); \
})
-#ifdef CONFIG_GENERIC_COMPAT_VDSO
+#ifdef CONFIG_COMPAT_VDSO
#define COMPAT_ARCH_DLINFO \
do { \
/* \
#define kvm_arm_exception_class \
ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \
- ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(CP14_64), ECN(SVC64), \
- ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(IMP_DEF), ECN(IABT_LOW), \
- ECN(IABT_CUR), ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \
+ ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(PAC), ECN(CP14_64), \
+ ECN(SVC64), ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(SVE), \
+ ECN(IMP_DEF), ECN(IABT_LOW), ECN(IABT_CUR), \
+ ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \
ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
#define __tag_reset(addr) untagged_addr(addr)
#define __tag_get(addr) (__u8)((u64)(addr) >> 56)
#else
-#define __tag_set(addr, tag) (addr)
+static inline const void *__tag_set(const void *addr, u8 tag)
+{
+ return addr;
+}
+
#define __tag_reset(addr) (addr)
#define __tag_get(addr) 0
#endif
#define page_to_virt(page) ({ \
unsigned long __addr = \
((__page_to_voff(page)) | PAGE_OFFSET); \
- unsigned long __addr_tag = \
- __tag_set(__addr, page_kasan_tag(page)); \
+ const void *__addr_tag = \
+ __tag_set((void *)__addr, page_kasan_tag(page)); \
((void *)__addr_tag); \
})
static inline pte_t pte_mkdevmap(pte_t pte)
{
- return set_pte_bit(pte, __pgprot(PTE_DEVMAP));
+ return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
}
static inline void set_pte(pte_t *ptep, pte_t pte)
/*
* Huge pte definitions.
*/
-#define pte_huge(pte) (!(pte_val(pte) & PTE_TABLE_BIT))
#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT))
/*
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd))
#endif
-#define pmd_mkdevmap(pmd) pte_pmd(pte_mkdevmap(pmd_pte(pmd)))
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+ return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP)));
+}
#define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd))
#define __phys_to_pmd_val(phys) __phys_to_pte_val(phys)
PMD_TYPE_SECT)
#if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3
-#define pud_sect(pud) (0)
-#define pud_table(pud) (1)
+static inline bool pud_sect(pud_t pud) { return false; }
+static inline bool pud_table(pud_t pud) { return true; }
#else
#define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \
PUD_TYPE_SECT)
regs->pmr_save = GIC_PRIO_IRQON;
}
+static inline void set_ssbs_bit(struct pt_regs *regs)
+{
+ regs->pstate |= PSR_SSBS_BIT;
+}
+
+static inline void set_compat_ssbs_bit(struct pt_regs *regs)
+{
+ regs->pstate |= PSR_AA32_SSBS_BIT;
+}
+
static inline void start_thread(struct pt_regs *regs, unsigned long pc,
unsigned long sp)
{
regs->pstate = PSR_MODE_EL0t;
if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
- regs->pstate |= PSR_SSBS_BIT;
+ set_ssbs_bit(regs);
regs->sp = sp;
}
#endif
if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
- regs->pstate |= PSR_AA32_SSBS_BIT;
+ set_compat_ssbs_bit(regs);
regs->compat_sp = sp;
}
* in the the priority mask, it indicates that PSR.I should be set and
* interrupt disabling temporarily does not rely on IRQ priorities.
*/
-#define GIC_PRIO_IRQON 0xc0
+#define GIC_PRIO_IRQON 0xe0
#define GIC_PRIO_IRQOFF (GIC_PRIO_IRQON & ~0x80)
#define GIC_PRIO_PSR_I_SET (1 << 4)
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
+#include <linux/types.h>
#include <asm/memory.h>
#include <asm/ptrace.h>
#include <asm/sdei.h>
-struct stackframe {
- unsigned long fp;
- unsigned long pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- int graph;
-#endif
-};
-
enum stack_type {
STACK_TYPE_UNKNOWN,
STACK_TYPE_TASK,
STACK_TYPE_OVERFLOW,
STACK_TYPE_SDEI_NORMAL,
STACK_TYPE_SDEI_CRITICAL,
+ __NR_STACK_TYPES
};
struct stack_info {
enum stack_type type;
};
+/*
+ * A snapshot of a frame record or fp/lr register values, along with some
+ * accounting information necessary for robust unwinding.
+ *
+ * @fp: The fp value in the frame record (or the real fp)
+ * @pc: The fp value in the frame record (or the real lr)
+ *
+ * @stacks_done: Stacks which have been entirely unwound, for which it is no
+ * longer valid to unwind to.
+ *
+ * @prev_fp: The fp that pointed to this frame record, or a synthetic value
+ * of 0. This is used to ensure that within a stack, each
+ * subsequent frame record is at an increasing address.
+ * @prev_type: The type of stack this frame record was on, or a synthetic
+ * value of STACK_TYPE_UNKNOWN. This is used to detect a
+ * transition from one stack to another.
+ *
+ * @graph: When FUNCTION_GRAPH_TRACER is selected, holds the index of a
+ * replacement lr value in the ftrace graph stack.
+ */
+struct stackframe {
+ unsigned long fp;
+ unsigned long pc;
+ DECLARE_BITMAP(stacks_done, __NR_STACK_TYPES);
+ unsigned long prev_fp;
+ enum stack_type prev_type;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ int graph;
+#endif
+};
+
extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data);
return true;
}
-static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp,
- struct stack_info *info)
+static inline bool on_task_stack(const struct task_struct *tsk,
+ unsigned long sp,
+ struct stack_info *info)
{
unsigned long low = (unsigned long)task_stack_page(tsk);
unsigned long high = low + THREAD_SIZE;
* We can only safely access per-cpu stacks from current in a non-preemptible
* context.
*/
-static inline bool on_accessible_stack(struct task_struct *tsk,
- unsigned long sp,
- struct stack_info *info)
+static inline bool on_accessible_stack(const struct task_struct *tsk,
+ unsigned long sp,
+ struct stack_info *info)
{
+ if (info)
+ info->type = STACK_TYPE_UNKNOWN;
+
if (on_task_stack(tsk, sp, info))
return true;
if (tsk != current || preemptible())
return false;
}
+static inline void start_backtrace(struct stackframe *frame,
+ unsigned long fp, unsigned long pc)
+{
+ frame->fp = fp;
+ frame->pc = pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ frame->graph = 0;
+#endif
+
+ /*
+ * Prime the first unwind.
+ *
+ * In unwind_frame() we'll check that the FP points to a valid stack,
+ * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be
+ * treated as a transition to whichever stack that happens to be. The
+ * prev_fp value won't be used, but we set it to 0 such that it is
+ * definitely not an accessible stack address.
+ */
+ bitmap_zero(frame->stacks_done, __NR_STACK_TYPES);
+ frame->prev_fp = 0;
+ frame->prev_type = STACK_TYPE_UNKNOWN;
+}
+
#endif /* __ASM_STACKTRACE_H */
#define VDSO_HAS_CLOCK_GETRES 1
+#define VDSO_HAS_32BIT_FALLBACK 1
+
static __always_inline
int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
struct timezone *_tz)
return ret;
}
+static __always_inline
+long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ register struct old_timespec32 *ts asm("r1") = _ts;
+ register clockid_t clkid asm("r0") = _clkid;
+ register long ret asm ("r0");
+ register long nr asm("r7") = __NR_compat_clock_gettime;
+
+ asm volatile(
+ " swi #0\n"
+ : "=r" (ret)
+ : "r" (clkid), "r" (ts), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
static __always_inline
int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
{
return ret;
}
+static __always_inline
+int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ register struct old_timespec32 *ts asm("r1") = _ts;
+ register clockid_t clkid asm("r0") = _clkid;
+ register long ret asm ("r0");
+ register long nr asm("r7") = __NR_compat_clock_getres;
+
+ /* The checks below are required for ABI consistency with arm */
+ if ((_clkid >= MAX_CLOCKS) && (_ts == NULL))
+ return -EINVAL;
+
+ asm volatile(
+ " swi #0\n"
+ : "=r" (ret)
+ : "r" (clkid), "r" (ts), "r" (nr)
+ : "memory");
+
+ return ret;
+}
+
static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
{
u64 res;
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
#define _UAPI__ASM_BPF_PERF_EVENT_H__
};
static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
- S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
- S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+ /*
+ * We already refuse to boot CPUs that don't support our configured
+ * page size, so we can only detect mismatches for a page size other
+ * than the one we're currently using. Unfortunately, SoCs like this
+ * exist in the wild so, even though we don't like it, we'll have to go
+ * along with it and treat them as non-strict.
+ */
+ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
+ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI),
+
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0),
/* Linux shouldn't care about secure memory */
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1),
/*
* Linux can handle differing I-cache policies. Userspace JITs will
case FTR_LOWER_SAFE:
ret = new < cur ? new : cur;
break;
+ case FTR_HIGHER_OR_ZERO_SAFE:
+ if (!cur || !new)
+ break;
+ /* Fallthrough */
case FTR_HIGHER_SAFE:
ret = new > cur ? new : cur;
break;
list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
- rcu_read_lock();
-
+ /*
+ * Since single-step exception disables interrupt, this function is
+ * entirely not preemptible, and we can use rcu list safely here.
+ */
list_for_each_entry_rcu(hook, list, node) {
retval = hook->fn(regs, esr);
if (retval == DBG_HOOK_HANDLED)
break;
}
- rcu_read_unlock();
-
return retval;
}
NOKPROBE_SYMBOL(call_step_hook);
list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
- rcu_read_lock();
+ /*
+ * Since brk exception disables interrupt, this function is
+ * entirely not preemptible, and we can use rcu list safely here.
+ */
list_for_each_entry_rcu(hook, list, node) {
unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
if ((comment & ~hook->mask) == hook->imm)
fn = hook->fn;
}
- rcu_read_unlock();
return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
}
b.eq el1_ia
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
b.eq el1_undef
- cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
- b.eq el1_sp_pc
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
- b.eq el1_sp_pc
+ b.eq el1_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1
b.eq el1_undef
cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1
bl do_mem_abort
kernel_exit 1
-el1_sp_pc:
+el1_pc:
/*
- * Stack or PC alignment exception handling
+ * PC alignment exception handling. We don't handle SP alignment faults,
+ * since we will have hit a recursive exception when trying to push the
+ * initial pt_regs.
*/
mrs x0, far_el1
inherit_daif pstate=x23, tmp=x2
ccmp x24, #ESR_ELx_EC_WFx, #4, ne
b.eq el0_sys
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
- b.eq el0_sp_pc
+ b.eq el0_sp
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
- b.eq el0_sp_pc
+ b.eq el0_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0
cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception
b.eq el0_fpsimd_exc
cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception
- b.eq el0_sp_pc
+ b.eq el0_pc
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap
mov x1, sp
bl do_fpsimd_exc
b ret_to_user
+el0_sp:
+ ldr x26, [sp, #S_SP]
+ b el0_sp_pc
+el0_pc:
+ mrs x26, far_el1
el0_sp_pc:
/*
* Stack or PC alignment exception handling
*/
- mrs x26, far_el1
gic_prio_kentry_setup tmp=x0
enable_da_f
#ifdef CONFIG_TRACE_IRQFLAGS
#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x)
+static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
+ unsigned int vq)
+{
+ unsigned int i;
+ __uint128_t *p;
+
+ for (i = 0; i < SVE_NUM_ZREGS; ++i) {
+ p = (__uint128_t *)ZREG(sst, vq, i);
+ *p = arm64_cpu_to_le128(fst->vregs[i]);
+ }
+}
+
/*
* Transfer the FPSIMD state in task->thread.uw.fpsimd_state to
* task->thread.sve_state.
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
- unsigned int i;
- __uint128_t *p;
if (!system_supports_sve())
return;
vq = sve_vq_from_vl(task->thread.sve_vl);
- for (i = 0; i < 32; ++i) {
- p = (__uint128_t *)ZREG(sst, vq, i);
- *p = arm64_cpu_to_le128(fst->vregs[i]);
- }
+ __fpsimd_to_sve(sst, fst, vq);
}
/*
return;
vq = sve_vq_from_vl(task->thread.sve_vl);
- for (i = 0; i < 32; ++i) {
+ for (i = 0; i < SVE_NUM_ZREGS; ++i) {
p = (__uint128_t const *)ZREG(sst, vq, i);
fst->vregs[i] = arm64_le128_to_cpu(*p);
}
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
- unsigned int i;
- __uint128_t *p;
if (!test_tsk_thread_flag(task, TIF_SVE))
return;
vq = sve_vq_from_vl(task->thread.sve_vl);
memset(sst, 0, SVE_SIG_REGS_SIZE(vq));
-
- for (i = 0; i < 32; ++i) {
- p = (__uint128_t *)ZREG(sst, vq, i);
- *p = arm64_cpu_to_le128(fst->vregs[i]);
- }
+ __fpsimd_to_sve(sst, fst, vq);
}
int sve_set_vector_length(struct task_struct *task,
if (offset < -SZ_128M || offset >= SZ_128M) {
#ifdef CONFIG_ARM64_MODULE_PLTS
- struct plt_entry trampoline;
+ struct plt_entry trampoline, *dst;
struct module *mod;
/*
* to check if the actual opcodes are in fact identical,
* regardless of the offset in memory so use memcmp() instead.
*/
- trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
- if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
- sizeof(trampoline))) {
- if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
+ dst = mod->arch.ftrace_trampoline;
+ trampoline = get_plt_entry(addr, dst);
+ if (memcmp(dst, &trampoline, sizeof(trampoline))) {
+ if (plt_entry_is_initialized(dst)) {
pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
return -EINVAL;
}
/* point the trampoline to our ftrace entry point */
module_disable_ro(mod);
- *mod->arch.ftrace_trampoline = trampoline;
+ *dst = trampoline;
module_enable_ro(mod, true);
- /* update trampoline before patching in the branch */
- smp_wmb();
+ /*
+ * Ensure updated trampoline is visible to instruction
+ * fetch before we patch in the branch.
+ */
+ __flush_icache_range((unsigned long)&dst[0],
+ (unsigned long)&dst[1]);
}
- addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
+ addr = (unsigned long)dst;
#else /* CONFIG_ARM64_MODULE_PLTS */
return -EINVAL;
#endif /* CONFIG_ARM64_MODULE_PLTS */
/* Aligned */
break;
case 1:
- /* Allow single byte watchpoint. */
- if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
- break;
case 2:
/* Allow halfword watchpoints and breakpoints. */
if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
break;
+
+ /* Fallthrough */
+ case 3:
+ /* Allow single byte watchpoint. */
+ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
+ break;
+
+ /* Fallthrough */
default:
return -EINVAL;
}
/* MOVW instruction relocations. */
case R_AARCH64_MOVW_UABS_G0_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_MOVW_UABS_G0:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0,
AARCH64_INSN_IMM_MOVKZ);
break;
case R_AARCH64_MOVW_UABS_G1_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_MOVW_UABS_G1:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16,
AARCH64_INSN_IMM_MOVKZ);
break;
case R_AARCH64_MOVW_UABS_G2_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_MOVW_UABS_G2:
ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32,
AARCH64_INSN_IMM_MOVKZ);
break;
case R_AARCH64_ADR_PREL_PG_HI21_NC:
overflow_check = false;
+ /* Fall through */
case R_AARCH64_ADR_PREL_PG_HI21:
ovf = reloc_insn_adrp(me, sechdrs, loc, val);
if (ovf && ovf != -ERANGE)
return;
}
- frame.fp = regs->regs[29];
- frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
-
+ start_backtrace(&frame, regs->regs[29], regs->pc);
walk_stackframe(current, &frame, callchain_trace, entry);
}
#include <asm/ptrace.h>
#include <asm/cacheflush.h>
#include <asm/debug-monitors.h>
+#include <asm/daifflags.h>
#include <asm/system_misc.h>
#include <asm/insn.h>
#include <linux/uaccess.h>
__this_cpu_write(current_kprobe, p);
}
-/*
- * When PSTATE.D is set (masked), then software step exceptions can not be
- * generated.
- * SPSR's D bit shows the value of PSTATE.D immediately before the
- * exception was taken. PSTATE.D is set while entering into any exception
- * mode, however software clears it for any normal (none-debug-exception)
- * mode in the exception entry. Therefore, when we are entering into kprobe
- * breakpoint handler from any normal mode then SPSR.D bit is already
- * cleared, however it is set when we are entering from any debug exception
- * mode.
- * Since we always need to generate single step exception after a kprobe
- * breakpoint exception therefore we need to clear it unconditionally, when
- * we become sure that the current breakpoint exception is for kprobe.
- */
-static void __kprobes
-spsr_set_debug_flag(struct pt_regs *regs, int mask)
-{
- unsigned long spsr = regs->pstate;
-
- if (mask)
- spsr |= PSR_D_BIT;
- else
- spsr &= ~PSR_D_BIT;
-
- regs->pstate = spsr;
-}
-
/*
* Interrupts need to be disabled before single-step mode is set, and not
* reenabled until after single-step mode ends.
static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
- kcb->saved_irqflag = regs->pstate;
+ kcb->saved_irqflag = regs->pstate & DAIF_MASK;
regs->pstate |= PSR_I_BIT;
+ /* Unmask PSTATE.D for enabling software step exceptions. */
+ regs->pstate &= ~PSR_D_BIT;
}
static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb,
struct pt_regs *regs)
{
- if (kcb->saved_irqflag & PSR_I_BIT)
- regs->pstate |= PSR_I_BIT;
- else
- regs->pstate &= ~PSR_I_BIT;
+ regs->pstate &= ~DAIF_MASK;
+ regs->pstate |= kcb->saved_irqflag;
}
static void __kprobes
set_ss_context(kcb, slot); /* mark pending ss */
- spsr_set_debug_flag(regs, 0);
-
/* IRQs and single stepping do not mix well. */
kprobes_save_local_irqflag(kcb, regs);
kernel_enable_single_step(regs);
childregs->pstate |= PSR_UAO_BIT;
if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
- childregs->pstate |= PSR_SSBS_BIT;
+ set_ssbs_bit(childregs);
if (system_uses_irq_prio_masking())
childregs->pmr_save = GIC_PRIO_IRQON;
}
}
+/*
+ * Force SSBS state on context-switch, since it may be lost after migrating
+ * from a CPU which treats the bit as RES0 in a heterogeneous system.
+ */
+static void ssbs_thread_switch(struct task_struct *next)
+{
+ struct pt_regs *regs = task_pt_regs(next);
+
+ /*
+ * Nothing to do for kernel threads, but 'regs' may be junk
+ * (e.g. idle task) so check the flags and bail early.
+ */
+ if (unlikely(next->flags & PF_KTHREAD))
+ return;
+
+ /* If the mitigation is enabled, then we leave SSBS clear. */
+ if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) ||
+ test_tsk_thread_flag(next, TIF_SSBD))
+ return;
+
+ if (compat_user_mode(regs))
+ set_compat_ssbs_bit(regs);
+ else if (user_mode(regs))
+ set_ssbs_bit(regs);
+}
+
/*
* We store our current task in sp_el0, which is clobbered by userspace. Keep a
* shadow copy so that we can restore this upon entry from userspace.
entry_task_switch(next);
uao_thread_switch(next);
ptrauth_thread_switch(next);
+ ssbs_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
if (!stack_page)
return 0;
- frame.fp = thread_saved_fp(p);
- frame.pc = thread_saved_pc(p);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
+ start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p));
+
do {
if (unwind_frame(p, &frame))
goto out;
#include <linux/export.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
return 0;
}
}
+NOKPROBE_SYMBOL(save_return_addr);
void *return_address(unsigned int level)
{
data.level = level + 2;
data.addr = NULL;
- frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.pc = (unsigned long)return_address; /* dummy */
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
-
+ start_backtrace(&frame,
+ (unsigned long)__builtin_frame_address(0),
+ (unsigned long)return_address);
walk_stackframe(current, &frame, save_return_addr, &data);
if (!data.level)
return NULL;
}
EXPORT_SYMBOL_GPL(return_address);
+NOKPROBE_SYMBOL(return_address);
pr_crit("CPU%u: died during early boot\n", cpu);
break;
}
- /* Fall through */
pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+ /* Fall through */
case CPU_STUCK_IN_KERNEL:
pr_crit("CPU%u: is stuck in kernel\n", cpu);
if (status & CPU_STUCK_REASON_52_BIT_VA)
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
* ldp x29, x30, [sp]
* add sp, sp, #0x10
*/
+
+/*
+ * Unwind from one frame record (A) to the next frame record (B).
+ *
+ * We terminate early if the location of B indicates a malformed chain of frame
+ * records (e.g. a cycle), determined based on the location and fp value of A
+ * and the location (but not the fp value) of B.
+ */
int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
{
unsigned long fp = frame->fp;
+ struct stack_info info;
if (fp & 0xf)
return -EINVAL;
if (!tsk)
tsk = current;
- if (!on_accessible_stack(tsk, fp, NULL))
+ if (!on_accessible_stack(tsk, fp, &info))
+ return -EINVAL;
+
+ if (test_bit(info.type, frame->stacks_done))
return -EINVAL;
+ /*
+ * As stacks grow downward, any valid record on the same stack must be
+ * at a strictly higher address than the prior record.
+ *
+ * Stacks can nest in several valid orders, e.g.
+ *
+ * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL
+ * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW
+ *
+ * ... but the nesting itself is strict. Once we transition from one
+ * stack to another, it's never valid to unwind back to that first
+ * stack.
+ */
+ if (info.type == frame->prev_type) {
+ if (fp <= frame->prev_fp)
+ return -EINVAL;
+ } else {
+ set_bit(frame->prev_type, frame->stacks_done);
+ }
+
+ /*
+ * Record this frame record's values and location. The prev_fp and
+ * prev_type are only meaningful to the next unwind_frame() invocation.
+ */
frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
+ frame->prev_fp = fp;
+ frame->prev_type = info.type;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
if (tsk->ret_stack &&
return 0;
}
+NOKPROBE_SYMBOL(unwind_frame);
void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data)
break;
}
}
+NOKPROBE_SYMBOL(walk_stackframe);
#ifdef CONFIG_STACKTRACE
struct stack_trace_data {
data.skip = trace->skip;
data.no_sched_functions = 0;
- frame.fp = regs->regs[29];
- frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
-
+ start_backtrace(&frame, regs->regs[29], regs->pc);
walk_stackframe(current, &frame, save_trace, &data);
}
EXPORT_SYMBOL_GPL(save_stack_trace_regs);
data.no_sched_functions = nosched;
if (tsk != current) {
- frame.fp = thread_saved_fp(tsk);
- frame.pc = thread_saved_pc(tsk);
+ start_backtrace(&frame, thread_saved_fp(tsk),
+ thread_saved_pc(tsk));
} else {
/* We don't want this function nor the caller */
data.skip += 2;
- frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.pc = (unsigned long)__save_stack_trace;
+ start_backtrace(&frame,
+ (unsigned long)__builtin_frame_address(0),
+ (unsigned long)__save_stack_trace);
}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
walk_stackframe(tsk, &frame, save_trace, &data);
if (!in_lock_functions(regs->pc))
return regs->pc;
- frame.fp = regs->regs[29];
- frame.pc = regs->pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
+ start_backtrace(&frame, regs->regs[29], regs->pc);
+
do {
int ret = unwind_frame(NULL, &frame);
if (ret < 0)
return;
if (tsk == current) {
- frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.pc = (unsigned long)dump_backtrace;
+ start_backtrace(&frame,
+ (unsigned long)__builtin_frame_address(0),
+ (unsigned long)dump_backtrace);
} else {
/*
* task blocked in __switch_to
*/
- frame.fp = thread_saved_fp(tsk);
- frame.pc = thread_saved_pc(tsk);
+ start_backtrace(&frame,
+ thread_saved_fp(tsk),
+ thread_saved_pc(tsk));
}
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame.graph = 0;
-#endif
printk("Call trace:\n");
do {
[ESR_ELx_EC_CP14_LS] = "CP14 LDC/STC",
[ESR_ELx_EC_FP_ASIMD] = "ASIMD",
[ESR_ELx_EC_CP10_ID] = "CP10 MRC/VMRS",
+ [ESR_ELx_EC_PAC] = "PAC",
[ESR_ELx_EC_CP14_64] = "CP14 MCRR/MRRC",
[ESR_ELx_EC_ILL] = "PSTATE.IL",
[ESR_ELx_EC_SVC32] = "SVC (AArch32)",
OBJECT_FILES_NON_STANDARD := y
KCOV_INSTRUMENT := n
-ifeq ($(c-gettimeofday-y),)
CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny
-else
-CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny -include $(c-gettimeofday-y)
+
+ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
endif
# Clang versions less than 8 do not support -mcmodel=tiny
# Link rule for the .so file, .lds has to be first
$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
- $(call if_changed,ld)
- $(call if_changed,vdso_check)
+ $(call if_changed,vdsold_and_vdso_check)
# Strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
$(call if_changed,vdsosym)
# Actual build commands
-quiet_cmd_vdsocc = VDSOCC $@
- cmd_vdsocc = $(CC) $(a_flags) $(c_flags) -c -o $@ $<
+quiet_cmd_vdsold_and_vdso_check = LD $@
+ cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check)
# Install commands for the unstripped file
quiet_cmd_vdso_install = INSTALL $@
# Link rule for the .so file, .lds has to be first
$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE
- $(call if_changed,vdsold)
- $(call if_changed,vdso_check)
+ $(call if_changed,vdsold_and_vdso_check)
# Compilation rules for the vDSO sources
$(c-obj-vdso): %.o: %.c FORCE
$(call if_changed_dep,vdsoas)
# Actual build commands
-quiet_cmd_vdsold = VDSOL $@
+quiet_cmd_vdsold_and_vdso_check = LD32 $@
+ cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
+
+quiet_cmd_vdsold = LD32 $@
cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
-Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
-quiet_cmd_vdsocc = VDSOC $@
+quiet_cmd_vdsocc = CC32 $@
cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
-quiet_cmd_vdsocc_gettimeofday = VDSOC_GTD $@
+quiet_cmd_vdsocc_gettimeofday = CC32 $@
cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
-quiet_cmd_vdsoas = VDSOA $@
+quiet_cmd_vdsoas = AS32 $@
cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
quiet_cmd_vdsomunge = MUNGE $@
#define save_debug(ptr,reg,nr) \
switch (nr) { \
case 15: ptr[15] = read_debug(reg, 15); \
+ /* Fall through */ \
case 14: ptr[14] = read_debug(reg, 14); \
+ /* Fall through */ \
case 13: ptr[13] = read_debug(reg, 13); \
+ /* Fall through */ \
case 12: ptr[12] = read_debug(reg, 12); \
+ /* Fall through */ \
case 11: ptr[11] = read_debug(reg, 11); \
+ /* Fall through */ \
case 10: ptr[10] = read_debug(reg, 10); \
+ /* Fall through */ \
case 9: ptr[9] = read_debug(reg, 9); \
+ /* Fall through */ \
case 8: ptr[8] = read_debug(reg, 8); \
+ /* Fall through */ \
case 7: ptr[7] = read_debug(reg, 7); \
+ /* Fall through */ \
case 6: ptr[6] = read_debug(reg, 6); \
+ /* Fall through */ \
case 5: ptr[5] = read_debug(reg, 5); \
+ /* Fall through */ \
case 4: ptr[4] = read_debug(reg, 4); \
+ /* Fall through */ \
case 3: ptr[3] = read_debug(reg, 3); \
+ /* Fall through */ \
case 2: ptr[2] = read_debug(reg, 2); \
+ /* Fall through */ \
case 1: ptr[1] = read_debug(reg, 1); \
+ /* Fall through */ \
default: ptr[0] = read_debug(reg, 0); \
}
#define restore_debug(ptr,reg,nr) \
switch (nr) { \
case 15: write_debug(ptr[15], reg, 15); \
+ /* Fall through */ \
case 14: write_debug(ptr[14], reg, 14); \
+ /* Fall through */ \
case 13: write_debug(ptr[13], reg, 13); \
+ /* Fall through */ \
case 12: write_debug(ptr[12], reg, 12); \
+ /* Fall through */ \
case 11: write_debug(ptr[11], reg, 11); \
+ /* Fall through */ \
case 10: write_debug(ptr[10], reg, 10); \
+ /* Fall through */ \
case 9: write_debug(ptr[9], reg, 9); \
+ /* Fall through */ \
case 8: write_debug(ptr[8], reg, 8); \
+ /* Fall through */ \
case 7: write_debug(ptr[7], reg, 7); \
+ /* Fall through */ \
case 6: write_debug(ptr[6], reg, 6); \
+ /* Fall through */ \
case 5: write_debug(ptr[5], reg, 5); \
+ /* Fall through */ \
case 4: write_debug(ptr[4], reg, 4); \
+ /* Fall through */ \
case 3: write_debug(ptr[3], reg, 3); \
+ /* Fall through */ \
case 2: write_debug(ptr[2], reg, 2); \
+ /* Fall through */ \
case 1: write_debug(ptr[1], reg, 1); \
+ /* Fall through */ \
default: write_debug(ptr[0], reg, 0); \
}
switch (spsr_idx) {
case KVM_SPSR_SVC:
write_sysreg_el1(v, SYS_SPSR);
+ break;
case KVM_SPSR_ABT:
write_sysreg(v, spsr_abt);
+ break;
case KVM_SPSR_UND:
write_sysreg(v, spsr_und);
+ break;
case KVM_SPSR_IRQ:
write_sysreg(v, spsr_irq);
+ break;
case KVM_SPSR_FIQ:
write_sysreg(v, spsr_fiq);
+ break;
}
}
*/
val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
| (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
- __vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+ __vcpu_sys_reg(vcpu, r->reg) = val;
}
static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
{ SYS_DESC(SYS_DBGBVRn_EL1(n)), \
- trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \
+ trap_bvr, reset_bvr, 0, 0, get_bvr, set_bvr }, \
{ SYS_DESC(SYS_DBGBCRn_EL1(n)), \
- trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \
+ trap_bcr, reset_bcr, 0, 0, get_bcr, set_bcr }, \
{ SYS_DESC(SYS_DBGWVRn_EL1(n)), \
- trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \
+ trap_wvr, reset_wvr, 0, 0, get_wvr, set_wvr }, \
{ SYS_DESC(SYS_DBGWCRn_EL1(n)), \
- trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr }
+ trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr }
/* Macro to expand the PMEVCNTRn_EL0 register */
#define PMU_PMEVCNTR_EL0(n) \
{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
{ SYS_DESC(SYS_CTR_EL0), access_ctr },
- { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, },
+ { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 },
{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
{ SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 },
{ SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 },
}
static void reset_sys_reg_descs(struct kvm_vcpu *vcpu,
- const struct sys_reg_desc *table, size_t num)
+ const struct sys_reg_desc *table, size_t num,
+ unsigned long *bmap)
{
unsigned long i;
for (i = 0; i < num; i++)
- if (table[i].reset)
+ if (table[i].reset) {
+ int reg = table[i].reg;
+
table[i].reset(vcpu, &table[i]);
+ if (reg > 0 && reg < NR_SYS_REGS)
+ set_bit(reg, bmap);
+ }
}
/**
{
size_t num;
const struct sys_reg_desc *table;
-
- /* Catch someone adding a register without putting in reset entry. */
- memset(&vcpu->arch.ctxt.sys_regs, 0x42, sizeof(vcpu->arch.ctxt.sys_regs));
+ DECLARE_BITMAP(bmap, NR_SYS_REGS) = { 0, };
/* Generic chip reset first (so target could override). */
- reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
+ reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs), bmap);
table = get_target_table(vcpu->arch.target, true, &num);
- reset_sys_reg_descs(vcpu, table, num);
+ reset_sys_reg_descs(vcpu, table, num, bmap);
for (num = 1; num < NR_SYS_REGS; num++) {
- if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242,
+ if (WARN(!test_bit(num, bmap),
"Didn't reset __vcpu_sys_reg(%zi)\n", num))
break;
}
pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
unsigned long attrs)
{
- if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE))
- return pgprot_writecombine(prot);
- return prot;
+ return pgprot_writecombine(prot);
}
void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
debug_fault_info[nr].name = name;
}
+/*
+ * In debug exception context, we explicitly disable preemption despite
+ * having interrupts disabled.
+ * This serves two purposes: it makes it much less likely that we would
+ * accidentally schedule in exception context and it will force a warning
+ * if we somehow manage to schedule by accident.
+ */
+static void debug_exception_enter(struct pt_regs *regs)
+{
+ /*
+ * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
+ * already disabled to preserve the last enabled/disabled addresses.
+ */
+ if (interrupts_enabled(regs))
+ trace_hardirqs_off();
+
+ if (user_mode(regs)) {
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+ } else {
+ /*
+ * We might have interrupted pretty much anything. In
+ * fact, if we're a debug exception, we can even interrupt
+ * NMI processing. We don't want this code makes in_nmi()
+ * to return true, but we need to notify RCU.
+ */
+ rcu_nmi_enter();
+ }
+
+ preempt_disable();
+
+ /* This code is a bit fragile. Test it. */
+ RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work");
+}
+NOKPROBE_SYMBOL(debug_exception_enter);
+
+static void debug_exception_exit(struct pt_regs *regs)
+{
+ preempt_enable_no_resched();
+
+ if (!user_mode(regs))
+ rcu_nmi_exit();
+
+ if (interrupts_enabled(regs))
+ trace_hardirqs_on();
+}
+NOKPROBE_SYMBOL(debug_exception_exit);
+
#ifdef CONFIG_ARM64_ERRATUM_1463225
DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa);
if (cortex_a76_erratum_1463225_debug_handler(regs))
return;
- /*
- * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
- * already disabled to preserve the last enabled/disabled addresses.
- */
- if (interrupts_enabled(regs))
- trace_hardirqs_off();
+ debug_exception_enter(regs);
if (user_mode(regs) && !is_ttbr0_addr(pc))
arm64_apply_bp_hardening();
inf->sig, inf->code, (void __user *)pc, esr);
}
- if (interrupts_enabled(regs))
- trace_hardirqs_on();
+ debug_exception_exit(regs);
}
NOKPROBE_SYMBOL(do_debug_exception);
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#ifndef __ASM_CSKY_BYTEORDER_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef __ASM_CSKY_CACHECTL_H
#define __ASM_CSKY_CACHECTL_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd.
#ifndef _ASM_CSKY_PERF_REGS_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#ifndef _CSKY_PTRACE_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#ifndef __ASM_CSKY_SIGCONTEXT_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#define __ARCH_WANT_SYS_CLONE
default:
dev_err(dev, "Invalid ref_clk %u, using 100000000 instead\n",
clock_rate);
+ /* fall through */
case 100000000:
mpll_mul = 0x19;
if (ref_clk_sel < 2)
case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
if (OCTEON_IS_MODEL(OCTEON_CN78XX_PASS1_X))
return 0x0000000000003CB0ull;
+ /* Else, fall through */
default:
return 0x0000000000023CB0ull;
}
if (c->tcache.waysize)
populate_cache(tcache, this_leaf, 3, CACHE_TYPE_UNIFIED);
+ this_cpu_ci->cpu_map_populated = true;
+
return 0;
}
static int __init init_pit_clocksource(void)
{
- if (num_possible_cpus() > 1) /* PIT does not scale! */
+ if (num_possible_cpus() > 1 || /* PIT does not scale! */
+ !clockevent_state_periodic(&i8253_clockevent))
return 0;
return clocksource_i8253_init();
/* These are unconditional and in j_format. */
case jal_op:
arch->gprs[31] = instpc + 8;
+ /* fall through */
case j_op:
epc += 4;
epc >>= 28;
return 0;
}
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return false;
-}
-
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
-{
- return 0;
-}
-
void kvm_mips_free_vcpus(struct kvm *kvm)
{
unsigned int i;
case 4:
w_c0_perfctrl3(0);
w_c0_perfcntr3(reg.counter[3]);
+ /* fall through */
case 3:
w_c0_perfctrl2(0);
w_c0_perfcntr2(reg.counter[2]);
+ /* fall through */
case 2:
w_c0_perfctrl1(0);
w_c0_perfcntr1(reg.counter[1]);
+ /* fall through */
case 1:
w_c0_perfctrl0(0);
w_c0_perfcntr0(reg.counter[0]);
switch (counters) {
case 4:
w_c0_perfctrl3(WHAT | reg.control[3]);
+ /* fall through */
case 3:
w_c0_perfctrl2(WHAT | reg.control[2]);
+ /* fall through */
case 2:
w_c0_perfctrl1(WHAT | reg.control[1]);
+ /* fall through */
case 1:
w_c0_perfctrl0(WHAT | reg.control[0]);
}
switch (counters) {
case 4:
w_c0_perfctrl3(0);
+ /* fall through */
case 3:
w_c0_perfctrl2(0);
+ /* fall through */
case 2:
w_c0_perfctrl1(0);
+ /* fall through */
case 1:
w_c0_perfctrl0(0);
}
switch (counters) {
#define HANDLE_COUNTER(n) \
+ /* fall through */ \
case n + 1: \
control = r_c0_perfctrl ## n(); \
counter = r_c0_perfcntr ## n(); \
case 4:
w_c0_perfctrl3(0);
w_c0_perfcntr3(0);
+ /* fall through */
case 3:
w_c0_perfctrl2(0);
w_c0_perfcntr2(0);
+ /* fall through */
case 2:
w_c0_perfctrl1(0);
w_c0_perfcntr1(0);
+ /* fall through */
case 1:
w_c0_perfctrl0(0);
w_c0_perfcntr0(0);
if (PCI_SLOT(devfn) == 0)
return bcm_pcie_readl(PCIE_DLSTATUS_REG)
& DLSTATUS_PHYLINKUP;
+ /* else, fall through */
default:
return false;
}
#if _MIPS_SIM != _MIPS_SIM_ABI64 && defined(CONFIG_64BIT)
/* Building 32-bit VDSO for the 64-bit kernel. Fake a 32-bit Kconfig. */
+#define BUILD_VDSO32_64
#undef CONFIG_64BIT
#define CONFIG_32BIT 1
#ifndef __ASSEMBLY__
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2005-2017 Andes Technology Corporation
#ifndef __ASM_AUXVEC_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2005-2017 Andes Technology Corporation
#ifndef __NDS32_BYTEORDER_H__
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 1994, 1995, 1996 by Ralf Baechle
// Copyright (C) 2005-2017 Andes Technology Corporation
#ifndef _ASM_CACHECTL
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/* Copyright (C) 2005-2019 Andes Technology Corporation */
#ifndef _FP_UDF_IEX_CRTL_H
#define _FP_UDF_IEX_CRTL_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2005-2017 Andes Technology Corporation
#ifndef __ASM_NDS32_PARAM_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2005-2017 Andes Technology Corporation
#ifndef __UAPI_ASM_NDS32_PTRACE_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2005-2017 Andes Technology Corporation
#ifndef _ASMNDS32_SIGCONTEXT_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
// Copyright (C) 2005-2017 Andes Technology Corporation
#define __ARCH_WANT_STAT64
regs->uregs[0] = -EINTR;
break;
}
+ /* Else, fall through */
case -ERESTARTNOINTR:
regs->uregs[0] = regs->orig_r0;
regs->ipc -= 4;
switch (regs->uregs[0]) {
case -ERESTART_RESTARTBLOCK:
regs->uregs[15] = __NR_restart_syscall;
+ /* Fall through */
case -ERESTARTNOHAND:
case -ERESTARTSYS:
case -ERESTARTNOINTR:
KBUILD_IMAGE := vmlinuz
-KBUILD_DEFCONFIG := default_defconfig
-
NM = sh $(srctree)/arch/parisc/nm
CHECKFLAGS += -D__hppa__=1
LIBGCC = $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
@echo ' zinstall - Install compressed vmlinuz kernel'
endef
+archclean:
+ $(Q)$(MAKE) $(clean)=$(boot)
+
archheaders:
$(Q)$(MAKE) $(build)=arch/parisc/kernel/syscalls all
targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
targets += misc.o piggy.o sizes.h head.o real2.o firmware.o
+targets += real2.S firmware.c
KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
CPPFLAGS_vmlinux.lds += -I$(objtree)/$(obj) -DBOOTLOADER
$(obj)/vmlinux.lds: $(obj)/sizes.h
-$(obj)/vmlinux.bin: vmlinux
+OBJCOPYFLAGS_vmlinux.bin := -R .comment -R .note -S
+$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
vmlinux.bin.all-y := $(obj)/vmlinux.bin
*(.rodata.compressed)
}
- /* bootloader code and data starts behind area of extracted kernel */
- . = (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START);
+ /* bootloader code and data starts at least behind area of extracted kernel */
+ . = MAX(ABSOLUTE(.), (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START));
/* align on next page boundary */
. = ALIGN(4096);
+++ /dev/null
-# CONFIG_LOCALVERSION_AUTO is not set
-CONFIG_SYSVIPC=y
-CONFIG_POSIX_MQUEUE=y
-CONFIG_IKCONFIG=y
-CONFIG_IKCONFIG_PROC=y
-CONFIG_LOG_BUF_SHIFT=16
-CONFIG_BLK_DEV_INITRD=y
-CONFIG_KALLSYMS_ALL=y
-CONFIG_SLAB=y
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-CONFIG_MODULE_FORCE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
-CONFIG_PA7100LC=y
-CONFIG_PREEMPT_VOLUNTARY=y
-CONFIG_IOMMU_CCIO=y
-CONFIG_GSC_LASI=y
-CONFIG_GSC_WAX=y
-CONFIG_EISA=y
-CONFIG_PCI=y
-CONFIG_GSC_DINO=y
-CONFIG_PCI_LBA=y
-CONFIG_PCCARD=y
-CONFIG_YENTA=y
-CONFIG_PD6729=y
-CONFIG_I82092=y
-CONFIG_BINFMT_MISC=m
-CONFIG_NET=y
-CONFIG_PACKET=y
-CONFIG_UNIX=y
-CONFIG_XFRM_USER=m
-CONFIG_NET_KEY=m
-CONFIG_INET=y
-CONFIG_IP_MULTICAST=y
-CONFIG_IP_PNP=y
-CONFIG_IP_PNP_DHCP=y
-CONFIG_IP_PNP_BOOTP=y
-CONFIG_INET_AH=m
-CONFIG_INET_ESP=m
-CONFIG_INET_DIAG=m
-CONFIG_INET6_AH=y
-CONFIG_INET6_ESP=y
-CONFIG_INET6_IPCOMP=y
-CONFIG_LLC2=m
-CONFIG_DEVTMPFS=y
-CONFIG_DEVTMPFS_MOUNT=y
-# CONFIG_STANDALONE is not set
-# CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_PARPORT=y
-CONFIG_PARPORT_PC=m
-CONFIG_PARPORT_PC_PCMCIA=m
-CONFIG_PARPORT_1284=y
-CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_CRYPTOLOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=6144
-CONFIG_IDE=y
-CONFIG_BLK_DEV_IDECS=y
-CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_NS87415=y
-CONFIG_SCSI=y
-CONFIG_BLK_DEV_SD=y
-CONFIG_CHR_DEV_ST=y
-CONFIG_BLK_DEV_SR=y
-CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_LASI700=y
-CONFIG_SCSI_SYM53C8XX_2=y
-CONFIG_SCSI_ZALON=y
-CONFIG_MD=y
-CONFIG_BLK_DEV_MD=y
-CONFIG_MD_LINEAR=y
-CONFIG_MD_RAID0=y
-CONFIG_MD_RAID1=y
-CONFIG_MD_RAID10=y
-CONFIG_BLK_DEV_DM=y
-CONFIG_NETDEVICES=y
-CONFIG_BONDING=m
-CONFIG_DUMMY=m
-CONFIG_TUN=m
-CONFIG_ACENIC=y
-CONFIG_TIGON3=y
-CONFIG_NET_TULIP=y
-CONFIG_TULIP=y
-CONFIG_LASI_82596=y
-CONFIG_PPP=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPPOE=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-# CONFIG_KEYBOARD_HIL_OLD is not set
-CONFIG_MOUSE_SERIAL=y
-CONFIG_LEGACY_PTY_COUNT=64
-CONFIG_SERIAL_8250=y
-CONFIG_SERIAL_8250_CONSOLE=y
-CONFIG_SERIAL_8250_CS=y
-CONFIG_SERIAL_8250_NR_UARTS=17
-CONFIG_SERIAL_8250_EXTENDED=y
-CONFIG_SERIAL_8250_MANY_PORTS=y
-CONFIG_SERIAL_8250_SHARE_IRQ=y
-CONFIG_PRINTER=m
-CONFIG_PPDEV=m
-# CONFIG_HW_RANDOM is not set
-# CONFIG_HWMON is not set
-CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_TILEBLITTING=y
-CONFIG_DUMMY_CONSOLE_COLUMNS=128
-CONFIG_DUMMY_CONSOLE_ROWS=48
-CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
-# CONFIG_LOGO_LINUX_CLUT224 is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_DYNAMIC_MINORS=y
-CONFIG_SND_SEQUENCER=y
-CONFIG_SND_AD1889=y
-CONFIG_SND_HARMONY=y
-CONFIG_HID_GYRATION=y
-CONFIG_HID_NTRIG=y
-CONFIG_HID_PANTHERLORD=y
-CONFIG_HID_PETALYNX=y
-CONFIG_HID_SAMSUNG=y
-CONFIG_HID_SUNPLUS=y
-CONFIG_HID_TOPSEED=y
-CONFIG_USB=y
-CONFIG_USB_MON=y
-CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_UHCI_HCD=y
-CONFIG_EXT2_FS=y
-CONFIG_EXT3_FS=y
-CONFIG_ISO9660_FS=y
-CONFIG_JOLIET=y
-CONFIG_VFAT_FS=y
-CONFIG_PROC_KCORE=y
-CONFIG_TMPFS=y
-CONFIG_NFS_FS=y
-CONFIG_ROOT_NFS=y
-CONFIG_NFSD=y
-CONFIG_NFSD_V4=y
-CONFIG_CIFS=m
-CONFIG_NLS_CODEPAGE_437=y
-CONFIG_NLS_CODEPAGE_737=m
-CONFIG_NLS_CODEPAGE_775=m
-CONFIG_NLS_CODEPAGE_850=m
-CONFIG_NLS_CODEPAGE_852=m
-CONFIG_NLS_CODEPAGE_855=m
-CONFIG_NLS_CODEPAGE_857=m
-CONFIG_NLS_CODEPAGE_860=m
-CONFIG_NLS_CODEPAGE_861=m
-CONFIG_NLS_CODEPAGE_862=m
-CONFIG_NLS_CODEPAGE_863=m
-CONFIG_NLS_CODEPAGE_864=m
-CONFIG_NLS_CODEPAGE_865=m
-CONFIG_NLS_CODEPAGE_866=m
-CONFIG_NLS_CODEPAGE_869=m
-CONFIG_NLS_CODEPAGE_936=m
-CONFIG_NLS_CODEPAGE_950=m
-CONFIG_NLS_CODEPAGE_932=m
-CONFIG_NLS_CODEPAGE_949=m
-CONFIG_NLS_CODEPAGE_874=m
-CONFIG_NLS_ISO8859_8=m
-CONFIG_NLS_CODEPAGE_1250=y
-CONFIG_NLS_CODEPAGE_1251=m
-CONFIG_NLS_ASCII=m
-CONFIG_NLS_ISO8859_1=y
-CONFIG_NLS_ISO8859_2=m
-CONFIG_NLS_ISO8859_3=m
-CONFIG_NLS_ISO8859_4=m
-CONFIG_NLS_ISO8859_5=m
-CONFIG_NLS_ISO8859_6=m
-CONFIG_NLS_ISO8859_7=m
-CONFIG_NLS_ISO8859_9=m
-CONFIG_NLS_ISO8859_13=m
-CONFIG_NLS_ISO8859_14=m
-CONFIG_NLS_ISO8859_15=m
-CONFIG_NLS_KOI8_R=m
-CONFIG_NLS_KOI8_U=m
-CONFIG_NLS_UTF8=y
-CONFIG_DEBUG_FS=y
-CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_KERNEL=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_KEYS=y
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-# CONFIG_CRYPTO_HW is not set
-CONFIG_LIBCRC32C=m
-CONFIG_FONTS=y
--- /dev/null
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_SLAB=y
+CONFIG_PROFILING=y
+CONFIG_OPROFILE=m
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_PA7100LC=y
+CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_IOMMU_CCIO=y
+CONFIG_GSC_LASI=y
+CONFIG_GSC_WAX=y
+CONFIG_EISA=y
+CONFIG_PCI=y
+CONFIG_GSC_DINO=y
+CONFIG_PCI_LBA=y
+CONFIG_PCCARD=y
+CONFIG_YENTA=y
+CONFIG_PD6729=y
+CONFIG_I82092=y
+CONFIG_BINFMT_MISC=m
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=m
+CONFIG_NET_KEY=m
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_INET_AH=m
+CONFIG_INET_ESP=m
+CONFIG_INET_DIAG=m
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_IPCOMP=y
+CONFIG_LLC2=m
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_PARPORT=y
+CONFIG_PARPORT_PC=m
+CONFIG_PARPORT_PC_PCMCIA=m
+CONFIG_PARPORT_1284=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_CRYPTOLOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=6144
+CONFIG_IDE=y
+CONFIG_BLK_DEV_IDECS=y
+CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_GENERIC=y
+CONFIG_BLK_DEV_NS87415=y
+CONFIG_SCSI=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_ST=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_LASI700=y
+CONFIG_SCSI_SYM53C8XX_2=y
+CONFIG_SCSI_ZALON=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_MD_LINEAR=y
+CONFIG_MD_RAID0=y
+CONFIG_MD_RAID1=y
+CONFIG_MD_RAID10=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_NETDEVICES=y
+CONFIG_BONDING=m
+CONFIG_DUMMY=m
+CONFIG_TUN=m
+CONFIG_ACENIC=y
+CONFIG_TIGON3=y
+CONFIG_NET_TULIP=y
+CONFIG_TULIP=y
+CONFIG_LASI_82596=y
+CONFIG_PPP=m
+CONFIG_PPP_BSDCOMP=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
+# CONFIG_KEYBOARD_HIL_OLD is not set
+CONFIG_MOUSE_SERIAL=y
+CONFIG_LEGACY_PTY_COUNT=64
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_CS=y
+CONFIG_SERIAL_8250_NR_UARTS=17
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_PRINTER=m
+CONFIG_PPDEV=m
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+CONFIG_FB=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_DUMMY_CONSOLE_COLUMNS=128
+CONFIG_DUMMY_CONSOLE_ROWS=48
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+# CONFIG_LOGO_LINUX_CLUT224 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_DYNAMIC_MINORS=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_AD1889=y
+CONFIG_SND_HARMONY=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_TOPSEED=y
+CONFIG_USB=y
+CONFIG_USB_MON=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_UHCI_HCD=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=y
+CONFIG_NFSD_V4=y
+CONFIG_CIFS=m
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_CODEPAGE_737=m
+CONFIG_NLS_CODEPAGE_775=m
+CONFIG_NLS_CODEPAGE_850=m
+CONFIG_NLS_CODEPAGE_852=m
+CONFIG_NLS_CODEPAGE_855=m
+CONFIG_NLS_CODEPAGE_857=m
+CONFIG_NLS_CODEPAGE_860=m
+CONFIG_NLS_CODEPAGE_861=m
+CONFIG_NLS_CODEPAGE_862=m
+CONFIG_NLS_CODEPAGE_863=m
+CONFIG_NLS_CODEPAGE_864=m
+CONFIG_NLS_CODEPAGE_865=m
+CONFIG_NLS_CODEPAGE_866=m
+CONFIG_NLS_CODEPAGE_869=m
+CONFIG_NLS_CODEPAGE_936=m
+CONFIG_NLS_CODEPAGE_950=m
+CONFIG_NLS_CODEPAGE_932=m
+CONFIG_NLS_CODEPAGE_949=m
+CONFIG_NLS_CODEPAGE_874=m
+CONFIG_NLS_ISO8859_8=m
+CONFIG_NLS_CODEPAGE_1250=y
+CONFIG_NLS_CODEPAGE_1251=m
+CONFIG_NLS_ASCII=m
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_ISO8859_2=m
+CONFIG_NLS_ISO8859_3=m
+CONFIG_NLS_ISO8859_4=m
+CONFIG_NLS_ISO8859_5=m
+CONFIG_NLS_ISO8859_6=m
+CONFIG_NLS_ISO8859_7=m
+CONFIG_NLS_ISO8859_9=m
+CONFIG_NLS_ISO8859_13=m
+CONFIG_NLS_ISO8859_14=m
+CONFIG_NLS_ISO8859_15=m
+CONFIG_NLS_KOI8_R=m
+CONFIG_NLS_KOI8_U=m
+CONFIG_NLS_UTF8=y
+CONFIG_DEBUG_FS=y
+CONFIG_HEADERS_INSTALL=y
+CONFIG_HEADERS_CHECK=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_KEYS=y
+CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_SHA512=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+# CONFIG_CRYPTO_HW is not set
+CONFIG_LIBCRC32C=m
+CONFIG_FONTS=y
int __kprobes parisc_kprobe_break_handler(struct pt_regs *regs);
int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs);
+static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+ return 0;
+}
#endif /* CONFIG_KPROBES */
#endif /* _PARISC_KPROBES_H */
#ifndef _PARISC_PGTABLE_H
#define _PARISC_PGTABLE_H
+#include <asm/page.h>
#include <asm-generic/4level-fixup.h>
#include <asm/fixmap.h>
#endif /* !__ASSEMBLY__ */
-#include <asm/page.h>
-
#define pte_ERROR(e) \
printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
#define pmd_ERROR(e) \
for (i = 0; i < ARRAY_SIZE(insn); i++)
insn[i] = INSN_NOP;
+ __patch_text((void *)rec->ip, INSN_NOP);
__patch_text_multiple((void *)rec->ip + 4 - sizeof(insn),
- insn, sizeof(insn));
+ insn, sizeof(insn)-4);
return 0;
}
#endif
/* Flush Instruction Tlb */
- LDREG ITLB_SID_BASE(%r1), %r20
+88: LDREG ITLB_SID_BASE(%r1), %r20
LDREG ITLB_SID_STRIDE(%r1), %r21
LDREG ITLB_SID_COUNT(%r1), %r22
LDREG ITLB_OFF_BASE(%r1), %arg0
add %r21, %r20, %r20 /* increment space */
fitdone:
+ ALTERNATIVE(88b, fitdone, ALT_COND_NO_SPLIT_TLB, INSN_NOP)
/* Flush Data Tlb */
# other very old or stripped-down PA-RISC CPUs -- not currently supported
obj-$(CONFIG_MATH_EMULATION) += unimplemented-math-emulation.o
+CFLAGS_REMOVE_fpudispatch.o = -Wimplicit-fallthrough
case 0x30000000: /* coproc2 */
if (bit22set(inst))
return VM_WRITE;
+ /* fall through */
case 0x0: /* indexed/memory management */
if (bit22set(inst)) {
static inline void dcbz(void *addr)
{
- __asm__ __volatile__ ("dcbz %y0" : : "Z"(*(u8 *)addr) : "memory");
+ __asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory");
}
static inline void dcbi(void *addr)
{
- __asm__ __volatile__ ("dcbi %y0" : : "Z"(*(u8 *)addr) : "memory");
+ __asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory");
}
static inline void dcbf(void *addr)
{
- __asm__ __volatile__ ("dcbf %y0" : : "Z"(*(u8 *)addr) : "memory");
+ __asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory");
}
static inline void dcbst(void *addr)
{
- __asm__ __volatile__ ("dcbst %y0" : : "Z"(*(u8 *)addr) : "memory");
+ __asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory");
}
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#define H_SCM_UNBIND_MEM 0x3F0
#define H_SCM_QUERY_BLOCK_MEM_BINDING 0x3F4
#define H_SCM_QUERY_LOGICAL_MEM_BINDING 0x3F8
-#define H_SCM_MEM_QUERY 0x3FC
-#define H_SCM_BLOCK_CLEAR 0x400
-#define MAX_HCALL_OPCODE H_SCM_BLOCK_CLEAR
+#define H_SCM_UNBIND_ALL 0x3FC
+#define H_SCM_HEALTH 0x400
+#define H_SCM_PERFORMANCE_STATS 0x418
+#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS
+
+/* Scope args for H_SCM_UNBIND_ALL */
+#define H_UNBIND_SCOPE_ALL (0x1)
+#define H_UNBIND_SCOPE_DRC (0x2)
/* H_VIOCTL functions */
#define H_GET_VIOA_DUMP_SIZE 0x01
#ifdef CONFIG_PPC_PSERIES
get_lppaca()->pmcregs_in_use = inuse;
#endif
- } else {
+ }
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
- get_paca()->pmcregs_in_use = inuse;
+ get_paca()->pmcregs_in_use = inuse;
#endif
- }
#endif
}
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_VFORK
#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_UNISTD_H_ */
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
#define _UAPI__ASM_BPF_PERF_EVENT_H__
* Struct fields are always 32 or 64 bit aligned, depending on them being 32
* or 64 bit wide respectively.
*
- * See Documentation/virtual/kvm/ppc-pv.txt
+ * See Documentation/virt/kvm/ppc-pv.txt
*/
struct kvm_vcpu_arch_shared {
__u64 scratch1;
ret |= __get_user_inatomic(temp.v[1], p++);
ret |= __get_user_inatomic(temp.v[2], p++);
ret |= __get_user_inatomic(temp.v[3], p++);
+ /* fall through */
case 4:
ret |= __get_user_inatomic(temp.v[4], p++);
ret |= __get_user_inatomic(temp.v[5], p++);
+ /* fall through */
case 2:
ret |= __get_user_inatomic(temp.v[6], p++);
ret |= __get_user_inatomic(temp.v[7], p++);
ret |= __put_user_inatomic(data.v[1], p++);
ret |= __put_user_inatomic(data.v[2], p++);
ret |= __put_user_inatomic(data.v[3], p++);
+ /* fall through */
case 4:
ret |= __put_user_inatomic(data.v[4], p++);
ret |= __put_user_inatomic(data.v[5], p++);
+ /* fall through */
case 2:
ret |= __put_user_inatomic(data.v[6], p++);
ret |= __put_user_inatomic(data.v[7], p++);
stw r0,_TRAP(r1) /* register set saved */
b sys_clone
+ .globl ppc_clone3
+ppc_clone3:
+ SAVE_NVGPRS(r1)
+ lwz r0,_TRAP(r1)
+ rlwinm r0,r0,0,0,30 /* clear LSB to indicate full */
+ stw r0,_TRAP(r1) /* register set saved */
+ b sys_clone3
+
.globl ppc_swapcontext
ppc_swapcontext:
SAVE_NVGPRS(r1)
bl sys_clone
b .Lsyscall_exit
+_GLOBAL(ppc_clone3)
+ bl save_nvgprs
+ bl sys_clone3
+ b .Lsyscall_exit
+
_GLOBAL(ppc32_swapcontext)
bl save_nvgprs
bl compat_sys_swapcontext
*
* Call convention:
*
- * syscall register convention is in Documentation/powerpc/syscall64-abi.txt
+ * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
*
* For hypercalls, the register convention is as follows:
* r0 volatile
}
}
-static bool tm_active_with_fp(struct task_struct *tsk)
-{
- return MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
- (tsk->thread.ckpt_regs.msr & MSR_FP);
-}
-
-static bool tm_active_with_altivec(struct task_struct *tsk)
-{
- return MSR_TM_ACTIVE(tsk->thread.regs->msr) &&
- (tsk->thread.ckpt_regs.msr & MSR_VEC);
-}
#else
static inline void check_if_tm_restore_required(struct task_struct *tsk) { }
-static inline bool tm_active_with_fp(struct task_struct *tsk) { return false; }
-static inline bool tm_active_with_altivec(struct task_struct *tsk) { return false; }
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
bool strict_msr_control;
static int restore_fp(struct task_struct *tsk)
{
- if (tsk->thread.load_fp || tm_active_with_fp(tsk)) {
+ if (tsk->thread.load_fp) {
load_fp_state(¤t->thread.fp_state);
current->thread.load_fp++;
return 1;
static int restore_altivec(struct task_struct *tsk)
{
- if (cpu_has_feature(CPU_FTR_ALTIVEC) &&
- (tsk->thread.load_vec || tm_active_with_altivec(tsk))) {
+ if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
load_vr_state(&tsk->thread.vr_state);
tsk->thread.used_vr = 1;
tsk->thread.load_vec++;
if (!tsk->thread.regs)
return;
+ check_if_tm_restore_required(tsk);
+
usermsr = tsk->thread.regs->msr;
if ((usermsr & msr_all_available) == 0)
return;
msr_check_and_set(msr_all_available);
- check_if_tm_restore_required(tsk);
WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC)));
goto bad;
if (MSR_TM_ACTIVE(msr_hi<<32)) {
+ /* Trying to start TM on non TM system */
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto bad;
/* We only recheckpoint on return if we're
* transaction.
*/
if (MSR_TM_ACTIVE(msr)) {
/* We recheckpoint on return. */
struct ucontext __user *uc_transact;
+
+ /* Trying to start TM on non TM system */
+ if (!cpu_has_feature(CPU_FTR_TM))
+ goto badframe;
+
if (__get_user(uc_transact, &uc->uc_link))
goto badframe;
if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
432 common fsmount sys_fsmount
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
-# 435 reserved for clone3
+435 nospu clone3 ppc_clone3
case 2:
case 6:
pte->may_write = true;
+ /* fall through */
case 3:
case 5:
case 7:
}
tce = be64_to_cpu(tce);
- if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua))
- return H_PARAMETER;
+ if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
+ ret = H_PARAMETER;
+ goto unlock_exit;
+ }
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
ret = kvmppc_tce_iommu_map(vcpu->kvm, stt,
unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
ua = 0;
- if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
- return H_PARAMETER;
+ if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+ ret = H_PARAMETER;
+ goto unlock_exit;
+ }
list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
ret = kvmppc_rm_tce_iommu_map(vcpu->kvm, stt,
mtspr(SPRN_DEC, vcpu->arch.dec_expires - mftb());
if (kvmhv_on_pseries()) {
+ /*
+ * We need to save and restore the guest visible part of the
+ * psscr (i.e. using SPRN_PSSCR_PR) since the hypervisor
+ * doesn't do this for us. Note only required if pseries since
+ * this is done in kvmhv_load_hv_regs_and_go() below otherwise.
+ */
+ unsigned long host_psscr;
/* call our hypervisor to load up HV regs and go */
struct hv_guest_state hvregs;
+ host_psscr = mfspr(SPRN_PSSCR_PR);
+ mtspr(SPRN_PSSCR_PR, vcpu->arch.psscr);
kvmhv_save_hv_regs(vcpu, &hvregs);
hvregs.lpcr = lpcr;
vcpu->arch.regs.msr = vcpu->arch.shregs.msr;
vcpu->arch.shregs.msr = vcpu->arch.regs.msr;
vcpu->arch.shregs.dar = mfspr(SPRN_DAR);
vcpu->arch.shregs.dsisr = mfspr(SPRN_DSISR);
+ vcpu->arch.psscr = mfspr(SPRN_PSSCR_PR);
+ mtspr(SPRN_PSSCR_PR, host_psscr);
/* H_CEDE has to be handled now, not later */
if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
vcpu->arch.vpa.dirty = 1;
save_pmu = lp->pmcregs_in_use;
}
+ /* Must save pmu if this guest is capable of running nested guests */
+ save_pmu |= nesting_enabled(vcpu->kvm);
kvmhv_save_guest_pmu(vcpu, save_pmu);
xive->single_escalation = xive_native_has_single_escalation();
- if (ret) {
- kfree(xive);
+ if (ret)
return ret;
- }
return 0;
}
xive->ops = &kvmppc_xive_native_ops;
if (ret)
- kfree(xive);
+ return ret;
- return ret;
+ return 0;
}
/*
return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
}
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ return kvm_arch_vcpu_runnable(vcpu);
+}
+
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
return false;
return -EINVAL;
}
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return false;
-}
-
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
-{
- return 0;
-}
-
void kvm_arch_destroy_vm(struct kvm *kvm)
{
unsigned int i;
*
* For guests on platforms before POWER9, we clamp the it limit to 1G
* to avoid some funky things such as RTAS bugs etc...
+ *
+ * On POWER9 we limit to 1TB in case the host erroneously told us that
+ * the RMA was >1TB. Effective address bits 0:23 are treated as zero
+ * (meaning the access is aliased to zero i.e. addr = addr % 1TB)
+ * for virtual real mode addressing and so it doesn't make sense to
+ * have an area larger than 1TB as it can't be addressed.
*/
if (!early_cpu_has_feature(CPU_FTR_HVMODE)) {
ppc64_rma_size = first_memblock_size;
if (!early_cpu_has_feature(CPU_FTR_ARCH_300))
ppc64_rma_size = min_t(u64, ppc64_rma_size, 0x40000000);
+ else
+ ppc64_rma_size = min_t(u64, ppc64_rma_size,
+ 1UL << SID_SHIFT_1T);
/* Finally limit subsequent allocations */
memblock_set_current_limit(ppc64_rma_size);
__set_pte_at(&init_mm, va, ptep, pfn_pte(PHYS_PFN(pa), prot), 0);
}
-static int kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
+static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned long k_end)
{
pmd_t *pmd;
unsigned long k_cur, k_next;
if ((void *)pmd_page_vaddr(*pmd) != kasan_early_shadow_pte)
continue;
- new = pte_alloc_one_kernel(&init_mm);
+ if (slab_is_available())
+ new = pte_alloc_one_kernel(&init_mm);
+ else
+ new = memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
if (!new)
return -ENOMEM;
#ifdef CONFIG_ZONE_DMA
max_zone_pfns[ZONE_DMA] = min(max_low_pfn,
- ((1UL << ARCH_ZONE_DMA_BITS) - 1) >> PAGE_SHIFT);
+ 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT));
#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
#ifdef CONFIG_PPC_FSL_BOOK3E
if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
unsigned int num_cams;
- int __maybe_unused cpu = smp_processor_id();
bool map = true;
/* use a quarter of the TLBCAM for bolted linear map */
#include <linux/sched.h>
#include <linux/libnvdimm.h>
#include <linux/platform_device.h>
+#include <linux/delay.h>
#include <asm/plpar_wrappers.h>
static int drc_pmem_bind(struct papr_scm_priv *p)
{
unsigned long ret[PLPAR_HCALL_BUFSIZE];
- uint64_t rc, token;
uint64_t saved = 0;
+ uint64_t token;
+ int64_t rc;
/*
* When the hypervisor cannot map all the requested memory in a single
} while (rc == H_BUSY);
if (rc) {
+ /* H_OVERLAP needs a separate error path */
+ if (rc == H_OVERLAP)
+ return -EBUSY;
+
dev_err(&p->pdev->dev, "bind err: %lld\n", rc);
return -ENXIO;
}
static int drc_pmem_unbind(struct papr_scm_priv *p)
{
unsigned long ret[PLPAR_HCALL_BUFSIZE];
- uint64_t rc, token;
+ uint64_t token = 0;
+ int64_t rc;
- token = 0;
+ dev_dbg(&p->pdev->dev, "unbind drc %x\n", p->drc_index);
- /* NB: unbind has the same retry requirements mentioned above */
+ /* NB: unbind has the same retry requirements as drc_pmem_bind() */
do {
- rc = plpar_hcall(H_SCM_UNBIND_MEM, ret, p->drc_index,
- p->bound_addr, p->blocks, token);
+
+ /* Unbind of all SCM resources associated with drcIndex */
+ rc = plpar_hcall(H_SCM_UNBIND_ALL, ret, H_UNBIND_SCOPE_DRC,
+ p->drc_index, token);
token = ret[0];
- cond_resched();
+
+ /* Check if we are stalled for some time */
+ if (H_IS_LONG_BUSY(rc)) {
+ msleep(get_longbusy_msecs(rc));
+ rc = H_BUSY;
+ } else if (rc == H_BUSY) {
+ cond_resched();
+ }
+
} while (rc == H_BUSY);
if (rc)
dev_err(&p->pdev->dev, "unbind error: %lld\n", rc);
+ else
+ dev_dbg(&p->pdev->dev, "unbind drc %x complete\n",
+ p->drc_index);
- return !!rc;
+ return rc == H_SUCCESS ? 0 : -ENXIO;
}
static int papr_scm_meta_get(struct papr_scm_priv *p,
NULL,
};
+static inline int papr_scm_node(int node)
+{
+ int min_dist = INT_MAX, dist;
+ int nid, min_node;
+
+ if ((node == NUMA_NO_NODE) || node_online(node))
+ return node;
+
+ min_node = first_online_node;
+ for_each_online_node(nid) {
+ dist = node_distance(node, nid);
+ if (dist < min_dist) {
+ min_dist = dist;
+ min_node = nid;
+ }
+ }
+ return min_node;
+}
+
static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
{
struct device *dev = &p->pdev->dev;
struct nd_mapping_desc mapping;
struct nd_region_desc ndr_desc;
unsigned long dimm_flags;
+ int target_nid, online_nid;
p->bus_desc.ndctl = papr_scm_ndctl;
p->bus_desc.module = THIS_MODULE;
memset(&ndr_desc, 0, sizeof(ndr_desc));
ndr_desc.attr_groups = region_attr_groups;
- ndr_desc.numa_node = dev_to_node(&p->pdev->dev);
- ndr_desc.target_node = ndr_desc.numa_node;
+ target_nid = dev_to_node(&p->pdev->dev);
+ online_nid = papr_scm_node(target_nid);
+ ndr_desc.numa_node = online_nid;
+ ndr_desc.target_node = target_nid;
ndr_desc.res = &p->res;
ndr_desc.of_node = p->dn;
ndr_desc.provider_data = p;
ndr_desc.res, p->dn);
goto err;
}
+ if (target_nid != online_nid)
+ dev_info(dev, "Region registered with target node %d and online node %d",
+ target_nid, online_nid);
return 0;
/* request the hypervisor to bind this region to somewhere in memory */
rc = drc_pmem_bind(p);
+
+ /* If phyp says drc memory still bound then force unbound and retry */
+ if (rc == -EBUSY) {
+ dev_warn(&pdev->dev, "Retrying bind after unbinding\n");
+ drc_pmem_unbind(p);
+ rc = drc_pmem_bind(p);
+ }
+
if (rc)
goto err;
* Now go through the entire mask until we find a valid
* target.
*/
- for (;;) {
+ do {
/*
* We re-check online as the fallback case passes us
* an untested affinity mask
if (cpu_online(cpu) && xive_try_pick_target(cpu))
return cpu;
cpu = cpumask_next(cpu, mask);
- if (cpu == first)
- break;
/* Wrap around */
if (cpu >= nr_cpu_ids)
cpu = cpumask_first(mask);
- }
+ } while (cpu != first);
+
return -1;
}
cpus {
#address-cells = <1>;
#size-cells = <0>;
- timebase-frequency = <1000000>;
cpu0: cpu@0 {
compatible = "sifive,e51", "sifive,rocket0", "riscv";
device_type = "cpu";
#size-cells = <0>;
status = "disabled";
};
+ eth0: ethernet@10090000 {
+ compatible = "sifive,fu540-c000-gem";
+ interrupt-parent = <&plic0>;
+ interrupts = <53>;
+ reg = <0x0 0x10090000 0x0 0x2000
+ 0x0 0x100a0000 0x0 0x1000>;
+ local-mac-address = [00 00 00 00 00 00];
+ clock-names = "pclk", "hclk";
+ clocks = <&prci PRCI_CLK_GEMGXLPLL>,
+ <&prci PRCI_CLK_GEMGXLPLL>;
+ #address-cells = <1>;
+ #size-cells = <0>;
+ status = "disabled";
+ };
+
};
};
disable-wp;
};
};
+
+ð0 {
+ status = "okay";
+ phy-mode = "gmii";
+ phy-handle = <&phy0>;
+ phy0: ethernet-phy@0 {
+ reg = <0>;
+ };
+};
CONFIG_PCI_HOST_GENERIC=y
CONFIG_PCIE_XILINX=y
CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_SD=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
CONFIG_HVC_RISCV_SBI=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_VIRTIO=y
+CONFIG_SPI=y
+CONFIG_SPI_SIFIVE=y
# CONFIG_PTP_1588_CLOCK is not set
CONFIG_DRM=y
CONFIG_DRM_RADEON=y
CONFIG_USB_OHCI_HCD_PLATFORM=y
CONFIG_USB_STORAGE=y
CONFIG_USB_UAS=y
+CONFIG_MMC=y
+CONFIG_MMC_SPI=y
CONFIG_VIRTIO_MMIO=y
-CONFIG_SPI_SIFIVE=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_AUTOFS4_FS=y
CONFIG_CRYPTO_USER_API_HASH=y
CONFIG_CRYPTO_DEV_VIRTIO=y
CONFIG_PRINTK_TIME=y
-CONFIG_SPI=y
-CONFIG_MMC_SPI=y
-CONFIG_MMC=y
-CONFIG_DEVTMPFS_MOUNT=y
# CONFIG_RCU_TRACE is not set
CONFIG_PCI_HOST_GENERIC=y
CONFIG_PCIE_XILINX=y
CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_SD=y
CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
CONFIG_HVC_RISCV_SBI=y
+CONFIG_HW_RANDOM=y
+CONFIG_HW_RANDOM_VIRTIO=y
# CONFIG_PTP_1588_CLOCK is not set
CONFIG_DRM=y
CONFIG_DRM_RADEON=y
generic-y += local.h
generic-y += local64.h
generic-y += mm-arch-hooks.h
+generic-y += msi.h
generic-y += percpu.h
generic-y += preempt.h
generic-y += sections.h
__end_of_fixed_addresses
};
-#define FIXADDR_SIZE (__end_of_fixed_addresses * PAGE_SIZE)
-#define FIXADDR_TOP (VMALLOC_START)
-#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
-
#define FIXMAP_PAGE_IO PAGE_KERNEL
#define __early_set_fixmap __set_fixmap
#define VMALLOC_END (PAGE_OFFSET - 1)
#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE)
+#define FIXADDR_TOP VMALLOC_START
+#ifdef CONFIG_64BIT
+#define FIXADDR_SIZE PMD_SIZE
+#else
+#define FIXADDR_SIZE PGDIR_SIZE
+#endif
+#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
+
/*
- * Task size is 0x4000000000 for RV64 or 0xb800000 for RV32.
+ * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32.
* Note that PGDIR_SIZE must evenly divide TASK_SIZE.
*/
#ifdef CONFIG_64BIT
#define TASK_SIZE (PGDIR_SIZE * PTRS_PER_PGD / 2)
#else
-#define TASK_SIZE VMALLOC_START
+#define TASK_SIZE FIXADDR_START
#endif
#include <asm-generic/pgtable.h>
static inline void __fstate_clean(struct pt_regs *regs)
{
- regs->sstatus |= (regs->sstatus & ~(SR_FS)) | SR_FS_CLEAN;
+ regs->sstatus = (regs->sstatus & ~SR_FS) | SR_FS_CLEAN;
+}
+
+static inline void fstate_off(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ regs->sstatus = (regs->sstatus & ~SR_FS) | SR_FS_OFF;
}
static inline void fstate_save(struct task_struct *task,
}
#define flush_tlb_all() sbi_remote_sfence_vma(NULL, 0, -1)
-#define flush_tlb_page(vma, addr) flush_tlb_range(vma, addr, 0)
+
#define flush_tlb_range(vma, start, end) \
remote_sfence_vma(mm_cpumask((vma)->vm_mm), start, (end) - (start))
-#define flush_tlb_mm(mm) \
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ flush_tlb_range(vma, addr, addr + PAGE_SIZE);
+}
+
+#define flush_tlb_mm(mm) \
remote_sfence_vma(mm_cpumask(mm), 0, -1)
#endif /* CONFIG_SMP */
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2015 Regents of the University of California
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2015 Regents of the University of California
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2015 Regents of the University of California
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copied from arch/arm64/include/asm/hwcap.h
*
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copyright (C) 2012 Regents of the University of California
*/
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copyright (C) 2012 Regents of the University of California
*/
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2017 SiFive, Inc.
#ifdef __LP64__
#define __ARCH_WANT_NEW_STAT
#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_CLONE3
#endif /* __LP64__ */
#include <asm-generic/unistd.h>
unsigned long sp)
{
regs->sstatus = SR_SPIE;
- if (has_fpu)
+ if (has_fpu) {
regs->sstatus |= SR_FS_INITIAL;
+ /*
+ * Restore the initial value to the FP register
+ * before starting the user program.
+ */
+ fstate_restore(current, regs);
+ }
regs->sepc = pc;
regs->sp = sp;
set_fs(USER_DS);
{
#ifdef CONFIG_FPU
/*
- * Reset FPU context
+ * Reset FPU state and context
* frm: round to nearest, ties to even (IEEE default)
* fflags: accrued exceptions cleared
*/
+ fstate_off(current, task_pt_regs(current));
memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate));
#endif
}
# these symbols in the kernel code rather than hand-coded addresses.
SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \
- -Wl,--hash-style=both
+ -Wl,--build-id -Wl,--hash-style=both
$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE
$(call if_changed,vdsold)
lib-y += uaccess.o
lib-$(CONFIG_64BIT) += tishift.o
-
-lib-$(CONFIG_32BIT) += udivdi3.o
void udelay(unsigned long usecs)
{
u64 ucycles = (u64)usecs * lpj_fine * UDELAY_MULT;
+ u64 n;
if (unlikely(usecs > MAX_UDELAY_US)) {
- __delay((u64)usecs * riscv_timebase / 1000000ULL);
+ n = (u64)usecs * riscv_timebase;
+ do_div(n, 1000000);
+
+ __delay(n);
return;
}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2016-2017 Free Software Foundation, Inc.
- */
-
-#include <linux/linkage.h>
-
-ENTRY(__udivdi3)
- mv a2, a1
- mv a1, a0
- li a0, -1
- beqz a2, .L5
- li a3, 1
- bgeu a2, a1, .L2
-.L1:
- blez a2, .L2
- slli a2, a2, 1
- slli a3, a3, 1
- bgtu a1, a2, .L1
-.L2:
- li a0, 0
-.L3:
- bltu a1, a2, .L4
- sub a1, a1, a2
- or a0, a0, a3
-.L4:
- srli a3, a3, 1
- srli a2, a2, 1
- bnez a3, .L3
-.L5:
- ret
-ENDPROC(__udivdi3)
obj-y := head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
-obj-y += ctype.o text_dma.o
+obj-y += version.o ctype.o text_dma.o
obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) += uv.o
obj-$(CONFIG_RELOCATABLE) += machine_kexec_reloc.o
obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
void setup_boot_command_line(void);
void parse_boot_command_line(void);
void setup_memory_end(void);
+void verify_facilities(void);
void print_missing_facilities(void);
unsigned long get_random_base(unsigned long safe_addr);
extern int kaslr_enabled;
+extern const char kernel_version[];
unsigned long read_ipl_report(unsigned long safe_offset);
.quad 0 # INITRD_SIZE
.quad 0 # OLDMEM_BASE
.quad 0 # OLDMEM_SIZE
+ .quad kernel_version # points to kernel version string
.org COMMAND_LINE
.byte "root=/dev/ram0 ro"
{
int rc;
- uv_set_shared(__pa(&ipl_block));
rc = __diag308(DIAG308_STORE, &ipl_block);
- uv_remove_shared(__pa(&ipl_block));
if (rc == DIAG308_RC_OK &&
ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
ipl_block_valid = 1;
#include <asm/timex.h>
#include <asm/sclp.h>
#include "compressed/decompressor.h"
+#include "boot.h"
#define PRNG_MODE_TDES 1
#define PRNG_MODE_SHA512 2
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <generated/utsrelease.h>
+#include <generated/compile.h>
+#include "boot.h"
+
+const char kernel_version[] = UTS_RELEASE
+ " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") " UTS_VERSION;
CONFIG_AUDIT=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_PREEMPT=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
CONFIG_CPUSETS=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_BPF=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
+CONFIG_LIVEPATCH=y
+CONFIG_TUNE_ZEC12=y
+CONFIG_NR_CPUS=512
+CONFIG_NUMA=y
+CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
+CONFIG_CHSC_SCH=y
+CONFIG_VFIO_CCW=m
+CONFIG_VFIO_AP=m
+CONFIG_CRASH_DUMP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_CMM=m
+CONFIG_APPLDATA_BASE=y
+CONFIG_KVM=m
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_STATIC_KEYS_SELFTEST=y
+CONFIG_REFCOUNT_FULL=y
+CONFIG_LOCK_EVENT_COUNTS=y
CONFIG_MODULES=y
CONFIG_MODULE_FORCE_LOAD=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
CONFIG_MODVERSIONS=y
CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG=y
+CONFIG_MODULE_SIG_SHA256=y
CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
-CONFIG_BLK_WBT_SQ=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=512
-CONFIG_NUMA=y
-CONFIG_PREEMPT=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
-CONFIG_KEXEC_VERIFY_SIG=y
-CONFIG_EXPOLINE=y
-CONFIG_EXPOLINE_AUTO=y
+CONFIG_IOSCHED_BFQ=y
+CONFIG_BFQ_GROUP_IOSCHED=y
+CONFIG_BINFMT_MISC=m
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_PCI=y
-CONFIG_PCI_DEBUG=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_S390=y
-CONFIG_CHSC_SCH=y
-CONFIG_VFIO_AP=m
-CONFIG_VFIO_CCW=m
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
+CONFIG_PERCPU_STATS=y
+CONFIG_GUP_BENCHMARK=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_PACKET_DIAG=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
CONFIG_TCP_CONG_ADVANCED=y
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_SIT=m
CONFIG_IPV6_GRE=m
CONFIG_IP_VS_NQ=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NF_TABLES_IPV4=y
-CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=y
-CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_TABLES_IPV6=y
-CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=y
+CONFIG_NF_TABLES_BRIDGE=m
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
+CONFIG_PCI=y
+CONFIG_PCI_DEBUG=y
+CONFIG_HOTPLUG_PCI=y
+CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
-CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
CONFIG_BLK_DEV_SR=m
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_SCH=m
CONFIG_SCSI_DH_HP_SW=m
CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
CONFIG_MD_LINEAR=m
CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
+CONFIG_MD_CLUSTER=m
+CONFIG_BCACHE=m
CONFIG_BLK_DEV_DM=m
+CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_MIRROR=m
CONFIG_DM_LOG_USERSPACE=m
CONFIG_DM_RAID=m
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
CONFIG_VIRTIO_NET=m
CONFIG_NLMON=m
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_AGERE is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_VENDOR_AURORA is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
+# CONFIG_NET_VENDOR_CAVIUM is not set
# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
+# CONFIG_NET_VENDOR_GOOGLE is not set
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_MLX5_CORE_EN=y
+# CONFIG_MLXFW is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROCHIP is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
+# CONFIG_NET_VENDOR_MYRI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETERION is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
+# CONFIG_NET_VENDOR_ROCKER is not set
+# CONFIG_NET_VENDOR_SAMSUNG is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_FILTER=y
CONFIG_PPP_MPPE=m
+CONFIG_PPP_MULTILINK=y
CONFIG_PPPOE=m
CONFIG_PPTP=m
CONFIG_PPPOL2TP=m
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+CONFIG_NULL_TTY=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+CONFIG_PPS=m
+# CONFIG_PTP_1588_CLOCK is not set
# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
-CONFIG_S390_AP_IOMMU=y
CONFIG_S390_CCW_IOMMU=y
+CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_BTRFS_FS=y
CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_BTRFS_DEBUG=y
+CONFIG_BTRFS_ASSERT=y
CONFIG_NILFS2_FS=m
CONFIG_FS_DAX=y
CONFIG_EXPORTFS_BLOCK_OPS=y
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
CONFIG_SQUASHFS_XATTR=y
+CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SQUASHFS_XZ=y
+CONFIG_SQUASHFS_ZSTD=y
CONFIG_ROMFS_FS=m
CONFIG_NFS_FS=m
CONFIG_NFS_V3_ACL=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
CONFIG_DLM=m
+CONFIG_UNICODE=y
+CONFIG_PERSISTENT_KEYRINGS=y
+CONFIG_BIG_KEYS=y
+CONFIG_ENCRYPTED_KEYS=m
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_INTEGRITY_SIGNATURE=y
+CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
+CONFIG_IMA=y
+CONFIG_IMA_DEFAULT_HASH_SHA256=y
+CONFIG_IMA_WRITE_POLICY=y
+CONFIG_IMA_APPRAISE=y
+CONFIG_CRYPTO_USER=m
+# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
+CONFIG_CRYPTO_PCRYPT=m
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
+CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_ADIANTUM=m
+CONFIG_CRYPTO_XCBC=m
+CONFIG_CRYPTO_VMAC=m
+CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_XXHASH=m
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
+CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
+CONFIG_CRYPTO_TGR192=m
+CONFIG_CRYPTO_WP512=m
+CONFIG_CRYPTO_AES_TI=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
+CONFIG_CRYPTO_CAST5=m
+CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_FCRYPT=m
+CONFIG_CRYPTO_KHAZAD=m
+CONFIG_CRYPTO_SALSA20=m
+CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_842=m
+CONFIG_CRYPTO_LZ4=m
+CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
+CONFIG_CRYPTO_ANSI_CPRNG=m
+CONFIG_CRYPTO_USER_API_HASH=m
+CONFIG_CRYPTO_USER_API_SKCIPHER=m
+CONFIG_CRYPTO_USER_API_RNG=m
+CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_STATS=y
+CONFIG_ZCRYPT=m
+CONFIG_PKEY=m
+CONFIG_CRYPTO_PAES_S390=m
+CONFIG_CRYPTO_SHA1_S390=m
+CONFIG_CRYPTO_SHA256_S390=m
+CONFIG_CRYPTO_SHA512_S390=m
+CONFIG_CRYPTO_DES_S390=m
+CONFIG_CRYPTO_AES_S390=m
+CONFIG_CRYPTO_GHASH_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CORDIC=m
+CONFIG_CRC32_SELFTEST=y
+CONFIG_CRC4=m
+CONFIG_CRC7=m
+CONFIG_CRC8=m
+CONFIG_RANDOM32_SELFTEST=y
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
+CONFIG_DMA_API_DEBUG=y
+CONFIG_STRING_SELFTEST=y
CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_GDB_SCRIPTS=y
CONFIG_FRAME_WARN=1024
-CONFIG_READABLE_ASM=y
CONFIG_UNUSED_SYMBOLS=y
CONFIG_HEADERS_INSTALL=y
CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_PAGE_OWNER=y
CONFIG_DEBUG_RODATA_TEST=y
CONFIG_DEBUG_OBJECTS=y
CONFIG_DEBUG_OBJECTS_SELFTEST=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_FUNCTION_PROFILER=y
CONFIG_HIST_TRIGGERS=y
-CONFIG_DMA_API_DEBUG=y
CONFIG_LKDTM=m
CONFIG_TEST_LIST_SORT=y
CONFIG_TEST_SORT=y
CONFIG_TEST_BPF=m
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_S390_PTDUMP=y
-CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
-CONFIG_ENCRYPTED_KEYS=m
-CONFIG_SECURITY=y
-CONFIG_SECURITY_NETWORK=y
-CONFIG_FORTIFY_SOURCE=y
-CONFIG_SECURITY_SELINUX=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
-CONFIG_SECURITY_SELINUX_DISABLE=y
-CONFIG_INTEGRITY_SIGNATURE=y
-CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
-CONFIG_IMA=y
-CONFIG_IMA_DEFAULT_HASH_SHA256=y
-CONFIG_IMA_WRITE_POLICY=y
-CONFIG_IMA_APPRAISE=y
-CONFIG_CRYPTO_DH=m
-CONFIG_CRYPTO_ECDH=m
-CONFIG_CRYPTO_USER=m
-# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
-CONFIG_CRYPTO_PCRYPT=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_CHACHA20POLY1305=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_KEYWRAP=m
-CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_VMAC=m
-CONFIG_CRYPTO_CRC32=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
-CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_WP512=m
-CONFIG_CRYPTO_AES_TI=m
-CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_CAMELLIA=m
-CONFIG_CRYPTO_CAST5=m
-CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
-CONFIG_CRYPTO_SEED=m
-CONFIG_CRYPTO_SERPENT=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_842=m
-CONFIG_CRYPTO_LZ4=m
-CONFIG_CRYPTO_LZ4HC=m
-CONFIG_CRYPTO_ANSI_CPRNG=m
-CONFIG_CRYPTO_USER_API_HASH=m
-CONFIG_CRYPTO_USER_API_SKCIPHER=m
-CONFIG_CRYPTO_USER_API_RNG=m
-CONFIG_CRYPTO_USER_API_AEAD=m
-CONFIG_ZCRYPT=m
-CONFIG_PKEY=m
-CONFIG_CRYPTO_PAES_S390=m
-CONFIG_CRYPTO_SHA1_S390=m
-CONFIG_CRYPTO_SHA256_S390=m
-CONFIG_CRYPTO_SHA512_S390=m
-CONFIG_CRYPTO_DES_S390=m
-CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=y
-CONFIG_PKCS7_MESSAGE_PARSER=y
-CONFIG_SYSTEM_TRUSTED_KEYRING=y
-CONFIG_CRC7=m
-CONFIG_CRC8=m
-CONFIG_RANDOM32_SELFTEST=y
-CONFIG_CORDIC=m
-CONFIG_CMM=m
-CONFIG_APPLDATA_BASE=y
-CONFIG_KVM=m
-CONFIG_KVM_S390_UCONTROL=y
-CONFIG_VHOST_NET=m
-CONFIG_VHOST_VSOCK=m
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_NUMA_BALANCING=y
-# CONFIG_NUMA_BALANCING_DEFAULT_ENABLED is not set
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
CONFIG_BLK_CGROUP=y
CONFIG_CFS_BANDWIDTH=y
CONFIG_RT_GROUP_SCHED=y
CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_RDMA=y
CONFIG_CGROUP_FREEZER=y
CONFIG_CGROUP_HUGETLB=y
CONFIG_CPUSETS=y
CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_BPF=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_CHECKPOINT_RESTORE=y
CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
+CONFIG_LIVEPATCH=y
+CONFIG_TUNE_ZEC12=y
+CONFIG_NR_CPUS=512
+CONFIG_NUMA=y
+# CONFIG_NUMA_EMU is not set
+CONFIG_HZ_100=y
+CONFIG_KEXEC_FILE=y
+CONFIG_EXPOLINE=y
+CONFIG_EXPOLINE_AUTO=y
+CONFIG_CHSC_SCH=y
+CONFIG_VFIO_CCW=m
+CONFIG_VFIO_AP=m
+CONFIG_CRASH_DUMP=y
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_CMM=m
+CONFIG_APPLDATA_BASE=y
+CONFIG_KVM=m
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
CONFIG_OPROFILE=m
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
CONFIG_MODULE_SRCVERSION_ALL=y
CONFIG_MODULE_SIG=y
CONFIG_MODULE_SIG_SHA256=y
-CONFIG_BLK_DEV_INTEGRITY=y
CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
-CONFIG_BLK_WBT_SQ=y
+CONFIG_BLK_CGROUP_IOLATENCY=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_IBM_PARTITION=y
CONFIG_BSD_DISKLABEL=y
CONFIG_MINIX_SUBPARTITION=y
CONFIG_SOLARIS_X86_PARTITION=y
CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_CFQ_GROUP_IOSCHED=y
-CONFIG_DEFAULT_DEADLINE=y
-CONFIG_LIVEPATCH=y
-CONFIG_TUNE_ZEC12=y
-CONFIG_NR_CPUS=512
-CONFIG_NUMA=y
-CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
-CONFIG_KEXEC_VERIFY_SIG=y
-CONFIG_EXPOLINE=y
-CONFIG_EXPOLINE_AUTO=y
+CONFIG_IOSCHED_BFQ=y
+CONFIG_BFQ_GROUP_IOSCHED=y
+CONFIG_BINFMT_MISC=m
CONFIG_MEMORY_HOTPLUG=y
CONFIG_MEMORY_HOTREMOVE=y
CONFIG_KSM=y
CONFIG_ZSMALLOC_STAT=y
CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
CONFIG_IDLE_PAGE_TRACKING=y
-CONFIG_PCI=y
-CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_S390=y
-CONFIG_CHSC_SCH=y
-CONFIG_VFIO_AP=m
-CONFIG_VFIO_CCW=m
-CONFIG_CRASH_DUMP=y
-CONFIG_BINFMT_MISC=m
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
+CONFIG_PERCPU_STATS=y
+CONFIG_GUP_BENCHMARK=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_PACKET_DIAG=m
CONFIG_INET_AH=m
CONFIG_INET_ESP=m
CONFIG_INET_IPCOMP=m
-CONFIG_INET_XFRM_MODE_TRANSPORT=m
-CONFIG_INET_XFRM_MODE_TUNNEL=m
-CONFIG_INET_XFRM_MODE_BEET=m
CONFIG_INET_DIAG=m
CONFIG_INET_UDP_DIAG=m
CONFIG_TCP_CONG_ADVANCED=y
CONFIG_INET6_ESP=m
CONFIG_INET6_IPCOMP=m
CONFIG_IPV6_MIP6=m
-CONFIG_INET6_XFRM_MODE_TRANSPORT=m
-CONFIG_INET6_XFRM_MODE_TUNNEL=m
-CONFIG_INET6_XFRM_MODE_BEET=m
-CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
CONFIG_IPV6_VTI=m
CONFIG_IPV6_SIT=m
CONFIG_IPV6_GRE=m
CONFIG_IP_VS_NQ=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_CONNTRACK_IPV4=m
CONFIG_NF_TABLES_IPV4=y
-CONFIG_NFT_CHAIN_ROUTE_IPV4=m
CONFIG_NF_TABLES_ARP=y
-CONFIG_NFT_CHAIN_NAT_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_CONNTRACK_IPV6=m
CONFIG_NF_TABLES_IPV6=y
-CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
CONFIG_IP6_NF_MATCH_EUI64=m
CONFIG_IP6_NF_SECURITY=m
CONFIG_IP6_NF_NAT=m
CONFIG_IP6_NF_TARGET_MASQUERADE=m
-CONFIG_NF_TABLES_BRIDGE=y
+CONFIG_NF_TABLES_BRIDGE=m
CONFIG_RDS=m
CONFIG_RDS_RDMA=m
CONFIG_RDS_TCP=m
CONFIG_CGROUP_NET_PRIO=y
CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
+CONFIG_PCI=y
+CONFIG_HOTPLUG_PCI=y
+CONFIG_HOTPLUG_PCI_S390=y
+CONFIG_UEVENT_HELPER=y
CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
-CONFIG_CMA_SIZE_MBYTES=0
CONFIG_CONNECTOR=y
CONFIG_ZRAM=m
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_NBD=m
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_SIZE=32768
+# CONFIG_BLK_DEV_XPRAM is not set
CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_RBD=m
CONFIG_BLK_DEV_NVME=m
CONFIG_SCSI=y
CONFIG_BLK_DEV_SD=y
CONFIG_CHR_DEV_ST=m
-CONFIG_CHR_DEV_OSST=m
CONFIG_BLK_DEV_SR=m
CONFIG_CHR_DEV_SG=y
CONFIG_CHR_DEV_SCH=m
CONFIG_SCSI_DH_HP_SW=m
CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
-CONFIG_SCSI_OSD_INITIATOR=m
-CONFIG_SCSI_OSD_ULD=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
CONFIG_MD_LINEAR=m
CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
+CONFIG_MD_CLUSTER=m
+CONFIG_BCACHE=m
CONFIG_BLK_DEV_DM=m
+CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
CONFIG_DM_MIRROR=m
CONFIG_DM_LOG_USERSPACE=m
CONFIG_DM_RAID=m
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
CONFIG_DM_SWITCH=m
+CONFIG_DM_INTEGRITY=m
CONFIG_NETDEVICES=y
CONFIG_BONDING=m
CONFIG_DUMMY=m
CONFIG_IFB=m
CONFIG_MACVLAN=m
CONFIG_MACVTAP=m
-CONFIG_VXLAN=m
CONFIG_TUN=m
CONFIG_VETH=m
CONFIG_VIRTIO_NET=m
CONFIG_NLMON=m
+# CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ADAPTEC is not set
+# CONFIG_NET_VENDOR_AGERE is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
+# CONFIG_NET_VENDOR_ALTEON is not set
+# CONFIG_NET_VENDOR_AMAZON is not set
+# CONFIG_NET_VENDOR_AMD is not set
+# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
+# CONFIG_NET_VENDOR_ATHEROS is not set
+# CONFIG_NET_VENDOR_AURORA is not set
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_BROCADE is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
+# CONFIG_NET_VENDOR_CAVIUM is not set
# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CISCO is not set
+# CONFIG_NET_VENDOR_CORTINA is not set
+# CONFIG_NET_VENDOR_DEC is not set
+# CONFIG_NET_VENDOR_DLINK is not set
+# CONFIG_NET_VENDOR_EMULEX is not set
+# CONFIG_NET_VENDOR_EZCHIP is not set
+# CONFIG_NET_VENDOR_GOOGLE is not set
+# CONFIG_NET_VENDOR_HP is not set
+# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_MLX5_CORE_EN=y
+# CONFIG_MLXFW is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROCHIP is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
+# CONFIG_NET_VENDOR_MYRI is not set
# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_NETERION is not set
+# CONFIG_NET_VENDOR_NETRONOME is not set
+# CONFIG_NET_VENDOR_NI is not set
+# CONFIG_NET_VENDOR_NVIDIA is not set
+# CONFIG_NET_VENDOR_OKI is not set
+# CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_QLOGIC is not set
+# CONFIG_NET_VENDOR_QUALCOMM is not set
+# CONFIG_NET_VENDOR_RDC is not set
+# CONFIG_NET_VENDOR_REALTEK is not set
+# CONFIG_NET_VENDOR_RENESAS is not set
+# CONFIG_NET_VENDOR_ROCKER is not set
+# CONFIG_NET_VENDOR_SAMSUNG is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
+# CONFIG_NET_VENDOR_SILAN is not set
+# CONFIG_NET_VENDOR_SIS is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+# CONFIG_NET_VENDOR_SOCIONEXT is not set
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
+# CONFIG_NET_VENDOR_TEHUTI is not set
+# CONFIG_NET_VENDOR_TI is not set
+# CONFIG_NET_VENDOR_VIA is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
CONFIG_PPP=m
CONFIG_PPP_BSDCOMP=m
CONFIG_PPP_DEFLATE=m
+CONFIG_PPP_FILTER=y
CONFIG_PPP_MPPE=m
+CONFIG_PPP_MULTILINK=y
CONFIG_PPPOE=m
CONFIG_PPTP=m
CONFIG_PPPOL2TP=m
# CONFIG_INPUT_MOUSE is not set
# CONFIG_SERIO is not set
CONFIG_LEGACY_PTY_COUNT=0
+CONFIG_NULL_TTY=m
CONFIG_HW_RANDOM_VIRTIO=m
CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
+# CONFIG_PTP_1588_CLOCK is not set
# CONFIG_HWMON is not set
CONFIG_WATCHDOG=y
+CONFIG_WATCHDOG_CORE=y
CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
CONFIG_DRM=y
CONFIG_DRM_VIRTIO_GPU=y
+# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_HID is not set
# CONFIG_USB_SUPPORT is not set
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
-CONFIG_S390_AP_IOMMU=y
CONFIG_S390_CCW_IOMMU=y
+CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_CRAMFS=m
CONFIG_SQUASHFS=m
CONFIG_SQUASHFS_XATTR=y
+CONFIG_SQUASHFS_LZ4=y
CONFIG_SQUASHFS_LZO=y
CONFIG_SQUASHFS_XZ=y
+CONFIG_SQUASHFS_ZSTD=y
CONFIG_ROMFS_FS=m
CONFIG_NFS_FS=m
CONFIG_NFS_V3_ACL=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS=y
CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
CONFIG_NLS_ISO8859_15=m
CONFIG_NLS_UTF8=m
CONFIG_DLM=m
-CONFIG_PRINTK_TIME=y
-CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_INFO_DWARF4=y
-CONFIG_GDB_SCRIPTS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
-CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_MEMORY_INIT=y
-CONFIG_PANIC_ON_OOPS=y
-CONFIG_RCU_TORTURE_TEST=m
-CONFIG_RCU_CPU_STALL_TIMEOUT=60
-CONFIG_LATENCYTOP=y
-CONFIG_SCHED_TRACER=y
-CONFIG_FTRACE_SYSCALLS=y
-CONFIG_STACK_TRACER=y
-CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_FUNCTION_PROFILER=y
-CONFIG_HIST_TRIGGERS=y
-CONFIG_LKDTM=m
-CONFIG_PERCPU_TEST=m
-CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_TEST_BPF=m
-CONFIG_BUG_ON_DATA_CORRUPTION=y
-CONFIG_S390_PTDUMP=y
+CONFIG_UNICODE=y
CONFIG_PERSISTENT_KEYRINGS=y
CONFIG_BIG_KEYS=y
CONFIG_ENCRYPTED_KEYS=m
CONFIG_SECURITY_NETWORK=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
CONFIG_CRYPTO_FIPS=y
-CONFIG_CRYPTO_DH=m
-CONFIG_CRYPTO_ECDH=m
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
CONFIG_CRYPTO_PCRYPT=m
CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_DH=m
+CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECRDSA=m
CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
+CONFIG_CRYPTO_CFB=m
CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_OFB=m
CONFIG_CRYPTO_PCBC=m
CONFIG_CRYPTO_KEYWRAP=m
+CONFIG_CRYPTO_ADIANTUM=m
CONFIG_CRYPTO_XCBC=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_XXHASH=m
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
CONFIG_CRYPTO_RMD256=m
CONFIG_CRYPTO_RMD320=m
-CONFIG_CRYPTO_SHA512=m
CONFIG_CRYPTO_SHA3=m
+CONFIG_CRYPTO_SM3=m
CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
CONFIG_CRYPTO_BLOWFISH=m
CONFIG_CRYPTO_CAMELLIA=m
CONFIG_CRYPTO_CAST5=m
CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
CONFIG_CRYPTO_842=m
CONFIG_CRYPTO_LZ4=m
CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
CONFIG_CRYPTO_ANSI_CPRNG=m
CONFIG_CRYPTO_USER_API_HASH=m
CONFIG_CRYPTO_USER_API_SKCIPHER=m
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_USER_API_AEAD=m
+CONFIG_CRYPTO_STATS=y
CONFIG_ZCRYPT=m
CONFIG_PKEY=m
CONFIG_CRYPTO_PAES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
CONFIG_CRYPTO_CRC32_S390=y
+CONFIG_CORDIC=m
+CONFIG_CRC4=m
CONFIG_CRC7=m
CONFIG_CRC8=m
-CONFIG_CORDIC=m
-CONFIG_CMM=m
-CONFIG_APPLDATA_BASE=y
-CONFIG_KVM=m
-CONFIG_KVM_S390_UCONTROL=y
-CONFIG_VHOST_NET=m
-CONFIG_VHOST_VSOCK=m
+CONFIG_DMA_CMA=y
+CONFIG_CMA_SIZE_MBYTES=0
+CONFIG_PRINTK_TIME=y
+CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_DWARF4=y
+CONFIG_GDB_SCRIPTS=y
+CONFIG_FRAME_WARN=1024
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_RCU_TORTURE_TEST=m
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_LATENCYTOP=y
+CONFIG_SCHED_TRACER=y
+CONFIG_FTRACE_SYSCALLS=y
+CONFIG_STACK_TRACER=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_FUNCTION_PROFILER=y
+CONFIG_HIST_TRIGGERS=y
+CONFIG_LKDTM=m
+CONFIG_PERCPU_TEST=m
+CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_BPF=m
+CONFIG_BUG_ON_DATA_CORRUPTION=y
+CONFIG_S390_PTDUMP=y
# CONFIG_SWAP is not set
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+# CONFIG_CPU_ISOLATION is not set
+# CONFIG_UTS_NS is not set
+# CONFIG_PID_NS is not set
+# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
# CONFIG_COMPAT_BRK is not set
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
-CONFIG_DEFAULT_DEADLINE=y
CONFIG_TUNE_ZEC12=y
# CONFIG_COMPAT is not set
CONFIG_NR_CPUS=2
-# CONFIG_HOTPLUG_CPU is not set
CONFIG_HZ_100=y
# CONFIG_ARCH_RANDOM is not set
-# CONFIG_COMPACTION is not set
-# CONFIG_MIGRATION is not set
-# CONFIG_BOUNCE is not set
-# CONFIG_CHECK_STACK is not set
+# CONFIG_RELOCATABLE is not set
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
CONFIG_CRASH_DUMP=y
-# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_SECCOMP is not set
+# CONFIG_PFAULT is not set
+# CONFIG_S390_HYPFS_FS is not set
+# CONFIG_VIRTUALIZATION is not set
+# CONFIG_S390_GUEST is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_IBM_PARTITION=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_COMPACTION is not set
+# CONFIG_MIGRATION is not set
+# CONFIG_BOUNCE is not set
CONFIG_NET=y
# CONFIG_IUCV is not set
CONFIG_DEVTMPFS=y
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
CONFIG_RAW_DRIVER=y
-# CONFIG_SCLP_ASYNC is not set
# CONFIG_HMC_DRV is not set
# CONFIG_S390_TAPE is not set
# CONFIG_VMCP is not set
CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
+# CONFIG_DIMLIB is not set
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_FS=y
# CONFIG_SCHED_DEBUG is not set
CONFIG_RCU_CPU_STALL_TIMEOUT=60
# CONFIG_FTRACE is not set
-# CONFIG_PFAULT is not set
-# CONFIG_S390_HYPFS_FS is not set
-# CONFIG_VIRTUALIZATION is not set
-# CONFIG_S390_GUEST is not set
+# CONFIG_RUNTIME_TESTING_MENU is not set
return PTR_ERR(rc); \
} while(0)
-static int hpyfs_vm_create_guest(struct dentry *systems_dir,
+static int hypfs_vm_create_guest(struct dentry *systems_dir,
struct diag2fc_data *data)
{
char guest_name[NAME_LEN + 1] = {};
}
for (i = 0; i < count; i++) {
- rc = hpyfs_vm_create_guest(dir, &(data[i]));
+ rc = hypfs_vm_create_guest(dir, &(data[i]));
if (rc)
goto failed;
}
#include <linux/typecheck.h>
#include <linux/compiler.h>
+#include <linux/types.h>
#include <asm/atomic_ops.h>
#include <asm/barrier.h>
return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
}
-static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long mask;
__atomic64_or(mask, (long *)addr);
}
-static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long mask;
__atomic64_and(mask, (long *)addr);
}
-static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch_change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long mask;
__atomic64_xor(mask, (long *)addr);
}
-static inline int
-test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch_test_and_set_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long old, mask;
return (old & mask) != 0;
}
-static inline int
-test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch_test_and_clear_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long old, mask;
return (old & ~mask) != 0;
}
-static inline int
-test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch_test_and_change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned long *addr = __bitops_word(nr, ptr);
unsigned long old, mask;
return (old & mask) != 0;
}
-static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
*addr |= 1 << (nr & 7);
}
-static inline void
-__clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch___clear_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
*addr &= ~(1 << (nr & 7));
}
-static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline void arch___change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
*addr ^= 1 << (nr & 7);
}
-static inline int
-__test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch___test_and_set_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
unsigned char ch;
return (ch >> (nr & 7)) & 1;
}
-static inline int
-__test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch___test_and_clear_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
unsigned char ch;
return (ch >> (nr & 7)) & 1;
}
-static inline int
-__test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
+static inline bool arch___test_and_change_bit(unsigned long nr,
+ volatile unsigned long *ptr)
{
unsigned char *addr = __bitops_byte(nr, ptr);
unsigned char ch;
return (ch >> (nr & 7)) & 1;
}
-static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
+static inline bool arch_test_bit(unsigned long nr,
+ const volatile unsigned long *ptr)
{
const volatile unsigned char *addr;
return (*addr >> (nr & 7)) & 1;
}
-static inline int test_and_set_bit_lock(unsigned long nr,
- volatile unsigned long *ptr)
+static inline bool arch_test_and_set_bit_lock(unsigned long nr,
+ volatile unsigned long *ptr)
{
- if (test_bit(nr, ptr))
+ if (arch_test_bit(nr, ptr))
return 1;
- return test_and_set_bit(nr, ptr);
+ return arch_test_and_set_bit(nr, ptr);
}
-static inline void clear_bit_unlock(unsigned long nr,
- volatile unsigned long *ptr)
+static inline void arch_clear_bit_unlock(unsigned long nr,
+ volatile unsigned long *ptr)
{
smp_mb__before_atomic();
- clear_bit(nr, ptr);
+ arch_clear_bit(nr, ptr);
}
-static inline void __clear_bit_unlock(unsigned long nr,
- volatile unsigned long *ptr)
+static inline void arch___clear_bit_unlock(unsigned long nr,
+ volatile unsigned long *ptr)
{
smp_mb();
- __clear_bit(nr, ptr);
+ arch___clear_bit(nr, ptr);
}
+#include <asm-generic/bitops-instrumented.h>
+
/*
* Functions which use MSB0 bit numbering.
* The bits are numbered:
return clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
-static inline int test_and_clear_bit_inv(unsigned long nr, volatile unsigned long *ptr)
+static inline bool test_and_clear_bit_inv(unsigned long nr,
+ volatile unsigned long *ptr)
{
return test_and_clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
return __clear_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
-static inline int test_bit_inv(unsigned long nr,
- const volatile unsigned long *ptr)
+static inline bool test_bit_inv(unsigned long nr,
+ const volatile unsigned long *ptr)
{
return test_bit(nr ^ (BITS_PER_LONG - 1), ptr);
}
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define ARCH_ZONE_DMA_BITS 31
+
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
* @sliba: storage list information block address
* @sla: storage list address
* @slsba: storage list state block address
- * @akey: access key for DLIB
+ * @akey: access key for SLIB
* @bkey: access key for SL
* @ckey: access key for SBALs
* @dkey: access key for SLSB
/**
* struct qdr - queue description record (QDR)
* @qfmt: queue format
- * @pfmt: implementation dependent parameter format
* @ac: adapter characteristics
* @iqdcnt: input queue descriptor count
* @oqdcnt: output queue descriptor count
- * @iqdsz: inpout queue descriptor size
+ * @iqdsz: input queue descriptor size
* @oqdsz: output queue descriptor size
* @qiba: queue information block address
* @qkey: queue information block key
*/
struct qdr {
u32 qfmt : 8;
- u32 pfmt : 8;
- u32 : 8;
+ u32 : 16;
u32 ac : 8;
u32 : 8;
u32 iqdcnt : 8;
* struct qdio_initialize - qdio initialization data
* @cdev: associated ccw device
* @q_format: queue format
+ * @qdr_ac: feature flags to set
* @adapter_name: name for the adapter
* @qib_param_field_format: format for qib_parm_field
* @qib_param_field: pointer to 128 bytes or NULL, if no param field
* @input_handler: handler to be called for input queues
* @output_handler: handler to be called for output queues
* @queue_start_poll_array: polling handlers (one per input queue or NULL)
+ * @scan_threshold: # of in-use buffers that triggers scan on output queue
* @int_parm: interruption parameter
* @input_sbal_addr_array: address of no_input_qs * 128 pointers
* @output_sbal_addr_array: address of no_output_qs * 128 pointers
#define INITRD_SIZE_OFFSET 0x10410
#define OLDMEM_BASE_OFFSET 0x10418
#define OLDMEM_SIZE_OFFSET 0x10420
+#define KERNEL_VERSION_OFFSET 0x10428
#define COMMAND_LINE_OFFSET 0x10480
#ifndef __ASSEMBLY__
unsigned long initrd_size; /* 0x10410 */
unsigned long oldmem_base; /* 0x10418 */
unsigned long oldmem_size; /* 0x10420 */
- char pad1[0x10480 - 0x10428]; /* 0x10428 - 0x10480 */
+ unsigned long kernel_version; /* 0x10428 */
+ char pad1[0x10480 - 0x10430]; /* 0x10430 - 0x10480 */
char command_line[ARCH_COMMAND_LINE_SIZE]; /* 0x10480 */
};
extern int memory_end_set;
extern unsigned long memory_end;
extern unsigned long max_physmem_end;
+extern unsigned long __swsusp_reset_dma;
#define MACHINE_IS_VM (S390_lowcore.machine_flags & MACHINE_FLAG_VM)
#define MACHINE_IS_KVM (S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_VFORK
#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
#endif /* _ASM_S390_UNISTD_H_ */
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
#define _UAPI__ASM_BPF_PERF_EVENT_H__
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_S390_UAPI_IPL_H
#define _ASM_S390_UAPI_IPL_H
#include <linux/ioctl.h>
#include <linux/compiler.h>
+#include <linux/types.h>
/* Name of the zcrypt device driver. */
#define ZCRYPT_NAME "zcrypt"
* @payload_len: Payload length
*/
struct ep11_cprb {
- uint16_t cprb_len;
+ __u16 cprb_len;
unsigned char cprb_ver_id;
unsigned char pad_000[2];
unsigned char flags;
unsigned char func_id[2];
- uint32_t source_id;
- uint32_t target_id;
- uint32_t ret_code;
- uint32_t reserved1;
- uint32_t reserved2;
- uint32_t payload_len;
+ __u32 source_id;
+ __u32 target_id;
+ __u32 ret_code;
+ __u32 reserved1;
+ __u32 reserved2;
+ __u32 payload_len;
} __attribute__((packed));
/**
* @dom_id: Usage domain id
*/
struct ep11_target_dev {
- uint16_t ap_id;
- uint16_t dom_id;
+ __u16 ap_id;
+ __u16 dom_id;
};
/**
* @resp: Addr to response block
*/
struct ep11_urb {
- uint16_t targets_num;
- uint64_t targets;
- uint64_t weight;
- uint64_t req_no;
- uint64_t req_len;
- uint64_t req;
- uint64_t resp_len;
- uint64_t resp;
+ __u16 targets_num;
+ __u64 targets;
+ __u64 weight;
+ __u64 req_no;
+ __u64 req_len;
+ __u64 req;
+ __u64 resp_len;
+ __u64 resp;
} __attribute__((packed));
/**
* If it comes up a second time then there's something wrong going on:
* just break out and report an unknown stack type.
*/
- if (*visit_mask & (1UL << info->type)) {
- printk_deferred_once(KERN_WARNING
- "WARNING: stack recursion on stack type %d\n",
- info->type);
+ if (*visit_mask & (1UL << info->type))
goto unknown;
- }
*visit_mask |= 1UL << info->type;
return 0;
unknown:
.align 16
.LPG1:
-.Lpcmsk:.quad 0x0000000180000000
-.L4malign:.quad 0xffffffffffc00000
-.Lscan2g:.quad 0x80000000 + 0x20000 - 8 # 2GB + 128K - 8
-.Lnop: .long 0x07000700
-.Lparmaddr:
- .quad PARMAREA
- .align 64
.Ldw: .quad 0x0002000180000000,0x0000000000000000
.Laregs:.long 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
#include <asm/os_info.h>
#include <asm/sections.h>
#include <asm/boot_data.h>
-#include <asm/uv.h>
#include "entry.h"
#define IPL_PARM_BLOCK_VERSION 0
{
switch (reipl_type) {
case IPL_TYPE_CCW:
- uv_set_shared(__pa(reipl_block_ccw));
diag308(DIAG308_SET, reipl_block_ccw);
- uv_remove_shared(__pa(reipl_block_ccw));
diag308(DIAG308_LOAD_CLEAR, NULL);
break;
case IPL_TYPE_FCP:
- uv_set_shared(__pa(reipl_block_fcp));
diag308(DIAG308_SET, reipl_block_fcp);
- uv_remove_shared(__pa(reipl_block_fcp));
diag308(DIAG308_LOAD_CLEAR, NULL);
break;
case IPL_TYPE_NSS:
- uv_set_shared(__pa(reipl_block_nss));
diag308(DIAG308_SET, reipl_block_nss);
- uv_remove_shared(__pa(reipl_block_nss));
diag308(DIAG308_LOAD_CLEAR, NULL);
break;
case IPL_TYPE_UNKNOWN:
static void diag308_dump(void *dump_block)
{
- uv_set_shared(__pa(dump_block));
diag308(DIAG308_SET, dump_block);
- uv_remove_shared(__pa(dump_block));
while (1) {
if (diag308(DIAG308_LOAD_NORMAL_DUMP, NULL) != 0x302)
break;
// SPDX-License-Identifier: GPL-2.0
#include <linux/elf.h>
+#include <asm/kexec.h>
int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
unsigned long addr)
unsigned char start[PAGE_SIZE]; /* Counter set at event start */
unsigned char data[PAGE_SIZE]; /* Counter set at event delete */
};
-DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd);
+static DEFINE_PER_CPU(struct cf_diag_csd, cf_diag_csd);
/* Counter sets are stored as data stream in a page sized memory buffer and
* exported to user space via raw data attached to the event sample data.
ROOT_DEV = Root_RAM0;
- /* Is init_mm really needed? */
- init_mm.start_code = PAGE_OFFSET;
+ init_mm.start_code = (unsigned long) _text;
init_mm.end_code = (unsigned long) _etext;
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = (unsigned long) _end;
432 common fsmount sys_fsmount sys_fsmount
433 common fspick sys_fspick sys_fspick
434 common pidfd_open sys_pidfd_open sys_pidfd_open
-# 435 reserved for clone3
+435 common clone3 sys_clone3 sys_clone3
if (!vdso_enabled)
return 0;
- /*
- * Only map the vdso for dynamically linked elf binaries.
- */
- if (!uses_interp)
- return 0;
vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT_VDSO
SECTIONS
{
. = 0x100000;
- _stext = .; /* Start of text section */
.text : {
- /* Text and read-only data */
- _text = .;
+ _stext = .; /* Start of text section */
+ _text = .; /* Text and read-only data */
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
*(.text.*_indirect_*)
*(.fixup)
*(.gnu.warning)
+ . = ALIGN(PAGE_SIZE);
+ _etext = .; /* End of text section */
} :text = 0x0700
- . = ALIGN(PAGE_SIZE);
- _etext = .; /* End of text section */
-
NOTES :text :note
.dummy : { *(.dummy) } :data
return rc;
}
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return false;
-}
-
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
-{
- return 0;
-}
-
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 3, "%s", "free cpu");
#include <linux/types.h>
#include <linux/export.h>
#include <linux/raid/xor.h>
+#include <asm/xor.h>
static void xor_xc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
}
#endif
- for (i = 0; i < PTRS_PER_PMD && addr < max_addr; i++) {
+ pmd = pmd_offset(pud, addr);
+ for (i = 0; i < PTRS_PER_PMD && addr < max_addr; i++, pmd++) {
st->current_address = addr;
- pmd = pmd_offset(pud, addr);
if (!pmd_none(*pmd)) {
if (pmd_large(*pmd)) {
prot = pmd_val(*pmd) &
}
#endif
- for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++) {
+ pud = pud_offset(p4d, addr);
+ for (i = 0; i < PTRS_PER_PUD && addr < max_addr; i++, pud++) {
st->current_address = addr;
- pud = pud_offset(p4d, addr);
if (!pud_none(*pud))
if (pud_large(*pud)) {
prot = pud_val(*pud) &
}
#endif
- for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++) {
+ p4d = p4d_offset(pgd, addr);
+ for (i = 0; i < PTRS_PER_P4D && addr < max_addr; i++, p4d++) {
st->current_address = addr;
- p4d = p4d_offset(pgd, addr);
if (!p4d_none(*p4d))
walk_pud_level(m, st, p4d, addr);
else
case VM_FAULT_BADACCESS:
if (access == VM_EXEC && signal_return(regs) == 0)
break;
+ /* fallthrough */
case VM_FAULT_BADMAP:
/* Bad memory access. Check if it is kernel or user space. */
if (user_mode(regs)) {
do_sigsegv(regs, si_code);
break;
}
+ /* fallthrough */
case VM_FAULT_BADCONTEXT:
+ /* fallthrough */
case VM_FAULT_PFAULT:
do_no_context(regs);
break;
* This function is assumed to be called with the guest_table_lock
* held.
*/
-bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
- unsigned long gaddr)
+static bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
+ unsigned long gaddr)
{
if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
return false;
#ifdef CONFIG_PGSTE
-static int page_table_allocate_pgste_min = 0;
-static int page_table_allocate_pgste_max = 1;
int page_table_allocate_pgste = 0;
EXPORT_SYMBOL(page_table_allocate_pgste);
.maxlen = sizeof(int),
.mode = S_IRUGO | S_IWUSR,
.proc_handler = proc_dointvec_minmax,
- .extra1 = &page_table_allocate_pgste_min,
- .extra2 = &page_table_allocate_pgste_max,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
},
{ }
};
break;
case BPF_ALU64 | BPF_NEG: /* dst = -dst */
/* lcgr %dst,%dst */
- EMIT4(0xb9130000, dst_reg, dst_reg);
+ EMIT4(0xb9030000, dst_reg, dst_reg);
break;
/*
* BPF_FROM_BE/LE
/* llgf %w1,map.max_entries(%b2) */
EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_2,
offsetof(struct bpf_array, map.max_entries));
- /* clgrj %b3,%w1,0xa,label0: if %b3 >= %w1 goto out */
- EMIT6_PCREL_LABEL(0xec000000, 0x0065, BPF_REG_3,
+ /* clrj %b3,%w1,0xa,label0: if (u32)%b3 >= (u32)%w1 goto out */
+ EMIT6_PCREL_LABEL(0xec000000, 0x0077, BPF_REG_3,
REG_W1, 0, 0xa);
/*
* goto out;
*/
- /* sllg %r1,%b3,3: %r1 = index * 8 */
- EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, BPF_REG_3, REG_0, 3);
+ /* llgfr %r1,%b3: %r1 = (u32) index */
+ EMIT4(0xb9160000, REG_1, BPF_REG_3);
+ /* sllg %r1,%r1,3: %r1 *= 8 */
+ EMIT6_DISP_LH(0xeb000000, 0x000d, REG_1, REG_1, REG_0, 3);
/* lg %r1,prog(%b2,%r1) */
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, BPF_REG_2,
REG_1, offsetof(struct bpf_array, ptrs));
quiet_cmd_chkbss = CHKBSS $<
cmd_chkbss = \
- if $(OBJDUMP) -h $< | grep -q "\.bss" && \
- ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
+ if ! $(OBJSIZE) --common $< | $(AWK) 'END { if ($$3) exit 1 }'; then \
echo "error: $< .bss section is not empty" >&2; exit 1; \
fi; \
touch $@;
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#include <asm-generic/setup.h>
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#include <asm-generic/types.h>
printk("dbr");
break;
case FD_REG_N:
- if (0)
- goto d_reg_n;
case F_REG_N:
printk("fr%d", rn);
break;
printk("xd%d", rn & ~1);
break;
}
- d_reg_n:
+ /* else, fall through */
case D_REG_N:
printk("dr%d", rn);
break;
printk("xd%d", rm & ~1);
break;
}
+ /* else, fall through */
case D_REG_M:
printk("dr%d", rm);
break;
switch (sh_type) {
case SH_BREAKPOINT_READ:
*gen_type = HW_BREAKPOINT_R;
+ break;
case SH_BREAKPOINT_WRITE:
*gen_type = HW_BREAKPOINT_W;
break;
-/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */
/*
* Copyright (c) 2017, Oracle and/or its affiliates. All rights reserved.
*/
time_travel_time = ns;
}
-static inline void time_travel_set_timer(enum time_travel_timer_mode mode,
- unsigned long long expiry)
+static inline void time_travel_set_timer_mode(enum time_travel_timer_mode mode)
{
time_travel_timer_mode = mode;
+}
+
+static inline void time_travel_set_timer_expiry(unsigned long long expiry)
+{
time_travel_timer_expiry = expiry;
}
#else
{
}
-static inline void time_travel_set_timer(enum time_travel_timer_mode mode,
- unsigned long long expiry)
+static inline void time_travel_set_timer_mode(enum time_travel_timer_mode mode)
+{
+}
+
+static inline void time_travel_set_timer_expiry(unsigned long long expiry)
{
}
if (time_travel_timer_mode != TT_TMR_DISABLED ||
time_travel_timer_expiry < next) {
if (time_travel_timer_mode == TT_TMR_ONESHOT)
- time_travel_set_timer(TT_TMR_DISABLED, 0);
+ time_travel_set_timer_mode(TT_TMR_DISABLED);
/*
* time_travel_time will be adjusted in the timer
* IRQ handler so it works even when the signal
static int itimer_shutdown(struct clock_event_device *evt)
{
if (time_travel_mode != TT_MODE_OFF)
- time_travel_set_timer(TT_TMR_DISABLED, 0);
+ time_travel_set_timer_mode(TT_TMR_DISABLED);
if (time_travel_mode != TT_MODE_INFCPU)
os_timer_disable();
{
unsigned long long interval = NSEC_PER_SEC / HZ;
- if (time_travel_mode != TT_MODE_OFF)
- time_travel_set_timer(TT_TMR_PERIODIC,
- time_travel_time + interval);
+ if (time_travel_mode != TT_MODE_OFF) {
+ time_travel_set_timer_mode(TT_TMR_PERIODIC);
+ time_travel_set_timer_expiry(time_travel_time + interval);
+ }
if (time_travel_mode != TT_MODE_INFCPU)
os_timer_set_interval(interval);
{
delta += 1;
- if (time_travel_mode != TT_MODE_OFF)
- time_travel_set_timer(TT_TMR_ONESHOT,
- time_travel_time + delta);
+ if (time_travel_mode != TT_MODE_OFF) {
+ time_travel_set_timer_mode(TT_TMR_ONESHOT);
+ time_travel_set_timer_expiry(time_travel_time + delta);
+ }
if (time_travel_mode != TT_MODE_INFCPU)
return os_timer_one_shot(delta);
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding)
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector)
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member)
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
export REALMODE_CFLAGS
/* Find the first usable memory region under bios_start. */
for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+ unsigned long new = bios_start;
+
entry = &boot_params->e820_table[i];
/* Skip all entries above bios_start. */
/* Adjust bios_start to the end of the entry if needed. */
if (bios_start > entry->addr + entry->size)
- bios_start = entry->addr + entry->size;
+ new = entry->addr + entry->size;
/* Keep bios_start page-aligned. */
- bios_start = round_down(bios_start, PAGE_SIZE);
+ new = round_down(new, PAGE_SIZE);
/* Skip the entry if it's too small. */
- if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr)
+ if (new - TRAMPOLINE_32BIT_SIZE < entry->addr)
continue;
+ /* Protect against underflow. */
+ if (new - TRAMPOLINE_32BIT_SIZE > bios_start)
+ break;
+
+ bios_start = new;
break;
}
return diff;
}
+/*
+ * Clang may lower `memcmp == 0` to `bcmp == 0`.
+ */
+int bcmp(const void *s1, const void *s2, size_t len)
+{
+ return memcmp(s1, s2, len);
+}
+
int strcmp(const char *str1, const char *str2)
{
const unsigned char *s1 = (const unsigned char *)str1;
#endif
+/*
+ * Mitigate Spectre v1 for conditional swapgs code paths.
+ *
+ * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to
+ * prevent a speculative swapgs when coming from kernel space.
+ *
+ * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path,
+ * to prevent the swapgs from getting speculatively skipped when coming from
+ * user space.
+ */
+.macro FENCE_SWAPGS_USER_ENTRY
+ ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER
+.endm
+.macro FENCE_SWAPGS_KERNEL_ENTRY
+ ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL
+.endm
+
.macro STACKLEAK_ERASE_NOCLOBBER
#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
PUSH_AND_CLEAR_REGS
ENTRY(page_fault)
ASM_CLAC
- pushl $0; /* %gs's slot on the stack */
+ pushl $do_page_fault
+ jmp common_exception_read_cr2
+END(page_fault)
+common_exception_read_cr2:
+ /* the function address is in %gs's slot on the stack */
SAVE_ALL switch_stacks=1 skip_gs=1
ENCODE_FRAME_POINTER
/* fixup %gs */
GS_TO_REG %ecx
+ movl PT_GS(%esp), %edi
REG_TO_PTGS %ecx
SET_KERNEL_GS %ecx
TRACE_IRQS_OFF
movl %esp, %eax # pt_regs pointer
- call do_page_fault
+ CALL_NOSPEC %edi
jmp ret_from_exception
-END(page_fault)
+END(common_exception_read_cr2)
common_exception:
/* the function address is in %gs's slot on the stack */
ENTRY(async_page_fault)
ASM_CLAC
pushl $do_async_page_fault
- jmp common_exception
+ jmp common_exception_read_cr2
END(async_page_fault)
#endif
testb $3, CS-ORIG_RAX+8(%rsp)
jz 1f
SWAPGS
-
+ FENCE_SWAPGS_USER_ENTRY
/*
* Switch to the thread stack. The IRET frame and orig_ax are
* on the stack, as well as the return address. RDI..R12 are
UNWIND_HINT_FUNC
movq (%rdi), %rdi
+ jmp 2f
1:
-
+ FENCE_SWAPGS_KERNEL_ENTRY
+2:
PUSH_AND_CLEAR_REGS save_ret=1
ENCODE_FRAME_POINTER 8
*/
SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+ /*
+ * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
+ * unconditional CR3 write, even in the PTI case. So do an lfence
+ * to prevent GS speculation, regardless of whether PTI is enabled.
+ */
+ FENCE_SWAPGS_KERNEL_ENTRY
+
ret
END(paranoid_entry)
* from user mode due to an IRET fault.
*/
SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
/* We have user CR3. Change to kernel CR3. */
SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
pushq %r12
ret
+.Lerror_entry_done_lfence:
+ FENCE_SWAPGS_KERNEL_ENTRY
.Lerror_entry_done:
ret
cmpq %rax, RIP+8(%rsp)
je .Lbstep_iret
cmpq $.Lgs_change, RIP+8(%rsp)
- jne .Lerror_entry_done
+ jne .Lerror_entry_done_lfence
/*
* hack: .Lgs_change can fail with user gsbase. If this happens, fix up
* .Lgs_change's error handler with kernel gsbase.
*/
SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
jmp .Lerror_entry_done
* gsbase and CR3. Switch to kernel gsbase and CR3:
*/
SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
/*
swapgs
cld
+ FENCE_SWAPGS_USER_ENTRY
SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
throttle = perf_event_overflow(event, &data, ®s);
out:
- if (throttle)
+ if (throttle) {
perf_ibs_stop(event, 0);
- else
- perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
+ } else {
+ period >>= 4;
+
+ if ((ibs_caps & IBS_CAPS_RDWROPCNT) &&
+ (*config & IBS_OP_CNT_CTL))
+ period |= *config & IBS_OP_CUR_CNT_RAND;
+
+ perf_ibs_enable_event(perf_ibs, hwc, period);
+ }
perf_event_update_userpage(event);
* Add a single event to the PMU.
*
* The event is added to the group of enabled events
- * but only if it can be scehduled with existing events.
+ * but only if it can be scheduled with existing events.
*/
static int x86_pmu_add(struct perf_event *event, int flags)
{
#include <asm/intel-family.h>
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
-#include <asm/hypervisor.h>
#include "../perf_event.h"
};
static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
- INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
- INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffffbfffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffffbfffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
EVENT_EXTRA_END
return left;
}
+static u64 nhm_limit_period(struct perf_event *event, u64 left)
+{
+ return max(left, 32ULL);
+}
+
PMU_FORMAT_ATTR(event, "config:0-7" );
PMU_FORMAT_ATTR(umask, "config:8-15" );
PMU_FORMAT_ATTR(edge, "config:18" );
* Disable the check for real HW, so we don't
* mess with potentionaly enabled registers:
*/
- if (hypervisor_is_type(X86_HYPER_NATIVE))
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
return true;
/*
x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
x86_pmu.enable_all = intel_pmu_nhm_enable_all;
x86_pmu.extra_regs = intel_nehalem_extra_regs;
+ x86_pmu.limit_period = nhm_limit_period;
mem_attr = nhm_mem_events_attrs;
case INTEL_FAM6_SKYLAKE_X:
pmem = true;
+ /* fall through */
case INTEL_FAM6_SKYLAKE_MOBILE:
case INTEL_FAM6_SKYLAKE_DESKTOP:
case INTEL_FAM6_KABYLAKE_MOBILE:
case INTEL_FAM6_ICELAKE_X:
case INTEL_FAM6_ICELAKE_XEON_D:
pmem = true;
+ /* fall through */
case INTEL_FAM6_ICELAKE_MOBILE:
case INTEL_FAM6_ICELAKE_DESKTOP:
x86_pmu.late_ack = true;
struct event_constraint intel_icl_pebs_event_constraints[] = {
INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
- INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL), /* SLOTS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */
INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
* Lower 12 bits encode the number of additional
* pages to flush (in addition to the 'cur' page).
*/
- if (diff >= HV_TLB_FLUSH_UNIT)
+ if (diff >= HV_TLB_FLUSH_UNIT) {
gva_list[gva_n] |= ~PAGE_MASK;
- else if (diff)
+ cur += HV_TLB_FLUSH_UNIT;
+ } else if (diff) {
gva_list[gva_n] |= (diff - 1) >> PAGE_SHIFT;
+ cur = end;
+ }
- cur += HV_TLB_FLUSH_UNIT;
gva_n++;
} while (cur < end);
* Note: efi_info is commonly left uninitialized, but that field has a
* private magic, so it is better to leave it unchanged.
*/
+
+#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); })
+
+#define BOOT_PARAM_PRESERVE(struct_member) \
+ { \
+ .start = offsetof(struct boot_params, struct_member), \
+ .len = sizeof_mbr(struct boot_params, struct_member), \
+ }
+
+struct boot_params_to_save {
+ unsigned int start;
+ unsigned int len;
+};
+
static void sanitize_boot_params(struct boot_params *boot_params)
{
/*
* problems again.
*/
if (boot_params->sentinel) {
- /* fields in boot_params are left uninitialized, clear them */
- boot_params->acpi_rsdp_addr = 0;
- memset(&boot_params->ext_ramdisk_image, 0,
- (char *)&boot_params->efi_info -
- (char *)&boot_params->ext_ramdisk_image);
- memset(&boot_params->kbd_status, 0,
- (char *)&boot_params->hdr -
- (char *)&boot_params->kbd_status);
- memset(&boot_params->_pad7[0], 0,
- (char *)&boot_params->edd_mbr_sig_buffer[0] -
- (char *)&boot_params->_pad7[0]);
- memset(&boot_params->_pad8[0], 0,
- (char *)&boot_params->eddbuf[0] -
- (char *)&boot_params->_pad8[0]);
- memset(&boot_params->_pad9[0], 0, sizeof(boot_params->_pad9));
+ static struct boot_params scratch;
+ char *bp_base = (char *)boot_params;
+ char *save_base = (char *)&scratch;
+ int i;
+
+ const struct boot_params_to_save to_save[] = {
+ BOOT_PARAM_PRESERVE(screen_info),
+ BOOT_PARAM_PRESERVE(apm_bios_info),
+ BOOT_PARAM_PRESERVE(tboot_addr),
+ BOOT_PARAM_PRESERVE(ist_info),
+ BOOT_PARAM_PRESERVE(hd0_info),
+ BOOT_PARAM_PRESERVE(hd1_info),
+ BOOT_PARAM_PRESERVE(sys_desc_table),
+ BOOT_PARAM_PRESERVE(olpc_ofw_header),
+ BOOT_PARAM_PRESERVE(efi_info),
+ BOOT_PARAM_PRESERVE(alt_mem_k),
+ BOOT_PARAM_PRESERVE(scratch),
+ BOOT_PARAM_PRESERVE(e820_entries),
+ BOOT_PARAM_PRESERVE(eddbuf_entries),
+ BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries),
+ BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer),
+ BOOT_PARAM_PRESERVE(secure_boot),
+ BOOT_PARAM_PRESERVE(hdr),
+ BOOT_PARAM_PRESERVE(e820_table),
+ BOOT_PARAM_PRESERVE(eddbuf),
+ };
+
+ memset(&scratch, 0, sizeof(scratch));
+
+ for (i = 0; i < ARRAY_SIZE(to_save); i++) {
+ memcpy(save_base + to_save[i].start,
+ bp_base + to_save[i].start, to_save[i].len);
+ }
+
+ memcpy(boot_params, save_base, sizeof(*boot_params));
}
}
#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* LLC occupancy monitoring */
#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* LLC Total MBM monitoring */
#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */
+#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
+#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
#define X86_BUG_L1TF X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */
+#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
#endif /* _ASM_X86_CPUFEATURES_H */
#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
#ifndef __ASSEMBLY__
-extern void mcount(void);
extern atomic_t modifying_ftrace_code;
extern void __fentry__(void);
* While adding a new CPUID for a new microarchitecture, add a new
* group to keep logically sorted out in chronological order. Within
* that group keep the CPUID for the variants sorted by model number.
+ *
+ * The defined symbol names have the following form:
+ * INTEL_FAM6{OPTFAMILY}_{MICROARCH}{OPTDIFF}
+ * where:
+ * OPTFAMILY Describes the family of CPUs that this belongs to. Default
+ * is assumed to be "_CORE" (and should be omitted). Other values
+ * currently in use are _ATOM and _XEON_PHI
+ * MICROARCH Is the code name for the micro-architecture for this core.
+ * N.B. Not the platform name.
+ * OPTDIFF If needed, a short string to differentiate by market segment.
+ * Exact strings here will vary over time. _DESKTOP, _MOBILE, and
+ * _X (short for Xeon server) should be used when they are
+ * appropriate.
+ *
+ * The #define line may optionally include a comment including platform names.
*/
#define INTEL_FAM6_CORE_YONAH 0x0E
#include <asm/kvm_vcpu_regs.h>
#include <asm/hyperv-tlfs.h>
+#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
+
#define KVM_MAX_VCPUS 288
#define KVM_SOFT_MAX_VCPUS 240
#define KVM_MAX_VCPU_ID 1023
/*
* QEMU userspace and the guest each have their own FPU state.
- * In vcpu_run, we switch between the user, maintained in the
- * task_struct struct, and guest FPU contexts. While running a VCPU,
- * the VCPU thread will have the guest FPU context.
+ * In vcpu_run, we switch between the user and guest FPU contexts.
+ * While running a VCPU, the VCPU thread will have the guest FPU
+ * context.
*
* Note that while the PKRU state lives inside the fpu registers,
* it is switched out separately at VMENTER and VMEXIT time. The
* "guest_fpu" state here contains the guest FPU context, with the
* host PRKU bits.
*/
+ struct fpu *user_fpu;
struct fpu *guest_fpu;
u64 xcr0;
int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
+ bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
bool *expired);
#define MSR_AMD64_PATCH_LEVEL 0x0000008b
#define MSR_AMD64_TSC_RATIO 0xc0000104
#define MSR_AMD64_NB_CFG 0xc001001f
+#define MSR_AMD64_CPUID_FN_1 0xc0011004
#define MSR_AMD64_PATCH_LOADER 0xc0010020
#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
#define MSR_AMD64_OSVW_STATUS 0xc0010141
" lfence;\n" \
" jmp 902b;\n" \
" .align 16\n" \
- "903: addl $4, %%esp;\n" \
+ "903: lea 4(%%esp), %%esp;\n" \
" pushl %[thunk_target];\n" \
" ret;\n" \
" .align 16\n" \
#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8)
#define IBSCTL_LVT_OFFSET_MASK 0x0F
-/* ibs fetch bits/masks */
+/* IBS fetch bits/masks */
#define IBS_FETCH_RAND_EN (1ULL<<57)
#define IBS_FETCH_VAL (1ULL<<49)
#define IBS_FETCH_ENABLE (1ULL<<48)
#define IBS_FETCH_CNT 0xFFFF0000ULL
#define IBS_FETCH_MAX_CNT 0x0000FFFFULL
-/* ibs op bits/masks */
-/* lower 4 bits of the current count are ignored: */
-#define IBS_OP_CUR_CNT (0xFFFF0ULL<<32)
+/*
+ * IBS op bits/masks
+ * The lower 7 bits of the current count are random bits
+ * preloaded by hardware and ignored in software
+ */
+#define IBS_OP_CUR_CNT (0xFFF80ULL<<32)
+#define IBS_OP_CUR_CNT_RAND (0x0007FULL<<32)
#define IBS_OP_CNT_CTL (1ULL<<19)
#define IBS_OP_VAL (1ULL<<18)
#define IBS_OP_ENABLE (1ULL<<17)
({ \
int __gu_err; \
__inttype(*(ptr)) __gu_val; \
+ __typeof__(ptr) __gu_ptr = (ptr); \
+ __typeof__(size) __gu_size = (size); \
__uaccess_begin_nospec(); \
- __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \
+ __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err, -EFAULT); \
__uaccess_end(); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
__builtin_expect(__gu_err, 0); \
#else
+#define VDSO_HAS_32BIT_FALLBACK 1
+
static __always_inline
long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
{
return ret;
}
+static __always_inline
+long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_gettime), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
static __always_inline
long gettimeofday_fallback(struct __kernel_old_timeval *_tv,
struct timezone *_tz)
return ret;
}
+static __always_inline
+long clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*_ts)
+ : "0" (__NR_clock_getres), [clock] "g" (_clkid), "c" (_ts)
+ : "edx");
+
+ return ret;
+}
+
#endif
#ifdef CONFIG_PARAVIRT_CLOCK
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_X86_BYTEORDER_H
#define _ASM_X86_BYTEORDER_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_X86_HWCAP2_H
#define _ASM_X86_HWCAP2_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_X86_SIGCONTEXT32_H
#define _ASM_X86_SIGCONTEXT32_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_X86_TYPES_H
#define _ASM_X86_TYPES_H
static __initdata unsigned long lapic_cal_j1, lapic_cal_j2;
/*
- * Temporary interrupt handler.
+ * Temporary interrupt handler and polled calibration function.
*/
static void __init lapic_cal_handler(struct clock_event_device *dev)
{
static int __init calibrate_APIC_clock(void)
{
struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
- void (*real_handler)(struct clock_event_device *dev);
+ u64 tsc_perj = 0, tsc_start = 0;
+ unsigned long jif_start;
unsigned long deltaj;
long delta, deltatsc;
int pm_referenced = 0;
apic_printk(APIC_VERBOSE, "Using local APIC timer interrupts.\n"
"calibrating APIC timer ...\n");
+ /*
+ * There are platforms w/o global clockevent devices. Instead of
+ * making the calibration conditional on that, use a polling based
+ * approach everywhere.
+ */
local_irq_disable();
- /* Replace the global interrupt handler */
- real_handler = global_clock_event->event_handler;
- global_clock_event->event_handler = lapic_cal_handler;
-
/*
* Setup the APIC counter to maximum. There is no way the lapic
* can underflow in the 100ms detection time frame
*/
__setup_APIC_LVTT(0xffffffff, 0, 0);
- /* Let the interrupts run */
+ /*
+ * Methods to terminate the calibration loop:
+ * 1) Global clockevent if available (jiffies)
+ * 2) TSC if available and frequency is known
+ */
+ jif_start = READ_ONCE(jiffies);
+
+ if (tsc_khz) {
+ tsc_start = rdtsc();
+ tsc_perj = div_u64((u64)tsc_khz * 1000, HZ);
+ }
+
+ /*
+ * Enable interrupts so the tick can fire, if a global
+ * clockevent device is available
+ */
local_irq_enable();
- while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
- cpu_relax();
+ while (lapic_cal_loops <= LAPIC_CAL_LOOPS) {
+ /* Wait for a tick to elapse */
+ while (1) {
+ if (tsc_khz) {
+ u64 tsc_now = rdtsc();
+ if ((tsc_now - tsc_start) >= tsc_perj) {
+ tsc_start += tsc_perj;
+ break;
+ }
+ } else {
+ unsigned long jif_now = READ_ONCE(jiffies);
- local_irq_disable();
+ if (time_after(jif_now, jif_start)) {
+ jif_start = jif_now;
+ break;
+ }
+ }
+ cpu_relax();
+ }
- /* Restore the real event handler */
- global_clock_event->event_handler = real_handler;
+ /* Invoke the calibration routine */
+ local_irq_disable();
+ lapic_cal_handler(NULL);
+ local_irq_enable();
+ }
+
+ local_irq_disable();
/* Build delta t1-t2 as apic timer counts down */
delta = lapic_cal_t1 - lapic_cal_t2;
levt->features &= ~CLOCK_EVT_FEAT_DUMMY;
/*
- * PM timer calibration failed or not turned on
- * so lets try APIC timer based calibration
+ * PM timer calibration failed or not turned on so lets try APIC
+ * timer based calibration, if a global clockevent device is
+ * available.
*/
- if (!pm_referenced) {
+ if (!pm_referenced && global_clock_event) {
apic_printk(APIC_VERBOSE, "... verify APIC timer\n");
/*
return early_per_cpu(x86_cpu_to_apicid, cpu);
}
-static inline unsigned long calculate_ldr(int cpu)
-{
- unsigned long val, id;
-
- val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
- id = per_cpu(x86_bios_cpu_apicid, cpu);
- val |= SET_APIC_LOGICAL_ID(id);
-
- return val;
-}
-
/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116). So here it goes...
+ * bigsmp enables physical destination mode
+ * and doesn't use LDR and DFR
*/
static void bigsmp_init_apic_ldr(void)
{
- unsigned long val;
- int cpu = smp_processor_id();
-
- apic_write(APIC_DFR, APIC_DFR_FLAT);
- val = calculate_ldr(cpu);
- apic_write(APIC_LDR, val);
}
static void bigsmp_setup_apic_routing(void)
* dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use
* gsi_top if ioapic_dynirq_base hasn't been initialized yet.
*/
- return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
+ if (!ioapic_initialized)
+ return gsi_top;
+ /*
+ * For DT enabled machines ioapic_dynirq_base is irrelevant and not
+ * updated. So simply return @from if ioapic_dynirq_base == 0.
+ */
+ return ioapic_dynirq_base ? : from;
}
#ifdef CONFIG_X86_32
def_to_bigsmp = 0;
break;
}
- /* If P4 and above fall through */
+ /* P4 and above */
+ /* fall through */
case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
def_to_bigsmp = 1;
msr_set_bit(MSR_AMD64_DE_CFG, 31);
}
+static bool rdrand_force;
+
+static int __init rdrand_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "force"))
+ rdrand_force = true;
+ else
+ return -EINVAL;
+
+ return 0;
+}
+early_param("rdrand", rdrand_cmdline);
+
+static void clear_rdrand_cpuid_bit(struct cpuinfo_x86 *c)
+{
+ /*
+ * Saving of the MSR used to hide the RDRAND support during
+ * suspend/resume is done by arch/x86/power/cpu.c, which is
+ * dependent on CONFIG_PM_SLEEP.
+ */
+ if (!IS_ENABLED(CONFIG_PM_SLEEP))
+ return;
+
+ /*
+ * The nordrand option can clear X86_FEATURE_RDRAND, so check for
+ * RDRAND support using the CPUID function directly.
+ */
+ if (!(cpuid_ecx(1) & BIT(30)) || rdrand_force)
+ return;
+
+ msr_clear_bit(MSR_AMD64_CPUID_FN_1, 62);
+
+ /*
+ * Verify that the CPUID change has occurred in case the kernel is
+ * running virtualized and the hypervisor doesn't support the MSR.
+ */
+ if (cpuid_ecx(1) & BIT(30)) {
+ pr_info_once("BIOS may not properly restore RDRAND after suspend, but hypervisor does not support hiding RDRAND via CPUID.\n");
+ return;
+ }
+
+ clear_cpu_cap(c, X86_FEATURE_RDRAND);
+ pr_info_once("BIOS may not properly restore RDRAND after suspend, hiding RDRAND via CPUID. Use rdrand=force to reenable.\n");
+}
+
+static void init_amd_jg(struct cpuinfo_x86 *c)
+{
+ /*
+ * Some BIOS implementations do not restore proper RDRAND support
+ * across suspend and resume. Check on whether to hide the RDRAND
+ * instruction support via CPUID.
+ */
+ clear_rdrand_cpuid_bit(c);
+}
+
static void init_amd_bd(struct cpuinfo_x86 *c)
{
u64 value;
wrmsrl_safe(MSR_F15H_IC_CFG, value);
}
}
+
+ /*
+ * Some BIOS implementations do not restore proper RDRAND support
+ * across suspend and resume. Check on whether to hide the RDRAND
+ * instruction support via CPUID.
+ */
+ clear_rdrand_cpuid_bit(c);
}
static void init_amd_zn(struct cpuinfo_x86 *c)
case 0x10: init_amd_gh(c); break;
case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
+ case 0x16: init_amd_jg(c); break;
case 0x17: init_amd_zn(c); break;
}
#include "cpu.h"
+static void __init spectre_v1_select_mitigation(void);
static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
if (boot_cpu_has(X86_FEATURE_STIBP))
x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
- /* Select the proper spectre mitigation before patching alternatives */
+ /* Select the proper CPU mitigations before patching alternatives: */
+ spectre_v1_select_mitigation();
spectre_v2_select_mitigation();
-
- /*
- * Select proper mitigation for any exposure to the Speculative Store
- * Bypass vulnerability.
- */
ssb_select_mitigation();
-
l1tf_select_mitigation();
-
mds_select_mitigation();
arch_smt_update();
}
early_param("mds", mds_cmdline);
+#undef pr_fmt
+#define pr_fmt(fmt) "Spectre V1 : " fmt
+
+enum spectre_v1_mitigation {
+ SPECTRE_V1_MITIGATION_NONE,
+ SPECTRE_V1_MITIGATION_AUTO,
+};
+
+static enum spectre_v1_mitigation spectre_v1_mitigation __ro_after_init =
+ SPECTRE_V1_MITIGATION_AUTO;
+
+static const char * const spectre_v1_strings[] = {
+ [SPECTRE_V1_MITIGATION_NONE] = "Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers",
+ [SPECTRE_V1_MITIGATION_AUTO] = "Mitigation: usercopy/swapgs barriers and __user pointer sanitization",
+};
+
+/*
+ * Does SMAP provide full mitigation against speculative kernel access to
+ * userspace?
+ */
+static bool smap_works_speculatively(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_SMAP))
+ return false;
+
+ /*
+ * On CPUs which are vulnerable to Meltdown, SMAP does not
+ * prevent speculative access to user data in the L1 cache.
+ * Consider SMAP to be non-functional as a mitigation on these
+ * CPUs.
+ */
+ if (boot_cpu_has(X86_BUG_CPU_MELTDOWN))
+ return false;
+
+ return true;
+}
+
+static void __init spectre_v1_select_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) {
+ spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+ return;
+ }
+
+ if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) {
+ /*
+ * With Spectre v1, a user can speculatively control either
+ * path of a conditional swapgs with a user-controlled GS
+ * value. The mitigation is to add lfences to both code paths.
+ *
+ * If FSGSBASE is enabled, the user can put a kernel address in
+ * GS, in which case SMAP provides no protection.
+ *
+ * [ NOTE: Don't check for X86_FEATURE_FSGSBASE until the
+ * FSGSBASE enablement patches have been merged. ]
+ *
+ * If FSGSBASE is disabled, the user can only put a user space
+ * address in GS. That makes an attack harder, but still
+ * possible if there's no SMAP protection.
+ */
+ if (!smap_works_speculatively()) {
+ /*
+ * Mitigation can be provided from SWAPGS itself or
+ * PTI as the CR3 write in the Meltdown mitigation
+ * is serializing.
+ *
+ * If neither is there, mitigate with an LFENCE to
+ * stop speculation through swapgs.
+ */
+ if (boot_cpu_has_bug(X86_BUG_SWAPGS) &&
+ !boot_cpu_has(X86_FEATURE_PTI))
+ setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_USER);
+
+ /*
+ * Enable lfences in the kernel entry (non-swapgs)
+ * paths, to prevent user entry from speculatively
+ * skipping swapgs.
+ */
+ setup_force_cpu_cap(X86_FEATURE_FENCE_SWAPGS_KERNEL);
+ }
+ }
+
+ pr_info("%s\n", spectre_v1_strings[spectre_v1_mitigation]);
+}
+
+static int __init nospectre_v1_cmdline(char *str)
+{
+ spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+ return 0;
+}
+early_param("nospectre_v1", nospectre_v1_cmdline);
+
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V2 : " fmt
static ssize_t mds_show_state(char *buf)
{
- if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
return sprintf(buf, "%s; SMT Host state unknown\n",
mds_strings[mds_mitigation]);
}
break;
case X86_BUG_SPECTRE_V1:
- return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+ return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]);
case X86_BUG_SPECTRE_V2:
return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
#define NO_L1TF BIT(3)
#define NO_MDS BIT(4)
#define MSBDS_ONLY BIT(5)
+#define NO_SWAPGS BIT(6)
#define VULNWL(_vendor, _family, _model, _whitelist) \
{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION),
VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),
- VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY),
- VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_SILVERMONT_X, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
+ VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(CORE_YONAH, NO_SSB),
- VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY),
+ VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
- VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF),
- VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF),
- VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF),
+ VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_GOLDMONT_X, NO_MDS | NO_L1TF | NO_SWAPGS),
+ VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS),
+
+ /*
+ * Technically, swapgs isn't serializing on AMD (despite it previously
+ * being documented as such in the APM). But according to AMD, %gs is
+ * updated non-speculatively, and the issuing of %gs-relative memory
+ * operands will be blocked until the %gs update completes, which is
+ * good enough for our purposes.
+ */
/* AMD Family 0xf - 0x12 */
- VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
- VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
- VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
- VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
{}
};
setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
}
+ if (!cpu_matches(NO_SWAPGS))
+ setup_force_cpu_bug(X86_BUG_SWAPGS);
+
if (cpu_matches(NO_MELTDOWN))
return;
case 7:
if (size < 0x40)
break;
+ /* Else, fall through */
case 6:
case 5:
case 4:
*/
static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+/*
+ * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
+ * hardware or BIOS before kernel boot.
+ */
+static u32 orig_umwait_control_cached __ro_after_init;
+
/*
* Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
* the sysfs write functions.
return 0;
}
+/*
+ * The CPU hotplug callback sets the control MSR to the original control
+ * value.
+ */
+static int umwait_cpu_offline(unsigned int cpu)
+{
+ /*
+ * This code is protected by the CPU hotplug already and
+ * orig_umwait_control_cached is never changed after it caches
+ * the original control MSR value in umwait_init(). So there
+ * is no race condition here.
+ */
+ wrmsr(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached, 0);
+
+ return 0;
+}
+
/*
* On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
* is the only active CPU at this time. The MSR is set up on the APs via the
if (!boot_cpu_has(X86_FEATURE_WAITPKG))
return -ENODEV;
+ /*
+ * Cache the original control MSR value before the control MSR is
+ * changed. This is the only place where orig_umwait_control_cached
+ * is modified.
+ */
+ rdmsrl(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
+
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
- umwait_cpu_online, NULL);
+ umwait_cpu_online, umwait_cpu_offline);
+ if (ret < 0) {
+ /*
+ * On failure, the control MSR on all CPUs has the
+ * original control value.
+ */
+ return ret;
+ }
register_syscore_ops(&umwait_syscore_ops);
/* Set up %gs.
*
- * The base of %gs always points to the bottom of the irqstack
- * union. If the stack protector canary is enabled, it is
- * located at %gs:40. Note that, on SMP, the boot cpu uses
- * init data section till per cpu areas are set up.
+ * The base of %gs always points to fixed_percpu_data. If the
+ * stack protector canary is enabled, it is located at %gs:40.
+ * Note that, on SMP, the boot cpu uses init data section until
+ * the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
movl initial_gs(%rip),%eax
if (!hpet_cfg_working())
goto out_nohpet;
- /* Validate that the counter is counting */
- if (!hpet_counting())
- goto out_nohpet;
-
/*
* Read the period and check for a sane value:
*/
}
hpet_print_config();
+ /*
+ * Validate that the counter is counting. This needs to be done
+ * after sanitizing the config registers to properly deal with
+ * force enabled HPETs.
+ */
+ if (!hpet_counting())
+ goto out_nohpet;
+
clocksource_register_hz(&clocksource_hpet, (u32)hpet_freq);
if (id & HPET_ID_LEGSUP) {
static void kvm_guest_cpu_init(void)
{
- if (!kvm_para_available())
- return;
-
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
{
int i;
- if (!kvm_para_available())
- return;
-
paravirt_ops_setup();
register_reboot_notifier(&kvm_pv_reboot_nb);
for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
*/
void __init kvm_spinlock_init(void)
{
- if (!kvm_para_available())
- return;
/* Does host kernel support KVM_FEATURE_PV_UNHALT? */
if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
return;
case offsetof(struct user_regs_struct, ss):
if (unlikely(value == 0))
return -EIO;
+ /* Else, fall through */
default:
*pt_regs_access(task_pt_regs(task), offset) = value;
{
int ret;
- if (!access_ok(fp, sizeof(*frame)))
+ if (__range_not_ok(fp, sizeof(*frame), TASK_SIZE))
return 0;
ret = 1;
{},
};
+/*
+ * Some devices have a portrait LCD but advertise a landscape resolution (and
+ * pitch). We simply swap width and height for these devices so that we can
+ * correctly deal with some of them coming with multiple resolutions.
+ */
+static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = {
+ {
+ /*
+ * Lenovo MIIX310-10ICR, only some batches have the troublesome
+ * 800x1280 portrait screen. Luckily the portrait version has
+ * its own BIOS version, so we match on that.
+ */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "MIIX 310-10ICR"),
+ DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1HCN44WW"),
+ },
+ },
+ {
+ /* Lenovo MIIX 320-10ICR with 800x1280 portrait screen */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+ "Lenovo MIIX 320-10ICR"),
+ },
+ },
+ {
+ /* Lenovo D330 with 800x1280 or 1200x1920 portrait screen */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+ "Lenovo ideapad D330-10IGM"),
+ },
+ },
+ {},
+};
+
__init void sysfb_apply_efi_quirks(void)
{
if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
!(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
dmi_check_system(efifb_dmi_system_table);
+
+ if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI &&
+ dmi_check_system(efifb_dmi_swap_width_height)) {
+ u16 temp = screen_info.lfb_width;
+
+ screen_info.lfb_width = screen_info.lfb_height;
+ screen_info.lfb_height = temp;
+ screen_info.lfb_linelength = 4 * screen_info.lfb_width;
+ }
}
void (*abort)(struct arch_uprobe *, struct pt_regs *);
};
-static inline int sizeof_long(void)
+static inline int sizeof_long(struct pt_regs *regs)
{
- return in_ia32_syscall() ? 4 : 8;
+ /*
+ * Check registers for mode as in_xxx_syscall() does not apply here.
+ */
+ return user_64bit_mode(regs) ? 8 : 4;
}
static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
{
- unsigned long new_sp = regs->sp - sizeof_long();
+ unsigned long new_sp = regs->sp - sizeof_long(regs);
- if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
+ if (copy_to_user((void __user *)new_sp, &val, sizeof_long(regs)))
return -EFAULT;
regs->sp = new_sp;
long correction = utask->vaddr - utask->xol_vaddr;
regs->ip += correction;
} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
- regs->sp += sizeof_long(); /* Pop incorrect return address */
+ regs->sp += sizeof_long(regs); /* Pop incorrect return address */
if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
return -ERESTART;
}
* "call" insn was executed out-of-line. Just restore ->sp and restart.
* We could also restore ->ip and try to call branch_emulate_op() again.
*/
- regs->sp += sizeof_long();
+ regs->sp += sizeof_long(regs);
return -ERESTART;
}
unsigned long
arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
{
- int rasize = sizeof_long(), nleft;
+ int rasize = sizeof_long(regs), nleft;
unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize))
#include <linux/debugfs.h>
#include "lapic.h"
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return true;
-}
-
static int vcpu_get_timer_advance_ns(void *data, u64 *val)
{
struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bits, NULL, "%llu\n");
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
- struct dentry *ret;
-
- ret = debugfs_create_file("tsc-offset", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_tsc_offset_fops);
- if (!ret)
- return -ENOMEM;
+ debugfs_create_file("tsc-offset", 0444, vcpu->debugfs_dentry, vcpu,
+ &vcpu_tsc_offset_fops);
- if (lapic_in_kernel(vcpu)) {
- ret = debugfs_create_file("lapic_timer_advance_ns", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_timer_advance_ns_fops);
- if (!ret)
- return -ENOMEM;
- }
+ if (lapic_in_kernel(vcpu))
+ debugfs_create_file("lapic_timer_advance_ns", 0444,
+ vcpu->debugfs_dentry, vcpu,
+ &vcpu_timer_advance_ns_fops);
if (kvm_has_tsc_control) {
- ret = debugfs_create_file("tsc-scaling-ratio", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_tsc_scaling_fops);
- if (!ret)
- return -ENOMEM;
- ret = debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_tsc_scaling_frac_fops);
- if (!ret)
- return -ENOMEM;
-
+ debugfs_create_file("tsc-scaling-ratio", 0444,
+ vcpu->debugfs_dentry, vcpu,
+ &vcpu_tsc_scaling_fops);
+ debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
+ vcpu->debugfs_dentry, vcpu,
+ &vcpu_tsc_scaling_frac_fops);
}
-
- return 0;
}
int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries)
{
- uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+ uint16_t evmcs_ver = 0;
struct kvm_cpuid_entry2 cpuid_entries[] = {
{ .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
{ .function = HYPERV_CPUID_INTERFACE },
};
int i, nent = ARRAY_SIZE(cpuid_entries);
+ if (kvm_x86_ops->nested_get_evmcs_version)
+ evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+
/* Skip NESTED_FEATURES if eVMCS is not supported */
if (!evmcs_ver)
--nent;
if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
new->phys_map[xapic_id] = apic;
+ if (!kvm_apic_sw_enabled(apic))
+ continue;
+
ldr = kvm_lapic_get_reg(apic, APIC_LDR);
if (apic_x2apic_mode(apic)) {
static_key_slow_dec_deferred(&apic_sw_disabled);
else
static_key_slow_inc(&apic_sw_disabled.key);
+
+ recalculate_apic_map(apic->vcpu->kvm);
}
}
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
- struct swait_queue_head *q = &vcpu->wq;
struct kvm_timer *ktimer = &apic->lapic_timer;
if (atomic_read(&apic->lapic_timer.pending))
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
-
- /*
- * For x86, the atomic_inc() is serialized, thus
- * using swait_active() is safe.
- */
- if (swait_active(q))
- swake_up_one(q);
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
/*
* Currently, fast page fault only works for direct mapping
* since the gfn is not stable for indirect shadow page. See
- * Documentation/virtual/kvm/locking.txt to get more detail.
+ * Documentation/virt/kvm/locking.txt to get more detail.
*/
fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
iterator.sptep, spte,
struct kvm_memory_slot *slot,
struct kvm_page_track_notifier_node *node)
{
- struct kvm_mmu_page *sp;
- LIST_HEAD(invalid_list);
- unsigned long i;
- bool flush;
- gfn_t gfn;
-
- spin_lock(&kvm->mmu_lock);
-
- if (list_empty(&kvm->arch.active_mmu_pages))
- goto out_unlock;
-
- flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false);
-
- for (i = 0; i < slot->npages; i++) {
- gfn = slot->base_gfn + i;
-
- for_each_valid_sp(kvm, sp, gfn) {
- if (sp->gfn != gfn)
- continue;
-
- kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
- }
- if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
- kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
- flush = false;
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
- kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
-
-out_unlock:
- spin_unlock(&kvm->mmu_lock);
+ kvm_mmu_zap_all(kvm);
}
void kvm_mmu_init_vm(struct kvm *kvm)
if (!entry)
return -EINVAL;
- new_entry = READ_ONCE(*entry);
new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
goto out;
}
+ svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+ GFP_KERNEL_ACCOUNT);
+ if (!svm->vcpu.arch.user_fpu) {
+ printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+ err = -ENOMEM;
+ goto free_partial_svm;
+ }
+
svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
GFP_KERNEL_ACCOUNT);
if (!svm->vcpu.arch.guest_fpu) {
printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
err = -ENOMEM;
- goto free_partial_svm;
+ goto free_user_fpu;
}
err = kvm_vcpu_init(&svm->vcpu, kvm, id);
kvm_vcpu_uninit(&svm->vcpu);
free_svm:
kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
+free_user_fpu:
+ kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
free_partial_svm:
kmem_cache_free(kvm_vcpu_cache, svm);
out:
__free_page(virt_to_page(svm->nested.hsave));
__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
kvm_vcpu_uninit(vcpu);
+ kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
kmem_cache_free(kvm_vcpu_cache, svm);
}
kvm_vcpu_wake_up(vcpu);
}
+static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
{
unsigned long flags;
return ret;
}
-static uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
-{
- /* Not supported */
- return 0;
-}
-
static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version)
{
.pmu_ops = &amd_pmu_ops,
.deliver_posted_interrupt = svm_deliver_avic_intr,
+ .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
.update_pi_irte = svm_update_pi_irte,
.setup_mce = svm_setup_mce,
.mem_enc_unreg_region = svm_unregister_enc_region,
.nested_enable_evmcs = nested_enable_evmcs,
- .nested_get_evmcs_version = nested_get_evmcs_version,
+ .nested_get_evmcs_version = NULL,
.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
};
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
+ kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+
vmx->nested.vmxon = false;
vmx->nested.smm.vmxon = false;
free_vpid(vmx->nested.vpid02);
vmx->vmcs01.shadow_vmcs = NULL;
}
kfree(vmx->nested.cached_vmcs12);
+ vmx->nested.cached_vmcs12 = NULL;
kfree(vmx->nested.cached_shadow_vmcs12);
+ vmx->nested.cached_shadow_vmcs12 = NULL;
/* Unpin physical memory we referred to in the vmcs02 */
if (vmx->nested.apic_access_page) {
kvm_release_page_dirty(vmx->nested.apic_access_page);
return max_irr;
}
+static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+ return pi_test_on(vcpu_to_pi_desc(vcpu));
+}
+
static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
{
if (!kvm_vcpu_apicv_active(vcpu))
free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
+ kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
}
if (!vmx)
return ERR_PTR(-ENOMEM);
+ vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+ GFP_KERNEL_ACCOUNT);
+ if (!vmx->vcpu.arch.user_fpu) {
+ printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+ err = -ENOMEM;
+ goto free_partial_vcpu;
+ }
+
vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
GFP_KERNEL_ACCOUNT);
if (!vmx->vcpu.arch.guest_fpu) {
printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
err = -ENOMEM;
- goto free_partial_vcpu;
+ goto free_user_fpu;
}
vmx->vpid = allocate_vpid();
free_vcpu:
free_vpid(vmx->vpid);
kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+free_user_fpu:
+ kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
free_partial_vcpu:
kmem_cache_free(kvm_vcpu_cache, vmx);
return ERR_PTR(err);
.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
.sync_pir_to_irr = vmx_sync_pir_to_irr,
.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+ .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt,
.set_tss_addr = vmx_set_tss_addr,
.set_identity_map_addr = vmx_set_identity_map_addr,
.set_nested_state = NULL,
.get_vmcs12_pages = NULL,
.nested_enable_evmcs = NULL,
+ .nested_get_evmcs_version = NULL,
.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
};
kvm_x86_ops->vcpu_load(vcpu, cpu);
+ fpregs_assert_state_consistent();
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ switch_fpu_return();
+
/* Apply any externally detected TSC adjustments (due to suspend) */
if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
- kvm_rip_write(vcpu, ctxt->eip);
- if (r == EMULATE_DONE && ctxt->tf)
- kvm_vcpu_do_singlestep(vcpu, &r);
if (!ctxt->have_exception ||
- exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+ kvm_rip_write(vcpu, ctxt->eip);
+ if (r == EMULATE_DONE && ctxt->tf)
+ kvm_vcpu_do_singlestep(vcpu, &r);
__kvm_set_rflags(vcpu, ctxt->eflags);
+ }
/*
* For STI, interrupts are shadowed; so KVM_REQ_EVENT will
rcu_read_unlock();
- if (target)
+ if (target && READ_ONCE(target->ready))
kvm_vcpu_yield_to(target);
}
break;
case KVM_HC_KICK_CPU:
kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+ kvm_sched_yield(vcpu->kvm, a1);
ret = 0;
break;
#ifdef CONFIG_X86_64
trace_kvm_entry(vcpu->vcpu_id);
guest_enter_irqoff();
- fpregs_assert_state_consistent();
- if (test_thread_flag(TIF_NEED_FPU_LOAD))
- switch_fpu_return();
+ /* The preempt notifier should have taken care of the FPU already. */
+ WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
if (unlikely(vcpu->arch.switch_db_regs)) {
set_debugreg(0, 7);
{
fpregs_lock();
- copy_fpregs_to_fpstate(¤t->thread.fpu);
+ copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
/* PKRU is separately restored in kvm_x86_ops->run. */
__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
~XFEATURE_MASK_PKRU);
fpregs_lock();
copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
- copy_kernel_to_fpregs(¤t->thread.fpu.state);
+ copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
fpregs_mark_activate();
fpregs_unlock();
return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
}
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
+ return true;
+
+ if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+ kvm_test_request(KVM_REQ_SMI, vcpu) ||
+ kvm_test_request(KVM_REQ_EVENT, vcpu))
+ return true;
+
+ if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu))
+ return true;
+
+ return false;
+}
+
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
return vcpu->arch.preempted_in_kernel;
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/types.h>
#include <linux/export.h>
+#include <asm/cpu.h>
unsigned int x86_family(unsigned int sig)
{
for (i = 0; i < 8; i++) {
FPU_REG *r = &st(i);
u_char tagi = FPU_gettagi(i);
+
switch (tagi) {
case TAG_Empty:
continue;
- break;
case TAG_Zero:
case TAG_Special:
+ /* Update tagi for the printk below */
tagi = FPU_Special(r);
+ /* fall through */
case TAG_Valid:
printk("st(%d) %c .%04lx %04lx %04lx %04lx e%+-6d ", i,
getsign(r) ? '-' : '+',
printk("Whoops! Error in errors.c: tag%d is %d ", i,
tagi);
continue;
- break;
}
printk("%s\n", tag_desc[(int)(unsigned)tagi]);
}
case TW_Denormal:
if (denormal_operand() < 0)
return;
-
+ /* fall through */
case TAG_Zero:
case TAG_Valid:
setsign(st0_ptr, getsign(st0_ptr) ^ getsign(st1_ptr));
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
- if (!pmd_present(*pmd_k))
- return NULL;
- if (!pmd_present(*pmd))
+ if (pmd_present(*pmd) != pmd_present(*pmd_k))
set_pmd(pmd, *pmd_k);
+
+ if (!pmd_present(*pmd_k))
+ return NULL;
else
- BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+ BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k));
return pmd_k;
}
spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
spinlock_t *pgt_lock;
- pmd_t *ret;
/* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
- ret = vmalloc_sync_one(page_address(page), address);
+ vmalloc_sync_one(page_address(page), address);
spin_unlock(pgt_lock);
-
- if (!ret)
- break;
}
spin_unlock(&pgd_lock);
}
*/
static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
unsigned long pfn, unsigned long npg,
- int warnlvl)
+ unsigned long lpsize, int warnlvl)
{
pgprotval_t forbidden, res;
unsigned long end;
check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX");
forbidden = res;
- res = protect_kernel_text_ro(start, end);
- check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
- forbidden |= res;
+ /*
+ * Special case to preserve a large page. If the change spawns the
+ * full large page mapping then there is no point to split it
+ * up. Happens with ftrace and is going to be removed once ftrace
+ * switched to text_poke().
+ */
+ if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) {
+ res = protect_kernel_text_ro(start, end);
+ check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
+ forbidden |= res;
+ }
/* Check the PFN directly */
res = protect_pci_bios(pfn, pfn + npg - 1);
* extra conditional required here.
*/
chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages,
- CPA_CONFLICT);
+ psize, CPA_CONFLICT);
if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) {
/*
* protection requirement in the large page.
*/
new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
- CPA_DETECT);
+ psize, CPA_DETECT);
/*
* If there is a conflict, split the large page.
if (!cpa->force_static_prot)
goto set;
- prot = static_protections(ref_prot, address, pfn, npg, CPA_PROTECT);
+ /* Hand in lpsize = 0 to enforce the protection mechanism */
+ prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT);
if (pgprot_val(prot) == pgprot_val(ref_prot))
goto set;
pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
cpa_inc_4k_install();
- new_prot = static_protections(new_prot, address, pfn, 1,
+ /* Hand in lpsize = 0 to enforce the protection mechanism */
+ new_prot = static_protections(new_prot, address, pfn, 1, 0,
CPA_PROTECT);
new_prot = pgprot_clear_protnone_bits(new_prot);
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog));
+ addrs[0] = prog - temp;
- for (i = 0; i < insn_cnt; i++, insn++) {
+ for (i = 1; i <= insn_cnt; i++, insn++) {
const s32 imm32 = insn->imm;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
extra_pass = true;
goto skip_init_addrs;
}
- addrs = kmalloc_array(prog->len, sizeof(*addrs), GFP_KERNEL);
+ addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
if (!addrs) {
prog = orig_prog;
goto out_addrs;
* Before first pass, make a rough estimation of addrs[]
* each BPF instruction is translated to less than 64 bytes
*/
- for (proglen = 0, i = 0; i < prog->len; i++) {
+ for (proglen = 0, i = 0; i <= prog->len; i++) {
proglen += 64;
addrs[i] = proglen;
}
if (!image || !prog->is_func || extra_pass) {
if (image)
- bpf_prog_fill_jited_linfo(prog, addrs);
+ bpf_prog_fill_jited_linfo(prog, addrs + 1);
out_addrs:
kfree(addrs);
kfree(jit_data);
#include <linux/smp.h>
#include <linux/perf_event.h>
#include <linux/tboot.h>
+#include <linux/dmi.h>
#include <asm/pgtable.h>
#include <asm/proto.h>
#include <asm/debugreg.h>
#include <asm/cpu.h>
#include <asm/mmu_context.h>
-#include <linux/dmi.h>
+#include <asm/cpu_device_id.h>
#ifdef CONFIG_X86_32
__visible unsigned long saved_context_ebx;
core_initcall(bsp_pm_check_init);
-static int msr_init_context(const u32 *msr_id, const int total_num)
+static int msr_build_context(const u32 *msr_id, const int num)
{
- int i = 0;
+ struct saved_msrs *saved_msrs = &saved_context.saved_msrs;
struct saved_msr *msr_array;
+ int total_num;
+ int i, j;
- if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) {
- pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n");
- return -EINVAL;
- }
+ total_num = saved_msrs->num + num;
msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL);
if (!msr_array) {
return -ENOMEM;
}
- for (i = 0; i < total_num; i++) {
- msr_array[i].info.msr_no = msr_id[i];
+ if (saved_msrs->array) {
+ /*
+ * Multiple callbacks can invoke this function, so copy any
+ * MSR save requests from previous invocations.
+ */
+ memcpy(msr_array, saved_msrs->array,
+ sizeof(struct saved_msr) * saved_msrs->num);
+
+ kfree(saved_msrs->array);
+ }
+
+ for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) {
+ msr_array[i].info.msr_no = msr_id[j];
msr_array[i].valid = false;
msr_array[i].info.reg.q = 0;
}
- saved_context.saved_msrs.num = total_num;
- saved_context.saved_msrs.array = msr_array;
+ saved_msrs->num = total_num;
+ saved_msrs->array = msr_array;
return 0;
}
/*
- * The following section is a quirk framework for problematic BIOSen:
+ * The following sections are a quirk framework for problematic BIOSen:
* Sometimes MSRs are modified by the BIOSen after suspended to
* RAM, this might cause unexpected behavior after wakeup.
* Thus we save/restore these specified MSRs across suspend/resume
u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL };
pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident);
- return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id));
+ return msr_build_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id));
}
static const struct dmi_system_id msr_save_dmi_table[] = {
{}
};
+static int msr_save_cpuid_features(const struct x86_cpu_id *c)
+{
+ u32 cpuid_msr_id[] = {
+ MSR_AMD64_CPUID_FN_1,
+ };
+
+ pr_info("x86/pm: family %#hx cpu detected, MSR saving is needed during suspending.\n",
+ c->family);
+
+ return msr_build_context(cpuid_msr_id, ARRAY_SIZE(cpuid_msr_id));
+}
+
+static const struct x86_cpu_id msr_save_cpu_table[] = {
+ {
+ .vendor = X86_VENDOR_AMD,
+ .family = 0x15,
+ .model = X86_MODEL_ANY,
+ .feature = X86_FEATURE_ANY,
+ .driver_data = (kernel_ulong_t)msr_save_cpuid_features,
+ },
+ {
+ .vendor = X86_VENDOR_AMD,
+ .family = 0x16,
+ .model = X86_MODEL_ANY,
+ .feature = X86_FEATURE_ANY,
+ .driver_data = (kernel_ulong_t)msr_save_cpuid_features,
+ },
+ {}
+};
+
+typedef int (*pm_cpu_match_t)(const struct x86_cpu_id *);
+static int pm_cpu_check(const struct x86_cpu_id *c)
+{
+ const struct x86_cpu_id *m;
+ int ret = 0;
+
+ m = x86_match_cpu(msr_save_cpu_table);
+ if (m) {
+ pm_cpu_match_t fn;
+
+ fn = (pm_cpu_match_t)m->driver_data;
+ ret = fn(m);
+ }
+
+ return ret;
+}
+
static int pm_check_save_msr(void)
{
dmi_check_system(msr_save_dmi_table);
+ pm_cpu_check(msr_save_cpu_table);
+
return 0;
}
targets += $(purgatory-y)
PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+$(obj)/string.o: $(srctree)/arch/x86/boot/compressed/string.c FORCE
+ $(call if_changed_rule,cc_o_c)
+
$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
$(call if_changed_rule,cc_o_c)
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
# in turn leaves some undefined symbols like __fentry__ in purgatory and not
-# sure how to relocate those. Like kexec-tools, use custom flags.
-
-KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -Os -mcmodel=large
-KBUILD_CFLAGS += -m$(BITS)
-KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+# sure how to relocate those.
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_sha256.o += $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_purgatory.o += $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_string.o += $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_kexec-purgatory.o += $(CC_FLAGS_FTRACE)
+endif
+
+ifdef CONFIG_STACKPROTECTOR
+CFLAGS_REMOVE_sha256.o += -fstack-protector
+CFLAGS_REMOVE_purgatory.o += -fstack-protector
+CFLAGS_REMOVE_string.o += -fstack-protector
+CFLAGS_REMOVE_kexec-purgatory.o += -fstack-protector
+endif
+
+ifdef CONFIG_STACKPROTECTOR_STRONG
+CFLAGS_REMOVE_sha256.o += -fstack-protector-strong
+CFLAGS_REMOVE_purgatory.o += -fstack-protector-strong
+CFLAGS_REMOVE_string.o += -fstack-protector-strong
+CFLAGS_REMOVE_kexec-purgatory.o += -fstack-protector-strong
+endif
+
+ifdef CONFIG_RETPOLINE
+CFLAGS_REMOVE_sha256.o += $(RETPOLINE_CFLAGS)
+CFLAGS_REMOVE_purgatory.o += $(RETPOLINE_CFLAGS)
+CFLAGS_REMOVE_string.o += $(RETPOLINE_CFLAGS)
+CFLAGS_REMOVE_kexec-purgatory.o += $(RETPOLINE_CFLAGS)
+endif
$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
$(call if_changed,ld)
}
copy_backup_region();
}
+
+/*
+ * Defined in order to reuse memcpy() and memset() from
+ * arch/x86/boot/compressed/string.c
+ */
+void warn(const char *msg) {}
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Simple string functions.
- *
- * Copyright (C) 2014 Red Hat Inc.
- *
- * Author:
- * Vivek Goyal <vgoyal@redhat.com>
- */
-
-#include <linux/types.h>
-
-#include "../boot/string.c"
-
-void *memcpy(void *dst, const void *src, size_t len)
-{
- return __builtin_memcpy(dst, src, len);
-}
-
-void *memset(void *dst, int c, size_t len)
-{
- return __builtin_memset(dst, c, len);
-}
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
+#include <asm/asmmacro.h>
#include <asm/processor.h>
#include <asm/coprocessor.h>
#include <asm/thread_info.h>
"add %2, %2, %7\n\t"
"addi %0, %0, -1\n\t"
"bnez %0, 1b\n\t"
+ "isync\n\t"
/* Jump to identity mapping */
"jx %3\n"
"2:\n\t"
* confirmed no later than during the next
* I/O-plugging interval for bfqq.
*/
- if (!bfq_bfqq_has_short_ttime(bfqq) &&
+ if (bfqd->last_completed_rq_bfqq &&
+ !bfq_bfqq_has_short_ttime(bfqq) &&
ktime_get_ns() - bfqd->last_completion <
200 * NSEC_PER_USEC) {
if (bfqd->last_completed_rq_bfqq != bfqq &&
- bfqd->last_completed_rq_bfqq !=
- bfqq->waker_bfqq) {
+ bfqd->last_completed_rq_bfqq !=
+ bfqq->waker_bfqq) {
/*
* First synchronization detected with
* a candidate waker queue, or with a
blk_rq_pos(container_of(rb_prev(&req->rb_node),
struct request, rb_node))) {
struct bfq_queue *bfqq = bfq_init_rq(req);
- struct bfq_data *bfqd = bfqq->bfqd;
+ struct bfq_data *bfqd;
struct request *prev, *next_rq;
+ if (!bfqq)
+ return;
+
+ bfqd = bfqq->bfqd;
+
/* Reposition request in its sort_list */
elv_rb_del(&bfqq->sort_list, req);
elv_rb_add(&bfqq->sort_list, req);
struct bfq_queue *bfqq = bfq_init_rq(rq),
*next_bfqq = bfq_init_rq(next);
+ if (!bfqq)
+ return;
+
/*
* If next and rq belong to the same bfq_queue and next is older
* than rq, then reposition rq in the fifo (by substituting next
* there is no active group, then the primary expectation for
* this device is probably a high throughput.
*
- * We are now left only with explaining the additional
- * compound condition that is checked below for deciding
- * whether the scenario is asymmetric. To explain this
- * compound condition, we need to add that the function
+ * We are now left only with explaining the two sub-conditions in the
+ * additional compound condition that is checked below for deciding
+ * whether the scenario is asymmetric. To explain the first
+ * sub-condition, we need to add that the function
* bfq_asymmetric_scenario checks the weights of only
- * non-weight-raised queues, for efficiency reasons (see
- * comments on bfq_weights_tree_add()). Then the fact that
- * bfqq is weight-raised is checked explicitly here. More
- * precisely, the compound condition below takes into account
- * also the fact that, even if bfqq is being weight-raised,
- * the scenario is still symmetric if all queues with requests
- * waiting for completion happen to be
- * weight-raised. Actually, we should be even more precise
- * here, and differentiate between interactive weight raising
- * and soft real-time weight raising.
+ * non-weight-raised queues, for efficiency reasons (see comments on
+ * bfq_weights_tree_add()). Then the fact that bfqq is weight-raised
+ * is checked explicitly here. More precisely, the compound condition
+ * below takes into account also the fact that, even if bfqq is being
+ * weight-raised, the scenario is still symmetric if all queues with
+ * requests waiting for completion happen to be
+ * weight-raised. Actually, we should be even more precise here, and
+ * differentiate between interactive weight raising and soft real-time
+ * weight raising.
+ *
+ * The second sub-condition checked in the compound condition is
+ * whether there is a fair amount of already in-flight I/O not
+ * belonging to bfqq. If so, I/O dispatching is to be plugged, for the
+ * following reason. The drive may decide to serve in-flight
+ * non-bfqq's I/O requests before bfqq's ones, thereby delaying the
+ * arrival of new I/O requests for bfqq (recall that bfqq is sync). If
+ * I/O-dispatching is not plugged, then, while bfqq remains empty, a
+ * basically uncontrolled amount of I/O from other queues may be
+ * dispatched too, possibly causing the service of bfqq's I/O to be
+ * delayed even longer in the drive. This problem gets more and more
+ * serious as the speed and the queue depth of the drive grow,
+ * because, as these two quantities grow, the probability to find no
+ * queue busy but many requests in flight grows too. By contrast,
+ * plugging I/O dispatching minimizes the delay induced by already
+ * in-flight I/O, and enables bfqq to recover the bandwidth it may
+ * lose because of this delay.
*
* As a side note, it is worth considering that the above
- * device-idling countermeasures may however fail in the
- * following unlucky scenario: if idling is (correctly)
- * disabled in a time period during which all symmetry
- * sub-conditions hold, and hence the device is allowed to
- * enqueue many requests, but at some later point in time some
- * sub-condition stops to hold, then it may become impossible
- * to let requests be served in the desired order until all
- * the requests already queued in the device have been served.
+ * device-idling countermeasures may however fail in the following
+ * unlucky scenario: if I/O-dispatch plugging is (correctly) disabled
+ * in a time period during which all symmetry sub-conditions hold, and
+ * therefore the device is allowed to enqueue many requests, but at
+ * some later point in time some sub-condition stops to hold, then it
+ * may become impossible to make requests be served in the desired
+ * order until all the requests already queued in the device have been
+ * served. The last sub-condition commented above somewhat mitigates
+ * this problem for weight-raised queues.
*/
static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd,
struct bfq_queue *bfqq)
{
return (bfqq->wr_coeff > 1 &&
- bfqd->wr_busy_queues <
- bfq_tot_busy_queues(bfqd)) ||
+ (bfqd->wr_busy_queues <
+ bfq_tot_busy_queues(bfqd) ||
+ bfqd->rq_in_driver >=
+ bfqq->dispatched + 4)) ||
bfq_asymmetric_scenario(bfqd, bfqq);
}
*/
void bfq_put_queue(struct bfq_queue *bfqq)
{
+ struct bfq_queue *item;
+ struct hlist_node *n;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_group *bfqg = bfqq_group(bfqq);
#endif
bfqq->bfqd->burst_size--;
}
+ /*
+ * bfqq does not exist any longer, so it cannot be woken by
+ * any other queue, and cannot wake any other queue. Then bfqq
+ * must be removed from the woken list of its possible waker
+ * queue, and all queues in the woken list of bfqq must stop
+ * having a waker queue. Strictly speaking, these updates
+ * should be performed when bfqq remains with no I/O source
+ * attached to it, which happens before bfqq gets freed. In
+ * particular, this happens when the last process associated
+ * with bfqq exits or gets associated with a different
+ * queue. However, both events lead to bfqq being freed soon,
+ * and dangling references would come out only after bfqq gets
+ * freed. So these updates are done here, as a simple and safe
+ * way to handle all cases.
+ */
+ /* remove bfqq from woken list */
+ if (!hlist_unhashed(&bfqq->woken_list_node))
+ hlist_del_init(&bfqq->woken_list_node);
+
+ /* reset waker for all queues in woken list */
+ hlist_for_each_entry_safe(item, n, &bfqq->woken_list,
+ woken_list_node) {
+ item->waker_bfqq = NULL;
+ bfq_clear_bfqq_has_waker(item);
+ hlist_del_init(&item->woken_list_node);
+ }
+
+ if (bfqq->bfqd && bfqq->bfqd->last_completed_rq_bfqq == bfqq)
+ bfqq->bfqd->last_completed_rq_bfqq = NULL;
+
kmem_cache_free(bfq_pool, bfqq);
#ifdef CONFIG_BFQ_GROUP_IOSCHED
bfqg_and_blkg_put(bfqg);
static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
{
- struct bfq_queue *item;
- struct hlist_node *n;
-
if (bfqq == bfqd->in_service_queue) {
__bfq_bfqq_expire(bfqd, bfqq, BFQQE_BUDGET_TIMEOUT);
bfq_schedule_dispatch(bfqd);
bfq_put_cooperator(bfqq);
- /* remove bfqq from woken list */
- if (!hlist_unhashed(&bfqq->woken_list_node))
- hlist_del_init(&bfqq->woken_list_node);
-
- /* reset waker for all queues in woken list */
- hlist_for_each_entry_safe(item, n, &bfqq->woken_list,
- woken_list_node) {
- item->waker_bfqq = NULL;
- bfq_clear_bfqq_has_waker(item);
- hlist_del_init(&item->woken_list_node);
- }
-
bfq_put_queue(bfqq); /* release process reference */
}
spin_lock_irq(&bfqd->lock);
bfqq = bfq_init_rq(rq);
- if (at_head || blk_rq_is_passthrough(rq)) {
+ if (!bfqq || at_head || blk_rq_is_passthrough(rq)) {
if (at_head)
list_add(&rq->queuelist, &bfqd->dispatch);
else
list_add_tail(&rq->queuelist, &bfqd->dispatch);
- } else { /* bfqq is assumed to be non null here */
+ } else {
idle_timer_disabled = __bfq_insert_request(bfqd, rq);
/*
* Update bfqq, because, if a queue merge has occurred
static LIST_HEAD(all_blkcgs); /* protected by blkcg_pol_mutex */
-static bool blkcg_debug_stats = false;
+bool blkcg_debug_stats = false;
static struct workqueue_struct *blkcg_punt_bio_wq;
static bool blkcg_policy_enabled(struct request_queue *q,
dbytes, dios);
}
- if (!blkcg_debug_stats)
- goto next;
-
- if (atomic_read(&blkg->use_delay)) {
+ if (blkcg_debug_stats && atomic_read(&blkg->use_delay)) {
has_stats = true;
off += scnprintf(buf+off, size-off,
" use_delay=%d delay_nsec=%llu",
has_stats = true;
off += written;
}
-next:
+
if (has_stats) {
if (off < size - 1) {
off += scnprintf(buf+off, size-off, "\n");
unsigned long long avg_lat;
unsigned long long cur_win;
+ if (!blkcg_debug_stats)
+ return 0;
+
if (iolat->ssd)
return iolatency_ssd_stat(iolat, buf, size);
e->type->ops.completed_request(rq, now);
}
-static inline void blk_mq_sched_started_request(struct request *rq)
-{
- struct request_queue *q = rq->q;
- struct elevator_queue *e = q->elevator;
-
- if (e && e->type->ops.started_request)
- e->type->ops.started_request(rq);
-}
-
static inline void blk_mq_sched_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
{
struct request_queue *q = rq->q;
- blk_mq_sched_started_request(rq);
-
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
struct blk_mq_hw_ctx *hctx, *next;
int i;
- cancel_delayed_work_sync(&q->requeue_work);
-
queue_for_each_hw_ctx(q, hctx, i)
WARN_ON_ONCE(hctx && list_empty(&hctx->hctx_list));
return -1;
data->got_token = true;
+ smp_wmb();
list_del_init(&curr->entry);
wake_up_process(data->task);
return 1;
return;
prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE);
+ has_sleeper = !wq_has_single_sleeper(&rqw->wait);
do {
+ /* The memory barrier in set_task_state saves us here. */
if (data.got_token)
break;
if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) {
* which means we now have two. Put our local token
* and wake anyone else potentially waiting for one.
*/
+ smp_rmb();
if (data.got_token)
cleanup_cb(rqw, private_data);
break;
}
io_schedule();
- has_sleeper = false;
+ has_sleeper = true;
+ set_current_state(TASK_UNINTERRUPTIBLE);
} while (1);
finish_wait(&rqw->wait, &data.wq);
}
* page (which might not be idential to the Linux PAGE_SIZE). Because
* of that they are not limited by our notion of "segment size".
*/
- q->limits.max_segment_size = UINT_MAX;
+ if (mask)
+ q->limits.max_segment_size = UINT_MAX;
}
EXPORT_SYMBOL(blk_queue_virt_boundary);
blk_free_queue_stats(q->stats);
+ if (queue_is_mq(q))
+ cancel_delayed_work_sync(&q->requeue_work);
+
blk_exit_queue(q);
blk_queue_free_zone_bitmaps(q);
* The default polling interval can be specified by the kernel
* parameter block.events_dfl_poll_msecs which defaults to 0
* (disable). This can also be modified runtime by writing to
- * /sys/module/block/events_dfl_poll_msecs.
+ * /sys/module/block/parameters/events_dfl_poll_msecs.
*/
static int disk_events_set_dfl_poll_msecs(const char *val,
const struct kernel_param *kp)
/* Move to ITS specific data */
its = (struct acpi_iort_its_group *)node->node_data;
- if (idx > its->its_count) {
- dev_err(dev, "requested ITS ID index [%d] is greater than available [%d]\n",
+ if (idx >= its->its_count) {
+ dev_err(dev, "requested ITS ID index [%d] overruns ITS entries [%d]\n",
idx, its->its_count);
return -ENXIO;
}
if (device->power.flags.power_resources)
result = acpi_power_transition(device, target_state);
} else {
+ int cur_state = device->power.state;
+
if (device->power.flags.power_resources) {
result = acpi_power_transition(device, ACPI_STATE_D0);
if (result)
goto end;
}
- if (device->power.state == ACPI_STATE_D0) {
+ if (cur_state == ACPI_STATE_D0) {
int psc;
/* Nothing to do here if _PSC is not present. */
if (rc)
return rc;
- device_lock(dev);
+ nfit_device_lock(dev);
nd_desc = dev_get_drvdata(dev);
if (nd_desc) {
struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
break;
}
}
- device_unlock(dev);
+ nfit_device_unlock(dev);
if (rc)
return rc;
return size;
ssize_t rc = -ENXIO;
bool busy;
- device_lock(dev);
+ nfit_device_lock(dev);
nd_desc = dev_get_drvdata(dev);
if (!nd_desc) {
device_unlock(dev);
}
mutex_unlock(&acpi_desc->init_mutex);
- device_unlock(dev);
+ nfit_device_unlock(dev);
return rc;
}
if (val != 1)
return -EINVAL;
- device_lock(dev);
+ nfit_device_lock(dev);
nd_desc = dev_get_drvdata(dev);
if (nd_desc) {
struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
rc = acpi_nfit_ars_rescan(acpi_desc, ARS_REQ_LONG);
}
- device_unlock(dev);
+ nfit_device_unlock(dev);
if (rc)
return rc;
return size;
struct acpi_device *adev = data;
struct device *dev = &adev->dev;
- device_lock(dev->parent);
+ nfit_device_lock(dev->parent);
__acpi_nvdimm_notify(dev, event);
- device_unlock(dev->parent);
+ nfit_device_unlock(dev->parent);
}
static bool acpi_nvdimm_has_method(struct acpi_device *adev, char *method)
struct device *dev = acpi_desc->dev;
/* Bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */
- device_lock(dev);
- device_unlock(dev);
+ nfit_device_lock(dev);
+ nfit_device_unlock(dev);
/* Bounce the init_mutex to complete initial registration */
mutex_lock(&acpi_desc->init_mutex);
* acpi_nfit_ars_rescan() submissions have had a chance to
* either submit or see ->cancel set.
*/
- device_lock(bus_dev);
- device_unlock(bus_dev);
+ nfit_device_lock(bus_dev);
+ nfit_device_unlock(bus_dev);
flush_workqueue(nfit_wq);
}
static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
{
- device_lock(&adev->dev);
+ nfit_device_lock(&adev->dev);
__acpi_nfit_notify(&adev->dev, adev->handle, event);
- device_unlock(&adev->dev);
+ nfit_device_unlock(&adev->dev);
}
static const struct acpi_device_id acpi_nfit_ids[] = {
return container_of(nd_desc, struct acpi_nfit_desc, nd_desc);
}
+#ifdef CONFIG_PROVE_LOCKING
+static inline void nfit_device_lock(struct device *dev)
+{
+ device_lock(dev);
+ mutex_lock(&dev->lockdep_mutex);
+}
+
+static inline void nfit_device_unlock(struct device *dev)
+{
+ mutex_unlock(&dev->lockdep_mutex);
+ device_unlock(dev);
+}
+#else
+static inline void nfit_device_lock(struct device *dev)
+{
+ device_lock(dev);
+}
+
+static inline void nfit_device_unlock(struct device *dev)
+{
+ device_unlock(dev);
+}
+#endif
+
const guid_t *to_nfit_uuid(enum nfit_uuids id);
int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz);
void acpi_nfit_shutdown(void *data);
acpi_gpe_apply_masked_gpes();
acpi_update_all_gpes();
+ /*
+ * Although we call __add_memory() that is documented to require the
+ * device_hotplug_lock, it is not necessary here because this is an
+ * early code when userspace or any other code path cannot trigger
+ * hotplug/hotunplug operations.
+ */
mutex_lock(&acpi_scan_lock);
/*
* Enumerate devices in the ACPI namespace.
else
return_error = BR_DEAD_REPLY;
mutex_unlock(&context->context_mgr_node_lock);
- if (target_node && target_proc == proc) {
+ if (target_node && target_proc->pid == proc->pid) {
binder_user_error("%d:%d got transaction to context manager from process owning it\n",
proc->pid, thread->pid);
return_error = BR_FAILED_REPLY;
buffer_offset = off_start_offset;
off_end_offset = off_start_offset + tr->offsets_size;
sg_buf_offset = ALIGN(off_end_offset, sizeof(void *));
- sg_buf_end_offset = sg_buf_offset + extra_buffers_size;
+ sg_buf_end_offset = sg_buf_offset + extra_buffers_size -
+ ALIGN(secctx_sz, sizeof(u64));
off_min = 0;
for (buffer_offset = off_start_offset; buffer_offset < off_end_offset;
buffer_offset += sizeof(binder_size_t)) {
hpriv->phys[port] = NULL;
rc = 0;
break;
+ case -EPROBE_DEFER:
+ /* Do not complain yet */
+ break;
default:
dev_err(dev,
hpriv->mmio = devm_ioremap_resource(dev,
platform_get_resource(pdev, IORESOURCE_MEM, 0));
if (IS_ERR(hpriv->mmio)) {
- dev_err(dev, "no mmio space\n");
rc = PTR_ERR(hpriv->mmio);
goto err_out;
}
return 1;
}
+static bool ata_check_nblocks(struct scsi_cmnd *scmd, u32 n_blocks)
+{
+ struct request *rq = scmd->request;
+ u32 req_blocks;
+
+ if (!blk_rq_is_passthrough(rq))
+ return true;
+
+ req_blocks = blk_rq_bytes(rq) / scmd->device->sector_size;
+ if (n_blocks > req_blocks)
+ return false;
+
+ return true;
+}
+
/**
* ata_scsi_rw_xlat - Translate SCSI r/w command into an ATA one
* @qc: Storage for translated ATA taskfile
scsi_10_lba_len(cdb, &block, &n_block);
if (cdb[1] & (1 << 3))
tf_flags |= ATA_TFLAG_FUA;
+ if (!ata_check_nblocks(scmd, n_block))
+ goto invalid_fld;
break;
case READ_6:
case WRITE_6:
*/
if (!n_block)
n_block = 256;
+ if (!ata_check_nblocks(scmd, n_block))
+ goto invalid_fld;
break;
case READ_16:
case WRITE_16:
scsi_16_lba_len(cdb, &block, &n_block);
if (cdb[1] & (1 << 3))
tf_flags |= ATA_TFLAG_FUA;
+ if (!ata_check_nblocks(scmd, n_block))
+ goto invalid_fld;
break;
default:
DPRINTK("no-byte command\n");
unsigned int offset;
unsigned char *buf;
+ if (!qc->cursg) {
+ qc->curbytes = qc->nbytes;
+ return;
+ }
if (qc->curbytes == qc->nbytes - qc->sect_size)
ap->hsm_task_state = HSM_ST_LAST;
if (qc->cursg_ofs == qc->cursg->length) {
qc->cursg = sg_next(qc->cursg);
+ if (!qc->cursg)
+ ap->hsm_task_state = HSM_ST_LAST;
qc->cursg_ofs = 0;
}
}
unsigned int ret;
struct rm_feature_desc *desc;
struct ata_taskfile tf;
- static const char cdb[] = { GPCMD_GET_CONFIGURATION,
+ static const char cdb[ATAPI_CDB_LEN] = { GPCMD_GET_CONFIGURATION,
2, /* only 1 feature descriptor requested */
0, 3, /* 3, removable medium feature */
0, 0, 0,/* reserved */
static int rb532_pata_driver_remove(struct platform_device *pdev)
{
struct ata_host *ah = platform_get_drvdata(pdev);
- struct rb532_cf_info *info = ah->private_data;
ata_host_detach(ah);
make the card work).
config ATM_NICSTAR_USE_IDT77105
- bool "Use IDT77015 PHY driver (25Mbps)"
+ bool "Use IDT77105 PHY driver (25Mbps)"
depends on ATM_NICSTAR
help
Support for the PHYsical layer chip in ForeRunner LE25 cards. In
#include <asm/byteorder.h>
#include <linux/vmalloc.h>
#include <linux/jiffies.h>
+#include <linux/nospec.h>
#include "iphase.h"
#include "suni.h"
#define swap_byte_order(x) (((x & 0xff) << 8) | ((x & 0xff00) >> 8))
}
if (copy_from_user(&ia_cmds, arg, sizeof ia_cmds)) return -EFAULT;
board = ia_cmds.status;
- if ((board < 0) || (board > iadev_count))
- board = 0;
+
+ if ((board < 0) || (board > iadev_count))
+ board = 0;
+ board = array_index_nospec(board, iadev_count + 1);
+
iadev = ia_dev[board];
switch (ia_cmds.cmd) {
case MEMDUMP:
choice
prompt "Backlight initial state"
default CHARLCD_BL_FLASH
+ ---help---
+ Select the initial backlight state on boot or module load.
+
+ Previously, there was no option for this: the backlight flashed
+ briefly on init. Now you can also turn it off/on.
config CHARLCD_BL_OFF
bool "Off"
#include <generated/utsrelease.h>
-#include <misc/charlcd.h>
+#include "charlcd.h"
#define LCD_MINOR 156
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Character LCD driver for Linux
+ *
+ * Copyright (C) 2000-2008, Willy Tarreau <w@1wt.eu>
+ * Copyright (C) 2016-2017 Glider bvba
+ */
+
+#ifndef _CHARLCD_H
+#define _CHARLCD_H
+
+struct charlcd {
+ const struct charlcd_ops *ops;
+ const unsigned char *char_conv; /* Optional */
+
+ int ifwidth; /* 4-bit or 8-bit (default) */
+ int height;
+ int width;
+ int bwidth; /* Default set by charlcd_alloc() */
+ int hwidth; /* Default set by charlcd_alloc() */
+
+ void *drvdata; /* Set by charlcd_alloc() */
+};
+
+struct charlcd_ops {
+ /* Required */
+ void (*write_cmd)(struct charlcd *lcd, int cmd);
+ void (*write_data)(struct charlcd *lcd, int data);
+
+ /* Optional */
+ void (*write_cmd_raw4)(struct charlcd *lcd, int cmd); /* 4-bit only */
+ void (*clear_fast)(struct charlcd *lcd);
+ void (*backlight)(struct charlcd *lcd, int on);
+};
+
+struct charlcd *charlcd_alloc(unsigned int drvdata_size);
+void charlcd_free(struct charlcd *lcd);
+
+int charlcd_register(struct charlcd *lcd);
+int charlcd_unregister(struct charlcd *lcd);
+
+void charlcd_poke(struct charlcd *lcd);
+
+#endif /* CHARLCD_H */
#include <linux/property.h>
#include <linux/slab.h>
-#include <misc/charlcd.h>
-
+#include "charlcd.h"
enum hd44780_pin {
/* Order does matter due to writing to GPIO array subsets! */
struct ht16k33_fbdev fbdev;
};
-static struct fb_fix_screeninfo ht16k33_fb_fix = {
+static const struct fb_fix_screeninfo ht16k33_fb_fix = {
.id = DRIVER_NAME,
.type = FB_TYPE_PACKED_PIXELS,
.visual = FB_VISUAL_MONO10,
.accel = FB_ACCEL_NONE,
};
-static struct fb_var_screeninfo ht16k33_fb_var = {
+static const struct fb_var_screeninfo ht16k33_fb_var = {
.xres = HT16K33_MATRIX_LED_MAX_ROWS,
.yres = HT16K33_MATRIX_LED_MAX_COLS,
.xres_virtual = HT16K33_MATRIX_LED_MAX_ROWS,
#include <linux/io.h>
#include <linux/uaccess.h>
-#include <misc/charlcd.h>
+#include "charlcd.h"
#define KEYPAD_MINOR 185
return;
err_lcd_unreg:
+ if (scan_timer.function)
+ del_timer_sync(&scan_timer);
if (lcd.enabled)
charlcd_unregister(lcd.charlcd);
err_unreg_device:
kobject_init(&dev->kobj, &device_ktype);
INIT_LIST_HEAD(&dev->dma_pools);
mutex_init(&dev->mutex);
+#ifdef CONFIG_PROVE_LOCKING
+ mutex_init(&dev->lockdep_mutex);
+#endif
lockdep_set_novalidate_class(&dev->mutex);
spin_lock_init(&dev->devres_lock);
INIT_LIST_HEAD(&dev->devres_head);
*/
static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
{
+ unsigned int ref;
+
/* see if we live in a "glue" directory */
if (!live_in_glue_dir(glue_dir, dev))
return;
mutex_lock(&gdp_mutex);
- if (!kobject_has_children(glue_dir))
+ /**
+ * There is a race condition between removing glue directory
+ * and adding a new device under the glue directory.
+ *
+ * CPU1: CPU2:
+ *
+ * device_add()
+ * get_device_parent()
+ * class_dir_create_and_add()
+ * kobject_add_internal()
+ * create_dir() // create glue_dir
+ *
+ * device_add()
+ * get_device_parent()
+ * kobject_get() // get glue_dir
+ *
+ * device_del()
+ * cleanup_glue_dir()
+ * kobject_del(glue_dir)
+ *
+ * kobject_add()
+ * kobject_add_internal()
+ * create_dir() // in glue_dir
+ * sysfs_create_dir_ns()
+ * kernfs_create_dir_ns(sd)
+ *
+ * sysfs_remove_dir() // glue_dir->sd=NULL
+ * sysfs_put() // free glue_dir->sd
+ *
+ * // sd is freed
+ * kernfs_new_node(sd)
+ * kernfs_get(glue_dir)
+ * kernfs_add_one()
+ * kernfs_put()
+ *
+ * Before CPU1 remove last child device under glue dir, if CPU2 add
+ * a new device under glue dir, the glue_dir kobject reference count
+ * will be increase to 2 in kobject_get(k). And CPU2 has been called
+ * kernfs_create_dir_ns(). Meanwhile, CPU1 call sysfs_remove_dir()
+ * and sysfs_put(). This result in glue_dir->sd is freed.
+ *
+ * Then the CPU2 will see a stale "empty" but still potentially used
+ * glue dir around in kernfs_new_node().
+ *
+ * In order to avoid this happening, we also should make sure that
+ * kernfs_node for glue_dir is released in CPU1 only when refcount
+ * for glue_dir kobj is 1.
+ */
+ ref = kref_read(&glue_dir->kref);
+ if (!kobject_has_children(glue_dir) && !--ref)
kobject_del(glue_dir);
kobject_put(glue_dir);
mutex_unlock(&gdp_mutex);
}
EXPORT_SYMBOL_GPL(put_device);
+bool kill_device(struct device *dev)
+{
+ /*
+ * Require the device lock and set the "dead" flag to guarantee that
+ * the update behavior is consistent with the other bitfields near
+ * it and that we cannot have an asynchronous probe routine trying
+ * to run while we are tearing out the bus/class/sysfs from
+ * underneath the device.
+ */
+ lockdep_assert_held(&dev->mutex);
+
+ if (dev->p->dead)
+ return false;
+ dev->p->dead = true;
+ return true;
+}
+EXPORT_SYMBOL_GPL(kill_device);
+
/**
* device_del - delete device from system.
* @dev: device.
struct kobject *glue_dir = NULL;
struct class_interface *class_intf;
- /*
- * Hold the device lock and set the "dead" flag to guarantee that
- * the update behavior is consistent with the other bitfields near
- * it and that we cannot have an asynchronous probe routine trying
- * to run while we are tearing out the bus/class/sysfs from
- * underneath the device.
- */
device_lock(dev);
- dev->p->dead = true;
+ kill_device(dev);
device_unlock(dev);
/* Notify clients of device removal. This call must come
int fw_map_paged_buf(struct fw_priv *fw_priv);
#else
static inline void fw_free_paged_buf(struct fw_priv *fw_priv) {}
-int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; }
-int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; }
+static inline int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed) { return -ENXIO; }
+static inline int fw_map_paged_buf(struct fw_priv *fw_priv) { return -ENXIO; }
#endif
#endif /* __FIRMWARE_LOADER_H */
* the device will only expose one IRQ, and this fallback
* allows a common code path across either kind of resource.
*/
- if (num == 0 && has_acpi_companion(&dev->dev))
- return acpi_dev_gpio_irq_get(ACPI_COMPANION(&dev->dev), num);
+ if (num == 0 && has_acpi_companion(&dev->dev)) {
+ int ret = acpi_dev_gpio_irq_get(ACPI_COMPANION(&dev->dev), num);
+
+ /* Our callers expect -ENXIO for missing IRQs. */
+ if (ret >= 0 || ret == -EPROBE_DEFER)
+ return ret;
+ }
return -ENXIO;
#endif
config REGMAP_SOUNDWIRE
tristate
- depends on SOUNDWIRE_BUS
+ depends on SOUNDWIRE
config REGMAP_SCCB
tristate
}
flush_scheduled_work();
- /* pass one: without sleeping, do aoedev_downdev */
+ /* pass one: do aoedev_downdev, which might sleep */
+restart1:
spin_lock_irqsave(&devlist_lock, flags);
for (d = devlist; d; d = d->next) {
spin_lock(&d->lock);
+ if (d->flags & DEVFL_TKILL)
+ goto cont;
+
if (exiting) {
/* unconditionally take each device down */
} else if (specified) {
|| d->ref)
goto cont;
+ spin_unlock(&d->lock);
+ spin_unlock_irqrestore(&devlist_lock, flags);
aoedev_downdev(d);
d->flags |= DEVFL_TKILL;
+ goto restart1;
cont:
spin_unlock(&d->lock);
}
/* pass two: call freedev, which might sleep,
* for aoedevs marked with DEVFL_TKILL
*/
-restart:
+restart2:
spin_lock_irqsave(&devlist_lock, flags);
for (d = devlist; d; d = d->next) {
spin_lock(&d->lock);
spin_unlock(&d->lock);
spin_unlock_irqrestore(&devlist_lock, flags);
freedev(d);
- goto restart;
+ goto restart2;
}
spin_unlock(&d->lock);
}
/* MSch: invalidate default_params */
default_params[drive].blocks = 0;
set_capacity(floppy->disk, MAX_DISK_SIZE * 2);
+ /* Fall through */
case FDFMTEND:
case FDFLUSH:
/* invalidate the buffer track to force a reread */
thi->name[0],
resource->name);
+ allow_kernel_signal(DRBD_SIGKILL);
+ allow_kernel_signal(SIGXCPU);
restart:
retval = thi->function(thi);
unsigned int key_len;
char secret[SHARED_SECRET_MAX]; /* 64 byte */
unsigned int resp_size;
- SHASH_DESC_ON_STACK(desc, connection->cram_hmac_tfm);
+ struct shash_desc *desc;
struct packet_info pi;
struct net_conf *nc;
int err, rv;
memcpy(secret, nc->shared_secret, key_len);
rcu_read_unlock();
+ desc = kmalloc(sizeof(struct shash_desc) +
+ crypto_shash_descsize(connection->cram_hmac_tfm),
+ GFP_KERNEL);
+ if (!desc) {
+ rv = -1;
+ goto fail;
+ }
desc->tfm = connection->cram_hmac_tfm;
rv = crypto_shash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len);
kfree(peers_ch);
kfree(response);
kfree(right_response);
- shash_desc_zero(desc);
+ if (desc) {
+ shash_desc_zero(desc);
+ kfree(desc);
+ }
return rv;
}
static int loop_kthread_worker_fn(void *worker_ptr)
{
- current->flags |= PF_LESS_THROTTLE;
+ current->flags |= PF_LESS_THROTTLE | PF_MEMALLOC_NOIO;
return kthread_worker_fn(worker_ptr);
}
struct file *file;
struct inode *inode;
struct address_space *mapping;
+ struct block_device *claimed_bdev = NULL;
int lo_flags = 0;
int error;
loff_t size;
* here to avoid changing device under exclusive owner.
*/
if (!(mode & FMODE_EXCL)) {
- bdgrab(bdev);
- error = blkdev_get(bdev, mode | FMODE_EXCL, loop_set_fd);
- if (error)
+ claimed_bdev = bd_start_claiming(bdev, loop_set_fd);
+ if (IS_ERR(claimed_bdev)) {
+ error = PTR_ERR(claimed_bdev);
goto out_putf;
+ }
}
error = mutex_lock_killable(&loop_ctl_mutex);
mutex_unlock(&loop_ctl_mutex);
if (partscan)
loop_reread_partitions(lo, bdev);
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
+ if (claimed_bdev)
+ bd_abort_claiming(bdev, claimed_bdev, loop_set_fd);
return 0;
out_unlock:
mutex_unlock(&loop_ctl_mutex);
out_bdev:
- if (!(mode & FMODE_EXCL))
- blkdev_put(bdev, mode | FMODE_EXCL);
+ if (claimed_bdev)
+ bd_abort_claiming(bdev, claimed_bdev, loop_set_fd);
out_putf:
fput(file);
out:
struct block_device *bdev)
{
sock_shutdown(nbd);
- kill_bdev(bdev);
+ __invalidate_device(bdev, true);
nbd_bdev_reset(bdev);
if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
&nbd->config->runtime_flags))
}
return true;
case RBD_OBJ_READ_PARENT:
+ /*
+ * The parent image is read only up to the overlap -- zero-fill
+ * from the overlap to the end of the request.
+ */
+ if (!*result) {
+ u32 obj_overlap = rbd_obj_img_extents_bytes(obj_req);
+
+ if (obj_overlap < obj_req->ex.oe_len)
+ rbd_obj_zero_range(obj_req, obj_overlap,
+ obj_req->ex.oe_len - obj_overlap);
+ }
return true;
default:
BUG();
}
}
+ err = -ENOMEM;
for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) {
req = kzalloc(sizeof(*req), GFP_KERNEL);
if (!req)
err = xen_blkif_map(ring, ring_ref, nr_grefs, evtchn);
if (err) {
xenbus_dev_fatal(dev, err, "mapping ring-ref port %u", evtchn);
- return err;
+ goto fail;
}
return 0;
}
kfree(req);
}
- return -ENOMEM;
-
+ return err;
}
static int connect_ring(struct backend_info *be)
return 0;
}
+int qca_send_pre_shutdown_cmd(struct hci_dev *hdev)
+{
+ struct sk_buff *skb;
+ int err;
+
+ bt_dev_dbg(hdev, "QCA pre shutdown cmd");
+
+ skb = __hci_cmd_sync(hdev, QCA_PRE_SHUTDOWN_CMD, 0,
+ NULL, HCI_INIT_TIMEOUT);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ bt_dev_err(hdev, "QCA preshutdown_cmd failed (%d)", err);
+ return err;
+ }
+
+ kfree_skb(skb);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(qca_send_pre_shutdown_cmd);
+
static void qca_tlv_check_data(struct rome_config *config,
const struct firmware *fw)
{
BT_DBG("Length\t\t : %d bytes", length);
config->dnld_mode = ROME_SKIP_EVT_NONE;
+ config->dnld_type = ROME_SKIP_EVT_NONE;
switch (config->type) {
case TLV_TYPE_PATCH:
evt = skb_put(skb, sizeof(*evt));
evt->ncmd = 1;
- evt->opcode = QCA_HCI_CC_OPCODE;
+ evt->opcode = cpu_to_le16(QCA_HCI_CC_OPCODE);
skb_put_u8(skb, QCA_HCI_CC_SUCCESS);
*/
if (config->dnld_type == ROME_SKIP_EVT_VSE_CC ||
config->dnld_type == ROME_SKIP_EVT_VSE)
- return qca_inject_cmd_complete_event(hdev);
+ ret = qca_inject_cmd_complete_event(hdev);
out:
release_firmware(fw);
return err;
}
+ /* Give the controller some time to get ready to receive the NVM */
+ msleep(10);
+
/* Download NVM configuration */
config.type = TLV_TYPE_NVM;
if (firmware_name)
#define EDL_PATCH_TLV_REQ_CMD (0x1E)
#define EDL_NVM_ACCESS_SET_REQ_CMD (0x01)
#define MAX_SIZE_PER_TLV_SEGMENT (243)
+#define QCA_PRE_SHUTDOWN_CMD (0xFC08)
#define EDL_CMD_REQ_RES_EVT (0x00)
#define EDL_PATCH_VER_RES_EVT (0x19)
const char *firmware_name);
int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version);
int qca_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr);
+int qca_send_pre_shutdown_cmd(struct hci_dev *hdev);
static inline bool qca_is_wcn399x(enum qca_btsoc_type soc_type)
{
return soc_type == QCA_WCN3990 || soc_type == QCA_WCN3998;
{
return false;
}
+
+static inline int qca_send_pre_shutdown_cmd(struct hci_dev *hdev)
+{
+ return -EOPNOTSUPP;
+}
#endif
fw_size = fw->size;
/* The size of patch header is 30 bytes, should be skip */
- if (fw_size < 30)
+ if (fw_size < 30) {
+ err = -EINVAL;
goto err_release_fw;
+ }
fw_size -= 30;
fw_ptr += 30;
BT_DBG("hu %p", hu);
+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
ath = kzalloc(sizeof(*ath), GFP_KERNEL);
if (!ath)
return -ENOMEM;
bt_dev_dbg(hu->hdev, "hu %p", hu);
+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
bcm = kzalloc(sizeof(*bcm), GFP_KERNEL);
if (!bcm)
return -ENOMEM;
BT_DBG("hu %p", hu);
+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
intel = kzalloc(sizeof(*intel), GFP_KERNEL);
if (!intel)
return -ENOMEM;
return 0;
}
+/* Check the underlying device or tty has flow control support */
+bool hci_uart_has_flow_control(struct hci_uart *hu)
+{
+ /* serdev nodes check if the needed operations are present */
+ if (hu->serdev)
+ return true;
+
+ if (hu->tty->driver->ops->tiocmget && hu->tty->driver->ops->tiocmset)
+ return true;
+
+ return false;
+}
+
/* Flow control or un-flow control the device */
void hci_uart_set_flow_control(struct hci_uart *hu, bool enable)
{
BT_DBG("hu %p", hu);
+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
mrvl = kzalloc(sizeof(*mrvl), GFP_KERNEL);
if (!mrvl)
return -ENOMEM;
BT_DBG("hu %p qca_open", hu);
+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL);
if (!qca)
return -ENOMEM;
unsigned long flags;
struct qca_data *qca = hu->priv;
- BT_DBG("hu %p want to sleep", hu);
+ BT_DBG("hu %p want to sleep in %d state", hu, qca->rx_ibs_state);
spin_lock_irqsave(&qca->hci_ibs_lock, flags);
break;
case HCI_IBS_RX_ASLEEP:
- /* Fall through */
+ break;
default:
/* Any other state is illegal */
if (hdr->evt == HCI_EV_VENDOR)
complete(&qca->drop_ev_comp);
- kfree(skb);
+ kfree_skb(skb);
return 0;
}
{
struct hci_uart *hu = hci_get_drvdata(hdev);
+ /* Perform pre shutdown command */
+ qca_send_pre_shutdown_cmd(hdev);
+
qca_power_shutdown(hu);
return 0;
}
int hci_uart_init_ready(struct hci_uart *hu);
void hci_uart_init_work(struct work_struct *work);
void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed);
+bool hci_uart_has_flow_control(struct hci_uart *hu);
void hci_uart_set_flow_control(struct hci_uart *hu, bool enable);
void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed,
unsigned int oper_speed);
size_t pdata_size;
};
+static void hisi_lpc_acpi_remove(struct device *hostdev)
+{
+ struct acpi_device *adev = ACPI_COMPANION(hostdev);
+ struct acpi_device *child;
+
+ device_for_each_child(hostdev, NULL, hisi_lpc_acpi_remove_subdev);
+
+ list_for_each_entry(child, &adev->children, node)
+ acpi_device_clear_enumerated(child);
+}
+
/*
* hisi_lpc_acpi_probe - probe children for ACPI FW
* @hostdev: LPC host device pointer
return 0;
fail:
- device_for_each_child(hostdev, NULL,
- hisi_lpc_acpi_remove_subdev);
+ hisi_lpc_acpi_remove(hostdev);
return ret;
}
{
return -ENODEV;
}
+
+static void hisi_lpc_acpi_remove(struct device *hostdev)
+{
+}
#endif // CONFIG_ACPI
/*
range->fwnode = dev->fwnode;
range->flags = LOGIC_PIO_INDIRECT;
range->size = PIO_INDIRECT_SIZE;
+ range->hostdata = lpcdev;
+ range->ops = &hisi_lpc_ops;
+ lpcdev->io_host = range;
ret = logic_pio_register_range(range);
if (ret) {
dev_err(dev, "register IO range failed (%d)!\n", ret);
return ret;
}
- lpcdev->io_host = range;
/* register the LPC host PIO resources */
if (acpi_device)
ret = hisi_lpc_acpi_probe(dev);
else
ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
- if (ret)
+ if (ret) {
+ logic_pio_unregister_range(range);
return ret;
+ }
- lpcdev->io_host->hostdata = lpcdev;
- lpcdev->io_host->ops = &hisi_lpc_ops;
+ dev_set_drvdata(dev, lpcdev);
io_end = lpcdev->io_host->io_start + lpcdev->io_host->size;
dev_info(dev, "registered range [%pa - %pa]\n",
return ret;
}
+static int hisi_lpc_remove(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct acpi_device *acpi_device = ACPI_COMPANION(dev);
+ struct hisi_lpc_dev *lpcdev = dev_get_drvdata(dev);
+ struct logic_pio_hwaddr *range = lpcdev->io_host;
+
+ if (acpi_device)
+ hisi_lpc_acpi_remove(dev);
+ else
+ of_platform_depopulate(dev);
+
+ logic_pio_unregister_range(range);
+
+ return 0;
+}
+
static const struct of_device_id hisi_lpc_of_match[] = {
{ .compatible = "hisilicon,hip06-lpc", },
{ .compatible = "hisilicon,hip07-lpc", },
.acpi_match_table = ACPI_PTR(hisi_lpc_acpi_match),
},
.probe = hisi_lpc_probe,
+ .remove = hisi_lpc_remove,
};
builtin_platform_driver(hisi_lpc_driver);
*best_mode = SYSC_IDLE_SMART_WKUP;
else if (idlemodes & BIT(SYSC_IDLE_SMART))
*best_mode = SYSC_IDLE_SMART;
- else if (idlemodes & SYSC_IDLE_FORCE)
+ else if (idlemodes & BIT(SYSC_IDLE_FORCE))
*best_mode = SYSC_IDLE_FORCE;
else
return -EINVAL;
SYSC_QUIRK("control", 0, 0, 0x10, -1, 0x40000900, 0xffffffff, 0),
SYSC_QUIRK("cpgmac", 0, 0x1200, 0x1208, 0x1204, 0x4edb1902,
0xffff00f0, 0),
- SYSC_QUIRK("dcan", 0, 0, -1, -1, 0xffffffff, 0xffffffff, 0),
+ SYSC_QUIRK("dcan", 0, 0x20, -1, -1, 0xa3170504, 0xffffffff, 0),
+ SYSC_QUIRK("dcan", 0, 0x20, -1, -1, 0x4edb1902, 0xffffffff, 0),
SYSC_QUIRK("dmic", 0, 0, 0x10, -1, 0x50010000, 0xffffffff, 0),
SYSC_QUIRK("dwc3", 0, 0, 0x10, -1, 0x500a0200, 0xffffffff, 0),
SYSC_QUIRK("epwmss", 0, 0, 0x4, -1, 0x47400001, 0xffffffff, 0),
if (error)
return 0;
- if (val)
- ddata->cfg.sysc_val = val & ddata->cap->sysc_mask;
- else
- ddata->cfg.sysc_val = ddata->cap->sysc_mask;
+ ddata->cfg.sysc_val = val & ddata->cap->sysc_mask;
return 0;
}
error = sysc_init_dts_quirks(ddata);
if (error)
- goto unprepare;
+ return error;
error = sysc_map_and_check_registers(ddata);
if (error)
- goto unprepare;
+ return error;
error = sysc_init_sysc_mask(ddata);
if (error)
- goto unprepare;
+ return error;
error = sysc_init_idlemodes(ddata);
if (error)
- goto unprepare;
+ return error;
error = sysc_init_syss_mask(ddata);
if (error)
- goto unprepare;
+ return error;
error = sysc_init_pdata(ddata);
if (error)
- goto unprepare;
+ return error;
sysc_init_early_quirks(ddata);
error = sysc_init_resets(ddata);
if (error)
- return error;
+ goto unprepare;
error = sysc_init_module(ddata);
if (error)
unsigned long long m;
m = hpets->hp_tick_freq + (dis >> 1);
- do_div(m, dis);
- return (unsigned long)m;
+ return div64_ul(m, dis);
}
static int
struct ipmb_dev *ipmb_dev = to_ipmb_dev(file);
struct ipmb_request_elem *queue_elem;
struct ipmb_msg msg;
- ssize_t ret;
+ ssize_t ret = 0;
memset(&msg, 0, sizeof(msg));
return chip->ops->go_idle(chip);
}
+static void tpm_clk_enable(struct tpm_chip *chip)
+{
+ if (chip->ops->clk_enable)
+ chip->ops->clk_enable(chip, true);
+}
+
+static void tpm_clk_disable(struct tpm_chip *chip)
+{
+ if (chip->ops->clk_enable)
+ chip->ops->clk_enable(chip, false);
+}
+
/**
* tpm_chip_start() - power on the TPM
* @chip: a TPM chip to use
{
int ret;
- if (chip->ops->clk_enable)
- chip->ops->clk_enable(chip, true);
+ tpm_clk_enable(chip);
if (chip->locality == -1) {
ret = tpm_request_locality(chip);
if (ret) {
- chip->ops->clk_enable(chip, false);
+ tpm_clk_disable(chip);
return ret;
}
}
ret = tpm_cmd_ready(chip);
if (ret) {
tpm_relinquish_locality(chip);
- if (chip->ops->clk_enable)
- chip->ops->clk_enable(chip, false);
+ tpm_clk_disable(chip);
return ret;
}
{
tpm_go_idle(chip);
tpm_relinquish_locality(chip);
- if (chip->ops->clk_enable)
- chip->ops->clk_enable(chip, false);
+ tpm_clk_disable(chip);
}
EXPORT_SYMBOL_GPL(tpm_chip_stop);
return hwrng_register(&chip->hwrng);
}
+static int tpm_get_pcr_allocation(struct tpm_chip *chip)
+{
+ int rc;
+
+ rc = (chip->flags & TPM_CHIP_FLAG_TPM2) ?
+ tpm2_get_pcr_allocation(chip) :
+ tpm1_get_pcr_allocation(chip);
+
+ if (rc > 0)
+ return -ENODEV;
+
+ return rc;
+}
+
/*
* tpm_chip_register() - create a character device for the TPM chip
* @chip: TPM chip to use.
if (rc)
return rc;
rc = tpm_auto_startup(chip);
+ if (rc) {
+ tpm_chip_stop(chip);
+ return rc;
+ }
+
+ rc = tpm_get_pcr_allocation(chip);
tpm_chip_stop(chip);
if (rc)
return rc;
ssize_t tpm1_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap,
const char *desc, size_t min_cap_length);
int tpm1_get_random(struct tpm_chip *chip, u8 *out, size_t max);
+int tpm1_get_pcr_allocation(struct tpm_chip *chip);
unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
int tpm_pm_suspend(struct device *dev);
int tpm_pm_resume(struct device *dev);
ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,
u32 *value, const char *desc);
+ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip);
int tpm2_auto_startup(struct tpm_chip *chip);
void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type);
unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal);
goto out;
}
- chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks),
- GFP_KERNEL);
- if (!chip->allocated_banks) {
- rc = -ENOMEM;
- goto out;
- }
-
- chip->allocated_banks[0].alg_id = TPM_ALG_SHA1;
- chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1];
- chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1;
- chip->nr_allocated_banks = 1;
-
return rc;
out:
if (rc > 0)
return rc;
}
+/**
+ * tpm1_get_pcr_allocation() - initialize the allocated bank
+ * @chip: TPM chip to use.
+ *
+ * The function initializes the SHA1 allocated bank to extend PCR
+ *
+ * Return:
+ * * 0 on success,
+ * * < 0 on error.
+ */
+int tpm1_get_pcr_allocation(struct tpm_chip *chip)
+{
+ chip->allocated_banks = kcalloc(1, sizeof(*chip->allocated_banks),
+ GFP_KERNEL);
+ if (!chip->allocated_banks)
+ return -ENOMEM;
+
+ chip->allocated_banks[0].alg_id = TPM_ALG_SHA1;
+ chip->allocated_banks[0].digest_size = hash_digest_size[HASH_ALGO_SHA1];
+ chip->allocated_banks[0].crypto_id = HASH_ALGO_SHA1;
+ chip->nr_allocated_banks = 1;
+
+ return 0;
+}
u8 pcr_select[3];
} __packed;
-static ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip)
+ssize_t tpm2_get_pcr_allocation(struct tpm_chip *chip)
{
struct tpm2_pcr_selection pcr_selection;
struct tpm_buf buf;
goto out;
}
- rc = tpm2_get_pcr_allocation(chip);
- if (rc)
- goto out;
-
rc = tpm2_get_cc_attrs_tbl(chip);
out:
continue;
div = DIV_ROUND_CLOSEST(parent_rate, req->rate);
+ if (div > GENERATED_MAX_DIV + 1)
+ div = GENERATED_MAX_DIV + 1;
clk_generated_best_diff(req, parent, parent_rate, div,
&best_diff, &best_rate);
return NULL;
}
+#ifdef CONFIG_OF
+static int of_parse_clkspec(const struct device_node *np, int index,
+ const char *name, struct of_phandle_args *out_args);
+static struct clk_hw *
+of_clk_get_hw_from_clkspec(struct of_phandle_args *clkspec);
+#else
+static inline int of_parse_clkspec(const struct device_node *np, int index,
+ const char *name,
+ struct of_phandle_args *out_args)
+{
+ return -ENOENT;
+}
+static inline struct clk_hw *
+of_clk_get_hw_from_clkspec(struct of_phandle_args *clkspec)
+{
+ return ERR_PTR(-ENOENT);
+}
+#endif
+
/**
* clk_core_get - Find the clk_core parent of a clk
* @core: clk to find parent of
* };
*
* Returns: -ENOENT when the provider can't be found or the clk doesn't
- * exist in the provider. -EINVAL when the name can't be found. NULL when the
- * provider knows about the clk but it isn't provided on this system.
+ * exist in the provider or the name can't be found in the DT node or
+ * in a clkdev lookup. NULL when the provider knows about the clk but it
+ * isn't provided on this system.
* A valid clk_core pointer when the clk can be found in the provider.
*/
static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index)
struct device *dev = core->dev;
const char *dev_id = dev ? dev_name(dev) : NULL;
struct device_node *np = core->of_node;
+ struct of_phandle_args clkspec;
- if (np && (name || index >= 0))
- hw = of_clk_get_hw(np, index, name);
-
- /*
- * If the DT search above couldn't find the provider or the provider
- * didn't know about this clk, fallback to looking up via clkdev based
- * clk_lookups
- */
- if (PTR_ERR(hw) == -ENOENT && name)
+ if (np && (name || index >= 0) &&
+ !of_parse_clkspec(np, index, name, &clkspec)) {
+ hw = of_clk_get_hw_from_clkspec(&clkspec);
+ of_node_put(clkspec.np);
+ } else if (name) {
+ /*
+ * If the DT search above couldn't find the provider fallback to
+ * looking up via clkdev based clk_lookups.
+ */
hw = clk_find_hw(dev_id, name);
+ }
if (IS_ERR(hw))
return ERR_CAST(hw);
parent = ERR_PTR(-EPROBE_DEFER);
} else {
parent = clk_core_get(core, index);
- if (IS_ERR(parent) && PTR_ERR(parent) == -ENOENT)
+ if (IS_ERR(parent) && PTR_ERR(parent) == -ENOENT && entry->name)
parent = clk_core_lookup(entry->name);
}
break;
/* Fallback to comparing globally unique names */
- if (!strcmp(parent->name, core->parents[i].name))
+ if (core->parents[i].name &&
+ !strcmp(parent->name, core->parents[i].name))
break;
}
FIXED_CLK(CLK_TOP_UNIVP_192M, "univpll_192m", "univpll", 192000000),
};
+static const struct mtk_fixed_factor top_early_divs[] = {
+ FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1, 2),
+};
+
static const struct mtk_fixed_factor top_divs[] = {
- FACTOR(CLK_TOP_CLK13M, "clk13m", "clk26m", 1,
- 2),
FACTOR(CLK_TOP_F26M_CK_D2, "csw_f26m_ck_d2", "clk26m", 1,
2),
FACTOR(CLK_TOP_SYSPLL_CK, "syspll_ck", "mainpll", 1,
return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
}
+static struct clk_onecell_data *top_clk_data;
+
+static void clk_mt8183_top_init_early(struct device_node *node)
+{
+ int i;
+
+ top_clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
+
+ for (i = 0; i < CLK_TOP_NR_CLK; i++)
+ top_clk_data->clks[i] = ERR_PTR(-EPROBE_DEFER);
+
+ mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs),
+ top_clk_data);
+
+ of_clk_add_provider(node, of_clk_src_onecell_get, top_clk_data);
+}
+
+CLK_OF_DECLARE_DRIVER(mt8183_topckgen, "mediatek,mt8183-topckgen",
+ clk_mt8183_top_init_early);
+
static int clk_mt8183_top_probe(struct platform_device *pdev)
{
struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
void __iomem *base;
- struct clk_onecell_data *clk_data;
struct device_node *node = pdev->dev.of_node;
base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(base))
return PTR_ERR(base);
- clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
-
mtk_clk_register_fixed_clks(top_fixed_clks, ARRAY_SIZE(top_fixed_clks),
- clk_data);
+ top_clk_data);
+
+ mtk_clk_register_factors(top_early_divs, ARRAY_SIZE(top_early_divs),
+ top_clk_data);
- mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data);
+ mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), top_clk_data);
mtk_clk_register_muxes(top_muxes, ARRAY_SIZE(top_muxes),
- node, &mt8183_clk_lock, clk_data);
+ node, &mt8183_clk_lock, top_clk_data);
mtk_clk_register_composites(top_aud_muxes, ARRAY_SIZE(top_aud_muxes),
- base, &mt8183_clk_lock, clk_data);
+ base, &mt8183_clk_lock, top_clk_data);
mtk_clk_register_composites(top_aud_divs, ARRAY_SIZE(top_aud_divs),
- base, &mt8183_clk_lock, clk_data);
+ base, &mt8183_clk_lock, top_clk_data);
mtk_clk_register_gates(node, top_clks, ARRAY_SIZE(top_clks),
- clk_data);
+ top_clk_data);
- return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ return of_clk_add_provider(node, of_clk_src_onecell_get, top_clk_data);
}
static int clk_mt8183_infra_probe(struct platform_device *pdev)
unsigned int reg = id / 32;
unsigned int bit = id % 32;
u32 bitmask = BIT(bit);
- unsigned long flags;
- u32 value;
dev_dbg(priv->dev, "reset %u%02u\n", reg, bit);
/* Reset module */
- spin_lock_irqsave(&priv->rmw_lock, flags);
- value = readl(priv->base + SRCR(reg));
- value |= bitmask;
- writel(value, priv->base + SRCR(reg));
- spin_unlock_irqrestore(&priv->rmw_lock, flags);
+ writel(bitmask, priv->base + SRCR(reg));
/* Wait for at least one cycle of the RCLK clock (@ ca. 32 kHz) */
udelay(35);
unsigned int reg = id / 32;
unsigned int bit = id % 32;
u32 bitmask = BIT(bit);
- unsigned long flags;
- u32 value;
dev_dbg(priv->dev, "assert %u%02u\n", reg, bit);
- spin_lock_irqsave(&priv->rmw_lock, flags);
- value = readl(priv->base + SRCR(reg));
- value |= bitmask;
- writel(value, priv->base + SRCR(reg));
- spin_unlock_irqrestore(&priv->rmw_lock, flags);
+ writel(bitmask, priv->base + SRCR(reg));
return 0;
}
#include "clk-exynos5-subcmu.h"
static struct samsung_clk_provider *ctx;
-static const struct exynos5_subcmu_info *cmu;
+static const struct exynos5_subcmu_info **cmu;
static int nr_cmus;
static void exynos5_subcmu_clk_save(void __iomem *base,
* when OF-core populates all device-tree nodes.
*/
void exynos5_subcmus_init(struct samsung_clk_provider *_ctx, int _nr_cmus,
- const struct exynos5_subcmu_info *_cmu)
+ const struct exynos5_subcmu_info **_cmu)
{
ctx = _ctx;
cmu = _cmu;
nr_cmus = _nr_cmus;
for (; _nr_cmus--; _cmu++) {
- exynos5_subcmu_defer_gate(ctx, _cmu->gate_clks,
- _cmu->nr_gate_clks);
- exynos5_subcmu_clk_save(ctx->reg_base, _cmu->suspend_regs,
- _cmu->nr_suspend_regs);
+ exynos5_subcmu_defer_gate(ctx, (*_cmu)->gate_clks,
+ (*_cmu)->nr_gate_clks);
+ exynos5_subcmu_clk_save(ctx->reg_base, (*_cmu)->suspend_regs,
+ (*_cmu)->nr_suspend_regs);
}
}
if (of_property_read_string(np, "label", &name) < 0)
continue;
for (i = 0; i < nr_cmus; i++)
- if (strcmp(cmu[i].pd_name, name) == 0)
+ if (strcmp(cmu[i]->pd_name, name) == 0)
exynos5_clk_register_subcmu(&pdev->dev,
- &cmu[i], np);
+ cmu[i], np);
}
return 0;
}
};
void exynos5_subcmus_init(struct samsung_clk_provider *ctx, int nr_cmus,
- const struct exynos5_subcmu_info *cmu);
+ const struct exynos5_subcmu_info **cmu);
#endif
.pd_name = "DISP1",
};
+static const struct exynos5_subcmu_info *exynos5250_subcmus[] = {
+ &exynos5250_disp_subcmu,
+};
+
static const struct samsung_pll_rate_table vpll_24mhz_tbl[] __initconst = {
/* sorted in descending order */
/* PLL_36XX_RATE(rate, m, p, s, k) */
samsung_clk_sleep_init(reg_base, exynos5250_clk_regs,
ARRAY_SIZE(exynos5250_clk_regs));
- exynos5_subcmus_init(ctx, 1, &exynos5250_disp_subcmu);
+ exynos5_subcmus_init(ctx, ARRAY_SIZE(exynos5250_subcmus),
+ exynos5250_subcmus);
samsung_clk_of_add_provider(np, ctx);
GATE_BUS_TOP, 24, 0, 0),
GATE(CLK_ACLK432_SCALER, "aclk432_scaler", "mout_user_aclk432_scaler",
GATE_BUS_TOP, 27, CLK_IS_CRITICAL, 0),
- GATE(CLK_MAU_EPLL, "mau_epll", "mout_user_mau_epll",
- SRC_MASK_TOP7, 20, CLK_SET_RATE_PARENT, 0),
};
static const struct samsung_mux_clock exynos5420_mux_clks[] __initconst = {
static const struct samsung_gate_clock exynos5420_gate_clks[] __initconst = {
GATE(CLK_SECKEY, "seckey", "aclk66_psgen", GATE_BUS_PERIS1, 1, 0, 0),
+ /* Maudio Block */
GATE(CLK_MAU_EPLL, "mau_epll", "mout_mau_epll_clk",
SRC_MASK_TOP7, 20, CLK_SET_RATE_PARENT, 0),
+ GATE(CLK_SCLK_MAUDIO0, "sclk_maudio0", "dout_maudio0",
+ GATE_TOP_SCLK_MAU, 0, CLK_SET_RATE_PARENT, 0),
+ GATE(CLK_SCLK_MAUPCM0, "sclk_maupcm0", "dout_maupcm0",
+ GATE_TOP_SCLK_MAU, 1, CLK_SET_RATE_PARENT, 0),
};
static const struct samsung_mux_clock exynos5x_mux_clks[] __initconst = {
/* GSCL Block */
DIV(0, "dout_gscl_blk_333", "aclk333_432_gscl", DIV2_RATIO0, 6, 2),
- /* MSCL Block */
- DIV(0, "dout_mscl_blk", "aclk400_mscl", DIV2_RATIO0, 28, 2),
-
/* PSGEN */
DIV(0, "dout_gen_blk", "mout_user_aclk266", DIV2_RATIO0, 8, 1),
DIV(0, "dout_jpg_blk", "aclk166", DIV2_RATIO0, 20, 1),
GATE(CLK_SCLK_DP1, "sclk_dp1", "dout_dp1",
GATE_TOP_SCLK_DISP1, 20, CLK_SET_RATE_PARENT, 0),
- /* Maudio Block */
- GATE(CLK_SCLK_MAUDIO0, "sclk_maudio0", "dout_maudio0",
- GATE_TOP_SCLK_MAU, 0, CLK_SET_RATE_PARENT, 0),
- GATE(CLK_SCLK_MAUPCM0, "sclk_maupcm0", "dout_maupcm0",
- GATE_TOP_SCLK_MAU, 1, CLK_SET_RATE_PARENT, 0),
-
/* FSYS Block */
GATE(CLK_TSI, "tsi", "aclk200_fsys", GATE_BUS_FSYS0, 0, 0, 0),
GATE(CLK_PDMA0, "pdma0", "aclk200_fsys", GATE_BUS_FSYS0, 1, 0, 0),
GATE(CLK_FIMC_LITE3, "fimc_lite3", "aclk333_432_gscl",
GATE_IP_GSCL1, 17, 0, 0),
- /* MSCL Block */
- GATE(CLK_MSCL0, "mscl0", "aclk400_mscl", GATE_IP_MSCL, 0, 0, 0),
- GATE(CLK_MSCL1, "mscl1", "aclk400_mscl", GATE_IP_MSCL, 1, 0, 0),
- GATE(CLK_MSCL2, "mscl2", "aclk400_mscl", GATE_IP_MSCL, 2, 0, 0),
- GATE(CLK_SMMU_MSCL0, "smmu_mscl0", "dout_mscl_blk",
- GATE_IP_MSCL, 8, 0, 0),
- GATE(CLK_SMMU_MSCL1, "smmu_mscl1", "dout_mscl_blk",
- GATE_IP_MSCL, 9, 0, 0),
- GATE(CLK_SMMU_MSCL2, "smmu_mscl2", "dout_mscl_blk",
- GATE_IP_MSCL, 10, 0, 0),
-
/* ISP */
GATE(CLK_SCLK_UART_ISP, "sclk_uart_isp", "dout_uart_isp",
GATE_TOP_SCLK_ISP, 0, CLK_SET_RATE_PARENT, 0),
{ DIV4_RATIO, 0, 0x3 }, /* DIV dout_mfc_blk */
};
-static const struct exynos5_subcmu_info exynos5x_subcmus[] = {
- {
- .div_clks = exynos5x_disp_div_clks,
- .nr_div_clks = ARRAY_SIZE(exynos5x_disp_div_clks),
- .gate_clks = exynos5x_disp_gate_clks,
- .nr_gate_clks = ARRAY_SIZE(exynos5x_disp_gate_clks),
- .suspend_regs = exynos5x_disp_suspend_regs,
- .nr_suspend_regs = ARRAY_SIZE(exynos5x_disp_suspend_regs),
- .pd_name = "DISP",
- }, {
- .div_clks = exynos5x_gsc_div_clks,
- .nr_div_clks = ARRAY_SIZE(exynos5x_gsc_div_clks),
- .gate_clks = exynos5x_gsc_gate_clks,
- .nr_gate_clks = ARRAY_SIZE(exynos5x_gsc_gate_clks),
- .suspend_regs = exynos5x_gsc_suspend_regs,
- .nr_suspend_regs = ARRAY_SIZE(exynos5x_gsc_suspend_regs),
- .pd_name = "GSC",
- }, {
- .div_clks = exynos5x_mfc_div_clks,
- .nr_div_clks = ARRAY_SIZE(exynos5x_mfc_div_clks),
- .gate_clks = exynos5x_mfc_gate_clks,
- .nr_gate_clks = ARRAY_SIZE(exynos5x_mfc_gate_clks),
- .suspend_regs = exynos5x_mfc_suspend_regs,
- .nr_suspend_regs = ARRAY_SIZE(exynos5x_mfc_suspend_regs),
- .pd_name = "MFC",
- },
+static const struct samsung_gate_clock exynos5x_mscl_gate_clks[] __initconst = {
+ /* MSCL Block */
+ GATE(CLK_MSCL0, "mscl0", "aclk400_mscl", GATE_IP_MSCL, 0, 0, 0),
+ GATE(CLK_MSCL1, "mscl1", "aclk400_mscl", GATE_IP_MSCL, 1, 0, 0),
+ GATE(CLK_MSCL2, "mscl2", "aclk400_mscl", GATE_IP_MSCL, 2, 0, 0),
+ GATE(CLK_SMMU_MSCL0, "smmu_mscl0", "dout_mscl_blk",
+ GATE_IP_MSCL, 8, 0, 0),
+ GATE(CLK_SMMU_MSCL1, "smmu_mscl1", "dout_mscl_blk",
+ GATE_IP_MSCL, 9, 0, 0),
+ GATE(CLK_SMMU_MSCL2, "smmu_mscl2", "dout_mscl_blk",
+ GATE_IP_MSCL, 10, 0, 0),
+};
+
+static const struct samsung_div_clock exynos5x_mscl_div_clks[] __initconst = {
+ DIV(0, "dout_mscl_blk", "aclk400_mscl", DIV2_RATIO0, 28, 2),
+};
+
+static struct exynos5_subcmu_reg_dump exynos5x_mscl_suspend_regs[] = {
+ { GATE_IP_MSCL, 0xffffffff, 0xffffffff }, /* MSCL gates */
+ { SRC_TOP3, 0, BIT(4) }, /* MUX mout_user_aclk400_mscl */
+ { DIV2_RATIO0, 0, 0x30000000 }, /* DIV dout_mscl_blk */
+};
+
+static const struct samsung_gate_clock exynos5800_mau_gate_clks[] __initconst = {
+ GATE(CLK_MAU_EPLL, "mau_epll", "mout_user_mau_epll",
+ SRC_MASK_TOP7, 20, CLK_SET_RATE_PARENT, 0),
+ GATE(CLK_SCLK_MAUDIO0, "sclk_maudio0", "dout_maudio0",
+ GATE_TOP_SCLK_MAU, 0, CLK_SET_RATE_PARENT, 0),
+ GATE(CLK_SCLK_MAUPCM0, "sclk_maupcm0", "dout_maupcm0",
+ GATE_TOP_SCLK_MAU, 1, CLK_SET_RATE_PARENT, 0),
+};
+
+static struct exynos5_subcmu_reg_dump exynos5800_mau_suspend_regs[] = {
+ { SRC_TOP9, 0, BIT(8) }, /* MUX mout_user_mau_epll */
+};
+
+static const struct exynos5_subcmu_info exynos5x_disp_subcmu = {
+ .div_clks = exynos5x_disp_div_clks,
+ .nr_div_clks = ARRAY_SIZE(exynos5x_disp_div_clks),
+ .gate_clks = exynos5x_disp_gate_clks,
+ .nr_gate_clks = ARRAY_SIZE(exynos5x_disp_gate_clks),
+ .suspend_regs = exynos5x_disp_suspend_regs,
+ .nr_suspend_regs = ARRAY_SIZE(exynos5x_disp_suspend_regs),
+ .pd_name = "DISP",
+};
+
+static const struct exynos5_subcmu_info exynos5x_gsc_subcmu = {
+ .div_clks = exynos5x_gsc_div_clks,
+ .nr_div_clks = ARRAY_SIZE(exynos5x_gsc_div_clks),
+ .gate_clks = exynos5x_gsc_gate_clks,
+ .nr_gate_clks = ARRAY_SIZE(exynos5x_gsc_gate_clks),
+ .suspend_regs = exynos5x_gsc_suspend_regs,
+ .nr_suspend_regs = ARRAY_SIZE(exynos5x_gsc_suspend_regs),
+ .pd_name = "GSC",
+};
+
+static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = {
+ .div_clks = exynos5x_mfc_div_clks,
+ .nr_div_clks = ARRAY_SIZE(exynos5x_mfc_div_clks),
+ .gate_clks = exynos5x_mfc_gate_clks,
+ .nr_gate_clks = ARRAY_SIZE(exynos5x_mfc_gate_clks),
+ .suspend_regs = exynos5x_mfc_suspend_regs,
+ .nr_suspend_regs = ARRAY_SIZE(exynos5x_mfc_suspend_regs),
+ .pd_name = "MFC",
+};
+
+static const struct exynos5_subcmu_info exynos5x_mscl_subcmu = {
+ .div_clks = exynos5x_mscl_div_clks,
+ .nr_div_clks = ARRAY_SIZE(exynos5x_mscl_div_clks),
+ .gate_clks = exynos5x_mscl_gate_clks,
+ .nr_gate_clks = ARRAY_SIZE(exynos5x_mscl_gate_clks),
+ .suspend_regs = exynos5x_mscl_suspend_regs,
+ .nr_suspend_regs = ARRAY_SIZE(exynos5x_mscl_suspend_regs),
+ .pd_name = "MSC",
+};
+
+static const struct exynos5_subcmu_info exynos5800_mau_subcmu = {
+ .gate_clks = exynos5800_mau_gate_clks,
+ .nr_gate_clks = ARRAY_SIZE(exynos5800_mau_gate_clks),
+ .suspend_regs = exynos5800_mau_suspend_regs,
+ .nr_suspend_regs = ARRAY_SIZE(exynos5800_mau_suspend_regs),
+ .pd_name = "MAU",
+};
+
+static const struct exynos5_subcmu_info *exynos5x_subcmus[] = {
+ &exynos5x_disp_subcmu,
+ &exynos5x_gsc_subcmu,
+ &exynos5x_mfc_subcmu,
+ &exynos5x_mscl_subcmu,
+};
+
+static const struct exynos5_subcmu_info *exynos5800_subcmus[] = {
+ &exynos5x_disp_subcmu,
+ &exynos5x_gsc_subcmu,
+ &exynos5x_mfc_subcmu,
+ &exynos5x_mscl_subcmu,
+ &exynos5800_mau_subcmu,
};
static const struct samsung_pll_rate_table exynos5420_pll2550x_24mhz_tbl[] __initconst = {
samsung_clk_extended_sleep_init(reg_base,
exynos5x_clk_regs, ARRAY_SIZE(exynos5x_clk_regs),
exynos5420_set_clksrc, ARRAY_SIZE(exynos5420_set_clksrc));
- if (soc == EXYNOS5800)
+
+ if (soc == EXYNOS5800) {
samsung_clk_sleep_init(reg_base, exynos5800_clk_regs,
ARRAY_SIZE(exynos5800_clk_regs));
- exynos5_subcmus_init(ctx, ARRAY_SIZE(exynos5x_subcmus),
- exynos5x_subcmus);
+
+ exynos5_subcmus_init(ctx, ARRAY_SIZE(exynos5800_subcmus),
+ exynos5800_subcmus);
+ } else {
+ exynos5_subcmus_init(ctx, ARRAY_SIZE(exynos5x_subcmus),
+ exynos5x_subcmus);
+ }
samsung_clk_of_add_provider(np, ctx);
}
if (socfpgaclk->fixed_div) {
div = socfpgaclk->fixed_div;
} else {
- if (!socfpgaclk->bypass_reg)
+ if (socfpgaclk->hw.reg)
div = ((readl(socfpgaclk->hw.reg) & 0x7ff) + 1);
}
tristate "Clock support for Spreadtrum SoCs"
depends on ARCH_SPRD || COMPILE_TEST
default ARCH_SPRD
+ select REGMAP_MMIO
if SPRD_COMMON_CLK
return get_cycles64();
}
-static DEFINE_PER_CPU(struct clocksource, riscv_clocksource) = {
+static struct clocksource riscv_clocksource = {
.name = "riscv_clocksource",
.rating = 300,
.mask = CLOCKSOURCE_MASK(64),
static int __init riscv_timer_init_dt(struct device_node *n)
{
int cpuid, hartid, error;
- struct clocksource *cs;
hartid = riscv_of_processor_hartid(n);
if (hartid < 0) {
pr_info("%s: Registering clocksource cpuid [%d] hartid [%d]\n",
__func__, cpuid, hartid);
- cs = per_cpu_ptr(&riscv_clocksource, cpuid);
- error = clocksource_register_hz(cs, riscv_timebase);
+ error = clocksource_register_hz(&riscv_clocksource, riscv_timebase);
if (error) {
pr_err("RISCV timer register failed [%d] for cpu = [%d]\n",
error, cpuid);
return 0;
}
-static struct cn_dev cdev = {
- .input = cn_rx_skb,
-};
-
static int cn_init(void)
{
struct cn_dev *dev = &cdev;
struct netlink_kernel_cfg cfg = {
.groups = CN_NETLINK_USERS + 0xf,
- .input = dev->input,
+ .input = cn_rx_skb,
};
dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg);
}
ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max);
- if (ret)
+ if (ret < 0)
break;
}
int err = -ENODEV;
cpu = of_get_cpu_node(policy->cpu, NULL);
+ if (!cpu)
+ goto out;
+ max_freqp = of_get_property(cpu, "clock-frequency", NULL);
of_node_put(cpu);
- if (!cpu)
+ if (!max_freqp) {
+ err = -EINVAL;
goto out;
+ }
+
+ /* we need the freq in kHz */
+ max_freq = *max_freqp / 1000;
dn = of_find_compatible_node(NULL, NULL, "1682m-sdc");
if (!dn)
}
pr_debug("init cpufreq on CPU %d\n", policy->cpu);
-
- max_freqp = of_get_property(cpu, "clock-frequency", NULL);
- if (!max_freqp) {
- err = -EINVAL;
- goto out_unmap_sdcpwr;
- }
-
- /* we need the freq in kHz */
- max_freq = *max_freqp / 1000;
-
pr_debug("max clock-frequency is at %u kHz\n", max_freq);
pr_debug("initializing frequency table\n");
cpufreq_generic_init(policy, pas_freqs, get_gizmo_latency());
return 0;
-out_unmap_sdcpwr:
- iounmap(sdcpwr_mapbase);
-
out_unmap_sdcasr:
iounmap(sdcasr_mapbase);
out:
static int ccp_aes_gcm_setauthsize(struct crypto_aead *tfm,
unsigned int authsize)
{
+ switch (authsize) {
+ case 16:
+ case 15:
+ case 14:
+ case 13:
+ case 12:
+ case 8:
+ case 4:
+ break;
+ default:
+ return -EINVAL;
+ }
+
return 0;
}
memset(&rctx->cmd, 0, sizeof(rctx->cmd));
INIT_LIST_HEAD(&rctx->cmd.entry);
rctx->cmd.engine = CCP_ENGINE_AES;
+ rctx->cmd.u.aes.authsize = crypto_aead_authsize(tfm);
rctx->cmd.u.aes.type = ctx->u.aes.type;
rctx->cmd.u.aes.mode = ctx->u.aes.mode;
rctx->cmd.u.aes.action = encrypt;
unsigned long flags;
unsigned int i;
+ /* If there's no device there's nothing to do */
+ if (!ccp)
+ return 0;
+
spin_lock_irqsave(&ccp->cmd_lock, flags);
ccp->suspending = 1;
unsigned long flags;
unsigned int i;
+ /* If there's no device there's nothing to do */
+ if (!ccp)
+ return 0;
+
spin_lock_irqsave(&ccp->cmd_lock, flags);
ccp->suspending = 0;
unsigned long long *final;
unsigned int dm_offset;
+ unsigned int authsize;
unsigned int jobid;
unsigned int ilen;
bool in_place = true; /* Default value */
if (!aes->key) /* Gotta have a key SGL */
return -EINVAL;
+ /* Zero defaults to 16 bytes, the maximum size */
+ authsize = aes->authsize ? aes->authsize : AES_BLOCK_SIZE;
+ switch (authsize) {
+ case 16:
+ case 15:
+ case 14:
+ case 13:
+ case 12:
+ case 8:
+ case 4:
+ break;
+ default:
+ return -EINVAL;
+ }
+
/* First, decompose the source buffer into AAD & PT,
* and the destination buffer into AAD, CT & tag, or
* the input into CT & tag.
p_tag = scatterwalk_ffwd(sg_tag, p_outp, ilen);
} else {
/* Input length for decryption includes tag */
- ilen = aes->src_len - AES_BLOCK_SIZE;
+ ilen = aes->src_len - authsize;
p_tag = scatterwalk_ffwd(sg_tag, p_inp, ilen);
}
while (src.sg_wa.bytes_left) {
ccp_prepare_data(&src, &dst, &op, AES_BLOCK_SIZE, true);
if (!src.sg_wa.bytes_left) {
- unsigned int nbytes = aes->src_len
- % AES_BLOCK_SIZE;
+ unsigned int nbytes = ilen % AES_BLOCK_SIZE;
if (nbytes) {
op.eom = 1;
if (aes->action == CCP_AES_ACTION_ENCRYPT) {
/* Put the ciphered tag after the ciphertext. */
- ccp_get_dm_area(&final_wa, 0, p_tag, 0, AES_BLOCK_SIZE);
+ ccp_get_dm_area(&final_wa, 0, p_tag, 0, authsize);
} else {
/* Does this ciphered tag match the input? */
- ret = ccp_init_dm_workarea(&tag, cmd_q, AES_BLOCK_SIZE,
+ ret = ccp_init_dm_workarea(&tag, cmd_q, authsize,
DMA_BIDIRECTIONAL);
if (ret)
goto e_tag;
- ret = ccp_set_dm_area(&tag, 0, p_tag, 0, AES_BLOCK_SIZE);
+ ret = ccp_set_dm_area(&tag, 0, p_tag, 0, authsize);
if (ret)
goto e_tag;
ret = crypto_memneq(tag.address, final_wa.address,
- AES_BLOCK_SIZE) ? -EBADMSG : 0;
+ authsize) ? -EBADMSG : 0;
ccp_dm_free(&tag);
}
ccp_dm_free(&final_wa);
e_dst:
- if (aes->src_len && !in_place)
+ if (ilen > 0 && !in_place)
ccp_free_data(&dst, cmd_q);
e_src:
- if (aes->src_len)
+ if (ilen > 0)
ccp_free_data(&src, cmd_q);
e_aad:
case CRYP_KEY_SIZE_256:
ctx->key_4_l = readl_relaxed(&src_reg->key_4_l);
ctx->key_4_r = readl_relaxed(&src_reg->key_4_r);
+ /* Fall through */
case CRYP_KEY_SIZE_192:
ctx->key_3_l = readl_relaxed(&src_reg->key_3_l);
ctx->key_3_r = readl_relaxed(&src_reg->key_3_r);
+ /* Fall through */
case CRYP_KEY_SIZE_128:
ctx->key_2_l = readl_relaxed(&src_reg->key_2_l);
ctx->key_2_r = readl_relaxed(&src_reg->key_2_r);
+ /* Fall through */
default:
ctx->key_1_l = readl_relaxed(&src_reg->key_1_l);
case CRYP_KEY_SIZE_256:
writel_relaxed(ctx->key_4_l, ®->key_4_l);
writel_relaxed(ctx->key_4_r, ®->key_4_r);
+ /* Fall through */
case CRYP_KEY_SIZE_192:
writel_relaxed(ctx->key_3_l, ®->key_3_l);
writel_relaxed(ctx->key_3_r, ®->key_3_r);
+ /* Fall through */
case CRYP_KEY_SIZE_128:
writel_relaxed(ctx->key_2_l, ®->key_2_l);
writel_relaxed(ctx->key_2_r, ®->key_2_r);
+ /* Fall through */
default:
writel_relaxed(ctx->key_1_l, ®->key_1_l);
struct dw_edma_region {
phys_addr_t paddr;
- dma_addr_t vaddr;
+ void __iomem *vaddr;
size_t sz;
};
chip->id = pdev->devfn;
chip->irq = pdev->irq;
- dw->rg_region.vaddr = (dma_addr_t)pcim_iomap_table(pdev)[pdata->rg_bar];
+ dw->rg_region.vaddr = pcim_iomap_table(pdev)[pdata->rg_bar];
dw->rg_region.vaddr += pdata->rg_off;
dw->rg_region.paddr = pdev->resource[pdata->rg_bar].start;
dw->rg_region.paddr += pdata->rg_off;
dw->rg_region.sz = pdata->rg_sz;
- dw->ll_region.vaddr = (dma_addr_t)pcim_iomap_table(pdev)[pdata->ll_bar];
+ dw->ll_region.vaddr = pcim_iomap_table(pdev)[pdata->ll_bar];
dw->ll_region.vaddr += pdata->ll_off;
dw->ll_region.paddr = pdev->resource[pdata->ll_bar].start;
dw->ll_region.paddr += pdata->ll_off;
dw->ll_region.sz = pdata->ll_sz;
- dw->dt_region.vaddr = (dma_addr_t)pcim_iomap_table(pdev)[pdata->dt_bar];
+ dw->dt_region.vaddr = pcim_iomap_table(pdev)[pdata->dt_bar];
dw->dt_region.vaddr += pdata->dt_off;
dw->dt_region.paddr = pdev->resource[pdata->dt_bar].start;
dw->dt_region.paddr += pdata->dt_off;
pci_dbg(pdev, "Mode:\t%s\n",
dw->mode == EDMA_MODE_LEGACY ? "Legacy" : "Unroll");
- pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%pa, p=%pa)\n",
+ pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
pdata->rg_bar, pdata->rg_off, pdata->rg_sz,
- &dw->rg_region.vaddr, &dw->rg_region.paddr);
+ dw->rg_region.vaddr, &dw->rg_region.paddr);
- pci_dbg(pdev, "L. List:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%pa, p=%pa)\n",
+ pci_dbg(pdev, "L. List:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
pdata->ll_bar, pdata->ll_off, pdata->ll_sz,
- &dw->ll_region.vaddr, &dw->ll_region.paddr);
+ dw->ll_region.vaddr, &dw->ll_region.paddr);
- pci_dbg(pdev, "Data:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%pa, p=%pa)\n",
+ pci_dbg(pdev, "Data:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
pdata->dt_bar, pdata->dt_off, pdata->dt_sz,
- &dw->dt_region.vaddr, &dw->dt_region.paddr);
+ dw->dt_region.vaddr, &dw->dt_region.paddr);
pci_dbg(pdev, "Nr. IRQs:\t%u\n", dw->nr_irqs);
static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
{
- return (struct dw_edma_v0_regs __iomem *)dw->rg_region.vaddr;
+ return dw->rg_region.vaddr;
}
#define SET(dw, name, value) \
static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
{
struct dw_edma_burst *child;
- struct dw_edma_v0_lli *lli;
- struct dw_edma_v0_llp *llp;
+ struct dw_edma_v0_lli __iomem *lli;
+ struct dw_edma_v0_llp __iomem *llp;
u32 control = 0, i = 0;
- u64 sar, dar, addr;
int j;
- lli = (struct dw_edma_v0_lli *)chunk->ll_region.vaddr;
+ lli = chunk->ll_region.vaddr;
if (chunk->cb)
control = DW_EDMA_V0_CB;
/* Transfer size */
SET_LL(&lli[i].transfer_size, child->sz);
/* SAR - low, high */
- sar = cpu_to_le64(child->sar);
- SET_LL(&lli[i].sar_low, lower_32_bits(sar));
- SET_LL(&lli[i].sar_high, upper_32_bits(sar));
+ SET_LL(&lli[i].sar_low, lower_32_bits(child->sar));
+ SET_LL(&lli[i].sar_high, upper_32_bits(child->sar));
/* DAR - low, high */
- dar = cpu_to_le64(child->dar);
- SET_LL(&lli[i].dar_low, lower_32_bits(dar));
- SET_LL(&lli[i].dar_high, upper_32_bits(dar));
+ SET_LL(&lli[i].dar_low, lower_32_bits(child->dar));
+ SET_LL(&lli[i].dar_high, upper_32_bits(child->dar));
i++;
}
- llp = (struct dw_edma_v0_llp *)&lli[i];
+ llp = (void __iomem *)&lli[i];
control = DW_EDMA_V0_LLP | DW_EDMA_V0_TCB;
if (!chunk->cb)
control |= DW_EDMA_V0_CB;
/* Channel control */
SET_LL(&llp->control, control);
/* Linked list - low, high */
- addr = cpu_to_le64(chunk->ll_region.paddr);
- SET_LL(&llp->llp_low, lower_32_bits(addr));
- SET_LL(&llp->llp_high, upper_32_bits(addr));
+ SET_LL(&llp->llp_low, lower_32_bits(chunk->ll_region.paddr));
+ SET_LL(&llp->llp_high, upper_32_bits(chunk->ll_region.paddr));
}
void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
struct dw_edma_chan *chan = chunk->chan;
struct dw_edma *dw = chan->chip->dw;
u32 tmp;
- u64 llp;
dw_edma_v0_core_write_chunk(chunk);
SET_CH(dw, chan->dir, chan->id, ch_control1,
(DW_EDMA_V0_CCS | DW_EDMA_V0_LLE));
/* Linked list - low, high */
- llp = cpu_to_le64(chunk->ll_region.paddr);
- SET_CH(dw, chan->dir, chan->id, llp_low, lower_32_bits(llp));
- SET_CH(dw, chan->dir, chan->id, llp_high, upper_32_bits(llp));
+ SET_CH(dw, chan->dir, chan->id, llp_low,
+ lower_32_bits(chunk->ll_region.paddr));
+ SET_CH(dw, chan->dir, chan->id, llp_high,
+ upper_32_bits(chunk->ll_region.paddr));
}
/* Doorbell */
SET_RW(dw, chan->dir, doorbell,
#include "dw-edma-core.h"
#define REGS_ADDR(name) \
- ((dma_addr_t *)®s->name)
+ ((void __force *)®s->name)
#define REGISTER(name) \
{ #name, REGS_ADDR(name) }
static struct dentry *base_dir;
static struct dw_edma *dw;
-static struct dw_edma_v0_regs *regs;
+static struct dw_edma_v0_regs __iomem *regs;
static struct {
- void *start;
- void *end;
+ void __iomem *start;
+ void __iomem *end;
} lim[2][EDMA_V0_MAX_NR_CH];
struct debugfs_entries {
- char name[24];
+ const char *name;
dma_addr_t *reg;
};
static int dw_edma_debugfs_u32_get(void *data, u64 *val)
{
+ void __iomem *reg = (void __force __iomem *)data;
if (dw->mode == EDMA_MODE_LEGACY &&
- data >= (void *)®s->type.legacy.ch) {
- void *ptr = (void *)®s->type.legacy.ch;
+ reg >= (void __iomem *)®s->type.legacy.ch) {
+ void __iomem *ptr = ®s->type.legacy.ch;
u32 viewport_sel = 0;
unsigned long flags;
u16 ch;
for (ch = 0; ch < dw->wr_ch_cnt; ch++)
- if (lim[0][ch].start >= data && data < lim[0][ch].end) {
- ptr += (data - lim[0][ch].start);
+ if (lim[0][ch].start >= reg && reg < lim[0][ch].end) {
+ ptr += (reg - lim[0][ch].start);
goto legacy_sel_wr;
}
for (ch = 0; ch < dw->rd_ch_cnt; ch++)
- if (lim[1][ch].start >= data && data < lim[1][ch].end) {
- ptr += (data - lim[1][ch].start);
+ if (lim[1][ch].start >= reg && reg < lim[1][ch].end) {
+ ptr += (reg - lim[1][ch].start);
goto legacy_sel_rd;
}
raw_spin_unlock_irqrestore(&dw->lock, flags);
} else {
- *val = readl(data);
+ *val = readl(reg);
}
return 0;
}
}
-static void dw_edma_debugfs_regs_ch(struct dw_edma_v0_ch_regs *regs,
+static void dw_edma_debugfs_regs_ch(struct dw_edma_v0_ch_regs __iomem *regs,
struct dentry *dir)
{
int nr_entries;
if (!dw)
return;
- regs = (struct dw_edma_v0_regs *)dw->rg_region.vaddr;
+ regs = dw->rg_region.vaddr;
if (!regs)
return;
switch (chan->feature & FSL_DMA_IP_MASK) {
case FSL_DMA_IP_85XX:
chan->toggle_ext_pause = fsl_chan_toggle_ext_pause;
+ /* Fall through */
case FSL_DMA_IP_83XX:
chan->toggle_ext_start = fsl_chan_toggle_ext_start;
chan->set_src_loop_size = fsl_chan_set_src_loop_size;
* @iomem: remapped I/O memory base
* @n_channels: number of available channels
* @channels: array of DMAC channels
+ * @channels_mask: bitfield of which DMA channels are managed by this driver
* @modules: bitmask of client modules in use
*/
struct rcar_dmac {
unsigned int n_channels;
struct rcar_dmac_chan *channels;
+ unsigned int channels_mask;
DECLARE_BITMAP(modules, 256);
};
u16 dmaor;
/* Clear all channels and enable the DMAC globally. */
- rcar_dmac_write(dmac, RCAR_DMACHCLR, GENMASK(dmac->n_channels - 1, 0));
+ rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask);
rcar_dmac_write(dmac, RCAR_DMAOR,
RCAR_DMAOR_PRI_FIXED | RCAR_DMAOR_DME);
for (i = 0; i < dmac->n_channels; ++i) {
struct rcar_dmac_chan *chan = &dmac->channels[i];
+ if (!(dmac->channels_mask & BIT(i)))
+ continue;
+
/* Stop and reinitialize the channel. */
spin_lock_irq(&chan->lock);
rcar_dmac_chan_halt(chan);
return 0;
}
+#define RCAR_DMAC_MAX_CHANNELS 32
+
static int rcar_dmac_parse_of(struct device *dev, struct rcar_dmac *dmac)
{
struct device_node *np = dev->of_node;
return ret;
}
- if (dmac->n_channels <= 0 || dmac->n_channels >= 100) {
+ /* The hardware and driver don't support more than 32 bits in CHCLR */
+ if (dmac->n_channels <= 0 ||
+ dmac->n_channels >= RCAR_DMAC_MAX_CHANNELS) {
dev_err(dev, "invalid number of channels %u\n",
dmac->n_channels);
return -EINVAL;
}
+ dmac->channels_mask = GENMASK(dmac->n_channels - 1, 0);
+
return 0;
}
DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES |
DMA_SLAVE_BUSWIDTH_8_BYTES | DMA_SLAVE_BUSWIDTH_16_BYTES |
DMA_SLAVE_BUSWIDTH_32_BYTES | DMA_SLAVE_BUSWIDTH_64_BYTES;
- unsigned int channels_offset = 0;
struct dma_device *engine;
struct rcar_dmac *dmac;
struct resource *mem;
* level we can't disable it selectively, so ignore channel 0 for now if
* the device is part of an IOMMU group.
*/
- if (device_iommu_mapped(&pdev->dev)) {
- dmac->n_channels--;
- channels_offset = 1;
- }
+ if (device_iommu_mapped(&pdev->dev))
+ dmac->channels_mask &= ~BIT(0);
dmac->channels = devm_kcalloc(&pdev->dev, dmac->n_channels,
sizeof(*dmac->channels), GFP_KERNEL);
INIT_LIST_HEAD(&engine->channels);
for (i = 0; i < dmac->n_channels; ++i) {
- ret = rcar_dmac_chan_probe(dmac, &dmac->channels[i],
- i + channels_offset);
+ if (!(dmac->channels_mask & BIT(i)))
+ continue;
+
+ ret = rcar_dmac_chan_probe(dmac, &dmac->channels[i], i);
if (ret < 0)
goto error;
}
struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
struct dma_slave_config *slave_cfg = &schan->slave_cfg;
dma_addr_t src = 0, dst = 0;
+ dma_addr_t start_src = 0, start_dst = 0;
struct sprd_dma_desc *sdesc;
struct scatterlist *sg;
u32 len = 0;
dst = sg_dma_address(sg);
}
+ if (!i) {
+ start_src = src;
+ start_dst = dst;
+ }
+
/*
* The link-list mode needs at least 2 link-list
* configurations. If there is only one sg, it doesn't
}
}
- ret = sprd_dma_fill_desc(chan, &sdesc->chn_hw, 0, 0, src, dst, len,
- dir, flags, slave_cfg);
+ ret = sprd_dma_fill_desc(chan, &sdesc->chn_hw, 0, 0, start_src,
+ start_dst, len, dir, flags, slave_cfg);
if (ret) {
kfree(sdesc);
return NULL;
* when the DMA hw is powered off.
* TODO: Add save/restore of D40_DREG_GCC on dma40 v3 or later, if that works.
*/
-static u32 d40_backup_regs[] = {
+static __maybe_unused u32 d40_backup_regs[] = {
D40_DREG_LCPA,
D40_DREG_LCLA,
D40_DREG_PRMSE,
#define BACKUP_REGS_SZ_V4B ARRAY_SIZE(d40_backup_regs_v4b)
-static u32 d40_backup_regs_chan[] = {
+static __maybe_unused u32 d40_backup_regs_chan[] = {
D40_CHAN_REG_SSCFG,
D40_CHAN_REG_SSELT,
D40_CHAN_REG_SSPTR,
chan = &dmadev->chan[id];
if (!chan) {
- dev_err(chan2dev(chan), "MDMA channel not initialized\n");
+ dev_dbg(mdma2dev(dmadev), "MDMA channel not initialized\n");
goto exit;
}
return chan;
}
-static int tegra_adma_runtime_suspend(struct device *dev)
+static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
{
struct tegra_adma *tdma = dev_get_drvdata(dev);
struct tegra_adma_chan_regs *ch_reg;
return 0;
}
-static int tegra_adma_runtime_resume(struct device *dev)
+static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
{
struct tegra_adma *tdma = dev_get_drvdata(dev);
struct tegra_adma_chan_regs *ch_reg;
ret = of_property_read_u32_array(node, pname, (u32 *)rsv_events,
nelm * 2);
- if (ret)
+ if (ret) {
+ kfree(rsv_events);
return ret;
+ }
for (i = 0; i < nelm; i++) {
ti_dra7_xbar_reserve(rsv_events[i][0], rsv_events[i][1],
if (src_icg) {
d->ccr |= CCR_SRC_AMODE_DBLIDX;
d->ei = 1;
- d->fi = src_icg;
+ d->fi = src_icg + 1;
} else if (xt->src_inc) {
d->ccr |= CCR_SRC_AMODE_POSTINC;
d->fi = 0;
if (dst_icg) {
d->ccr |= CCR_DST_AMODE_DBLIDX;
sg->ei = 1;
- sg->fi = dst_icg;
+ sg->fi = dst_icg + 1;
} else if (xt->dst_inc) {
d->ccr |= CCR_DST_AMODE_POSTINC;
sg->fi = 0;
rc = devm_request_irq(&pdev->dev, irq, omap_dma_irq,
IRQF_SHARED, "omap-dma-engine", od);
- if (rc)
+ if (rc) {
+ omap_dma_free(od);
return rc;
+ }
}
if (omap_dma_glbl_read(od, CAPS_0) & CAPS_0_SUPPORT_LL123)
device->bc_implemented = BC_IMPLEMENTED;
break;
}
- /* else fall through to case address error */
+ /* else, fall through - to case address error */
case RCODE_ADDRESS_ERROR:
device->bc_implemented = BC_UNIMPLEMENTED;
}
if ((data[0] & bit) == (data[1] & bit))
continue;
- /* 1394-1995 IRM, fall through to retry. */
+ /* fall through - It's a 1394-1995 IRM, retry. */
default:
if (retry) {
retry--;
switch (port_type) {
case SELFID_PORT_CHILD:
(*child_port_count)++;
+ /* fall through */
case SELFID_PORT_PARENT:
case SELFID_PORT_NCONN:
(*total_port_count)++;
config ISCSI_IBFT_FIND
bool "iSCSI Boot Firmware Table Attributes"
- depends on X86 && ACPI
+ depends on X86 && ISCSI_IBFT
default n
help
This option enables the kernel to find the region of memory
config ISCSI_IBFT
tristate "iSCSI Boot Firmware Table Attributes module"
select ISCSI_BOOT_SYSFS
- depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL
+ select ISCSI_IBFT_FIND if X86
+ depends on ACPI && SCSI && SCSI_LOWLEVEL
default n
help
This option enables support for detection and exposing of iSCSI
return status;
}
+#define GET_EFI_CONFIG_TABLE(bits) \
+static void *get_efi_config_table##bits(efi_system_table_t *_sys_table, \
+ efi_guid_t guid) \
+{ \
+ efi_system_table_##bits##_t *sys_table; \
+ efi_config_table_##bits##_t *tables; \
+ int i; \
+ \
+ sys_table = (typeof(sys_table))_sys_table; \
+ tables = (typeof(tables))(unsigned long)sys_table->tables; \
+ \
+ for (i = 0; i < sys_table->nr_tables; i++) { \
+ if (efi_guidcmp(tables[i].guid, guid) != 0) \
+ continue; \
+ \
+ return (void *)(unsigned long)tables[i].table; \
+ } \
+ \
+ return NULL; \
+}
+GET_EFI_CONFIG_TABLE(32)
+GET_EFI_CONFIG_TABLE(64)
+
void *get_efi_config_table(efi_system_table_t *sys_table, efi_guid_t guid)
{
- efi_config_table_t *tables = (efi_config_table_t *)sys_table->tables;
- int i;
-
- for (i = 0; i < sys_table->nr_tables; i++) {
- if (efi_guidcmp(tables[i].guid, guid) != 0)
- continue;
-
- return (void *)tables[i].table;
- }
-
- return NULL;
+ if (efi_is_64bit())
+ return get_efi_config_table64(sys_table, guid);
+ else
+ return get_efi_config_table32(sys_table, guid);
}
MODULE_LICENSE("GPL");
MODULE_VERSION(IBFT_ISCSI_VERSION);
+#ifndef CONFIG_ISCSI_IBFT_FIND
+struct acpi_table_ibft *ibft_addr;
+#endif
+
struct ibft_hdr {
u8 id;
u8 version;
config FPGA_MGR_ALTERA_PS_SPI
tristate "Altera FPGA Passive Serial over SPI"
depends on SPI
+ select BITREVERSE
help
FPGA manager driver support for Altera Arria/Cyclone/Stratix
using the passive serial interface over SPI.
return -EIO;
}
- if (!IS_ERR(conf->confd)) {
+ if (conf->confd) {
if (!gpiod_get_raw_value_cansleep(conf->confd)) {
dev_err(&mgr->dev, "CONF_DONE is inactive!\n");
return -EIO;
return PTR_ERR(conf->status);
}
- conf->confd = devm_gpiod_get(&spi->dev, "confd", GPIOD_IN);
+ conf->confd = devm_gpiod_get_optional(&spi->dev, "confd", GPIOD_IN);
if (IS_ERR(conf->confd)) {
- dev_warn(&spi->dev, "Not using confd gpio: %ld\n",
- PTR_ERR(conf->confd));
+ dev_err(&spi->dev, "Failed to get confd gpio: %ld\n",
+ PTR_ERR(conf->confd));
+ return PTR_ERR(conf->confd);
+ } else if (!conf->confd) {
+ dev_warn(&spi->dev, "Not using confd gpio");
}
/* Register manager with unique name */
#define SCOM_STATUS_PIB_RESP_MASK 0x00007000
#define SCOM_STATUS_PIB_RESP_SHIFT 12
-#define SCOM_STATUS_ANY_ERR (SCOM_STATUS_ERR_SUMMARY | \
- SCOM_STATUS_PROTECTION | \
+#define SCOM_STATUS_ANY_ERR (SCOM_STATUS_PROTECTION | \
SCOM_STATUS_PARITY | \
SCOM_STATUS_PIB_ABORT | \
SCOM_STATUS_PIB_RESP_MASK)
/* Return -EBUSY on PIB abort to force a retry */
if (status & SCOM_STATUS_PIB_ABORT)
return -EBUSY;
- if (status & SCOM_STATUS_ERR_SUMMARY) {
- fsi_device_write(scom->fsi_dev, SCOM_FSI2PIB_RESET_REG, &dummy,
- sizeof(uint32_t));
- return -EIO;
- }
return 0;
}
u8 new_irqs;
int level, i;
u8 invert_irq_mask[MAX_BANK];
- int reg_direction[MAX_BANK];
+ u8 reg_direction[MAX_BANK];
- regmap_bulk_read(chip->regmap, chip->regs->direction, reg_direction,
- NBANK(chip));
+ pca953x_read_regs(chip, chip->regs->direction, reg_direction);
if (chip->driver_data & PCA_PCAL) {
/* Enable latch on interrupt-enabled inputs */
bool pending_seen = false;
bool trigger_seen = false;
u8 trigger[MAX_BANK];
- int reg_direction[MAX_BANK];
+ u8 reg_direction[MAX_BANK];
int ret, i;
if (chip->driver_data & PCA_PCAL) {
return false;
/* Remove output pins from the equation */
- regmap_bulk_read(chip->regmap, chip->regs->direction, reg_direction,
- NBANK(chip));
+ pca953x_read_regs(chip, chip->regs->direction, reg_direction);
for (i = 0; i < NBANK(chip); i++)
cur_stat[i] &= reg_direction[i];
{
struct i2c_client *client = chip->client;
struct irq_chip *irq_chip = &chip->irq_chip;
- int reg_direction[MAX_BANK];
+ u8 reg_direction[MAX_BANK];
int ret, i;
if (!client->irq)
* interrupt. We have to rely on the previous read for
* this purpose.
*/
- regmap_bulk_read(chip->regmap, chip->regs->direction, reg_direction,
- NBANK(chip));
+ pca953x_read_regs(chip, chip->regs->direction, reg_direction);
for (i = 0; i < NBANK(chip); i++)
chip->irq_stat[i] &= reg_direction[i];
mutex_init(&chip->irq_lock);
/* Special handling for SPI GPIOs if used */
if (IS_ERR(desc))
desc = of_find_spi_gpio(dev, con_id, &of_flags);
- if (IS_ERR(desc)) {
+ if (IS_ERR(desc) && PTR_ERR(desc) != -EPROBE_DEFER) {
/* This quirk looks up flags and all */
desc = of_find_spi_cs_gpio(dev, con_id, idx, flags);
if (!IS_ERR(desc))
}
if (eflags & GPIOEVENT_REQUEST_RISING_EDGE)
- irqflags |= IRQF_TRIGGER_RISING;
+ irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
+ IRQF_TRIGGER_FALLING : IRQF_TRIGGER_RISING;
if (eflags & GPIOEVENT_REQUEST_FALLING_EDGE)
- irqflags |= IRQF_TRIGGER_FALLING;
+ irqflags |= test_bit(FLAG_ACTIVE_LOW, &desc->flags) ?
+ IRQF_TRIGGER_RISING : IRQF_TRIGGER_FALLING;
irqflags |= IRQF_ONESHOT;
INIT_KFIFO(le->events);
if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
lineinfo.flags |= GPIOLINE_FLAG_ACTIVE_LOW;
if (test_bit(FLAG_OPEN_DRAIN, &desc->flags))
- lineinfo.flags |= GPIOLINE_FLAG_OPEN_DRAIN;
+ lineinfo.flags |= (GPIOLINE_FLAG_OPEN_DRAIN |
+ GPIOLINE_FLAG_IS_OUT);
if (test_bit(FLAG_OPEN_SOURCE, &desc->flags))
- lineinfo.flags |= GPIOLINE_FLAG_OPEN_SOURCE;
+ lineinfo.flags |= (GPIOLINE_FLAG_OPEN_SOURCE |
+ GPIOLINE_FLAG_IS_OUT);
if (copy_to_user(ip, &lineinfo, sizeof(lineinfo)))
return -EFAULT;
if (status)
goto err_remove_from_list;
- status = gpiochip_irqchip_init_valid_mask(chip);
- if (status)
- goto err_remove_from_list;
-
status = gpiochip_alloc_valid_mask(chip);
if (status)
- goto err_remove_irqchip_mask;
-
- status = gpiochip_add_irqchip(chip, lock_key, request_key);
- if (status)
- goto err_free_gpiochip_mask;
+ goto err_remove_from_list;
status = of_gpiochip_add(chip);
if (status)
- goto err_remove_chip;
+ goto err_free_gpiochip_mask;
status = gpiochip_init_valid_mask(chip);
if (status)
for (i = 0; i < chip->ngpio; i++) {
struct gpio_desc *desc = &gdev->descs[i];
- if (chip->get_direction && gpiochip_line_is_valid(chip, i))
- desc->flags = !chip->get_direction(chip, i) ?
- (1 << FLAG_IS_OUT) : 0;
- else
- desc->flags = !chip->direction_input ?
- (1 << FLAG_IS_OUT) : 0;
+ if (chip->get_direction && gpiochip_line_is_valid(chip, i)) {
+ if (!chip->get_direction(chip, i))
+ set_bit(FLAG_IS_OUT, &desc->flags);
+ else
+ clear_bit(FLAG_IS_OUT, &desc->flags);
+ } else {
+ if (!chip->direction_input)
+ set_bit(FLAG_IS_OUT, &desc->flags);
+ else
+ clear_bit(FLAG_IS_OUT, &desc->flags);
+ }
}
acpi_gpiochip_add(chip);
machine_gpiochip_add(chip);
+ status = gpiochip_irqchip_init_valid_mask(chip);
+ if (status)
+ goto err_remove_acpi_chip;
+
+ status = gpiochip_add_irqchip(chip, lock_key, request_key);
+ if (status)
+ goto err_remove_irqchip_mask;
+
/*
* By first adding the chardev, and then adding the device,
* we get a device node entry in sysfs under
if (gpiolib_initialized) {
status = gpiochip_setup_dev(gdev);
if (status)
- goto err_remove_acpi_chip;
+ goto err_remove_irqchip;
}
return 0;
+err_remove_irqchip:
+ gpiochip_irqchip_remove(chip);
+err_remove_irqchip_mask:
+ gpiochip_irqchip_free_valid_mask(chip);
err_remove_acpi_chip:
acpi_gpiochip_remove(chip);
err_remove_of_chip:
gpiochip_free_hogs(chip);
of_gpiochip_remove(chip);
-err_remove_chip:
- gpiochip_irqchip_remove(chip);
err_free_gpiochip_mask:
gpiochip_free_valid_mask(chip);
-err_remove_irqchip_mask:
- gpiochip_irqchip_free_valid_mask(chip);
err_remove_from_list:
spin_lock_irqsave(&gpio_lock, flags);
list_del(&gdev->list);
config DRM_I810
tristate "Intel I810"
# !PREEMPT because of missing ioctl locking
- depends on DRM && AGP && AGP_INTEL && (!PREEMPT || BROKEN)
+ depends on DRM && AGP && AGP_INTEL && (!PREEMPTION || BROKEN)
help
Choose this option if you have an Intel I810 graphics card. If M is
selected, the module will be called i810. AGP support is required
adev->asic_type != CHIP_FIJI &&
adev->asic_type != CHIP_POLARIS10 &&
adev->asic_type != CHIP_POLARIS11 &&
- adev->asic_type != CHIP_POLARIS12) ?
+ adev->asic_type != CHIP_POLARIS12 &&
+ adev->asic_type != CHIP_VEGAM) ?
VI_BO_SIZE_ALIGN : 1;
mapping_flags = AMDGPU_VM_PAGE_READABLE;
{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
+ { 0x1002, 0x699f, 0x1028, 0x0814, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0x1002, 0x6900, 0x1025, 0x125A, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0x1002, 0x6900, 0x17AA, 0x3806, AMDGPU_PX_QUIRK_FORCE_ATPX },
{ 0, 0, 0, 0, 0 },
return r;
}
- fence = amdgpu_ctx_get_fence(ctx, entity,
- deps[i].handle);
+ fence = amdgpu_ctx_get_fence(ctx, entity, deps[i].handle);
+ amdgpu_ctx_put(ctx);
+
+ if (IS_ERR(fence))
+ return PTR_ERR(fence);
+ else if (!fence)
+ continue;
if (chunk->chunk_id == AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES) {
- struct drm_sched_fence *s_fence = to_drm_sched_fence(fence);
+ struct drm_sched_fence *s_fence;
struct dma_fence *old = fence;
+ s_fence = to_drm_sched_fence(fence);
fence = dma_fence_get(&s_fence->scheduled);
dma_fence_put(old);
}
- if (IS_ERR(fence)) {
- r = PTR_ERR(fence);
- amdgpu_ctx_put(ctx);
+ r = amdgpu_sync_fence(p->adev, &p->job->sync, fence, true);
+ dma_fence_put(fence);
+ if (r)
return r;
- } else if (fence) {
- r = amdgpu_sync_fence(p->adev, &p->job->sync, fence,
- true);
- dma_fence_put(fence);
- amdgpu_ctx_put(ctx);
- if (r)
- return r;
- }
}
return 0;
}
num_deps = chunk->length_dw * 4 /
sizeof(struct drm_amdgpu_cs_chunk_sem);
+ if (p->post_deps)
+ return -EINVAL;
+
p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps),
GFP_KERNEL);
p->num_post_deps = 0;
static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p,
- struct amdgpu_cs_chunk
- *chunk)
+ struct amdgpu_cs_chunk *chunk)
{
struct drm_amdgpu_cs_chunk_syncobj *syncobj_deps;
unsigned num_deps;
num_deps = chunk->length_dw * 4 /
sizeof(struct drm_amdgpu_cs_chunk_syncobj);
+ if (p->post_deps)
+ return -EINVAL;
+
p->post_deps = kmalloc_array(num_deps, sizeof(*p->post_deps),
GFP_KERNEL);
p->num_post_deps = 0;
struct drm_sched_entity *entity)
{
struct amdgpu_ctx_entity *centity = to_amdgpu_ctx_entity(entity);
- unsigned idx = centity->sequence & (amdgpu_sched_jobs - 1);
- struct dma_fence *other = centity->fences[idx];
+ struct dma_fence *other;
+ unsigned idx;
+ long r;
- if (other) {
- signed long r;
- r = dma_fence_wait(other, true);
- if (r < 0) {
- if (r != -ERESTARTSYS)
- DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+ spin_lock(&ctx->ring_lock);
+ idx = centity->sequence & (amdgpu_sched_jobs - 1);
+ other = dma_fence_get(centity->fences[idx]);
+ spin_unlock(&ctx->ring_lock);
- return r;
- }
- }
+ if (!other)
+ return 0;
- return 0;
+ r = dma_fence_wait(other, true);
+ if (r < 0 && r != -ERESTARTSYS)
+ DRM_ERROR("Error (%ld) waiting for fence!\n", r);
+
+ dma_fence_put(other);
+ return r;
}
void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
thread = (*pos & GENMASK_ULL(59, 52)) >> 52;
bank = (*pos & GENMASK_ULL(61, 60)) >> 60;
- data = kmalloc_array(1024, sizeof(*data), GFP_KERNEL);
+ data = kcalloc(1024, sizeof(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
};
int amdgpu_ras_enable = -1;
-uint amdgpu_ras_mask = 0xffffffff;
+uint amdgpu_ras_mask = 0xfffffffb;
/**
* DOC: vramlimit (int)
uint32_t gws_size;
uint32_t oa_size;
uint32_t gds_compute_max_wave_id;
- uint32_t vgt_gs_max_wave_id;
};
struct amdgpu_gds_reg_offset {
struct amdgpu_device *adev = ddev->dev_private;
enum amd_pm_state_type pm;
- if (is_support_sw_smu(adev) && adev->smu.ppt_funcs->get_current_power_state)
- pm = amdgpu_smu_get_current_power_state(adev);
- else if (adev->powerplay.pp_funcs->get_current_power_state)
+ if (is_support_sw_smu(adev)) {
+ if (adev->smu.ppt_funcs->get_current_power_state)
+ pm = amdgpu_smu_get_current_power_state(adev);
+ else
+ pm = adev->pm.dpm.user_state;
+ } else if (adev->powerplay.pp_funcs->get_current_power_state) {
pm = amdgpu_dpm_get_current_power_state(adev);
- else
+ } else {
pm = adev->pm.dpm.user_state;
+ }
return snprintf(buf, PAGE_SIZE, "%s\n",
(pm == POWER_STATE_TYPE_BATTERY) ? "battery" :
goto fail;
}
- if (adev->powerplay.pp_funcs->dispatch_tasks) {
+ if (is_support_sw_smu(adev)) {
+ mutex_lock(&adev->pm.mutex);
+ adev->pm.dpm.user_state = state;
+ mutex_unlock(&adev->pm.mutex);
+ } else if (adev->powerplay.pp_funcs->dispatch_tasks) {
amdgpu_dpm_dispatch_task(adev, AMD_PP_TASK_ENABLE_USER_STATE, &state);
} else {
mutex_lock(&adev->pm.mutex);
return -EINVAL;
if (is_support_sw_smu(adev)) {
- err = smu_get_current_rpm(&adev->smu, &speed);
+ err = smu_get_fan_speed_rpm(&adev->smu, &speed);
if (err)
return err;
} else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
return -EINVAL;
if (is_support_sw_smu(adev)) {
- err = smu_get_current_rpm(&adev->smu, &rpm);
+ err = smu_get_fan_speed_rpm(&adev->smu, &rpm);
if (err)
return err;
} else if (adev->powerplay.pp_funcs->get_fan_speed_rpm) {
if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK, (void *)&value64, &size))
seq_printf(m, "SMC Feature Mask: 0x%016llx\n", value64);
- /* UVD clocks */
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) {
- if (!value) {
- seq_printf(m, "UVD: Disabled\n");
- } else {
- seq_printf(m, "UVD: Enabled\n");
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
- seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
- seq_printf(m, "\t%u MHz (VCLK)\n", value/100);
+ if (adev->asic_type > CHIP_VEGA20) {
+ /* VCN clocks */
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCN_POWER_STATE, (void *)&value, &size)) {
+ if (!value) {
+ seq_printf(m, "VCN: Disabled\n");
+ } else {
+ seq_printf(m, "VCN: Enabled\n");
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
+ seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
+ seq_printf(m, "\t%u MHz (VCLK)\n", value/100);
+ }
}
- }
- seq_printf(m, "\n");
+ seq_printf(m, "\n");
+ } else {
+ /* UVD clocks */
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_POWER, (void *)&value, &size)) {
+ if (!value) {
+ seq_printf(m, "UVD: Disabled\n");
+ } else {
+ seq_printf(m, "UVD: Enabled\n");
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_DCLK, (void *)&value, &size))
+ seq_printf(m, "\t%u MHz (DCLK)\n", value/100);
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_UVD_VCLK, (void *)&value, &size))
+ seq_printf(m, "\t%u MHz (VCLK)\n", value/100);
+ }
+ }
+ seq_printf(m, "\n");
- /* VCE clocks */
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) {
- if (!value) {
- seq_printf(m, "VCE: Disabled\n");
- } else {
- seq_printf(m, "VCE: Enabled\n");
- if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size))
- seq_printf(m, "\t%u MHz (ECCLK)\n", value/100);
+ /* VCE clocks */
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_POWER, (void *)&value, &size)) {
+ if (!value) {
+ seq_printf(m, "VCE: Disabled\n");
+ } else {
+ seq_printf(m, "VCE: Enabled\n");
+ if (!amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_VCE_ECCLK, (void *)&value, &size))
+ seq_printf(m, "\t%u MHz (ECCLK)\n", value/100);
+ }
}
}
static int amdgpu_ras_release_vram(struct amdgpu_device *adev,
struct amdgpu_bo **bo_ptr);
-static void amdgpu_ras_self_test(struct amdgpu_device *adev)
-{
- /* TODO */
-}
-
static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
size_t size, loff_t *pos)
{
if (!obj)
return -EINVAL;
+ if (block_info.block_id != TA_RAS_BLOCK__UMC) {
+ DRM_INFO("%s error injection is not supported yet\n",
+ ras_block_str(info->head.block));
+ return -EINVAL;
+ }
+
ret = psp_ras_trigger_error(&adev->psp, &block_info);
if (ret)
DRM_ERROR("RAS ERROR: inject %s error failed ret %d\n",
amdgpu_ras_check_supported(adev, &con->hw_supported,
&con->supported);
+ if (!con->hw_supported) {
+ amdgpu_ras_set_context(adev, NULL);
+ kfree(con);
+ return 0;
+ }
+
con->features = 0;
INIT_LIST_HEAD(&con->head);
/* Might need get this flag from vbios. */
if (amdgpu_ras_fs_init(adev))
goto fs_out;
- amdgpu_ras_self_test(adev);
-
DRM_INFO("RAS INFO: ras initialized successfully, "
"hardware ability[%x] ras_mask[%x]\n",
con->hw_supported, con->supported);
#define AMDGPU_VCN_FIRMWARE_OFFSET 256
#define AMDGPU_VCN_MAX_ENC_RINGS 3
+#define VCN_DEC_KMD_CMD 0x80000000
#define VCN_DEC_CMD_FENCE 0x00000000
#define VCN_DEC_CMD_TRAP 0x00000001
#define VCN_DEC_CMD_WRITE_REG 0x00000004
}
nv_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
+
+ /* Initialize all compute VMIDs to have no GDS, GWS, or OA
+ acccess. These should be enabled by FW for target VMIDs. */
+ for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0);
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0);
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0);
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0);
+ }
}
static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev)
unsigned vmid = AMDGPU_JOB_GET_VMID(job);
u32 header, control = 0;
- /* Prevent a hw deadlock due to a wave ID mismatch between ME and GDS.
- * This resets the wave ID counters. (needed by transform feedback)
- * TODO: This might only be needed on a VMID switch when we change
- * the GDS OA mapping, not sure.
- */
- amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
- amdgpu_ring_write(ring, mmVGT_GS_MAX_WAVE_ID);
- amdgpu_ring_write(ring, ring->adev->gds.vgt_gs_max_wave_id);
-
if (ib->flags & AMDGPU_IB_FLAG_CE)
header = PACKET3(PACKET3_INDIRECT_BUFFER_CNST, 2);
else
cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
TIME_STAMP_INT_ENABLE, 0);
WREG32(cp_int_cntl_reg, cp_int_cntl);
+ break;
case AMDGPU_IRQ_STATE_ENABLE:
cp_int_cntl = RREG32(cp_int_cntl_reg);
cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0,
5 + /* HDP_INVL */
8 + 8 + /* FENCE x2 */
2, /* SWITCH_BUFFER */
- .emit_ib_size = 7, /* gfx_v10_0_ring_emit_ib_gfx */
+ .emit_ib_size = 4, /* gfx_v10_0_ring_emit_ib_gfx */
.emit_ib = gfx_v10_0_ring_emit_ib_gfx,
.emit_fence = gfx_v10_0_ring_emit_fence,
.emit_pipeline_sync = gfx_v10_0_ring_emit_pipeline_sync,
default:
adev->gds.gds_size = 0x10000;
adev->gds.gds_compute_max_wave_id = 0x4ff;
- adev->gds.vgt_gs_max_wave_id = 0x3ff;
break;
}
}
cik_srbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
+
+ /* Initialize all compute VMIDs to have no GDS, GWS, or OA
+ acccess. These should be enabled by FW for target VMIDs. */
+ for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+ WREG32(amdgpu_gds_reg_offset[i].mem_base, 0);
+ WREG32(amdgpu_gds_reg_offset[i].mem_size, 0);
+ WREG32(amdgpu_gds_reg_offset[i].gws, 0);
+ WREG32(amdgpu_gds_reg_offset[i].oa, 0);
+ }
}
static void gfx_v7_0_config_init(struct amdgpu_device *adev)
return 0;
}
+static int gfx_v8_0_csb_vram_pin(struct amdgpu_device *adev)
+{
+ int r;
+
+ r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
+ if (unlikely(r != 0))
+ return r;
+
+ r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
+ AMDGPU_GEM_DOMAIN_VRAM);
+ if (!r)
+ adev->gfx.rlc.clear_state_gpu_addr =
+ amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
+
+ amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+
+ return r;
+}
+
+static void gfx_v8_0_csb_vram_unpin(struct amdgpu_device *adev)
+{
+ int r;
+
+ if (!adev->gfx.rlc.clear_state_obj)
+ return;
+
+ r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
+ if (likely(r == 0)) {
+ amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
+ amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+ }
+}
+
static void gfx_v8_0_mec_fini(struct amdgpu_device *adev)
{
amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
}
vi_srbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
+
+ /* Initialize all compute VMIDs to have no GDS, GWS, or OA
+ acccess. These should be enabled by FW for target VMIDs. */
+ for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+ WREG32(amdgpu_gds_reg_offset[i].mem_base, 0);
+ WREG32(amdgpu_gds_reg_offset[i].mem_size, 0);
+ WREG32(amdgpu_gds_reg_offset[i].gws, 0);
+ WREG32(amdgpu_gds_reg_offset[i].oa, 0);
+ }
}
static void gfx_v8_0_config_init(struct amdgpu_device *adev)
gfx_v8_0_init_golden_registers(adev);
gfx_v8_0_constants_init(adev);
+ r = gfx_v8_0_csb_vram_pin(adev);
+ if (r)
+ return r;
+
r = adev->gfx.rlc.funcs->resume(adev);
if (r)
return r;
else
pr_err("rlc is busy, skip halt rlc\n");
amdgpu_gfx_rlc_exit_safe_mode(adev);
+
+ gfx_v8_0_csb_vram_unpin(adev);
+
return 0;
}
case CHIP_VEGA20:
break;
case CHIP_RAVEN:
- if (adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
- break;
- if ((adev->gfx.rlc_fw_version != 106 &&
- adev->gfx.rlc_fw_version < 531) ||
- (adev->gfx.rlc_fw_version == 53815) ||
- (adev->gfx.rlc_feature_version < 1) ||
- !adev->gfx.rlc.is_rlc_v2_1)
+ if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
+ &&((adev->gfx.rlc_fw_version != 106 &&
+ adev->gfx.rlc_fw_version < 531) ||
+ (adev->gfx.rlc_fw_version == 53815) ||
+ (adev->gfx.rlc_feature_version < 1) ||
+ !adev->gfx.rlc.is_rlc_v2_1))
adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+
+ if (adev->pm.pp_feature & PP_GFXOFF_MASK)
+ adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+ AMD_PG_SUPPORT_CP |
+ AMD_PG_SUPPORT_RLC_SMU_HS;
break;
default:
break;
}
soc15_grbm_select(adev, 0, 0, 0, 0);
mutex_unlock(&adev->srbm_mutex);
+
+ /* Initialize all compute VMIDs to have no GDS, GWS, or OA
+ acccess. These should be enabled by FW for target VMIDs. */
+ for (i = FIRST_COMPUTE_VMID; i < LAST_COMPUTE_VMID; i++) {
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_BASE, 2 * i, 0);
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_VMID0_SIZE, 2 * i, 0);
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_GWS_VMID0, i, 0);
+ WREG32_SOC15_OFFSET(GC, 0, mmGDS_OA_VMID0, i, 0);
+ }
}
static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01);
value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1);
value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid);
- WREG32(mmSQ_CMD, value);
+ WREG32_SOC15(GC, 0, mmSQ_CMD, value);
}
static void gfx_v9_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
AMD_CG_SUPPORT_BIF_LS;
adev->pg_flags = AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_VCN_DPG |
- AMD_PG_SUPPORT_MMHUB |
AMD_PG_SUPPORT_ATHUB;
adev->external_rev_id = adev->rev_id + 0x1;
break;
adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
}
-
- if (adev->pm.pp_feature & PP_GFXOFF_MASK)
- adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
- AMD_PG_SUPPORT_CP |
- AMD_PG_SUPPORT_RLC_SMU_HS;
break;
default:
/* FIXME: not supported yet */
WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
upper_32_bits(adev->vcn.gpu_addr));
offset = size;
- /* No signed header for now from firmware
WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
- */
- WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, 0);
}
WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size);
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
amdgpu_ring_write(ring, 0);
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
- amdgpu_ring_write(ring, VCN_DEC_CMD_PACKET_START << 1);
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1));
}
/**
static void vcn_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring)
{
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
- amdgpu_ring_write(ring, VCN_DEC_CMD_PACKET_END << 1);
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_END << 1));
}
/**
amdgpu_ring_write(ring, upper_32_bits(addr) & 0xff);
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
- amdgpu_ring_write(ring, VCN_DEC_CMD_FENCE << 1);
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_FENCE << 1));
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET, 0));
amdgpu_ring_write(ring, 0);
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
- amdgpu_ring_write(ring, VCN_DEC_CMD_TRAP << 1);
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_TRAP << 1));
}
/**
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
- amdgpu_ring_write(ring, VCN_DEC_CMD_REG_READ_COND_WAIT << 1);
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_REG_READ_COND_WAIT << 1));
}
static void vcn_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
- amdgpu_ring_write(ring, VCN_DEC_CMD_WRITE_REG << 1);
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_WRITE_REG << 1));
}
/**
return 0;
}
+static int vcn_v2_0_dec_ring_test_ring(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+ uint32_t tmp = 0;
+ unsigned i;
+ int r;
+
+ WREG32(adev->vcn.external.scratch9, 0xCAFEDEAD);
+ r = amdgpu_ring_alloc(ring, 4);
+ if (r)
+ return r;
+ amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET, 0));
+ amdgpu_ring_write(ring, VCN_DEC_KMD_CMD | (VCN_DEC_CMD_PACKET_START << 1));
+ amdgpu_ring_write(ring, PACKET0(adev->vcn.internal.scratch9, 0));
+ amdgpu_ring_write(ring, 0xDEADBEEF);
+ amdgpu_ring_commit(ring);
+ for (i = 0; i < adev->usec_timeout; i++) {
+ tmp = RREG32(adev->vcn.external.scratch9);
+ if (tmp == 0xDEADBEEF)
+ break;
+ DRM_UDELAY(1);
+ }
+
+ if (i >= adev->usec_timeout)
+ r = -ETIMEDOUT;
+
+ return r;
+}
+
+
static int vcn_v2_0_set_powergating_state(void *handle,
enum amd_powergating_state state)
{
.emit_ib = vcn_v2_0_dec_ring_emit_ib,
.emit_fence = vcn_v2_0_dec_ring_emit_fence,
.emit_vm_flush = vcn_v2_0_dec_ring_emit_vm_flush,
- .test_ring = amdgpu_vcn_dec_ring_test_ring,
+ .test_ring = vcn_v2_0_dec_ring_test_ring,
.test_ib = amdgpu_vcn_dec_ring_test_ib,
.insert_nop = vcn_v2_0_dec_ring_insert_nop,
.insert_start = vcn_v2_0_dec_ring_insert_start,
return err;
}
-static int kfd_ioctl_alloc_queue_gws(struct file *filep,
- struct kfd_process *p, void *data)
-{
- int retval;
- struct kfd_ioctl_alloc_queue_gws_args *args = data;
- struct kfd_dev *dev;
-
- if (!hws_gws_support)
- return -ENODEV;
-
- dev = kfd_device_by_id(args->gpu_id);
- if (!dev) {
- pr_debug("Could not find gpu id 0x%x\n", args->gpu_id);
- return -ENODEV;
- }
- if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS)
- return -ENODEV;
-
- mutex_lock(&p->mutex);
- retval = pqm_set_gws(&p->pqm, args->queue_id, args->num_gws ? dev->gws : NULL);
- mutex_unlock(&p->mutex);
-
- args->first_gws = 0;
- return retval;
-}
-
static int kfd_ioctl_get_dmabuf_info(struct file *filep,
struct kfd_process *p, void *data)
{
AMDKFD_IOCTL_DEF(AMDKFD_IOC_IMPORT_DMABUF,
kfd_ioctl_import_dmabuf, 0),
- AMDKFD_IOCTL_DEF(AMDKFD_IOC_ALLOC_QUEUE_GWS,
- kfd_ioctl_alloc_queue_gws, 0),
};
#define AMDKFD_CORE_IOCTL_COUNT ARRAY_SIZE(amdkfd_ioctls)
case CHIP_RAVEN:
pcache_info = raven_cache_info;
num_of_cache_types = ARRAY_SIZE(raven_cache_info);
+ break;
case CHIP_NAVI10:
pcache_info = navi10_cache_info;
num_of_cache_types = ARRAY_SIZE(navi10_cache_info);
switch (type) {
case KFD_MQD_TYPE_CP:
- pr_debug("%s@%i\n", __func__, __LINE__);
case KFD_MQD_TYPE_COMPUTE:
pr_debug("%s@%i\n", __func__, __LINE__);
mqd->allocate_mqd = allocate_mqd;
convert_color_depth_from_display_info(const struct drm_connector *connector,
const struct drm_connector_state *state)
{
- uint32_t bpc = connector->display_info.bpc;
+ uint8_t bpc = (uint8_t)connector->display_info.bpc;
+
+ /* Assume 8 bpc by default if no bpc is specified. */
+ bpc = bpc ? bpc : 8;
if (!state)
state = connector->state;
if (state) {
- bpc = state->max_bpc;
+ /*
+ * Cap display bpc based on the user requested value.
+ *
+ * The value for state->max_bpc may not correctly updated
+ * depending on when the connector gets added to the state
+ * or if this was called outside of atomic check, so it
+ * can't be used directly.
+ */
+ bpc = min(bpc, state->max_requested_bpc);
+
/* Round down to the nearest even number. */
bpc = bpc - (bpc & 1);
}
struct dc_context *ctx,
struct clk_mgr_internal *clk_mgr)
{
+ dce_clk_mgr_construct(ctx, clk_mgr);
+
memcpy(clk_mgr->max_clks_by_state,
dce110_max_clks_by_state,
sizeof(dce110_max_clks_by_state));
- dce_clk_mgr_construct(ctx, clk_mgr);
-
clk_mgr->regs = &disp_clk_regs;
clk_mgr->clk_mgr_shift = &disp_clk_shift;
clk_mgr->clk_mgr_mask = &disp_clk_mask;
struct dc_context *ctx,
struct clk_mgr_internal *clk_mgr)
{
+ dce_clk_mgr_construct(ctx, clk_mgr);
+
memcpy(clk_mgr->max_clks_by_state,
dce112_max_clks_by_state,
sizeof(dce112_max_clks_by_state));
- dce_clk_mgr_construct(ctx, clk_mgr);
-
clk_mgr->regs = &disp_clk_regs;
clk_mgr->clk_mgr_shift = &disp_clk_shift;
clk_mgr->clk_mgr_mask = &disp_clk_mask;
void dce120_clk_mgr_construct(struct dc_context *ctx, struct clk_mgr_internal *clk_mgr)
{
+ dce_clk_mgr_construct(ctx, clk_mgr);
+
memcpy(clk_mgr->max_clks_by_state,
dce120_max_clks_by_state,
sizeof(dce120_max_clks_by_state));
- dce_clk_mgr_construct(ctx, clk_mgr);
-
clk_mgr->base.dprefclk_khz = 600000;
clk_mgr->base.funcs = &dce120_funcs;
}
void dcn2_init_clocks(struct clk_mgr *clk_mgr)
{
memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+ // Assumption is that boot state always supports pstate
+ clk_mgr->clks.p_state_change_support = true;
}
void dcn2_enable_pme_wa(struct clk_mgr *clk_mgr_base)
struct dccg *dccg)
{
clk_mgr->base.ctx = ctx;
+ clk_mgr->pp_smu = pp_smu;
clk_mgr->base.funcs = &dcn2_funcs;
clk_mgr->regs = &clk_mgr_regs;
clk_mgr->clk_mgr_shift = &clk_mgr_shift;
*/
#include <linux/slab.h>
+#include <linux/mm.h>
#include "dm_services.h"
static void destruct(struct dc *dc)
{
- dc_release_state(dc->current_state);
- dc->current_state = NULL;
+ if (dc->current_state) {
+ dc_release_state(dc->current_state);
+ dc->current_state = NULL;
+ }
destroy_links(dc);
struct dc_state *dc_create_state(struct dc *dc)
{
- struct dc_state *context = kzalloc(sizeof(struct dc_state),
- GFP_KERNEL);
+ struct dc_state *context = kvzalloc(sizeof(struct dc_state),
+ GFP_KERNEL);
if (!context)
return NULL;
struct dc_state *dc_copy_state(struct dc_state *src_ctx)
{
int i, j;
- struct dc_state *new_ctx = kmemdup(src_ctx,
- sizeof(struct dc_state), GFP_KERNEL);
+ struct dc_state *new_ctx = kvmalloc(sizeof(struct dc_state), GFP_KERNEL);
if (!new_ctx)
return NULL;
+ memcpy(new_ctx, src_ctx, sizeof(struct dc_state));
for (i = 0; i < MAX_PIPES; i++) {
struct pipe_ctx *cur_pipe = &new_ctx->res_ctx.pipe_ctx[i];
{
struct dc_state *context = container_of(kref, struct dc_state, refcount);
dc_resource_state_destruct(context);
- kfree(context);
+ kvfree(context);
}
void dc_release_state(struct dc_state *context)
uint32_t read_dpcd_retry_cnt = 10;
enum dc_status status = DC_ERROR_UNEXPECTED;
int i;
+ union max_down_spread max_down_spread = { {0} };
// Read DPCD 00101h to find out the number of lanes currently set
for (i = 0; i < read_dpcd_retry_cnt; i++) {
msleep(8);
}
- ASSERT(status == DC_OK);
-
// Read DPCD 00100h to find if standard link rates are set
core_link_read_dpcd(link, DP_LINK_BW_SET,
&link_bw_set, sizeof(link_bw_set));
link->cur_link_settings.link_rate = link_bw_set;
link->cur_link_settings.use_link_rate_set = false;
}
+ // Read DPCD 00003h to find the max down spread.
+ core_link_read_dpcd(link, DP_MAX_DOWNSPREAD,
+ &max_down_spread.raw, sizeof(max_down_spread));
+ link->cur_link_settings.link_spread =
+ max_down_spread.bits.MAX_DOWN_SPREAD ?
+ LINK_SPREAD_05_DOWNSPREAD_30KHZ : LINK_SPREAD_DISABLED;
}
static bool detect_dp(
return false;
}
- if (link->connector_signal == SIGNAL_TYPE_EDP) {
- /* On detect, we want to make sure current link settings are
- * up to date, especially if link was powered on by GOP.
- */
- read_edp_current_link_settings_on_detect(link);
- }
-
prev_sink = link->local_sink;
if (prev_sink != NULL) {
dc_sink_retain(prev_sink);
}
case SIGNAL_TYPE_EDP: {
+ read_edp_current_link_settings_on_detect(link);
detect_edp_sink_caps(link);
sink_caps.transaction_type =
DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
if (core_dc->current_state->res_ctx.pipe_ctx[i].stream) {
if (core_dc->current_state->res_ctx.
pipe_ctx[i].stream->link
- == link)
+ == link) {
/* DMCU -1 for all controller id values,
* therefore +1 here
*/
core_dc->current_state->
res_ctx.pipe_ctx[i].stream_res.tg->inst +
1;
+
+ /* Disable brightness ramping when the display is blanked
+ * as it can hang the DMCU
+ */
+ if (core_dc->current_state->res_ctx.pipe_ctx[i].plane_state == NULL)
+ frame_ramp = 0;
+ }
}
}
abm->funcs->set_backlight_level_pwm(
/* Retrain with preferred link settings only relevant for
* DP signal type
+ * Check for non-DP signal or if passive dongle present
*/
- if (!dc_is_dp_signal(link->connector_signal))
+ if (!dc_is_dp_signal(link->connector_signal) ||
+ link->dongle_max_pix_clk > 0)
return;
for (i = 0; i < MAX_PIPES; i++) {
link->dpcd_caps.dongle_type = DISPLAY_DONGLE_NONE;
ddc_service_set_dongle_type(link->ddc,
link->dpcd_caps.dongle_type);
+ link->dpcd_caps.is_branch_dev = false;
return;
}
/* DPCD 0x5 bit 0 = 1, it indicate it's branch device */
- link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT;
+ if (ds_port.fields.PORT_TYPE == DOWNSTREAM_DP) {
+ link->dpcd_caps.is_branch_dev = false;
+ }
+
+ else {
+ link->dpcd_caps.is_branch_dev = ds_port.fields.PORT_PRESENT;
+ }
switch (ds_port.fields.PORT_TYPE) {
case DOWNSTREAM_VGA:
link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_VGA_CONVERTER;
break;
- case DOWNSTREAM_DVI_HDMI:
- /* At this point we don't know is it DVI or HDMI,
+ case DOWNSTREAM_DVI_HDMI_DP_PLUS_PLUS:
+ /* At this point we don't know is it DVI or HDMI or DP++,
* assume DVI.*/
link->dpcd_caps.dongle_type = DISPLAY_DONGLE_DP_DVI_CONVERTER;
break;
det_caps, sizeof(det_caps));
switch (port_caps->bits.DWN_STRM_PORTX_TYPE) {
+ /*Handle DP case as DONGLE_NONE*/
+ case DOWN_STREAM_DETAILED_DP:
+ link->dpcd_caps.dongle_type = DISPLAY_DONGLE_NONE;
+ break;
case DOWN_STREAM_DETAILED_VGA:
link->dpcd_caps.dongle_type =
DISPLAY_DONGLE_DP_VGA_CONVERTER;
DISPLAY_DONGLE_DP_DVI_CONVERTER;
break;
case DOWN_STREAM_DETAILED_HDMI:
+ case DOWN_STREAM_DETAILED_DP_PLUS_PLUS:
+ /*Handle DP++ active converter case, process DP++ case as HDMI case according DP1.4 spec*/
link->dpcd_caps.dongle_type =
DISPLAY_DONGLE_DP_HDMI_CONVERTER;
link->dpcd_caps.dongle_caps.is_dp_hdmi_s3d_converter =
hdmi_caps.bits.FRAME_SEQ_TO_FRAME_PACK;
- link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_pass_through =
- hdmi_caps.bits.YCrCr422_PASS_THROUGH;
- link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_pass_through =
- hdmi_caps.bits.YCrCr420_PASS_THROUGH;
- link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_converter =
- hdmi_caps.bits.YCrCr422_CONVERSION;
- link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_converter =
- hdmi_caps.bits.YCrCr420_CONVERSION;
+ /*YCBCR capability only for HDMI case*/
+ if (port_caps->bits.DWN_STRM_PORTX_TYPE
+ == DOWN_STREAM_DETAILED_HDMI) {
+ link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_pass_through =
+ hdmi_caps.bits.YCrCr422_PASS_THROUGH;
+ link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_pass_through =
+ hdmi_caps.bits.YCrCr420_PASS_THROUGH;
+ link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr422_converter =
+ hdmi_caps.bits.YCrCr422_CONVERSION;
+ link->dpcd_caps.dongle_caps.is_dp_hdmi_ycbcr420_converter =
+ hdmi_caps.bits.YCrCr420_CONVERSION;
+ }
link->dpcd_caps.dongle_caps.dp_hdmi_max_bpc =
translate_dpcd_max_bpc(
* PORT_CONNECTIVITY == 1 (as instructed by HW team).
*/
update_num_audio(&straps, &num_audio, &pool->audio_support);
- for (i = 0; i < pool->pipe_count && i < num_audio; i++) {
+ for (i = 0; i < caps->num_audio; i++) {
struct audio *aud = create_funcs->create_audio(ctx, i);
if (aud == NULL) {
return pool->audios[i];
}
}
+
+ /* use engine id to find free audio */
+ if ((id < pool->audio_count) && (res_ctx->is_audio_acquired[id] == false)) {
+ return pool->audios[id];
+ }
+
/*not found the matching one, first come first serve*/
for (i = 0; i < pool->audio_count; i++) {
if (res_ctx->is_audio_acquired[i] == false) {
pix_clk /= 2;
if (timing->pixel_encoding != PIXEL_ENCODING_YCBCR422) {
switch (timing->display_color_depth) {
+ case COLOR_DEPTH_666:
case COLOR_DEPTH_888:
normalized_pix_clk = pix_clk;
break;
/* TODO: Add check if ASIC support and EDID audio */
if (!stream->converter_disable_audio &&
dc_is_audio_capable_signal(pipe_ctx->stream->signal) &&
- stream->audio_info.mode_count) {
+ stream->audio_info.mode_count && stream->audio_info.flags.all) {
pipe_ctx->stream_res.audio = find_first_free_audio(
&context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id);
pipe_ctx->stream->dmdata_address = attr->address;
- if (pipe_ctx->stream_res.stream_enc->funcs->set_dynamic_metadata != NULL) {
+ if (pipe_ctx->stream_res.stream_enc &&
+ pipe_ctx->stream_res.stream_enc->funcs->set_dynamic_metadata != NULL) {
if (pipe_ctx->stream->dmdata_address.quad_part != 0) {
/* if using dynamic meta, don't set up generic infopackets */
pipe_ctx->stream_res.encoder_info_frame.hdrsmd.valid = false;
s2 |= (backlight_8_bit << ATOM_S2_CURRENT_BL_LEVEL_SHIFT);
REG_WRITE(BIOS_SCRATCH_2, s2);
+
+ /* waitDMCUReadyForCmd */
+ REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT,
+ 0, 1, 80000);
}
static void dce_abm_init(struct abm *abm)
void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
{
/* notify audio driver for audio modes of monitor */
- struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+ struct dc *core_dc;
struct pp_smu_funcs *pp_smu = NULL;
- struct clk_mgr *clk_mgr = core_dc->clk_mgr;
+ struct clk_mgr *clk_mgr;
unsigned int i, num_audio = 1;
+ if (!pipe_ctx->stream)
+ return;
+
+ core_dc = pipe_ctx->stream->ctx->dc;
+ clk_mgr = core_dc->clk_mgr;
+
if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == true)
return;
void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option)
{
- struct dc *dc = pipe_ctx->stream->ctx->dc;
+ struct dc *dc;
struct pp_smu_funcs *pp_smu = NULL;
- struct clk_mgr *clk_mgr = dc->clk_mgr;
+ struct clk_mgr *clk_mgr;
+
+ if (!pipe_ctx || !pipe_ctx->stream)
+ return;
+
+ dc = pipe_ctx->stream->ctx->dc;
+ clk_mgr = dc->clk_mgr;
if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == false)
return;
pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
pipe_ctx->stream_res.stream_enc, true);
if (pipe_ctx->stream_res.audio) {
+ pipe_ctx->stream_res.audio->enabled = false;
+
if (dc->res_pool->pp_smu)
pp_smu = dc->res_pool->pp_smu;
/* dal_audio_disable_azalia_audio_jack_presence(stream->audio,
* stream->stream_engine_id);
*/
- if (pipe_ctx->stream_res.audio)
- pipe_ctx->stream_res.audio->enabled = false;
}
}
* everything down.
*/
if (dcb->funcs->is_accelerated_mode(dcb) || dc->config.power_down_display_on_boot) {
- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- struct hubp *hubp = dc->res_pool->hubps[i];
- struct dpp *dpp = dc->res_pool->dpps[i];
-
- hubp->funcs->hubp_init(hubp);
- dc->res_pool->opps[i]->mpc_tree_params.opp_id = dc->res_pool->opps[i]->inst;
- plane_atomic_power_down(dc, dpp, hubp);
- }
-
- apply_DEGVIDCN10_253_wa(dc);
+ dc->hwss.init_pipes(dc, dc->current_state);
}
for (i = 0; i < dc->res_pool->audio_count; i++) {
return result;
}
-
-
-
-
static bool
dcn10_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
const struct dc_stream_state *stream)
if (removed_pipe[i])
dcn10_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
+ for (i = 0; i < dc->res_pool->pipe_count; i++)
+ if (removed_pipe[i]) {
+ dc->hwss.optimize_bandwidth(dc, context);
+ break;
+ }
+
if (dc->hwseq->wa.DEGVIDCN10_254)
hubbub1_wm_change_req_wa(dc->res_pool->hubbub);
}
.num_audio = 3,
.num_stream_encoder = 3,
.num_pll = 3,
- .num_ddc = 3,
+ .num_ddc = 4,
};
static const struct dc_plane_cap plane_cap = {
switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) {
case 6:
REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1);
+ /* Fall through */
case 5:
REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1);
+ /* Fall through */
case 4:
REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1);
+ /* Fall through */
case 3:
REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1);
+ /* Fall through */
case 2:
REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1);
+ /* Fall through */
case 1:
REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1);
break;
break;
default:
ASSERT(false);
+ block_size = page_table_block_size;
break;
}
struct dcn_vmid_page_table_config phys_config;
REG_SET(DCN_VM_FB_LOCATION_BASE, 0,
- FB_BASE, pa_config->system_aperture.fb_base);
+ FB_BASE, pa_config->system_aperture.fb_base >> 24);
REG_SET(DCN_VM_FB_LOCATION_TOP, 0,
- FB_TOP, pa_config->system_aperture.fb_top);
+ FB_TOP, pa_config->system_aperture.fb_top >> 24);
REG_SET(DCN_VM_FB_OFFSET, 0,
- FB_OFFSET, pa_config->system_aperture.fb_offset);
+ FB_OFFSET, pa_config->system_aperture.fb_offset >> 24);
REG_SET(DCN_VM_AGP_BOT, 0,
- AGP_BOT, pa_config->system_aperture.agp_bot);
+ AGP_BOT, pa_config->system_aperture.agp_bot >> 24);
REG_SET(DCN_VM_AGP_TOP, 0,
- AGP_TOP, pa_config->system_aperture.agp_top);
+ AGP_TOP, pa_config->system_aperture.agp_top >> 24);
REG_SET(DCN_VM_AGP_BASE, 0,
- AGP_BASE, pa_config->system_aperture.agp_base);
+ AGP_BASE, pa_config->system_aperture.agp_base >> 24);
if (pa_config->gart_config.page_table_start_addr != pa_config->gart_config.page_table_end_addr) {
- phys_config.depth = 1;
- phys_config.block_size = 4096;
phys_config.page_table_start_addr = pa_config->gart_config.page_table_start_addr >> 12;
phys_config.page_table_end_addr = pa_config->gart_config.page_table_end_addr >> 12;
phys_config.page_table_base_addr = pa_config->gart_config.page_table_base_addr;
-
+ phys_config.depth = 0;
+ phys_config.block_size = 0;
// Init VMID 0 based on PA config
dcn20_vmid_setup(&hubbub1->vmid[0], &phys_config);
}
apt.sys_default.quad_part = 0;
- apt.sys_high.quad_part = dc->vm_pa_config.system_aperture.start_addr;
- apt.sys_low.quad_part = dc->vm_pa_config.system_aperture.end_addr;
+ apt.sys_low.quad_part = dc->vm_pa_config.system_aperture.start_addr;
+ apt.sys_high.quad_part = dc->vm_pa_config.system_aperture.end_addr;
// Program system aperture settings
pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt);
CRTC_STATE_VACTIVE);
pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg,
CRTC_STATE_VBLANK);
+ pipe->stream_res.tg->funcs->wait_for_state(pipe->stream_res.tg,
+ CRTC_STATE_VACTIVE);
pipe->stream_res.tg->funcs->lock_doublebuffer_disable(
pipe->stream_res.tg);
}
if (pipe->plane_state != NULL)
flip_immediate = pipe->plane_state->flip_immediate;
+ if (flip_immediate && lock) {
+ while (pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp)) {
+ udelay(1);
+ }
+
+ if (pipe->bottom_pipe != NULL)
+ while (pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp)) {
+ udelay(1);
+ }
+ }
+
/* In flip immediate and pipe splitting case, we need to use GSL
* for synchronization. Only do setup on locking and on flip type change.
*/
else if (pipe_ctx->stream_res.audio) {
dc->hwss.disable_audio_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE);
}
-
}
+#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+ else if (pipe_ctx->stream_res.dsc)
+ dp_set_dsc_enable(pipe_ctx, false);
+#endif
/* by upper caller loop, parent pipe: pipe0, will be reset last.
* back end share by all pipes and will be disable only when disable
optc1->min_h_blank = 32;
optc1->min_v_blank = 3;
optc1->min_v_blank_interlace = 5;
- optc1->min_h_sync_width = 8;
+ optc1->min_h_sync_width = 4;// Minimum HSYNC = 8 pixels asked By HW in the first place for no actual reason. Oculus Rift S will not light up with 8 as it's hsyncWidth is 6. Changing it to 4 to fix that issue.
optc1->min_v_sync_width = 1;
optc1->comb_opp_id = 0xf;
}
if (dc->bb_overrides.min_dcfclk_mhz > 0)
min_dcfclk = dc->bb_overrides.min_dcfclk_mhz;
+ else
+ // Accounting for SOC/DCF relationship, we can go as high as
+ // 506Mhz in Vmin. We need to code 507 since SMU will round down to 506.
+ min_dcfclk = 507;
for (i = 0; i < num_states; i++) {
int min_fclk_required_by_uclk;
*
*/
+#include <linux/delay.h>
+
#include "dcn20_vmid.h"
#include "reg_helper.h"
#define FN(reg_name, field_name) \
vmid->shifts->field_name, vmid->masks->field_name
+static void dcn20_wait_for_vmid_ready(struct dcn20_vmid *vmid)
+{
+ /* According the hardware spec, we need to poll for the lowest
+ * bit of PAGE_TABLE_BASE_ADDR_LO32 = 1 any time a GPUVM
+ * context is updated. We can't use REG_WAIT here since we
+ * don't have a seperate field to wait on.
+ *
+ * TODO: Confirm timeout / poll interval with hardware team
+ */
+
+ int max_times = 10000;
+ int delay_us = 5;
+ int i;
+
+ for (i = 0; i < max_times; ++i) {
+ uint32_t entry_lo32;
+
+ REG_GET(PAGE_TABLE_BASE_ADDR_LO32,
+ VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_LO32,
+ &entry_lo32);
+
+ if (entry_lo32 & 0x1)
+ return;
+
+ udelay(delay_us);
+ }
+
+ /* VM setup timed out */
+ DC_LOG_WARNING("Timeout while waiting for GPUVM context update\n");
+ ASSERT(0);
+}
+
void dcn20_vmid_setup(struct dcn20_vmid *vmid, const struct dcn_vmid_page_table_config *config)
{
REG_SET(PAGE_TABLE_START_ADDR_HI32, 0,
REG_SET(PAGE_TABLE_BASE_ADDR_HI32, 0,
VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_HI32, (config->page_table_base_addr >> 32) & 0xFFFFFFFF);
+ /* Note: per hardware spec PAGE_TABLE_BASE_ADDR_LO32 must be programmed last in sequence */
REG_SET(PAGE_TABLE_BASE_ADDR_LO32, 0,
VM_CONTEXT0_PAGE_DIRECTORY_ENTRY_LO32, config->page_table_base_addr & 0xFFFFFFFF);
+
+ dcn20_wait_for_vmid_ready(vmid);
}
vdsc_cfg->rc_bits = (hrd_delay * vdsc_cfg->bits_per_pixel) / 16;
vdsc_cfg->initial_dec_delay = hrd_delay - vdsc_cfg->initial_xmit_delay;
+ /* As per DSC spec v1.2a recommendation: */
+ if (vdsc_cfg->native_420)
+ vdsc_cfg->second_line_offset_adj = 512;
+ else
+ vdsc_cfg->second_line_offset_adj = 0;
+
return 0;
}
EXPORT_SYMBOL(drm_dsc_compute_rc_parameters);
struct clock_source *clock_sources[MAX_CLOCK_SOURCES];
unsigned int clk_src_count;
- struct audio *audios[MAX_PIPES];
+ struct audio *audios[MAX_AUDIOS];
unsigned int audio_count;
struct audio_support audio_support;
};
enum dcn_hubbub_page_table_block_size {
- DCN_PAGE_TABLE_BLOCK_SIZE_4KB,
- DCN_PAGE_TABLE_BLOCK_SIZE_64KB
+ DCN_PAGE_TABLE_BLOCK_SIZE_4KB = 0,
+ DCN_PAGE_TABLE_BLOCK_SIZE_64KB = 4,
};
struct dcn_hubbub_phys_addr_config {
* Data types shared between different Virtual HW blocks
******************************************************************************/
+#define MAX_AUDIOS 7
#define MAX_PIPES 6
#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
#define MAX_DWB_PIPES 1
enum dpcd_downstream_port_type {
DOWNSTREAM_DP = 0,
DOWNSTREAM_VGA,
- DOWNSTREAM_DVI_HDMI,
+ DOWNSTREAM_DVI_HDMI_DP_PLUS_PLUS,/* DVI, HDMI, DP++ */
DOWNSTREAM_NONDDC /* has no EDID (TV,CV) */
};
AMDGPU_PP_SENSOR_ENABLED_SMC_FEATURES_MASK,
AMDGPU_PP_SENSOR_MIN_FAN_RPM,
AMDGPU_PP_SENSOR_MAX_FAN_RPM,
+ AMDGPU_PP_SENSOR_VCN_POWER_STATE,
};
enum amd_pp_task {
{
int ret = 0, clk_id = 0;
uint32_t param = 0;
+ uint32_t clock_limit;
if (!min && !max)
return -EINVAL;
- if (!smu_clk_dpm_is_enabled(smu, clk_type))
+ if (!smu_clk_dpm_is_enabled(smu, clk_type)) {
+ switch (clk_type) {
+ case SMU_MCLK:
+ case SMU_UCLK:
+ clock_limit = smu->smu_table.boot_values.uclk;
+ break;
+ case SMU_GFXCLK:
+ case SMU_SCLK:
+ clock_limit = smu->smu_table.boot_values.gfxclk;
+ break;
+ case SMU_SOCCLK:
+ clock_limit = smu->smu_table.boot_values.socclk;
+ break;
+ default:
+ clock_limit = 0;
+ break;
+ }
+
+ /* clock in Mhz unit */
+ if (min)
+ *min = clock_limit / 100;
+ if (max)
+ *max = clock_limit / 100;
+
return 0;
+ }
mutex_lock(&smu->mutex);
clk_id = smu_clk_get_index(smu, clk_type);
/* not support power state */
memset(state_info, 0, sizeof(struct pp_states_info));
- state_info->nums = 0;
+ state_info->nums = 1;
+ state_info->states[0] = POWER_STATE_TYPE_DEFAULT;
return 0;
}
int smu_common_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor,
void *data, uint32_t *size)
{
+ struct smu_power_context *smu_power = &smu->smu_power;
+ struct smu_power_gate *power_gate = &smu_power->power_gate;
int ret = 0;
switch (sensor) {
*(uint32_t *)data = smu_feature_is_enabled(smu, SMU_FEATURE_DPM_VCE_BIT) ? 1 : 0;
*size = 4;
break;
+ case AMDGPU_PP_SENSOR_VCN_POWER_STATE:
+ *(uint32_t *)data = power_gate->vcn_gated ? 0 : 1;
+ *size = 4;
+ break;
default:
ret = -EINVAL;
break;
return ret;
}
+ ret = smu_register_irq_handler(smu);
+ if (ret) {
+ pr_err("Failed to register smc irq handler!\n");
+ return ret;
+ }
+
return 0;
}
struct smu_context *smu = &adev->smu;
int ret;
+ kfree(smu->irq_source);
+ smu->irq_source = NULL;
+
ret = smu_smc_table_sw_fini(smu);
if (ret) {
pr_err("Failed to sw fini smc table!\n");
if (ret)
goto failed;
- ret = smu_register_irq_handler(smu);
- if (ret)
- goto failed;
-
if (!smu->pm_enabled)
adev->pm.dpm_enabled = false;
else
kfree(table_context->overdrive_table);
table_context->overdrive_table = NULL;
- kfree(smu->irq_source);
- smu->irq_source = NULL;
-
ret = smu_fini_fb_allocations(smu);
if (ret)
return ret;
return 0;
}
+static int smu_default_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+{
+ int ret = 0;
+ uint32_t sclk_mask, mclk_mask, soc_mask;
+
+ switch (level) {
+ case AMD_DPM_FORCED_LEVEL_HIGH:
+ ret = smu_force_dpm_limit_value(smu, true);
+ break;
+ case AMD_DPM_FORCED_LEVEL_LOW:
+ ret = smu_force_dpm_limit_value(smu, false);
+ break;
+ case AMD_DPM_FORCED_LEVEL_AUTO:
+ case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
+ ret = smu_unforce_dpm_levels(smu);
+ break;
+ case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
+ case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
+ case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+ ret = smu_get_profiling_clk_mask(smu, level,
+ &sclk_mask,
+ &mclk_mask,
+ &soc_mask);
+ if (ret)
+ return ret;
+ smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask);
+ smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask);
+ smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask);
+ break;
+ case AMD_DPM_FORCED_LEVEL_MANUAL:
+ case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
+ default:
+ break;
+ }
+ return ret;
+}
+
int smu_adjust_power_state_dynamic(struct smu_context *smu,
enum amd_dpm_forced_level level,
bool skip_display_settings)
{
int ret = 0;
int index = 0;
- uint32_t sclk_mask, mclk_mask, soc_mask;
long workload;
struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
}
if (smu_dpm_ctx->dpm_level != level) {
- switch (level) {
- case AMD_DPM_FORCED_LEVEL_HIGH:
- ret = smu_force_dpm_limit_value(smu, true);
- break;
- case AMD_DPM_FORCED_LEVEL_LOW:
- ret = smu_force_dpm_limit_value(smu, false);
- break;
-
- case AMD_DPM_FORCED_LEVEL_AUTO:
- case AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD:
- ret = smu_unforce_dpm_levels(smu);
- break;
-
- case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
- case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
- case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
- ret = smu_get_profiling_clk_mask(smu, level,
- &sclk_mask,
- &mclk_mask,
- &soc_mask);
- if (ret)
- return ret;
- smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask);
- smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask);
- smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask);
- break;
-
- case AMD_DPM_FORCED_LEVEL_MANUAL:
- case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
- default:
- break;
+ ret = smu_asic_set_performance_level(smu, level);
+ if (ret) {
+ ret = smu_default_set_performance_level(smu, level);
}
-
if (!ret)
smu_dpm_ctx->dpm_level = level;
}
static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
void *value, int *size)
{
+ struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
uint32_t sclk, mclk;
int ret = 0;
case AMDGPU_PP_SENSOR_GPU_TEMP:
*((uint32_t *)value) = smu10_thermal_get_temperature(hwmgr);
break;
+ case AMDGPU_PP_SENSOR_VCN_POWER_STATE:
+ *(uint32_t *)value = smu10_data->vcn_power_gated ? 0 : 1;
+ *size = 4;
+ break;
default:
ret = -EINVAL;
break;
static void smu10_powergate_vcn(struct pp_hwmgr *hwmgr, bool bgate)
{
+ struct smu10_hwmgr *smu10_data = (struct smu10_hwmgr *)(hwmgr->backend);
+
if (bgate) {
amdgpu_device_ip_set_powergating_state(hwmgr->adev,
AMD_IP_BLOCK_TYPE_VCN,
AMD_PG_STATE_GATE);
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_PowerDownVcn, 0);
+ smu10_data->vcn_power_gated = true;
} else {
smum_send_msg_to_smc_with_parameter(hwmgr,
PPSMC_MSG_PowerUpVcn, 0);
amdgpu_device_ip_set_powergating_state(hwmgr->adev,
AMD_IP_BLOCK_TYPE_VCN,
AMD_PG_STATE_UNGATE);
+ smu10_data->vcn_power_gated = false;
}
}
if (ret)
return ret;
- *query = metrics_table.CurrSocketPower << 8;
+ /* For the 40.46 release, they changed the value name */
+ if (hwmgr->smu_version == 0x282e00)
+ *query = metrics_table.AverageSocketPower << 8;
+ else
+ *query = metrics_table.CurrSocketPower << 8;
return ret;
}
data->dpm_table.soc_table.dpm_state.soft_max_level =
data->dpm_table.soc_table.dpm_levels[soft_level].value;
- ret = vega20_upload_dpm_min_level(hwmgr, 0xFFFFFFFF);
+ ret = vega20_upload_dpm_min_level(hwmgr, FEATURE_DPM_GFXCLK_MASK |
+ FEATURE_DPM_UCLK_MASK |
+ FEATURE_DPM_SOCCLK_MASK);
PP_ASSERT_WITH_CODE(!ret,
"Failed to upload boot level to highest!",
return ret);
- ret = vega20_upload_dpm_max_level(hwmgr, 0xFFFFFFFF);
+ ret = vega20_upload_dpm_max_level(hwmgr, FEATURE_DPM_GFXCLK_MASK |
+ FEATURE_DPM_UCLK_MASK |
+ FEATURE_DPM_SOCCLK_MASK);
PP_ASSERT_WITH_CODE(!ret,
"Failed to upload dpm max level to highest!",
return ret);
data->dpm_table.soc_table.dpm_state.soft_max_level =
data->dpm_table.soc_table.dpm_levels[soft_level].value;
- ret = vega20_upload_dpm_min_level(hwmgr, 0xFFFFFFFF);
+ ret = vega20_upload_dpm_min_level(hwmgr, FEATURE_DPM_GFXCLK_MASK |
+ FEATURE_DPM_UCLK_MASK |
+ FEATURE_DPM_SOCCLK_MASK);
PP_ASSERT_WITH_CODE(!ret,
"Failed to upload boot level to highest!",
return ret);
- ret = vega20_upload_dpm_max_level(hwmgr, 0xFFFFFFFF);
+ ret = vega20_upload_dpm_max_level(hwmgr, FEATURE_DPM_GFXCLK_MASK |
+ FEATURE_DPM_UCLK_MASK |
+ FEATURE_DPM_SOCCLK_MASK);
PP_ASSERT_WITH_CODE(!ret,
"Failed to upload dpm max level to highest!",
return ret);
static int vega20_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
{
+ struct vega20_hwmgr *data =
+ (struct vega20_hwmgr *)(hwmgr->backend);
+ uint32_t soft_min_level, soft_max_level;
int ret = 0;
- ret = vega20_upload_dpm_min_level(hwmgr, 0xFFFFFFFF);
+ /* gfxclk soft min/max settings */
+ soft_min_level =
+ vega20_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
+ soft_max_level =
+ vega20_find_highest_dpm_level(&(data->dpm_table.gfx_table));
+
+ data->dpm_table.gfx_table.dpm_state.soft_min_level =
+ data->dpm_table.gfx_table.dpm_levels[soft_min_level].value;
+ data->dpm_table.gfx_table.dpm_state.soft_max_level =
+ data->dpm_table.gfx_table.dpm_levels[soft_max_level].value;
+
+ /* uclk soft min/max settings */
+ soft_min_level =
+ vega20_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+ soft_max_level =
+ vega20_find_highest_dpm_level(&(data->dpm_table.mem_table));
+
+ data->dpm_table.mem_table.dpm_state.soft_min_level =
+ data->dpm_table.mem_table.dpm_levels[soft_min_level].value;
+ data->dpm_table.mem_table.dpm_state.soft_max_level =
+ data->dpm_table.mem_table.dpm_levels[soft_max_level].value;
+
+ /* socclk soft min/max settings */
+ soft_min_level =
+ vega20_find_lowest_dpm_level(&(data->dpm_table.soc_table));
+ soft_max_level =
+ vega20_find_highest_dpm_level(&(data->dpm_table.soc_table));
+
+ data->dpm_table.soc_table.dpm_state.soft_min_level =
+ data->dpm_table.soc_table.dpm_levels[soft_min_level].value;
+ data->dpm_table.soc_table.dpm_state.soft_max_level =
+ data->dpm_table.soc_table.dpm_levels[soft_max_level].value;
+
+ ret = vega20_upload_dpm_min_level(hwmgr, FEATURE_DPM_GFXCLK_MASK |
+ FEATURE_DPM_UCLK_MASK |
+ FEATURE_DPM_SOCCLK_MASK);
PP_ASSERT_WITH_CODE(!ret,
"Failed to upload DPM Bootup Levels!",
return ret);
- ret = vega20_upload_dpm_max_level(hwmgr, 0xFFFFFFFF);
+ ret = vega20_upload_dpm_max_level(hwmgr, FEATURE_DPM_GFXCLK_MASK |
+ FEATURE_DPM_UCLK_MASK |
+ FEATURE_DPM_SOCCLK_MASK);
PP_ASSERT_WITH_CODE(!ret,
"Failed to upload DPM Max Levels!",
return ret);
struct smu_table *tables;
uint32_t table_count;
struct smu_table memory_pool;
- uint16_t software_shutdown_temp;
uint8_t thermal_controller_type;
uint16_t TDPODLimit;
struct smu_power_gate {
bool uvd_gated;
bool vce_gated;
+ bool vcn_gated;
};
struct smu_power_context {
int (*tables_init)(struct smu_context *smu, struct smu_table *tables);
int (*set_thermal_fan_table)(struct smu_context *smu);
int (*get_fan_speed_percent)(struct smu_context *smu, uint32_t *speed);
+ int (*get_fan_speed_rpm)(struct smu_context *smu, uint32_t *speed);
int (*set_watermarks_table)(struct smu_context *smu, void *watermarks,
struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
int (*get_current_clk_freq_by_table)(struct smu_context *smu,
int (*get_thermal_temperature_range)(struct smu_context *smu, struct smu_temperature_range *range);
int (*get_uclk_dpm_states)(struct smu_context *smu, uint32_t *clocks_in_khz, uint32_t *num_states);
int (*set_default_od_settings)(struct smu_context *smu, bool initialize);
+ int (*set_performance_level)(struct smu_context *smu, enum amd_dpm_forced_level level);
};
struct smu_funcs
int (*set_watermarks_for_clock_ranges)(struct smu_context *smu,
struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
int (*conv_power_profile_to_pplib_workload)(int power_profile);
- int (*get_current_rpm)(struct smu_context *smu, uint32_t *speed);
uint32_t (*get_fan_control_mode)(struct smu_context *smu);
int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode);
int (*set_fan_speed_percent)(struct smu_context *smu, uint32_t speed);
((smu)->funcs->init_max_sustainable_clocks ? (smu)->funcs->init_max_sustainable_clocks((smu)) : 0)
#define smu_set_default_od_settings(smu, initialize) \
((smu)->ppt_funcs->set_default_od_settings ? (smu)->ppt_funcs->set_default_od_settings((smu), (initialize)) : 0)
-#define smu_get_current_rpm(smu, speed) \
- ((smu)->funcs->get_current_rpm ? (smu)->funcs->get_current_rpm((smu), (speed)) : 0)
#define smu_set_fan_speed_rpm(smu, speed) \
((smu)->funcs->set_fan_speed_rpm ? (smu)->funcs->set_fan_speed_rpm((smu), (speed)) : 0)
#define smu_send_smc_msg(smu, msg) \
((smu)->ppt_funcs->get_fan_speed_percent ? (smu)->ppt_funcs->get_fan_speed_percent((smu), (speed)) : 0)
#define smu_set_fan_speed_percent(smu, speed) \
((smu)->funcs->set_fan_speed_percent ? (smu)->funcs->set_fan_speed_percent((smu), (speed)) : 0)
+#define smu_get_fan_speed_rpm(smu, speed) \
+ ((smu)->ppt_funcs->get_fan_speed_rpm ? (smu)->ppt_funcs->get_fan_speed_rpm((smu), (speed)) : 0)
#define smu_msg_get_index(smu, msg) \
((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_msg_index? (smu)->ppt_funcs->get_smu_msg_index((smu), (msg)) : -EINVAL) : -EINVAL)
((smu)->funcs->register_irq_handler ? (smu)->funcs->register_irq_handler(smu) : 0)
#define smu_set_azalia_d3_pme(smu) \
((smu)->funcs->set_azalia_d3_pme ? (smu)->funcs->set_azalia_d3_pme((smu)) : 0)
-#define smu_get_uclk_dpm_states(smu, clocks_in_khz, num_states) \
- ((smu)->ppt_funcs->get_uclk_dpm_states ? (smu)->ppt_funcs->get_uclk_dpm_states((smu), (clocks_in_khz), (num_states)) : 0)
#define smu_get_max_sustainable_clocks_by_dc(smu, max_clocks) \
((smu)->funcs->get_max_sustainable_clocks_by_dc ? (smu)->funcs->get_max_sustainable_clocks_by_dc((smu), (max_clocks)) : 0)
#define smu_get_uclk_dpm_states(smu, clocks_in_khz, num_states) \
((smu)->funcs->baco_get_state? (smu)->funcs->baco_get_state((smu), (state)) : 0)
#define smu_baco_reset(smu) \
((smu)->funcs->baco_reset? (smu)->funcs->baco_reset((smu)) : 0)
+#define smu_asic_set_performance_level(smu, level) \
+ ((smu)->ppt_funcs->set_performance_level? (smu)->ppt_funcs->set_performance_level((smu), (level)) : -EINVAL);
+
extern int smu_get_atom_data_table(struct smu_context *smu, uint32_t table,
uint16_t *size, uint8_t *frev, uint8_t *crev,
#include "pp_debug.h"
#include <linux/firmware.h>
+#include <linux/pci.h>
#include "amdgpu.h"
#include "amdgpu_smu.h"
#include "atomfirmware.h"
static int navi10_tables_init(struct smu_context *smu, struct smu_table *tables)
{
+ struct smu_table_context *smu_table = &smu->smu_table;
+
SMU_TABLE_INIT(tables, SMU_TABLE_PPTABLE, sizeof(PPTable_t),
PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
SMU_TABLE_INIT(tables, SMU_TABLE_WATERMARKS, sizeof(Watermarks_t),
sizeof(DpmActivityMonitorCoeffInt_t), PAGE_SIZE,
AMDGPU_GEM_DOMAIN_VRAM);
+ smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
+ if (!smu_table->metrics_table)
+ return -ENOMEM;
+ smu_table->metrics_time = 0;
+
return 0;
}
+static int navi10_get_metrics_table(struct smu_context *smu,
+ SmuMetrics_t *metrics_table)
+{
+ struct smu_table_context *smu_table= &smu->smu_table;
+ int ret = 0;
+
+ if (!smu_table->metrics_time || time_after(jiffies, smu_table->metrics_time + HZ / 1000)) {
+ ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
+ (void *)smu_table->metrics_table, false);
+ if (ret) {
+ pr_info("Failed to export SMU metrics table!\n");
+ return ret;
+ }
+ smu_table->metrics_time = jiffies;
+ }
+
+ memcpy(metrics_table, smu_table->metrics_table, sizeof(SmuMetrics_t));
+
+ return ret;
+}
+
static int navi10_allocate_dpm_context(struct smu_context *smu)
{
struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
static int navi10_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
{
- int ret = 0;
struct smu_power_context *smu_power = &smu->smu_power;
struct smu_power_gate *power_gate = &smu_power->power_gate;
+ int ret = 0;
- if (enable && power_gate->uvd_gated) {
- if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UVD_BIT)) {
+ if (enable) {
+ /* vcn dpm on is a prerequisite for vcn power gate messages */
+ if (smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 1);
if (ret)
return ret;
}
- power_gate->uvd_gated = false;
+ power_gate->vcn_gated = false;
} else {
- if (!enable && !power_gate->uvd_gated) {
- if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UVD_BIT)) {
- ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn);
- if (ret)
- return ret;
- }
- power_gate->uvd_gated = true;
+ if (smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
+ ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn);
+ if (ret)
+ return ret;
}
+ power_gate->vcn_gated = true;
}
- return 0;
+ return ret;
}
static int navi10_get_current_clk_freq_by_table(struct smu_context *smu,
enum smu_clk_type clk_type,
uint32_t *value)
{
- static SmuMetrics_t metrics;
int ret = 0, clk_id = 0;
+ SmuMetrics_t metrics;
- if (!value)
- return -EINVAL;
-
- memset(&metrics, 0, sizeof(metrics));
-
- ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)&metrics, false);
+ ret = navi10_get_metrics_table(smu, &metrics);
if (ret)
return ret;
return ret;
}
+static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type)
+{
+ PPTable_t *pptable = smu->smu_table.driver_pptable;
+ DpmDescriptor_t *dpm_desc = NULL;
+ uint32_t clk_index = 0;
+
+ clk_index = smu_clk_get_index(smu, clk_type);
+ dpm_desc = &pptable->DpmDescriptor[clk_index];
+
+ /* 0 - Fine grained DPM, 1 - Discrete DPM */
+ return dpm_desc->SnapToDiscrete == 0 ? true : false;
+}
+
static int navi10_print_clk_levels(struct smu_context *smu,
enum smu_clk_type clk_type, char *buf)
{
int i, size = 0, ret = 0;
uint32_t cur_value = 0, value = 0, count = 0;
+ uint32_t freq_values[3] = {0};
+ uint32_t mark_index = 0;
switch (clk_type) {
case SMU_GFXCLK:
ret = smu_get_current_clk_freq(smu, clk_type, &cur_value);
if (ret)
return size;
+
/* 10KHz -> MHz */
cur_value = cur_value / 100;
- size += sprintf(buf, "current clk: %uMhz\n", cur_value);
-
ret = smu_get_dpm_level_count(smu, clk_type, &count);
if (ret)
return size;
- for (i = 0; i < count; i++) {
- ret = smu_get_dpm_freq_by_index(smu, clk_type, i, &value);
+ if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) {
+ for (i = 0; i < count; i++) {
+ ret = smu_get_dpm_freq_by_index(smu, clk_type, i, &value);
+ if (ret)
+ return size;
+
+ size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
+ cur_value == value ? "*" : "");
+ }
+ } else {
+ ret = smu_get_dpm_freq_by_index(smu, clk_type, 0, &freq_values[0]);
if (ret)
return size;
+ ret = smu_get_dpm_freq_by_index(smu, clk_type, count - 1, &freq_values[2]);
+ if (ret)
+ return size;
+
+ freq_values[1] = cur_value;
+ mark_index = cur_value == freq_values[0] ? 0 :
+ cur_value == freq_values[2] ? 2 : 1;
+ if (mark_index != 1)
+ freq_values[1] = (freq_values[0] + freq_values[2]) / 2;
+
+ for (i = 0; i < 3; i++) {
+ size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i],
+ i == mark_index ? "*" : "");
+ }
- size += sprintf(buf + size, "%d: %uMhz %s\n", i, value,
- cur_value == value ? "*" : "");
}
break;
default:
if (!value)
return -EINVAL;
- ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)&metrics,
- false);
+ ret = navi10_get_metrics_table(smu, &metrics);
+ if (ret)
+ return ret;
if (ret)
return ret;
if (!value)
return -EINVAL;
- msleep(1);
-
- ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
- (void *)&metrics, false);
+ ret = navi10_get_metrics_table(smu, &metrics);
if (ret)
return ret;
return !!(feature_enabled & SMC_DPM_FEATURE);
}
-static int navi10_get_fan_speed(struct smu_context *smu, uint16_t *value)
+static int navi10_get_fan_speed_rpm(struct smu_context *smu,
+ uint32_t *speed)
{
SmuMetrics_t metrics;
int ret = 0;
- if (!value)
+ if (!speed)
return -EINVAL;
- memset(&metrics, 0, sizeof(metrics));
-
- ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
- (void *)&metrics, false);
+ ret = navi10_get_metrics_table(smu, &metrics);
+ if (ret)
+ return ret;
if (ret)
return ret;
- *value = metrics.CurrFanSpeed;
+ *speed = metrics.CurrFanSpeed;
return ret;
}
{
int ret = 0;
uint32_t percent = 0;
- uint16_t current_rpm;
+ uint32_t current_rpm;
PPTable_t *pptable = smu->smu_table.driver_pptable;
- ret = navi10_get_fan_speed(smu, ¤t_rpm);
+ ret = navi10_get_fan_speed_rpm(smu, ¤t_rpm);
if (ret)
return ret;
if (!value)
return -EINVAL;
- ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0, (void *)&metrics, false);
+ ret = navi10_get_metrics_table(smu, &metrics);
if (ret)
return ret;
return 0;
}
+static int navi10_set_peak_clock_by_device(struct smu_context *smu)
+{
+ struct amdgpu_device *adev = smu->adev;
+ int ret = 0;
+ uint32_t sclk_freq = 0, uclk_freq = 0;
+ uint32_t uclk_level = 0;
+
+ switch (adev->pdev->revision) {
+ case 0xf0: /* XTX */
+ case 0xc0:
+ sclk_freq = NAVI10_PEAK_SCLK_XTX;
+ break;
+ case 0xf1: /* XT */
+ case 0xc1:
+ sclk_freq = NAVI10_PEAK_SCLK_XT;
+ break;
+ default: /* XL */
+ sclk_freq = NAVI10_PEAK_SCLK_XL;
+ break;
+ }
+
+ ret = smu_get_dpm_level_count(smu, SMU_UCLK, &uclk_level);
+ if (ret)
+ return ret;
+ ret = smu_get_dpm_freq_by_index(smu, SMU_UCLK, uclk_level - 1, &uclk_freq);
+ if (ret)
+ return ret;
+
+ ret = smu_set_soft_freq_range(smu, SMU_SCLK, sclk_freq, sclk_freq);
+ if (ret)
+ return ret;
+ ret = smu_set_soft_freq_range(smu, SMU_UCLK, uclk_freq, uclk_freq);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
+static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+{
+ int ret = 0;
+
+ switch (level) {
+ case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+ ret = navi10_set_peak_clock_by_device(smu);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static int navi10_get_thermal_temperature_range(struct smu_context *smu,
+ struct smu_temperature_range *range)
+{
+ struct smu_table_context *table_context = &smu->smu_table;
+ struct smu_11_0_powerplay_table *powerplay_table = table_context->power_play_table;
+
+ if (!range || !powerplay_table)
+ return -EINVAL;
+
+ /* The unit is temperature */
+ range->min = 0;
+ range->max = powerplay_table->software_shutdown_temp;
+
+ return 0;
+}
+
static const struct pptable_funcs navi10_ppt_funcs = {
.tables_init = navi10_tables_init,
.alloc_dpm_context = navi10_allocate_dpm_context,
.unforce_dpm_levels = navi10_unforce_dpm_levels,
.is_dpm_running = navi10_is_dpm_running,
.get_fan_speed_percent = navi10_get_fan_speed_percent,
+ .get_fan_speed_rpm = navi10_get_fan_speed_rpm,
.get_power_profile_mode = navi10_get_power_profile_mode,
.set_power_profile_mode = navi10_set_power_profile_mode,
.get_profiling_clk_mask = navi10_get_profiling_clk_mask,
.get_uclk_dpm_states = navi10_get_uclk_dpm_states,
.get_ppfeature_status = navi10_get_ppfeature_status,
.set_ppfeature_status = navi10_set_ppfeature_status,
+ .set_performance_level = navi10_set_performance_level,
+ .get_thermal_temperature_range = navi10_get_thermal_temperature_range,
};
void navi10_set_ppt_funcs(struct smu_context *smu)
#ifndef __NAVI10_PPT_H__
#define __NAVI10_PPT_H__
+#define NAVI10_PEAK_SCLK_XTX (1830)
+#define NAVI10_PEAK_SCLK_XT (1755)
+#define NAVI10_PEAK_SCLK_XL (1625)
+
extern void navi10_set_ppt_funcs(struct smu_context *smu);
#endif
struct amdgpu_device *adev = smu->adev;
const struct smc_firmware_header_v1_0 *hdr;
int ret, index;
- uint32_t size;
+ uint32_t size = 0;
+ uint16_t atom_table_size;
uint8_t frev, crev;
void *table;
uint16_t version_major, version_minor;
index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
powerplayinfo);
- ret = smu_get_atom_data_table(smu, index, (uint16_t *)&size, &frev, &crev,
+ ret = smu_get_atom_data_table(smu, index, &atom_table_size, &frev, &crev,
(uint8_t **)&table);
if (ret)
return ret;
+ size = atom_table_size;
}
if (!smu->smu_table.power_play_table)
struct smu_temperature_range *range)
{
struct amdgpu_device *adev = smu->adev;
- int low = SMU_THERMAL_MINIMUM_ALERT_TEMP *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
- int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ int low = SMU_THERMAL_MINIMUM_ALERT_TEMP;
+ int high = SMU_THERMAL_MAXIMUM_ALERT_TEMP;
uint32_t val;
if (!range)
if (high > range->max)
high = range->max;
+ low = max(SMU_THERMAL_MINIMUM_ALERT_TEMP, range->min);
+ high = min(SMU_THERMAL_MAXIMUM_ALERT_TEMP, range->max);
+
if (low > high)
return -EINVAL;
val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_IH_HW_ENA, 1);
val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_INTH_MASK, 0);
val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, THERM_INTL_MASK, 0);
- val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES));
- val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low / SMU_TEMPERATURE_UNITS_PER_CENTIGRADES));
+ val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTH, (high & 0xff));
+ val = REG_SET_FIELD(val, THM_THERMAL_INT_CTRL, DIG_THERM_INTL, (low & 0xff));
val = val & (~THM_THERMAL_INT_CTRL__THERM_TRIGGER_MASK_MASK);
WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_CTRL, val);
if (!smu->pm_enabled)
return ret;
+
ret = smu_get_thermal_temperature_range(smu, &range);
+ if (ret)
+ return ret;
if (smu->smu_table.thermal_controller_type) {
ret = smu_v11_0_set_thermal_range(smu, &range);
return ret;
}
- adev->pm.dpm.thermal.min_temp = range.min;
- adev->pm.dpm.thermal.max_temp = range.max;
- adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max;
- adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min;
- adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max;
- adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max;
- adev->pm.dpm.thermal.min_mem_temp = range.mem_min;
- adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max;
- adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max;
+ adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_edge_emergency_temp = range.edge_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.min_hotspot_temp = range.hotspot_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_hotspot_crit_temp = range.hotspot_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_hotspot_emergency_temp = range.hotspot_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.min_mem_temp = range.mem_min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_mem_crit_temp = range.mem_crit_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_mem_emergency_temp = range.mem_emergency_max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.min_temp = range.min * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ adev->pm.dpm.thermal.max_temp = range.max * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
return ret;
}
return ret;
}
-static int smu_v11_0_get_current_rpm(struct smu_context *smu,
- uint32_t *current_rpm)
-{
- int ret;
-
- ret = smu_send_smc_msg(smu, SMU_MSG_GetCurrentRpm);
-
- if (ret) {
- pr_err("Attempt to get current RPM from SMC Failed!\n");
- return ret;
- }
-
- smu_read_smc_arg(smu, current_rpm);
-
- return 0;
-}
-
static uint32_t
smu_v11_0_get_fan_control_mode(struct smu_context *smu)
{
{
int ret = 0;
- if (smu_feature_is_supported(smu, SMU_FEATURE_FAN_CONTROL_BIT))
+ if (!smu_feature_is_supported(smu, SMU_FEATURE_FAN_CONTROL_BIT))
return 0;
ret = smu_feature_set_enabled(smu, SMU_FEATURE_FAN_CONTROL_BIT, start);
.set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk,
.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
.set_watermarks_for_clock_ranges = smu_v11_0_set_watermarks_for_clock_ranges,
- .get_current_rpm = smu_v11_0_get_current_rpm,
.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
memcpy(table_context->driver_pptable, &powerplay_table->smcPPTable,
sizeof(PPTable_t));
- table_context->software_shutdown_temp = powerplay_table->usSoftwareShutdownTemp;
table_context->thermal_controller_type = powerplay_table->ucThermalControllerType;
table_context->TDPODLimit = le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPERCENTAGE]);
return ret;
}
+static int vega20_get_fan_speed_rpm(struct smu_context *smu,
+ uint32_t *speed)
+{
+ int ret;
+
+ ret = smu_send_smc_msg(smu, SMU_MSG_GetCurrentRpm);
+
+ if (ret) {
+ pr_err("Attempt to get current RPM from SMC Failed!\n");
+ return ret;
+ }
+
+ smu_read_smc_arg(smu, speed);
+
+ return 0;
+}
+
static int vega20_get_fan_speed_percent(struct smu_context *smu,
uint32_t *speed)
{
uint32_t current_rpm = 0, percent = 0;
PPTable_t *pptable = smu->smu_table.driver_pptable;
- ret = smu_get_current_rpm(smu, ¤t_rpm);
+ ret = vega20_get_fan_speed_rpm(smu, ¤t_rpm);
if (ret)
return ret;
static int vega20_get_gpu_power(struct smu_context *smu, uint32_t *value)
{
+ uint32_t smu_version;
int ret = 0;
SmuMetrics_t metrics;
if (ret)
return ret;
- *value = metrics.CurrSocketPower << 8;
+ ret = smu_get_smc_version(smu, NULL, &smu_version);
+ if (ret)
+ return ret;
+
+ /* For the 40.46 release, they changed the value name */
+ if (smu_version == 0x282e00)
+ *value = metrics.AverageSocketPower << 8;
+ else
+ *value = metrics.CurrSocketPower << 8;
return 0;
}
return 0;
}
-static const struct smu_temperature_range vega20_thermal_policy[] =
-{
- {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000},
- { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000},
-};
-
static int vega20_get_thermal_temperature_range(struct smu_context *smu,
struct smu_temperature_range *range)
{
-
+ struct smu_table_context *table_context = &smu->smu_table;
+ ATOM_Vega20_POWERPLAYTABLE *powerplay_table = table_context->power_play_table;
PPTable_t *pptable = smu->smu_table.driver_pptable;
- if (!range)
+ if (!range || !powerplay_table)
return -EINVAL;
- memcpy(range, &vega20_thermal_policy[0], sizeof(struct smu_temperature_range));
-
- range->max = pptable->TedgeLimit *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
- range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE) *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
- range->hotspot_crit_max = pptable->ThotspotLimit *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
- range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT) *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
- range->mem_crit_max = pptable->ThbmLimit *
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
- range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM)*
- SMU_TEMPERATURE_UNITS_PER_CENTIGRADES;
+ /* The unit is temperature */
+ range->min = 0;
+ range->max = powerplay_table->usSoftwareShutdownTemp;
+ range->edge_emergency_max = (pptable->TedgeLimit + CTF_OFFSET_EDGE);
+ range->hotspot_crit_max = pptable->ThotspotLimit;
+ range->hotspot_emergency_max = (pptable->ThotspotLimit + CTF_OFFSET_HOTSPOT);
+ range->mem_crit_max = pptable->ThbmLimit;
+ range->mem_emergency_max = (pptable->ThbmLimit + CTF_OFFSET_HBM);
return 0;
.is_dpm_running = vega20_is_dpm_running,
.set_thermal_fan_table = vega20_set_thermal_fan_table,
.get_fan_speed_percent = vega20_get_fan_speed_percent,
+ .get_fan_speed_rpm = vega20_get_fan_speed_rpm,
.set_watermarks_table = vega20_set_watermarks_table,
.get_thermal_temperature_range = vega20_get_thermal_temperature_range
};
#include <linux/iommu.h>
#include <linux/of_device.h>
#include <linux/of_graph.h>
+#include <linux/of_reserved_mem.h>
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
#ifdef CONFIG_DEBUG_FS
pipe->of_output_port =
of_graph_get_port_by_id(np, KOMEDA_OF_PORT_OUTPUT);
- pipe->of_node = np;
+ pipe->of_node = of_node_get(np);
return 0;
}
return mdev->irq;
}
+ /* Get the optional framebuffer memory resource */
+ ret = of_reserved_mem_device_init(dev);
+ if (ret && ret != -ENODEV)
+ return ret;
+ ret = 0;
+
for_each_available_child_of_node(np, child) {
if (of_node_cmp(child->name, "pipeline") == 0) {
ret = komeda_parse_pipe_dt(mdev, child);
mdev->n_pipelines = 0;
+ of_reserved_mem_device_release(dev);
+
if (funcs && funcs->cleanup)
funcs->cleanup(mdev);
return NULL;
}
+u32 komeda_get_afbc_format_bpp(const struct drm_format_info *info, u64 modifier)
+{
+ u32 bpp;
+
+ switch (info->format) {
+ case DRM_FORMAT_YUV420_8BIT:
+ bpp = 12;
+ break;
+ case DRM_FORMAT_YUV420_10BIT:
+ bpp = 15;
+ break;
+ default:
+ bpp = info->cpp[0] * 8;
+ break;
+ }
+
+ return bpp;
+}
+
/* Two assumptions
* 1. RGB always has YTR
* 2. Tiled RGB always has SC
komeda_get_format_caps(struct komeda_format_caps_table *table,
u32 fourcc, u64 modifier);
+u32 komeda_get_afbc_format_bpp(const struct drm_format_info *info,
+ u64 modifier);
+
u32 *komeda_get_layer_fourcc_list(struct komeda_format_caps_table *table,
u32 layer_type, u32 *n_fmts);
struct drm_framebuffer *fb = &kfb->base;
const struct drm_format_info *info = fb->format;
struct drm_gem_object *obj;
- u32 alignment_w = 0, alignment_h = 0, alignment_header, n_blocks;
+ u32 alignment_w = 0, alignment_h = 0, alignment_header, n_blocks, bpp;
u64 min_size;
obj = drm_gem_object_lookup(file, mode_cmd->handles[0]);
kfb->offset_payload = ALIGN(n_blocks * AFBC_HEADER_SIZE,
alignment_header);
+ bpp = komeda_get_afbc_format_bpp(info, fb->modifier);
kfb->afbc_size = kfb->offset_payload + n_blocks *
- ALIGN(info->cpp[0] * AFBC_SUPERBLK_PIXELS,
+ ALIGN(bpp * AFBC_SUPERBLK_PIXELS / 8,
AFBC_SUPERBLK_ALIGNMENT);
min_size = kfb->afbc_size + fb->offsets[0];
if (min_size > obj->size) {
#include <drm/drm_gem_cma_helper.h>
#include <drm/drm_gem_framebuffer_helper.h>
#include <drm/drm_irq.h>
+#include <drm/drm_probe_helper.h>
#include <drm/drm_vblank.h>
#include "komeda_dev.h"
struct komeda_crtc_state *kcrtc_st = to_kcrtc_st(crtc_st);
struct komeda_plane_state *kplane_st;
struct drm_plane_state *plane_st;
- struct drm_framebuffer *fb;
struct drm_plane *plane;
struct list_head zorder_list;
int order = 0, err;
list_for_each_entry(kplane_st, &zorder_list, zlist_node) {
plane_st = &kplane_st->base;
- fb = plane_st->fb;
plane = plane_st->plane;
plane_st->normalized_zpos = order++;
struct drm_atomic_state *state)
{
struct drm_crtc *crtc;
- struct drm_crtc_state *old_crtc_st, *new_crtc_st;
+ struct drm_crtc_state *new_crtc_st;
int i, err;
err = drm_atomic_helper_check_modeset(dev, state);
* so need to add all affected_planes (even unchanged) to
* drm_atomic_state.
*/
- for_each_oldnew_crtc_in_state(state, crtc, old_crtc_st, new_crtc_st, i) {
+ for_each_new_crtc_in_state(state, crtc, new_crtc_st, i) {
err = drm_atomic_add_affected_planes(state, crtc);
if (err)
return err;
komeda_kms_irq_handler, IRQF_SHARED,
drm->driver->name, drm);
if (err)
- goto cleanup_mode_config;
+ goto free_component_binding;
err = mdev->funcs->enable_irq(mdev);
if (err)
- goto cleanup_mode_config;
+ goto free_component_binding;
drm->irq_enabled = true;
+ drm_kms_helper_poll_init(drm);
+
err = drm_dev_register(drm, 0);
if (err)
- goto cleanup_mode_config;
+ goto free_interrupts;
return kms;
-cleanup_mode_config:
+free_interrupts:
+ drm_kms_helper_poll_fini(drm);
drm->irq_enabled = false;
+ mdev->funcs->disable_irq(mdev);
+free_component_binding:
+ component_unbind_all(mdev->dev, drm);
+cleanup_mode_config:
drm_mode_config_cleanup(drm);
komeda_kms_cleanup_private_objs(kms);
+ drm->dev_private = NULL;
+ drm_dev_put(drm);
free_kms:
kfree(kms);
return ERR_PTR(err);
struct drm_device *drm = &kms->base;
struct komeda_dev *mdev = drm->dev_private;
+ drm_dev_unregister(drm);
+ drm_kms_helper_poll_fini(drm);
+ drm_atomic_helper_shutdown(drm);
drm->irq_enabled = false;
mdev->funcs->disable_irq(mdev);
- drm_dev_unregister(drm);
component_unbind_all(mdev->dev, drm);
- komeda_kms_cleanup_private_objs(kms);
drm_mode_config_cleanup(drm);
+ komeda_kms_cleanup_private_objs(kms);
drm->dev_private = NULL;
drm_dev_put(drm);
}
struct seq_file *sf);
/* component APIs */
+extern __printf(10, 11)
struct komeda_component *
komeda_component_add(struct komeda_pipeline *pipe,
size_t comp_sz, u32 id, u32 hw_id,
if (!kcrtc->master->wb_layer)
return 0;
- kwb_conn = kzalloc(sizeof(*wb_conn), GFP_KERNEL);
+ kwb_conn = kzalloc(sizeof(*kwb_conn), GFP_KERNEL);
if (!kwb_conn)
return -ENOMEM;
/* Enable extended register access */
- ast_enable_mmio(dev);
ast_open_key(ast);
+ ast_enable_mmio(dev);
/* Find out whether P2A works or whether to use device-tree */
ast_detect_config_mode(dev, &scu_rev);
{
struct ast_private *ast = dev->dev_private;
+ /* enable standard VGA decode */
+ ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x04);
+
ast_release_firmware(dev);
kfree(ast->dp501_fw_addr);
ast_mode_fini(dev);
return -EINVAL;
ast_open_key(ast);
- ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04);
+ ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06);
ast_set_std_reg(crtc, adjusted_mode, &vbios_mode);
ast_set_crtc_reg(crtc, adjusted_mode, &vbios_mode);
{
struct ast_private *ast = dev->dev_private;
- ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa1, 0xff, 0x04);
+ ast_set_index_reg(ast, AST_IO_CRTC_PORT, 0xa1, 0x06);
}
bochs->dev->mode_config.fb_base = bochs->fb_base;
bochs->dev->mode_config.preferred_depth = 24;
bochs->dev->mode_config.prefer_shadow = 0;
+ bochs->dev->mode_config.prefer_shadow_fbdev = 1;
bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
bochs->dev->mode_config.funcs = &bochs_mode_funcs;
config DRM_LVDS_ENCODER
tristate "Transparent parallel to LVDS encoder support"
depends on OF
+ select DRM_KMS_HELPER
select DRM_PANEL_BRIDGE
help
Support for transparent parallel to LVDS encoders that don't require
config DRM_TOSHIBA_TC358764
tristate "TC358764 DSI/LVDS bridge"
- depends on DRM && DRM_PANEL
depends on OF
select DRM_MIPI_DSI
+ select DRM_KMS_HELPER
+ select DRM_PANEL
help
Toshiba TC358764 DSI/LVDS bridge driver.
struct drm_device *dev = client->dev;
struct drm_client_buffer *buffer;
struct drm_gem_object *obj;
- void *vaddr;
int ret;
buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
buffer->gem = obj;
+ return buffer;
+
+err_delete:
+ drm_client_buffer_delete(buffer);
+
+ return ERR_PTR(ret);
+}
+
+/**
+ * drm_client_buffer_vmap - Map DRM client buffer into address space
+ * @buffer: DRM client buffer
+ *
+ * This function maps a client buffer into kernel address space. If the
+ * buffer is already mapped, it returns the mapping's address.
+ *
+ * Client buffer mappings are not ref'counted. Each call to
+ * drm_client_buffer_vmap() should be followed by a call to
+ * drm_client_buffer_vunmap(); or the client buffer should be mapped
+ * throughout its lifetime.
+ *
+ * Returns:
+ * The mapped memory's address
+ */
+void *drm_client_buffer_vmap(struct drm_client_buffer *buffer)
+{
+ void *vaddr;
+
+ if (buffer->vaddr)
+ return buffer->vaddr;
+
/*
* FIXME: The dependency on GEM here isn't required, we could
* convert the driver handle to a dma-buf instead and use the
* fd_install step out of the driver backend hooks, to make that
* final step optional for internal users.
*/
- vaddr = drm_gem_vmap(obj);
- if (IS_ERR(vaddr)) {
- ret = PTR_ERR(vaddr);
- goto err_delete;
- }
+ vaddr = drm_gem_vmap(buffer->gem);
+ if (IS_ERR(vaddr))
+ return vaddr;
buffer->vaddr = vaddr;
- return buffer;
-
-err_delete:
- drm_client_buffer_delete(buffer);
+ return vaddr;
+}
+EXPORT_SYMBOL(drm_client_buffer_vmap);
- return ERR_PTR(ret);
+/**
+ * drm_client_buffer_vunmap - Unmap DRM client buffer
+ * @buffer: DRM client buffer
+ *
+ * This function removes a client buffer's memory mapping. Calling this
+ * function is only required by clients that manage their buffer mappings
+ * by themselves.
+ */
+void drm_client_buffer_vunmap(struct drm_client_buffer *buffer)
+{
+ drm_gem_vunmap(buffer->gem, buffer->vaddr);
+ buffer->vaddr = NULL;
}
+EXPORT_SYMBOL(drm_client_buffer_vunmap);
static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer)
{
* simple XOR between the two handle the addition nicely.
*/
cmdline = &connector->cmdline_mode;
- if (cmdline->specified) {
+ if (cmdline->specified && cmdline->rotation_reflection) {
unsigned int cmdline_rest, panel_rest;
unsigned int cmdline_rot, panel_rot;
unsigned int sum_rot, sum_rest;
struct drm_clip_rect *clip = &helper->dirty_clip;
struct drm_clip_rect clip_copy;
unsigned long flags;
+ void *vaddr;
spin_lock_irqsave(&helper->dirty_lock, flags);
clip_copy = *clip;
/* call dirty callback only when it has been really touched */
if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) {
+
/* Generic fbdev uses a shadow buffer */
- if (helper->buffer)
+ if (helper->buffer) {
+ vaddr = drm_client_buffer_vmap(helper->buffer);
+ if (IS_ERR(vaddr))
+ return;
drm_fb_helper_dirty_blit_real(helper, &clip_copy);
- helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
+ }
+ if (helper->fb->funcs->dirty)
+ helper->fb->funcs->dirty(helper->fb, NULL, 0, 0,
+ &clip_copy, 1);
+
+ if (helper->buffer)
+ drm_client_buffer_vunmap(helper->buffer);
}
}
}
EXPORT_SYMBOL(drm_fb_helper_unlink_fbi);
+static bool drm_fbdev_use_shadow_fb(struct drm_fb_helper *fb_helper)
+{
+ struct drm_device *dev = fb_helper->dev;
+ struct drm_framebuffer *fb = fb_helper->fb;
+
+ return dev->mode_config.prefer_shadow_fbdev ||
+ dev->mode_config.prefer_shadow ||
+ fb->funcs->dirty;
+}
+
static void drm_fb_helper_dirty(struct fb_info *info, u32 x, u32 y,
u32 width, u32 height)
{
struct drm_clip_rect *clip = &helper->dirty_clip;
unsigned long flags;
- if (!helper->fb->funcs->dirty)
+ if (!drm_fbdev_use_shadow_fb(helper))
return;
spin_lock_irqsave(&helper->dirty_lock, flags);
struct drm_framebuffer *fb;
struct fb_info *fbi;
u32 format;
+ void *vaddr;
DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
sizes->surface_width, sizes->surface_height,
fbi->fbops = &drm_fbdev_fb_ops;
fbi->screen_size = fb->height * fb->pitches[0];
fbi->fix.smem_len = fbi->screen_size;
- fbi->screen_buffer = buffer->vaddr;
- /* Shamelessly leak the physical address to user-space */
-#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM)
- if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0)
- fbi->fix.smem_start =
- page_to_phys(virt_to_page(fbi->screen_buffer));
-#endif
+
drm_fb_helper_fill_info(fbi, fb_helper, sizes);
- if (fb->funcs->dirty) {
+ if (drm_fbdev_use_shadow_fb(fb_helper)) {
struct fb_ops *fbops;
void *shadow;
fbi->fbdefio = &drm_fbdev_defio;
fb_deferred_io_init(fbi);
+ } else {
+ /* buffer is mapped for HW framebuffer */
+ vaddr = drm_client_buffer_vmap(fb_helper->buffer);
+ if (IS_ERR(vaddr))
+ return PTR_ERR(vaddr);
+
+ fbi->screen_buffer = vaddr;
+ /* Shamelessly leak the physical address to user-space */
+#if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM)
+ if (drm_leak_fbdev_smem && fbi->fix.smem_start == 0)
+ fbi->fix.smem_start =
+ page_to_phys(virt_to_page(fbi->screen_buffer));
+#endif
}
return 0;
struct drm_device *dev = fb->dev;
struct drm_atomic_state *state;
struct drm_plane *plane;
- struct drm_connector *conn;
+ struct drm_connector *conn __maybe_unused;
struct drm_connector_state *conn_state;
int i, ret;
unsigned plane_mask;
}
static int drm_mode_parse_cmdline_extra(const char *str, int length,
+ bool freestanding,
const struct drm_connector *connector,
struct drm_cmdline_mode *mode)
{
for (i = 0; i < length; i++) {
switch (str[i]) {
case 'i':
+ if (freestanding)
+ return -EINVAL;
+
mode->interlace = true;
break;
case 'm':
+ if (freestanding)
+ return -EINVAL;
+
mode->margins = true;
break;
case 'D':
if (extras) {
int ret = drm_mode_parse_cmdline_extra(end_ptr + i,
1,
+ false,
connector,
mode);
if (ret)
return 0;
}
+static const char *drm_named_modes_whitelist[] = {
+ "NTSC",
+ "PAL",
+};
+
+static bool drm_named_mode_is_in_whitelist(const char *mode, unsigned int size)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(drm_named_modes_whitelist); i++)
+ if (!strncmp(mode, drm_named_modes_whitelist[i], size))
+ return true;
+
+ return false;
+}
+
/**
* drm_mode_parse_command_line_for_connector - parse command line modeline for connector
* @mode_option: optional per connector mode option
*
* Additionals options can be provided following the mode, using a comma to
* separate each option. Valid options can be found in
- * Documentation/fb/modedb.txt.
+ * Documentation/fb/modedb.rst.
*
* The intermediate drm_cmdline_mode structure is required to store additional
* options from the command line modline like the force-enable/disable flag.
* bunch of things:
* - We need to make sure that the first character (which
* would be our resolution in X) is a digit.
- * - However, if the X resolution is missing, then we end up
- * with something like x<yres>, with our first character
- * being an alpha-numerical character, which would be
- * considered a named mode.
+ * - If not, then it's either a named mode or a force on/off.
+ * To distinguish between the two, we need to run the
+ * extra parsing function, and if not, then we consider it
+ * a named mode.
*
* If this isn't enough, we should add more heuristics here,
* and matching unit-tests.
*/
- if (!isdigit(name[0]) && name[0] != 'x')
+ if (!isdigit(name[0]) && name[0] != 'x') {
+ unsigned int namelen = strlen(name);
+
+ /*
+ * Only the force on/off options can be in that case,
+ * and they all take a single character.
+ */
+ if (namelen == 1) {
+ ret = drm_mode_parse_cmdline_extra(name, namelen, true,
+ connector, mode);
+ if (!ret)
+ return true;
+ }
+
named_mode = true;
+ }
/* Try to locate the bpp and refresh specifiers, if any */
bpp_ptr = strchr(name, '-');
}
if (named_mode) {
- strncpy(mode->name, name, mode_end);
+ if (mode_end + 1 > DRM_DISPLAY_MODE_LEN)
+ return false;
+
+ if (!drm_named_mode_is_in_whitelist(name, mode_end))
+ return false;
+
+ strscpy(mode->name, name, mode_end + 1);
} else {
ret = drm_mode_parse_cmdline_res_mode(name, mode_end,
parse_extras,
extra_ptr != options_ptr) {
int len = strlen(name) - (extra_ptr - name);
- ret = drm_mode_parse_cmdline_extra(extra_ptr, len,
+ ret = drm_mode_parse_cmdline_extra(extra_ptr, len, false,
connector, mode);
if (ret)
return false;
config DRM_EXYNOS
tristate "DRM Support for Samsung SoC EXYNOS Series"
depends on OF && DRM && (ARCH_S3C64XX || ARCH_S5PV210 || ARCH_EXYNOS || ARCH_MULTIPLATFORM || COMPILE_TEST)
+ depends on MMU
select DRM_KMS_HELPER
select VIDEOMODE_HELPERS
select SND_SOC_HDMI_CODEC if SND_SOC
module_param_named(fimc_devs, fimc_mask, uint, 0644);
MODULE_PARM_DESC(fimc_devs, "Alias mask for assigning FIMC devices to Exynos DRM");
-#define get_fimc_context(dev) platform_get_drvdata(to_platform_device(dev))
+#define get_fimc_context(dev) dev_get_drvdata(dev)
enum {
FIMC_CLK_LCLK,
static int g2d_init_cmdlist(struct g2d_data *g2d)
{
struct device *dev = g2d->dev;
- struct g2d_cmdlist_node *node = g2d->cmdlist_node;
+ struct g2d_cmdlist_node *node;
int nr;
int ret;
struct g2d_buf_info *buf_info;
#define GSC_COEF_DEPTH 3
#define GSC_AUTOSUSPEND_DELAY 2000
-#define get_gsc_context(dev) platform_get_drvdata(to_platform_device(dev))
+#define get_gsc_context(dev) dev_get_drvdata(dev)
#define gsc_read(offset) readl(ctx->regs + (offset))
#define gsc_write(cfg, offset) writel(cfg, ctx->regs + (offset))
scaler_write(SCALER_CFG_SOFT_RESET, SCALER_CFG);
do {
cpu_relax();
- } while (retry > 1 &&
+ } while (--retry > 1 &&
scaler_read(SCALER_CFG) & SCALER_CFG_SOFT_RESET);
do {
cpu_relax();
scaler_write(1, SCALER_INT_EN);
- } while (retry > 0 && scaler_read(SCALER_INT_EN) != 1);
+ } while (--retry > 0 && scaler_read(SCALER_INT_EN) != 1);
return retry ? 0 : -EIO;
}
subdir-ccflags-y += $(call cc-disable-warning, unused-parameter)
subdir-ccflags-y += $(call cc-disable-warning, type-limits)
subdir-ccflags-y += $(call cc-disable-warning, missing-field-initializers)
-subdir-ccflags-y += $(call cc-disable-warning, implicit-fallthrough)
subdir-ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
# clang warnings
subdir-ccflags-y += $(call cc-disable-warning, sign-compare)
}
if (bdb->version >= 226) {
- u32 wakeup_time = psr_table->psr2_tp2_tp3_wakeup_time;
+ u32 wakeup_time = psr->psr2_tp2_tp3_wakeup_time;
wakeup_time = (wakeup_time >> (2 * panel_type)) & 0x3;
switch (wakeup_time) {
clpchgroup = (sa->deburst * deinterleave / num_channels) << i;
bi->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1;
+ bi->num_qgv_points = qi.num_points;
+
for (j = 0; j < qi.num_points; j++) {
const struct intel_qgv_point *sp = &qi.points[j];
int ct, bw;
bi->deratedbw[j] = min(maxdebw,
bw * 9 / 10); /* 90% */
- DRM_DEBUG_KMS("BW%d / QGV %d: num_planes=%d deratedbw=%d\n",
+ DRM_DEBUG_KMS("BW%d / QGV %d: num_planes=%d deratedbw=%u\n",
i, j, bi->num_planes, bi->deratedbw[j]);
}
{
int i;
- /* Did we initialize the bw limits successfully? */
- if (dev_priv->max_bw[0].num_planes == 0)
- return UINT_MAX;
-
for (i = 0; i < ARRAY_SIZE(dev_priv->max_bw); i++) {
const struct intel_bw_info *bi =
&dev_priv->max_bw[i];
+ /*
+ * Pcode will not expose all QGV points when
+ * SAGV is forced to off/min/med/max.
+ */
+ if (qgv_point >= bi->num_qgv_points)
+ return UINT_MAX;
+
if (num_planes >= bi->num_planes)
return bi->deratedbw[qgv_point];
}
if (crtc_state->has_audio && INTEL_GEN(dev_priv) >= 9)
min_cdclk = max(2 * 96000, min_cdclk);
+ /*
+ * "For DP audio configuration, cdclk frequency shall be set to
+ * meet the following requirements:
+ * DP Link Frequency(MHz) | Cdclk frequency(MHz)
+ * 270 | 320 or higher
+ * 162 | 200 or higher"
+ */
+ if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+ intel_crtc_has_dp_encoder(crtc_state) && crtc_state->has_audio)
+ min_cdclk = max(crtc_state->port_clock, min_cdclk);
+
/*
* On Valleyview some DSI panels lose (v|h)sync when the clock is lower
* than 320000KHz.
else if (intel_crtc_has_dp_encoder(pipe_config))
dotclock = intel_dotclock_calculate(pipe_config->port_clock,
&pipe_config->dp_m_n);
- else if (pipe_config->has_hdmi_sink && pipe_config->pipe_bpp == 36)
- dotclock = pipe_config->port_clock * 2 / 3;
+ else if (pipe_config->has_hdmi_sink && pipe_config->pipe_bpp > 24)
+ dotclock = pipe_config->port_clock * 24 / pipe_config->pipe_bpp;
else
dotclock = pipe_config->port_clock;
/* FIXME: assert CPU port conditions for SNB+ */
}
- trace_intel_pipe_enable(dev_priv, pipe);
+ trace_intel_pipe_enable(crtc);
reg = PIPECONF(cpu_transcoder);
val = I915_READ(reg);
*/
assert_planes_disabled(crtc);
- trace_intel_pipe_disable(dev_priv, pipe);
+ trace_intel_pipe_disable(crtc);
reg = PIPECONF(cpu_transcoder);
val = I915_READ(reg);
case INTEL_OUTPUT_DDI:
if (WARN_ON(!HAS_DDI(to_i915(dev))))
break;
- /* else: fall through */
+ /* else, fall through */
case INTEL_OUTPUT_DP:
case INTEL_OUTPUT_HDMI:
case INTEL_OUTPUT_EDP:
#define ICL_AUX_PW_TO_CH(pw_idx) \
((pw_idx) - ICL_PW_CTL_IDX_AUX_A + AUX_CH_A)
+#define ICL_TBT_AUX_PW_TO_CH(pw_idx) \
+ ((pw_idx) - ICL_PW_CTL_IDX_AUX_TBT1 + AUX_CH_C)
+
static void
icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
struct i915_power_well *power_well)
{
- enum aux_ch aux_ch = ICL_AUX_PW_TO_CH(power_well->desc->hsw.idx);
+ int pw_idx = power_well->desc->hsw.idx;
+ bool is_tbt = power_well->desc->hsw.is_tc_tbt;
+ enum aux_ch aux_ch;
u32 val;
+ aux_ch = is_tbt ? ICL_TBT_AUX_PW_TO_CH(pw_idx) :
+ ICL_AUX_PW_TO_CH(pw_idx);
val = I915_READ(DP_AUX_CH_CTL(aux_ch));
val &= ~DP_AUX_CH_CTL_TBT_IO;
- if (power_well->desc->hsw.is_tc_tbt)
+ if (is_tbt)
val |= DP_AUX_CH_CTL_TBT_IO;
I915_WRITE(DP_AUX_CH_CTL(aux_ch), val);
switch (lane_info) {
default:
MISSING_CASE(lane_info);
+ /* fall through */
case 1:
case 2:
case 4:
intel_attach_force_audio_property(connector);
intel_attach_broadcast_rgb_property(connector);
- drm_connector_attach_max_bpc_property(connector, 6, 12);
+
+ /*
+ * Reuse the prop from the SST connector because we're
+ * not allowed to create new props after device registration.
+ */
+ connector->max_bpc_property =
+ intel_dp->attached_connector->base.max_bpc_property;
+ if (connector->max_bpc_property)
+ drm_connector_attach_max_bpc_property(connector, 6, 12);
return connector;
if (drm_hdcp_check_ksvs_revoked(dev, ksv_fifo, num_downstream)) {
DRM_ERROR("Revoked Ksv(s) in ksv_fifo\n");
- return -EPERM;
+ ret = -EPERM;
+ goto err;
}
/*
/* TP wake up time in multiple of 100 */
u16 tp1_wakeup_time;
u16 tp2_tp3_wakeup_time;
-
- /* PSR2 TP2/TP3 wakeup time for 16 panels */
- u32 psr2_tp2_tp3_wakeup_time;
} __packed;
struct bdb_psr {
struct psr_table psr_table[16];
+
+ /* PSR2 TP2/TP3 wakeup time for 16 panels */
+ u32 psr2_tp2_tp3_wakeup_time;
} __packed;
/*
pps_val |= DSC_PIC_HEIGHT(vdsc_cfg->pic_height) |
DSC_PIC_WIDTH(vdsc_cfg->pic_width / num_vdsc_instances);
DRM_INFO("PPS2 = 0x%08x\n", pps_val);
- if (encoder->type == INTEL_OUTPUT_EDP) {
+ if (cpu_transcoder == TRANSCODER_EDP) {
I915_WRITE(DSCA_PICTURE_PARAMETER_SET_2, pps_val);
/*
* If 2 VDSC instances are needed, configure PPS for second
else
txesc2_div = 10;
- I915_WRITE(MIPIO_TXESC_CLK_DIV1, txesc1_div & GLK_TX_ESC_CLK_DIV1_MASK);
- I915_WRITE(MIPIO_TXESC_CLK_DIV2, txesc2_div & GLK_TX_ESC_CLK_DIV2_MASK);
+ I915_WRITE(MIPIO_TXESC_CLK_DIV1, (1 << (txesc1_div - 1)) & GLK_TX_ESC_CLK_DIV1_MASK);
+ I915_WRITE(MIPIO_TXESC_CLK_DIV2, (1 << (txesc2_div - 1)) & GLK_TX_ESC_CLK_DIV2_MASK);
}
/* Program BXT Mipi clocks and dividers */
static int eb_copy_relocations(const struct i915_execbuffer *eb)
{
+ struct drm_i915_gem_relocation_entry *relocs;
const unsigned int count = eb->buffer_count;
unsigned int i;
int err;
for (i = 0; i < count; i++) {
const unsigned int nreloc = eb->exec[i].relocation_count;
struct drm_i915_gem_relocation_entry __user *urelocs;
- struct drm_i915_gem_relocation_entry *relocs;
unsigned long size;
unsigned long copied;
if (__copy_from_user((char *)relocs + copied,
(char __user *)urelocs + copied,
- len)) {
-end_user:
- user_access_end();
-end:
- kvfree(relocs);
- err = -EFAULT;
- goto err;
- }
+ len))
+ goto end;
copied += len;
} while (copied < size);
return 0;
+end_user:
+ user_access_end();
+end:
+ kvfree(relocs);
+ err = -EFAULT;
err:
while (i--) {
- struct drm_i915_gem_relocation_entry *relocs =
- u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr);
+ relocs = u64_to_ptr(typeof(*relocs), eb->exec[i].relocs_ptr);
if (eb->exec[i].relocation_count)
kvfree(relocs);
}
*/
if (!i915_terminally_wedged(i915))
return VM_FAULT_SIGBUS;
- /* else: fall through */
+ /* else, fall through */
case -EAGAIN:
/*
* EAGAIN means the gpu is hung and we'll wait for the error
switch (type) {
default:
MISSING_CASE(type);
- /* fallthrough to use PAGE_KERNEL anyway */
+ /* fallthrough - to use PAGE_KERNEL anyway */
case I915_MAP_WB:
pgprot = PAGE_KERNEL;
break;
i915_gem_restore_gtt_mappings(i915);
i915_gem_restore_fences(i915);
+ if (i915_gem_init_hw(i915))
+ goto err_wedged;
+
/*
* As we didn't flush the kernel context before suspend, we cannot
* guarantee that the context image is complete. So let's just reset
* it and start again.
*/
- intel_gt_resume(i915);
-
- if (i915_gem_init_hw(i915))
+ if (intel_gt_resume(i915))
goto err_wedged;
intel_uc_resume(i915);
for_each_sgt_page(page, sgt_iter, pages) {
if (obj->mm.dirty)
- set_page_dirty(page);
+ /*
+ * As this may not be anonymous memory (e.g. shmem)
+ * but exist on a real mapping, we have to lock
+ * the page in order to dirty it -- holding
+ * the page reference is not sufficient to
+ * prevent the inode from being truncated.
+ * Play safe and take the lock.
+ */
+ set_page_dirty_lock(page);
mark_page_accessed(page);
put_page(page);
if (ce->state)
__context_unpin_state(ce->state);
+ intel_ring_unpin(ce->ring);
intel_context_put(ce);
}
intel_context_get(ce);
+ err = intel_ring_pin(ce->ring);
+ if (err)
+ goto err_put;
+
if (!ce->state)
return 0;
err = __context_pin_state(ce->state, flags);
- if (err) {
- i915_active_cancel(&ce->active);
- intel_context_put(ce);
- return err;
- }
+ if (err)
+ goto err_ring;
/* Preallocate tracking nodes */
if (!i915_gem_context_is_kernel(ce->gem_context)) {
err = i915_active_acquire_preallocate_barrier(&ce->active,
ce->engine);
- if (err) {
- i915_active_release(&ce->active);
- return err;
- }
+ if (err)
+ goto err_state;
}
return 0;
+
+err_state:
+ __context_unpin_state(ce->state);
+err_ring:
+ intel_ring_unpin(ce->ring);
+err_put:
+ intel_context_put(ce);
+ i915_active_cancel(&ce->active);
+ return err;
}
void intel_context_active_release(struct intel_context *ce)
u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
{
const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
+ unsigned int slice = fls(sseu->slice_mask) - 1;
+ unsigned int subslice;
u32 mcr_s_ss_select;
- u32 slice = fls(sseu->slice_mask);
- u32 subslice = fls(sseu->subslice_mask[slice]);
+
+ GEM_BUG_ON(slice >= ARRAY_SIZE(sseu->subslice_mask));
+ subslice = fls(sseu->subslice_mask[slice]);
+ GEM_BUG_ON(!subslice);
+ subslice--;
if (IS_GEN(dev_priv, 10))
mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
struct i915_gpu_error * const error = &engine->i915->gpu_error;
struct i915_request *rq;
intel_wakeref_t wakeref;
+ unsigned long flags;
if (header) {
va_list ap;
i915_reset_engine_count(error, engine),
i915_reset_count(error));
- rcu_read_lock();
-
drm_printf(m, "\tRequests:\n");
+ spin_lock_irqsave(&engine->active.lock, flags);
rq = intel_engine_find_active_request(engine);
if (rq) {
print_request(m, rq, "\t\tactive ");
print_request_ring(m, rq);
}
-
- rcu_read_unlock();
+ spin_unlock_irqrestore(&engine->active.lock, flags);
wakeref = intel_runtime_pm_get_if_in_use(&engine->i915->runtime_pm);
if (wakeref) {
intel_engine_find_active_request(struct intel_engine_cs *engine)
{
struct i915_request *request, *active = NULL;
- unsigned long flags;
/*
* We are called by the error capture, reset and to dump engine
* At all other times, we must assume the GPU is still running, but
* we only care about the snapshot of this moment.
*/
- spin_lock_irqsave(&engine->active.lock, flags);
+ lockdep_assert_held(&engine->active.lock);
list_for_each_entry(request, &engine->active.requests, sched.link) {
if (i915_request_completed(request))
continue;
active = request;
break;
}
- spin_unlock_irqrestore(&engine->active.lock, flags);
return active;
}
{
intel_wakeref_init(&engine->wakeref);
}
-
-int intel_engines_resume(struct drm_i915_private *i915)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
- int err = 0;
-
- intel_gt_pm_get(i915);
- for_each_engine(engine, i915, id) {
- intel_engine_pm_get(engine);
- engine->serial++; /* kernel context lost */
- err = engine->resume(engine);
- intel_engine_pm_put(engine);
- if (err) {
- dev_err(i915->drm.dev,
- "Failed to restart %s (%d)\n",
- engine->name, err);
- break;
- }
- }
- intel_gt_pm_put(i915);
-
- return err;
-}
#ifndef INTEL_ENGINE_PM_H
#define INTEL_ENGINE_PM_H
+#include "intel_engine_types.h"
+#include "intel_wakeref.h"
+
struct drm_i915_private;
-struct intel_engine_cs;
void intel_engine_pm_get(struct intel_engine_cs *engine);
void intel_engine_pm_put(struct intel_engine_cs *engine);
+static inline bool
+intel_engine_pm_get_if_awake(struct intel_engine_cs *engine)
+{
+ return intel_wakeref_get_if_active(&engine->wakeref);
+}
+
void intel_engine_park(struct intel_engine_cs *engine);
void intel_engine_init__pm(struct intel_engine_cs *engine);
-int intel_engines_resume(struct drm_i915_private *i915);
-
#endif /* INTEL_ENGINE_PM_H */
struct list_head request_list;
struct list_head active_link;
+ /*
+ * As we have two types of rings, one global to the engine used
+ * by ringbuffer submission and those that are exclusive to a
+ * context used by execlists, we have to play safe and allow
+ * atomic updates to the pin_count. However, the actual pinning
+ * of the context is either done during initialisation for
+ * ringbuffer submission or serialised as part of the context
+ * pinning for execlists, and so we do not need a mutex ourselves
+ * to serialise intel_ring_pin/intel_ring_unpin.
+ */
+ atomic_t pin_count;
+
u32 head;
u32 tail;
u32 emit;
*/
#include "i915_drv.h"
+#include "intel_engine_pm.h"
#include "intel_gt_pm.h"
#include "intel_pm.h"
#include "intel_wakeref.h"
intel_engine_reset(engine, false);
}
-void intel_gt_resume(struct drm_i915_private *i915)
+int intel_gt_resume(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
+ int err = 0;
/*
* After resume, we may need to poke into the pinned kernel
* Only the kernel contexts should remain pinned over suspend,
* allowing us to fixup the user contexts on their first pin.
*/
+ intel_gt_pm_get(i915);
for_each_engine(engine, i915, id) {
struct intel_context *ce;
+ intel_engine_pm_get(engine);
+
ce = engine->kernel_context;
if (ce)
ce->ops->reset(ce);
ce = engine->preempt_context;
if (ce)
ce->ops->reset(ce);
+
+ engine->serial++; /* kernel context lost */
+ err = engine->resume(engine);
+
+ intel_engine_pm_put(engine);
+ if (err) {
+ dev_err(i915->drm.dev,
+ "Failed to restart %s (%d)\n",
+ engine->name, err);
+ break;
+ }
}
+ intel_gt_pm_put(i915);
+
+ return err;
}
void intel_gt_pm_init(struct drm_i915_private *i915);
void intel_gt_sanitize(struct drm_i915_private *i915, bool force);
-void intel_gt_resume(struct drm_i915_private *i915);
+int intel_gt_resume(struct drm_i915_private *i915);
#endif /* INTEL_GT_PM_H */
{
struct intel_context *ce = container_of(kref, typeof(*ce), ref);
+ GEM_BUG_ON(!i915_active_is_idle(&ce->active));
GEM_BUG_ON(intel_context_is_pinned(ce));
if (ce->state)
{
i915_gem_context_unpin_hw_id(ce->gem_context);
i915_gem_object_unpin_map(ce->state->obj);
- intel_ring_unpin(ce->ring);
}
static void
goto unpin_active;
}
- ret = intel_ring_pin(ce->ring);
- if (ret)
- goto unpin_map;
-
ret = i915_gem_context_pin_hw_id(ce->gem_context);
if (ret)
- goto unpin_ring;
+ goto unpin_map;
ce->lrc_desc = lrc_descriptor(ce, engine);
ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
return 0;
-unpin_ring:
- intel_ring_unpin(ce->ring);
unpin_map:
i915_gem_object_unpin_map(ce->state->obj);
unpin_active:
* written to the powercontext is undefined and so we may lose
* GPU state upon resume, i.e. fail to restart after a reset.
*/
- intel_engine_pm_get(engine);
intel_uncore_forcewake_get(engine->uncore, FORCEWAKE_ALL);
engine->reset.prepare(engine);
}
}
}
-static void reset_prepare(struct drm_i915_private *i915)
+static intel_engine_mask_t reset_prepare(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
+ intel_engine_mask_t awake = 0;
enum intel_engine_id id;
- intel_gt_pm_get(i915);
- for_each_engine(engine, i915, id)
+ for_each_engine(engine, i915, id) {
+ if (intel_engine_pm_get_if_awake(engine))
+ awake |= engine->mask;
reset_prepare_engine(engine);
+ }
intel_uc_reset_prepare(i915);
+
+ return awake;
}
static void gt_revoke(struct drm_i915_private *i915)
static void reset_finish_engine(struct intel_engine_cs *engine)
{
engine->reset.finish(engine);
- intel_engine_pm_put(engine);
intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
+
+ intel_engine_signal_breadcrumbs(engine);
}
-static void reset_finish(struct drm_i915_private *i915)
+static void reset_finish(struct drm_i915_private *i915,
+ intel_engine_mask_t awake)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
for_each_engine(engine, i915, id) {
reset_finish_engine(engine);
- intel_engine_signal_breadcrumbs(engine);
+ if (awake & engine->mask)
+ intel_engine_pm_put(engine);
}
- intel_gt_pm_put(i915);
}
static void nop_submit_request(struct i915_request *request)
{
struct i915_gpu_error *error = &i915->gpu_error;
struct intel_engine_cs *engine;
+ intel_engine_mask_t awake;
enum intel_engine_id id;
if (test_bit(I915_WEDGED, &error->flags))
* rolling the global seqno forward (since this would complete requests
* for which we haven't set the fence error to EIO yet).
*/
- reset_prepare(i915);
+ awake = reset_prepare(i915);
/* Even if the GPU reset fails, it should still stop the engines */
if (!INTEL_INFO(i915)->gpu_reset_clobbers_display)
for_each_engine(engine, i915, id)
engine->cancel_requests(engine);
- reset_finish(i915);
+ reset_finish(i915, awake);
GEM_TRACE("end\n");
}
return gt_reset(i915, stalled_mask);
}
+static int resume(struct drm_i915_private *i915)
+{
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ int ret;
+
+ for_each_engine(engine, i915, id) {
+ ret = engine->resume(engine);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
/**
* i915_reset - reset chip after a hang
* @i915: #drm_i915_private to reset
const char *reason)
{
struct i915_gpu_error *error = &i915->gpu_error;
+ intel_engine_mask_t awake;
int ret;
GEM_TRACE("flags=%lx\n", error->flags);
dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason);
error->reset_count++;
- reset_prepare(i915);
+ awake = reset_prepare(i915);
if (!intel_has_gpu_reset(i915)) {
if (i915_modparams.reset)
if (ret) {
DRM_ERROR("Failed to initialise HW following reset (%d)\n",
ret);
- goto error;
+ goto taint;
}
+ ret = resume(i915);
+ if (ret)
+ goto taint;
+
i915_queue_hangcheck(i915);
finish:
- reset_finish(i915);
+ reset_finish(i915, awake);
unlock:
mutex_unlock(&error->wedge_mutex);
return;
GEM_TRACE("%s flags=%lx\n", engine->name, error->flags);
GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
- if (!intel_wakeref_active(&engine->wakeref))
+ if (!intel_engine_pm_get_if_awake(engine))
return 0;
reset_prepare_engine(engine);
* process to program RING_MODE, HWSP and re-enable submission.
*/
ret = engine->resume(engine);
- if (ret)
- goto out;
out:
intel_engine_cancel_stop_cs(engine);
reset_finish_engine(engine);
+ intel_engine_pm_put(engine);
return ret;
}
int intel_ring_pin(struct intel_ring *ring)
{
struct i915_vma *vma = ring->vma;
- enum i915_map_type map = i915_coherent_map_type(vma->vm->i915);
unsigned int flags;
void *addr;
int ret;
- GEM_BUG_ON(ring->vaddr);
+ if (atomic_fetch_inc(&ring->pin_count))
+ return 0;
ret = i915_timeline_pin(ring->timeline);
if (ret)
- return ret;
+ goto err_unpin;
flags = PIN_GLOBAL;
ret = i915_vma_pin(vma, 0, 0, flags);
if (unlikely(ret))
- goto unpin_timeline;
+ goto err_timeline;
if (i915_vma_is_map_and_fenceable(vma))
addr = (void __force *)i915_vma_pin_iomap(vma);
else
- addr = i915_gem_object_pin_map(vma->obj, map);
+ addr = i915_gem_object_pin_map(vma->obj,
+ i915_coherent_map_type(vma->vm->i915));
if (IS_ERR(addr)) {
ret = PTR_ERR(addr);
- goto unpin_ring;
+ goto err_ring;
}
vma->obj->pin_global++;
+ GEM_BUG_ON(ring->vaddr);
ring->vaddr = addr;
+
return 0;
-unpin_ring:
+err_ring:
i915_vma_unpin(vma);
-unpin_timeline:
+err_timeline:
i915_timeline_unpin(ring->timeline);
+err_unpin:
+ atomic_dec(&ring->pin_count);
return ret;
}
void intel_ring_unpin(struct intel_ring *ring)
{
- GEM_BUG_ON(!ring->vma);
- GEM_BUG_ON(!ring->vaddr);
+ if (!atomic_dec_and_test(&ring->pin_count))
+ return;
/* Discard any unused bytes beyond that submitted to hw. */
intel_ring_reset(ring, ring->tail);
+ GEM_BUG_ON(!ring->vma);
if (i915_vma_is_map_and_fenceable(ring->vma))
i915_vma_unpin_iomap(ring->vma);
else
i915_gem_object_unpin_map(ring->vma->obj);
+
+ GEM_BUG_ON(!ring->vaddr);
ring->vaddr = NULL;
ring->vma->obj->pin_global--;
WARN_ON(INTEL_GEN(dev_priv) > 2 &&
(ENGINE_READ(engine, RING_MI_MODE) & MODE_IDLE) == 0);
+ intel_engine_cleanup_common(engine);
+
intel_ring_unpin(engine->buffer);
intel_ring_put(engine->buffer);
- intel_engine_cleanup_common(engine);
kfree(engine);
}
static void cfl_whitelist_build(struct intel_engine_cs *engine)
{
+ struct i915_wa_list *w = &engine->whitelist;
+
if (engine->class != RENDER_CLASS)
return;
- gen9_whitelist_build(&engine->whitelist);
+ gen9_whitelist_build(w);
+
+ /*
+ * WaAllowPMDepthAndInvocationCountAccessFromUMD:cfl,whl,cml,aml
+ *
+ * This covers 4 register which are next to one another :
+ * - PS_INVOCATION_COUNT
+ * - PS_INVOCATION_COUNT_UDW
+ * - PS_DEPTH_COUNT
+ * - PS_DEPTH_COUNT_UDW
+ */
+ whitelist_reg_ext(w, PS_INVOCATION_COUNT,
+ RING_FORCE_TO_NONPRIV_RD |
+ RING_FORCE_TO_NONPRIV_RANGE_4);
}
static void cnl_whitelist_build(struct intel_engine_cs *engine)
/* WaEnableStateCacheRedirectToCS:icl */
whitelist_reg(w, GEN9_SLICE_COMMON_ECO_CHICKEN1);
+
+ /*
+ * WaAllowPMDepthAndInvocationCountAccessFromUMD:icl
+ *
+ * This covers 4 register which are next to one another :
+ * - PS_INVOCATION_COUNT
+ * - PS_INVOCATION_COUNT_UDW
+ * - PS_DEPTH_COUNT
+ * - PS_DEPTH_COUNT_UDW
+ */
+ whitelist_reg_ext(w, PS_INVOCATION_COUNT,
+ RING_FORCE_TO_NONPRIV_RD |
+ RING_FORCE_TO_NONPRIV_RANGE_4);
break;
case VIDEO_DECODE_CLASS:
if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0))
wa_write_or(wal,
GEN7_SARCHKMD,
- GEN7_DISABLE_DEMAND_PREFETCH |
- GEN7_DISABLE_SAMPLER_PREFETCH);
+ GEN7_DISABLE_DEMAND_PREFETCH);
+
+ /* Wa_1606682166:icl */
+ wa_write_or(wal,
+ GEN7_SARCHKMD,
+ GEN7_DISABLE_SAMPLER_PREFETCH);
}
if (IS_GEN_RANGE(i915, 9, 11)) {
ring->base.effective_size = sz;
ring->base.vaddr = (void *)(ring + 1);
ring->base.timeline = &ring->timeline;
+ atomic_set(&ring->base.pin_count, 1);
INIT_LIST_HEAD(&ring->base.request_list);
intel_ring_update_space(&ring->base);
goto unlock;
for (p = igt_atomic_phases; p->name; p++) {
+ intel_engine_mask_t awake;
+
GEM_TRACE("intel_gpu_reset under %s\n", p->name);
+ awake = reset_prepare(i915);
p->critical_section_begin();
reset_prepare(i915);
err = intel_gpu_reset(i915, ALL_ENGINES);
- reset_finish(i915);
p->critical_section_end();
+ reset_finish(i915, awake);
if (err) {
pr_err("intel_gpu_reset failed under %s\n", p->name);
err = 0;
for (i = 0; i < engine->whitelist.count; i++) {
- if (!fn(engine, a[i], b[i], engine->whitelist.list[i].reg))
+ const struct i915_wa *wa = &engine->whitelist.list[i];
+
+ if (i915_mmio_reg_offset(wa->reg) & RING_FORCE_TO_NONPRIV_RD)
+ continue;
+
+ if (!fn(engine, a[i], b[i], wa->reg))
err = -EINVAL;
}
gma_head == gma_tail)
return 0;
- if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) {
- ret = -EINVAL;
- goto out;
- }
-
ret = ip_gma_set(&s, gma_head);
if (ret)
goto out;
s.workload = workload;
s.is_ctx_wa = true;
- if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) {
- ret = -EINVAL;
- goto out;
- }
-
ret = ip_gma_set(&s, gma_head);
if (ret)
goto out;
plane->hw_format = fmt;
plane->base = vgpu_vreg_t(vgpu, DSPSURF(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
+ if (!vgpu_gmadr_is_valid(vgpu, plane->base))
return -EINVAL;
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
alpha_plane, alpha_force);
plane->base = vgpu_vreg_t(vgpu, CURBASE(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
+ if (!vgpu_gmadr_is_valid(vgpu, plane->base))
return -EINVAL;
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
plane->drm_format = drm_format;
plane->base = vgpu_vreg_t(vgpu, SPRSURF(pipe)) & I915_GTT_PAGE_MASK;
- if (!intel_gvt_ggtt_validate_range(vgpu, plane->base, 0))
+ if (!vgpu_gmadr_is_valid(vgpu, plane->base))
return -EINVAL;
plane->base_gpa = intel_vgpu_gma_to_gpa(vgpu->gtt.ggtt_mm, plane->base);
struct intel_vgpu_mm *ggtt_mm = vgpu->gtt.ggtt_mm;
const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
unsigned long index = off >> info->gtt_entry_size_shift;
+ unsigned long gma;
struct intel_gvt_gtt_entry e;
if (bytes != 4 && bytes != 8)
return -EINVAL;
+ gma = index << I915_GTT_PAGE_SHIFT;
+ if (!intel_gvt_ggtt_validate_range(vgpu,
+ gma, 1 << I915_GTT_PAGE_SHIFT)) {
+ gvt_dbg_mm("read invalid ggtt at 0x%lx\n", gma);
+ memset(p_data, 0, bytes);
+ return 0;
+ }
+
ggtt_get_guest_entry(ggtt_mm, &e, index);
memcpy(p_data, (void *)&e.val64 + (off & (info->gtt_entry_size - 1)),
bytes);
entry = __gvt_cache_find_gfn(info->vgpu, gfn);
if (!entry) {
+ ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size);
+ if (ret)
+ goto err_unlock;
+
+ ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size);
+ if (ret)
+ goto err_unmap;
+ } else if (entry->size != size) {
+ /* the same gfn with different size: unmap and re-map */
+ gvt_dma_unmap_page(vgpu, gfn, entry->dma_addr, entry->size);
+ __gvt_cache_remove_entry(vgpu, entry);
+
ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size);
if (ret)
goto err_unlock;
wa_ctx->indirect_ctx.shadow_va = NULL;
}
-static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
- struct i915_gem_context *ctx)
+static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
+ struct i915_gem_context *ctx)
{
struct intel_vgpu_mm *mm = workload->shadow_mm;
struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ctx->vm);
int i = 0;
- if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed)
- return -EINVAL;
-
if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
px_dma(ppgtt->pd) = mm->ppgtt_mm.shadow_pdps[0];
} else {
px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i];
}
}
-
- return 0;
}
static int
static int prepare_workload(struct intel_vgpu_workload *workload)
{
struct intel_vgpu *vgpu = workload->vgpu;
+ struct intel_vgpu_submission *s = &vgpu->submission;
+ int ring = workload->ring_id;
int ret = 0;
ret = intel_vgpu_pin_mm(workload->shadow_mm);
return ret;
}
+ if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT ||
+ !workload->shadow_mm->ppgtt_mm.shadowed) {
+ gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
+ return -EINVAL;
+ }
+
update_shadow_pdps(workload);
+ set_context_ppgtt_from_shadow(workload, s->shadow[ring]->gem_context);
+
ret = intel_vgpu_sync_oos_pages(workload->vgpu);
if (ret) {
gvt_vgpu_err("fail to vgpu sync oos pages\n");
{
struct intel_vgpu *vgpu = workload->vgpu;
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
- struct intel_vgpu_submission *s = &vgpu->submission;
struct i915_request *rq;
int ring_id = workload->ring_id;
int ret;
mutex_lock(&vgpu->vgpu_lock);
mutex_lock(&dev_priv->drm.struct_mutex);
- ret = set_context_ppgtt_from_shadow(workload,
- s->shadow[ring_id]->gem_context);
- if (ret < 0) {
- gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
- goto err_req;
- }
-
ret = intel_gvt_workload_req_alloc(workload);
if (ret)
goto err_req;
int ret;
bool need_force_wake = (INTEL_GEN(gvt->dev_priv) >= 9);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ struct intel_runtime_pm *rpm = &gvt->dev_priv->runtime_pm;
kfree(p);
workload->ring_id, workload,
workload->vgpu->id);
+ intel_runtime_pm_get(rpm);
+
gvt_dbg_sched("ring id %d will dispatch workload %p\n",
workload->ring_id, workload);
intel_uncore_forcewake_put(&gvt->dev_priv->uncore,
FORCEWAKE_ALL);
+ intel_runtime_pm_put_unchecked(rpm);
if (ret && (vgpu_is_vm_unhealthy(ret)))
enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
}
intel_gvt_hypervisor_read_gpa(vgpu, ring_context_gpa +
RING_CTX_OFF(ctx_ctrl.val), &ctx_ctl, 4);
+ if (!intel_gvt_ggtt_validate_range(vgpu, start,
+ _RING_CTL_BUF_SIZE(ctl))) {
+ gvt_vgpu_err("context contain invalid rb at: 0x%x\n", start);
+ return ERR_PTR(-EINVAL);
+ }
+
workload = alloc_workload(vgpu);
if (IS_ERR(workload))
return workload;
workload->wa_ctx.indirect_ctx.size =
(indirect_ctx & INDIRECT_CTX_SIZE_MASK) *
CACHELINE_BYTES;
+
+ if (workload->wa_ctx.indirect_ctx.size != 0) {
+ if (!intel_gvt_ggtt_validate_range(vgpu,
+ workload->wa_ctx.indirect_ctx.guest_gma,
+ workload->wa_ctx.indirect_ctx.size)) {
+ gvt_vgpu_err("invalid wa_ctx at: 0x%lx\n",
+ workload->wa_ctx.indirect_ctx.guest_gma);
+ kmem_cache_free(s->workloads, workload);
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
workload->wa_ctx.per_ctx.guest_gma =
per_ctx & PER_CTX_ADDR_MASK;
workload->wa_ctx.per_ctx.valid = per_ctx & 1;
+ if (workload->wa_ctx.per_ctx.valid) {
+ if (!intel_gvt_ggtt_validate_range(vgpu,
+ workload->wa_ctx.per_ctx.guest_gma,
+ CACHELINE_BYTES)) {
+ gvt_vgpu_err("invalid per_ctx at: 0x%lx\n",
+ workload->wa_ctx.per_ctx.guest_gma);
+ kmem_cache_free(s->workloads, workload);
+ return ERR_PTR(-EINVAL);
+ }
+ }
}
gvt_dbg_el("workload %p ring id %d head %x tail %x start %x ctl %x\n",
*
*/
-#include "trace.h"
-
#ifndef __CHECKER__
#define CREATE_TRACE_POINTS
#include "trace.h"
pci_set_master(pdev);
+ /*
+ * We don't have a max segment size, so set it to the max so sg's
+ * debugging layer doesn't complain
+ */
+ dma_set_max_seg_size(&pdev->dev, UINT_MAX);
+
/* overlay on gen2 is broken and can't address above 1G */
if (IS_GEN(dev_priv, 2)) {
ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(30));
} dram_info;
struct intel_bw_info {
- int num_planes;
- int deratedbw[3];
+ unsigned int deratedbw[3]; /* for each QGV point */
+ u8 num_qgv_points;
+ u8 num_planes;
} max_bw[6];
struct drm_private_obj bw_obj;
#include "gem/i915_gem_ioctls.h"
#include "gem/i915_gem_pm.h"
#include "gem/i915_gemfs.h"
-#include "gt/intel_engine_pm.h"
#include "gt/intel_gt_pm.h"
#include "gt/intel_mocs.h"
#include "gt/intel_reset.h"
intel_mocs_init_l3cc_table(dev_priv);
- /* Only when the HW is re-initialised, can we replay the requests */
- ret = intel_engines_resume(dev_priv);
- if (ret)
- goto cleanup_uc;
-
intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
intel_engines_set_scheduler_caps(dev_priv);
return 0;
-cleanup_uc:
- intel_uc_fini_hw(dev_priv);
out:
intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-
return ret;
}
if (ret)
goto err_uc_init;
+ /* Only when the HW is re-initialised, can we replay the requests */
+ ret = intel_gt_resume(dev_priv);
+ if (ret)
+ goto err_init_hw;
+
/*
* Despite its name intel_init_clock_gating applies both display
* clock gating workarounds; GT mmio workarounds and the occasional
ret = intel_engines_verify_workarounds(dev_priv);
if (ret)
- goto err_init_hw;
+ goto err_gt;
ret = __intel_engines_record_defaults(dev_priv);
if (ret)
- goto err_init_hw;
+ goto err_gt;
if (i915_inject_load_failure()) {
ret = -ENODEV;
- goto err_init_hw;
+ goto err_gt;
}
if (i915_inject_load_failure()) {
ret = -EIO;
- goto err_init_hw;
+ goto err_gt;
}
intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
* HW as irrevisibly wedged, but keep enough state around that the
* driver doesn't explode during runtime.
*/
-err_init_hw:
+err_gt:
mutex_unlock(&dev_priv->drm.struct_mutex);
i915_gem_set_wedged(dev_priv);
i915_gem_drain_workqueue(dev_priv);
mutex_lock(&dev_priv->drm.struct_mutex);
+err_init_hw:
intel_uc_fini_hw(dev_priv);
err_uc_init:
intel_uc_fini(dev_priv);
spin_lock(&pdp->lock);
if (atomic_dec_and_test(&pd->used)) {
gen8_ppgtt_set_pdpe(pdp, vm->scratch_pd, pdpe);
+ pdp->entry[pdpe] = vm->scratch_pd;
GEM_BUG_ON(!atomic_read(&pdp->used));
atomic_dec(&pdp->used);
- free_pd(vm, pd);
+ GEM_BUG_ON(alloc);
+ alloc = pd; /* defer the free to after the lock */
}
spin_unlock(&pdp->lock);
unwind:
spin_lock(&pml4->lock);
if (atomic_dec_and_test(&pdp->used)) {
gen8_ppgtt_set_pml4e(pml4, vm->scratch_pdp, pml4e);
- free_pd(vm, pdp);
+ pml4->entry[pml4e] = vm->scratch_pdp;
+ GEM_BUG_ON(alloc);
+ alloc = pdp; /* defer the free until after the lock */
}
spin_unlock(&pml4->lock);
unwind:
switch (engine->id) {
default:
MISSING_CASE(engine->id);
+ /* fall through */
case RCS0:
mmio = RENDER_HWS_PGA_GEN7;
break;
struct intel_engine_cs *engine = i915->engine[i];
struct drm_i915_error_engine *ee = &error->engine[i];
struct i915_request *request;
+ unsigned long flags;
ee->engine_id = -1;
error_record_engine_registers(error, engine, ee);
error_record_engine_execlists(engine, ee);
+ spin_lock_irqsave(&engine->active.lock, flags);
request = intel_engine_find_active_request(engine);
if (request) {
struct i915_gem_context *ctx = request->gem_context;
- struct intel_ring *ring;
+ struct intel_ring *ring = request->ring;
ee->vm = ctx->vm ?: &ggtt->vm;
ee->rq_post = request->postfix;
ee->rq_tail = request->tail;
- ring = request->ring;
ee->cpu_ring_head = ring->head;
ee->cpu_ring_tail = ring->tail;
ee->ringbuffer =
engine_record_requests(engine, request, ee);
}
+ spin_unlock_irqrestore(&engine->active.lock, flags);
ee->hws_page =
i915_error_object_create(i915,
}
}
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static void delay_after_mux(void)
{
- struct drm_i915_private *dev_priv = stream->dev_priv;
- const struct i915_oa_config *oa_config = stream->oa_config;
-
- /* PRM:
- *
- * OA unit is using “crclk” for its functionality. When trunk
- * level clock gating takes place, OA clock would be gated,
- * unable to count the events from non-render clock domain.
- * Render clock gating must be disabled when OA is enabled to
- * count the events from non-render domain. Unit level clock
- * gating for RCS should also be disabled.
- */
- I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
- ~GEN7_DOP_CLOCK_GATE_ENABLE));
- I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) |
- GEN6_CSUNIT_CLOCK_GATE_DISABLE));
-
- config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len);
-
- /* It apparently takes a fairly long time for a new MUX
+ /*
+ * It apparently takes a fairly long time for a new MUX
* configuration to be be applied after these register writes.
* This delay duration was derived empirically based on the
* render_basic config but hopefully it covers the maximum
* a delay at this location would mitigate any invalid reports.
*/
usleep_range(15000, 20000);
+}
+
+static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+{
+ struct drm_i915_private *dev_priv = stream->dev_priv;
+ const struct i915_oa_config *oa_config = stream->oa_config;
+
+ /*
+ * PRM:
+ *
+ * OA unit is using “crclk” for its functionality. When trunk
+ * level clock gating takes place, OA clock would be gated,
+ * unable to count the events from non-render clock domain.
+ * Render clock gating must be disabled when OA is enabled to
+ * count the events from non-render domain. Unit level clock
+ * gating for RCS should also be disabled.
+ */
+ I915_WRITE(GEN7_MISCCPCTL, (I915_READ(GEN7_MISCCPCTL) &
+ ~GEN7_DOP_CLOCK_GATE_ENABLE));
+ I915_WRITE(GEN6_UCGCTL1, (I915_READ(GEN6_UCGCTL1) |
+ GEN6_CSUNIT_CLOCK_GATE_DISABLE));
+
+ config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len);
+ delay_after_mux();
config_oa_regs(dev_priv, oa_config->b_counter_regs,
oa_config->b_counter_regs_len);
return ret;
config_oa_regs(dev_priv, oa_config->mux_regs, oa_config->mux_regs_len);
+ delay_after_mux();
config_oa_regs(dev_priv, oa_config->b_counter_regs,
oa_config->b_counter_regs_len);
i915_perf_destroy_locked(stream);
mutex_unlock(&dev_priv->perf.lock);
+ /* Release the reference the perf stream kept on the driver. */
+ drm_dev_put(&dev_priv->drm);
+
return 0;
}
if (!(param->flags & I915_PERF_FLAG_DISABLED))
i915_perf_enable_locked(stream);
+ /* Take a reference on the driver that will be kept with stream_fd
+ * until its release.
+ */
+ drm_dev_get(&dev_priv->drm);
+
return stream_fd;
err_open:
dev_priv->perf.oa.ops.enable_metric_set = gen8_enable_metric_set;
dev_priv->perf.oa.ops.disable_metric_set = gen10_disable_metric_set;
- dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128;
- dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de;
-
+ if (IS_GEN(dev_priv, 10)) {
+ dev_priv->perf.oa.ctx_oactxctrl_offset = 0x128;
+ dev_priv->perf.oa.ctx_flexeu0_offset = 0x3de;
+ } else {
+ dev_priv->perf.oa.ctx_oactxctrl_offset = 0x124;
+ dev_priv->perf.oa.ctx_flexeu0_offset = 0x78e;
+ }
dev_priv->perf.oa.gen8_valid_ctx_bit = (1<<16);
}
}
/* watermark/fifo updates */
TRACE_EVENT(intel_pipe_enable,
- TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe),
- TP_ARGS(dev_priv, pipe),
+ TP_PROTO(struct intel_crtc *crtc),
+ TP_ARGS(crtc),
TP_STRUCT__entry(
__array(u32, frame, 3)
__array(u32, scanline, 3)
__field(enum pipe, pipe)
),
-
TP_fast_assign(
- enum pipe _pipe;
- for_each_pipe(dev_priv, _pipe) {
- __entry->frame[_pipe] =
- dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, _pipe);
- __entry->scanline[_pipe] =
- intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, _pipe));
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ struct intel_crtc *it__;
+ for_each_intel_crtc(&dev_priv->drm, it__) {
+ __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__);
+ __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__);
}
- __entry->pipe = pipe;
+ __entry->pipe = crtc->pipe;
),
TP_printk("pipe %c enable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u",
);
TRACE_EVENT(intel_pipe_disable,
- TP_PROTO(struct drm_i915_private *dev_priv, enum pipe pipe),
- TP_ARGS(dev_priv, pipe),
+ TP_PROTO(struct intel_crtc *crtc),
+ TP_ARGS(crtc),
TP_STRUCT__entry(
__array(u32, frame, 3)
),
TP_fast_assign(
- enum pipe _pipe;
- for_each_pipe(dev_priv, _pipe) {
- __entry->frame[_pipe] =
- dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, _pipe);
- __entry->scanline[_pipe] =
- intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, _pipe));
+ struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+ struct intel_crtc *it__;
+ for_each_intel_crtc(&dev_priv->drm, it__) {
+ __entry->frame[it__->pipe] = intel_crtc_get_vblank_counter(it__);
+ __entry->scanline[it__->pipe] = intel_get_crtc_scanline(it__);
}
- __entry->pipe = pipe;
+ __entry->pipe = crtc->pipe;
),
TP_printk("pipe %c disable, pipe A: frame=%u, scanline=%u, pipe B: frame=%u, scanline=%u, pipe C: frame=%u, scanline=%u",
TP_fast_assign(
__entry->pipe = crtc->pipe;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
memcpy(__entry->crcs, crcs, sizeof(__entry->crcs));
),
),
TP_fast_assign(
+ struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
__entry->pipe = pipe;
- __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe);
- __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe));
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
+ __entry->scanline = intel_get_crtc_scanline(crtc);
),
TP_printk("pipe %c, frame=%u, scanline=%u",
TP_fast_assign(
enum pipe pipe = pch_transcoder;
+ struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
__entry->pipe = pipe;
- __entry->frame = dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe);
- __entry->scanline = intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe));
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
+ __entry->scanline = intel_get_crtc_scanline(crtc);
),
TP_printk("pch transcoder %c, frame=%u, scanline=%u",
),
TP_fast_assign(
- enum pipe pipe;
- for_each_pipe(dev_priv, pipe) {
- __entry->frame[pipe] =
- dev_priv->drm.driver->get_vblank_counter(&dev_priv->drm, pipe);
- __entry->scanline[pipe] =
- intel_get_crtc_scanline(intel_get_crtc_for_pipe(dev_priv, pipe));
+ struct intel_crtc *crtc;
+ for_each_intel_crtc(&dev_priv->drm, crtc) {
+ __entry->frame[crtc->pipe] = intel_crtc_get_vblank_counter(crtc);
+ __entry->scanline[crtc->pipe] = intel_get_crtc_scanline(crtc);
}
__entry->old = old;
__entry->new = new;
TP_fast_assign(
__entry->pipe = crtc->pipe;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
__entry->primary = wm->pipe[crtc->pipe].plane[PLANE_PRIMARY];
__entry->sprite = wm->pipe[crtc->pipe].plane[PLANE_SPRITE0];
TP_fast_assign(
__entry->pipe = crtc->pipe;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
__entry->level = wm->level;
__entry->cxsr = wm->cxsr;
TP_fast_assign(
__entry->pipe = crtc->pipe;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
__entry->sprite0_start = sprite0_start;
__entry->sprite1_start = sprite1_start;
TP_fast_assign(
__entry->pipe = crtc->pipe;
__entry->name = plane->name;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
memcpy(__entry->src, &plane->state->src, sizeof(__entry->src));
memcpy(__entry->dst, &plane->state->dst, sizeof(__entry->dst));
TP_fast_assign(
__entry->pipe = crtc->pipe;
__entry->name = plane->name;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
),
TP_fast_assign(
__entry->pipe = crtc->pipe;
- __entry->frame = crtc->base.dev->driver->get_vblank_counter(crtc->base.dev,
- crtc->pipe);
+ __entry->frame = intel_crtc_get_vblank_counter(crtc);
__entry->scanline = intel_get_crtc_scanline(crtc);
__entry->min = crtc->debug.min_vbl;
__entry->max = crtc->debug.max_vbl;
static void vgt_deballoon_space(struct i915_ggtt *ggtt,
struct drm_mm_node *node)
{
+ if (!drm_mm_node_allocated(node))
+ return;
+
DRM_DEBUG_DRIVER("deballoon space: range [0x%llx - 0x%llx] %llu KiB.\n",
node->start,
node->start + node->size,
/*
* Frequence the dpll for the port should run at. Differs from the
- * adjusted dotclock e.g. for DP or 12bpc hdmi mode. This is also
+ * adjusted dotclock e.g. for DP or 10/12bpc hdmi mode. This is also
* already multiplied by pixel_multiplier.
*/
int port_clock;
static void
dump_and_free_wakeref_tracking(struct intel_runtime_pm_debug *debug)
{
- struct drm_printer p;
+ if (debug->count) {
+ struct drm_printer p = drm_debug_printer("i915");
- if (!debug->count)
- return;
-
- p = drm_debug_printer("i915");
- __print_intel_runtime_pm_wakeref(&p, debug);
+ __print_intel_runtime_pm_wakeref(&p, debug);
+ }
kfree(debug->owners);
}
return 0;
}
+/**
+ * intel_wakeref_get_if_in_use: Acquire the wakeref
+ * @wf: the wakeref
+ *
+ * Acquire a hold on the wakeref, but only if the wakeref is already
+ * active.
+ *
+ * Returns: true if the wakeref was acquired, false otherwise.
+ */
+static inline bool
+intel_wakeref_get_if_active(struct intel_wakeref *wf)
+{
+ return atomic_inc_not_zero(&wf->count);
+}
+
/**
* intel_wakeref_put: Release the wakeref
* @i915: the drm_i915_private device
return ret;
}
- if (panel) {
+ if (panel)
bridge = devm_drm_panel_bridge_add(dev, panel,
- DRM_MODE_CONNECTOR_Unknown);
- }
+ DRM_MODE_CONNECTOR_DPI);
priv->dma_hwdesc = dma_alloc_coherent(dev, sizeof(*priv->dma_hwdesc),
&priv->dma_hwdesc_phys,
#include <linux/of_address.h>
#include <linux/of_platform.h>
#include <linux/pm_runtime.h>
+#include <linux/dma-mapping.h>
#include "mtk_drm_crtc.h"
#include "mtk_drm_ddp.h"
struct mtk_drm_private *private = drm->dev_private;
struct platform_device *pdev;
struct device_node *np;
+ struct device *dma_dev;
int ret;
if (!iommu_present(&platform_bus_type))
goto err_component_unbind;
}
- private->dma_dev = &pdev->dev;
+ dma_dev = &pdev->dev;
+ private->dma_dev = dma_dev;
+
+ /*
+ * Configure the DMA segment size to make sure we get contiguous IOVA
+ * when importing PRIME buffers.
+ */
+ if (!dma_dev->dma_parms) {
+ private->dma_parms_allocated = true;
+ dma_dev->dma_parms =
+ devm_kzalloc(drm->dev, sizeof(*dma_dev->dma_parms),
+ GFP_KERNEL);
+ }
+ if (!dma_dev->dma_parms) {
+ ret = -ENOMEM;
+ goto err_component_unbind;
+ }
+
+ ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32));
+ if (ret) {
+ dev_err(dma_dev, "Failed to set DMA segment size\n");
+ goto err_unset_dma_parms;
+ }
/*
* We don't use the drm_irq_install() helpers provided by the DRM
drm->irq_enabled = true;
ret = drm_vblank_init(drm, MAX_CRTC);
if (ret < 0)
- goto err_component_unbind;
+ goto err_unset_dma_parms;
drm_kms_helper_poll_init(drm);
drm_mode_config_reset(drm);
return 0;
+err_unset_dma_parms:
+ if (private->dma_parms_allocated)
+ dma_dev->dma_parms = NULL;
err_component_unbind:
component_unbind_all(drm->dev, drm);
err_config_cleanup:
static void mtk_drm_kms_deinit(struct drm_device *drm)
{
+ struct mtk_drm_private *private = drm->dev_private;
+
drm_kms_helper_poll_fini(drm);
drm_atomic_helper_shutdown(drm);
+ if (private->dma_parms_allocated)
+ private->dma_dev->dma_parms = NULL;
+
component_unbind_all(drm->dev, drm);
drm_mode_config_cleanup(drm);
}
.compat_ioctl = drm_compat_ioctl,
};
+/*
+ * We need to override this because the device used to import the memory is
+ * not dev->dev, as drm_gem_prime_import() expects.
+ */
+struct drm_gem_object *mtk_drm_gem_prime_import(struct drm_device *dev,
+ struct dma_buf *dma_buf)
+{
+ struct mtk_drm_private *private = dev->dev_private;
+
+ return drm_gem_prime_import_dev(dev, dma_buf, private->dma_dev);
+}
+
static struct drm_driver mtk_drm_driver = {
.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME |
DRIVER_ATOMIC,
.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
.gem_prime_export = drm_gem_prime_export,
- .gem_prime_import = drm_gem_prime_import,
+ .gem_prime_import = mtk_drm_gem_prime_import,
.gem_prime_get_sg_table = mtk_gem_prime_get_sg_table,
.gem_prime_import_sg_table = mtk_gem_prime_import_sg_table,
.gem_prime_mmap = mtk_drm_gem_mmap_buf,
comp = devm_kzalloc(dev, sizeof(*comp), GFP_KERNEL);
if (!comp) {
ret = -ENOMEM;
+ of_node_put(node);
goto err_node;
}
ret = mtk_ddp_comp_init(dev, node, comp, comp_id, NULL);
- if (ret)
+ if (ret) {
+ of_node_put(node);
goto err_node;
+ }
private->ddp_comp[comp_id] = comp;
}
} commit;
struct drm_atomic_state *suspend_state;
+
+ bool dma_parms_allocated;
};
extern struct platform_driver mtk_ddp_driver;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
if (priv->lastctx == ctx)
break;
+ /* fall-thru */
case MSM_SUBMIT_CMD_BUF:
/* copy commands into RB: */
obj = submit->bos[submit->cmd[i].idx].obj;
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
if (priv->lastctx == ctx)
break;
+ /* fall-thru */
case MSM_SUBMIT_CMD_BUF:
OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
case MSM_SUBMIT_CMD_CTX_RESTORE_BUF:
if (priv->lastctx == ctx)
break;
+ /* fall-thru */
case MSM_SUBMIT_CMD_BUF:
OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3);
OUT_RING(ring, lower_32_bits(submit->cmd[i].iova));
/* ignore if there has not been a ctx switch: */
if (priv->lastctx == ctx)
break;
+ /* fall-thru */
case MSM_SUBMIT_CMD_BUF:
OUT_PKT3(ring, adreno_is_a430(adreno_gpu) ?
CP_INDIRECT_BUFFER_PFE : CP_INDIRECT_BUFFER_PFD, 2);
if (ret)
goto fail;
- spin_lock_init(&dpu_enc->enc_spinlock);
-
atomic_set(&dpu_enc->frame_done_timeout_ms, 0);
timer_setup(&dpu_enc->frame_done_timer,
dpu_encoder_frame_done_timeout, 0);
drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs);
+ spin_lock_init(&dpu_enc->enc_spinlock);
dpu_enc->enabled = false;
return &dpu_enc->base;
mdp5_crtc->enabled = false;
}
+static void mdp5_crtc_vblank_on(struct drm_crtc *crtc)
+{
+ struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc->state);
+ struct mdp5_interface *intf = mdp5_cstate->pipeline.intf;
+ u32 count;
+
+ count = intf->mode == MDP5_INTF_DSI_MODE_COMMAND ? 0 : 0xffffffff;
+ drm_crtc_set_max_vblank_count(crtc, count);
+
+ drm_crtc_vblank_on(crtc);
+}
+
static void mdp5_crtc_atomic_enable(struct drm_crtc *crtc,
struct drm_crtc_state *old_state)
{
}
/* Restore vblank irq handling after power is enabled */
- drm_crtc_vblank_on(crtc);
+ mdp5_crtc_vblank_on(crtc);
mdp5_crtc_mode_set_nofb(crtc);
mdp5_crtc_destroy_state(crtc, crtc->state);
__drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base);
+
+ drm_crtc_vblank_reset(crtc);
}
static const struct drm_crtc_funcs mdp5_crtc_funcs = {
dev->driver->get_vblank_timestamp = drm_calc_vbltimestamp_from_scanoutpos;
dev->driver->get_scanout_position = mdp5_get_scanoutpos;
dev->driver->get_vblank_counter = mdp5_get_vblank_counter;
- dev->max_vblank_count = 0xffffffff;
+ dev->max_vblank_count = 0; /* max_vblank_count is set on each CRTC */
dev->vblank_disable_immediate = true;
return kms;
msm_submitqueue_init(dev, ctx);
- ctx->aspace = priv->gpu->aspace;
+ ctx->aspace = priv->gpu ? priv->gpu->aspace : NULL;
file->driver_priv = ctx;
return 0;
if (!np)
return 0;
- drm_of_component_match_add(dev, matchptr, compare_of, np);
+ if (of_device_is_available(np))
+ drm_of_component_match_add(dev, matchptr, compare_of, np);
of_node_put(np);
return !msm_obj->vram_node;
}
+/*
+ * Cache sync.. this is a bit over-complicated, to fit dma-mapping
+ * API. Really GPU cache is out of scope here (handled on cmdstream)
+ * and all we need to do is invalidate newly allocated pages before
+ * mapping to CPU as uncached/writecombine.
+ *
+ * On top of this, we have the added headache, that depending on
+ * display generation, the display's iommu may be wired up to either
+ * the toplevel drm device (mdss), or to the mdp sub-node, meaning
+ * that here we either have dma-direct or iommu ops.
+ *
+ * Let this be a cautionary tail of abstraction gone wrong.
+ */
+
+static void sync_for_device(struct msm_gem_object *msm_obj)
+{
+ struct device *dev = msm_obj->base.dev->dev;
+
+ if (get_dma_ops(dev)) {
+ dma_sync_sg_for_device(dev, msm_obj->sgt->sgl,
+ msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ } else {
+ dma_map_sg(dev, msm_obj->sgt->sgl,
+ msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ }
+}
+
+static void sync_for_cpu(struct msm_gem_object *msm_obj)
+{
+ struct device *dev = msm_obj->base.dev->dev;
+
+ if (get_dma_ops(dev)) {
+ dma_sync_sg_for_cpu(dev, msm_obj->sgt->sgl,
+ msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ } else {
+ dma_unmap_sg(dev, msm_obj->sgt->sgl,
+ msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ }
+}
+
/* allocate pages from VRAM carveout, used when no IOMMU: */
static struct page **get_pages_vram(struct drm_gem_object *obj, int npages)
{
* because display controller, GPU, etc. are not coherent:
*/
if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
- dma_map_sg(dev->dev, msm_obj->sgt->sgl,
- msm_obj->sgt->nents, DMA_BIDIRECTIONAL);
+ sync_for_device(msm_obj);
}
return msm_obj->pages;
* GPU, etc. are not coherent:
*/
if (msm_obj->flags & (MSM_BO_WC|MSM_BO_UNCACHED))
- dma_unmap_sg(obj->dev->dev, msm_obj->sgt->sgl,
- msm_obj->sgt->nents,
- DMA_BIDIRECTIONAL);
+ sync_for_cpu(msm_obj);
sg_free_table(msm_obj->sgt);
kfree(msm_obj->sgt);
struct nv50_head_atom *asyh = nv50_head_atom(crtc_state);
int slots;
- /* When restoring duplicated states, we need to make sure that the
- * bw remains the same and avoid recalculating it, as the connector's
- * bpc may have changed after the state was duplicated
- */
- if (!state->duplicated)
- asyh->dp.pbn =
- drm_dp_calc_pbn_mode(crtc_state->adjusted_mode.clock,
- connector->display_info.bpc * 3);
+ if (crtc_state->mode_changed || crtc_state->connectors_changed) {
+ /*
+ * When restoring duplicated states, we need to make sure that
+ * the bw remains the same and avoid recalculating it, as the
+ * connector's bpc may have changed after the state was
+ * duplicated
+ */
+ if (!state->duplicated) {
+ const int bpp = connector->display_info.bpc * 3;
+ const int clock = crtc_state->adjusted_mode.clock;
+
+ asyh->dp.pbn = drm_dp_calc_pbn_mode(clock, bpp);
+ }
- if (drm_atomic_crtc_needs_modeset(crtc_state)) {
slots = drm_dp_atomic_find_vcpi_slots(state, &mstm->mgr,
mstc->port,
asyh->dp.pbn);
fault->inst, fault->addr, fault->access);
}
+static inline bool
+nouveau_range_done(struct hmm_range *range)
+{
+ bool ret = hmm_range_valid(range);
+
+ hmm_range_unregister(range);
+ return ret;
+}
+
+static int
+nouveau_range_fault(struct hmm_mirror *mirror, struct hmm_range *range)
+{
+ long ret;
+
+ range->default_flags = 0;
+ range->pfn_flags_mask = -1UL;
+
+ ret = hmm_range_register(range, mirror,
+ range->start, range->end,
+ PAGE_SHIFT);
+ if (ret) {
+ up_read(&range->vma->vm_mm->mmap_sem);
+ return (int)ret;
+ }
+
+ if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
+ up_read(&range->vma->vm_mm->mmap_sem);
+ return -EAGAIN;
+ }
+
+ ret = hmm_range_fault(range, true);
+ if (ret <= 0) {
+ if (ret == 0)
+ ret = -EBUSY;
+ up_read(&range->vma->vm_mm->mmap_sem);
+ hmm_range_unregister(range);
+ return ret;
+ }
+ return 0;
+}
+
static int
nouveau_svm_fault(struct nvif_notify *notify)
{
range.values = nouveau_svm_pfn_values;
range.pfn_shift = NVIF_VMM_PFNMAP_V0_ADDR_SHIFT;
again:
- ret = hmm_vma_fault(&svmm->mirror, &range, true);
+ ret = nouveau_range_fault(&svmm->mirror, &range);
if (ret == 0) {
mutex_lock(&svmm->mutex);
- if (!hmm_vma_range_done(&range)) {
+ if (!nouveau_range_done(&range)) {
mutex_unlock(&svmm->mutex);
goto again;
}
NULL);
svmm->vmm->vmm.object.client->super = false;
mutex_unlock(&svmm->mutex);
+ up_read(&svmm->mm->mmap_sem);
}
- up_read(&svmm->mm->mmap_sem);
/* Cancel any faults in the window whose pages didn't manage
* to keep their valid bit, or stay writeable when required.
u8 *ptr = msg->buf;
while (remaining) {
- u8 cnt = (remaining > 16) ? 16 : remaining;
- u8 cmd;
+ u8 cnt, retries, cmd;
if (msg->flags & I2C_M_RD)
cmd = 1;
if (mcnt || remaining > 16)
cmd |= 4; /* MOT */
- ret = aux->func->xfer(aux, true, cmd, msg->addr, ptr, &cnt);
- if (ret < 0) {
- nvkm_i2c_aux_release(aux);
- return ret;
+ for (retries = 0, cnt = 0;
+ retries < 32 && !cnt;
+ retries++) {
+ cnt = min_t(u8, remaining, 16);
+ ret = aux->func->xfer(aux, true, cmd,
+ msg->addr, ptr, &cnt);
+ if (ret < 0)
+ goto out;
+ }
+ if (!cnt) {
+ AUX_TRACE(aux, "no data after 32 retries");
+ ret = -EIO;
+ goto out;
}
ptr += cnt;
msg++;
}
+ ret = num;
+out:
nvkm_i2c_aux_release(aux);
- return num;
+ return ret;
}
static u32
MODULE_FIRMWARE("nvidia/gp102/sec2/desc.bin");
MODULE_FIRMWARE("nvidia/gp102/sec2/image.bin");
MODULE_FIRMWARE("nvidia/gp102/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp102/sec2/sig-1.bin");
MODULE_FIRMWARE("nvidia/gp104/acr/bl.bin");
MODULE_FIRMWARE("nvidia/gp104/acr/unload_bl.bin");
MODULE_FIRMWARE("nvidia/gp104/acr/ucode_load.bin");
MODULE_FIRMWARE("nvidia/gp104/sec2/desc.bin");
MODULE_FIRMWARE("nvidia/gp104/sec2/image.bin");
MODULE_FIRMWARE("nvidia/gp104/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp104/sec2/sig-1.bin");
MODULE_FIRMWARE("nvidia/gp106/acr/bl.bin");
MODULE_FIRMWARE("nvidia/gp106/acr/unload_bl.bin");
MODULE_FIRMWARE("nvidia/gp106/acr/ucode_load.bin");
MODULE_FIRMWARE("nvidia/gp106/sec2/desc.bin");
MODULE_FIRMWARE("nvidia/gp106/sec2/image.bin");
MODULE_FIRMWARE("nvidia/gp106/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp106/sec2/sig-1.bin");
MODULE_FIRMWARE("nvidia/gp107/acr/bl.bin");
MODULE_FIRMWARE("nvidia/gp107/acr/unload_bl.bin");
MODULE_FIRMWARE("nvidia/gp107/acr/ucode_load.bin");
MODULE_FIRMWARE("nvidia/gp107/sec2/desc.bin");
MODULE_FIRMWARE("nvidia/gp107/sec2/image.bin");
MODULE_FIRMWARE("nvidia/gp107/sec2/sig.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/desc-1.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/image-1.bin");
+MODULE_FIRMWARE("nvidia/gp107/sec2/sig-1.bin");
* Author: Archit Taneja <archit@ti.com>
*/
+#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/platform_device.h>
{
struct device_node *remote_node;
- remote_node = of_graph_get_remote_node(out->dev->of_node, 0, 0);
+ remote_node = of_graph_get_remote_node(out->dev->of_node,
+ ffs(out->of_ports) - 1, 0);
if (!remote_node) {
dev_dbg(out->dev, "failed to find video sink\n");
return 0;
if (omapdss_is_initialized() == false)
return -EPROBE_DEFER;
- ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+ ret = dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
if (ret) {
dev_err(&pdev->dev, "Failed to set the DMA mask\n");
return ret;
static struct drm_driver qxl_driver;
static struct pci_driver qxl_pci_driver;
+static bool is_vga(struct pci_dev *pdev)
+{
+ return pdev->class == PCI_CLASS_DISPLAY_VGA << 8;
+}
+
static int
qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
{
if (ret)
goto disable_pci;
+ if (is_vga(pdev)) {
+ ret = vga_get_interruptible(pdev, VGA_RSRC_LEGACY_IO);
+ if (ret) {
+ DRM_ERROR("can't get legacy vga ioports\n");
+ goto disable_pci;
+ }
+ }
+
ret = qxl_device_init(qdev, &qxl_driver, pdev);
if (ret)
- goto disable_pci;
+ goto put_vga;
ret = qxl_modeset_init(qdev);
if (ret)
qxl_modeset_fini(qdev);
unload:
qxl_device_fini(qdev);
+put_vga:
+ if (is_vga(pdev))
+ vga_put(pdev, VGA_RSRC_LEGACY_IO);
disable_pci:
pci_disable_device(pdev);
free_dev:
qxl_modeset_fini(qdev);
qxl_device_fini(qdev);
+ if (is_vga(pdev))
+ vga_put(pdev, VGA_RSRC_LEGACY_IO);
dev->dev_private = NULL;
kfree(qdev);
/* Locate the companion LVDS encoder for dual-link operation, if any. */
companion = of_parse_phandle(dev->of_node, "renesas,companion", 0);
- if (!companion) {
- dev_err(dev, "Companion LVDS encoder not found\n");
- return -ENXIO;
- }
+ if (!companion)
+ return 0;
/*
* Sanity check: the companion encoder must have the same compatible
static const struct dev_pm_ops rockchip_dp_pm_ops = {
#ifdef CONFIG_PM_SLEEP
- .suspend = rockchip_dp_suspend,
+ .suspend_late = rockchip_dp_suspend,
.resume_early = rockchip_dp_resume,
#endif
};
rmb(); /* for list_empty to work without lock */
if (list_empty(&entity->list) ||
- spsc_queue_peek(&entity->job_queue) == NULL)
+ spsc_queue_count(&entity->job_queue) == 0)
return true;
return false;
/* Consumption of existing IBs wasn't completed. Forcefully
* remove them here.
*/
- if (spsc_queue_peek(&entity->job_queue)) {
+ if (spsc_queue_count(&entity->job_queue)) {
if (sched) {
/* Park the kernel for a moment to make sure it isn't processing
* our enity.
#define cmdline_test(test) selftest(test, test)
+cmdline_test(drm_cmdline_test_force_d_only)
+cmdline_test(drm_cmdline_test_force_D_only_dvi)
+cmdline_test(drm_cmdline_test_force_D_only_hdmi)
+cmdline_test(drm_cmdline_test_force_D_only_not_digital)
+cmdline_test(drm_cmdline_test_force_e_only)
+cmdline_test(drm_cmdline_test_margin_only)
+cmdline_test(drm_cmdline_test_interlace_only)
cmdline_test(drm_cmdline_test_res)
cmdline_test(drm_cmdline_test_res_missing_x)
cmdline_test(drm_cmdline_test_res_missing_y)
static const struct drm_connector no_connector = {};
+static int drm_cmdline_test_force_e_only(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(!drm_mode_parse_command_line_for_connector("e",
+ &no_connector,
+ &mode));
+ FAIL_ON(mode.specified);
+ FAIL_ON(mode.refresh_specified);
+ FAIL_ON(mode.bpp_specified);
+
+ FAIL_ON(mode.rb);
+ FAIL_ON(mode.cvt);
+ FAIL_ON(mode.interlace);
+ FAIL_ON(mode.margins);
+ FAIL_ON(mode.force != DRM_FORCE_ON);
+
+ return 0;
+}
+
+static int drm_cmdline_test_force_D_only_not_digital(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(!drm_mode_parse_command_line_for_connector("D",
+ &no_connector,
+ &mode));
+ FAIL_ON(mode.specified);
+ FAIL_ON(mode.refresh_specified);
+ FAIL_ON(mode.bpp_specified);
+
+ FAIL_ON(mode.rb);
+ FAIL_ON(mode.cvt);
+ FAIL_ON(mode.interlace);
+ FAIL_ON(mode.margins);
+ FAIL_ON(mode.force != DRM_FORCE_ON);
+
+ return 0;
+}
+
+static const struct drm_connector connector_hdmi = {
+ .connector_type = DRM_MODE_CONNECTOR_HDMIB,
+};
+
+static int drm_cmdline_test_force_D_only_hdmi(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(!drm_mode_parse_command_line_for_connector("D",
+ &connector_hdmi,
+ &mode));
+ FAIL_ON(mode.specified);
+ FAIL_ON(mode.refresh_specified);
+ FAIL_ON(mode.bpp_specified);
+
+ FAIL_ON(mode.rb);
+ FAIL_ON(mode.cvt);
+ FAIL_ON(mode.interlace);
+ FAIL_ON(mode.margins);
+ FAIL_ON(mode.force != DRM_FORCE_ON_DIGITAL);
+
+ return 0;
+}
+
+static const struct drm_connector connector_dvi = {
+ .connector_type = DRM_MODE_CONNECTOR_DVII,
+};
+
+static int drm_cmdline_test_force_D_only_dvi(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(!drm_mode_parse_command_line_for_connector("D",
+ &connector_dvi,
+ &mode));
+ FAIL_ON(mode.specified);
+ FAIL_ON(mode.refresh_specified);
+ FAIL_ON(mode.bpp_specified);
+
+ FAIL_ON(mode.rb);
+ FAIL_ON(mode.cvt);
+ FAIL_ON(mode.interlace);
+ FAIL_ON(mode.margins);
+ FAIL_ON(mode.force != DRM_FORCE_ON_DIGITAL);
+
+ return 0;
+}
+
+static int drm_cmdline_test_force_d_only(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(!drm_mode_parse_command_line_for_connector("d",
+ &no_connector,
+ &mode));
+ FAIL_ON(mode.specified);
+ FAIL_ON(mode.refresh_specified);
+ FAIL_ON(mode.bpp_specified);
+
+ FAIL_ON(mode.rb);
+ FAIL_ON(mode.cvt);
+ FAIL_ON(mode.interlace);
+ FAIL_ON(mode.margins);
+ FAIL_ON(mode.force != DRM_FORCE_OFF);
+
+ return 0;
+}
+
+static int drm_cmdline_test_margin_only(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(drm_mode_parse_command_line_for_connector("m",
+ &no_connector,
+ &mode));
+
+ return 0;
+}
+
+static int drm_cmdline_test_interlace_only(void *ignored)
+{
+ struct drm_cmdline_mode mode = { };
+
+ FAIL_ON(drm_mode_parse_command_line_for_connector("i",
+ &no_connector,
+ &mode));
+
+ return 0;
+}
+
static int drm_cmdline_test_res(void *ignored)
{
struct drm_cmdline_mode mode = { };
/* R and B components are only 5 bits deep */
val |= SUN4I_TCON0_FRM_CTL_MODE_R;
val |= SUN4I_TCON0_FRM_CTL_MODE_B;
+ /* Fall through */
case MEDIA_BUS_FMT_RGB666_1X18:
case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG:
/* Fall through: enable dithering */
ret = sun6i_dsi_dcs_read(dsi, msg);
break;
}
+ /* Else, fall through */
default:
ret = -EINVAL;
"nvidia,hpd-gpio", 0,
GPIOD_IN,
"HDMI hotplug detect");
- if (IS_ERR(output->hpd_gpio))
- return PTR_ERR(output->hpd_gpio);
+ if (IS_ERR(output->hpd_gpio)) {
+ if (PTR_ERR(output->hpd_gpio) != -ENOENT)
+ return PTR_ERR(output->hpd_gpio);
+
+ output->hpd_gpio = NULL;
+ }
if (output->hpd_gpio) {
err = gpiod_to_irq(output->hpd_gpio);
static void __ttm_dma_free_page(struct dma_pool *pool, struct dma_page *d_page)
{
+ unsigned long attrs = 0;
dma_addr_t dma = d_page->dma;
d_page->vaddr &= ~VADDR_FLAG_HUGE_POOL;
- dma_free_coherent(pool->dev, pool->size, (void *)d_page->vaddr, dma);
+ if (pool->type & IS_HUGE)
+ attrs = DMA_ATTR_NO_WARN;
+
+ dma_free_attrs(pool->dev, pool->size, (void *)d_page->vaddr, dma, attrs);
kfree(d_page);
d_page = NULL;
.interruptible = false,
.no_wait_gpu = false
};
+ size_t max_segment;
/* wtf swapping */
if (bo->pages)
if (!bo->pages)
goto out;
- ret = sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0,
- nr_pages << PAGE_SHIFT, GFP_KERNEL);
+ max_segment = virtio_max_dma_size(qdev->vdev);
+ max_segment &= PAGE_MASK;
+ if (max_segment > SCATTERLIST_MAX_SEGMENT)
+ max_segment = SCATTERLIST_MAX_SEGMENT;
+ ret = __sg_alloc_table_from_pages(bo->pages, pages, nr_pages, 0,
+ nr_pages << PAGE_SHIFT,
+ max_segment, GFP_KERNEL);
if (ret)
goto out;
return 0;
!!(HIGH_WORD(ecx) & MESSAGE_STATUS_HB));
if ((HIGH_WORD(ebx) & MESSAGE_STATUS_SUCCESS) == 0) {
kfree(reply);
-
+ reply = NULL;
if ((HIGH_WORD(ebx) & MESSAGE_STATUS_CPT) != 0) {
/* A checkpoint occurred. Retry. */
continue;
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0) {
kfree(reply);
-
+ reply = NULL;
if ((HIGH_WORD(ecx) & MESSAGE_STATUS_CPT) != 0) {
/* A checkpoint occurred. Retry. */
continue;
break;
}
- if (retries == RETRIES)
+ if (!reply)
return -EINVAL;
*msg_len = reply_len;
#define A4_2WHEEL_MOUSE_HACK_7 0x01
#define A4_2WHEEL_MOUSE_HACK_B8 0x02
+#define A4_WHEEL_ORIENTATION (HID_UP_GENDESK | 0x000000b8)
+
struct a4tech_sc {
unsigned long quirks;
unsigned int hw_wheel;
__s32 delayed_value;
};
+static int a4_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+ struct hid_field *field, struct hid_usage *usage,
+ unsigned long **bit, int *max)
+{
+ struct a4tech_sc *a4 = hid_get_drvdata(hdev);
+
+ if (a4->quirks & A4_2WHEEL_MOUSE_HACK_B8 &&
+ usage->hid == A4_WHEEL_ORIENTATION) {
+ /*
+ * We do not want to have this usage mapped to anything as it's
+ * nonstandard and doesn't really behave like an HID report.
+ * It's only selecting the orientation (vertical/horizontal) of
+ * the previous mouse wheel report. The input_events will be
+ * generated once both reports are recorded in a4_event().
+ */
+ return -1;
+ }
+
+ return 0;
+
+}
+
static int a4_input_mapped(struct hid_device *hdev, struct hid_input *hi,
struct hid_field *field, struct hid_usage *usage,
unsigned long **bit, int *max)
struct a4tech_sc *a4 = hid_get_drvdata(hdev);
struct input_dev *input;
- if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput ||
- !usage->type)
+ if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput)
return 0;
input = field->hidinput->input;
return 1;
}
- if (usage->hid == 0x000100b8) {
+ if (usage->hid == A4_WHEEL_ORIENTATION) {
input_event(input, EV_REL, value ? REL_HWHEEL :
REL_WHEEL, a4->delayed_value);
input_event(input, EV_REL, value ? REL_HWHEEL_HI_RES :
static struct hid_driver a4_driver = {
.name = "a4tech",
.id_table = a4_devices,
+ .input_mapping = a4_input_mapping,
.input_mapped = a4_input_mapped,
.event = a4_event,
.probe = a4_probe,
INIT_DELAYED_WORK(&dev->gpio_poll_worker, cp2112_gpio_poll_callback);
- cp2112_gpio_direction_input(gc, d->hwirq);
-
if (!dev->gpio_poll) {
dev->gpio_poll = true;
schedule_delayed_work(&dev->gpio_poll_worker, 0);
return PTR_ERR(dev->desc[pin]);
}
+ ret = cp2112_gpio_direction_input(&dev->gc, pin);
+ if (ret < 0) {
+ dev_err(dev->gc.parent, "Failed to set GPIO to input dir\n");
+ goto err_desc;
+ }
+
ret = gpiochip_lock_as_irq(&dev->gc, pin);
if (ret) {
dev_err(dev->gc.parent, "Failed to lock GPIO as interrupt\n");
/* Locate the boot interface, to receive the LED change events */
struct usb_interface *boot_interface = usb_ifnum_to_if(usb_dev, 0);
+ struct hid_device *boot_hid;
+ struct hid_input *boot_hid_input;
- struct hid_device *boot_hid = usb_get_intfdata(boot_interface);
- struct hid_input *boot_hid_input = list_first_entry(&boot_hid->inputs,
+ if (unlikely(boot_interface == NULL))
+ return -ENODEV;
+
+ boot_hid = usb_get_intfdata(boot_interface);
+ boot_hid_input = list_first_entry(&boot_hid->inputs,
struct hid_input, list);
return boot_hid_input->input->event(boot_hid_input->input, type, code,
#define USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A 0x0b4a
#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE 0x134a
#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A 0x094a
+#define USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641 0x0641
#define USB_VENDOR_ID_HUION 0x256c
#define USB_DEVICE_ID_HUION_TABLET 0x006e
#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER 0xc52f
#define USB_DEVICE_ID_LOGITECH_UNIFYING_RECEIVER_2 0xc532
#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2 0xc534
-#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_GAMING 0xc539
+#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED 0xc539
+#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY 0xc53a
#define USB_DEVICE_ID_SPACETRAVELLER 0xc623
#define USB_DEVICE_ID_SPACENAVIGATOR 0xc626
#define USB_DEVICE_ID_DINOVO_DESKTOP 0xc704
#define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7
#define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa
#define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0
+#define USB_DEVICE_ID_SAITEK_X52 0x075c
#define USB_VENDOR_ID_SAMSUNG 0x0419
#define USB_DEVICE_ID_SAMSUNG_IR_REMOTE 0x0001
HID_REQ_SET_REPORT);
kfree(hidpp_report);
- return retval;
+ return (retval < 0) ? retval : 0;
}
static int logi_dj_recv_query_paired_devices(struct dj_receiver_dev *djrcv_dev)
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2),
.driver_data = recvr_type_hidpp},
- { /* Logitech gaming receiver (0xc539) */
+ { /* Logitech lightspeed receiver (0xc539) */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
- USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_GAMING),
+ USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED),
.driver_data = recvr_type_gaming_hidpp},
{ /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER),
.driver_data = recvr_type_27mhz},
+ { /* Logitech powerplay receiver (0xc53a) */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
+ USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY),
+ .driver_data = recvr_type_gaming_hidpp},
{ /* Logitech 27 MHz HID++ 1.0 receiver (0xc517) */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH,
USB_DEVICE_ID_S510_RECEIVER_2),
{ L27MHZ_DEVICE(HID_ANY_ID) },
- { /* Logitech G403 Gaming Mouse over USB */
+ { /* Logitech G403 Wireless Gaming Mouse over USB */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC082) },
- { /* Logitech G700 Gaming Mouse over USB */
- HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC06B) },
+ { /* Logitech G703 Gaming Mouse over USB */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC087) },
+ { /* Logitech G703 Hero Gaming Mouse over USB */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC090) },
{ /* Logitech G900 Gaming Mouse over USB */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC081) },
+ { /* Logitech G903 Gaming Mouse over USB */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC086) },
+ { /* Logitech G903 Hero Gaming Mouse over USB */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC091) },
{ /* Logitech G920 Wheel over USB */
HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G920_WHEEL),
.driver_data = HIDPP_QUIRK_CLASS_G920 | HIDPP_QUIRK_FORCE_OUTPUT_REPORTS},
+ { /* Logitech G Pro Gaming Mouse over USB */
+ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, 0xC088) },
{ /* MX5000 keyboard over Bluetooth */
HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb305),
{ HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_LOGITECH_OEM_USB_OPTICAL_MOUSE_0B4A), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_094A), HID_QUIRK_ALWAYS_POLL },
+ { HID_USB_DEVICE(USB_VENDOR_ID_HP, USB_PRODUCT_ID_HP_PIXART_OEM_USB_OPTICAL_MOUSE_0641), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_IDEACOM, USB_DEVICE_ID_IDEACOM_IDC6680), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_INNOMEDIA, USB_DEVICE_ID_INNEX_GENESIS_ATARI), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M610X), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
{ HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
{ HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_X52), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE },
{ HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_SENNHEISER, USB_DEVICE_ID_SENNHEISER_BTD500USB), HID_QUIRK_NOGET },
static inline void sony_schedule_work(struct sony_sc *sc,
enum sony_worker which)
{
+ unsigned long flags;
+
switch (which) {
case SONY_WORKER_STATE:
- if (!sc->defer_initialization)
+ spin_lock_irqsave(&sc->lock, flags);
+ if (!sc->defer_initialization && sc->state_worker_initialized)
schedule_work(&sc->state_worker);
+ spin_unlock_irqrestore(&sc->lock, flags);
break;
case SONY_WORKER_HOTPLUG:
if (sc->hotplug_worker_initialized)
static inline void sony_cancel_work_sync(struct sony_sc *sc)
{
+ unsigned long flags;
+
if (sc->hotplug_worker_initialized)
cancel_work_sync(&sc->hotplug_worker);
- if (sc->state_worker_initialized)
+ if (sc->state_worker_initialized) {
+ spin_lock_irqsave(&sc->lock, flags);
+ sc->state_worker_initialized = 0;
+ spin_unlock_irqrestore(&sc->lock, flags);
cancel_work_sync(&sc->state_worker);
+ }
}
-
static int sony_input_configured(struct hid_device *hdev,
struct hid_input *hidinput)
{
#include "hid-ids.h"
+#define THRUSTMASTER_DEVICE_ID_2_IN_1_DT 0xb320
+
static const signed short ff_rumble[] = {
FF_RUMBLE,
-1
struct hid_field *ff_field = tmff->ff_field;
int x, y;
int left, right; /* Rumbling */
+ int motor_swap;
switch (effect->type) {
case FF_CONSTANT:
ff_field->logical_minimum,
ff_field->logical_maximum);
+ /* 2-in-1 strong motor is left */
+ if (hid->product == THRUSTMASTER_DEVICE_ID_2_IN_1_DT) {
+ motor_swap = left;
+ left = right;
+ right = motor_swap;
+ }
+
dbg_hid("(left,right)=(%08x, %08x)\n", left, right);
ff_field->value[0] = left;
ff_field->value[1] = right;
.driver_data = (unsigned long)ff_rumble },
{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb304), /* FireStorm Dual Power 2 (and 3) */
.driver_data = (unsigned long)ff_rumble },
+ { HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, THRUSTMASTER_DEVICE_ID_2_IN_1_DT), /* Dual Trigger 2-in-1 */
+ .driver_data = (unsigned long)ff_rumble },
{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb323), /* Dual Trigger 3-in-1 (PC Mode) */
.driver_data = (unsigned long)ff_rumble },
{ HID_USB_DEVICE(USB_VENDOR_ID_THRUSTMASTER, 0xb324), /* Dual Trigger 3-in-1 (PS3 Mode) */
#define ICL_MOBILE_DEVICE_ID 0x34FC
#define SPT_H_DEVICE_ID 0xA135
#define CML_LP_DEVICE_ID 0x02FC
+#define EHL_Ax_DEVICE_ID 0x4BB3
#define REVISION_ID_CHT_A0 0x6
#define REVISION_ID_CHT_Ax_SI 0x0
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, ICL_MOBILE_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CML_LP_DEVICE_ID)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, EHL_Ax_DEVICE_ID)},
{0, }
};
MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
spin_unlock_irq(&list->hiddev->list_lock);
mutex_lock(&hiddev->existancelock);
+ /*
+ * recheck exist with existance lock held to
+ * avoid opening a disconnected device
+ */
+ if (!list->hiddev->exist) {
+ res = -ENODEV;
+ goto bail_unlock;
+ }
if (!list->hiddev->open++)
if (list->hiddev->exist) {
struct hid_device *hid = hiddev->hid;
hid_hw_power(hid, PM_HINT_NORMAL);
bail_unlock:
mutex_unlock(&hiddev->existancelock);
+
+ spin_lock_irq(&list->hiddev->list_lock);
+ list_del(&list->node);
+ spin_unlock_irq(&list->hiddev->list_lock);
bail:
file->private_data = NULL;
vfree(list);
*/
buttons = (data[4] << 1) | (data[3] & 0x01);
} else if (features->type == CINTIQ_COMPANION_2) {
- /* d-pad right -> data[4] & 0x10
- * d-pad up -> data[4] & 0x20
- * d-pad left -> data[4] & 0x40
- * d-pad down -> data[4] & 0x80
- * d-pad center -> data[3] & 0x01
+ /* d-pad right -> data[2] & 0x10
+ * d-pad up -> data[2] & 0x20
+ * d-pad left -> data[2] & 0x40
+ * d-pad down -> data[2] & 0x80
+ * d-pad center -> data[1] & 0x01
*/
buttons = ((data[2] >> 4) << 7) |
- ((data[1] & 0x04) << 6) |
+ ((data[1] & 0x04) << 4) |
((data[2] & 0x0F) << 2) |
(data[1] & 0x03);
} else if (features->type >= INTUOS5S && features->type <= INTUOSPL) {
y >>= 1;
distance >>= 1;
}
+ if (features->type == INTUOSHT2)
+ distance = features->distance_max - distance;
input_report_abs(input, ABS_X, x);
input_report_abs(input, ABS_Y, y);
input_report_abs(input, ABS_DISTANCE, distance);
input_report_key(input, BTN_BASE2, (data[11] & 0x02));
if (data[12] & 0x80)
- input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f));
+ input_report_abs(input, ABS_WHEEL, (data[12] & 0x7f) - 1);
else
input_report_abs(input, ABS_WHEEL, 0);
}
if (wacom->tool[0]) {
input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5]));
- if (wacom->features.type == INTUOSP2_BT) {
+ if (wacom->features.type == INTUOSP2_BT ||
+ wacom->features.type == INTUOSP2S_BT) {
input_report_abs(pen_input, ABS_DISTANCE,
range ? frame[13] : wacom->features.distance_max);
} else {
static unsigned long virt_to_hvpfn(void *addr)
{
- unsigned long paddr;
+ phys_addr_t paddr;
if (is_vmalloc_addr(addr))
paddr = page_to_phys(vmalloc_to_page(addr)) +
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM hyperv
*/
u64 guestid;
- void *tsc_page;
-
struct hv_per_cpu_context __percpu *cpu_context;
/*
data->sample_time = MSEC_PER_SEC / 2;
break;
case tmp75b: /* not one-shot mode, Conversion rate 37Hz */
- clr_mask |= 1 << 15 | 0x3 << 13;
+ clr_mask |= 1 << 7 | 0x3 << 5;
data->resolution = 12;
data->sample_time = MSEC_PER_SEC / 37;
break;
static const u16 NCT6106_REG_WEIGHT_TEMP_SEL[] = { 0x168, 0x178, 0x188 };
static const u16 NCT6106_REG_WEIGHT_TEMP_STEP[] = { 0x169, 0x179, 0x189 };
static const u16 NCT6106_REG_WEIGHT_TEMP_STEP_TOL[] = { 0x16a, 0x17a, 0x18a };
-static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x17c };
+static const u16 NCT6106_REG_WEIGHT_DUTY_STEP[] = { 0x16b, 0x17b, 0x18b };
static const u16 NCT6106_REG_WEIGHT_TEMP_BASE[] = { 0x16c, 0x17c, 0x18c };
static const u16 NCT6106_REG_WEIGHT_DUTY_BASE[] = { 0x16d, 0x17d, 0x18d };
data->REG_FAN_TIME[0] = NCT6106_REG_FAN_STOP_TIME;
data->REG_FAN_TIME[1] = NCT6106_REG_FAN_STEP_UP_TIME;
data->REG_FAN_TIME[2] = NCT6106_REG_FAN_STEP_DOWN_TIME;
+ data->REG_TOLERANCE_H = NCT6106_REG_TOLERANCE_H;
data->REG_PWM[0] = NCT6106_REG_PWM;
data->REG_PWM[1] = NCT6106_REG_FAN_START_OUTPUT;
data->REG_PWM[2] = NCT6106_REG_FAN_STOP_OUTPUT;
&sensor_dev_attr_in3_alarm.dev_attr.attr,
&sensor_dev_attr_in3_beep.dev_attr.attr,
- &sensor_dev_attr_in4_input.dev_attr.attr, /* 17 */
+ &sensor_dev_attr_in4_input.dev_attr.attr, /* 16 */
&sensor_dev_attr_in4_min.dev_attr.attr,
&sensor_dev_attr_in4_max.dev_attr.attr,
&sensor_dev_attr_in4_alarm.dev_attr.attr,
if (index >= 6 && index < 11 && (reg & 0x03) != 0x03) /* VSEN1 */
return 0;
- if (index >= 11 && index < 17 && (reg & 0x0c) != 0x0c) /* VSEN2 */
+ if (index >= 11 && index < 16 && (reg & 0x0c) != 0x0c) /* VSEN2 */
return 0;
- if (index >= 17 && (reg & 0x30) != 0x30) /* VSEN3 */
+ if (index >= 16 && (reg & 0x30) != 0x30) /* VSEN3 */
return 0;
return attr->mode;
static u64 occ_get_powr_avg(u64 *accum, u32 *samples)
{
- return div64_u64(get_unaligned_be64(accum) * 1000000ULL,
- get_unaligned_be32(samples));
+ u64 divisor = get_unaligned_be32(samples);
+
+ return (divisor == 0) ? 0 :
+ div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor);
}
static ssize_t occ_show_power_2(struct device *dev,
/* See function coresight_get_sink_by_id() to know where this is used */
hash = hashlen_hash(hashlen_string(NULL, name));
+ sysfs_attr_init(&ea->attr.attr);
ea->attr.attr.name = devm_kstrdup(dev, name, GFP_KERNEL);
if (!ea->attr.attr.name)
return -ENOMEM;
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Intel(R) Trace Hub Memory Storage Unit (MSU) data structures
*
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa1a6),
.driver_data = (kernel_ulong_t)0,
},
+ {
+ /* Lewisburg PCH */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa226),
+ .driver_data = (kernel_ulong_t)0,
+ },
{
/* Gemini Lake */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x318e),
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5),
.driver_data = (kernel_ulong_t)&intel_th_2x,
},
+ {
+ /* Tiger Lake PCH */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6),
+ .driver_data = (kernel_ulong_t)&intel_th_2x,
+ },
{ 0 },
};
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Intel(R) Trace Hub PTI output data structures
*
err:
put_device(&src->dev);
- kfree(src);
return err;
}
static struct at91_twi_pdata sama5d2_config = {
.clk_max_div = 7,
- .clk_offset = 4,
+ .clk_offset = 3,
.has_unre_flag = true,
.has_alt_cmd = true,
.has_hold_field = true,
writeb_relaxed(*dev->buf, dev->base + AT91_TWI_THR);
/* send stop when last byte has been written */
- if (--dev->buf_len == 0)
+ if (--dev->buf_len == 0) {
if (!dev->use_alt_cmd)
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
+ at91_twi_write(dev, AT91_TWI_IDR, AT91_TWI_TXRDY);
+ }
dev_dbg(dev->dev, "wrote 0x%x, to go %zu\n", *dev->buf, dev->buf_len);
} else {
at91_twi_write_next_byte(dev);
at91_twi_write(dev, AT91_TWI_IER,
- AT91_TWI_TXCOMP |
- AT91_TWI_NACK |
- AT91_TWI_TXRDY);
+ AT91_TWI_TXCOMP | AT91_TWI_NACK |
+ (dev->buf_len ? AT91_TWI_TXRDY : 0));
}
}
static void bcm_iproc_i2c_read_valid_bytes(struct bcm_iproc_i2c_dev *iproc_i2c)
{
struct i2c_msg *msg = iproc_i2c->msg;
+ uint32_t val;
/* Read valid data from RX FIFO */
while (iproc_i2c->rx_bytes < msg->len) {
- if (!((iproc_i2c_rd_reg(iproc_i2c, M_FIFO_CTRL_OFFSET) >> M_FIFO_RX_CNT_SHIFT)
- & M_FIFO_RX_CNT_MASK))
+ val = iproc_i2c_rd_reg(iproc_i2c, M_RX_OFFSET);
+
+ /* rx fifo empty */
+ if (!((val >> M_RX_STATUS_SHIFT) & M_RX_STATUS_MASK))
break;
msg->buf[iproc_i2c->rx_bytes] =
- (iproc_i2c_rd_reg(iproc_i2c, M_RX_OFFSET) >>
- M_RX_DATA_SHIFT) & M_RX_DATA_MASK;
+ (val >> M_RX_DATA_SHIFT) & M_RX_DATA_MASK;
iproc_i2c->rx_bytes++;
}
}
static uint32_t bcm_iproc_i2c_functionality(struct i2c_adapter *adap)
{
- u32 val = I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+ u32 val;
+
+ /* We do not support the SMBUS Quick command */
+ val = I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
if (adap->algo->reg_slave)
val |= I2C_FUNC_SLAVE;
dev->disable_int(dev);
dev->disable(dev);
+ synchronize_irq(dev->irq);
dev->slave = NULL;
pm_runtime_put(dev->dev);
struct completion msg_done;
struct clk *sclk;
struct i2c_client *slave;
+ int irq;
};
static inline void em_clear_set_bit(struct em_i2c_device *priv, u8 clear, u8 set, u8 reg)
writeb(0, priv->base + I2C_OFS_SVA0);
+ /*
+ * Wait for interrupt to finish. New slave irqs cannot happen because we
+ * cleared the slave address and, thus, only extension codes will be
+ * detected which do not use the slave ptr.
+ */
+ synchronize_irq(priv->irq);
priv->slave = NULL;
return 0;
{
struct em_i2c_device *priv;
struct resource *r;
- int irq, ret;
+ int ret;
priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
if (!priv)
em_i2c_reset(&priv->adap);
- irq = platform_get_irq(pdev, 0);
- ret = devm_request_irq(&pdev->dev, irq, em_i2c_irq_handler, 0,
+ priv->irq = platform_get_irq(pdev, 0);
+ ret = devm_request_irq(&pdev->dev, priv->irq, em_i2c_irq_handler, 0,
"em_i2c", priv);
if (ret)
goto err_clk;
if (ret)
goto err_clk;
- dev_info(&pdev->dev, "Added i2c controller %d, irq %d\n", priv->adap.nr, irq);
+ dev_info(&pdev->dev, "Added i2c controller %d, irq %d\n", priv->adap.nr,
+ priv->irq);
return 0;
int i;
status = acpi_get_object_info(obj_handle, &info);
- if (!ACPI_SUCCESS(status) || !(info->valid & ACPI_VALID_HID))
+ if (ACPI_FAILURE(status))
return AE_OK;
+ if (!(info->valid & ACPI_VALID_HID))
+ goto smo88xx_not_found;
+
hid = info->hardware_id.string;
if (!hid)
- return AE_OK;
+ goto smo88xx_not_found;
i = match_string(acpi_smo8800_ids, ARRAY_SIZE(acpi_smo8800_ids), hid);
if (i < 0)
- return AE_OK;
+ goto smo88xx_not_found;
+
+ kfree(info);
*((bool *)return_value) = true;
return AE_CTRL_TERMINATE;
+
+smo88xx_not_found:
+ kfree(info);
+ return AE_OK;
}
static bool is_dell_system_with_lis3lv02d(void)
}
/* Functions for DMA support */
-static int i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx,
- dma_addr_t phy_addr)
+static void i2c_imx_dma_request(struct imx_i2c_struct *i2c_imx,
+ dma_addr_t phy_addr)
{
struct imx_i2c_dma *dma;
struct dma_slave_config dma_sconfig;
dma = devm_kzalloc(dev, sizeof(*dma), GFP_KERNEL);
if (!dma)
- return -ENOMEM;
+ return;
dma->chan_tx = dma_request_chan(dev, "tx");
if (IS_ERR(dma->chan_tx)) {
dev_info(dev, "using %s (tx) and %s (rx) for DMA transfers\n",
dma_chan_name(dma->chan_tx), dma_chan_name(dma->chan_rx));
- return 0;
+ return;
fail_rx:
dma_release_channel(dma->chan_rx);
dma_release_channel(dma->chan_tx);
fail_al:
devm_kfree(dev, dma);
- /* return successfully if there is no dma support */
- return ret == -ENODEV ? 0 : ret;
}
static void i2c_imx_dma_callback(void *arg)
dev_dbg(&i2c_imx->adapter.dev, "device resources: %pR\n", res);
dev_dbg(&i2c_imx->adapter.dev, "adapter name: \"%s\"\n",
i2c_imx->adapter.name);
+ dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n");
/* Init DMA config if supported */
- ret = i2c_imx_dma_request(i2c_imx, phy_addr);
- if (ret < 0)
- goto del_adapter;
+ i2c_imx_dma_request(i2c_imx, phy_addr);
- dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n");
return 0; /* Return OK */
-del_adapter:
- i2c_del_adapter(&i2c_imx->adapter);
clk_notifier_unregister:
clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb);
rpm_disable:
.max_num_msgs = 255,
};
+static const struct i2c_adapter_quirks mt8183_i2c_quirks = {
+ .flags = I2C_AQ_NO_ZERO_LEN,
+};
+
static const struct mtk_i2c_compatible mt2712_compat = {
.regs = mt_i2c_regs_v1,
.pmic_i2c = 0,
};
static const struct mtk_i2c_compatible mt8183_compat = {
+ .quirks = &mt8183_i2c_quirks,
.regs = mt_i2c_regs_v2,
.pmic_i2c = 0,
.dcm = 0,
static u32 mtk_i2c_functionality(struct i2c_adapter *adap)
{
- return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+ if (adap->quirks->flags & I2C_AQ_NO_ZERO_LEN)
+ return I2C_FUNC_I2C |
+ (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
+ else
+ return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
}
static const struct i2c_algorithm mtk_i2c_algorithm = {
/*
* We need gpu_i2c_suspend() even if it is stub, for runtime pm to work
* correctly. Without it, lspci shows runtime pm status as "D0" for the card.
- * Documentation/power/pci.txt also insists for driver to provide this.
+ * Documentation/power/pci.rst also insists for driver to provide this.
*/
static __maybe_unused int gpu_i2c_suspend(struct device *dev)
{
#define SB800_PIIX4_PORT_IDX_MASK 0x06
#define SB800_PIIX4_PORT_IDX_SHIFT 1
-/* On kerncz, SmBus0Sel is at bit 20:19 of PMx00 DecodeEn */
+/* On kerncz and Hudson2, SmBus0Sel is at bit 20:19 of PMx00 DecodeEn */
#define SB800_PIIX4_PORT_IDX_KERNCZ 0x02
#define SB800_PIIX4_PORT_IDX_MASK_KERNCZ 0x18
#define SB800_PIIX4_PORT_IDX_SHIFT_KERNCZ 3
/* Find which register is used for port selection */
if (PIIX4_dev->vendor == PCI_VENDOR_ID_AMD ||
PIIX4_dev->vendor == PCI_VENDOR_ID_HYGON) {
- switch (PIIX4_dev->device) {
- case PCI_DEVICE_ID_AMD_KERNCZ_SMBUS:
+ if (PIIX4_dev->device == PCI_DEVICE_ID_AMD_KERNCZ_SMBUS ||
+ (PIIX4_dev->device == PCI_DEVICE_ID_AMD_HUDSON2_SMBUS &&
+ PIIX4_dev->revision >= 0x1F)) {
piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_KERNCZ;
piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK_KERNCZ;
piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT_KERNCZ;
- break;
- case PCI_DEVICE_ID_AMD_HUDSON2_SMBUS:
- default:
+ } else {
piix4_port_sel_sb800 = SB800_PIIX4_PORT_IDX_ALT;
piix4_port_mask_sb800 = SB800_PIIX4_PORT_IDX_MASK;
piix4_port_shift_sb800 = SB800_PIIX4_PORT_IDX_SHIFT;
- break;
}
} else {
if (!request_muxed_region(SB800_PIIX4_SMB_IDX, 2,
enum dma_data_direction dma_direction;
struct reset_control *rstc;
+ int irq;
};
#define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent)
WARN_ON(!priv->slave);
+ /* disable irqs and ensure none is running before clearing ptr */
rcar_i2c_write(priv, ICSIER, 0);
rcar_i2c_write(priv, ICSCR, 0);
+ synchronize_irq(priv->irq);
priv->slave = NULL;
pm_runtime_put(rcar_i2c_priv_to_dev(priv));
struct i2c_adapter *adap;
struct device *dev = &pdev->dev;
struct i2c_timings i2c_t;
- int irq, ret;
+ int ret;
/* Otherwise logic will break because some bytes must always use PIO */
BUILD_BUG_ON_MSG(RCAR_MIN_DMA_LEN < 3, "Invalid min DMA length");
pm_runtime_put(dev);
- irq = platform_get_irq(pdev, 0);
- ret = devm_request_irq(dev, irq, rcar_i2c_irq, 0, dev_name(dev), priv);
+ priv->irq = platform_get_irq(pdev, 0);
+ ret = devm_request_irq(dev, priv->irq, rcar_i2c_irq, 0, dev_name(dev), priv);
if (ret < 0) {
- dev_err(dev, "cannot get irq %d\n", irq);
+ dev_err(dev, "cannot get irq %d\n", priv->irq);
goto out_pm_disable;
}
* fall through to the write state, as we will need to
* send a byte as well
*/
+ /* Fall through */
case STATE_WRITE:
/*
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* i2c-stm32.h
*
*/
void i2c_unregister_device(struct i2c_client *client)
{
- if (!client)
+ if (IS_ERR_OR_NULL(client))
return;
if (client->dev.of_node) {
.modified = 1, \
.info_mask_separate = \
BIT(IIO_CHAN_INFO_RAW) | \
- BIT(IIO_CHAN_INFO_SCALE) | \
BIT(IIO_CHAN_INFO_CALIBBIAS), \
.info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SCALE), \
.ext_info = cros_ec_accel_legacy_ext_info, \
#include <linux/iio/iio.h>
#include <linux/io.h>
#include <linux/iopoll.h>
+#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/platform_device.h>
#define JZ_ADC_REG_ADTCH 0x18
#define JZ_ADC_REG_ADBDAT 0x1c
#define JZ_ADC_REG_ADSDAT 0x20
+#define JZ_ADC_REG_ADCLK 0x28
#define JZ_ADC_REG_CFG_BAT_MD BIT(4)
+#define JZ_ADC_REG_ADCLK_CLKDIV_LSB 0
+#define JZ_ADC_REG_ADCLK_CLKDIV10US_LSB 16
#define JZ_ADC_AUX_VREF 3300
#define JZ_ADC_AUX_VREF_BITS 12
#define JZ4740_ADC_BATTERY_HIGH_VREF (7500 * 0.986)
#define JZ4740_ADC_BATTERY_HIGH_VREF_BITS 12
+struct ingenic_adc;
+
struct ingenic_adc_soc_data {
unsigned int battery_high_vref;
unsigned int battery_high_vref_bits;
size_t battery_raw_avail_size;
const int *battery_scale_avail;
size_t battery_scale_avail_size;
+ int (*init_clk_div)(struct device *dev, struct ingenic_adc *adc);
};
struct ingenic_adc {
JZ_ADC_BATTERY_LOW_VREF, JZ_ADC_BATTERY_LOW_VREF_BITS,
};
+static int jz4725b_adc_init_clk_div(struct device *dev, struct ingenic_adc *adc)
+{
+ struct clk *parent_clk;
+ unsigned long parent_rate, rate;
+ unsigned int div_main, div_10us;
+
+ parent_clk = clk_get_parent(adc->clk);
+ if (!parent_clk) {
+ dev_err(dev, "ADC clock has no parent\n");
+ return -ENODEV;
+ }
+ parent_rate = clk_get_rate(parent_clk);
+
+ /*
+ * The JZ4725B ADC works at 500 kHz to 8 MHz.
+ * We pick the highest rate possible.
+ * In practice we typically get 6 MHz, half of the 12 MHz EXT clock.
+ */
+ div_main = DIV_ROUND_UP(parent_rate, 8000000);
+ div_main = clamp(div_main, 1u, 64u);
+ rate = parent_rate / div_main;
+ if (rate < 500000 || rate > 8000000) {
+ dev_err(dev, "No valid divider for ADC main clock\n");
+ return -EINVAL;
+ }
+
+ /* We also need a divider that produces a 10us clock. */
+ div_10us = DIV_ROUND_UP(rate, 100000);
+
+ writel(((div_10us - 1) << JZ_ADC_REG_ADCLK_CLKDIV10US_LSB) |
+ (div_main - 1) << JZ_ADC_REG_ADCLK_CLKDIV_LSB,
+ adc->base + JZ_ADC_REG_ADCLK);
+
+ return 0;
+}
+
static const struct ingenic_adc_soc_data jz4725b_adc_soc_data = {
.battery_high_vref = JZ4725B_ADC_BATTERY_HIGH_VREF,
.battery_high_vref_bits = JZ4725B_ADC_BATTERY_HIGH_VREF_BITS,
.battery_raw_avail_size = ARRAY_SIZE(jz4725b_adc_battery_raw_avail),
.battery_scale_avail = jz4725b_adc_battery_scale_avail,
.battery_scale_avail_size = ARRAY_SIZE(jz4725b_adc_battery_scale_avail),
+ .init_clk_div = jz4725b_adc_init_clk_div,
};
static const struct ingenic_adc_soc_data jz4740_adc_soc_data = {
.battery_raw_avail_size = ARRAY_SIZE(jz4740_adc_battery_raw_avail),
.battery_scale_avail = jz4740_adc_battery_scale_avail,
.battery_scale_avail_size = ARRAY_SIZE(jz4740_adc_battery_scale_avail),
+ .init_clk_div = NULL, /* no ADCLK register on JZ4740 */
};
static int ingenic_adc_read_avail(struct iio_dev *iio_dev,
return ret;
}
+ /* Set clock dividers. */
+ if (soc_data->init_clk_div) {
+ ret = soc_data->init_clk_div(dev, adc);
+ if (ret) {
+ clk_disable_unprepare(adc->clk);
+ return ret;
+ }
+ }
+
/* Put hardware in a known passive state. */
writeb(0x00, adc->base + JZ_ADC_REG_ENABLE);
writeb(0xff, adc->base + JZ_ADC_REG_CTRL);
#define MAX9611_TEMP_MAX_POS 0x7f80
#define MAX9611_TEMP_MAX_NEG 0xff80
#define MAX9611_TEMP_MIN_NEG 0xd980
-#define MAX9611_TEMP_MASK GENMASK(7, 15)
+#define MAX9611_TEMP_MASK GENMASK(15, 7)
#define MAX9611_TEMP_SHIFT 0x07
#define MAX9611_TEMP_RAW(_r) ((_r) >> MAX9611_TEMP_SHIFT)
#define MAX9611_TEMP_SCALE_NUM 1000000
if (ret)
return ret;
- regval = ret & MAX9611_TEMP_MASK;
+ regval &= MAX9611_TEMP_MASK;
if ((regval > MAX9611_TEMP_MAX_POS &&
regval < MAX9611_TEMP_MIN_NEG) ||
dev_err(dev,
"Only %i channels supported with %pOFn, but reg = <%i>.\n",
num_channels, child, reg);
- return ret;
+ return -EINVAL;
}
}
dev_err(dev,
"Channel %i uses different ADC mode than the rest.\n",
reg);
- return ret;
+ return -EINVAL;
}
/* Channel is valid, grab the regulator. */
st->buf[0] = st->integer >> 8;
st->buf[1] = 0x40; /* REG12 default */
st->buf[2] = 0x00;
- st->buf[3] = st->fract2 & 0xFF;
- st->buf[4] = st->fract2 >> 7;
- st->buf[5] = st->fract2 >> 15;
+ st->buf[3] = st->fract1 & 0xFF;
+ st->buf[4] = st->fract1 >> 8;
+ st->buf[5] = st->fract1 >> 16;
st->buf[6] = ADF4371_FRAC2WORD_L(st->fract2 & 0x7F) |
- ADF4371_FRAC1WORD(st->fract1 >> 23);
+ ADF4371_FRAC1WORD(st->fract1 >> 24);
st->buf[7] = ADF4371_FRAC2WORD_H(st->fract2 >> 7);
st->buf[8] = st->mod2 & 0xFF;
st->buf[9] = ADF4371_MOD2WORD(st->mod2 >> 8);
INV_MPU6050_CHAN(IIO_ACCEL, IIO_MOD_Z, INV_MPU6050_SCAN_ACCL_Z),
};
+static const unsigned long inv_mpu_scan_masks[] = {
+ /* 3-axis accel */
+ BIT(INV_MPU6050_SCAN_ACCL_X)
+ | BIT(INV_MPU6050_SCAN_ACCL_Y)
+ | BIT(INV_MPU6050_SCAN_ACCL_Z),
+ /* 3-axis gyro */
+ BIT(INV_MPU6050_SCAN_GYRO_X)
+ | BIT(INV_MPU6050_SCAN_GYRO_Y)
+ | BIT(INV_MPU6050_SCAN_GYRO_Z),
+ /* 6-axis accel + gyro */
+ BIT(INV_MPU6050_SCAN_ACCL_X)
+ | BIT(INV_MPU6050_SCAN_ACCL_Y)
+ | BIT(INV_MPU6050_SCAN_ACCL_Z)
+ | BIT(INV_MPU6050_SCAN_GYRO_X)
+ | BIT(INV_MPU6050_SCAN_GYRO_Y)
+ | BIT(INV_MPU6050_SCAN_GYRO_Z),
+ 0,
+};
+
static const struct iio_chan_spec inv_icm20602_channels[] = {
IIO_CHAN_SOFT_TIMESTAMP(INV_ICM20602_SCAN_TIMESTAMP),
{
INV_MPU6050_CHAN(IIO_ACCEL, IIO_MOD_Z, INV_ICM20602_SCAN_ACCL_Z),
};
+static const unsigned long inv_icm20602_scan_masks[] = {
+ /* 3-axis accel + temp (mandatory) */
+ BIT(INV_ICM20602_SCAN_ACCL_X)
+ | BIT(INV_ICM20602_SCAN_ACCL_Y)
+ | BIT(INV_ICM20602_SCAN_ACCL_Z)
+ | BIT(INV_ICM20602_SCAN_TEMP),
+ /* 3-axis gyro + temp (mandatory) */
+ BIT(INV_ICM20602_SCAN_GYRO_X)
+ | BIT(INV_ICM20602_SCAN_GYRO_Y)
+ | BIT(INV_ICM20602_SCAN_GYRO_Z)
+ | BIT(INV_ICM20602_SCAN_TEMP),
+ /* 6-axis accel + gyro + temp (mandatory) */
+ BIT(INV_ICM20602_SCAN_ACCL_X)
+ | BIT(INV_ICM20602_SCAN_ACCL_Y)
+ | BIT(INV_ICM20602_SCAN_ACCL_Z)
+ | BIT(INV_ICM20602_SCAN_GYRO_X)
+ | BIT(INV_ICM20602_SCAN_GYRO_Y)
+ | BIT(INV_ICM20602_SCAN_GYRO_Z)
+ | BIT(INV_ICM20602_SCAN_TEMP),
+ 0,
+};
+
/*
* The user can choose any frequency between INV_MPU6050_MIN_FIFO_RATE and
* INV_MPU6050_MAX_FIFO_RATE, but only these frequencies are matched by the
if (chip_type == INV_ICM20602) {
indio_dev->channels = inv_icm20602_channels;
indio_dev->num_channels = ARRAY_SIZE(inv_icm20602_channels);
+ indio_dev->available_scan_masks = inv_icm20602_scan_masks;
} else {
indio_dev->channels = inv_mpu_channels;
indio_dev->num_channels = ARRAY_SIZE(inv_mpu_channels);
+ indio_dev->available_scan_masks = inv_mpu_scan_masks;
}
indio_dev->info = &mpu_info;
if (ret)
goto err;
- cma_configfs_init();
+ ret = cma_configfs_init();
+ if (ret)
+ goto err_ib;
return 0;
+err_ib:
+ ib_unregister_client(&cma_client);
err:
unregister_netdevice_notifier(&cma_nb);
ib_sa_unregister_client(&sa_client);
struct ib_udata *udata,
struct ib_uobject *uobj)
{
+ enum ib_qp_type qp_type = attr->qp_type;
struct ib_qp *qp;
+ bool is_xrc;
if (!dev->ops.create_qp)
return ERR_PTR(-EOPNOTSUPP);
* and more importantly they are created internaly by driver,
* see mlx5 create_dev_resources() as an example.
*/
- if (attr->qp_type < IB_QPT_XRC_INI) {
+ is_xrc = qp_type == IB_QPT_XRC_INI || qp_type == IB_QPT_XRC_TGT;
+ if ((qp_type < IB_QPT_MAX && !is_xrc) || qp_type == IB_QPT_DRIVER) {
qp->res.type = RDMA_RESTRACK_QP;
if (uobj)
rdma_restrack_uadd(&qp->res);
int ret;
port_counter = &dev->port_data[port].port_counter;
+ if (!port_counter->hstats)
+ return -EOPNOTSUPP;
+
mutex_lock(&port_counter->lock);
if (on) {
ret = __counter_set_mode(&port_counter->mode,
struct auto_mode_param *param = &counter->mode.param;
bool match = true;
- if (rdma_is_kernel_res(&counter->res) != rdma_is_kernel_res(&qp->res))
+ if (!rdma_is_visible_in_pid_ns(&qp->res))
return false;
- /* Ensure that counter belong to right PID */
- if (!rdma_is_kernel_res(&counter->res) &&
- !rdma_is_kernel_res(&qp->res) &&
- (task_pid_vnr(counter->res.task) != current->pid))
+ /* Ensure that counter belongs to the right PID */
+ if (task_pid_nr(counter->res.task) != task_pid_nr(qp->res.task))
return false;
if (auto_mask & RDMA_COUNTER_MASK_QP_TYPE)
u64 sum;
port_counter = &dev->port_data[port].port_counter;
+ if (!port_counter->hstats)
+ return 0;
+
sum = get_running_counters_hwstat_sum(dev, port, index);
sum += port_counter->hstats->value[index];
return qp;
err:
- rdma_restrack_put(&qp->res);
+ rdma_restrack_put(res);
return NULL;
}
if (!rdma_is_port_valid(dev, port))
return -EINVAL;
+ if (!dev->port_data[port].port_counter.hstats)
+ return -EOPNOTSUPP;
+
qp = rdma_counter_get_qp(dev, qp_num);
if (!qp)
return -ENOENT;
struct rdma_port_counter *port_counter;
u32 port;
- if (!dev->ops.alloc_hw_stats || !dev->port_data)
+ if (!dev->port_data)
return;
rdma_for_each_port(dev, port) {
port_counter->mode.mode = RDMA_COUNTER_MODE_NONE;
mutex_init(&port_counter->lock);
+ if (!dev->ops.alloc_hw_stats)
+ continue;
+
port_counter->hstats = dev->ops.alloc_hw_stats(dev, port);
if (!port_counter->hstats)
goto fail;
struct rdma_port_counter *port_counter;
u32 port;
- if (!dev->ops.alloc_hw_stats)
- return;
-
rdma_for_each_port(dev, port) {
port_counter = &dev->port_data[port].port_counter;
kfree(port_counter->hstats);
static DECLARE_RWSEM(devices_rwsem);
#define DEVICE_REGISTERED XA_MARK_1
-static LIST_HEAD(client_list);
+static u32 highest_client_id;
#define CLIENT_REGISTERED XA_MARK_1
static DEFINE_XARRAY_FLAGS(clients, XA_FLAGS_ALLOC);
static DECLARE_RWSEM(clients_rwsem);
+static void ib_client_put(struct ib_client *client)
+{
+ if (refcount_dec_and_test(&client->uses))
+ complete(&client->uses_zero);
+}
+
/*
* If client_data is registered then the corresponding client must also still
* be registered.
return 0;
down_write(&device->client_data_rwsem);
+ /*
+ * So long as the client is registered hold both the client and device
+ * unregistration locks.
+ */
+ if (!refcount_inc_not_zero(&client->uses))
+ goto out_unlock;
+ refcount_inc(&device->refcount);
+
/*
* Another caller to add_client_context got here first and has already
* completely initialized context.
return 0;
out:
+ ib_device_put(device);
+ ib_client_put(client);
+out_unlock:
up_write(&device->client_data_rwsem);
return ret;
}
client_data = xa_load(&device->client_data, client_id);
xa_clear_mark(&device->client_data, client_id, CLIENT_DATA_REGISTERED);
client = xa_load(&clients, client_id);
- downgrade_write(&device->client_data_rwsem);
+ up_write(&device->client_data_rwsem);
/*
* Notice we cannot be holding any exclusive locks when calling the
*
* For this reason clients and drivers should not call the
* unregistration functions will holdling any locks.
- *
- * It tempting to drop the client_data_rwsem too, but this is required
- * to ensure that unregister_client does not return until all clients
- * are completely unregistered, which is required to avoid module
- * unloading races.
*/
if (client->remove)
client->remove(device, client_data);
xa_erase(&device->client_data, client_id);
- up_read(&device->client_data_rwsem);
+ ib_device_put(device);
+ ib_client_put(client);
}
static int alloc_port_data(struct ib_device *device)
static void disable_device(struct ib_device *device)
{
- struct ib_client *client;
+ u32 cid;
WARN_ON(!refcount_read(&device->refcount));
xa_clear_mark(&devices, device->index, DEVICE_REGISTERED);
up_write(&devices_rwsem);
+ /*
+ * Remove clients in LIFO order, see assign_client_id. This could be
+ * more efficient if xarray learns to reverse iterate. Since no new
+ * clients can be added to this ib_device past this point we only need
+ * the maximum possible client_id value here.
+ */
down_read(&clients_rwsem);
- list_for_each_entry_reverse(client, &client_list, list)
- remove_client_context(device, client->client_id);
+ cid = highest_client_id;
up_read(&clients_rwsem);
+ while (cid) {
+ cid--;
+ remove_client_context(device, cid);
+ }
/* Pairs with refcount_set in enable_device */
ib_device_put(device);
/*
* The add/remove callbacks must be called in FIFO/LIFO order. To
* achieve this we assign client_ids so they are sorted in
- * registration order, and retain a linked list we can reverse iterate
- * to get the LIFO order. The extra linked list can go away if xarray
- * learns to reverse iterate.
+ * registration order.
*/
- if (list_empty(&client_list)) {
- client->client_id = 0;
- } else {
- struct ib_client *last;
-
- last = list_last_entry(&client_list, struct ib_client, list);
- client->client_id = last->client_id + 1;
- }
+ client->client_id = highest_client_id;
ret = xa_insert(&clients, client->client_id, client, GFP_KERNEL);
if (ret)
goto out;
+ highest_client_id++;
xa_set_mark(&clients, client->client_id, CLIENT_REGISTERED);
- list_add_tail(&client->list, &client_list);
out:
up_write(&clients_rwsem);
return ret;
}
+static void remove_client_id(struct ib_client *client)
+{
+ down_write(&clients_rwsem);
+ xa_erase(&clients, client->client_id);
+ for (; highest_client_id; highest_client_id--)
+ if (xa_load(&clients, highest_client_id - 1))
+ break;
+ up_write(&clients_rwsem);
+}
+
/**
* ib_register_client - Register an IB client
* @client:Client to register
unsigned long index;
int ret;
+ refcount_set(&client->uses, 1);
+ init_completion(&client->uses_zero);
ret = assign_client_id(client);
if (ret)
return ret;
unsigned long index;
down_write(&clients_rwsem);
+ ib_client_put(client);
xa_clear_mark(&clients, client->client_id, CLIENT_REGISTERED);
up_write(&clients_rwsem);
- /*
- * Every device still known must be serialized to make sure we are
- * done with the client callbacks before we return.
- */
- down_read(&devices_rwsem);
- xa_for_each (&devices, index, device)
+
+ /* We do not want to have locks while calling client->remove() */
+ rcu_read_lock();
+ xa_for_each (&devices, index, device) {
+ if (!ib_device_try_get(device))
+ continue;
+ rcu_read_unlock();
+
remove_client_context(device, client->client_id);
- up_read(&devices_rwsem);
- down_write(&clients_rwsem);
- list_del(&client->list);
- xa_erase(&clients, client->client_id);
- up_write(&clients_rwsem);
+ ib_device_put(device);
+ rcu_read_lock();
+ }
+ rcu_read_unlock();
+
+ /*
+ * remove_client_context() is not a fence, it can return even though a
+ * removal is ongoing. Wait until all removals are completed.
+ */
+ wait_for_completion(&client->uses_zero);
+ remove_client_id(client);
}
EXPORT_SYMBOL(ib_unregister_client);
if (has_smi)
cq_size *= 2;
+ port_priv->pd = ib_alloc_pd(device, 0);
+ if (IS_ERR(port_priv->pd)) {
+ dev_err(&device->dev, "Couldn't create ib_mad PD\n");
+ ret = PTR_ERR(port_priv->pd);
+ goto error3;
+ }
+
port_priv->cq = ib_alloc_cq(port_priv->device, port_priv, cq_size, 0,
IB_POLL_UNBOUND_WORKQUEUE);
if (IS_ERR(port_priv->cq)) {
dev_err(&device->dev, "Couldn't create ib_mad CQ\n");
ret = PTR_ERR(port_priv->cq);
- goto error3;
- }
-
- port_priv->pd = ib_alloc_pd(device, 0);
- if (IS_ERR(port_priv->pd)) {
- dev_err(&device->dev, "Couldn't create ib_mad PD\n");
- ret = PTR_ERR(port_priv->pd);
goto error4;
}
error7:
destroy_mad_qp(&port_priv->qp_info[0]);
error6:
- ib_dealloc_pd(port_priv->pd);
-error4:
ib_free_cq(port_priv->cq);
cleanup_recv_queue(&port_priv->qp_info[1]);
cleanup_recv_queue(&port_priv->qp_info[0]);
+error4:
+ ib_dealloc_pd(port_priv->pd);
error3:
kfree(port_priv);
destroy_workqueue(port_priv->wq);
destroy_mad_qp(&port_priv->qp_info[1]);
destroy_mad_qp(&port_priv->qp_info[0]);
- ib_dealloc_pd(port_priv->pd);
ib_free_cq(port_priv->cq);
+ ib_dealloc_pd(port_priv->pd);
cleanup_recv_queue(&port_priv->qp_info[1]);
cleanup_recv_queue(&port_priv->qp_info[0]);
/* XXX: Handle deallocation of MAD registration tables */
for (i = 0; i < RDMA_RESTRACK_MAX; i++) {
if (!names[i])
continue;
- curr = rdma_restrack_count(device, i,
- task_active_pid_ns(current));
+ curr = rdma_restrack_count(device, i);
ret = fill_res_info_entry(msg, names[i], curr);
if (ret)
goto err;
if (fill_nldev_handle(msg, device) ||
nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port) ||
- nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode))
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_MODE, mode)) {
+ ret = -EMSGSIZE;
goto err_msg;
+ }
if ((mode == RDMA_COUNTER_MODE_AUTO) &&
- nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask))
+ nla_put_u32(msg, RDMA_NLDEV_ATTR_STAT_AUTO_MODE_MASK, mask)) {
+ ret = -EMSGSIZE;
goto err_msg;
+ }
nlmsg_end(msg, nlh);
ib_device_put(device);
* rdma_restrack_count() - the current usage of specific object
* @dev: IB device
* @type: actual type of object to operate
- * @ns: PID namespace
*/
-int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type,
- struct pid_namespace *ns)
+int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type)
{
struct rdma_restrack_root *rt = &dev->res[type];
struct rdma_restrack_entry *e;
xa_lock(&rt->xa);
xas_for_each(&xas, e, U32_MAX) {
- if (ns == &init_pid_ns ||
- (!rdma_is_kernel_res(e) &&
- ns == task_active_pid_ns(e->task)))
- cnt++;
+ if (!rdma_is_visible_in_pid_ns(e))
+ continue;
+ cnt++;
}
xa_unlock(&rt->xa);
return cnt;
*/
if (rdma_is_kernel_res(res))
return task_active_pid_ns(current) == &init_pid_ns;
- return task_active_pid_ns(current) == task_active_pid_ns(res->task);
+
+ /* PID 0 means that resource is not found in current namespace */
+ return task_pid_vnr(res->task);
}
int ib_umem_page_count(struct ib_umem *umem)
{
- int i;
- int n;
+ int i, n = 0;
struct scatterlist *sg;
- if (umem->is_odp)
- return ib_umem_num_pages(umem);
-
- n = 0;
for_each_sg(umem->sg_head.sgl, sg, umem->nmap, i)
n += sg_dma_len(sg) >> PAGE_SHIFT;
* prevent any further fault handling on this MR.
*/
ib_umem_notifier_start_account(umem_odp);
- umem_odp->dying = 1;
- /* Make sure that the fact the umem is dying is out before we release
- * all pending page faults. */
- smp_wmb();
complete_all(&umem_odp->notifier_completion);
umem_odp->umem.context->invalidate_range(
umem_odp, ib_umem_start(umem_odp), ib_umem_end(umem_odp));
#include <linux/sched.h>
#include <linux/semaphore.h>
#include <linux/slab.h>
+#include <linux/nospec.h>
#include <linux/uaccess.h>
if (get_user(id, arg))
return -EFAULT;
+ if (id >= IB_UMAD_MAX_AGENTS)
+ return -EINVAL;
mutex_lock(&file->port->file_mutex);
mutex_lock(&file->mutex);
- if (id >= IB_UMAD_MAX_AGENTS || !__get_agent(file, id)) {
+ id = array_index_nospec(id, IB_UMAD_MAX_AGENTS);
+ if (!__get_agent(file, id)) {
ret = -EINVAL;
goto out;
}
struct bnxt_re_dev *rdev = to_bnxt_re_dev(attr->device, ibdev);
struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
struct bnxt_qplib_gid *gid_to_del;
+ u16 vlan_id = 0xFFFF;
/* Delete the entry from the hardware */
ctx = *context;
if (sgid_tbl && sgid_tbl->active) {
if (ctx->idx >= sgid_tbl->max)
return -EINVAL;
- gid_to_del = &sgid_tbl->tbl[ctx->idx];
+ gid_to_del = &sgid_tbl->tbl[ctx->idx].gid;
+ vlan_id = sgid_tbl->tbl[ctx->idx].vlan_id;
/* DEL_GID is called in WQ context(netdevice_event_work_handler)
* or via the ib_unregister_device path. In the former case QP1
* may not be destroyed yet, in which case just return as FW
}
ctx->refcnt--;
if (!ctx->refcnt) {
- rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true);
+ rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del,
+ vlan_id, true);
if (rc) {
dev_err(rdev_to_dev(rdev),
"Failed to remove GID: %#x", rc);
spin_unlock_irqrestore(&cmdq->lock, flags);
return -EBUSY;
}
+
+ size = req->cmd_size;
+ /* change the cmd_size to the number of 16byte cmdq unit.
+ * req->cmd_size is modified here
+ */
+ bnxt_qplib_set_cmd_slots(req);
+
memset(resp, 0, sizeof(*resp));
crsqe->resp = (struct creq_qp_event *)resp;
crsqe->resp->cookie = req->cookie;
cmdq_ptr = (struct bnxt_qplib_cmdqe **)cmdq->pbl_ptr;
preq = (u8 *)req;
- size = req->cmd_size * BNXT_QPLIB_CMDQE_UNITS;
do {
/* Locate the next cmdq slot */
sw_prod = HWQ_CMP(cmdq->prod, cmdq);
do { \
memset(&(req), 0, sizeof((req))); \
(req).opcode = CMDQ_BASE_OPCODE_##CMD; \
- (req).cmd_size = (sizeof((req)) + \
- BNXT_QPLIB_CMDQE_UNITS - 1) / \
- BNXT_QPLIB_CMDQE_UNITS; \
+ (req).cmd_size = sizeof((req)); \
(req).flags = cpu_to_le16(cmd_flags); \
} while (0)
BNXT_QPLIB_CMDQE_UNITS);
}
+/* Set the cmd_size to a factor of CMDQE unit */
+static inline void bnxt_qplib_set_cmd_slots(struct cmdq_base *req)
+{
+ req->cmd_size = (req->cmd_size + BNXT_QPLIB_CMDQE_UNITS - 1) /
+ BNXT_QPLIB_CMDQE_UNITS;
+}
+
#define MAX_CMDQ_IDX(depth) ((depth) - 1)
static inline u32 bnxt_qplib_max_cmdq_idx_per_pg(u32 depth)
struct bnxt_qplib_sgid_tbl *sgid_tbl,
u16 max)
{
- sgid_tbl->tbl = kcalloc(max, sizeof(struct bnxt_qplib_gid), GFP_KERNEL);
+ sgid_tbl->tbl = kcalloc(max, sizeof(*sgid_tbl->tbl), GFP_KERNEL);
if (!sgid_tbl->tbl)
return -ENOMEM;
for (i = 0; i < sgid_tbl->max; i++) {
if (memcmp(&sgid_tbl->tbl[i], &bnxt_qplib_gid_zero,
sizeof(bnxt_qplib_gid_zero)))
- bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i], true);
+ bnxt_qplib_del_sgid(sgid_tbl, &sgid_tbl->tbl[i].gid,
+ sgid_tbl->tbl[i].vlan_id, true);
}
- memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
+ memset(sgid_tbl->tbl, 0, sizeof(*sgid_tbl->tbl) * sgid_tbl->max);
memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
memset(sgid_tbl->vlan, 0, sizeof(u8) * sgid_tbl->max);
sgid_tbl->active = 0;
static void bnxt_qplib_init_sgid_tbl(struct bnxt_qplib_sgid_tbl *sgid_tbl,
struct net_device *netdev)
{
- memset(sgid_tbl->tbl, 0, sizeof(struct bnxt_qplib_gid) * sgid_tbl->max);
+ u32 i;
+
+ for (i = 0; i < sgid_tbl->max; i++)
+ sgid_tbl->tbl[i].vlan_id = 0xffff;
+
memset(sgid_tbl->hw_id, -1, sizeof(u16) * sgid_tbl->max);
}
};
struct bnxt_qplib_sgid_tbl {
- struct bnxt_qplib_gid *tbl;
+ struct bnxt_qplib_gid_info *tbl;
u16 *hw_id;
u16 max;
u16 active;
index, sgid_tbl->max);
return -EINVAL;
}
- memcpy(gid, &sgid_tbl->tbl[index], sizeof(*gid));
+ memcpy(gid, &sgid_tbl->tbl[index].gid, sizeof(*gid));
return 0;
}
int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
- struct bnxt_qplib_gid *gid, bool update)
+ struct bnxt_qplib_gid *gid, u16 vlan_id, bool update)
{
struct bnxt_qplib_res *res = to_bnxt_qplib(sgid_tbl,
struct bnxt_qplib_res,
return -ENOMEM;
}
for (index = 0; index < sgid_tbl->max; index++) {
- if (!memcmp(&sgid_tbl->tbl[index], gid, sizeof(*gid)))
+ if (!memcmp(&sgid_tbl->tbl[index].gid, gid, sizeof(*gid)) &&
+ vlan_id == sgid_tbl->tbl[index].vlan_id)
break;
}
if (index == sgid_tbl->max) {
if (rc)
return rc;
}
- memcpy(&sgid_tbl->tbl[index], &bnxt_qplib_gid_zero,
+ memcpy(&sgid_tbl->tbl[index].gid, &bnxt_qplib_gid_zero,
sizeof(bnxt_qplib_gid_zero));
+ sgid_tbl->tbl[index].vlan_id = 0xFFFF;
sgid_tbl->vlan[index] = 0;
sgid_tbl->active--;
dev_dbg(&res->pdev->dev,
}
free_idx = sgid_tbl->max;
for (i = 0; i < sgid_tbl->max; i++) {
- if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid))) {
+ if (!memcmp(&sgid_tbl->tbl[i], gid, sizeof(*gid)) &&
+ sgid_tbl->tbl[i].vlan_id == vlan_id) {
dev_dbg(&res->pdev->dev,
"SGID entry already exist in entry %d!\n", i);
*index = i;
}
/* Add GID to the sgid_tbl */
memcpy(&sgid_tbl->tbl[free_idx], gid, sizeof(*gid));
+ sgid_tbl->tbl[free_idx].vlan_id = vlan_id;
sgid_tbl->active++;
if (vlan_id != 0xFFFF)
sgid_tbl->vlan[free_idx] = 1;
u8 data[16];
};
+struct bnxt_qplib_gid_info {
+ struct bnxt_qplib_gid gid;
+ u16 vlan_id;
+};
+
struct bnxt_qplib_ah {
struct bnxt_qplib_gid dgid;
struct bnxt_qplib_pd *pd;
struct bnxt_qplib_sgid_tbl *sgid_tbl, int index,
struct bnxt_qplib_gid *gid);
int bnxt_qplib_del_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
- struct bnxt_qplib_gid *gid, bool update);
+ struct bnxt_qplib_gid *gid, u16 vlan_id, bool update);
int bnxt_qplib_add_sgid(struct bnxt_qplib_sgid_tbl *sgid_tbl,
struct bnxt_qplib_gid *gid, u8 *mac, u16 vlan_id,
bool update, u32 *index);
clear_rcvctrl(dd, RCV_CTRL_RCV_RSM_ENABLE_SMASK);
}
-static void init_rxe(struct hfi1_devdata *dd)
+static int init_rxe(struct hfi1_devdata *dd)
{
struct rsm_map_table *rmt;
u64 val;
write_csr(dd, RCV_ERR_MASK, ~0ull);
rmt = alloc_rsm_map_table(dd);
+ if (!rmt)
+ return -ENOMEM;
+
/* set up QOS, including the QPN map table */
init_qos(dd, rmt);
init_fecn_handling(dd, rmt);
val |= ((4ull & RCV_BYPASS_HDR_SIZE_MASK) <<
RCV_BYPASS_HDR_SIZE_SHIFT);
write_csr(dd, RCV_BYPASS, val);
+ return 0;
}
static void init_other(struct hfi1_devdata *dd)
goto bail_cleanup;
/* set initial RXE CSRs */
- init_rxe(dd);
+ ret = init_rxe(dd);
+ if (ret)
+ goto bail_cleanup;
+
/* set initial TXE CSRs */
init_txe(dd);
/* set initial non-RXE, non-TXE CSRs */
if (!data)
return -ENOMEM;
copy = min(len, datalen - 1);
- if (copy_from_user(data, buf, copy))
- return -EFAULT;
+ if (copy_from_user(data, buf, copy)) {
+ ret = -EFAULT;
+ goto free_data;
+ }
ret = debugfs_file_get(file->f_path.dentry);
if (unlikely(ret))
- return ret;
+ goto free_data;
ptr = data;
token = ptr;
for (ptr = data; *ptr; ptr = end + 1, token = ptr) {
ret = len;
debugfs_file_put(file->f_path.dentry);
+free_data:
kfree(data);
return ret;
}
return -ENOMEM;
ret = debugfs_file_get(file->f_path.dentry);
if (unlikely(ret))
- return ret;
+ goto free_data;
bit = find_first_bit(fault->opcodes, bitsize);
while (bit < bitsize) {
zero = find_next_zero_bit(fault->opcodes, bitsize, bit);
data[size - 1] = '\n';
data[size] = '\0';
ret = simple_read_from_buffer(buf, len, pos, data, size);
+free_data:
kfree(data);
return ret;
}
cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) <= 0)
break;
trdma_clean_swqe(qp, wqe);
- rvt_qp_wqe_unreserve(qp, wqe);
trace_hfi1_qp_send_completion(qp, wqe, qp->s_last);
rvt_qp_complete_swqe(qp,
wqe,
if (cmp_psn(wqe->lpsn, qp->s_sending_psn) < 0 ||
cmp_psn(qp->s_sending_psn, qp->s_sending_hpsn) > 0) {
trdma_clean_swqe(qp, wqe);
- rvt_qp_wqe_unreserve(qp, wqe);
trace_hfi1_qp_send_completion(qp, wqe, qp->s_last);
rvt_qp_complete_swqe(qp,
wqe,
flows[i].req = req;
flows[i].npagesets = 0;
flows[i].pagesets[0].mapped = 0;
+ flows[i].resync_npkts = 0;
}
req->flows = flows;
return 0;
return NULL;
}
-static struct tid_rdma_flow *
-__find_flow_ranged(struct tid_rdma_request *req, u16 head, u16 tail,
- u32 psn, u16 *fidx)
-{
- for ( ; CIRC_CNT(head, tail, MAX_FLOWS);
- tail = CIRC_NEXT(tail, MAX_FLOWS)) {
- struct tid_rdma_flow *flow = &req->flows[tail];
- u32 spsn, lpsn;
-
- spsn = full_flow_psn(flow, flow->flow_state.spsn);
- lpsn = full_flow_psn(flow, flow->flow_state.lpsn);
-
- if (cmp_psn(psn, spsn) >= 0 && cmp_psn(psn, lpsn) <= 0) {
- if (fidx)
- *fidx = tail;
- return flow;
- }
- }
- return NULL;
-}
-
-static struct tid_rdma_flow *find_flow(struct tid_rdma_request *req,
- u32 psn, u16 *fidx)
-{
- return __find_flow_ranged(req, req->setup_head, req->clear_tail, psn,
- fidx);
-}
-
/* TID RDMA READ functions */
u32 hfi1_build_tid_rdma_read_packet(struct rvt_swqe *wqe,
struct ib_other_headers *ohdr, u32 *bth1,
hfi1_kern_clear_hw_flow(priv->rcd, qp);
}
-static bool tid_rdma_tid_err(struct hfi1_ctxtdata *rcd,
- struct hfi1_packet *packet, u8 rcv_type,
- u8 opcode)
+static bool tid_rdma_tid_err(struct hfi1_packet *packet, u8 rcv_type)
{
struct rvt_qp *qp = packet->qp;
- struct hfi1_qp_priv *qpriv = qp->priv;
- u32 ipsn;
- struct ib_other_headers *ohdr = packet->ohdr;
- struct rvt_ack_entry *e;
- struct tid_rdma_request *req;
- struct rvt_dev_info *rdi = ib_to_rvt(qp->ibqp.device);
- u32 i;
if (rcv_type >= RHF_RCV_TYPE_IB)
goto done;
if (rcv_type == RHF_RCV_TYPE_EAGER) {
hfi1_restart_rc(qp, qp->s_last_psn + 1, 1);
hfi1_schedule_send(qp);
- goto done_unlock;
- }
-
- /*
- * For TID READ response, error out QP after freeing the tid
- * resources.
- */
- if (opcode == TID_OP(READ_RESP)) {
- ipsn = mask_psn(be32_to_cpu(ohdr->u.tid_rdma.r_rsp.verbs_psn));
- if (cmp_psn(ipsn, qp->s_last_psn) > 0 &&
- cmp_psn(ipsn, qp->s_psn) < 0) {
- hfi1_kern_read_tid_flow_free(qp);
- spin_unlock(&qp->s_lock);
- rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
- goto done;
- }
- goto done_unlock;
}
- /*
- * Error out the qp for TID RDMA WRITE
- */
- hfi1_kern_clear_hw_flow(qpriv->rcd, qp);
- for (i = 0; i < rvt_max_atomic(rdi); i++) {
- e = &qp->s_ack_queue[i];
- if (e->opcode == TID_OP(WRITE_REQ)) {
- req = ack_to_tid_req(e);
- hfi1_kern_exp_rcv_clear_all(req);
- }
- }
- spin_unlock(&qp->s_lock);
- rvt_rc_error(qp, IB_WC_LOC_LEN_ERR);
- goto done;
-
-done_unlock:
+ /* Since no payload is delivered, just drop the packet */
spin_unlock(&qp->s_lock);
done:
return true;
u32 fpsn;
lockdep_assert_held(&qp->r_lock);
+ spin_lock(&qp->s_lock);
/* If the psn is out of valid range, drop the packet */
if (cmp_psn(ibpsn, qp->s_last_psn) < 0 ||
cmp_psn(ibpsn, qp->s_psn) > 0)
- return ret;
+ goto s_unlock;
- spin_lock(&qp->s_lock);
/*
* Note that NAKs implicitly ACK outstanding SEND and RDMA write
* requests and implicitly NAK RDMA read and atomic requests issued
wqe = do_rc_completion(qp, wqe, ibp);
if (qp->s_acked == qp->s_tail)
- break;
+ goto s_unlock;
}
+ if (qp->s_acked == qp->s_tail)
+ goto s_unlock;
+
/* Handle the eflags for the request */
if (wqe->wr.opcode != IB_WR_TID_RDMA_READ)
goto s_unlock;
* to prevent continuous Flow Sequence errors for any
* packets that could be still in the fabric.
*/
- flow = find_flow(req, psn, NULL);
- if (!flow) {
- /*
- * We can't find the IB PSN matching the
- * received KDETH PSN. The only thing we can
- * do at this point is report the error to
- * the QP.
- */
- hfi1_kern_read_tid_flow_free(qp);
- spin_unlock(&qp->s_lock);
- rvt_rc_error(qp, IB_WC_LOC_QP_OP_ERR);
- return ret;
- }
+ flow = &req->flows[req->clear_tail];
if (priv->s_flags & HFI1_R_TID_SW_PSN) {
diff = cmp_psn(psn,
flow->flow_state.r_next_psn);
if (lnh == HFI1_LRH_GRH)
goto r_unlock;
- if (tid_rdma_tid_err(rcd, packet, rcv_type, opcode))
+ if (tid_rdma_tid_err(packet, rcv_type))
goto r_unlock;
}
*/
spin_lock(&qp->s_lock);
qpriv = qp->priv;
+ if (qpriv->r_tid_tail == HFI1_QP_WQE_INVALID ||
+ qpriv->r_tid_tail == qpriv->r_tid_head)
+ goto unlock;
e = &qp->s_ack_queue[qpriv->r_tid_tail];
+ if (e->opcode != TID_OP(WRITE_REQ))
+ goto unlock;
req = ack_to_tid_req(e);
+ if (req->comp_seg == req->cur_seg)
+ goto unlock;
flow = &req->flows[req->clear_tail];
trace_hfi1_eflags_err_write(qp, rcv_type, rte, psn);
trace_hfi1_rsp_handle_kdeth_eflags(qp, psn);
struct rvt_swqe *wqe;
struct tid_rdma_request *req;
struct tid_rdma_flow *flow;
- u32 aeth, psn, req_psn, ack_psn, resync_psn, ack_kpsn;
+ u32 aeth, psn, req_psn, ack_psn, flpsn, resync_psn, ack_kpsn;
unsigned long flags;
u16 fidx;
ack_kpsn--;
}
+ if (unlikely(qp->s_acked == qp->s_tail))
+ goto ack_op_err;
+
wqe = rvt_get_swqe_ptr(qp, qp->s_acked);
if (wqe->wr.opcode != IB_WR_TID_RDMA_WRITE)
trace_hfi1_tid_flow_rcv_tid_ack(qp, req->acked_tail, flow);
/* Drop stale ACK/NAK */
- if (cmp_psn(psn, full_flow_psn(flow, flow->flow_state.spsn)) < 0)
+ if (cmp_psn(psn, full_flow_psn(flow, flow->flow_state.spsn)) < 0 ||
+ cmp_psn(req_psn, flow->flow_state.resp_ib_psn) < 0)
goto ack_op_err;
while (cmp_psn(ack_kpsn,
switch ((aeth >> IB_AETH_CREDIT_SHIFT) &
IB_AETH_CREDIT_MASK) {
case 0: /* PSN sequence error */
+ if (!req->flows)
+ break;
flow = &req->flows[req->acked_tail];
+ flpsn = full_flow_psn(flow, flow->flow_state.lpsn);
+ if (cmp_psn(psn, flpsn) > 0)
+ break;
trace_hfi1_tid_flow_rcv_tid_ack(qp, req->acked_tail,
flow);
req->r_ack_psn = mask_psn(be32_to_cpu(ohdr->bth[2]));
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <rdma/opa_addr.h>
+#include <linux/nospec.h>
#include "hfi.h"
#include "common.h"
sl = rdma_ah_get_sl(ah_attr);
if (sl >= ARRAY_SIZE(ibp->sl_to_sc))
return -EINVAL;
+ sl = array_index_nospec(sl, ARRAY_SIZE(ibp->sl_to_sc));
sc5 = ibp->sl_to_sc[sl];
if (sc_to_vlt(dd, sc5) > num_vls && sc_to_vlt(dd, sc5) != 0xf)
# SPDX-License-Identifier: GPL-2.0-only
config INFINIBAND_HNS
- tristate "HNS RoCE Driver"
+ bool "HNS RoCE Driver"
depends on NET_VENDOR_HISILICON
depends on ARM64 || (COMPILE_TEST && 64BIT)
---help---
To compile HIP06 or HIP08 driver as module, choose M here.
config INFINIBAND_HNS_HIP06
- bool "Hisilicon Hip06 Family RoCE support"
+ tristate "Hisilicon Hip06 Family RoCE support"
depends on INFINIBAND_HNS && HNS && HNS_DSAF && HNS_ENET
---help---
RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip06 and
module will be called hns-roce-hw-v1
config INFINIBAND_HNS_HIP08
- bool "Hisilicon Hip08 Family RoCE support"
+ tristate "Hisilicon Hip08 Family RoCE support"
depends on INFINIBAND_HNS && PCI && HNS3
---help---
RoCE driver support for Hisilicon RoCE engine in Hisilicon Hip08 SoC.
hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \
hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o
-ifdef CONFIG_INFINIBAND_HNS_HIP06
hns-roce-hw-v1-objs := hns_roce_hw_v1.o $(hns-roce-objs)
-obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v1.o
-endif
+obj-$(CONFIG_INFINIBAND_HNS_HIP06) += hns-roce-hw-v1.o
-ifdef CONFIG_INFINIBAND_HNS_HIP08
hns-roce-hw-v2-objs := hns_roce_hw_v2.o hns_roce_hw_v2_dfx.o $(hns-roce-objs)
-obj-$(CONFIG_INFINIBAND_HNS) += hns-roce-hw-v2.o
-endif
+obj-$(CONFIG_INFINIBAND_HNS_HIP08) += hns-roce-hw-v2.o
struct ib_udata *udata, unsigned long virt,
struct hns_roce_db *db)
{
+ unsigned long page_addr = virt & PAGE_MASK;
struct hns_roce_user_db_page *page;
+ unsigned int offset;
int ret = 0;
mutex_lock(&context->page_mutex);
list_for_each_entry(page, &context->page_list, list)
- if (page->user_virt == (virt & PAGE_MASK))
+ if (page->user_virt == page_addr)
goto found;
page = kmalloc(sizeof(*page), GFP_KERNEL);
}
refcount_set(&page->refcount, 1);
- page->user_virt = (virt & PAGE_MASK);
- page->umem = ib_umem_get(udata, virt & PAGE_MASK, PAGE_SIZE, 0, 0);
+ page->user_virt = page_addr;
+ page->umem = ib_umem_get(udata, page_addr, PAGE_SIZE, 0, 0);
if (IS_ERR(page->umem)) {
ret = PTR_ERR(page->umem);
kfree(page);
list_add(&page->list, &context->page_list);
found:
- db->dma = sg_dma_address(page->umem->sg_head.sgl) +
- (virt & ~PAGE_MASK);
- page->umem->sg_head.sgl->offset = virt & ~PAGE_MASK;
- db->virt_addr = sg_virt(page->umem->sg_head.sgl);
+ offset = virt - page_addr;
+ db->dma = sg_dma_address(page->umem->sg_head.sgl) + offset;
+ db->virt_addr = sg_virt(page->umem->sg_head.sgl) + offset;
db->u.user_page = page;
refcount_inc(&page->refcount);
atomic_set(&free_mr->mr_free_cq->ib_cq.usecnt, 0);
pd = rdma_zalloc_drv_obj(ibdev, ib_pd);
- if (!pd)
+ if (!pd) {
+ ret = -ENOMEM;
goto alloc_mem_failed;
+ }
pd->device = ibdev;
ret = hns_roce_alloc_pd(pd, NULL);
tx_buf_size, DMA_TO_DEVICE);
kfree(tun_qp->tx_ring[i].buf.addr);
}
- kfree(tun_qp->tx_ring);
- tun_qp->tx_ring = NULL;
i = MLX4_NUM_TUNNEL_BUFS;
err:
while (i > 0) {
rx_buf_size, DMA_FROM_DEVICE);
kfree(tun_qp->ring[i].addr);
}
+ kfree(tun_qp->tx_ring);
+ tun_qp->tx_ring = NULL;
kfree(tun_qp->ring);
tun_qp->ring = NULL;
return -ENOMEM;
event_sub->eventfd =
eventfd_ctx_fdget(redirect_fd);
- if (IS_ERR(event_sub)) {
+ if (IS_ERR(event_sub->eventfd)) {
err = PTR_ERR(event_sub->eventfd);
event_sub->eventfd = NULL;
goto err;
struct devx_async_event_file *ev_file = filp->private_data;
struct devx_event_subscription *event_sub, *event_sub_tmp;
struct devx_async_event_data *entry, *tmp;
+ struct mlx5_ib_dev *dev = ev_file->dev;
- mutex_lock(&ev_file->dev->devx_event_table.event_xa_lock);
+ mutex_lock(&dev->devx_event_table.event_xa_lock);
/* delete the subscriptions which are related to this FD */
list_for_each_entry_safe(event_sub, event_sub_tmp,
&ev_file->subscribed_events_list, file_list) {
- devx_cleanup_subscription(ev_file->dev, event_sub);
+ devx_cleanup_subscription(dev, event_sub);
if (event_sub->eventfd)
eventfd_ctx_put(event_sub->eventfd);
kfree_rcu(event_sub, rcu);
}
- mutex_unlock(&ev_file->dev->devx_event_table.event_xa_lock);
+ mutex_unlock(&dev->devx_event_table.event_xa_lock);
/* free the pending events allocation */
if (!ev_file->omit_data) {
}
uverbs_close_fd(filp);
- put_device(&ev_file->dev->ib_dev.dev);
+ put_device(&dev->ib_dev.dev);
return 0;
}
props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL;
if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
- if (MLX5_CAP_GEN(mdev, pg))
+ if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
props->odp_caps = dev->odp_caps;
}
return;
}
- if (mpi->mdev_events.notifier_call)
- mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
- mpi->mdev_events.notifier_call = NULL;
-
mpi->ibdev = NULL;
spin_unlock(&port->mp.mpi_lock);
+ if (mpi->mdev_events.notifier_call)
+ mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
+ mpi->mdev_events.notifier_call = NULL;
mlx5_remove_netdev_notifier(ibdev, port_num);
spin_lock(&port->mp.mpi_lock);
dev->port[i].roce.last_port_state = IB_PORT_DOWN;
}
+ mlx5_ib_internal_fill_odp_caps(dev);
+
err = mlx5_ib_init_multiport_master(dev);
if (err)
return err;
static int mlx5_ib_stage_odp_init(struct mlx5_ib_dev *dev)
{
- mlx5_ib_internal_fill_odp_caps(dev);
-
return mlx5_ib_odp_init_one(dev);
}
int entry;
if (umem->is_odp) {
- unsigned int page_shift = to_ib_umem_odp(umem)->page_shift;
+ struct ib_umem_odp *odp = to_ib_umem_odp(umem);
+ unsigned int page_shift = odp->page_shift;
- *ncont = ib_umem_page_count(umem);
+ *ncont = ib_umem_odp_num_pages(odp);
*count = *ncont << (page_shift - PAGE_SHIFT);
*shift = page_shift;
if (order)
u64 length;
int access_flags;
u32 mkey;
+ u8 ignore_free_state:1;
};
static inline const struct mlx5_umr_wr *umr_wr(const struct ib_send_wr *wr)
bool dyn_bfreg);
int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
+
+static inline bool mlx5_ib_can_use_umr(struct mlx5_ib_dev *dev,
+ bool do_modify_atomic)
+{
+ if (MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled))
+ return false;
+
+ if (do_modify_atomic &&
+ MLX5_CAP_GEN(dev->mdev, atomic) &&
+ MLX5_CAP_GEN(dev->mdev, umr_modify_atomic_disabled))
+ return false;
+
+ return true;
+}
#endif /* MLX5_IB_H */
static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
static int mr_cache_max_order(struct mlx5_ib_dev *dev);
static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
-static bool umr_can_modify_entity_size(struct mlx5_ib_dev *dev)
-{
- return !MLX5_CAP_GEN(dev->mdev, umr_modify_entity_size_disabled);
-}
static bool umr_can_use_indirect_mkey(struct mlx5_ib_dev *dev)
{
return !MLX5_CAP_GEN(dev->mdev, umr_indirect_mkey_disabled);
}
-static bool use_umr(struct mlx5_ib_dev *dev, int order)
-{
- return order <= mr_cache_max_order(dev) &&
- umr_can_modify_entity_size(dev);
-}
-
static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
{
int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey);
return;
c = order2idx(dev, mr->order);
- if (c < 0 || c >= MAX_MR_CACHE_ENTRIES) {
- mlx5_ib_warn(dev, "order %d, cache index %d\n", mr->order, c);
- return;
- }
+ WARN_ON(c < 0 || c >= MAX_MR_CACHE_ENTRIES);
- if (unreg_umr(dev, mr))
+ if (unreg_umr(dev, mr)) {
+ mr->allocated_from_cache = false;
+ destroy_mkey(dev, mr);
+ ent = &cache->ent[c];
+ if (ent->cur < ent->limit)
+ queue_work(cache->wq, &ent->work);
return;
+ }
ent = &cache->ent[c];
spin_lock_irq(&ent->lock);
{
struct mlx5_ib_dev *dev = to_mdev(pd->device);
struct mlx5_ib_mr *mr = NULL;
- bool populate_mtts = false;
+ bool use_umr;
struct ib_umem *umem;
int page_shift;
int npages;
if (err < 0)
return ERR_PTR(err);
- if (use_umr(dev, order)) {
+ use_umr = mlx5_ib_can_use_umr(dev, true);
+
+ if (order <= mr_cache_max_order(dev) && use_umr) {
mr = alloc_mr_from_cache(pd, umem, virt_addr, length, ncont,
page_shift, order, access_flags);
if (PTR_ERR(mr) == -EAGAIN) {
mlx5_ib_dbg(dev, "cache empty for order %d\n", order);
mr = NULL;
}
- populate_mtts = false;
} else if (!MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) {
if (access_flags & IB_ACCESS_ON_DEMAND) {
err = -EINVAL;
pr_err("Got MR registration for ODP MR > 512MB, not supported for Connect-IB\n");
goto error;
}
- populate_mtts = true;
+ use_umr = false;
}
if (!mr) {
- if (!umr_can_modify_entity_size(dev))
- populate_mtts = true;
mutex_lock(&dev->slow_path_mutex);
mr = reg_create(NULL, pd, virt_addr, length, umem, ncont,
- page_shift, access_flags, populate_mtts);
+ page_shift, access_flags, !use_umr);
mutex_unlock(&dev->slow_path_mutex);
}
update_odp_mr(mr);
- if (!populate_mtts) {
+ if (use_umr) {
int update_xlt_flags = MLX5_IB_UPD_XLT_ENABLE;
if (access_flags & IB_ACCESS_ON_DEMAND)
return 0;
umrwr.wr.send_flags = MLX5_IB_SEND_UMR_DISABLE_MR |
- MLX5_IB_SEND_UMR_FAIL_IF_FREE;
+ MLX5_IB_SEND_UMR_UPDATE_PD_ACCESS;
umrwr.wr.opcode = MLX5_IB_WR_UMR;
+ umrwr.pd = dev->umrc.pd;
umrwr.mkey = mr->mmkey.key;
+ umrwr.ignore_free_state = 1;
return mlx5_ib_post_send_wait(dev, &umrwr);
}
goto err;
}
- if (flags & IB_MR_REREG_TRANS && !use_umr_mtt_update(mr, addr, len)) {
+ if (!mlx5_ib_can_use_umr(dev, true) ||
+ (flags & IB_MR_REREG_TRANS && !use_umr_mtt_update(mr, addr, len))) {
/*
* UMR can't be used - MKey needs to be replaced.
*/
mr->sig = NULL;
}
- mlx5_free_priv_descs(mr);
-
- if (!allocated_from_cache)
+ if (!allocated_from_cache) {
destroy_mkey(dev, mr);
+ mlx5_free_priv_descs(mr);
+ }
}
static void dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
* overwrite the same MTTs. Concurent invalidations might race us,
* but they will write 0s as well, so no difference in the end result.
*/
-
+ mutex_lock(&umem_odp->umem_mutex);
for (addr = start; addr < end; addr += BIT(umem_odp->page_shift)) {
idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift;
/*
idx - blk_start_idx + 1, 0,
MLX5_IB_UPD_XLT_ZAP |
MLX5_IB_UPD_XLT_ATOMIC);
+ mutex_unlock(&umem_odp->umem_mutex);
/*
* We are now sure that the device will not access the
* memory. We can safely unmap it, and mark it as dirty if
memset(caps, 0, sizeof(*caps));
- if (!MLX5_CAP_GEN(dev->mdev, pg))
+ if (!MLX5_CAP_GEN(dev->mdev, pg) ||
+ !mlx5_ib_can_use_umr(dev, true))
return;
caps->general_caps = IB_ODP_SUPPORT;
if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) &&
MLX5_CAP_GEN(dev->mdev, null_mkey) &&
- MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset))
+ MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset) &&
+ !MLX5_CAP_GEN(dev->mdev, umr_indirect_mkey_disabled))
caps->general_caps |= IB_ODP_SUPPORT_IMPLICIT;
return;
u32 flags)
{
int npages = 0, current_seq, page_shift, ret, np;
- bool implicit = false;
struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem);
bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH;
if (IS_ERR(odp))
return PTR_ERR(odp);
mr = odp->private;
- implicit = true;
} else {
odp = odp_mr;
}
out:
if (ret == -EAGAIN) {
- if (implicit || !odp->dying) {
- unsigned long timeout =
- msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT);
-
- if (!wait_for_completion_timeout(
- &odp->notifier_completion,
- timeout)) {
- mlx5_ib_warn(dev, "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
- current_seq, odp->notifiers_seq, odp->notifiers_count);
- }
- } else {
- /* The MR is being killed, kill the QP as well. */
- ret = -EFAULT;
+ unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT);
+
+ if (!wait_for_completion_timeout(&odp->notifier_completion,
+ timeout)) {
+ mlx5_ib_warn(
+ dev,
+ "timeout waiting for mmu notifier. seq %d against %d. notifiers_count=%d\n",
+ current_seq, odp->notifiers_seq,
+ odp->notifiers_count);
}
}
{
int ret = 0;
- if (dev->odp_caps.general_caps & IB_ODP_SUPPORT)
- ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_odp_ops);
+ if (!(dev->odp_caps.general_caps & IB_ODP_SUPPORT))
+ return ret;
+
+ ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_odp_ops);
if (dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT) {
ret = mlx5_cmd_null_mkey(dev->mdev, &dev->null_mkey);
}
}
- if (!MLX5_CAP_GEN(dev->mdev, pg))
- return ret;
-
ret = mlx5_ib_create_pf_eq(dev, &dev->odp_pf_eq);
return ret;
void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *dev)
{
- if (!MLX5_CAP_GEN(dev->mdev, pg))
+ if (!(dev->odp_caps.general_caps & IB_ODP_SUPPORT))
return;
mlx5_ib_destroy_pf_eq(dev, &dev->odp_pf_eq);
num_pending_prefetch_dec(to_mdev(w->pd->device), w->sg_list,
w->num_sge, 0);
- kfree(w);
+ kvfree(w);
}
int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd,
if (valid_req)
queue_work(system_unbound_wq, &work->work);
else
- kfree(work);
+ kvfree(work);
srcu_read_unlock(&dev->mr_srcu, srcu_key);
}
MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_TOEPLITZ);
- MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
memcpy(rss_key, ucmd.rx_hash_key, len);
break;
}
MLX5_IB_UMR_OCTOWORD;
}
-static __be64 frwr_mkey_mask(void)
+static __be64 frwr_mkey_mask(bool atomic)
{
u64 result;
MLX5_MKEY_MASK_LW |
MLX5_MKEY_MASK_RR |
MLX5_MKEY_MASK_RW |
- MLX5_MKEY_MASK_A |
MLX5_MKEY_MASK_SMALL_FENCE |
MLX5_MKEY_MASK_FREE;
+ if (atomic)
+ result |= MLX5_MKEY_MASK_A;
+
return cpu_to_be64(result);
}
}
static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
- struct mlx5_ib_mr *mr, u8 flags)
+ struct mlx5_ib_mr *mr, u8 flags, bool atomic)
{
int size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
umr->flags = flags;
umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size));
- umr->mkey_mask = frwr_mkey_mask();
+ umr->mkey_mask = frwr_mkey_mask(atomic);
}
static void set_linv_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr)
memset(umr, 0, sizeof(*umr));
- if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE)
- umr->flags = MLX5_UMR_CHECK_FREE; /* fail if free */
- else
- umr->flags = MLX5_UMR_CHECK_NOT_FREE; /* fail if not free */
+ if (!umrwr->ignore_free_state) {
+ if (wr->send_flags & MLX5_IB_SEND_UMR_FAIL_IF_FREE)
+ /* fail if free */
+ umr->flags = MLX5_UMR_CHECK_FREE;
+ else
+ /* fail if not free */
+ umr->flags = MLX5_UMR_CHECK_NOT_FREE;
+ }
umr->xlt_octowords = cpu_to_be16(get_xlt_octo(umrwr->xlt_size));
if (wr->send_flags & MLX5_IB_SEND_UMR_UPDATE_XLT) {
{
struct mlx5_ib_mr *mr = to_mmr(wr->mr);
struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
+ struct mlx5_ib_dev *dev = to_mdev(pd->ibpd.device);
int mr_list_size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
bool umr_inline = mr_list_size <= MLX5_IB_SQ_UMR_INLINE_THRESHOLD;
+ bool atomic = wr->access & IB_ACCESS_REMOTE_ATOMIC;
u8 flags = 0;
+ if (!mlx5_ib_can_use_umr(dev, atomic)) {
+ mlx5_ib_warn(to_mdev(qp->ibqp.device),
+ "Fast update of %s for MR is disabled\n",
+ (MLX5_CAP_GEN(dev->mdev,
+ umr_modify_entity_size_disabled)) ?
+ "entity size" :
+ "atomic access");
+ return -EINVAL;
+ }
+
if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) {
mlx5_ib_warn(to_mdev(qp->ibqp.device),
"Invalid IB_SEND_INLINE send flag\n");
if (umr_inline)
flags |= MLX5_UMR_INLINE;
- set_reg_umr_seg(*seg, mr, flags);
+ set_reg_umr_seg(*seg, mr, flags, atomic);
*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
handle_post_send_edge(&qp->sq, seg, *size, cur_edge);
struct qedr_dev *dev =
rdma_device_to_drv_device(device, struct qedr_dev, ibdev);
- return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->pdev->vendor);
+ return scnprintf(buf, PAGE_SIZE, "0x%x\n", dev->attr.hw_ver);
}
static DEVICE_ATTR_RO(hw_rev);
static ssize_t hca_type_show(struct device *device,
struct device_attribute *attr, char *buf)
{
- return scnprintf(buf, PAGE_SIZE, "%s\n", "HCA_TYPE_TO_SET");
+ struct qedr_dev *dev =
+ rdma_device_to_drv_device(device, struct qedr_dev, ibdev);
+
+ return scnprintf(buf, PAGE_SIZE, "FastLinQ QL%x %s\n",
+ dev->pdev->device,
+ rdma_protocol_iwarp(&dev->ibdev, 1) ?
+ "iWARP" : "RoCE");
}
static DEVICE_ATTR_RO(hca_type);
config RDMA_SIW
tristate "Software RDMA over TCP/IP (iWARP) driver"
- depends on INET && INFINIBAND && LIBCRC32C && 64BIT
+ depends on INET && INFINIBAND && LIBCRC32C
select DMA_VIRT_OPS
help
This driver implements the iWARP RDMA transport over
};
struct siw_pble {
- u64 addr; /* Address of assigned user buffer */
- u64 size; /* Size of this entry */
- u64 pbl_off; /* Total offset from start of PBL */
+ dma_addr_t addr; /* Address of assigned buffer */
+ unsigned int size; /* Size of this entry */
+ unsigned long pbl_off; /* Total offset from start of PBL */
};
struct siw_pbl {
struct siw_cq {
struct ib_cq base_cq;
spinlock_t lock;
- u64 *notify;
+ struct siw_cq_ctrl *notify;
struct siw_cqe *queue;
u32 cq_put;
u32 cq_get;
"MEM[0x%08x] %s: " fmt, mem->stag, __func__, ##__VA_ARGS__)
#define siw_dbg_cep(cep, fmt, ...) \
- ibdev_dbg(&cep->sdev->base_dev, "CEP[0x%p] %s: " fmt, \
+ ibdev_dbg(&cep->sdev->base_dev, "CEP[0x%pK] %s: " fmt, \
cep, __func__, ##__VA_ARGS__)
void siw_cq_flush(struct siw_cq *cq);
static void siw_cep_set_inuse(struct siw_cep *cep)
{
unsigned long flags;
- int rv;
retry:
spin_lock_irqsave(&cep->lock, flags);
if (cep->in_use) {
spin_unlock_irqrestore(&cep->lock, flags);
- rv = wait_event_interruptible(cep->waitq, !cep->in_use);
+ wait_event_interruptible(cep->waitq, !cep->in_use);
if (signal_pending(current))
flush_signals(current);
goto retry;
getname_local(cep->sock, &event.local_addr);
getname_peer(cep->sock, &event.remote_addr);
}
- siw_dbg_cep(cep, "[QP %u]: id 0x%p, reason=%d, status=%d\n",
- cep->qp ? qp_id(cep->qp) : -1, id, reason, status);
+ siw_dbg_cep(cep, "[QP %u]: reason=%d, status=%d\n",
+ cep->qp ? qp_id(cep->qp) : UINT_MAX, reason, status);
return id->event_handler(id, &event);
}
siw_cep_get(new_cep);
new_s->sk->sk_user_data = new_cep;
- siw_dbg_cep(cep, "listen socket 0x%p, new 0x%p\n", s, new_s);
-
if (siw_tcp_nagle == false) {
int val = 1;
cep = work->cep;
siw_dbg_cep(cep, "[QP %u]: work type: %d, state %d\n",
- cep->qp ? qp_id(cep->qp) : -1, work->type, cep->state);
+ cep->qp ? qp_id(cep->qp) : UINT_MAX,
+ work->type, cep->state);
siw_cep_set_inuse(cep);
}
if (release_cep) {
siw_dbg_cep(cep,
- "release: timer=%s, QP[%u], id 0x%p\n",
+ "release: timer=%s, QP[%u]\n",
cep->mpa_timer ? "y" : "n",
- cep->qp ? qp_id(cep->qp) : -1, cep->cm_id);
+ cep->qp ? qp_id(cep->qp) : UINT_MAX);
siw_cancel_mpatimer(cep);
else
delay = MPAREP_TIMEOUT;
}
- siw_dbg_cep(cep, "[QP %u]: work type: %d, work 0x%p, timeout %lu\n",
- cep->qp ? qp_id(cep->qp) : -1, type, work, delay);
+ siw_dbg_cep(cep, "[QP %u]: work type: %d, timeout %lu\n",
+ cep->qp ? qp_id(cep->qp) : -1, type, delay);
queue_delayed_work(siw_cm_wq, &work->work, delay);
}
if (v4)
siw_dbg_qp(qp,
- "id 0x%p, pd_len %d, laddr %pI4 %d, raddr %pI4 %d\n",
- id, pd_len,
+ "pd_len %d, laddr %pI4 %d, raddr %pI4 %d\n",
+ pd_len,
&((struct sockaddr_in *)(laddr))->sin_addr,
ntohs(((struct sockaddr_in *)(laddr))->sin_port),
&((struct sockaddr_in *)(raddr))->sin_addr,
ntohs(((struct sockaddr_in *)(raddr))->sin_port));
else
siw_dbg_qp(qp,
- "id 0x%p, pd_len %d, laddr %pI6 %d, raddr %pI6 %d\n",
- id, pd_len,
+ "pd_len %d, laddr %pI6 %d, raddr %pI6 %d\n",
+ pd_len,
&((struct sockaddr_in6 *)(laddr))->sin6_addr,
ntohs(((struct sockaddr_in6 *)(laddr))->sin6_port),
&((struct sockaddr_in6 *)(raddr))->sin6_addr,
if (rv >= 0) {
rv = siw_cm_queue_work(cep, SIW_CM_WORK_MPATIMEOUT);
if (!rv) {
- siw_dbg_cep(cep, "id 0x%p, [QP %u]: exit\n", id,
- qp_id(qp));
+ siw_dbg_cep(cep, "[QP %u]: exit\n", qp_id(qp));
siw_cep_set_free(cep);
return 0;
}
}
error:
- siw_dbg_qp(qp, "failed: %d\n", rv);
+ siw_dbg(id->device, "failed: %d\n", rv);
if (cep) {
siw_socket_disassoc(s);
} else if (s) {
sock_release(s);
}
- siw_qp_put(qp);
+ if (qp)
+ siw_qp_put(qp);
return rv;
}
siw_cancel_mpatimer(cep);
if (cep->state != SIW_EPSTATE_RECVD_MPAREQ) {
- siw_dbg_cep(cep, "id 0x%p: out of state\n", id);
+ siw_dbg_cep(cep, "out of state\n");
siw_cep_set_free(cep);
siw_cep_put(cep);
up_write(&qp->state_lock);
goto error;
}
- siw_dbg_cep(cep, "id 0x%p\n", id);
+ siw_dbg_cep(cep, "[QP %d]\n", params->qpn);
if (try_gso && cep->mpa.hdr.params.bits & MPA_RR_FLAG_GSO_EXP) {
siw_dbg_cep(cep, "peer allows GSO on TX\n");
params->ird > sdev->attrs.max_ird) {
siw_dbg_cep(
cep,
- "id 0x%p, [QP %u]: ord %d (max %d), ird %d (max %d)\n",
- id, qp_id(qp), params->ord, sdev->attrs.max_ord,
+ "[QP %u]: ord %d (max %d), ird %d (max %d)\n",
+ qp_id(qp), params->ord, sdev->attrs.max_ord,
params->ird, sdev->attrs.max_ird);
rv = -EINVAL;
up_write(&qp->state_lock);
if (params->private_data_len > max_priv_data) {
siw_dbg_cep(
cep,
- "id 0x%p, [QP %u]: private data length: %d (max %d)\n",
- id, qp_id(qp), params->private_data_len, max_priv_data);
+ "[QP %u]: private data length: %d (max %d)\n",
+ qp_id(qp), params->private_data_len, max_priv_data);
rv = -EINVAL;
up_write(&qp->state_lock);
goto error;
qp_attrs.flags = SIW_MPA_CRC;
qp_attrs.state = SIW_QP_STATE_RTS;
- siw_dbg_cep(cep, "id 0x%p, [QP%u]: moving to rts\n", id, qp_id(qp));
+ siw_dbg_cep(cep, "[QP%u]: moving to rts\n", qp_id(qp));
/* Associate QP with CEP */
siw_cep_get(cep);
if (rv)
goto error;
- siw_dbg_cep(cep, "id 0x%p, [QP %u]: send mpa reply, %d byte pdata\n",
- id, qp_id(qp), params->private_data_len);
+ siw_dbg_cep(cep, "[QP %u]: send mpa reply, %d byte pdata\n",
+ qp_id(qp), params->private_data_len);
rv = siw_send_mpareqrep(cep, params->private_data,
params->private_data_len);
siw_cancel_mpatimer(cep);
if (cep->state != SIW_EPSTATE_RECVD_MPAREQ) {
- siw_dbg_cep(cep, "id 0x%p: out of state\n", id);
+ siw_dbg_cep(cep, "out of state\n");
siw_cep_set_free(cep);
siw_cep_put(cep); /* put last reference */
return -ECONNRESET;
}
- siw_dbg_cep(cep, "id 0x%p, cep->state %d, pd_len %d\n", id, cep->state,
+ siw_dbg_cep(cep, "cep->state %d, pd_len %d\n", cep->state,
pd_len);
if (__mpa_rr_revision(cep->mpa.hdr.params.bits) >= MPA_REVISION_1) {
rv = kernel_setsockopt(s, SOL_SOCKET, SO_REUSEADDR, (char *)&s_val,
sizeof(s_val));
if (rv) {
- siw_dbg(id->device, "id 0x%p: setsockopt error: %d\n", id, rv);
+ siw_dbg(id->device, "setsockopt error: %d\n", rv);
goto error;
}
rv = s->ops->bind(s, laddr, addr_family == AF_INET ?
sizeof(struct sockaddr_in) :
sizeof(struct sockaddr_in6));
if (rv) {
- siw_dbg(id->device, "id 0x%p: socket bind error: %d\n", id, rv);
+ siw_dbg(id->device, "socket bind error: %d\n", rv);
goto error;
}
cep = siw_cep_alloc(sdev);
rv = siw_cm_alloc_work(cep, backlog);
if (rv) {
siw_dbg(id->device,
- "id 0x%p: alloc_work error %d, backlog %d\n", id,
+ "alloc_work error %d, backlog %d\n",
rv, backlog);
goto error;
}
rv = s->ops->listen(s, backlog);
if (rv) {
- siw_dbg(id->device, "id 0x%p: listen error %d\n", id, rv);
+ siw_dbg(id->device, "listen error %d\n", rv);
goto error;
}
cep->cm_id = id;
list_del(p);
- siw_dbg_cep(cep, "id 0x%p: drop cep, state %d\n", id,
- cep->state);
+ siw_dbg_cep(cep, "drop cep, state %d\n", cep->state);
siw_cep_set_inuse(cep);
struct net_device *dev = to_siw_dev(id->device)->netdev;
int rv = 0, listeners = 0;
- siw_dbg(id->device, "id 0x%p: backlog %d\n", id, backlog);
+ siw_dbg(id->device, "backlog %d\n", backlog);
/*
* For each attached address of the interface, create a
struct sockaddr_in s_laddr, *s_raddr;
const struct in_ifaddr *ifa;
+ if (!in_dev) {
+ rv = -ENODEV;
+ goto out;
+ }
memcpy(&s_laddr, &id->local_addr, sizeof(s_laddr));
s_raddr = (struct sockaddr_in *)&id->remote_addr;
siw_dbg(id->device,
- "id 0x%p: laddr %pI4:%d, raddr %pI4:%d\n",
- id, &s_laddr.sin_addr, ntohs(s_laddr.sin_port),
+ "laddr %pI4:%d, raddr %pI4:%d\n",
+ &s_laddr.sin_addr, ntohs(s_laddr.sin_port),
&s_raddr->sin_addr, ntohs(s_raddr->sin_port));
rtnl_lock();
struct sockaddr_in6 *s_laddr = &to_sockaddr_in6(id->local_addr),
*s_raddr = &to_sockaddr_in6(id->remote_addr);
+ if (!in6_dev) {
+ rv = -ENODEV;
+ goto out;
+ }
siw_dbg(id->device,
- "id 0x%p: laddr %pI6:%d, raddr %pI6:%d\n",
- id, &s_laddr->sin6_addr, ntohs(s_laddr->sin6_port),
+ "laddr %pI6:%d, raddr %pI6:%d\n",
+ &s_laddr->sin6_addr, ntohs(s_laddr->sin6_port),
&s_raddr->sin6_addr, ntohs(s_raddr->sin6_port));
- read_lock_bh(&in6_dev->lock);
+ rtnl_lock();
list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
- struct sockaddr_in6 bind_addr;
-
+ if (ifp->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
+ continue;
if (ipv6_addr_any(&s_laddr->sin6_addr) ||
ipv6_addr_equal(&s_laddr->sin6_addr, &ifp->addr)) {
- bind_addr.sin6_family = AF_INET6;
- bind_addr.sin6_port = s_laddr->sin6_port;
- bind_addr.sin6_flowinfo = 0;
- bind_addr.sin6_addr = ifp->addr;
- bind_addr.sin6_scope_id = dev->ifindex;
+ struct sockaddr_in6 bind_addr = {
+ .sin6_family = AF_INET6,
+ .sin6_port = s_laddr->sin6_port,
+ .sin6_flowinfo = 0,
+ .sin6_addr = ifp->addr,
+ .sin6_scope_id = dev->ifindex };
rv = siw_listen_address(id, backlog,
(struct sockaddr *)&bind_addr,
listeners++;
}
}
- read_unlock_bh(&in6_dev->lock);
-
+ rtnl_unlock();
in6_dev_put(in6_dev);
} else {
- return -EAFNOSUPPORT;
+ rv = -EAFNOSUPPORT;
}
+out:
if (listeners)
rv = 0;
else if (!rv)
rv = -EINVAL;
- siw_dbg(id->device, "id 0x%p: %s\n", id, rv ? "FAIL" : "OK");
+ siw_dbg(id->device, "%s\n", rv ? "FAIL" : "OK");
return rv;
}
int siw_destroy_listen(struct iw_cm_id *id)
{
- siw_dbg(id->device, "id 0x%p\n", id);
-
if (!id->provider_data) {
- siw_dbg(id->device, "id 0x%p: no cep(s)\n", id);
+ siw_dbg(id->device, "no cep(s)\n");
return 0;
}
siw_drop_listeners(id);
wc->wc_flags = IB_WC_WITH_INVALIDATE;
}
wc->qp = cqe->base_qp;
- siw_dbg_cq(cq, "idx %u, type %d, flags %2x, id 0x%p\n",
+ siw_dbg_cq(cq,
+ "idx %u, type %d, flags %2x, id 0x%pK\n",
cq->cq_get % cq->num_cqe, cqe->opcode,
- cqe->flags, (void *)cqe->id);
+ cqe->flags, (void *)(uintptr_t)cqe->id);
}
WRITE_ONCE(cqe->flags, 0);
cq->cq_get++;
out_err:
siw_cpu_info.num_nodes = 0;
- while (i) {
+ while (--i >= 0)
kfree(siw_cpu_info.tx_valid_cpus[i]);
- siw_cpu_info.tx_valid_cpus[i--] = NULL;
- }
kfree(siw_cpu_info.tx_valid_cpus);
siw_cpu_info.tx_valid_cpus = NULL;
if (!siw_create_tx_threads()) {
pr_info("siw: Could not start any TX thread\n");
+ rv = -ENOMEM;
goto out_error;
}
/*
*/
if (addr < mem->va || addr + len > mem->va + mem->len) {
siw_dbg_pd(pd, "MEM interval len %d\n", len);
- siw_dbg_pd(pd, "[0x%016llx, 0x%016llx] out of bounds\n",
- (unsigned long long)addr,
- (unsigned long long)(addr + len));
- siw_dbg_pd(pd, "[0x%016llx, 0x%016llx] STag=0x%08x\n",
- (unsigned long long)mem->va,
- (unsigned long long)(mem->va + mem->len),
+ siw_dbg_pd(pd, "[0x%pK, 0x%pK] out of bounds\n",
+ (void *)(uintptr_t)addr,
+ (void *)(uintptr_t)(addr + len));
+ siw_dbg_pd(pd, "[0x%pK, 0x%pK] STag=0x%08x\n",
+ (void *)(uintptr_t)mem->va,
+ (void *)(uintptr_t)(mem->va + mem->len),
mem->stag);
return -E_BASE_BOUNDS;
* Optionally, provides remaining len within current element, and
* current PBL index for later resume at same element.
*/
-u64 siw_pbl_get_buffer(struct siw_pbl *pbl, u64 off, int *len, int *idx)
+dma_addr_t siw_pbl_get_buffer(struct siw_pbl *pbl, u64 off, int *len, int *idx)
{
int i = idx ? *idx : 0;
struct siw_umem *siw_umem_get(u64 start, u64 len, bool writable);
void siw_umem_release(struct siw_umem *umem, bool dirty);
struct siw_pbl *siw_pbl_alloc(u32 num_buf);
-u64 siw_pbl_get_buffer(struct siw_pbl *pbl, u64 off, int *len, int *idx);
+dma_addr_t siw_pbl_get_buffer(struct siw_pbl *pbl, u64 off, int *len, int *idx);
struct siw_mem *siw_mem_id2obj(struct siw_device *sdev, int stag_index);
int siw_mem_add(struct siw_device *sdev, struct siw_mem *m);
int siw_invalidate_stag(struct ib_pd *pd, u32 stag);
{
struct siw_rx_stream *c_rx = &qp->rx_stream;
struct siw_iwarp_tx *c_tx = &qp->tx_ctx;
- int size = crypto_shash_descsize(siw_crypto_shash) +
- sizeof(struct shash_desc);
+ int size;
if (siw_crypto_shash == NULL)
return -ENOENT;
+ size = crypto_shash_descsize(siw_crypto_shash) +
+ sizeof(struct shash_desc);
+
c_tx->mpa_crc_hd = kzalloc(size, GFP_KERNEL);
c_rx->mpa_crc_hd = kzalloc(size, GFP_KERNEL);
if (!c_tx->mpa_crc_hd || !c_rx->mpa_crc_hd) {
rv = -EINVAL;
goto out;
}
- wqe->sqe.sge[0].laddr = (u64)&wqe->sqe.sge[1];
+ wqe->sqe.sge[0].laddr = (uintptr_t)&wqe->sqe.sge[1];
wqe->sqe.sge[0].lkey = 0;
wqe->sqe.num_sge = 1;
}
*/
static bool siw_cq_notify_now(struct siw_cq *cq, u32 flags)
{
- u64 cq_notify;
+ u32 cq_notify;
if (!cq->base_cq.comp_handler)
return false;
- cq_notify = READ_ONCE(*cq->notify);
+ /* Read application shared notification state */
+ cq_notify = READ_ONCE(cq->notify->flags);
if ((cq_notify & SIW_NOTIFY_NEXT_COMPLETION) ||
((cq_notify & SIW_NOTIFY_SOLICITED) &&
(flags & SIW_WQE_SOLICITED))) {
- /* dis-arm CQ */
- smp_store_mb(*cq->notify, SIW_NOTIFY_NOT);
+ /*
+ * CQ notification is one-shot: Since the
+ * current CQE causes user notification,
+ * the CQ gets dis-aremd and must be re-aremd
+ * by the user for a new notification.
+ */
+ WRITE_ONCE(cq->notify->flags, SIW_NOTIFY_NOT);
return true;
}
p = siw_get_upage(umem, dest_addr);
if (unlikely(!p)) {
- pr_warn("siw: %s: [QP %u]: bogus addr: %p, %p\n",
+ pr_warn("siw: %s: [QP %u]: bogus addr: %pK, %pK\n",
__func__, qp_id(rx_qp(srx)),
- (void *)dest_addr, (void *)umem->fp_addr);
+ (void *)(uintptr_t)dest_addr,
+ (void *)(uintptr_t)umem->fp_addr);
/* siw internal error */
srx->skb_copied += copied;
srx->skb_new -= copied;
pg_off = dest_addr & ~PAGE_MASK;
bytes = min(len, (int)PAGE_SIZE - pg_off);
- siw_dbg_qp(rx_qp(srx), "page %p, bytes=%u\n", p, bytes);
+ siw_dbg_qp(rx_qp(srx), "page %pK, bytes=%u\n", p, bytes);
dest = kmap_atomic(p);
rv = skb_copy_bits(srx->skb, srx->skb_offset, dest + pg_off,
{
int rv;
- siw_dbg_qp(rx_qp(srx), "kva: 0x%p, len: %u\n", kva, len);
+ siw_dbg_qp(rx_qp(srx), "kva: 0x%pK, len: %u\n", kva, len);
rv = skb_copy_bits(srx->skb, srx->skb_offset, kva, len);
if (unlikely(rv)) {
- pr_warn("siw: [QP %u]: %s, len %d, kva 0x%p, rv %d\n",
+ pr_warn("siw: [QP %u]: %s, len %d, kva 0x%pK, rv %d\n",
qp_id(rx_qp(srx)), __func__, len, kva, rv);
return rv;
while (len) {
int bytes;
- u64 buf_addr =
+ dma_addr_t buf_addr =
siw_pbl_get_buffer(pbl, offset, &bytes, pbl_idx);
if (!buf_addr)
break;
mem_p = *mem;
if (mem_p->mem_obj == NULL)
rv = siw_rx_kva(srx,
- (void *)(sge->laddr + frx->sge_off),
- sge_bytes);
+ (void *)(uintptr_t)(sge->laddr + frx->sge_off),
+ sge_bytes);
else if (!mem_p->is_pbl)
rv = siw_rx_umem(srx, mem_p->umem,
sge->laddr + frx->sge_off, sge_bytes);
if (mem->mem_obj == NULL)
rv = siw_rx_kva(srx,
- (void *)(srx->ddp_to + srx->fpdu_part_rcvd),
- bytes);
+ (void *)(uintptr_t)(srx->ddp_to + srx->fpdu_part_rcvd),
+ bytes);
else if (!mem->is_pbl)
rv = siw_rx_umem(srx, mem->umem,
srx->ddp_to + srx->fpdu_part_rcvd, bytes);
bytes = min(srx->fpdu_part_rem, srx->skb_new);
if (mem_p->mem_obj == NULL)
- rv = siw_rx_kva(srx, (void *)(sge->laddr + wqe->processed),
- bytes);
+ rv = siw_rx_kva(srx,
+ (void *)(uintptr_t)(sge->laddr + wqe->processed),
+ bytes);
else if (!mem_p->is_pbl)
rv = siw_rx_umem(srx, mem_p->umem, sge->laddr + wqe->processed,
bytes);
{
struct siw_pbl *pbl = mem->pbl;
u64 offset = addr - mem->va;
- u64 paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx);
+ dma_addr_t paddr = siw_pbl_get_buffer(pbl, offset, NULL, idx);
if (paddr)
return virt_to_page(paddr);
/*
* Copy short payload at provided destination payload address
*/
-static int siw_try_1seg(struct siw_iwarp_tx *c_tx, u64 paddr)
+static int siw_try_1seg(struct siw_iwarp_tx *c_tx, void *paddr)
{
struct siw_wqe *wqe = &c_tx->wqe_active;
struct siw_sge *sge = &wqe->sqe.sge[0];
return 0;
if (tx_flags(wqe) & SIW_WQE_INLINE) {
- memcpy((void *)paddr, &wqe->sqe.sge[1], bytes);
+ memcpy(paddr, &wqe->sqe.sge[1], bytes);
} else {
struct siw_mem *mem = wqe->mem[0];
if (!mem->mem_obj) {
/* Kernel client using kva */
- memcpy((void *)paddr, (void *)sge->laddr, bytes);
+ memcpy(paddr,
+ (const void *)(uintptr_t)sge->laddr, bytes);
} else if (c_tx->in_syscall) {
- if (copy_from_user((void *)paddr,
- (const void __user *)sge->laddr,
+ if (copy_from_user(paddr, u64_to_user_ptr(sge->laddr),
bytes))
return -EFAULT;
} else {
buffer = kmap_atomic(p);
if (likely(PAGE_SIZE - off >= bytes)) {
- memcpy((void *)paddr, buffer + off, bytes);
+ memcpy(paddr, buffer + off, bytes);
kunmap_atomic(buffer);
} else {
unsigned long part = bytes - (PAGE_SIZE - off);
- memcpy((void *)paddr, buffer + off, part);
+ memcpy(paddr, buffer + off, part);
kunmap_atomic(buffer);
if (!mem->is_pbl)
return -EFAULT;
buffer = kmap_atomic(p);
- memcpy((void *)(paddr + part), buffer,
+ memcpy(paddr + part, buffer,
bytes - part);
kunmap_atomic(buffer);
}
c_tx->ctrl_len = sizeof(struct iwarp_send);
crc = (char *)&c_tx->pkt.send_pkt.crc;
- data = siw_try_1seg(c_tx, (u64)crc);
+ data = siw_try_1seg(c_tx, crc);
break;
case SIW_OP_SEND_REMOTE_INV:
c_tx->ctrl_len = sizeof(struct iwarp_send_inv);
crc = (char *)&c_tx->pkt.send_pkt.crc;
- data = siw_try_1seg(c_tx, (u64)crc);
+ data = siw_try_1seg(c_tx, crc);
break;
case SIW_OP_WRITE:
c_tx->ctrl_len = sizeof(struct iwarp_rdma_write);
crc = (char *)&c_tx->pkt.write_pkt.crc;
- data = siw_try_1seg(c_tx, (u64)crc);
+ data = siw_try_1seg(c_tx, crc);
break;
case SIW_OP_READ_RESPONSE:
c_tx->ctrl_len = sizeof(struct iwarp_rdma_rresp);
crc = (char *)&c_tx->pkt.write_pkt.crc;
- data = siw_try_1seg(c_tx, (u64)crc);
+ data = siw_try_1seg(c_tx, crc);
break;
default:
#define MAX_TRAILER (MPA_CRC_SIZE + 4)
-static void siw_unmap_pages(struct page **pages, int hdr_len, int num_maps)
+static void siw_unmap_pages(struct page **pp, unsigned long kmap_mask)
{
- if (hdr_len) {
- ++pages;
- --num_maps;
- }
- while (num_maps-- > 0) {
- kunmap(*pages);
- pages++;
+ while (kmap_mask) {
+ if (kmap_mask & BIT(0))
+ kunmap(*pp);
+ pp++;
+ kmap_mask >>= 1;
}
}
unsigned int data_len = c_tx->bytes_unsent, hdr_len = 0, trl_len = 0,
sge_off = c_tx->sge_off, sge_idx = c_tx->sge_idx,
pbl_idx = c_tx->pbl_idx;
+ unsigned long kmap_mask = 0L;
if (c_tx->state == SIW_SEND_HDR) {
if (c_tx->use_sendpage) {
if (!(tx_flags(wqe) & SIW_WQE_INLINE)) {
mem = wqe->mem[sge_idx];
- if (!mem->mem_obj)
- is_kva = 1;
+ is_kva = mem->mem_obj == NULL ? 1 : 0;
} else {
is_kva = 1;
}
* tx from kernel virtual address: either inline data
* or memory region with assigned kernel buffer
*/
- iov[seg].iov_base = (void *)(sge->laddr + sge_off);
+ iov[seg].iov_base =
+ (void *)(uintptr_t)(sge->laddr + sge_off);
iov[seg].iov_len = sge_len;
if (do_crc)
p = siw_get_upage(mem->umem,
sge->laddr + sge_off);
if (unlikely(!p)) {
- if (hdr_len)
- seg--;
- if (!c_tx->use_sendpage && seg) {
- siw_unmap_pages(page_array,
- hdr_len, seg);
- }
+ siw_unmap_pages(page_array, kmap_mask);
wqe->processed -= c_tx->bytes_unsent;
rv = -EFAULT;
goto done_crc;
if (!c_tx->use_sendpage) {
iov[seg].iov_base = kmap(p) + fp_off;
iov[seg].iov_len = plen;
+
+ /* Remember for later kunmap() */
+ kmap_mask |= BIT(seg);
+
if (do_crc)
crypto_shash_update(
c_tx->mpa_crc_hd,
page_address(p) + fp_off,
plen);
} else {
- u64 pa = ((sge->laddr + sge_off) & PAGE_MASK);
+ u64 va = sge->laddr + sge_off;
- page_array[seg] = virt_to_page(pa);
+ page_array[seg] = virt_to_page(va & PAGE_MASK);
if (do_crc)
crypto_shash_update(
c_tx->mpa_crc_hd,
- (void *)(sge->laddr + sge_off),
+ (void *)(uintptr_t)va,
plen);
}
if (++seg > (int)MAX_ARRAY) {
siw_dbg_qp(tx_qp(c_tx), "to many fragments\n");
- if (!is_kva && !c_tx->use_sendpage) {
- siw_unmap_pages(page_array, hdr_len,
- seg - 1);
- }
+ siw_unmap_pages(page_array, kmap_mask);
wqe->processed -= c_tx->bytes_unsent;
rv = -EMSGSIZE;
goto done_crc;
} else {
rv = kernel_sendmsg(s, &msg, iov, seg + 1,
hdr_len + data_len + trl_len);
- if (!is_kva)
- siw_unmap_pages(page_array, hdr_len, seg);
+ siw_unmap_pages(page_array, kmap_mask);
}
if (rv < (int)hdr_len) {
/* Not even complete hdr pushed or negative rv */
rv = -EINVAL;
goto tx_error;
}
- wqe->sqe.sge[0].laddr = (u64)&wqe->sqe.sge[1];
+ wqe->sqe.sge[0].laddr =
+ (u64)(uintptr_t)&wqe->sqe.sge[1];
}
}
wqe->wr_status = SIW_WR_INPROGRESS;
static int siw_fastreg_mr(struct ib_pd *pd, struct siw_sqe *sqe)
{
- struct ib_mr *base_mr = (struct ib_mr *)sqe->base_mr;
+ struct ib_mr *base_mr = (struct ib_mr *)(uintptr_t)sqe->base_mr;
struct siw_device *sdev = to_siw_dev(pd->device);
struct siw_mem *mem = siw_mem_id2obj(sdev, sqe->rkey >> 8);
int rv = 0;
mem->stag = sqe->rkey;
mem->perms = sqe->access;
- siw_dbg_mem(mem, "STag now valid, MR va: 0x%016llx -> 0x%016llx\n",
- mem->va, base_mr->iova);
+ siw_dbg_mem(mem, "STag 0x%08x now valid\n", sqe->rkey);
mem->va = base_mr->iova;
mem->stag_valid = 1;
out:
*/
qp->srq = to_siw_srq(attrs->srq);
qp->attrs.rq_size = 0;
- siw_dbg(base_dev, "QP [%u]: [SRQ 0x%p] attached\n",
- qp->qp_num, qp->srq);
+ siw_dbg(base_dev, "QP [%u]: SRQ attached\n", qp->qp_num);
} else if (num_rqe) {
if (qp->kernel_verbs)
qp->recvq = vzalloc(num_rqe * sizeof(struct siw_rqe));
base_ucontext);
struct siw_qp_attrs qp_attrs;
- siw_dbg_qp(qp, "state %d, cep 0x%p\n", qp->attrs.state, qp->cep);
+ siw_dbg_qp(qp, "state %d\n", qp->attrs.state);
/*
* Mark QP as in process of destruction to prevent from
void *kbuf = &sqe->sge[1];
int num_sge = core_wr->num_sge, bytes = 0;
- sqe->sge[0].laddr = (u64)kbuf;
+ sqe->sge[0].laddr = (uintptr_t)kbuf;
sqe->sge[0].lkey = 0;
while (num_sge--) {
break;
case IB_WR_REG_MR:
- sqe->base_mr = (uint64_t)reg_wr(wr)->mr;
+ sqe->base_mr = (uintptr_t)reg_wr(wr)->mr;
sqe->rkey = reg_wr(wr)->key;
sqe->access = reg_wr(wr)->access & IWARP_ACCESS_MASK;
sqe->opcode = SIW_OP_REG_MR;
rv = -EINVAL;
break;
}
- siw_dbg_qp(qp, "opcode %d, flags 0x%x, wr_id 0x%p\n",
- sqe->opcode, sqe->flags, (void *)sqe->id);
+ siw_dbg_qp(qp, "opcode %d, flags 0x%x, wr_id 0x%pK\n",
+ sqe->opcode, sqe->flags,
+ (void *)(uintptr_t)sqe->id);
if (unlikely(rv < 0))
break;
spin_lock_init(&cq->lock);
- cq->notify = &((struct siw_cq_ctrl *)&cq->queue[size])->notify;
+ cq->notify = (struct siw_cq_ctrl *)&cq->queue[size];
if (udata) {
struct siw_uresp_create_cq uresp = {};
siw_dbg_cq(cq, "flags: 0x%02x\n", flags);
if ((flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED)
- /* CQ event for next solicited completion */
- smp_store_mb(*cq->notify, SIW_NOTIFY_SOLICITED);
+ /*
+ * Enable CQ event for next solicited completion.
+ * and make it visible to all associated producers.
+ */
+ smp_store_mb(cq->notify->flags, SIW_NOTIFY_SOLICITED);
else
- /* CQ event for any signalled completion */
- smp_store_mb(*cq->notify, SIW_NOTIFY_ALL);
+ /*
+ * Enable CQ event for any signalled completion.
+ * and make it visible to all associated producers.
+ */
+ smp_store_mb(cq->notify->flags, SIW_NOTIFY_ALL);
if (flags & IB_CQ_REPORT_MISSED_EVENTS)
return cq->cq_put - cq->cq_get;
unsigned long mem_limit = rlimit(RLIMIT_MEMLOCK);
int rv;
- siw_dbg_pd(pd, "start: 0x%016llx, va: 0x%016llx, len: %llu\n",
- (unsigned long long)start, (unsigned long long)rnic_va,
+ siw_dbg_pd(pd, "start: 0x%pK, va: 0x%pK, len: %llu\n",
+ (void *)(uintptr_t)start, (void *)(uintptr_t)rnic_va,
(unsigned long long)len);
if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) {
struct siw_mem *mem = mr->mem;
struct siw_pbl *pbl = mem->pbl;
struct siw_pble *pble;
- u64 pbl_size;
+ unsigned long pbl_size;
int i, rv;
if (!pbl) {
pbl_size += sg_dma_len(slp);
}
siw_dbg_mem(mem,
- "sge[%d], size %llu, addr 0x%016llx, total %llu\n",
- i, pble->size, pble->addr, pbl_size);
+ "sge[%d], size %u, addr 0x%p, total %lu\n",
+ i, pble->size, (void *)(uintptr_t)pble->addr,
+ pbl_size);
}
rv = ib_sg_to_pages(base_mr, sl, num_sle, sg_off, siw_set_pbl_page);
if (rv > 0) {
mem->len = base_mr->length;
mem->va = base_mr->iova;
siw_dbg_mem(mem,
- "%llu bytes, start 0x%016llx, %u SLE to %u entries\n",
- mem->len, mem->va, num_sle, pbl->num_buf);
+ "%llu bytes, start 0x%pK, %u SLE to %u entries\n",
+ mem->len, (void *)(uintptr_t)mem->va, num_sle,
+ pbl->num_buf);
}
return rv;
}
}
spin_lock_init(&srq->lock);
- siw_dbg_pd(base_srq->pd, "[SRQ 0x%p]: success\n", srq);
+ siw_dbg_pd(base_srq->pd, "[SRQ]: success\n");
return 0;
if (unlikely(!srq->kernel_verbs)) {
siw_dbg_pd(base_srq->pd,
- "[SRQ 0x%p]: no kernel post_recv for mapped srq\n",
- srq);
+ "[SRQ]: no kernel post_recv for mapped srq\n");
rv = -EINVAL;
goto out;
}
}
if (unlikely(wr->num_sge > srq->max_sge)) {
siw_dbg_pd(base_srq->pd,
- "[SRQ 0x%p]: too many sge's: %d\n", srq,
- wr->num_sge);
+ "[SRQ]: too many sge's: %d\n", wr->num_sge);
rv = -EINVAL;
break;
}
spin_unlock_irqrestore(&srq->lock, flags);
out:
if (unlikely(rv < 0)) {
- siw_dbg_pd(base_srq->pd, "[SRQ 0x%p]: error %d\n", srq, rv);
+ siw_dbg_pd(base_srq->pd, "[SRQ]: error %d\n", rv);
*bad_wr = wr;
}
return rv;
return -ENODEV;
epirq = &interface->endpoint[0].desc;
+ if (!usb_endpoint_is_int_in(epirq))
+ return -ENODEV;
+
epout = &interface->endpoint[1].desc;
+ if (!usb_endpoint_is_int_out(epout))
+ return -ENODEV;
iforce_usb = kzalloc(sizeof(*iforce_usb), GFP_KERNEL);
if (!iforce_usb)
depends on ACPI && EFI
depends on SPI
depends on X86 || COMPILE_TEST
+ depends on LEDS_CLASS
+ select CRC16
help
Say Y here if you are running Linux on any Apple MacBook8,1 or later,
or any MacBookPro13,* or MacBookPro14,*.
* struct tp_finger - single trackpad finger structure, le16-aligned
*
* @origin: zero when switching track finger
- * @abs_x: absolute x coodinate
- * @abs_y: absolute y coodinate
- * @rel_x: relative x coodinate
- * @rel_y: relative y coodinate
+ * @abs_x: absolute x coordinate
+ * @abs_y: absolute y coordinate
+ * @rel_x: relative x coordinate
+ * @rel_y: relative y coordinate
* @tool_major: tool area, major axis
* @tool_minor: tool area, minor axis
* @orientation: 16384 when point, else 15 bit angle
static void applespi_debug_update_dimensions(struct applespi_data *applespi,
const struct tp_finger *f)
{
- applespi->tp_dim_min_x = min_t(int, applespi->tp_dim_min_x, f->abs_x);
- applespi->tp_dim_max_x = max_t(int, applespi->tp_dim_max_x, f->abs_x);
- applespi->tp_dim_min_y = min_t(int, applespi->tp_dim_min_y, f->abs_y);
- applespi->tp_dim_max_y = max_t(int, applespi->tp_dim_max_y, f->abs_y);
+ applespi->tp_dim_min_x = min(applespi->tp_dim_min_x,
+ le16_to_int(f->abs_x));
+ applespi->tp_dim_max_x = max(applespi->tp_dim_max_x,
+ le16_to_int(f->abs_x));
+ applespi->tp_dim_min_y = min(applespi->tp_dim_min_y,
+ le16_to_int(f->abs_y));
+ applespi->tp_dim_max_y = max(applespi->tp_dim_max_y,
+ le16_to_int(f->abs_y));
}
static int applespi_tp_dim_open(struct inode *inode, struct file *file)
size_t tp_len;
tp = &message->touchpad;
- tp_len = sizeof(*tp) +
- tp->number_of_fingers * sizeof(tp->fingers[0]);
+ tp_len = struct_size(tp, fingers, tp->number_of_fingers);
if (le16_to_cpu(message->length) + 2 != tp_len) {
dev_warn_ratelimited(&applespi->spi->dev,
efi_attr = EFI_VARIABLE_NON_VOLATILE | EFI_VARIABLE_BOOTSERVICE_ACCESS |
EFI_VARIABLE_RUNTIME_ACCESS;
- sts = efivar_entry_set_safe(EFI_BL_LEVEL_NAME, efi_guid, efi_attr, true,
- efi_data_len, &efi_data);
+ sts = efivar_entry_set_safe((efi_char16_t *)EFI_BL_LEVEL_NAME, efi_guid,
+ efi_attr, true, efi_data_len, &efi_data);
if (sts)
dev_warn(&applespi->spi->dev,
"Error saving backlight level to EFI vars: %d\n", sts);
};
MODULE_DEVICE_TABLE(acpi, applespi_acpi_match);
-const struct dev_pm_ops applespi_pm_ops = {
+static const struct dev_pm_ops applespi_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(applespi_suspend, applespi_resume)
.poweroff_late = applespi_poweroff_late,
};
leave_breadcrumbs);
}
+static bool elantech_use_host_notify(struct psmouse *psmouse,
+ struct elantech_device_info *info)
+{
+ if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
+ return true;
+
+ switch (info->bus) {
+ case ETP_BUS_PS2_ONLY:
+ /* expected case */
+ break;
+ case ETP_BUS_SMB_HST_NTFY_ONLY:
+ case ETP_BUS_PS2_SMB_HST_NTFY:
+ /* SMbus implementation is stable since 2018 */
+ if (dmi_get_bios_year() >= 2018)
+ return true;
+ /* fall through */
+ default:
+ psmouse_dbg(psmouse,
+ "Ignoring SMBus bus provider %d\n", info->bus);
+ break;
+ }
+
+ return false;
+}
+
/**
* elantech_setup_smbus - called once the PS/2 devices are enumerated
* and decides to instantiate a SMBus InterTouch device.
* i2c_blacklist_pnp_ids.
* Old ICs are up to the user to decide.
*/
- if (!ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version) ||
+ if (!elantech_use_host_notify(psmouse, info) ||
psmouse_matches_pnp_id(psmouse, i2c_blacklist_pnp_ids))
return -ENXIO;
}
return 0;
}
-static bool elantech_use_host_notify(struct psmouse *psmouse,
- struct elantech_device_info *info)
-{
- if (ETP_NEW_IC_SMBUS_HOST_NOTIFY(info->fw_version))
- return true;
-
- switch (info->bus) {
- case ETP_BUS_PS2_ONLY:
- /* expected case */
- break;
- case ETP_BUS_SMB_ALERT_ONLY:
- /* fall-through */
- case ETP_BUS_PS2_SMB_ALERT:
- psmouse_dbg(psmouse, "Ignoring SMBus provider through alert protocol.\n");
- break;
- case ETP_BUS_SMB_HST_NTFY_ONLY:
- /* fall-through */
- case ETP_BUS_PS2_SMB_HST_NTFY:
- return true;
- default:
- psmouse_dbg(psmouse,
- "Ignoring SMBus bus provider %d.\n",
- info->bus);
- }
-
- return false;
-}
-
int elantech_init_smbus(struct psmouse *psmouse)
{
struct elantech_device_info info;
"LEN2055", /* E580 */
"SYN3052", /* HP EliteBook 840 G4 */
"SYN3221", /* HP 15-ay000 */
+ "SYN323d", /* HP Spectre X360 13-w013dx */
NULL
};
static void hv_kbd_on_channel_callback(void *context)
{
+ struct vmpacket_descriptor *desc;
struct hv_device *hv_dev = context;
- void *buffer;
- int bufferlen = 0x100; /* Start with sensible size */
u32 bytes_recvd;
u64 req_id;
- int error;
- buffer = kmalloc(bufferlen, GFP_ATOMIC);
- if (!buffer)
- return;
-
- while (1) {
- error = vmbus_recvpacket_raw(hv_dev->channel, buffer, bufferlen,
- &bytes_recvd, &req_id);
- switch (error) {
- case 0:
- if (bytes_recvd == 0) {
- kfree(buffer);
- return;
- }
-
- hv_kbd_handle_received_packet(hv_dev, buffer,
- bytes_recvd, req_id);
- break;
+ foreach_vmbus_pkt(desc, hv_dev->channel) {
+ bytes_recvd = desc->len8 * 8;
+ req_id = desc->trans_id;
- case -ENOBUFS:
- kfree(buffer);
- /* Handle large packet */
- bufferlen = bytes_recvd;
- buffer = kmalloc(bytes_recvd, GFP_ATOMIC);
- if (!buffer)
- return;
- break;
- }
+ hv_kbd_handle_received_packet(hv_dev, desc, bytes_recvd,
+ req_id);
}
}
if (intf->cur_altsetting->desc.bNumEndpoints < 1)
return -ENODEV;
+ endpoint = &intf->cur_altsetting->endpoint[0].desc;
+ if (!usb_endpoint_is_int_in(endpoint))
+ return -ENODEV;
+
kbtab = kzalloc(sizeof(struct kbtab), GFP_KERNEL);
input_dev = input_allocate_device();
if (!kbtab || !input_dev)
input_set_abs_params(input_dev, ABS_Y, 0, 0x1750, 4, 0);
input_set_abs_params(input_dev, ABS_PRESSURE, 0, 0xff, 0, 0);
- endpoint = &intf->cur_altsetting->endpoint[0].desc;
-
usb_fill_int_urb(kbtab->irq, dev,
usb_rcvintpipe(dev, endpoint->bEndpointAddress),
kbtab->data, 8,
if (!usbtouch || !input_dev)
goto out_free;
+ mutex_init(&usbtouch->pm_mutex);
+
type = &usbtouch_dev_info[id->driver_info];
usbtouch->type = type;
if (!type->process_pkt)
iommu_completion_wait(iommu);
}
+static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
+{
+ struct iommu_cmd cmd;
+
+ build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+ dom_id, 1);
+ iommu_queue_command(iommu, &cmd);
+
+ iommu_completion_wait(iommu);
+}
+
static void amd_iommu_flush_all(struct amd_iommu *iommu)
{
struct iommu_cmd cmd;
* another level increases the size of the address space by 9 bits to a size up
* to 64 bits.
*/
-static bool increase_address_space(struct protection_domain *domain,
+static void increase_address_space(struct protection_domain *domain,
gfp_t gfp)
{
+ unsigned long flags;
u64 *pte;
- if (domain->mode == PAGE_MODE_6_LEVEL)
+ spin_lock_irqsave(&domain->lock, flags);
+
+ if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
/* address space already 64 bit large */
- return false;
+ goto out;
pte = (void *)get_zeroed_page(gfp);
if (!pte)
- return false;
+ goto out;
*pte = PM_LEVEL_PDE(domain->mode,
iommu_virt_to_phys(domain->pt_root));
domain->mode += 1;
domain->updated = true;
- return true;
+out:
+ spin_unlock_irqrestore(&domain->lock, flags);
+
+ return;
}
static u64 *alloc_pte(struct protection_domain *domain,
{
u64 pte_root = 0;
u64 flags = 0;
+ u32 old_domid;
if (domain->mode != PAGE_MODE_NONE)
pte_root = iommu_virt_to_phys(domain->pt_root);
flags &= ~DEV_DOMID_MASK;
flags |= domain->id;
+ old_domid = amd_iommu_dev_table[devid].data[1] & DEV_DOMID_MASK;
amd_iommu_dev_table[devid].data[1] = flags;
amd_iommu_dev_table[devid].data[0] = pte_root;
+
+ /*
+ * A kdump kernel might be replacing a domain ID that was copied from
+ * the previous kernel--if so, it needs to flush the translation cache
+ * entries for the old domain ID that is being overwritten
+ */
+ if (old_domid) {
+ struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+ amd_iommu_flush_tlb_domid(iommu, old_domid);
+ }
}
static void clear_dte_entry(u16 devid)
#include <linux/mem_encrypt.h>
#include <asm/pci-direct.h>
#include <asm/iommu.h>
+#include <asm/apic.h>
+#include <asm/msidef.h>
#include <asm/gart.h>
#include <asm/x86_init.h>
#include <asm/iommu_table.h>
return 0;
}
+#define XT_INT_DEST_MODE(x) (((x) & 0x1ULL) << 2)
+#define XT_INT_DEST_LO(x) (((x) & 0xFFFFFFULL) << 8)
+#define XT_INT_VEC(x) (((x) & 0xFFULL) << 32)
+#define XT_INT_DEST_HI(x) ((((x) >> 24) & 0xFFULL) << 56)
+
+/**
+ * Setup the IntCapXT registers with interrupt routing information
+ * based on the PCI MSI capability block registers, accessed via
+ * MMIO MSI address low/hi and MSI data registers.
+ */
+static void iommu_update_intcapxt(struct amd_iommu *iommu)
+{
+ u64 val;
+ u32 addr_lo = readl(iommu->mmio_base + MMIO_MSI_ADDR_LO_OFFSET);
+ u32 addr_hi = readl(iommu->mmio_base + MMIO_MSI_ADDR_HI_OFFSET);
+ u32 data = readl(iommu->mmio_base + MMIO_MSI_DATA_OFFSET);
+ bool dm = (addr_lo >> MSI_ADDR_DEST_MODE_SHIFT) & 0x1;
+ u32 dest = ((addr_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xFF);
+
+ if (x2apic_enabled())
+ dest |= MSI_ADDR_EXT_DEST_ID(addr_hi);
+
+ val = XT_INT_VEC(data & 0xFF) |
+ XT_INT_DEST_MODE(dm) |
+ XT_INT_DEST_LO(dest) |
+ XT_INT_DEST_HI(dest);
+
+ /**
+ * Current IOMMU implemtation uses the same IRQ for all
+ * 3 IOMMU interrupts.
+ */
+ writeq(val, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
+ writeq(val, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
+ writeq(val, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+}
+
+static void _irq_notifier_notify(struct irq_affinity_notify *notify,
+ const cpumask_t *mask)
+{
+ struct amd_iommu *iommu;
+
+ for_each_iommu(iommu) {
+ if (iommu->dev->irq == notify->irq) {
+ iommu_update_intcapxt(iommu);
+ break;
+ }
+ }
+}
+
+static void _irq_notifier_release(struct kref *ref)
+{
+}
+
+static int iommu_init_intcapxt(struct amd_iommu *iommu)
+{
+ int ret;
+ struct irq_affinity_notify *notify = &iommu->intcapxt_notify;
+
+ /**
+ * IntCapXT requires XTSup=1, which can be inferred
+ * amd_iommu_xt_mode.
+ */
+ if (amd_iommu_xt_mode != IRQ_REMAP_X2APIC_MODE)
+ return 0;
+
+ /**
+ * Also, we need to setup notifier to update the IntCapXT registers
+ * whenever the irq affinity is changed from user-space.
+ */
+ notify->irq = iommu->dev->irq;
+ notify->notify = _irq_notifier_notify,
+ notify->release = _irq_notifier_release,
+ ret = irq_set_affinity_notifier(iommu->dev->irq, notify);
+ if (ret) {
+ pr_err("Failed to register irq affinity notifier (devid=%#x, irq %d)\n",
+ iommu->devid, iommu->dev->irq);
+ return ret;
+ }
+
+ iommu_update_intcapxt(iommu);
+ iommu_feature_enable(iommu, CONTROL_INTCAPXT_EN);
+ return ret;
+}
+
static int iommu_init_msi(struct amd_iommu *iommu)
{
int ret;
return ret;
enable_faults:
+ ret = iommu_init_intcapxt(iommu);
+ if (ret)
+ return ret;
+
iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
if (iommu->ppr_log != NULL)
#define MMIO_PPR_LOG_OFFSET 0x0038
#define MMIO_GA_LOG_BASE_OFFSET 0x00e0
#define MMIO_GA_LOG_TAIL_OFFSET 0x00e8
+#define MMIO_MSI_ADDR_LO_OFFSET 0x015C
+#define MMIO_MSI_ADDR_HI_OFFSET 0x0160
+#define MMIO_MSI_DATA_OFFSET 0x0164
+#define MMIO_INTCAPXT_EVT_OFFSET 0x0170
+#define MMIO_INTCAPXT_PPR_OFFSET 0x0178
+#define MMIO_INTCAPXT_GALOG_OFFSET 0x0180
#define MMIO_CMD_HEAD_OFFSET 0x2000
#define MMIO_CMD_TAIL_OFFSET 0x2008
#define MMIO_EVT_HEAD_OFFSET 0x2010
#define CONTROL_GALOG_EN 0x1CULL
#define CONTROL_GAINT_EN 0x1DULL
#define CONTROL_XT_EN 0x32ULL
+#define CONTROL_INTCAPXT_EN 0x33ULL
#define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT)
#define CTRL_INV_TO_NONE 0
/* DebugFS Info */
struct dentry *debugfs;
#endif
+ /* IRQ notifier for IntCapXT interrupt */
+ struct irq_affinity_notify intcapxt_notify;
};
static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev)
ste_live = true;
break;
case STRTAB_STE_0_CFG_ABORT:
- if (disable_bypass)
- break;
+ BUG_ON(!disable_bypass);
+ break;
default:
BUG(); /* STE corruption */
}
{
struct iommu_domain *domain = iommu_get_dma_domain(dev);
struct iommu_dma_cookie *cookie = domain->iova_cookie;
- size_t iova_off = 0;
+ struct iova_domain *iovad = &cookie->iovad;
+ size_t iova_off = iova_offset(iovad, phys);
dma_addr_t iova;
- if (cookie->type == IOMMU_DMA_IOVA_COOKIE) {
- iova_off = iova_offset(&cookie->iovad, phys);
- size = iova_align(&cookie->iovad, size + iova_off);
- }
+ size = iova_align(iovad, size + iova_off);
iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
if (!iova)
struct iova_domain *iovad = &cookie->iovad;
bool coherent = dev_is_dma_coherent(dev);
int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
- pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+ pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
struct page **pages;
struct sg_table sgt;
* - and wouldn't make the resulting output segment too long
*/
if (cur_len && !s_iova_off && (dma_addr & seg_mask) &&
- (cur_len + s_length <= max_len)) {
+ (max_len - cur_len >= s_length)) {
/* ...then concatenate it with the previous one */
cur_len += s_length;
} else {
{
bool coherent = dev_is_dma_coherent(dev);
size_t alloc_size = PAGE_ALIGN(size);
+ int node = dev_to_node(dev);
struct page *page = NULL;
void *cpu_addr;
page = dma_alloc_contiguous(dev, alloc_size, gfp);
+ if (!page)
+ page = alloc_pages_node(node, gfp, get_order(alloc_size));
if (!page)
return NULL;
if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
- pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
+ pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
cpu_addr = dma_common_contiguous_remap(page, alloc_size,
VM_USERMAP, prot, __builtin_return_address(0));
unsigned long pfn, off = vma->vm_pgoff;
int ret;
- vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+ vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
if (!msi_page)
return NULL;
- iova = __iommu_dma_map(dev, msi_addr, size, prot);
- if (iova == DMA_MAPPING_ERROR)
+ iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+ if (!iova)
goto out_free_page;
+ if (iommu_map(domain, iova, msi_addr, size, prot))
+ goto out_free_iova;
+
INIT_LIST_HEAD(&msi_page->list);
msi_page->phys = msi_addr;
msi_page->iova = iova;
list_add(&msi_page->list, &cookie->msi_page_list);
return msi_page;
+out_free_iova:
+ iommu_dma_free_iova(cookie, iova, size);
out_free_page:
kfree(msi_page);
return NULL;
(u64)0, (u64)0, (u64)0);
else
seq_printf(m, "%-6d\t0x%016llx:0x%016llx:0x%016llx\n",
- tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[0],
+ tbl_wlk->pasid, tbl_wlk->pasid_tbl_entry->val[2],
tbl_wlk->pasid_tbl_entry->val[1],
- tbl_wlk->pasid_tbl_entry->val[2]);
+ tbl_wlk->pasid_tbl_entry->val[0]);
}
static void pasid_tbl_walk(struct seq_file *m, struct pasid_entry *tbl_entry,
tbl_wlk.ctx_entry = context;
m->private = &tbl_wlk;
- if (pasid_supported(iommu) && is_pasid_enabled(context)) {
+ if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT) {
pasid_dir_ptr = context->lo & VTD_PAGE_MASK;
pasid_dir_size = get_pasid_dir_size(context);
pasid_dir_walk(m, pasid_dir_ptr, pasid_dir_size);
return agaw;
}
+static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
+ int guest_width)
+{
+ int adjust_width, agaw;
+ unsigned long sagaw;
+ int err;
+
+ init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
+
+ err = init_iova_flush_queue(&domain->iovad,
+ iommu_flush_iova, iova_entry_free);
+ if (err)
+ return err;
+
+ domain_reserve_special_ranges(domain);
+
+ /* calculate AGAW */
+ if (guest_width > cap_mgaw(iommu->cap))
+ guest_width = cap_mgaw(iommu->cap);
+ domain->gaw = guest_width;
+ adjust_width = guestwidth_to_adjustwidth(guest_width);
+ agaw = width_to_agaw(adjust_width);
+ sagaw = cap_sagaw(iommu->cap);
+ if (!test_bit(agaw, &sagaw)) {
+ /* hardware doesn't support it, choose a bigger one */
+ pr_debug("Hardware doesn't support agaw %d\n", agaw);
+ agaw = find_next_bit(&sagaw, 5, agaw);
+ if (agaw >= 5)
+ return -ENODEV;
+ }
+ domain->agaw = agaw;
+
+ if (ecap_coherent(iommu->ecap))
+ domain->iommu_coherency = 1;
+ else
+ domain->iommu_coherency = 0;
+
+ if (ecap_sc_support(iommu->ecap))
+ domain->iommu_snooping = 1;
+ else
+ domain->iommu_snooping = 0;
+
+ if (intel_iommu_superpage)
+ domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
+ else
+ domain->iommu_superpage = 0;
+
+ domain->nid = iommu->node;
+
+ /* always allocate the top pgd */
+ domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+ if (!domain->pgd)
+ return -ENOMEM;
+ __iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
+ return 0;
+}
+
static void domain_exit(struct dmar_domain *domain)
{
- struct page *freelist;
/* Remove associated devices and clear attached or cached domains */
domain_remove_dev_info(domain);
/* destroy iovas */
put_iova_domain(&domain->iovad);
- freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+ if (domain->pgd) {
+ struct page *freelist;
- dma_free_pagelist(freelist);
+ freelist = domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
+ dma_free_pagelist(freelist);
+ }
free_domain_mem(domain);
}
return 0;
}
-static int domain_init(struct dmar_domain *domain, int guest_width)
-{
- int adjust_width;
-
- init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
- domain_reserve_special_ranges(domain);
-
- /* calculate AGAW */
- domain->gaw = guest_width;
- adjust_width = guestwidth_to_adjustwidth(guest_width);
- domain->agaw = width_to_agaw(adjust_width);
-
- domain->iommu_coherency = 0;
- domain->iommu_snooping = 0;
- domain->iommu_superpage = 0;
- domain->max_addr = 0;
-
- /* always allocate the top pgd */
- domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
- if (!domain->pgd)
- return -ENOMEM;
- domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
- return 0;
-}
-
static struct dmar_domain *find_or_alloc_domain(struct device *dev, int gaw)
{
struct device_domain_info *info;
domain = alloc_domain(0);
if (!domain)
return NULL;
-
- if (domain_init(domain, gaw)) {
+ if (domain_init(domain, iommu, gaw)) {
domain_exit(domain);
return NULL;
}
- if (init_iova_flush_queue(&domain->iovad,
- iommu_flush_iova,
- iova_entry_free)) {
- pr_warn("iova flush queue initialization failed\n");
- intel_iommu_strict = 1;
- }
-
out:
return domain;
}
return iommu_domain_identity_map(domain, start, end);
}
+static int md_domain_init(struct dmar_domain *domain, int guest_width);
+
static int __init si_domain_init(int hw)
{
struct dmar_rmrr_unit *rmrr;
if (!si_domain)
return -EFAULT;
- if (domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+ if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
domain_exit(si_domain);
return -EFAULT;
}
dmar_domain = to_dmar_domain(domain);
dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
}
+ dmar_remove_one_dev_info(dev);
get_private_domain_for_dev(dev);
}
freelist = domain_unmap(domain, start_pfn, last_pfn);
- if (intel_iommu_strict || (pdev && pdev->untrusted)) {
+ if (intel_iommu_strict || (pdev && pdev->untrusted) ||
+ !has_iova_flush_queue(&domain->iovad)) {
iommu_flush_iotlb_psi(iommu, domain, start_pfn,
nrpages, !freelist, 0);
/* free iova */
/* free the private domain */
if (domain->flags & DOMAIN_FLAG_LOSE_CHILDREN &&
- !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY))
+ !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) &&
+ list_empty(&domain->devices))
domain_exit(info->domain);
free_devinfo_mem(info);
spin_lock_irqsave(&device_domain_lock, flags);
info = dev->archdata.iommu;
- __dmar_remove_one_dev_info(info);
+ if (info)
+ __dmar_remove_one_dev_info(info);
spin_unlock_irqrestore(&device_domain_lock, flags);
}
+static int md_domain_init(struct dmar_domain *domain, int guest_width)
+{
+ int adjust_width;
+
+ init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
+ domain_reserve_special_ranges(domain);
+
+ /* calculate AGAW */
+ domain->gaw = guest_width;
+ adjust_width = guestwidth_to_adjustwidth(guest_width);
+ domain->agaw = width_to_agaw(adjust_width);
+
+ domain->iommu_coherency = 0;
+ domain->iommu_snooping = 0;
+ domain->iommu_superpage = 0;
+ domain->max_addr = 0;
+
+ /* always allocate the top pgd */
+ domain->pgd = (struct dma_pte *)alloc_pgtable_page(domain->nid);
+ if (!domain->pgd)
+ return -ENOMEM;
+ domain_flush_cache(domain, domain->pgd, PAGE_SIZE);
+ return 0;
+}
+
static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
{
struct dmar_domain *dmar_domain;
pr_err("Can't allocate dmar_domain\n");
return NULL;
}
- if (domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
+ if (md_domain_init(dmar_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) {
pr_err("Domain initialization failed\n");
domain_exit(dmar_domain);
return NULL;
if (device_def_domain_type(dev) == IOMMU_DOMAIN_IDENTITY) {
ret = iommu_request_dm_for_dev(dev);
if (ret) {
+ dmar_remove_one_dev_info(dev);
dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
domain_add_dev_info(si_domain, dev);
dev_info(dev,
if (device_def_domain_type(dev) == IOMMU_DOMAIN_DMA) {
ret = iommu_request_dma_domain_for_dev(dev);
if (ret) {
+ dmar_remove_one_dev_info(dev);
dmar_domain->flags |= DOMAIN_FLAG_LOSE_CHILDREN;
if (!get_private_domain_for_dev(dev)) {
dev_warn(dev,
if (!iommu)
return;
+ dmar_remove_one_dev_info(dev);
+
iommu_group_remove_device(dev);
iommu_device_unlink(&iommu->iommu, dev);
}
static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
- unsigned long address, unsigned long pages, int ih, int gl)
+ unsigned long address, unsigned long pages, int ih)
{
struct qi_desc desc;
- if (pages == -1) {
- /* For global kernel pages we have to flush them in *all* PASIDs
- * because that's the only option the hardware gives us. Despite
- * the fact that they are actually only accessible through one. */
- if (gl)
- desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
- QI_EIOTLB_DID(sdev->did) |
- QI_EIOTLB_GRAN(QI_GRAN_ALL_ALL) |
- QI_EIOTLB_TYPE;
- else
- desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
- QI_EIOTLB_DID(sdev->did) |
- QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
- QI_EIOTLB_TYPE;
+ /*
+ * Do PASID granu IOTLB invalidation if page selective capability is
+ * not available.
+ */
+ if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) {
+ desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
+ QI_EIOTLB_DID(sdev->did) |
+ QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+ QI_EIOTLB_TYPE;
desc.qw1 = 0;
} else {
int mask = ilog2(__roundup_pow_of_two(pages));
QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
QI_EIOTLB_TYPE;
desc.qw1 = QI_EIOTLB_ADDR(address) |
- QI_EIOTLB_GL(gl) |
QI_EIOTLB_IH(ih) |
QI_EIOTLB_AM(mask);
}
}
static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
- unsigned long pages, int ih, int gl)
+ unsigned long pages, int ih)
{
struct intel_svm_dev *sdev;
rcu_read_lock();
list_for_each_entry_rcu(sdev, &svm->devs, list)
- intel_flush_svm_range_dev(svm, sdev, address, pages, ih, gl);
+ intel_flush_svm_range_dev(svm, sdev, address, pages, ih);
rcu_read_unlock();
}
struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
intel_flush_svm_range(svm, start,
- (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0, 0);
+ (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
}
static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
rcu_read_lock();
list_for_each_entry_rcu(sdev, &svm->devs, list) {
intel_pasid_tear_down_entry(svm->iommu, sdev->dev, svm->pasid);
- intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+ intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
}
rcu_read_unlock();
* large and has to be physically contiguous. So it's
* hard to be as defensive as we might like. */
intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
- intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+ intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
kfree_rcu(sdev, rcu);
if (list_empty(&svm->devs)) {
}
EXPORT_SYMBOL_GPL(init_iova_domain);
+bool has_iova_flush_queue(struct iova_domain *iovad)
+{
+ return !!iovad->fq;
+}
+
static void free_iova_flush_queue(struct iova_domain *iovad)
{
- if (!iovad->fq)
+ if (!has_iova_flush_queue(iovad))
return;
if (timer_pending(&iovad->fq_timer))
int init_iova_flush_queue(struct iova_domain *iovad,
iova_flush_cb flush_cb, iova_entry_dtor entry_dtor)
{
+ struct iova_fq __percpu *queue;
int cpu;
atomic64_set(&iovad->fq_flush_start_cnt, 0);
atomic64_set(&iovad->fq_flush_finish_cnt, 0);
- iovad->fq = alloc_percpu(struct iova_fq);
- if (!iovad->fq)
+ queue = alloc_percpu(struct iova_fq);
+ if (!queue)
return -ENOMEM;
iovad->flush_cb = flush_cb;
for_each_possible_cpu(cpu) {
struct iova_fq *fq;
- fq = per_cpu_ptr(iovad->fq, cpu);
+ fq = per_cpu_ptr(queue, cpu);
fq->head = 0;
fq->tail = 0;
spin_lock_init(&fq->lock);
}
+ smp_wmb();
+
+ iovad->fq = queue;
+
timer_setup(&iovad->fq_timer, fq_flush_timeout, 0);
atomic_set(&iovad->fq_timer_on, 0);
struct iova *cached_iova;
cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
- if (free->pfn_hi < iovad->dma_32bit_pfn &&
- free->pfn_lo >= cached_iova->pfn_lo) {
+ if (free == cached_iova ||
+ (free->pfn_hi < iovad->dma_32bit_pfn &&
+ free->pfn_lo >= cached_iova->pfn_lo)) {
iovad->cached32_node = rb_next(&free->node);
iovad->max32_alloc_size = iovad->dma_32bit_pfn;
}
/*
* Virtio driver for the paravirtualized IOMMU
*
- * Copyright (C) 2018 Arm Limited
+ * Copyright (C) 2019 Arm Limited
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
/* Device configuration */
struct iommu_domain_geometry geometry;
u64 pgsize_bitmap;
- u8 domain_bits;
+ u32 first_domain;
+ u32 last_domain;
+ /* Supported MAP flags */
+ u32 map_flags;
u32 probe_size;
};
struct viommu_dev *viommu;
struct mutex mutex; /* protects viommu pointer */
unsigned int id;
+ u32 map_flags;
spinlock_t mappings_lock;
struct rb_root_cached mappings;
return -ENOENT;
case VIRTIO_IOMMU_S_FAULT:
return -EFAULT;
+ case VIRTIO_IOMMU_S_NOMEM:
+ return -ENOMEM;
case VIRTIO_IOMMU_S_IOERR:
case VIRTIO_IOMMU_S_DEVERR:
default:
{
int ret;
struct viommu_domain *vdomain = to_viommu_domain(domain);
- unsigned int max_domain = viommu->domain_bits > 31 ? ~0 :
- (1U << viommu->domain_bits) - 1;
vdomain->viommu = viommu;
+ vdomain->map_flags = viommu->map_flags;
domain->pgsize_bitmap = viommu->pgsize_bitmap;
domain->geometry = viommu->geometry;
- ret = ida_alloc_max(&viommu->domain_ids, max_domain, GFP_KERNEL);
+ ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain,
+ viommu->last_domain, GFP_KERNEL);
if (ret >= 0)
vdomain->id = (unsigned int)ret;
phys_addr_t paddr, size_t size, int prot)
{
int ret;
- int flags;
+ u32 flags;
struct virtio_iommu_req_map map;
struct viommu_domain *vdomain = to_viommu_domain(domain);
(prot & IOMMU_WRITE ? VIRTIO_IOMMU_MAP_F_WRITE : 0) |
(prot & IOMMU_MMIO ? VIRTIO_IOMMU_MAP_F_MMIO : 0);
+ if (flags & ~vdomain->map_flags)
+ return -EINVAL;
+
ret = viommu_add_mapping(vdomain, iova, paddr, size, flags);
if (ret)
return ret;
goto err_free_vqs;
}
- viommu->domain_bits = 32;
+ viommu->map_flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE;
+ viommu->last_domain = ~0U;
/* Optional features */
virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
struct virtio_iommu_config, input_range.end,
&input_end);
- virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_BITS,
- struct virtio_iommu_config, domain_bits,
- &viommu->domain_bits);
+ virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+ struct virtio_iommu_config, domain_range.start,
+ &viommu->first_domain);
+
+ virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
+ struct virtio_iommu_config, domain_range.end,
+ &viommu->last_domain);
virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE,
struct virtio_iommu_config, probe_size,
.force_aperture = true,
};
+ if (virtio_has_feature(vdev, VIRTIO_IOMMU_F_MMIO))
+ viommu->map_flags |= VIRTIO_IOMMU_MAP_F_MMIO;
+
viommu_ops.pgsize_bitmap = viommu->pgsize_bitmap;
virtio_device_ready(vdev);
static unsigned int features[] = {
VIRTIO_IOMMU_F_MAP_UNMAP,
- VIRTIO_IOMMU_F_DOMAIN_BITS,
VIRTIO_IOMMU_F_INPUT_RANGE,
+ VIRTIO_IOMMU_F_DOMAIN_RANGE,
VIRTIO_IOMMU_F_PROBE,
+ VIRTIO_IOMMU_F_MMIO,
};
static struct virtio_device_id id_table[] = {
if (!its_alloc_vpe_table(vpe_id)) {
its_vpe_id_free(vpe_id);
- its_free_pending_table(vpe->vpt_page);
+ its_free_pending_table(vpt_page);
return -ENOMEM;
}
case 7:
write_gicreg(0, ICC_AP0R3_EL1);
write_gicreg(0, ICC_AP0R2_EL1);
+ /* Fall through */
case 6:
write_gicreg(0, ICC_AP0R1_EL1);
+ /* Fall through */
case 5:
case 4:
write_gicreg(0, ICC_AP0R0_EL1);
case 7:
write_gicreg(0, ICC_AP1R3_EL1);
write_gicreg(0, ICC_AP1R2_EL1);
+ /* Fall through */
case 6:
write_gicreg(0, ICC_AP1R1_EL1);
+ /* Fall through */
case 5:
case 4:
write_gicreg(0, ICC_AP1R0_EL1);
.irq_unmask = imx_gpcv2_irq_unmask,
.irq_set_wake = imx_gpcv2_irq_set_wake,
.irq_retrigger = irq_chip_retrigger_hierarchy,
+ .irq_set_type = irq_chip_set_type_parent,
#ifdef CONFIG_SMP
.irq_set_affinity = irq_chip_set_affinity_parent,
#endif
parent = platform_bus_type.dev_root;
child = of_platform_device_create(np, NULL, parent);
- if (!child)
+ if (!child) {
+ of_node_put(np);
return -ENOMEM;
+ }
if (of_property_read_u32(child->dev.of_node, "num-pins",
&num_pins) < 0) {
dev_err(&pdev->dev, "No num-pins property\n");
+ of_node_put(np);
return -EINVAL;
}
mbigen_write_msg,
&mbigen_domain_ops,
mgn_chip);
- if (!domain)
+ if (!domain) {
+ of_node_put(np);
return -ENOMEM;
+ }
}
return 0;
printk(KERN_DEBUG
"%s: %s: alloc urb for fifo %i failed",
hw->name, __func__, fifo->fifonum);
+ continue;
}
fifo->iso[i].owner_fifo = (struct usb_fifo *) fifo;
fifo->iso[i].indx = i;
static int
setup_hfcsusb(struct hfcsusb *hw)
{
+ void *dmabuf = kmalloc(sizeof(u_char), GFP_KERNEL);
u_char b;
+ int ret;
if (debug & DBG_HFC_CALL_TRACE)
printk(KERN_DEBUG "%s: %s\n", hw->name, __func__);
+ if (!dmabuf)
+ return -ENOMEM;
+
+ ret = read_reg_atomic(hw, HFCUSB_CHIP_ID, dmabuf);
+
+ memcpy(&b, dmabuf, sizeof(u_char));
+ kfree(dmabuf);
+
/* check the chip id */
- if (read_reg_atomic(hw, HFCUSB_CHIP_ID, &b) != 1) {
+ if (ret != 1) {
printk(KERN_DEBUG "%s: %s: cannot read chip id\n",
hw->name, __func__);
return 1;
break;
case SMU_I2C_TRANSFER_COMBINED:
cmd->info.devaddr &= 0xfe;
+ /* fall through */
case SMU_I2C_TRANSFER_STDSUB:
if (cmd->info.sublen > 3)
return -EINVAL;
if (dc->io_disable) {
pr_err("I/O disabled on cached dev %s",
dc->backing_dev_name);
+ kfree(env[1]);
+ kfree(env[2]);
+ kfree(buf);
return -EIO;
}
"writethrough",
"writeback",
"writearound",
- "none"
+ "none",
+ NULL
};
/* Default is 0 ("auto") */
static const char * const bch_stop_on_failure_modes[] = {
"auto",
- "always"
+ "always",
+ NULL
};
static const char * const cache_replacement_policies[] = {
"lru",
"fifo",
- "random"
+ "random",
+ NULL
};
static const char * const error_actions[] = {
"unregister",
- "panic"
+ "panic",
+ NULL
};
write_attribute(attach);
}
if (attr == &sysfs_cache_mode) {
- v = sysfs_match_string(bch_cache_modes, buf);
+ v = __sysfs_match_string(bch_cache_modes, -1, buf);
if (v < 0)
return v;
}
if (attr == &sysfs_stop_when_cache_set_failed) {
- v = sysfs_match_string(bch_stop_on_failure_modes, buf);
+ v = __sysfs_match_string(bch_stop_on_failure_modes, -1, buf);
if (v < 0)
return v;
0, UINT_MAX);
if (attr == &sysfs_errors) {
- v = sysfs_match_string(error_actions, buf);
+ v = __sysfs_match_string(error_actions, -1, buf);
if (v < 0)
return v;
}
if (attr == &sysfs_cache_replacement_policy) {
- v = sysfs_match_string(cache_replacement_policies, buf);
+ v = __sysfs_match_string(cache_replacement_policies, -1, buf);
if (v < 0)
return v;
unsigned long freed;
c = container_of(shrink, struct dm_bufio_client, shrinker);
- if (!dm_bufio_trylock(c))
+ if (sc->gfp_mask & __GFP_FS)
+ dm_bufio_lock(c);
+ else if (!dm_bufio_trylock(c))
return SHRINK_STOP;
freed = __scan(c, sc->nr_to_scan, sc->gfp_mask);
unsigned long long badblock_count;
spinlock_t dust_lock;
unsigned int blksz;
+ int sect_per_block_shift;
unsigned int sect_per_block;
sector_t start;
bool fail_read_on_bb:1;
unsigned long flags;
spin_lock_irqsave(&dd->dust_lock, flags);
- bblock = dust_rb_search(&dd->badblocklist, block * dd->sect_per_block);
+ bblock = dust_rb_search(&dd->badblocklist, block);
if (bblock == NULL) {
if (!dd->quiet_mode) {
}
spin_lock_irqsave(&dd->dust_lock, flags);
- bblock->bb = block * dd->sect_per_block;
+ bblock->bb = block;
if (!dust_rb_insert(&dd->badblocklist, bblock)) {
if (!dd->quiet_mode) {
DMERR("%s: block %llu already in badblocklist",
unsigned long flags;
spin_lock_irqsave(&dd->dust_lock, flags);
- bblock = dust_rb_search(&dd->badblocklist, block * dd->sect_per_block);
+ bblock = dust_rb_search(&dd->badblocklist, block);
if (bblock != NULL)
DMINFO("%s: block %llu found in badblocklist", __func__, block);
else
int ret = DM_MAPIO_REMAPPED;
if (fail_read_on_bb) {
+ thisblock >>= dd->sect_per_block_shift;
spin_lock_irqsave(&dd->dust_lock, flags);
ret = __dust_map_read(dd, thisblock);
spin_unlock_irqrestore(&dd->dust_lock, flags);
unsigned long flags;
if (fail_read_on_bb) {
+ thisblock >>= dd->sect_per_block_shift;
spin_lock_irqsave(&dd->dust_lock, flags);
__dust_map_write(dd, thisblock);
spin_unlock_irqrestore(&dd->dust_lock, flags);
dd->blksz = blksz;
dd->start = tmp;
+ dd->sect_per_block_shift = __ffs(sect_per_block);
+
/*
* Whether to fail a read on a "bad" block.
* Defaults to false; enabled later by message.
queue_work(ic->wait_wq, &dio->work);
return;
}
+ if (journal_read_pos != NOT_FOUND)
+ dio->range.n_sectors = ic->sectors_per_block;
wait_and_add_new_range(ic, &dio->range);
+ /*
+ * wait_and_add_new_range drops the spinlock, so the journal
+ * may have been changed arbitrarily. We need to recheck.
+ * To simplify the code, we restrict I/O size to just one block.
+ */
+ if (journal_read_pos != NOT_FOUND) {
+ sector_t next_sector;
+ unsigned new_pos = find_journal_node(ic, dio->range.logical_sector, &next_sector);
+ if (unlikely(new_pos != journal_read_pos)) {
+ remove_range_unlocked(ic, &dio->range);
+ goto retry;
+ }
+ }
}
spin_unlock_irq(&ic->endio_wait.lock);
* no point in continuing.
*/
if (test_bit(DM_KCOPYD_WRITE_SEQ, &job->flags) &&
- job->master_job->write_err)
+ job->master_job->write_err) {
+ job->write_err = job->master_job->write_err;
return -EIO;
+ }
io_job_start(job->kc->throttle);
else
job->read_err = 1;
push(&kc->complete_jobs, job);
+ wake(kc);
break;
}
*/
r = rs_prepare_reshape(rs);
if (r)
- return r;
+ goto bad;
/* Reshaping ain't recovery, so disable recovery */
rs_setup_recovery(rs, MaxSector);
/* validate the dax capability of the target device span */
int device_supports_dax(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
+ sector_t start, sector_t len, void *data)
{
int blocksize = *(int *) data;
return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize,
- start, len);
+ start, len);
}
/* Check devices support synchronous DAX */
-static int device_synchronous(struct dm_target *ti, struct dm_dev *dev,
- sector_t start, sector_t len, void *data)
+static int device_dax_synchronous(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
{
- return dax_synchronous(dev->dax_dev);
+ return dev->dax_dev && dax_synchronous(dev->dax_dev);
}
bool dm_table_supports_dax(struct dm_table *t,
- iterate_devices_callout_fn iterate_fn, int *blocksize)
+ iterate_devices_callout_fn iterate_fn, int *blocksize)
{
struct dm_target *ti;
unsigned i;
return false;
if (!ti->type->iterate_devices ||
- !ti->type->iterate_devices(ti, iterate_fn, blocksize))
+ !ti->type->iterate_devices(ti, iterate_fn, blocksize))
return false;
}
}
EXPORT_SYMBOL(dm_table_event);
-sector_t dm_table_get_size(struct dm_table *t)
+inline sector_t dm_table_get_size(struct dm_table *t)
{
return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0;
}
unsigned int l, n = 0, k = 0;
sector_t *node;
+ if (unlikely(sector >= dm_table_get_size(t)))
+ return &t->targets[t->num_targets];
+
for (l = 0; l < t->depth; l++) {
n = get_child(n, k);
node = get_node(t, l, n);
if (dm_table_supports_dax(t, device_supports_dax, &page_size)) {
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
- if (dm_table_supports_dax(t, device_synchronous, NULL))
+ if (dm_table_supports_dax(t, device_dax_synchronous, NULL))
set_dax_synchronous(t->md->dax_dev);
}
else
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 Western Digital Corporation or its affiliates.
*
* (1) Super block (1 block)
* (2) Chunk mapping table (nr_map_blocks)
* (3) Bitmap blocks (nr_bitmap_blocks)
- * All metadata blocks are stored in conventional zones, starting from the
+ * All metadata blocks are stored in conventional zones, starting from
* the first conventional zone found on disk.
*/
struct dmz_super {
* Lock/unlock metadata access. This is a "read" lock on a semaphore
* that prevents metadata flush from running while metadata are being
* modified. The actual metadata write mutual exclusion is achieved with
- * the map lock and zone styate management (active and reclaim state are
+ * the map lock and zone state management (active and reclaim state are
* mutually exclusive).
*/
void dmz_lock_metadata(struct dmz_metadata *zmd)
sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no;
struct bio *bio;
+ if (dmz_bdev_is_dying(zmd->dev))
+ return ERR_PTR(-EIO);
+
/* Get a new block and a BIO to read it */
mblk = dmz_alloc_mblock(zmd, mblk_no);
if (!mblk)
- return NULL;
+ return ERR_PTR(-ENOMEM);
bio = bio_alloc(GFP_NOIO, 1);
if (!bio) {
dmz_free_mblock(zmd, mblk);
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
spin_lock(&zmd->mblk_lock);
if (!mblk) {
/* Cache miss: read the block from disk */
mblk = dmz_get_mblock_slow(zmd, mblk_no);
- if (!mblk)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(mblk))
+ return mblk;
}
/* Wait for on-going read I/O and check for error */
/*
* Issue a metadata block write BIO.
*/
-static void dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
- unsigned int set)
+static int dmz_write_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk,
+ unsigned int set)
{
sector_t block = zmd->sb[set].block + mblk->no;
struct bio *bio;
+ if (dmz_bdev_is_dying(zmd->dev))
+ return -EIO;
+
bio = bio_alloc(GFP_NOIO, 1);
if (!bio) {
set_bit(DMZ_META_ERROR, &mblk->state);
- return;
+ return -ENOMEM;
}
set_bit(DMZ_META_WRITING, &mblk->state);
bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_META | REQ_PRIO);
bio_add_page(bio, mblk->page, DMZ_BLOCK_SIZE, 0);
submit_bio(bio);
+
+ return 0;
}
/*
struct bio *bio;
int ret;
+ if (dmz_bdev_is_dying(zmd->dev))
+ return -EIO;
+
bio = bio_alloc(GFP_NOIO, 1);
if (!bio)
return -ENOMEM;
{
struct dmz_mblock *mblk;
struct blk_plug plug;
- int ret = 0;
+ int ret = 0, nr_mblks_submitted = 0;
/* Issue writes */
blk_start_plug(&plug);
- list_for_each_entry(mblk, write_list, link)
- dmz_write_mblock(zmd, mblk, set);
+ list_for_each_entry(mblk, write_list, link) {
+ ret = dmz_write_mblock(zmd, mblk, set);
+ if (ret)
+ break;
+ nr_mblks_submitted++;
+ }
blk_finish_plug(&plug);
/* Wait for completion */
list_for_each_entry(mblk, write_list, link) {
+ if (!nr_mblks_submitted)
+ break;
wait_on_bit_io(&mblk->state, DMZ_META_WRITING,
TASK_UNINTERRUPTIBLE);
if (test_bit(DMZ_META_ERROR, &mblk->state)) {
clear_bit(DMZ_META_ERROR, &mblk->state);
ret = -EIO;
}
+ nr_mblks_submitted--;
}
/* Flush drive cache (this will also sync data) */
*/
dmz_lock_flush(zmd);
+ if (dmz_bdev_is_dying(zmd->dev)) {
+ ret = -EIO;
+ goto out;
+ }
+
/* Get dirty blocks */
spin_lock(&zmd->mblk_lock);
list_splice_init(&zmd->mblk_dirty_list, &write_list);
struct dm_zone *zone;
if (list_empty(&zmd->map_rnd_list))
- return NULL;
+ return ERR_PTR(-EBUSY);
list_for_each_entry(zone, &zmd->map_rnd_list, link) {
if (dmz_is_buf(zone))
return dzone;
}
- return NULL;
+ return ERR_PTR(-EBUSY);
}
/*
struct dm_zone *zone;
if (list_empty(&zmd->map_seq_list))
- return NULL;
+ return ERR_PTR(-EBUSY);
list_for_each_entry(zone, &zmd->map_seq_list, link) {
if (!zone->bzone)
return zone;
}
- return NULL;
+ return ERR_PTR(-EBUSY);
}
/*
if (op != REQ_OP_WRITE)
goto out;
- /* Alloate a random zone */
+ /* Allocate a random zone */
dzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
if (!dzone) {
+ if (dmz_bdev_is_dying(zmd->dev)) {
+ dzone = ERR_PTR(-EIO);
+ goto out;
+ }
dmz_wait_for_free_zones(zmd);
goto again;
}
if (bzone)
goto out;
- /* Alloate a random zone */
+ /* Allocate a random zone */
bzone = dmz_alloc_zone(zmd, DMZ_ALLOC_RND);
if (!bzone) {
+ if (dmz_bdev_is_dying(zmd->dev)) {
+ bzone = ERR_PTR(-EIO);
+ goto out;
+ }
dmz_wait_for_free_zones(zmd);
goto again;
}
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 Western Digital Corporation or its affiliates.
*
/*
* Number of seconds of target BIO inactivity to consider the target idle.
*/
-#define DMZ_IDLE_PERIOD (10UL * HZ)
+#define DMZ_IDLE_PERIOD (10UL * HZ)
/*
* Percentage of unmapped (free) random zones below which reclaim starts
set_bit(DM_KCOPYD_WRITE_SEQ, &flags);
while (block < end_block) {
+ if (dev->flags & DMZ_BDEV_DYING)
+ return -EIO;
+
/* Get a valid region from the source zone */
ret = dmz_first_valid_block(zmd, src_zone, &block);
if (ret <= 0)
dmz_unlock_flush(zmd);
- return 0;
+ return ret;
}
/*
dmz_unlock_flush(zmd);
- return 0;
+ return ret;
}
/*
dmz_unlock_flush(zmd);
- return 0;
+ return ret;
}
/*
/*
* Find a candidate zone for reclaim and process it.
*/
-static void dmz_reclaim(struct dmz_reclaim *zrc)
+static int dmz_do_reclaim(struct dmz_reclaim *zrc)
{
struct dmz_metadata *zmd = zrc->metadata;
struct dm_zone *dzone;
/* Get a data zone */
dzone = dmz_get_zone_for_reclaim(zmd);
- if (!dzone)
- return;
+ if (IS_ERR(dzone))
+ return PTR_ERR(dzone);
start = jiffies;
out:
if (ret) {
dmz_unlock_zone_reclaim(dzone);
- return;
+ return ret;
}
- (void) dmz_flush_metadata(zrc->metadata);
+ ret = dmz_flush_metadata(zrc->metadata);
+ if (ret) {
+ dmz_dev_debug(zrc->dev,
+ "Metadata flush for zone %u failed, err %d\n",
+ dmz_id(zmd, rzone), ret);
+ return ret;
+ }
dmz_dev_debug(zrc->dev, "Reclaimed zone %u in %u ms",
dmz_id(zmd, rzone), jiffies_to_msecs(jiffies - start));
+ return 0;
}
/*
return false;
/*
- * If the percentage of unmappped random zones is low,
+ * If the percentage of unmapped random zones is low,
* reclaim even if the target is busy.
*/
return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND;
struct dmz_metadata *zmd = zrc->metadata;
unsigned int nr_rnd, nr_unmap_rnd;
unsigned int p_unmap_rnd;
+ int ret;
+
+ if (dmz_bdev_is_dying(zrc->dev))
+ return;
if (!dmz_should_reclaim(zrc)) {
mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
(dmz_target_idle(zrc) ? "Idle" : "Busy"),
p_unmap_rnd, nr_unmap_rnd, nr_rnd);
- dmz_reclaim(zrc);
+ ret = dmz_do_reclaim(zrc);
+ if (ret) {
+ dmz_dev_debug(zrc->dev, "Reclaim error %d\n", ret);
+ if (ret == -EIO)
+ /*
+ * LLD might be performing some error handling sequence
+ * at the underlying device. To not interfere, do not
+ * attempt to schedule the next reclaim run immediately.
+ */
+ return;
+ }
dmz_schedule_reclaim(zrc);
}
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 Western Digital Corporation or its affiliates.
*
refcount_inc(&bioctx->ref);
generic_make_request(clone);
+ if (clone->bi_status == BLK_STS_IOERR)
+ return -EIO;
if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
zone->wp_block += nr_blocks;
/* Get the buffer zone. One will be allocated if needed */
bzone = dmz_get_chunk_buffer(zmd, zone);
- if (!bzone)
- return -ENOSPC;
+ if (IS_ERR(bzone))
+ return PTR_ERR(bzone);
if (dmz_is_readonly(bzone))
return -EROFS;
dmz_lock_metadata(zmd);
+ if (dmz->dev->flags & DMZ_BDEV_DYING) {
+ ret = -EIO;
+ goto out;
+ }
+
/*
* Get the data zone mapping the chunk. There may be no
* mapping for read and discard. If a mapping is obtained,
/* Flush dirty metadata blocks */
ret = dmz_flush_metadata(dmz->metadata);
+ if (ret)
+ dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret);
/* Process queued flush requests */
while (1) {
* Get a chunk work and start it to process a new BIO.
* If the BIO chunk has no work yet, create one.
*/
-static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
+static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
{
unsigned int chunk = dmz_bio_chunk(dmz->dev, bio);
struct dm_chunk_work *cw;
+ int ret = 0;
mutex_lock(&dmz->chunk_lock);
/* Get the BIO chunk work. If one is not active yet, create one */
cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk);
if (!cw) {
- int ret;
/* Create a new chunk work */
cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO);
- if (!cw)
+ if (unlikely(!cw)) {
+ ret = -ENOMEM;
goto out;
+ }
INIT_WORK(&cw->work, dmz_chunk_work);
refcount_set(&cw->refcount, 0);
ret = radix_tree_insert(&dmz->chunk_rxtree, chunk, cw);
if (unlikely(ret)) {
kfree(cw);
- cw = NULL;
goto out;
}
}
bio_list_add(&cw->bio_list, bio);
dmz_get_chunk_work(cw);
+ dmz_reclaim_bio_acc(dmz->reclaim);
if (queue_work(dmz->chunk_wq, &cw->work))
dmz_get_chunk_work(cw);
out:
mutex_unlock(&dmz->chunk_lock);
+ return ret;
+}
+
+/*
+ * Check the backing device availability. If it's on the way out,
+ * start failing I/O. Reclaim and metadata components also call this
+ * function to cleanly abort operation in the event of such failure.
+ */
+bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev)
+{
+ struct gendisk *disk;
+
+ if (!(dmz_dev->flags & DMZ_BDEV_DYING)) {
+ disk = dmz_dev->bdev->bd_disk;
+ if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
+ dmz_dev_warn(dmz_dev, "Backing device queue dying");
+ dmz_dev->flags |= DMZ_BDEV_DYING;
+ } else if (disk->fops->check_events) {
+ if (disk->fops->check_events(disk, 0) &
+ DISK_EVENT_MEDIA_CHANGE) {
+ dmz_dev_warn(dmz_dev, "Backing device offline");
+ dmz_dev->flags |= DMZ_BDEV_DYING;
+ }
+ }
+ }
+
+ return dmz_dev->flags & DMZ_BDEV_DYING;
}
/*
sector_t sector = bio->bi_iter.bi_sector;
unsigned int nr_sectors = bio_sectors(bio);
sector_t chunk_sector;
+ int ret;
+
+ if (dmz_bdev_is_dying(dmz->dev))
+ return DM_MAPIO_KILL;
dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks",
bio_op(bio), (unsigned long long)sector, nr_sectors,
dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector);
/* Now ready to handle this BIO */
- dmz_reclaim_bio_acc(dmz->reclaim);
- dmz_queue_chunk_work(dmz, bio);
+ ret = dmz_queue_chunk_work(dmz, bio);
+ if (ret) {
+ dmz_dev_debug(dmz->dev,
+ "BIO op %d, can't process chunk %llu, err %i\n",
+ bio_op(bio), (u64)dmz_bio_chunk(dmz->dev, bio),
+ ret);
+ return DM_MAPIO_REQUEUE;
+ }
return DM_MAPIO_SUBMITTED;
}
{
struct dmz_target *dmz = ti->private;
+ if (dmz_bdev_is_dying(dmz->dev))
+ return -ENODEV;
+
*bdev = dmz->dev->bdev;
return 0;
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2017 Western Digital Corporation or its affiliates.
*
unsigned int nr_zones;
+ unsigned int flags;
+
sector_t zone_nr_sectors;
unsigned int zone_nr_sectors_shift;
(dev)->zone_nr_sectors_shift)
#define dmz_chunk_block(dev, b) ((b) & ((dev)->zone_nr_blocks - 1))
+/* Device flags. */
+#define DMZ_BDEV_DYING (1 << 0)
+
/*
* Zone descriptor.
*/
void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc);
void dmz_schedule_reclaim(struct dmz_reclaim *zrc);
+/*
+ * Functions defined in dm-zoned-target.c
+ */
+bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev);
+
#endif /* DM_ZONED_H */
new_parent = shadow_current(s);
+ pn = dm_block_data(new_parent);
+ size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
+ sizeof(__le64) : s->info->value_type.size;
+
+ /* create & init the left block */
r = new_block(s->info, &left);
if (r < 0)
return r;
+ ln = dm_block_data(left);
+ nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
+
+ ln->header.flags = pn->header.flags;
+ ln->header.nr_entries = cpu_to_le32(nr_left);
+ ln->header.max_entries = pn->header.max_entries;
+ ln->header.value_size = pn->header.value_size;
+ memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
+ memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
+
+ /* create & init the right block */
r = new_block(s->info, &right);
if (r < 0) {
unlock_block(s->info, left);
return r;
}
- pn = dm_block_data(new_parent);
- ln = dm_block_data(left);
rn = dm_block_data(right);
-
- nr_left = le32_to_cpu(pn->header.nr_entries) / 2;
nr_right = le32_to_cpu(pn->header.nr_entries) - nr_left;
- ln->header.flags = pn->header.flags;
- ln->header.nr_entries = cpu_to_le32(nr_left);
- ln->header.max_entries = pn->header.max_entries;
- ln->header.value_size = pn->header.value_size;
-
rn->header.flags = pn->header.flags;
rn->header.nr_entries = cpu_to_le32(nr_right);
rn->header.max_entries = pn->header.max_entries;
rn->header.value_size = pn->header.value_size;
-
- memcpy(ln->keys, pn->keys, nr_left * sizeof(pn->keys[0]));
memcpy(rn->keys, pn->keys + nr_left, nr_right * sizeof(pn->keys[0]));
-
- size = le32_to_cpu(pn->header.flags) & INTERNAL_NODE ?
- sizeof(__le64) : s->info->value_type.size;
- memcpy(value_ptr(ln, 0), value_ptr(pn, 0), nr_left * size);
memcpy(value_ptr(rn, 0), value_ptr(pn, nr_left),
nr_right * size);
}
if (smm->recursion_count == 1)
- apply_bops(smm);
+ r = apply_bops(smm);
smm->recursion_count--;
*/
pixsize = vout->bpp * vout->vrfb_bpp;
- dst_icg = ((MAX_PIXELS_PER_LINE * pixsize) -
- (vout->pix.width * vout->bpp)) + 1;
+ dst_icg = MAX_PIXELS_PER_LINE * pixsize - vout->pix.width * vout->bpp;
xt->src_start = vout->buf_phy_addr[vb->i];
xt->dst_start = vout->vrfb_context[vb->i].paddr[0];
/* start creating the vb2 queues */
if (dev->has_vid_cap) {
+ snprintf(dev->vid_cap_dev.name, sizeof(dev->vid_cap_dev.name),
+ "vivid-%03d-vid-cap", inst);
/* initialize vid_cap queue */
q = &dev->vb_vid_cap_q;
q->type = dev->multiplanar ? V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
}
if (dev->has_vid_out) {
+ snprintf(dev->vid_out_dev.name, sizeof(dev->vid_out_dev.name),
+ "vivid-%03d-vid-out", inst);
/* initialize vid_out queue */
q = &dev->vb_vid_out_q;
q->type = dev->multiplanar ? V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
/* finally start creating the device nodes */
if (dev->has_vid_cap) {
vfd = &dev->vid_cap_dev;
- snprintf(vfd->name, sizeof(vfd->name),
- "vivid-%03d-vid-cap", inst);
vfd->fops = &vivid_fops;
vfd->ioctl_ops = &vivid_ioctl_ops;
vfd->device_caps = dev->vid_cap_caps;
if (dev->has_vid_out) {
vfd = &dev->vid_out_dev;
- snprintf(vfd->name, sizeof(vfd->name),
- "vivid-%03d-vid-out", inst);
vfd->vfl_dir = VFL_DIR_TX;
vfd->fops = &vivid_fops;
vfd->ioctl_ops = &vivid_ioctl_ops;
static inline int check_pad(struct v4l2_subdev *sd, __u32 pad)
{
#if defined(CONFIG_MEDIA_CONTROLLER)
- if (sd->entity.graph_obj.mdev) {
+ if (sd->entity.num_pads) {
if (pad >= sd->entity.num_pads)
return -EINVAL;
return 0;
switch (divsel) {
case PRCM_DSI_PLLOUT_SEL_PHI_4:
div *= 2;
+ /* Fall through */
case PRCM_DSI_PLLOUT_SEL_PHI_2:
div *= 2;
+ /* Fall through */
case PRCM_DSI_PLLOUT_SEL_PHI:
return pll_rate(PRCM_PLLDSI_FREQ, clock_rate(PRCMU_HDMICLK),
PLL_RAW) / div;
i, r);
}
}
- /* Fall through as HSIC mode needs utmi_clk */
+ /* Fall through - as HSIC mode needs utmi_clk */
case OMAP_EHCI_PORT_MODE_TLL:
if (!IS_ERR(omap->utmi_clk[i])) {
if (!IS_ERR(omap->hsic480m_clk[i]))
clk_disable_unprepare(omap->hsic480m_clk[i]);
- /* Fall through as utmi_clks were used in HSIC mode */
+ /* Fall through - as utmi_clks were used in HSIC mode */
case OMAP_EHCI_PORT_MODE_TLL:
if (!IS_ERR(omap->utmi_clk[i]))
return 0;
}
-static int rk8xx_suspend(struct device *dev)
+static int __maybe_unused rk8xx_suspend(struct device *dev)
{
struct rk808 *rk808 = i2c_get_clientdata(rk808_i2c_client);
int ret = 0;
return ret;
}
-static int rk8xx_resume(struct device *dev)
+static int __maybe_unused rk8xx_resume(struct device *dev)
{
struct rk808 *rk808 = i2c_get_clientdata(rk808_i2c_client);
int ret = 0;
return ret;
}
-SIMPLE_DEV_PM_OPS(rk8xx_pm_ops, rk8xx_suspend, rk8xx_resume);
+static SIMPLE_DEV_PM_OPS(rk8xx_pm_ops, rk8xx_suspend, rk8xx_resume);
static struct i2c_driver rk808_i2c_driver = {
.driver = {
config XILINX_SDFEC
tristate "Xilinx SDFEC 16"
+ depends on HAS_IOMEM
help
This option enables support for the Xilinx SDFEC (Soft Decision
Forward Error Correction) driver. This enables a char driver
tristate "I2C EEPROMs / RAMs / ROMs from most vendors"
depends on I2C && SYSFS
select NVMEM
+ select NVMEM_SYSFS
select REGMAP_I2C
help
Enable this driver to get read/write support to most I2C EEPROMs
tristate "SPI EEPROMs from most vendors"
depends on SPI && SYSFS
select NVMEM
+ select NVMEM_SYSFS
help
Enable this driver to get read/write support to most SPI EEPROMs,
after you configure the board init code to know about each eeprom
depends on SPI && SYSFS
select REGMAP
select NVMEM
+ select NVMEM_SYSFS
help
Driver for the microwire EEPROM chipsets 93xx46x. The driver
supports both read and write commands and also the command to
nvmem_config.name = dev_name(dev);
nvmem_config.dev = dev;
nvmem_config.read_only = !writable;
- nvmem_config.root_only = true;
+ nvmem_config.root_only = !(flags & AT24_FLAG_IRUGO);
nvmem_config.owner = THIS_MODULE;
nvmem_config.compat = true;
nvmem_config.base_dev = dev;
rc = hl_poll_timeout_memory(hdev,
&ctx->thread_ctx_switch_wait_token, tmp, (tmp == 1),
- 100, jiffies_to_usecs(hdev->timeout_jiffies));
+ 100, jiffies_to_usecs(hdev->timeout_jiffies), false);
if (rc == -ETIMEDOUT) {
dev_err(hdev->dev,
rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
if (rc) {
dev_err(hdev->dev, "failed to initialize kernel context\n");
- goto free_ctx;
+ kfree(hdev->kernel_ctx);
+ goto mmu_fini;
}
rc = hl_cb_pool_init(hdev);
if (hl_ctx_put(hdev->kernel_ctx) != 1)
dev_err(hdev->dev,
"kernel ctx is still alive on initialization failure\n");
-free_ctx:
- kfree(hdev->kernel_ctx);
mmu_fini:
hl_mmu_fini(hdev);
eq_fini:
{
const struct firmware *fw;
const u64 *fw_data;
- size_t fw_size, i;
+ size_t fw_size;
int rc;
rc = request_firmware(&fw, fw_name, hdev->dev);
fw_data = (const u64 *) fw->data;
- if ((fw->size % 8) != 0)
- fw_size -= 8;
-
- for (i = 0 ; i < fw_size ; i += 8, fw_data++, dst += 8) {
- if (!(i & (0x80000 - 1))) {
- dev_dbg(hdev->dev,
- "copied so far %zu out of %zu for %s firmware",
- i, fw_size, fw_name);
- usleep_range(20, 100);
- }
-
- writeq(*fw_data, dst);
- }
-
- if ((fw->size % 8) != 0)
- writel(*(const u32 *) fw_data, dst);
+ memcpy_toio(dst, fw_data, fw_size);
out:
release_firmware(fw);
}
rc = hl_poll_timeout_memory(hdev, &pkt->fence, tmp,
- (tmp == ARMCP_PACKET_FENCE_VAL), 1000, timeout);
+ (tmp == ARMCP_PACKET_FENCE_VAL), 1000,
+ timeout, true);
hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
goto free_dma_pool;
}
- dev_dbg(hdev->dev, "cpu accessible memory at bus address 0x%llx\n",
- hdev->cpu_accessible_dma_address);
+ dev_dbg(hdev->dev, "cpu accessible memory at bus address %pad\n",
+ &hdev->cpu_accessible_dma_address);
hdev->cpu_accessible_dma_pool = gen_pool_create(ilog2(32), -1);
if (!hdev->cpu_accessible_dma_pool) {
GOYA_ASYNC_EVENT_ID_PI_UPDATE);
}
-void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val)
+void goya_pqe_write(struct hl_device *hdev, __le64 *pqe, struct hl_bd *bd)
{
- /* Not needed in Goya */
+ /* The QMANs are on the SRAM so need to copy to IO space */
+ memcpy_toio((void __iomem *) pqe, bd, sizeof(struct hl_bd));
}
static void *goya_dma_alloc_coherent(struct hl_device *hdev, size_t size,
}
rc = hl_poll_timeout_memory(hdev, fence_ptr, tmp,
- (tmp == GOYA_QMAN0_FENCE_VAL), 1000, timeout);
+ (tmp == GOYA_QMAN0_FENCE_VAL), 1000,
+ timeout, true);
hl_hw_queue_inc_ci_kernel(hdev, GOYA_QUEUE_ID_DMA_0);
}
rc = hl_poll_timeout_memory(hdev, fence_ptr, tmp, (tmp == fence_val),
- 1000, GOYA_TEST_QUEUE_WAIT_USEC);
+ 1000, GOYA_TEST_QUEUE_WAIT_USEC, true);
hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id);
int rc;
dev_dbg(hdev->dev, "DMA packet details:\n");
- dev_dbg(hdev->dev, "source == 0x%llx\n", user_dma_pkt->src_addr);
- dev_dbg(hdev->dev, "destination == 0x%llx\n", user_dma_pkt->dst_addr);
- dev_dbg(hdev->dev, "size == %u\n", user_dma_pkt->tsize);
+ dev_dbg(hdev->dev, "source == 0x%llx\n",
+ le64_to_cpu(user_dma_pkt->src_addr));
+ dev_dbg(hdev->dev, "destination == 0x%llx\n",
+ le64_to_cpu(user_dma_pkt->dst_addr));
+ dev_dbg(hdev->dev, "size == %u\n", le32_to_cpu(user_dma_pkt->tsize));
ctl = le32_to_cpu(user_dma_pkt->ctl);
user_dir = (ctl & GOYA_PKT_LIN_DMA_CTL_DMA_DIR_MASK) >>
struct packet_lin_dma *user_dma_pkt)
{
dev_dbg(hdev->dev, "DMA packet details:\n");
- dev_dbg(hdev->dev, "source == 0x%llx\n", user_dma_pkt->src_addr);
- dev_dbg(hdev->dev, "destination == 0x%llx\n", user_dma_pkt->dst_addr);
- dev_dbg(hdev->dev, "size == %u\n", user_dma_pkt->tsize);
+ dev_dbg(hdev->dev, "source == 0x%llx\n",
+ le64_to_cpu(user_dma_pkt->src_addr));
+ dev_dbg(hdev->dev, "destination == 0x%llx\n",
+ le64_to_cpu(user_dma_pkt->dst_addr));
+ dev_dbg(hdev->dev, "size == %u\n", le32_to_cpu(user_dma_pkt->tsize));
/*
* WA for HW-23.
dev_dbg(hdev->dev, "WREG32 packet details:\n");
dev_dbg(hdev->dev, "reg_offset == 0x%x\n", reg_offset);
- dev_dbg(hdev->dev, "value == 0x%x\n", wreg_pkt->value);
+ dev_dbg(hdev->dev, "value == 0x%x\n",
+ le32_to_cpu(wreg_pkt->value));
if (reg_offset != (mmDMA_CH_0_WR_COMP_ADDR_LO & 0x1FFF)) {
dev_err(hdev->dev, "WREG32 packet with illegal address 0x%x\n",
while (cb_parsed_length < parser->user_cb_size) {
enum packet_id pkt_id;
u16 pkt_size;
- void *user_pkt;
+ struct goya_packet *user_pkt;
- user_pkt = (void *) (uintptr_t)
+ user_pkt = (struct goya_packet *) (uintptr_t)
(parser->user_cb->kernel_address + cb_parsed_length);
- pkt_id = (enum packet_id) (((*(u64 *) user_pkt) &
+ pkt_id = (enum packet_id) (
+ (le64_to_cpu(user_pkt->header) &
PACKET_HEADER_PACKET_ID_MASK) >>
PACKET_HEADER_PACKET_ID_SHIFT);
* need to validate here as well because patch_cb() is
* not called in MMU path while this function is called
*/
- rc = goya_validate_wreg32(hdev, parser, user_pkt);
+ rc = goya_validate_wreg32(hdev,
+ parser, (struct packet_wreg32 *) user_pkt);
break;
case PACKET_WREG_BULK:
case PACKET_LIN_DMA:
if (is_mmu)
rc = goya_validate_dma_pkt_mmu(hdev, parser,
- user_pkt);
+ (struct packet_lin_dma *) user_pkt);
else
rc = goya_validate_dma_pkt_no_mmu(hdev, parser,
- user_pkt);
+ (struct packet_lin_dma *) user_pkt);
break;
case PACKET_MSG_LONG:
enum packet_id pkt_id;
u16 pkt_size;
u32 new_pkt_size = 0;
- void *user_pkt, *kernel_pkt;
+ struct goya_packet *user_pkt, *kernel_pkt;
- user_pkt = (void *) (uintptr_t)
+ user_pkt = (struct goya_packet *) (uintptr_t)
(parser->user_cb->kernel_address + cb_parsed_length);
- kernel_pkt = (void *) (uintptr_t)
+ kernel_pkt = (struct goya_packet *) (uintptr_t)
(parser->patched_cb->kernel_address +
cb_patched_cur_length);
- pkt_id = (enum packet_id) (((*(u64 *) user_pkt) &
+ pkt_id = (enum packet_id) (
+ (le64_to_cpu(user_pkt->header) &
PACKET_HEADER_PACKET_ID_MASK) >>
PACKET_HEADER_PACKET_ID_SHIFT);
switch (pkt_id) {
case PACKET_LIN_DMA:
- rc = goya_patch_dma_packet(hdev, parser, user_pkt,
- kernel_pkt, &new_pkt_size);
+ rc = goya_patch_dma_packet(hdev, parser,
+ (struct packet_lin_dma *) user_pkt,
+ (struct packet_lin_dma *) kernel_pkt,
+ &new_pkt_size);
cb_patched_cur_length += new_pkt_size;
break;
case PACKET_WREG_32:
memcpy(kernel_pkt, user_pkt, pkt_size);
cb_patched_cur_length += pkt_size;
- rc = goya_validate_wreg32(hdev, parser, kernel_pkt);
+ rc = goya_validate_wreg32(hdev, parser,
+ (struct packet_wreg32 *) kernel_pkt);
break;
case PACKET_WREG_BULK:
size_t total_pkt_size;
long result;
int rc;
+ int irq_num_entries, irq_arr_index;
+ __le32 *goya_irq_arr;
total_pkt_size = sizeof(struct armcp_unmask_irq_arr_packet) +
irq_arr_size;
if (!pkt)
return -ENOMEM;
- pkt->length = cpu_to_le32(irq_arr_size / sizeof(irq_arr[0]));
- memcpy(&pkt->irqs, irq_arr, irq_arr_size);
+ irq_num_entries = irq_arr_size / sizeof(irq_arr[0]);
+ pkt->length = cpu_to_le32(irq_num_entries);
+
+ /* We must perform any necessary endianness conversation on the irq
+ * array being passed to the goya hardware
+ */
+ for (irq_arr_index = 0, goya_irq_arr = (__le32 *) &pkt->irqs;
+ irq_arr_index < irq_num_entries ; irq_arr_index++)
+ goya_irq_arr[irq_arr_index] =
+ cpu_to_le32(irq_arr[irq_arr_index]);
pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY <<
ARMCP_PKT_CTL_OPCODE_SHIFT);
case GOYA_ASYNC_EVENT_ID_AXI_ECC:
case GOYA_ASYNC_EVENT_ID_L2_RAM_ECC:
case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_05_SW_RESET:
- case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT:
goya_print_irq_info(hdev, event_type, false);
hl_device_reset(hdev, true, false);
break;
goya_unmask_irq(hdev, event_type);
break;
+ case GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT:
case GOYA_ASYNC_EVENT_ID_TPC0_BMON_SPMU:
case GOYA_ASYNC_EVENT_ID_TPC1_BMON_SPMU:
case GOYA_ASYNC_EVENT_ID_TPC2_BMON_SPMU:
.resume = goya_resume,
.cb_mmap = goya_cb_mmap,
.ring_doorbell = goya_ring_doorbell,
- .flush_pq_write = goya_flush_pq_write,
+ .pqe_write = goya_pqe_write,
.asic_dma_alloc_coherent = goya_dma_alloc_coherent,
.asic_dma_free_coherent = goya_dma_free_coherent,
.get_int_queue_base = goya_get_int_queue_base,
void goya_late_fini(struct hl_device *hdev);
void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi);
-void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val);
+void goya_pqe_write(struct hl_device *hdev, __le64 *pqe, struct hl_bd *bd);
void goya_update_eq_ci(struct hl_device *hdev, u32 val);
void goya_restore_phase_topology(struct hl_device *hdev);
int goya_context_switch(struct hl_device *hdev, u32 asid);
* @resume: handles IP specific H/W or SW changes for resume.
* @cb_mmap: maps a CB.
* @ring_doorbell: increment PI on a given QMAN.
- * @flush_pq_write: flush PQ entry write if necessary, WARN if flushing failed.
+ * @pqe_write: Write the PQ entry to the PQ. This is ASIC-specific
+ * function because the PQs are located in different memory areas
+ * per ASIC (SRAM, DRAM, Host memory) and therefore, the method of
+ * writing the PQE must match the destination memory area
+ * properties.
* @asic_dma_alloc_coherent: Allocate coherent DMA memory by calling
* dma_alloc_coherent(). This is ASIC function because
* its implementation is not trivial when the driver
int (*cb_mmap)(struct hl_device *hdev, struct vm_area_struct *vma,
u64 kaddress, phys_addr_t paddress, u32 size);
void (*ring_doorbell)(struct hl_device *hdev, u32 hw_queue_id, u32 pi);
- void (*flush_pq_write)(struct hl_device *hdev, u64 *pq, u64 exp_val);
+ void (*pqe_write)(struct hl_device *hdev, __le64 *pqe,
+ struct hl_bd *bd);
void* (*asic_dma_alloc_coherent)(struct hl_device *hdev, size_t size,
dma_addr_t *dma_handle, gfp_t flag);
void (*asic_dma_free_coherent)(struct hl_device *hdev, size_t size,
/*
* address in this macro points always to a memory location in the
* host's (server's) memory. That location is updated asynchronously
- * either by the direct access of the device or by another core
+ * either by the direct access of the device or by another core.
+ *
+ * To work both in LE and BE architectures, we need to distinguish between the
+ * two states (device or another core updates the memory location). Therefore,
+ * if mem_written_by_device is true, the host memory being polled will be
+ * updated directly by the device. If false, the host memory being polled will
+ * be updated by host CPU. Required so host knows whether or not the memory
+ * might need to be byte-swapped before returning value to caller.
*/
-#define hl_poll_timeout_memory(hdev, addr, val, cond, sleep_us, timeout_us) \
+#define hl_poll_timeout_memory(hdev, addr, val, cond, sleep_us, timeout_us, \
+ mem_written_by_device) \
({ \
ktime_t __timeout; \
/* timeout should be longer when working with simulator */ \
/* Verify we read updates done by other cores or by device */ \
mb(); \
(val) = *((u32 *) (uintptr_t) (addr)); \
+ if (mem_written_by_device) \
+ (val) = le32_to_cpu(val); \
if (cond) \
break; \
if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \
(val) = *((u32 *) (uintptr_t) (addr)); \
+ if (mem_written_by_device) \
+ (val) = le32_to_cpu(val); \
break; \
} \
if (sleep_us) \
struct hl_device *hdev = job->cs->ctx->hdev;
struct hl_hw_queue *q = &hdev->kernel_queues[job->hw_queue_id];
struct hl_bd bd;
- u64 *pi, *pbd = (u64 *) &bd;
+ __le64 *pi;
bd.ctl = 0;
- bd.len = __cpu_to_le32(job->job_cb_size);
- bd.ptr = __cpu_to_le64((u64) (uintptr_t) job->user_cb);
+ bd.len = cpu_to_le32(job->job_cb_size);
+ bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb);
- pi = (u64 *) (uintptr_t) (q->kernel_address +
+ pi = (__le64 *) (uintptr_t) (q->kernel_address +
((q->pi & (q->int_queue_len - 1)) * sizeof(bd)));
- pi[0] = pbd[0];
- pi[1] = pbd[1];
-
q->pi++;
q->pi &= ((q->int_queue_len << 1) - 1);
- /* Flush PQ entry write. Relevant only for specific ASICs */
- hdev->asic_funcs->flush_pq_write(hdev, pi, pbd[0]);
+ hdev->asic_funcs->pqe_write(hdev, pi, &bd);
hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi);
}
#define GOYA_PKT_CTL_MB_SHIFT 31
#define GOYA_PKT_CTL_MB_MASK 0x80000000
+/* All packets have, at least, an 8-byte header, which contains
+ * the packet type. The kernel driver uses the packet header for packet
+ * validation and to perform any necessary required preparation before
+ * sending them off to the hardware.
+ */
+struct goya_packet {
+ __le64 header;
+ /* The rest of the packet data follows. Use the corresponding
+ * packet_XXX struct to deference the data, based on packet type
+ */
+ u8 contents[0];
+};
+
struct packet_nop {
__le32 reserved;
__le32 ctl;
struct hl_cs_job *job;
bool shadow_index_valid;
u16 shadow_index;
- u32 *cq_entry;
- u32 *cq_base;
+ struct hl_cq_entry *cq_entry, *cq_base;
if (hdev->disabled) {
dev_dbg(hdev->dev,
return IRQ_HANDLED;
}
- cq_base = (u32 *) (uintptr_t) cq->kernel_address;
+ cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address;
while (1) {
- bool entry_ready = ((cq_base[cq->ci] & CQ_ENTRY_READY_MASK)
+ bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) &
+ CQ_ENTRY_READY_MASK)
>> CQ_ENTRY_READY_SHIFT);
if (!entry_ready)
break;
- cq_entry = (u32 *) &cq_base[cq->ci];
+ cq_entry = (struct hl_cq_entry *) &cq_base[cq->ci];
- /*
- * Make sure we read CQ entry contents after we've
+ /* Make sure we read CQ entry contents after we've
* checked the ownership bit.
*/
dma_rmb();
- shadow_index_valid =
- ((*cq_entry & CQ_ENTRY_SHADOW_INDEX_VALID_MASK)
+ shadow_index_valid = ((le32_to_cpu(cq_entry->data) &
+ CQ_ENTRY_SHADOW_INDEX_VALID_MASK)
>> CQ_ENTRY_SHADOW_INDEX_VALID_SHIFT);
- shadow_index = (u16)
- ((*cq_entry & CQ_ENTRY_SHADOW_INDEX_MASK)
+ shadow_index = (u16) ((le32_to_cpu(cq_entry->data) &
+ CQ_ENTRY_SHADOW_INDEX_MASK)
>> CQ_ENTRY_SHADOW_INDEX_SHIFT);
queue = &hdev->kernel_queues[cq->hw_queue_id];
queue_work(hdev->cq_wq, &job->finish_work);
}
- /*
- * Update ci of the context's queue. There is no
+ /* Update ci of the context's queue. There is no
* need to protect it with spinlock because this update is
* done only inside IRQ and there is a different IRQ per
* queue
queue->ci = hl_queue_inc_ptr(queue->ci);
/* Clear CQ entry ready bit */
- cq_base[cq->ci] &= ~CQ_ENTRY_READY_MASK;
+ cq_entry->data = cpu_to_le32(le32_to_cpu(cq_entry->data) &
+ ~CQ_ENTRY_READY_MASK);
cq->ci = hl_cq_inc_ptr(cq->ci);
dev_dbg(hdev->dev,
"page list 0x%p of asid %d is still alive\n",
phys_pg_list, ctx->asid);
+ atomic64_sub(phys_pg_list->total_size,
+ &hdev->dram_used_mem);
free_phys_pg_pack(hdev, phys_pg_list);
idr_remove(&vm->phys_pg_pack_handles, i);
}
* recurse past the end of THREAD_SIZE by default.
*/
#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN > 0)
-#define REC_STACK_SIZE (CONFIG_FRAME_WARN / 2)
+#define REC_STACK_SIZE (_AC(CONFIG_FRAME_WARN, UL) / 2)
#else
#define REC_STACK_SIZE (THREAD_SIZE / 8)
#endif
void lkdtm_EXHAUST_STACK(void)
{
- pr_info("Calling function with %d frame size to depth %d ...\n",
+ pr_info("Calling function with %lu frame size to depth %d ...\n",
REC_STACK_SIZE, recur_count);
recursive_loop(recur_count);
pr_info("FAIL: survived without exhausting stack?!\n");
#define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */
+#define MEI_DEV_ID_TGP_LP 0xA0E0 /* Tiger Lake Point LP */
+
+#define MEI_DEV_ID_MCC 0x4B70 /* Mule Creek Canyon (EHL) */
+#define MEI_DEV_ID_MCC_4 0x4B75 /* Mule Creek Canyon 4 (EHL) */
+
/*
* MEI HW Section
*/
{MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_TGP_LP, MEI_ME_PCH12_CFG)},
+
+ {MEI_PCI_DEVICE(MEI_DEV_ID_MCC, MEI_ME_PCH12_CFG)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_MCC_4, MEI_ME_PCH8_CFG)},
+
/* required last entry */
{0, }
};
}
if (page) {
- vmballoon_mark_page_offline(page, ctl->page_size);
/* Success. Add the page to the list and continue. */
list_add(&page->lru, &ctl->pages);
continue;
list_for_each_entry_safe(page, tmp, page_list, lru) {
list_del(&page->lru);
- vmballoon_mark_page_online(page, page_size);
__free_pages(page, vmballoon_page_order(page_size));
}
enum vmballoon_page_size_type page_size)
{
unsigned long flags;
+ struct page *page;
if (page_size == VMW_BALLOON_4K_PAGE) {
balloon_page_list_enqueue(&b->b_dev_info, pages);
* for the balloon compaction mechanism.
*/
spin_lock_irqsave(&b->b_dev_info.pages_lock, flags);
+
+ list_for_each_entry(page, pages, lru) {
+ vmballoon_mark_page_offline(page, VMW_BALLOON_2M_PAGE);
+ }
+
list_splice_init(pages, &b->huge_pages);
__count_vm_events(BALLOON_INFLATE, *n_pages *
vmballoon_page_in_frames(VMW_BALLOON_2M_PAGE));
/* 2MB pages */
spin_lock_irqsave(&b->b_dev_info.pages_lock, flags);
list_for_each_entry_safe(page, tmp, &b->huge_pages, lru) {
+ vmballoon_mark_page_online(page, VMW_BALLOON_2M_PAGE);
+
list_move(&page->lru, pages);
if (++i == n_req_pages)
break;
entry = container_of(resource, struct dbell_entry, resource);
if (entry->run_delayed) {
- schedule_work(&entry->work);
+ if (!schedule_work(&entry->work))
+ vmci_resource_put(resource);
} else {
entry->notify_cb(entry->client_data);
vmci_resource_put(resource);
atomic_read(&dbell->active) == 1) {
if (dbell->run_delayed) {
vmci_resource_get(&dbell->resource);
- schedule_work(&dbell->work);
+ if (!schedule_work(&dbell->work))
+ vmci_resource_put(&dbell->resource);
} else {
dbell->notify_cb(dbell->client_data);
}
if (index == EXT_CSD_SANITIZE_START)
cmd.sanitize_busy = true;
- err = mmc_wait_for_cmd(host, &cmd, 0);
+ err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES);
if (err)
goto out;
#include <linux/kthread.h>
#include <linux/scatterlist.h>
#include <linux/dma-mapping.h>
+#include <linux/backing-dev.h>
#include <linux/mmc/card.h>
#include <linux/mmc/host.h>
goto free_tag_set;
}
+ if (mmc_host_is_spi(host) && host->use_spi_crc)
+ mq->queue->backing_dev_info->capabilities |=
+ BDI_CAP_STABLE_WRITES;
+
mq->queue->queuedata = mq;
blk_queue_rq_timeout(mq->queue, 60 * HZ);
goto err;
}
+ /*
+ * Some SD cards claims an out of spec VDD voltage range. Let's treat
+ * these bits as being in-valid and especially also bit7.
+ */
+ ocr &= ~0x7FFF;
+
rocr = mmc_select_voltage(host, ocr);
/*
{
data->bytes_xfered = data->blocks * data->blksz;
data->error = 0;
+ dma_unmap_sg(host->dev, data->sg, data->sg_len, get_dma_dir(data));
return 1;
}
mmc->max_segs = 1;
/* DMA size field can address up to 8 MB */
- mmc->max_seg_size = 8 * 1024 * 1024;
+ mmc->max_seg_size = min_t(unsigned int, 8 * 1024 * 1024,
+ dma_get_max_seg_size(host->dev));
mmc->max_req_size = mmc->max_seg_size;
/* External DMA is in 512 byte blocks */
mmc->max_blk_size = 512;
* delayed. Allowing the transfer to take place
* avoids races and keeps things simple.
*/
- if ((err != -ETIMEDOUT) &&
- (cmd->opcode == MMC_SEND_TUNING_BLOCK)) {
+ if (err != -ETIMEDOUT) {
state = STATE_SENDING_DATA;
continue;
}
#define MESON_MX_SDIO_IRQC_IF_CONFIG_MASK GENMASK(7, 6)
#define MESON_MX_SDIO_IRQC_FORCE_DATA_CLK BIT(8)
#define MESON_MX_SDIO_IRQC_FORCE_DATA_CMD BIT(9)
- #define MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK GENMASK(10, 13)
+ #define MESON_MX_SDIO_IRQC_FORCE_DATA_DAT_MASK GENMASK(13, 10)
#define MESON_MX_SDIO_IRQC_SOFT_RESET BIT(15)
#define MESON_MX_SDIO_IRQC_FORCE_HALT BIT(30)
#define MESON_MX_SDIO_IRQC_HALT_HOLE BIT(31)
sdhci_acpi_byt_setting(&c->pdev->dev);
- return sdhci_runtime_resume_host(c->host);
+ return sdhci_runtime_resume_host(c->host, 0);
}
#endif
host->mmc_host_ops.execute_tuning = sdhci_cdns_execute_tuning;
host->mmc_host_ops.hs400_enhanced_strobe =
sdhci_cdns_hs400_enhanced_strobe;
+ sdhci_enable_v4_mode(host);
sdhci_get_of_property(pdev);
esdhc_pltfm_set_clock(host, imx_data->actual_clock);
}
- err = sdhci_runtime_resume_host(host);
+ err = sdhci_runtime_resume_host(host, 0);
if (err)
goto disable_ipg_clk;
}
out:
- return sdhci_runtime_resume_host(host);
+ return sdhci_runtime_resume_host(host, 0);
}
#endif /* CONFIG_PM */
pm_runtime_set_autosuspend_delay(&pdev->dev, 50);
pm_runtime_use_autosuspend(&pdev->dev);
+ /* HS200 is broken at this moment */
+ host->quirks2 = SDHCI_QUIRK2_BROKEN_HS200;
+
ret = sdhci_add_host(host);
if (ret)
goto pm_runtime_disable;
err_pci_runtime_suspend:
while (--i >= 0)
- sdhci_runtime_resume_host(chip->slots[i]->host);
+ sdhci_runtime_resume_host(chip->slots[i]->host, 0);
return ret;
}
if (!slot)
continue;
- ret = sdhci_runtime_resume_host(slot->host);
+ ret = sdhci_runtime_resume_host(slot->host, 0);
if (ret)
return ret;
}
if (!IS_ERR(pxa->clk_core))
clk_prepare_enable(pxa->clk_core);
- return sdhci_runtime_resume_host(host);
+ return sdhci_runtime_resume_host(host, 0);
}
#endif
clk_prepare_enable(busclk);
if (ourhost->cur_clk >= 0)
clk_prepare_enable(ourhost->clk_bus[ourhost->cur_clk]);
- ret = sdhci_runtime_resume_host(host);
+ ret = sdhci_runtime_resume_host(host, 0);
return ret;
}
#endif
struct sdhci_sprd_host *sprd_host = TO_SPRD_HOST(host);
u32 div, val, mask;
- div = sdhci_sprd_calc_div(sprd_host->base_rate, clk);
+ sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
- clk |= ((div & 0x300) >> 2) | ((div & 0xFF) << 8);
- sdhci_enable_clk(host, clk);
+ div = sdhci_sprd_calc_div(sprd_host->base_rate, clk);
+ div = ((div & 0x300) >> 2) | ((div & 0xFF) << 8);
+ sdhci_enable_clk(host, div);
/* enable auto gate sdhc_enable_auto_gate */
val = sdhci_readl(host, SDHCI_SPRD_REG_32_BUSY_POSI);
return 1 << 31;
}
+static unsigned int sdhci_sprd_get_ro(struct sdhci_host *host)
+{
+ return 0;
+}
+
static struct sdhci_ops sdhci_sprd_ops = {
.read_l = sdhci_sprd_readl,
.write_l = sdhci_sprd_writel,
.set_uhs_signaling = sdhci_sprd_set_uhs_signaling,
.hw_reset = sdhci_sprd_hw_reset,
.get_max_timeout_count = sdhci_sprd_get_max_timeout_count,
+ .get_ro = sdhci_sprd_get_ro,
};
static void sdhci_sprd_request(struct mmc_host *mmc, struct mmc_request *mrq)
}
static const struct sdhci_pltfm_data sdhci_sprd_pdata = {
- .quirks = SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK,
+ .quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
+ SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
+ SDHCI_QUIRK_MISSING_CAPS,
.quirks2 = SDHCI_QUIRK2_BROKEN_HS200 |
- SDHCI_QUIRK2_USE_32BIT_BLK_CNT,
+ SDHCI_QUIRK2_USE_32BIT_BLK_CNT |
+ SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
.ops = &sdhci_sprd_ops,
};
sdhci_enable_v4_mode(host);
+ /*
+ * Supply the existing CAPS, but clear the UHS-I modes. This
+ * will allow these modes to be specified only by device
+ * tree properties through mmc_of_parse().
+ */
+ host->caps = sdhci_readl(host, SDHCI_CAPABILITIES);
+ host->caps1 = sdhci_readl(host, SDHCI_CAPABILITIES_1);
+ host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 |
+ SDHCI_SUPPORT_DDR50);
+
ret = sdhci_setup_host(host);
if (ret)
goto pm_runtime_disable;
sdhci_cleanup_host(host);
pm_runtime_disable:
+ pm_runtime_put_noidle(&pdev->dev);
pm_runtime_disable(&pdev->dev);
pm_runtime_set_suspended(&pdev->dev);
if (ret)
goto clk_disable;
- sdhci_runtime_resume_host(host);
+ sdhci_runtime_resume_host(host, 1);
return 0;
clk_disable:
}
}
+static unsigned int tegra_sdhci_get_ro(struct sdhci_host *host)
+{
+ /*
+ * Write-enable shall be assumed if GPIO is missing in a board's
+ * device-tree because SDHCI's WRITE_PROTECT bit doesn't work on
+ * Tegra.
+ */
+ return mmc_gpio_get_ro(host->mmc);
+}
+
static bool tegra_sdhci_is_pad_and_regulator_valid(struct sdhci_host *host)
{
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
};
static const struct sdhci_ops tegra_sdhci_ops = {
+ .get_ro = tegra_sdhci_get_ro,
.read_w = tegra_sdhci_readw,
.write_l = tegra_sdhci_writel,
.set_clock = tegra_sdhci_set_clock,
};
static const struct sdhci_ops tegra114_sdhci_ops = {
+ .get_ro = tegra_sdhci_get_ro,
.read_w = tegra_sdhci_readw,
.write_w = tegra_sdhci_writew,
.write_l = tegra_sdhci_writel,
};
static const struct sdhci_ops tegra210_sdhci_ops = {
+ .get_ro = tegra_sdhci_get_ro,
.read_w = tegra_sdhci_readw,
.write_w = tegra210_sdhci_writew,
.write_l = tegra_sdhci_writel,
};
static const struct sdhci_ops tegra186_sdhci_ops = {
+ .get_ro = tegra_sdhci_get_ro,
.read_w = tegra_sdhci_readw,
.write_l = tegra_sdhci_writel,
.set_clock = tegra_sdhci_set_clock,
priv->restore_needed = false;
}
- ret = sdhci_runtime_resume_host(host);
+ ret = sdhci_runtime_resume_host(host, 0);
if (ret)
goto out;
return 0;
}
EXPORT_SYMBOL_GPL(sdhci_runtime_suspend_host);
-int sdhci_runtime_resume_host(struct sdhci_host *host)
+int sdhci_runtime_resume_host(struct sdhci_host *host, int soft_reset)
{
struct mmc_host *mmc = host->mmc;
unsigned long flags;
host->ops->enable_dma(host);
}
- sdhci_init(host, 0);
+ sdhci_init(host, soft_reset);
if (mmc->ios.power_mode != MMC_POWER_UNDEFINED &&
mmc->ios.power_mode != MMC_POWER_OFF) {
int sdhci_suspend_host(struct sdhci_host *host);
int sdhci_resume_host(struct sdhci_host *host);
int sdhci_runtime_suspend_host(struct sdhci_host *host);
-int sdhci_runtime_resume_host(struct sdhci_host *host);
+int sdhci_runtime_resume_host(struct sdhci_host *host, int soft_reset);
#endif
void sdhci_cqe_enable(struct mmc_host *mmc);
menuconfig MTD_HYPERBUS
tristate "HyperBus support"
+ depends on HAS_IOMEM
select MTD_CFI
select MTD_MAP_BANK_WIDTH_2
select MTD_CFI_AMDSTD
config HBMC_AM654
tristate "HyperBus controller driver for AM65x SoC"
+ depends on ARM64 || COMPILE_TEST
select MULTIPLEXER
- select MUX_MMIO
+ imply MUX_MMIO
help
This is the driver for HyperBus controller on TI's AM65x and
other SoCs
default:
printk(KERN_WARNING "SA1100 flash: unknown base address "
"0x%08lx, assuming CS0\n", phys);
+ /* Fall through */
case SA1100_CS0_PHYS:
subdev->map.bankwidth = (MSC0 & MSC_RBW) ? 2 : 4;
switch (density) {
case ONENAND_DEVICE_DENSITY_8Gb:
this->options |= ONENAND_HAS_NOP_1;
+ /* fall through */
case ONENAND_DEVICE_DENSITY_4Gb:
if (ONENAND_IS_DDP(this))
this->options |= ONENAND_HAS_2PLANE;
(chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2)
return MICRON_ON_DIE_UNSUPPORTED;
+ /*
+ * It seems that there are devices which do not support ECC officially.
+ * At least the MT29F2G08ABAGA / MT29F2G08ABBGA devices supports
+ * enabling the ECC feature but don't reflect that to the READ_ID table.
+ * So we have to guarantee that we disable the ECC feature directly
+ * after we did the READ_ID table command. Later we can evaluate the
+ * ECC_ENABLE support.
+ */
ret = micron_nand_on_die_ecc_setup(chip, true);
if (ret)
return MICRON_ON_DIE_UNSUPPORTED;
if (ret)
return MICRON_ON_DIE_UNSUPPORTED;
- if (!(id[4] & MICRON_ID_ECC_ENABLED))
- return MICRON_ON_DIE_UNSUPPORTED;
-
ret = micron_nand_on_die_ecc_setup(chip, false);
if (ret)
return MICRON_ON_DIE_UNSUPPORTED;
+ if (!(id[4] & MICRON_ID_ECC_ENABLED))
+ return MICRON_ON_DIE_UNSUPPORTED;
+
ret = nand_readid_op(chip, 0, id, sizeof(id));
if (ret)
return MICRON_ON_DIE_UNSUPPORTED;
default:
/* Kept only for backward compatibility purpose. */
params->quad_enable = spansion_quad_enable;
- if (nor->clear_sr_bp)
- nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp;
break;
}
int err;
if (nor->clear_sr_bp) {
+ if (nor->quad_enable == spansion_quad_enable)
+ nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp;
+
err = nor->clear_sr_bp(nor);
if (err) {
dev_err(nor->dev,
switch (ints[0]) {
default: /* ERROR */
pr_err("Too many arguments\n");
+ /* Fall through */
case 3: /* Node ID */
node = ints[3];
+ /* Fall through */
case 2: /* IRQ */
irq = ints[2];
+ /* Fall through */
case 1: /* IO address */
io = ints[1];
}
switch (ints[0]) {
default: /* ERROR */
pr_info("Too many arguments\n");
+ /* Fall through */
case 6: /* Timeout */
timeout = ints[6];
+ /* Fall through */
case 5: /* CKP value */
clockp = ints[5];
+ /* Fall through */
case 4: /* Backplane flag */
backplane = ints[4];
+ /* Fall through */
case 3: /* Node ID */
node = ints[3];
+ /* Fall through */
case 2: /* IRQ */
irq = ints[2];
+ /* Fall through */
case 1: /* IO address */
io = ints[1];
}
switch (ints[0]) {
default: /* ERROR */
pr_err("Too many arguments\n");
+ /* Fall through */
case 2: /* IRQ */
irq = ints[2];
+ /* Fall through */
case 1: /* IO address */
io = ints[1];
}
switch (ints[0]) {
default: /* ERROR */
pr_err("Too many arguments\n");
+ /* Fall through */
case 3: /* Mem address */
shmem = ints[3];
+ /* Fall through */
case 2: /* IRQ */
irq = ints[2];
+ /* Fall through */
case 1: /* IO address */
io = ints[1];
}
done:
bond_dev->vlan_features = vlan_features;
bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX |
NETIF_F_GSO_UDP_L4;
bond_dev->mpls_features = mpls_features;
bond_dev->gso_max_segs = gso_max_segs;
bond_for_each_slave(bond, slave, iter) {
switch (slave->new_link) {
case BOND_LINK_NOCHANGE:
+ /* For 802.3ad mode, check current slave speed and
+ * duplex again in case its port was disabled after
+ * invalid speed/duplex reporting but recovered before
+ * link monitoring could make a decision on the actual
+ * link status
+ */
+ if (BOND_MODE(bond) == BOND_MODE_8023AD &&
+ slave->link == BOND_LINK_UP)
+ bond_3ad_adapter_speed_duplex_changed(slave);
continue;
case BOND_LINK_UP:
CAN_ERR_CRTL_TX_WARNING :
CAN_ERR_CRTL_RX_WARNING;
}
- case CAN_STATE_ERROR_WARNING: /* fallthrough */
+ /* fall through */
+ case CAN_STATE_ERROR_WARNING:
/*
* from: ERROR_ACTIVE, ERROR_WARNING
* to : ERROR_PASSIVE, BUS_OFF
netdev_dbg(dev, "Error Active\n");
cf->can_id |= CAN_ERR_PROT;
cf->data[2] = CAN_ERR_PROT_ACTIVE;
- case CAN_STATE_ERROR_WARNING: /* fallthrough */
+ /* fall through */
+ case CAN_STATE_ERROR_WARNING:
reg_idr = AT91_IRQ_ERRA | AT91_IRQ_WARN | AT91_IRQ_BOFF;
reg_ier = AT91_IRQ_ERRP;
break;
return -EINVAL;
dev->rtnl_link_ops = &can_link_ops;
+ netif_carrier_off(dev);
+
return register_netdev(dev);
}
EXPORT_SYMBOL_GPL(register_candev);
priv->write(reg_mcr, ®s->mcr);
}
-static inline void flexcan_enter_stop_mode(struct flexcan_priv *priv)
+static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv)
{
struct flexcan_regs __iomem *regs = priv->regs;
+ unsigned int ackval;
u32 reg_mcr;
reg_mcr = priv->read(®s->mcr);
/* enable stop request */
regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr,
1 << priv->stm.req_bit, 1 << priv->stm.req_bit);
+
+ /* get stop acknowledgment */
+ if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr,
+ ackval, ackval & (1 << priv->stm.ack_bit),
+ 0, FLEXCAN_TIMEOUT_US))
+ return -ETIMEDOUT;
+
+ return 0;
}
-static inline void flexcan_exit_stop_mode(struct flexcan_priv *priv)
+static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv)
{
struct flexcan_regs __iomem *regs = priv->regs;
+ unsigned int ackval;
u32 reg_mcr;
/* remove stop request */
regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr,
1 << priv->stm.req_bit, 0);
+ /* get stop acknowledgment */
+ if (regmap_read_poll_timeout(priv->stm.gpr, priv->stm.ack_gpr,
+ ackval, !(ackval & (1 << priv->stm.ack_bit)),
+ 0, FLEXCAN_TIMEOUT_US))
+ return -ETIMEDOUT;
+
reg_mcr = priv->read(®s->mcr);
reg_mcr &= ~FLEXCAN_MCR_SLF_WAK;
priv->write(reg_mcr, ®s->mcr);
+
+ return 0;
}
static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv)
priv = netdev_priv(dev);
priv->stm.gpr = syscon_node_to_regmap(gpr_np);
- of_node_put(gpr_np);
if (IS_ERR(priv->stm.gpr)) {
dev_dbg(&pdev->dev, "could not find gpr regmap\n");
- return PTR_ERR(priv->stm.gpr);
+ ret = PTR_ERR(priv->stm.gpr);
+ goto out_put_node;
}
priv->stm.req_gpr = out_val[1];
device_set_wakeup_capable(&pdev->dev, true);
- return 0;
+out_put_node:
+ of_node_put(gpr_np);
+ return ret;
}
static const struct of_device_id flexcan_of_match[] = {
*/
if (device_may_wakeup(device)) {
enable_irq_wake(dev->irq);
- flexcan_enter_stop_mode(priv);
+ err = flexcan_enter_stop_mode(priv);
+ if (err)
+ return err;
} else {
err = flexcan_chip_disable(priv);
if (err)
{
struct net_device *dev = dev_get_drvdata(device);
struct flexcan_priv *priv = netdev_priv(dev);
+ int err;
if (netif_running(dev) && device_may_wakeup(device)) {
flexcan_enable_wakeup_irq(priv, false);
- flexcan_exit_stop_mode(priv);
+ err = flexcan_exit_stop_mode(priv);
+ if (err)
+ return err;
}
return 0;
pciefd_can_writereg(priv, CANFD_CLK_SEL_80MHZ,
PCIEFD_REG_CAN_CLK_SEL);
- /* fallthough */
+ /* fall through */
case CANFD_CLK_SEL_80MHZ:
priv->ucan.can.clock.freq = 80 * 1000 * 1000;
break;
/* All packets processed */
if (num_pkts < quota) {
- napi_complete_done(napi, num_pkts);
- /* Enable Rx FIFO interrupts */
- rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx),
- RCANFD_RFCC_RFIE);
+ if (napi_complete_done(napi, num_pkts)) {
+ /* Enable Rx FIFO interrupts */
+ rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx),
+ RCANFD_RFCC_RFIE);
+ }
}
return num_pkts;
}
if (!netdev)
continue;
- strncpy(name, netdev->name, IFNAMSIZ);
+ strlcpy(name, netdev->name, IFNAMSIZ);
unregister_sja1000dev(netdev);
return regulator_disable(reg);
}
-static void mcp251x_open_clean(struct net_device *net)
-{
- struct mcp251x_priv *priv = netdev_priv(net);
- struct spi_device *spi = priv->spi;
-
- free_irq(spi->irq, priv);
- mcp251x_hw_sleep(spi);
- mcp251x_power_enable(priv->transceiver, 0);
- close_candev(net);
-}
-
static int mcp251x_stop(struct net_device *net)
{
struct mcp251x_priv *priv = netdev_priv(net);
if (new_state >= CAN_STATE_ERROR_WARNING &&
new_state <= CAN_STATE_BUS_OFF)
priv->can.can_stats.error_warning++;
- case CAN_STATE_ERROR_WARNING: /* fallthrough */
+ /* fall through */
+ case CAN_STATE_ERROR_WARNING:
if (new_state >= CAN_STATE_ERROR_PASSIVE &&
new_state <= CAN_STATE_BUS_OFF)
priv->can.can_stats.error_passive++;
flags | IRQF_ONESHOT, DEVICE_NAME, priv);
if (ret) {
dev_err(&spi->dev, "failed to acquire irq %d\n", spi->irq);
- mcp251x_power_enable(priv->transceiver, 0);
- close_candev(net);
- goto open_unlock;
+ goto out_close;
}
priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
0);
+ if (!priv->wq) {
+ ret = -ENOMEM;
+ goto out_clean;
+ }
INIT_WORK(&priv->tx_work, mcp251x_tx_work_handler);
INIT_WORK(&priv->restart_work, mcp251x_restart_work_handler);
ret = mcp251x_hw_reset(spi);
- if (ret) {
- mcp251x_open_clean(net);
- goto open_unlock;
- }
+ if (ret)
+ goto out_free_wq;
ret = mcp251x_setup(net, spi);
- if (ret) {
- mcp251x_open_clean(net);
- goto open_unlock;
- }
+ if (ret)
+ goto out_free_wq;
ret = mcp251x_set_normal_mode(spi);
- if (ret) {
- mcp251x_open_clean(net);
- goto open_unlock;
- }
+ if (ret)
+ goto out_free_wq;
can_led_event(net, CAN_LED_EVENT_OPEN);
netif_wake_queue(net);
+ mutex_unlock(&priv->mcp_lock);
-open_unlock:
+ return 0;
+
+out_free_wq:
+ destroy_workqueue(priv->wq);
+out_clean:
+ free_irq(spi->irq, priv);
+ mcp251x_hw_sleep(spi);
+out_close:
+ mcp251x_power_enable(priv->transceiver, 0);
+ close_candev(net);
mutex_unlock(&priv->mcp_lock);
return ret;
}
new_state = CAN_STATE_ERROR_WARNING;
break;
}
- /* else: fall through */
+ /* fall through */
case CAN_STATE_ERROR_WARNING:
if (n & PCAN_USB_ERROR_BUS_HEAVY) {
dev->state &= ~PCAN_USB_STATE_STARTED;
netif_stop_queue(netdev);
+ close_candev(netdev);
+
+ dev->can.state = CAN_STATE_STOPPED;
+
/* unlink all pending urbs and free used memory */
peak_usb_unlink_all_urbs(dev);
if (dev->adapter->dev_stop)
dev->adapter->dev_stop(dev);
- close_candev(netdev);
-
- dev->can.state = CAN_STATE_STOPPED;
-
/* can set bus off now */
if (dev->adapter->dev_set_bus) {
int err = dev->adapter->dev_set_bus(dev, 0);
dev_prev_siblings = dev->prev_siblings;
dev->state &= ~PCAN_USB_STATE_CONNECTED;
- strncpy(name, netdev->name, IFNAMSIZ);
+ strlcpy(name, netdev->name, IFNAMSIZ);
unregister_netdev(netdev);
goto err_out;
/* allocate command buffer once for all for the interface */
- pdev->cmd_buffer_addr = kmalloc(PCAN_UFD_CMD_BUFFER_SIZE,
+ pdev->cmd_buffer_addr = kzalloc(PCAN_UFD_CMD_BUFFER_SIZE,
GFP_KERNEL);
if (!pdev->cmd_buffer_addr)
goto err_out_1;
u8 *buffer;
int err;
- buffer = kmalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL);
+ buffer = kzalloc(PCAN_USBPRO_FCT_DRVLD_REQ_LEN, GFP_KERNEL);
if (!buffer)
return -ENOMEM;
unsigned long *supported,
struct phylink_link_state *state)
{
+ struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
if (!phy_interface_mode_is_rgmii(state->interface) &&
state->interface != PHY_INTERFACE_MODE_INTERNAL &&
state->interface != PHY_INTERFACE_MODE_MOCA) {
bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS);
- dev_err(ds->dev,
- "Unsupported interface: %d\n", state->interface);
+ if (port != core_readl(priv, CORE_IMP0_PRT_ID))
+ dev_err(ds->dev,
+ "Unsupported interface: %d for port %d\n",
+ state->interface, port);
return;
}
u32 id_mode_dis = 0, port_mode;
u32 reg, offset;
+ if (port == core_readl(priv, CORE_IMP0_PRT_ID))
+ return;
+
if (priv->type == BCM7445_DEVICE_ID)
offset = CORE_STS_OVERRIDE_GMIIP_PORT(port);
else
{ .compatible = "microchip,ksz9897" },
{ .compatible = "microchip,ksz9893" },
{ .compatible = "microchip,ksz9563" },
+ { .compatible = "microchip,ksz8563" },
{},
};
MODULE_DEVICE_TABLE(of, ksz9477_dt_ids);
#define KSZ_REGMAP_ENTRY(width, swp, regbits, regpad, regalign) \
{ \
+ .name = #width, \
.val_bits = (width), \
.reg_stride = (width) / 8, \
.reg_bits = (regbits) + (regalign), \
#include <linux/platform_data/mv88e6xxx.h>
#include <linux/netdevice.h>
#include <linux/gpio/consumer.h>
-#include <linux/phy.h>
#include <linux/phylink.h>
#include <net/dsa.h>
return 0;
/* Port's MAC control must not be changed unless the link is down */
- err = chip->info->ops->port_set_link(chip, port, 0);
+ err = chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN);
if (err)
return err;
return port < chip->info->num_internal_phys;
}
-/* We expect the switch to perform auto negotiation if there is a real
- * phy. However, in the case of a fixed link phy, we force the port
- * settings from the fixed link settings.
- */
-static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
- struct phy_device *phydev)
-{
- struct mv88e6xxx_chip *chip = ds->priv;
- int err;
-
- if (!phy_is_pseudo_fixed_link(phydev) &&
- mv88e6xxx_phy_is_internal(ds, port))
- return;
-
- mv88e6xxx_reg_lock(chip);
- err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed,
- phydev->duplex, phydev->pause,
- phydev->interface);
- mv88e6xxx_reg_unlock(chip);
-
- if (err && err != -EOPNOTSUPP)
- dev_err(ds->dev, "p%d: failed to configure MAC\n", port);
-}
-
static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port,
unsigned long *mask,
struct phylink_link_state *state)
err = mv88e6xxx_mdio_register(chip, child, true);
if (err) {
mv88e6xxx_mdios_unregister(chip);
+ of_node_put(child);
return err;
}
}
static const struct dsa_switch_ops mv88e6xxx_switch_ops = {
.get_tag_protocol = mv88e6xxx_get_tag_protocol,
.setup = mv88e6xxx_setup,
- .adjust_link = mv88e6xxx_adjust_link,
.phylink_validate = mv88e6xxx_validate,
.phylink_mac_link_state = mv88e6xxx_link_state,
.phylink_mac_config = mv88e6xxx_mac_config,
/*
* Copyright (C) 2009 Felix Fietkau <nbd@nbd.name>
* Copyright (C) 2011-2012 Gabor Juhos <juhosg@openwrt.org>
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2015, 2019, The Linux Foundation. All rights reserved.
* Copyright (c) 2016 John Crispin <john@phrozen.org>
*/
for_each_available_child_of_node(ports, port) {
err = of_property_read_u32(port, "reg", ®);
- if (err)
+ if (err) {
+ of_node_put(port);
+ of_node_put(ports);
return err;
+ }
if (!dsa_is_user_port(priv->ds, reg))
continue;
internal_mdio_mask |= BIT(reg);
}
+ of_node_put(ports);
if (!external_mdio_mask && !internal_mdio_mask) {
dev_err(priv->dev, "no PHYs are defined.\n");
return -EINVAL;
qca8k_port_set_status(priv, port, 1);
priv->port_sts[port].enabled = 1;
+ phy_support_asym_pause(phy);
+
return 0;
}
SJA1105ET_SIZE_L2_LOOKUP_ENTRY, op);
}
+static size_t sja1105et_dyn_l2_lookup_entry_packing(void *buf, void *entry_ptr,
+ enum packing_op op)
+{
+ struct sja1105_l2_lookup_entry *entry = entry_ptr;
+ u8 *cmd = buf + SJA1105ET_SIZE_L2_LOOKUP_ENTRY;
+ const int size = SJA1105_SIZE_DYN_CMD;
+
+ sja1105_packing(cmd, &entry->lockeds, 28, 28, size, op);
+
+ return sja1105et_l2_lookup_entry_packing(buf, entry_ptr, op);
+}
+
static void
sja1105et_mgmt_route_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
enum packing_op op)
/* SJA1105E/T: First generation */
struct sja1105_dynamic_table_ops sja1105et_dyn_ops[BLK_IDX_MAX_DYN] = {
[BLK_IDX_L2_LOOKUP] = {
- .entry_packing = sja1105et_l2_lookup_entry_packing,
+ .entry_packing = sja1105et_dyn_l2_lookup_entry_packing,
.cmd_packing = sja1105et_l2_lookup_cmd_packing,
.access = (OP_READ | OP_WRITE | OP_DEL),
.max_entry_count = SJA1105_MAX_L2_LOOKUP_COUNT,
/* This selects between Independent VLAN Learning (IVL) and
* Shared VLAN Learning (SVL)
*/
- .shared_learn = false,
+ .shared_learn = true,
/* Don't discard management traffic based on ENFPORT -
* we don't perform SMAC port enforcement anyway, so
* what we are setting here doesn't matter.
if (of_property_read_u32(child, "reg", &index) < 0) {
dev_err(dev, "Port number not defined in device tree "
"(property \"reg\")\n");
+ of_node_put(child);
return -ENODEV;
}
dev_err(dev, "Failed to read phy-mode or "
"phy-interface-type property for port %d\n",
index);
+ of_node_put(child);
return -ENODEV;
}
ports[index].phy_mode = phy_mode;
if (!of_phy_is_fixed_link(child)) {
dev_err(dev, "phy-handle or fixed-link "
"properties missing!\n");
+ of_node_put(child);
return -ENODEV;
}
/* phy-handle is missing, but fixed-link isn't.
l2_lookup.vlanid = vid;
l2_lookup.iotag = SJA1105_S_TAG;
l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0);
- l2_lookup.mask_vlanid = VLAN_VID_MASK;
- l2_lookup.mask_iotag = BIT(0);
+ if (dsa_port_is_vlan_filtering(&ds->ports[port])) {
+ l2_lookup.mask_vlanid = VLAN_VID_MASK;
+ l2_lookup.mask_iotag = BIT(0);
+ } else {
+ l2_lookup.mask_vlanid = 0;
+ l2_lookup.mask_iotag = 0;
+ }
l2_lookup.destports = BIT(port);
rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
l2_lookup.vlanid = vid;
l2_lookup.iotag = SJA1105_S_TAG;
l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0);
- l2_lookup.mask_vlanid = VLAN_VID_MASK;
- l2_lookup.mask_iotag = BIT(0);
+ if (dsa_port_is_vlan_filtering(&ds->ports[port])) {
+ l2_lookup.mask_vlanid = VLAN_VID_MASK;
+ l2_lookup.mask_iotag = BIT(0);
+ } else {
+ l2_lookup.mask_vlanid = 0;
+ l2_lookup.mask_iotag = 0;
+ }
l2_lookup.destports = BIT(port);
rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
const unsigned char *addr, u16 vid)
{
struct sja1105_private *priv = ds->priv;
- u16 rx_vid, tx_vid;
- int rc, i;
- if (dsa_port_is_vlan_filtering(&ds->ports[port]))
- return priv->info->fdb_add_cmd(ds, port, addr, vid);
-
- /* Since we make use of VLANs even when the bridge core doesn't tell us
- * to, translate these FDB entries into the correct dsa_8021q ones.
- * The basic idea (also repeats for removal below) is:
- * - Each of the other front-panel ports needs to be able to forward a
- * pvid-tagged (aka tagged with their rx_vid) frame that matches this
- * DMAC.
- * - The CPU port (aka the tx_vid of this port) needs to be able to
- * send a frame matching this DMAC to the specified port.
- * For a better picture see net/dsa/tag_8021q.c.
+ /* dsa_8021q is in effect when the bridge's vlan_filtering isn't,
+ * so the switch still does some VLAN processing internally.
+ * But Shared VLAN Learning (SVL) is also active, and it will take
+ * care of autonomous forwarding between the unique pvid's of each
+ * port. Here we just make sure that users can't add duplicate FDB
+ * entries when in this mode - the actual VID doesn't matter except
+ * for what gets printed in 'bridge fdb show'. In the case of zero,
+ * no VID gets printed at all.
*/
- for (i = 0; i < SJA1105_NUM_PORTS; i++) {
- if (i == port)
- continue;
- if (i == dsa_upstream_port(priv->ds, port))
- continue;
+ if (!dsa_port_is_vlan_filtering(&ds->ports[port]))
+ vid = 0;
- rx_vid = dsa_8021q_rx_vid(ds, i);
- rc = priv->info->fdb_add_cmd(ds, port, addr, rx_vid);
- if (rc < 0)
- return rc;
- }
- tx_vid = dsa_8021q_tx_vid(ds, port);
- return priv->info->fdb_add_cmd(ds, port, addr, tx_vid);
+ return priv->info->fdb_add_cmd(ds, port, addr, vid);
}
static int sja1105_fdb_del(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid)
{
struct sja1105_private *priv = ds->priv;
- u16 rx_vid, tx_vid;
- int rc, i;
- if (dsa_port_is_vlan_filtering(&ds->ports[port]))
- return priv->info->fdb_del_cmd(ds, port, addr, vid);
+ if (!dsa_port_is_vlan_filtering(&ds->ports[port]))
+ vid = 0;
- for (i = 0; i < SJA1105_NUM_PORTS; i++) {
- if (i == port)
- continue;
- if (i == dsa_upstream_port(priv->ds, port))
- continue;
-
- rx_vid = dsa_8021q_rx_vid(ds, i);
- rc = priv->info->fdb_del_cmd(ds, port, addr, rx_vid);
- if (rc < 0)
- return rc;
- }
- tx_vid = dsa_8021q_tx_vid(ds, port);
- return priv->info->fdb_del_cmd(ds, port, addr, tx_vid);
+ return priv->info->fdb_del_cmd(ds, port, addr, vid);
}
static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
{
struct sja1105_private *priv = ds->priv;
struct device *dev = ds->dev;
- u16 rx_vid, tx_vid;
int i;
- rx_vid = dsa_8021q_rx_vid(ds, port);
- tx_vid = dsa_8021q_tx_vid(ds, port);
-
for (i = 0; i < SJA1105_MAX_L2_LOOKUP_COUNT; i++) {
struct sja1105_l2_lookup_entry l2_lookup = {0};
u8 macaddr[ETH_ALEN];
continue;
u64_to_ether_addr(l2_lookup.macaddr, macaddr);
- /* On SJA1105 E/T, the switch doesn't implement the LOCKEDS
- * bit, so it doesn't tell us whether a FDB entry is static
- * or not.
- * But, of course, we can find out - we're the ones who added
- * it in the first place.
- */
- if (priv->info->device_id == SJA1105E_DEVICE_ID ||
- priv->info->device_id == SJA1105T_DEVICE_ID) {
- int match;
-
- match = sja1105_find_static_fdb_entry(priv, port,
- &l2_lookup);
- l2_lookup.lockeds = (match >= 0);
- }
-
- /* We need to hide the dsa_8021q VLANs from the user. This
- * basically means hiding the duplicates and only showing
- * the pvid that is supposed to be active in standalone and
- * non-vlan_filtering modes (aka 1).
- * - For statically added FDB entries (bridge fdb add), we
- * can convert the TX VID (coming from the CPU port) into the
- * pvid and ignore the RX VIDs of the other ports.
- * - For dynamically learned FDB entries, a single entry with
- * no duplicates is learned - that which has the real port's
- * pvid, aka RX VID.
- */
- if (!dsa_port_is_vlan_filtering(&ds->ports[port])) {
- if (l2_lookup.vlanid == tx_vid ||
- l2_lookup.vlanid == rx_vid)
- l2_lookup.vlanid = 1;
- else
- continue;
- }
+ /* We need to hide the dsa_8021q VLANs from the user. */
+ if (!dsa_port_is_vlan_filtering(&ds->ports[port]))
+ l2_lookup.vlanid = 0;
cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data);
}
return 0;
*/
static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled)
{
+ struct sja1105_l2_lookup_params_entry *l2_lookup_params;
struct sja1105_general_params_entry *general_params;
struct sja1105_private *priv = ds->priv;
struct sja1105_table *table;
general_params->incl_srcpt1 = enabled;
general_params->incl_srcpt0 = enabled;
+ /* VLAN filtering => independent VLAN learning.
+ * No VLAN filtering => shared VLAN learning.
+ *
+ * In shared VLAN learning mode, untagged traffic still gets
+ * pvid-tagged, and the FDB table gets populated with entries
+ * containing the "real" (pvid or from VLAN tag) VLAN ID.
+ * However the switch performs a masked L2 lookup in the FDB,
+ * effectively only looking up a frame's DMAC (and not VID) for the
+ * forwarding decision.
+ *
+ * This is extremely convenient for us, because in modes with
+ * vlan_filtering=0, dsa_8021q actually installs unique pvid's into
+ * each front panel port. This is good for identification but breaks
+ * learning badly - the VID of the learnt FDB entry is unique, aka
+ * no frames coming from any other port are going to have it. So
+ * for forwarding purposes, this is as though learning was broken
+ * (all frames get flooded).
+ */
+ table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS];
+ l2_lookup_params = table->entries;
+ l2_lookup_params->shared_learn = !enabled;
+
rc = sja1105_static_config_reload(priv);
if (rc)
dev_err(ds->dev, "Failed to change VLAN Ethertype\n");
cancel_work_sync(&priv->tagger_data.rxtstamp_work);
skb_queue_purge(&priv->tagger_data.skb_rxtstamp_queue);
+ sja1105_ptp_clock_unregister(priv);
+ sja1105_static_config_free(&priv->static_config);
}
static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot,
{
struct sja1105_private *priv = spi_get_drvdata(spi);
- sja1105_ptp_clock_unregister(priv);
dsa_unregister_switch(priv->ds);
- sja1105_static_config_free(&priv->static_config);
return 0;
}
.mult = SJA1105_CC_MULT,
};
mutex_init(&priv->ptp_lock);
- INIT_DELAYED_WORK(&priv->refresh_work, sja1105_ptp_overflow_check);
-
- schedule_delayed_work(&priv->refresh_work, SJA1105_REFRESH_INTERVAL);
-
priv->ptp_caps = sja1105_ptp_caps;
priv->clock = ptp_clock_register(&priv->ptp_caps, ds->dev);
if (IS_ERR_OR_NULL(priv->clock))
return PTR_ERR(priv->clock);
+ INIT_DELAYED_WORK(&priv->refresh_work, sja1105_ptp_overflow_check);
+ schedule_delayed_work(&priv->refresh_work, SJA1105_REFRESH_INTERVAL);
+
return sja1105_ptp_reset(priv);
}
Note that the answer to this question doesn't directly affect the
kernel: saying N will just cause the configurator to skip all
- the questions about Western Digital cards. If you say Y, you will be
- asked for your specific card in the following questions.
+ the questions about National Semiconductor 8390 cards. If you say Y,
+ you will be asked for your specific card in the following questions.
if NET_VENDOR_8390
/* Allocate memory for the TCB's (Transmit Control Block) */
tx_ring->tcb_ring = kcalloc(NUM_TCB, sizeof(struct tcb),
- GFP_ATOMIC | GFP_DMA);
+ GFP_KERNEL | GFP_DMA);
if (!tx_ring->tcb_ring)
return -ENOMEM;
goto out_clk_disable_unprepare;
}
- db->phy_node = of_parse_phandle(np, "phy", 0);
+ db->phy_node = of_parse_phandle(np, "phy-handle", 0);
+ if (!db->phy_node)
+ db->phy_node = of_parse_phandle(np, "phy", 0);
if (!db->phy_node) {
dev_err(&pdev->dev, "no associated PHY\n");
ret = -ENODEV;
say Y.
Note that the answer to this question does not directly affect
- the kernel: saying N will just case the configurator to skip all
+ the kernel: saying N will just cause the configurator to skip all
the questions regarding AMD chipsets. If you say Y, you will be asked
for your specific chipset/driver in the following questions.
ret = xgbe_platform_init();
if (ret)
- return ret;
+ goto err_platform_init;
ret = xgbe_pci_init();
if (ret)
- return ret;
+ goto err_pci_init;
return 0;
+
+err_pci_init:
+ xgbe_platform_exit();
+err_platform_init:
+ unregister_netdevice_notifier(&xgbe_netdev_notifier);
+ return ret;
}
static void __exit xgbe_mod_exit(void)
If you have a network (Ethernet) card belonging to this class, say Y.
Note that the answer to this question doesn't directly affect the
- kernel: saying N will just cause the configurator to skip all
- the questions about IBM devices. If you say Y, you will be asked for
+ kernel: saying N will just cause the configurator to skip all the
+ questions about Apple devices. If you say Y, you will be asked for
your specific card in the following questions.
if NET_VENDOR_APPLE
if (be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id)
break;
}
- if (rule && be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id) {
+ if (rule && rule->type == aq_rx_filter_vlan &&
+ be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id) {
struct ethtool_rxnfc cmd;
cmd.fs.location = rule->aq_fsp.location;
return err;
if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
- if (hweight < AQ_VLAN_MAX_FILTERS && hweight > 0) {
+ if (hweight <= AQ_VLAN_MAX_FILTERS && hweight > 0) {
err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw,
!(aq_nic->packet_filter & IFF_PROMISC));
aq_nic->aq_nic_cfg.is_vlan_force_promisc = false;
if (err < 0)
goto err_exit;
+ err = aq_filters_vlans_update(aq_nic);
+ if (err < 0)
+ goto err_exit;
+
err = aq_nic_start(aq_nic);
if (err < 0)
goto err_exit;
self->aq_nic_cfg.link_irq_vec);
err = request_threaded_irq(irqvec, NULL,
aq_linkstate_threaded_isr,
- IRQF_SHARED,
+ IRQF_SHARED | IRQF_ONESHOT,
self->ndev->name, self);
if (err < 0)
goto err_exit;
}
}
+err_exit:
if (!was_tx_cleaned)
work_done = budget;
1U << self->aq_ring_param.vec_idx);
}
}
-err_exit:
+
return work_done;
}
tx->descs_cpu = dma_alloc_coherent(&ag->pdev->dev,
ring_size * AG71XX_DESC_SIZE,
- &tx->descs_dma, GFP_ATOMIC);
+ &tx->descs_dma, GFP_KERNEL);
if (!tx->descs_cpu) {
kfree(tx->buf);
tx->buf = NULL;
say Y.
Note that the answer to this question does not directly affect
- the kernel: saying N will just case the configurator to skip all
- the questions regarding AMD chipsets. If you say Y, you will be asked
- for your specific chipset/driver in the following questions.
+ the kernel: saying N will just cause the configurator to skip all
+ the questions regarding Broadcom chipsets. If you say Y, you will
+ be asked for your specific chipset/driver in the following questions.
if NET_VENDOR_BROADCOM
{
struct bcm_sysport_priv *priv =
container_of(napi, struct bcm_sysport_priv, napi);
- struct dim_sample dim_sample;
+ struct dim_sample dim_sample = {};
unsigned int work_done = 0;
work_done = bcm_sysport_desc_rx(priv, budget);
hw_cons = le16_to_cpu(*txdata->tx_cons_sb);
sw_cons = txdata->tx_pkt_cons;
+ /* Ensure subsequent loads occur after hw_cons */
+ smp_rmb();
+
while (sw_cons != hw_cons) {
u16 pkt_cons;
}
/* select a non-FCoE queue */
- return netdev_pick_tx(dev, skb, NULL) %
- (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+ return netdev_pick_tx(dev, skb, NULL) % (BNX2X_NUM_ETH_QUEUES(bp));
}
void bnx2x_set_num_queues(struct bnx2x *bp)
/* if VF indicate to PF this function is going down (PF will delete sp
* elements and clear initializations
*/
- if (IS_VF(bp))
+ if (IS_VF(bp)) {
+ bnx2x_clear_vlan_info(bp);
bnx2x_vfpf_close_vf(bp);
- else if (unload_mode != UNLOAD_RECOVERY)
+ } else if (unload_mode != UNLOAD_RECOVERY) {
/* if this is a normal/close unload need to clean up chip*/
bnx2x_chip_cleanup(bp, unload_mode, keep_link);
- else {
+ } else {
/* Send the UNLOAD_REQUEST to the MCP */
bnx2x_send_unload_req(bp, unload_mode);
void bnx2x_disable_close_the_gate(struct bnx2x *bp);
int bnx2x_init_hw_func_cnic(struct bnx2x *bp);
+void bnx2x_clear_vlan_info(struct bnx2x *bp);
+
/**
* bnx2x_sp_event - handle ramrods completion.
*
return rc;
}
+void bnx2x_clear_vlan_info(struct bnx2x *bp)
+{
+ struct bnx2x_vlan_entry *vlan;
+
+ /* Mark that hw forgot all entries */
+ list_for_each_entry(vlan, &bp->vlan_reg, link)
+ vlan->hw = false;
+
+ bp->vlan_cnt = 0;
+}
+
static int bnx2x_del_all_vlans(struct bnx2x *bp)
{
struct bnx2x_vlan_mac_obj *vlan_obj = &bp->sp_objs[0].vlan_obj;
unsigned long ramrod_flags = 0, vlan_flags = 0;
- struct bnx2x_vlan_entry *vlan;
int rc;
__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
if (rc)
return rc;
- /* Mark that hw forgot all entries */
- list_for_each_entry(vlan, &bp->vlan_reg, link)
- vlan->hw = false;
- bp->vlan_cnt = 0;
+ bnx2x_clear_vlan_info(bp);
return 0;
}
if (bnapi->events & BNXT_RX_EVENT) {
struct bnxt_rx_ring_info *rxr = bnapi->rx_ring;
- bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
if (bnapi->events & BNXT_AGG_EVENT)
bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
+ bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
}
bnapi->events = 0;
}
}
}
if (bp->flags & BNXT_FLAG_DIM) {
- struct dim_sample dim_sample;
+ struct dim_sample dim_sample = {};
dim_update_sample(cpr->event_ctr,
cpr->rx_packets,
static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
{
+ bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS);
int i, rc = 0;
u32 type;
if (rc)
goto err_out;
bnxt_set_db(bp, &rxr->rx_db, type, map_idx, ring->fw_ring_id);
- bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
+ /* If we have agg rings, post agg buffers first. */
+ if (!agg_rings)
+ bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id;
if (bp->flags & BNXT_FLAG_CHIP_P5) {
struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
}
}
- if (bp->flags & BNXT_FLAG_AGG_RINGS) {
+ if (agg_rings) {
type = HWRM_RING_ALLOC_AGG;
for (i = 0; i < bp->rx_nr_rings; i++) {
struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
bnxt_set_db(bp, &rxr->rx_agg_db, type, map_idx,
ring->fw_ring_id);
bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
+ bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id;
}
}
bnxt_hwrm_vnic_set_rss(bp, i, false);
}
-static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
- bool irq_re_init)
+static void bnxt_clear_vnic(struct bnxt *bp)
{
- if (bp->vnic_info) {
- bnxt_hwrm_clear_vnic_filter(bp);
+ if (!bp->vnic_info)
+ return;
+
+ bnxt_hwrm_clear_vnic_filter(bp);
+ if (!(bp->flags & BNXT_FLAG_CHIP_P5)) {
/* clear all RSS setting before free vnic ctx */
bnxt_hwrm_clear_vnic_rss(bp);
bnxt_hwrm_vnic_ctx_free(bp);
- /* before free the vnic, undo the vnic tpa settings */
- if (bp->flags & BNXT_FLAG_TPA)
- bnxt_set_tpa(bp, false);
- bnxt_hwrm_vnic_free(bp);
}
+ /* before free the vnic, undo the vnic tpa settings */
+ if (bp->flags & BNXT_FLAG_TPA)
+ bnxt_set_tpa(bp, false);
+ bnxt_hwrm_vnic_free(bp);
+ if (bp->flags & BNXT_FLAG_CHIP_P5)
+ bnxt_hwrm_vnic_ctx_free(bp);
+}
+
+static void bnxt_hwrm_resource_free(struct bnxt *bp, bool close_path,
+ bool irq_re_init)
+{
+ bnxt_clear_vnic(bp);
bnxt_hwrm_ring_free(bp, close_path);
bnxt_hwrm_ring_grp_free(bp);
if (irq_re_init) {
if (idx)
req->dimensions = cpu_to_le16(1);
- if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE))
+ if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
memcpy(data_addr, buf, bytesize);
-
- rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+ rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+ } else {
+ rc = hwrm_send_message_silent(bp, msg, msg_len,
+ HWRM_CMD_TIMEOUT);
+ }
if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE))
memcpy(buf, data_addr, bytesize);
mutex_lock(&bp->hwrm_cmd_lock);
hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
INSTALL_PACKAGE_TIMEOUT);
- if (hwrm_err)
- goto flash_pkg_exit;
-
- if (resp->error_code) {
+ if (hwrm_err) {
u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
- if (error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
+ if (resp->error_code && error_code ==
+ NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
install.flags |= cpu_to_le16(
NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
hwrm_err = _hwrm_send_message(bp, &install,
sizeof(install),
INSTALL_PACKAGE_TIMEOUT);
- if (hwrm_err)
- goto flash_pkg_exit;
}
+ if (hwrm_err)
+ goto flash_pkg_exit;
}
if (resp->result) {
static void bnxt_tc_set_flow_dir(struct bnxt *bp, struct bnxt_tc_flow *flow,
u16 src_fid)
{
- flow->dir = (bp->pf.fw_fid == src_fid) ? BNXT_DIR_RX : BNXT_DIR_TX;
+ flow->l2_key.dir = (bp->pf.fw_fid == src_fid) ? BNXT_DIR_RX : BNXT_DIR_TX;
}
static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
goto free_node;
bnxt_tc_set_src_fid(bp, flow, src_fid);
-
- if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
- bnxt_tc_set_flow_dir(bp, flow, src_fid);
+ bnxt_tc_set_flow_dir(bp, flow, flow->src_fid);
if (!bnxt_tc_can_offload(bp, flow)) {
rc = -EOPNOTSUPP;
* 2. 15th bit of flow_handle must specify the flow
* direction (TX/RX).
*/
- if (flow_node->flow.dir == BNXT_DIR_RX)
+ if (flow_node->flow.l2_key.dir == BNXT_DIR_RX)
handle = CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX |
CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK;
else
__be16 inner_vlan_tci;
__be16 ether_type;
u8 num_vlans;
+ u8 dir;
+#define BNXT_DIR_RX 1
+#define BNXT_DIR_TX 0
};
struct bnxt_tc_l3_key {
/* flow applicable to pkts ingressing on this fid */
u16 src_fid;
- u8 dir;
-#define BNXT_DIR_RX 1
-#define BNXT_DIR_TX 0
struct bnxt_tc_l2_key l2_key;
struct bnxt_tc_l2_key l2_mask;
struct bnxt_tc_l3_key l3_key;
.set_coalesce = bcmgenet_set_coalesce,
.get_link_ksettings = bcmgenet_get_link_ksettings,
.set_link_ksettings = bcmgenet_set_link_ksettings,
+ .get_ts_info = ethtool_op_get_ts_info,
};
/* Power down the unimac, based on mode. */
{
struct bcmgenet_rx_ring *ring = container_of(napi,
struct bcmgenet_rx_ring, napi);
- struct dim_sample dim_sample;
+ struct dim_sample dim_sample = {};
unsigned int work_done;
work_done = bcmgenet_desc_rx(ring, budget);
{ .compatible = "cdns,emac", .data = &emac_config },
{ .compatible = "cdns,zynqmp-gem", .data = &zynqmp_config},
{ .compatible = "cdns,zynq-gem", .data = &zynq_config },
- { .compatible = "sifive,fu540-macb", .data = &fu540_c000_config },
+ { .compatible = "sifive,fu540-c000-gem", .data = &fu540_c000_config },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, macb_dt_ids);
#include "cavium_ptp.h"
-#define DRV_NAME "Cavium PTP Driver"
+#define DRV_NAME "cavium_ptp"
#define PCI_DEVICE_ID_CAVIUM_PTP 0xA00C
#define PCI_DEVICE_ID_CAVIUM_RST 0xA00E
}
oct->num_iqs++;
- if (oct->fn_list.enable_io_queues(oct))
+ if (oct->fn_list.enable_io_queues(oct)) {
+ octeon_delete_instr_queue(oct, iq_no);
return 1;
+ }
return 0;
}
u8 *dst)
{
u8 mac[ETH_ALEN];
- int ret;
+ u8 *addr;
- ret = fwnode_property_read_u8_array(acpi_fwnode_handle(adev),
- "mac-address", mac, ETH_ALEN);
- if (ret)
- goto out;
-
- if (!is_valid_ether_addr(mac)) {
+ addr = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac, ETH_ALEN);
+ if (!addr) {
dev_err(dev, "MAC address invalid: %pM\n", mac);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
dev_info(dev, "MAC address set to: %pM\n", mac);
- memcpy(dst, mac, ETH_ALEN);
-out:
- return ret;
+ ether_addr_copy(dst, mac);
+ return 0;
}
/* Currently only sets the MAC address. */
return cphy_cause_link_change;
}
-static void my3216_poll(struct work_struct *work)
+static void my3126_poll(struct work_struct *work)
{
struct cphy *cphy = container_of(work, struct cphy, phy_update.work);
return NULL;
cphy_init(cphy, dev, phy_addr, &my3126_ops, mdio_ops);
- INIT_DELAYED_WORK(&cphy->phy_update, my3216_poll);
+ INIT_DELAYED_WORK(&cphy->phy_update, my3126_poll);
cphy->bmsr = 0;
return cphy;
if (!adapter->regs) {
dev_err(&pdev->dev, "cannot map device registers\n");
err = -ENOMEM;
- goto out_free_adapter;
+ goto out_free_adapter_nofail;
}
adapter->pdev = pdev;
if (adapter->port[i])
free_netdev(adapter->port[i]);
+out_free_adapter_nofail:
+ kfree_skb(adapter->nofail_skb);
+
out_free_adapter:
kfree(adapter);
return -ENOMEM;
err = bitmap_parse_user(ubuf, count, t, adap->sge.egr_sz);
- if (err)
+ if (err) {
+ kvfree(t);
return err;
+ }
bitmap_copy(adap->sge.blocked_fl, t, adap->sge.egr_sz);
kvfree(t);
char name[IFNAMSIZ];
u32 devcap2;
u16 flags;
- int pos;
/* If we want to instantiate Virtual Functions, then our
* parent bridge's PCI-E needs to support Alternative Routing
* and above.
*/
pbridge = pdev->bus->self;
- pos = pci_find_capability(pbridge, PCI_CAP_ID_EXP);
- pci_read_config_word(pbridge, pos + PCI_EXP_FLAGS, &flags);
- pci_read_config_dword(pbridge, pos + PCI_EXP_DEVCAP2, &devcap2);
+ pcie_capability_read_word(pbridge, PCI_EXP_FLAGS, &flags);
+ pcie_capability_read_dword(pbridge, PCI_EXP_DEVCAP2, &devcap2);
if ((flags & PCI_EXP_FLAGS_VERS) < 2 ||
!(devcap2 & PCI_EXP_DEVCAP2_ARI)) {
static struct ch_tc_flower_entry *allocate_flower_entry(void)
{
struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL);
- spin_lock_init(&new->lock);
+ if (new)
+ spin_lock_init(&new->lock);
return new;
}
} else {
unsigned int pack_align;
unsigned int ingpad, ingpack;
- unsigned int pcie_cap;
/* T5 introduced the separation of the Free List Padding and
* Packing Boundaries. Thus, we can select a smaller Padding
* multiple of the Maximum Payload Size.
*/
pack_align = fl_align;
- pcie_cap = pci_find_capability(adap->pdev, PCI_CAP_ID_EXP);
- if (pcie_cap) {
+ if (pci_is_pcie(adap->pdev)) {
unsigned int mps, mps_log;
u16 devctl;
* [bits 7:5] encodes sizes as powers of 2 starting at
* 128 bytes.
*/
- pci_read_config_word(adap->pdev,
- pcie_cap + PCI_EXP_DEVCTL,
- &devctl);
+ pcie_capability_read_word(adap->pdev, PCI_EXP_DEVCTL,
+ &devctl);
mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
mps = 1 << mps_log;
if (mps > pack_align)
int num = 0, status = 0;
struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
- spin_lock(&adapter->mcc_cq_lock);
+ spin_lock_bh(&adapter->mcc_cq_lock);
while ((compl = be_mcc_compl_get(adapter))) {
if (compl->flags & CQE_FLAGS_ASYNC_MASK) {
if (num)
be_cq_notify(adapter, mcc_obj->cq.id, mcc_obj->rearm_cq, num);
- spin_unlock(&adapter->mcc_cq_lock);
+ spin_unlock_bh(&adapter->mcc_cq_lock);
return status;
}
if (be_check_error(adapter, BE_ERROR_ANY))
return -EIO;
- local_bh_disable();
status = be_process_mcc(adapter);
- local_bh_enable();
if (atomic_read(&mcc_obj->q.used) == 0)
break;
int status;
if (netif_running(netdev)) {
+ /* be_tx_timeout() must not run concurrently with this
+ * function, synchronize with an already-running dev_watchdog
+ */
+ netif_tx_lock_bh(netdev);
/* device cannot transmit now, avoid dev_watchdog timeouts */
netif_carrier_off(netdev);
+ netif_tx_unlock_bh(netdev);
be_close(netdev);
}
* mcc completions
*/
if (!netif_running(adapter->netdev)) {
- local_bh_disable();
be_process_mcc(adapter);
- local_bh_enable();
goto reschedule;
}
};
/**
- * nps_reg_set - Sets ENET register with provided value.
+ * nps_enet_reg_set - Sets ENET register with provided value.
* @priv: Pointer to EZchip ENET private data structure.
* @reg: Register offset from base address.
* @value: Value to set in register.
}
/**
- * nps_reg_get - Gets value of specified ENET register.
+ * nps_enet_reg_get - Gets value of specified ENET register.
* @priv: Pointer to EZchip ENET private data structure.
* @reg: Register offset from base address.
*
config FSL_ENETC
tristate "ENETC PF driver"
depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+ select PHYLIB
help
This driver supports NXP ENETC gigabit ethernet controller PCIe
physical function (PF) devices, managing ENETC Ports at a privileged
config FSL_ENETC_VF
tristate "ENETC VF driver"
depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+ select PHYLIB
help
This driver supports NXP ENETC gigabit ethernet controller PCIe
virtual function (VF) devices enabled by the ENETC PF driver.
n = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
if (n != 1) {
err = -EPERM;
- goto err_irq;
+ goto err_irq_vectors;
}
ptp_qoriq->irq = pci_irq_vector(pdev, 0);
err_no_clock:
free_irq(ptp_qoriq->irq, ptp_qoriq);
err_irq:
+ pci_free_irq_vectors(pdev);
+err_irq_vectors:
iounmap(base);
err_ioremap:
kfree(ptp_qoriq);
enetc_phc_index = -1;
ptp_qoriq_free(ptp_qoriq);
+ pci_free_irq_vectors(pdev);
kfree(ptp_qoriq);
pci_release_mem_regions(pdev);
* buffers when not using jumbo frames.
* Must be large enough to accommodate the network MTU, but small enough
* to avoid wasting skb memory.
- *
- * Could be overridden once, at boot-time, via the
- * fm_set_max_frm() callback.
*/
static int fsl_fm_max_frm = FSL_FM_MAX_FRAME_SIZE;
module_param(fsl_fm_max_frm, int, 0);
struct gve_rx_desc_queue {
struct gve_rx_desc *desc_ring; /* the descriptor ring */
dma_addr_t bus; /* the bus for the desc_ring */
- u32 cnt; /* free-running total number of completed packets */
- u32 fill_cnt; /* free-running total number of descriptors posted */
- u32 mask; /* masks the cnt to the size of the ring */
u8 seqno; /* the next expected seqno for this desc*/
};
dma_addr_t data_bus; /* dma mapping of the slots */
struct gve_rx_slot_page_info *page_info; /* page info of the buffers */
struct gve_queue_page_list *qpl; /* qpl assigned to this queue */
- u32 mask; /* masks the cnt to the size of the ring */
- u32 cnt; /* free-running total number of completed packets */
};
struct gve_priv;
struct gve_rx_data_queue data;
u64 rbytes; /* free-running bytes received */
u64 rpackets; /* free-running packets received */
+ u32 cnt; /* free-running total number of completed packets */
+ u32 fill_cnt; /* free-running total number of descs and buffs posted */
+ u32 mask; /* masks the cnt and fill_cnt to the size of the ring */
u32 q_num; /* queue index */
u32 ntfy_id; /* notification block index */
struct gve_queue_resources *q_resources; /* head and tail pointer idx */
for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
struct gve_rx_ring *rx = &priv->rx[ring];
- data[i++] = rx->desc.cnt;
- data[i++] = rx->desc.fill_cnt;
+ data[i++] = rx->cnt;
+ data[i++] = rx->fill_cnt;
}
} else {
i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS;
u64_stats_fetch_begin(&priv->tx[ring].statss);
s->tx_packets += priv->tx[ring].pkt_done;
s->tx_bytes += priv->tx[ring].bytes_done;
- } while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+ } while (u64_stats_fetch_retry(&priv->tx[ring].statss,
start));
}
}
rx->data.qpl = NULL;
kvfree(rx->data.page_info);
- slots = rx->data.mask + 1;
+ slots = rx->mask + 1;
bytes = sizeof(*rx->data.data_ring) * slots;
dma_free_coherent(dev, bytes, rx->data.data_ring,
rx->data.data_bus);
/* Allocate one page per Rx queue slot. Each page is split into two
* packet buffers, when possible we "page flip" between the two.
*/
- slots = rx->data.mask + 1;
+ slots = rx->mask + 1;
rx->data.page_info = kvzalloc(slots *
sizeof(*rx->data.page_info), GFP_KERNEL);
rx->q_num = idx;
slots = priv->rx_pages_per_qpl;
- rx->data.mask = slots - 1;
+ rx->mask = slots - 1;
/* alloc rx data ring */
bytes = sizeof(*rx->data.data_ring) * slots;
err = -ENOMEM;
goto abort_with_slots;
}
- rx->desc.fill_cnt = filled_pages;
+ rx->fill_cnt = filled_pages;
/* Ensure data ring slots (packet buffers) are visible. */
dma_wmb();
err = -ENOMEM;
goto abort_with_q_resources;
}
- rx->desc.mask = slots - 1;
- rx->desc.cnt = 0;
+ rx->mask = slots - 1;
+ rx->cnt = 0;
rx->desc.seqno = 1;
gve_rx_add_to_block(priv, idx);
{
u32 db_idx = be32_to_cpu(rx->q_resources->db_index);
- iowrite32be(rx->desc.fill_cnt, &priv->db_bar2[db_idx]);
+ iowrite32be(rx->fill_cnt, &priv->db_bar2[db_idx]);
}
static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
}
static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
- netdev_features_t feat)
+ netdev_features_t feat, u32 idx)
{
struct gve_rx_slot_page_info *page_info;
struct gve_priv *priv = rx->gve;
struct sk_buff *skb;
int pagecount;
u16 len;
- u32 idx;
/* drop this packet */
if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR))
return true;
len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
- idx = rx->data.cnt & rx->data.mask;
page_info = &rx->data.page_info[idx];
/* gvnic can only receive into registered segments. If the buffer
if (!skb)
return true;
- rx->data.cnt++;
-
if (likely(feat & NETIF_F_RXCSUM)) {
/* NIC passes up the partial sum */
if (rx_desc->csum)
__be16 flags_seq;
u32 next_idx;
- next_idx = rx->desc.cnt & rx->desc.mask;
+ next_idx = rx->cnt & rx->mask;
desc = rx->desc.desc_ring + next_idx;
flags_seq = desc->flags_seq;
{
struct gve_priv *priv = rx->gve;
struct gve_rx_desc *desc;
- u32 cnt = rx->desc.cnt;
- u32 idx = cnt & rx->desc.mask;
+ u32 cnt = rx->cnt;
+ u32 idx = cnt & rx->mask;
u32 work_done = 0;
u64 bytes = 0;
rx->q_num, GVE_SEQNO(desc->flags_seq),
rx->desc.seqno);
bytes += be16_to_cpu(desc->len) - GVE_RX_PAD;
- if (!gve_rx(rx, desc, feat))
+ if (!gve_rx(rx, desc, feat, idx))
gve_schedule_reset(priv);
cnt++;
- idx = cnt & rx->desc.mask;
+ idx = cnt & rx->mask;
desc = rx->desc.desc_ring + idx;
rx->desc.seqno = gve_next_seqno(rx->desc.seqno);
work_done++;
rx->rpackets += work_done;
rx->rbytes += bytes;
u64_stats_update_end(&rx->statss);
- rx->desc.cnt = cnt;
- rx->desc.fill_cnt += work_done;
+ rx->cnt = cnt;
+ rx->fill_cnt += work_done;
/* restock desc ring slots */
dma_wmb(); /* Ensure descs are visible before ringing doorbell */
unsigned int reg_inten;
struct napi_struct napi;
+ struct device *dev;
struct net_device *ndev;
struct tx_desc *tx_desc;
static inline unsigned int tx_count(unsigned int head, unsigned int tail)
{
- return (head - tail) % (TX_DESC_NUM - 1);
+ return (head - tail) % TX_DESC_NUM;
}
static void hip04_config_port(struct net_device *ndev, u32 speed, u32 duplex)
}
if (priv->tx_phys[tx_tail]) {
- dma_unmap_single(&ndev->dev, priv->tx_phys[tx_tail],
+ dma_unmap_single(priv->dev, priv->tx_phys[tx_tail],
priv->tx_skb[tx_tail]->len,
DMA_TO_DEVICE);
priv->tx_phys[tx_tail] = 0;
return NETDEV_TX_BUSY;
}
- phys = dma_map_single(&ndev->dev, skb->data, skb->len, DMA_TO_DEVICE);
- if (dma_mapping_error(&ndev->dev, phys)) {
+ phys = dma_map_single(priv->dev, skb->data, skb->len, DMA_TO_DEVICE);
+ if (dma_mapping_error(priv->dev, phys)) {
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
u16 len;
u32 err;
+ /* clean up tx descriptors */
+ tx_remaining = hip04_tx_reclaim(ndev, false);
+
while (cnt && !last) {
buf = priv->rx_buf[priv->rx_head];
skb = build_skb(buf, priv->rx_buf_size);
goto refill;
}
- dma_unmap_single(&ndev->dev, priv->rx_phys[priv->rx_head],
+ dma_unmap_single(priv->dev, priv->rx_phys[priv->rx_head],
RX_BUF_SIZE, DMA_FROM_DEVICE);
priv->rx_phys[priv->rx_head] = 0;
buf = netdev_alloc_frag(priv->rx_buf_size);
if (!buf)
goto done;
- phys = dma_map_single(&ndev->dev, buf,
+ phys = dma_map_single(priv->dev, buf,
RX_BUF_SIZE, DMA_FROM_DEVICE);
- if (dma_mapping_error(&ndev->dev, phys))
+ if (dma_mapping_error(priv->dev, phys))
goto done;
priv->rx_buf[priv->rx_head] = buf;
priv->rx_phys[priv->rx_head] = phys;
}
napi_complete_done(napi, rx);
done:
- /* clean up tx descriptors and start a new timer if necessary */
- tx_remaining = hip04_tx_reclaim(ndev, false);
+ /* start a new timer if necessary */
if (rx < budget && tx_remaining)
hip04_start_tx_timer(priv);
for (i = 0; i < RX_DESC_NUM; i++) {
dma_addr_t phys;
- phys = dma_map_single(&ndev->dev, priv->rx_buf[i],
+ phys = dma_map_single(priv->dev, priv->rx_buf[i],
RX_BUF_SIZE, DMA_FROM_DEVICE);
- if (dma_mapping_error(&ndev->dev, phys))
+ if (dma_mapping_error(priv->dev, phys))
return -EIO;
priv->rx_phys[i] = phys;
for (i = 0; i < RX_DESC_NUM; i++) {
if (priv->rx_phys[i]) {
- dma_unmap_single(&ndev->dev, priv->rx_phys[i],
+ dma_unmap_single(priv->dev, priv->rx_phys[i],
RX_BUF_SIZE, DMA_FROM_DEVICE);
priv->rx_phys[i] = 0;
}
return -ENOMEM;
priv = netdev_priv(ndev);
+ priv->dev = d;
priv->ndev = ndev;
platform_set_drvdata(pdev, ndev);
SET_NETDEV_DEV(ndev, &pdev->dev);
HCLGE_MBX_GET_QID_IN_PF, /* (VF -> PF) get queue id in pf */
HCLGE_MBX_LINK_STAT_MODE, /* (PF -> VF) link mode has changed */
HCLGE_MBX_GET_LINK_MODE, /* (VF -> PF) get the link mode of pf */
- HLCGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */
+ HCLGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */
HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */
HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */
memcpy(&msg_data[6], &vlan_tag, sizeof(u16));
return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
- HLCGE_MBX_PUSH_VLAN_INFO, vfid);
+ HCLGE_MBX_PUSH_VLAN_INFO, vfid);
}
static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
case HCLGE_MBX_LINK_STAT_CHANGE:
case HCLGE_MBX_ASSERTING_RESET:
case HCLGE_MBX_LINK_STAT_MODE:
- case HLCGE_MBX_PUSH_VLAN_INFO:
+ case HCLGE_MBX_PUSH_VLAN_INFO:
/* set this mbx event as pending. This is required as we
* might loose interrupt event when mbx task is busy
* handling. This shall be cleared when mbx task just
hclgevf_reset_task_schedule(hdev);
break;
- case HLCGE_MBX_PUSH_VLAN_INFO:
+ case HCLGE_MBX_PUSH_VLAN_INFO:
state = le16_to_cpu(msg_q[1]);
vlan_info = &msg_q[1];
hclgevf_update_port_base_vlan_info(hdev, state,
switch (action) {
case MEM_CANCEL_OFFLINE:
pr_info("memory offlining canceled");
- /* Fall through: re-add canceled memory block */
+ /* Fall through - re-add canceled memory block */
case MEM_ONLINE:
pr_info("memory is going online");
struct net_device *netdev;
struct ibmveth_adapter *adapter;
unsigned char *mac_addr_p;
- unsigned int *mcastFilterSize_p;
+ __be32 *mcastFilterSize_p;
long ret;
unsigned long ret_attr;
return -EINVAL;
}
- mcastFilterSize_p = (unsigned int *)vio_get_attribute(dev,
- VETH_MCAST_FILTER_SIZE, NULL);
+ mcastFilterSize_p = (__be32 *)vio_get_attribute(dev,
+ VETH_MCAST_FILTER_SIZE,
+ NULL);
if (!mcastFilterSize_p) {
dev_err(&dev->dev, "Can't find VETH_MCAST_FILTER_SIZE "
"attribute\n");
adapter->vdev = dev;
adapter->netdev = netdev;
- adapter->mcastFilterSize = *mcastFilterSize_p;
+ adapter->mcastFilterSize = be32_to_cpu(*mcastFilterSize_p);
adapter->pool_config = 0;
netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16);
lpar_rc = send_subcrq_indirect(adapter, handle_array[queue_num],
(u64)tx_buff->indir_dma,
(u64)num_entries);
+ dma_unmap_single(dev, tx_buff->indir_dma,
+ sizeof(tx_buff->indir_arr), DMA_TO_DEVICE);
} else {
tx_buff->num_entries = num_entries;
lpar_rc = send_subcrq(adapter, handle_array[queue_num],
rwi = get_next_rwi(adapter);
while (rwi) {
+ if (adapter->state == VNIC_REMOVING ||
+ adapter->state == VNIC_REMOVED)
+ goto out;
+
if (adapter->force_reset_recovery) {
adapter->force_reset_recovery = false;
rc = do_hard_reset(adapter, rwi, reset_state);
netdev_dbg(adapter->netdev, "Reset failed\n");
free_all_rwi(adapter);
}
-
+out:
adapter->resetting = false;
if (we_lock_rtnl)
rtnl_unlock();
union sub_crq *next;
int index;
int i, j;
- u8 *first;
restart_loop:
while (pending_scrq(adapter, scrq)) {
txbuff->data_dma[j] = 0;
}
- /* if sub_crq was sent indirectly */
- first = &txbuff->indir_arr[0].generic.first;
- if (*first == IBMVNIC_CRQ_CMD) {
- dma_unmap_single(dev, txbuff->indir_dma,
- sizeof(txbuff->indir_arr),
- DMA_TO_DEVICE);
- *first = 0;
- }
if (txbuff->last_frag) {
dev_kfree_skb_any(txbuff->skb);
s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
{
struct igc_adapter *adapter = hw->back;
- u16 cap_offset;
- cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
- if (!cap_offset)
+ if (!pci_is_pcie(adapter->pdev))
return -IGC_ERR_CONFIG;
- pci_read_config_word(adapter->pdev, cap_offset + reg, value);
+ pcie_capability_read_word(adapter->pdev, reg, value);
return IGC_SUCCESS;
}
s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value)
{
struct igc_adapter *adapter = hw->back;
- u16 cap_offset;
- cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP);
- if (!cap_offset)
+ if (!pci_is_pcie(adapter->pdev))
return -IGC_ERR_CONFIG;
- pci_write_config_word(adapter->pdev, cap_offset + reg, *value);
+ pcie_capability_write_word(adapter->pdev, reg, *value);
return IGC_SUCCESS;
}
return;
}
if (ixgbe_check_fw_error(adapter)) {
- if (!test_bit(__IXGBE_DOWN, &adapter->state)) {
- rtnl_lock();
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
unregister_netdev(adapter->netdev);
- rtnl_unlock();
- }
ixgbe_service_event_complete(adapter);
return;
}
init_waitqueue_head(&dev->smi_busy_wait);
- for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
- dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
- if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+ if (pdev->dev.of_node) {
+ for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
+ dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+ if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto out_clk;
+ }
+ if (IS_ERR(dev->clk[i]))
+ break;
+ clk_prepare_enable(dev->clk[i]);
+ }
+
+ if (!IS_ERR(of_clk_get(pdev->dev.of_node,
+ ARRAY_SIZE(dev->clk))))
+ dev_warn(&pdev->dev,
+ "unsupported number of clocks, limiting to the first "
+ __stringify(ARRAY_SIZE(dev->clk)) "\n");
+ } else {
+ dev->clk[0] = clk_get(&pdev->dev, NULL);
+ if (PTR_ERR(dev->clk[0]) == -EPROBE_DEFER) {
ret = -EPROBE_DEFER;
goto out_clk;
}
- if (IS_ERR(dev->clk[i]))
- break;
- clk_prepare_enable(dev->clk[i]);
+ if (!IS_ERR(dev->clk[0]))
+ clk_prepare_enable(dev->clk[0]);
}
- if (!IS_ERR(of_clk_get(pdev->dev.of_node, ARRAY_SIZE(dev->clk))))
- dev_warn(&pdev->dev, "unsupported number of clocks, limiting to the first "
- __stringify(ARRAY_SIZE(dev->clk)) "\n");
dev->err_interrupt = platform_get_irq(pdev, 0);
if (dev->err_interrupt > 0 &&
return 0;
}
+static void mvpp2_set_hw_csum(struct mvpp2_port *port,
+ enum mvpp2_bm_pool_log_num new_long_pool)
+{
+ const netdev_features_t csums = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+
+ /* Update L4 checksum when jumbo enable/disable on port.
+ * Only port 0 supports hardware checksum offload due to
+ * the Tx FIFO size limitation.
+ * Also, don't set NETIF_F_HW_CSUM because L3_offset in TX descriptor
+ * has 7 bits, so the maximum L3 offset is 128.
+ */
+ if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) {
+ port->dev->features &= ~csums;
+ port->dev->hw_features &= ~csums;
+ } else {
+ port->dev->features |= csums;
+ port->dev->hw_features |= csums;
+ }
+}
+
static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu)
{
struct mvpp2_port *port = netdev_priv(dev);
/* Add port to new short & long pool */
mvpp2_swf_bm_pool_init(port);
- /* Update L4 checksum when jumbo enable/disable on port */
- if (new_long_pool == MVPP2_BM_JUMBO && port->id != 0) {
- dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- dev->hw_features &= ~(NETIF_F_IP_CSUM |
- NETIF_F_IPV6_CSUM);
- } else {
- dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
- dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
- }
+ mvpp2_set_hw_csum(port, new_long_pool);
}
dev->mtu = mtu;
static int mvpp2_change_mtu(struct net_device *dev, int mtu)
{
struct mvpp2_port *port = netdev_priv(dev);
+ bool running = netif_running(dev);
int err;
if (!IS_ALIGNED(MVPP2_RX_PKT_SIZE(mtu), 8)) {
mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8);
}
- if (!netif_running(dev)) {
- err = mvpp2_bm_update_mtu(dev, mtu);
- if (!err) {
- port->pkt_size = MVPP2_RX_PKT_SIZE(mtu);
- return 0;
- }
-
- /* Reconfigure BM to the original MTU */
- err = mvpp2_bm_update_mtu(dev, dev->mtu);
- if (err)
- goto log_error;
- }
-
- mvpp2_stop_dev(port);
+ if (running)
+ mvpp2_stop_dev(port);
err = mvpp2_bm_update_mtu(dev, mtu);
- if (!err) {
+ if (err) {
+ netdev_err(dev, "failed to change MTU\n");
+ /* Reconfigure BM to the original MTU */
+ mvpp2_bm_update_mtu(dev, dev->mtu);
+ } else {
port->pkt_size = MVPP2_RX_PKT_SIZE(mtu);
- goto out_start;
}
- /* Reconfigure BM to the original MTU */
- err = mvpp2_bm_update_mtu(dev, dev->mtu);
- if (err)
- goto log_error;
-
-out_start:
- mvpp2_start_dev(port);
- mvpp2_egress_enable(port);
- mvpp2_ingress_enable(port);
+ if (running) {
+ mvpp2_start_dev(port);
+ mvpp2_egress_enable(port);
+ mvpp2_ingress_enable(port);
+ }
- return 0;
-log_error:
- netdev_err(dev, "failed to change MTU\n");
return err;
}
else
ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
- ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC;
- ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC |
- MVPP22_XLG_CTRL4_EN_IDLE_CHECK;
+ ctrl4 &= ~(MVPP22_XLG_CTRL4_MACMODSELECT_GMAC |
+ MVPP22_XLG_CTRL4_EN_IDLE_CHECK);
+ ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC;
if (old_ctrl0 != ctrl0)
writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
dev->features |= NETIF_F_NTUPLE;
}
- if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) {
- dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
- }
+ mvpp2_set_hw_csum(port, port->pool_long->id);
dev->vlan_features |= features;
dev->gso_max_segs = MVPP2_MAX_TSO_SEGS;
mvpp2_dbgfs_cleanup(priv);
- flush_workqueue(priv->stats_queue);
- destroy_workqueue(priv->stats_queue);
-
fwnode_for_each_available_child_node(fwnode, port_fwnode) {
if (priv->port_list[i]) {
mutex_destroy(&priv->port_list[i]->gather_stats_lock);
i++;
}
+ destroy_workqueue(priv->stats_queue);
+
for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) {
struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i];
DMI_MATCH(DMI_PRODUCT_NAME, "P5W DH Deluxe"),
},
},
+ {
+ .ident = "ASUS P6T",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "P6T"),
+ },
+ },
+ {
+ .ident = "ASUS P6X",
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "P6X"),
+ },
+ },
{}
};
config NET_MEDIATEK_SOC
tristate "MediaTek SoC Gigabit Ethernet support"
- depends on NET_VENDOR_MEDIATEK
select PHYLIB
---help---
This driver supports the gigabit ethernet MACs in the
err = mlx4_qp_alloc(mdev->dev, priv->base_qpn, rss_map->indir_qp);
if (err) {
en_err(priv, "Failed to allocate RSS indirection QP\n");
- goto rss_err;
+ goto qp_alloc_err;
}
rss_map->indir_qp->event = mlx4_en_sqp_event;
MLX4_QP_STATE_RST, NULL, 0, 0, rss_map->indir_qp);
mlx4_qp_remove(mdev->dev, rss_map->indir_qp);
mlx4_qp_free(mdev->dev, rss_map->indir_qp);
+qp_alloc_err:
kfree(rss_map->indir_qp);
rss_map->indir_qp = NULL;
rss_err:
struct mlx5_interface *intf;
mutex_lock(&mlx5_intf_mutex);
- list_for_each_entry(intf, &intf_list, list)
+ list_for_each_entry_reverse(intf, &intf_list, list)
mlx5_remove_device(intf, priv);
list_del(&priv->dev_list);
mutex_unlock(&mlx5_intf_mutex);
enum mlx5e_rq_group {
MLX5E_RQ_GROUP_REGULAR,
MLX5E_RQ_GROUP_XSK,
- MLX5E_NUM_RQ_GROUPS /* Keep last. */
+#define MLX5E_NUM_RQ_GROUPS(g) (1 + MLX5E_RQ_GROUP_##g)
};
static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS);
}
-/* Use this function to get max num channels after netdev was created */
-static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev)
-{
- return min_t(unsigned int,
- netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS,
- netdev->num_tx_queues);
-}
-
struct mlx5e_tx_wqe {
struct mlx5_wqe_ctrl_seg ctrl;
- struct mlx5_wqe_eth_seg eth;
- struct mlx5_wqe_data_seg data[0];
+ union {
+ struct {
+ struct mlx5_wqe_eth_seg eth;
+ struct mlx5_wqe_data_seg data[0];
+ };
+ u8 tls_progress_params_ctx[0];
+ };
};
struct mlx5e_rx_wqe_ll {
struct net_device *netdev;
struct mlx5e_stats stats;
struct mlx5e_channel_stats channel_stats[MLX5E_MAX_NUM_CHANNELS];
+ u16 max_nch;
u8 max_opened_tc;
struct hwtstamp_config tstamp;
u16 q_counter;
mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
} rx_handlers;
int max_tc;
+ u8 rq_groups;
};
void mlx5e_build_ptys2ethtool_map(void);
u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
struct ethtool_ts_info *info);
+int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
+ struct ethtool_flash *flash);
void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
struct ethtool_pauseparam *pauseparam);
int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
*group = qid / nch;
}
-static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid)
+static inline bool mlx5e_qid_validate(const struct mlx5e_profile *profile,
+ struct mlx5e_params *params, u64 qid)
{
- return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS;
+ return qid < params->num_channels * profile->rq_groups;
}
/* Parameter calculations */
};
static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
- const u32 **arr, u32 *size)
+ const u32 **arr, u32 *size,
+ bool force_legacy)
{
- bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+ bool ext = force_legacy ? false : MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
ARRAY_SIZE(mlx5e_link_speed);
sizeof(out), MLX5_REG_PTYS, 0, 1);
}
-u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
+ bool force_legacy)
{
unsigned long temp = eth_proto_oper;
const u32 *table;
u32 max_size;
int i;
- mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+ mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
i = find_first_bit(&temp, max_size);
if (i < max_size)
speed = table[i];
int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
{
struct mlx5e_port_eth_proto eproto;
+ bool force_legacy = false;
bool ext;
int err;
err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
if (err)
goto out;
-
- *speed = mlx5e_port_ptys2speed(mdev, eproto.oper);
+ if (ext && !eproto.admin) {
+ force_legacy = true;
+ err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto);
+ if (err)
+ goto out;
+ }
+ *speed = mlx5e_port_ptys2speed(mdev, eproto.oper, force_legacy);
if (!(*speed))
err = -EINVAL;
if (err)
return err;
- mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+ mlx5e_port_get_speed_arr(mdev, &table, &max_size, false);
for (i = 0; i < max_size; ++i)
if (eproto.cap & MLX5E_PROT_MASK(i))
max_speed = max(max_speed, table[i]);
return 0;
}
-u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed)
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
+ bool force_legacy)
{
u32 link_modes = 0;
const u32 *table;
u32 max_size;
int i;
- mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+ mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
for (i = 0; i < max_size; ++i) {
if (table[i] == speed)
link_modes |= MLX5E_PROT_MASK(i);
u8 *an_disable_cap, u8 *an_disable_admin);
int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
u32 proto_admin, bool ext);
-u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper);
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
+ bool force_legacy);
int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed);
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
+ bool force_legacy);
int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
u8 state;
int err;
- if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
- return 0;
-
err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
if (err) {
netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
sq->sqn, err);
- return err;
+ goto out;
}
- if (state != MLX5_SQC_STATE_ERR) {
- netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
- return -EINVAL;
- }
+ if (state != MLX5_SQC_STATE_ERR)
+ goto out;
mlx5e_tx_disable_queue(sq->txq);
err = mlx5e_wait_for_sq_flush(sq);
if (err)
- return err;
+ goto out;
/* At this point, no new packets will arrive from the stack as TXQ is
* marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
err = mlx5e_sq_to_ready(sq, state);
if (err)
- return err;
+ goto out;
mlx5e_reset_txqsq_cc_pc(sq);
sq->stats->recover++;
+ clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
mlx5e_activate_txqsq(sq);
return 0;
+out:
+ clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
+ return err;
}
static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
{
set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state);
/* TX queue is created active. */
+
+ spin_lock(&c->xskicosq_lock);
mlx5e_trigger_irq(&c->xskicosq);
+ spin_unlock(&c->xskicosq_lock);
}
void mlx5e_deactivate_xsk(struct mlx5e_channel *c)
#include "accel/tls.h"
#define MLX5E_KTLS_STATIC_UMR_WQE_SZ \
- (sizeof(struct mlx5e_umr_wqe) + MLX5_ST_SZ_BYTES(tls_static_params))
+ (offsetof(struct mlx5e_umr_wqe, tls_static_params_ctx) + \
+ MLX5_ST_SZ_BYTES(tls_static_params))
#define MLX5E_KTLS_STATIC_WQEBBS \
(DIV_ROUND_UP(MLX5E_KTLS_STATIC_UMR_WQE_SZ, MLX5_SEND_WQE_BB))
#define MLX5E_KTLS_PROGRESS_WQE_SZ \
- (sizeof(struct mlx5e_tx_wqe) + MLX5_ST_SZ_BYTES(tls_progress_params))
+ (offsetof(struct mlx5e_tx_wqe, tls_progress_params_ctx) + \
+ MLX5_ST_SZ_BYTES(tls_progress_params))
#define MLX5E_KTLS_PROGRESS_WQEBBS \
(DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB))
#define MLX5E_KTLS_MAX_DUMP_WQEBBS 2
cseg->qpn_ds = cpu_to_be32((sqn << MLX5_WQE_CTRL_QPN_SHIFT) |
STATIC_PARAMS_DS_CNT);
cseg->fm_ce_se = fence ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
- cseg->imm = cpu_to_be32(priv_tx->tisn);
+ cseg->tisn = cpu_to_be32(priv_tx->tisn << 8);
ucseg->flags = MLX5_UMR_INLINE;
ucseg->bsf_octowords = cpu_to_be16(MLX5_ST_SZ_BYTES(tls_static_params) / 16);
static void
fill_progress_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
{
- MLX5_SET(tls_progress_params, ctx, pd, priv_tx->tisn);
+ MLX5_SET(tls_progress_params, ctx, tisn, priv_tx->tisn);
MLX5_SET(tls_progress_params, ctx, record_tracker_state,
MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_START);
MLX5_SET(tls_progress_params, ctx, auth_state,
PROGRESS_PARAMS_DS_CNT);
cseg->fm_ce_se = fence ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
- fill_progress_params_ctx(wqe->data, priv_tx);
+ fill_progress_params_ctx(wqe->tls_progress_params_ctx, priv_tx);
}
static void tx_fill_wi(struct mlx5e_txqsq *sq,
u16 pi, u8 num_wqebbs,
- skb_frag_t *resync_dump_frag)
+ skb_frag_t *resync_dump_frag,
+ u32 num_bytes)
{
struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
wi->skb = NULL;
wi->num_wqebbs = num_wqebbs;
wi->resync_dump_frag = resync_dump_frag;
+ wi->num_bytes = num_bytes;
}
void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx)
umr_wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_STATIC_UMR_WQE_SZ, &pi);
build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence);
- tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, NULL);
+ tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, NULL, 0);
sq->pc += MLX5E_KTLS_STATIC_WQEBBS;
}
wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_PROGRESS_WQE_SZ, &pi);
build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence);
- tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, NULL);
+ tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, NULL, 0);
sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS;
}
mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, skip_static_post, true);
}
+struct mlx5e_dump_wqe {
+ struct mlx5_wqe_ctrl_seg ctrl;
+ struct mlx5_wqe_data_seg data;
+};
+
static int
tx_post_resync_dump(struct mlx5e_txqsq *sq, struct sk_buff *skb,
skb_frag_t *frag, u32 tisn, bool first)
{
struct mlx5_wqe_ctrl_seg *cseg;
- struct mlx5_wqe_eth_seg *eseg;
struct mlx5_wqe_data_seg *dseg;
- struct mlx5e_tx_wqe *wqe;
+ struct mlx5e_dump_wqe *wqe;
dma_addr_t dma_addr = 0;
- u16 ds_cnt, ds_cnt_inl;
u8 num_wqebbs;
- u16 pi, ihs;
+ u16 ds_cnt;
int fsz;
-
- ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
- ihs = eth_get_headlen(skb->dev, skb->data, skb_headlen(skb));
- ds_cnt_inl = DIV_ROUND_UP(ihs - INL_HDR_START_SZ, MLX5_SEND_WQE_DS);
- ds_cnt += ds_cnt_inl;
- ds_cnt += 1; /* one frag */
+ u16 pi;
wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
+ ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
cseg = &wqe->ctrl;
- eseg = &wqe->eth;
- dseg = wqe->data;
+ dseg = &wqe->data;
cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_DUMP);
cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
- cseg->imm = cpu_to_be32(tisn);
+ cseg->tisn = cpu_to_be32(tisn << 8);
cseg->fm_ce_se = first ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
- eseg->inline_hdr.sz = cpu_to_be16(ihs);
- memcpy(eseg->inline_hdr.start, skb->data, ihs);
- dseg += ds_cnt_inl;
-
fsz = skb_frag_size(frag);
dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz,
DMA_TO_DEVICE);
dseg->byte_count = cpu_to_be32(fsz);
mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
- tx_fill_wi(sq, pi, num_wqebbs, frag);
+ tx_fill_wi(sq, pi, num_wqebbs, frag, fsz);
sq->pc += num_wqebbs;
WARN(num_wqebbs > MLX5E_KTLS_MAX_DUMP_WQEBBS,
struct mlx5_wq_cyc *wq = &sq->wq;
u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
- tx_fill_wi(sq, pi, 1, NULL);
+ tx_fill_wi(sq, pi, 1, NULL, 0);
mlx5e_post_nop_fence(wq, sq->sqn, &sq->pc);
}
goto out;
tls_ctx = tls_get_ctx(skb->sk);
- if (unlikely(tls_ctx->netdev != netdev))
+ if (unlikely(WARN_ON_ONCE(tls_ctx->netdev != netdev)))
goto err_out;
priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
priv_tx->expected_seq = seq + datalen;
cseg = &(*wqe)->ctrl;
- cseg->imm = cpu_to_be32(priv_tx->tisn);
+ cseg->tisn = cpu_to_be32(priv_tx->tisn << 8);
stats->tls_encrypted_packets += skb_is_gso(skb) ? skb_shinfo(skb)->gso_segs : 1;
stats->tls_encrypted_bytes += datalen;
return &arfs_t->rules_hash[bucket_idx];
}
-static u8 arfs_get_ip_proto(const struct sk_buff *skb)
-{
- return (skb->protocol == htons(ETH_P_IP)) ?
- ip_hdr(skb)->protocol : ipv6_hdr(skb)->nexthdr;
-}
-
static struct arfs_table *arfs_get_table(struct mlx5e_arfs_tables *arfs,
u8 ip_proto, __be16 etype)
{
arfs_may_expire_flow(priv);
}
-/* return L4 destination port from ip4/6 packets */
-static __be16 arfs_get_dst_port(const struct sk_buff *skb)
-{
- char *transport_header;
-
- transport_header = skb_transport_header(skb);
- if (arfs_get_ip_proto(skb) == IPPROTO_TCP)
- return ((struct tcphdr *)transport_header)->dest;
- return ((struct udphdr *)transport_header)->dest;
-}
-
-/* return L4 source port from ip4/6 packets */
-static __be16 arfs_get_src_port(const struct sk_buff *skb)
-{
- char *transport_header;
-
- transport_header = skb_transport_header(skb);
- if (arfs_get_ip_proto(skb) == IPPROTO_TCP)
- return ((struct tcphdr *)transport_header)->source;
- return ((struct udphdr *)transport_header)->source;
-}
-
static struct arfs_rule *arfs_alloc_rule(struct mlx5e_priv *priv,
struct arfs_table *arfs_t,
- const struct sk_buff *skb,
+ const struct flow_keys *fk,
u16 rxq, u32 flow_id)
{
struct arfs_rule *rule;
INIT_WORK(&rule->arfs_work, arfs_handle_work);
tuple = &rule->tuple;
- tuple->etype = skb->protocol;
+ tuple->etype = fk->basic.n_proto;
+ tuple->ip_proto = fk->basic.ip_proto;
if (tuple->etype == htons(ETH_P_IP)) {
- tuple->src_ipv4 = ip_hdr(skb)->saddr;
- tuple->dst_ipv4 = ip_hdr(skb)->daddr;
+ tuple->src_ipv4 = fk->addrs.v4addrs.src;
+ tuple->dst_ipv4 = fk->addrs.v4addrs.dst;
} else {
- memcpy(&tuple->src_ipv6, &ipv6_hdr(skb)->saddr,
+ memcpy(&tuple->src_ipv6, &fk->addrs.v6addrs.src,
sizeof(struct in6_addr));
- memcpy(&tuple->dst_ipv6, &ipv6_hdr(skb)->daddr,
+ memcpy(&tuple->dst_ipv6, &fk->addrs.v6addrs.dst,
sizeof(struct in6_addr));
}
- tuple->ip_proto = arfs_get_ip_proto(skb);
- tuple->src_port = arfs_get_src_port(skb);
- tuple->dst_port = arfs_get_dst_port(skb);
+ tuple->src_port = fk->ports.src;
+ tuple->dst_port = fk->ports.dst;
rule->flow_id = flow_id;
rule->filter_id = priv->fs.arfs.last_filter_id++ % RPS_NO_FILTER;
return rule;
}
-static bool arfs_cmp_ips(struct arfs_tuple *tuple,
- const struct sk_buff *skb)
+static bool arfs_cmp(const struct arfs_tuple *tuple, const struct flow_keys *fk)
{
- if (tuple->etype == htons(ETH_P_IP) &&
- tuple->src_ipv4 == ip_hdr(skb)->saddr &&
- tuple->dst_ipv4 == ip_hdr(skb)->daddr)
- return true;
- if (tuple->etype == htons(ETH_P_IPV6) &&
- (!memcmp(&tuple->src_ipv6, &ipv6_hdr(skb)->saddr,
- sizeof(struct in6_addr))) &&
- (!memcmp(&tuple->dst_ipv6, &ipv6_hdr(skb)->daddr,
- sizeof(struct in6_addr))))
- return true;
+ if (tuple->src_port != fk->ports.src || tuple->dst_port != fk->ports.dst)
+ return false;
+ if (tuple->etype != fk->basic.n_proto)
+ return false;
+ if (tuple->etype == htons(ETH_P_IP))
+ return tuple->src_ipv4 == fk->addrs.v4addrs.src &&
+ tuple->dst_ipv4 == fk->addrs.v4addrs.dst;
+ if (tuple->etype == htons(ETH_P_IPV6))
+ return !memcmp(&tuple->src_ipv6, &fk->addrs.v6addrs.src,
+ sizeof(struct in6_addr)) &&
+ !memcmp(&tuple->dst_ipv6, &fk->addrs.v6addrs.dst,
+ sizeof(struct in6_addr));
return false;
}
static struct arfs_rule *arfs_find_rule(struct arfs_table *arfs_t,
- const struct sk_buff *skb)
+ const struct flow_keys *fk)
{
struct arfs_rule *arfs_rule;
struct hlist_head *head;
- __be16 src_port = arfs_get_src_port(skb);
- __be16 dst_port = arfs_get_dst_port(skb);
- head = arfs_hash_bucket(arfs_t, src_port, dst_port);
+ head = arfs_hash_bucket(arfs_t, fk->ports.src, fk->ports.dst);
hlist_for_each_entry(arfs_rule, head, hlist) {
- if (arfs_rule->tuple.src_port == src_port &&
- arfs_rule->tuple.dst_port == dst_port &&
- arfs_cmp_ips(&arfs_rule->tuple, skb)) {
+ if (arfs_cmp(&arfs_rule->tuple, fk))
return arfs_rule;
- }
}
return NULL;
struct mlx5e_arfs_tables *arfs = &priv->fs.arfs;
struct arfs_table *arfs_t;
struct arfs_rule *arfs_rule;
+ struct flow_keys fk;
+
+ if (!skb_flow_dissect_flow_keys(skb, &fk, 0))
+ return -EPROTONOSUPPORT;
- if (skb->protocol != htons(ETH_P_IP) &&
- skb->protocol != htons(ETH_P_IPV6))
+ if (fk.basic.n_proto != htons(ETH_P_IP) &&
+ fk.basic.n_proto != htons(ETH_P_IPV6))
return -EPROTONOSUPPORT;
if (skb->encapsulation)
return -EPROTONOSUPPORT;
- arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
+ arfs_t = arfs_get_table(arfs, fk.basic.ip_proto, fk.basic.n_proto);
if (!arfs_t)
return -EPROTONOSUPPORT;
spin_lock_bh(&arfs->arfs_lock);
- arfs_rule = arfs_find_rule(arfs_t, skb);
+ arfs_rule = arfs_find_rule(arfs_t, &fk);
if (arfs_rule) {
if (arfs_rule->rxq == rxq_index) {
spin_unlock_bh(&arfs->arfs_lock);
}
arfs_rule->rxq = rxq_index;
} else {
- arfs_rule = arfs_alloc_rule(priv, arfs_t, skb,
- rxq_index, flow_id);
+ arfs_rule = arfs_alloc_rule(priv, arfs_t, &fk, rxq_index, flow_id);
if (!arfs_rule) {
spin_unlock_bh(&arfs->arfs_lock);
return -ENOMEM;
{
mutex_lock(&priv->state_lock);
- ch->max_combined = mlx5e_get_netdev_max_channels(priv->netdev);
+ ch->max_combined = priv->max_nch;
ch->combined_count = priv->channels.params.num_channels;
if (priv->xsk.refcnt) {
/* The upper half are XSK queues. */
}
static void get_speed_duplex(struct net_device *netdev,
- u32 eth_proto_oper,
+ u32 eth_proto_oper, bool force_legacy,
struct ethtool_link_ksettings *link_ksettings)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
if (!netif_carrier_ok(netdev))
goto out;
- speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper);
+ speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy);
if (!speed) {
speed = SPEED_UNKNOWN;
goto out;
/* Fields: eth_proto_admin and ext_eth_proto_admin are
* mutually exclusive. Hence try reading legacy advertising
* when extended advertising is zero.
- * admin_ext indicates how eth_proto_admin should be
- * interpreted
+ * admin_ext indicates which proto_admin (ext vs. legacy)
+ * should be read and interpreted
*/
admin_ext = ext;
if (ext && !eth_proto_admin) {
admin_ext = false;
}
- eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+ eth_proto_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, admin_ext,
eth_proto_oper);
eth_proto_lp = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
get_supported(mdev, eth_proto_cap, link_ksettings);
get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
admin_ext);
- get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
+ get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext,
+ link_ksettings);
eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
return ptys_modes;
}
+static bool ext_link_mode_requested(const unsigned long *adver)
+{
+#define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT
+ int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT;
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(modes);
+
+ bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size);
+ return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
+static bool ext_speed_requested(u32 speed)
+{
+#define MLX5E_MAX_PTYS_LEGACY_SPEED 100000
+ return !!(speed > MLX5E_MAX_PTYS_LEGACY_SPEED);
+}
+
+static bool ext_requested(u8 autoneg, const unsigned long *adver, u32 speed)
+{
+ bool ext_link_mode = ext_link_mode_requested(adver);
+ bool ext_speed = ext_speed_requested(speed);
+
+ return autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_speed;
+}
+
int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
const struct ethtool_link_ksettings *link_ksettings)
{
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_port_eth_proto eproto;
+ const unsigned long *adver;
bool an_changes = false;
u8 an_disable_admin;
bool ext_supported;
- bool ext_requested;
u8 an_disable_cap;
bool an_disable;
u32 link_modes;
u8 an_status;
+ u8 autoneg;
u32 speed;
+ bool ext;
int err;
u32 (*ethtool2ptys_adver_func)(const unsigned long *adver);
-#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1)
+ adver = link_ksettings->link_modes.advertising;
+ autoneg = link_ksettings->base.autoneg;
+ speed = link_ksettings->base.speed;
- ext_requested = !!(link_ksettings->link_modes.advertising[0] >
- MLX5E_PTYS_EXT ||
- link_ksettings->link_modes.advertising[1]);
+ ext = ext_requested(autoneg, adver, speed),
ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
- ext_requested &= ext_supported;
+ if (!ext_supported && ext)
+ return -EOPNOTSUPP;
- speed = link_ksettings->base.speed;
- ethtool2ptys_adver_func = ext_requested ?
- mlx5e_ethtool2ptys_ext_adver_link :
+ ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link :
mlx5e_ethtool2ptys_adver_link;
- err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto);
+ err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
if (err) {
netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
__func__, err);
goto out;
}
- link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
- ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) :
- mlx5e_port_speed2linkmodes(mdev, speed);
+ link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
+ mlx5e_port_speed2linkmodes(mdev, speed, !ext);
+
+ if ((link_modes & MLX5E_PROT_MASK(MLX5E_56GBASE_R4)) &&
+ autoneg != AUTONEG_ENABLE) {
+ netdev_err(priv->netdev, "%s: 56G link speed requires autoneg enabled\n",
+ __func__);
+ err = -EINVAL;
+ goto out;
+ }
link_modes = link_modes & eproto.cap;
if (!link_modes) {
mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap,
&an_disable_admin);
- an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
+ an_disable = autoneg == AUTONEG_DISABLE;
an_changes = ((!an_disable && an_disable_admin) ||
(an_disable && !an_disable_admin));
if (!an_changes && link_modes == eproto.admin)
goto out;
- mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested);
+ mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
mlx5_toggle_port_link(mdev);
out:
struct mlx5_core_dev *mdev = priv->mdev;
int err;
+ if (!MLX5_CAP_GEN(mdev, vport_group_manager))
+ return -EOPNOTSUPP;
+
if (pauseparam->autoneg)
return -EINVAL;
return 0;
}
+int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
+ struct ethtool_flash *flash)
+{
+ struct mlx5_core_dev *mdev = priv->mdev;
+ struct net_device *dev = priv->netdev;
+ const struct firmware *fw;
+ int err;
+
+ if (flash->region != ETHTOOL_FLASH_ALL_REGIONS)
+ return -EOPNOTSUPP;
+
+ err = request_firmware_direct(&fw, flash->data, &dev->dev);
+ if (err)
+ return err;
+
+ dev_hold(dev);
+ rtnl_unlock();
+
+ err = mlx5_firmware_flash(mdev, fw, NULL);
+ release_firmware(fw);
+
+ rtnl_lock();
+ dev_put(dev);
+ return err;
+}
+
+static int mlx5e_flash_device(struct net_device *dev,
+ struct ethtool_flash *flash)
+{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
+ return mlx5e_ethtool_flash_device(priv, flash);
+}
+
static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
bool is_rx_cq)
{
.set_wol = mlx5e_set_wol,
.get_module_info = mlx5e_get_module_info,
.get_module_eeprom = mlx5e_get_module_eeprom,
+ .flash_device = mlx5e_flash_device,
.get_priv_flags = mlx5e_get_priv_flags,
.set_priv_flags = mlx5e_set_priv_flags,
.self_test = mlx5e_self_test,
return -ENOSPC;
if (fs->ring_cookie != RX_CLS_FLOW_DISC)
- if (!mlx5e_qid_validate(&priv->channels.params, fs->ring_cookie))
+ if (!mlx5e_qid_validate(priv->profile, &priv->channels.params,
+ fs->ring_cookie))
return -EINVAL;
switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
{
- struct mlx5e_wqe_frag_info next_frag, *prev;
+ struct mlx5e_wqe_frag_info next_frag = {};
+ struct mlx5e_wqe_frag_info *prev = NULL;
int i;
next_frag.di = &rq->wqe.di[0];
- next_frag.offset = 0;
- prev = NULL;
for (i = 0; i < mlx5_wq_cyc_get_size(&rq->wqe.wq); i++) {
struct mlx5e_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
{
sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
- clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
netdev_tx_reset_queue(sq->txq);
netif_tx_start_queue(sq->txq);
struct mlx5e_channel_param *cparam)
{
struct mlx5e_priv *priv = c->priv;
- int err, tc, max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
+ int err, tc;
for (tc = 0; tc < params->num_tc; tc++) {
- int txq_ix = c->ix + tc * max_nch;
+ int txq_ix = c->ix + tc * priv->max_nch;
err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix,
params, &cparam->sq, &c->sq[tc], tc);
int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int err;
int ix;
- for (ix = 0; ix < max_nch; ix++) {
+ for (ix = 0; ix < priv->max_nch; ix++) {
err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt);
if (unlikely(err))
goto err_destroy_rqts;
void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int i;
- for (i = 0; i < max_nch; i++)
+ for (i = 0; i < priv->max_nch; i++)
mlx5e_destroy_rqt(priv, &tirs[i].rqt);
}
mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
}
- for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) {
+ for (ix = 0; ix < priv->max_nch; ix++) {
struct mlx5e_redirect_rqt_param direct_rrp = {
.is_rss = false,
{
goto free_in;
}
- for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) {
+ for (ix = 0; ix < priv->max_nch; ix++) {
err = mlx5_core_modify_tir(mdev, priv->direct_tir[ix].tirn,
in, inlen);
if (err)
static void mlx5e_build_tc2txq_maps(struct mlx5e_priv *priv)
{
- int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int i, tc;
- for (i = 0; i < max_nch; i++)
+ for (i = 0; i < priv->max_nch; i++)
for (tc = 0; tc < priv->profile->max_tc; tc++)
- priv->channel_tc2txq[i][tc] = i + tc * max_nch;
+ priv->channel_tc2txq[i][tc] = i + tc * priv->max_nch;
}
static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv)
void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
{
int num_txqs = priv->channels.num * priv->channels.params.num_tc;
- int num_rxqs = priv->channels.num * MLX5E_NUM_RQ_GROUPS;
+ int num_rxqs = priv->channels.num * priv->profile->rq_groups;
struct net_device *netdev = priv->netdev;
mlx5e_netdev_set_tcs(netdev);
int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
struct mlx5e_tir *tir;
void *tirc;
int inlen;
if (!in)
return -ENOMEM;
- for (ix = 0; ix < max_nch; ix++) {
+ for (ix = 0; ix < priv->max_nch; ix++) {
memset(in, 0, inlen);
tir = &tirs[ix];
tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs)
{
- const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
int i;
- for (i = 0; i < max_nch; i++)
+ for (i = 0; i < priv->max_nch; i++)
mlx5e_destroy_tir(priv->mdev, &tirs[i]);
}
{
int i;
- for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) {
+ for (i = 0; i < priv->max_nch; i++) {
struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq;
struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
return err;
mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params,
- mlx5e_get_netdev_max_channels(netdev),
- netdev->mtu);
+ priv->max_nch, netdev->mtu);
mlx5e_timestamp_init(priv);
.rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe,
.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
.max_tc = MLX5E_MAX_NUM_TC,
+ .rq_groups = MLX5E_NUM_RQ_GROUPS(XSK),
};
/* mlx5e generic netdev management API (move to en_common.c) */
priv->profile = profile;
priv->ppriv = ppriv;
priv->msglevel = MLX5E_MSG_LEVEL;
+ priv->max_nch = netdev->num_rx_queues / max_t(u8, profile->rq_groups, 1);
priv->max_opened_tc = 1;
mutex_init(&priv->state_lock);
netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv),
nch * profile->max_tc,
- nch * MLX5E_NUM_RQ_GROUPS);
+ nch * profile->rq_groups);
if (!netdev) {
mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n");
return NULL;
list_add(&indr_priv->list,
&rpriv->uplink_priv.tc_indr_block_priv_list);
- block_cb = flow_block_cb_alloc(f->net,
- mlx5e_rep_indr_setup_block_cb,
+ block_cb = flow_block_cb_alloc(mlx5e_rep_indr_setup_block_cb,
indr_priv, indr_priv,
mlx5e_rep_indr_tc_block_unbind);
if (IS_ERR(block_cb)) {
if (!indr_priv)
return -ENOENT;
- block_cb = flow_block_cb_lookup(f,
+ block_cb = flow_block_cb_lookup(f->block,
mlx5e_rep_indr_setup_block_cb,
indr_priv);
if (!block_cb)
.rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep,
.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
.max_tc = 1,
+ .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
};
static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
.rx_handlers.handle_rx_cqe = mlx5e_handle_rx_cqe_rep,
.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
.max_tc = MLX5E_MAX_NUM_TC,
+ .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
};
static bool
memset(s, 0, sizeof(*s));
- for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) {
+ for (i = 0; i < priv->max_nch; i++) {
struct mlx5e_channel_stats *channel_stats =
&priv->channel_stats[i];
struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq;
static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
{
- int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
+ int max_nch = priv->max_nch;
return (NUM_RQ_STATS * max_nch) +
(NUM_CH_STATS * max_nch) +
static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
int idx)
{
- int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
bool is_xsk = priv->xsk.ever_used;
+ int max_nch = priv->max_nch;
int i, j, tc;
for (i = 0; i < max_nch; i++)
static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
int idx)
{
- int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
bool is_xsk = priv->xsk.ever_used;
+ int max_nch = priv->max_nch;
int i, j, tc;
for (i = 0; i < max_nch; i++)
void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
{
struct mlx5e_neigh *m_neigh = &nhe->m_neigh;
- u64 bytes, packets, lastuse = 0;
struct mlx5e_tc_flow *flow;
struct mlx5e_encap_entry *e;
struct mlx5_fc *counter;
struct neigh_table *tbl;
bool neigh_used = false;
struct neighbour *n;
+ u64 lastuse;
if (m_neigh->family == AF_INET)
tbl = &arp_tbl;
encaps[efi->index]);
if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
counter = mlx5e_tc_get_counter(flow);
- mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+ lastuse = mlx5_fc_query_lastuse(counter);
if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) {
neigh_used = true;
break;
struct mlx5_flow_spec *spec,
struct flow_cls_offload *f,
struct net_device *filter_dev,
- u8 *match_level, u8 *tunnel_match_level)
+ u8 *inner_match_level, u8 *outer_match_level)
{
struct netlink_ext_ack *extack = f->common.extack;
void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
struct flow_dissector *dissector = rule->match.dissector;
u16 addr_type = 0;
u8 ip_proto = 0;
+ u8 *match_level;
- *match_level = MLX5_MATCH_NONE;
+ match_level = outer_match_level;
if (dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_META) |
}
if (mlx5e_get_tc_tun(filter_dev)) {
- if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level))
+ if (parse_tunnel_attr(priv, spec, f, filter_dev,
+ outer_match_level))
return -EOPNOTSUPP;
- /* In decap flow, header pointers should point to the inner
+ /* At this point, header pointers should point to the inner
* headers, outer header were already set by parse_tunnel_attr
*/
+ match_level = inner_match_level;
headers_c = get_match_headers_criteria(MLX5_FLOW_CONTEXT_ACTION_DECAP,
spec);
headers_v = get_match_headers_value(MLX5_FLOW_CONTEXT_ACTION_DECAP,
struct flow_cls_offload *f,
struct net_device *filter_dev)
{
+ u8 inner_match_level, outer_match_level, non_tunnel_match_level;
struct netlink_ext_ack *extack = f->common.extack;
struct mlx5_core_dev *dev = priv->mdev;
struct mlx5_eswitch *esw = dev->priv.eswitch;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
- u8 match_level, tunnel_match_level = MLX5_MATCH_NONE;
struct mlx5_eswitch_rep *rep;
int err;
- err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level);
+ inner_match_level = MLX5_MATCH_NONE;
+ outer_match_level = MLX5_MATCH_NONE;
+
+ err = __parse_cls_flower(priv, spec, f, filter_dev, &inner_match_level,
+ &outer_match_level);
+ non_tunnel_match_level = (inner_match_level == MLX5_MATCH_NONE) ?
+ outer_match_level : inner_match_level;
if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
rep = rpriv->rep;
if (rep->vport != MLX5_VPORT_UPLINK &&
(esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
- esw->offloads.inline_mode < match_level)) {
+ esw->offloads.inline_mode < non_tunnel_match_level)) {
NL_SET_ERR_MSG_MOD(extack,
"Flow is not offloaded due to min inline setting");
netdev_warn(priv->netdev,
"Flow is not offloaded due to min inline setting, required %d actual %d\n",
- match_level, esw->offloads.inline_mode);
+ non_tunnel_match_level, esw->offloads.inline_mode);
return -EOPNOTSUPP;
}
}
if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
- flow->esw_attr->match_level = match_level;
- flow->esw_attr->tunnel_match_level = tunnel_match_level;
+ flow->esw_attr->inner_match_level = inner_match_level;
+ flow->esw_attr->outer_match_level = outer_match_level;
} else {
- flow->nic_attr->match_level = match_level;
+ flow->nic_attr->match_level = non_tunnel_match_level;
}
return err;
esw_attr->parse_attr = parse_attr;
esw_attr->chain = f->common.chain_index;
- esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
+ esw_attr->prio = f->common.prio;
esw_attr->in_rep = in_rep;
esw_attr->in_mdev = in_mdev;
static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)
{
struct mlx5e_sq_stats *stats = sq->stats;
- struct dim_sample dim_sample;
+ struct dim_sample dim_sample = {};
if (unlikely(!test_bit(MLX5E_SQ_STATE_AM, &sq->state)))
return;
static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq)
{
struct mlx5e_rq_stats *stats = rq->stats;
- struct dim_sample dim_sample;
+ struct dim_sample dim_sample = {};
if (unlikely(!test_bit(MLX5E_RQ_STATE_AM, &rq->state)))
return;
struct mlx5_termtbl_handle *termtbl;
} dests[MLX5_MAX_FLOW_FWD_VPORTS];
u32 mod_hdr_id;
- u8 match_level;
- u8 tunnel_match_level;
+ u8 inner_match_level;
+ u8 outer_match_level;
struct mlx5_fc *counter;
u32 chain;
u16 prio;
mlx5_eswitch_set_rule_source_port(esw, spec, attr);
- if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
- if (attr->tunnel_match_level != MLX5_MATCH_NONE)
- spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
- if (attr->match_level != MLX5_MATCH_NONE)
- spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
- } else if (attr->match_level != MLX5_MATCH_NONE) {
+ if (attr->outer_match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
- }
+ if (attr->inner_match_level != MLX5_MATCH_NONE)
+ spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
flow_act.modify_id = attr->mod_hdr_id;
mlx5_eswitch_set_rule_source_port(esw, spec, attr);
spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
- if (attr->match_level != MLX5_MATCH_NONE)
+ if (attr->outer_match_level != MLX5_MATCH_NONE)
spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
FS_FT_SNIFFER_RX = 0X5,
FS_FT_SNIFFER_TX = 0X6,
FS_FT_RDMA_RX = 0X7,
- FS_FT_MAX_TYPE = FS_FT_SNIFFER_TX,
+ FS_FT_MAX_TYPE = FS_FT_RDMA_RX,
};
enum fs_flow_table_op_mod {
(type == FS_FT_FDB) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) : \
(type == FS_FT_SNIFFER_RX) ? MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) : \
(type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \
- (BUILD_BUG_ON_ZERO(FS_FT_SNIFFER_TX != FS_FT_MAX_TYPE))\
+ (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \
+ (BUILD_BUG_ON_ZERO(FS_FT_RDMA_RX != FS_FT_MAX_TYPE))\
)
#endif
}
EXPORT_SYMBOL(mlx5_fc_query);
+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter)
+{
+ return counter->cache.lastuse;
+}
+
void mlx5_fc_query_cached(struct mlx5_fc *counter,
u64 *bytes, u64 *packets, u64 *lastuse)
{
data_size = crdump_size - offset;
else
data_size = MLX5_CR_DUMP_CHUNK_SIZE;
- err = devlink_fmsg_binary_put(fmsg, cr_data, data_size);
+ err = devlink_fmsg_binary_put(fmsg, (char *)cr_data + offset,
+ data_size);
if (err)
goto free_data;
}
if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
goto out;
+ fatal_error = check_fatal_sensors(dev);
+
+ if (fatal_error && !health->fatal_error) {
+ mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);
+ dev->priv.health.fatal_error = fatal_error;
+ print_health_info(dev);
+ mlx5_trigger_health_work(dev);
+ goto out;
+ }
+
count = ioread32be(health->health_counter);
if (count == health->prev)
++health->miss_counter;
if (health->synd && health->synd != prev_synd)
queue_work(health->wq, &health->report_work);
- fatal_error = check_fatal_sensors(dev);
-
- if (fatal_error && !health->fatal_error) {
- mlx5_core_err(dev, "Fatal error %u detected\n", fatal_error);
- dev->priv.health.fatal_error = fatal_error;
- print_health_info(dev);
- mlx5_trigger_health_work(dev);
- }
-
out:
mod_timer(&health->timer, get_next_poll_jiffies());
}
return mlx5e_ethtool_get_ts_info(priv, info);
}
+static int mlx5i_flash_device(struct net_device *netdev,
+ struct ethtool_flash *flash)
+{
+ struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+
+ return mlx5e_ethtool_flash_device(priv, flash);
+}
+
enum mlx5_ptys_width {
MLX5_PTYS_WIDTH_1X = 1 << 0,
MLX5_PTYS_WIDTH_2X = 1 << 1,
.get_ethtool_stats = mlx5i_get_ethtool_stats,
.get_ringparam = mlx5i_get_ringparam,
.set_ringparam = mlx5i_set_ringparam,
+ .flash_device = mlx5i_flash_device,
.get_channels = mlx5i_get_channels,
.set_channels = mlx5i_set_channels,
.get_coalesce = mlx5i_get_coalesce,
netdev->mtu = netdev->max_mtu;
mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params,
- mlx5e_get_netdev_max_channels(netdev),
- netdev->mtu);
+ priv->max_nch, netdev->mtu);
mlx5i_build_nic_params(mdev, &priv->channels.params);
mlx5e_timestamp_init(priv);
static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv)
{
- int max_nch = mlx5e_get_netdev_max_channels(priv->netdev);
struct mlx5e_sw_stats s = { 0 };
int i, j;
- for (i = 0; i < max_nch; i++) {
+ for (i = 0; i < priv->max_nch; i++) {
struct mlx5e_channel_stats *channel_stats;
struct mlx5e_rq_stats *rq_stats;
.rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe,
.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
.max_tc = MLX5I_MAX_NUM_TC,
+ .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
};
/* mlx5i netdev NDos */
.rx_handlers.handle_rx_cqe = mlx5i_handle_rx_cqe,
.rx_handlers.handle_rx_cqe_mpwqe = NULL, /* Not supported */
.max_tc = MLX5I_MAX_NUM_TC,
+ .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR),
};
const struct mlx5e_profile *mlx5i_pkey_get_profile(void)
case 128:
general_obj_key_size =
MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128;
+ key_p += sz_bytes;
break;
case 256:
general_obj_key_size =
bool register_block = false;
int err;
- block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+ block_cb = flow_block_cb_lookup(f->block,
+ mlxsw_sp_setup_tc_block_cb_flower,
mlxsw_sp);
if (!block_cb) {
acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net);
if (!acl_block)
return -ENOMEM;
- block_cb = flow_block_cb_alloc(f->net,
- mlxsw_sp_setup_tc_block_cb_flower,
+ block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb_flower,
mlxsw_sp, acl_block,
mlxsw_sp_tc_block_flower_release);
if (IS_ERR(block_cb)) {
struct flow_block_cb *block_cb;
int err;
- block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+ block_cb = flow_block_cb_lookup(f->block,
+ mlxsw_sp_setup_tc_block_cb_flower,
mlxsw_sp);
if (!block_cb)
return;
struct flow_block_offload *f)
{
struct flow_block_cb *block_cb;
- tc_setup_cb_t *cb;
+ flow_setup_cb_t *cb;
bool ingress;
int err;
&mlxsw_sp_block_cb_list))
return -EBUSY;
- block_cb = flow_block_cb_alloc(f->net, cb, mlxsw_sp_port,
+ block_cb = flow_block_cb_alloc(cb, mlxsw_sp_port,
mlxsw_sp_port, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
case FLOW_BLOCK_UNBIND:
mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port,
f, ingress);
- block_cb = flow_block_cb_lookup(f, cb, mlxsw_sp_port);
+ block_cb = flow_block_cb_lookup(f->block, cb, mlxsw_sp_port);
if (!block_cb)
return -ENOENT;
return 0;
err_sp2_pci_driver_register:
- mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+ mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
err_sp1_pci_driver_register:
mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
err_sp2_core_driver_register:
int mlxsw_sp_nve_init(struct mlxsw_sp *mlxsw_sp);
void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp);
+/* spectrum_nve_vxlan.c */
+int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp);
+void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp);
+
#endif
void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
unsigned int priority)
{
- rulei->priority = priority >> 16;
+ rulei->priority = priority;
}
void mlxsw_sp_acl_rulei_keymask_u32(struct mlxsw_sp_acl_rule_info *rulei,
MLXSW_SP1_SB_PR_CPU_SIZE, true, false),
};
-#define MLXSW_SP2_SB_PR_INGRESS_SIZE 38128752
-#define MLXSW_SP2_SB_PR_EGRESS_SIZE 38128752
+#define MLXSW_SP2_SB_PR_INGRESS_SIZE 35297568
+#define MLXSW_SP2_SB_PR_EGRESS_SIZE 35297568
#define MLXSW_SP2_SB_PR_CPU_SIZE (256 * 1000)
/* Order according to mlxsw_sp2_sb_pool_dess */
ops->fini(nve);
mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1,
nve->tunnel_index);
+ memset(&nve->config, 0, sizeof(nve->config));
}
nve->num_nve_tunnels--;
}
unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX];
u32 tunnel_index;
u16 ul_rif_index; /* Reserved for Spectrum */
+ unsigned int inc_parsing_depth_refs;
};
struct mlxsw_sp_nve_ops {
config->udp_dport = cfg->dst_port;
}
-static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
- unsigned int parsing_depth,
- __be16 udp_dport)
+static int __mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
+ unsigned int parsing_depth,
+ __be16 udp_dport)
{
char mprs_pl[MLXSW_REG_MPRS_LEN];
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
}
+static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
+ __be16 udp_dport)
+{
+ int parsing_depth = mlxsw_sp->nve->inc_parsing_depth_refs ?
+ MLXSW_SP_NVE_VXLAN_PARSING_DEPTH :
+ MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH;
+
+ return __mlxsw_sp_nve_parsing_set(mlxsw_sp, parsing_depth, udp_dport);
+}
+
+static int
+__mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp,
+ __be16 udp_dport)
+{
+ int err;
+
+ mlxsw_sp->nve->inc_parsing_depth_refs++;
+
+ err = mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport);
+ if (err)
+ goto err_nve_parsing_set;
+ return 0;
+
+err_nve_parsing_set:
+ mlxsw_sp->nve->inc_parsing_depth_refs--;
+ return err;
+}
+
+static void
+__mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp,
+ __be16 udp_dport)
+{
+ mlxsw_sp->nve->inc_parsing_depth_refs--;
+ mlxsw_sp_nve_parsing_set(mlxsw_sp, udp_dport);
+}
+
+int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp)
+{
+ __be16 udp_dport = mlxsw_sp->nve->config.udp_dport;
+
+ return __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, udp_dport);
+}
+
+void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp)
+{
+ __be16 udp_dport = mlxsw_sp->nve->config.udp_dport;
+
+ __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, udp_dport);
+}
+
static void
mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl,
const struct mlxsw_sp_nve_config *config)
struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
int err;
- err = mlxsw_sp_nve_parsing_set(mlxsw_sp,
- MLXSW_SP_NVE_VXLAN_PARSING_DEPTH,
- config->udp_dport);
+ err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport);
if (err)
return err;
err_rtdp_set:
mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp);
err_config_set:
- mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
- config->udp_dport);
+ __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
return err;
}
mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id,
config->ul_proto, &config->ul_sip);
mlxsw_sp1_nve_vxlan_config_clear(mlxsw_sp);
- mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
- config->udp_dport);
+ __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
}
static int
struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
int err;
- err = mlxsw_sp_nve_parsing_set(mlxsw_sp,
- MLXSW_SP_NVE_VXLAN_PARSING_DEPTH,
- config->udp_dport);
+ err = __mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp, config->udp_dport);
if (err)
return err;
err_rtdp_set:
mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
err_config_set:
- mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
- config->udp_dport);
+ __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
return err;
}
mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id,
config->ul_proto, &config->ul_sip);
mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
- mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
- config->udp_dport);
+ __mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp, 0);
}
const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = {
struct mlxsw_sp_ptp_state {
struct mlxsw_sp *mlxsw_sp;
- struct rhashtable unmatched_ht;
+ struct rhltable unmatched_ht;
spinlock_t unmatched_lock; /* protects the HT */
struct delayed_work ht_gc_dw;
u32 gc_cycle;
struct mlxsw_sp1_ptp_unmatched {
struct mlxsw_sp1_ptp_key key;
- struct rhash_head ht_node;
+ struct rhlist_head ht_node;
struct rcu_head rcu;
struct sk_buff *skb;
u64 timestamp;
/* Returns NULL on successful insertion, a pointer on conflict, or an ERR_PTR on
* error.
*/
-static struct mlxsw_sp1_ptp_unmatched *
+static int
mlxsw_sp1_ptp_unmatched_save(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp1_ptp_key key,
struct sk_buff *skb,
int cycles = MLXSW_SP1_PTP_HT_GC_TIMEOUT / MLXSW_SP1_PTP_HT_GC_INTERVAL;
struct mlxsw_sp_ptp_state *ptp_state = mlxsw_sp->ptp_state;
struct mlxsw_sp1_ptp_unmatched *unmatched;
- struct mlxsw_sp1_ptp_unmatched *conflict;
+ int err;
unmatched = kzalloc(sizeof(*unmatched), GFP_ATOMIC);
if (!unmatched)
- return ERR_PTR(-ENOMEM);
+ return -ENOMEM;
unmatched->key = key;
unmatched->skb = skb;
unmatched->timestamp = timestamp;
unmatched->gc_cycle = mlxsw_sp->ptp_state->gc_cycle + cycles;
- conflict = rhashtable_lookup_get_insert_fast(&ptp_state->unmatched_ht,
- &unmatched->ht_node,
- mlxsw_sp1_ptp_unmatched_ht_params);
- if (conflict)
+ err = rhltable_insert(&ptp_state->unmatched_ht, &unmatched->ht_node,
+ mlxsw_sp1_ptp_unmatched_ht_params);
+ if (err)
kfree(unmatched);
- return conflict;
+ return err;
}
static struct mlxsw_sp1_ptp_unmatched *
mlxsw_sp1_ptp_unmatched_lookup(struct mlxsw_sp *mlxsw_sp,
- struct mlxsw_sp1_ptp_key key)
+ struct mlxsw_sp1_ptp_key key, int *p_length)
{
- return rhashtable_lookup(&mlxsw_sp->ptp_state->unmatched_ht, &key,
- mlxsw_sp1_ptp_unmatched_ht_params);
+ struct mlxsw_sp1_ptp_unmatched *unmatched, *last = NULL;
+ struct rhlist_head *tmp, *list;
+ int length = 0;
+
+ list = rhltable_lookup(&mlxsw_sp->ptp_state->unmatched_ht, &key,
+ mlxsw_sp1_ptp_unmatched_ht_params);
+ rhl_for_each_entry_rcu(unmatched, tmp, list, ht_node) {
+ last = unmatched;
+ length++;
+ }
+
+ *p_length = length;
+ return last;
}
static int
mlxsw_sp1_ptp_unmatched_remove(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp1_ptp_unmatched *unmatched)
{
- return rhashtable_remove_fast(&mlxsw_sp->ptp_state->unmatched_ht,
- &unmatched->ht_node,
- mlxsw_sp1_ptp_unmatched_ht_params);
+ return rhltable_remove(&mlxsw_sp->ptp_state->unmatched_ht,
+ &unmatched->ht_node,
+ mlxsw_sp1_ptp_unmatched_ht_params);
}
/* This function is called in the following scenarios:
struct mlxsw_sp1_ptp_key key,
struct sk_buff *skb, u64 timestamp)
{
- struct mlxsw_sp1_ptp_unmatched *unmatched, *conflict;
+ struct mlxsw_sp1_ptp_unmatched *unmatched;
+ int length;
int err;
rcu_read_lock();
- unmatched = mlxsw_sp1_ptp_unmatched_lookup(mlxsw_sp, key);
-
spin_lock(&mlxsw_sp->ptp_state->unmatched_lock);
- if (unmatched) {
- /* There was an unmatched entry when we looked, but it may have
- * been removed before we took the lock.
- */
- err = mlxsw_sp1_ptp_unmatched_remove(mlxsw_sp, unmatched);
- if (err)
- unmatched = NULL;
- }
-
- if (!unmatched) {
- /* We have no unmatched entry, but one may have been added after
- * we looked, but before we took the lock.
- */
- unmatched = mlxsw_sp1_ptp_unmatched_save(mlxsw_sp, key,
- skb, timestamp);
- if (IS_ERR(unmatched)) {
- if (skb)
- mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb,
- key.local_port,
- key.ingress, NULL);
- unmatched = NULL;
- } else if (unmatched) {
- /* Save just told us, under lock, that the entry is
- * there, so this has to work.
- */
- err = mlxsw_sp1_ptp_unmatched_remove(mlxsw_sp,
- unmatched);
- WARN_ON_ONCE(err);
- }
- }
-
- /* If unmatched is non-NULL here, it comes either from the lookup, or
- * from the save attempt above. In either case the entry was removed
- * from the hash table. If unmatched is NULL, a new unmatched entry was
- * added to the hash table, and there was no conflict.
- */
-
+ unmatched = mlxsw_sp1_ptp_unmatched_lookup(mlxsw_sp, key, &length);
if (skb && unmatched && unmatched->timestamp) {
unmatched->skb = skb;
} else if (timestamp && unmatched && unmatched->skb) {
unmatched->timestamp = timestamp;
- } else if (unmatched) {
- /* unmatched holds an older entry of the same type: either an
- * skb if we are handling skb, or a timestamp if we are handling
- * timestamp. We can't match that up, so save what we have.
+ } else {
+ /* Either there is no entry to match, or one that is there is
+ * incompatible.
*/
- conflict = mlxsw_sp1_ptp_unmatched_save(mlxsw_sp, key,
- skb, timestamp);
- if (IS_ERR(conflict)) {
- if (skb)
- mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb,
- key.local_port,
- key.ingress, NULL);
- } else {
- /* Above, we removed an object with this key from the
- * hash table, under lock, so conflict can not be a
- * valid pointer.
- */
- WARN_ON_ONCE(conflict);
- }
+ if (length < 100)
+ err = mlxsw_sp1_ptp_unmatched_save(mlxsw_sp, key,
+ skb, timestamp);
+ else
+ err = -E2BIG;
+ if (err && skb)
+ mlxsw_sp1_ptp_packet_finish(mlxsw_sp, skb,
+ key.local_port,
+ key.ingress, NULL);
+ unmatched = NULL;
+ }
+
+ if (unmatched) {
+ err = mlxsw_sp1_ptp_unmatched_remove(mlxsw_sp, unmatched);
+ WARN_ON_ONCE(err);
}
spin_unlock(&mlxsw_sp->ptp_state->unmatched_lock);
local_bh_disable();
spin_lock(&ptp_state->unmatched_lock);
- err = rhashtable_remove_fast(&ptp_state->unmatched_ht,
- &unmatched->ht_node,
- mlxsw_sp1_ptp_unmatched_ht_params);
+ err = rhltable_remove(&ptp_state->unmatched_ht, &unmatched->ht_node,
+ mlxsw_sp1_ptp_unmatched_ht_params);
spin_unlock(&ptp_state->unmatched_lock);
if (err)
ptp_state = container_of(dwork, struct mlxsw_sp_ptp_state, ht_gc_dw);
gc_cycle = ptp_state->gc_cycle++;
- rhashtable_walk_enter(&ptp_state->unmatched_ht, &iter);
+ rhltable_walk_enter(&ptp_state->unmatched_ht, &iter);
rhashtable_walk_start(&iter);
while ((obj = rhashtable_walk_next(&iter))) {
if (IS_ERR(obj))
spin_lock_init(&ptp_state->unmatched_lock);
- err = rhashtable_init(&ptp_state->unmatched_ht,
- &mlxsw_sp1_ptp_unmatched_ht_params);
+ err = rhltable_init(&ptp_state->unmatched_ht,
+ &mlxsw_sp1_ptp_unmatched_ht_params);
if (err)
goto err_hashtable_init;
err_mtptpt1_set:
mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0, 0);
err_mtptpt_set:
- rhashtable_destroy(&ptp_state->unmatched_ht);
+ rhltable_destroy(&ptp_state->unmatched_ht);
err_hashtable_init:
kfree(ptp_state);
return ERR_PTR(err);
mlxsw_sp1_ptp_set_fifo_clr_on_trap(mlxsw_sp, false);
mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP1, 0);
mlxsw_sp_ptp_mtptpt_set(mlxsw_sp, MLXSW_REG_MTPTPT_TRAP_ID_PTP0, 0);
- rhashtable_free_and_destroy(&ptp_state->unmatched_ht,
- &mlxsw_sp1_ptp_unmatched_free_fn, NULL);
+ rhltable_free_and_destroy(&ptp_state->unmatched_ht,
+ &mlxsw_sp1_ptp_unmatched_free_fn, NULL);
kfree(ptp_state);
}
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_port *tmp;
+ u16 orig_ing_types = 0;
+ u16 orig_egr_types = 0;
+ int err;
int i;
/* MTPPPC configures timestamping globally, not per port. Find the
*/
for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) {
tmp = mlxsw_sp->ports[i];
+ if (tmp) {
+ orig_ing_types |= tmp->ptp.ing_types;
+ orig_egr_types |= tmp->ptp.egr_types;
+ }
if (tmp && tmp != mlxsw_sp_port) {
ing_types |= tmp->ptp.ing_types;
egr_types |= tmp->ptp.egr_types;
}
}
+ if ((ing_types || egr_types) && !(orig_ing_types || orig_egr_types)) {
+ err = mlxsw_sp_nve_inc_parsing_depth_get(mlxsw_sp);
+ if (err) {
+ netdev_err(mlxsw_sp_port->dev, "Failed to increase parsing depth");
+ return err;
+ }
+ }
+ if (!(ing_types || egr_types) && (orig_ing_types || orig_egr_types))
+ mlxsw_sp_nve_inc_parsing_depth_put(mlxsw_sp);
+
return mlxsw_sp1_ptp_mtpppc_set(mlxsw_sp_port->mlxsw_sp,
ing_types, egr_types);
}
void ocelot_deinit(struct ocelot *ocelot)
{
+ cancel_delayed_work(&ocelot->stats_work);
destroy_workqueue(ocelot->stats_queue);
mutex_destroy(&ocelot->stats_lock);
ocelot_ace_deinit();
break;
case OCELOT_ACL_ACTION_TRAP:
VCAP_ACT_SET(PORT_MASK, 0x0);
- VCAP_ACT_SET(MASK_MODE, 0x0);
+ VCAP_ACT_SET(MASK_MODE, 0x1);
VCAP_ACT_SET(POLICE_ENA, 0x0);
VCAP_ACT_SET(POLICE_IDX, 0x0);
VCAP_ACT_SET(CPU_QU_NUM, 0x0);
struct ocelot_port *port;
};
-static u16 get_prio(u32 prio)
-{
- /* prio starts from 0x1000 while the ids starts from 0 */
- return prio >> 16;
-}
-
static int ocelot_flower_parse_action(struct flow_cls_offload *f,
struct ocelot_ace_rule *rule)
{
}
finished_key_parsing:
- ocelot_rule->prio = get_prio(f->common.prio);
+ ocelot_rule->prio = f->common.prio;
ocelot_rule->id = f->cookie;
return ocelot_flower_parse_action(f, ocelot_rule);
}
struct ocelot_ace_rule rule;
int ret;
- rule.prio = get_prio(f->common.prio);
+ rule.prio = f->common.prio;
rule.port = port_block->port;
rule.id = f->cookie;
struct ocelot_ace_rule rule;
int ret;
- rule.prio = get_prio(f->common.prio);
+ rule.prio = f->common.prio;
rule.port = port_block->port;
rule.id = f->cookie;
ret = ocelot_ace_rule_stats_update(&rule);
if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
return -EOPNOTSUPP;
- block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
- port);
+ block_cb = flow_block_cb_lookup(f->block,
+ ocelot_setup_tc_block_cb_flower, port);
if (!block_cb) {
port_block = ocelot_port_block_create(port);
if (!port_block)
return -ENOMEM;
- block_cb = flow_block_cb_alloc(f->net,
- ocelot_setup_tc_block_cb_flower,
+ block_cb = flow_block_cb_alloc(ocelot_setup_tc_block_cb_flower,
port, port_block,
ocelot_tc_block_unbind);
if (IS_ERR(block_cb)) {
{
struct flow_block_cb *block_cb;
- block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
- port);
+ block_cb = flow_block_cb_lookup(f->block,
+ ocelot_setup_tc_block_cb_flower, port);
if (!block_cb)
return;
struct flow_block_offload *f)
{
struct flow_block_cb *block_cb;
- tc_setup_cb_t *cb;
+ flow_setup_cb_t *cb;
int err;
netdev_dbg(port->dev, "tc_block command %d, binder_type %d\n",
if (flow_block_cb_is_busy(cb, port, &ocelot_block_cb_list))
return -EBUSY;
- block_cb = flow_block_cb_alloc(f->net, cb, port, port, NULL);
+ block_cb = flow_block_cb_alloc(cb, port, port, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
list_add_tail(&block_cb->driver_list, f->driver_block_list);
return 0;
case FLOW_BLOCK_UNBIND:
- block_cb = flow_block_cb_lookup(f, cb, port);
+ block_cb = flow_block_cb_lookup(f->block, cb, port);
if (!block_cb)
return -ENOENT;
* setup (if available). */
status = myri10ge_request_irq(mgp);
if (status != 0)
- goto abort_with_firmware;
+ goto abort_with_slices;
myri10ge_free_irq(mgp);
/* Save configuration space to be restored if the
bool clr_gpr, lmem_step step)
{
s32 off = nfp_prog->stack_frame_depth + meta->insn.off + ptr_off;
- bool first = true, last;
+ bool first = true, narrow_ld, last;
bool needs_inc = false;
swreg stack_off_reg;
u8 prev_gpr = 255;
needs_inc = true;
}
+
+ narrow_ld = clr_gpr && size < 8;
+
if (lm3) {
+ unsigned int nop_cnt;
+
emit_csr_wr(nfp_prog, imm_b(nfp_prog), NFP_CSR_ACT_LM_ADDR3);
- /* For size < 4 one slot will be filled by zeroing of upper. */
- wrp_nops(nfp_prog, clr_gpr && size < 8 ? 2 : 3);
+ /* For size < 4 one slot will be filled by zeroing of upper,
+ * but be careful, that zeroing could be eliminated by zext
+ * optimization.
+ */
+ nop_cnt = narrow_ld && meta->flags & FLAG_INSN_DO_ZEXT ? 2 : 3;
+ wrp_nops(nfp_prog, nop_cnt);
}
- if (clr_gpr && size < 8)
+ if (narrow_ld)
wrp_zext(nfp_prog, meta, gpr);
while (size) {
&nfp_block_cb_list))
return -EBUSY;
- block_cb = flow_block_cb_alloc(f->net,
- nfp_flower_setup_tc_block_cb,
+ block_cb = flow_block_cb_alloc(nfp_flower_setup_tc_block_cb,
repr, repr, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
list_add_tail(&block_cb->driver_list, &nfp_block_cb_list);
return 0;
case FLOW_BLOCK_UNBIND:
- block_cb = flow_block_cb_lookup(f, nfp_flower_setup_tc_block_cb,
+ block_cb = flow_block_cb_lookup(f->block,
+ nfp_flower_setup_tc_block_cb,
repr);
if (!block_cb)
return -ENOENT;
struct nfp_flower_priv *priv = app->priv;
struct flow_block_cb *block_cb;
- if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
- !(f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
- nfp_flower_internal_port_can_offload(app, netdev)))
+ if ((f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+ !nfp_flower_internal_port_can_offload(app, netdev)) ||
+ (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
+ nfp_flower_internal_port_can_offload(app, netdev)))
return -EOPNOTSUPP;
switch (f->command) {
case FLOW_BLOCK_BIND:
+ cb_priv = nfp_flower_indr_block_cb_priv_lookup(app, netdev);
+ if (cb_priv &&
+ flow_block_cb_is_busy(nfp_flower_setup_indr_block_cb,
+ cb_priv,
+ &nfp_block_cb_list))
+ return -EBUSY;
+
cb_priv = kmalloc(sizeof(*cb_priv), GFP_KERNEL);
if (!cb_priv)
return -ENOMEM;
cb_priv->app = app;
list_add(&cb_priv->list, &priv->indr_block_cb_priv);
- block_cb = flow_block_cb_alloc(f->net,
- nfp_flower_setup_indr_block_cb,
+ block_cb = flow_block_cb_alloc(nfp_flower_setup_indr_block_cb,
cb_priv, cb_priv,
nfp_flower_setup_indr_tc_release);
if (IS_ERR(block_cb)) {
if (!cb_priv)
return -ENOENT;
- block_cb = flow_block_cb_lookup(f,
+ block_cb = flow_block_cb_lookup(f->block,
nfp_flower_setup_indr_block_cb,
cb_priv);
if (!block_cb)
return -EOPNOTSUPP;
}
- if (flow->common.prio != (1 << 16)) {
+ if (flow->common.prio != 1) {
NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload requires highest priority");
return -EOPNOTSUPP;
}
flow.daddr = *(__be32 *)n->primary_key;
- /* Only concerned with route changes for representors. */
- if (!nfp_netdev_is_nfp_repr(n->dev))
- return NOTIFY_DONE;
-
app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
app = app_priv->app;
+ if (!nfp_netdev_is_nfp_repr(n->dev) &&
+ !nfp_flower_internal_port_can_offload(app, n->dev))
+ return NOTIFY_DONE;
+
/* Only concerned with changes to routes already added to NFP. */
if (!nfp_tun_has_route(app, flow.daddr))
return NOTIFY_DONE;
data = nfp_pr_et(data, "hw_rx_csum_complete");
data = nfp_pr_et(data, "hw_rx_csum_err");
data = nfp_pr_et(data, "rx_replace_buf_alloc_fail");
- data = nfp_pr_et(data, "rx_tls_decrypted");
+ data = nfp_pr_et(data, "rx_tls_decrypted_packets");
data = nfp_pr_et(data, "hw_tx_csum");
data = nfp_pr_et(data, "hw_tx_inner_csum");
data = nfp_pr_et(data, "tx_gather");
data = nfp_pr_et(data, "tx_lso");
- data = nfp_pr_et(data, "tx_tls_encrypted");
+ data = nfp_pr_et(data, "tx_tls_encrypted_packets");
data = nfp_pr_et(data, "tx_tls_ooo");
data = nfp_pr_et(data, "tx_tls_drop_no_sync_data");
Note that the answer to this question doesn't directly affect the
kernel: saying N will just cause the configurator to skip all
- the questions about National Instrument devices.
+ the questions about National Instruments devices.
If you say Y, you will be asked for your specific device in the
following questions.
# SPDX-License-Identifier: GPL-2.0-only
#
-# Packet engine device configuration
+# Packet Engines device configuration
#
config NET_VENDOR_PACKET_ENGINES
- bool "Packet Engine devices"
+ bool "Packet Engines devices"
default y
depends on PCI
---help---
Note that the answer to this question doesn't directly affect the
kernel: saying N will just cause the configurator to skip all
- the questions about packet engine devices. If you say Y, you will
+ the questions about Packet Engines devices. If you say Y, you will
be asked for your specific card in the following questions.
if NET_VENDOR_PACKET_ENGINES
# SPDX-License-Identifier: GPL-2.0-only
#
-# Makefile for the Packet Engine network device drivers.
+# Makefile for the Packet Engines network device drivers.
#
obj-$(CONFIG_HAMACHI) += hamachi.o
snprintf(bit_name, 30,
p_aeu->bit_name, num);
else
- strncpy(bit_name,
+ strlcpy(bit_name,
p_aeu->bit_name, 30);
/* We now need to pass bitmask in its
&drv_version);
if (rc) {
DP_NOTICE(cdev, "Failed sending drv version command\n");
- return rc;
+ goto err4;
}
}
return 0;
+err4:
+ qed_ll2_dealloc_if(cdev);
err3:
qed_hw_stop(cdev);
err2:
/* Vendor specific information */
dev->vendor_id = cdev->vendor_id;
dev->vendor_part_id = cdev->device_id;
- dev->hw_ver = 0;
+ dev->hw_ver = cdev->chip_rev;
dev->fw_ver = (FW_MAJOR_VERSION << 24) | (FW_MINOR_VERSION << 16) |
(FW_REVISION_VERSION << 8) | (FW_ENGINEERING_VERSION);
SET_FIELD(dev->dev_caps, QED_RDMA_DEV_CAP_LOCAL_INV_FENCE, 1);
/* Check atomic operations support in PCI configuration space. */
- pci_read_config_dword(cdev->pdev,
- cdev->pdev->pcie_cap + PCI_EXP_DEVCTL2,
- &pci_status_control);
+ pcie_capability_read_dword(cdev->pdev, PCI_EXP_DEVCTL2,
+ &pci_status_control);
if (pci_status_control & PCI_EXP_DEVCTL2_LTR_EN)
SET_FIELD(dev->dev_caps, QED_RDMA_DEV_CAP_ATOMIC_OP, 1);
ul_header->csum_insert_offset = skb->csum_offset;
ul_header->csum_enabled = 1;
if (ip4h->protocol == IPPROTO_UDP)
- ul_header->udp_ip4_ind = 1;
+ ul_header->udp_ind = 1;
else
- ul_header->udp_ip4_ind = 0;
+ ul_header->udp_ind = 0;
/* Changing remaining fields to network order */
hdr++;
struct rmnet_map_ul_csum_header *ul_header,
struct sk_buff *skb)
{
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)ip6hdr;
__be16 *hdr = (__be16 *)ul_header, offset;
offset = htons((__force u16)(skb_transport_header(skb) -
ul_header->csum_start_offset = offset;
ul_header->csum_insert_offset = skb->csum_offset;
ul_header->csum_enabled = 1;
- ul_header->udp_ip4_ind = 0;
+
+ if (ip6h->nexthdr == IPPROTO_UDP)
+ ul_header->udp_ind = 1;
+ else
+ ul_header->udp_ind = 0;
/* Changing remaining fields to network order */
hdr++;
ul_header->csum_start_offset = 0;
ul_header->csum_insert_offset = 0;
ul_header->csum_enabled = 0;
- ul_header->udp_ip4_ind = 0;
+ ul_header->udp_ind = 0;
priv->stats.csum_sw++;
}
ret = phy_read_paged(tp->phydev, 0x0a46, 0x13);
if (ret & BIT(8))
- phy_modify_paged(tp->phydev, 0x0c41, 0x12, 0, BIT(1));
+ phy_modify_paged(tp->phydev, 0x0c41, 0x15, 0, BIT(1));
else
- phy_modify_paged(tp->phydev, 0x0c41, 0x12, BIT(1), 0);
+ phy_modify_paged(tp->phydev, 0x0c41, 0x15, BIT(1), 0);
/* Enable PHY auto speed down */
phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2));
skb = napi_alloc_skb(&tp->napi, pkt_size);
if (skb)
skb_copy_to_linear_data(skb, data, pkt_size);
+ dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE);
return skb;
}
if (ret)
return ret;
- if (tp->supports_gmii)
- phy_remove_link_mode(phydev,
- ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
- else
+ if (!tp->supports_gmii)
phy_set_max_speed(phydev, SPEED_100);
phy_support_asym_pause(phydev);
{
unsigned int flags;
- if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06:
rtl_unlock_config_regs(tp);
RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
rtl_lock_config_regs(tp);
+ /* fall through */
+ case RTL_GIGA_MAC_VER_07 ... RTL_GIGA_MAC_VER_24:
flags = PCI_IRQ_LEGACY;
- } else {
+ break;
+ default:
flags = PCI_IRQ_ALL_TYPES;
+ break;
}
return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags);
// SPDX-License-Identifier: GPL-2.0
/* Renesas Ethernet AVB device driver
*
- * Copyright (C) 2014-2015 Renesas Electronics Corporation
+ * Copyright (C) 2014-2019 Renesas Electronics Corporation
* Copyright (C) 2015 Renesas Solutions Corp.
* Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com>
*
kfree(ts_skb);
if (tag == tfa_tag) {
skb_tstamp_tx(skb, &shhwtstamps);
+ dev_consume_skb_any(skb);
break;
+ } else {
+ dev_kfree_skb_any(skb);
}
}
ravb_modify(ndev, TCCR, TCCR_TFR, TCCR_TFR);
}
goto unmap;
}
- ts_skb->skb = skb;
+ ts_skb->skb = skb_get(skb);
ts_skb->tag = priv->ts_skb_tag++;
priv->ts_skb_tag &= 0x3ff;
list_add_tail(&ts_skb->list, &priv->ts_skb_list);
/* Clear the timestamp list */
list_for_each_entry_safe(ts_skb, ts_skb2, &priv->ts_skb_list, list) {
list_del(&ts_skb->list);
+ kfree_skb(ts_skb->skb);
kfree(ts_skb);
}
if (fen_info->fi->fib_nh_is_v6) {
NL_SET_ERR_MSG_MOD(info->extack, "IPv6 gateway with IPv4 route is not supported");
+ kfree(fib_work);
return notifier_from_errno(-EINVAL);
}
if (fen_info->fi->nh) {
NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported");
+ kfree(fib_work);
return notifier_from_errno(-EINVAL);
}
}
say Y.
Note that the answer to this question does not directly affect
- the kernel: saying N will just case the configurator to skip all
+ the kernel: saying N will just cause the configurator to skip all
the questions about Samsung chipsets. If you say Y, you will be asked
for your specific chipset/driver in the following questions.
printk(KERN_ERR "Sgiseeq: Cannot register net device, "
"aborting.\n");
err = -ENODEV;
- goto err_out_free_page;
+ goto err_out_free_attrs;
}
printk(KERN_INFO "%s: %s %pM\n", dev->name, sgiseeqstr, dev->dev_addr);
return 0;
-err_out_free_page:
- free_page((unsigned long) sp->srings);
+err_out_free_attrs:
+ dma_free_attrs(&pdev->dev, sizeof(*sp->srings), sp->srings,
+ sp->srings_dma, DMA_ATTR_NON_CONSISTENT);
err_out_free_dev:
free_netdev(dev);
/* Found an external PHY */
break;
}
+ /* Else, fall through */
default:
/* Internal media only */
SMC_GET_PHY_ID1(lp, 1, id1);
int ret;
struct device *dev = &bsp_priv->pdev->dev;
- if (!ldo) {
- dev_err(dev, "no regulator found\n");
- return -1;
- }
+ if (!ldo)
+ return 0;
if (enable) {
ret = regulator_enable(ldo);
u32 value;
base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
+ if (queue >= 4)
+ queue -= 4;
value = readl(ioaddr + base_register);
u32 value;
base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1;
+ if (queue >= 4)
+ queue -= 4;
value = readl(ioaddr + base_register);
#define XGMAC_CORE_INIT_RX 0
#define XGMAC_PACKET_FILTER 0x00000008
#define XGMAC_FILTER_RA BIT(31)
+#define XGMAC_FILTER_HPF BIT(10)
#define XGMAC_FILTER_PCF BIT(7)
#define XGMAC_FILTER_PM BIT(4)
#define XGMAC_FILTER_HMC BIT(2)
#define XGMAC_FILTER_PR BIT(0)
#define XGMAC_HASH_TABLE(x) (0x00000010 + (x) * 4)
+#define XGMAC_MAX_HASH_TABLE 8
#define XGMAC_RXQ_CTRL0 0x000000a0
#define XGMAC_RXQEN(x) GENMASK((x) * 2 + 1, (x) * 2)
#define XGMAC_RXQEN_SHIFT(x) ((x) * 2)
#define XGMAC_MDIO_ADDR 0x00000200
#define XGMAC_MDIO_DATA 0x00000204
#define XGMAC_MDIO_C22P 0x00000220
-#define XGMAC_ADDR0_HIGH 0x00000300
+#define XGMAC_ADDRx_HIGH(x) (0x00000300 + (x) * 0x8)
+#define XGMAC_ADDR_MAX 32
#define XGMAC_AE BIT(31)
#define XGMAC_DCS GENMASK(19, 16)
#define XGMAC_DCS_SHIFT 16
-#define XGMAC_ADDR0_LOW 0x00000304
+#define XGMAC_ADDRx_LOW(x) (0x00000304 + (x) * 0x8)
#define XGMAC_ARP_ADDR 0x00000c10
#define XGMAC_TIMESTAMP_STATUS 0x00000d20
#define XGMAC_TXTSC BIT(15)
* stmmac XGMAC support.
*/
+#include <linux/bitrev.h>
+#include <linux/crc32.h>
#include "stmmac.h"
#include "dwxgmac2.h"
u32 value, reg;
reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3;
+ if (queue >= 4)
+ queue -= 4;
value = readl(ioaddr + reg);
value &= ~XGMAC_PSRQ(queue);
u32 value, reg;
reg = (queue < 4) ? XGMAC_MTL_RXQ_DMA_MAP0 : XGMAC_MTL_RXQ_DMA_MAP1;
+ if (queue >= 4)
+ queue -= 4;
value = readl(ioaddr + reg);
value &= ~XGMAC_QxMDMACH(queue);
u32 value;
value = (addr[5] << 8) | addr[4];
- writel(value | XGMAC_AE, ioaddr + XGMAC_ADDR0_HIGH);
+ writel(value | XGMAC_AE, ioaddr + XGMAC_ADDRx_HIGH(reg_n));
value = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
- writel(value, ioaddr + XGMAC_ADDR0_LOW);
+ writel(value, ioaddr + XGMAC_ADDRx_LOW(reg_n));
}
static void dwxgmac2_get_umac_addr(struct mac_device_info *hw,
u32 hi_addr, lo_addr;
/* Read the MAC address from the hardware */
- hi_addr = readl(ioaddr + XGMAC_ADDR0_HIGH);
- lo_addr = readl(ioaddr + XGMAC_ADDR0_LOW);
+ hi_addr = readl(ioaddr + XGMAC_ADDRx_HIGH(reg_n));
+ lo_addr = readl(ioaddr + XGMAC_ADDRx_LOW(reg_n));
/* Extract the MAC address from the high and low words */
addr[0] = lo_addr & 0xff;
addr[5] = (hi_addr >> 8) & 0xff;
}
+static void dwxgmac2_set_mchash(void __iomem *ioaddr, u32 *mcfilterbits,
+ int mcbitslog2)
+{
+ int numhashregs, regs;
+
+ switch (mcbitslog2) {
+ case 6:
+ numhashregs = 2;
+ break;
+ case 7:
+ numhashregs = 4;
+ break;
+ case 8:
+ numhashregs = 8;
+ break;
+ default:
+ return;
+ }
+
+ for (regs = 0; regs < numhashregs; regs++)
+ writel(mcfilterbits[regs], ioaddr + XGMAC_HASH_TABLE(regs));
+}
+
static void dwxgmac2_set_filter(struct mac_device_info *hw,
struct net_device *dev)
{
void __iomem *ioaddr = (void __iomem *)dev->base_addr;
- u32 value = XGMAC_FILTER_RA;
+ u32 value = readl(ioaddr + XGMAC_PACKET_FILTER);
+ int mcbitslog2 = hw->mcast_bits_log2;
+ u32 mc_filter[8];
+ int i;
+
+ value &= ~(XGMAC_FILTER_PR | XGMAC_FILTER_HMC | XGMAC_FILTER_PM);
+ value |= XGMAC_FILTER_HPF;
+
+ memset(mc_filter, 0, sizeof(mc_filter));
if (dev->flags & IFF_PROMISC) {
- value |= XGMAC_FILTER_PR | XGMAC_FILTER_PCF;
+ value |= XGMAC_FILTER_PR;
+ value |= XGMAC_FILTER_PCF;
} else if ((dev->flags & IFF_ALLMULTI) ||
- (netdev_mc_count(dev) > HASH_TABLE_SIZE)) {
+ (netdev_mc_count(dev) > hw->multicast_filter_bins)) {
value |= XGMAC_FILTER_PM;
- writel(~0x0, ioaddr + XGMAC_HASH_TABLE(0));
- writel(~0x0, ioaddr + XGMAC_HASH_TABLE(1));
+
+ for (i = 0; i < XGMAC_MAX_HASH_TABLE; i++)
+ writel(~0x0, ioaddr + XGMAC_HASH_TABLE(i));
+ } else if (!netdev_mc_empty(dev)) {
+ struct netdev_hw_addr *ha;
+
+ value |= XGMAC_FILTER_HMC;
+
+ netdev_for_each_mc_addr(ha, dev) {
+ int nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >>
+ (32 - mcbitslog2));
+ mc_filter[nr >> 5] |= (1 << (nr & 0x1F));
+ }
+ }
+
+ dwxgmac2_set_mchash(ioaddr, mc_filter, mcbitslog2);
+
+ /* Handle multiple unicast addresses */
+ if (netdev_uc_count(dev) > XGMAC_ADDR_MAX) {
+ value |= XGMAC_FILTER_PR;
+ } else {
+ struct netdev_hw_addr *ha;
+ int reg = 1;
+
+ netdev_for_each_uc_addr(ha, dev) {
+ dwxgmac2_set_umac_addr(hw, ha->addr, reg);
+ reg++;
+ }
+
+ for ( ; reg < XGMAC_ADDR_MAX; reg++) {
+ writel(0, ioaddr + XGMAC_ADDRx_HIGH(reg));
+ writel(0, ioaddr + XGMAC_ADDRx_LOW(reg));
+ }
}
writel(value, ioaddr + XGMAC_PACKET_FILTER);
phylink_set(mac_supported, 10baseT_Full);
phylink_set(mac_supported, 100baseT_Half);
phylink_set(mac_supported, 100baseT_Full);
+ phylink_set(mac_supported, 1000baseT_Half);
+ phylink_set(mac_supported, 1000baseT_Full);
+ phylink_set(mac_supported, 1000baseKX_Full);
phylink_set(mac_supported, Autoneg);
phylink_set(mac_supported, Pause);
phylink_set(mac_supported, Asym_Pause);
phylink_set_port_modes(mac_supported);
- if (priv->plat->has_gmac ||
- priv->plat->has_gmac4 ||
- priv->plat->has_xgmac) {
- phylink_set(mac_supported, 1000baseT_Half);
- phylink_set(mac_supported, 1000baseT_Full);
- phylink_set(mac_supported, 1000baseKX_Full);
- }
-
/* Cut down 1G if asked to */
if ((max_speed > 0) && (max_speed < 1000)) {
phylink_set(mask, 1000baseT_Full);
"(%s) dma_rx_phy=0x%08x\n", __func__,
(u32)rx_q->dma_rx_phy);
+ stmmac_clear_rx_descriptors(priv, queue);
+
for (i = 0; i < DMA_RX_SIZE; i++) {
struct dma_desc *p;
rx_q->cur_rx = 0;
rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
- stmmac_clear_rx_descriptors(priv, queue);
-
/* Setup the chained descriptor addresses */
if (priv->mode == STMMAC_CHAIN_MODE) {
if (priv->extend_desc)
goto err_dma;
}
- rx_q->buf_pool = kmalloc_array(DMA_RX_SIZE,
- sizeof(*rx_q->buf_pool),
- GFP_KERNEL);
+ rx_q->buf_pool = kcalloc(DMA_RX_SIZE, sizeof(*rx_q->buf_pool),
+ GFP_KERNEL);
if (!rx_q->buf_pool)
goto err_dma;
tx_q->queue_index = queue;
tx_q->priv_data = priv;
- tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
- sizeof(*tx_q->tx_skbuff_dma),
- GFP_KERNEL);
+ tx_q->tx_skbuff_dma = kcalloc(DMA_TX_SIZE,
+ sizeof(*tx_q->tx_skbuff_dma),
+ GFP_KERNEL);
if (!tx_q->tx_skbuff_dma)
goto err_dma;
- tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE,
- sizeof(struct sk_buff *),
- GFP_KERNEL);
+ tx_q->tx_skbuff = kcalloc(DMA_TX_SIZE,
+ sizeof(struct sk_buff *),
+ GFP_KERNEL);
if (!tx_q->tx_skbuff)
goto err_dma;
static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
{
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
- int dirty = stmmac_rx_dirty(priv, queue);
+ int len, dirty = stmmac_rx_dirty(priv, queue);
unsigned int entry = rx_q->dirty_rx;
+ len = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
+
while (dirty-- > 0) {
struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
struct dma_desc *p;
}
buf->addr = page_pool_get_dma_addr(buf->page);
+
+ /* Sync whole allocation to device. This will invalidate old
+ * data.
+ */
+ dma_sync_single_for_device(priv->device, buf->addr, len,
+ DMA_FROM_DEVICE);
+
stmmac_set_desc_addr(priv, p, buf->addr);
stmmac_refill_desc3(priv, rx_q, p);
skb_copy_to_linear_data(skb, page_address(buf->page),
frame_len);
skb_put(skb, frame_len);
- dma_sync_single_for_device(priv->device, buf->addr,
- frame_len, DMA_FROM_DEVICE);
if (netif_msg_pktdata(priv)) {
netdev_dbg(priv->dev, "frame received (%dbytes)",
NAPI_POLL_WEIGHT);
}
if (queue < priv->plat->tx_queues_to_use) {
- netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx,
- NAPI_POLL_WEIGHT);
+ netif_tx_napi_add(ndev, &ch->tx_napi,
+ stmmac_napi_poll_tx,
+ NAPI_POLL_WEIGHT);
}
}
return ERR_PTR(-ENOMEM);
*mac = of_get_mac_address(np);
+ if (IS_ERR(*mac)) {
+ if (PTR_ERR(*mac) == -EPROBE_DEFER)
+ return ERR_CAST(*mac);
+
+ *mac = NULL;
+ }
+
plat->interface = of_get_phy_mode(np);
/* Some wrapper drivers still rely on phy_node. Let's save it while
entry = &priv->tc_entries[i];
if (!entry->in_use && !first && free)
first = entry;
- if (entry->handle == loc && !free)
+ if ((entry->handle == loc) && !free && !entry->is_frag)
dup = entry;
}
struct stmmac_tc_entry *entry, *frag = NULL;
struct tc_u32_sel *sel = cls->knode.sel;
u32 off, data, mask, real_off, rem;
- u32 prio = cls->common.prio;
+ u32 prio = cls->common.prio << 16;
int ret;
/* Only 1 match per entry */
if (!cpsw)
return -ENOMEM;
+ platform_set_drvdata(pdev, cpsw);
cpsw->dev = dev;
mode = devm_gpiod_get_array_optional(dev, "mode", GPIOD_OUT_LOW);
goto clean_cpts;
}
- platform_set_drvdata(pdev, cpsw);
priv = netdev_priv(ndev);
priv->cpsw = cpsw;
priv->ndev = ndev;
/* fallthrough, if we release the descriptors
* brutally (then we don't care about
* SPIDER_NET_DESCR_CARDOWNED) */
+ /* Fall through */
case SPIDER_NET_DESCR_RESPONSE_ERROR:
case SPIDER_NET_DESCR_PROTECTION_ERROR:
pci_unmap_single(lp->pci_dev,
lp->rx_skbs[cur_bd].skb_dma,
RX_BUF_SIZE, PCI_DMA_FROMDEVICE);
- if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
+ if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN != 0)
memmove(skb->data, skb->data - NET_IP_ALIGN,
pkt_len);
data = skb_put(skb, pkt_len);
static void tsi108_stat_carry(struct net_device *dev)
{
struct tsi108_prv_data *data = netdev_priv(dev);
+ unsigned long flags;
u32 carry1, carry2;
- spin_lock_irq(&data->misclock);
+ spin_lock_irqsave(&data->misclock, flags);
carry1 = TSI_READ(TSI108_STAT_CARRY1);
carry2 = TSI_READ(TSI108_STAT_CARRY2);
TSI108_STAT_TXPAUSEDROP_CARRY,
&data->tx_pause_drop);
- spin_unlock_irq(&data->misclock);
+ spin_unlock_irqrestore(&data->misclock, flags);
}
/* Read a stat counter atomically with respect to carries.
Note that the answer to this question does not directly affect the
kernel: saying N will just cause the configurator to skip all
- the questions about XSacle IXP devices. If you say Y, you will be
+ the questions about XScale IXP devices. If you say Y, you will be
asked for your specific card in the following questions.
if NET_VENDOR_XSCALE
}
break;
}
+ /* fall through */
- default: /* fall through */
+ default:
if (bc->hdlctx.calibrate <= 0)
return 0;
i = min_t(int, cnt, bc->hdlctx.calibrate);
if (unlikely(!skb)) {
++net_device_ctx->eth_stats.rx_no_memory;
- rcu_read_unlock();
return NVSP_STAT_FAIL;
}
struct rtnl_link_stats64 *t)
{
struct net_device_context *ndev_ctx = netdev_priv(net);
- struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
+ struct netvsc_device *nvdev;
struct netvsc_vf_pcpu_stats vf_tot;
int i;
+ rcu_read_lock();
+
+ nvdev = rcu_dereference(ndev_ctx->nvdev);
if (!nvdev)
- return;
+ goto out;
netdev_stats_to_stats64(t, &net->stats);
t->rx_packets += packets;
t->multicast += multicast;
}
+out:
+ rcu_read_unlock();
}
static int netvsc_set_mac_addr(struct net_device *ndev, void *p)
err = hwsim_subscribe_all_others(phy);
if (err < 0) {
mutex_unlock(&hwsim_phys_lock);
- goto err_reg;
+ goto err_subscribe;
}
}
list_add_tail(&phy->list, &hwsim_phys);
return idx;
+err_subscribe:
+ ieee802154_unregister_hw(phy->hw);
err_reg:
kfree(pib);
err_pib:
return 0;
platform_drv:
- genl_unregister_family(&hwsim_genl_family);
-platform_dev:
platform_device_unregister(mac802154hwsim_dev);
+platform_dev:
+ genl_unregister_family(&hwsim_genl_family);
return rc;
}
debugfs_remove_recursive(nsim_dev_port->ddir);
}
+static struct net *nsim_devlink_net(struct devlink *devlink)
+{
+ return &init_net;
+}
+
static u64 nsim_dev_ipv4_fib_resource_occ_get(void *priv)
{
- struct nsim_dev *nsim_dev = priv;
+ struct net *net = priv;
- return nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV4_FIB, false);
+ return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, false);
}
static u64 nsim_dev_ipv4_fib_rules_res_occ_get(void *priv)
{
- struct nsim_dev *nsim_dev = priv;
+ struct net *net = priv;
- return nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV4_FIB_RULES, false);
+ return nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, false);
}
static u64 nsim_dev_ipv6_fib_resource_occ_get(void *priv)
{
- struct nsim_dev *nsim_dev = priv;
+ struct net *net = priv;
- return nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV6_FIB, false);
+ return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, false);
}
static u64 nsim_dev_ipv6_fib_rules_res_occ_get(void *priv)
{
- struct nsim_dev *nsim_dev = priv;
+ struct net *net = priv;
- return nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV6_FIB_RULES, false);
+ return nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, false);
}
static int nsim_dev_resources_register(struct devlink *devlink)
{
- struct nsim_dev *nsim_dev = devlink_priv(devlink);
struct devlink_resource_size_params params = {
.size_max = (u64)-1,
.size_granularity = 1,
.unit = DEVLINK_RESOURCE_UNIT_ENTRY
};
+ struct net *net = nsim_devlink_net(devlink);
int err;
u64 n;
goto out;
}
- n = nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV4_FIB, true);
+ n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB, true);
err = devlink_resource_register(devlink, "fib", n,
NSIM_RESOURCE_IPV4_FIB,
NSIM_RESOURCE_IPV4, ¶ms);
return err;
}
- n = nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV4_FIB_RULES, true);
+ n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV4_FIB_RULES, true);
err = devlink_resource_register(devlink, "fib-rules", n,
NSIM_RESOURCE_IPV4_FIB_RULES,
NSIM_RESOURCE_IPV4, ¶ms);
goto out;
}
- n = nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV6_FIB, true);
+ n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB, true);
err = devlink_resource_register(devlink, "fib", n,
NSIM_RESOURCE_IPV6_FIB,
NSIM_RESOURCE_IPV6, ¶ms);
return err;
}
- n = nsim_fib_get_val(nsim_dev->fib_data,
- NSIM_RESOURCE_IPV6_FIB_RULES, true);
+ n = nsim_fib_get_val(net, NSIM_RESOURCE_IPV6_FIB_RULES, true);
err = devlink_resource_register(devlink, "fib-rules", n,
NSIM_RESOURCE_IPV6_FIB_RULES,
NSIM_RESOURCE_IPV6, ¶ms);
devlink_resource_occ_get_register(devlink,
NSIM_RESOURCE_IPV4_FIB,
nsim_dev_ipv4_fib_resource_occ_get,
- nsim_dev);
+ net);
devlink_resource_occ_get_register(devlink,
NSIM_RESOURCE_IPV4_FIB_RULES,
nsim_dev_ipv4_fib_rules_res_occ_get,
- nsim_dev);
+ net);
devlink_resource_occ_get_register(devlink,
NSIM_RESOURCE_IPV6_FIB,
nsim_dev_ipv6_fib_resource_occ_get,
- nsim_dev);
+ net);
devlink_resource_occ_get_register(devlink,
NSIM_RESOURCE_IPV6_FIB_RULES,
nsim_dev_ipv6_fib_rules_res_occ_get,
- nsim_dev);
+ net);
out:
return err;
}
static int nsim_dev_reload(struct devlink *devlink,
struct netlink_ext_ack *extack)
{
- struct nsim_dev *nsim_dev = devlink_priv(devlink);
enum nsim_resource_id res_ids[] = {
NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES,
NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES
};
+ struct net *net = nsim_devlink_net(devlink);
int i;
for (i = 0; i < ARRAY_SIZE(res_ids); ++i) {
err = devlink_resource_size_get(devlink, res_ids[i], &val);
if (!err) {
- err = nsim_fib_set_max(nsim_dev->fib_data,
- res_ids[i], val, extack);
+ err = nsim_fib_set_max(net, res_ids[i], val, extack);
if (err)
return err;
}
mutex_init(&nsim_dev->port_list_lock);
nsim_dev->fw_update_status = true;
- nsim_dev->fib_data = nsim_fib_create();
- if (IS_ERR(nsim_dev->fib_data)) {
- err = PTR_ERR(nsim_dev->fib_data);
- goto err_devlink_free;
- }
-
err = nsim_dev_resources_register(devlink);
if (err)
- goto err_fib_destroy;
+ goto err_devlink_free;
err = devlink_register(devlink, &nsim_bus_dev->dev);
if (err)
devlink_unregister(devlink);
err_resources_unregister:
devlink_resources_unregister(devlink, NULL);
-err_fib_destroy:
- nsim_fib_destroy(nsim_dev->fib_data);
err_devlink_free:
devlink_free(devlink);
return ERR_PTR(err);
nsim_dev_debugfs_exit(nsim_dev);
devlink_unregister(devlink);
devlink_resources_unregister(devlink, NULL);
- nsim_fib_destroy(nsim_dev->fib_data);
mutex_destroy(&nsim_dev->port_list_lock);
devlink_free(devlink);
}
#include <net/ip_fib.h>
#include <net/ip6_fib.h>
#include <net/fib_rules.h>
+#include <net/netns/generic.h>
#include "netdevsim.h"
};
struct nsim_fib_data {
- struct notifier_block fib_nb;
struct nsim_per_fib_data ipv4;
struct nsim_per_fib_data ipv6;
};
-u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
- enum nsim_resource_id res_id, bool max)
+static unsigned int nsim_fib_net_id;
+
+u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max)
{
+ struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id);
struct nsim_fib_entry *entry;
switch (res_id) {
return max ? entry->max : entry->num;
}
-int nsim_fib_set_max(struct nsim_fib_data *fib_data,
- enum nsim_resource_id res_id, u64 val,
+int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
struct netlink_ext_ack *extack)
{
+ struct nsim_fib_data *fib_data = net_generic(net, nsim_fib_net_id);
struct nsim_fib_entry *entry;
int err = 0;
return err;
}
-static int nsim_fib_rule_event(struct nsim_fib_data *data,
- struct fib_notifier_info *info, bool add)
+static int nsim_fib_rule_event(struct fib_notifier_info *info, bool add)
{
+ struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id);
struct netlink_ext_ack *extack = info->extack;
int err = 0;
return err;
}
-static int nsim_fib_event(struct nsim_fib_data *data,
- struct fib_notifier_info *info, bool add)
+static int nsim_fib_event(struct fib_notifier_info *info, bool add)
{
+ struct nsim_fib_data *data = net_generic(info->net, nsim_fib_net_id);
struct netlink_ext_ack *extack = info->extack;
int err = 0;
static int nsim_fib_event_nb(struct notifier_block *nb, unsigned long event,
void *ptr)
{
- struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
- fib_nb);
struct fib_notifier_info *info = ptr;
int err = 0;
switch (event) {
case FIB_EVENT_RULE_ADD: /* fall through */
case FIB_EVENT_RULE_DEL:
- err = nsim_fib_rule_event(data, info,
- event == FIB_EVENT_RULE_ADD);
+ err = nsim_fib_rule_event(info, event == FIB_EVENT_RULE_ADD);
break;
case FIB_EVENT_ENTRY_ADD: /* fall through */
case FIB_EVENT_ENTRY_DEL:
- err = nsim_fib_event(data, info,
- event == FIB_EVENT_ENTRY_ADD);
+ err = nsim_fib_event(info, event == FIB_EVENT_ENTRY_ADD);
break;
}
/* inconsistent dump, trying again */
static void nsim_fib_dump_inconsistent(struct notifier_block *nb)
{
- struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data,
- fib_nb);
+ struct nsim_fib_data *data;
+ struct net *net;
+
+ rcu_read_lock();
+ for_each_net_rcu(net) {
+ data = net_generic(net, nsim_fib_net_id);
+
+ data->ipv4.fib.num = 0ULL;
+ data->ipv4.rules.num = 0ULL;
- data->ipv4.fib.num = 0ULL;
- data->ipv4.rules.num = 0ULL;
- data->ipv6.fib.num = 0ULL;
- data->ipv6.rules.num = 0ULL;
+ data->ipv6.fib.num = 0ULL;
+ data->ipv6.rules.num = 0ULL;
+ }
+ rcu_read_unlock();
}
-struct nsim_fib_data *nsim_fib_create(void)
-{
- struct nsim_fib_data *data;
- int err;
+static struct notifier_block nsim_fib_nb = {
+ .notifier_call = nsim_fib_event_nb,
+};
- data = kzalloc(sizeof(*data), GFP_KERNEL);
- if (!data)
- return ERR_PTR(-ENOMEM);
+/* Initialize per network namespace state */
+static int __net_init nsim_fib_netns_init(struct net *net)
+{
+ struct nsim_fib_data *data = net_generic(net, nsim_fib_net_id);
data->ipv4.fib.max = (u64)-1;
data->ipv4.rules.max = (u64)-1;
data->ipv6.fib.max = (u64)-1;
data->ipv6.rules.max = (u64)-1;
- data->fib_nb.notifier_call = nsim_fib_event_nb;
- err = register_fib_notifier(&data->fib_nb, nsim_fib_dump_inconsistent);
- if (err) {
- pr_err("Failed to register fib notifier\n");
- goto err_out;
- }
+ return 0;
+}
- return data;
+static struct pernet_operations nsim_fib_net_ops = {
+ .init = nsim_fib_netns_init,
+ .id = &nsim_fib_net_id,
+ .size = sizeof(struct nsim_fib_data),
+};
-err_out:
- kfree(data);
- return ERR_PTR(err);
+void nsim_fib_exit(void)
+{
+ unregister_pernet_subsys(&nsim_fib_net_ops);
+ unregister_fib_notifier(&nsim_fib_nb);
}
-void nsim_fib_destroy(struct nsim_fib_data *data)
+int nsim_fib_init(void)
{
- unregister_fib_notifier(&data->fib_nb);
- kfree(data);
+ int err;
+
+ err = register_pernet_subsys(&nsim_fib_net_ops);
+ if (err < 0) {
+ pr_err("Failed to register pernet subsystem\n");
+ goto err_out;
+ }
+
+ err = register_fib_notifier(&nsim_fib_nb, nsim_fib_dump_inconsistent);
+ if (err < 0) {
+ pr_err("Failed to register fib notifier\n");
+ goto err_out;
+ }
+
+err_out:
+ return err;
}
if (err)
goto err_dev_exit;
- err = rtnl_link_register(&nsim_link_ops);
+ err = nsim_fib_init();
if (err)
goto err_bus_exit;
+ err = rtnl_link_register(&nsim_link_ops);
+ if (err)
+ goto err_fib_exit;
+
return 0;
+err_fib_exit:
+ nsim_fib_exit();
err_bus_exit:
nsim_bus_exit();
err_dev_exit:
static void __exit nsim_module_exit(void)
{
rtnl_link_unregister(&nsim_link_ops);
+ nsim_fib_exit();
nsim_bus_exit();
nsim_dev_exit();
}
int nsim_dev_port_del(struct nsim_bus_dev *nsim_bus_dev,
unsigned int port_index);
-struct nsim_fib_data *nsim_fib_create(void);
-void nsim_fib_destroy(struct nsim_fib_data *fib_data);
-u64 nsim_fib_get_val(struct nsim_fib_data *fib_data,
- enum nsim_resource_id res_id, bool max);
-int nsim_fib_set_max(struct nsim_fib_data *fib_data,
- enum nsim_resource_id res_id, u64 val,
+int nsim_fib_init(void);
+void nsim_fib_exit(void);
+u64 nsim_fib_get_val(struct net *net, enum nsim_resource_id res_id, bool max);
+int nsim_fib_set_max(struct net *net, enum nsim_resource_id res_id, u64 val,
struct netlink_ext_ack *extack);
#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
* after HW reset: RX delay enabled and TX delay disabled
* after SW reset: RX delay enabled, while TX delay retains the
* value before reset.
- *
- * So let's first disable the RX and TX delays in PHY and enable
- * them based on the mode selected (this also takes care of RGMII
- * mode where we expect delays to be disabled)
*/
-
- ret = at803x_disable_rx_delay(phydev);
- if (ret < 0)
- return ret;
- ret = at803x_disable_tx_delay(phydev);
- if (ret < 0)
- return ret;
-
if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
- phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
- /* If RGMII_ID or RGMII_RXID are specified enable RX delay,
- * otherwise keep it disabled
- */
+ phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
ret = at803x_enable_rx_delay(phydev);
- if (ret < 0)
- return ret;
- }
+ else
+ ret = at803x_disable_rx_delay(phydev);
+ if (ret < 0)
+ return ret;
if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
- phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
- /* If RGMII_ID or RGMII_TXID are specified enable TX delay,
- * otherwise keep it disabled
- */
+ phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
ret = at803x_enable_tx_delay(phydev);
- }
+ else
+ ret = at803x_disable_tx_delay(phydev);
return ret;
}
if (IS_ERR(gpiod)) {
if (PTR_ERR(gpiod) == -EPROBE_DEFER)
return gpiod;
- pr_err("error getting GPIO for fixed link %pOF, proceed without\n",
- fixed_link_node);
+
+ if (PTR_ERR(gpiod) != -ENOENT)
+ pr_err("error getting GPIO for fixed link %pOF, proceed without\n",
+ fixed_link_node);
gpiod = NULL;
}
vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES;
vsc8531->hw_stats = vsc85xx_hw_stats;
vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats);
- vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
- sizeof(u64), GFP_KERNEL);
+ vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+ sizeof(u64), GFP_KERNEL);
if (!vsc8531->stats)
return -ENOMEM;
vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES;
vsc8531->hw_stats = vsc8584_hw_stats;
vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats);
- vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
- sizeof(u64), GFP_KERNEL);
+ vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+ sizeof(u64), GFP_KERNEL);
if (!vsc8531->stats)
return -ENOMEM;
vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES;
vsc8531->hw_stats = vsc8584_hw_stats;
vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats);
- vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
- sizeof(u64), GFP_KERNEL);
+ vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+ sizeof(u64), GFP_KERNEL);
if (!vsc8531->stats)
return -ENOMEM;
vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES;
vsc8531->hw_stats = vsc85xx_hw_stats;
vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats);
- vsc8531->stats = devm_kmalloc_array(&phydev->mdio.dev, vsc8531->nstats,
- sizeof(u64), GFP_KERNEL);
+ vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats,
+ sizeof(u64), GFP_KERNEL);
if (!vsc8531->stats)
return -ENOMEM;
int val, devad;
bool link = true;
+ if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) {
+ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1);
+ if (val < 0)
+ return val;
+
+ /* Autoneg is being started, therefore disregard current
+ * link status and report link as down.
+ */
+ if (val & MDIO_AN_CTRL1_RESTART) {
+ phydev->link = 0;
+ return 0;
+ }
+ }
+
while (mmd_mask && link) {
devad = __ffs(mmd_mask);
mmd_mask &= ~BIT(devad);
}
EXPORT_SYMBOL_GPL(genphy_c45_read_status);
+/**
+ * genphy_c45_config_aneg - restart auto-negotiation or forced setup
+ * @phydev: target phy_device struct
+ *
+ * Description: If auto-negotiation is enabled, we configure the
+ * advertising, and then restart auto-negotiation. If it is not
+ * enabled, then we force a configuration.
+ */
+int genphy_c45_config_aneg(struct phy_device *phydev)
+{
+ bool changed = false;
+ int ret;
+
+ if (phydev->autoneg == AUTONEG_DISABLE)
+ return genphy_c45_pma_setup_forced(phydev);
+
+ ret = genphy_c45_an_config_aneg(phydev);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ changed = true;
+
+ return genphy_c45_check_and_restart_aneg(phydev, changed);
+}
+EXPORT_SYMBOL_GPL(genphy_c45_config_aneg);
+
/* The gen10g_* functions are the old Clause 45 stub */
int gen10g_config_aneg(struct phy_device *phydev)
* allowed to call genphy_config_aneg()
*/
if (phydev->is_c45 && !(phydev->c45_ids.devices_in_package & BIT(0)))
- return -EOPNOTSUPP;
+ return genphy_c45_config_aneg(phydev);
return genphy_config_aneg(phydev);
}
*/
int genphy_update_link(struct phy_device *phydev)
{
- int status;
+ int status = 0, bmcr;
+
+ bmcr = phy_read(phydev, MII_BMCR);
+ if (bmcr < 0)
+ return bmcr;
+
+ /* Autoneg is being started, therefore disregard BMSR value and
+ * report link as down.
+ */
+ if (bmcr & BMCR_ANRESTART)
+ goto done;
/* The link state is latched low so that momentary link
* drops can be detected. Do not double-read the status
phydev->link = status & BMSR_LSTATUS ? 1 : 0;
phydev->autoneg_complete = status & BMSR_ANEGCOMPLETE ? 1 : 0;
+ /* Consider the case that autoneg was started and "aneg complete"
+ * bit has been reset, but "link up" bit not yet.
+ */
+ if (phydev->autoneg == AUTONEG_ENABLE && !phydev->autoneg_complete)
+ phydev->link = 0;
+
return 0;
}
EXPORT_SYMBOL(genphy_update_link);
if (!phy->last_triggered)
led_trigger_event(&phy->led_link_trigger->trigger,
LED_FULL);
+ else
+ led_trigger_event(&phy->last_triggered->trigger, LED_OFF);
- led_trigger_event(&phy->last_triggered->trigger, LED_OFF);
led_trigger_event(&plt->trigger, LED_FULL);
phy->last_triggered = plt;
}
pl->supported, true);
linkmode_zero(pl->supported);
phylink_set(pl->supported, MII);
+ phylink_set(pl->supported, Pause);
+ phylink_set(pl->supported, Asym_Pause);
if (s) {
__set_bit(s->bit, pl->supported);
} else {
}
if (pl->link_an_mode == MLO_AN_FIXED && pl->get_fixed_state)
mod_timer(&pl->link_poll, jiffies + HZ);
- if (pl->sfp_bus)
- sfp_upstream_start(pl->sfp_bus);
if (pl->phydev)
phy_start(pl->phydev);
+ if (pl->sfp_bus)
+ sfp_upstream_start(pl->sfp_bus);
}
EXPORT_SYMBOL_GPL(phylink_start);
{
ASSERT_RTNL();
- if (pl->phydev)
- phy_stop(pl->phydev);
if (pl->sfp_bus)
sfp_upstream_stop(pl->sfp_bus);
+ if (pl->phydev)
+ phy_stop(pl->phydev);
del_timer_sync(&pl->link_poll);
if (pl->link_irq) {
free_irq(pl->link_irq, pl);
static void sfp_hwmon_to_rx_power(long *value)
{
- *value = DIV_ROUND_CLOSEST(*value, 100);
+ *value = DIV_ROUND_CLOSEST(*value, 10);
}
static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset,
.recvmsg = pppoe_recvmsg,
.mmap = sock_no_mmap,
.ioctl = pppox_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = pppox_compat_ioctl,
+#endif
};
static const struct pppox_proto pppoe_proto = {
#include <linux/string.h>
#include <linux/module.h>
#include <linux/kernel.h>
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/net.h>
EXPORT_SYMBOL(pppox_ioctl);
+#ifdef CONFIG_COMPAT
+int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+ if (cmd == PPPOEIOCSFWD32)
+ cmd = PPPOEIOCSFWD;
+
+ return pppox_ioctl(sock, cmd, (unsigned long)compat_ptr(arg));
+}
+
+EXPORT_SYMBOL(pppox_compat_ioctl);
+#endif
+
static int pppox_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
.recvmsg = sock_no_recvmsg,
.mmap = sock_no_mmap,
.ioctl = pppox_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = pppox_compat_ioctl,
+#endif
};
static const struct pppox_proto pppox_pptp_proto = {
team->dev->vlan_features = vlan_features;
team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL |
+ NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX |
NETIF_F_GSO_UDP_L4;
team->dev->hard_header_len = max_hard_header_len;
return true;
}
-static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf,
+static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
+ struct page_frag *alloc_frag, char *buf,
int buflen, int len, int pad)
{
struct sk_buff *skb = build_skb(buf, buflen);
skb_reserve(skb, pad);
skb_put(skb, len);
+ skb_set_owner_w(skb, tfile->socket.sk);
get_page(alloc_frag->page);
alloc_frag->offset += buflen;
*/
if (hdr->gso_type || !xdp_prog) {
*skb_xdp = 1;
- return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+ return __tun_build_skb(tfile, alloc_frag, buf, buflen, len,
+ pad);
}
*skb_xdp = 0;
rcu_read_unlock();
local_bh_enable();
- return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+ return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
err_xdp:
put_page(alloc_frag->page);
}
if (!timeout) {
dev_err(&udev->dev, "firmware not ready in time\n");
- return -ETIMEDOUT;
+ ret = -ETIMEDOUT;
+ goto err;
}
/* enable ethernet mode (?) */
status = kalmia_send_init_packet(dev, usb_buf, ARRAY_SIZE(init_msg_1),
usb_buf, 24);
if (status != 0)
- return status;
+ goto out;
memcpy(usb_buf, init_msg_2, 12);
status = kalmia_send_init_packet(dev, usb_buf, ARRAY_SIZE(init_msg_2),
usb_buf, 28);
if (status != 0)
- return status;
+ goto out;
memcpy(ethernet_addr, usb_buf + 10, ETH_ALEN);
-
+out:
kfree(usb_buf);
return status;
}
ret = register_netdev(netdev);
if (ret != 0) {
netif_err(dev, probe, netdev, "couldn't register the device\n");
- goto out3;
+ goto out4;
}
usb_set_intfdata(intf, dev);
ret = lan78xx_phy_init(dev);
if (ret < 0)
- goto out4;
+ goto out5;
return 0;
-out4:
+out5:
unregister_netdev(netdev);
+out4:
+ usb_free_urb(dev->urb_intr);
out3:
lan78xx_unbind(dev, intf);
out2:
static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata)
{
int i;
- __u8 tmp;
+ __u8 tmp = 0;
__le16 retdatai;
int ret;
{QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */
{QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */
{QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */
+ {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */
{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)}, /* Sierra Wireless MC7700 */
{QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */
{QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */
#define PLA_TEREDO_WAKE_BASE 0xc0c4
#define PLA_MAR 0xcd00
#define PLA_BACKUP 0xd000
-#define PAL_BDC_CR 0xd1a0
+#define PLA_BDC_CR 0xd1a0
#define PLA_TEREDO_TIMER 0xd2cc
#define PLA_REALWOW_TIMER 0xd2e8
#define PLA_SUSPEND_FLAG 0xd38a
#define TEREDO_RS_EVENT_MASK 0x00fe
#define OOB_TEREDO_EN 0x0001
-/* PAL_BDC_CR */
+/* PLA_BDC_CR */
#define ALDPS_PROXY_MODE 0x0001
/* PLA_EFUSE_CMD */
ret = usb_control_msg(tp->udev, usb_rcvctrlpipe(tp->udev, 0),
RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
value, index, tmp, size, 500);
+ if (ret < 0)
+ memset(data, 0xff, size);
+ else
+ memcpy(data, tmp, size);
- memcpy(data, tmp, size);
kfree(tmp);
return ret;
rtl_rx_vlan_en(tp, true);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PAL_BDC_CR);
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_BDC_CR);
ocp_data |= ALDPS_PROXY_MODE;
- ocp_write_word(tp, MCU_TYPE_PLA, PAL_BDC_CR, ocp_data);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_BDC_CR, ocp_data);
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB;
rtl_rx_vlan_en(tp, true);
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PAL_BDC_CR);
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_BDC_CR);
ocp_data |= ALDPS_PROXY_MODE;
- ocp_write_word(tp, MCU_TYPE_PLA, PAL_BDC_CR, ocp_data);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_BDC_CR, ocp_data);
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
ocp_data |= NOW_IS_OOB | DIS_MCU_CLROOB;
#ifdef CONFIG_PM_SLEEP
unregister_pm_notifier(&tp->pm_notifier);
#endif
- if (!test_bit(RTL8152_UNPLUG, &tp->flags))
- napi_disable(&tp->napi);
+ napi_disable(&tp->napi);
clear_bit(WORK_ENABLE, &tp->flags);
usb_kill_urb(tp->intr_urb);
cancel_delayed_work_sync(&tp->schedule);
return 0;
out1:
- netif_napi_del(&tp->napi);
usb_set_intfdata(intf, NULL);
out:
free_netdev(netdev);
if (tp) {
rtl_set_unplug(tp);
- netif_napi_del(&tp->napi);
unregister_netdev(tp->netdev);
cancel_delayed_work_sync(&tp->hw_phy_work);
tp->rtl_ops.unload(tp);
}
}
- if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) {
+ if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
if (!try_fill_recv(vi, rq, GFP_ATOMIC))
schedule_delayed_work(&vi->refill, 0);
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
- const struct ipv6hdr *iph = ipv6_hdr(skb);
+ const struct ipv6hdr *iph;
struct net *net = dev_net(skb->dev);
- struct flowi6 fl6 = {
- /* needed to match OIF rule */
- .flowi6_oif = dev->ifindex,
- .flowi6_iif = LOOPBACK_IFINDEX,
- .daddr = iph->daddr,
- .saddr = iph->saddr,
- .flowlabel = ip6_flowinfo(iph),
- .flowi6_mark = skb->mark,
- .flowi6_proto = iph->nexthdr,
- .flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
- };
+ struct flowi6 fl6;
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
+ if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
+ goto err;
+
+ iph = ipv6_hdr(skb);
+
+ memset(&fl6, 0, sizeof(fl6));
+ /* needed to match OIF rule */
+ fl6.flowi6_oif = dev->ifindex;
+ fl6.flowi6_iif = LOOPBACK_IFINDEX;
+ fl6.daddr = iph->daddr;
+ fl6.saddr = iph->saddr;
+ fl6.flowlabel = ip6_flowinfo(iph);
+ fl6.flowi6_mark = skb->mark;
+ fl6.flowi6_proto = iph->nexthdr;
+ fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
+
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
struct net_device *vrf_dev)
{
- struct iphdr *ip4h = ip_hdr(skb);
+ struct iphdr *ip4h;
int ret = NET_XMIT_DROP;
- struct flowi4 fl4 = {
- /* needed to match OIF rule */
- .flowi4_oif = vrf_dev->ifindex,
- .flowi4_iif = LOOPBACK_IFINDEX,
- .flowi4_tos = RT_TOS(ip4h->tos),
- .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
- .flowi4_proto = ip4h->protocol,
- .daddr = ip4h->daddr,
- .saddr = ip4h->saddr,
- };
+ struct flowi4 fl4;
struct net *net = dev_net(vrf_dev);
struct rtable *rt;
+ if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
+ goto err;
+
+ ip4h = ip_hdr(skb);
+
+ memset(&fl4, 0, sizeof(fl4));
+ /* needed to match OIF rule */
+ fl4.flowi4_oif = vrf_dev->ifindex;
+ fl4.flowi4_iif = LOOPBACK_IFINDEX;
+ fl4.flowi4_tos = RT_TOS(ip4h->tos);
+ fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF;
+ fl4.flowi4_proto = ip4h->protocol;
+ fl4.daddr = ip4h->daddr;
+ fl4.saddr = ip4h->saddr;
+
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto err;
case SDLA_RET_NO_BUFS:
if (cmd == SDLA_INFORMATION_WRITE)
break;
+ /* Else, fall through */
default:
netdev_dbg(dev, "Cmd 0x%02X generated return code 0x%02X\n",
}
result = i2400m_barker_db_add(barker);
if (result < 0)
- goto error_add;
+ goto error_parse_add;
}
kfree(options_orig);
}
return 0;
+error_parse_add:
error_parse:
+ kfree(options_orig);
error_add:
kfree(i2400m_barker_db);
return result;
.info.subcmd = QCA_NL80211_VENDOR_SUBCMD_DMG_RF_GET_SECTOR_CFG,
.flags = WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
+ .policy = wil_rf_sector_policy,
.doit = wil_rf_sector_get_cfg
},
{
.info.subcmd = QCA_NL80211_VENDOR_SUBCMD_DMG_RF_SET_SECTOR_CFG,
.flags = WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
+ .policy = wil_rf_sector_policy,
.doit = wil_rf_sector_set_cfg
},
{
QCA_NL80211_VENDOR_SUBCMD_DMG_RF_GET_SELECTED_SECTOR,
.flags = WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
+ .policy = wil_rf_sector_policy,
.doit = wil_rf_sector_get_selected
},
{
QCA_NL80211_VENDOR_SUBCMD_DMG_RF_SET_SELECTED_SECTOR,
.flags = WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
+ .policy = wil_rf_sector_policy,
.doit = wil_rf_sector_set_selected
},
};
},
.flags = WIPHY_VENDOR_CMD_NEED_WDEV |
WIPHY_VENDOR_CMD_NEED_NETDEV,
+ .policy = VENDOR_CMD_RAW_DATA,
.doit = brcmf_cfg80211_vndr_cmds_dcmd_handler
},
};
.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
};
+const struct iwl_cfg killer1650s_2ax_cfg_qu_c0_hr_b0 = {
+ .name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)",
+ .fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
+ IWL_DEVICE_22500,
+ /*
+ * This device doesn't support receiving BlockAck with a large bitmap
+ * so we need to restrict the size of transmitted aggregation to the
+ * HT size; mac80211 would otherwise pick the HE max (256) by default.
+ */
+ .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
+const struct iwl_cfg killer1650i_2ax_cfg_qu_c0_hr_b0 = {
+ .name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)",
+ .fw_name_pre = IWL_QU_C_HR_B_FW_PRE,
+ IWL_DEVICE_22500,
+ /*
+ * This device doesn't support receiving BlockAck with a large bitmap
+ * so we need to restrict the size of transmitted aggregation to the
+ * HT size; mac80211 would otherwise pick the HE max (256) by default.
+ */
+ .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
const struct iwl_cfg iwl22000_2ax_cfg_jf = {
.name = "Intel(R) Dual Band Wireless AX 22000",
.fw_name_pre = IWL_QU_B_JF_B_FW_PRE,
u8 indirection_table[IWL_RSS_INDIRECTION_TABLE_SIZE];
} __packed; /* RSS_CONFIG_CMD_API_S_VER_1 */
-#define IWL_MULTI_QUEUE_SYNC_MSG_MAX_SIZE 128
#define IWL_MULTI_QUEUE_SYNC_SENDER_POS 0
#define IWL_MULTI_QUEUE_SYNC_SENDER_MSK 0xf
*
* @IWL_MVM_RXQ_EMPTY: empty sync notification
* @IWL_MVM_RXQ_NOTIF_DEL_BA: notify RSS queues of delBA
+ * @IWL_MVM_RXQ_NSSN_SYNC: notify all the RSS queues with the new NSSN
*/
enum iwl_mvm_rxq_notif_type {
IWL_MVM_RXQ_EMPTY,
IWL_MVM_RXQ_NOTIF_DEL_BA,
+ IWL_MVM_RXQ_NSSN_SYNC,
};
/**
{
u32 img_name_len = le32_to_cpu(dbg_info->img_name_len);
u32 dbg_cfg_name_len = le32_to_cpu(dbg_info->dbg_cfg_name_len);
- const char err_str[] =
- "WRT: ext=%d. Invalid %s name length %d, expected %d\n";
if (img_name_len != IWL_FW_INI_MAX_IMG_NAME_LEN) {
- IWL_WARN(fwrt, err_str, ext, "image", img_name_len,
+ IWL_WARN(fwrt,
+ "WRT: ext=%d. Invalid image name length %d, expected %d\n",
+ ext, img_name_len,
IWL_FW_INI_MAX_IMG_NAME_LEN);
return;
}
if (dbg_cfg_name_len != IWL_FW_INI_MAX_DBG_CFG_NAME_LEN) {
- IWL_WARN(fwrt, err_str, ext, "debug cfg", dbg_cfg_name_len,
+ IWL_WARN(fwrt,
+ "WRT: ext=%d. Invalid debug cfg name length %d, expected %d\n",
+ ext, dbg_cfg_name_len,
IWL_FW_INI_MAX_DBG_CFG_NAME_LEN);
return;
}
struct iwl_ucode_tlv *tlv = iter;
void *ini_tlv = (void *)tlv->data;
u32 type = le32_to_cpu(tlv->type);
- const char invalid_ap_str[] =
- "WRT: ext=%d. Invalid apply point %d for %s\n";
switch (type) {
case IWL_UCODE_TLV_TYPE_DEBUG_INFO:
struct iwl_fw_ini_allocation_data *buf_alloc = ini_tlv;
if (pnt != IWL_FW_INI_APPLY_EARLY) {
- IWL_ERR(fwrt, invalid_ap_str, ext, pnt,
- "buffer allocation");
+ IWL_ERR(fwrt,
+ "WRT: ext=%d. Invalid apply point %d for buffer allocation\n",
+ ext, pnt);
goto next;
}
}
case IWL_UCODE_TLV_TYPE_HCMD:
if (pnt < IWL_FW_INI_APPLY_AFTER_ALIVE) {
- IWL_ERR(fwrt, invalid_ap_str, ext, pnt,
- "host command");
+ IWL_ERR(fwrt,
+ "WRT: ext=%d. Invalid apply point %d for host command\n",
+ ext, pnt);
goto next;
}
iwl_fw_dbg_send_hcmd(fwrt, tlv, ext);
extern const struct iwl_cfg iwl_ax1650s_cfg_quz_hr;
extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0;
extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0;
+extern const struct iwl_cfg killer1650s_2ax_cfg_qu_c0_hr_b0;
+extern const struct iwl_cfg killer1650i_2ax_cfg_qu_c0_hr_b0;
extern const struct iwl_cfg killer1650x_2ax_cfg;
extern const struct iwl_cfg killer1650w_2ax_cfg;
extern const struct iwl_cfg iwl9461_2ac_cfg_qu_b0_jf_b0;
init_completion(&drv->request_firmware_complete);
INIT_LIST_HEAD(&drv->list);
+ iwl_load_fw_dbg_tlv(drv->trans->dev, drv->trans);
+
#ifdef CONFIG_IWLWIFI_DEBUGFS
/* Create the device debugfs entries. */
drv->dbgfs_drv = debugfs_create_dir(dev_name(trans->dev),
err_fw:
#ifdef CONFIG_IWLWIFI_DEBUGFS
debugfs_remove_recursive(drv->dbgfs_drv);
- iwl_fw_dbg_free(drv->trans);
#endif
+ iwl_fw_dbg_free(drv->trans);
kfree(drv);
err:
return ERR_PTR(ret);
for (i = 0; i < n_profiles; i++) {
/* the tables start at element 3 */
- static int pos = 3;
+ int pos = 3;
/* The EWRD profiles officially go from 2 to 4, but we
* save them in sar_profiles[1-3] (because we don't
return iwl_mvm_send_cmd_pdu(mvm, REDUCE_TX_POWER_CMD, 0, len, &cmd);
}
+static bool iwl_mvm_sar_geo_support(struct iwl_mvm *mvm)
+{
+ /*
+ * The GEO_TX_POWER_LIMIT command is not supported on earlier
+ * firmware versions. Unfortunately, we don't have a TLV API
+ * flag to rely on, so rely on the major version which is in
+ * the first byte of ucode_ver. This was implemented
+ * initially on version 38 and then backported to 36, 29 and
+ * 17.
+ */
+ return IWL_UCODE_SERIAL(mvm->fw->ucode_ver) >= 38 ||
+ IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 36 ||
+ IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 29 ||
+ IWL_UCODE_SERIAL(mvm->fw->ucode_ver) == 17;
+}
+
int iwl_mvm_get_sar_geo_profile(struct iwl_mvm *mvm)
{
struct iwl_geo_tx_power_profiles_resp *resp;
.data = { data },
};
+ if (!iwl_mvm_sar_geo_support(mvm))
+ return -EOPNOTSUPP;
+
ret = iwl_mvm_send_cmd(mvm, &cmd);
if (ret) {
IWL_ERR(mvm, "Failed to get geographic profile info %d\n", ret);
int ret, i, j;
u16 cmd_wide_id = WIDE_ID(PHY_OPS_GROUP, GEO_TX_POWER_LIMIT);
- /*
- * This command is not supported on earlier firmware versions.
- * Unfortunately, we don't have a TLV API flag to rely on, so
- * rely on the major version which is in the first byte of
- * ucode_ver.
- */
- if (IWL_UCODE_SERIAL(mvm->fw->ucode_ver) < 41)
+ if (!iwl_mvm_sar_geo_support(mvm))
return 0;
ret = iwl_mvm_sar_get_wgds_table(mvm);
cpu_to_le32(vif->bss_conf.use_short_slot ?
MAC_FLG_SHORT_SLOT : 0);
- cmd->filter_flags = cpu_to_le32(MAC_FILTER_ACCEPT_GRP);
+ cmd->filter_flags = 0;
for (i = 0; i < IEEE80211_NUM_ACS; i++) {
u8 txf = iwl_mvm_mac_ac_to_tx_fifo(mvm, i);
/* We need the dtim_period to set the MAC as associated */
if (vif->bss_conf.assoc && vif->bss_conf.dtim_period &&
!force_assoc_off) {
+ struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+ u8 ap_sta_id = mvmvif->ap_sta_id;
u32 dtim_offs;
/*
dtim_offs);
ctxt_sta->is_assoc = cpu_to_le32(1);
+
+ /*
+ * allow multicast data frames only as long as the station is
+ * authorized, i.e., GTK keys are already installed (if needed)
+ */
+ if (ap_sta_id < IWL_MVM_STATION_COUNT) {
+ struct ieee80211_sta *sta;
+
+ rcu_read_lock();
+
+ sta = rcu_dereference(mvm->fw_id_to_mac_id[ap_sta_id]);
+ if (!IS_ERR_OR_NULL(sta)) {
+ struct iwl_mvm_sta *mvmsta =
+ iwl_mvm_sta_from_mac80211(sta);
+
+ if (mvmsta->sta_state ==
+ IEEE80211_STA_AUTHORIZED)
+ cmd.filter_flags |=
+ cpu_to_le32(MAC_FILTER_ACCEPT_GRP);
+ }
+
+ rcu_read_unlock();
+ }
} else {
ctxt_sta->is_assoc = cpu_to_le32(0);
MAC_FILTER_IN_CONTROL_AND_MGMT |
MAC_FILTER_IN_BEACON |
MAC_FILTER_IN_PROBE_REQUEST |
- MAC_FILTER_IN_CRC32);
+ MAC_FILTER_IN_CRC32 |
+ MAC_FILTER_ACCEPT_GRP);
ieee80211_hw_set(mvm->hw, RX_INCLUDES_FCS);
/* Allocate sniffer station */
iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, NULL, action);
cmd.filter_flags = cpu_to_le32(MAC_FILTER_IN_BEACON |
- MAC_FILTER_IN_PROBE_REQUEST);
+ MAC_FILTER_IN_PROBE_REQUEST |
+ MAC_FILTER_ACCEPT_GRP);
/* cmd.ibss.beacon_time/cmd.ibss.beacon_tsf are curently ignored */
cmd.ibss.bi = cpu_to_le32(vif->bss_conf.beacon_int);
},
};
-static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
- enum set_key_cmd cmd,
- struct ieee80211_vif *vif,
- struct ieee80211_sta *sta,
- struct ieee80211_key_conf *key);
+static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
+ enum set_key_cmd cmd,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta,
+ struct ieee80211_key_conf *key);
void iwl_mvm_ref(struct iwl_mvm *mvm, enum iwl_mvm_ref_type ref_type)
{
ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
ieee80211_hw_set(hw, BUFF_MMPDU_TXQ);
ieee80211_hw_set(hw, STA_MMPDU_TXQ);
- ieee80211_hw_set(hw, TX_AMSDU);
+ /*
+ * On older devices, enabling TX A-MSDU occasionally leads to
+ * something getting messed up, the command read from the FIFO
+ * gets out of sync and isn't a TX command, so that we have an
+ * assert EDC.
+ *
+ * It's not clear where the bug is, but since we didn't used to
+ * support A-MSDU until moving the mac80211 iTXQs, just leave it
+ * for older devices. We also don't see this issue on any newer
+ * devices.
+ */
+ if (mvm->cfg->device_family >= IWL_DEVICE_FAMILY_9000)
+ ieee80211_hw_set(hw, TX_AMSDU);
ieee80211_hw_set(hw, TX_FRAG_LIST);
if (iwl_mvm_has_tlc_offload(mvm)) {
mvmvif->ap_early_keys[i] = NULL;
- ret = iwl_mvm_mac_set_key(hw, SET_KEY, vif, NULL, key);
+ ret = __iwl_mvm_mac_set_key(hw, SET_KEY, vif, NULL, key);
if (ret)
goto out_quota_failed;
}
/* enable beacon filtering */
WARN_ON(iwl_mvm_enable_beacon_filter(mvm, vif, 0));
+ /*
+ * Now that the station is authorized, i.e., keys were already
+ * installed, need to indicate to the FW that
+ * multicast data frames can be forwarded to the driver
+ */
+ iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
+
iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band,
true);
} else if (old_state == IEEE80211_STA_AUTHORIZED &&
new_state == IEEE80211_STA_ASSOC) {
+ /* Multicast data frames are no longer allowed */
+ iwl_mvm_mac_ctxt_changed(mvm, vif, false, NULL);
+
/* disable beacon filtering */
ret = iwl_mvm_disable_beacon_filter(mvm, vif, 0);
WARN_ON(ret &&
return ret;
}
-static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
- enum set_key_cmd cmd,
- struct ieee80211_vif *vif,
- struct ieee80211_sta *sta,
- struct ieee80211_key_conf *key)
+static int __iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
+ enum set_key_cmd cmd,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta,
+ struct ieee80211_key_conf *key)
{
struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
return -EOPNOTSUPP;
}
- mutex_lock(&mvm->mutex);
-
switch (cmd) {
case SET_KEY:
if ((vif->type == NL80211_IFTYPE_ADHOC ||
ret = -EINVAL;
}
+ return ret;
+}
+
+static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
+ enum set_key_cmd cmd,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta,
+ struct ieee80211_key_conf *key)
+{
+ struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+ int ret;
+
+ mutex_lock(&mvm->mutex);
+ ret = __iwl_mvm_mac_set_key(hw, cmd, vif, sta, key);
mutex_unlock(&mvm->mutex);
+
return ret;
}
u32 qmask = BIT(mvm->trans->num_rx_queues) - 1;
int ret;
- lockdep_assert_held(&mvm->mutex);
if (!iwl_mvm_has_new_rx_api(mvm))
return;
atomic_set(&mvm->queue_sync_counter,
mvm->trans->num_rx_queues);
- ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, size);
+ ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif,
+ size, !notif->sync);
if (ret) {
IWL_ERR(mvm, "Failed to trigger RX queues sync (%d)\n", ret);
goto out;
}
if (notif->sync) {
+ lockdep_assert_held(&mvm->mutex);
ret = wait_event_timeout(mvm->rx_sync_waitq,
atomic_read(&mvm->queue_sync_counter) == 0 ||
iwl_mvm_is_radio_killed(mvm),
void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi,
struct iwl_rx_cmd_buffer *rxb, int queue);
int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask,
- const u8 *data, u32 count);
-void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
- int queue);
+ const u8 *data, u32 count, bool async);
+void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi,
+ struct iwl_rx_cmd_buffer *rxb, int queue);
void iwl_mvm_rx_tx_cmd(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb);
void iwl_mvm_mfu_assert_dump_notif(struct iwl_mvm *mvm,
struct iwl_rx_cmd_buffer *rxb);
#endif /* CONFIG_IWLWIFI_DEBUGFS */
/* rate scaling */
-int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool sync);
+int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq);
void iwl_mvm_update_frame_stats(struct iwl_mvm *mvm, u32 rate, bool agg);
int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate);
void rs_update_last_rssi(struct iwl_mvm *mvm,
enum iwl_mcc_source src;
char mcc[3];
struct ieee80211_regdomain *regd;
- u32 wgds_tbl_idx;
+ int wgds_tbl_idx;
lockdep_assert_held(&mvm->mutex);
iwl_mvm_rx_mpdu_mq(mvm, napi, rxb, 0);
else if (unlikely(cmd == WIDE_ID(DATA_PATH_GROUP,
RX_QUEUES_NOTIFICATION)))
- iwl_mvm_rx_queue_notif(mvm, rxb, 0);
+ iwl_mvm_rx_queue_notif(mvm, napi, rxb, 0);
else if (cmd == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE))
iwl_mvm_rx_frame_release(mvm, napi, rxb, 0);
else if (cmd == WIDE_ID(DATA_PATH_GROUP, RX_NO_DATA_NOTIF))
iwl_mvm_rx_frame_release(mvm, napi, rxb, queue);
else if (unlikely(cmd == WIDE_ID(DATA_PATH_GROUP,
RX_QUEUES_NOTIFICATION)))
- iwl_mvm_rx_queue_notif(mvm, rxb, queue);
+ iwl_mvm_rx_queue_notif(mvm, napi, rxb, queue);
else if (likely(cmd == WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD)))
iwl_mvm_rx_mpdu_mq(mvm, napi, rxb, queue);
}
return tid;
}
-void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
- int tid, struct ieee80211_tx_info *info, bool ndp)
-{
- int legacy_success;
- int retries;
- int i;
- struct iwl_lq_cmd *table;
- u32 lq_hwrate;
- struct rs_rate lq_rate, tx_resp_rate;
- struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl;
- u32 tlc_info = (uintptr_t)info->status.status_driver_data[0];
- u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK;
- u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info);
- u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1];
- struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
- struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv;
-
- /* Treat uninitialized rate scaling data same as non-existing. */
- if (!lq_sta) {
- IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n");
- return;
- } else if (!lq_sta->pers.drv) {
- IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n");
- return;
- }
-
- /* This packet was aggregated but doesn't carry status info */
- if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
- !(info->flags & IEEE80211_TX_STAT_AMPDU))
- return;
-
- if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band,
- &tx_resp_rate)) {
- WARN_ON_ONCE(1);
- return;
- }
-
-#ifdef CONFIG_MAC80211_DEBUGFS
- /* Disable last tx check if we are debugging with fixed rate but
- * update tx stats */
- if (lq_sta->pers.dbg_fixed_rate) {
- int index = tx_resp_rate.index;
- enum rs_column column;
- int attempts, success;
-
- column = rs_get_column_from_rate(&tx_resp_rate);
- if (WARN_ONCE(column == RS_COLUMN_INVALID,
- "Can't map rate 0x%x to column",
- tx_resp_hwrate))
- return;
-
- if (info->flags & IEEE80211_TX_STAT_AMPDU) {
- attempts = info->status.ampdu_len;
- success = info->status.ampdu_ack_len;
- } else {
- attempts = info->status.rates[0].count;
- success = !!(info->flags & IEEE80211_TX_STAT_ACK);
- }
-
- lq_sta->pers.tx_stats[column][index].total += attempts;
- lq_sta->pers.tx_stats[column][index].success += success;
-
- IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n",
- tx_resp_hwrate, success, attempts);
- return;
- }
-#endif
-
- if (time_after(jiffies,
- (unsigned long)(lq_sta->last_tx +
- (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) {
- IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n");
- iwl_mvm_rs_rate_init(mvm, sta, info->band, true);
- return;
- }
- lq_sta->last_tx = jiffies;
-
- /* Ignore this Tx frame response if its initial rate doesn't match
- * that of latest Link Quality command. There may be stragglers
- * from a previous Link Quality command, but we're no longer interested
- * in those; they're either from the "active" mode while we're trying
- * to check "search" mode, or a prior "search" mode after we've moved
- * to a new "search" mode (which might become the new "active" mode).
- */
- table = &lq_sta->lq;
- lq_hwrate = le32_to_cpu(table->rs_table[0]);
- if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) {
- WARN_ON_ONCE(1);
- return;
- }
-
- /* Here we actually compare this rate to the latest LQ command */
- if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) {
- IWL_DEBUG_RATE(mvm,
- "tx resp color 0x%x does not match 0x%x\n",
- lq_color, LQ_FLAG_COLOR_GET(table->flags));
-
- /*
- * Since rates mis-match, the last LQ command may have failed.
- * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with
- * ... driver.
- */
- lq_sta->missed_rate_counter++;
- if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) {
- lq_sta->missed_rate_counter = 0;
- IWL_DEBUG_RATE(mvm,
- "Too many rates mismatch. Send sync LQ. rs_state %d\n",
- lq_sta->rs_state);
- iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, false);
- }
- /* Regardless, ignore this status info for outdated rate */
- return;
- } else
- /* Rate did match, so reset the missed_rate_counter */
- lq_sta->missed_rate_counter = 0;
-
- if (!lq_sta->search_better_tbl) {
- curr_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]);
- other_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]);
- } else {
- curr_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]);
- other_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]);
- }
-
- if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) {
- IWL_DEBUG_RATE(mvm,
- "Neither active nor search matches tx rate\n");
- tmp_tbl = &(lq_sta->lq_info[lq_sta->active_tbl]);
- rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE");
- tmp_tbl = &(lq_sta->lq_info[1 - lq_sta->active_tbl]);
- rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH");
- rs_dump_rate(mvm, &lq_rate, "ACTUAL");
-
- /*
- * no matching table found, let's by-pass the data collection
- * and continue to perform rate scale to find the rate table
- */
- rs_stay_in_table(lq_sta, true);
- goto done;
- }
-
- /*
- * Updating the frame history depends on whether packets were
- * aggregated.
- *
- * For aggregation, all packets were transmitted at the same rate, the
- * first index into rate scale table.
- */
- if (info->flags & IEEE80211_TX_STAT_AMPDU) {
- rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index,
- info->status.ampdu_len,
- info->status.ampdu_ack_len,
- reduced_txp);
-
- /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat
- * it as a single frame loss as we don't want the success ratio
- * to dip too quickly because a BA wasn't received.
- * For TPC, there's no need for this optimisation since we want
- * to recover very quickly from a bad power reduction and,
- * therefore we'd like the success ratio to get an immediate hit
- * when failing to get a BA, so we'd switch back to a lower or
- * zero power reduction. When FW transmits agg with a rate
- * different from the initial rate, it will not use reduced txp
- * and will send BA notification twice (one empty with reduced
- * txp equal to the value from LQ and one with reduced txp 0).
- * We need to update counters for each txp level accordingly.
- */
- if (info->status.ampdu_ack_len == 0)
- info->status.ampdu_len = 1;
-
- rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl, tx_resp_rate.index,
- info->status.ampdu_len,
- info->status.ampdu_ack_len);
-
- /* Update success/fail counts if not searching for new mode */
- if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) {
- lq_sta->total_success += info->status.ampdu_ack_len;
- lq_sta->total_failed += (info->status.ampdu_len -
- info->status.ampdu_ack_len);
- }
- } else {
- /* For legacy, update frame history with for each Tx retry. */
- retries = info->status.rates[0].count - 1;
- /* HW doesn't send more than 15 retries */
- retries = min(retries, 15);
-
- /* The last transmission may have been successful */
- legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK);
- /* Collect data for each rate used during failed TX attempts */
- for (i = 0; i <= retries; ++i) {
- lq_hwrate = le32_to_cpu(table->rs_table[i]);
- if (rs_rate_from_ucode_rate(lq_hwrate, info->band,
- &lq_rate)) {
- WARN_ON_ONCE(1);
- return;
- }
-
- /*
- * Only collect stats if retried rate is in the same RS
- * table as active/search.
- */
- if (rs_rate_column_match(&lq_rate, &curr_tbl->rate))
- tmp_tbl = curr_tbl;
- else if (rs_rate_column_match(&lq_rate,
- &other_tbl->rate))
- tmp_tbl = other_tbl;
- else
- continue;
-
- rs_collect_tpc_data(mvm, lq_sta, tmp_tbl,
- tx_resp_rate.index, 1,
- i < retries ? 0 : legacy_success,
- reduced_txp);
- rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl,
- tx_resp_rate.index, 1,
- i < retries ? 0 : legacy_success);
- }
-
- /* Update success/fail counts if not searching for new mode */
- if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) {
- lq_sta->total_success += legacy_success;
- lq_sta->total_failed += retries + (1 - legacy_success);
- }
- }
- /* The last TX rate is cached in lq_sta; it's set in if/else above */
- lq_sta->last_rate_n_flags = lq_hwrate;
- IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp);
-done:
- /* See if there's a better rate or modulation mode to try. */
- if (sta->supp_rates[info->band])
- rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp);
-}
-
/*
* mac80211 sends us Tx status
*/
struct iwl_op_mode *op_mode = mvm_r;
struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode);
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
- if (!iwl_mvm_sta_from_mac80211(sta)->vif)
+ if (!mvmsta->vif)
return;
if (!ieee80211_is_data(hdr->frame_control) ||
tbl->expected_tpt = rs_get_expected_tpt_table(lq_sta, column, rate->bw);
}
+/* rs uses two tables, one is active and the second is for searching better
+ * configuration. This function, according to the index of the currently
+ * active table returns the search table, which is located at the
+ * index complementary to 1 according to the active table (active = 1,
+ * search = 0 or active = 0, search = 1).
+ * Since lq_info is an arary of size 2, make sure index cannot be out of bounds.
+ */
+static inline u8 rs_search_tbl(u8 active_tbl)
+{
+ return (active_tbl ^ 1) & 1;
+}
+
static s32 rs_get_best_rate(struct iwl_mvm *mvm,
struct iwl_lq_sta *lq_sta,
struct iwl_scale_tbl_info *tbl, /* "search" */
struct iwl_scale_tbl_info *tbl)
{
rs_fill_lq_cmd(mvm, sta, lq_sta, &tbl->rate);
- iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, false);
+ iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq);
}
static bool rs_tweak_rate_tbl(struct iwl_mvm *mvm,
struct ieee80211_sta *sta,
enum rs_column col_id)
{
- struct iwl_scale_tbl_info *tbl = &(lq_sta->lq_info[lq_sta->active_tbl]);
+ struct iwl_scale_tbl_info *tbl = &lq_sta->lq_info[lq_sta->active_tbl];
struct iwl_scale_tbl_info *search_tbl =
- &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]);
+ &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)];
struct rs_rate *rate = &search_tbl->rate;
const struct rs_tx_column *column = &rs_tx_columns[col_id];
const struct rs_tx_column *curr_column = &rs_tx_columns[tbl->column];
if (!lq_sta->search_better_tbl)
active_tbl = lq_sta->active_tbl;
else
- active_tbl = 1 - lq_sta->active_tbl;
+ active_tbl = rs_search_tbl(lq_sta->active_tbl);
tbl = &(lq_sta->lq_info[active_tbl]);
rate = &tbl->rate;
/* If new "search" mode was selected, set up in uCode table */
if (lq_sta->search_better_tbl) {
/* Access the "search" table, clear its history. */
- tbl = &(lq_sta->lq_info[(1 - lq_sta->active_tbl)]);
+ tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)];
rs_rate_scale_clear_tbl_windows(mvm, tbl);
/* Use new "search" start rate */
static void rs_initialize_lq(struct iwl_mvm *mvm,
struct ieee80211_sta *sta,
struct iwl_lq_sta *lq_sta,
- enum nl80211_band band, bool update)
+ enum nl80211_band band)
{
struct iwl_scale_tbl_info *tbl;
struct rs_rate *rate;
if (!lq_sta->search_better_tbl)
active_tbl = lq_sta->active_tbl;
else
- active_tbl = 1 - lq_sta->active_tbl;
+ active_tbl = rs_search_tbl(lq_sta->active_tbl);
tbl = &(lq_sta->lq_info[active_tbl]);
rate = &tbl->rate;
rs_set_expected_tpt_table(lq_sta, tbl);
rs_fill_lq_cmd(mvm, sta, lq_sta, rate);
/* TODO restore station should remember the lq cmd */
- iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq, !update);
+ iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq);
}
static void rs_drv_get_rate(void *mvm_r, struct ieee80211_sta *sta,
* Called after adding a new station to initialize rate scaling
*/
static void rs_drv_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
- enum nl80211_band band, bool update)
+ enum nl80211_band band)
{
int i, j;
struct ieee80211_hw *hw = mvm->hw;
struct ieee80211_supported_band *sband;
unsigned long supp; /* must be unsigned long for for_each_set_bit */
+ lockdep_assert_held(&mvmsta->lq_sta.rs_drv.pers.lock);
+
/* clear all non-persistent lq data */
memset(lq_sta, 0, offsetof(typeof(*lq_sta), pers));
#ifdef CONFIG_IWLWIFI_DEBUGFS
iwl_mvm_reset_frame_stats(mvm);
#endif
- rs_initialize_lq(mvm, sta, lq_sta, band, update);
+ rs_initialize_lq(mvm, sta, lq_sta, band);
}
static void rs_drv_rate_update(void *mvm_r,
iwl_mvm_rs_rate_init(mvm, sta, sband->band, true);
}
+static void __iwl_mvm_rs_tx_status(struct iwl_mvm *mvm,
+ struct ieee80211_sta *sta,
+ int tid, struct ieee80211_tx_info *info,
+ bool ndp)
+{
+ int legacy_success;
+ int retries;
+ int i;
+ struct iwl_lq_cmd *table;
+ u32 lq_hwrate;
+ struct rs_rate lq_rate, tx_resp_rate;
+ struct iwl_scale_tbl_info *curr_tbl, *other_tbl, *tmp_tbl;
+ u32 tlc_info = (uintptr_t)info->status.status_driver_data[0];
+ u8 reduced_txp = tlc_info & RS_DRV_DATA_TXP_MSK;
+ u8 lq_color = RS_DRV_DATA_LQ_COLOR_GET(tlc_info);
+ u32 tx_resp_hwrate = (uintptr_t)info->status.status_driver_data[1];
+ struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+ struct iwl_lq_sta *lq_sta = &mvmsta->lq_sta.rs_drv;
+
+ /* Treat uninitialized rate scaling data same as non-existing. */
+ if (!lq_sta) {
+ IWL_DEBUG_RATE(mvm, "Station rate scaling not created yet.\n");
+ return;
+ } else if (!lq_sta->pers.drv) {
+ IWL_DEBUG_RATE(mvm, "Rate scaling not initialized yet.\n");
+ return;
+ }
+
+ /* This packet was aggregated but doesn't carry status info */
+ if ((info->flags & IEEE80211_TX_CTL_AMPDU) &&
+ !(info->flags & IEEE80211_TX_STAT_AMPDU))
+ return;
+
+ if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band,
+ &tx_resp_rate)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+#ifdef CONFIG_MAC80211_DEBUGFS
+ /* Disable last tx check if we are debugging with fixed rate but
+ * update tx stats
+ */
+ if (lq_sta->pers.dbg_fixed_rate) {
+ int index = tx_resp_rate.index;
+ enum rs_column column;
+ int attempts, success;
+
+ column = rs_get_column_from_rate(&tx_resp_rate);
+ if (WARN_ONCE(column == RS_COLUMN_INVALID,
+ "Can't map rate 0x%x to column",
+ tx_resp_hwrate))
+ return;
+
+ if (info->flags & IEEE80211_TX_STAT_AMPDU) {
+ attempts = info->status.ampdu_len;
+ success = info->status.ampdu_ack_len;
+ } else {
+ attempts = info->status.rates[0].count;
+ success = !!(info->flags & IEEE80211_TX_STAT_ACK);
+ }
+
+ lq_sta->pers.tx_stats[column][index].total += attempts;
+ lq_sta->pers.tx_stats[column][index].success += success;
+
+ IWL_DEBUG_RATE(mvm, "Fixed rate 0x%x success %d attempts %d\n",
+ tx_resp_hwrate, success, attempts);
+ return;
+ }
+#endif
+
+ if (time_after(jiffies,
+ (unsigned long)(lq_sta->last_tx +
+ (IWL_MVM_RS_IDLE_TIMEOUT * HZ)))) {
+ IWL_DEBUG_RATE(mvm, "Tx idle for too long. reinit rs\n");
+ /* reach here only in case of driver RS, call directly
+ * the unlocked version
+ */
+ rs_drv_rate_init(mvm, sta, info->band);
+ return;
+ }
+ lq_sta->last_tx = jiffies;
+
+ /* Ignore this Tx frame response if its initial rate doesn't match
+ * that of latest Link Quality command. There may be stragglers
+ * from a previous Link Quality command, but we're no longer interested
+ * in those; they're either from the "active" mode while we're trying
+ * to check "search" mode, or a prior "search" mode after we've moved
+ * to a new "search" mode (which might become the new "active" mode).
+ */
+ table = &lq_sta->lq;
+ lq_hwrate = le32_to_cpu(table->rs_table[0]);
+ if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ /* Here we actually compare this rate to the latest LQ command */
+ if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) {
+ IWL_DEBUG_RATE(mvm,
+ "tx resp color 0x%x does not match 0x%x\n",
+ lq_color, LQ_FLAG_COLOR_GET(table->flags));
+
+ /* Since rates mis-match, the last LQ command may have failed.
+ * After IWL_MISSED_RATE_MAX mis-matches, resync the uCode with
+ * ... driver.
+ */
+ lq_sta->missed_rate_counter++;
+ if (lq_sta->missed_rate_counter > IWL_MVM_RS_MISSED_RATE_MAX) {
+ lq_sta->missed_rate_counter = 0;
+ IWL_DEBUG_RATE(mvm,
+ "Too many rates mismatch. Send sync LQ. rs_state %d\n",
+ lq_sta->rs_state);
+ iwl_mvm_send_lq_cmd(mvm, &lq_sta->lq);
+ }
+ /* Regardless, ignore this status info for outdated rate */
+ return;
+ }
+
+ /* Rate did match, so reset the missed_rate_counter */
+ lq_sta->missed_rate_counter = 0;
+
+ if (!lq_sta->search_better_tbl) {
+ curr_tbl = &lq_sta->lq_info[lq_sta->active_tbl];
+ other_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)];
+ } else {
+ curr_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)];
+ other_tbl = &lq_sta->lq_info[lq_sta->active_tbl];
+ }
+
+ if (WARN_ON_ONCE(!rs_rate_column_match(&lq_rate, &curr_tbl->rate))) {
+ IWL_DEBUG_RATE(mvm,
+ "Neither active nor search matches tx rate\n");
+ tmp_tbl = &lq_sta->lq_info[lq_sta->active_tbl];
+ rs_dump_rate(mvm, &tmp_tbl->rate, "ACTIVE");
+ tmp_tbl = &lq_sta->lq_info[rs_search_tbl(lq_sta->active_tbl)];
+ rs_dump_rate(mvm, &tmp_tbl->rate, "SEARCH");
+ rs_dump_rate(mvm, &lq_rate, "ACTUAL");
+
+ /* no matching table found, let's by-pass the data collection
+ * and continue to perform rate scale to find the rate table
+ */
+ rs_stay_in_table(lq_sta, true);
+ goto done;
+ }
+
+ /* Updating the frame history depends on whether packets were
+ * aggregated.
+ *
+ * For aggregation, all packets were transmitted at the same rate, the
+ * first index into rate scale table.
+ */
+ if (info->flags & IEEE80211_TX_STAT_AMPDU) {
+ rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index,
+ info->status.ampdu_len,
+ info->status.ampdu_ack_len,
+ reduced_txp);
+
+ /* ampdu_ack_len = 0 marks no BA was received. For TLC, treat
+ * it as a single frame loss as we don't want the success ratio
+ * to dip too quickly because a BA wasn't received.
+ * For TPC, there's no need for this optimisation since we want
+ * to recover very quickly from a bad power reduction and,
+ * therefore we'd like the success ratio to get an immediate hit
+ * when failing to get a BA, so we'd switch back to a lower or
+ * zero power reduction. When FW transmits agg with a rate
+ * different from the initial rate, it will not use reduced txp
+ * and will send BA notification twice (one empty with reduced
+ * txp equal to the value from LQ and one with reduced txp 0).
+ * We need to update counters for each txp level accordingly.
+ */
+ if (info->status.ampdu_ack_len == 0)
+ info->status.ampdu_len = 1;
+
+ rs_collect_tlc_data(mvm, mvmsta, tid, curr_tbl,
+ tx_resp_rate.index,
+ info->status.ampdu_len,
+ info->status.ampdu_ack_len);
+
+ /* Update success/fail counts if not searching for new mode */
+ if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) {
+ lq_sta->total_success += info->status.ampdu_ack_len;
+ lq_sta->total_failed += (info->status.ampdu_len -
+ info->status.ampdu_ack_len);
+ }
+ } else {
+ /* For legacy, update frame history with for each Tx retry. */
+ retries = info->status.rates[0].count - 1;
+ /* HW doesn't send more than 15 retries */
+ retries = min(retries, 15);
+
+ /* The last transmission may have been successful */
+ legacy_success = !!(info->flags & IEEE80211_TX_STAT_ACK);
+ /* Collect data for each rate used during failed TX attempts */
+ for (i = 0; i <= retries; ++i) {
+ lq_hwrate = le32_to_cpu(table->rs_table[i]);
+ if (rs_rate_from_ucode_rate(lq_hwrate, info->band,
+ &lq_rate)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ /* Only collect stats if retried rate is in the same RS
+ * table as active/search.
+ */
+ if (rs_rate_column_match(&lq_rate, &curr_tbl->rate))
+ tmp_tbl = curr_tbl;
+ else if (rs_rate_column_match(&lq_rate,
+ &other_tbl->rate))
+ tmp_tbl = other_tbl;
+ else
+ continue;
+
+ rs_collect_tpc_data(mvm, lq_sta, tmp_tbl,
+ tx_resp_rate.index, 1,
+ i < retries ? 0 : legacy_success,
+ reduced_txp);
+ rs_collect_tlc_data(mvm, mvmsta, tid, tmp_tbl,
+ tx_resp_rate.index, 1,
+ i < retries ? 0 : legacy_success);
+ }
+
+ /* Update success/fail counts if not searching for new mode */
+ if (lq_sta->rs_state == RS_STATE_STAY_IN_COLUMN) {
+ lq_sta->total_success += legacy_success;
+ lq_sta->total_failed += retries + (1 - legacy_success);
+ }
+ }
+ /* The last TX rate is cached in lq_sta; it's set in if/else above */
+ lq_sta->last_rate_n_flags = lq_hwrate;
+ IWL_DEBUG_RATE(mvm, "reduced txpower: %d\n", reduced_txp);
+done:
+ /* See if there's a better rate or modulation mode to try. */
+ if (sta->supp_rates[info->band])
+ rs_rate_scale_perform(mvm, sta, lq_sta, tid, ndp);
+}
+
+void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
+ int tid, struct ieee80211_tx_info *info, bool ndp)
+{
+ struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
+ /* If it's locked we are in middle of init flow
+ * just wait for next tx status to update the lq_sta data
+ */
+ if (!spin_trylock(&mvmsta->lq_sta.rs_drv.pers.lock))
+ return;
+
+ __iwl_mvm_rs_tx_status(mvm, sta, tid, info, ndp);
+ spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock);
+}
+
#ifdef CONFIG_MAC80211_DEBUGFS
static void rs_build_rates_table_from_fixed(struct iwl_mvm *mvm,
struct iwl_lq_cmd *lq_cmd,
bfersta_ss_params &= ~LQ_SS_BFER_ALLOWED;
bfersta_lq_cmd->ss_params = cpu_to_le32(bfersta_ss_params);
- iwl_mvm_send_lq_cmd(mvm, bfersta_lq_cmd, false);
+ iwl_mvm_send_lq_cmd(mvm, bfersta_lq_cmd);
ss_params |= LQ_SS_BFER_ALLOWED;
IWL_DEBUG_RATE(mvm,
if (lq_sta->pers.dbg_fixed_rate) {
rs_fill_lq_cmd(mvm, NULL, lq_sta, NULL);
- iwl_mvm_send_lq_cmd(lq_sta->pers.drv, &lq_sta->lq, false);
+ iwl_mvm_send_lq_cmd(lq_sta->pers.drv, &lq_sta->lq);
}
}
void iwl_mvm_rs_rate_init(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
enum nl80211_band band, bool update)
{
- if (iwl_mvm_has_tlc_offload(mvm))
+ if (iwl_mvm_has_tlc_offload(mvm)) {
rs_fw_rate_init(mvm, sta, band, update);
- else
- rs_drv_rate_init(mvm, sta, band, update);
+ } else {
+ struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
+ spin_lock(&mvmsta->lq_sta.rs_drv.pers.lock);
+ rs_drv_rate_init(mvm, sta, band);
+ spin_unlock(&mvmsta->lq_sta.rs_drv.pers.lock);
+ }
}
int iwl_mvm_rate_control_register(void)
lq->flags &= ~LQ_FLAG_USE_RTS_MSK;
}
- return iwl_mvm_send_lq_cmd(mvm, lq, false);
+ return iwl_mvm_send_lq_cmd(mvm, lq);
}
/**
* Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
* Copyright(c) 2015 Intel Mobile Communications GmbH
* Copyright(c) 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
*
* Contact Information:
* Intel Linux Wireless <linuxwifi@intel.com>
s8 last_rssi;
struct rs_rate_stats tx_stats[RS_COLUMN_COUNT][IWL_RATE_COUNT];
struct iwl_mvm *drv;
+ spinlock_t lock; /* for races in reinit/update table */
} pers;
};
}
int iwl_mvm_notify_rx_queue(struct iwl_mvm *mvm, u32 rxq_mask,
- const u8 *data, u32 count)
+ const u8 *data, u32 count, bool async)
{
- struct iwl_rxq_sync_cmd *cmd;
+ u8 buf[sizeof(struct iwl_rxq_sync_cmd) +
+ sizeof(struct iwl_mvm_rss_sync_notif)];
+ struct iwl_rxq_sync_cmd *cmd = (void *)buf;
u32 data_size = sizeof(*cmd) + count;
int ret;
- /* should be DWORD aligned */
- if (WARN_ON(count & 3 || count > IWL_MULTI_QUEUE_SYNC_MSG_MAX_SIZE))
+ /*
+ * size must be a multiple of DWORD
+ * Ensure we don't overflow buf
+ */
+ if (WARN_ON(count & 3 ||
+ count > sizeof(struct iwl_mvm_rss_sync_notif)))
return -EINVAL;
- cmd = kzalloc(data_size, GFP_KERNEL);
- if (!cmd)
- return -ENOMEM;
-
cmd->rxq_mask = cpu_to_le32(rxq_mask);
cmd->count = cpu_to_le32(count);
cmd->flags = 0;
ret = iwl_mvm_send_cmd_pdu(mvm,
WIDE_ID(DATA_PATH_GROUP,
TRIGGER_RX_QUEUES_NOTIF_CMD),
- 0, data_size, cmd);
+ async ? CMD_ASYNC : 0, data_size, cmd);
- kfree(cmd);
return ret;
}
!ieee80211_sn_less(sn1, sn2 - buffer_size);
}
+static void iwl_mvm_sync_nssn(struct iwl_mvm *mvm, u8 baid, u16 nssn)
+{
+ struct iwl_mvm_rss_sync_notif notif = {
+ .metadata.type = IWL_MVM_RXQ_NSSN_SYNC,
+ .metadata.sync = 0,
+ .nssn_sync.baid = baid,
+ .nssn_sync.nssn = nssn,
+ };
+
+ iwl_mvm_sync_rx_queues_internal(mvm, (void *)¬if, sizeof(notif));
+}
+
#define RX_REORDER_BUF_TIMEOUT_MQ (HZ / 10)
+enum iwl_mvm_release_flags {
+ IWL_MVM_RELEASE_SEND_RSS_SYNC = BIT(0),
+ IWL_MVM_RELEASE_FROM_RSS_SYNC = BIT(1),
+};
+
static void iwl_mvm_release_frames(struct iwl_mvm *mvm,
struct ieee80211_sta *sta,
struct napi_struct *napi,
struct iwl_mvm_baid_data *baid_data,
struct iwl_mvm_reorder_buffer *reorder_buf,
- u16 nssn)
+ u16 nssn, u32 flags)
{
struct iwl_mvm_reorder_buf_entry *entries =
&baid_data->entries[reorder_buf->queue *
lockdep_assert_held(&reorder_buf->lock);
+ /*
+ * We keep the NSSN not too far behind, if we are sync'ing it and it
+ * is more than 2048 ahead of us, it must be behind us. Discard it.
+ * This can happen if the queue that hit the 0 / 2048 seqno was lagging
+ * behind and this queue already processed packets. The next if
+ * would have caught cases where this queue would have processed less
+ * than 64 packets, but it may have processed more than 64 packets.
+ */
+ if ((flags & IWL_MVM_RELEASE_FROM_RSS_SYNC) &&
+ ieee80211_sn_less(nssn, ssn))
+ goto set_timer;
+
/* ignore nssn smaller than head sn - this can happen due to timeout */
if (iwl_mvm_is_sn_less(nssn, ssn, reorder_buf->buf_size))
goto set_timer;
struct sk_buff *skb;
ssn = ieee80211_sn_inc(ssn);
+ if ((flags & IWL_MVM_RELEASE_SEND_RSS_SYNC) &&
+ (ssn == 2048 || ssn == 0))
+ iwl_mvm_sync_nssn(mvm, baid_data->baid, ssn);
/*
* Empty the list. Will have more than one frame for A-MSDU.
sta_id, sn);
iwl_mvm_event_frame_timeout_callback(buf->mvm, mvmsta->vif,
sta, baid_data->tid);
- iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data, buf, sn);
+ iwl_mvm_release_frames(buf->mvm, sta, NULL, baid_data,
+ buf, sn, IWL_MVM_RELEASE_SEND_RSS_SYNC);
rcu_read_unlock();
} else {
/*
spin_lock_bh(&reorder_buf->lock);
iwl_mvm_release_frames(mvm, sta, NULL, ba_data, reorder_buf,
ieee80211_sn_add(reorder_buf->head_sn,
- reorder_buf->buf_size));
+ reorder_buf->buf_size),
+ 0);
spin_unlock_bh(&reorder_buf->lock);
del_timer_sync(&reorder_buf->reorder_timer);
rcu_read_unlock();
}
-void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb,
- int queue)
+static void iwl_mvm_release_frames_from_notif(struct iwl_mvm *mvm,
+ struct napi_struct *napi,
+ u8 baid, u16 nssn, int queue,
+ u32 flags)
+{
+ struct ieee80211_sta *sta;
+ struct iwl_mvm_reorder_buffer *reorder_buf;
+ struct iwl_mvm_baid_data *ba_data;
+
+ IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n",
+ baid, nssn);
+
+ if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID ||
+ baid >= ARRAY_SIZE(mvm->baid_map)))
+ return;
+
+ rcu_read_lock();
+
+ ba_data = rcu_dereference(mvm->baid_map[baid]);
+ if (WARN_ON_ONCE(!ba_data))
+ goto out;
+
+ sta = rcu_dereference(mvm->fw_id_to_mac_id[ba_data->sta_id]);
+ if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta)))
+ goto out;
+
+ reorder_buf = &ba_data->reorder_buf[queue];
+
+ spin_lock_bh(&reorder_buf->lock);
+ iwl_mvm_release_frames(mvm, sta, napi, ba_data,
+ reorder_buf, nssn, flags);
+ spin_unlock_bh(&reorder_buf->lock);
+
+out:
+ rcu_read_unlock();
+}
+
+static void iwl_mvm_nssn_sync(struct iwl_mvm *mvm,
+ struct napi_struct *napi, int queue,
+ const struct iwl_mvm_nssn_sync_data *data)
+{
+ iwl_mvm_release_frames_from_notif(mvm, napi, data->baid,
+ data->nssn, queue,
+ IWL_MVM_RELEASE_FROM_RSS_SYNC);
+}
+
+void iwl_mvm_rx_queue_notif(struct iwl_mvm *mvm, struct napi_struct *napi,
+ struct iwl_rx_cmd_buffer *rxb, int queue)
{
struct iwl_rx_packet *pkt = rxb_addr(rxb);
struct iwl_rxq_sync_notification *notif;
case IWL_MVM_RXQ_NOTIF_DEL_BA:
iwl_mvm_del_ba(mvm, queue, (void *)internal_notif->data);
break;
+ case IWL_MVM_RXQ_NSSN_SYNC:
+ iwl_mvm_nssn_sync(mvm, napi, queue,
+ (void *)internal_notif->data);
+ break;
default:
WARN_ONCE(1, "Invalid identifier %d", internal_notif->type);
}
}
if (ieee80211_is_back_req(hdr->frame_control)) {
- iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, nssn);
+ iwl_mvm_release_frames(mvm, sta, napi, baid_data,
+ buffer, nssn, 0);
goto drop;
}
* If the SN is smaller than the NSSN it might need to first go into
* the reorder buffer, in which case we just release up to it and the
* rest of the function will take care of storing it and releasing up to
- * the nssn
+ * the nssn.
+ * This should not happen. This queue has been lagging and it should
+ * have been updated by a IWL_MVM_RXQ_NSSN_SYNC notification. Be nice
+ * and update the other queues.
*/
if (!iwl_mvm_is_sn_less(nssn, buffer->head_sn + buffer->buf_size,
buffer->buf_size) ||
u16 min_sn = ieee80211_sn_less(sn, nssn) ? sn : nssn;
iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer,
- min_sn);
+ min_sn, IWL_MVM_RELEASE_SEND_RSS_SYNC);
}
/* drop any oudated packets */
if (!buffer->num_stored && ieee80211_sn_less(sn, nssn)) {
if (iwl_mvm_is_sn_less(buffer->head_sn, nssn,
buffer->buf_size) &&
- (!amsdu || last_subframe))
+ (!amsdu || last_subframe)) {
+ /*
+ * If we crossed the 2048 or 0 SN, notify all the
+ * queues. This is done in order to avoid having a
+ * head_sn that lags behind for too long. When that
+ * happens, we can get to a situation where the head_sn
+ * is within the interval [nssn - buf_size : nssn]
+ * which will make us think that the nssn is a packet
+ * that we already freed because of the reordering
+ * buffer and we will ignore it. So maintain the
+ * head_sn somewhat updated across all the queues:
+ * when it crosses 0 and 2048.
+ */
+ if (sn == 2048 || sn == 0)
+ iwl_mvm_sync_nssn(mvm, baid, sn);
buffer->head_sn = nssn;
+ }
/* No need to update AMSDU last SN - we are moving the head */
spin_unlock_bh(&buffer->lock);
return false;
* while technically there is no hole and we can move forward.
*/
if (!buffer->num_stored && sn == buffer->head_sn) {
- if (!amsdu || last_subframe)
+ if (!amsdu || last_subframe) {
+ if (sn == 2048 || sn == 0)
+ iwl_mvm_sync_nssn(mvm, baid, sn);
buffer->head_sn = ieee80211_sn_inc(buffer->head_sn);
+ }
/* No need to update AMSDU last SN - we are moving the head */
spin_unlock_bh(&buffer->lock);
return false;
* release notification with up to date NSSN.
*/
if (!amsdu || last_subframe)
- iwl_mvm_release_frames(mvm, sta, napi, baid_data, buffer, nssn);
+ iwl_mvm_release_frames(mvm, sta, napi, baid_data,
+ buffer, nssn,
+ IWL_MVM_RELEASE_SEND_RSS_SYNC);
spin_unlock_bh(&buffer->lock);
return true;
out:
rcu_read_unlock();
}
+
void iwl_mvm_rx_frame_release(struct iwl_mvm *mvm, struct napi_struct *napi,
struct iwl_rx_cmd_buffer *rxb, int queue)
{
struct iwl_rx_packet *pkt = rxb_addr(rxb);
struct iwl_frame_release *release = (void *)pkt->data;
- struct ieee80211_sta *sta;
- struct iwl_mvm_reorder_buffer *reorder_buf;
- struct iwl_mvm_baid_data *ba_data;
-
- int baid = release->baid;
-
- IWL_DEBUG_HT(mvm, "Frame release notification for BAID %u, NSSN %d\n",
- release->baid, le16_to_cpu(release->nssn));
- if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID))
- return;
-
- rcu_read_lock();
-
- ba_data = rcu_dereference(mvm->baid_map[baid]);
- if (WARN_ON_ONCE(!ba_data))
- goto out;
-
- sta = rcu_dereference(mvm->fw_id_to_mac_id[ba_data->sta_id]);
- if (WARN_ON_ONCE(IS_ERR_OR_NULL(sta)))
- goto out;
-
- reorder_buf = &ba_data->reorder_buf[queue];
-
- spin_lock_bh(&reorder_buf->lock);
- iwl_mvm_release_frames(mvm, sta, napi, ba_data, reorder_buf,
- le16_to_cpu(release->nssn));
- spin_unlock_bh(&reorder_buf->lock);
-
-out:
- rcu_read_unlock();
+ iwl_mvm_release_frames_from_notif(mvm, napi, release->baid,
+ le16_to_cpu(release->nssn),
+ queue, 0);
}
*/
if (iwl_mvm_has_tlc_offload(mvm))
iwl_mvm_rs_add_sta(mvm, mvm_sta);
+ else
+ spin_lock_init(&mvm_sta->lq_sta.rs_drv.pers.lock);
iwl_mvm_toggle_tx_ant(mvm, &mvm_sta->tx_ant);
static void iwl_mvm_sync_rxq_del_ba(struct iwl_mvm *mvm, u8 baid)
{
- struct iwl_mvm_delba_notif notif = {
+ struct iwl_mvm_rss_sync_notif notif = {
.metadata.type = IWL_MVM_RXQ_NOTIF_DEL_BA,
.metadata.sync = 1,
.delba.baid = baid,
IWL_DEBUG_HT(mvm, "Tx aggregation enabled on ra = %pM tid = %d\n",
sta->addr, tid);
- return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.rs_drv.lq, false);
+ return iwl_mvm_send_lq_cmd(mvm, &mvmsta->lq_sta.rs_drv.lq);
}
static void iwl_mvm_unreserve_agg_queue(struct iwl_mvm *mvm,
u32 baid;
} __packed;
-struct iwl_mvm_delba_notif {
+struct iwl_mvm_nssn_sync_data {
+ u32 baid;
+ u32 nssn;
+} __packed;
+
+struct iwl_mvm_rss_sync_notif {
struct iwl_mvm_internal_rxq_notif metadata;
- struct iwl_mvm_delba_data delba;
+ union {
+ struct iwl_mvm_delba_data delba;
+ struct iwl_mvm_nssn_sync_data nssn_sync;
+ };
} __packed;
/**
unsigned int tcp_payload_len;
unsigned int mss = skb_shinfo(skb)->gso_size;
bool ipv4 = (skb->protocol == htons(ETH_P_IP));
+ bool qos = ieee80211_is_data_qos(hdr->frame_control);
u16 ip_base_id = ipv4 ? ntohs(ip_hdr(skb)->id) : 0;
skb_shinfo(skb)->gso_size = num_subframes * mss;
if (tcp_payload_len > mss) {
skb_shinfo(tmp)->gso_size = mss;
} else {
- if (ieee80211_is_data_qos(hdr->frame_control)) {
+ if (qos) {
u8 *qc;
if (ipv4)
* this case to clear the state indicating that station creation is in
* progress.
*/
-int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq, bool sync)
+int iwl_mvm_send_lq_cmd(struct iwl_mvm *mvm, struct iwl_lq_cmd *lq)
{
struct iwl_host_cmd cmd = {
.id = LQ_CMD,
.len = { sizeof(struct iwl_lq_cmd), },
- .flags = sync ? 0 : CMD_ASYNC,
+ .flags = CMD_ASYNC,
.data = { lq, },
};
{IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)},
{IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)},
+ {IWL_PCI_DEVICE(0x2526, 0x6010, iwl9260_2ac_160_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x6014, iwl9260_2ac_160_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_160_cfg)},
{IWL_PCI_DEVICE(0x2526, 0x8010, iwl9260_2ac_160_cfg)},
{IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_160_cfg)},
+ {IWL_PCI_DEVICE(0x2526, 0xE010, iwl9260_2ac_160_cfg)},
+ {IWL_PCI_DEVICE(0x2526, 0xE014, iwl9260_2ac_160_cfg)},
{IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)},
{IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)},
{IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)},
iwl_trans->cfg = &iwl9560_2ac_cfg_qu_c0_jf_b0;
else if (iwl_trans->cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0)
iwl_trans->cfg = &iwl9560_2ac_160_cfg_qu_c0_jf_b0;
+ else if (iwl_trans->cfg == &killer1650s_2ax_cfg_qu_b0_hr_b0)
+ iwl_trans->cfg = &killer1650s_2ax_cfg_qu_c0_hr_b0;
+ else if (iwl_trans->cfg == &killer1650i_2ax_cfg_qu_b0_hr_b0)
+ iwl_trans->cfg = &killer1650i_2ax_cfg_qu_c0_hr_b0;
}
+
+ /* same thing for QuZ... */
+ if (iwl_trans->hw_rev == CSR_HW_REV_TYPE_QUZ) {
+ if (cfg == &iwl_ax101_cfg_qu_hr)
+ cfg = &iwl_ax101_cfg_quz_hr;
+ else if (cfg == &iwl_ax201_cfg_qu_hr)
+ cfg = &iwl_ax201_cfg_quz_hr;
+ else if (cfg == &iwl9461_2ac_cfg_qu_b0_jf_b0)
+ cfg = &iwl9461_2ac_cfg_quz_a0_jf_b0_soc;
+ else if (cfg == &iwl9462_2ac_cfg_qu_b0_jf_b0)
+ cfg = &iwl9462_2ac_cfg_quz_a0_jf_b0_soc;
+ else if (cfg == &iwl9560_2ac_cfg_qu_b0_jf_b0)
+ cfg = &iwl9560_2ac_cfg_quz_a0_jf_b0_soc;
+ else if (cfg == &iwl9560_2ac_160_cfg_qu_b0_jf_b0)
+ cfg = &iwl9560_2ac_160_cfg_quz_a0_jf_b0_soc;
+ }
+
#endif
pci_set_drvdata(pdev, iwl_trans);
}
} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
- ((trans->cfg != &iwl_ax200_cfg_cc &&
- trans->cfg != &killer1650x_2ax_cfg &&
- trans->cfg != &killer1650w_2ax_cfg &&
- trans->cfg != &iwl_ax201_cfg_quz_hr) ||
- trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) {
+ trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) {
u32 hw_status;
hw_status = iwl_read_prph(trans, UMAG_GEN_HW_STATUS);
u16 len = byte_cnt;
__le16 bc_ent;
- if (trans_pcie->bc_table_dword)
- len = DIV_ROUND_UP(len, 4);
-
- if (WARN_ON(len > 0xFFF || idx >= txq->n_window))
+ if (WARN(idx >= txq->n_window, "%d >= %d\n", idx, txq->n_window))
return;
filled_tfd_size = offsetof(struct iwl_tfh_tfd, tbs) +
*/
num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
- bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
- if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+ if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+ /* Starting from 22560, the HW expects bytes */
+ WARN_ON(trans_pcie->bc_table_dword);
+ WARN_ON(len > 0x3FFF);
+ bc_ent = cpu_to_le16(len | (num_fetch_chunks << 14));
scd_bc_tbl_gen3->tfd_offset[idx] = bc_ent;
- else
+ } else {
+ /* Until 22560, the HW expects DW */
+ WARN_ON(!trans_pcie->bc_table_dword);
+ len = DIV_ROUND_UP(len, 4);
+ WARN_ON(len > 0xFFF);
+ bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
scd_bc_tbl->tfd_offset[idx] = bc_ent;
+ }
}
/*
DMA_TO_DEVICE);
}
+ meta->tbs = 0;
+
if (trans->cfg->use_tfh) {
struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, &hwsim_genl_family,
NLM_F_MULTI, HWSIM_CMD_GET_RADIO);
- if (!hdr)
+ if (hdr) {
+ genl_dump_check_consistent(cb, hdr);
+ genlmsg_end(skb, hdr);
+ } else {
res = -EMSGSIZE;
- genl_dump_check_consistent(cb, hdr);
- genlmsg_end(skb, hdr);
+ }
}
done:
#define MWIFIEX_MAX_TOTAL_SCAN_TIME (MWIFIEX_TIMER_10S - MWIFIEX_TIMER_1S)
+#define WPA_GTK_OUI_OFFSET 2
#define RSN_GTK_OUI_OFFSET 2
#define MWIFIEX_OUI_NOT_PRESENT 0
u8 ret = MWIFIEX_OUI_NOT_PRESENT;
if (has_vendor_hdr(bss_desc->bcn_wpa_ie, WLAN_EID_VENDOR_SPECIFIC)) {
- iebody = (struct ie_body *) bss_desc->bcn_wpa_ie->data;
+ iebody = (struct ie_body *)((u8 *)bss_desc->bcn_wpa_ie->data +
+ WPA_GTK_OUI_OFFSET);
oui = &mwifiex_wpa_oui[cipher][0];
ret = mwifiex_search_oui_in_ie(iebody, oui);
if (ret)
.release_buffered_frames = mt76_release_buffered_frames,
};
-static int mt76x0u_init_hardware(struct mt76x02_dev *dev)
+static int mt76x0u_init_hardware(struct mt76x02_dev *dev, bool reset)
{
int err;
- mt76x0_chip_onoff(dev, true, true);
+ mt76x0_chip_onoff(dev, true, reset);
if (!mt76x02_wait_for_mac(&dev->mt76))
return -ETIMEDOUT;
if (err < 0)
goto out_err;
- err = mt76x0u_init_hardware(dev);
+ err = mt76x0u_init_hardware(dev, true);
if (err < 0)
goto out_err;
if (ret < 0)
goto err;
- ret = mt76x0u_init_hardware(dev);
+ ret = mt76x0u_init_hardware(dev, false);
if (ret)
goto err;
rt2800_delete_wcid_attr(rt2x00dev, i);
}
+ /*
+ * Clear encryption initialization vectors on start, but keep them
+ * for watchdog reset. Otherwise we will have wrong IVs and not be
+ * able to keep connections after reset.
+ */
+ if (!test_bit(DEVICE_STATE_RESET, &rt2x00dev->flags))
+ for (i = 0; i < 256; i++)
+ rt2800_register_write(rt2x00dev, MAC_IVEIV_ENTRY(i), 0);
+
/*
* Clear all beacons
*/
DEVICE_STATE_ENABLED_RADIO,
DEVICE_STATE_SCANNING,
DEVICE_STATE_FLUSHING,
+ DEVICE_STATE_RESET,
/*
* Driver configuration
int rt2x00lib_start(struct rt2x00_dev *rt2x00dev)
{
- int retval;
+ int retval = 0;
if (test_bit(DEVICE_STATE_STARTED, &rt2x00dev->flags)) {
/*
* This is special case for ieee80211_restart_hw(), otherwise
* mac80211 never call start() two times in row without stop();
*/
+ set_bit(DEVICE_STATE_RESET, &rt2x00dev->flags);
rt2x00dev->ops->lib->pre_reset_hw(rt2x00dev);
rt2x00lib_stop(rt2x00dev);
}
*/
retval = rt2x00lib_load_firmware(rt2x00dev);
if (retval)
- return retval;
+ goto out;
/*
* Initialize the device.
*/
retval = rt2x00lib_initialize(rt2x00dev);
if (retval)
- return retval;
+ goto out;
rt2x00dev->intf_ap_count = 0;
rt2x00dev->intf_sta_count = 0;
/* Enable the radio */
retval = rt2x00lib_enable_radio(rt2x00dev);
if (retval)
- return retval;
+ goto out;
set_bit(DEVICE_STATE_STARTED, &rt2x00dev->flags);
- return 0;
+out:
+ clear_bit(DEVICE_STATE_RESET, &rt2x00dev->flags);
+ return retval;
}
void rt2x00lib_stop(struct rt2x00_dev *rt2x00dev)
.flags = WIPHY_VENDOR_CMD_NEED_NETDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
.doit = wlcore_vendor_cmd_smart_config_start,
+ .policy = wlcore_vendor_attr_policy,
},
{
.info = {
.flags = WIPHY_VENDOR_CMD_NEED_NETDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
.doit = wlcore_vendor_cmd_smart_config_stop,
+ .policy = wlcore_vendor_attr_policy,
},
{
.info = {
.flags = WIPHY_VENDOR_CMD_NEED_NETDEV |
WIPHY_VENDOR_CMD_NEED_RUNNING,
.doit = wlcore_vendor_cmd_smart_config_set_group_key,
+ .policy = wlcore_vendor_attr_policy,
},
};
skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS;
nskb = xenvif_alloc_skb(0);
if (unlikely(nskb == NULL)) {
+ skb_shinfo(skb)->nr_frags = 0;
kfree_skb(skb);
xenvif_tx_err(queue, &txreq, extra_count, idx);
if (net_ratelimit())
if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
/* Failure in xenvif_set_skb_gso is fatal. */
+ skb_shinfo(skb)->nr_frags = 0;
kfree_skb(skb);
kfree_skb(nskb);
break;
/* Reset possible fault of previous session */
clear_bit(NFCMRVL_PHY_ERROR, &priv->flags);
- if (priv->config.reset_n_io) {
+ if (gpio_is_valid(priv->config.reset_n_io)) {
nfc_info(priv->dev, "reset the chip\n");
gpio_set_value(priv->config.reset_n_io, 0);
usleep_range(5000, 10000);
void nfcmrvl_chip_halt(struct nfcmrvl_private *priv)
{
- if (priv->config.reset_n_io)
+ if (gpio_is_valid(priv->config.reset_n_io))
gpio_set_value(priv->config.reset_n_io, 0);
}
static unsigned int hci_muxed;
static unsigned int flow_control;
static unsigned int break_control;
-static unsigned int reset_n_io;
+static int reset_n_io = -EINVAL;
/*
** NFCMRVL NCI OPS
module_param(hci_muxed, uint, 0);
MODULE_PARM_DESC(hci_muxed, "Tell if transport is muxed in HCI one.");
-module_param(reset_n_io, uint, 0);
+module_param(reset_n_io, int, 0);
MODULE_PARM_DESC(reset_n_io, "GPIO that is wired to RESET_N signal.");
/* No configuration for USB */
memset(&config, 0, sizeof(config));
+ config.reset_n_io = -EINVAL;
nfc_info(&udev->dev, "intf %p id %p\n", intf, id);
transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev,
skb->len - 2, GFP_KERNEL);
+ if (!transaction)
+ return -ENOMEM;
transaction->aid_len = skb->data[1];
memcpy(transaction->aid, &skb->data[2], transaction->aid_len);
transaction = (struct nfc_evt_transaction *)devm_kzalloc(dev,
skb->len - 2, GFP_KERNEL);
+ if (!transaction)
+ return -ENOMEM;
transaction->aid_len = skb->data[1];
memcpy(transaction->aid, &skb->data[2],
#include <linux/msi.h>
#include <linux/pci.h>
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_VERSION("0.1");
-MODULE_AUTHOR("Logan Gunthorpe <logang@deltatee.com>");
-MODULE_DESCRIPTION("NTB MSI Interrupt Library");
-
struct ntb_msi {
u64 base_addr;
u64 end_addr;
struct nd_btt *nd_btt = to_nd_btt(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_size_select_store(dev, buf, &nd_btt->lbasize,
btt_lbasize_supported);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
struct nd_btt *nd_btt = to_nd_btt(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
rc = nd_uuid_store(dev, &nd_btt->uuid, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
struct nd_btt *nd_btt = to_nd_btt(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
struct nd_btt *nd_btt = to_nd_btt(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver)
rc = sprintf(buf, "%llu\n", nd_btt->size);
else {
/* no size to convey if the btt instance is disabled */
rc = -ENXIO;
}
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
int nvdimm_major;
static int nvdimm_bus_major;
-static struct class *nd_class;
+struct class *nd_class;
static DEFINE_IDA(nd_ida);
static int to_nd_device_type(struct device *dev)
{
nvdimm_bus_lock(&nvdimm_bus->dev);
if (--nvdimm_bus->probe_active == 0)
- wake_up(&nvdimm_bus->probe_wait);
+ wake_up(&nvdimm_bus->wait);
nvdimm_bus_unlock(&nvdimm_bus->dev);
}
dev->driver->name, dev_name(dev));
nvdimm_bus_probe_start(nvdimm_bus);
+ debug_nvdimm_lock(dev);
rc = nd_drv->probe(dev);
+ debug_nvdimm_unlock(dev);
+
if (rc == 0)
nd_region_probe_success(nvdimm_bus, dev);
else
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
int rc = 0;
- if (nd_drv->remove)
+ if (nd_drv->remove) {
+ debug_nvdimm_lock(dev);
rc = nd_drv->remove(dev);
+ debug_nvdimm_unlock(dev);
+ }
nd_region_disable(nvdimm_bus, dev);
dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name,
void nd_device_notify(struct device *dev, enum nvdimm_event event)
{
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver) {
struct nd_device_driver *nd_drv;
if (nd_drv->notify)
nd_drv->notify(dev, event);
}
- device_unlock(dev);
+ nd_device_unlock(dev);
}
EXPORT_SYMBOL(nd_device_notify);
kfree(nvdimm_bus);
}
-static bool is_nvdimm_bus(struct device *dev)
+bool is_nvdimm_bus(struct device *dev)
{
return dev->release == nvdimm_bus_release;
}
return NULL;
INIT_LIST_HEAD(&nvdimm_bus->list);
INIT_LIST_HEAD(&nvdimm_bus->mapping_list);
- init_waitqueue_head(&nvdimm_bus->probe_wait);
+ init_waitqueue_head(&nvdimm_bus->wait);
nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
if (nvdimm_bus->id < 0) {
kfree(nvdimm_bus);
list_del_init(&nvdimm_bus->list);
mutex_unlock(&nvdimm_bus_list_mutex);
+ wait_event(nvdimm_bus->wait,
+ atomic_read(&nvdimm_bus->ioctl_active) == 0);
+
nd_synchronize();
device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
void nd_device_unregister(struct device *dev, enum nd_async_mode mode)
{
+ bool killed;
+
switch (mode) {
case ND_ASYNC:
+ /*
+ * In the async case this is being triggered with the
+ * device lock held and the unregistration work needs to
+ * be moved out of line iff this is thread has won the
+ * race to schedule the deletion.
+ */
+ if (!kill_device(dev))
+ return;
+
get_device(dev);
async_schedule_domain(nd_async_device_unregister, dev,
&nd_async_domain);
break;
case ND_SYNC:
+ /*
+ * In the sync case the device is being unregistered due
+ * to a state change of the parent. Claim the kill state
+ * to synchronize against other unregistration requests,
+ * or otherwise let the async path handle it if the
+ * unregistration was already queued.
+ */
+ nd_device_lock(dev);
+ killed = kill_device(dev);
+ nd_device_unlock(dev);
+
+ if (!killed)
+ return;
+
nd_synchronize();
device_unregister(dev);
break;
do {
if (nvdimm_bus->probe_active == 0)
break;
- nvdimm_bus_unlock(&nvdimm_bus->dev);
- wait_event(nvdimm_bus->probe_wait,
+ nvdimm_bus_unlock(dev);
+ nd_device_unlock(dev);
+ wait_event(nvdimm_bus->wait,
nvdimm_bus->probe_active == 0);
- nvdimm_bus_lock(&nvdimm_bus->dev);
+ nd_device_lock(dev);
+ nvdimm_bus_lock(dev);
} while (true);
}
int read_only, unsigned int ioctl_cmd, unsigned long arg)
{
struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
- static char out_env[ND_CMD_MAX_ENVELOPE];
- static char in_env[ND_CMD_MAX_ENVELOPE];
const struct nd_cmd_desc *desc = NULL;
unsigned int cmd = _IOC_NR(ioctl_cmd);
struct device *dev = &nvdimm_bus->dev;
void __user *p = (void __user *) arg;
+ char *out_env = NULL, *in_env = NULL;
const char *cmd_name, *dimm_name;
u32 in_len = 0, out_len = 0;
unsigned int func = cmd;
unsigned long cmd_mask;
struct nd_cmd_pkg pkg;
int rc, i, cmd_rc;
+ void *buf = NULL;
u64 buf_len = 0;
- void *buf;
if (nvdimm) {
desc = nd_cmd_dimm_desc(cmd);
case ND_CMD_ARS_START:
case ND_CMD_CLEAR_ERROR:
case ND_CMD_CALL:
- dev_dbg(&nvdimm_bus->dev, "'%s' command while read-only.\n",
+ dev_dbg(dev, "'%s' command while read-only.\n",
nvdimm ? nvdimm_cmd_name(cmd)
: nvdimm_bus_cmd_name(cmd));
return -EPERM;
}
/* process an input envelope */
+ in_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL);
+ if (!in_env)
+ return -ENOMEM;
for (i = 0; i < desc->in_num; i++) {
u32 in_size, copy;
if (in_size == UINT_MAX) {
dev_err(dev, "%s:%s unknown input size cmd: %s field: %d\n",
__func__, dimm_name, cmd_name, i);
- return -ENXIO;
+ rc = -ENXIO;
+ goto out;
}
- if (in_len < sizeof(in_env))
- copy = min_t(u32, sizeof(in_env) - in_len, in_size);
+ if (in_len < ND_CMD_MAX_ENVELOPE)
+ copy = min_t(u32, ND_CMD_MAX_ENVELOPE - in_len, in_size);
else
copy = 0;
- if (copy && copy_from_user(&in_env[in_len], p + in_len, copy))
- return -EFAULT;
+ if (copy && copy_from_user(&in_env[in_len], p + in_len, copy)) {
+ rc = -EFAULT;
+ goto out;
+ }
in_len += in_size;
}
}
/* process an output envelope */
+ out_env = kzalloc(ND_CMD_MAX_ENVELOPE, GFP_KERNEL);
+ if (!out_env) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
for (i = 0; i < desc->out_num; i++) {
u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i,
(u32 *) in_env, (u32 *) out_env, 0);
if (out_size == UINT_MAX) {
dev_dbg(dev, "%s unknown output size cmd: %s field: %d\n",
dimm_name, cmd_name, i);
- return -EFAULT;
+ rc = -EFAULT;
+ goto out;
}
- if (out_len < sizeof(out_env))
- copy = min_t(u32, sizeof(out_env) - out_len, out_size);
+ if (out_len < ND_CMD_MAX_ENVELOPE)
+ copy = min_t(u32, ND_CMD_MAX_ENVELOPE - out_len, out_size);
else
copy = 0;
if (copy && copy_from_user(&out_env[out_len],
- p + in_len + out_len, copy))
- return -EFAULT;
+ p + in_len + out_len, copy)) {
+ rc = -EFAULT;
+ goto out;
+ }
out_len += out_size;
}
if (buf_len > ND_IOCTL_MAX_BUFLEN) {
dev_dbg(dev, "%s cmd: %s buf_len: %llu > %d\n", dimm_name,
cmd_name, buf_len, ND_IOCTL_MAX_BUFLEN);
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
buf = vmalloc(buf_len);
- if (!buf)
- return -ENOMEM;
+ if (!buf) {
+ rc = -ENOMEM;
+ goto out;
+ }
if (copy_from_user(buf, p, buf_len)) {
rc = -EFAULT;
goto out;
}
- nvdimm_bus_lock(&nvdimm_bus->dev);
+ nd_device_lock(dev);
+ nvdimm_bus_lock(dev);
rc = nd_cmd_clear_to_send(nvdimm_bus, nvdimm, func, buf);
if (rc)
goto out_unlock;
nvdimm_account_cleared_poison(nvdimm_bus, clear_err->address,
clear_err->cleared);
}
- nvdimm_bus_unlock(&nvdimm_bus->dev);
if (copy_to_user(p, buf, buf_len))
rc = -EFAULT;
- vfree(buf);
- return rc;
-
- out_unlock:
- nvdimm_bus_unlock(&nvdimm_bus->dev);
- out:
+out_unlock:
+ nvdimm_bus_unlock(dev);
+ nd_device_unlock(dev);
+out:
+ kfree(in_env);
+ kfree(out_env);
vfree(buf);
return rc;
}
-static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
- long id = (long) file->private_data;
- int rc = -ENXIO, ro;
- struct nvdimm_bus *nvdimm_bus;
-
- ro = ((file->f_flags & O_ACCMODE) == O_RDONLY);
- mutex_lock(&nvdimm_bus_list_mutex);
- list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
- if (nvdimm_bus->id == id) {
- rc = __nd_ioctl(nvdimm_bus, NULL, ro, cmd, arg);
- break;
- }
- }
- mutex_unlock(&nvdimm_bus_list_mutex);
-
- return rc;
-}
+enum nd_ioctl_mode {
+ BUS_IOCTL,
+ DIMM_IOCTL,
+};
static int match_dimm(struct device *dev, void *data)
{
return 0;
}
-static long nvdimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static long nd_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
+ enum nd_ioctl_mode mode)
+
{
- int rc = -ENXIO, ro;
- struct nvdimm_bus *nvdimm_bus;
+ struct nvdimm_bus *nvdimm_bus, *found = NULL;
+ long id = (long) file->private_data;
+ struct nvdimm *nvdimm = NULL;
+ int rc, ro;
ro = ((file->f_flags & O_ACCMODE) == O_RDONLY);
mutex_lock(&nvdimm_bus_list_mutex);
list_for_each_entry(nvdimm_bus, &nvdimm_bus_list, list) {
- struct device *dev = device_find_child(&nvdimm_bus->dev,
- file->private_data, match_dimm);
- struct nvdimm *nvdimm;
-
- if (!dev)
- continue;
+ if (mode == DIMM_IOCTL) {
+ struct device *dev;
+
+ dev = device_find_child(&nvdimm_bus->dev,
+ file->private_data, match_dimm);
+ if (!dev)
+ continue;
+ nvdimm = to_nvdimm(dev);
+ found = nvdimm_bus;
+ } else if (nvdimm_bus->id == id) {
+ found = nvdimm_bus;
+ }
- nvdimm = to_nvdimm(dev);
- rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg);
- put_device(dev);
- break;
+ if (found) {
+ atomic_inc(&nvdimm_bus->ioctl_active);
+ break;
+ }
}
mutex_unlock(&nvdimm_bus_list_mutex);
+ if (!found)
+ return -ENXIO;
+
+ nvdimm_bus = found;
+ rc = __nd_ioctl(nvdimm_bus, nvdimm, ro, cmd, arg);
+
+ if (nvdimm)
+ put_device(&nvdimm->dev);
+ if (atomic_dec_and_test(&nvdimm_bus->ioctl_active))
+ wake_up(&nvdimm_bus->wait);
+
return rc;
}
+static long bus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return nd_ioctl(file, cmd, arg, BUS_IOCTL);
+}
+
+static long dimm_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ return nd_ioctl(file, cmd, arg, DIMM_IOCTL);
+}
+
static int nd_open(struct inode *inode, struct file *file)
{
long minor = iminor(inode);
static const struct file_operations nvdimm_bus_fops = {
.owner = THIS_MODULE,
.open = nd_open,
- .unlocked_ioctl = nd_ioctl,
- .compat_ioctl = nd_ioctl,
+ .unlocked_ioctl = bus_ioctl,
+ .compat_ioctl = bus_ioctl,
.llseek = noop_llseek,
};
static const struct file_operations nvdimm_fops = {
.owner = THIS_MODULE,
.open = nd_open,
- .unlocked_ioctl = nvdimm_ioctl,
- .compat_ioctl = nvdimm_ioctl,
+ .unlocked_ioctl = dimm_ioctl,
+ .compat_ioctl = dimm_ioctl,
.llseek = noop_llseek,
};
*
* Enforce that uuids can only be changed while the device is disabled
* (driver detached)
- * LOCKING: expects device_lock() is held on entry
+ * LOCKING: expects nd_device_lock() is held on entry
*/
int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
size_t len)
static int flush_namespaces(struct device *dev, void *data)
{
- device_lock(dev);
- device_unlock(dev);
+ nd_device_lock(dev);
+ nd_device_unlock(dev);
return 0;
}
static int flush_regions_dimms(struct device *dev, void *data)
{
- device_lock(dev);
- device_unlock(dev);
+ nd_device_lock(dev);
+ nd_device_unlock(dev);
device_for_each_child(dev, NULL, flush_namespaces);
return 0;
}
* done while probing is idle and the DIMM is not in active use
* in any region.
*/
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __security_store(dev, buf, len);
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
struct nd_region *nd_region = to_nd_region(dev->parent);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __alt_name_store(dev, buf, len);
rc = nd_namespace_label_update(nd_region, dev);
dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc);
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc < 0 ? rc : len;
}
if (rc)
return rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __size_store(dev, val);
dev_dbg(dev, "%llx %s (%d)\n", val, rc < 0 ? "fail" : "success", rc);
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc < 0 ? rc : len;
}
} else
return -ENXIO;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
if (to_ndns(dev)->claim)
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc < 0 ? rc : len;
}
} else
return -ENXIO;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
if (to_ndns(dev)->claim)
rc = -EBUSY;
dev_dbg(dev, "result: %zd %s: %s%s", rc, rc < 0 ? "tried" : "wrote",
buf, buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
struct nd_namespace_common *ndns = to_ndns(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
rc = sprintf(buf, "%s\n", ndns->claim ? dev_name(ndns->claim) : "");
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
struct nd_region *nd_region = to_nd_region(dev->parent);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __holder_class_store(dev, buf);
rc = nd_namespace_label_update(nd_region, dev);
dev_dbg(dev, "%s(%zd)\n", rc < 0 ? "fail " : "", rc);
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc < 0 ? rc : len;
}
struct nd_namespace_common *ndns = to_ndns(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (ndns->claim_class == NVDIMM_CCLASS_NONE)
rc = sprintf(buf, "\n");
else if ((ndns->claim_class == NVDIMM_CCLASS_BTT) ||
rc = sprintf(buf, "dax\n");
else
rc = sprintf(buf, "<unknown>\n");
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
char *mode;
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
claim = ndns->claim;
if (claim && is_nd_btt(claim))
mode = "safe";
else
mode = "raw";
rc = sprintf(buf, "%s\n", mode);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
* Flush any in-progess probes / removals in the driver
* for the raw personality of this namespace.
*/
- device_lock(&ndns->dev);
- device_unlock(&ndns->dev);
+ nd_device_lock(&ndns->dev);
+ nd_device_unlock(&ndns->dev);
if (ndns->dev.driver) {
dev_dbg(&ndns->dev, "is active, can't bind %s\n",
dev_name(dev));
#include <linux/sizes.h>
#include <linux/mutex.h>
#include <linux/nd.h>
+#include "nd.h"
extern struct list_head nvdimm_bus_list;
extern struct mutex nvdimm_bus_list_mutex;
struct nvdimm_bus {
struct nvdimm_bus_descriptor *nd_desc;
- wait_queue_head_t probe_wait;
+ wait_queue_head_t wait;
struct list_head list;
struct device dev;
int id, probe_active;
+ atomic_t ioctl_active;
struct list_head mapping_list;
struct mutex reconfig_mutex;
struct badrange badrange;
struct nd_namespace_common **_ndns, const char *buf,
size_t len);
struct nd_pfn *to_nd_pfn_safe(struct device *dev);
+bool is_nvdimm_bus(struct device *dev);
+
+#ifdef CONFIG_PROVE_LOCKING
+extern struct class *nd_class;
+
+enum {
+ LOCK_BUS,
+ LOCK_NDCTL,
+ LOCK_REGION,
+ LOCK_DIMM = LOCK_REGION,
+ LOCK_NAMESPACE,
+ LOCK_CLAIM,
+};
+
+static inline void debug_nvdimm_lock(struct device *dev)
+{
+ if (is_nd_region(dev))
+ mutex_lock_nested(&dev->lockdep_mutex, LOCK_REGION);
+ else if (is_nvdimm(dev))
+ mutex_lock_nested(&dev->lockdep_mutex, LOCK_DIMM);
+ else if (is_nd_btt(dev) || is_nd_pfn(dev) || is_nd_dax(dev))
+ mutex_lock_nested(&dev->lockdep_mutex, LOCK_CLAIM);
+ else if (dev->parent && (is_nd_region(dev->parent)))
+ mutex_lock_nested(&dev->lockdep_mutex, LOCK_NAMESPACE);
+ else if (is_nvdimm_bus(dev))
+ mutex_lock_nested(&dev->lockdep_mutex, LOCK_BUS);
+ else if (dev->class && dev->class == nd_class)
+ mutex_lock_nested(&dev->lockdep_mutex, LOCK_NDCTL);
+ else
+ dev_WARN(dev, "unknown lock level\n");
+}
+
+static inline void debug_nvdimm_unlock(struct device *dev)
+{
+ mutex_unlock(&dev->lockdep_mutex);
+}
+
+static inline void nd_device_lock(struct device *dev)
+{
+ device_lock(dev);
+ debug_nvdimm_lock(dev);
+}
+
+static inline void nd_device_unlock(struct device *dev)
+{
+ debug_nvdimm_unlock(dev);
+ device_unlock(dev);
+}
+#else
+static inline void nd_device_lock(struct device *dev)
+{
+ device_lock(dev);
+}
+
+static inline void nd_device_unlock(struct device *dev)
+{
+ device_unlock(dev);
+}
+
+static inline void debug_nvdimm_lock(struct device *dev)
+{
+}
+
+static inline void debug_nvdimm_unlock(struct device *dev)
+{
+}
+#endif
#endif /* __ND_CORE_H__ */
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc = 0;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
if (dev->driver)
rc = -EBUSY;
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_size_select_store(dev, buf, &nd_pfn->align,
nd_pfn_supported_alignments());
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
rc = nd_uuid_store(dev, &nd_pfn->uuid, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc ? rc : len;
}
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
/* no address to convey if the pfn instance is disabled */
rc = -ENXIO;
}
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
/* no size to convey if the pfn instance is disabled */
rc = -ENXIO;
}
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
resource_size_t start, size;
struct nd_region *nd_region;
unsigned long npfns, align;
+ u32 end_trunc;
struct nd_pfn_sb *pfn_sb;
phys_addr_t offset;
const char *sig;
size = resource_size(&nsio->res);
npfns = PHYS_PFN(size - SZ_8K);
align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT));
+ end_trunc = start + size - ALIGN_DOWN(start + size, align);
if (nd_pfn->mode == PFN_MODE_PMEM) {
/*
* The altmap should be padded out to the block size used
return -ENXIO;
}
- npfns = PHYS_PFN(size - offset);
+ npfns = PHYS_PFN(size - offset - end_trunc);
pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
pfn_sb->dataoff = cpu_to_le64(offset);
pfn_sb->npfns = cpu_to_le64(npfns);
memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
pfn_sb->version_major = cpu_to_le16(1);
pfn_sb->version_minor = cpu_to_le16(3);
+ pfn_sb->end_trunc = cpu_to_le32(end_trunc);
pfn_sb->align = cpu_to_le32(nd_pfn->align);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
nvdimm_namespace_detach_btt(to_nd_btt(dev));
else {
/*
- * Note, this assumes device_lock() context to not race
- * nd_pmem_notify()
+ * Note, this assumes nd_device_lock() context to not
+ * race nd_pmem_notify()
*/
sysfs_put(pmem->bb_state);
pmem->bb_state = NULL;
if (rc)
return rc;
- rc = nd_region_register_namespaces(nd_region, &err);
- if (rc < 0)
- return rc;
-
- ndrd = dev_get_drvdata(dev);
- ndrd->ns_active = rc;
- ndrd->ns_count = rc + err;
-
- if (rc && err && rc == err)
- return -ENODEV;
-
if (is_nd_pmem(&nd_region->dev)) {
struct resource ndr_res;
nvdimm_badblocks_populate(nd_region, &nd_region->bb, &ndr_res);
}
+ rc = nd_region_register_namespaces(nd_region, &err);
+ if (rc < 0)
+ return rc;
+
+ ndrd = dev_get_drvdata(dev);
+ ndrd->ns_active = rc;
+ ndrd->ns_count = rc + err;
+
+ if (rc && err && rc == err)
+ return -ENODEV;
+
nd_region->btt_seed = nd_btt_create(nd_region);
nd_region->pfn_seed = nd_pfn_create(nd_region);
nd_region->dax_seed = nd_dax_create(nd_region);
nvdimm_bus_unlock(dev);
/*
- * Note, this assumes device_lock() context to not race
+ * Note, this assumes nd_device_lock() context to not race
* nd_region_notify()
*/
sysfs_put(nd_region->bb_state);
* the v1.1 namespace label cookie definition. To read all this
* data we need to wait for probing to settle.
*/
- device_lock(dev);
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
if (nd_region->ndr_mappings) {
}
}
nvdimm_bus_unlock(dev);
- device_unlock(dev);
+ nd_device_unlock(dev);
if (rc)
return rc;
* memory nvdimm_bus_lock() is dropped, but that's userspace's
* problem to not race itself.
*/
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
available = nd_region_available_dpa(nd_region);
nvdimm_bus_unlock(dev);
+ nd_device_unlock(dev);
return sprintf(buf, "%llu\n", available);
}
struct nd_region *nd_region = to_nd_region(dev);
unsigned long long available = 0;
+ nd_device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
available = nd_region_allocatable_dpa(nd_region);
nvdimm_bus_unlock(dev);
+ nd_device_unlock(dev);
return sprintf(buf, "%llu\n", available);
}
struct nd_region *nd_region = to_nd_region(dev);
ssize_t rc;
- device_lock(dev);
+ nd_device_lock(dev);
if (dev->driver)
rc = badblocks_show(&nd_region->bb, buf, 0);
else
rc = -ENXIO;
- device_unlock(dev);
+ nd_device_unlock(dev);
return rc;
}
*/
if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
mutex_lock(&ctrl->scan_lock);
+ mutex_lock(&ctrl->subsys->lock);
+ nvme_mpath_start_freeze(ctrl->subsys);
+ nvme_mpath_wait_freeze(ctrl->subsys);
nvme_start_freeze(ctrl);
nvme_wait_freeze(ctrl);
}
nvme_update_formats(ctrl);
if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
nvme_unfreeze(ctrl);
+ nvme_mpath_unfreeze(ctrl->subsys);
+ mutex_unlock(&ctrl->subsys->lock);
mutex_unlock(&ctrl->scan_lock);
}
if (effects & NVME_CMD_EFFECTS_CCC)
if (ns->head->disk) {
nvme_update_disk_info(ns->head->disk, ns, id);
blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+ revalidate_disk(ns->head->disk);
}
#endif
}
.vid = 0x1179,
.mn = "THNSF5256GPUK TOSHIBA",
.quirks = NVME_QUIRK_NO_APST,
+ },
+ {
+ /*
+ * This LiteON CL1-3D*-Q11 firmware version has a race
+ * condition associated with actions related to suspend to idle
+ * LiteON has resolved the problem in future firmware
+ */
+ .vid = 0x14a4,
+ .fr = "22301111",
+ .quirks = NVME_QUIRK_SIMPLE_SUSPEND,
}
};
memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off);
}
-static void __nvme_release_subsystem(struct nvme_subsystem *subsys)
+static void nvme_release_subsystem(struct device *dev)
{
+ struct nvme_subsystem *subsys =
+ container_of(dev, struct nvme_subsystem, dev);
+
ida_simple_remove(&nvme_subsystems_ida, subsys->instance);
kfree(subsys);
}
-static void nvme_release_subsystem(struct device *dev)
-{
- __nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev));
-}
-
static void nvme_destroy_subsystem(struct kref *ref)
{
struct nvme_subsystem *subsys =
mutex_lock(&nvme_subsystems_lock);
found = __nvme_find_get_subsystem(subsys->subnqn);
if (found) {
- __nvme_release_subsystem(subsys);
+ put_device(&subsys->dev);
subsys = found;
if (!nvme_validate_cntlid(subsys, ctrl, id)) {
if (ret) {
dev_err(ctrl->device,
"failed to register subsystem device.\n");
+ put_device(&subsys->dev);
goto out_unlock;
}
ida_init(&subsys->ns_ida);
nvme_put_subsystem(subsys);
out_unlock:
mutex_unlock(&nvme_subsystems_lock);
- put_device(&subsys->dev);
return ret;
}
goto out_free;
}
+ if (!(ctrl->ops->flags & NVME_F_FABRICS))
+ ctrl->cntlid = le16_to_cpu(id->cntlid);
+
if (!ctrl->identified) {
int i;
goto out_free;
}
} else {
- ctrl->cntlid = le16_to_cpu(id->cntlid);
ctrl->hmpre = le32_to_cpu(id->hmpre);
ctrl->hmmin = le32_to_cpu(id->hmmin);
ctrl->hmminds = le32_to_cpu(id->hmminds);
struct nvme_ns *ns, *next;
LIST_HEAD(ns_list);
+ /*
+ * make sure to requeue I/O to all namespaces as these
+ * might result from the scan itself and must complete
+ * for the scan_work to make progress
+ */
+ nvme_mpath_clear_ctrl_paths(ctrl);
+
/* prevent racing with ns scanning */
flush_work(&ctrl->scan_work);
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");
-inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
{
- return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
+ struct nvme_ns_head *h;
+
+ lockdep_assert_held(&subsys->lock);
+ list_for_each_entry(h, &subsys->nsheads, entry)
+ if (h->disk)
+ blk_mq_unfreeze_queue(h->disk->queue);
+}
+
+void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
+{
+ struct nvme_ns_head *h;
+
+ lockdep_assert_held(&subsys->lock);
+ list_for_each_entry(h, &subsys->nsheads, entry)
+ if (h->disk)
+ blk_mq_freeze_queue_wait(h->disk->queue);
+}
+
+void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
+{
+ struct nvme_ns_head *h;
+
+ lockdep_assert_held(&subsys->lock);
+ list_for_each_entry(h, &subsys->nsheads, entry)
+ if (h->disk)
+ blk_freeze_queue_start(h->disk->queue);
}
/*
[NVME_ANA_CHANGE] = "change",
};
-void nvme_mpath_clear_current_path(struct nvme_ns *ns)
+bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
{
struct nvme_ns_head *head = ns->head;
+ bool changed = false;
int node;
if (!head)
- return;
+ goto out;
for_each_node(node) {
- if (ns == rcu_access_pointer(head->current_path[node]))
+ if (ns == rcu_access_pointer(head->current_path[node])) {
rcu_assign_pointer(head->current_path[node], NULL);
+ changed = true;
+ }
}
+out:
+ return changed;
+}
+
+void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
+{
+ struct nvme_ns *ns;
+
+ mutex_lock(&ctrl->scan_lock);
+ list_for_each_entry(ns, &ctrl->namespaces, list)
+ if (nvme_mpath_clear_current_path(ns))
+ kblockd_schedule_work(&ns->head->requeue_work);
+ mutex_unlock(&ctrl->scan_lock);
}
static bool nvme_path_is_disabled(struct nvme_ns *ns)
return ns;
}
+static bool nvme_available_path(struct nvme_ns_head *head)
+{
+ struct nvme_ns *ns;
+
+ list_for_each_entry_rcu(ns, &head->list, siblings) {
+ switch (ns->ctrl->state) {
+ case NVME_CTRL_LIVE:
+ case NVME_CTRL_RESETTING:
+ case NVME_CTRL_CONNECTING:
+ /* fallthru */
+ return true;
+ default:
+ break;
+ }
+ }
+ return false;
+}
+
static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
struct bio *bio)
{
disk_devt(ns->head->disk),
bio->bi_iter.bi_sector);
ret = direct_make_request(bio);
- } else if (!list_empty_careful(&head->list)) {
- dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");
+ } else if (nvme_available_path(head)) {
+ dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
spin_lock_irq(&head->requeue_lock);
bio_list_add(&head->requeue_list, bio);
spin_unlock_irq(&head->requeue_lock);
} else {
- dev_warn_ratelimited(dev, "no path - failing I/O\n");
+ dev_warn_ratelimited(dev, "no available path - failing I/O\n");
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
srcu_read_unlock(&head->srcu, srcu_idx);
}
+ synchronize_srcu(&ns->head->srcu);
kblockd_schedule_work(&ns->head->requeue_work);
}
{
int error;
- if (!nvme_ctrl_use_ana(ctrl))
+ /* check if multipath is enabled and we have the capability */
+ if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3)))
return 0;
ctrl->anacap = id->anacap;
* Broken Write Zeroes.
*/
NVME_QUIRK_DISABLE_WRITE_ZEROES = (1 << 9),
+
+ /*
+ * Force simple suspend/resume path.
+ */
+ NVME_QUIRK_SIMPLE_SUSPEND = (1 << 10),
};
/*
extern const struct block_device_operations nvme_ns_head_ops;
#ifdef CONFIG_NVME_MULTIPATH
-bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+ return ctrl->ana_log_buf != NULL;
+}
+
+void nvme_mpath_unfreeze(struct nvme_subsystem *subsys);
+void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
+void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
void nvme_mpath_stop(struct nvme_ctrl *ctrl);
-void nvme_mpath_clear_current_path(struct nvme_ns *ns);
+bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
+void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
{
}
-static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
+static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
+{
+ return false;
+}
+static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
}
static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
{
}
+static inline void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
+{
+}
+static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
+{
+}
+static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
+{
+}
#endif /* CONFIG_NVME_MULTIPATH */
#ifdef CONFIG_NVM
if (!dev->ctrl.tagset) {
dev->tagset.ops = &nvme_mq_ops;
dev->tagset.nr_hw_queues = dev->online_queues - 1;
- dev->tagset.nr_maps = 1; /* default */
- if (dev->io_queues[HCTX_TYPE_READ])
- dev->tagset.nr_maps++;
+ dev->tagset.nr_maps = 2; /* default + read */
if (dev->io_queues[HCTX_TYPE_POLL])
dev->tagset.nr_maps++;
dev->tagset.timeout = NVME_IO_TIMEOUT;
{
struct nvme_dev *dev = data;
- nvme_reset_ctrl_sync(&dev->ctrl);
+ flush_work(&dev->ctrl.reset_work);
flush_work(&dev->ctrl.scan_work);
nvme_put_ctrl(&dev->ctrl);
}
dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
+ nvme_reset_ctrl(&dev->ctrl);
nvme_get_ctrl(&dev->ctrl);
async_schedule(nvme_async_probe, dev);
struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
struct nvme_ctrl *ctrl = &ndev->ctrl;
- if (pm_resume_via_firmware() || !ctrl->npss ||
+ if (ndev->last_ps == U32_MAX ||
nvme_set_power_state(ctrl, ndev->last_ps) != 0)
nvme_reset_ctrl(ctrl);
return 0;
struct nvme_ctrl *ctrl = &ndev->ctrl;
int ret = -EBUSY;
+ ndev->last_ps = U32_MAX;
+
/*
* The platform does not remove power for a kernel managed suspend so
* use host managed nvme power settings for lowest idle power if
* shutdown. But if the firmware is involved after the suspend or the
* device does not support any non-default power states, shut down the
* device fully.
+ *
+ * If ASPM is not enabled for the device, shut down the device and allow
+ * the PCI bus layer to put it into D3 in order to take the PCIe link
+ * down, so as to allow the platform to achieve its minimum low-power
+ * state (which may not be possible if the link is up).
*/
- if (pm_suspend_via_firmware() || !ctrl->npss) {
+ if (pm_suspend_via_firmware() || !ctrl->npss ||
+ !pcie_aspm_enabled(pdev) ||
+ (ndev->ctrl.quirks & NVME_QUIRK_SIMPLE_SUSPEND)) {
nvme_dev_disable(ndev, true);
return 0;
}
ctrl->state != NVME_CTRL_ADMIN_ONLY)
goto unfreeze;
- ndev->last_ps = 0;
ret = nvme_get_power_state(ctrl, &ndev->last_ps);
if (ret < 0)
goto unfreeze;
.driver_data = NVME_QUIRK_LIGHTNVM, },
{ PCI_DEVICE(0x1d1d, 0x2601), /* CNEX Granby */
.driver_data = NVME_QUIRK_LIGHTNVM, },
+ { PCI_DEVICE(0x10ec, 0x5762), /* ADATA SX6000LNP */
+ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
return ret;
}
+static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
+{
+ rdma_disconnect(queue->cm_id);
+ ib_drain_qp(queue->qp);
+}
+
static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
{
if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags))
return;
-
- rdma_disconnect(queue->cm_id);
- ib_drain_qp(queue->qp);
+ __nvme_rdma_stop_queue(queue);
}
static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
else
ret = nvmf_connect_admin_queue(&ctrl->ctrl);
- if (!ret)
+ if (!ret) {
set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
- else
+ } else {
+ __nvme_rdma_stop_queue(queue);
dev_info(ctrl->ctrl.device,
"failed to connect queue: %d ret=%d\n", idx, ret);
+ }
return ret;
}
found:
list_del(&p->entry);
+ nvmet_port_del_ctrls(port, subsys);
nvmet_port_disc_changed(port, subsys);
if (list_empty(&port->subsystems))
u16 status;
switch (errno) {
+ case 0:
+ status = NVME_SC_SUCCESS;
+ break;
case -ENOSPC:
req->error_loc = offsetof(struct nvme_rw_command, length);
status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
}
EXPORT_SYMBOL_GPL(nvmet_unregister_transport);
+void nvmet_port_del_ctrls(struct nvmet_port *port, struct nvmet_subsys *subsys)
+{
+ struct nvmet_ctrl *ctrl;
+
+ mutex_lock(&subsys->lock);
+ list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+ if (ctrl->port == port)
+ ctrl->ops->delete_ctrl(ctrl);
+ }
+ mutex_unlock(&subsys->lock);
+}
+
int nvmet_enable_port(struct nvmet_port *port)
{
const struct nvmet_fabrics_ops *ops;
mutex_lock(&nvme_loop_ports_mutex);
list_del_init(&port->entry);
mutex_unlock(&nvme_loop_ports_mutex);
+
+ /*
+ * Ensure any ctrls that are in the process of being
+ * deleted are in fact deleted before we return
+ * and free the port. This is to prevent active
+ * ctrls from using a port after it's freed.
+ */
+ flush_workqueue(nvme_delete_wq);
}
static const struct nvmet_fabrics_ops nvme_loop_ops = {
int nvmet_register_transport(const struct nvmet_fabrics_ops *ops);
void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops);
+void nvmet_port_del_ctrls(struct nvmet_port *port,
+ struct nvmet_subsys *subsys);
+
int nvmet_enable_port(struct nvmet_port *port);
void nvmet_disable_port(struct nvmet_port *port);
if (!config->base_dev)
return -EINVAL;
- if (nvmem->read_only)
- nvmem->eeprom = bin_attr_ro_root_nvmem;
- else
- nvmem->eeprom = bin_attr_rw_root_nvmem;
+ if (nvmem->read_only) {
+ if (config->root_only)
+ nvmem->eeprom = bin_attr_ro_root_nvmem;
+ else
+ nvmem->eeprom = bin_attr_ro_nvmem;
+ } else {
+ if (config->root_only)
+ nvmem->eeprom = bin_attr_rw_root_nvmem;
+ else
+ nvmem->eeprom = bin_attr_rw_nvmem;
+ }
nvmem->eeprom.attr.name = "eeprom";
nvmem->eeprom.size = nvmem->size;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
* of_irq_parse_one - Resolve an interrupt for a device
* @device: the device whose interrupt is to be resolved
* @index: index of the interrupt to resolve
- * @out_irq: structure of_irq filled by this function
+ * @out_irq: structure of_phandle_args filled by this function
*
* This function resolves an interrupt for a node by walking the interrupt tree,
* finding which interrupt controller node it is attached to, and returning the
for_each_child_of_node(local_fixups, child) {
for_each_child_of_node(overlay, overlay_child)
- if (!node_name_cmp(child, overlay_child))
+ if (!node_name_cmp(child, overlay_child)) {
+ of_node_put(overlay_child);
break;
+ }
- if (!overlay_child)
+ if (!overlay_child) {
+ of_node_put(child);
return -EINVAL;
+ }
err = adjust_local_phandle_references(child, overlay_child,
phandle_delta);
- if (err)
+ if (err) {
+ of_node_put(child);
return err;
+ }
}
return 0;
if (state == PCI_D0) {
pci_platform_power_transition(dev, PCI_D0);
/*
- * Mandatory power management transition delays are
- * handled in the PCIe portdrv resume hooks.
+ * Mandatory power management transition delays, see
+ * PCI Express Base Specification Revision 2.0 Section
+ * 6.6.1: Conventional Reset. Do not delay for
+ * devices powered on/off by corresponding bridge,
+ * because have already delayed for the bridge.
*/
if (dev->runtime_d3cold) {
+ if (dev->d3cold_delay && !dev->imm_ready)
+ msleep(dev->d3cold_delay);
/*
* When powering on a bridge from D3cold, the
* whole hierarchy may be powered on into
return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS);
}
-
/**
- * pcie_wait_for_link_delay - Wait until link is active or inactive
+ * pcie_wait_for_link - Wait until link is active or inactive
* @pdev: Bridge device
* @active: waiting for active or inactive?
- * @delay: Delay to wait after link has become active (in ms)
*
* Use this to wait till link becomes active or inactive.
*/
-bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay)
+bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
{
int timeout = 1000;
bool ret;
timeout -= 10;
}
if (active && ret)
- msleep(delay);
+ msleep(100);
else if (ret != active)
pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n",
active ? "set" : "cleared");
return ret == active;
}
-/**
- * pcie_wait_for_link - Wait until link is active or inactive
- * @pdev: Bridge device
- * @active: waiting for active or inactive?
- *
- * Use this to wait till link becomes active or inactive.
- */
-bool pcie_wait_for_link(struct pci_dev *pdev, bool active)
-{
- return pcie_wait_for_link_delay(pdev, active, 100);
-}
-
void pci_reset_secondary_bus(struct pci_dev *dev)
{
u16 ctrl;
void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state,
u32 service);
-bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay);
bool pcie_wait_for_link(struct pci_dev *pdev, bool active);
#ifdef CONFIG_PCIEASPM
void pcie_aspm_init_link_state(struct pci_dev *pdev);
module_param_call(policy, pcie_aspm_set_policy, pcie_aspm_get_policy,
NULL, 0644);
+/**
+ * pcie_aspm_enabled - Check if PCIe ASPM has been enabled for a device.
+ * @pdev: Target device.
+ */
+bool pcie_aspm_enabled(struct pci_dev *pdev)
+{
+ struct pci_dev *bridge = pci_upstream_bridge(pdev);
+ bool ret;
+
+ if (!bridge)
+ return false;
+
+ mutex_lock(&aspm_lock);
+ ret = bridge->link_state ? !!bridge->link_state->aspm_enabled : false;
+ mutex_unlock(&aspm_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(pcie_aspm_enabled);
+
#ifdef CONFIG_PCIEASPM_DEBUG
static ssize_t link_state_show(struct device *dev,
struct device_attribute *attr,
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/kernel.h>
-#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/pm_runtime.h>
return 0;
}
-static int get_downstream_delay(struct pci_bus *bus)
-{
- struct pci_dev *pdev;
- int min_delay = 100;
- int max_delay = 0;
-
- list_for_each_entry(pdev, &bus->devices, bus_list) {
- if (!pdev->imm_ready)
- min_delay = 0;
- else if (pdev->d3cold_delay < min_delay)
- min_delay = pdev->d3cold_delay;
- if (pdev->d3cold_delay > max_delay)
- max_delay = pdev->d3cold_delay;
- }
-
- return max(min_delay, max_delay);
-}
-
-/*
- * wait_for_downstream_link - Wait for downstream link to establish
- * @pdev: PCIe port whose downstream link is waited
- *
- * Handle delays according to PCIe 4.0 section 6.6.1 before configuration
- * access to the downstream component is permitted.
- *
- * This blocks PCI core resume of the hierarchy below this port until the
- * link is trained. Should be called before resuming port services to
- * prevent pciehp from starting to tear-down the hierarchy too soon.
- */
-static void wait_for_downstream_link(struct pci_dev *pdev)
-{
- int delay;
-
- if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
- pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM)
- return;
-
- if (pci_dev_is_disconnected(pdev))
- return;
-
- if (!pdev->subordinate || list_empty(&pdev->subordinate->devices) ||
- !pdev->bridge_d3)
- return;
-
- delay = get_downstream_delay(pdev->subordinate);
- if (!delay)
- return;
-
- dev_dbg(&pdev->dev, "waiting downstream link for %d ms\n", delay);
-
- /*
- * If downstream port does not support speeds greater than 5 GT/s
- * need to wait 100ms. For higher speeds (gen3) we need to wait
- * first for the data link layer to become active.
- */
- if (pcie_get_speed_cap(pdev) <= PCIE_SPEED_5_0GT)
- msleep(delay);
- else
- pcie_wait_for_link_delay(pdev, true, delay);
-}
-
/**
* pcie_port_device_suspend - suspend port services associated with a PCIe port
* @dev: PCI Express port to handle
int pcie_port_device_resume_noirq(struct device *dev)
{
size_t off = offsetof(struct pcie_port_service_driver, resume_noirq);
-
- wait_for_downstream_link(to_pci_dev(dev));
return device_for_each_child(dev, &off, pm_iter);
}
int pcie_port_device_runtime_resume(struct device *dev)
{
size_t off = offsetof(struct pcie_port_service_driver, runtime_resume);
-
- wait_for_downstream_link(to_pci_dev(dev));
return device_for_each_child(dev, &off, pm_iter);
}
#endif /* PM */
*/
if (ioread32(map + 0x2240c) & 0x2) {
pci_info(pdev, FW_BUG "GPU left initialized by EFI, resetting\n");
- ret = pci_reset_function(pdev);
+ ret = pci_reset_bus(pdev);
if (ret < 0)
pci_err(pdev, "Failed to reset GPU: %d\n", ret);
}
switch (state->Vcc) {
case 50:
++v;
+ /* fall through */
case 33:
++v;
+ /* fall through */
case 0:
break;
default:
switch (state->Vpp) {
case 12:
++p;
+ /* fall through */
case 33:
case 50:
++p;
+ /* fall through */
case 0:
break;
default:
cpu_pm_pmu_setup(armpmu, cmd);
break;
case CPU_PM_EXIT:
- cpu_pm_pmu_setup(armpmu, cmd);
case CPU_PM_ENTER_FAILED:
+ cpu_pm_pmu_setup(armpmu, cmd);
armpmu->start(armpmu);
break;
default:
{ PIN_CONFIG_INPUT_DEBOUNCE, { C14, B14 }, SCUA8, 27 },
};
-static int aspeed_g4_sig_expr_set(const struct aspeed_pinmux_data *ctx,
+static int aspeed_g4_sig_expr_set(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr,
bool enable)
{
{ PIN_CONFIG_INPUT_DEBOUNCE, { A20, B19 }, SCUA8, 27 },
};
+static struct regmap *aspeed_g5_acquire_regmap(struct aspeed_pinmux_data *ctx,
+ int ip)
+{
+ if (ip == ASPEED_IP_SCU) {
+ WARN(!ctx->maps[ip], "Missing SCU syscon!");
+ return ctx->maps[ip];
+ }
+
+ if (ip >= ASPEED_NR_PINMUX_IPS)
+ return ERR_PTR(-EINVAL);
+
+ if (likely(ctx->maps[ip]))
+ return ctx->maps[ip];
+
+ if (ip == ASPEED_IP_GFX) {
+ struct device_node *node;
+ struct regmap *map;
+
+ node = of_parse_phandle(ctx->dev->of_node,
+ "aspeed,external-nodes", 0);
+ if (node) {
+ map = syscon_node_to_regmap(node);
+ of_node_put(node);
+ if (IS_ERR(map))
+ return map;
+ } else
+ return ERR_PTR(-ENODEV);
+
+ ctx->maps[ASPEED_IP_GFX] = map;
+ dev_dbg(ctx->dev, "Acquired GFX regmap");
+ return map;
+ }
+
+ if (ip == ASPEED_IP_LPC) {
+ struct device_node *node;
+ struct regmap *map;
+
+ node = of_parse_phandle(ctx->dev->of_node,
+ "aspeed,external-nodes", 1);
+ if (node) {
+ map = syscon_node_to_regmap(node->parent);
+ of_node_put(node);
+ if (IS_ERR(map))
+ return map;
+ } else
+ map = ERR_PTR(-ENODEV);
+
+ ctx->maps[ASPEED_IP_LPC] = map;
+ dev_dbg(ctx->dev, "Acquired LPC regmap");
+ return map;
+ }
+
+ return ERR_PTR(-EINVAL);
+}
+
/**
* Configure a pin's signal by applying an expression's descriptor state for
* all descriptors in the expression.
* Return: 0 if the expression is configured as requested and a negative error
* code otherwise
*/
-static int aspeed_g5_sig_expr_set(const struct aspeed_pinmux_data *ctx,
+static int aspeed_g5_sig_expr_set(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr,
bool enable)
{
const struct aspeed_sig_desc *desc = &expr->descs[i];
u32 pattern = enable ? desc->enable : desc->disable;
u32 val = (pattern << __ffs(desc->mask));
+ struct regmap *map;
- if (!ctx->maps[desc->ip])
- return -ENODEV;
+ map = aspeed_g5_acquire_regmap(ctx, desc->ip);
+ if (IS_ERR(map)) {
+ dev_err(ctx->dev,
+ "Failed to acquire regmap for IP block %d\n",
+ desc->ip);
+ return PTR_ERR(map);
+ }
/*
* Strap registers are configured in hardware or by early-boot
static int aspeed_g5_pinctrl_probe(struct platform_device *pdev)
{
int i;
- struct regmap *map;
- struct device_node *node;
for (i = 0; i < ARRAY_SIZE(aspeed_g5_pins); i++)
aspeed_g5_pins[i].number = i;
- node = of_parse_phandle(pdev->dev.of_node, "aspeed,external-nodes", 0);
- map = syscon_node_to_regmap(node);
- of_node_put(node);
- if (IS_ERR(map)) {
- dev_warn(&pdev->dev, "No GFX phandle found, some mux configurations may fail\n");
- map = NULL;
- }
- aspeed_g5_pinctrl_data.pinmux.maps[ASPEED_IP_GFX] = map;
-
- node = of_parse_phandle(pdev->dev.of_node, "aspeed,external-nodes", 1);
- if (node) {
- map = syscon_node_to_regmap(node->parent);
- if (IS_ERR(map)) {
- dev_warn(&pdev->dev, "LHC parent is not a syscon, some mux configurations may fail\n");
- map = NULL;
- }
- } else {
- dev_warn(&pdev->dev, "No LHC phandle found, some mux configurations may fail\n");
- map = NULL;
- }
- of_node_put(node);
- aspeed_g5_pinctrl_data.pinmux.maps[ASPEED_IP_LPC] = map;
+ aspeed_g5_pinctrl_data.pinmux.dev = &pdev->dev;
return aspeed_pinctrl_probe(pdev, &aspeed_g5_pinctrl_desc,
&aspeed_g5_pinctrl_data);
return 0;
}
-static int aspeed_sig_expr_enable(const struct aspeed_pinmux_data *ctx,
+static int aspeed_sig_expr_enable(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr)
{
int ret;
return 0;
}
-static int aspeed_sig_expr_disable(const struct aspeed_pinmux_data *ctx,
+static int aspeed_sig_expr_disable(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr)
{
int ret;
*
* Return: 0 if all expressions are disabled, otherwise a negative error code
*/
-static int aspeed_disable_sig(const struct aspeed_pinmux_data *ctx,
+static int aspeed_disable_sig(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr **exprs)
{
int ret = 0;
{
int i;
int ret;
- const struct aspeed_pinctrl_data *pdata =
- pinctrl_dev_get_drvdata(pctldev);
+ struct aspeed_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
const struct aspeed_pin_group *pgroup = &pdata->pinmux.groups[group];
const struct aspeed_pin_function *pfunc =
&pdata->pinmux.functions[function];
unsigned int offset)
{
int ret;
- const struct aspeed_pinctrl_data *pdata =
- pinctrl_dev_get_drvdata(pctldev);
+ struct aspeed_pinctrl_data *pdata = pinctrl_dev_get_drvdata(pctldev);
const struct aspeed_pin_desc *pdesc = pdata->pins[offset].drv_data;
const struct aspeed_sig_expr ***prios, **funcs, *expr;
#include "pinmux-aspeed.h"
-const char *const aspeed_pinmux_ips[] = {
+static const char *const aspeed_pinmux_ips[] = {
[ASPEED_IP_SCU] = "SCU",
[ASPEED_IP_GFX] = "GFX",
[ASPEED_IP_LPC] = "LPC",
struct aspeed_pinmux_data;
struct aspeed_pinmux_ops {
- int (*set)(const struct aspeed_pinmux_data *ctx,
+ int (*set)(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr, bool enabled);
};
struct aspeed_pinmux_data {
+ struct device *dev;
struct regmap *maps[ASPEED_NR_PINMUX_IPS];
const struct aspeed_pinmux_ops *ops;
const struct aspeed_sig_expr *expr,
bool enabled);
-static inline int aspeed_sig_expr_set(const struct aspeed_pinmux_data *ctx,
+static inline int aspeed_sig_expr_set(struct aspeed_pinmux_data *ctx,
const struct aspeed_sig_expr *expr,
bool enabled)
{
*/
static int __maybe_unused cros_ec_ishtp_suspend(struct device *device)
{
- struct ishtp_cl_device *cl_device = dev_get_drvdata(device);
+ struct ishtp_cl_device *cl_device = ishtp_dev_to_cl_device(device);
struct ishtp_cl *cros_ish_cl = ishtp_get_drvdata(cl_device);
struct ishtp_cl_data *client_data = ishtp_get_client_data(cros_ish_cl);
*/
static int __maybe_unused cros_ec_ishtp_resume(struct device *device)
{
- struct ishtp_cl_device *cl_device = dev_get_drvdata(device);
+ struct ishtp_cl_device *cl_device = ishtp_dev_to_cl_device(device);
struct ishtp_cl *cros_ish_cl = ishtp_get_drvdata(cl_device);
struct ishtp_cl_data *client_data = ishtp_get_client_data(cros_ish_cl);
};
MODULE_DEVICE_TABLE(of, olpc_xo175_ec_of_match);
+static const struct spi_device_id olpc_xo175_ec_id_table[] = {
+ { "xo1.75-ec", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(spi, olpc_xo175_ec_id_table);
+
static struct spi_driver olpc_xo175_ec_spi_driver = {
.driver = {
.name = "olpc-xo175-ec",
INTEL_CPU_FAM6(KABYLAKE_DESKTOP, spt_reg_map),
INTEL_CPU_FAM6(CANNONLAKE_MOBILE, cnp_reg_map),
INTEL_CPU_FAM6(ICELAKE_MOBILE, icl_reg_map),
+ INTEL_CPU_FAM6(ICELAKE_NNPI, icl_reg_map),
{}
};
static struct gpio_keys_button apu2_keys_buttons[] = {
{
- .code = KEY_SETUP,
+ .code = KEY_RESTART,
.active_low = 1,
.desc = "front button",
.type = EV_KEY,
MODULE_LICENSE("GPL");
MODULE_DEVICE_TABLE(dmi, apu_gpio_dmi_table);
MODULE_ALIAS("platform:pcengines-apuv2");
-MODULE_SOFTDEP("pre: platform:" AMD_FCH_GPIO_DRIVER_NAME);
-MODULE_SOFTDEP("pre: platform:leds-gpio");
-MODULE_SOFTDEP("pre: platform:gpio_keys_polled");
+MODULE_SOFTDEP("pre: platform:" AMD_FCH_GPIO_DRIVER_NAME " platform:leds-gpio platform:gpio_keys_polled");
USB_CH_IP_CUR_LVL_1P5;
break;
}
+ /* Else, fall through */
case USB_STAT_HM_IDGND:
dev_err(di->dev, "USB Type - Charging not allowed\n");
di->max_usb_in_curr.usb_type_max = USB_CH_IP_CUR_LVL_0P05;
unregister_pm_notifier(&rapl_pm_notifier);
}
-module_init(rapl_init);
+fs_initcall(rapl_init);
module_exit(rapl_exit);
MODULE_DESCRIPTION("Intel Runtime Average Power Limit (RAPL) common code");
return class_register(&powercap_class);
}
-device_initcall(powercap_init);
+fs_initcall(powercap_init);
MODULE_DESCRIPTION("PowerCap sysfs Driver");
MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
return of_pwm_get(dev, dev->of_node, con_id);
/* then lookup via ACPI */
- if (dev && is_acpi_node(dev->fwnode))
- return acpi_pwm_get(dev->fwnode);
+ if (dev && is_acpi_node(dev->fwnode)) {
+ pwm = acpi_pwm_get(dev->fwnode);
+ if (!IS_ERR(pwm) || PTR_ERR(pwm) != -ENOENT)
+ return pwm;
+ }
/*
* We look up the provider in the static table typically provided by
#define AXP803_DCDC5_1140mV_STEPS 35
#define AXP803_DCDC5_1140mV_END \
(AXP803_DCDC5_1140mV_START + AXP803_DCDC5_1140mV_STEPS)
-#define AXP803_DCDC5_NUM_VOLTAGES 68
+#define AXP803_DCDC5_NUM_VOLTAGES 69
#define AXP803_DCDC6_600mV_START 0x00
#define AXP803_DCDC6_600mV_STEPS 50
#define AXP803_DCDC6_600mV_END \
(AXP803_DCDC6_600mV_START + AXP803_DCDC6_600mV_STEPS)
#define AXP803_DCDC6_1120mV_START 0x33
-#define AXP803_DCDC6_1120mV_STEPS 14
+#define AXP803_DCDC6_1120mV_STEPS 20
#define AXP803_DCDC6_1120mV_END \
(AXP803_DCDC6_1120mV_START + AXP803_DCDC6_1120mV_STEPS)
#define AXP803_DCDC6_NUM_VOLTAGES 72
#define AXP806_DCDCA_600mV_END \
(AXP806_DCDCA_600mV_START + AXP806_DCDCA_600mV_STEPS)
#define AXP806_DCDCA_1120mV_START 0x33
-#define AXP806_DCDCA_1120mV_STEPS 14
+#define AXP806_DCDCA_1120mV_STEPS 20
#define AXP806_DCDCA_1120mV_END \
(AXP806_DCDCA_1120mV_START + AXP806_DCDCA_1120mV_STEPS)
#define AXP806_DCDCA_NUM_VOLTAGES 72
AXP806_DCDCD_600mV_END,
20000),
REGULATOR_LINEAR_RANGE(1600000,
- AXP806_DCDCD_600mV_START,
- AXP806_DCDCD_600mV_END,
+ AXP806_DCDCD_1600mV_START,
+ AXP806_DCDCD_1600mV_END,
100000),
};
struct lp87565 *lp87565 = dev_get_drvdata(pdev->dev.parent);
struct regulator_config config = { };
struct regulator_dev *rdev;
- int i, min_idx = LP87565_BUCK_0, max_idx = LP87565_BUCK_3;
+ int i, min_idx, max_idx;
platform_set_drvdata(pdev, lp87565);
max_idx = LP87565_BUCK_3210;
break;
default:
- dev_err(lp87565->dev, "Invalid lp config %d\n",
- lp87565->dev_type);
- return -EINVAL;
+ min_idx = LP87565_BUCK_0;
+ max_idx = LP87565_BUCK_3;
+ break;
}
for (i = min_idx; i <= max_idx; i++) {
if (!name)
name = child->name;
- if (!strcmp(desc->of_match, name))
+ if (!strcmp(desc->of_match, name)) {
+ of_node_put(search);
return of_node_get(child);
+ }
}
of_node_put(search);
char msg_format;
char msg_no;
+ /*
+ * intrc values ENODEV, ENOLINK and EPERM
+ * will be optained from sleep_on to indicate that no
+ * IO operation can be started
+ */
+ if (cqr->intrc == -ENODEV)
+ return 1;
+
+ if (cqr->intrc == -ENOLINK)
+ return 1;
+
+ if (cqr->intrc == -EPERM)
+ return 1;
+
sense = dasd_get_sense(&cqr->irb);
if (!sense)
return 0;
lcu->flags &= ~NEED_UAC_UPDATE;
spin_unlock_irqrestore(&lcu->lock, flags);
- do {
- rc = dasd_sleep_on(cqr);
- if (rc && suborder_not_supported(cqr))
- return -EOPNOTSUPP;
- } while (rc && (cqr->retries > 0));
- if (rc) {
+ rc = dasd_sleep_on(cqr);
+ if (rc && !suborder_not_supported(cqr)) {
spin_lock_irqsave(&lcu->lock, flags);
lcu->flags |= NEED_UAC_UPDATE;
spin_unlock_irqrestore(&lcu->lock, flags);
}
if (dstat == 0x08)
break;
+ /* else, fall through */
case 0x04:
/* Device end interrupt. */
if ((raw = req->info) == NULL)
switch (device->tape_state) {
case TS_INIT:
tape_state_set(device, TS_NOT_OPER);
+ /* fallthrough */
case TS_NOT_OPER:
/*
* Nothing to do.
break;
if (device->tape_state == TS_UNUSED)
break;
+ /* fallthrough */
default:
if (device->tape_state == TS_BLKUSE)
break;
case -ETIMEDOUT:
DBF_LH(1, "(%08x): Request timed out\n",
device->cdev_id);
+ /* fallthrough */
case -EIO:
__tape_end_request(device, request, -EIO);
break;
int retries = 0, cc;
unsigned long laob = 0;
- WARN_ON_ONCE(aob && ((queue_type(q) != QDIO_IQDIO_QFMT) ||
- !q->u.out.use_cq));
- if (q->u.out.use_cq && aob != 0) {
+ if (aob) {
fc = QDIO_SIGA_WRITEQ;
laob = aob;
}
{
unsigned long phys_aob = 0;
- if (!q->use_cq)
- return 0;
-
if (!q->aobs[bufnr]) {
struct qaob *aob = qdio_allocate_aob();
q->aobs[bufnr] = aob;
for_each_output_queue(irq_ptr, q, i) {
if (use_cq) {
+ if (multicast_outbound(q))
+ continue;
if (qdio_enable_async_operation(&q->u.out) < 0) {
use_cq = 0;
continue;
/* One SIGA-W per buffer required for unicast HSI */
WARN_ON_ONCE(count > 1 && !multicast_outbound(q));
- phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr);
+ if (q->u.out.use_cq)
+ phys_aob = qdio_aob_for_buffer(&q->u.out, bufnr);
rc = qdio_kick_outbound_q(q, phys_aob);
} else if (need_siga_sync(q)) {
rc = qdio_siga_sync_q(q);
+ } else if (count < QDIO_MAX_BUFFERS_PER_Q &&
+ get_buf_state(q, prev_buf(bufnr), &state, 0) > 0 &&
+ state == SLSB_CU_OUTPUT_PRIMED) {
+ /* The previous buffer is not processed yet, tack on. */
+ qperf_inc(q, fast_requeue);
} else {
- /* try to fast requeue buffers */
- get_buf_state(q, prev_buf(bufnr), &state, 0);
- if (state != SLSB_CU_OUTPUT_PRIMED)
- rc = qdio_kick_outbound_q(q, 0);
- else
- qperf_inc(q, fast_requeue);
+ rc = qdio_kick_outbound_q(q, 0);
}
/* in case of SIGA errors we must process the error immediately */
}
-const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
+static const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
.read = vfio_ccw_async_region_read,
.write = vfio_ccw_async_region_write,
.release = vfio_ccw_async_region_release,
sizeof(*pa->pa_iova_pfn) +
sizeof(*pa->pa_pfn),
GFP_KERNEL);
- if (unlikely(!pa->pa_iova_pfn))
+ if (unlikely(!pa->pa_iova_pfn)) {
+ pa->pa_nr = 0;
return -ENOMEM;
+ }
pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
{
struct ccwchain *chain;
- int len;
+ int len, ret;
/* Copy 2K (the most we support today) of possible CCWs */
len = copy_from_iova(cp->mdev, cp->guest_cp, cda,
memcpy(chain->ch_ccw, cp->guest_cp, len * sizeof(struct ccw1));
/* Loop for tics on this new chain. */
- return ccwchain_loop_tic(chain, cp);
+ ret = ccwchain_loop_tic(chain, cp);
+
+ if (ret)
+ ccwchain_free(chain);
+
+ return ret;
}
/* Loop for TICs. */
/* Build a ccwchain for the first CCW segment */
ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
- if (ret)
- cp_free(cp);
-
- /* It is safe to force: if not set but idals used
- * ccwchain_calc_length returns an error.
- */
- cp->orb.cmd.c64 = 1;
- if (!ret)
+ if (!ret) {
cp->initialized = true;
+ /* It is safe to force: if it was not set but idals used
+ * ccwchain_calc_length would have returned an error.
+ */
+ cp->orb.cmd.c64 = 1;
+ }
+
return ret;
}
(SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
if (scsw_is_solicited(&irb->scsw)) {
cp_update_scsw(&private->cp, &irb->scsw);
- if (is_final)
+ if (is_final && private->state == VFIO_CCW_STATE_CP_PENDING)
cp_free(&private->cp);
}
mutex_lock(&private->io_mutex);
ap_msg->receive(aq, ap_msg, aq->reply);
break;
}
+ /* fall through */
case AP_RESPONSE_NO_PENDING_REPLY:
if (!status.queue_empty || aq->queue_count <= 0)
break;
if (msg->cprbx.cprb_ver_id == 0x02)
return convert_type86_ica(zq, reply,
outputdata, outputdatalength);
- /*
- * Fall through, no break, incorrect cprb version is an unknown
- * response
- */
+ /* fall through - wrong cprb version is an unknown response */
default: /* Unknown response type, this should NEVER EVER happen */
zq->online = 0;
pr_err("Cryptographic device %02x.%04x failed and was set offline\n",
}
if (msg->cprbx.cprb_ver_id == 0x02)
return convert_type86_xcrb(zq, reply, xcRB);
- /*
- * Fall through, no break, incorrect cprb version is an unknown
- * response
- */
+ /* fall through - wrong cprb version is an unknown response */
default: /* Unknown response type, this should NEVER EVER happen */
xcRB->status = 0x0008044DL; /* HDD_InvalidParm */
zq->online = 0;
return convert_error(zq, reply);
if (msg->cprbx.cprb_ver_id == 0x04)
return convert_type86_ep11_xcrb(zq, reply, xcRB);
- /* Fall through, no break, incorrect cprb version is an unknown resp.*/
+ /* fall through - wrong cprb version is an unknown resp */
default: /* Unknown response type, this should NEVER EVER happen */
zq->online = 0;
pr_err("Cryptographic device %02x.%04x failed and was set offline\n",
return -EINVAL;
if (msg->cprbx.cprb_ver_id == 0x02)
return convert_type86_rng(zq, reply, data);
- /*
- * Fall through, no break, incorrect cprb version is an unknown
- * response
- */
+ /* fall through - wrong cprb version is an unknown response */
default: /* Unknown response type, this should NEVER EVER happen */
zq->online = 0;
pr_err("Cryptographic device %02x.%04x failed and was set offline\n",
grp->changed_side = 2;
break;
}
+ /* Else, fall through */
case MPCG_STATE_XID0IOWAIX:
case MPCG_STATE_XID7INITW:
case MPCG_STATE_XID7INITX:
/*fsm_newstate(grp->fsm, MPCG_STATE_XID2INITW);*/
if (callback)
grp->send_qllc_disc = 1;
+ /* Else, fall through */
case MPCG_STATE_XID0IOWAIT:
fsm_deltimer(&grp->timer);
grp->outstanding_xid2 = 0;
if ((fsm_getstate(rch->fsm) == CH_XID0_PENDING) &&
(fsm_getstate(wch->fsm) == CH_XID0_PENDING))
break;
+ /* Else, fall through */
default:
fsm_event(grp->fsm, MPCG_EVENT_INOP, dev);
}
grp->estconnfunc = NULL;
break;
}
+ /* Else, fall through */
case MPCG_STATE_FLOWC:
case MPCG_STATE_READY:
grp->send_qllc_disc = 2;
struct qeth_reply {
struct list_head list;
struct completion received;
+ spinlock_t lock;
int (*callback)(struct qeth_card *, struct qeth_reply *,
unsigned long);
u32 seqno;
if (reply) {
refcount_set(&reply->refcnt, 1);
init_completion(&reply->received);
+ spin_lock_init(&reply->lock);
}
return reply;
}
if (!reply->callback) {
rc = 0;
+ goto no_callback;
+ }
+
+ spin_lock_irqsave(&reply->lock, flags);
+ if (reply->rc) {
+ /* Bail out when the requestor has already left: */
+ rc = reply->rc;
} else {
if (cmd) {
reply->offset = (u16)((char *)cmd - (char *)iob->data);
rc = reply->callback(card, reply, (unsigned long)iob);
}
}
+ spin_unlock_irqrestore(&reply->lock, flags);
+no_callback:
if (rc <= 0)
qeth_notify_reply(reply, rc);
qeth_put_reply(reply);
rc = (timeout == -ERESTARTSYS) ? -EINTR : -ETIME;
qeth_dequeue_reply(card, reply);
+
+ if (reply_cb) {
+ /* Wait until the callback for a late reply has completed: */
+ spin_lock_irq(&reply->lock);
+ if (rc)
+ /* Zap any callback that's still pending: */
+ reply->rc = rc;
+ spin_unlock_irq(&reply->lock);
+ }
+
if (!rc)
rc = reply->rc;
qeth_put_reply(reply);
get_user(req_len, &ureq->hdr.req_len))
return -EFAULT;
+ /* Sanitize user input, to avoid overflows in iob size calculation: */
+ if (req_len > QETH_BUFSIZE)
+ return -EINVAL;
+
iob = qeth_get_adapter_cmd(card, IPA_SETADP_SET_SNMP_CONTROL, req_len);
if (!iob)
return -ENOMEM;
card->osn_info.data_cb(skb);
break;
}
- /* else unknown */
+ /* Else, fall through */
default:
dev_kfree_skb_any(skb);
QETH_CARD_TEXT(card, 3, "inbunkno");
struct airq_iv *aiv;
};
static struct airq_info *airq_areas[MAX_AIRQ_AREAS];
+static DEFINE_MUTEX(airq_areas_lock);
+
static u8 *summary_indicators;
static inline u8 *get_summary_indicator(struct airq_info *info)
unsigned long bit, flags;
for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) {
+ mutex_lock(&airq_areas_lock);
if (!airq_areas[i])
airq_areas[i] = new_airq_info(i);
info = airq_areas[i];
+ mutex_unlock(&airq_areas_lock);
if (!info)
return 0;
write_lock_irqsave(&info->lock, flags);
source "drivers/scsi/csiostor/Kconfig"
-endif # SCSI_LOWLEVEL
-
source "drivers/scsi/pcmcia/Kconfig"
+endif # SCSI_LOWLEVEL
+
source "drivers/scsi/device_handler/Kconfig"
endmenu
msgqueue_flush(&info->scsi.msgs);
msgqueue_addmsg(&info->scsi.msgs, 1, MESSAGE_REJECT);
info->scsi.phase = PHASE_MSGOUT_EXPECT;
+ /* fall through */
case async:
dev->period = info->ifcfg.asyncperiod / 4;
fas216_done(info, DID_ABORT);
break;
}
+ /* else, fall through */
default: /* huh? */
printk(KERN_ERR "scsi%d.%c: unexpected disconnect in phase %s\n",
case STATE(STAT_STATUS, PHASE_DATAOUT): /* Data Out -> Status */
case STATE(STAT_STATUS, PHASE_DATAIN): /* Data In -> Status */
fas216_stoptransfer(info);
+ /* fall through */
+
case STATE(STAT_STATUS, PHASE_SELSTEPS):/* Sel w/ steps -> Status */
case STATE(STAT_STATUS, PHASE_MSGOUT): /* Message Out -> Status */
case STATE(STAT_STATUS, PHASE_COMMAND): /* Command -> Status */
case STATE(STAT_MESGIN, PHASE_DATAOUT): /* Data Out -> Message In */
case STATE(STAT_MESGIN, PHASE_DATAIN): /* Data In -> Message In */
fas216_stoptransfer(info);
+ /* fall through */
+
case STATE(STAT_MESGIN, PHASE_COMMAND): /* Command -> Message In */
case STATE(STAT_MESGIN, PHASE_SELSTEPS):/* Sel w/ steps -> Message In */
case STATE(STAT_MESGIN, PHASE_MSGOUT): /* Message Out -> Message In */
fas216_message(info);
break;
}
+ /* else, fall through */
default:
fas216_log(info, 0, "internal phase %s for function done?"
switch (where_from) {
case TYPE_QUEUE:
fas216_allocate_tag(info, SCpnt);
+ /* fall through */
case TYPE_OTHER:
fas216_start_command(info, SCpnt);
break;
#define ALUA_FAILOVER_TIMEOUT 60
#define ALUA_FAILOVER_RETRIES 5
#define ALUA_RTPG_DELAY_MSECS 5
+#define ALUA_RTPG_RETRY_DELAY 2
/* device handler flags */
#define ALUA_OPTIMIZE_STPG 0x01
case SCSI_ACCESS_STATE_TRANSITIONING:
if (time_before(jiffies, pg->expiry)) {
/* State transition, retry */
- pg->interval = 2;
+ pg->interval = ALUA_RTPG_RETRY_DELAY;
err = SCSI_DH_RETRY;
} else {
struct alua_dh_data *h;
spin_lock_irqsave(&pg->lock, flags);
pg->flags &= ~ALUA_PG_RUNNING;
pg->flags |= ALUA_PG_RUN_RTPG;
+ if (!pg->interval)
+ pg->interval = ALUA_RTPG_RETRY_DELAY;
spin_unlock_irqrestore(&pg->lock, flags);
queue_delayed_work(kaluad_wq, &pg->rtpg_work,
pg->interval * HZ);
spin_lock_irqsave(&pg->lock, flags);
if (err == SCSI_DH_RETRY || pg->flags & ALUA_PG_RUN_RTPG) {
pg->flags &= ~ALUA_PG_RUNNING;
+ if (!pg->interval && !(pg->flags & ALUA_PG_RUN_RTPG))
+ pg->interval = ALUA_RTPG_RETRY_DELAY;
pg->flags |= ALUA_PG_RUN_RTPG;
spin_unlock_irqrestore(&pg->lock, flags);
queue_delayed_work(kaluad_wq, &pg->rtpg_work,
{
struct fcoe_fcf *fcf;
struct fcoe_fcf new;
- unsigned long sol_tov = msecs_to_jiffies(FCOE_CTRL_SOL_TOV);
+ unsigned long sol_tov = msecs_to_jiffies(FCOE_CTLR_SOL_TOV);
int first = 0;
int mtu_valid;
int found = 0;
*/
static inline struct fcoe_rport *fcoe_ctlr_rport(struct fc_rport_priv *rdata)
{
- return (struct fcoe_rport *)(rdata + 1);
+ return container_of(rdata, struct fcoe_rport, rdata);
}
/**
*/
static int fcoe_ctlr_vn_parse(struct fcoe_ctlr *fip,
struct sk_buff *skb,
- struct fc_rport_priv *rdata)
+ struct fcoe_rport *frport)
{
struct fip_header *fiph;
struct fip_desc *desc = NULL;
struct fip_wwn_desc *wwn = NULL;
struct fip_vn_desc *vn = NULL;
struct fip_size_desc *size = NULL;
- struct fcoe_rport *frport;
size_t rlen;
size_t dlen;
u32 desc_mask = 0;
u32 dtype;
u8 sub;
- memset(rdata, 0, sizeof(*rdata) + sizeof(*frport));
- frport = fcoe_ctlr_rport(rdata);
-
fiph = (struct fip_header *)skb->data;
frport->flags = ntohs(fiph->fip_flags);
if (dlen != sizeof(struct fip_wwn_desc))
goto len_err;
wwn = (struct fip_wwn_desc *)desc;
- rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn);
+ frport->rdata.ids.node_name =
+ get_unaligned_be64(&wwn->fd_wwn);
break;
case FIP_DT_VN_ID:
if (dlen != sizeof(struct fip_vn_desc))
goto len_err;
vn = (struct fip_vn_desc *)desc;
memcpy(frport->vn_mac, vn->fd_mac, ETH_ALEN);
- rdata->ids.port_id = ntoh24(vn->fd_fc_id);
- rdata->ids.port_name = get_unaligned_be64(&vn->fd_wwpn);
+ frport->rdata.ids.port_id = ntoh24(vn->fd_fc_id);
+ frport->rdata.ids.port_name =
+ get_unaligned_be64(&vn->fd_wwpn);
break;
case FIP_DT_FC4F:
if (dlen != sizeof(struct fip_fc4_feat))
/**
* fcoe_ctlr_vn_probe_req() - handle incoming VN2VN probe request.
* @fip: The FCoE controller
- * @rdata: parsed remote port with frport from the probe request
+ * @frport: parsed FCoE rport from the probe request
*
* Called with ctlr_mutex held.
*/
static void fcoe_ctlr_vn_probe_req(struct fcoe_ctlr *fip,
- struct fc_rport_priv *rdata)
+ struct fcoe_rport *frport)
{
- struct fcoe_rport *frport = fcoe_ctlr_rport(rdata);
-
- if (rdata->ids.port_id != fip->port_id)
+ if (frport->rdata.ids.port_id != fip->port_id)
return;
switch (fip->state) {
* Probe's REC bit is not set.
* If we don't reply, we will change our address.
*/
- if (fip->lp->wwpn > rdata->ids.port_name &&
+ if (fip->lp->wwpn > frport->rdata.ids.port_name &&
!(frport->flags & FIP_FL_REC_OR_P2P)) {
LIBFCOE_FIP_DBG(fip, "vn_probe_req: "
"port_id collision\n");
/**
* fcoe_ctlr_vn_probe_reply() - handle incoming VN2VN probe reply.
* @fip: The FCoE controller
- * @rdata: parsed remote port with frport from the probe request
+ * @frport: parsed FCoE rport from the probe request
*
* Called with ctlr_mutex held.
*/
static void fcoe_ctlr_vn_probe_reply(struct fcoe_ctlr *fip,
- struct fc_rport_priv *rdata)
+ struct fcoe_rport *frport)
{
- if (rdata->ids.port_id != fip->port_id)
+ if (frport->rdata.ids.port_id != fip->port_id)
return;
switch (fip->state) {
case FIP_ST_VNMP_START:
/**
* fcoe_ctlr_vn_add() - Add a VN2VN entry to the list, based on a claim reply.
* @fip: The FCoE controller
- * @new: newly-parsed remote port with frport as a template for new rdata
+ * @new: newly-parsed FCoE rport as a template for new rdata
*
* Called with ctlr_mutex held.
*/
-static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fc_rport_priv *new)
+static void fcoe_ctlr_vn_add(struct fcoe_ctlr *fip, struct fcoe_rport *new)
{
struct fc_lport *lport = fip->lp;
struct fc_rport_priv *rdata;
struct fcoe_rport *frport;
u32 port_id;
- port_id = new->ids.port_id;
+ port_id = new->rdata.ids.port_id;
if (port_id == fip->port_id)
return;
rdata->disc_id = lport->disc.disc_id;
ids = &rdata->ids;
- if ((ids->port_name != -1 && ids->port_name != new->ids.port_name) ||
- (ids->node_name != -1 && ids->node_name != new->ids.node_name)) {
+ if ((ids->port_name != -1 &&
+ ids->port_name != new->rdata.ids.port_name) ||
+ (ids->node_name != -1 &&
+ ids->node_name != new->rdata.ids.node_name)) {
mutex_unlock(&rdata->rp_mutex);
LIBFCOE_FIP_DBG(fip, "vn_add rport logoff %6.6x\n", port_id);
fc_rport_logoff(rdata);
mutex_lock(&rdata->rp_mutex);
}
- ids->port_name = new->ids.port_name;
- ids->node_name = new->ids.node_name;
+ ids->port_name = new->rdata.ids.port_name;
+ ids->node_name = new->rdata.ids.node_name;
mutex_unlock(&rdata->rp_mutex);
frport = fcoe_ctlr_rport(rdata);
LIBFCOE_FIP_DBG(fip, "vn_add rport %6.6x %s state %d\n",
port_id, frport->fcoe_len ? "old" : "new",
rdata->rp_state);
- *frport = *fcoe_ctlr_rport(new);
+ frport->fcoe_len = new->fcoe_len;
+ frport->flags = new->flags;
+ frport->login_count = new->login_count;
+ memcpy(frport->enode_mac, new->enode_mac, ETH_ALEN);
+ memcpy(frport->vn_mac, new->vn_mac, ETH_ALEN);
frport->time = 0;
}
/**
* fcoe_ctlr_vn_claim_notify() - handle received FIP VN2VN Claim Notification
* @fip: The FCoE controller
- * @new: newly-parsed remote port with frport as a template for new rdata
+ * @new: newly-parsed FCoE rport as a template for new rdata
*
* Called with ctlr_mutex held.
*/
static void fcoe_ctlr_vn_claim_notify(struct fcoe_ctlr *fip,
- struct fc_rport_priv *new)
+ struct fcoe_rport *new)
{
- struct fcoe_rport *frport = fcoe_ctlr_rport(new);
-
- if (frport->flags & FIP_FL_REC_OR_P2P) {
+ if (new->flags & FIP_FL_REC_OR_P2P) {
LIBFCOE_FIP_DBG(fip, "send probe req for P2P/REC\n");
fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0);
return;
case FIP_ST_VNMP_START:
case FIP_ST_VNMP_PROBE1:
case FIP_ST_VNMP_PROBE2:
- if (new->ids.port_id == fip->port_id) {
+ if (new->rdata.ids.port_id == fip->port_id) {
LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
"restart, state %d\n",
fip->state);
break;
case FIP_ST_VNMP_CLAIM:
case FIP_ST_VNMP_UP:
- if (new->ids.port_id == fip->port_id) {
- if (new->ids.port_name > fip->lp->wwpn) {
+ if (new->rdata.ids.port_id == fip->port_id) {
+ if (new->rdata.ids.port_name > fip->lp->wwpn) {
LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
"restart, port_id collision\n");
fcoe_ctlr_vn_restart(fip);
break;
}
LIBFCOE_FIP_DBG(fip, "vn_claim_notify: send reply to %x\n",
- new->ids.port_id);
- fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, frport->enode_mac,
- min((u32)frport->fcoe_len,
+ new->rdata.ids.port_id);
+ fcoe_ctlr_vn_send(fip, FIP_SC_VN_CLAIM_REP, new->enode_mac,
+ min((u32)new->fcoe_len,
fcoe_ctlr_fcoe_size(fip)));
fcoe_ctlr_vn_add(fip, new);
break;
default:
LIBFCOE_FIP_DBG(fip, "vn_claim_notify: "
- "ignoring claim from %x\n", new->ids.port_id);
+ "ignoring claim from %x\n",
+ new->rdata.ids.port_id);
break;
}
}
/**
* fcoe_ctlr_vn_claim_resp() - handle received Claim Response
* @fip: The FCoE controller that received the frame
- * @new: newly-parsed remote port with frport from the Claim Response
+ * @new: newly-parsed FCoE rport from the Claim Response
*
* Called with ctlr_mutex held.
*/
static void fcoe_ctlr_vn_claim_resp(struct fcoe_ctlr *fip,
- struct fc_rport_priv *new)
+ struct fcoe_rport *new)
{
LIBFCOE_FIP_DBG(fip, "claim resp from from rport %x - state %s\n",
- new->ids.port_id, fcoe_ctlr_state(fip->state));
+ new->rdata.ids.port_id, fcoe_ctlr_state(fip->state));
if (fip->state == FIP_ST_VNMP_UP || fip->state == FIP_ST_VNMP_CLAIM)
fcoe_ctlr_vn_add(fip, new);
}
/**
* fcoe_ctlr_vn_beacon() - handle received beacon.
* @fip: The FCoE controller that received the frame
- * @new: newly-parsed remote port with frport from the Beacon
+ * @new: newly-parsed FCoE rport from the Beacon
*
* Called with ctlr_mutex held.
*/
static void fcoe_ctlr_vn_beacon(struct fcoe_ctlr *fip,
- struct fc_rport_priv *new)
+ struct fcoe_rport *new)
{
struct fc_lport *lport = fip->lp;
struct fc_rport_priv *rdata;
struct fcoe_rport *frport;
- frport = fcoe_ctlr_rport(new);
- if (frport->flags & FIP_FL_REC_OR_P2P) {
+ if (new->flags & FIP_FL_REC_OR_P2P) {
LIBFCOE_FIP_DBG(fip, "p2p beacon while in vn2vn mode\n");
fcoe_ctlr_vn_send(fip, FIP_SC_VN_PROBE_REQ, fcoe_all_vn2vn, 0);
return;
}
- rdata = fc_rport_lookup(lport, new->ids.port_id);
+ rdata = fc_rport_lookup(lport, new->rdata.ids.port_id);
if (rdata) {
- if (rdata->ids.node_name == new->ids.node_name &&
- rdata->ids.port_name == new->ids.port_name) {
+ if (rdata->ids.node_name == new->rdata.ids.node_name &&
+ rdata->ids.port_name == new->rdata.ids.port_name) {
frport = fcoe_ctlr_rport(rdata);
+
LIBFCOE_FIP_DBG(fip, "beacon from rport %x\n",
rdata->ids.port_id);
if (!frport->time && fip->state == FIP_ST_VNMP_UP) {
* Don't add the neighbor yet.
*/
LIBFCOE_FIP_DBG(fip, "beacon from new rport %x. sending claim notify\n",
- new->ids.port_id);
+ new->rdata.ids.port_id);
if (time_after(jiffies,
fip->sol_time + msecs_to_jiffies(FIP_VN_ANN_WAIT)))
fcoe_ctlr_vn_send_claim(fip);
{
struct fip_header *fiph;
enum fip_vn2vn_subcode sub;
- struct {
- struct fc_rport_priv rdata;
- struct fcoe_rport frport;
- } buf;
+ struct fcoe_rport frport = { };
int rc, vlan_id = 0;
fiph = (struct fip_header *)skb->data;
goto drop;
}
- rc = fcoe_ctlr_vn_parse(fip, skb, &buf.rdata);
+ rc = fcoe_ctlr_vn_parse(fip, skb, &frport);
if (rc) {
LIBFCOE_FIP_DBG(fip, "vn_recv vn_parse error %d\n", rc);
goto drop;
mutex_lock(&fip->ctlr_mutex);
switch (sub) {
case FIP_SC_VN_PROBE_REQ:
- fcoe_ctlr_vn_probe_req(fip, &buf.rdata);
+ fcoe_ctlr_vn_probe_req(fip, &frport);
break;
case FIP_SC_VN_PROBE_REP:
- fcoe_ctlr_vn_probe_reply(fip, &buf.rdata);
+ fcoe_ctlr_vn_probe_reply(fip, &frport);
break;
case FIP_SC_VN_CLAIM_NOTIFY:
- fcoe_ctlr_vn_claim_notify(fip, &buf.rdata);
+ fcoe_ctlr_vn_claim_notify(fip, &frport);
break;
case FIP_SC_VN_CLAIM_REP:
- fcoe_ctlr_vn_claim_resp(fip, &buf.rdata);
+ fcoe_ctlr_vn_claim_resp(fip, &frport);
break;
case FIP_SC_VN_BEACON:
- fcoe_ctlr_vn_beacon(fip, &buf.rdata);
+ fcoe_ctlr_vn_beacon(fip, &frport);
break;
default:
LIBFCOE_FIP_DBG(fip, "vn_recv unknown subcode %d\n", sub);
*/
static int fcoe_ctlr_vlan_parse(struct fcoe_ctlr *fip,
struct sk_buff *skb,
- struct fc_rport_priv *rdata)
+ struct fcoe_rport *frport)
{
struct fip_header *fiph;
struct fip_desc *desc = NULL;
struct fip_mac_desc *macd = NULL;
struct fip_wwn_desc *wwn = NULL;
- struct fcoe_rport *frport;
size_t rlen;
size_t dlen;
u32 desc_mask = 0;
u32 dtype;
u8 sub;
- memset(rdata, 0, sizeof(*rdata) + sizeof(*frport));
- frport = fcoe_ctlr_rport(rdata);
-
fiph = (struct fip_header *)skb->data;
frport->flags = ntohs(fiph->fip_flags);
if (dlen != sizeof(struct fip_wwn_desc))
goto len_err;
wwn = (struct fip_wwn_desc *)desc;
- rdata->ids.node_name = get_unaligned_be64(&wwn->fd_wwn);
+ frport->rdata.ids.node_name =
+ get_unaligned_be64(&wwn->fd_wwn);
break;
default:
LIBFCOE_FIP_DBG(fip, "unexpected descriptor type %x "
/**
* fcoe_ctlr_vlan_disk_reply() - send FIP VLAN Discovery Notification.
* @fip: The FCoE controller
+ * @frport: The newly-parsed FCoE rport from the Discovery Request
*
* Called with ctlr_mutex held.
*/
static void fcoe_ctlr_vlan_disc_reply(struct fcoe_ctlr *fip,
- struct fc_rport_priv *rdata)
+ struct fcoe_rport *frport)
{
- struct fcoe_rport *frport = fcoe_ctlr_rport(rdata);
enum fip_vlan_subcode sub = FIP_SC_VL_NOTE;
if (fip->mode == FIP_MODE_VN2VN)
{
struct fip_header *fiph;
enum fip_vlan_subcode sub;
- struct {
- struct fc_rport_priv rdata;
- struct fcoe_rport frport;
- } buf;
+ struct fcoe_rport frport = { };
int rc;
fiph = (struct fip_header *)skb->data;
sub = fiph->fip_subcode;
- rc = fcoe_ctlr_vlan_parse(fip, skb, &buf.rdata);
+ rc = fcoe_ctlr_vlan_parse(fip, skb, &frport);
if (rc) {
LIBFCOE_FIP_DBG(fip, "vlan_recv vlan_parse error %d\n", rc);
goto drop;
}
mutex_lock(&fip->ctlr_mutex);
if (sub == FIP_SC_VL_REQ)
- fcoe_ctlr_vlan_disc_reply(fip, &buf.rdata);
+ fcoe_ctlr_vlan_disc_reply(fip, &frport);
mutex_unlock(&fip->ctlr_mutex);
drop:
case IOACCEL2_SERV_RESPONSE_COMPLETE:
switch (c2->error_data.status) {
case IOACCEL2_STATUS_SR_TASK_COMP_GOOD:
+ if (cmd)
+ cmd->result = 0;
break;
case IOACCEL2_STATUS_SR_TASK_COMP_CHK_COND:
cmd->result |= SAM_STAT_CHECK_CONDITION;
/* check for good status */
if (likely(c2->error_data.serv_response == 0 &&
- c2->error_data.status == 0))
+ c2->error_data.status == 0)) {
+ cmd->result = 0;
return hpsa_cmd_free_and_done(h, c, cmd);
+ }
/*
* Any RAID offload error results in retry which will use
if (c == NULL)
return SCSI_MLQUEUE_DEVICE_BUSY;
+ /*
+ * This is necessary because the SML doesn't zero out this field during
+ * error recovery.
+ */
+ cmd->result = 0;
+
/*
* Call alternate submit routine for I/O accelerated commands.
* Retries always go down the normal I/O path.
if (idx != h->last_collision_tag) { /* Print once per tag */
dev_warn(&h->pdev->dev,
"%s: tag collision (tag=%d)\n", __func__, idx);
- if (c->scsi_cmd != NULL)
- scsi_print_command(c->scsi_cmd);
if (scmd)
scsi_print_command(scmd);
h->last_collision_tag = idx;
hpsa_disable_interrupt_mode(h); /* pci_init 2 */
/*
* call pci_disable_device before pci_release_regions per
- * Documentation/PCI/pci.rst
+ * Documentation/driver-api/pci/pci.rst
*/
pci_disable_device(h->pdev); /* pci_init 1 */
pci_release_regions(h->pdev); /* pci_init 2 */
clean1:
/*
* call pci_disable_device before pci_release_regions per
- * Documentation/PCI/pci.rst
+ * Documentation/driver-api/pci/pci.rst
*/
pci_disable_device(h->pdev);
pci_release_regions(h->pdev);
spin_lock_irqsave(vhost->host->host_lock, flags);
ibmvfc_purge_requests(vhost, DID_ERROR);
- ibmvfc_free_event_pool(vhost);
spin_unlock_irqrestore(vhost->host->host_lock, flags);
+ ibmvfc_free_event_pool(vhost);
ibmvfc_free_mem(vhost);
spin_lock(&ibmvfc_driver_lock);
struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)
{
struct fc_rport_priv *rdata;
+ size_t rport_priv_size = sizeof(*rdata);
lockdep_assert_held(&lport->disc.disc_mutex);
if (rdata)
return rdata;
- rdata = kzalloc(sizeof(*rdata) + lport->rport_priv_size, GFP_KERNEL);
+ if (lport->rport_priv_size > 0)
+ rport_priv_size = lport->rport_priv_size;
+ rdata = kzalloc(rport_priv_size, GFP_KERNEL);
if (!rdata)
return NULL;
pr_notice("ATA device seen but CONFIG_SCSI_SAS_ATA=N so cannot attach\n");
/* Fall through */
#endif
+ /* Fall through - only for the #else condition above. */
default:
error = -ENXIO;
pr_err("unhandled device %d\n", dev->dev_type);
uint32_t cfg_cq_poll_threshold;
uint32_t cfg_cq_max_proc_limit;
uint32_t cfg_fcp_cpu_map;
+ uint32_t cfg_fcp_mq_threshold;
uint32_t cfg_hdw_queue;
uint32_t cfg_irq_chann;
uint32_t cfg_suppress_rsp;
LPFC_ATTR_RW(nvme_embed_cmd, 1, 0, 2,
"Embed NVME Command in WQE");
+/*
+ * lpfc_fcp_mq_threshold: Set the maximum number of Hardware Queues
+ * the driver will advertise it supports to the SCSI layer.
+ *
+ * 0 = Set nr_hw_queues by the number of CPUs or HW queues.
+ * 1,128 = Manually specify the maximum nr_hw_queue value to be set,
+ *
+ * Value range is [0,256]. Default value is 8.
+ */
+LPFC_ATTR_R(fcp_mq_threshold, LPFC_FCP_MQ_THRESHOLD_DEF,
+ LPFC_FCP_MQ_THRESHOLD_MIN, LPFC_FCP_MQ_THRESHOLD_MAX,
+ "Set the number of SCSI Queues advertised");
+
/*
* lpfc_hdw_queue: Set the number of Hardware Queues the driver
* will advertise it supports to the NVME and SCSI layers. This also
&dev_attr_lpfc_cq_poll_threshold,
&dev_attr_lpfc_cq_max_proc_limit,
&dev_attr_lpfc_fcp_cpu_map,
+ &dev_attr_lpfc_fcp_mq_threshold,
&dev_attr_lpfc_hdw_queue,
&dev_attr_lpfc_irq_chann,
&dev_attr_lpfc_suppress_rsp,
/* Initialize first burst. Target vs Initiator are different. */
lpfc_nvme_enable_fb_init(phba, lpfc_nvme_enable_fb);
lpfc_nvmet_fb_size_init(phba, lpfc_nvmet_fb_size);
+ lpfc_fcp_mq_threshold_init(phba, lpfc_fcp_mq_threshold);
lpfc_hdw_queue_init(phba, lpfc_hdw_queue);
lpfc_irq_chann_init(phba, lpfc_irq_chann);
lpfc_enable_bbcr_init(phba, lpfc_enable_bbcr);
shost->max_cmd_len = 16;
if (phba->sli_rev == LPFC_SLI_REV4) {
- if (phba->cfg_fcp_io_sched == LPFC_FCP_SCHED_BY_HDWQ)
- shost->nr_hw_queues = phba->cfg_hdw_queue;
- else
- shost->nr_hw_queues = phba->sli4_hba.num_present_cpu;
+ if (!phba->cfg_fcp_mq_threshold ||
+ phba->cfg_fcp_mq_threshold > phba->cfg_hdw_queue)
+ phba->cfg_fcp_mq_threshold = phba->cfg_hdw_queue;
+
+ shost->nr_hw_queues = min_t(int, 2 * num_possible_nodes(),
+ phba->cfg_fcp_mq_threshold);
shost->dma_boundary =
phba->sli4_hba.pc_sli4_params.sge_supp_len-1;
/* This loop sets up all CPUs that are affinitized with a
* irq vector assigned to the driver. All affinitized CPUs
* will get a link to that vectors IRQ and EQ.
+ *
+ * NULL affinity mask handling:
+ * If irq count is greater than one, log an error message.
+ * If the null mask is received for the first irq, find the
+ * first present cpu, and assign the eq index to ensure at
+ * least one EQ is assigned.
*/
for (idx = 0; idx < phba->cfg_irq_chann; idx++) {
/* Get a CPU mask for all CPUs affinitized to this vector */
maskp = pci_irq_get_affinity(phba->pcidev, idx);
- if (!maskp)
- continue;
+ if (!maskp) {
+ if (phba->cfg_irq_chann > 1)
+ lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+ "3329 No affinity mask found "
+ "for vector %d (%d)\n",
+ idx, phba->cfg_irq_chann);
+ if (!idx) {
+ cpu = cpumask_first(cpu_present_mask);
+ cpup = &phba->sli4_hba.cpu_map[cpu];
+ cpup->eq = idx;
+ cpup->irq = pci_irq_vector(phba->pcidev, idx);
+ cpup->flag |= LPFC_CPU_FIRST_IRQ;
+ }
+ break;
+ }
i = 0;
/* Loop through all CPUs associated with vector idx */
#define LPFC_HBA_HDWQ_MAX 128
#define LPFC_HBA_HDWQ_DEF 0
+/* FCP MQ queue count limiting */
+#define LPFC_FCP_MQ_THRESHOLD_MIN 0
+#define LPFC_FCP_MQ_THRESHOLD_MAX 256
+#define LPFC_FCP_MQ_THRESHOLD_DEF 8
+
/* Common buffer size to accomidate SCSI and NVME IO buffers */
#define LPFC_COMMON_IO_BUF_SZ 768
(struct megasas_instance *) shost->hostdata;
u32 size;
unsigned long dmachunk = CRASH_DMA_BUF_SIZE;
+ unsigned long chunk_left_bytes;
unsigned long src_addr;
unsigned long flags;
u32 buff_offset;
}
size = (instance->fw_crash_buffer_size * dmachunk) - buff_offset;
+ chunk_left_bytes = dmachunk - (buff_offset % dmachunk);
+ size = (size > chunk_left_bytes) ? chunk_left_bytes : size;
size = (size >= PAGE_SIZE) ? (PAGE_SIZE - 1) : size;
src_addr = (unsigned long)instance->crash_buf[buff_offset / dmachunk] +
if ((event_log_level < MFI_EVT_CLASS_DEBUG) ||
(event_log_level > MFI_EVT_CLASS_DEAD)) {
- printk(KERN_WARNING "megarid_sas: provided event log level is out of range, setting it to default 2(CLASS_CRITICAL), permissible range is: -2 to 4\n");
+ pr_warn("megaraid_sas: provided event log level is out of range, setting it to default 2(CLASS_CRITICAL), permissible range is: -2 to 4\n");
event_log_level = MFI_EVT_CLASS_CRITICAL;
}
return 0;
}
-int
+static int
megasas_alloc_cmdlist_fusion(struct megasas_instance *instance)
{
u32 max_mpt_cmd, i, j;
return 0;
}
-int
+
+static int
megasas_alloc_request_fusion(struct megasas_instance *instance)
{
struct fusion_context *fusion;
return 0;
}
-int
+static int
megasas_alloc_reply_fusion(struct megasas_instance *instance)
{
int i, count;
return 0;
}
-int
+static int
megasas_alloc_rdpq_fusion(struct megasas_instance *instance)
{
int i, j, k, msix_count;
* and is used as SMID of the cmd.
* SMID value range is from 1 to max_fw_cmds.
*/
-int
+static int
megasas_alloc_cmds_fusion(struct megasas_instance *instance)
{
int i;
*
* This is the main function for initializing firmware.
*/
-u32
+static u32
megasas_init_adapter_fusion(struct megasas_instance *instance)
{
struct fusion_context *fusion;
* @ext_status : ext status of cmd returned by FW
*/
-void
+static void
map_cmd_status(struct fusion_context *fusion,
struct scsi_cmnd *scmd, u8 status, u8 ext_status,
u32 data_length, u8 *sense)
*
* Used to set the PD LBA in CDB for FP IOs
*/
-void
+static void
megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
struct IO_REQUEST_INFO *io_info, struct scsi_cmnd *scp,
struct MR_DRV_RAID_MAP_ALL *local_map_ptr, u32 ref_tag)
* Prepares the io_request and chain elements (sg_frame) for IO
* The IO can be for PD (Fast Path) or LD
*/
-void
+static void
megasas_build_ldio_fusion(struct megasas_instance *instance,
struct scsi_cmnd *scp,
struct megasas_cmd_fusion *cmd)
* Invokes helper functions to prepare request frames
* and sets flags appropriate for IO/Non-IO cmd
*/
-int
+static int
megasas_build_io_fusion(struct megasas_instance *instance,
struct scsi_cmnd *scp,
struct megasas_cmd_fusion *cmd)
/* megasas_prepate_secondRaid1_IO
* It prepares the raid 1 second IO
*/
-void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance,
- struct megasas_cmd_fusion *cmd,
- struct megasas_cmd_fusion *r1_cmd)
+static void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance,
+ struct megasas_cmd_fusion *cmd,
+ struct megasas_cmd_fusion *r1_cmd)
{
union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc, *req_desc2 = NULL;
struct fusion_context *fusion;
{
u64 required_mask, coherent_mask;
struct sysinfo s;
+ /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */
+ int dma_mask = (ioc->hba_mpi_version_belonged > MPI2_VERSION) ? 63 : 64;
if (ioc->is_mcpu_endpoint)
goto try_32bit;
goto try_32bit;
if (ioc->dma_mask)
- coherent_mask = DMA_BIT_MASK(64);
+ coherent_mask = DMA_BIT_MASK(dma_mask);
else
coherent_mask = DMA_BIT_MASK(32);
- if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) ||
+ if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(dma_mask)) ||
dma_set_coherent_mask(&pdev->dev, coherent_mask))
goto try_32bit;
ioc->base_add_sg_single = &_base_add_sg_single_64;
ioc->sge_size = sizeof(Mpi2SGESimple64_t);
- ioc->dma_mask = 64;
+ ioc->dma_mask = dma_mask;
goto out;
try_32bit:
_base_change_consistent_dma_mask(struct MPT3SAS_ADAPTER *ioc,
struct pci_dev *pdev)
{
- if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64))) {
+ if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(ioc->dma_mask))) {
if (pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)))
return -ENODEV;
}
total_sz += sz;
} while (ioc->rdpq_array_enable && (++i < ioc->reply_queue_count));
- if (ioc->dma_mask == 64) {
+ if (ioc->dma_mask > 32) {
if (_base_change_consistent_dma_mask(ioc, ioc->pdev) != 0) {
ioc_warn(ioc, "no suitable consistent DMA mask for %s\n",
pci_name(ioc->pdev));
dma_free_coherent(&ha->pdev->dev, vha->gnl.size, vha->gnl.l,
vha->gnl.ldma);
+ vha->gnl.l = NULL;
+
vfree(vha->scan.l);
if (vha->qpair && vha->qpair->vp_idx == vha->vp_idx) {
ql_log(ql_log_warn, vha, 0xd049,
"Failed to allocate ct_sns request.\n");
kfree(fcport);
- fcport = NULL;
+ return NULL;
}
INIT_WORK(&fcport->del_work, qla24xx_delete_sess_fn);
return 0;
probe_failed:
+ if (base_vha->gnl.l) {
+ dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size,
+ base_vha->gnl.l, base_vha->gnl.ldma);
+ base_vha->gnl.l = NULL;
+ }
+
if (base_vha->timer_active)
qla2x00_stop_timer(base_vha);
base_vha->flags.online = 0;
if (!atomic_read(&pdev->enable_cnt)) {
dma_free_coherent(&ha->pdev->dev, base_vha->gnl.size,
base_vha->gnl.l, base_vha->gnl.ldma);
-
+ base_vha->gnl.l = NULL;
scsi_host_put(base_vha->host);
kfree(ha);
pci_set_drvdata(pdev, NULL);
dma_free_coherent(&ha->pdev->dev,
base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma);
+ base_vha->gnl.l = NULL;
+
vfree(base_vha->scan.l);
if (IS_QLAFX00(ha))
"Alloc failed for scan database.\n");
dma_free_coherent(&ha->pdev->dev, vha->gnl.size,
vha->gnl.l, vha->gnl.ldma);
+ vha->gnl.l = NULL;
scsi_remove_host(vha->host);
return NULL;
}
blk_queue_max_integrity_segments(q, shost->sg_prot_tablesize);
}
- shost->max_sectors = min_t(unsigned int, shost->max_sectors,
- dma_max_mapping_size(dev) << SECTOR_SHIFT);
+ if (dev->dma_mask) {
+ shost->max_sectors = min_t(unsigned int, shost->max_sectors,
+ dma_max_mapping_size(dev) >> SECTOR_SHIFT);
+ }
blk_queue_max_hw_sectors(q, shost->max_sectors);
if (shost->unchecked_isa_dma)
blk_queue_bounce_limit(q, BLK_BOUNCE_ISA);
static inline int ufshcd_config_vreg_hpm(struct ufs_hba *hba,
struct ufs_vreg *vreg)
{
+ if (!vreg)
+ return 0;
+
return ufshcd_config_vreg_load(hba->dev, vreg, vreg->max_uA);
}
/*
* Upload a microcode to the I-RAM at a specific address.
*
- * See Documentation/powerpc/qe_firmware.txt for information on QE microcode
+ * See Documentation/powerpc/qe_firmware.rst for information on QE microcode
* uploading.
*
* Currently, only version 1 is supported, so the 'version' field must be
# SPDX-License-Identifier: GPL-2.0-only
+if ARCH_IXP4XX || COMPILE_TEST
+
menu "IXP4xx SoC drivers"
config IXP4XX_QMGR
and is automatically selected by Ethernet and HSS drivers.
endmenu
+
+endif
struct geni_wrapper *wrapper = se->wrapper;
u32 val;
+ if (!wrapper)
+ return -EINVAL;
+
*iova = dma_map_single(wrapper->dev, buf, len, DMA_TO_DEVICE);
if (dma_mapping_error(wrapper->dev, *iova))
return -EIO;
struct geni_wrapper *wrapper = se->wrapper;
u32 val;
+ if (!wrapper)
+ return -EINVAL;
+
*iova = dma_map_single(wrapper->dev, buf, len, DMA_FROM_DEVICE);
if (dma_mapping_error(wrapper->dev, *iova))
return -EIO;
}
#ifdef CONFIG_SUSPEND
-struct wkup_m3_wakeup_src rtc_wake_src(void)
+static struct wkup_m3_wakeup_src rtc_wake_src(void)
{
u32 i;
return rtc_ext_wakeup;
}
-int am33xx_rtc_only_idle(unsigned long wfi_flags)
+static int am33xx_rtc_only_idle(unsigned long wfi_flags)
{
omap_rtc_power_off_program(&omap_rtc->dev);
am33xx_do_wfi_sram(wfi_flags);
if (state == PM_SUSPEND_MEM && pm_ops->check_off_mode_enable()) {
nvmem = devm_nvmem_device_get(&omap_rtc->dev,
"omap_rtc_scratch0");
- if (nvmem)
+ if (!IS_ERR(nvmem))
nvmem_device_write(nvmem, RTC_SCRATCH_MAGIC_REG * 4, 4,
(void *)&rtc_magic_val);
rtc_only_idle = 1;
struct nvmem_device *nvmem;
nvmem = devm_nvmem_device_get(&omap_rtc->dev, "omap_rtc_scratch0");
+ if (IS_ERR(nvmem))
+ return;
+
m3_ipc->ops->finish_low_power(m3_ipc);
if (rtc_only_idle) {
- if (retrigger_irq)
+ if (retrigger_irq) {
/*
* 32 bits of Interrupt Set-Pending correspond to 32
* 32 interrupts. Compute the bit offset of the
writel_relaxed(1 << (retrigger_irq & 31),
gic_dist_base + GIC_INT_SET_PENDING_BASE
+ retrigger_irq / 32 * 4);
- nvmem_device_write(nvmem, RTC_SCRATCH_MAGIC_REG * 4, 4,
- (void *)&val);
+ }
+
+ nvmem_device_write(nvmem, RTC_SCRATCH_MAGIC_REG * 4, 4,
+ (void *)&val);
}
rtc_only_idle = 0;
nvmem = devm_nvmem_device_get(&omap_rtc->dev,
"omap_rtc_scratch0");
- if (nvmem) {
+ if (!IS_ERR(nvmem)) {
nvmem_device_read(nvmem, RTC_SCRATCH_MAGIC_REG * 4,
4, (void *)&rtc_magic_val);
if ((rtc_magic_val & 0xffff) != RTC_REG_BOOT_MAGIC)
#
menuconfig SOUNDWIRE
- bool "SoundWire support"
+ tristate "SoundWire support"
help
SoundWire is a 2-Pin interface with data and clock line ratified
by the MIPI Alliance. SoundWire is used for transporting data
comment "SoundWire Devices"
-config SOUNDWIRE_BUS
- tristate
- select REGMAP_SOUNDWIRE
-
config SOUNDWIRE_CADENCE
tristate
config SOUNDWIRE_INTEL
tristate "Intel SoundWire Master driver"
select SOUNDWIRE_CADENCE
- select SOUNDWIRE_BUS
depends on X86 && ACPI && SND_SOC
help
SoundWire Intel Master driver.
#Bus Objs
soundwire-bus-objs := bus_type.o bus.o slave.o mipi_disco.o stream.o
-obj-$(CONFIG_SOUNDWIRE_BUS) += soundwire-bus.o
+obj-$(CONFIG_SOUNDWIRE) += soundwire-bus.o
#Cadence Objs
soundwire-cadence-objs := cadence_master.o
#define CDNS_MCP_INTSET 0x4C
-#define CDNS_SDW_SLAVE_STAT 0x50
-#define CDNS_MCP_SLAVE_STAT_MASK BIT(1, 0)
+#define CDNS_MCP_SLAVE_STAT 0x50
+#define CDNS_MCP_SLAVE_STAT_MASK GENMASK(1, 0)
#define CDNS_MCP_SLAVE_INTSTAT0 0x54
#define CDNS_MCP_SLAVE_INTSTAT1 0x58
#define CDNS_MCP_SLAVE_INTMASK0 0x5C
#define CDNS_MCP_SLAVE_INTMASK1 0x60
-#define CDNS_MCP_SLAVE_INTMASK0_MASK GENMASK(30, 0)
-#define CDNS_MCP_SLAVE_INTMASK1_MASK GENMASK(16, 0)
+#define CDNS_MCP_SLAVE_INTMASK0_MASK GENMASK(31, 0)
+#define CDNS_MCP_SLAVE_INTMASK1_MASK GENMASK(15, 0)
#define CDNS_MCP_PORT_INTSTAT 0x64
#define CDNS_MCP_PDI_STAT 0x6C
bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);
/* handle all the 3-wire mode */
- if ((spi->mode & SPI_3WIRE) && (tfr->rx_buf))
+ if (spi->mode & SPI_3WIRE && tfr->rx_buf &&
+ tfr->rx_buf != ctlr->dummy_rx)
cs |= BCM2835_SPI_CS_REN;
else
cs &= ~BCM2835_SPI_CS_REN;
};
static const struct fsl_qspi_devtype_data imx7d_data = {
- .rxfifo = SZ_512,
+ .rxfifo = SZ_128,
.txfifo = SZ_512,
.ahb_buf_size = SZ_1K,
.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK,
bb = &spi_gpio->bitbang;
bb->master = master;
+ /*
+ * There is some additional business, apart from driving the CS GPIO
+ * line, that we need to do on selection. This makes the local
+ * callback for chipselect always get called.
+ */
+ master->flags |= SPI_MASTER_GPIO_SS;
bb->chipselect = spi_gpio_chipselect;
bb->set_line_direction = spi_gpio_set_direction;
{ PCI_VDEVICE(INTEL, 0x02aa), LPSS_CNL_SSP },
{ PCI_VDEVICE(INTEL, 0x02ab), LPSS_CNL_SSP },
{ PCI_VDEVICE(INTEL, 0x02fb), LPSS_CNL_SSP },
+ /* TGL-LP */
+ { PCI_VDEVICE(INTEL, 0xa0aa), LPSS_CNL_SSP },
+ { PCI_VDEVICE(INTEL, 0xa0ab), LPSS_CNL_SSP },
+ { PCI_VDEVICE(INTEL, 0xa0de), LPSS_CNL_SSP },
+ { PCI_VDEVICE(INTEL, 0xa0df), LPSS_CNL_SSP },
+ { PCI_VDEVICE(INTEL, 0xa0fb), LPSS_CNL_SSP },
+ { PCI_VDEVICE(INTEL, 0xa0fd), LPSS_CNL_SSP },
+ { PCI_VDEVICE(INTEL, 0xa0fe), LPSS_CNL_SSP },
{ },
};
status = devm_spi_register_controller(&pdev->dev, controller);
if (status != 0) {
dev_err(&pdev->dev, "problem registering spi controller\n");
- goto out_error_clock_enabled;
+ goto out_error_pm_runtime_enabled;
}
return status;
-out_error_clock_enabled:
+out_error_pm_runtime_enabled:
pm_runtime_put_noidle(&pdev->dev);
pm_runtime_disable(&pdev->dev);
+
+out_error_clock_enabled:
clk_disable_unprepare(ssp->clk);
out_error_dma_irq_alloc:
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/swap.h>
+#include <linux/sched/signal.h>
#include "ion.h"
static inline struct page *ion_page_pool_alloc_pages(struct ion_page_pool *pool)
{
+ if (fatal_signal_pending(current))
+ return NULL;
return alloc_pages(pool->gfp_mask, pool->order);
}
static int dt3k_ns_to_timer(unsigned int timer_base, unsigned int *nanosec,
unsigned int flags)
{
- int divider, base, prescale;
+ unsigned int divider, base, prescale;
- /* This function needs improvment */
+ /* This function needs improvement */
/* Don't know if divider==0 works. */
for (prescale = 0; prescale < 16; prescale++) {
divider = (*nanosec) / base;
break;
case CMDF_ROUND_UP:
- divider = (*nanosec) / base;
+ divider = DIV_ROUND_UP(*nanosec, base);
break;
}
if (divider < 65536) {
}
prescale = 15;
- base = timer_base * (1 << prescale);
+ base = timer_base * (prescale + 1);
divider = 65535;
*nanosec = divider * base;
return (prescale << 16) | (divider);
static int init_display(struct fbtft_par *par)
{
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
par->fbtftops.reset(par);
{
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
write_reg(par, MIPI_DCS_SOFT_RESET); /* software reset */
{
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
bt &= 0x07;
{
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
/* Initialization sequence from Lib_UTFT */
{
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
write_reg(par, 0x00, 0x0001);
va_start(args, len);
*buf = (u8)va_arg(args, unsigned int);
- if (!par->gpio.dc)
+ if (par->gpio.dc)
gpiod_set_value(par->gpio.dc, 0);
ret = par->fbtftops.write(par, par->buf, sizeof(u8));
if (ret < 0) {
return;
}
}
- if (!par->gpio.dc)
+ if (par->gpio.dc)
gpiod_set_value(par->gpio.dc, 1);
va_end(args);
}
{
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
/* Initialization sequence from Lib_UTFT */
remain = len / 2;
vmem16 = (u16 *)(par->info->screen_buffer + offset);
- if (!par->gpio.dc)
+ if (par->gpio.dc)
gpiod_set_value(par->gpio.dc, 1);
/* non buffered write */
struct gpio_desc **gpiop)
{
struct device *dev = par->info->device;
- struct device_node *node = dev->of_node;
int ret = 0;
- if (of_find_property(node, name, NULL)) {
- *gpiop = devm_gpiod_get_index(dev, dev->driver->name, index,
- GPIOD_OUT_HIGH);
- if (IS_ERR(*gpiop)) {
- ret = PTR_ERR(*gpiop);
- dev_err(dev,
- "Failed to request %s GPIO:%d\n", name, ret);
- return ret;
- }
- fbtft_par_dbg(DEBUG_REQUEST_GPIOS, par, "%s: '%s' GPIO\n",
- __func__, name);
+ *gpiop = devm_gpiod_get_index_optional(dev, name, index,
+ GPIOD_OUT_HIGH);
+ if (IS_ERR(*gpiop)) {
+ ret = PTR_ERR(*gpiop);
+ dev_err(dev,
+ "Failed to request %s GPIO: %d\n", name, ret);
+ return ret;
}
+ fbtft_par_dbg(DEBUG_REQUEST_GPIOS, par, "%s: '%s' GPIO\n",
+ __func__, name);
return ret;
}
if (!par->info->device->of_node)
return -EINVAL;
- ret = fbtft_request_one_gpio(par, "reset-gpios", 0, &par->gpio.reset);
+ ret = fbtft_request_one_gpio(par, "reset", 0, &par->gpio.reset);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "dc-gpios", 0, &par->gpio.dc);
+ ret = fbtft_request_one_gpio(par, "dc", 0, &par->gpio.dc);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "rd-gpios", 0, &par->gpio.rd);
+ ret = fbtft_request_one_gpio(par, "rd", 0, &par->gpio.rd);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "wr-gpios", 0, &par->gpio.wr);
+ ret = fbtft_request_one_gpio(par, "wr", 0, &par->gpio.wr);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "cs-gpios", 0, &par->gpio.cs);
+ ret = fbtft_request_one_gpio(par, "cs", 0, &par->gpio.cs);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "latch-gpios", 0, &par->gpio.latch);
+ ret = fbtft_request_one_gpio(par, "latch", 0, &par->gpio.latch);
if (ret)
return ret;
for (i = 0; i < 16; i++) {
- ret = fbtft_request_one_gpio(par, "db-gpios", i,
+ ret = fbtft_request_one_gpio(par, "db", i,
&par->gpio.db[i]);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "led-gpios", i,
+ ret = fbtft_request_one_gpio(par, "led", i,
&par->gpio.led[i]);
if (ret)
return ret;
- ret = fbtft_request_one_gpio(par, "aux-gpios", i,
+ ret = fbtft_request_one_gpio(par, "aux", i,
&par->gpio.aux[i]);
if (ret)
return ret;
if (!par->gpio.reset)
return;
fbtft_par_dbg(DEBUG_RESET, par, "%s()\n", __func__);
- gpiod_set_value_cansleep(par->gpio.reset, 0);
- usleep_range(20, 40);
gpiod_set_value_cansleep(par->gpio.reset, 1);
+ usleep_range(20, 40);
+ gpiod_set_value_cansleep(par->gpio.reset, 0);
msleep(120);
}
return -EINVAL;
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
while (p) {
}
par->fbtftops.reset(par);
- if (!par->gpio.cs)
+ if (par->gpio.cs)
gpiod_set_value(par->gpio.cs, 0); /* Activate chip */
i = 0;
break;
case ATTR_KERNEL_HIB_SIMPLE_PAGE_TABLE_SIZE:
ret = scnprintf(buf, PAGE_SIZE, "%u\n",
- gasket_page_table_num_entries(
+ gasket_page_table_num_simple_entries(
gasket_dev->page_table[0]));
break;
case ATTR_KERNEL_HIB_NUM_ACTIVE_PAGES:
}
/* poll_for_irq - checks the status of the response queue
- * @v: Void pointer to the visronic devdata struct.
+ * @t: pointer to the 'struct timer_list' from which we can retrieve the
+ * the visornic devdata struct.
*
* Main function of the vnic_incoming thread. Periodically check the response
* queue and drain it if needed.
priv->p2p_listen_state = false;
+ flush_workqueue(vif->wilc->hif_workqueue);
mutex_destroy(&priv->scan_req_lock);
ret = wilc_deinit(vif);
return 0;
if (caps & DCB_CAP_DCBX_VER_IEEE) {
- iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY;
-
+ iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_STREAM;
ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app);
-
+ if (!ret) {
+ iscsi_dcb_app.selector = IEEE_8021QAZ_APP_SEL_ANY;
+ ret = dcb_ieee_getapp_mask(ndev, &iscsi_dcb_app);
+ }
} else if (caps & DCB_CAP_DCBX_VER_CEE) {
iscsi_dcb_app.selector = DCB_APP_IDTYPE_PORTNUM;
iscsi_app = &dcb_work->dcb_app;
if (iscsi_app->dcbx & DCB_CAP_DCBX_VER_IEEE) {
- if (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY)
+ if ((iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_STREAM) &&
+ (iscsi_app->app.selector != IEEE_8021QAZ_APP_SEL_ANY))
goto out;
priority = iscsi_app->app.priority;
struct se_cmd *se_cmd = cmd->se_cmd;
struct tcmu_dev *udev = cmd->tcmu_dev;
bool read_len_valid = false;
- uint32_t read_len = se_cmd->data_length;
+ uint32_t read_len;
/*
* cmd has been completed already from timeout, just reclaim
* data area space and free cmd
*/
- if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags))
+ if (test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) {
+ WARN_ON_ONCE(se_cmd);
goto out;
+ }
list_del_init(&cmd->queue_entry);
goto done;
}
+ read_len = se_cmd->data_length;
if (se_cmd->data_direction == DMA_FROM_DEVICE &&
(entry->hdr.uflags & TCMU_UFLAG_READ_LEN) && entry->rsp.read_len) {
read_len_valid = true;
*/
scsi_status = SAM_STAT_CHECK_CONDITION;
list_del_init(&cmd->queue_entry);
+ cmd->se_cmd = NULL;
} else {
list_del_init(&cmd->queue_entry);
idr_remove(&udev->commands, id);
idr_remove(&udev->commands, i);
if (!test_bit(TCMU_CMD_BIT_EXPIRED, &cmd->flags)) {
+ WARN_ON(!cmd->se_cmd);
list_del_init(&cmd->queue_entry);
if (err_level == 1) {
/*
rapl_mmio_cpu_online, rapl_mmio_cpu_down_prep);
if (ret < 0) {
powercap_unregister_control_type(rapl_mmio_priv.control_type);
+ rapl_mmio_priv.control_type = NULL;
return ret;
}
rapl_mmio_priv.pcap_rapl_online = ret;
static void proc_thermal_rapl_remove(void)
{
+ if (IS_ERR_OR_NULL(rapl_mmio_priv.control_type))
+ return;
+
cpuhp_remove_state(rapl_mmio_priv.pcap_rapl_online);
powercap_unregister_control_type(rapl_mmio_priv.control_type);
}
* using the 2.6 Linux kernel kref construct.
*
* For direction on installation and usage of this driver please reference
- * Documentation/powerpc/hvcs.txt.
+ * Documentation/powerpc/hvcs.rst.
*/
#include <linux/device.h>
depends on SERIAL_VT8500=y
select SERIAL_CORE_CONSOLE
-config SERIAL_NETX
- tristate "NetX serial port support"
- depends on ARCH_NETX
- select SERIAL_CORE
- help
- If you have a machine based on a Hilscher NetX SoC you
- can enable its onboard serial port by enabling this option.
-
- To compile this driver as a module, choose M here: the
- module will be called netx-serial.
-
-config SERIAL_NETX_CONSOLE
- bool "Console on NetX serial port"
- depends on SERIAL_NETX=y
- select SERIAL_CORE_CONSOLE
- help
- If you have enabled the serial port on the Hilscher NetX SoC
- you can make it the console by answering Y to this option.
-
config SERIAL_OMAP
tristate "OMAP serial port support"
depends on ARCH_OMAP2PLUS
obj-$(CONFIG_SERIAL_UARTLITE) += uartlite.o
obj-$(CONFIG_SERIAL_MSM) += msm_serial.o
obj-$(CONFIG_SERIAL_QCOM_GENI) += qcom_geni_serial.o
-obj-$(CONFIG_SERIAL_NETX) += netx-serial.o
obj-$(CONFIG_SERIAL_KS8695) += serial_ks8695.o
obj-$(CONFIG_SERIAL_OMAP) += omap-serial.o
obj-$(CONFIG_SERIAL_ALTERA_UART) += altera_uart.o
/* Increment the module count when the debugger is active */
if (!kgdb_connected)
try_module_get(THIS_MODULE);
+
+ atomic_inc(&ignore_console_lock_warning);
}
static void kgdboc_post_exp_handler(void)
{
+ atomic_dec(&ignore_console_lock_warning);
+
/* decrement the module count when the debugger detaches */
if (!kgdb_connected)
module_put(THIS_MODULE);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- */
-
-#if defined(CONFIG_SERIAL_NETX_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ)
-#define SUPPORT_SYSRQ
-#endif
-
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/console.h>
-#include <linux/sysrq.h>
-#include <linux/platform_device.h>
-#include <linux/tty.h>
-#include <linux/tty_flip.h>
-#include <linux/serial_core.h>
-#include <linux/serial.h>
-
-#include <asm/io.h>
-#include <asm/irq.h>
-#include <mach/hardware.h>
-#include <mach/netx-regs.h>
-
-/* We've been assigned a range on the "Low-density serial ports" major */
-#define SERIAL_NX_MAJOR 204
-#define MINOR_START 170
-
-enum uart_regs {
- UART_DR = 0x00,
- UART_SR = 0x04,
- UART_LINE_CR = 0x08,
- UART_BAUDDIV_MSB = 0x0c,
- UART_BAUDDIV_LSB = 0x10,
- UART_CR = 0x14,
- UART_FR = 0x18,
- UART_IIR = 0x1c,
- UART_ILPR = 0x20,
- UART_RTS_CR = 0x24,
- UART_RTS_LEAD = 0x28,
- UART_RTS_TRAIL = 0x2c,
- UART_DRV_ENABLE = 0x30,
- UART_BRM_CR = 0x34,
- UART_RXFIFO_IRQLEVEL = 0x38,
- UART_TXFIFO_IRQLEVEL = 0x3c,
-};
-
-#define SR_FE (1<<0)
-#define SR_PE (1<<1)
-#define SR_BE (1<<2)
-#define SR_OE (1<<3)
-
-#define LINE_CR_BRK (1<<0)
-#define LINE_CR_PEN (1<<1)
-#define LINE_CR_EPS (1<<2)
-#define LINE_CR_STP2 (1<<3)
-#define LINE_CR_FEN (1<<4)
-#define LINE_CR_5BIT (0<<5)
-#define LINE_CR_6BIT (1<<5)
-#define LINE_CR_7BIT (2<<5)
-#define LINE_CR_8BIT (3<<5)
-#define LINE_CR_BITS_MASK (3<<5)
-
-#define CR_UART_EN (1<<0)
-#define CR_SIREN (1<<1)
-#define CR_SIRLP (1<<2)
-#define CR_MSIE (1<<3)
-#define CR_RIE (1<<4)
-#define CR_TIE (1<<5)
-#define CR_RTIE (1<<6)
-#define CR_LBE (1<<7)
-
-#define FR_CTS (1<<0)
-#define FR_DSR (1<<1)
-#define FR_DCD (1<<2)
-#define FR_BUSY (1<<3)
-#define FR_RXFE (1<<4)
-#define FR_TXFF (1<<5)
-#define FR_RXFF (1<<6)
-#define FR_TXFE (1<<7)
-
-#define IIR_MIS (1<<0)
-#define IIR_RIS (1<<1)
-#define IIR_TIS (1<<2)
-#define IIR_RTIS (1<<3)
-#define IIR_MASK 0xf
-
-#define RTS_CR_AUTO (1<<0)
-#define RTS_CR_RTS (1<<1)
-#define RTS_CR_COUNT (1<<2)
-#define RTS_CR_MOD2 (1<<3)
-#define RTS_CR_RTS_POL (1<<4)
-#define RTS_CR_CTS_CTR (1<<5)
-#define RTS_CR_CTS_POL (1<<6)
-#define RTS_CR_STICK (1<<7)
-
-#define UART_PORT_SIZE 0x40
-#define DRIVER_NAME "netx-uart"
-
-struct netx_port {
- struct uart_port port;
-};
-
-static void netx_stop_tx(struct uart_port *port)
-{
- unsigned int val;
- val = readl(port->membase + UART_CR);
- writel(val & ~CR_TIE, port->membase + UART_CR);
-}
-
-static void netx_stop_rx(struct uart_port *port)
-{
- unsigned int val;
- val = readl(port->membase + UART_CR);
- writel(val & ~CR_RIE, port->membase + UART_CR);
-}
-
-static void netx_enable_ms(struct uart_port *port)
-{
- unsigned int val;
- val = readl(port->membase + UART_CR);
- writel(val | CR_MSIE, port->membase + UART_CR);
-}
-
-static inline void netx_transmit_buffer(struct uart_port *port)
-{
- struct circ_buf *xmit = &port->state->xmit;
-
- if (port->x_char) {
- writel(port->x_char, port->membase + UART_DR);
- port->icount.tx++;
- port->x_char = 0;
- return;
- }
-
- if (uart_tx_stopped(port) || uart_circ_empty(xmit)) {
- netx_stop_tx(port);
- return;
- }
-
- do {
- /* send xmit->buf[xmit->tail]
- * out the port here */
- writel(xmit->buf[xmit->tail], port->membase + UART_DR);
- xmit->tail = (xmit->tail + 1) &
- (UART_XMIT_SIZE - 1);
- port->icount.tx++;
- if (uart_circ_empty(xmit))
- break;
- } while (!(readl(port->membase + UART_FR) & FR_TXFF));
-
- if (uart_circ_empty(xmit))
- netx_stop_tx(port);
-}
-
-static void netx_start_tx(struct uart_port *port)
-{
- writel(
- readl(port->membase + UART_CR) | CR_TIE, port->membase + UART_CR);
-
- if (!(readl(port->membase + UART_FR) & FR_TXFF))
- netx_transmit_buffer(port);
-}
-
-static unsigned int netx_tx_empty(struct uart_port *port)
-{
- return readl(port->membase + UART_FR) & FR_BUSY ? 0 : TIOCSER_TEMT;
-}
-
-static void netx_txint(struct uart_port *port)
-{
- struct circ_buf *xmit = &port->state->xmit;
-
- if (uart_circ_empty(xmit) || uart_tx_stopped(port)) {
- netx_stop_tx(port);
- return;
- }
-
- netx_transmit_buffer(port);
-
- if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
- uart_write_wakeup(port);
-}
-
-static void netx_rxint(struct uart_port *port, unsigned long *flags)
-{
- unsigned char rx, flg, status;
-
- while (!(readl(port->membase + UART_FR) & FR_RXFE)) {
- rx = readl(port->membase + UART_DR);
- flg = TTY_NORMAL;
- port->icount.rx++;
- status = readl(port->membase + UART_SR);
- if (status & SR_BE) {
- writel(0, port->membase + UART_SR);
- if (uart_handle_break(port))
- continue;
- }
-
- if (unlikely(status & (SR_FE | SR_PE | SR_OE))) {
-
- if (status & SR_PE)
- port->icount.parity++;
- else if (status & SR_FE)
- port->icount.frame++;
- if (status & SR_OE)
- port->icount.overrun++;
-
- status &= port->read_status_mask;
-
- if (status & SR_BE)
- flg = TTY_BREAK;
- else if (status & SR_PE)
- flg = TTY_PARITY;
- else if (status & SR_FE)
- flg = TTY_FRAME;
- }
-
- if (uart_handle_sysrq_char(port, rx))
- continue;
-
- uart_insert_char(port, status, SR_OE, rx, flg);
- }
-
- spin_unlock_irqrestore(&port->lock, *flags);
- tty_flip_buffer_push(&port->state->port);
- spin_lock_irqsave(&port->lock, *flags);
-}
-
-static irqreturn_t netx_int(int irq, void *dev_id)
-{
- struct uart_port *port = dev_id;
- unsigned long flags;
- unsigned char status;
-
- spin_lock_irqsave(&port->lock,flags);
-
- status = readl(port->membase + UART_IIR) & IIR_MASK;
- while (status) {
- if (status & IIR_RIS)
- netx_rxint(port, &flags);
- if (status & IIR_TIS)
- netx_txint(port);
- if (status & IIR_MIS) {
- if (readl(port->membase + UART_FR) & FR_CTS)
- uart_handle_cts_change(port, 1);
- else
- uart_handle_cts_change(port, 0);
- }
- writel(0, port->membase + UART_IIR);
- status = readl(port->membase + UART_IIR) & IIR_MASK;
- }
-
- spin_unlock_irqrestore(&port->lock,flags);
- return IRQ_HANDLED;
-}
-
-static unsigned int netx_get_mctrl(struct uart_port *port)
-{
- unsigned int ret = TIOCM_DSR | TIOCM_CAR;
-
- if (readl(port->membase + UART_FR) & FR_CTS)
- ret |= TIOCM_CTS;
-
- return ret;
-}
-
-static void netx_set_mctrl(struct uart_port *port, unsigned int mctrl)
-{
- unsigned int val;
-
- /* FIXME: Locking needed ? */
- if (mctrl & TIOCM_RTS) {
- val = readl(port->membase + UART_RTS_CR);
- writel(val | RTS_CR_RTS, port->membase + UART_RTS_CR);
- }
-}
-
-static void netx_break_ctl(struct uart_port *port, int break_state)
-{
- unsigned int line_cr;
- spin_lock_irq(&port->lock);
-
- line_cr = readl(port->membase + UART_LINE_CR);
- if (break_state != 0)
- line_cr |= LINE_CR_BRK;
- else
- line_cr &= ~LINE_CR_BRK;
- writel(line_cr, port->membase + UART_LINE_CR);
-
- spin_unlock_irq(&port->lock);
-}
-
-static int netx_startup(struct uart_port *port)
-{
- int ret;
-
- ret = request_irq(port->irq, netx_int, 0,
- DRIVER_NAME, port);
- if (ret) {
- dev_err(port->dev, "unable to grab irq%d\n",port->irq);
- goto exit;
- }
-
- writel(readl(port->membase + UART_LINE_CR) | LINE_CR_FEN,
- port->membase + UART_LINE_CR);
-
- writel(CR_MSIE | CR_RIE | CR_TIE | CR_RTIE | CR_UART_EN,
- port->membase + UART_CR);
-
-exit:
- return ret;
-}
-
-static void netx_shutdown(struct uart_port *port)
-{
- writel(0, port->membase + UART_CR) ;
-
- free_irq(port->irq, port);
-}
-
-static void
-netx_set_termios(struct uart_port *port, struct ktermios *termios,
- struct ktermios *old)
-{
- unsigned int baud, quot;
- unsigned char old_cr;
- unsigned char line_cr = LINE_CR_FEN;
- unsigned char rts_cr = 0;
-
- switch (termios->c_cflag & CSIZE) {
- case CS5:
- line_cr |= LINE_CR_5BIT;
- break;
- case CS6:
- line_cr |= LINE_CR_6BIT;
- break;
- case CS7:
- line_cr |= LINE_CR_7BIT;
- break;
- case CS8:
- line_cr |= LINE_CR_8BIT;
- break;
- }
-
- if (termios->c_cflag & CSTOPB)
- line_cr |= LINE_CR_STP2;
-
- if (termios->c_cflag & PARENB) {
- line_cr |= LINE_CR_PEN;
- if (!(termios->c_cflag & PARODD))
- line_cr |= LINE_CR_EPS;
- }
-
- if (termios->c_cflag & CRTSCTS)
- rts_cr = RTS_CR_AUTO | RTS_CR_CTS_CTR | RTS_CR_RTS_POL;
-
- baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk/16);
- quot = baud * 4096;
- quot /= 1000;
- quot *= 256;
- quot /= 100000;
-
- spin_lock_irq(&port->lock);
-
- uart_update_timeout(port, termios->c_cflag, baud);
-
- old_cr = readl(port->membase + UART_CR);
-
- /* disable interrupts */
- writel(old_cr & ~(CR_MSIE | CR_RIE | CR_TIE | CR_RTIE),
- port->membase + UART_CR);
-
- /* drain transmitter */
- while (readl(port->membase + UART_FR) & FR_BUSY);
-
- /* disable UART */
- writel(old_cr & ~CR_UART_EN, port->membase + UART_CR);
-
- /* modem status interrupts */
- old_cr &= ~CR_MSIE;
- if (UART_ENABLE_MS(port, termios->c_cflag))
- old_cr |= CR_MSIE;
-
- writel((quot>>8) & 0xff, port->membase + UART_BAUDDIV_MSB);
- writel(quot & 0xff, port->membase + UART_BAUDDIV_LSB);
- writel(line_cr, port->membase + UART_LINE_CR);
-
- writel(rts_cr, port->membase + UART_RTS_CR);
-
- /*
- * Characters to ignore
- */
- port->ignore_status_mask = 0;
- if (termios->c_iflag & IGNPAR)
- port->ignore_status_mask |= SR_PE;
- if (termios->c_iflag & IGNBRK) {
- port->ignore_status_mask |= SR_BE;
- /*
- * If we're ignoring parity and break indicators,
- * ignore overruns too (for real raw support).
- */
- if (termios->c_iflag & IGNPAR)
- port->ignore_status_mask |= SR_PE;
- }
-
- port->read_status_mask = 0;
- if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK))
- port->read_status_mask |= SR_BE;
- if (termios->c_iflag & INPCK)
- port->read_status_mask |= SR_PE | SR_FE;
-
- writel(old_cr, port->membase + UART_CR);
-
- spin_unlock_irq(&port->lock);
-}
-
-static const char *netx_type(struct uart_port *port)
-{
- return port->type == PORT_NETX ? "NETX" : NULL;
-}
-
-static void netx_release_port(struct uart_port *port)
-{
- release_mem_region(port->mapbase, UART_PORT_SIZE);
-}
-
-static int netx_request_port(struct uart_port *port)
-{
- return request_mem_region(port->mapbase, UART_PORT_SIZE,
- DRIVER_NAME) != NULL ? 0 : -EBUSY;
-}
-
-static void netx_config_port(struct uart_port *port, int flags)
-{
- if (flags & UART_CONFIG_TYPE && netx_request_port(port) == 0)
- port->type = PORT_NETX;
-}
-
-static int
-netx_verify_port(struct uart_port *port, struct serial_struct *ser)
-{
- int ret = 0;
-
- if (ser->type != PORT_UNKNOWN && ser->type != PORT_NETX)
- ret = -EINVAL;
-
- return ret;
-}
-
-static struct uart_ops netx_pops = {
- .tx_empty = netx_tx_empty,
- .set_mctrl = netx_set_mctrl,
- .get_mctrl = netx_get_mctrl,
- .stop_tx = netx_stop_tx,
- .start_tx = netx_start_tx,
- .stop_rx = netx_stop_rx,
- .enable_ms = netx_enable_ms,
- .break_ctl = netx_break_ctl,
- .startup = netx_startup,
- .shutdown = netx_shutdown,
- .set_termios = netx_set_termios,
- .type = netx_type,
- .release_port = netx_release_port,
- .request_port = netx_request_port,
- .config_port = netx_config_port,
- .verify_port = netx_verify_port,
-};
-
-static struct netx_port netx_ports[] = {
- {
- .port = {
- .type = PORT_NETX,
- .iotype = UPIO_MEM,
- .membase = (char __iomem *)io_p2v(NETX_PA_UART0),
- .mapbase = NETX_PA_UART0,
- .irq = NETX_IRQ_UART0,
- .uartclk = 100000000,
- .fifosize = 16,
- .flags = UPF_BOOT_AUTOCONF,
- .ops = &netx_pops,
- .line = 0,
- },
- }, {
- .port = {
- .type = PORT_NETX,
- .iotype = UPIO_MEM,
- .membase = (char __iomem *)io_p2v(NETX_PA_UART1),
- .mapbase = NETX_PA_UART1,
- .irq = NETX_IRQ_UART1,
- .uartclk = 100000000,
- .fifosize = 16,
- .flags = UPF_BOOT_AUTOCONF,
- .ops = &netx_pops,
- .line = 1,
- },
- }, {
- .port = {
- .type = PORT_NETX,
- .iotype = UPIO_MEM,
- .membase = (char __iomem *)io_p2v(NETX_PA_UART2),
- .mapbase = NETX_PA_UART2,
- .irq = NETX_IRQ_UART2,
- .uartclk = 100000000,
- .fifosize = 16,
- .flags = UPF_BOOT_AUTOCONF,
- .ops = &netx_pops,
- .line = 2,
- },
- }
-};
-
-#ifdef CONFIG_SERIAL_NETX_CONSOLE
-
-static void netx_console_putchar(struct uart_port *port, int ch)
-{
- while (readl(port->membase + UART_FR) & FR_BUSY);
- writel(ch, port->membase + UART_DR);
-}
-
-static void
-netx_console_write(struct console *co, const char *s, unsigned int count)
-{
- struct uart_port *port = &netx_ports[co->index].port;
- unsigned char cr_save;
-
- cr_save = readl(port->membase + UART_CR);
- writel(cr_save | CR_UART_EN, port->membase + UART_CR);
-
- uart_console_write(port, s, count, netx_console_putchar);
-
- while (readl(port->membase + UART_FR) & FR_BUSY);
- writel(cr_save, port->membase + UART_CR);
-}
-
-static void __init
-netx_console_get_options(struct uart_port *port, int *baud,
- int *parity, int *bits, int *flow)
-{
- unsigned char line_cr;
-
- *baud = (readl(port->membase + UART_BAUDDIV_MSB) << 8) |
- readl(port->membase + UART_BAUDDIV_LSB);
- *baud *= 1000;
- *baud /= 4096;
- *baud *= 1000;
- *baud /= 256;
- *baud *= 100;
-
- line_cr = readl(port->membase + UART_LINE_CR);
- *parity = 'n';
- if (line_cr & LINE_CR_PEN) {
- if (line_cr & LINE_CR_EPS)
- *parity = 'e';
- else
- *parity = 'o';
- }
-
- switch (line_cr & LINE_CR_BITS_MASK) {
- case LINE_CR_8BIT:
- *bits = 8;
- break;
- case LINE_CR_7BIT:
- *bits = 7;
- break;
- case LINE_CR_6BIT:
- *bits = 6;
- break;
- case LINE_CR_5BIT:
- *bits = 5;
- break;
- }
-
- if (readl(port->membase + UART_RTS_CR) & RTS_CR_AUTO)
- *flow = 'r';
-}
-
-static int __init
-netx_console_setup(struct console *co, char *options)
-{
- struct netx_port *sport;
- int baud = 9600;
- int bits = 8;
- int parity = 'n';
- int flow = 'n';
-
- /*
- * Check whether an invalid uart number has been specified, and
- * if so, search for the first available port that does have
- * console support.
- */
- if (co->index == -1 || co->index >= ARRAY_SIZE(netx_ports))
- co->index = 0;
- sport = &netx_ports[co->index];
-
- if (options) {
- uart_parse_options(options, &baud, &parity, &bits, &flow);
- } else {
- /* if the UART is enabled, assume it has been correctly setup
- * by the bootloader and get the options
- */
- if (readl(sport->port.membase + UART_CR) & CR_UART_EN) {
- netx_console_get_options(&sport->port, &baud,
- &parity, &bits, &flow);
- }
-
- }
-
- return uart_set_options(&sport->port, co, baud, parity, bits, flow);
-}
-
-static struct uart_driver netx_reg;
-static struct console netx_console = {
- .name = "ttyNX",
- .write = netx_console_write,
- .device = uart_console_device,
- .setup = netx_console_setup,
- .flags = CON_PRINTBUFFER,
- .index = -1,
- .data = &netx_reg,
-};
-
-static int __init netx_console_init(void)
-{
- register_console(&netx_console);
- return 0;
-}
-console_initcall(netx_console_init);
-
-#define NETX_CONSOLE &netx_console
-#else
-#define NETX_CONSOLE NULL
-#endif
-
-static struct uart_driver netx_reg = {
- .owner = THIS_MODULE,
- .driver_name = DRIVER_NAME,
- .dev_name = "ttyNX",
- .major = SERIAL_NX_MAJOR,
- .minor = MINOR_START,
- .nr = ARRAY_SIZE(netx_ports),
- .cons = NETX_CONSOLE,
-};
-
-static int serial_netx_suspend(struct platform_device *pdev, pm_message_t state)
-{
- struct netx_port *sport = platform_get_drvdata(pdev);
-
- if (sport)
- uart_suspend_port(&netx_reg, &sport->port);
-
- return 0;
-}
-
-static int serial_netx_resume(struct platform_device *pdev)
-{
- struct netx_port *sport = platform_get_drvdata(pdev);
-
- if (sport)
- uart_resume_port(&netx_reg, &sport->port);
-
- return 0;
-}
-
-static int serial_netx_probe(struct platform_device *pdev)
-{
- struct uart_port *port = &netx_ports[pdev->id].port;
-
- dev_info(&pdev->dev, "initialising\n");
-
- port->dev = &pdev->dev;
-
- writel(1, port->membase + UART_RXFIFO_IRQLEVEL);
- uart_add_one_port(&netx_reg, &netx_ports[pdev->id].port);
- platform_set_drvdata(pdev, &netx_ports[pdev->id]);
-
- return 0;
-}
-
-static int serial_netx_remove(struct platform_device *pdev)
-{
- struct netx_port *sport = platform_get_drvdata(pdev);
-
- if (sport)
- uart_remove_one_port(&netx_reg, &sport->port);
-
- return 0;
-}
-
-static struct platform_driver serial_netx_driver = {
- .probe = serial_netx_probe,
- .remove = serial_netx_remove,
-
- .suspend = serial_netx_suspend,
- .resume = serial_netx_resume,
-
- .driver = {
- .name = DRIVER_NAME,
- },
-};
-
-static int __init netx_serial_init(void)
-{
- int ret;
-
- printk(KERN_INFO "Serial: NetX driver\n");
-
- ret = uart_register_driver(&netx_reg);
- if (ret)
- return ret;
-
- ret = platform_driver_register(&serial_netx_driver);
- if (ret != 0)
- uart_unregister_driver(&netx_reg);
-
- return 0;
-}
-
-static void __exit netx_serial_exit(void)
-{
- platform_driver_unregister(&serial_netx_driver);
- uart_unregister_driver(&netx_reg);
-}
-
-module_init(netx_serial_init);
-module_exit(netx_serial_exit);
-
-MODULE_AUTHOR("Sascha Hauer");
-MODULE_DESCRIPTION("NetX serial port driver");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:" DRIVER_NAME);
list_for_each_entry_safe(waiter, next, &sem->read_wait, list) {
tsk = waiter->task;
- smp_mb();
- waiter->task = NULL;
+ smp_store_release(&waiter->task, NULL);
wake_up_process(tsk);
put_task_struct(tsk);
}
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
- if (!waiter.task)
+ if (!smp_load_acquire(&waiter.task))
break;
if (!timeout)
break;
char *buf)
{
struct con_driver *con = dev_get_drvdata(dev);
- int bind = con_is_bound(con->con);
+ int bind;
+
+ console_lock();
+ bind = con_is_bound(con->con);
+ console_unlock();
return snprintf(buf, PAGE_SIZE, "%i\n", bind);
}
imx_disable_unprepare_clks(dev);
disable_hsic_regulator:
if (data->hsic_pad_regulator)
- ret = regulator_disable(data->hsic_pad_regulator);
+ /* don't overwrite original ret (cf. EPROBE_DEFER) */
+ regulator_disable(data->hsic_pad_regulator);
if (pdata.flags & CI_HDRC_PMQOS)
pm_qos_remove_request(&data->pm_qos_req);
+ data->ci_pdev = NULL;
return ret;
}
pm_runtime_disable(&pdev->dev);
pm_runtime_put_noidle(&pdev->dev);
}
- ci_hdrc_remove_device(data->ci_pdev);
+ if (data->ci_pdev)
+ ci_hdrc_remove_device(data->ci_pdev);
if (data->override_phy_control)
usb_phy_shutdown(data->phy);
- imx_disable_unprepare_clks(&pdev->dev);
- if (data->plat_data->flags & CI_HDRC_PMQOS)
- pm_qos_remove_request(&data->pm_qos_req);
- if (data->hsic_pad_regulator)
- regulator_disable(data->hsic_pad_regulator);
+ if (data->ci_pdev) {
+ imx_disable_unprepare_clks(&pdev->dev);
+ if (data->plat_data->flags & CI_HDRC_PMQOS)
+ pm_qos_remove_request(&data->pm_qos_req);
+ if (data->hsic_pad_regulator)
+ regulator_disable(data->hsic_pad_regulator);
+ }
return 0;
}
struct ci_hdrc *ci = container_of(gadget, struct ci_hdrc, gadget);
unsigned long flags;
- spin_lock_irqsave(&ci->lock, flags);
- ci->gadget.speed = USB_SPEED_UNKNOWN;
- ci->remote_wakeup = 0;
- ci->suspended = 0;
- spin_unlock_irqrestore(&ci->lock, flags);
-
/* flush all endpoints */
gadget_for_each_ep(ep, gadget) {
usb_ep_fifo_flush(ep);
ci->status = NULL;
}
+ spin_lock_irqsave(&ci->lock, flags);
+ ci->gadget.speed = USB_SPEED_UNKNOWN;
+ ci->remote_wakeup = 0;
+ ci->suspended = 0;
+ spin_unlock_irqrestore(&ci->lock, flags);
+
return 0;
}
return -EBUSY;
spin_lock_irqsave(hwep->lock, flags);
+ if (hwep->ci->gadget.speed == USB_SPEED_UNKNOWN) {
+ spin_unlock_irqrestore(hwep->lock, flags);
+ return 0;
+ }
/* only internal SW should disable ctrl endpts */
return -EINVAL;
spin_lock_irqsave(hwep->lock, flags);
+ if (hwep->ci->gadget.speed == USB_SPEED_UNKNOWN) {
+ spin_unlock_irqrestore(hwep->lock, flags);
+ return 0;
+ }
retval = _ep_queue(ep, req, gfp_flags);
spin_unlock_irqrestore(hwep->lock, flags);
return retval;
return -EINVAL;
spin_lock_irqsave(hwep->lock, flags);
-
- hw_ep_flush(hwep->ci, hwep->num, hwep->dir);
+ if (hwep->ci->gadget.speed != USB_SPEED_UNKNOWN)
+ hw_ep_flush(hwep->ci, hwep->num, hwep->dir);
list_for_each_entry_safe(node, tmpnode, &hwreq->tds, td) {
dma_pool_free(hwep->td_pool, node->ptr, node->dma);
}
spin_lock_irqsave(hwep->lock, flags);
+ if (hwep->ci->gadget.speed == USB_SPEED_UNKNOWN) {
+ spin_unlock_irqrestore(hwep->lock, flags);
+ return;
+ }
hw_ep_flush(hwep->ci, hwep->num, hwep->dir);
int ret = 0;
spin_lock_irqsave(&ci->lock, flags);
+ if (ci->gadget.speed == USB_SPEED_UNKNOWN) {
+ spin_unlock_irqrestore(&ci->lock, flags);
+ return 0;
+ }
if (!ci->remote_wakeup) {
ret = -EOPNOTSUPP;
goto out;
tty_port_init(&acm->port);
acm->port.ops = &acm_port_ops;
- minor = acm_alloc_minor(acm);
- if (minor < 0)
- goto alloc_fail1;
-
ctrlsize = usb_endpoint_maxp(epctrl);
readsize = usb_endpoint_maxp(epread) *
(quirks == SINGLE_RX_URB ? 1 : 2);
acm->writesize = usb_endpoint_maxp(epwrite) * 20;
acm->control = control_interface;
acm->data = data_interface;
+
+ usb_get_intf(acm->control); /* undone in destruct() */
+
+ minor = acm_alloc_minor(acm);
+ if (minor < 0)
+ goto alloc_fail1;
+
acm->minor = minor;
acm->dev = usb_dev;
if (h.usb_cdc_acm_descriptor)
usb_driver_claim_interface(&acm_driver, data_interface, acm);
usb_set_intfdata(data_interface, acm);
- usb_get_intf(control_interface);
tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor,
&control_interface->dev);
if (IS_ERR(tty_dev)) {
{
struct wdm_device *desc = file->private_data;
- wait_event(desc->wait, !test_bit(WDM_IN_USE, &desc->flags));
+ wait_event(desc->wait,
+ /*
+ * needs both flags. We cannot do with one
+ * because resetting it would cause a race
+ * with write() yet we need to signal
+ * a disconnect
+ */
+ !test_bit(WDM_IN_USE, &desc->flags) ||
+ test_bit(WDM_DISCONNECTING, &desc->flags));
/* cannot dereference desc->intf if WDM_DISCONNECTING */
- if (desc->werr < 0 && !test_bit(WDM_DISCONNECTING, &desc->flags))
+ if (test_bit(WDM_DISCONNECTING, &desc->flags))
+ return -ENODEV;
+ if (desc->werr < 0)
dev_err(&desc->intf->dev, "Error in flush path: %d\n",
desc->werr);
spin_lock_irqsave(&desc->iuspin, flags);
set_bit(WDM_DISCONNECTING, &desc->flags);
set_bit(WDM_READ, &desc->flags);
- /* to terminate pending flushes */
- clear_bit(WDM_IN_USE, &desc->flags);
spin_unlock_irqrestore(&desc->iuspin, flags);
wake_up_all(&desc->wait);
mutex_lock(&desc->rlock);
goto err_put;
}
+ retcode = -EINVAL;
data->bulk_in = bulk_in->bEndpointAddress;
data->wMaxPacketSize = usb_endpoint_maxp(bulk_in);
+ if (!data->wMaxPacketSize)
+ goto err_put;
dev_dbg(&intf->dev, "Found bulk in endpoint at %u\n", data->bulk_in);
data->bulk_out = bulk_out->bEndpointAddress;
char name[16];
int i, size;
- if (!IS_ENABLED(CONFIG_HAS_DMA) ||
- (!is_device_dma_capable(hcd->self.sysdev) &&
- !hcd->localmem_pool))
+ if (hcd->localmem_pool || !hcd_uses_dma(hcd))
return 0;
for (i = 0; i < HCD_BUFFER_POOLS; i++) {
return gen_pool_dma_alloc(hcd->localmem_pool, size, dma);
/* some USB hosts just use PIO */
- if (!IS_ENABLED(CONFIG_HAS_DMA) ||
- !is_device_dma_capable(bus->sysdev)) {
+ if (!hcd_uses_dma(hcd)) {
*dma = ~(dma_addr_t) 0;
return kmalloc(size, mem_flags);
}
return;
}
- if (!IS_ENABLED(CONFIG_HAS_DMA) ||
- !is_device_dma_capable(bus->sysdev)) {
+ if (!hcd_uses_dma(hcd)) {
kfree(addr);
return;
}
return 0;
error:
- if (as && as->usbm)
- dec_usb_memory_use_count(as->usbm, &as->usbm->urb_use_count);
kfree(isopkt);
kfree(dr);
if (as)
intf->minor = minor;
break;
}
- up_write(&minor_rwsem);
- if (intf->minor < 0)
+ if (intf->minor < 0) {
+ up_write(&minor_rwsem);
return -EXFULL;
+ }
/* create a usb class device for this usb interface */
snprintf(name, sizeof(name), class_driver->name, minor - minor_base);
MKDEV(USB_MAJOR, minor), class_driver,
"%s", kbasename(name));
if (IS_ERR(intf->usb_dev)) {
- down_write(&minor_rwsem);
usb_minors[minor] = NULL;
intf->minor = -1;
- up_write(&minor_rwsem);
retval = PTR_ERR(intf->usb_dev);
}
+ up_write(&minor_rwsem);
return retval;
}
EXPORT_SYMBOL_GPL(usb_register_dev);
return;
dev_dbg(&intf->dev, "removing %d minor\n", intf->minor);
+ device_destroy(usb_class->class, MKDEV(USB_MAJOR, intf->minor));
down_write(&minor_rwsem);
usb_minors[intf->minor] = NULL;
up_write(&minor_rwsem);
- device_destroy(usb_class->class, MKDEV(USB_MAJOR, intf->minor));
intf->usb_dev = NULL;
intf->minor = -1;
destroy_usb_class();
/* EHCI, OHCI */
hcd->rsrc_start = pci_resource_start(dev, 0);
hcd->rsrc_len = pci_resource_len(dev, 0);
- if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len,
- driver->description)) {
+ if (!devm_request_mem_region(&dev->dev, hcd->rsrc_start,
+ hcd->rsrc_len, driver->description)) {
dev_dbg(&dev->dev, "controller already in use\n");
retval = -EBUSY;
goto put_hcd;
}
- hcd->regs = ioremap_nocache(hcd->rsrc_start, hcd->rsrc_len);
+ hcd->regs = devm_ioremap_nocache(&dev->dev, hcd->rsrc_start,
+ hcd->rsrc_len);
if (hcd->regs == NULL) {
dev_dbg(&dev->dev, "error mapping memory\n");
retval = -EFAULT;
- goto release_mem_region;
+ goto put_hcd;
}
} else {
hcd->rsrc_start = pci_resource_start(dev, region);
hcd->rsrc_len = pci_resource_len(dev, region);
- if (request_region(hcd->rsrc_start, hcd->rsrc_len,
- driver->description))
+ if (devm_request_region(&dev->dev, hcd->rsrc_start,
+ hcd->rsrc_len, driver->description))
break;
}
if (region == PCI_ROM_RESOURCE) {
}
if (retval != 0)
- goto unmap_registers;
+ goto put_hcd;
device_wakeup_enable(hcd->self.controller);
if (pci_dev_run_wake(dev))
pm_runtime_put_noidle(&dev->dev);
return retval;
-unmap_registers:
- if (driver->flags & HCD_MEMORY) {
- iounmap(hcd->regs);
-release_mem_region:
- release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
- } else
- release_region(hcd->rsrc_start, hcd->rsrc_len);
put_hcd:
usb_put_hcd(hcd);
disable_pci:
dev_set_drvdata(&dev->dev, NULL);
up_read(&companions_rwsem);
}
-
- if (hcd->driver->flags & HCD_MEMORY) {
- iounmap(hcd->regs);
- release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
- } else {
- release_region(hcd->rsrc_start, hcd->rsrc_len);
- }
-
usb_put_hcd(hcd);
pci_disable_device(dev);
}
/* wait queue for synchronous unlinks */
DECLARE_WAIT_QUEUE_HEAD(usb_kill_urb_queue);
-static inline int is_root_hub(struct usb_device *udev)
-{
- return (udev->parent == NULL);
-}
-
/*-------------------------------------------------------------------------*/
/*
}
-
-/*
- * Show & store the current value of authorized_default
- */
-static ssize_t authorized_default_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct usb_device *rh_usb_dev = to_usb_device(dev);
- struct usb_bus *usb_bus = rh_usb_dev->bus;
- struct usb_hcd *hcd;
-
- hcd = bus_to_hcd(usb_bus);
- return snprintf(buf, PAGE_SIZE, "%u\n", hcd->dev_policy);
-}
-
-static ssize_t authorized_default_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t size)
-{
- ssize_t result;
- unsigned val;
- struct usb_device *rh_usb_dev = to_usb_device(dev);
- struct usb_bus *usb_bus = rh_usb_dev->bus;
- struct usb_hcd *hcd;
-
- hcd = bus_to_hcd(usb_bus);
- result = sscanf(buf, "%u\n", &val);
- if (result == 1) {
- hcd->dev_policy = val <= USB_DEVICE_AUTHORIZE_INTERNAL ?
- val : USB_DEVICE_AUTHORIZE_ALL;
- result = size;
- } else {
- result = -EINVAL;
- }
- return result;
-}
-static DEVICE_ATTR_RW(authorized_default);
-
-/*
- * interface_authorized_default_show - show default authorization status
- * for USB interfaces
- *
- * note: interface_authorized_default is the default value
- * for initializing the authorized attribute of interfaces
- */
-static ssize_t interface_authorized_default_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct usb_device *usb_dev = to_usb_device(dev);
- struct usb_hcd *hcd = bus_to_hcd(usb_dev->bus);
-
- return sprintf(buf, "%u\n", !!HCD_INTF_AUTHORIZED(hcd));
-}
-
-/*
- * interface_authorized_default_store - store default authorization status
- * for USB interfaces
- *
- * note: interface_authorized_default is the default value
- * for initializing the authorized attribute of interfaces
- */
-static ssize_t interface_authorized_default_store(struct device *dev,
- struct device_attribute *attr, const char *buf, size_t count)
-{
- struct usb_device *usb_dev = to_usb_device(dev);
- struct usb_hcd *hcd = bus_to_hcd(usb_dev->bus);
- int rc = count;
- bool val;
-
- if (strtobool(buf, &val) != 0)
- return -EINVAL;
-
- if (val)
- set_bit(HCD_FLAG_INTF_AUTHORIZED, &hcd->flags);
- else
- clear_bit(HCD_FLAG_INTF_AUTHORIZED, &hcd->flags);
-
- return rc;
-}
-static DEVICE_ATTR_RW(interface_authorized_default);
-
-/* Group all the USB bus attributes */
-static struct attribute *usb_bus_attrs[] = {
- &dev_attr_authorized_default.attr,
- &dev_attr_interface_authorized_default.attr,
- NULL,
-};
-
-static const struct attribute_group usb_bus_attr_group = {
- .name = NULL, /* we want them in the same directory */
- .attrs = usb_bus_attrs,
-};
-
-
-
/*-------------------------------------------------------------------------*/
/**
if (usb_endpoint_xfer_control(&urb->ep->desc)) {
if (hcd->self.uses_pio_for_control)
return ret;
- if (IS_ENABLED(CONFIG_HAS_DMA) && hcd->self.uses_dma) {
+ if (hcd_uses_dma(hcd)) {
if (is_vmalloc_addr(urb->setup_packet)) {
WARN_ONCE(1, "setup packet is not dma capable\n");
return -EAGAIN;
dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
if (urb->transfer_buffer_length != 0
&& !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) {
- if (IS_ENABLED(CONFIG_HAS_DMA) && hcd->self.uses_dma) {
+ if (hcd_uses_dma(hcd)) {
if (urb->num_sgs) {
int n;
if (retval != 0)
goto err_register_root_hub;
- retval = sysfs_create_group(&rhdev->dev.kobj, &usb_bus_attr_group);
- if (retval < 0) {
- printk(KERN_ERR "Cannot register USB bus sysfs attributes: %d\n",
- retval);
- goto error_create_attr_group;
- }
if (hcd->uses_new_polling && HCD_POLL_RH(hcd))
usb_hcd_poll_rh_status(hcd);
return retval;
-error_create_attr_group:
- clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
- if (HC_IS_RUNNING(hcd->state))
- hcd->state = HC_STATE_QUIESCING;
- spin_lock_irq(&hcd_root_hub_lock);
- hcd->rh_registered = 0;
- spin_unlock_irq(&hcd_root_hub_lock);
-
-#ifdef CONFIG_PM
- cancel_work_sync(&hcd->wakeup_work);
-#endif
- cancel_work_sync(&hcd->died_work);
- mutex_lock(&usb_bus_idr_lock);
- usb_disconnect(&rhdev); /* Sets rhdev to NULL */
- mutex_unlock(&usb_bus_idr_lock);
err_register_root_hub:
hcd->rh_pollable = 0;
clear_bit(HCD_FLAG_POLL_RH, &hcd->flags);
dev_info(hcd->self.controller, "remove, state %x\n", hcd->state);
usb_get_dev(rhdev);
- sysfs_remove_group(&rhdev->dev.kobj, &usb_bus_attr_group);
-
clear_bit(HCD_FLAG_RH_RUNNING, &hcd->flags);
if (HC_IS_RUNNING (hcd->state))
hcd->state = HC_STATE_QUIESCING;
local_mem = devm_memremap(hcd->self.sysdev, phys_addr,
size, MEMREMAP_WC);
- if (!local_mem)
- return -ENOMEM;
+ if (IS_ERR(local_mem))
+ return PTR_ERR(local_mem);
/*
* Here we pass a dma_addr_t but the arg type is a phys_addr_t.
(struct usb_cdc_dmm_desc *)buffer;
break;
case USB_CDC_MDLM_TYPE:
- if (elength < sizeof(struct usb_cdc_mdlm_desc *))
+ if (elength < sizeof(struct usb_cdc_mdlm_desc))
goto next_desc;
if (desc)
return -EINVAL;
desc = (struct usb_cdc_mdlm_desc *)buffer;
break;
case USB_CDC_MDLM_DETAIL_TYPE:
- if (elength < sizeof(struct usb_cdc_mdlm_detail_desc *))
+ if (elength < sizeof(struct usb_cdc_mdlm_detail_desc))
goto next_desc;
if (detail)
return -EINVAL;
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/usb.h>
+#include <linux/usb/hcd.h>
#include <linux/usb/quirks.h>
#include <linux/of.h>
#include "usb.h"
.size = 18 + 65535, /* dev descr + max-size raw descriptor */
};
+/*
+ * Show & store the current value of authorized_default
+ */
+static ssize_t authorized_default_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct usb_device *rh_usb_dev = to_usb_device(dev);
+ struct usb_bus *usb_bus = rh_usb_dev->bus;
+ struct usb_hcd *hcd;
+
+ hcd = bus_to_hcd(usb_bus);
+ return snprintf(buf, PAGE_SIZE, "%u\n", hcd->dev_policy);
+}
+
+static ssize_t authorized_default_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ ssize_t result;
+ unsigned int val;
+ struct usb_device *rh_usb_dev = to_usb_device(dev);
+ struct usb_bus *usb_bus = rh_usb_dev->bus;
+ struct usb_hcd *hcd;
+
+ hcd = bus_to_hcd(usb_bus);
+ result = sscanf(buf, "%u\n", &val);
+ if (result == 1) {
+ hcd->dev_policy = val <= USB_DEVICE_AUTHORIZE_INTERNAL ?
+ val : USB_DEVICE_AUTHORIZE_ALL;
+ result = size;
+ } else {
+ result = -EINVAL;
+ }
+ return result;
+}
+static DEVICE_ATTR_RW(authorized_default);
+
+/*
+ * interface_authorized_default_show - show default authorization status
+ * for USB interfaces
+ *
+ * note: interface_authorized_default is the default value
+ * for initializing the authorized attribute of interfaces
+ */
+static ssize_t interface_authorized_default_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct usb_device *usb_dev = to_usb_device(dev);
+ struct usb_hcd *hcd = bus_to_hcd(usb_dev->bus);
+
+ return sprintf(buf, "%u\n", !!HCD_INTF_AUTHORIZED(hcd));
+}
+
+/*
+ * interface_authorized_default_store - store default authorization status
+ * for USB interfaces
+ *
+ * note: interface_authorized_default is the default value
+ * for initializing the authorized attribute of interfaces
+ */
+static ssize_t interface_authorized_default_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t count)
+{
+ struct usb_device *usb_dev = to_usb_device(dev);
+ struct usb_hcd *hcd = bus_to_hcd(usb_dev->bus);
+ int rc = count;
+ bool val;
+
+ if (strtobool(buf, &val) != 0)
+ return -EINVAL;
+
+ if (val)
+ set_bit(HCD_FLAG_INTF_AUTHORIZED, &hcd->flags);
+ else
+ clear_bit(HCD_FLAG_INTF_AUTHORIZED, &hcd->flags);
+
+ return rc;
+}
+static DEVICE_ATTR_RW(interface_authorized_default);
+
+/* Group all the USB bus attributes */
+static struct attribute *usb_bus_attrs[] = {
+ &dev_attr_authorized_default.attr,
+ &dev_attr_interface_authorized_default.attr,
+ NULL,
+};
+
+static const struct attribute_group usb_bus_attr_group = {
+ .name = NULL, /* we want them in the same directory */
+ .attrs = usb_bus_attrs,
+};
+
+
+static int add_default_authorized_attributes(struct device *dev)
+{
+ int rc = 0;
+
+ if (is_usb_device(dev))
+ rc = sysfs_create_group(&dev->kobj, &usb_bus_attr_group);
+
+ return rc;
+}
+
+static void remove_default_authorized_attributes(struct device *dev)
+{
+ if (is_usb_device(dev)) {
+ sysfs_remove_group(&dev->kobj, &usb_bus_attr_group);
+ }
+}
+
int usb_create_sysfs_dev_files(struct usb_device *udev)
{
struct device *dev = &udev->dev;
retval = add_power_attributes(dev);
if (retval)
goto error;
+
+ if (is_root_hub(udev)) {
+ retval = add_default_authorized_attributes(dev);
+ if (retval)
+ goto error;
+ }
return retval;
+
error:
usb_remove_sysfs_dev_files(udev);
return retval;
{
struct device *dev = &udev->dev;
+ if (is_root_hub(udev))
+ remove_default_authorized_attributes(dev);
+
remove_power_attributes(dev);
remove_persist_attributes(dev);
device_remove_bin_file(dev, &dev_bin_attr_descriptors);
return dev->type == &usb_port_device_type;
}
+static inline int is_root_hub(struct usb_device *udev)
+{
+ return (udev->parent == NULL);
+}
+
/* Do the same for device drivers and interface drivers. */
static inline int is_usb_device_driver(struct device_driver *drv)
buf = urb->transfer_buffer;
- if (hcd->self.uses_dma) {
+ if (hcd_uses_dma(hcd)) {
if (!buf && (urb->transfer_dma & 3)) {
dev_err(hsotg->dev,
"%s: unaligned transfer with no transfer_buffer",
* disconnect callbacks?
*/
spin_lock_irqsave(&cdev->lock, flags);
+ cdev->suspended = 0;
if (cdev->config)
reset_config(cdev);
if (cdev->driver->disconnect)
struct fsg_common {
struct usb_gadget *gadget;
struct usb_composite_dev *cdev;
- struct fsg_dev *fsg, *new_fsg;
+ struct fsg_dev *fsg;
wait_queue_head_t io_wait;
wait_queue_head_t fsg_wait;
unsigned int bulk_out_maxpacket;
enum fsg_state state; /* For exception handling */
unsigned int exception_req_tag;
+ void *exception_arg;
enum data_direction data_dir;
u32 data_size;
/* These routines may be called in process context or in_irq */
-static void raise_exception(struct fsg_common *common, enum fsg_state new_state)
+static void __raise_exception(struct fsg_common *common, enum fsg_state new_state,
+ void *arg)
{
unsigned long flags;
if (common->state <= new_state) {
common->exception_req_tag = common->ep0_req_tag;
common->state = new_state;
+ common->exception_arg = arg;
if (common->thread_task)
send_sig_info(SIGUSR1, SEND_SIG_PRIV,
common->thread_task);
spin_unlock_irqrestore(&common->lock, flags);
}
+static void raise_exception(struct fsg_common *common, enum fsg_state new_state)
+{
+ __raise_exception(common, new_state, NULL);
+}
/*-------------------------------------------------------------------------*/
static int fsg_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
{
struct fsg_dev *fsg = fsg_from_func(f);
- fsg->common->new_fsg = fsg;
- raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE);
+
+ __raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE, fsg);
return USB_GADGET_DELAYED_STATUS;
}
static void fsg_disable(struct usb_function *f)
{
struct fsg_dev *fsg = fsg_from_func(f);
- fsg->common->new_fsg = NULL;
- raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE);
+
+ __raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE, NULL);
}
enum fsg_state old_state;
struct fsg_lun *curlun;
unsigned int exception_req_tag;
+ struct fsg_dev *new_fsg;
/*
* Clear the existing signals. Anything but SIGUSR1 is converted
common->next_buffhd_to_fill = &common->buffhds[0];
common->next_buffhd_to_drain = &common->buffhds[0];
exception_req_tag = common->exception_req_tag;
+ new_fsg = common->exception_arg;
old_state = common->state;
common->state = FSG_STATE_NORMAL;
break;
case FSG_STATE_CONFIG_CHANGE:
- do_set_interface(common, common->new_fsg);
- if (common->new_fsg)
+ do_set_interface(common, new_fsg);
+ if (new_fsg)
usb_composite_setup_continue(common->cdev);
break;
DBG(fsg, "unbind\n");
if (fsg->common->fsg == fsg) {
- fsg->common->new_fsg = NULL;
- raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE);
+ __raise_exception(fsg->common, FSG_STATE_CONFIG_CHANGE, NULL);
/* FIXME: make interruptible or killable somehow? */
wait_event(common->fsg_wait, common->fsg != fsg);
}
default:
break;
}
-
+ break;
case USB_REQ_SET_ADDRESS:
if (reqtype == (USB_TYPE_STANDARD | USB_RECIP_DEVICE)) {
#include <linux/pm_runtime.h>
#include <linux/sizes.h>
#include <linux/slab.h>
+#include <linux/string.h>
#include <linux/sys_soc.h>
#include <linux/uaccess.h>
#include <linux/usb/ch9.h>
if (usb3->forced_b_device)
return -EBUSY;
- if (!strncmp(buf, "host", strlen("host")))
+ if (sysfs_streq(buf, "host"))
new_mode_is_host = true;
- else if (!strncmp(buf, "peripheral", strlen("peripheral")))
+ else if (sysfs_streq(buf, "peripheral"))
new_mode_is_host = false;
else
return -EINVAL;
break;
case PCI_VENDOR_ID_AMD:
/* AMD PLL quirk */
- if (usb_amd_find_chipset_info())
+ if (usb_amd_quirk_pll_check())
ehci->amd_pll_fix = 1;
/* AMD8111 EHCI doesn't work, according to AMD errata */
if (pdev->device == 0x7463) {
break;
case PCI_VENDOR_ID_ATI:
/* AMD PLL quirk */
- if (usb_amd_find_chipset_info())
+ if (usb_amd_quirk_pll_check())
ehci->amd_pll_fix = 1;
/*
/* see what we found out */
temp = check_reset_complete(fotg210, wIndex, status_reg,
fotg210_readl(fotg210, status_reg));
+
+ /* restart schedule */
+ fotg210->command |= CMD_RUN;
+ fotg210_writel(fotg210, fotg210->command, &fotg210->regs->command);
}
if (!(temp & (PORT_RESUME|PORT_RESET))) {
return result;
error_set_cluster_id:
- wusb_cluster_id_put(wusbhc->cluster_id);
+ wusb_cluster_id_put(addr);
error_cluster_id_get:
goto out;
* other cases where the next software may expect clean state from the
* "firmware". this is bus-neutral, unlike shutdown() methods.
*/
-static void
-ohci_shutdown (struct usb_hcd *hcd)
+static void _ohci_shutdown(struct usb_hcd *hcd)
{
struct ohci_hcd *ohci;
ohci->rh_state = OHCI_RH_HALTED;
}
+static void ohci_shutdown(struct usb_hcd *hcd)
+{
+ struct ohci_hcd *ohci = hcd_to_ohci(hcd);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ohci->lock, flags);
+ _ohci_shutdown(hcd);
+ spin_unlock_irqrestore(&ohci->lock, flags);
+}
+
/*-------------------------------------------------------------------------*
* HC functions
*-------------------------------------------------------------------------*/
died:
usb_hc_died(ohci_to_hcd(ohci));
ohci_dump(ohci);
- ohci_shutdown(ohci_to_hcd(ohci));
+ _ohci_shutdown(ohci_to_hcd(ohci));
goto done;
} else {
/* No write back because the done queue was empty */
{
struct ohci_hcd *ohci = hcd_to_ohci(hcd);
- if (usb_amd_find_chipset_info())
+ if (usb_amd_quirk_pll_check())
ohci->flags |= OHCI_QUIRK_AMD_PLL;
/* SB800 needs pre-fetch fix */
struct amd_chipset_type sb_type;
int isoc_reqs;
int probe_count;
- int probe_result;
+ bool need_pll_quirk;
} amd_chipset;
static DEFINE_SPINLOCK(amd_lock);
}
EXPORT_SYMBOL_GPL(sb800_prefetch);
-int usb_amd_find_chipset_info(void)
+static void usb_amd_find_chipset_info(void)
{
unsigned long flags;
struct amd_chipset_info info;
- int ret;
+ info.need_pll_quirk = 0;
spin_lock_irqsave(&amd_lock, flags);
if (amd_chipset.probe_count > 0) {
amd_chipset.probe_count++;
spin_unlock_irqrestore(&amd_lock, flags);
- return amd_chipset.probe_result;
+ return;
}
memset(&info, 0, sizeof(info));
spin_unlock_irqrestore(&amd_lock, flags);
if (!amd_chipset_sb_type_init(&info)) {
- ret = 0;
goto commit;
}
- /* Below chipset generations needn't enable AMD PLL quirk */
- if (info.sb_type.gen == AMD_CHIPSET_UNKNOWN ||
- info.sb_type.gen == AMD_CHIPSET_SB600 ||
- info.sb_type.gen == AMD_CHIPSET_YANGTZE ||
- (info.sb_type.gen == AMD_CHIPSET_SB700 &&
- info.sb_type.rev > 0x3b)) {
+ switch (info.sb_type.gen) {
+ case AMD_CHIPSET_SB700:
+ info.need_pll_quirk = info.sb_type.rev <= 0x3B;
+ break;
+ case AMD_CHIPSET_SB800:
+ case AMD_CHIPSET_HUDSON2:
+ case AMD_CHIPSET_BOLTON:
+ info.need_pll_quirk = 1;
+ break;
+ default:
+ info.need_pll_quirk = 0;
+ break;
+ }
+
+ if (!info.need_pll_quirk) {
if (info.smbus_dev) {
pci_dev_put(info.smbus_dev);
info.smbus_dev = NULL;
}
- ret = 0;
goto commit;
}
}
}
- ret = info.probe_result = 1;
printk(KERN_DEBUG "QUIRK: Enable AMD PLL fix\n");
commit:
/* Mark that we where here */
amd_chipset.probe_count++;
- ret = amd_chipset.probe_result;
spin_unlock_irqrestore(&amd_lock, flags);
amd_chipset = info;
spin_unlock_irqrestore(&amd_lock, flags);
}
-
- return ret;
}
-EXPORT_SYMBOL_GPL(usb_amd_find_chipset_info);
int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev)
{
}
EXPORT_SYMBOL_GPL(usb_amd_prefetch_quirk);
+bool usb_amd_quirk_pll_check(void)
+{
+ usb_amd_find_chipset_info();
+ return amd_chipset.need_pll_quirk;
+}
+EXPORT_SYMBOL_GPL(usb_amd_quirk_pll_check);
+
/*
* The hardware normally enables the A-link power management feature, which
* lets the system lower the power consumption in idle states.
amd_chipset.nb_type = 0;
memset(&amd_chipset.sb_type, 0, sizeof(amd_chipset.sb_type));
amd_chipset.isoc_reqs = 0;
- amd_chipset.probe_result = 0;
+ amd_chipset.need_pll_quirk = 0;
spin_unlock_irqrestore(&amd_lock, flags);
#ifdef CONFIG_USB_PCI
void uhci_reset_hc(struct pci_dev *pdev, unsigned long base);
int uhci_check_and_reset_hc(struct pci_dev *pdev, unsigned long base);
-int usb_amd_find_chipset_info(void);
int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *pdev);
bool usb_amd_hang_symptom_quirk(void);
bool usb_amd_prefetch_quirk(void);
void usb_amd_dev_put(void);
+bool usb_amd_quirk_pll_check(void);
void usb_amd_quirk_pll_disable(void);
void usb_amd_quirk_pll_enable(void);
void usb_asmedia_modifyflowcontrol(struct pci_dev *pdev);
xhci->quirks |= XHCI_AMD_0x96_HOST;
/* AMD PLL quirk */
- if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
+ if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_quirk_pll_check())
xhci->quirks |= XHCI_AMD_PLL_FIX;
if (pdev->vendor == PCI_VENDOR_ID_AMD &&
return of_device_is_compatible(node, "renesas,xhci-r8a7790") ||
of_device_is_compatible(node, "renesas,xhci-r8a7791") ||
of_device_is_compatible(node, "renesas,xhci-r8a7793") ||
- of_device_is_compatible(node, "renensas,rcar-gen2-xhci");
+ of_device_is_compatible(node, "renesas,rcar-gen2-xhci");
}
static int xhci_rcar_is_gen3(struct device *dev)
* pointers. So, this driver clears the AC64 bit of xhci->hcc_params
* to call dma_set_coherent_mask(dev, DMA_BIT_MASK(32)) in
* xhci_gen_setup().
+ *
+ * And, since the firmware/internal CPU control the USBSTS.STS_HALT
+ * and the process speed is down when the roothub port enters U3,
+ * long delay for the handshake of STS_HALT is neeed in xhci_suspend().
*/
if (xhci_rcar_is_gen2(hcd->self.controller) ||
- xhci_rcar_is_gen3(hcd->self.controller))
- xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
+ xhci_rcar_is_gen3(hcd->self.controller)) {
+ xhci->quirks |= XHCI_NO_64BIT_SUPPORT | XHCI_SLOW_SUSPEND;
+ }
if (!xhci_rcar_wait_for_pll_active(hcd))
return -ETIMEDOUT;
tegra_xusb_config(tegra, regs);
+ /*
+ * The XUSB Falcon microcontroller can only address 40 bits, so set
+ * the DMA mask accordingly.
+ */
+ err = dma_set_mask_and_coherent(tegra->dev, DMA_BIT_MASK(40));
+ if (err < 0) {
+ dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err);
+ goto put_rpm;
+ }
+
err = tegra_xusb_load_firmware(tegra);
if (err < 0) {
dev_err(&pdev->dev, "failed to load firmware: %d\n", err);
return;
udev = (struct usb_device *) host_ep->hcpriv;
vdev = xhci->devs[udev->slot_id];
+
+ /*
+ * vdev may be lost due to xHC restore error and re-initialization
+ * during S3/S4 resume. A new vdev will be allocated later by
+ * xhci_discover_or_reset_device()
+ */
+ if (!udev->slot_id || !vdev)
+ return;
ep_index = xhci_get_endpoint_index(&host_ep->desc);
ep = &vdev->eps[ep_index];
+ if (!ep)
+ return;
/* Bail out if toggle is already being cleared by a endpoint reset */
if (ep->ep_state & EP_HARD_CLEAR_TOGGLE) {
if (!usb_endpoint_xfer_isoc(&urb->ep->desc) && usb_urb_dir_out(urb) &&
usb_endpoint_maxp(&urb->ep->desc) >= TRB_IDT_MAX_SIZE &&
urb->transfer_buffer_length <= TRB_IDT_MAX_SIZE &&
- !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP))
+ !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP) &&
+ !urb->num_sgs)
return true;
return false;
dev = usb_get_intfdata(interface);
mutex_lock(&iowarrior_open_disc_lock);
usb_set_intfdata(interface, NULL);
+ /* prevent device read, write and ioctl */
+ dev->present = 0;
minor = dev->minor;
+ mutex_unlock(&iowarrior_open_disc_lock);
+ /* give back our minor - this will call close() locks need to be dropped at this point*/
- /* give back our minor */
usb_deregister_dev(interface, &iowarrior_class);
mutex_lock(&dev->mutex);
/* prevent device read, write and ioctl */
- dev->present = 0;
mutex_unlock(&dev->mutex);
- mutex_unlock(&iowarrior_open_disc_lock);
if (dev->opened) {
/* There is a process that holds a filedescriptor to the device ,
char *obuf, *ibuf; /* transfer buffers */
char bulk_in_ep, bulk_out_ep; /* Endpoint assignments */
wait_queue_head_t wait_q; /* for timeouts */
+ struct mutex lock; /* general race avoidance */
};
static DEFINE_MUTEX(rio500_mutex);
/* against disconnect() */
mutex_lock(&rio500_mutex);
+ mutex_lock(&(rio->lock));
if (rio->isopen || !rio->present) {
+ mutex_unlock(&(rio->lock));
mutex_unlock(&rio500_mutex);
return -EBUSY;
}
init_waitqueue_head(&rio->wait_q);
+ mutex_unlock(&(rio->lock));
dev_info(&rio->rio_dev->dev, "Rio opened.\n");
mutex_unlock(&rio500_mutex);
/* against disconnect() */
mutex_lock(&rio500_mutex);
+ mutex_lock(&(rio->lock));
rio->isopen = 0;
if (!rio->present) {
} else {
dev_info(&rio->rio_dev->dev, "Rio closed.\n");
}
+ mutex_unlock(&(rio->lock));
mutex_unlock(&rio500_mutex);
return 0;
}
int retries;
int retval=0;
- mutex_lock(&rio500_mutex);
+ mutex_lock(&(rio->lock));
/* Sanity check to make sure rio is connected, powered, etc */
if (rio->present == 0 || rio->rio_dev == NULL) {
retval = -ENODEV;
err_out:
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return retval;
}
int errn = 0;
int intr;
- intr = mutex_lock_interruptible(&rio500_mutex);
+ intr = mutex_lock_interruptible(&(rio->lock));
if (intr)
return -EINTR;
/* Sanity check to make sure rio is connected, powered, etc */
if (rio->present == 0 || rio->rio_dev == NULL) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return -ENODEV;
}
goto error;
}
if (signal_pending(current)) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return bytes_written ? bytes_written : -EINTR;
}
buffer += copy_size;
} while (count > 0);
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return bytes_written ? bytes_written : -EIO;
error:
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return errn;
}
char *ibuf;
int intr;
- intr = mutex_lock_interruptible(&rio500_mutex);
+ intr = mutex_lock_interruptible(&(rio->lock));
if (intr)
return -EINTR;
/* Sanity check to make sure rio is connected, powered, etc */
if (rio->present == 0 || rio->rio_dev == NULL) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return -ENODEV;
}
while (count > 0) {
if (signal_pending(current)) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return read_count ? read_count : -EINTR;
}
if (!rio->rio_dev) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return -ENODEV;
}
this_read = (count >= IBUF_SIZE) ? IBUF_SIZE : count;
count = this_read = partial;
} else if (result == -ETIMEDOUT || result == 15) { /* FIXME: 15 ??? */
if (!maxretry--) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
dev_err(&rio->rio_dev->dev,
"read_rio: maxretry timeout\n");
return -ETIME;
finish_wait(&rio->wait_q, &wait);
continue;
} else if (result != -EREMOTEIO) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
dev_err(&rio->rio_dev->dev,
"Read Whoops - result:%d partial:%u this_read:%u\n",
result, partial, this_read);
return -EIO;
} else {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return (0);
}
if (this_read) {
if (copy_to_user(buffer, ibuf, this_read)) {
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return -EFAULT;
}
count -= this_read;
buffer += this_read;
}
}
- mutex_unlock(&rio500_mutex);
+ mutex_unlock(&(rio->lock));
return read_count;
}
}
dev_dbg(&intf->dev, "ibuf address:%p\n", rio->ibuf);
+ mutex_init(&(rio->lock));
+
usb_set_intfdata (intf, rio);
rio->present = 1;
bail_out:
if (rio) {
usb_deregister_dev(intf, &usb_rio_class);
+ mutex_lock(&(rio->lock));
if (rio->isopen) {
rio->isopen = 0;
/* better let it finish - the release will do whats needed */
rio->rio_dev = NULL;
+ mutex_unlock(&(rio->lock));
mutex_unlock(&rio500_mutex);
return;
}
dev_info(&intf->dev, "USB Rio disconnected.\n");
rio->present = 0;
+ mutex_unlock(&(rio->lock));
}
mutex_unlock(&rio500_mutex);
}
#ifdef CONFIG_OF
static void usb251xb_get_ports_field(struct usb251xb *hub,
- const char *prop_name, u8 port_cnt, u8 *fld)
+ const char *prop_name, u8 port_cnt,
+ bool ds_only, u8 *fld)
{
struct device *dev = hub->dev;
struct property *prop;
u32 port;
of_property_for_each_u32(dev->of_node, prop_name, prop, p, port) {
- if ((port >= 1) && (port <= port_cnt))
+ if ((port >= ds_only ? 1 : 0) && (port <= port_cnt))
*fld |= BIT(port);
else
dev_warn(dev, "port %u doesn't exist\n", port);
hub->non_rem_dev = USB251XB_DEF_NON_REMOVABLE_DEVICES;
usb251xb_get_ports_field(hub, "non-removable-ports", data->port_cnt,
- &hub->non_rem_dev);
+ true, &hub->non_rem_dev);
hub->port_disable_sp = USB251XB_DEF_PORT_DISABLE_SELF;
usb251xb_get_ports_field(hub, "sp-disabled-ports", data->port_cnt,
- &hub->port_disable_sp);
+ true, &hub->port_disable_sp);
hub->port_disable_bp = USB251XB_DEF_PORT_DISABLE_BUS;
usb251xb_get_ports_field(hub, "bp-disabled-ports", data->port_cnt,
- &hub->port_disable_bp);
+ true, &hub->port_disable_bp);
hub->max_power_sp = USB251XB_DEF_MAX_POWER_SELF;
if (!of_property_read_u32(np, "sp-max-total-current-microamp",
*/
hub->port_swap = USB251XB_DEF_PORT_SWAP;
usb251xb_get_ports_field(hub, "swap-dx-lanes", data->port_cnt,
- &hub->port_swap);
- if (of_get_property(np, "swap-us-lanes", NULL))
- hub->port_swap |= BIT(0);
+ false, &hub->port_swap);
/* The following parameters are currently not exposed to devicetree, but
* may be as soon as needed.
dev_dbg(&dev->interface->dev, "%s\n", __func__);
- usb_put_dev(dev->udev);
if (dev->cntl_urb) {
usb_kill_urb(dev->cntl_urb);
kfree(dev->cntl_req);
dev->int_buffer, dev->urb->transfer_dma);
usb_free_urb(dev->urb);
}
+ usb_put_dev(dev->udev);
kfree(dev);
}
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7B) },
{ USB_VENDOR_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, 0xff, 0x06, 0x7C) },
+ /* Motorola devices */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x2a70, 0xff, 0xff, 0xff) }, /* mdm6600 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x2e0a, 0xff, 0xff, 0xff) }, /* mdm9600 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x4281, 0x0a, 0x00, 0xfc) }, /* mdm ram dl */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x22b8, 0x900e, 0xff, 0xff, 0xff) }, /* mdm qc dl */
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1428, 0xff, 0xff, 0xff), /* Telewell TW-LTE 4G v2 */
.driver_info = RSVD(2) },
{ USB_DEVICE_INTERFACE_CLASS(ZTE_VENDOR_ID, 0x1476, 0xff) }, /* GosunCn ZTE WeLink ME3630 (ECM/NCM mode) */
+ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1481, 0xff, 0x00, 0x00) }, /* ZTE MF871A */
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1533, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1534, 0xff, 0xff, 0xff) },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x1535, 0xff, 0xff, 0xff) },
.driver_info = RSVD(4) },
{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff), /* D-Link DWM-222 */
.driver_info = RSVD(4) },
+ { USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e3d, 0xff), /* D-Link DWM-222 A2 */
+ .driver_info = RSVD(4) },
{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */
{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff), /* Olicard 600 */
.driver_info = RSVD(4) },
+ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2060, 0xff), /* BroadMobi BM818 */
+ .driver_info = RSVD(4) },
{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */
{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
static int auto_delink_en = 1;
module_param(auto_delink_en, int, S_IRUGO | S_IWUSR);
-MODULE_PARM_DESC(auto_delink_en, "enable auto delink");
+MODULE_PARM_DESC(auto_delink_en, "auto delink mode (0=firmware, 1=software [default])");
#ifdef CONFIG_REALTEK_AUTOPM
static int ss_en = 1;
goto INIT_FAIL;
}
- if (CHECK_FW_VER(chip, 0x5888) || CHECK_FW_VER(chip, 0x5889) ||
- CHECK_FW_VER(chip, 0x5901))
- SET_AUTO_DELINK(chip);
- if (STATUS_LEN(chip) == 16) {
- if (SUPPORT_AUTO_DELINK(chip))
+ if (CHECK_PID(chip, 0x0138) || CHECK_PID(chip, 0x0158) ||
+ CHECK_PID(chip, 0x0159)) {
+ if (CHECK_FW_VER(chip, 0x5888) || CHECK_FW_VER(chip, 0x5889) ||
+ CHECK_FW_VER(chip, 0x5901))
SET_AUTO_DELINK(chip);
+ if (STATUS_LEN(chip) == 16) {
+ if (SUPPORT_AUTO_DELINK(chip))
+ SET_AUTO_DELINK(chip);
+ }
}
#ifdef CONFIG_REALTEK_AUTOPM
if (ss_en)
* status of a command.
*/
+#include <linux/blkdev.h>
+#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/mutex.h>
static int slave_configure(struct scsi_device *sdev)
{
struct us_data *us = host_to_us(sdev->host);
+ struct device *dev = us->pusb_dev->bus->sysdev;
/*
* Many devices have trouble transferring more than 32KB at a time,
blk_queue_max_hw_sectors(sdev->request_queue, 2048);
}
+ /*
+ * The max_hw_sectors should be up to maximum size of a mapping for
+ * the device. Otherwise, a DMA API might fail on swiotlb environment.
+ */
+ blk_queue_max_hw_sectors(sdev->request_queue,
+ min_t(size_t, queue_max_hw_sectors(sdev->request_queue),
+ dma_max_mapping_size(dev) >> SECTOR_SHIFT));
+
/*
* Some USB host controllers can't do DMA; they have to use PIO.
* They indicate this by setting their dma_mask to NULL. For
US_FL_IGNORE_RESIDUE ),
/* Reported by Michael Büsch <m@bues.ch> */
-UNUSUAL_DEV( 0x152d, 0x0567, 0x0114, 0x0116,
+UNUSUAL_DEV( 0x152d, 0x0567, 0x0114, 0x0117,
"JMicron",
"USB to ATA/ATAPI Bridge",
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
return SNK_UNATTACHED;
else if (port->try_role == TYPEC_SOURCE)
return SRC_UNATTACHED;
- else if (port->tcpc->config->default_role == TYPEC_SINK)
+ else if (port->tcpc->config &&
+ port->tcpc->config->default_role == TYPEC_SINK)
return SNK_UNATTACHED;
/* Fall through to return SRC_UNATTACHED */
} else if (port->port_type == TYPEC_PORT_SNK) {
static void tcpm_debugfs_exit(struct tcpm_port *port)
{
+ int i;
+
+ mutex_lock(&port->logbuffer_lock);
+ for (i = 0; i < LOG_BUFFER_ENTRIES; i++) {
+ kfree(port->logbuffer[i]);
+ port->logbuffer[i] = NULL;
+ }
+ mutex_unlock(&port->logbuffer_lock);
+
debugfs_remove(port->dentry);
+ if (list_empty(&rootdir->d_subdirs)) {
+ debugfs_remove(rootdir);
+ rootdir = NULL;
+ }
}
#else
break;
case CMD_ATTENTION:
/* Attention command does not have response */
- typec_altmode_attention(adev, p[1]);
+ if (adev)
+ typec_altmode_attention(adev, p[1]);
return 0;
default:
break;
}
break;
case CMD_ENTER_MODE:
- typec_altmode_update_active(pdev, true);
-
- if (typec_altmode_vdm(adev, p[0], &p[1], cnt)) {
- response[0] = VDO(adev->svid, 1, CMD_EXIT_MODE);
- response[0] |= VDO_OPOS(adev->mode);
- return 1;
+ if (adev && pdev) {
+ typec_altmode_update_active(pdev, true);
+
+ if (typec_altmode_vdm(adev, p[0], &p[1], cnt)) {
+ response[0] = VDO(adev->svid, 1,
+ CMD_EXIT_MODE);
+ response[0] |= VDO_OPOS(adev->mode);
+ return 1;
+ }
}
return 0;
case CMD_EXIT_MODE:
- typec_altmode_update_active(pdev, false);
+ if (adev && pdev) {
+ typec_altmode_update_active(pdev, false);
- /* Back to USB Operation */
- WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB,
- NULL));
+ /* Back to USB Operation */
+ WARN_ON(typec_altmode_notify(adev,
+ TYPEC_STATE_USB,
+ NULL));
+ }
break;
default:
break;
switch (cmd) {
case CMD_ENTER_MODE:
/* Back to USB Operation */
- WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB,
- NULL));
+ if (adev)
+ WARN_ON(typec_altmode_notify(adev,
+ TYPEC_STATE_USB,
+ NULL));
break;
default:
break;
}
/* Informing the alternate mode drivers about everything */
- typec_altmode_vdm(adev, p[0], &p[1], cnt);
+ if (adev)
+ typec_altmode_vdm(adev, p[0], &p[1], cnt);
return rlen;
}
else if ((pdo_min_voltage(pdo[i]) ==
pdo_min_voltage(pdo[i - 1])) &&
(pdo_max_voltage(pdo[i]) ==
- pdo_min_voltage(pdo[i - 1])))
+ pdo_max_voltage(pdo[i - 1])))
return PDO_ERR_DUPE_PDO;
break;
/*
mutex_lock(&port->lock);
if (tcpc->try_role)
ret = tcpc->try_role(tcpc, role);
- if (!ret && !tcpc->config->try_role_hw)
+ if (!ret && (!tcpc->config || !tcpc->config->try_role_hw))
port->try_role = role;
port->try_src_count = 0;
port->try_snk_count = 0;
port->typec_caps.prefer_role = tcfg->default_role;
port->typec_caps.type = tcfg->type;
port->typec_caps.data = tcfg->data;
- port->self_powered = port->tcpc->config->self_powered;
+ port->self_powered = tcfg->self_powered;
return 0;
}
******************************************************************************/
static int ccg_fw_update(struct ucsi_ccg *uc, enum enum_flash_mode flash_mode)
{
- int err;
+ int err = 0;
while (flash_mode != FLASH_NOT_NEEDED) {
err = do_flash(uc, flash_mode);
* Using this limit prevents one virtqueue from starving others. */
#define VHOST_TEST_WEIGHT 0x80000
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * pkts.
+ */
+#define VHOST_TEST_PKT_WEIGHT 256
+
enum {
VHOST_TEST_VQ = 0,
VHOST_TEST_VQ_MAX = 1,
}
vhost_add_used_and_signal(&n->dev, vq, head, 0);
total_len += len;
- if (unlikely(total_len >= VHOST_TEST_WEIGHT)) {
- vhost_poll_queue(&vq->poll);
+ if (unlikely(vhost_exceeds_weight(vq, 0, total_len)))
break;
- }
}
mutex_unlock(&vq->mutex);
dev = &n->dev;
vqs[VHOST_TEST_VQ] = &n->vqs[VHOST_TEST_VQ];
n->vqs[VHOST_TEST_VQ].handle_kick = handle_vq_kick;
- vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX);
+ vhost_dev_init(dev, vqs, VHOST_TEST_VQ_MAX, UIO_MAXIOV,
+ VHOST_TEST_PKT_WEIGHT, VHOST_TEST_WEIGHT);
f->private_data = n;
int vhost_poll_start(struct vhost_poll *poll, struct file *file)
{
__poll_t mask;
- int ret = 0;
if (poll->wqh)
return 0;
vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask));
if (mask & EPOLLERR) {
vhost_poll_stop(poll);
- ret = -EINVAL;
+ return -EINVAL;
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL_GPL(vhost_poll_start);
__vhost_vq_meta_reset(d->vqs[i]);
}
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
-static void vhost_map_unprefetch(struct vhost_map *map)
-{
- kfree(map->pages);
- map->pages = NULL;
- map->npages = 0;
- map->addr = NULL;
-}
-
-static void vhost_uninit_vq_maps(struct vhost_virtqueue *vq)
-{
- struct vhost_map *map[VHOST_NUM_ADDRS];
- int i;
-
- spin_lock(&vq->mmu_lock);
- for (i = 0; i < VHOST_NUM_ADDRS; i++) {
- map[i] = rcu_dereference_protected(vq->maps[i],
- lockdep_is_held(&vq->mmu_lock));
- if (map[i])
- rcu_assign_pointer(vq->maps[i], NULL);
- }
- spin_unlock(&vq->mmu_lock);
-
- synchronize_rcu();
-
- for (i = 0; i < VHOST_NUM_ADDRS; i++)
- if (map[i])
- vhost_map_unprefetch(map[i]);
-
-}
-
-static void vhost_reset_vq_maps(struct vhost_virtqueue *vq)
-{
- int i;
-
- vhost_uninit_vq_maps(vq);
- for (i = 0; i < VHOST_NUM_ADDRS; i++)
- vq->uaddrs[i].size = 0;
-}
-
-static bool vhost_map_range_overlap(struct vhost_uaddr *uaddr,
- unsigned long start,
- unsigned long end)
-{
- if (unlikely(!uaddr->size))
- return false;
-
- return !(end < uaddr->uaddr || start > uaddr->uaddr - 1 + uaddr->size);
-}
-
-static void vhost_invalidate_vq_start(struct vhost_virtqueue *vq,
- int index,
- unsigned long start,
- unsigned long end)
-{
- struct vhost_uaddr *uaddr = &vq->uaddrs[index];
- struct vhost_map *map;
- int i;
-
- if (!vhost_map_range_overlap(uaddr, start, end))
- return;
-
- spin_lock(&vq->mmu_lock);
- ++vq->invalidate_count;
-
- map = rcu_dereference_protected(vq->maps[index],
- lockdep_is_held(&vq->mmu_lock));
- if (map) {
- if (uaddr->write) {
- for (i = 0; i < map->npages; i++)
- set_page_dirty(map->pages[i]);
- }
- rcu_assign_pointer(vq->maps[index], NULL);
- }
- spin_unlock(&vq->mmu_lock);
-
- if (map) {
- synchronize_rcu();
- vhost_map_unprefetch(map);
- }
-}
-
-static void vhost_invalidate_vq_end(struct vhost_virtqueue *vq,
- int index,
- unsigned long start,
- unsigned long end)
-{
- if (!vhost_map_range_overlap(&vq->uaddrs[index], start, end))
- return;
-
- spin_lock(&vq->mmu_lock);
- --vq->invalidate_count;
- spin_unlock(&vq->mmu_lock);
-}
-
-static int vhost_invalidate_range_start(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
-{
- struct vhost_dev *dev = container_of(mn, struct vhost_dev,
- mmu_notifier);
- int i, j;
-
- if (!mmu_notifier_range_blockable(range))
- return -EAGAIN;
-
- for (i = 0; i < dev->nvqs; i++) {
- struct vhost_virtqueue *vq = dev->vqs[i];
-
- for (j = 0; j < VHOST_NUM_ADDRS; j++)
- vhost_invalidate_vq_start(vq, j,
- range->start,
- range->end);
- }
-
- return 0;
-}
-
-static void vhost_invalidate_range_end(struct mmu_notifier *mn,
- const struct mmu_notifier_range *range)
-{
- struct vhost_dev *dev = container_of(mn, struct vhost_dev,
- mmu_notifier);
- int i, j;
-
- for (i = 0; i < dev->nvqs; i++) {
- struct vhost_virtqueue *vq = dev->vqs[i];
-
- for (j = 0; j < VHOST_NUM_ADDRS; j++)
- vhost_invalidate_vq_end(vq, j,
- range->start,
- range->end);
- }
-}
-
-static const struct mmu_notifier_ops vhost_mmu_notifier_ops = {
- .invalidate_range_start = vhost_invalidate_range_start,
- .invalidate_range_end = vhost_invalidate_range_end,
-};
-
-static void vhost_init_maps(struct vhost_dev *dev)
-{
- struct vhost_virtqueue *vq;
- int i, j;
-
- dev->mmu_notifier.ops = &vhost_mmu_notifier_ops;
-
- for (i = 0; i < dev->nvqs; ++i) {
- vq = dev->vqs[i];
- for (j = 0; j < VHOST_NUM_ADDRS; j++)
- RCU_INIT_POINTER(vq->maps[j], NULL);
- }
-}
-#endif
-
static void vhost_vq_reset(struct vhost_dev *dev,
struct vhost_virtqueue *vq)
{
vq->busyloop_timeout = 0;
vq->umem = NULL;
vq->iotlb = NULL;
- vq->invalidate_count = 0;
__vhost_vq_meta_reset(vq);
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- vhost_reset_vq_maps(vq);
-#endif
}
static int vhost_worker(void *data)
INIT_LIST_HEAD(&dev->read_list);
INIT_LIST_HEAD(&dev->pending_list);
spin_lock_init(&dev->iotlb_lock);
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- vhost_init_maps(dev);
-#endif
+
for (i = 0; i < dev->nvqs; ++i) {
vq = dev->vqs[i];
vq->heads = NULL;
vq->dev = dev;
mutex_init(&vq->mutex);
- spin_lock_init(&vq->mmu_lock);
vhost_vq_reset(dev, vq);
if (vq->handle_kick)
vhost_poll_init(&vq->poll, vq->handle_kick,
if (err)
goto err_cgroup;
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- err = mmu_notifier_register(&dev->mmu_notifier, dev->mm);
- if (err)
- goto err_mmu_notifier;
-#endif
-
return 0;
-
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
-err_mmu_notifier:
- vhost_dev_free_iovecs(dev);
-#endif
err_cgroup:
kthread_stop(worker);
dev->worker = NULL;
spin_unlock(&dev->iotlb_lock);
}
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
-static void vhost_setup_uaddr(struct vhost_virtqueue *vq,
- int index, unsigned long uaddr,
- size_t size, bool write)
-{
- struct vhost_uaddr *addr = &vq->uaddrs[index];
-
- addr->uaddr = uaddr;
- addr->size = size;
- addr->write = write;
-}
-
-static void vhost_setup_vq_uaddr(struct vhost_virtqueue *vq)
-{
- vhost_setup_uaddr(vq, VHOST_ADDR_DESC,
- (unsigned long)vq->desc,
- vhost_get_desc_size(vq, vq->num),
- false);
- vhost_setup_uaddr(vq, VHOST_ADDR_AVAIL,
- (unsigned long)vq->avail,
- vhost_get_avail_size(vq, vq->num),
- false);
- vhost_setup_uaddr(vq, VHOST_ADDR_USED,
- (unsigned long)vq->used,
- vhost_get_used_size(vq, vq->num),
- true);
-}
-
-static int vhost_map_prefetch(struct vhost_virtqueue *vq,
- int index)
-{
- struct vhost_map *map;
- struct vhost_uaddr *uaddr = &vq->uaddrs[index];
- struct page **pages;
- int npages = DIV_ROUND_UP(uaddr->size, PAGE_SIZE);
- int npinned;
- void *vaddr, *v;
- int err;
- int i;
-
- spin_lock(&vq->mmu_lock);
-
- err = -EFAULT;
- if (vq->invalidate_count)
- goto err;
-
- err = -ENOMEM;
- map = kmalloc(sizeof(*map), GFP_ATOMIC);
- if (!map)
- goto err;
-
- pages = kmalloc_array(npages, sizeof(struct page *), GFP_ATOMIC);
- if (!pages)
- goto err_pages;
-
- err = EFAULT;
- npinned = __get_user_pages_fast(uaddr->uaddr, npages,
- uaddr->write, pages);
- if (npinned > 0)
- release_pages(pages, npinned);
- if (npinned != npages)
- goto err_gup;
-
- for (i = 0; i < npinned; i++)
- if (PageHighMem(pages[i]))
- goto err_gup;
-
- vaddr = v = page_address(pages[0]);
-
- /* For simplicity, fallback to userspace address if VA is not
- * contigious.
- */
- for (i = 1; i < npinned; i++) {
- v += PAGE_SIZE;
- if (v != page_address(pages[i]))
- goto err_gup;
- }
-
- map->addr = vaddr + (uaddr->uaddr & (PAGE_SIZE - 1));
- map->npages = npages;
- map->pages = pages;
-
- rcu_assign_pointer(vq->maps[index], map);
- /* No need for a synchronize_rcu(). This function should be
- * called by dev->worker so we are serialized with all
- * readers.
- */
- spin_unlock(&vq->mmu_lock);
-
- return 0;
-
-err_gup:
- kfree(pages);
-err_pages:
- kfree(map);
-err:
- spin_unlock(&vq->mmu_lock);
- return err;
-}
-#endif
-
void vhost_dev_cleanup(struct vhost_dev *dev)
{
int i;
kthread_stop(dev->worker);
dev->worker = NULL;
}
- if (dev->mm) {
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- mmu_notifier_unregister(&dev->mmu_notifier, dev->mm);
-#endif
+ if (dev->mm)
mmput(dev->mm);
- }
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- for (i = 0; i < dev->nvqs; i++)
- vhost_uninit_vq_maps(dev->vqs[i]);
-#endif
dev->mm = NULL;
}
EXPORT_SYMBOL_GPL(vhost_dev_cleanup);
static inline int vhost_put_avail_event(struct vhost_virtqueue *vq)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_used *used;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
- if (likely(map)) {
- used = map->addr;
- *((__virtio16 *)&used->ring[vq->num]) =
- cpu_to_vhost16(vq, vq->avail_idx);
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx),
vhost_avail_event(vq));
}
struct vring_used_elem *head, int idx,
int count)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_used *used;
- size_t size;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
- if (likely(map)) {
- used = map->addr;
- size = count * sizeof(*head);
- memcpy(used->ring + idx, head, size);
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_copy_to_user(vq, vq->used->ring + idx, head,
count * sizeof(*head));
}
static inline int vhost_put_used_flags(struct vhost_virtqueue *vq)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_used *used;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
- if (likely(map)) {
- used = map->addr;
- used->flags = cpu_to_vhost16(vq, vq->used_flags);
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags),
&vq->used->flags);
}
static inline int vhost_put_used_idx(struct vhost_virtqueue *vq)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_used *used;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
- if (likely(map)) {
- used = map->addr;
- used->idx = cpu_to_vhost16(vq, vq->last_used_idx);
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx),
&vq->used->idx);
}
static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq,
__virtio16 *idx)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_avail *avail;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
- if (likely(map)) {
- avail = map->addr;
- *idx = avail->idx;
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_get_avail(vq, *idx, &vq->avail->idx);
}
static inline int vhost_get_avail_head(struct vhost_virtqueue *vq,
__virtio16 *head, int idx)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_avail *avail;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
- if (likely(map)) {
- avail = map->addr;
- *head = avail->ring[idx & (vq->num - 1)];
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_get_avail(vq, *head,
&vq->avail->ring[idx & (vq->num - 1)]);
}
static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq,
__virtio16 *flags)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_avail *avail;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
- if (likely(map)) {
- avail = map->addr;
- *flags = avail->flags;
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_get_avail(vq, *flags, &vq->avail->flags);
}
static inline int vhost_get_used_event(struct vhost_virtqueue *vq,
__virtio16 *event)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_avail *avail;
-
- if (!vq->iotlb) {
- rcu_read_lock();
- map = rcu_dereference(vq->maps[VHOST_ADDR_AVAIL]);
- if (likely(map)) {
- avail = map->addr;
- *event = (__virtio16)avail->ring[vq->num];
- rcu_read_unlock();
- return 0;
- }
- rcu_read_unlock();
- }
-#endif
-
return vhost_get_avail(vq, *event, vhost_used_event(vq));
}
static inline int vhost_get_used_idx(struct vhost_virtqueue *vq,
__virtio16 *idx)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_used *used;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_USED]);
- if (likely(map)) {
- used = map->addr;
- *idx = used->idx;
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_get_used(vq, *idx, &vq->used->idx);
}
static inline int vhost_get_desc(struct vhost_virtqueue *vq,
struct vring_desc *desc, int idx)
{
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- struct vhost_map *map;
- struct vring_desc *d;
-
- if (!vq->iotlb) {
- rcu_read_lock();
-
- map = rcu_dereference(vq->maps[VHOST_ADDR_DESC]);
- if (likely(map)) {
- d = map->addr;
- *desc = *(d + idx);
- rcu_read_unlock();
- return 0;
- }
-
- rcu_read_unlock();
- }
-#endif
-
return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
}
return true;
}
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
-static void vhost_vq_map_prefetch(struct vhost_virtqueue *vq)
-{
- struct vhost_map __rcu *map;
- int i;
-
- for (i = 0; i < VHOST_NUM_ADDRS; i++) {
- rcu_read_lock();
- map = rcu_dereference(vq->maps[i]);
- rcu_read_unlock();
- if (unlikely(!map))
- vhost_map_prefetch(vq, i);
- }
-}
-#endif
-
int vq_meta_prefetch(struct vhost_virtqueue *vq)
{
unsigned int num = vq->num;
- if (!vq->iotlb) {
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- vhost_vq_map_prefetch(vq);
-#endif
+ if (!vq->iotlb)
return 1;
- }
return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
mutex_lock(&vq->mutex);
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- /* Unregister MMU notifer to allow invalidation callback
- * can access vq->uaddrs[] without holding a lock.
- */
- if (d->mm)
- mmu_notifier_unregister(&d->mmu_notifier, d->mm);
-
- vhost_uninit_vq_maps(vq);
-#endif
-
switch (ioctl) {
case VHOST_SET_VRING_NUM:
r = vhost_vring_set_num(d, vq, argp);
BUG();
}
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- vhost_setup_vq_uaddr(vq);
-
- if (d->mm)
- mmu_notifier_register(&d->mmu_notifier, d->mm);
-#endif
-
mutex_unlock(&vq->mutex);
return r;
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
#include <linux/atomic.h>
-#include <linux/pagemap.h>
-#include <linux/mmu_notifier.h>
-#include <asm/cacheflush.h>
struct vhost_work;
typedef void (*vhost_work_fn_t)(struct vhost_work *work);
VHOST_NUM_ADDRS = 3,
};
-struct vhost_map {
- int npages;
- void *addr;
- struct page **pages;
-};
-
-struct vhost_uaddr {
- unsigned long uaddr;
- size_t size;
- bool write;
-};
-
-#if defined(CONFIG_MMU_NOTIFIER) && ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 0
-#define VHOST_ARCH_CAN_ACCEL_UACCESS 1
-#else
-#define VHOST_ARCH_CAN_ACCEL_UACCESS 0
-#endif
-
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
struct vring_desc __user *desc;
struct vring_avail __user *avail;
struct vring_used __user *used;
-
-#if VHOST_ARCH_CAN_ACCEL_UACCESS
- /* Read by memory accessors, modified by meta data
- * prefetching, MMU notifier and vring ioctl().
- * Synchonrized through mmu_lock (writers) and RCU (writers
- * and readers).
- */
- struct vhost_map __rcu *maps[VHOST_NUM_ADDRS];
- /* Read by MMU notifier, modified by vring ioctl(),
- * synchronized through MMU notifier
- * registering/unregistering.
- */
- struct vhost_uaddr uaddrs[VHOST_NUM_ADDRS];
-#endif
const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
-
struct file *kick;
struct eventfd_ctx *call_ctx;
struct eventfd_ctx *error_ctx;
bool user_be;
#endif
u32 busyloop_timeout;
- spinlock_t mmu_lock;
- int invalidate_count;
};
struct vhost_msg_node {
struct vhost_dev {
struct mm_struct *mm;
-#ifdef CONFIG_MMU_NOTIFIER
- struct mmu_notifier mmu_notifier;
-#endif
struct mutex mutex;
struct vhost_virtqueue **vqs;
int nvqs;
case 'M':
case 'm':
size *= 1024;
+ /* Fall through */
case 'K':
case 'k':
size *= 1024;
return 0;
case 12:
var->bits_per_pixel = 16;
+ /* fall through */
case 16:
if (plane->fbdev->panel->bpp == 12)
plane->color_mode = OMAPFB_COLOR_RGB444;
case OMAPFB_ACTIVE:
for (i = 0; i < fbdev->mem_desc.region_cnt; i++)
unregister_framebuffer(fbdev->fb_info[i]);
+ /* fall through */
case 7:
omapfb_unregister_sysfs(fbdev);
+ /* fall through */
case 6:
if (fbdev->panel->disable)
fbdev->panel->disable(fbdev->panel);
+ /* fall through */
case 5:
omapfb_set_update_mode(fbdev, OMAPFB_UPDATE_DISABLED);
+ /* fall through */
case 4:
planes_cleanup(fbdev);
+ /* fall through */
case 3:
ctrl_cleanup(fbdev);
+ /* fall through */
case 2:
if (fbdev->panel->cleanup)
fbdev->panel->cleanup(fbdev->panel);
+ /* fall through */
case 1:
dev_set_drvdata(fbdev->dev, NULL);
kfree(fbdev);
ar7_wdt_update_margin(new_margin);
ar7_wdt_kick(1);
spin_unlock(&wdt_lock);
+ /* Fall through */
case WDIOC_GETTIMEOUT:
if (put_user(margin, (int *)arg))
return -EINVAL;
pcwd_keepalive();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(heartbeat, argp);
return -EINVAL;
riowd_timeout = (new_margin + 59) / 60;
riowd_writereg(p, riowd_timeout, WDTO_INDEX);
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(riowd_timeout * 60, (int __user *)argp);
timeout = time;
sbwdog_set(user_dog, timeout);
sbwdog_pet(user_dog);
+ /* Fall through */
case WDIOC_GETTIMEOUT:
/*
margin = new_margin;
scx200_wdt_update_margin();
scx200_wdt_ping();
+ /* Fall through */
case WDIOC_GETTIMEOUT:
if (put_user(margin, p))
return -EFAULT;
if (wdt_set_heartbeat(new_heartbeat))
return -EINVAL;
wdt_ping();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(heartbeat, p);
default:
soft_margin = new_margin;
reload = soft_margin * (mem_fclk_21285 / 256);
watchdog_ping();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
ret = put_user(soft_margin, int_arg);
break;
return -EINVAL;
wdt977_keepalive();
- /* Fall */
+ /* Fall through */
case WDIOC_GETTIMEOUT:
return put_user(timeout, uarg.i);
goto out_put_map;
if (!use_ptemod) {
- err = vm_map_pages(vma, map->pages, map->count);
+ err = vm_map_pages_zero(vma, map->pages, map->count);
if (err)
goto out_put_map;
} else {
return 0;
}
-struct remap_pfn {
- struct mm_struct *mm;
- struct page **pages;
- pgprot_t prot;
- unsigned long i;
-};
-
-static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data)
-{
- struct remap_pfn *r = data;
- struct page *page = r->pages[r->i];
- pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), r->prot));
-
- set_pte_at(r->mm, addr, ptep, pte);
- r->i++;
-
- return 0;
-}
-
static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
{
struct privcmd_data *data = file->private_data;
goto out;
}
- if (xen_feature(XENFEAT_auto_translated_physmap)) {
+ if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) &&
+ xen_feature(XENFEAT_auto_translated_physmap)) {
unsigned int nr = DIV_ROUND_UP(kdata.num, XEN_PFN_PER_PAGE);
struct page **pages;
unsigned int i;
if (rc)
goto out;
- if (xen_feature(XENFEAT_auto_translated_physmap)) {
- struct remap_pfn r = {
- .mm = vma->vm_mm,
- .pages = vma->vm_private_data,
- .prot = vma->vm_page_prot,
- };
-
- rc = apply_to_page_range(r.mm, kdata.addr,
- kdata.num << PAGE_SHIFT,
- remap_pfn_fn, &r);
+ if (IS_ENABLED(CONFIG_XEN_AUTO_XLATE) &&
+ xen_feature(XENFEAT_auto_translated_physmap)) {
+ rc = xen_remap_vma_range(vma, kdata.addr, kdata.num << PAGE_SHIFT);
} else {
unsigned int domid =
(xdata.flags & XENMEM_rsrc_acq_caller_owned) ?
return xen_phys_to_bus(virt_to_phys(address));
}
-static int check_pages_physically_contiguous(unsigned long xen_pfn,
- unsigned int offset,
- size_t length)
+static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
{
- unsigned long next_bfn;
- int i;
- int nr_pages;
+ unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p);
+ unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size);
next_bfn = pfn_to_bfn(xen_pfn);
- nr_pages = (offset + length + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT;
- for (i = 1; i < nr_pages; i++) {
+ for (i = 1; i < nr_pages; i++)
if (pfn_to_bfn(++xen_pfn) != ++next_bfn)
- return 0;
- }
- return 1;
-}
+ return 1;
-static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
-{
- unsigned long xen_pfn = XEN_PFN_DOWN(p);
- unsigned int offset = p & ~XEN_PAGE_MASK;
-
- if (offset + size <= XEN_PAGE_SIZE)
- return 0;
- if (check_pages_physically_contiguous(xen_pfn, offset, size))
- return 0;
- return 1;
+ return 0;
}
static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
xen_free_coherent_pages(hwdev, size, ret, (dma_addr_t)phys, attrs);
return NULL;
}
+ SetPageXenRemapped(virt_to_page(ret));
}
memset(ret, 0, size);
return ret;
/* Convert the size to actually allocated. */
size = 1UL << (order + XEN_PAGE_SHIFT);
- if (((dev_addr + size - 1 <= dma_mask)) ||
- range_straddles_page_boundary(phys, size))
+ if (!WARN_ON((dev_addr + size - 1 > dma_mask) ||
+ range_straddles_page_boundary(phys, size)) &&
+ TestClearPageXenRemapped(virt_to_page(vaddr)))
xen_destroy_contiguous_region(phys, order);
xen_free_coherent_pages(hwdev, size, vaddr, (dma_addr_t)phys, attrs);
{
int err;
u16 old_value;
- pci_power_t new_state, old_state;
+ pci_power_t new_state;
err = pci_read_config_word(dev, offset, &old_value);
if (err)
goto out;
- old_state = (pci_power_t)(old_value & PCI_PM_CTRL_STATE_MASK);
new_state = (pci_power_t)(new_value & PCI_PM_CTRL_STATE_MASK);
new_value &= PM_OK_BITS;
return 0;
}
EXPORT_SYMBOL_GPL(xen_xlate_map_ballooned_pages);
+
+struct remap_pfn {
+ struct mm_struct *mm;
+ struct page **pages;
+ pgprot_t prot;
+ unsigned long i;
+};
+
+static int remap_pfn_fn(pte_t *ptep, unsigned long addr, void *data)
+{
+ struct remap_pfn *r = data;
+ struct page *page = r->pages[r->i];
+ pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), r->prot));
+
+ set_pte_at(r->mm, addr, ptep, pte);
+ r->i++;
+
+ return 0;
+}
+
+/* Used by the privcmd module, but has to be built-in on ARM */
+int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr, unsigned long len)
+{
+ struct remap_pfn r = {
+ .mm = vma->vm_mm,
+ .pages = vma->vm_private_data,
+ .prot = vma->vm_page_prot,
+ };
+
+ return apply_to_page_range(vma->vm_mm, addr, len, remap_pfn_fn, &r);
+}
+EXPORT_SYMBOL_GPL(xen_remap_vma_range);
cell = rcu_dereference_raw(net->ws_cell);
if (cell) {
afs_get_cell(cell);
+ ret = 0;
break;
}
ret = -EDESTADDRREQ;
done_seqretry(&net->cells_lock, seq);
+ if (ret != 0 && cell)
+ afs_put_cell(net, cell);
+
return ret == 0 ? cell : ERR_PTR(ret);
}
struct afs_call *call = container_of(work, struct afs_call, work);
struct afs_uuid *r = call->request;
- struct {
- __be32 match;
- } reply;
-
_enter("");
if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0)
- reply.match = htonl(0);
+ afs_send_empty_reply(call);
else
- reply.match = htonl(1);
+ rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+ 1, 1, "K-1");
- afs_send_simple_reply(call, &reply, sizeof(reply));
afs_put_call(call);
_leave("");
}
* iterate through the data blob that lists the contents of an AFS directory
*/
static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx,
- struct key *key)
+ struct key *key, afs_dataversion_t *_dir_version)
{
struct afs_vnode *dvnode = AFS_FS_I(dir);
struct afs_xdr_dir_page *dbuf;
req = afs_read_dir(dvnode, key);
if (IS_ERR(req))
return PTR_ERR(req);
+ *_dir_version = req->data_version;
/* round the file position up to the next entry boundary */
ctx->pos += sizeof(union afs_xdr_dirent) - 1;
*/
static int afs_readdir(struct file *file, struct dir_context *ctx)
{
- return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file));
+ afs_dataversion_t dir_version;
+
+ return afs_dir_iterate(file_inode(file), ctx, afs_file_key(file),
+ &dir_version);
}
/*
* - just returns the FID the dentry name maps to if found
*/
static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry,
- struct afs_fid *fid, struct key *key)
+ struct afs_fid *fid, struct key *key,
+ afs_dataversion_t *_dir_version)
{
struct afs_super_info *as = dir->i_sb->s_fs_info;
struct afs_lookup_one_cookie cookie = {
_enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);
/* search the directory */
- ret = afs_dir_iterate(dir, &cookie.ctx, key);
+ ret = afs_dir_iterate(dir, &cookie.ctx, key, _dir_version);
if (ret < 0) {
_leave(" = %d [iter]", ret);
return ret;
struct afs_server *server;
struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode;
struct inode *inode = NULL, *ti;
+ afs_dataversion_t data_version = READ_ONCE(dvnode->status.data_version);
int ret, i;
_enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry);
cookie->fids[i].vid = as->volume->vid;
/* search the directory */
- ret = afs_dir_iterate(dir, &cookie->ctx, key);
+ ret = afs_dir_iterate(dir, &cookie->ctx, key, &data_version);
if (ret < 0) {
inode = ERR_PTR(ret);
goto out;
}
+ dentry->d_fsdata = (void *)(unsigned long)data_version;
+
inode = ERR_PTR(-ENOENT);
if (!cookie->found)
goto out;
inode ? AFS_FS_I(inode) : NULL);
} else {
trace_afs_lookup(dvnode, &dentry->d_name,
- inode ? AFS_FS_I(inode) : NULL);
+ IS_ERR_OR_NULL(inode) ? NULL
+ : AFS_FS_I(inode));
}
return d;
}
struct dentry *parent;
struct inode *inode;
struct key *key;
- long dir_version, de_version;
+ afs_dataversion_t dir_version;
+ long de_version;
int ret;
if (flags & LOOKUP_RCU)
* on a 32-bit system, we only have 32 bits in the dentry to store the
* version.
*/
- dir_version = (long)dir->status.data_version;
+ dir_version = dir->status.data_version;
de_version = (long)dentry->d_fsdata;
- if (de_version == dir_version)
- goto out_valid;
+ if (de_version == (long)dir_version)
+ goto out_valid_noupdate;
- dir_version = (long)dir->invalid_before;
- if (de_version - dir_version >= 0)
+ dir_version = dir->invalid_before;
+ if (de_version - (long)dir_version >= 0)
goto out_valid;
_debug("dir modified");
afs_stat_v(dir, n_reval);
/* search the directory for this vnode */
- ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key);
+ ret = afs_do_lookup_one(&dir->vfs_inode, dentry, &fid, key, &dir_version);
switch (ret) {
case 0:
/* the filename maps to something */
}
out_valid:
- dentry->d_fsdata = (void *)dir_version;
+ dentry->d_fsdata = (void *)(unsigned long)dir_version;
+out_valid_noupdate:
dput(parent);
key_put(key);
_leave(" = 1 [valid]");
iget_data->cb_s_break = fc->cbi->server->cb_s_break;
}
+/*
+ * Note that a dentry got changed. We need to set d_fsdata to the data version
+ * number derived from the result of the operation. It doesn't matter if
+ * d_fsdata goes backwards as we'll just revalidate.
+ */
+static void afs_update_dentry_version(struct afs_fs_cursor *fc,
+ struct dentry *dentry,
+ struct afs_status_cb *scb)
+{
+ if (fc->ac.error == 0)
+ dentry->d_fsdata =
+ (void *)(unsigned long)scb->status.data_version;
+}
+
/*
* create a directory on an AFS filesystem
*/
afs_check_for_remote_deletion(&fc, dvnode);
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, &scb[0]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]);
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, scb);
+ afs_update_dentry_version(&fc, dentry, scb);
ret = afs_end_vnode_operation(&fc);
if (ret == 0) {
afs_dir_remove_subdir(dentry);
&data_version, &scb[0]);
afs_vnode_commit_status(&fc, vnode, fc.cb_break_2,
&data_version_2, &scb[1]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
ret = afs_end_vnode_operation(&fc);
if (ret == 0 && !(scb[1].have_status || scb[1].have_error))
ret = afs_dir_remove_link(dvnode, dentry, key);
afs_check_for_remote_deletion(&fc, dvnode);
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, &scb[0]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]);
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
afs_vnode_commit_status(&fc, vnode, fc.cb_break_2,
NULL, &scb[1]);
ihold(&vnode->vfs_inode);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
d_instantiate(dentry, &vnode->vfs_inode);
mutex_unlock(&vnode->io_lock);
afs_check_for_remote_deletion(&fc, dvnode);
afs_vnode_commit_status(&fc, dvnode, fc.cb_break,
&data_version, &scb[0]);
+ afs_update_dentry_version(&fc, dentry, &scb[0]);
afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]);
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
}
}
+ /* This bit is potentially nasty as there's a potential race with
+ * afs_d_revalidate{,_rcu}(). We have to change d_fsdata on the dentry
+ * to reflect it's new parent's new data_version after the op, but
+ * d_revalidate may see old_dentry between the op having taken place
+ * and the version being updated.
+ *
+ * So drop the old_dentry for now to make other threads go through
+ * lookup instead - which we hold a lock against.
+ */
+ d_drop(old_dentry);
+
ret = -ERESTARTSYS;
if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) {
afs_dataversion_t orig_data_version;
if (orig_dvnode != new_dvnode) {
if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) {
afs_end_vnode_operation(&fc);
- goto error_rehash;
+ goto error_rehash_old;
}
- new_data_version = new_dvnode->status.data_version;
+ new_data_version = new_dvnode->status.data_version + 1;
} else {
new_data_version = orig_data_version;
new_scb = &scb[0];
}
ret = afs_end_vnode_operation(&fc);
if (ret < 0)
- goto error_rehash;
+ goto error_rehash_old;
}
if (ret == 0) {
drop_nlink(new_inode);
spin_unlock(&new_inode->i_lock);
}
+
+ /* Now we can update d_fsdata on the dentries to reflect their
+ * new parent's data_version.
+ *
+ * Note that if we ever implement RENAME_EXCHANGE, we'll have
+ * to update both dentries with opposing dir versions.
+ */
+ if (new_dvnode != orig_dvnode) {
+ afs_update_dentry_version(&fc, old_dentry, &scb[1]);
+ afs_update_dentry_version(&fc, new_dentry, &scb[1]);
+ } else {
+ afs_update_dentry_version(&fc, old_dentry, &scb[0]);
+ afs_update_dentry_version(&fc, new_dentry, &scb[0]);
+ }
d_move(old_dentry, new_dentry);
goto error_tmp;
}
+error_rehash_old:
+ d_rehash(new_dentry);
error_rehash:
if (rehash)
d_rehash(rehash);
int i;
if (refcount_dec_and_test(&req->usage)) {
- for (i = 0; i < req->nr_pages; i++)
- if (req->pages[i])
- put_page(req->pages[i]);
- if (req->pages != req->array)
- kfree(req->pages);
+ if (req->pages) {
+ for (i = 0; i < req->nr_pages; i++)
+ if (req->pages[i])
+ put_page(req->pages[i]);
+ if (req->pages != req->array)
+ kfree(req->pages);
+ }
kfree(req);
}
}
call->tmp_u = htonl(0);
afs_extract_to_tmp(call);
}
+ /* Fall through */
- /* Fall through - and extract the returned data length */
+ /* extract the returned data length */
case 1:
_debug("extract data length");
ret = afs_extract_data(call, true);
call->bvec[0].bv_page = req->pages[req->index];
iov_iter_bvec(&call->iter, READ, call->bvec, 1, size);
ASSERTCMP(size, <=, PAGE_SIZE);
+ /* Fall through */
- /* Fall through - and extract the returned data */
+ /* extract the returned data */
case 2:
_debug("extract data %zu/%llu",
iov_iter_count(&call->iter), req->remain);
/* Discard any excess data the server gave us */
iov_iter_discard(&call->iter, READ, req->actual_len - req->len);
call->unmarshall = 3;
-
/* Fall through */
+
case 3:
_debug("extract discard %zu/%llu",
iov_iter_count(&call->iter), req->actual_len - req->len);
no_more_data:
call->unmarshall = 4;
afs_extract_to_buf(call, (21 + 3 + 6) * 4);
+ /* Fall through */
- /* Fall through - and extract the metadata */
+ /* extract the metadata */
case 4:
ret = afs_extract_data(call, false);
if (ret < 0)
case 0:
call->unmarshall++;
afs_extract_to_buf(call, 12 * 4);
+ /* Fall through */
- /* Fall through - and extract the returned status record */
+ /* extract the returned status record */
case 1:
_debug("extract status");
ret = afs_extract_data(call, true);
xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus);
call->unmarshall++;
afs_extract_to_tmp(call);
+ /* Fall through */
- /* Fall through - and extract the volume name length */
+ /* extract the volume name length */
case 2:
ret = afs_extract_data(call, true);
if (ret < 0)
size = (call->count + 3) & ~3; /* It's padded */
afs_extract_to_buf(call, size);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the volume name */
+ /* extract the volume name */
case 3:
_debug("extract volname");
ret = afs_extract_data(call, true);
_debug("volname '%s'", p);
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the offline message length */
+ /* extract the offline message length */
case 4:
ret = afs_extract_data(call, true);
if (ret < 0)
size = (call->count + 3) & ~3; /* It's padded */
afs_extract_to_buf(call, size);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the offline message */
+ /* extract the offline message */
case 5:
_debug("extract offline");
ret = afs_extract_data(call, true);
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the message of the day length */
+ /* extract the message of the day length */
case 6:
ret = afs_extract_data(call, true);
if (ret < 0)
size = (call->count + 3) & ~3; /* It's padded */
afs_extract_to_buf(call, size);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the message of the day */
+ /* extract the message of the day */
case 7:
_debug("extract motd");
ret = afs_extract_data(call, false);
case 0:
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the capabilities word count */
+ /* Extract the capabilities word count */
case 1:
ret = afs_extract_data(call, true);
if (ret < 0)
call->count2 = count;
iov_iter_discard(&call->iter, READ, count * sizeof(__be32));
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract capabilities words */
+ /* Extract capabilities words */
case 2:
ret = afs_extract_data(call, false);
if (ret < 0)
case 0:
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
/* Extract the file status count and array in two steps */
- /* Fall through */
case 1:
_debug("extract status count");
ret = afs_extract_data(call, true);
call->unmarshall++;
more_counts:
afs_extract_to_buf(call, 21 * sizeof(__be32));
-
/* Fall through */
+
case 2:
_debug("extract status array %u", call->count);
ret = afs_extract_data(call, true);
call->count = 0;
call->unmarshall++;
afs_extract_to_tmp(call);
+ /* Fall through */
/* Extract the callback count and array in two steps */
- /* Fall through */
case 3:
_debug("extract CB count");
ret = afs_extract_data(call, true);
call->unmarshall++;
more_cbs:
afs_extract_to_buf(call, 3 * sizeof(__be32));
-
/* Fall through */
+
case 4:
_debug("extract CB array");
ret = afs_extract_data(call, true);
afs_extract_to_buf(call, 6 * sizeof(__be32));
call->unmarshall++;
-
/* Fall through */
+
case 5:
ret = afs_extract_data(call, false);
if (ret < 0)
case 0:
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
/* extract the returned data length */
case 1:
acl->size = call->count2;
afs_extract_begin(call, acl->data, size);
call->unmarshall++;
+ /* Fall through */
/* extract the returned data */
case 2:
afs_extract_to_buf(call, (21 + 6) * 4);
call->unmarshall++;
+ /* Fall through */
/* extract the metadata */
case 3:
struct afs_uuid__xdr *xdr;
struct afs_uuid *uuid;
int j;
+ int n = entry->nr_servers;
tmp = ntohl(uvldb->serverFlags[i]);
if (tmp & AFS_VLSF_DONTUSE ||
(new_only && !(tmp & AFS_VLSF_NEWREPSITE)))
continue;
if (tmp & AFS_VLSF_RWVOL) {
- entry->fs_mask[i] |= AFS_VOL_VTM_RW;
+ entry->fs_mask[n] |= AFS_VOL_VTM_RW;
if (vlflags & AFS_VLF_BACKEXISTS)
- entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
+ entry->fs_mask[n] |= AFS_VOL_VTM_BAK;
}
if (tmp & AFS_VLSF_ROVOL)
- entry->fs_mask[i] |= AFS_VOL_VTM_RO;
- if (!entry->fs_mask[i])
+ entry->fs_mask[n] |= AFS_VOL_VTM_RO;
+ if (!entry->fs_mask[n])
continue;
xdr = &uvldb->serverNumber[i];
- uuid = (struct afs_uuid *)&entry->fs_server[i];
+ uuid = (struct afs_uuid *)&entry->fs_server[n];
uuid->time_low = xdr->time_low;
uuid->time_mid = htons(ntohl(xdr->time_mid));
uuid->time_hi_and_version = htons(ntohl(xdr->time_hi_and_version));
req->offset = req->pos & (PAGE_SIZE - 1);
afs_extract_to_tmp64(call);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the returned data length */
+ /* extract the returned data length */
case 1:
_debug("extract data length");
ret = afs_extract_data(call, true);
call->bvec[0].bv_page = req->pages[req->index];
iov_iter_bvec(&call->iter, READ, call->bvec, 1, size);
ASSERTCMP(size, <=, PAGE_SIZE);
+ /* Fall through */
- /* Fall through - and extract the returned data */
+ /* extract the returned data */
case 2:
_debug("extract data %zu/%llu",
iov_iter_count(&call->iter), req->remain);
/* Discard any excess data the server gave us */
iov_iter_discard(&call->iter, READ, req->actual_len - req->len);
call->unmarshall = 3;
-
/* Fall through */
+
case 3:
_debug("extract discard %zu/%llu",
iov_iter_count(&call->iter), req->actual_len - req->len);
sizeof(struct yfs_xdr_YFSFetchStatus) +
sizeof(struct yfs_xdr_YFSCallBack) +
sizeof(struct yfs_xdr_YFSVolSync));
+ /* Fall through */
- /* Fall through - and extract the metadata */
+ /* extract the metadata */
case 4:
ret = afs_extract_data(call, false);
if (ret < 0)
req->file_size = call->out_scb->status.size;
call->unmarshall++;
-
/* Fall through */
+
case 5:
break;
}
case 0:
call->unmarshall++;
afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus));
+ /* Fall through */
- /* Fall through - and extract the returned status record */
+ /* extract the returned status record */
case 1:
_debug("extract status");
ret = afs_extract_data(call, true);
xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus);
call->unmarshall++;
afs_extract_to_tmp(call);
+ /* Fall through */
- /* Fall through - and extract the volume name length */
+ /* extract the volume name length */
case 2:
ret = afs_extract_data(call, true);
if (ret < 0)
size = (call->count + 3) & ~3; /* It's padded */
afs_extract_to_buf(call, size);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the volume name */
+ /* extract the volume name */
case 3:
_debug("extract volname");
ret = afs_extract_data(call, true);
_debug("volname '%s'", p);
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the offline message length */
+ /* extract the offline message length */
case 4:
ret = afs_extract_data(call, true);
if (ret < 0)
size = (call->count + 3) & ~3; /* It's padded */
afs_extract_to_buf(call, size);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the offline message */
+ /* extract the offline message */
case 5:
_debug("extract offline");
ret = afs_extract_data(call, true);
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the message of the day length */
+ /* extract the message of the day length */
case 6:
ret = afs_extract_data(call, true);
if (ret < 0)
size = (call->count + 3) & ~3; /* It's padded */
afs_extract_to_buf(call, size);
call->unmarshall++;
+ /* Fall through */
- /* Fall through - and extract the message of the day */
+ /* extract the message of the day */
case 7:
_debug("extract motd");
ret = afs_extract_data(call, false);
_debug("motd '%s'", p);
call->unmarshall++;
-
/* Fall through */
+
case 8:
break;
}
case 0:
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
/* Extract the file status count and array in two steps */
- /* Fall through */
case 1:
_debug("extract status count");
ret = afs_extract_data(call, true);
call->unmarshall++;
more_counts:
afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus));
-
/* Fall through */
+
case 2:
_debug("extract status array %u", call->count);
ret = afs_extract_data(call, true);
call->count = 0;
call->unmarshall++;
afs_extract_to_tmp(call);
+ /* Fall through */
/* Extract the callback count and array in two steps */
- /* Fall through */
case 3:
_debug("extract CB count");
ret = afs_extract_data(call, true);
call->unmarshall++;
more_cbs:
afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack));
-
/* Fall through */
+
case 4:
_debug("extract CB array");
ret = afs_extract_data(call, true);
afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync));
call->unmarshall++;
-
/* Fall through */
+
case 5:
ret = afs_extract_data(call, false);
if (ret < 0)
xdr_decode_YFSVolSync(&bp, call->out_volsync);
call->unmarshall++;
-
/* Fall through */
+
case 6:
break;
}
case 0:
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
/* Extract the file ACL length */
case 1:
iov_iter_discard(&call->iter, READ, size);
}
call->unmarshall++;
+ /* Fall through */
/* Extract the file ACL */
case 2:
afs_extract_to_tmp(call);
call->unmarshall++;
+ /* Fall through */
/* Extract the volume ACL length */
case 3:
iov_iter_discard(&call->iter, READ, size);
}
call->unmarshall++;
+ /* Fall through */
/* Extract the volume ACL */
case 4:
sizeof(struct yfs_xdr_YFSFetchStatus) +
sizeof(struct yfs_xdr_YFSVolSync));
call->unmarshall++;
+ /* Fall through */
/* extract the metadata */
case 5:
xdr_decode_YFSVolSync(&bp, call->out_volsync);
call->unmarshall++;
+ /* Fall through */
case 6:
break;
key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode);
size = round_up(acl->size, 4);
- call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus,
+ call = afs_alloc_flat_call(net, &yfs_RXYFSStoreOpaqueACL2,
sizeof(__be32) * 2 +
sizeof(struct yfs_xdr_YFSFid) +
sizeof(__be32) + size,
* Pointer to the block device containing @bdev on success, ERR_PTR()
* value on failure.
*/
-static struct block_device *bd_start_claiming(struct block_device *bdev,
- void *holder)
+struct block_device *bd_start_claiming(struct block_device *bdev, void *holder)
{
struct gendisk *disk;
struct block_device *whole;
return ERR_PTR(err);
}
}
+EXPORT_SYMBOL(bd_start_claiming);
+
+static void bd_clear_claiming(struct block_device *whole, void *holder)
+{
+ lockdep_assert_held(&bdev_lock);
+ /* tell others that we're done */
+ BUG_ON(whole->bd_claiming != holder);
+ whole->bd_claiming = NULL;
+ wake_up_bit(&whole->bd_claiming, 0);
+}
+
+/**
+ * bd_finish_claiming - finish claiming of a block device
+ * @bdev: block device of interest
+ * @whole: whole block device (returned from bd_start_claiming())
+ * @holder: holder that has claimed @bdev
+ *
+ * Finish exclusive open of a block device. Mark the device as exlusively
+ * open by the holder and wake up all waiters for exclusive open to finish.
+ */
+void bd_finish_claiming(struct block_device *bdev, struct block_device *whole,
+ void *holder)
+{
+ spin_lock(&bdev_lock);
+ BUG_ON(!bd_may_claim(bdev, whole, holder));
+ /*
+ * Note that for a whole device bd_holders will be incremented twice,
+ * and bd_holder will be set to bd_may_claim before being set to holder
+ */
+ whole->bd_holders++;
+ whole->bd_holder = bd_may_claim;
+ bdev->bd_holders++;
+ bdev->bd_holder = holder;
+ bd_clear_claiming(whole, holder);
+ spin_unlock(&bdev_lock);
+}
+EXPORT_SYMBOL(bd_finish_claiming);
+
+/**
+ * bd_abort_claiming - abort claiming of a block device
+ * @bdev: block device of interest
+ * @whole: whole block device (returned from bd_start_claiming())
+ * @holder: holder that has claimed @bdev
+ *
+ * Abort claiming of a block device when the exclusive open failed. This can be
+ * also used when exclusive open is not actually desired and we just needed
+ * to block other exclusive openers for a while.
+ */
+void bd_abort_claiming(struct block_device *bdev, struct block_device *whole,
+ void *holder)
+{
+ spin_lock(&bdev_lock);
+ bd_clear_claiming(whole, holder);
+ spin_unlock(&bdev_lock);
+}
+EXPORT_SYMBOL(bd_abort_claiming);
#ifdef CONFIG_SYSFS
struct bd_holder_disk {
/* finish claiming */
mutex_lock(&bdev->bd_mutex);
- spin_lock(&bdev_lock);
-
- if (!res) {
- BUG_ON(!bd_may_claim(bdev, whole, holder));
- /*
- * Note that for a whole device bd_holders
- * will be incremented twice, and bd_holder
- * will be set to bd_may_claim before being
- * set to holder
- */
- whole->bd_holders++;
- whole->bd_holder = bd_may_claim;
- bdev->bd_holders++;
- bdev->bd_holder = holder;
- }
-
- /* tell others that we're done */
- BUG_ON(whole->bd_claiming != holder);
- whole->bd_claiming = NULL;
- wake_up_bit(&whole->bd_claiming, 0);
-
- spin_unlock(&bdev_lock);
-
+ if (!res)
+ bd_finish_claiming(bdev, whole, holder);
+ else
+ bd_abort_claiming(bdev, whole, holder);
/*
* Block event polling for write claims if requested. Any
* write holder makes the write_holder state stick until
tristate "Btrfs filesystem support"
select CRYPTO
select CRYPTO_CRC32C
+ select LIBCRC32C
select ZLIB_INFLATE
select ZLIB_DEFLATE
select LZO_COMPRESS
ulist_init(roots);
ulist_init(tmp);
- trans = btrfs_attach_transaction(root);
+ trans = btrfs_join_transaction_nostart(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) {
ret = PTR_ERR(trans);
struct raid_kobject {
u64 flags;
struct kobject kobj;
- struct list_head list;
};
/*
u32 thread_pool_size;
struct kobject *space_info_kobj;
- struct list_head pending_raid_kobjs;
- spinlock_t pending_raid_kobjs_lock; /* uncontended */
u64 total_pinned;
int btrfs_make_block_group(struct btrfs_trans_handle *trans,
u64 bytes_used, u64 type, u64 chunk_offset,
u64 size);
-void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
struct btrfs_fs_info *fs_info,
const u64 chunk_offset);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
INIT_LIST_HEAD(&fs_info->delalloc_roots);
INIT_LIST_HEAD(&fs_info->caching_block_groups);
- INIT_LIST_HEAD(&fs_info->pending_raid_kobjs);
- spin_lock_init(&fs_info->pending_raid_kobjs_lock);
spin_lock_init(&fs_info->delalloc_root_lock);
spin_lock_init(&fs_info->trans_lock);
spin_lock_init(&fs_info->fs_roots_radix_lock);
percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
cleanup_srcu_struct(&fs_info->subvol_srcu);
+ btrfs_free_csum_hash(fs_info);
btrfs_free_stripe_hash_table(fs_info);
btrfs_free_ref_cache(fs_info);
}
*/
#include <linux/sched.h>
+#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
return 0;
}
-/* link_block_group will queue up kobjects to add when we're reclaim-safe */
-void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info)
-{
- struct btrfs_space_info *space_info;
- struct raid_kobject *rkobj;
- LIST_HEAD(list);
- int ret = 0;
-
- spin_lock(&fs_info->pending_raid_kobjs_lock);
- list_splice_init(&fs_info->pending_raid_kobjs, &list);
- spin_unlock(&fs_info->pending_raid_kobjs_lock);
-
- list_for_each_entry(rkobj, &list, list) {
- space_info = btrfs_find_space_info(fs_info, rkobj->flags);
-
- ret = kobject_add(&rkobj->kobj, &space_info->kobj,
- "%s", btrfs_bg_type_to_raid_name(rkobj->flags));
- if (ret) {
- kobject_put(&rkobj->kobj);
- break;
- }
- }
- if (ret)
- btrfs_warn(fs_info,
- "failed to add kobject for block cache, ignoring");
-}
-
static void link_block_group(struct btrfs_block_group_cache *cache)
{
struct btrfs_space_info *space_info = cache->space_info;
up_write(&space_info->groups_sem);
if (first) {
- struct raid_kobject *rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
+ struct raid_kobject *rkobj;
+ unsigned int nofs_flag;
+ int ret;
+
+ /*
+ * Setup a NOFS context because kobject_add(), deep in its call
+ * chain, does GFP_KERNEL allocations, and we are often called
+ * in a context where if reclaim is triggered we can deadlock
+ * (we are either holding a transaction handle or some lock
+ * required for a transaction commit).
+ */
+ nofs_flag = memalloc_nofs_save();
+ rkobj = kzalloc(sizeof(*rkobj), GFP_KERNEL);
if (!rkobj) {
+ memalloc_nofs_restore(nofs_flag);
btrfs_warn(cache->fs_info,
"couldn't alloc memory for raid level kobject");
return;
}
rkobj->flags = cache->flags;
kobject_init(&rkobj->kobj, &btrfs_raid_ktype);
-
- spin_lock(&fs_info->pending_raid_kobjs_lock);
- list_add_tail(&rkobj->list, &fs_info->pending_raid_kobjs);
- spin_unlock(&fs_info->pending_raid_kobjs_lock);
+ ret = kobject_add(&rkobj->kobj, &space_info->kobj, "%s",
+ btrfs_bg_type_to_raid_name(rkobj->flags));
+ memalloc_nofs_restore(nofs_flag);
+ if (ret) {
+ kobject_put(&rkobj->kobj);
+ btrfs_warn(fs_info,
+ "failed to add kobject for block cache, ignoring");
+ return;
+ }
space_info->block_group_kobjs[index] = &rkobj->kobj;
}
}
inc_block_group_ro(cache, 1);
}
- btrfs_add_raid_kobjects(info);
btrfs_init_global_block_rsv(info);
ret = check_chunk_block_group_mappings(info);
error:
struct btrfs_device *device;
struct list_head *devices;
u64 group_trimmed;
+ u64 range_end = U64_MAX;
u64 start;
u64 end;
u64 trimmed = 0;
int dev_ret = 0;
int ret = 0;
+ /*
+ * Check range overflow if range->len is set.
+ * The default range->len is U64_MAX.
+ */
+ if (range->len != U64_MAX &&
+ check_add_overflow(range->start, range->len, &range_end))
+ return -EINVAL;
+
cache = btrfs_lookup_first_block_group(fs_info, range->start);
for (; cache; cache = next_block_group(cache)) {
- if (cache->key.objectid >= (range->start + range->len)) {
+ if (cache->key.objectid >= range_end) {
btrfs_put_block_group(cache);
break;
}
start = max(range->start, cache->key.objectid);
- end = min(range->start + range->len,
- cache->key.objectid + cache->key.offset);
+ end = min(range_end, cache->key.objectid + cache->key.offset);
if (end - start >= range->minlen) {
if (!block_group_cache_done(cache)) {
return 0;
}
+/*
+ * Check if the inode has flags compatible with compression
+ */
+static inline bool inode_can_compress(struct inode *inode)
+{
+ if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW ||
+ BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+ return false;
+ return true;
+}
+
+/*
+ * Check if the inode needs to be submitted to compression, based on mount
+ * options, defragmentation, properties or heuristics.
+ */
static inline int inode_need_compress(struct inode *inode, u64 start, u64 end)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ if (!inode_can_compress(inode)) {
+ WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
+ KERN_ERR "BTRFS: unexpected compression for ino %llu\n",
+ btrfs_ino(BTRFS_I(inode)));
+ return 0;
+ }
/* force compress */
if (btrfs_test_opt(fs_info, FORCE_COMPRESS))
return 1;
} else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) {
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 0, nr_written);
- } else if (!inode_need_compress(inode, start, end)) {
+ } else if (!inode_can_compress(inode) ||
+ !inode_need_compress(inode, start, end)) {
ret = cow_file_range(inode, locked_page, start, end, end,
page_started, nr_written, 1, NULL);
} else {
if (blockers) {
btrfs_assert_no_spinning_writers(eb);
eb->blocking_writers--;
- /* Use the lighter barrier after atomic */
- smp_mb__after_atomic();
- cond_wake_up_nomb(&eb->write_lock_wq);
+ /*
+ * We need to order modifying blocking_writers above with
+ * actually waking up the sleepers to ensure they see the
+ * updated value of blocking_writers
+ */
+ cond_wake_up(&eb->write_lock_wq);
} else {
btrfs_assert_spinning_writers_put(eb);
write_unlock(&eb->lock);
struct extent_state **cached_state)
{
struct btrfs_ordered_extent *ordered;
- struct extent_state *cachedp = NULL;
+ struct extent_state *cache = NULL;
+ struct extent_state **cachedp = &cache;
if (cached_state)
- cachedp = *cached_state;
+ cachedp = cached_state;
while (1) {
- lock_extent_bits(tree, start, end, &cachedp);
+ lock_extent_bits(tree, start, end, cachedp);
ordered = btrfs_lookup_ordered_range(inode, start,
end - start + 1);
if (!ordered) {
* aren't exposing it outside of this function
*/
if (!cached_state)
- refcount_dec(&cachedp->refs);
+ refcount_dec(&cache->refs);
break;
}
- unlock_extent_cached(tree, start, end, &cachedp);
+ unlock_extent_cached(tree, start, end, cachedp);
btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1);
btrfs_put_ordered_extent(ordered);
}
{
int ret = 0;
- if (sctx->cur_ino != sctx->cmp_key->objectid) {
-
- if (result == BTRFS_COMPARE_TREE_CHANGED) {
- struct extent_buffer *leaf_l;
- struct extent_buffer *leaf_r;
- struct btrfs_file_extent_item *ei_l;
- struct btrfs_file_extent_item *ei_r;
-
- leaf_l = sctx->left_path->nodes[0];
- leaf_r = sctx->right_path->nodes[0];
- ei_l = btrfs_item_ptr(leaf_l,
- sctx->left_path->slots[0],
- struct btrfs_file_extent_item);
- ei_r = btrfs_item_ptr(leaf_r,
- sctx->right_path->slots[0],
- struct btrfs_file_extent_item);
-
- /*
- * We may have found an extent item that has changed
- * only its disk_bytenr field and the corresponding
- * inode item was not updated. This case happens due to
- * very specific timings during relocation when a leaf
- * that contains file extent items is COWed while
- * relocation is ongoing and its in the stage where it
- * updates data pointers. So when this happens we can
- * safely ignore it since we know it's the same extent,
- * but just at different logical and physical locations
- * (when an extent is fully replaced with a new one, we
- * know the generation number must have changed too,
- * since snapshot creation implies committing the current
- * transaction, and the inode item must have been updated
- * as well).
- * This replacement of the disk_bytenr happens at
- * relocation.c:replace_file_extents() through
- * relocation.c:btrfs_reloc_cow_block().
- */
- if (btrfs_file_extent_generation(leaf_l, ei_l) ==
- btrfs_file_extent_generation(leaf_r, ei_r) &&
- btrfs_file_extent_ram_bytes(leaf_l, ei_l) ==
- btrfs_file_extent_ram_bytes(leaf_r, ei_r) &&
- btrfs_file_extent_compression(leaf_l, ei_l) ==
- btrfs_file_extent_compression(leaf_r, ei_r) &&
- btrfs_file_extent_encryption(leaf_l, ei_l) ==
- btrfs_file_extent_encryption(leaf_r, ei_r) &&
- btrfs_file_extent_other_encoding(leaf_l, ei_l) ==
- btrfs_file_extent_other_encoding(leaf_r, ei_r) &&
- btrfs_file_extent_type(leaf_l, ei_l) ==
- btrfs_file_extent_type(leaf_r, ei_r) &&
- btrfs_file_extent_disk_bytenr(leaf_l, ei_l) !=
- btrfs_file_extent_disk_bytenr(leaf_r, ei_r) &&
- btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) ==
- btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) &&
- btrfs_file_extent_offset(leaf_l, ei_l) ==
- btrfs_file_extent_offset(leaf_r, ei_r) &&
- btrfs_file_extent_num_bytes(leaf_l, ei_l) ==
- btrfs_file_extent_num_bytes(leaf_r, ei_r))
- return 0;
- }
-
- inconsistent_snapshot_error(sctx, result, "extent");
- return -EIO;
- }
+ /*
+ * We have found an extent item that changed without the inode item
+ * having changed. This can happen either after relocation (where the
+ * disk_bytenr of an extent item is replaced at
+ * relocation.c:replace_file_extents()) or after deduplication into a
+ * file in both the parent and send snapshots (where an extent item can
+ * get modified or replaced with a new one). Note that deduplication
+ * updates the inode item, but it only changes the iversion (sequence
+ * field in the inode item) of the inode, so if a file is deduplicated
+ * the same amount of times in both the parent and send snapshots, its
+ * iversion becames the same in both snapshots, whence the inode item is
+ * the same on both snapshots.
+ */
+ if (sctx->cur_ino != sctx->cmp_key->objectid)
+ return 0;
if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
if (result != BTRFS_COMPARE_TREE_DELETED)
[TRANS_STATE_COMMIT_START] = (__TRANS_START | __TRANS_ATTACH),
[TRANS_STATE_COMMIT_DOING] = (__TRANS_START |
__TRANS_ATTACH |
- __TRANS_JOIN),
+ __TRANS_JOIN |
+ __TRANS_JOIN_NOSTART),
[TRANS_STATE_UNBLOCKED] = (__TRANS_START |
__TRANS_ATTACH |
__TRANS_JOIN |
- __TRANS_JOIN_NOLOCK),
+ __TRANS_JOIN_NOLOCK |
+ __TRANS_JOIN_NOSTART),
[TRANS_STATE_COMPLETED] = (__TRANS_START |
__TRANS_ATTACH |
__TRANS_JOIN |
- __TRANS_JOIN_NOLOCK),
+ __TRANS_JOIN_NOLOCK |
+ __TRANS_JOIN_NOSTART),
};
void btrfs_put_transaction(struct btrfs_transaction *transaction)
ret = join_transaction(fs_info, type);
if (ret == -EBUSY) {
wait_current_trans(fs_info);
- if (unlikely(type == TRANS_ATTACH))
+ if (unlikely(type == TRANS_ATTACH ||
+ type == TRANS_JOIN_NOSTART))
ret = -ENOENT;
}
} while (ret == -EBUSY);
BTRFS_RESERVE_NO_FLUSH, true);
}
+/*
+ * Similar to regular join but it never starts a transaction when none is
+ * running or after waiting for the current one to finish.
+ */
+struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root)
+{
+ return start_transaction(root, 0, TRANS_JOIN_NOSTART,
+ BTRFS_RESERVE_NO_FLUSH, true);
+}
+
/*
* btrfs_attach_transaction() - catch the running transaction
*
}
} else {
spin_unlock(&fs_info->trans_lock);
+ /*
+ * The previous transaction was aborted and was already removed
+ * from the list of transactions at fs_info->trans_list. So we
+ * abort to prevent writing a new superblock that reflects a
+ * corrupt state (pointing to trees with unwritten nodes/leafs).
+ */
+ if (test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) {
+ ret = -EROFS;
+ goto cleanup_transaction;
+ }
}
extwriter_counter_dec(cur_trans, trans->type);
#define __TRANS_JOIN (1U << 11)
#define __TRANS_JOIN_NOLOCK (1U << 12)
#define __TRANS_DUMMY (1U << 13)
+#define __TRANS_JOIN_NOSTART (1U << 14)
#define TRANS_START (__TRANS_START | __TRANS_FREEZABLE)
#define TRANS_ATTACH (__TRANS_ATTACH)
#define TRANS_JOIN (__TRANS_JOIN | __TRANS_FREEZABLE)
#define TRANS_JOIN_NOLOCK (__TRANS_JOIN_NOLOCK)
+#define TRANS_JOIN_NOSTART (__TRANS_JOIN_NOSTART)
#define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH)
int min_factor);
struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
struct btrfs_root *root);
if (ret)
return ret;
- /*
- * We add the kobjects here (and after forcing data chunk creation)
- * since relocation is the only place we'll create chunks of a new
- * type at runtime. The only place where we'll remove the last
- * chunk of a type is the call immediately below this one. Even
- * so, we're protected against races with the cleaner thread since
- * we're covered by the delete_unused_bgs_mutex.
- */
- btrfs_add_raid_kobjects(fs_info);
-
trans = btrfs_start_trans_remove_block_group(root->fs_info,
chunk_offset);
if (IS_ERR(trans)) {
btrfs_end_transaction(trans);
if (ret < 0)
return ret;
-
- btrfs_add_raid_kobjects(fs_info);
-
return 1;
}
}
u64 stripe_len;
u64 raid56_full_stripe_start = (u64)-1;
int data_stripes;
+ int ret = 0;
ASSERT(op != BTRFS_MAP_DISCARD);
btrfs_crit(fs_info,
"stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu",
stripe_offset, offset, em->start, logical, stripe_len);
- free_extent_map(em);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
/* stripe_offset is the offset of this block in its stripe */
io_geom->stripe_offset = stripe_offset;
io_geom->raid56_stripe_offset = raid56_full_stripe_start;
- return 0;
+out:
+ /* once for us */
+ free_extent_map(em);
+ return ret;
}
static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
if (page_offset(page) >= ceph_wbc.i_size) {
dout("%p page eof %llu\n",
page, ceph_wbc.i_size);
- if (ceph_wbc.size_stable ||
- page_offset(page) >= i_size_read(inode))
+ if ((ceph_wbc.size_stable ||
+ page_offset(page) >= i_size_read(inode)) &&
+ clear_page_dirty_for_io(page))
mapping->a_ops->invalidatepage(page,
0, PAGE_SIZE);
unlock_page(page);
{
struct ceph_inode_info *ci = cap->ci;
struct inode *inode = &ci->vfs_inode;
+ struct ceph_buffer *old_blob = NULL;
struct cap_msg_args arg;
int held, revoking;
int wake = 0;
ci->i_requested_max_size = arg.max_size;
if (flushing & CEPH_CAP_XATTR_EXCL) {
- __ceph_build_xattrs_blob(ci);
+ old_blob = __ceph_build_xattrs_blob(ci);
arg.xattr_version = ci->i_xattrs.version;
arg.xattr_buf = ci->i_xattrs.blob;
} else {
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
+
ret = send_cap_msg(&arg);
if (ret < 0) {
dout("error sending cap msg, must requeue %p\n", inode);
int issued, new_issued, info_caps;
struct timespec64 mtime, atime, ctime;
struct ceph_buffer *xattr_blob = NULL;
+ struct ceph_buffer *old_blob = NULL;
struct ceph_string *pool_ns = NULL;
struct ceph_cap *new_cap = NULL;
int err = 0;
if ((ci->i_xattrs.version == 0 || !(issued & CEPH_CAP_XATTR_EXCL)) &&
le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) {
if (ci->i_xattrs.blob)
- ceph_buffer_put(ci->i_xattrs.blob);
+ old_blob = ci->i_xattrs.blob;
ci->i_xattrs.blob = xattr_blob;
if (xattr_blob)
memcpy(ci->i_xattrs.blob->vec.iov_base,
out:
if (new_cap)
ceph_put_cap(mdsc, new_cap);
- if (xattr_blob)
- ceph_buffer_put(xattr_blob);
+ ceph_buffer_put(old_blob);
+ ceph_buffer_put(xattr_blob);
ceph_put_string(pool_ns);
return err;
}
req->r_wait_for_completion = ceph_lock_wait_for_completion;
err = ceph_mdsc_do_request(mdsc, inode, req);
-
- if (operation == CEPH_MDS_OP_GETFILELOCK) {
+ if (!err && operation == CEPH_MDS_OP_GETFILELOCK) {
fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
struct inode *inode = &ci->vfs_inode;
struct ceph_cap_snap *capsnap;
struct ceph_snap_context *old_snapc, *new_snapc;
+ struct ceph_buffer *old_blob = NULL;
int used, dirty;
capsnap = kzalloc(sizeof(*capsnap), GFP_NOFS);
capsnap->gid = inode->i_gid;
if (dirty & CEPH_CAP_XATTR_EXCL) {
- __ceph_build_xattrs_blob(ci);
+ old_blob = __ceph_build_xattrs_blob(ci);
capsnap->xattr_blob =
ceph_buffer_get(ci->i_xattrs.blob);
capsnap->xattr_version = ci->i_xattrs.version;
}
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
kfree(capsnap);
ceph_put_snap_context(old_snapc);
}
int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
ssize_t __ceph_getxattr(struct inode *, const char *, void *, size_t);
extern ssize_t ceph_listxattr(struct dentry *, char *, size_t);
-extern void __ceph_build_xattrs_blob(struct ceph_inode_info *ci);
+extern struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci);
extern void __ceph_destroy_xattrs(struct ceph_inode_info *ci);
extern const struct xattr_handler *ceph_xattr_handlers[];
/*
* If there are dirty xattrs, reencode xattrs into the prealloc_blob
- * and swap into place.
+ * and swap into place. It returns the old i_xattrs.blob (or NULL) so
+ * that it can be freed by the caller as the i_ceph_lock is likely to be
+ * held.
*/
-void __ceph_build_xattrs_blob(struct ceph_inode_info *ci)
+struct ceph_buffer *__ceph_build_xattrs_blob(struct ceph_inode_info *ci)
{
struct rb_node *p;
struct ceph_inode_xattr *xattr = NULL;
+ struct ceph_buffer *old_blob = NULL;
void *dest;
dout("__build_xattrs_blob %p\n", &ci->vfs_inode);
dest - ci->i_xattrs.prealloc_blob->vec.iov_base;
if (ci->i_xattrs.blob)
- ceph_buffer_put(ci->i_xattrs.blob);
+ old_blob = ci->i_xattrs.blob;
ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = NULL;
ci->i_xattrs.dirty = false;
ci->i_xattrs.version++;
}
+
+ return old_blob;
}
static inline int __get_request_mask(struct inode *in) {
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_cap_flush *prealloc_cf = NULL;
+ struct ceph_buffer *old_blob = NULL;
int issued;
int err;
int dirty = 0;
struct ceph_buffer *blob;
spin_unlock(&ci->i_ceph_lock);
- dout(" preaallocating new blob size=%d\n", required_blob_size);
+ ceph_buffer_put(old_blob); /* Shouldn't be required */
+ dout(" pre-allocating new blob size=%d\n", required_blob_size);
blob = ceph_buffer_new(required_blob_size, GFP_NOFS);
if (!blob)
goto do_sync_unlocked;
spin_lock(&ci->i_ceph_lock);
+ /* prealloc_blob can't be released while holding i_ceph_lock */
if (ci->i_xattrs.prealloc_blob)
- ceph_buffer_put(ci->i_xattrs.prealloc_blob);
+ old_blob = ci->i_xattrs.prealloc_blob;
ci->i_xattrs.prealloc_blob = blob;
goto retry;
}
}
spin_unlock(&ci->i_ceph_lock);
+ ceph_buffer_put(old_blob);
if (lock_snap_rwsem)
up_read(&mdsc->snap_rwsem);
if (dirty)
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.21"
+#define CIFS_VERSION "2.22"
#endif /* _CIFSFS_H */
unsigned int *len, unsigned int *offset);
void extract_unc_hostname(const char *unc, const char **h, size_t *len);
+int copy_path_name(char *dst, const char *src);
#ifdef CONFIG_CIFS_DFS_UPCALL
static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses,
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB add path length overrun check */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, fileName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, fileName);
}
params = 6 + name_len;
remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve check for buffer overruns BB */
- name_len = strnlen(name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->fileName, name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->fileName, name);
}
pSMB->SearchAttributes =
cpu_to_le16(ATTR_READONLY | ATTR_HIDDEN | ATTR_SYSTEM);
remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve check for buffer overruns BB */
- name_len = strnlen(name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->DirName, name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->DirName, name);
}
pSMB->BufferFormat = 0x04;
remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve check for buffer overruns BB */
- name_len = strnlen(name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->DirName, name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->DirName, name);
}
pSMB->BufferFormat = 0x04;
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, name);
}
params = 6 + name_len;
fileName, PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve check for buffer overruns BB */
+ } else {
count = 0; /* no pad */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->fileName, fileName, name_len);
+ name_len = copy_path_name(pSMB->fileName, fileName);
}
if (*pOplock & REQ_OPLOCK)
pSMB->OpenFlags = cpu_to_le16(REQ_OPLOCK);
/* BB improve check for buffer overruns BB */
/* no pad */
count = 0;
- name_len = strnlen(path, PATH_MAX);
- /* trailing null */
- name_len++;
+ name_len = copy_path_name(req->fileName, path);
req->NameLength = cpu_to_le16(name_len);
- strncpy(req->fileName, path, name_len);
}
if (*oplock & REQ_OPLOCK)
remap);
name_len2 += 1 /* trailing null */ + 1 /* Signature word */ ;
name_len2 *= 2; /* convert to bytes */
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(from_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->OldFileName, from_name, name_len);
- name_len2 = strnlen(to_name, PATH_MAX);
- name_len2++; /* trailing null */
+ } else {
+ name_len = copy_path_name(pSMB->OldFileName, from_name);
+ name_len2 = copy_path_name(pSMB->OldFileName+name_len+1, to_name);
pSMB->OldFileName[name_len] = 0x04; /* 2nd buffer format */
- strncpy(&pSMB->OldFileName[name_len + 1], to_name, name_len2);
- name_len2++; /* trailing null */
name_len2++; /* signature byte */
}
toName, PATH_MAX, nls_codepage, remap);
name_len2 += 1 /* trailing null */ + 1 /* Signature word */ ;
name_len2 *= 2; /* convert to bytes */
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(fromName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->OldFileName, fromName, name_len);
- name_len2 = strnlen(toName, PATH_MAX);
- name_len2++; /* trailing null */
+ } else {
+ name_len = copy_path_name(pSMB->OldFileName, fromName);
pSMB->OldFileName[name_len] = 0x04; /* 2nd buffer format */
- strncpy(&pSMB->OldFileName[name_len + 1], toName, name_len2);
- name_len2++; /* trailing null */
+ name_len2 = copy_path_name(pSMB->OldFileName+name_len+1, toName);
name_len2++; /* signature byte */
}
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(fromName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, fromName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, fromName);
}
params = 6 + name_len;
pSMB->MaxSetupCount = 0;
PATH_MAX, nls_codepage, remap);
name_len_target++; /* trailing null */
name_len_target *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len_target = strnlen(toName, PATH_MAX);
- name_len_target++; /* trailing null */
- strncpy(data_offset, toName, name_len_target);
+ } else {
+ name_len_target = copy_path_name(data_offset, toName);
}
pSMB->MaxParameterCount = cpu_to_le16(2);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(toName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, toName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, toName);
}
params = 6 + name_len;
pSMB->MaxSetupCount = 0;
PATH_MAX, nls_codepage, remap);
name_len_target++; /* trailing null */
name_len_target *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len_target = strnlen(fromName, PATH_MAX);
- name_len_target++; /* trailing null */
- strncpy(data_offset, fromName, name_len_target);
+ } else {
+ name_len_target = copy_path_name(data_offset, fromName);
}
pSMB->MaxParameterCount = cpu_to_le16(2);
remap);
name_len2 += 1 /* trailing null */ + 1 /* Signature word */ ;
name_len2 *= 2; /* convert to bytes */
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(from_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->OldFileName, from_name, name_len);
- name_len2 = strnlen(to_name, PATH_MAX);
- name_len2++; /* trailing null */
+ } else {
+ name_len = copy_path_name(pSMB->OldFileName, from_name);
pSMB->OldFileName[name_len] = 0x04; /* 2nd buffer format */
- strncpy(&pSMB->OldFileName[name_len + 1], to_name, name_len2);
- name_len2++; /* trailing null */
+ name_len2 = copy_path_name(pSMB->OldFileName+name_len+1, to_name);
name_len2++; /* signature byte */
}
remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(searchName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, searchName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, searchName);
}
params = 2 /* level */ + 4 /* rsrvd */ + name_len /* incl null */ ;
name_len *= 2;
pSMB->FileName[name_len] = 0;
pSMB->FileName[name_len+1] = 0;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(searchName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, searchName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, searchName);
}
params = 2 /* level */ + 4 /* rsrvd */ + name_len /* incl null */ ;
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, fileName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, fileName);
}
params = 6 + name_len;
pSMB->MaxParameterCount = cpu_to_le16(2);
name_len++; /* trailing null */
name_len *= 2;
} else {
- name_len = strnlen(search_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, search_name, name_len);
+ name_len = copy_path_name(pSMB->FileName, search_name);
}
pSMB->BufferFormat = 0x04;
name_len++; /* account for buffer type byte */
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(search_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, search_name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, search_name);
}
params = 2 /* level */ + 4 /* reserved */ + name_len /* includes NUL */;
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(searchName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, searchName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, searchName);
}
params = 2 /* level */ + 4 /* reserved */ + name_len /* includes NUL */;
pSMB->FileName[name_len+1] = 0;
name_len += 2;
}
- } else { /* BB add check for overrun of SMB buf BB */
- name_len = strnlen(searchName, PATH_MAX);
-/* BB fix here and in unicode clause above ie
- if (name_len > buffersize-header)
- free buffer exit; BB */
- strncpy(pSMB->FileName, searchName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, searchName);
if (msearch) {
- pSMB->FileName[name_len] = CIFS_DIR_SEP(cifs_sb);
- pSMB->FileName[name_len+1] = '*';
- pSMB->FileName[name_len+2] = 0;
- name_len += 3;
+ if (WARN_ON_ONCE(name_len > PATH_MAX-2))
+ name_len = PATH_MAX-2;
+ /* overwrite nul byte */
+ pSMB->FileName[name_len-1] = CIFS_DIR_SEP(cifs_sb);
+ pSMB->FileName[name_len] = '*';
+ pSMB->FileName[name_len+1] = 0;
+ name_len += 2;
}
}
remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(search_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, search_name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, search_name);
}
params = 2 /* level */ + 4 /* rsrvd */ + name_len /* incl null */ ;
name_len++; /* trailing null */
name_len *= 2;
} else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(search_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->RequestFileName, search_name, name_len);
+ name_len = copy_path_name(pSMB->RequestFileName, search_name);
}
if (ses->server->sign)
PATH_MAX, cifs_sb->local_nls, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(file_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, file_name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, file_name);
}
params = 6 + name_len;
data_count = sizeof(struct file_end_of_file_info);
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, fileName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, fileName);
}
params = 6 + name_len;
PATH_MAX, nls_codepage);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->fileName, fileName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->fileName, fileName);
}
pSMB->attr = cpu_to_le16(dos_attrs);
pSMB->BufferFormat = 0x04;
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(file_name, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, file_name, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, file_name);
}
params = 6 + name_len;
PATH_MAX, nls_codepage, remap);
list_len++; /* trailing null */
list_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- list_len = strnlen(searchName, PATH_MAX);
- list_len++; /* trailing null */
- strncpy(pSMB->FileName, searchName, list_len);
+ } else {
+ list_len = copy_path_name(pSMB->FileName, searchName);
}
params = 2 /* level */ + 4 /* reserved */ + list_len /* includes NUL */;
PATH_MAX, nls_codepage, remap);
name_len++; /* trailing null */
name_len *= 2;
- } else { /* BB improve the check for buffer overruns BB */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- strncpy(pSMB->FileName, fileName, name_len);
+ } else {
+ name_len = copy_path_name(pSMB->FileName, fileName);
}
params = 6 + name_len;
mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
set_freezable();
+ allow_kernel_signal(SIGKILL);
while (server->tcpStatus != CifsExiting) {
if (try_to_freeze())
continue;
cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses)
{
int rc = 0;
+ int is_domain = 0;
const char *delim, *payload;
char *desc;
ssize_t len;
rc = PTR_ERR(key);
goto out_err;
}
+ is_domain = 1;
}
down_read(&key->sem);
goto out_key_put;
}
+ /*
+ * If we have a domain key then we must set the domainName in the
+ * for the request.
+ */
+ if (is_domain && ses->domainName) {
+ vol->domainname = kstrndup(ses->domainName,
+ strlen(ses->domainName),
+ GFP_KERNEL);
+ if (!vol->domainname) {
+ cifs_dbg(FYI, "Unable to allocate %zd bytes for "
+ "domain\n", len);
+ rc = -ENOMEM;
+ kfree(vol->username);
+ vol->username = NULL;
+ kzfree(vol->password);
+ vol->password = NULL;
+ goto out_key_put;
+ }
+ }
+
out_key_put:
up_read(&key->sem);
key_put(key);
strlen(vol->prepath) + 1 : 0;
unsigned int unc_len = strnlen(vol->UNC, MAX_TREE_SIZE + 1);
+ if (unc_len > MAX_TREE_SIZE)
+ return ERR_PTR(-EINVAL);
+
full_path = kmalloc(unc_len + pplen + 1, GFP_KERNEL);
if (full_path == NULL)
return ERR_PTR(-ENOMEM);
- strncpy(full_path, vol->UNC, unc_len);
+ memcpy(full_path, vol->UNC, unc_len);
pos = full_path + unc_len;
if (pplen) {
*pos = CIFS_DIR_SEP(cifs_sb);
- strncpy(pos + 1, vol->prepath, pplen);
+ memcpy(pos + 1, vol->prepath, pplen);
pos += pplen;
}
return full_path;
if (dfsplen)
- strncpy(full_path, tcon->treeName, dfsplen);
+ memcpy(full_path, tcon->treeName, dfsplen);
full_path[dfsplen] = CIFS_DIR_SEP(cifs_sb);
- strncpy(full_path + dfsplen + 1, vol->prepath, pplen);
+ memcpy(full_path + dfsplen + 1, vol->prepath, pplen);
convert_delimiter(full_path, CIFS_DIR_SEP(cifs_sb));
- full_path[dfsplen + pplen] = 0; /* add trailing null */
return full_path;
}
*h = unc;
*len = end - unc;
}
+
+/**
+ * copy_path_name - copy src path to dst, possibly truncating
+ *
+ * returns number of bytes written (including trailing nul)
+ */
+int copy_path_name(char *dst, const char *src)
+{
+ int name_len;
+
+ /*
+ * PATH_MAX includes nul, so if strlen(src) >= PATH_MAX it
+ * will truncate and strlen(dst) will be PATH_MAX-1
+ */
+ name_len = strscpy(dst, src, PATH_MAX);
+ if (WARN_ON_ONCE(name_len < 0))
+ name_len = PATH_MAX-1;
+
+ /* we count the trailing nul */
+ name_len++;
+ return name_len;
+}
const struct nls_table *nls_cp)
{
char *bcc_ptr = *pbcc_area;
+ int len;
/* copy user */
/* BB what about null user mounts - check that we do this BB */
/* copy user */
if (ses->user_name != NULL) {
- strncpy(bcc_ptr, ses->user_name, CIFS_MAX_USERNAME_LEN);
- bcc_ptr += strnlen(ses->user_name, CIFS_MAX_USERNAME_LEN);
+ len = strscpy(bcc_ptr, ses->user_name, CIFS_MAX_USERNAME_LEN);
+ if (WARN_ON_ONCE(len < 0))
+ len = CIFS_MAX_USERNAME_LEN - 1;
+ bcc_ptr += len;
}
/* else null user mount */
*bcc_ptr = 0;
/* copy domain */
if (ses->domainName != NULL) {
- strncpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
- bcc_ptr += strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ len = strscpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ if (WARN_ON_ONCE(len < 0))
+ len = CIFS_MAX_DOMAINNAME_LEN - 1;
+ bcc_ptr += len;
} /* else we will send a null domain name
so the server will default to its own domain */
*bcc_ptr = 0;
kfree(ses->serverOS);
- ses->serverOS = kzalloc(len + 1, GFP_KERNEL);
+ ses->serverOS = kmalloc(len + 1, GFP_KERNEL);
if (ses->serverOS) {
- strncpy(ses->serverOS, bcc_ptr, len);
+ memcpy(ses->serverOS, bcc_ptr, len);
+ ses->serverOS[len] = 0;
if (strncmp(ses->serverOS, "OS/2", 4) == 0)
cifs_dbg(FYI, "OS/2 server\n");
}
kfree(ses->serverNOS);
- ses->serverNOS = kzalloc(len + 1, GFP_KERNEL);
- if (ses->serverNOS)
- strncpy(ses->serverNOS, bcc_ptr, len);
+ ses->serverNOS = kmalloc(len + 1, GFP_KERNEL);
+ if (ses->serverNOS) {
+ memcpy(ses->serverNOS, bcc_ptr, len);
+ ses->serverNOS[len] = 0;
+ }
bcc_ptr += len + 1;
bleft -= len + 1;
static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf,
unsigned int buflen)
{
- sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
+ void *addr;
+ /*
+ * VMAP_STACK (at least) puts stack into the vmalloc address space
+ */
+ if (is_vmalloc_addr(buf))
+ addr = vmalloc_to_page(buf);
+ else
+ addr = virt_to_page(buf);
+ sg_set_page(sg, addr, buflen, offset_in_page(buf));
}
/* Assumes the first rqst has a transform header as the first iov.
{
int ret, length;
char *buf = server->smallbuf;
- char *tmpbuf;
struct smb2_sync_hdr *shdr;
unsigned int pdu_length = server->pdu_size;
unsigned int buf_size;
return length;
next_is_large = server->large_buf;
- one_more:
+one_more:
shdr = (struct smb2_sync_hdr *)buf;
if (shdr->NextCommand) {
- if (next_is_large) {
- tmpbuf = server->bigbuf;
+ if (next_is_large)
next_buffer = (char *)cifs_buf_get();
- } else {
- tmpbuf = server->smallbuf;
+ else
next_buffer = (char *)cifs_small_buf_get();
- }
memcpy(next_buffer,
- tmpbuf + le32_to_cpu(shdr->NextCommand),
+ buf + le32_to_cpu(shdr->NextCommand),
pdu_length - le32_to_cpu(shdr->NextCommand));
}
pdu_length -= le32_to_cpu(shdr->NextCommand);
server->large_buf = next_is_large;
if (next_is_large)
- server->bigbuf = next_buffer;
+ server->bigbuf = buf = next_buffer;
else
- server->smallbuf = next_buffer;
-
- buf += le32_to_cpu(shdr->NextCommand);
+ server->smallbuf = buf = next_buffer;
goto one_more;
+ } else if (ret != 0) {
+ /*
+ * ret != 0 here means that we didn't get to handle_mid() thus
+ * server->smallbuf and server->bigbuf are still valid. We need
+ * to free next_buffer because it is not going to be used
+ * anywhere.
+ */
+ if (next_is_large)
+ free_rsp_buf(CIFS_LARGE_BUFFER, next_buffer);
+ else
+ free_rsp_buf(CIFS_SMALL_BUFFER, next_buffer);
}
return ret;
if (tcon == NULL)
return 0;
- if (smb2_command == SMB2_TREE_CONNECT)
+ if (smb2_command == SMB2_TREE_CONNECT || smb2_command == SMB2_IOCTL)
return 0;
if (tcon->tidStatus == CifsExiting) {
else
req->SecurityMode = 0;
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ req->Capabilities = cpu_to_le32(SMB2_GLOBAL_CAP_DFS);
+#else
req->Capabilities = 0;
+#endif /* DFS_UPCALL */
+
req->Channel = 0; /* MBZ */
sess_data->iov[0].iov_base = (char *)req;
COMPATIBLE_IOCTL(PPPIOCATTCHAN)
COMPATIBLE_IOCTL(PPPIOCGCHAN)
COMPATIBLE_IOCTL(PPPIOCGL2TPSTATS)
-/* PPPOX */
-COMPATIBLE_IOCTL(PPPOEIOCSFWD)
-COMPATIBLE_IOCTL(PPPOEIOCDFWD)
/* Big A */
/* sparc only */
/* Big Q for sound/OSS */
#include <linux/list.h>
#include <linux/spinlock.h>
+struct configfs_fragment {
+ atomic_t frag_count;
+ struct rw_semaphore frag_sem;
+ bool frag_dead;
+};
+
+void put_fragment(struct configfs_fragment *);
+struct configfs_fragment *get_fragment(struct configfs_fragment *);
+
struct configfs_dirent {
atomic_t s_count;
int s_dependent_count;
#ifdef CONFIG_LOCKDEP
int s_depth;
#endif
+ struct configfs_fragment *s_frag;
};
#define CONFIGFS_ROOT 0x0001
extern int configfs_create_file(struct config_item *, const struct configfs_attribute *);
extern int configfs_create_bin_file(struct config_item *,
const struct configfs_bin_attribute *);
-extern int configfs_make_dirent(struct configfs_dirent *,
- struct dentry *, void *, umode_t, int);
+extern int configfs_make_dirent(struct configfs_dirent *, struct dentry *,
+ void *, umode_t, int, struct configfs_fragment *);
extern int configfs_dirent_is_ready(struct configfs_dirent *);
extern void configfs_hash_and_remove(struct dentry * dir, const char * name);
{
if (!(sd->s_type & CONFIGFS_ROOT)) {
kfree(sd->s_iattr);
+ put_fragment(sd->s_frag);
kmem_cache_free(configfs_dir_cachep, sd);
}
}
#endif /* CONFIG_LOCKDEP */
+static struct configfs_fragment *new_fragment(void)
+{
+ struct configfs_fragment *p;
+
+ p = kmalloc(sizeof(struct configfs_fragment), GFP_KERNEL);
+ if (p) {
+ atomic_set(&p->frag_count, 1);
+ init_rwsem(&p->frag_sem);
+ p->frag_dead = false;
+ }
+ return p;
+}
+
+void put_fragment(struct configfs_fragment *frag)
+{
+ if (frag && atomic_dec_and_test(&frag->frag_count))
+ kfree(frag);
+}
+
+struct configfs_fragment *get_fragment(struct configfs_fragment *frag)
+{
+ if (likely(frag))
+ atomic_inc(&frag->frag_count);
+ return frag;
+}
+
/*
* Allocates a new configfs_dirent and links it to the parent configfs_dirent
*/
static struct configfs_dirent *configfs_new_dirent(struct configfs_dirent *parent_sd,
- void *element, int type)
+ void *element, int type,
+ struct configfs_fragment *frag)
{
struct configfs_dirent * sd;
kmem_cache_free(configfs_dir_cachep, sd);
return ERR_PTR(-ENOENT);
}
+ sd->s_frag = get_fragment(frag);
list_add(&sd->s_sibling, &parent_sd->s_children);
spin_unlock(&configfs_dirent_lock);
int configfs_make_dirent(struct configfs_dirent * parent_sd,
struct dentry * dentry, void * element,
- umode_t mode, int type)
+ umode_t mode, int type, struct configfs_fragment *frag)
{
struct configfs_dirent * sd;
- sd = configfs_new_dirent(parent_sd, element, type);
+ sd = configfs_new_dirent(parent_sd, element, type, frag);
if (IS_ERR(sd))
return PTR_ERR(sd);
* until it is validated by configfs_dir_set_ready()
*/
-static int configfs_create_dir(struct config_item *item, struct dentry *dentry)
+static int configfs_create_dir(struct config_item *item, struct dentry *dentry,
+ struct configfs_fragment *frag)
{
int error;
umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
return error;
error = configfs_make_dirent(p->d_fsdata, dentry, item, mode,
- CONFIGFS_DIR | CONFIGFS_USET_CREATING);
+ CONFIGFS_DIR | CONFIGFS_USET_CREATING,
+ frag);
if (unlikely(error))
return error;
{
int err = 0;
umode_t mode = S_IFLNK | S_IRWXUGO;
+ struct configfs_dirent *p = parent->d_fsdata;
- err = configfs_make_dirent(parent->d_fsdata, dentry, sl, mode,
- CONFIGFS_ITEM_LINK);
+ err = configfs_make_dirent(p, dentry, sl, mode,
+ CONFIGFS_ITEM_LINK, p->s_frag);
if (!err) {
err = configfs_create(dentry, mode, init_symlink);
if (err) {
static int configfs_attach_group(struct config_item *parent_item,
struct config_item *item,
- struct dentry *dentry);
+ struct dentry *dentry,
+ struct configfs_fragment *frag);
static void configfs_detach_group(struct config_item *item);
static void detach_groups(struct config_group *group)
* try using vfs_mkdir. Just a thought.
*/
static int create_default_group(struct config_group *parent_group,
- struct config_group *group)
+ struct config_group *group,
+ struct configfs_fragment *frag)
{
int ret;
struct configfs_dirent *sd;
d_add(child, NULL);
ret = configfs_attach_group(&parent_group->cg_item,
- &group->cg_item, child);
+ &group->cg_item, child, frag);
if (!ret) {
sd = child->d_fsdata;
sd->s_type |= CONFIGFS_USET_DEFAULT;
return ret;
}
-static int populate_groups(struct config_group *group)
+static int populate_groups(struct config_group *group,
+ struct configfs_fragment *frag)
{
struct config_group *new_group;
int ret = 0;
list_for_each_entry(new_group, &group->default_groups, group_entry) {
- ret = create_default_group(group, new_group);
+ ret = create_default_group(group, new_group, frag);
if (ret) {
detach_groups(group);
break;
*/
static int configfs_attach_item(struct config_item *parent_item,
struct config_item *item,
- struct dentry *dentry)
+ struct dentry *dentry,
+ struct configfs_fragment *frag)
{
int ret;
- ret = configfs_create_dir(item, dentry);
+ ret = configfs_create_dir(item, dentry, frag);
if (!ret) {
ret = populate_attrs(item);
if (ret) {
static int configfs_attach_group(struct config_item *parent_item,
struct config_item *item,
- struct dentry *dentry)
+ struct dentry *dentry,
+ struct configfs_fragment *frag)
{
int ret;
struct configfs_dirent *sd;
- ret = configfs_attach_item(parent_item, item, dentry);
+ ret = configfs_attach_item(parent_item, item, dentry, frag);
if (!ret) {
sd = dentry->d_fsdata;
sd->s_type |= CONFIGFS_USET_DIR;
*/
inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
configfs_adjust_dir_dirent_depth_before_populate(sd);
- ret = populate_groups(to_config_group(item));
+ ret = populate_groups(to_config_group(item), frag);
if (ret) {
configfs_detach_item(item);
d_inode(dentry)->i_flags |= S_DEAD;
struct configfs_dirent *sd;
const struct config_item_type *type;
struct module *subsys_owner = NULL, *new_item_owner = NULL;
+ struct configfs_fragment *frag;
char *name;
sd = dentry->d_parent->d_fsdata;
goto out;
}
+ frag = new_fragment();
+ if (!frag) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
/* Get a working ref for the duration of this function */
parent_item = configfs_get_config_item(dentry->d_parent);
type = parent_item->ci_type;
spin_unlock(&configfs_dirent_lock);
if (group)
- ret = configfs_attach_group(parent_item, item, dentry);
+ ret = configfs_attach_group(parent_item, item, dentry, frag);
else
- ret = configfs_attach_item(parent_item, item, dentry);
+ ret = configfs_attach_item(parent_item, item, dentry, frag);
spin_lock(&configfs_dirent_lock);
sd->s_type &= ~CONFIGFS_USET_IN_MKDIR;
* reference.
*/
config_item_put(parent_item);
+ put_fragment(frag);
out:
return ret;
struct config_item *item;
struct configfs_subsystem *subsys;
struct configfs_dirent *sd;
+ struct configfs_fragment *frag;
struct module *subsys_owner = NULL, *dead_item_owner = NULL;
int ret;
}
} while (ret == -EAGAIN);
+ frag = sd->s_frag;
+ if (down_write_killable(&frag->frag_sem)) {
+ spin_lock(&configfs_dirent_lock);
+ configfs_detach_rollback(dentry);
+ spin_unlock(&configfs_dirent_lock);
+ return -EINTR;
+ }
+ frag->frag_dead = true;
+ up_write(&frag->frag_sem);
+
/* Get a working ref for the duration of this function */
item = configfs_get_config_item(dentry);
*/
err = -ENOENT;
if (configfs_dirent_is_ready(parent_sd)) {
- file->private_data = configfs_new_dirent(parent_sd, NULL, 0);
+ file->private_data = configfs_new_dirent(parent_sd, NULL, 0, NULL);
if (IS_ERR(file->private_data))
err = PTR_ERR(file->private_data);
else
{
struct configfs_subsystem *subsys = parent_group->cg_subsys;
struct dentry *parent;
+ struct configfs_fragment *frag;
int ret;
+ frag = new_fragment();
+ if (!frag)
+ return -ENOMEM;
+
mutex_lock(&subsys->su_mutex);
link_group(parent_group, group);
mutex_unlock(&subsys->su_mutex);
parent = parent_group->cg_item.ci_dentry;
inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
- ret = create_default_group(parent_group, group);
+ ret = create_default_group(parent_group, group, frag);
if (ret)
goto err_out;
configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
spin_unlock(&configfs_dirent_lock);
inode_unlock(d_inode(parent));
+ put_fragment(frag);
return 0;
err_out:
inode_unlock(d_inode(parent));
mutex_lock(&subsys->su_mutex);
unlink_group(group);
mutex_unlock(&subsys->su_mutex);
+ put_fragment(frag);
return ret;
}
EXPORT_SYMBOL(configfs_register_group);
struct configfs_subsystem *subsys = group->cg_subsys;
struct dentry *dentry = group->cg_item.ci_dentry;
struct dentry *parent = group->cg_item.ci_parent->ci_dentry;
+ struct configfs_dirent *sd = dentry->d_fsdata;
+ struct configfs_fragment *frag = sd->s_frag;
- mutex_lock(&subsys->su_mutex);
- if (!group->cg_item.ci_parent->ci_group) {
- /*
- * The parent has already been unlinked and detached
- * due to a rmdir.
- */
- goto unlink_group;
- }
- mutex_unlock(&subsys->su_mutex);
+ down_write(&frag->frag_sem);
+ frag->frag_dead = true;
+ up_write(&frag->frag_sem);
inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
spin_lock(&configfs_dirent_lock);
dput(dentry);
mutex_lock(&subsys->su_mutex);
-unlink_group:
unlink_group(group);
mutex_unlock(&subsys->su_mutex);
}
struct dentry *dentry;
struct dentry *root;
struct configfs_dirent *sd;
+ struct configfs_fragment *frag;
+
+ frag = new_fragment();
+ if (!frag)
+ return -ENOMEM;
root = configfs_pin_fs();
- if (IS_ERR(root))
+ if (IS_ERR(root)) {
+ put_fragment(frag);
return PTR_ERR(root);
+ }
if (!group->cg_item.ci_name)
group->cg_item.ci_name = group->cg_item.ci_namebuf;
d_add(dentry, NULL);
err = configfs_attach_group(sd->s_element, &group->cg_item,
- dentry);
+ dentry, frag);
if (err) {
BUG_ON(d_inode(dentry));
d_drop(dentry);
unlink_group(group);
configfs_release_fs();
}
+ put_fragment(frag);
return err;
}
struct config_group *group = &subsys->su_group;
struct dentry *dentry = group->cg_item.ci_dentry;
struct dentry *root = dentry->d_sb->s_root;
+ struct configfs_dirent *sd = dentry->d_fsdata;
+ struct configfs_fragment *frag = sd->s_frag;
if (dentry->d_parent != root) {
pr_err("Tried to unregister non-subsystem!\n");
return;
}
+ down_write(&frag->frag_sem);
+ frag->frag_dead = true;
+ up_write(&frag->frag_sem);
+
inode_lock_nested(d_inode(root),
I_MUTEX_PARENT);
inode_lock_nested(d_inode(dentry), I_MUTEX_CHILD);
bool write_in_progress;
char *bin_buffer;
int bin_buffer_size;
+ int cb_max_size;
+ struct config_item *item;
+ struct module *owner;
+ union {
+ struct configfs_attribute *attr;
+ struct configfs_bin_attribute *bin_attr;
+ };
};
+static inline struct configfs_fragment *to_frag(struct file *file)
+{
+ struct configfs_dirent *sd = file->f_path.dentry->d_fsdata;
-/**
- * fill_read_buffer - allocate and fill buffer from item.
- * @dentry: dentry pointer.
- * @buffer: data buffer for file.
- *
- * Allocate @buffer->page, if it hasn't been already, then call the
- * config_item's show() method to fill the buffer with this attribute's
- * data.
- * This is called only once, on the file's first read.
- */
-static int fill_read_buffer(struct dentry * dentry, struct configfs_buffer * buffer)
+ return sd->s_frag;
+}
+
+static int fill_read_buffer(struct file *file, struct configfs_buffer *buffer)
{
- struct configfs_attribute * attr = to_attr(dentry);
- struct config_item * item = to_item(dentry->d_parent);
- int ret = 0;
- ssize_t count;
+ struct configfs_fragment *frag = to_frag(file);
+ ssize_t count = -ENOENT;
if (!buffer->page)
buffer->page = (char *) get_zeroed_page(GFP_KERNEL);
if (!buffer->page)
return -ENOMEM;
- count = attr->show(item, buffer->page);
-
- BUG_ON(count > (ssize_t)SIMPLE_ATTR_SIZE);
- if (count >= 0) {
- buffer->needs_read_fill = 0;
- buffer->count = count;
- } else
- ret = count;
- return ret;
+ down_read(&frag->frag_sem);
+ if (!frag->frag_dead)
+ count = buffer->attr->show(buffer->item, buffer->page);
+ up_read(&frag->frag_sem);
+
+ if (count < 0)
+ return count;
+ if (WARN_ON_ONCE(count > (ssize_t)SIMPLE_ATTR_SIZE))
+ return -EIO;
+ buffer->needs_read_fill = 0;
+ buffer->count = count;
+ return 0;
}
/**
static ssize_t
configfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
- struct configfs_buffer * buffer = file->private_data;
+ struct configfs_buffer *buffer = file->private_data;
ssize_t retval = 0;
mutex_lock(&buffer->mutex);
if (buffer->needs_read_fill) {
- if ((retval = fill_read_buffer(file->f_path.dentry,buffer)))
+ retval = fill_read_buffer(file, buffer);
+ if (retval)
goto out;
}
pr_debug("%s: count = %zd, ppos = %lld, buf = %s\n",
configfs_read_bin_file(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
+ struct configfs_fragment *frag = to_frag(file);
struct configfs_buffer *buffer = file->private_data;
- struct dentry *dentry = file->f_path.dentry;
- struct config_item *item = to_item(dentry->d_parent);
- struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
ssize_t retval = 0;
ssize_t len = min_t(size_t, count, PAGE_SIZE);
if (buffer->needs_read_fill) {
/* perform first read with buf == NULL to get extent */
- len = bin_attr->read(item, NULL, 0);
+ down_read(&frag->frag_sem);
+ if (!frag->frag_dead)
+ len = buffer->bin_attr->read(buffer->item, NULL, 0);
+ else
+ len = -ENOENT;
+ up_read(&frag->frag_sem);
if (len <= 0) {
retval = len;
goto out;
}
/* do not exceed the maximum value */
- if (bin_attr->cb_max_size && len > bin_attr->cb_max_size) {
+ if (buffer->cb_max_size && len > buffer->cb_max_size) {
retval = -EFBIG;
goto out;
}
buffer->bin_buffer_size = len;
/* perform second read to fill buffer */
- len = bin_attr->read(item, buffer->bin_buffer, len);
+ down_read(&frag->frag_sem);
+ if (!frag->frag_dead)
+ len = buffer->bin_attr->read(buffer->item,
+ buffer->bin_buffer, len);
+ else
+ len = -ENOENT;
+ up_read(&frag->frag_sem);
if (len < 0) {
retval = len;
vfree(buffer->bin_buffer);
return error ? -EFAULT : count;
}
-
-/**
- * flush_write_buffer - push buffer to config_item.
- * @dentry: dentry to the attribute
- * @buffer: data buffer for file.
- * @count: number of bytes
- *
- * Get the correct pointers for the config_item and the attribute we're
- * dealing with, then call the store() method for the attribute,
- * passing the buffer that we acquired in fill_write_buffer().
- */
-
static int
-flush_write_buffer(struct dentry * dentry, struct configfs_buffer * buffer, size_t count)
+flush_write_buffer(struct file *file, struct configfs_buffer *buffer, size_t count)
{
- struct configfs_attribute * attr = to_attr(dentry);
- struct config_item * item = to_item(dentry->d_parent);
-
- return attr->store(item, buffer->page, count);
+ struct configfs_fragment *frag = to_frag(file);
+ int res = -ENOENT;
+
+ down_read(&frag->frag_sem);
+ if (!frag->frag_dead)
+ res = buffer->attr->store(buffer->item, buffer->page, count);
+ up_read(&frag->frag_sem);
+ return res;
}
static ssize_t
configfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
- struct configfs_buffer * buffer = file->private_data;
+ struct configfs_buffer *buffer = file->private_data;
ssize_t len;
mutex_lock(&buffer->mutex);
len = fill_write_buffer(buffer, buf, count);
if (len > 0)
- len = flush_write_buffer(file->f_path.dentry, buffer, len);
+ len = flush_write_buffer(file, buffer, len);
if (len > 0)
*ppos += len;
mutex_unlock(&buffer->mutex);
size_t count, loff_t *ppos)
{
struct configfs_buffer *buffer = file->private_data;
- struct dentry *dentry = file->f_path.dentry;
- struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
void *tbuf = NULL;
ssize_t len;
/* buffer grows? */
if (*ppos + count > buffer->bin_buffer_size) {
- if (bin_attr->cb_max_size &&
- *ppos + count > bin_attr->cb_max_size) {
+ if (buffer->cb_max_size &&
+ *ppos + count > buffer->cb_max_size) {
len = -EFBIG;
goto out;
}
return len;
}
-static int check_perm(struct inode * inode, struct file * file, int type)
+static int __configfs_open_file(struct inode *inode, struct file *file, int type)
{
- struct config_item *item = configfs_get_config_item(file->f_path.dentry->d_parent);
- struct configfs_attribute * attr = to_attr(file->f_path.dentry);
- struct configfs_bin_attribute *bin_attr = NULL;
- struct configfs_buffer * buffer;
- struct configfs_item_operations * ops = NULL;
- int error = 0;
+ struct dentry *dentry = file->f_path.dentry;
+ struct configfs_fragment *frag = to_frag(file);
+ struct configfs_attribute *attr;
+ struct configfs_buffer *buffer;
+ int error;
- if (!item || !attr)
- goto Einval;
+ error = -ENOMEM;
+ buffer = kzalloc(sizeof(struct configfs_buffer), GFP_KERNEL);
+ if (!buffer)
+ goto out;
- if (type & CONFIGFS_ITEM_BIN_ATTR)
- bin_attr = to_bin_attr(file->f_path.dentry);
+ error = -ENOENT;
+ down_read(&frag->frag_sem);
+ if (unlikely(frag->frag_dead))
+ goto out_free_buffer;
- /* Grab the module reference for this attribute if we have one */
- if (!try_module_get(attr->ca_owner)) {
- error = -ENODEV;
- goto Done;
+ error = -EINVAL;
+ buffer->item = to_item(dentry->d_parent);
+ if (!buffer->item)
+ goto out_free_buffer;
+
+ attr = to_attr(dentry);
+ if (!attr)
+ goto out_put_item;
+
+ if (type & CONFIGFS_ITEM_BIN_ATTR) {
+ buffer->bin_attr = to_bin_attr(dentry);
+ buffer->cb_max_size = buffer->bin_attr->cb_max_size;
+ } else {
+ buffer->attr = attr;
}
- if (item->ci_type)
- ops = item->ci_type->ct_item_ops;
- else
- goto Eaccess;
+ buffer->owner = attr->ca_owner;
+ /* Grab the module reference for this attribute if we have one */
+ error = -ENODEV;
+ if (!try_module_get(buffer->owner))
+ goto out_put_item;
+
+ error = -EACCES;
+ if (!buffer->item->ci_type)
+ goto out_put_module;
+
+ buffer->ops = buffer->item->ci_type->ct_item_ops;
/* File needs write support.
* The inode's perms must say it's ok,
*/
if (file->f_mode & FMODE_WRITE) {
if (!(inode->i_mode & S_IWUGO))
- goto Eaccess;
-
+ goto out_put_module;
if ((type & CONFIGFS_ITEM_ATTR) && !attr->store)
- goto Eaccess;
-
- if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->write)
- goto Eaccess;
+ goto out_put_module;
+ if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->write)
+ goto out_put_module;
}
/* File needs read support.
*/
if (file->f_mode & FMODE_READ) {
if (!(inode->i_mode & S_IRUGO))
- goto Eaccess;
-
+ goto out_put_module;
if ((type & CONFIGFS_ITEM_ATTR) && !attr->show)
- goto Eaccess;
-
- if ((type & CONFIGFS_ITEM_BIN_ATTR) && !bin_attr->read)
- goto Eaccess;
+ goto out_put_module;
+ if ((type & CONFIGFS_ITEM_BIN_ATTR) && !buffer->bin_attr->read)
+ goto out_put_module;
}
- /* No error? Great, allocate a buffer for the file, and store it
- * it in file->private_data for easy access.
- */
- buffer = kzalloc(sizeof(struct configfs_buffer),GFP_KERNEL);
- if (!buffer) {
- error = -ENOMEM;
- goto Enomem;
- }
mutex_init(&buffer->mutex);
buffer->needs_read_fill = 1;
buffer->read_in_progress = false;
buffer->write_in_progress = false;
- buffer->ops = ops;
file->private_data = buffer;
- goto Done;
+ up_read(&frag->frag_sem);
+ return 0;
- Einval:
- error = -EINVAL;
- goto Done;
- Eaccess:
- error = -EACCES;
- Enomem:
- module_put(attr->ca_owner);
- Done:
- if (error && item)
- config_item_put(item);
+out_put_module:
+ module_put(buffer->owner);
+out_put_item:
+ config_item_put(buffer->item);
+out_free_buffer:
+ up_read(&frag->frag_sem);
+ kfree(buffer);
+out:
return error;
}
static int configfs_release(struct inode *inode, struct file *filp)
{
- struct config_item * item = to_item(filp->f_path.dentry->d_parent);
- struct configfs_attribute * attr = to_attr(filp->f_path.dentry);
- struct module * owner = attr->ca_owner;
- struct configfs_buffer * buffer = filp->private_data;
-
- if (item)
- config_item_put(item);
- /* After this point, attr should not be accessed. */
- module_put(owner);
-
- if (buffer) {
- if (buffer->page)
- free_page((unsigned long)buffer->page);
- mutex_destroy(&buffer->mutex);
- kfree(buffer);
- }
+ struct configfs_buffer *buffer = filp->private_data;
+
+ module_put(buffer->owner);
+ if (buffer->page)
+ free_page((unsigned long)buffer->page);
+ mutex_destroy(&buffer->mutex);
+ kfree(buffer);
return 0;
}
static int configfs_open_file(struct inode *inode, struct file *filp)
{
- return check_perm(inode, filp, CONFIGFS_ITEM_ATTR);
+ return __configfs_open_file(inode, filp, CONFIGFS_ITEM_ATTR);
}
static int configfs_open_bin_file(struct inode *inode, struct file *filp)
{
- return check_perm(inode, filp, CONFIGFS_ITEM_BIN_ATTR);
+ return __configfs_open_file(inode, filp, CONFIGFS_ITEM_BIN_ATTR);
}
-static int configfs_release_bin_file(struct inode *inode, struct file *filp)
+static int configfs_release_bin_file(struct inode *inode, struct file *file)
{
- struct configfs_buffer *buffer = filp->private_data;
- struct dentry *dentry = filp->f_path.dentry;
- struct config_item *item = to_item(dentry->d_parent);
- struct configfs_bin_attribute *bin_attr = to_bin_attr(dentry);
- ssize_t len = 0;
- int ret;
+ struct configfs_buffer *buffer = file->private_data;
buffer->read_in_progress = false;
if (buffer->write_in_progress) {
+ struct configfs_fragment *frag = to_frag(file);
buffer->write_in_progress = false;
- len = bin_attr->write(item, buffer->bin_buffer,
- buffer->bin_buffer_size);
-
+ down_read(&frag->frag_sem);
+ if (!frag->frag_dead) {
+ /* result of ->release() is ignored */
+ buffer->bin_attr->write(buffer->item,
+ buffer->bin_buffer,
+ buffer->bin_buffer_size);
+ }
+ up_read(&frag->frag_sem);
/* vfree on NULL is safe */
vfree(buffer->bin_buffer);
buffer->bin_buffer = NULL;
buffer->needs_read_fill = 1;
}
- ret = configfs_release(inode, filp);
- if (len < 0)
- return len;
- return ret;
+ configfs_release(inode, file);
+ return 0;
}
inode_lock_nested(d_inode(dir), I_MUTEX_NORMAL);
error = configfs_make_dirent(parent_sd, NULL, (void *) attr, mode,
- CONFIGFS_ITEM_ATTR);
+ CONFIGFS_ITEM_ATTR, parent_sd->s_frag);
inode_unlock(d_inode(dir));
return error;
inode_lock_nested(dir->d_inode, I_MUTEX_NORMAL);
error = configfs_make_dirent(parent_sd, NULL, (void *) bin_attr, mode,
- CONFIGFS_ITEM_BIN_ATTR);
+ CONFIGFS_ITEM_BIN_ATTR, parent_sd->s_frag);
inode_unlock(dir->d_inode);
return error;
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
+#include <linux/ctype.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/pagemap.h>
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
*/
-static int format_corename(struct core_name *cn, struct coredump_params *cprm)
+static int format_corename(struct core_name *cn, struct coredump_params *cprm,
+ size_t **argv, int *argc)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
+ bool was_space = false;
int pid_in_pattern = 0;
int err = 0;
return -ENOMEM;
cn->corename[0] = '\0';
- if (ispipe)
+ if (ispipe) {
+ int argvs = sizeof(core_pattern) / 2;
+ (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL);
+ if (!(*argv))
+ return -ENOMEM;
+ (*argv)[(*argc)++] = 0;
++pat_ptr;
+ }
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
+ /*
+ * Split on spaces before doing template expansion so that
+ * %e and %E don't get split if they have spaces in them
+ */
+ if (ispipe) {
+ if (isspace(*pat_ptr)) {
+ was_space = true;
+ pat_ptr++;
+ continue;
+ } else if (was_space) {
+ was_space = false;
+ err = cn_printf(cn, "%c", '\0');
+ if (err)
+ return err;
+ (*argv)[(*argc)++] = cn->used;
+ }
+ }
if (*pat_ptr != '%') {
err = cn_printf(cn, "%c", *pat_ptr++);
} else {
struct cred *cred;
int retval = 0;
int ispipe;
+ size_t *argv = NULL;
+ int argc = 0;
struct files_struct *displaced;
/* require nonrelative corefile path and be extra careful */
bool need_suid_safe = false;
old_cred = override_creds(cred);
- ispipe = format_corename(&cn, &cprm);
+ ispipe = format_corename(&cn, &cprm, &argv, &argc);
if (ispipe) {
+ int argi;
int dump_count;
char **helper_argv;
struct subprocess_info *sub_info;
goto fail_dropcount;
}
- helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL);
+ helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv),
+ GFP_KERNEL);
if (!helper_argv) {
printk(KERN_WARNING "%s failed to allocate memory\n",
__func__);
goto fail_dropcount;
}
+ for (argi = 0; argi < argc; argi++)
+ helper_argv[argi] = cn.corename + argv[argi];
+ helper_argv[argi] = NULL;
retval = -ENOMEM;
sub_info = call_usermodehelper_setup(helper_argv[0],
retval = call_usermodehelper_exec(sub_info,
UMH_WAIT_EXEC);
- argv_free(helper_argv);
+ kfree(helper_argv);
if (retval) {
printk(KERN_INFO "Core dump to |%s pipe failed\n",
cn.corename);
if (ispipe)
atomic_dec(&core_dump_count);
fail_unlock:
+ kfree(argv);
kfree(cn.corename);
coredump_finish(mm, core_dumped);
revert_creds(old_cred);
static void put_unlocked_entry(struct xa_state *xas, void *entry)
{
/* If we were the only waiter woken, wake the next one */
- if (entry && dax_is_conflict(entry))
+ if (entry && !dax_is_conflict(entry))
dax_wake_entry(xas, entry, false);
}
* guaranteed to either see new references or prevent new
* references from being established.
*/
- unmap_mapping_range(mapping, 0, 0, 1);
+ unmap_mapping_range(mapping, 0, 0, 0);
xas_lock_irq(&xas);
xas_for_each(&xas, entry, ULONG_MAX) {
membarrier_execve(current);
rseq_execve(current);
acct_update_integrals(current);
- task_numa_free(current);
+ task_numa_free(current, false);
free_bprm(bprm);
kfree(pathbuf);
if (filename)
static int f2fs_setflags_common(struct inode *inode, u32 iflags, u32 mask)
{
struct f2fs_inode_info *fi = F2FS_I(inode);
- u32 oldflags;
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
return -EPERM;
- oldflags = fi->i_flags;
-
- if ((iflags ^ oldflags) & (F2FS_APPEND_FL | F2FS_IMMUTABLE_FL))
- if (!capable(CAP_LINUX_IMMUTABLE))
- return -EPERM;
-
- fi->i_flags = iflags | (oldflags & ~mask);
+ fi->i_flags = iflags | (fi->i_flags & ~mask);
if (fi->i_flags & F2FS_PROJINHERIT_FL)
set_inode_flag(inode, FI_PROJ_INHERIT);
static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
- u32 fsflags;
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ u32 fsflags, old_fsflags;
u32 iflags;
int ret;
inode_lock(inode);
+ old_fsflags = f2fs_iflags_to_fsflags(fi->i_flags);
+ ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags);
+ if (ret)
+ goto out;
+
ret = f2fs_setflags_common(inode, iflags,
f2fs_fsflags_to_iflags(F2FS_SETTABLE_FS_FL));
+out:
inode_unlock(inode);
mnt_drop_write_file(filp);
return ret;
return iflags;
}
-static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
+static void f2fs_fill_fsxattr(struct inode *inode, struct fsxattr *fa)
{
- struct inode *inode = file_inode(filp);
struct f2fs_inode_info *fi = F2FS_I(inode);
- struct fsxattr fa;
- memset(&fa, 0, sizeof(struct fsxattr));
- fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags);
+ simple_fill_fsxattr(fa, f2fs_iflags_to_xflags(fi->i_flags));
if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)))
- fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
- fi->i_projid);
-
- if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa)))
- return -EFAULT;
- return 0;
+ fa->fsx_projid = from_kprojid(&init_user_ns, fi->i_projid);
}
-static int f2fs_ioctl_check_project(struct inode *inode, struct fsxattr *fa)
+static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg)
{
- /*
- * Project Quota ID state is only allowed to change from within the init
- * namespace. Enforce that restriction only if we are trying to change
- * the quota ID state. Everything else is allowed in user namespaces.
- */
- if (current_user_ns() == &init_user_ns)
- return 0;
+ struct inode *inode = file_inode(filp);
+ struct fsxattr fa;
- if (__kprojid_val(F2FS_I(inode)->i_projid) != fa->fsx_projid)
- return -EINVAL;
-
- if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) {
- if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT))
- return -EINVAL;
- } else {
- if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
- return -EINVAL;
- }
+ f2fs_fill_fsxattr(inode, &fa);
+ if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa)))
+ return -EFAULT;
return 0;
}
static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
- struct fsxattr fa;
+ struct fsxattr fa, old_fa;
u32 iflags;
int err;
return err;
inode_lock(inode);
- err = f2fs_ioctl_check_project(inode, &fa);
+
+ f2fs_fill_fsxattr(inode, &old_fa);
+ err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa);
if (err)
goto out;
+
err = f2fs_setflags_common(inode, iflags,
f2fs_xflags_to_iflags(F2FS_SUPPORTED_XFLAGS));
if (err)
if (lfs_mode)
down_write(&fio.sbi->io_order_lock);
+ mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi),
+ fio.old_blkaddr, false);
+ if (!mpage)
+ goto up_out;
+
+ fio.encrypted_page = mpage;
+
+ /* read source block in mpage */
+ if (!PageUptodate(mpage)) {
+ err = f2fs_submit_page_bio(&fio);
+ if (err) {
+ f2fs_put_page(mpage, 1);
+ goto up_out;
+ }
+ lock_page(mpage);
+ if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) ||
+ !PageUptodate(mpage))) {
+ err = -EIO;
+ f2fs_put_page(mpage, 1);
+ goto up_out;
+ }
+ }
+
f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
&sum, CURSEG_COLD_DATA, NULL, false);
newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS);
if (!fio.encrypted_page) {
err = -ENOMEM;
- goto recover_block;
- }
-
- mpage = f2fs_pagecache_get_page(META_MAPPING(fio.sbi),
- fio.old_blkaddr, FGP_LOCK, GFP_NOFS);
- if (mpage) {
- bool updated = false;
-
- if (PageUptodate(mpage)) {
- memcpy(page_address(fio.encrypted_page),
- page_address(mpage), PAGE_SIZE);
- updated = true;
- }
f2fs_put_page(mpage, 1);
- invalidate_mapping_pages(META_MAPPING(fio.sbi),
- fio.old_blkaddr, fio.old_blkaddr);
- if (updated)
- goto write_page;
- }
-
- err = f2fs_submit_page_bio(&fio);
- if (err)
- goto put_page_out;
-
- /* write page */
- lock_page(fio.encrypted_page);
-
- if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) {
- err = -EIO;
- goto put_page_out;
- }
- if (unlikely(!PageUptodate(fio.encrypted_page))) {
- err = -EIO;
- goto put_page_out;
+ goto recover_block;
}
-write_page:
+ /* write target block */
f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true);
+ memcpy(page_address(fio.encrypted_page),
+ page_address(mpage), PAGE_SIZE);
+ f2fs_put_page(mpage, 1);
+ invalidate_mapping_pages(META_MAPPING(fio.sbi),
+ fio.old_blkaddr, fio.old_blkaddr);
+
set_page_dirty(fio.encrypted_page);
if (clear_page_dirty_for_io(fio.encrypted_page))
dec_page_count(fio.sbi, F2FS_DIRTY_META);
put_page_out:
f2fs_put_page(fio.encrypted_page, 1);
recover_block:
- if (lfs_mode)
- up_write(&fio.sbi->io_order_lock);
if (err)
f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr,
true, true);
+up_out:
+ if (lfs_mode)
+ up_write(&fio.sbi->io_order_lock);
put_out:
f2fs_put_dnode(&dn);
out:
size_t crc_offset = 0;
__u32 crc = 0;
+ if (le32_to_cpu(raw_super->magic) != F2FS_SUPER_MAGIC) {
+ f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)",
+ F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
+ return -EINVAL;
+ }
+
/* Check checksum_offset and crc in superblock */
if (__F2FS_HAS_FEATURE(raw_super, F2FS_FEATURE_SB_CHKSUM)) {
crc_offset = le32_to_cpu(raw_super->checksum_offset);
offsetof(struct f2fs_super_block, crc)) {
f2fs_info(sbi, "Invalid SB checksum offset: %zu",
crc_offset);
- return 1;
+ return -EFSCORRUPTED;
}
crc = le32_to_cpu(raw_super->crc);
if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) {
f2fs_info(sbi, "Invalid SB checksum value: %u", crc);
- return 1;
+ return -EFSCORRUPTED;
}
}
- if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) {
- f2fs_info(sbi, "Magic Mismatch, valid(0x%x) - read(0x%x)",
- F2FS_SUPER_MAGIC, le32_to_cpu(raw_super->magic));
- return 1;
- }
-
/* Currently, support only 4KB page cache size */
if (F2FS_BLKSIZE != PAGE_SIZE) {
f2fs_info(sbi, "Invalid page_cache_size (%lu), supports only 4KB",
PAGE_SIZE);
- return 1;
+ return -EFSCORRUPTED;
}
/* Currently, support only 4KB block size */
if (blocksize != F2FS_BLKSIZE) {
f2fs_info(sbi, "Invalid blocksize (%u), supports only 4KB",
blocksize);
- return 1;
+ return -EFSCORRUPTED;
}
/* check log blocks per segment */
if (le32_to_cpu(raw_super->log_blocks_per_seg) != 9) {
f2fs_info(sbi, "Invalid log blocks per segment (%u)",
le32_to_cpu(raw_super->log_blocks_per_seg));
- return 1;
+ return -EFSCORRUPTED;
}
/* Currently, support 512/1024/2048/4096 bytes sector size */
F2FS_MIN_LOG_SECTOR_SIZE) {
f2fs_info(sbi, "Invalid log sectorsize (%u)",
le32_to_cpu(raw_super->log_sectorsize));
- return 1;
+ return -EFSCORRUPTED;
}
if (le32_to_cpu(raw_super->log_sectors_per_block) +
le32_to_cpu(raw_super->log_sectorsize) !=
f2fs_info(sbi, "Invalid log sectors per block(%u) log sectorsize(%u)",
le32_to_cpu(raw_super->log_sectors_per_block),
le32_to_cpu(raw_super->log_sectorsize));
- return 1;
+ return -EFSCORRUPTED;
}
segment_count = le32_to_cpu(raw_super->segment_count);
if (segment_count > F2FS_MAX_SEGMENT ||
segment_count < F2FS_MIN_SEGMENTS) {
f2fs_info(sbi, "Invalid segment count (%u)", segment_count);
- return 1;
+ return -EFSCORRUPTED;
}
if (total_sections > segment_count ||
segs_per_sec > segment_count || !segs_per_sec) {
f2fs_info(sbi, "Invalid segment/section count (%u, %u x %u)",
segment_count, total_sections, segs_per_sec);
- return 1;
+ return -EFSCORRUPTED;
}
if ((segment_count / segs_per_sec) < total_sections) {
f2fs_info(sbi, "Small segment_count (%u < %u * %u)",
segment_count, segs_per_sec, total_sections);
- return 1;
+ return -EFSCORRUPTED;
}
if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) {
f2fs_info(sbi, "Wrong segment_count / block_count (%u > %llu)",
segment_count, le64_to_cpu(raw_super->block_count));
- return 1;
+ return -EFSCORRUPTED;
}
if (secs_per_zone > total_sections || !secs_per_zone) {
f2fs_info(sbi, "Wrong secs_per_zone / total_sections (%u, %u)",
secs_per_zone, total_sections);
- return 1;
+ return -EFSCORRUPTED;
}
if (le32_to_cpu(raw_super->extension_count) > F2FS_MAX_EXTENSION ||
raw_super->hot_ext_count > F2FS_MAX_EXTENSION ||
le32_to_cpu(raw_super->extension_count),
raw_super->hot_ext_count,
F2FS_MAX_EXTENSION);
- return 1;
+ return -EFSCORRUPTED;
}
if (le32_to_cpu(raw_super->cp_payload) >
f2fs_info(sbi, "Insane cp_payload (%u > %u)",
le32_to_cpu(raw_super->cp_payload),
blocks_per_seg - F2FS_CP_PACKS);
- return 1;
+ return -EFSCORRUPTED;
}
/* check reserved ino info */
le32_to_cpu(raw_super->node_ino),
le32_to_cpu(raw_super->meta_ino),
le32_to_cpu(raw_super->root_ino));
- return 1;
+ return -EFSCORRUPTED;
}
/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
if (sanity_check_area_boundary(sbi, bh))
- return 1;
+ return -EFSCORRUPTED;
return 0;
}
}
/* sanity checking of raw super */
- if (sanity_check_raw_super(sbi, bh)) {
+ err = sanity_check_raw_super(sbi, bh);
+ if (err) {
f2fs_err(sbi, "Can't find valid F2FS filesystem in %dth superblock",
block + 1);
- err = -EFSCORRUPTED;
brelse(bh);
continue;
}
return mp->mp_aheight - x - 1;
}
+static sector_t metapath_to_block(struct gfs2_sbd *sdp, struct metapath *mp)
+{
+ sector_t factor = 1, block = 0;
+ int hgt;
+
+ for (hgt = mp->mp_fheight - 1; hgt >= 0; hgt--) {
+ if (hgt < mp->mp_aheight)
+ block += mp->mp_list[hgt] * factor;
+ factor *= sdp->sd_inptrs;
+ }
+ return block;
+}
+
static void release_metapath(struct metapath *mp)
{
int i;
return ptr - first;
}
-typedef const __be64 *(*gfs2_metadata_walker)(
- struct metapath *mp,
- const __be64 *start, const __be64 *end,
- u64 factor, void *data);
+enum walker_status { WALK_STOP, WALK_FOLLOW, WALK_CONTINUE };
+
+/*
+ * gfs2_metadata_walker - walk an indirect block
+ * @mp: Metapath to indirect block
+ * @ptrs: Number of pointers to look at
+ *
+ * When returning WALK_FOLLOW, the walker must update @mp to point at the right
+ * indirect block to follow.
+ */
+typedef enum walker_status (*gfs2_metadata_walker)(struct metapath *mp,
+ unsigned int ptrs);
-#define WALK_STOP ((__be64 *)0)
-#define WALK_NEXT ((__be64 *)1)
+/*
+ * gfs2_walk_metadata - walk a tree of indirect blocks
+ * @inode: The inode
+ * @mp: Starting point of walk
+ * @max_len: Maximum number of blocks to walk
+ * @walker: Called during the walk
+ *
+ * Returns 1 if the walk was stopped by @walker, 0 if we went past @max_len or
+ * past the end of metadata, and a negative error code otherwise.
+ */
-static int gfs2_walk_metadata(struct inode *inode, sector_t lblock,
- u64 len, struct metapath *mp, gfs2_metadata_walker walker,
- void *data)
+static int gfs2_walk_metadata(struct inode *inode, struct metapath *mp,
+ u64 max_len, gfs2_metadata_walker walker)
{
- struct metapath clone;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
- const __be64 *start, *end, *ptr;
u64 factor = 1;
unsigned int hgt;
- int ret = 0;
+ int ret;
- for (hgt = ip->i_height - 1; hgt >= mp->mp_aheight; hgt--)
+ /*
+ * The walk starts in the lowest allocated indirect block, which may be
+ * before the position indicated by @mp. Adjust @max_len accordingly
+ * to avoid a short walk.
+ */
+ for (hgt = mp->mp_fheight - 1; hgt >= mp->mp_aheight; hgt--) {
+ max_len += mp->mp_list[hgt] * factor;
+ mp->mp_list[hgt] = 0;
factor *= sdp->sd_inptrs;
+ }
for (;;) {
- u64 step;
+ u16 start = mp->mp_list[hgt];
+ enum walker_status status;
+ unsigned int ptrs;
+ u64 len;
/* Walk indirect block. */
- start = metapointer(hgt, mp);
- end = metaend(hgt, mp);
-
- step = (end - start) * factor;
- if (step > len)
- end = start + DIV_ROUND_UP_ULL(len, factor);
-
- ptr = walker(mp, start, end, factor, data);
- if (ptr == WALK_STOP)
+ ptrs = (hgt >= 1 ? sdp->sd_inptrs : sdp->sd_diptrs) - start;
+ len = ptrs * factor;
+ if (len > max_len)
+ ptrs = DIV_ROUND_UP_ULL(max_len, factor);
+ status = walker(mp, ptrs);
+ switch (status) {
+ case WALK_STOP:
+ return 1;
+ case WALK_FOLLOW:
+ BUG_ON(mp->mp_aheight == mp->mp_fheight);
+ ptrs = mp->mp_list[hgt] - start;
+ len = ptrs * factor;
break;
- if (step >= len)
+ case WALK_CONTINUE:
break;
- len -= step;
- if (ptr != WALK_NEXT) {
- BUG_ON(!*ptr);
- mp->mp_list[hgt] += ptr - start;
- goto fill_up_metapath;
}
+ if (len >= max_len)
+ break;
+ max_len -= len;
+ if (status == WALK_FOLLOW)
+ goto fill_up_metapath;
lower_metapath:
/* Decrease height of metapath. */
- if (mp != &clone) {
- clone_metapath(&clone, mp);
- mp = &clone;
- }
brelse(mp->mp_bh[hgt]);
mp->mp_bh[hgt] = NULL;
+ mp->mp_list[hgt] = 0;
if (!hgt)
break;
hgt--;
/* Advance in metadata tree. */
(mp->mp_list[hgt])++;
- start = metapointer(hgt, mp);
- end = metaend(hgt, mp);
- if (start >= end) {
- mp->mp_list[hgt] = 0;
+ if (mp->mp_list[hgt] >= sdp->sd_inptrs) {
if (!hgt)
break;
goto lower_metapath;
fill_up_metapath:
/* Increase height of metapath. */
- if (mp != &clone) {
- clone_metapath(&clone, mp);
- mp = &clone;
- }
ret = fillup_metapath(ip, mp, ip->i_height - 1);
if (ret < 0)
- break;
+ return ret;
hgt += ret;
for (; ret; ret--)
do_div(factor, sdp->sd_inptrs);
mp->mp_aheight = hgt + 1;
}
- if (mp == &clone)
- release_metapath(mp);
- return ret;
+ return 0;
}
-struct gfs2_hole_walker_args {
- u64 blocks;
-};
-
-static const __be64 *gfs2_hole_walker(struct metapath *mp,
- const __be64 *start, const __be64 *end,
- u64 factor, void *data)
+static enum walker_status gfs2_hole_walker(struct metapath *mp,
+ unsigned int ptrs)
{
- struct gfs2_hole_walker_args *args = data;
- const __be64 *ptr;
+ const __be64 *start, *ptr, *end;
+ unsigned int hgt;
+
+ hgt = mp->mp_aheight - 1;
+ start = metapointer(hgt, mp);
+ end = start + ptrs;
for (ptr = start; ptr < end; ptr++) {
if (*ptr) {
- args->blocks += (ptr - start) * factor;
+ mp->mp_list[hgt] += ptr - start;
if (mp->mp_aheight == mp->mp_fheight)
return WALK_STOP;
- return ptr; /* increase height */
+ return WALK_FOLLOW;
}
}
- args->blocks += (end - start) * factor;
- return WALK_NEXT;
+ return WALK_CONTINUE;
}
/**
static int gfs2_hole_size(struct inode *inode, sector_t lblock, u64 len,
struct metapath *mp, struct iomap *iomap)
{
- struct gfs2_hole_walker_args args = { };
- int ret = 0;
+ struct metapath clone;
+ u64 hole_size;
+ int ret;
- ret = gfs2_walk_metadata(inode, lblock, len, mp, gfs2_hole_walker, &args);
- if (!ret)
- iomap->length = args.blocks << inode->i_blkbits;
+ clone_metapath(&clone, mp);
+ ret = gfs2_walk_metadata(inode, &clone, len, gfs2_hole_walker);
+ if (ret < 0)
+ goto out;
+
+ if (ret == 1)
+ hole_size = metapath_to_block(GFS2_SB(inode), &clone) - lblock;
+ else
+ hole_size = len;
+ iomap->length = hole_size << inode->i_blkbits;
+ ret = 0;
+
+out:
+ release_metapath(&clone);
return ret;
}
unsigned copied, struct page *page,
struct iomap *iomap)
{
+ struct gfs2_trans *tr = current->journal_info;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
if (page && !gfs2_is_stuffed(ip))
gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+
+ if (tr->tr_num_buf_new)
+ __mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+
gfs2_trans_end(sdp);
}
tr = current->journal_info;
if (tr->tr_num_buf_new)
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
- else
- gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[0]);
gfs2_trans_end(sdp);
}
if (ip->i_qadata && ip->i_qadata->qa_qd_num)
gfs2_quota_unlock(ip);
+
+ if (unlikely(!written))
+ goto out_unlock;
+
if (iomap->flags & IOMAP_F_SIZE_CHANGED)
mark_inode_dirty(inode);
- gfs2_write_unlock(inode);
+ set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
+out_unlock:
+ gfs2_write_unlock(inode);
out:
return 0;
}
struct file *file;
off_t io_end;
- size_t io_pages;
+ size_t io_len;
};
struct io_ring_ctx {
#define REQ_F_IO_DRAIN 16 /* drain existing IO first */
#define REQ_F_IO_DRAINED 32 /* drain done */
#define REQ_F_LINK 64 /* linked sqes */
-#define REQ_F_FAIL_LINK 128 /* fail rest of links */
+#define REQ_F_LINK_DONE 128 /* linked sqes done */
+#define REQ_F_FAIL_LINK 256 /* fail rest of links */
u64 user_data;
u32 result;
u32 sequence;
if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN)
return false;
- return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped;
+ return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped;
}
static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx)
nxt->flags |= REQ_F_LINK;
}
+ nxt->flags |= REQ_F_LINK_DONE;
INIT_WORK(&nxt->work, io_sq_wq_submit_work);
queue_work(req->ctx->sqo_wq, &nxt->work);
}
io_free_req(req);
}
+static unsigned io_cqring_events(struct io_cq_ring *ring)
+{
+ /* See comment at the top of this file */
+ smp_rmb();
+ return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
+}
+
/*
* Find and free completed poll iocbs
*/
static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
long min)
{
- while (!list_empty(&ctx->poll_list)) {
+ while (!list_empty(&ctx->poll_list) && !need_resched()) {
int ret;
ret = io_do_iopoll(ctx, nr_events, min);
unsigned int nr_events = 0;
io_iopoll_getevents(ctx, &nr_events, 1);
+
+ /*
+ * Ensure we allow local-to-the-cpu processing to take place,
+ * in this case we need to ensure that we reap all events.
+ */
+ cond_resched();
}
mutex_unlock(&ctx->uring_lock);
}
static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
long min)
{
- int ret = 0;
+ int iters, ret = 0;
+
+ /*
+ * We disallow the app entering submit/complete with polling, but we
+ * still need to lock the ring to prevent racing with polled issue
+ * that got punted to a workqueue.
+ */
+ mutex_lock(&ctx->uring_lock);
+ iters = 0;
do {
int tmin = 0;
+ /*
+ * Don't enter poll loop if we already have events pending.
+ * If we do, we can potentially be spinning for commands that
+ * already triggered a CQE (eg in error).
+ */
+ if (io_cqring_events(ctx->cq_ring))
+ break;
+
+ /*
+ * If a submit got punted to a workqueue, we can have the
+ * application entering polling for a command before it gets
+ * issued. That app will hold the uring_lock for the duration
+ * of the poll right here, so we need to take a breather every
+ * now and then to ensure that the issue has a chance to add
+ * the poll to the issued list. Otherwise we can spin here
+ * forever, while the workqueue is stuck trying to acquire the
+ * very same mutex.
+ */
+ if (!(++iters & 7)) {
+ mutex_unlock(&ctx->uring_lock);
+ mutex_lock(&ctx->uring_lock);
+ }
+
if (*nr_events < min)
tmin = min - *nr_events;
ret = 0;
} while (min && !*nr_events && !need_resched());
+ mutex_unlock(&ctx->uring_lock);
return ret;
}
*/
offset = buf_addr - imu->ubuf;
iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
- if (offset)
- iov_iter_advance(iter, offset);
+
+ if (offset) {
+ /*
+ * Don't use iov_iter_advance() here, as it's really slow for
+ * using the latter parts of a big fixed buffer - it iterates
+ * over each segment manually. We can cheat a bit here, because
+ * we know that:
+ *
+ * 1) it's a BVEC iter, we set it up
+ * 2) all bvecs are PAGE_SIZE in size, except potentially the
+ * first and last bvec
+ *
+ * So just find our index, and adjust the iterator afterwards.
+ * If the offset is within the first bvec (or the whole first
+ * bvec, just use iov_iter_advance(). This makes it easier
+ * since we can just skip the first segment, which may not
+ * be PAGE_SIZE aligned.
+ */
+ const struct bio_vec *bvec = imu->bvec;
+
+ if (offset <= bvec->bv_len) {
+ iov_iter_advance(iter, offset);
+ } else {
+ unsigned long seg_skip;
+
+ /* skip first vec */
+ offset -= bvec->bv_len;
+ seg_skip = 1 + (offset >> PAGE_SHIFT);
+
+ iter->bvec = bvec + seg_skip;
+ iter->nr_segs -= seg_skip;
+ iter->count -= bvec->bv_len + offset;
+ iter->iov_offset = offset & ~PAGE_MASK;
+ }
+ }
+
return 0;
}
off_t io_end = kiocb->ki_pos + len;
if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) {
- unsigned long max_pages;
+ unsigned long max_bytes;
/* Use 8x RA size as a decent limiter for both reads/writes */
- max_pages = filp->f_ra.ra_pages;
- if (!max_pages)
- max_pages = VM_READAHEAD_PAGES;
- max_pages *= 8;
-
- /* If max pages are exceeded, reset the state */
- len >>= PAGE_SHIFT;
- if (async_list->io_pages + len <= max_pages) {
+ max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3);
+ if (!max_bytes)
+ max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3);
+
+ /* If max len are exceeded, reset the state */
+ if (async_list->io_len + len <= max_bytes) {
req->flags |= REQ_F_SEQ_PREV;
- async_list->io_pages += len;
+ async_list->io_len += len;
} else {
io_end = 0;
- async_list->io_pages = 0;
+ async_list->io_len = 0;
}
}
/* New file? Reset state. */
if (async_list->file != filp) {
- async_list->io_pages = 0;
+ async_list->io_len = 0;
async_list->file = filp;
}
async_list->io_end = io_end;
INIT_LIST_HEAD(&poll->wait.entry);
init_waitqueue_func_entry(&poll->wait, io_poll_wake);
+ INIT_LIST_HEAD(&req->list);
+
mask = vfs_poll(poll->file, &ipt.pt) & poll->events;
spin_lock_irq(&ctx->completion_lock);
do {
struct sqe_submit *s = &req->submit;
const struct io_uring_sqe *sqe = s->sqe;
+ unsigned int flags = req->flags;
/* Ensure we clear previously set non-block flag */
req->rw.ki_flags &= ~IOCB_NOWAIT;
/* async context always use a copy of the sqe */
kfree(sqe);
+ /* req from defer and link list needn't decrease async cnt */
+ if (flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE))
+ goto out;
+
if (!async_list)
break;
if (!list_empty(&req_list)) {
}
}
+out:
if (cur_mm) {
set_fs(old_fs);
unuse_mm(cur_mm);
ret = true;
spin_lock(&list->lock);
list_add_tail(&req->list, &list->list);
+ /*
+ * Ensure we see a simultaneous modification from io_sq_wq_submit_work()
+ */
+ smp_mb();
if (!atomic_read(&list->cnt)) {
list_del_init(&req->list);
ret = false;
{
int ret;
+ ret = io_req_defer(ctx, req, s->sqe);
+ if (ret) {
+ if (ret != -EIOCBQUEUED) {
+ io_free_req(req);
+ io_cqring_add_event(ctx, s->sqe->user_data, ret);
+ }
+ return 0;
+ }
+
ret = __io_submit_sqe(ctx, req, s, true);
if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
struct io_uring_sqe *sqe_copy;
return;
}
- ret = io_req_defer(ctx, req, s->sqe);
- if (ret) {
- if (ret != -EIOCBQUEUED)
- goto err_req;
- return;
- }
-
/*
* If we already have a head request, queue this one for async
* submittal once the head completes. If we don't have a head but
unsigned nr_events = 0;
if (ctx->flags & IORING_SETUP_IOPOLL) {
- /*
- * We disallow the app entering submit/complete
- * with polling, but we still need to lock the
- * ring to prevent racing with polled issue
- * that got punted to a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
io_iopoll_check(ctx, &nr_events, 0);
- mutex_unlock(&ctx->uring_lock);
} else {
/*
* Normal IO, just pretend everything completed.
return submit;
}
-static unsigned io_cqring_events(struct io_cq_ring *ring)
-{
- /* See comment at the top of this file */
- smp_rmb();
- return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head);
-}
-
/*
* Wait until events become available, if we don't already have some. The
* application must reap them itself, as they reside on the shared cq ring.
min_complete = min(min_complete, ctx->cq_entries);
if (ctx->flags & IORING_SETUP_IOPOLL) {
- mutex_lock(&ctx->uring_lock);
ret = io_iopoll_check(ctx, &nr_events, min_complete);
- mutex_unlock(&ctx->uring_lock);
} else {
ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
}
-# SPDX-License-Identifier: GPL-2.0-or-newer
+# SPDX-License-Identifier: GPL-2.0-or-later
#
# Copyright (c) 2019 Oracle.
# All Rights Reserved.
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
disconnect = disconnect_mount(p, how);
-
if (mnt_has_parent(p)) {
mnt_add_count(p->mnt_parent, -1);
if (!disconnect) {
list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts);
} else {
umount_mnt(p);
- hlist_add_head(&p->mnt_umount, &unmounted);
}
}
change_mnt_propagation(p, MS_PRIVATE);
+ if (disconnect)
+ hlist_add_head(&p->mnt_umount, &unmounted);
}
}
/* Block nfs4_proc_unlck */
mutex_lock(&sp->so_delegreturn_mutex);
seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
- err = nfs4_open_delegation_recall(ctx, state, stateid, type);
+ err = nfs4_open_delegation_recall(ctx, state, stateid);
if (!err)
err = nfs_delegation_claim_locks(state, stateid);
if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
nfs4_schedule_state_manager(clp);
}
+static void
+nfs_delegation_test_free_expired(struct inode *inode,
+ nfs4_stateid *stateid,
+ const struct cred *cred)
+{
+ struct nfs_server *server = NFS_SERVER(inode);
+ const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops;
+ int status;
+
+ if (!cred)
+ return;
+ status = ops->test_and_free_expired(server, stateid, cred);
+ if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID)
+ nfs_remove_bad_delegation(inode, stateid);
+}
+
/**
* nfs_reap_expired_delegations - reap expired delegations
* @clp: nfs_client to process
*/
void nfs_reap_expired_delegations(struct nfs_client *clp)
{
- const struct nfs4_minor_version_ops *ops = clp->cl_mvops;
struct nfs_delegation *delegation;
struct nfs_server *server;
struct inode *inode;
nfs4_stateid_copy(&stateid, &delegation->stateid);
clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags);
rcu_read_unlock();
- if (cred != NULL &&
- ops->test_and_free_expired(server, &stateid, cred) < 0) {
- nfs_revoke_delegation(inode, &stateid);
- nfs_inode_find_state_and_recover(inode, &stateid);
- }
+ nfs_delegation_test_free_expired(inode, &stateid, cred);
put_cred(cred);
if (nfs4_server_rebooted(clp)) {
nfs_inode_mark_test_expired_delegation(server,inode);
/* NFSv4 delegation-related procedures */
int nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync);
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred);
bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
nfs_file_set_open_context(file, ctx);
else
- err = -ESTALE;
+ err = -EOPENSTALE;
out:
return err;
}
unsigned long bytes = 0;
struct nfs_direct_req *dreq = hdr->dreq;
- if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
- goto out_put;
-
spin_lock(&dreq->lock);
- if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
+ if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
dreq->error = hdr->error;
- else
+
+ if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ spin_unlock(&dreq->lock);
+ goto out_put;
+ }
+
+ if (hdr->good_bytes != 0)
nfs_direct_good_bytes(dreq, hdr);
+ if (test_bit(NFS_IOHDR_EOF, &hdr->flags))
+ dreq->error = 0;
+
spin_unlock(&dreq->lock);
while (!list_empty(&hdr->pages)) {
bool request_commit = false;
struct nfs_page *req = nfs_list_entry(hdr->pages.next);
- if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
- goto out_put;
-
nfs_init_cinfo_from_dreq(&cinfo, dreq);
spin_lock(&dreq->lock);
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags))
dreq->error = hdr->error;
- if (dreq->error == 0) {
+
+ if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ spin_unlock(&dreq->lock);
+ goto out_put;
+ }
+
+ if (hdr->good_bytes != 0) {
nfs_direct_good_bytes(dreq, hdr);
if (nfs_write_need_commit(hdr)) {
if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
*/
#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
#include <linux/sched/mm.h>
pgm = &pgio->pg_mirrors[0];
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
- pgio->pg_maxretrans = io_maxretrans;
+ if (NFS_SERVER(pgio->pg_inode)->flags &
+ (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+ pgio->pg_maxretrans = io_maxretrans;
return;
out_nolseg:
if (pgio->pg_error < 0)
pgio->pg_lseg);
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
+ pgio->pg_maxretrans = 0;
nfs_pageio_reset_read_mds(pgio);
}
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
}
- pgio->pg_maxretrans = io_maxretrans;
+ if (NFS_SERVER(pgio->pg_inode)->flags &
+ (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+ pgio->pg_maxretrans = io_maxretrans;
return;
out_mds:
pgio->pg_lseg);
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
+ pgio->pg_maxretrans = 0;
nfs_pageio_reset_write_mds(pgio);
}
break;
case -NFS4ERR_RETRY_UNCACHED_REP:
break;
- case -EAGAIN:
- return -NFS4ERR_RESET_TO_PNFS;
/* Invalidate Layout errors */
case -NFS4ERR_PNFS_NO_LAYOUT:
case -ESTALE: /* mapped NFS4ERR_STALE */
case -EBADHANDLE:
case -ELOOP:
case -ENOSPC:
- case -EAGAIN:
break;
case -EJUKEBOX:
nfs_inc_stats(lseg->pls_layout->plh_inode, NFSIOS_DELAY);
ff_layout_read_prepare_common(task, hdr);
}
-static void
-ff_layout_io_prepare_transmit(struct rpc_task *task,
- void *data)
-{
- struct nfs_pgio_header *hdr = data;
-
- if (!pnfs_is_valid_lseg(hdr->lseg))
- rpc_exit(task, -EAGAIN);
-}
-
static void ff_layout_read_call_done(struct rpc_task *task, void *data)
{
struct nfs_pgio_header *hdr = data;
static const struct rpc_call_ops ff_layout_read_call_ops_v3 = {
.rpc_call_prepare = ff_layout_read_prepare_v3,
- .rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
.rpc_call_done = ff_layout_read_call_done,
.rpc_count_stats = ff_layout_read_count_stats,
.rpc_release = ff_layout_read_release,
static const struct rpc_call_ops ff_layout_read_call_ops_v4 = {
.rpc_call_prepare = ff_layout_read_prepare_v4,
- .rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
.rpc_call_done = ff_layout_read_call_done,
.rpc_count_stats = ff_layout_read_count_stats,
.rpc_release = ff_layout_read_release,
static const struct rpc_call_ops ff_layout_write_call_ops_v3 = {
.rpc_call_prepare = ff_layout_write_prepare_v3,
- .rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
.rpc_call_done = ff_layout_write_call_done,
.rpc_count_stats = ff_layout_write_count_stats,
.rpc_release = ff_layout_write_release,
static const struct rpc_call_ops ff_layout_write_call_ops_v4 = {
.rpc_call_prepare = ff_layout_write_prepare_v4,
- .rpc_call_prepare_transmit = ff_layout_io_prepare_transmit,
.rpc_call_done = ff_layout_write_call_done,
.rpc_count_stats = ff_layout_write_count_stats,
.rpc_release = ff_layout_write_release,
struct rb_node **p, *parent;
int diff;
+ nfss->fscache_key = NULL;
+ nfss->fscache = NULL;
+ if (!(nfss->options & NFS_OPTION_FSCACHE))
+ return;
if (!uniq) {
uniq = "";
ulen = 1;
void nfs_fscache_init_inode(struct inode *inode)
{
struct nfs_fscache_inode_auxdata auxdata;
+ struct nfs_server *nfss = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
nfsi->fscache = NULL;
- if (!S_ISREG(inode->i_mode))
+ if (!(nfss->fscache && S_ISREG(inode->i_mode)))
return;
memset(&auxdata, 0, sizeof(auxdata));
*/
static inline const char *nfs_server_fscache_state(struct nfs_server *server)
{
- if (server->fscache && (server->options & NFS_OPTION_FSCACHE))
+ if (server->fscache)
return "yes";
return "no ";
}
if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
return 0;
+ if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
+ /* Only a mounted-on-fileid? Just exit */
+ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
+ return 0;
/* Has the inode gone and changed behind our back? */
- if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
+ } else if (nfsi->fileid != fattr->fileid) {
+ /* Is this perhaps the mounted-on fileid? */
+ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
+ nfsi->fileid == fattr->mounted_on_fileid)
+ return 0;
return -ESTALE;
+ }
if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
return -ESTALE;
+
if (!nfs_file_has_buffered_writers(nfsi)) {
/* Verify a few of the more important attributes */
if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) != 0 && !inode_eq_iversion_raw(inode, fattr->change_attr))
EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc);
-static inline bool nfs_fileid_valid(struct nfs_inode *nfsi,
- struct nfs_fattr *fattr)
-{
- bool ret1 = true, ret2 = true;
-
- if (fattr->valid & NFS_ATTR_FATTR_FILEID)
- ret1 = (nfsi->fileid == fattr->fileid);
- if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
- ret2 = (nfsi->fileid == fattr->mounted_on_fileid);
- return ret1 || ret2;
-}
-
/*
* Many nfs protocol calls return the new file attributes after
* an operation. Here we update the inode to reflect the state
nfs_display_fhandle_hash(NFS_FH(inode)),
atomic_read(&inode->i_count), fattr->valid);
- if (!nfs_fileid_valid(nfsi, fattr)) {
+ if (!(fattr->valid & NFS_ATTR_FATTR_FILEID)) {
+ /* Only a mounted-on-fileid? Just exit */
+ if (fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID)
+ return 0;
+ /* Has the inode gone and changed behind our back? */
+ } else if (nfsi->fileid != fattr->fileid) {
+ /* Is this perhaps the mounted-on fileid? */
+ if ((fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) &&
+ nfsi->fileid == fattr->mounted_on_fileid)
+ return 0;
printk(KERN_ERR "NFS: server %s error: fileid changed\n"
"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
NFS_SERVER(inode)->nfs_client->cl_hostname,
}
}
+static inline bool nfs_error_is_fatal_on_server(int err)
+{
+ switch (err) {
+ case 0:
+ case -ERESTARTSYS:
+ case -EINTR:
+ return false;
+ }
+ return nfs_error_is_fatal(err);
+}
extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, const struct cred *, gfp_t);
extern void nfs4_put_state_owner(struct nfs4_state_owner *);
-extern void nfs4_purge_state_owners(struct nfs_server *);
+extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *);
+extern void nfs4_free_state_owners(struct list_head *head);
extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
extern void nfs4_put_open_state(struct nfs4_state *);
extern void nfs4_close_state(struct nfs4_state *, fmode_t);
static void nfs4_destroy_server(struct nfs_server *server)
{
+ LIST_HEAD(freeme);
+
nfs_server_return_all_delegations(server);
unset_pnfs_layoutdriver(server);
- nfs4_purge_state_owners(server);
+ nfs4_purge_state_owners(server, &freeme);
+ nfs4_free_state_owners(&freeme);
}
/*
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
switch (err) {
- case -EPERM:
- case -EACCES:
- case -EDQUOT:
- case -ENOSPC:
- case -EROFS:
- goto out_put_ctx;
default:
+ goto out_put_ctx;
+ case -ENOENT:
+ case -ESTALE:
+ case -EISDIR:
+ case -ENOTDIR:
+ case -ELOOP:
goto out_drop;
}
}
write_sequnlock(&state->seqlock);
}
+static void nfs_state_clear_open_state_flags(struct nfs4_state *state)
+{
+ clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+ clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+ clear_bit(NFS_OPEN_STATE, &state->flags);
+}
+
static void nfs_state_set_delegation(struct nfs4_state *state,
const nfs4_stateid *deleg_stateid,
fmode_t fmode)
if (data->o_res.delegation_type != 0)
nfs4_opendata_check_deleg(data, state);
update:
- update_open_stateid(state, &data->o_res.stateid, NULL,
- data->o_arg.fmode);
+ if (!update_open_stateid(state, &data->o_res.stateid,
+ NULL, data->o_arg.fmode))
+ return ERR_PTR(-EAGAIN);
refcount_inc(&state->count);
return state;
if (data->o_res.delegation_type != 0)
nfs4_opendata_check_deleg(data, state);
- update_open_stateid(state, &data->o_res.stateid, NULL,
- data->o_arg.fmode);
+ if (!update_open_stateid(state, &data->o_res.stateid,
+ NULL, data->o_arg.fmode)) {
+ nfs4_put_open_state(state);
+ state = ERR_PTR(-EAGAIN);
+ }
out:
nfs_release_seqid(data->o_arg.seqid);
return state;
{
int ret;
- /* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
/* memory barrier prior to reading state->n_* */
- clear_bit(NFS_DELEGATED_STATE, &state->flags);
- clear_bit(NFS_OPEN_STATE, &state->flags);
smp_rmb();
ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
if (ret != 0)
ctx = nfs4_state_find_open_context(state);
if (IS_ERR(ctx))
return -EAGAIN;
+ clear_bit(NFS_DELEGATED_STATE, &state->flags);
+ nfs_state_clear_open_state_flags(state);
ret = nfs4_do_open_reclaim(ctx, state);
put_nfs_open_context(ctx);
return ret;
case -ENOENT:
case -EAGAIN:
case -ESTALE:
+ case -ETIMEDOUT:
break;
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
case -NFS4ERR_DEADSESSION:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
return -EAGAIN;
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
/* Don't recall a delegation if it was lost */
nfs4_schedule_lease_recovery(server->nfs_client);
return -EAGAIN;
return -EAGAIN;
case -NFS4ERR_DELAY:
case -NFS4ERR_GRACE:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
ssleep(1);
return -EAGAIN;
case -ENOMEM:
}
int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
- struct nfs4_state *state, const nfs4_stateid *stateid,
- fmode_t type)
+ struct nfs4_state *state, const nfs4_stateid *stateid)
{
struct nfs_server *server = NFS_SERVER(state->inode);
struct nfs4_opendata *opendata;
if (IS_ERR(opendata))
return PTR_ERR(opendata);
nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
- nfs_state_clear_delegation(state);
- switch (type & (FMODE_READ|FMODE_WRITE)) {
- case FMODE_READ|FMODE_WRITE:
- case FMODE_WRITE:
+ if (!test_bit(NFS_O_RDWR_STATE, &state->flags)) {
err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
if (err)
- break;
+ goto out;
+ }
+ if (!test_bit(NFS_O_WRONLY_STATE, &state->flags)) {
err = nfs4_open_recover_helper(opendata, FMODE_WRITE);
if (err)
- break;
- /* Fall through */
- case FMODE_READ:
+ goto out;
+ }
+ if (!test_bit(NFS_O_RDONLY_STATE, &state->flags)) {
err = nfs4_open_recover_helper(opendata, FMODE_READ);
+ if (err)
+ goto out;
}
+ nfs_state_clear_delegation(state);
+out:
nfs4_opendata_put(opendata);
return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err);
}
if (!ctx) {
nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1, 1);
data->is_recover = true;
+ task_setup_data.flags |= RPC_TASK_TIMEOUT;
} else {
nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1, 0);
pnfs_lgopen_prepare(data, ctx);
{
/* NFSv4.0 doesn't allow for delegation recovery on open expire */
nfs40_clear_delegation_stateid(state);
+ nfs_state_clear_open_state_flags(state);
return nfs4_open_expired(sp, state);
}
return -NFS4ERR_EXPIRED;
}
-static void nfs41_check_delegation_stateid(struct nfs4_state *state)
+static int nfs41_check_delegation_stateid(struct nfs4_state *state)
{
struct nfs_server *server = NFS_SERVER(state->inode);
nfs4_stateid stateid;
struct nfs_delegation *delegation;
const struct cred *cred = NULL;
- int status;
+ int status, ret = NFS_OK;
/* Get the delegation credential for use by test/free_stateid */
rcu_read_lock();
if (delegation == NULL) {
rcu_read_unlock();
nfs_state_clear_delegation(state);
- return;
+ return NFS_OK;
}
nfs4_stateid_copy(&stateid, &delegation->stateid);
- if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
- rcu_read_unlock();
- nfs_state_clear_delegation(state);
- return;
- }
if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
&delegation->flags)) {
rcu_read_unlock();
- return;
+ return NFS_OK;
}
if (delegation->cred)
trace_nfs4_test_delegation_stateid(state, NULL, status);
if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID)
nfs_finish_clear_delegation_stateid(state, &stateid);
+ else
+ ret = status;
- if (delegation->cred)
- put_cred(cred);
+ put_cred(cred);
+ return ret;
+}
+
+static void nfs41_delegation_recover_stateid(struct nfs4_state *state)
+{
+ nfs4_stateid tmp;
+
+ if (test_bit(NFS_DELEGATED_STATE, &state->flags) &&
+ nfs4_copy_delegation_stateid(state->inode, state->state,
+ &tmp, NULL) &&
+ nfs4_stateid_match_other(&state->stateid, &tmp))
+ nfs_state_set_delegation(state, &tmp, state->state);
+ else
+ nfs_state_clear_delegation(state);
}
/**
const struct cred *cred = state->owner->so_cred;
int status;
- if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) {
- if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) {
- if (nfs4_have_delegation(state->inode, state->state))
- return NFS_OK;
- return -NFS4ERR_OPENMODE;
- }
+ if (test_bit(NFS_OPEN_STATE, &state->flags) == 0)
return -NFS4ERR_BAD_STATEID;
- }
status = nfs41_test_and_free_expired_stateid(server, stateid, cred);
trace_nfs4_test_open_stateid(state, NULL, status);
if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) {
- clear_bit(NFS_O_RDONLY_STATE, &state->flags);
- clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
- clear_bit(NFS_OPEN_STATE, &state->flags);
+ nfs_state_clear_open_state_flags(state);
stateid->type = NFS4_INVALID_STATEID_TYPE;
return status;
}
{
int status;
- nfs41_check_delegation_stateid(state);
+ status = nfs41_check_delegation_stateid(state);
+ if (status != NFS_OK)
+ return status;
+ nfs41_delegation_recover_stateid(state);
+
status = nfs41_check_expired_locks(state);
if (status != NFS_OK)
return status;
if (nfs4_copy_delegation_stateid(inode, FMODE_WRITE, &arg->stateid, &delegation_cred)) {
/* Use that stateid */
- } else if (ctx != NULL) {
+ } else if (ctx != NULL && ctx->state) {
struct nfs_lock_context *l_ctx;
if (!nfs4_valid_open_stateid(ctx->state))
return -EBADF;
/**
* nfs4_purge_state_owners - Release all cached state owners
* @server: nfs_server with cached state owners to release
+ * @head: resulting list of state owners
*
* Called at umount time. Remaining state owners will be on
* the LRU with ref count of zero.
+ * Note that the state owners are not freed, but are added
+ * to the list @head, which can later be used as an argument
+ * to nfs4_free_state_owners.
*/
-void nfs4_purge_state_owners(struct nfs_server *server)
+void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state_owner *sp, *tmp;
- LIST_HEAD(doomed);
spin_lock(&clp->cl_lock);
list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
- list_move(&sp->so_lru, &doomed);
+ list_move(&sp->so_lru, head);
nfs4_remove_state_owner_locked(sp);
}
spin_unlock(&clp->cl_lock);
+}
- list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
+/**
+ * nfs4_purge_state_owners - Release all cached state owners
+ * @head: resulting list of state owners
+ *
+ * Frees a list of state owners that was generated by
+ * nfs4_purge_state_owners
+ */
+void nfs4_free_state_owners(struct list_head *head)
+{
+ struct nfs4_state_owner *sp, *tmp;
+
+ list_for_each_entry_safe(sp, tmp, head, so_lru) {
list_del(&sp->so_lru);
nfs4_free_state_owner(sp);
}
nfs4_schedule_state_manager(clp);
}
-static void nfs4_state_mark_open_context_bad(struct nfs4_state *state)
+static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err)
{
struct inode *inode = state->inode;
struct nfs_inode *nfsi = NFS_I(inode);
if (ctx->state != state)
continue;
set_bit(NFS_CONTEXT_BAD, &ctx->flags);
+ pr_warn("NFSv4: state recovery failed for open file %pd2, "
+ "error = %d\n", ctx->dentry, err);
}
rcu_read_unlock();
}
static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error)
{
set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags);
- nfs4_state_mark_open_context_bad(state);
+ nfs4_state_mark_open_context_bad(state, error);
}
switch (status) {
case 0:
break;
+ case -ETIMEDOUT:
case -ESTALE:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs4_state_recovery_ops *ops)
{
struct nfs4_state *state;
+ unsigned int loop = 0;
int status = 0;
/* Note: we rely on the sp->so_states list being ordered
switch (status) {
default:
- if (status >= 0)
+ if (status >= 0) {
+ loop = 0;
break;
+ }
printk(KERN_ERR "NFS: %s: unhandled error %d\n", __func__, status);
/* Fall through */
case -ENOENT:
break;
case -EAGAIN:
ssleep(1);
+ if (loop++ < 10) {
+ set_bit(ops->state_flag_bit, &state->flags);
+ break;
+ }
/* Fall through */
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_EXPIRED:
case -NFS4ERR_NO_GRACE:
nfs4_state_mark_reclaim_nograce(sp->so_server->nfs_client, state);
+ /* Fall through */
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_BADSESSION:
case -NFS4ERR_BADSLOT:
case -NFS4ERR_BAD_HIGH_SLOT:
case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ case -ETIMEDOUT:
goto out_err;
}
nfs4_put_open_state(state);
struct nfs4_state_owner *sp;
struct nfs_server *server;
struct rb_node *pos;
+ LIST_HEAD(freeme);
int status = 0;
restart:
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
- nfs4_purge_state_owners(server);
+ nfs4_purge_state_owners(server, &freeme);
spin_lock(&clp->cl_lock);
for (pos = rb_first(&server->state_owners);
pos != NULL;
spin_unlock(&clp->cl_lock);
}
rcu_read_unlock();
+ nfs4_free_state_owners(&freeme);
return 0;
}
return -EPERM;
case -EACCES:
case -NFS4ERR_DELAY:
- case -ETIMEDOUT:
case -EAGAIN:
ssleep(1);
break;
}
/* Now recover expired state... */
- if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
+ if (test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) {
section = "reclaim nograce";
status = nfs4_do_reclaim(clp,
clp->cl_mvops->nograce_recovery_ops);
continue;
if (status < 0)
goto out_error;
+ clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state);
}
nfs4_end_drain_session(clp);
}
hdr->res.fattr = &hdr->fattr;
- hdr->res.count = count;
+ hdr->res.count = 0;
hdr->res.eof = 0;
hdr->res.verf = &hdr->verf;
nfs_fattr_init(&hdr->fattr);
int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
- LIST_HEAD(failed);
+ LIST_HEAD(pages);
desc->pg_io_completion = hdr->io_completion;
desc->pg_dreq = hdr->dreq;
- while (!list_empty(&hdr->pages)) {
- struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+ list_splice_init(&hdr->pages, &pages);
+ while (!list_empty(&pages)) {
+ struct nfs_page *req = nfs_list_entry(pages.next);
if (!nfs_pageio_add_request(desc, req))
- nfs_list_move_request(req, &failed);
+ break;
}
nfs_pageio_complete(desc);
- if (!list_empty(&failed)) {
- list_move(&failed, &hdr->pages);
- return desc->pg_error < 0 ? desc->pg_error : -EIO;
+ if (!list_empty(&pages)) {
+ int err = desc->pg_error < 0 ? desc->pg_error : -EIO;
+ hdr->completion_ops->error_cleanup(&pages, err);
+ nfs_set_pgio_error(hdr, err, hdr->io_start);
+ return err;
}
return 0;
}
goto out_unlock;
}
- if (!nfs4_valid_open_stateid(ctx->state)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
- PNFS_UPDATE_LAYOUT_INVALID_OPEN);
- goto out_unlock;
- }
-
/*
* Choose a stateid for the LAYOUTGET. If we don't have a layout
* stateid, or it has been invalidated, then we must use the open
iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ,
NULL, &stateid, NULL);
if (status != 0) {
+ lseg = ERR_PTR(status);
trace_pnfs_update_layout(ino, pos, count,
iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_INVALID_OPEN);
/* Add this address as an alias */
rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
rpc_clnt_test_and_add_xprt, NULL);
- } else
- clp = get_v3_ds_connect(mds_srv,
- (struct sockaddr *)&da->da_addr,
- da->da_addrlen, IPPROTO_TCP,
- timeo, retrans);
+ continue;
+ }
+ clp = get_v3_ds_connect(mds_srv,
+ (struct sockaddr *)&da->da_addr,
+ da->da_addrlen, IPPROTO_TCP,
+ timeo, retrans);
+ if (IS_ERR(clp))
+ continue;
+ clp->cl_rpcclient->cl_softerr = 0;
+ clp->cl_rpcclient->cl_softrtry = 0;
}
if (IS_ERR(clp)) {
/* Emulate the eof flag, which isn't normally needed in NFSv2
* as it is guaranteed to always return the file attributes
*/
- if (hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
+ if ((hdr->res.count == 0 && hdr->args.count > 0) ||
+ hdr->args.offset + hdr->res.count >= hdr->res.fattr->size)
hdr->res.eof = 1;
}
return 0;
static int nfs_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
- if (task->tk_status >= 0)
+ if (task->tk_status >= 0) {
+ hdr->res.count = hdr->args.count;
nfs_writeback_update_inode(hdr);
+ }
return 0;
}
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
-static void nfs_readpage_release(struct nfs_page *req)
+static void nfs_readpage_release(struct nfs_page *req, int error)
{
struct inode *inode = d_inode(nfs_req_openctx(req)->dentry);
+ struct page *page = req->wb_page;
dprintk("NFS: read done (%s/%llu %d@%lld)\n", inode->i_sb->s_id,
(unsigned long long)NFS_FILEID(inode), req->wb_bytes,
(long long)req_offset(req));
+ if (nfs_error_is_fatal_on_server(error) && error != -ETIMEDOUT)
+ SetPageError(page);
if (nfs_page_group_sync_on_bit(req, PG_UNLOCKPAGE)) {
- if (PageUptodate(req->wb_page))
- nfs_readpage_to_fscache(inode, req->wb_page, 0);
+ struct address_space *mapping = page_file_mapping(page);
- unlock_page(req->wb_page);
+ if (PageUptodate(page))
+ nfs_readpage_to_fscache(inode, page, 0);
+ else if (!PageError(page) && !PagePrivate(page))
+ generic_error_remove_page(mapping, page);
+ unlock_page(page);
}
nfs_release_request(req);
}
&nfs_async_read_completion_ops);
if (!nfs_pageio_add_request(&pgio, new)) {
nfs_list_remove_request(new);
- nfs_readpage_release(new);
+ nfs_readpage_release(new, pgio.pg_error);
}
nfs_pageio_complete(&pgio);
static void nfs_read_completion(struct nfs_pgio_header *hdr)
{
unsigned long bytes = 0;
+ int error;
if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
goto out;
zero_user_segment(page, start, end);
}
}
+ error = 0;
bytes += req->wb_bytes;
if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
if (bytes <= hdr->good_bytes)
nfs_page_group_set_uptodate(req);
+ else {
+ error = hdr->error;
+ xchg(&nfs_req_openctx(req)->error, error);
+ }
} else
nfs_page_group_set_uptodate(req);
nfs_list_remove_request(req);
- nfs_readpage_release(req);
+ nfs_readpage_release(req, error);
}
out:
hdr->release(hdr);
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);
- nfs_readpage_release(req);
+ nfs_readpage_release(req, error);
}
}
goto out;
}
+ xchg(&ctx->error, 0);
error = nfs_readpage_async(ctx, inode, page);
-
+ if (!error) {
+ error = wait_on_page_locked_killable(page);
+ if (!PageUptodate(page) && !error)
+ error = xchg(&ctx->error, 0);
+ }
out:
put_nfs_open_context(ctx);
return error;
zero_user_segment(page, len, PAGE_SIZE);
if (!nfs_pageio_add_request(desc->pgio, new)) {
nfs_list_remove_request(new);
- nfs_readpage_release(new);
error = desc->pgio->pg_error;
+ nfs_readpage_release(new, error);
goto out;
}
return 0;
data->acdirmin != nfss->acdirmin / HZ ||
data->acdirmax != nfss->acdirmax / HZ ||
data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) ||
+ (data->options & NFS_OPTION_FSCACHE) != (nfss->options & NFS_OPTION_FSCACHE) ||
data->nfs_server.port != nfss->port ||
data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen ||
!rpc_cmp_addr((struct sockaddr *)&data->nfs_server.address,
static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
static const struct nfs_rw_ops nfs_rw_write_ops;
+static void nfs_inode_remove_request(struct nfs_page *req);
static void nfs_clear_request_commit(struct nfs_page *req);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
struct inode *inode);
static void nfs_write_error(struct nfs_page *req, int error)
{
+ nfs_set_pageerror(page_file_mapping(req->wb_page));
nfs_mapping_set_error(req->wb_page, error);
+ nfs_inode_remove_request(req);
nfs_end_page_writeback(req);
nfs_release_request(req);
}
-static bool
-nfs_error_is_fatal_on_server(int err)
-{
- switch (err) {
- case 0:
- case -ERESTARTSYS:
- case -EINTR:
- return false;
- }
- return nfs_error_is_fatal(err);
-}
-
/*
* Find an associated nfs write request, and prepare to flush it out
* May return an error if the user signalled nfs_wait_on_request().
static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
struct page *page)
{
- struct address_space *mapping;
struct nfs_page *req;
int ret = 0;
WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
/* If there is a fatal error that covers this write, just exit */
- ret = 0;
- mapping = page_file_mapping(page);
- if (test_bit(AS_ENOSPC, &mapping->flags) ||
- test_bit(AS_EIO, &mapping->flags))
+ ret = pgio->pg_error;
+ if (nfs_error_is_fatal_on_server(ret))
goto out_launder;
+ ret = 0;
if (!nfs_pageio_add_request(pgio, req)) {
ret = pgio->pg_error;
/*
} else
ret = -EAGAIN;
nfs_redirty_request(req);
+ pgio->pg_error = 0;
} else
nfs_add_stats(page_file_mapping(page)->host,
NFSIOS_WRITEPAGES, 1);
ret = nfs_page_async_flush(pgio, page);
if (ret == -EAGAIN) {
redirty_page_for_writepage(wbc, page);
- ret = 0;
+ ret = AOP_WRITEPAGE_ACTIVATE;
}
return ret;
}
nfs_pageio_init_write(&pgio, inode, 0,
false, &nfs_async_write_completion_ops);
err = nfs_do_writepage(page, wbc, &pgio);
+ pgio.pg_error = 0;
nfs_pageio_complete(&pgio);
if (err < 0)
return err;
- if (pgio.pg_error < 0)
+ if (nfs_error_is_fatal(pgio.pg_error))
return pgio.pg_error;
return 0;
}
int ret;
ret = nfs_writepage_locked(page, wbc);
- unlock_page(page);
+ if (ret != AOP_WRITEPAGE_ACTIVATE)
+ unlock_page(page);
return ret;
}
int ret;
ret = nfs_do_writepage(page, wbc, data);
- unlock_page(page);
+ if (ret != AOP_WRITEPAGE_ACTIVATE)
+ unlock_page(page);
return ret;
}
&nfs_async_write_completion_ops);
pgio.pg_io_completion = ioc;
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
+ pgio.pg_error = 0;
nfs_pageio_complete(&pgio);
nfs_io_completion_put(ioc);
if (err < 0)
goto out_err;
err = pgio.pg_error;
- if (err < 0)
+ if (nfs_error_is_fatal(err))
goto out_err;
return 0;
out_err:
*/
static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
{
- struct nfsd_net *nn = v;
+ struct nfsd_net *nn = m->private;
seq_printf(m, "max entries: %u\n", nn->max_drc_entries);
seq_printf(m, "num entries: %u\n",
return inode;
}
-static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl)
{
struct inode *inode;
inode = nfsd_get_inode(dir->i_sb, mode);
if (!inode)
return -ENOMEM;
+ if (ncl) {
+ inode->i_private = ncl;
+ kref_get(&ncl->cl_ref);
+ }
d_add(dentry, inode);
inc_nlink(dir);
fsnotify_mkdir(dir, dentry);
dentry = d_alloc_name(parent, name);
if (!dentry)
goto out_err;
- ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600);
+ ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl);
if (ret)
goto out_err;
- if (ncl) {
- d_inode(dentry)->i_private = ncl;
- kref_get(&ncl->cl_ref);
- }
out:
inode_unlock(dir);
return dentry;
out_err:
+ dput(dentry);
dentry = ERR_PTR(ret);
goto out;
}
struct nfsdfs_client *ncl = inode->i_private;
inode->i_private = NULL;
- synchronize_rcu();
kref_put(&ncl->cl_ref, ncl->cl_release);
}
-
static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode)
{
struct nfsdfs_client *nc = inode->i_private;
{
struct nfsdfs_client *nc;
- rcu_read_lock();
+ inode_lock_shared(inode);
nc = __get_nfsdfs_client(inode);
- rcu_read_unlock();
+ inode_unlock_shared(inode);
return nc;
}
/* from __rpc_unlink */
u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
int low_bucket = 0, bucket, high_bucket;
struct ocfs2_xattr_bucket *search;
- u32 last_hash;
u64 blkno, lower_blkno = 0;
search = ocfs2_xattr_bucket_new(inode);
if (xh->xh_count)
xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1];
- last_hash = le32_to_cpu(xe->xe_name_hash);
-
/* record lower_blkno which may be the insert place. */
lower_blkno = blkno;
override_cred->cap_permitted;
}
+ /*
+ * The new set of credentials can *only* be used in
+ * task-synchronous circumstances, and does not need
+ * RCU freeing, unless somebody then takes a separate
+ * reference to it.
+ *
+ * NOTE! This is _only_ true because this credential
+ * is used purely for override_creds() that installs
+ * it as the subjective cred. Other threads will be
+ * accessing ->real_cred, not the subjective cred.
+ *
+ * If somebody _does_ make a copy of this (using the
+ * 'get_current_cred()' function), that will clear the
+ * non_rcu field, because now that other user may be
+ * expecting RCU freeing. But normal thread-synchronous
+ * cred accesses will keep things non-RCY.
+ */
+ override_cred->non_rcu = 1;
+
old_cred = override_creds(override_cred);
retry:
res = user_path_at(dfd, filename, lookup_flags, &path);
return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL;
}
-/*
- * Read a page's worth of file data into the page cache. Return the page
- * locked.
- */
+/* Read a page's worth of file data into the page cache. */
static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)
{
struct page *page;
put_page(page);
return ERR_PTR(-EIO);
}
- lock_page(page);
return page;
}
+/*
+ * Lock two pages, ensuring that we lock in offset order if the pages are from
+ * the same file.
+ */
+static void vfs_lock_two_pages(struct page *page1, struct page *page2)
+{
+ /* Always lock in order of increasing index. */
+ if (page1->index > page2->index)
+ swap(page1, page2);
+
+ lock_page(page1);
+ if (page1 != page2)
+ lock_page(page2);
+}
+
+/* Unlock two pages, being careful not to unlock the same page twice. */
+static void vfs_unlock_two_pages(struct page *page1, struct page *page2)
+{
+ unlock_page(page1);
+ if (page1 != page2)
+ unlock_page(page2);
+}
+
/*
* Compare extents of two files to see if they are the same.
* Caller must have locked both inodes to prevent write races.
dest_page = vfs_dedupe_get_page(dest, destoff);
if (IS_ERR(dest_page)) {
error = PTR_ERR(dest_page);
- unlock_page(src_page);
put_page(src_page);
goto out_error;
}
+
+ vfs_lock_two_pages(src_page, dest_page);
+
+ /*
+ * Now that we've locked both pages, make sure they're still
+ * mapped to the file data we're interested in. If not,
+ * someone is invalidating pages on us and we lose.
+ */
+ if (!PageUptodate(src_page) || !PageUptodate(dest_page) ||
+ src_page->mapping != src->i_mapping ||
+ dest_page->mapping != dest->i_mapping) {
+ same = false;
+ goto unlock;
+ }
+
src_addr = kmap_atomic(src_page);
dest_addr = kmap_atomic(dest_page);
kunmap_atomic(dest_addr);
kunmap_atomic(src_addr);
- unlock_page(dest_page);
- unlock_page(src_page);
+unlock:
+ vfs_unlock_two_pages(src_page, dest_page);
put_page(dest_page);
put_page(src_page);
}
if (seq_has_overflowed(m))
goto Eoverflow;
+ p = m->op->next(m, p, &m->index);
if (pos + m->count > offset) {
m->from = offset - pos;
m->count -= m->from;
}
pos += m->count;
m->count = 0;
- p = m->op->next(m, p, &m->index);
if (pos == offset)
break;
}
bool mount_capable(struct fs_context *fc)
{
- struct user_namespace *user_ns = fc->global ? &init_user_ns
- : fc->user_ns;
-
if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT))
return capable(CAP_SYS_ADMIN);
else
- return ns_capable(user_ns, CAP_SYS_ADMIN);
+ return ns_capable(fc->user_ns, CAP_SYS_ADMIN);
}
/**
static void shrink_liability(struct ubifs_info *c, int nr_to_write)
{
down_read(&c->vfs_sb->s_umount);
- writeback_inodes_sb(c->vfs_sb, WB_REASON_FS_FREE_SPACE);
+ writeback_inodes_sb_nr(c->vfs_sb, nr_to_write, WB_REASON_FS_FREE_SPACE);
up_read(&c->vfs_sb->s_umount);
}
static void orphan_delete(struct ubifs_info *c, struct ubifs_orphan *orph)
{
if (orph->del) {
- spin_unlock(&c->orphan_lock);
dbg_gen("deleted twice ino %lu", orph->inum);
return;
}
orph->del = 1;
orph->dnext = c->orph_dnext;
c->orph_dnext = orph;
- spin_unlock(&c->orphan_lock);
dbg_gen("delete later ino %lu", orph->inum);
return;
}
c->max_bu_buf_len = UBIFS_MAX_BULK_READ * UBIFS_MAX_DATA_NODE_SZ;
if (c->max_bu_buf_len > c->leb_size)
c->max_bu_buf_len = c->leb_size;
+
+ /* Log is ready, preserve one LEB for commits. */
+ c->min_log_bytes = c->leb_size;
+
return 0;
}
/* len == 0 means wake all */
struct userfaultfd_wake_range range = { .len = 0, };
unsigned long new_flags;
+ bool still_valid;
WRITE_ONCE(ctx->released, true);
* taking the mmap_sem for writing.
*/
down_write(&mm->mmap_sem);
- if (!mmget_still_valid(mm))
- goto skip_mm;
+ still_valid = mmget_still_valid(mm);
prev = NULL;
for (vma = mm->mmap; vma; vma = vma->vm_next) {
cond_resched();
continue;
}
new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
- prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
- new_flags, vma->anon_vma,
- vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- NULL_VM_UFFD_CTX);
- if (prev)
- vma = prev;
- else
- prev = vma;
+ if (still_valid) {
+ prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
+ new_flags, vma->anon_vma,
+ vma->vm_file, vma->vm_pgoff,
+ vma_policy(vma),
+ NULL_VM_UFFD_CTX);
+ if (prev)
+ vma = prev;
+ else
+ prev = vma;
+ }
vma->vm_flags = new_flags;
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
-skip_mm:
up_write(&mm->mmap_sem);
mmput(mm);
wakeup:
XFS_STATS_INC(mp, xs_blk_mapr);
ifp = XFS_IFORK_PTR(ip, whichfork);
+ if (!ifp) {
+ /* No CoW fork? Return a hole. */
+ if (whichfork == XFS_COW_FORK) {
+ mval->br_startoff = bno;
+ mval->br_startblock = HOLESTARTBLOCK;
+ mval->br_blockcount = len;
+ mval->br_state = XFS_EXT_NORM;
+ *nmap = 1;
+ return 0;
+ }
- /* No CoW fork? Return a hole. */
- if (whichfork == XFS_COW_FORK && !ifp) {
- mval->br_startoff = bno;
- mval->br_startblock = HOLESTARTBLOCK;
- mval->br_blockcount = len;
- mval->br_state = XFS_EXT_NORM;
- *nmap = 1;
- return 0;
+ /*
+ * A missing attr ifork implies that the inode says we're in
+ * extents or btree format but failed to pass the inode fork
+ * verifier while trying to load it. Treat that as a file
+ * corruption too.
+ */
+#ifdef DEBUG
+ xfs_alert(mp, "%s: inode %llu missing fork %d",
+ __func__, ip->i_ino, whichfork);
+#endif /* DEBUG */
+ return -EFSCORRUPTED;
}
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
ASSERT(state->path.active == 0);
oldblk = &state->path.blk[0];
error = xfs_da3_root_split(state, oldblk, addblk);
- if (error) {
- addblk->bp = NULL;
- return error; /* GROT: dir is inconsistent */
- }
+ if (error)
+ goto out;
/*
* Update pointers to the node which used to be block 0 and just got
*/
node = oldblk->bp->b_addr;
if (node->hdr.info.forw) {
- ASSERT(be32_to_cpu(node->hdr.info.forw) == addblk->blkno);
+ if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
node = addblk->bp->b_addr;
node->hdr.info.back = cpu_to_be32(oldblk->blkno);
xfs_trans_log_buf(state->args->trans, addblk->bp,
}
node = oldblk->bp->b_addr;
if (node->hdr.info.back) {
- ASSERT(be32_to_cpu(node->hdr.info.back) == addblk->blkno);
+ if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
node = addblk->bp->b_addr;
node->hdr.info.forw = cpu_to_be32(oldblk->blkno);
xfs_trans_log_buf(state->args->trans, addblk->bp,
XFS_DA_LOGRANGE(node, &node->hdr.info,
sizeof(node->hdr.info)));
}
+out:
addblk->bp = NULL;
- return 0;
+ return error;
}
/*
ents = dp->d_ops->leaf_ents_p(leaf);
xfs_dir3_leaf_check(dp, bp);
- ASSERT(leafhdr.count > 0);
+ if (leafhdr.count <= 0)
+ return -EFSCORRUPTED;
/*
* Look up the hash value in the leaf entries.
/* Compare upper level pointer to sibling pointer. */
if (ds->state->altpath.blk[level].blkno != sibling)
xchk_da_set_corrupt(ds, level);
- xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp);
+ if (ds->state->altpath.blk[level].bp) {
+ xfs_trans_brelse(ds->dargs.trans,
+ ds->state->altpath.blk[level].bp);
+ ds->state->altpath.blk[level].bp = NULL;
+ }
out:
return error;
}
struct inode *inode = file_inode(filp);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
- void __user *arg = (void __user *)p;
+ void __user *arg = compat_ptr(p);
int error;
trace_xfs_file_compat_ioctl(ip);
switch (cmd) {
- /* No size or alignment issues on any arch */
- case XFS_IOC_DIOINFO:
- case XFS_IOC_FSGEOMETRY_V4:
- case XFS_IOC_FSGEOMETRY:
- case XFS_IOC_AG_GEOMETRY:
- case XFS_IOC_FSGETXATTR:
- case XFS_IOC_FSSETXATTR:
- case XFS_IOC_FSGETXATTRA:
- case XFS_IOC_FSSETDM:
- case XFS_IOC_GETBMAP:
- case XFS_IOC_GETBMAPA:
- case XFS_IOC_GETBMAPX:
- case XFS_IOC_FSCOUNTS:
- case XFS_IOC_SET_RESBLKS:
- case XFS_IOC_GET_RESBLKS:
- case XFS_IOC_FSGROWFSLOG:
- case XFS_IOC_GOINGDOWN:
- case XFS_IOC_ERROR_INJECTION:
- case XFS_IOC_ERROR_CLEARALL:
- case FS_IOC_GETFSMAP:
- case XFS_IOC_SCRUB_METADATA:
- case XFS_IOC_BULKSTAT:
- case XFS_IOC_INUMBERS:
- return xfs_file_ioctl(filp, cmd, p);
-#if !defined(BROKEN_X86_ALIGNMENT) || defined(CONFIG_X86_X32)
- /*
- * These are handled fine if no alignment issues. To support x32
- * which uses native 64-bit alignment we must emit these cases in
- * addition to the ia-32 compat set below.
- */
- case XFS_IOC_ALLOCSP:
- case XFS_IOC_FREESP:
- case XFS_IOC_RESVSP:
- case XFS_IOC_UNRESVSP:
- case XFS_IOC_ALLOCSP64:
- case XFS_IOC_FREESP64:
- case XFS_IOC_RESVSP64:
- case XFS_IOC_UNRESVSP64:
- case XFS_IOC_FSGEOMETRY_V1:
- case XFS_IOC_FSGROWFSDATA:
- case XFS_IOC_FSGROWFSRT:
- case XFS_IOC_ZERO_RANGE:
-#ifdef CONFIG_X86_X32
- /*
- * x32 special: this gets a different cmd number from the ia-32 compat
- * case below; the associated data will match native 64-bit alignment.
- */
- case XFS_IOC_SWAPEXT:
-#endif
- return xfs_file_ioctl(filp, cmd, p);
-#endif
#if defined(BROKEN_X86_ALIGNMENT)
case XFS_IOC_ALLOCSP_32:
case XFS_IOC_FREESP_32:
case XFS_IOC_FSSETDM_BY_HANDLE_32:
return xfs_compat_fssetdm_by_handle(filp, arg);
default:
- return -ENOIOCTLCMD;
+ /* try the native version */
+ return xfs_file_ioctl(filp, cmd, (unsigned long)arg);
}
}
out_cancel:
xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
struct xfs_bstat *bs1,
const struct xfs_bulkstat *bstat)
{
+ /* memset is needed here because of padding holes in the structure. */
memset(bs1, 0, sizeof(struct xfs_bstat));
bs1->bs_ino = bstat->bs_ino;
bs1->bs_mode = bstat->bs_mode;
struct xfs_inogrp *ig1,
const struct xfs_inumbers *ig)
{
+ /* memset is needed here because of padding holes in the structure. */
+ memset(ig1, 0, sizeof(struct xfs_inogrp));
ig1->xi_startino = ig->xi_startino;
ig1->xi_alloccount = ig->xi_alloccount;
ig1->xi_allocmask = ig->xi_allocmask;
ASSERT(*ticp == NULL);
tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent,
- KM_SLEEP | KM_MAYFAIL);
- if (!tic)
- return -ENOMEM;
-
+ KM_SLEEP);
*ticp = tic;
xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt
struct xfs_inode *ip = XFS_I(inode);
int error;
- while ((error = break_layout(inode, false) == -EWOULDBLOCK)) {
+ while ((error = break_layout(inode, false)) == -EWOULDBLOCK) {
xfs_iunlock(ip, *iolock);
*did_unlock = true;
error = break_layout(inode, true);
}
/*
- * Grab the exclusive iolock for a data copy from src to dest, making
- * sure to abide vfs locking order (lowest pointer value goes first) and
- * breaking the pnfs layout leases on dest before proceeding. The loop
- * is needed because we cannot call the blocking break_layout() with the
- * src iolock held, and therefore have to back out both locks.
+ * Grab the exclusive iolock for a data copy from src to dest, making sure to
+ * abide vfs locking order (lowest pointer value goes first) and breaking the
+ * layout leases before proceeding. The loop is needed because we cannot call
+ * the blocking break_layout() with the iolocks held, and therefore have to
+ * back out both locks.
*/
static int
xfs_iolock_two_inodes_and_break_layout(
{
int error;
-retry:
- if (src < dest) {
- inode_lock_shared(src);
- inode_lock_nested(dest, I_MUTEX_NONDIR2);
- } else {
- /* src >= dest */
- inode_lock(dest);
- }
+ if (src > dest)
+ swap(src, dest);
- error = break_layout(dest, false);
- if (error == -EWOULDBLOCK) {
- inode_unlock(dest);
- if (src < dest)
- inode_unlock_shared(src);
+retry:
+ /* Wait to break both inodes' layouts before we start locking. */
+ error = break_layout(src, true);
+ if (error)
+ return error;
+ if (src != dest) {
error = break_layout(dest, true);
if (error)
return error;
- goto retry;
}
+
+ /* Lock one inode and make sure nobody got in and leased it. */
+ inode_lock(src);
+ error = break_layout(src, false);
if (error) {
+ inode_unlock(src);
+ if (error == -EWOULDBLOCK)
+ goto retry;
+ return error;
+ }
+
+ if (src == dest)
+ return 0;
+
+ /* Lock the other inode and make sure nobody got in and leased it. */
+ inode_lock_nested(dest, I_MUTEX_NONDIR2);
+ error = break_layout(dest, false);
+ if (error) {
+ inode_unlock(src);
inode_unlock(dest);
- if (src < dest)
- inode_unlock_shared(src);
+ if (error == -EWOULDBLOCK)
+ goto retry;
return error;
}
- if (src > dest)
- inode_lock_shared_nested(src, I_MUTEX_NONDIR2);
+
return 0;
}
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
if (!same_inode)
- xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
+ xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
inode_unlock(inode_out);
if (!same_inode)
- inode_unlock_shared(inode_in);
+ inode_unlock(inode_in);
}
/*
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
- xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
+ xfs_lock_two_inodes(src, XFS_MMAPLOCK_EXCL, dest,
XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
#define p4d_alloc(mm, pgd, address) (pgd)
#define p4d_offset(pgd, start) (pgd)
-#define p4d_none(p4d) 0
-#define p4d_bad(p4d) 0
-#define p4d_present(p4d) 1
+
+#ifndef __ASSEMBLY__
+static inline int p4d_none(p4d_t p4d)
+{
+ return 0;
+}
+
+static inline int p4d_bad(p4d_t p4d)
+{
+ return 0;
+}
+
+static inline int p4d_present(p4d_t p4d)
+{
+ return 1;
+}
+#endif
+
#define p4d_ERROR(p4d) do { } while (0)
#define p4d_clear(p4d) pgd_clear(p4d)
#define p4d_val(p4d) pgd_val(p4d)
static inline int
arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
{
- int oldval = 0, ret;
-
- pagefault_disable();
-
- switch (op) {
- case FUTEX_OP_SET:
- case FUTEX_OP_ADD:
- case FUTEX_OP_OR:
- case FUTEX_OP_ANDN:
- case FUTEX_OP_XOR:
- default:
- ret = -ENOSYS;
- }
-
- pagefault_enable();
-
- if (!ret)
- *oval = oldval;
-
- return ret;
+ return -ENOSYS;
}
static inline int
#include <linux/compiler.h>
#include <linux/log2.h>
-/*
- * Runtime evaluation of get_order()
- */
-static inline __attribute_const__
-int __get_order(unsigned long size)
-{
- int order;
-
- size--;
- size >>= PAGE_SHIFT;
-#if BITS_PER_LONG == 32
- order = fls(size);
-#else
- order = fls64(size);
-#endif
- return order;
-}
-
/**
* get_order - Determine the allocation order of a memory size
* @size: The size for which to get the order
* to hold an object of the specified size.
*
* The result is undefined if the size is 0.
- *
- * This function may be used to initialise variables with compile time
- * evaluations of constants.
*/
-#define get_order(n) \
-( \
- __builtin_constant_p(n) ? ( \
- ((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT : \
- (((n) < (1UL << PAGE_SHIFT)) ? 0 : \
- ilog2((n) - 1) - PAGE_SHIFT + 1) \
- ) : \
- __get_order(n) \
-)
+static inline __attribute_const__ int get_order(unsigned long size)
+{
+ if (__builtin_constant_p(size)) {
+ if (!size)
+ return BITS_PER_LONG - PAGE_SHIFT;
+
+ if (size < (1UL << PAGE_SHIFT))
+ return 0;
+
+ return ilog2((size) - 1) - PAGE_SHIFT + 1;
+ }
+
+ size--;
+ size >>= PAGE_SHIFT;
+#if BITS_PER_LONG == 32
+ return fls(size);
+#else
+ return fls64(size);
+#endif
+}
#endif /* __ASSEMBLY__ */
struct drm_client_buffer *
drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format);
void drm_client_framebuffer_delete(struct drm_client_buffer *buffer);
+void *drm_client_buffer_vmap(struct drm_client_buffer *buffer);
+void drm_client_buffer_vunmap(struct drm_client_buffer *buffer);
int drm_client_modeset_create(struct drm_client_dev *client);
void drm_client_modeset_free(struct drm_client_dev *client);
/* dumb ioctl parameters */
uint32_t preferred_depth, prefer_shadow;
+ /**
+ * @prefer_shadow_fbdev:
+ *
+ * Hint to framebuffer emulation to prefer shadow-fb rendering.
+ */
+ bool prefer_shadow_fbdev;
+
/**
* @quirk_addfb_prefer_xbgr_30bpp:
*
u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu);
+void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val);
{
return 0;
}
+static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {}
static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {}
void kvm_vgic_load(struct kvm_vcpu *vcpu);
void kvm_vgic_put(struct kvm_vcpu *vcpu);
+void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) ((k)->arch.vgic.initialized)
extern struct blkcg blkcg_root;
extern struct cgroup_subsys_state * const blkcg_root_css;
+extern bool blkcg_debug_stats;
struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
struct request_queue *q, bool update_hint);
enum ccp_aes_mode mode;
enum ccp_aes_action action;
+ u32 authsize;
+
struct scatterlist *key;
u32 key_len; /* In bytes */
static inline void ceph_buffer_put(struct ceph_buffer *b)
{
- kref_put(&b->kref, ceph_buffer_release);
+ if (b)
+ kref_put(&b->kref, ceph_buffer_release);
}
extern int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end);
/**
* devm_clk_bulk_get_optional - managed get multiple optional consumer clocks
* @dev: device for clock "consumer"
+ * @num_clks: the number of clk_bulk_data
* @clks: pointer to the clk_bulk_data table of consumer
*
* Behaves the same as devm_clk_bulk_get() except where there is no clock
long ______r; \
static struct ftrace_likely_data \
__aligned(4) \
- __section("_ftrace_annotated_branch") \
+ __section(_ftrace_annotated_branch) \
______f = { \
.data.func = __func__, \
.data.file = __FILE__, \
#define __trace_if_value(cond) ({ \
static struct ftrace_branch_data \
__aligned(4) \
- __section("_ftrace_branch") \
+ __section(_ftrace_branch) \
__if_trace = { \
.func = __func__, \
.file = __FILE__, \
".popsection\n\t"
/* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table")
+#define __annotate_jump_table __section(.rodata..c_jump_table)
#else
#define annotate_reachable()
* visible to the compiler.
*/
#define __ADDRESSABLE(sym) \
- static void * __section(".discard.addressable") __used \
+ static void * __section(.discard.addressable) __used \
__PASTE(__addressable_##sym, __LINE__) = (void *)&sym;
/**
u32 seq, groups;
struct sock *nls;
- void (*input) (struct sk_buff *skb);
struct cn_queue_dev *cbdev;
};
struct user_struct *user; /* real user ID subscription */
struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */
struct group_info *group_info; /* supplementary groups for euid/fsgid */
- struct rcu_head rcu; /* RCU deletion hook */
+ /* RCU deletion */
+ union {
+ int non_rcu; /* Can we skip RCU deletion? */
+ struct rcu_head rcu; /* RCU deletion hook */
+ };
} __randomize_layout;
extern void __put_cred(struct cred *);
if (!cred)
return cred;
validate_creds(cred);
+ nonconst_cred->non_rcu = 0;
return get_new_cred(nonconst_cred);
}
if (!atomic_inc_not_zero(&nonconst_cred->usage))
return NULL;
validate_creds(cred);
+ nonconst_cred->non_rcu = 0;
return cred;
}
* This identifies the device type and carries type-specific
* information.
* @mutex: Mutex to synchronize calls to its driver.
+ * @lockdep_mutex: An optional debug lock that a subsystem can use as a
+ * peer lock to gain localized lockdep coverage of the device_lock.
* @bus: Type of bus device is on.
* @driver: Which driver has allocated this
* @platform_data: Platform data specific to the device.
core doesn't touch it */
void *driver_data; /* Driver data, set and get with
dev_set_drvdata/dev_get_drvdata */
+#ifdef CONFIG_PROVE_LOCKING
+ struct mutex lockdep_mutex;
+#endif
struct mutex mutex; /* mutex to synchronize calls to
* its driver.
*/
*/
extern struct device *get_device(struct device *dev);
extern void put_device(struct device *dev);
+extern bool kill_device(struct device *dev);
#ifdef CONFIG_DEVTMPFS
extern int devtmpfs_create_node(struct device *dev);
/* Net DIM */
-/*
- * Net DIM profiles:
- * There are different set of profiles for each CQ period mode.
- * There are different set of profiles for RX/TX CQs.
- * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES
- */
-#define NET_DIM_PARAMS_NUM_PROFILES 5
-#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256
-#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128
-#define NET_DIM_DEF_PROFILE_CQE 1
-#define NET_DIM_DEF_PROFILE_EQE 1
-
-#define NET_DIM_RX_EQE_PROFILES { \
- {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
-}
-
-#define NET_DIM_RX_CQE_PROFILES { \
- {2, 256}, \
- {8, 128}, \
- {16, 64}, \
- {32, 64}, \
- {64, 64} \
-}
-
-#define NET_DIM_TX_EQE_PROFILES { \
- {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
- {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \
-}
-
-#define NET_DIM_TX_CQE_PROFILES { \
- {5, 128}, \
- {8, 64}, \
- {16, 32}, \
- {32, 32}, \
- {64, 32} \
-}
-
-static const struct dim_cq_moder
-rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
- NET_DIM_RX_EQE_PROFILES,
- NET_DIM_RX_CQE_PROFILES,
-};
-
-static const struct dim_cq_moder
-tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
- NET_DIM_TX_EQE_PROFILES,
- NET_DIM_TX_CQE_PROFILES,
-};
-
/**
* net_dim_get_rx_moderation - provide a CQ moderation object for the given RX profile
* @cq_period_mode: CQ period mode
static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
gfp_t gfp)
{
- int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
- size_t align = get_order(PAGE_ALIGN(size));
-
- return alloc_pages_node(node, gfp, align);
+ return NULL;
}
static inline void dma_free_contiguous(struct device *dev, struct page *page,
*/
static inline bool dma_addressing_limited(struct device *dev)
{
- return min_not_zero(*dev->dma_mask, dev->bus_dma_mask) <
- dma_get_required_mask(dev);
+ return min_not_zero(dma_get_mask(dev), dev->bus_dma_mask) <
+ dma_get_required_mask(dev);
}
#ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
dma_addr_t dma_addr, unsigned long attrs);
long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
dma_addr_t dma_addr);
-
-#ifdef CONFIG_ARCH_HAS_DMA_MMAP_PGPROT
pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
unsigned long attrs);
+
+#ifdef CONFIG_MMU
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs);
#else
-# define arch_dma_mmap_pgprot(dev, prot, attrs) pgprot_noncached(prot)
-#endif
+static inline pgprot_t dma_pgprot(struct device *dev, pgprot_t prot,
+ unsigned long attrs)
+{
+ return prot; /* no protection bits supported without page tables */
+}
+#endif /* CONFIG_MMU */
#ifdef CONFIG_DMA_NONCOHERENT_CACHE_SYNC
void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
bool (*has_work)(struct blk_mq_hw_ctx *);
void (*completed_request)(struct request *, u64);
- void (*started_request)(struct request *);
void (*requeue_request)(struct request *);
struct request *(*former_request)(struct request_queue *, struct request *);
struct request *(*next_request)(struct request_queue *, struct request *);
#include <net/sch_generic.h>
+#include <asm/byteorder.h>
#include <uapi/linux/filter.h>
#include <uapi/linux/bpf.h>
return size <= size_default && (size & (size - 1)) == 0;
}
+static inline u8
+bpf_ctx_narrow_load_shift(u32 off, u32 size, u32 size_default)
+{
+ u8 load_off = off & (size_default - 1);
+
+#ifdef __LITTLE_ENDIAN
+ return load_off * 8;
+#else
+ return (size_default - (load_off + size)) * 8;
+#endif
+}
+
#define bpf_ctx_wide_access_ok(off, size, type, field) \
(size == sizeof(__u64) && \
off >= offsetof(type, field) && \
void *holder);
extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode,
void *holder);
+extern struct block_device *bd_start_claiming(struct block_device *bdev,
+ void *holder);
+extern void bd_finish_claiming(struct block_device *bdev,
+ struct block_device *whole, void *holder);
+extern void bd_abort_claiming(struct block_device *bdev,
+ struct block_device *whole, void *holder);
extern void blkdev_put(struct block_device *bdev, fmode_t mode);
extern int __blkdev_reread_part(struct block_device *bdev);
extern int blkdev_reread_part(struct block_device *bdev);
}
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
struct vm_area_struct *vma, unsigned long addr,
- int node, bool hugepage);
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
- alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true)
+ int node);
#else
#define alloc_pages(gfp_mask, order) \
alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
- alloc_pages(gfp_mask, order)
-#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
+#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\
alloc_pages(gfp_mask, order)
#endif
#define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
#define alloc_page_vma(gfp_mask, vma, addr) \
- alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false)
+ alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id())
#define alloc_page_vma_node(gfp_mask, vma, addr, node) \
- alloc_pages_vma(gfp_mask, 0, vma, addr, node, false)
+ alloc_pages_vma(gfp_mask, 0, vma, addr, node)
extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
extern unsigned long get_zeroed_page(gfp_t gfp_mask);
return -EINVAL;
}
-static inline int
-gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name,
- unsigned int gpio_offset, unsigned int pin_offset,
- unsigned int npins)
-{
- WARN_ON(1);
- return -EINVAL;
-}
-
-static inline int
-gpiochip_add_pingroup_range(struct gpio_chip *chip,
- struct pinctrl_dev *pctldev,
- unsigned int gpio_offset, const char *pin_group)
-{
- WARN_ON(1);
- return -EINVAL;
-}
-
-static inline void
-gpiochip_remove_pin_ranges(struct gpio_chip *chip)
-{
- WARN_ON(1);
-}
-
static inline int devm_gpio_request(struct device *dev, unsigned gpio,
const char *label)
{
might_sleep();
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline void devm_gpiod_unhinge(struct device *dev,
might_sleep();
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline void gpiod_put_array(struct gpio_descs *descs)
might_sleep();
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(descs);
}
static inline struct gpio_desc *__must_check
might_sleep();
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline void devm_gpiod_put_array(struct device *dev,
might_sleep();
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(descs);
}
static inline int gpiod_get_direction(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -ENOSYS;
}
static inline int gpiod_direction_input(struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -ENOSYS;
}
static inline int gpiod_direction_output(struct gpio_desc *desc, int value)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -ENOSYS;
}
static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -ENOSYS;
}
static inline int gpiod_get_value(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return 0;
}
static inline int gpiod_get_array_value(unsigned int array_size,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline void gpiod_set_value(struct gpio_desc *desc, int value)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline int gpiod_set_array_value(unsigned int array_size,
struct gpio_desc **desc_array,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline int gpiod_get_raw_value(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return 0;
}
static inline int gpiod_get_raw_array_value(unsigned int array_size,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline int gpiod_set_raw_array_value(unsigned int array_size,
struct gpio_desc **desc_array,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline int gpiod_get_value_cansleep(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return 0;
}
static inline int gpiod_get_array_value_cansleep(unsigned int array_size,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline int gpiod_set_array_value_cansleep(unsigned int array_size,
struct gpio_desc **desc_array,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return 0;
}
static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc,
int value)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
}
static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size,
struct gpio_desc **desc_array,
unsigned long *value_bitmap)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc_array);
return 0;
}
static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -ENOSYS;
}
static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -ENOSYS;
}
static inline int gpiod_is_active_low(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return 0;
}
static inline int gpiod_cansleep(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return 0;
}
static inline int gpiod_to_irq(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -EINVAL;
}
const char *name)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -EINVAL;
}
static inline int desc_to_gpio(const struct gpio_desc *desc)
{
/* GPIO can never have been requested */
- WARN_ON(1);
+ WARN_ON(desc);
return -EINVAL;
}
*/
#define HMM_RANGE_DEFAULT_TIMEOUT 1000
-/* This is a temporary helper to avoid merge conflict between trees. */
-static inline bool hmm_vma_range_done(struct hmm_range *range)
-{
- bool ret = hmm_range_valid(range);
-
- hmm_range_unregister(range);
- return ret;
-}
-
-/* This is a temporary helper to avoid merge conflict between trees. */
-static inline int hmm_vma_fault(struct hmm_mirror *mirror,
- struct hmm_range *range, bool block)
-{
- long ret;
-
- /*
- * With the old API the driver must set each individual entries with
- * the requested flags (valid, write, ...). So here we set the mask to
- * keep intact the entries provided by the driver and zero out the
- * default_flags.
- */
- range->default_flags = 0;
- range->pfn_flags_mask = -1UL;
-
- ret = hmm_range_register(range, mirror,
- range->start, range->end,
- PAGE_SHIFT);
- if (ret)
- return (int)ret;
-
- if (!hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT)) {
- /*
- * The mmap_sem was taken by driver we release it here and
- * returns -EAGAIN which correspond to mmap_sem have been
- * drop in the old API.
- */
- up_read(&range->vma->vm_mm->mmap_sem);
- return -EAGAIN;
- }
-
- ret = hmm_range_fault(range, block);
- if (ret <= 0) {
- if (ret == -EBUSY || !ret) {
- /* Same as above, drop mmap_sem to match old API. */
- up_read(&range->vma->vm_mm->mmap_sem);
- ret = -EBUSY;
- } else if (ret == -EAGAIN)
- ret = -EBUSY;
- hmm_range_unregister(range);
- return ret;
- }
- return 0;
-}
-
/* Below are for HMM internal use only! Not to be used by device driver! */
static inline void hmm_mm_init(struct mm_struct *mm)
{
extern void unregister_pppox_proto(int proto_num);
extern void pppox_unbind_sock(struct sock *sk);/* delete ppp-channel binding */
extern int pppox_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+extern int pppox_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg);
+
+#define PPPOEIOCSFWD32 _IOW(0xB1 ,0, compat_size_t)
/* PPPoX socket states */
enum {
__be16 csum_start_offset;
#if defined(__LITTLE_ENDIAN_BITFIELD)
u16 csum_insert_offset:14;
- u16 udp_ip4_ind:1;
+ u16 udp_ind:1;
u16 csum_enabled:1;
#elif defined (__BIG_ENDIAN_BITFIELD)
u16 csum_enabled:1;
- u16 udp_ip4_ind:1;
+ u16 udp_ind:1;
u16 csum_insert_offset:14;
#else
#error "Please fix <asm/byteorder.h>"
{ "ELAN0618", 0 },
{ "ELAN0619", 0 },
{ "ELAN061A", 0 },
- { "ELAN061B", 0 },
+/* { "ELAN061B", 0 }, not working on the Lenovo Legion Y7000 */
{ "ELAN061C", 0 },
{ "ELAN061D", 0 },
{ "ELAN061E", 0 },
#define QI_PC_PASID_SEL (QI_PC_TYPE | QI_PC_GRAN(1))
#define QI_EIOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK)
-#define QI_EIOTLB_GL(gl) (((u64)gl) << 7)
#define QI_EIOTLB_IH(ih) (((u64)ih) << 6)
#define QI_EIOTLB_AM(am) (((u64)am))
#define QI_EIOTLB_PASID(pasid) (((u64)pasid) << 32)
#define QI_RESP_INVALID 0x1
#define QI_RESP_FAILURE 0xf
-#define QI_GRAN_ALL_ALL 0
-#define QI_GRAN_NONG_ALL 1
#define QI_GRAN_NONG_PASID 2
#define QI_GRAN_PSI_PASID 3
void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
void init_iova_domain(struct iova_domain *iovad, unsigned long granule,
unsigned long start_pfn);
+bool has_iova_flush_queue(struct iova_domain *iovad);
int init_iova_flush_queue(struct iova_domain *iovad,
iova_flush_cb flush_cb, iova_entry_dtor entry_dtor);
struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
{
}
+static inline bool has_iova_flush_queue(struct iova_domain *iovad)
+{
+ return false;
+}
+
static inline int init_iova_flush_queue(struct iova_domain *iovad,
iova_flush_cb flush_cb,
iova_entry_dtor entry_dtor)
union {
struct {
#ifdef __LITTLE_ENDIAN /* Put desc_len at the LSB of x */
- u8 desc_len;
- char desc[sizeof(long) - 1]; /* First few chars of description */
+ u16 desc_len;
+ char desc[sizeof(long) - 2]; /* First few chars of description */
#else
- char desc[sizeof(long) - 1]; /* First few chars of description */
- u8 desc_len;
+ char desc[sizeof(long) - 2]; /* First few chars of description */
+ u16 desc_len;
#endif
};
unsigned long x;
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
-bool kvm_arch_has_vcpu_debugfs(void);
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu);
+#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
+void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu);
+#endif
int kvm_arch_hardware_enable(void);
void kvm_arch_hardware_disable(void);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
#ifndef __KVM_HAVE_ARCH_VM_ALLOC
/*
unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode,
resource_size_t hw_addr, resource_size_t size);
int logic_pio_register_range(struct logic_pio_hwaddr *newrange);
+void logic_pio_unregister_range(struct logic_pio_hwaddr *range);
resource_size_t logic_pio_to_hwaddr(unsigned long pio);
unsigned long logic_pio_trans_cpuaddr(resource_size_t hw_addr);
void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
int val);
+void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val);
static inline void mod_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx, int val)
mod_node_page_state(page_pgdat(page), idx, val);
}
+static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx,
+ int val)
+{
+ struct page *page = virt_to_head_page(p);
+
+ __mod_node_page_state(page_pgdat(page), idx, val);
+}
+
static inline
unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
gfp_t gfp_mask,
__mod_lruvec_page_state(page, idx, -1);
}
+static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx)
+{
+ __mod_lruvec_slab_state(p, idx, 1);
+}
+
+static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx)
+{
+ __mod_lruvec_slab_state(p, idx, -1);
+}
+
/* idx can be of type enum memcg_stat_item or node_stat_item */
static inline void inc_memcg_state(struct mem_cgroup *memcg,
int idx)
struct mempolicy *get_task_policy(struct task_struct *p);
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
unsigned long addr);
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+ unsigned long addr);
bool vma_policy_mof(struct vm_area_struct *vma);
extern void numa_default_policy(void);
};
enum {
- MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x20,
+ MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x1,
};
enum {
- MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x20,
+ MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x1,
};
enum {
struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
+u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter);
void mlx5_fc_query_cached(struct mlx5_fc *counter,
u64 *bytes, u64 *packets, u64 *lastuse);
int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
struct mlx5_ifc_cqc_bits cq_context;
- u8 reserved_at_280[0x40];
+ u8 reserved_at_280[0x60];
u8 cq_umem_valid[0x1];
- u8 reserved_at_2c1[0x5bf];
+ u8 reserved_at_2e1[0x1f];
+
+ u8 reserved_at_300[0x580];
u8 pas[0][0x40];
};
};
struct mlx5_ifc_tls_progress_params_bits {
- u8 valid[0x1];
- u8 reserved_at_1[0x7];
- u8 pd[0x18];
+ u8 reserved_at_0[0x8];
+ u8 tisn[0x18];
u8 next_record_tcp_sn[0x20];
/** @pgmap: Points to the hosting device page map. */
struct dev_pagemap *pgmap;
void *zone_device_data;
- unsigned long _zd_pad_1; /* uses mapping */
+ /*
+ * ZONE_DEVICE private pages are counted as being
+ * mapped so the next 3 words hold the mapping, index,
+ * and private fields from the source anonymous or
+ * page cache page while the page is migrated to device
+ * private memory.
+ * ZONE_DEVICE MEMORY_DEVICE_FS_DAX pages also
+ * use the mapping, index, and private fields when
+ * pmem backed DAX files are mapped.
+ */
};
/** @rcu_head: You can use this to free a page by RCU. */
NR_INACTIVE_FILE, /* " " " " " */
NR_ACTIVE_FILE, /* " " " " " */
NR_UNEVICTABLE, /* " " " " " */
- NR_SLAB_RECLAIMABLE,
- NR_SLAB_UNRECLAIMABLE,
+ NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */
+ NR_SLAB_UNRECLAIMABLE, /* and this one without looking at
+ * memcg_flush_percpu_vmstats() first. */
NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */
NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */
WORKINGSET_NODES,
/**
* struct wmi_device_id - WMI device identifier
* @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba
+ * @context: pointer to driver specific data
*/
struct wmi_device_id {
const char guid_string[UUID_STRING_LEN+1];
/* SPDX-License-Identifier: GPL-2.0-only */
/****************************************************************************
- * ip_conntrack_h323_asn1.h - BER and PER decoding library for H.323
- * conntrack/NAT module.
+ * BER and PER decoding library for H.323 conntrack/NAT module.
*
* Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net>
*
* Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net>
*/
+#ifndef _NF_CONNTRACK_H323_TYPES_H
+#define _NF_CONNTRACK_H323_TYPES_H
+
typedef struct TransportAddress_ipAddress { /* SEQUENCE */
int options; /* No use */
unsigned int ip;
InfoRequestResponse infoRequestResponse;
};
} RasMessage;
+
+#endif /* _NF_CONNTRACK_H323_TYPES_H */
}
/**
- * of_property_read_bool - Findfrom a property
+ * of_property_read_bool - Find a property
* @np: device node from which the property value is to be read.
* @propname: name of the property to be searched.
*
#endif /* CONFIG_SPARSEMEM */
+#ifndef BUILD_VDSO32_64
/*
* page->flags layout:
*
#define LAST_CPUPID_SHIFT 0
#endif
-#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
+#ifdef CONFIG_KASAN_SW_TAGS
+#define KASAN_TAG_WIDTH 8
+#else
+#define KASAN_TAG_WIDTH 0
+#endif
+
+#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT+KASAN_TAG_WIDTH \
+ <= BITS_PER_LONG - NR_PAGEFLAGS
#define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT
#else
#define LAST_CPUPID_WIDTH 0
#endif
-#ifdef CONFIG_KASAN_SW_TAGS
-#define KASAN_TAG_WIDTH 8
#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \
> BITS_PER_LONG - NR_PAGEFLAGS
-#error "KASAN: not enough bits in page flags for tag"
-#endif
-#else
-#define KASAN_TAG_WIDTH 0
+#error "Not enough bits in page flags"
#endif
/*
#define LAST_CPUPID_NOT_IN_PAGE_FLAGS
#endif
+#endif
#endif /* _LINUX_PAGE_FLAGS_LAYOUT */
PG_savepinned = PG_dirty,
/* Has a grant mapping of another (foreign) domain's page. */
PG_foreign = PG_owner_priv_1,
+ /* Remapped by swiotlb-xen. */
+ PG_xen_remapped = PG_owner_priv_1,
/* SLOB */
PG_slob_free = PG_private,
TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND)
PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND);
PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND);
+PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND)
+ TESTCLEARFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND)
PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
#ifdef CONFIG_PCIEASPM
bool pcie_aspm_support_enabled(void);
+bool pcie_aspm_enabled(struct pci_dev *pdev);
#else
static inline bool pcie_aspm_support_enabled(void) { return false; }
+static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; }
#endif
#ifdef CONFIG_PCIEAER
int genphy_c45_read_mdix(struct phy_device *phydev);
int genphy_c45_pma_read_abilities(struct phy_device *phydev);
int genphy_c45_read_status(struct phy_device *phydev);
+int genphy_c45_config_aneg(struct phy_device *phydev);
/* The gen10g_* functions are the old Clause 45 stub */
int gen10g_config_aneg(struct phy_device *phydev);
u64 last_sum_exec_runtime;
struct callback_head numa_work;
- struct numa_group *numa_group;
+ /*
+ * This pointer is only modified for current in syscall and
+ * pagefault context (and for tasks being destroyed), so it can be read
+ * from any of the following contexts:
+ * - RCU read-side critical section
+ * - current->numa_group from everywhere
+ * - task's runqueue locked, task not running
+ */
+ struct numa_group __rcu *numa_group;
/*
* numa_faults is an array split into four regions:
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
-extern void task_numa_free(struct task_struct *p);
+extern void task_numa_free(struct task_struct *p, bool final);
extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
int src_nid, int dst_cpu);
#else
static inline void set_numabalancing_state(bool enabled)
{
}
-static inline void task_numa_free(struct task_struct *p)
+static inline void task_numa_free(struct task_struct *p, bool final)
{
}
static inline bool should_numa_migrate_memory(struct task_struct *p,
extern void exit_signals(struct task_struct *tsk);
extern void kernel_sigaction(int, __sighandler_t);
+#define SIG_KTHREAD ((__force __sighandler_t)2)
+#define SIG_KTHREAD_KERNEL ((__force __sighandler_t)3)
+
static inline void allow_signal(int sig)
{
/*
* know it'll be handled, so that they don't get converted to
* SIGKILL or just silently dropped.
*/
- kernel_sigaction(sig, (__force __sighandler_t)2);
+ kernel_sigaction(sig, SIG_KTHREAD);
+}
+
+static inline void allow_kernel_signal(int sig)
+{
+ /*
+ * Kernel threads handle their own signals. Let the signal code
+ * know signals sent by the kernel will be handled, so that they
+ * don't get silently dropped.
+ */
+ kernel_sigaction(sig, SIG_KTHREAD_KERNEL);
}
static inline void disallow_signal(int sig)
to->l4_hash = from->l4_hash;
};
+static inline void skb_copy_decrypted(struct sk_buff *to,
+ const struct sk_buff *from)
+{
+#ifdef CONFIG_TLS_DEVICE
+ to->decrypted = from->decrypted;
+#endif
+}
+
#ifdef NET_SKBUFF_DATA_USES_OFFSET
static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
{
sk->sk_write_space = psock->saved_write_space;
if (psock->sk_proto) {
- sk->sk_prot = psock->sk_proto;
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ bool has_ulp = !!icsk->icsk_ulp_data;
+
+ if (has_ulp)
+ tcp_update_ulp(sk, psock->sk_proto);
+ else
+ sk->sk_prot = psock->sk_proto;
psock->sk_proto = NULL;
}
}
#define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */
#define MSG_EOF MSG_FIN
#define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
+#define MSG_SENDPAGE_DECRYPTED 0x100000 /* sendpage() internal : page may carry
+ * plain text and require encryption
+ */
#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */
#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
struct rpc_call_ops {
void (*rpc_call_prepare)(struct rpc_task *, void *);
- void (*rpc_call_prepare_transmit)(struct rpc_task *, void *);
void (*rpc_call_done)(struct rpc_task *, void *);
void (*rpc_count_stats)(struct rpc_task *, void *);
void (*rpc_release)(void *);
* @cs_was_changed_seq: The sequence number of clocksource change events
* @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second
* @raw_sec: CLOCK_MONOTONIC_RAW time in seconds
+ * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
* @cycle_interval: Number of clock cycles in one NTP interval
* @xtime_interval: Number of clock shifted nano seconds in one NTP
* interval.
*
* wall_to_monotonic is no longer the boot time, getboottime must be
* used instead.
+ *
+ * @monotonic_to_boottime is a timespec64 representation of @offs_boot to
+ * accelerate the VDSO update for CLOCK_BOOTTIME.
*/
struct timekeeper {
struct tk_read_base tkr_mono;
u8 cs_was_changed_seq;
ktime_t next_leap_ktime;
u64 raw_sec;
+ struct timespec64 monotonic_to_boot;
/* The following members are for timekeeping internal use */
u64 cycle_interval;
#define is_signed_type(type) (((type)(-1)) < (type)1)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set);
int trace_set_clr_event(const char *system, const char *event, int set);
/*
* field rather than determining a dma address themselves.
*
* Note that transfer_buffer must still be set if the controller
- * does not support DMA (as indicated by bus.uses_dma) and when talking
+ * does not support DMA (as indicated by hcd_uses_dma()) and when talking
* to root hub. If you have to trasfer between highmem zone and the device
* on such controller, create a bounce buffer or bail out with an error.
* If transfer_buffer cannot be set (is in highmem) and the controller is DMA
return hcd->high_prio_bh.completing_ep == ep;
}
+#define hcd_uses_dma(hcd) \
+ (IS_ENABLED(CONFIG_HAS_DMA) && (hcd)->self.uses_dma)
+
extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb);
extern int usb_hcd_check_unlink_urb(struct usb_hcd *hcd, struct urb *urb,
int status);
return !list_empty(&wq_head->head);
}
+/**
+ * wq_has_single_sleeper - check if there is only one sleeper
+ * @wq_head: wait queue head
+ *
+ * Returns true of wq_head has only one sleeper on the list.
+ *
+ * Please refer to the comment for waitqueue_active.
+ */
+static inline bool wq_has_single_sleeper(struct wait_queue_head *wq_head)
+{
+ return list_is_singular(&wq_head->head);
+}
+
/**
* wq_has_sleeper - check if there are any waiting processes
* @wq_head: wait queue head
\
case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \
R##_e = X##_e; \
+ /* Fall through */ \
case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_NORMAL): \
case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF): \
case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO): \
\
case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NORMAL): \
R##_e = Y##_e; \
+ /* Fall through */ \
case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_NAN): \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN): \
case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN): \
case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_INF): \
case _FP_CLS_COMBINE(FP_CLS_NAN,FP_CLS_ZERO): \
R##_s = X##_s; \
+ /* Fall through */ \
\
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF): \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NAN): \
case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_NAN): \
R##_s = Y##_s; \
+ /* Fall through */ \
\
case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_INF): \
case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \
\
case _FP_CLS_COMBINE(FP_CLS_NORMAL,FP_CLS_ZERO): \
FP_SET_EXCEPTION(FP_EX_DIVZERO); \
+ /* Fall through */ \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \
R##_c = FP_CLS_INF; \
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Character LCD driver for Linux
- *
- * Copyright (C) 2000-2008, Willy Tarreau <w@1wt.eu>
- * Copyright (C) 2016-2017 Glider bvba
- */
-
-struct charlcd {
- const struct charlcd_ops *ops;
- const unsigned char *char_conv; /* Optional */
-
- int ifwidth; /* 4-bit or 8-bit (default) */
- int height;
- int width;
- int bwidth; /* Default set by charlcd_alloc() */
- int hwidth; /* Default set by charlcd_alloc() */
-
- void *drvdata; /* Set by charlcd_alloc() */
-};
-
-struct charlcd_ops {
- /* Required */
- void (*write_cmd)(struct charlcd *lcd, int cmd);
- void (*write_data)(struct charlcd *lcd, int data);
-
- /* Optional */
- void (*write_cmd_raw4)(struct charlcd *lcd, int cmd); /* 4-bit only */
- void (*clear_fast)(struct charlcd *lcd);
- void (*backlight)(struct charlcd *lcd, int on);
-};
-
-struct charlcd *charlcd_alloc(unsigned int drvdata_size);
-void charlcd_free(struct charlcd *lcd);
-
-int charlcd_register(struct charlcd *lcd);
-int charlcd_unregister(struct charlcd *lcd);
-
-void charlcd_poke(struct charlcd *lcd);
struct tcf_idrinfo {
struct mutex lock;
struct idr action_idr;
+ struct net *net;
};
struct tc_action_ops;
};
static inline
-int tc_action_net_init(struct tc_action_net *tn,
+int tc_action_net_init(struct net *net, struct tc_action_net *tn,
const struct tc_action_ops *ops)
{
int err = 0;
if (!tn->idrinfo)
return -ENOMEM;
tn->ops = ops;
+ tn->idrinfo->net = net;
mutex_init(&tn->idrinfo->lock);
idr_init(&tn->idrinfo->action_idr);
return err;
unsigned int len)
{
if (skb_transport_offset(skb) + ipv6_transport_len(skb) < len)
- return -EINVAL;
+ return 0;
return pskb_may_pull(skb, len);
}
__u16 conn_info_min_age;
__u16 conn_info_max_age;
__u16 auth_payload_timeout;
+ __u8 min_enc_key_size;
__u8 ssp_debug_mode;
__u8 hw_error_code;
__u32 clock;
u8 rx_nss;
};
-#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)ERR_PTR(-ENODATA))
+#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)(long)(-ENODATA))
/**
* struct wiphy_vendor_command - vendor command definition
struct cfg80211_pmsr_request *req,
gfp_t gfp);
+/**
+ * cfg80211_iftype_allowed - check whether the interface can be allowed
+ * @wiphy: the wiphy
+ * @iftype: interface type
+ * @is_4addr: use_4addr flag, must be '0' when check_swif is '1'
+ * @check_swif: check iftype against software interfaces
+ *
+ * Check whether the interface is allowed to operate; additionally, this API
+ * can be used to check iftype against the software interfaces when
+ * check_swif is '1'.
+ */
+bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype,
+ bool is_4addr, u8 check_swif);
+
+
/* Logging, debugging and troubleshooting/diagnostic helpers. */
/* wiphy_printk helpers, similar to dev_printk */
#define _NET_FLOW_OFFLOAD_H
#include <linux/kernel.h>
+#include <linux/list.h>
#include <net/flow_dissector.h>
-#include <net/sch_generic.h>
struct flow_match {
struct flow_dissector *dissector;
FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
};
+struct flow_block {
+ struct list_head cb_list;
+};
+
struct netlink_ext_ack;
struct flow_block_offload {
enum flow_block_binder_type binder_type;
bool block_shared;
struct net *net;
+ struct flow_block *block;
struct list_head cb_list;
struct list_head *driver_block_list;
struct netlink_ext_ack *extack;
};
+enum tc_setup_type;
+typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data,
+ void *cb_priv);
+
struct flow_block_cb {
struct list_head driver_list;
struct list_head list;
- struct net *net;
- tc_setup_cb_t *cb;
+ flow_setup_cb_t *cb;
void *cb_ident;
void *cb_priv;
void (*release)(void *cb_priv);
unsigned int refcnt;
};
-struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv));
void flow_block_cb_free(struct flow_block_cb *block_cb);
-struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload,
- tc_setup_cb_t *cb, void *cb_ident);
+struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
+ flow_setup_cb_t *cb, void *cb_ident);
void *flow_block_cb_priv(struct flow_block_cb *block_cb);
void flow_block_cb_incref(struct flow_block_cb *block_cb);
list_move(&block_cb->list, &offload->cb_list);
}
-bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
struct list_head *driver_block_list);
int flow_block_cb_setup_simple(struct flow_block_offload *f,
- struct list_head *driver_list, tc_setup_cb_t *cb,
+ struct list_head *driver_list,
+ flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv, bool ingress_only);
enum flow_cls_command {
return flow_cmd->rule;
}
+static inline void flow_block_init(struct flow_block *flow_block)
+{
+ INIT_LIST_HEAD(&flow_block->cb_list);
+}
+
#endif /* _NET_FLOW_OFFLOAD_H */
void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
struct sk_buff *parent);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
- void *reasm_data);
+ void *reasm_data, bool try_coalesce);
struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q);
#endif
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
struct net {
- refcount_t passive; /* To decided when the network
+ refcount_t passive; /* To decide when the network
* namespace should be freed.
*/
refcount_t count; /* To decided when the network
spinlock_t rules_mod_lock;
u32 hash_mix;
- atomic64_t cookie_gen;
struct list_head list; /* list of network namespaces */
struct list_head exit_list; /* To linked to call pernet exit
#define NF_CT_EXPECT_CLASS_DEFAULT 0
#define NF_CT_EXPECT_MAX_CNT 255
+/* Allow to reuse expectations with the same tuples from different master
+ * conntracks.
+ */
+#define NF_CT_EXP_F_SKIP_MASTER 0x1
+
int nf_conntrack_expect_pernet_init(struct net *net);
void nf_conntrack_expect_pernet_fini(struct net *net);
u_int8_t, const __be16 *, const __be16 *);
void nf_ct_expect_put(struct nf_conntrack_expect *exp);
int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
- u32 portid, int report);
-static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect)
+ u32 portid, int report, unsigned int flags);
+static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect,
+ unsigned int flags)
{
- return nf_ct_expect_related_report(expect, 0, 0);
+ return nf_ct_expect_related_report(expect, 0, 0, flags);
}
#endif /*_NF_CONNTRACK_EXPECT_H*/
u8 options;
u8 wscale;
u16 mss;
+ u16 mss_encode;
u32 tsval;
u32 tsecr;
};
#include <linux/rhashtable.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netlink.h>
+#include <net/flow_offload.h>
struct module;
unsigned char *udata;
/* runtime data below here */
const struct nft_set_ops *ops ____cacheline_aligned;
- u16 flags:13,
- bound:1,
+ u16 flags:14,
genmask:2;
u8 klen;
u8 dlen;
* @stats: per-cpu chain stats
* @chain: the chain
* @dev_name: device name that this base chain is attached to (if any)
- * @cb_list: list of flow block callbacks (for hardware offload)
+ * @flow_block: flow block (for hardware offload)
*/
struct nft_base_chain {
struct nf_hook_ops ops;
struct nft_stats __percpu *stats;
struct nft_chain chain;
char dev_name[IFNAMSIZ];
- struct list_head cb_list;
+ struct flow_block flow_block;
};
static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain)
struct nft_trans_set {
struct nft_set *set;
u32 set_id;
+ bool bound;
};
#define nft_trans_set(trans) \
(((struct nft_trans_set *)trans->data)->set)
#define nft_trans_set_id(trans) \
(((struct nft_trans_set *)trans->data)->set_id)
+#define nft_trans_set_bound(trans) \
+ (((struct nft_trans_set *)trans->data)->bound)
struct nft_trans_chain {
bool update;
struct nft_trans_elem {
struct nft_set *set;
struct nft_set_elem elem;
+ bool bound;
};
#define nft_trans_elem_set(trans) \
(((struct nft_trans_elem *)trans->data)->set)
#define nft_trans_elem(trans) \
(((struct nft_trans_elem *)trans->data)->elem)
+#define nft_trans_elem_set_bound(trans) \
+ (((struct nft_trans_elem *)trans->data)->bound)
struct nft_trans_obj {
struct nft_object *obj;
(__reg)->key = __key; \
memset(&(__reg)->mask, 0xff, (__reg)->len);
+int nft_chain_offload_priority(struct nft_base_chain *basechain);
+
#endif
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
- return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
- nlmsg_attrlen(nlh, hdrlen), policy,
- NL_VALIDATE_STRICT, extack);
+ return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
+ NL_VALIDATE_STRICT, extack);
}
/**
nh_grp = rcu_dereference_rtnl(nh->nh_grp);
rc = nh_grp->num_nh;
- } else {
- const struct nh_info *nhi;
-
- nhi = rcu_dereference_rtnl(nh->nh_info);
- if (nhi->reject_nh)
- rc = 0;
}
return rc;
#include <linux/workqueue.h>
#include <net/sch_generic.h>
#include <net/act_api.h>
-#include <net/flow_offload.h>
#include <net/net_namespace.h>
/* TC action not accessible from user space */
}
static inline
-int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb,
+int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb,
void *cb_priv)
{
return 0;
}
static inline
-void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
+void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb,
void *cb_priv)
{
}
{
cls_common->chain_index = tp->chain->index;
cls_common->protocol = tp->protocol;
- cls_common->prio = tp->prio;
+ cls_common->prio = tp->prio >> 16;
if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE)
cls_common->extack = extack;
}
u32 group_num;
u32 refcount;
u32 seq;
+ struct rcu_head rcu;
};
struct psample_group *psample_group_get(struct net *net, u32 group_num);
int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb,
u32 table_id, struct fib_info *fi,
- int *fa_index, int fa_start);
+ int *fa_index, int fa_start, unsigned int flags);
static inline void ip_rt_put(struct rtable *rt)
{
#include <linux/mutex.h>
#include <net/gen_stats.h>
#include <net/rtnetlink.h>
+#include <net/flow_offload.h>
struct Qdisc_ops;
struct qdisc_walker;
struct module;
struct bpf_flow_keys;
-typedef int tc_setup_cb_t(enum tc_setup_type type,
- void *type_data, void *cb_priv);
-
typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
enum tc_setup_type type, void *type_data);
void (*walk)(struct tcf_proto *tp,
struct tcf_walker *arg, bool rtnl_held);
int (*reoffload)(struct tcf_proto *tp, bool add,
- tc_setup_cb_t *cb, void *cb_priv,
+ flow_setup_cb_t *cb, void *cb_priv,
struct netlink_ext_ack *extack);
void (*bind_class)(void *, u32, unsigned long);
void * (*tmplt_create)(struct net *net,
refcount_t refcnt;
struct net *net;
struct Qdisc *q;
- struct list_head cb_list;
+ struct flow_block flow_block;
struct list_head owner_list;
bool keep_dst;
unsigned int offloadcnt; /* Number of oddloaded filters */
/* Checks if this SKB belongs to an HW offloaded socket
* and whether any SW fallbacks are required based on dev.
+ * Check decrypted mark in case skb_orphan() cleared socket.
*/
static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
struct net_device *dev)
#ifdef CONFIG_SOCK_VALIDATE_XMIT
struct sock *sk = skb->sk;
- if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb)
+ if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) {
skb = sk->sk_validate_xmit_skb(sk, dev, skb);
+#ifdef CONFIG_TLS_DEVICE
+ } else if (unlikely(skb->decrypted)) {
+ pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
+ kfree_skb(skb);
+ skb = NULL;
+#endif
+ }
#endif
return skb;
struct tcf_police *police = to_police(act);
struct tcf_police_params *params;
- params = rcu_dereference_bh(police->params);
+ params = rcu_dereference_bh_rtnl(police->params);
return params->rate.rate_bytes_ps;
}
struct tcf_police *police = to_police(act);
struct tcf_police_params *params;
- params = rcu_dereference_bh(police->params);
+ params = rcu_dereference_bh_rtnl(police->params);
return params->tcfp_burst;
}
static inline struct psample_group *
tcf_sample_psample_group(const struct tc_action *a)
{
- return rcu_dereference(to_sample(a)->psample_group);
+ return rcu_dereference_rtnl(to_sample(a)->psample_group);
}
#endif /* __NET_TC_SAMPLE_H */
return skb_rb_first(&sk->tcp_rtx_queue);
}
+static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
+{
+ return skb_rb_last(&sk->tcp_rtx_queue);
+}
+
static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
{
return skb_peek(&sk->sk_write_queue);
/* initialize ulp */
int (*init)(struct sock *sk);
+ /* update ulp */
+ void (*update)(struct sock *sk, struct proto *p);
/* cleanup ulp */
void (*release)(struct sock *sk);
int tcp_set_ulp(struct sock *sk, const char *name);
void tcp_get_available_ulp(char *buf, size_t len);
void tcp_cleanup_ulp(struct sock *sk);
+void tcp_update_ulp(struct sock *sk, struct proto *p);
#define MODULE_ALIAS_TCP_ULP(name) \
__MODULE_INFO(alias, alias_userspace, name); \
enum {
TLS_BASE,
TLS_SW,
-#ifdef CONFIG_TLS_DEVICE
TLS_HW,
-#endif
TLS_HW_RECORD,
TLS_NUM_CONFIG,
};
int async_capable;
#define BIT_TX_SCHEDULED 0
+#define BIT_TX_CLOSING 1
unsigned long tx_bitmask;
};
unsigned long flags;
/* cache cold stuff */
+ struct proto *sk_proto;
+
void (*sk_destruct)(struct sock *sk);
void (*sk_proto_close)(struct sock *sk, long timeout);
unsigned int optlen);
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
+void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
+void tls_sw_strparser_done(struct tls_context *tls_ctx);
int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
int tls_sw_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
-void tls_sw_close(struct sock *sk, long timeout);
-void tls_sw_free_resources_tx(struct sock *sk);
+void tls_sw_cancel_work_tx(struct tls_context *tls_ctx);
+void tls_sw_release_resources_tx(struct sock *sk);
+void tls_sw_free_ctx_tx(struct tls_context *tls_ctx);
void tls_sw_free_resources_rx(struct sock *sk);
void tls_sw_release_resources_rx(struct sock *sk);
+void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
bool tls_sw_stream_read(const struct sock *sk);
const union ib_gid *gid,
const struct sockaddr *addr,
void *client_data);
- struct list_head list;
+
+ refcount_t uses;
+ struct completion uses_zero;
u32 client_id;
/* kverbs are not required by the client */
/**
* rvt_qp_wqe_unreserve - clean reserved operation
* @qp - the rvt qp
- * @wqe - the send wqe
+ * @flags - send wqe flags
*
* This decrements the reserve use count.
*
* the compiler does not juggle the order of the s_last
* ring index and the decrementing of s_reserved_used.
*/
-static inline void rvt_qp_wqe_unreserve(
- struct rvt_qp *qp,
- struct rvt_swqe *wqe)
+static inline void rvt_qp_wqe_unreserve(struct rvt_qp *qp, int flags)
{
- if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) {
+ if (unlikely(flags & RVT_SEND_RESERVE_USED)) {
atomic_dec(&qp->s_reserved_used);
/* insure no compiler re-order up to s_last change */
smp_mb__after_atomic();
u32 byte_len, last;
int flags = wqe->wr.send_flags;
+ rvt_qp_wqe_unreserve(qp, flags);
rvt_put_qp_swqe(qp, wqe);
need_completion =
};
int rdma_restrack_count(struct ib_device *dev,
- enum rdma_restrack_type type,
- struct pid_namespace *ns);
+ enum rdma_restrack_type type);
void rdma_restrack_kadd(struct rdma_restrack_entry *res);
void rdma_restrack_uadd(struct rdma_restrack_entry *res);
struct fc_lport *lp;
struct list_head peers;
struct work_struct rport_work;
- u32 port_id;
+ u32 port_id;
};
/**
*/
struct fc_rport_libfc_priv {
struct fc_lport *local_port;
- enum fc_rport_state rp_state;
+ enum fc_rport_state rp_state;
u16 flags;
#define FC_RP_FLAGS_REC_SUPPORTED (1 << 0)
#define FC_RP_FLAGS_RETRY (1 << 1)
#define FC_RP_STARTED (1 << 2)
#define FC_RP_FLAGS_CONF_REQ (1 << 3)
- unsigned int e_d_tov;
- unsigned int r_a_tov;
+ unsigned int e_d_tov;
+ unsigned int r_a_tov;
};
/**
struct fc_lport *local_port;
struct fc_rport *rport;
struct kref kref;
- enum fc_rport_state rp_state;
+ enum fc_rport_state rp_state;
struct fc_rport_identifiers ids;
u16 flags;
- u16 max_seq;
+ u16 max_seq;
u16 disc_id;
u16 maxframe_size;
- unsigned int retries;
- unsigned int major_retries;
- unsigned int e_d_tov;
- unsigned int r_a_tov;
- struct mutex rp_mutex;
+ unsigned int retries;
+ unsigned int major_retries;
+ unsigned int e_d_tov;
+ unsigned int r_a_tov;
+ struct mutex rp_mutex;
struct delayed_work retry_work;
- enum fc_rport_event event;
+ enum fc_rport_event event;
struct fc_rport_operations *ops;
- struct list_head peers;
- struct work_struct event_work;
+ struct list_head peers;
+ struct work_struct event_work;
u32 supported_classes;
- u16 prli_count;
+ u16 prli_count;
struct rcu_head rcu;
u16 sp_features;
u8 spp_type;
* @disc_callback: Callback routine called when discovery completes
*/
struct fc_disc {
- unsigned char retry_count;
- unsigned char pending;
- unsigned char requested;
- unsigned short seq_count;
- unsigned char buf_len;
- u16 disc_id;
+ unsigned char retry_count;
+ unsigned char pending;
+ unsigned char requested;
+ unsigned short seq_count;
+ unsigned char buf_len;
+ u16 disc_id;
struct list_head rports;
void *priv;
struct fc_rport_priv *ms_rdata;
struct fc_rport_priv *ptp_rdata;
void *scsi_priv;
- struct fc_disc disc;
+ struct fc_disc disc;
/* Virtual port information */
struct list_head vports;
u8 retry_count;
/* Fabric information */
- u32 port_id;
+ u32 port_id;
u64 wwpn;
u64 wwnn;
unsigned int service_params;
struct fc_ns_fts fcts;
/* Miscellaneous */
- struct mutex lp_mutex;
- struct list_head list;
+ struct mutex lp_mutex;
+ struct list_head list;
struct delayed_work retry_work;
void *prov[FC_FC4_PROV_SIZE];
- struct list_head lport_list;
+ struct list_head lport_list;
};
/**
* FIP tunable parameters.
*/
#define FCOE_CTLR_START_DELAY 2000 /* mS after first adv. to choose FCF */
-#define FCOE_CTRL_SOL_TOV 2000 /* min. solicitation interval (mS) */
+#define FCOE_CTLR_SOL_TOV 2000 /* min. solicitation interval (mS) */
#define FCOE_CTLR_FCF_LIMIT 20 /* max. number of FCF entries */
#define FCOE_CTLR_VN2VN_LOGIN_LIMIT 3 /* max. VN2VN rport login retries */
* @vn_mac: VN_Node assigned MAC address for data
*/
struct fcoe_rport {
+ struct fc_rport_priv rdata;
unsigned long time;
u16 fcoe_len;
u16 flags;
#define CMD_IDU_ENABLE 0x71
#define CMD_IDU_DISABLE 0x72
#define CMD_IDU_SET_MODE 0x74
+#define CMD_IDU_READ_MODE 0x75
#define CMD_IDU_SET_DEST 0x76
+#define CMD_IDU_ACK_CIRQ 0x79
#define CMD_IDU_SET_MASK 0x7C
#define IDU_M_TRIG_LEVEL 0x0
__mcip_cmd(cmd, param);
}
+/*
+ * Read MCIP register
+ */
+static inline unsigned int __mcip_cmd_read(unsigned int cmd, unsigned int param)
+{
+ __mcip_cmd(cmd, param);
+ return read_aux_reg(ARC_REG_MCIP_READBACK);
+}
+
#endif
/* Structure that defines QE firmware binary files.
*
- * See Documentation/powerpc/qe_firmware.txt for a description of these
+ * See Documentation/powerpc/qe_firmware.rst for a description of these
* fields.
*/
struct qe_firmware {
if (snd_BUG_ON(!stream))
return;
- if (stream->direction == SND_COMPRESS_PLAYBACK)
- stream->runtime->state = SNDRV_PCM_STATE_SETUP;
- else
- stream->runtime->state = SNDRV_PCM_STATE_PREPARED;
+ stream->runtime->state = SNDRV_PCM_STATE_SETUP;
wake_up(&stream->runtime->sleep);
}
struct snd_soc_dapm_widget *snd_soc_dapm_new_control(
struct snd_soc_dapm_context *dapm,
const struct snd_soc_dapm_widget *widget);
+struct snd_soc_dapm_widget *snd_soc_dapm_new_control_unlocked(
+ struct snd_soc_dapm_context *dapm,
+ const struct snd_soc_dapm_widget *widget);
int snd_soc_dapm_new_dai_widgets(struct snd_soc_dapm_context *dapm,
struct snd_soc_dai *dai);
int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card);
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
/*
* This file is provided under a dual BSD/GPLv2 license. When using or
* redistributing this file, you may do so under either license.
#undef TRACE_SYSTEM
#define TRACE_SYSTEM dma_fence
-#if !defined(_TRACE_FENCE_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_TRACE_DMA_FENCE_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_DMA_FENCE_H
#include <linux/tracepoint.h>
#define TRACE_SYSTEM napi
#if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_NAPI_H_
+#define _TRACE_NAPI_H
#include <linux/netdevice.h>
#include <linux/tracepoint.h>
#undef NO_DEV
-#endif /* _TRACE_NAPI_H_ */
+#endif /* _TRACE_NAPI_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
#define TRACE_SYSTEM qdisc
#if !defined(_TRACE_QDISC_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_QDISC_H_
+#define _TRACE_QDISC_H
#include <linux/skbuff.h>
#include <linux/netdevice.h>
__entry->txq_state, __entry->packets, __entry->skbaddr )
);
-#endif /* _TRACE_QDISC_H_ */
+#endif /* _TRACE_QDISC_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
#define __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY
enum rxrpc_skb_trace {
- rxrpc_skb_rx_cleaned,
- rxrpc_skb_rx_freed,
- rxrpc_skb_rx_got,
- rxrpc_skb_rx_lost,
- rxrpc_skb_rx_purged,
- rxrpc_skb_rx_received,
- rxrpc_skb_rx_rotated,
- rxrpc_skb_rx_seen,
- rxrpc_skb_tx_cleaned,
- rxrpc_skb_tx_freed,
- rxrpc_skb_tx_got,
- rxrpc_skb_tx_new,
- rxrpc_skb_tx_rotated,
- rxrpc_skb_tx_seen,
+ rxrpc_skb_cleaned,
+ rxrpc_skb_freed,
+ rxrpc_skb_got,
+ rxrpc_skb_lost,
+ rxrpc_skb_new,
+ rxrpc_skb_purged,
+ rxrpc_skb_received,
+ rxrpc_skb_rotated,
+ rxrpc_skb_seen,
+ rxrpc_skb_unshared,
+ rxrpc_skb_unshared_nomem,
};
enum rxrpc_local_trace {
* Declare tracing information enums and their string mappings for display.
*/
#define rxrpc_skb_traces \
- EM(rxrpc_skb_rx_cleaned, "Rx CLN") \
- EM(rxrpc_skb_rx_freed, "Rx FRE") \
- EM(rxrpc_skb_rx_got, "Rx GOT") \
- EM(rxrpc_skb_rx_lost, "Rx *L*") \
- EM(rxrpc_skb_rx_purged, "Rx PUR") \
- EM(rxrpc_skb_rx_received, "Rx RCV") \
- EM(rxrpc_skb_rx_rotated, "Rx ROT") \
- EM(rxrpc_skb_rx_seen, "Rx SEE") \
- EM(rxrpc_skb_tx_cleaned, "Tx CLN") \
- EM(rxrpc_skb_tx_freed, "Tx FRE") \
- EM(rxrpc_skb_tx_got, "Tx GOT") \
- EM(rxrpc_skb_tx_new, "Tx NEW") \
- EM(rxrpc_skb_tx_rotated, "Tx ROT") \
- E_(rxrpc_skb_tx_seen, "Tx SEE")
+ EM(rxrpc_skb_cleaned, "CLN") \
+ EM(rxrpc_skb_freed, "FRE") \
+ EM(rxrpc_skb_got, "GOT") \
+ EM(rxrpc_skb_lost, "*L*") \
+ EM(rxrpc_skb_new, "NEW") \
+ EM(rxrpc_skb_purged, "PUR") \
+ EM(rxrpc_skb_received, "RCV") \
+ EM(rxrpc_skb_rotated, "ROT") \
+ EM(rxrpc_skb_seen, "SEE") \
+ EM(rxrpc_skb_unshared, "UNS") \
+ E_(rxrpc_skb_unshared_nomem, "US0")
#define rxrpc_local_traces \
EM(rxrpc_local_got, "GOT") \
#define E_(a, b) { a, b }
TRACE_EVENT(rxrpc_local,
- TP_PROTO(struct rxrpc_local *local, enum rxrpc_local_trace op,
+ TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op,
int usage, const void *where),
- TP_ARGS(local, op, usage, where),
+ TP_ARGS(local_debug_id, op, usage, where),
TP_STRUCT__entry(
__field(unsigned int, local )
),
TP_fast_assign(
- __entry->local = local->debug_id;
+ __entry->local = local_debug_id;
__entry->op = op;
__entry->usage = usage;
__entry->where = where;
TRACE_EVENT(rxrpc_skb,
TP_PROTO(struct sk_buff *skb, enum rxrpc_skb_trace op,
- int usage, int mod_count, const void *where),
+ int usage, int mod_count, u8 flags, const void *where),
- TP_ARGS(skb, op, usage, mod_count, where),
+ TP_ARGS(skb, op, usage, mod_count, flags, where),
TP_STRUCT__entry(
__field(struct sk_buff *, skb )
__field(enum rxrpc_skb_trace, op )
+ __field(u8, flags )
__field(int, usage )
__field(int, mod_count )
__field(const void *, where )
TP_fast_assign(
__entry->skb = skb;
+ __entry->flags = flags;
__entry->op = op;
__entry->usage = usage;
__entry->mod_count = mod_count;
__entry->where = where;
),
- TP_printk("s=%p %s u=%d m=%d p=%pSR",
+ TP_printk("s=%p %cx %s u=%d m=%d p=%pSR",
__entry->skb,
+ __entry->flags & RXRPC_SKB_TX_BUFFER ? 'T' : 'R',
__print_symbolic(__entry->op, rxrpc_skb_traces),
__entry->usage,
__entry->mod_count,
#if !defined(_TRACE_TEGRA_APB_DMA_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_TEGRA_APM_DMA_H
+#define _TRACE_TEGRA_APB_DMA_H
#include <linux/tracepoint.h>
#include <linux/dmaengine.h>
TP_printk("%s: irq %d\n", __get_str(chan), __entry->irq)
);
-#endif /* _TRACE_TEGRADMA_H */
+#endif /* _TRACE_TEGRA_APB_DMA_H */
/* This part must be outside protection */
#include <trace/define_trace.h>
* If no cookie has been set yet, generate a new cookie. Once
* generated, the socket cookie remains stable for the life of the
* socket. This helper can be useful for monitoring per socket
- * networking traffic statistics as it provides a unique socket
- * identifier per namespace.
+ * networking traffic statistics as it provides a global socket
+ * identifier that can be assumed unique.
* Return
* A 8-byte long non-decreasing number on success, or 0 if the
* socket field is missing inside *skb*.
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_LINUX_BPFILTER_H
#define _UAPI_LINUX_BPFILTER_H
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* Copyright (c) 2015-2018, Intel Corporation.
*/
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* Intel Speed Select Interface: OS to hardware Interface
* Copyright (c) 2019, Intel Corporation.
#define JFFS2_ACL_VERSION 0x0001
-// Maybe later...
-//#define JFFS2_NODETYPE_CHECKPOINT (JFFS2_FEATURE_RWCOMPAT_DELETE | JFFS2_NODE_ACCURATE | 3)
-//#define JFFS2_NODETYPE_OPTIONS (JFFS2_FEATURE_RWCOMPAT_COPY | JFFS2_NODE_ACCURATE | 4)
-
-
#define JFFS2_INO_FLAG_PREREAD 1 /* Do read_inode() for this one at
mount time, don't wait for it to
happen later */
__u32 n_success; /* to/from KFD */
};
-/* Allocate GWS for specific queue
- *
- * @gpu_id: device identifier
- * @queue_id: queue's id that GWS is allocated for
- * @num_gws: how many GWS to allocate
- * @first_gws: index of the first GWS allocated.
- * only support contiguous GWS allocation
- */
-struct kfd_ioctl_alloc_queue_gws_args {
- __u32 gpu_id; /* to KFD */
- __u32 queue_id; /* to KFD */
- __u32 num_gws; /* to KFD */
- __u32 first_gws; /* from KFD */
-};
-
struct kfd_ioctl_get_dmabuf_info_args {
__u64 size; /* from KFD */
__u64 metadata_ptr; /* to KFD */
#define AMDKFD_IOC_IMPORT_DMABUF \
AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args)
-#define AMDKFD_IOC_ALLOC_QUEUE_GWS \
- AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args)
-
#define AMDKFD_COMMAND_START 0x01
-#define AMDKFD_COMMAND_END 0x1F
+#define AMDKFD_COMMAND_END 0x1E
#endif
* ACPI gsi notion of irq.
* For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
* For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
- * For ARM: See Documentation/virtual/kvm/api.txt
+ * For ARM: See Documentation/virt/kvm/api.txt
*/
union {
__u32 irq;
*
* KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
* the irqfd to operate in resampling mode for level triggered interrupt
- * emulation. See Documentation/virtual/kvm/api.txt.
+ * emulation. See Documentation/virt/kvm/api.txt.
*/
#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _NF_SYNPROXY_H
#define _NF_SYNPROXY_H
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_XT_CONNLABEL_H
+#define _UAPI_XT_CONNLABEL_H
+
#include <linux/types.h>
#define XT_CONNLABEL_MAXBIT 127
__u16 bit;
__u16 options;
};
+
+#endif /* _UAPI_XT_CONNLABEL_H */
struct nf_acct *nfacct;
};
+struct xt_nfacct_match_info_v1 {
+ char name[NFACCT_NAME_MAX];
+ struct nf_acct *nfacct __attribute__((aligned(8)));
+};
+
#endif /* _XT_NFACCT_MATCH_H */
#define NL80211_HT_CAPABILITY_LEN 26
#define NL80211_VHT_CAPABILITY_LEN 12
#define NL80211_HE_MIN_CAPABILITY_LEN 16
-#define NL80211_HE_MAX_CAPABILITY_LEN 51
+#define NL80211_HE_MAX_CAPABILITY_LEN 54
#define NL80211_MAX_NR_CIPHER_SUITES 5
#define NL80211_MAX_NR_AKM_SUITES 2
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* Userspace interface for AMD Secure Encrypted Virtualization (SEV)
* platform management commands.
__u32 rdma_mr_max;
__u32 rdma_mr_size;
__u8 tos;
+ __u8 sl;
__u32 cache_allocs;
};
__u32 rdma_mr_max;
__u32 rdma_mr_size;
__u8 tos;
+ __u8 sl;
__u32 cache_allocs;
};
-/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* SPDX-License-Identifier: GPL-2.0-or-later WITH Linux-syscall-note */
/* Types and definitions for AF_RXRPC.
*
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
#define PORT_PNX8XXX 70
-/* Hilscher netx */
-#define PORT_NETX 71
-
/* SUN4V Hypervisor Console */
#define PORT_SUNHV 72
* Desired design of maximum size and alignment (see RFC2553)
*/
#define _K_SS_MAXSIZE 128 /* Implementation specific max size */
-#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *))
- /* Implementation specific desired alignment */
typedef unsigned short __kernel_sa_family_t;
+/*
+ * The definition uses anonymous union and struct in order to control the
+ * default alignment.
+ */
struct __kernel_sockaddr_storage {
- __kernel_sa_family_t ss_family; /* address family */
- /* Following field(s) are implementation specific */
- char __data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+ union {
+ struct {
+ __kernel_sa_family_t ss_family; /* address family */
+ /* Following field(s) are implementation specific */
+ char __data[_K_SS_MAXSIZE - sizeof(unsigned short)];
/* space to achieve desired size, */
/* _SS_MAXSIZE value minus size of ss_family */
-} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */
+ };
+ void *__align; /* implementation specific desired alignment */
+ };
+};
#endif /* _UAPI_LINUX_SOCKET_H */
-/* SPDX-License-Identifier: GPL-2.0+ */
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
/*
* g_uvc.h -- USB Video Class Gadget driver API
*
-/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR CDDL-1.0) */
/*
* Virtual Device for Guest <-> VMM/Host communication, type definitions
* which are also used for the vboxguest ioctl interface / by vboxsf
-/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR CDDL-1.0) */
/*
* VBoxGuest - VirtualBox Guest Additions Driver Interface.
*
#define V4L2_PIX_FMT_RGBX444 v4l2_fourcc('R', 'X', '1', '2') /* 16 rrrrgggg bbbbxxxx */
#define V4L2_PIX_FMT_ABGR444 v4l2_fourcc('A', 'B', '1', '2') /* 16 aaaabbbb ggggrrrr */
#define V4L2_PIX_FMT_XBGR444 v4l2_fourcc('X', 'B', '1', '2') /* 16 xxxxbbbb ggggrrrr */
-#define V4L2_PIX_FMT_BGRA444 v4l2_fourcc('B', 'A', '1', '2') /* 16 bbbbgggg rrrraaaa */
+
+/*
+ * Originally this had 'BA12' as fourcc, but this clashed with the older
+ * V4L2_PIX_FMT_SGRBG12 which inexplicably used that same fourcc.
+ * So use 'GA12' instead for V4L2_PIX_FMT_BGRA444.
+ */
+#define V4L2_PIX_FMT_BGRA444 v4l2_fourcc('G', 'A', '1', '2') /* 16 bbbbgggg rrrraaaa */
#define V4L2_PIX_FMT_BGRX444 v4l2_fourcc('B', 'X', '1', '2') /* 16 bbbbgggg rrrrxxxx */
#define V4L2_PIX_FMT_RGB555 v4l2_fourcc('R', 'G', 'B', 'O') /* 16 RGB-5-5-5 */
#define V4L2_PIX_FMT_ARGB555 v4l2_fourcc('A', 'R', '1', '5') /* 16 ARGB-1-5-5-5 */
/* SPDX-License-Identifier: BSD-3-Clause */
/*
- * Virtio-iommu definition v0.9
+ * Virtio-iommu definition v0.12
*
- * Copyright (C) 2018 Arm Ltd.
+ * Copyright (C) 2019 Arm Ltd.
*/
#ifndef _UAPI_LINUX_VIRTIO_IOMMU_H
#define _UAPI_LINUX_VIRTIO_IOMMU_H
/* Feature bits */
#define VIRTIO_IOMMU_F_INPUT_RANGE 0
-#define VIRTIO_IOMMU_F_DOMAIN_BITS 1
+#define VIRTIO_IOMMU_F_DOMAIN_RANGE 1
#define VIRTIO_IOMMU_F_MAP_UNMAP 2
#define VIRTIO_IOMMU_F_BYPASS 3
#define VIRTIO_IOMMU_F_PROBE 4
+#define VIRTIO_IOMMU_F_MMIO 5
-struct virtio_iommu_range {
- __u64 start;
- __u64 end;
+struct virtio_iommu_range_64 {
+ __le64 start;
+ __le64 end;
+};
+
+struct virtio_iommu_range_32 {
+ __le32 start;
+ __le32 end;
};
struct virtio_iommu_config {
/* Supported page sizes */
- __u64 page_size_mask;
+ __le64 page_size_mask;
/* Supported IOVA range */
- struct virtio_iommu_range input_range;
+ struct virtio_iommu_range_64 input_range;
/* Max domain ID size */
- __u8 domain_bits;
- __u8 padding[3];
+ struct virtio_iommu_range_32 domain_range;
/* Probe buffer size */
- __u32 probe_size;
+ __le32 probe_size;
};
/* Request types */
#define VIRTIO_IOMMU_S_RANGE 0x05
#define VIRTIO_IOMMU_S_NOENT 0x06
#define VIRTIO_IOMMU_S_FAULT 0x07
+#define VIRTIO_IOMMU_S_NOMEM 0x08
struct virtio_iommu_req_head {
__u8 type;
#define VIRTIO_IOMMU_MAP_F_READ (1 << 0)
#define VIRTIO_IOMMU_MAP_F_WRITE (1 << 1)
-#define VIRTIO_IOMMU_MAP_F_EXEC (1 << 2)
-#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 3)
+#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 2)
#define VIRTIO_IOMMU_MAP_F_MASK (VIRTIO_IOMMU_MAP_F_READ | \
VIRTIO_IOMMU_MAP_F_WRITE | \
- VIRTIO_IOMMU_MAP_F_EXEC | \
VIRTIO_IOMMU_MAP_F_MMIO)
struct virtio_iommu_req_map {
-/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause */
/*
* Definitions for virtio-pmem devices.
*
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_VMCORE_H
#define _UAPI_VMCORE_H
-/* SPDX-License-Identifier: GPL-2.0-only */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
/*
* User API methods for ACPI-WMI mapping driver
*
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef __QCOM_FASTRPC_H__
#define __QCOM_FASTRPC_H__
-/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
/*
* This file contains defines, structures, etc. that are used
-/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) or BSD-3-Clause */
/* Authors: Bernard Metzler <bmt@zurich.ibm.com> */
/* Copyright (c) 2008-2019, IBM Corporation */
* to control CQ arming.
*/
struct siw_cq_ctrl {
- __aligned_u64 notify;
+ __u32 flags;
+ __u32 pad;
};
#endif
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* UFS Transport SGIO v4 BSG Message Support
*
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* skl-tplg-interface.h - Intel DSP FW private data interface
*
}
#endif
+int xen_remap_vma_range(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long len);
+
/*
* xen_remap_domain_gfn_array() - map an array of foreign frames by gfn
* @vma: VMA to map the pages into
Select this if you are building a kernel for a desktop system.
-config PREEMPT_LL
+config PREEMPT
bool "Preemptible Kernel (Low-Latency Desktop)"
depends on !ARCH_NO_PREEMPT
- select PREEMPT
+ select PREEMPTION
select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
help
This option reduces the latency of the kernel by making
config PREEMPT_RT
bool "Fully Preemptible Kernel (Real-Time)"
depends on EXPERT && ARCH_SUPPORTS_RT
- select PREEMPT
+ select PREEMPTION
help
This option turns the kernel into a real-time kernel by replacing
various locking primitives (spinlocks, rwlocks, etc.) with
config PREEMPT_COUNT
bool
-config PREEMPT
+config PREEMPTION
bool
select PREEMPT_COUNT
obj-$(CONFIG_TORTURE_TEST) += torture.o
obj-$(CONFIG_HAS_IOMEM) += iomem.o
-obj-$(CONFIG_ZONE_DEVICE) += memremap.o
obj-$(CONFIG_RSEQ) += rseq.o
obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
static int bpf_jit_blind_insn(const struct bpf_insn *from,
const struct bpf_insn *aux,
- struct bpf_insn *to_buff)
+ struct bpf_insn *to_buff,
+ bool emit_zext)
{
struct bpf_insn *to = to_buff;
u32 imm_rnd = get_random_int();
case 0: /* Part 2 of BPF_LD | BPF_IMM | BPF_DW. */
*to++ = BPF_ALU32_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[0].imm);
*to++ = BPF_ALU32_IMM(BPF_XOR, BPF_REG_AX, imm_rnd);
+ if (emit_zext)
+ *to++ = BPF_ZEXT_REG(BPF_REG_AX);
*to++ = BPF_ALU64_REG(BPF_OR, aux[0].dst_reg, BPF_REG_AX);
break;
insn[1].code == 0)
memcpy(aux, insn, sizeof(aux));
- rewritten = bpf_jit_blind_insn(insn, aux, insn_buff);
+ rewritten = bpf_jit_blind_insn(insn, aux, insn_buff,
+ clone->aux->verifier_zext);
if (!rewritten)
continue;
if (err)
goto free_used_maps;
- err = bpf_prog_new_fd(prog);
- if (err < 0) {
- /* failed to allocate fd.
- * bpf_prog_put() is needed because the above
- * bpf_prog_alloc_id() has published the prog
- * to the userspace and the userspace may
- * have refcnt-ed it through BPF_PROG_GET_FD_BY_ID.
- */
- bpf_prog_put(prog);
- return err;
- }
-
+ /* Upon success of bpf_prog_alloc_id(), the BPF prog is
+ * effectively publicly exposed. However, retrieving via
+ * bpf_prog_get_fd_by_id() will take another reference,
+ * therefore it cannot be gone underneath us.
+ *
+ * Only for the time /after/ successful bpf_prog_new_fd()
+ * and before returning to userspace, we might just hold
+ * one reference and any parallel close on that fd could
+ * rip everything out. Hence, below notifications must
+ * happen before bpf_prog_new_fd().
+ *
+ * Also, any failure handling from this point onwards must
+ * be using bpf_prog_put() given the program is exposed.
+ */
bpf_prog_kallsyms_add(prog);
perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0);
+
+ err = bpf_prog_new_fd(prog);
+ if (err < 0)
+ bpf_prog_put(prog);
return err;
free_used_maps:
reg->smax_value = S64_MAX;
reg->umin_value = 0;
reg->umax_value = U64_MAX;
-
- /* constant backtracking is enabled for root only for now */
- reg->precise = capable(CAP_SYS_ADMIN) ? false : true;
}
/* Mark a register as having a completely unknown (scalar) value. */
__mark_reg_not_init(regs + regno);
return;
}
- __mark_reg_unknown(regs + regno);
+ regs += regno;
+ __mark_reg_unknown(regs);
+ /* constant backtracking is enabled for root without bpf2bpf calls */
+ regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
+ true : false;
}
static void __mark_reg_not_init(struct bpf_reg_state *reg)
}
if (is_narrower_load && size < target_size) {
- u8 shift = (off & (size_default - 1)) * 8;
-
+ u8 shift = bpf_ctx_narrow_load_shift(off, size,
+ size_default);
if (ctx_field_size <= 4) {
if (shift)
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* kernel/configs.c
* Echo the kernel .config file used to build the kernel
* Copyright (C) 2002 Randy Dunlap <rdunlap@xenotime.net>
* Copyright (C) 2002 Al Stone <ahs3@fc.hp.com>
* Copyright (C) 2002 Hewlett-Packard Company
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/kernel.h>
BUG_ON(cred == current->cred);
BUG_ON(cred == current->real_cred);
- call_rcu(&cred->rcu, put_cred_rcu);
+ if (cred->non_rcu)
+ put_cred_rcu(&cred->rcu);
+ else
+ call_rcu(&cred->rcu, put_cred_rcu);
}
EXPORT_SYMBOL(__put_cred);
old = task->cred;
memcpy(new, old, sizeof(struct cred));
+ new->non_rcu = 0;
atomic_set(&new->usage, 1);
set_cred_subscribers(new, 0);
get_group_info(new->group_info);
validate_creds(old);
validate_creds(new);
- get_cred(new);
+
+ /*
+ * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'.
+ *
+ * That means that we do not clear the 'non_rcu' flag, since
+ * we are only installing the cred into the thread-synchronous
+ * '->cred' pointer, not the '->real_cred' pointer that is
+ * visible to other threads under RCU.
+ *
+ * Also note that we did validate_creds() manually, not depending
+ * on the validation in 'get_cred()'.
+ */
+ get_new_cred((struct cred *)new);
alter_cred_subscribers(new, 1);
rcu_assign_pointer(current->cred, new);
alter_cred_subscribers(old, -1);
validate_creds(old);
*new = *old;
+ new->non_rcu = 0;
atomic_set(&new->usage, 1);
set_cred_subscribers(new, 0);
get_uid(new->user);
*/
struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
{
- int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
- size_t count = PAGE_ALIGN(size) >> PAGE_SHIFT;
- size_t align = get_order(PAGE_ALIGN(size));
+ size_t count = size >> PAGE_SHIFT;
struct page *page = NULL;
struct cma *cma = NULL;
/* CMA can be used only in the context which permits sleeping */
if (cma && gfpflags_allow_blocking(gfp)) {
- align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
- page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN);
+ size_t align = get_order(size);
+ size_t cma_align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
+
+ page = cma_alloc(cma, count, cma_align, gfp & __GFP_NOWARN);
}
- /* Fallback allocation of normal pages */
- if (!page)
- page = alloc_pages_node(node, gfp, align);
return page;
}
*/
void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
{
- if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT))
+ if (!cma_release(dev_get_cma_area(dev), page,
+ PAGE_ALIGN(size) >> PAGE_SHIFT))
__free_pages(page, get_order(size));
}
{
u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
- if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma)
- max_dma = dev->bus_dma_mask;
-
return (1ULL << (fls64(max_dma) - 1)) * 2 - 1;
}
struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
{
+ size_t alloc_size = PAGE_ALIGN(size);
+ int node = dev_to_node(dev);
struct page *page = NULL;
u64 phys_mask;
gfp &= ~__GFP_ZERO;
gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
&phys_mask);
+ page = dma_alloc_contiguous(dev, alloc_size, gfp);
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ dma_free_contiguous(dev, page, alloc_size);
+ page = NULL;
+ }
again:
- page = dma_alloc_contiguous(dev, size, gfp);
+ if (!page)
+ page = alloc_pages_node(node, gfp, get_order(alloc_size));
if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
dma_free_contiguous(dev, page, size);
page = NULL;
if (!page)
return NULL;
- if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+ if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+ !force_dma_unencrypted(dev)) {
/* remove any dirty cache lines on the kernel alias */
if (!PageHighMem(page))
arch_dma_prep_coherent(page, size);
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
/* return the page pointer as the opaque cookie */
return page;
}
{
unsigned int page_order = get_order(size);
- if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
+ if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
+ !force_dma_unencrypted(dev)) {
/* cpu_addr is a struct page cookie, not a kernel address */
__dma_direct_free_pages(dev, size, cpu_addr);
return;
int ret;
if (!dev_is_dma_coherent(dev)) {
+ unsigned long pfn;
+
if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
return -ENXIO;
- page = pfn_to_page(arch_dma_coherent_to_pfn(dev, cpu_addr,
- dma_addr));
+ /* If the PFN is not valid, we do not have a struct page */
+ pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
+ if (!pfn_valid(pfn))
+ return -ENXIO;
+ page = pfn_to_page(pfn);
} else {
page = virt_to_page(cpu_addr);
}
}
EXPORT_SYMBOL(dma_get_sgtable_attrs);
+#ifdef CONFIG_MMU
+/*
+ * Return the page attributes used for mapping dma_alloc_* memory, either in
+ * kernel space if remapping is needed, or to userspace through dma_mmap_*.
+ */
+pgprot_t dma_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs)
+{
+ if (dev_is_dma_coherent(dev) ||
+ (IS_ENABLED(CONFIG_DMA_NONCOHERENT_CACHE_SYNC) &&
+ (attrs & DMA_ATTR_NON_CONSISTENT)))
+ return prot;
+ if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_MMAP_PGPROT))
+ return arch_dma_mmap_pgprot(dev, prot, attrs);
+ return pgprot_noncached(prot);
+}
+#endif /* CONFIG_MMU */
+
/*
* Create userspace mapping for the DMA-coherent memory.
*/
unsigned long pfn;
int ret = -ENXIO;
- vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
+ vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
if (!dev_is_dma_coherent(dev)) {
if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
return -ENXIO;
+
+ /* If the PFN is not valid, we do not have a struct page */
pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
+ if (!pfn_valid(pfn))
+ return -ENXIO;
} else {
pfn = page_to_pfn(virt_to_page(cpu_addr));
}
/* create a coherent mapping */
ret = dma_common_contiguous_remap(page, size, VM_USERMAP,
- arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs),
+ dma_pgprot(dev, PAGE_KERNEL, attrs),
__builtin_return_address(0));
if (!ret) {
__dma_direct_free_pages(dev, size, page);
goto err_unlock;
}
- perf_install_in_context(ctx, event, cpu);
+ perf_install_in_context(ctx, event, event->cpu);
perf_unpin_context(ctx);
mutex_unlock(&ctx->mutex);
if (group_dead)
kill_orphaned_pgrp(tsk->group_leader, NULL);
+ tsk->exit_state = EXIT_ZOMBIE;
if (unlikely(tsk->ptrace)) {
int sig = thread_group_leader(tsk) &&
thread_group_empty(tsk) &&
autoreap = true;
}
- tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
- if (tsk->exit_state == EXIT_DEAD)
+ if (autoreap) {
+ tsk->exit_state = EXIT_DEAD;
list_add(&tsk->ptrace_entry, &dead);
+ }
/* mt-exec, de_thread() is waiting for group leader */
if (unlikely(tsk->signal->notify_count < 0))
WARN_ON(tsk == current);
cgroup_free(tsk);
- task_numa_free(tsk);
+ task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
* Determine the number of vectors which need interrupt affinities
* assigned. If the pre/post request exhausts the available vectors
* then nothing to do here except for invoking the calc_sets()
- * callback so the device driver can adjust to the situation. If there
- * is only a single vector, then managing the queue is pointless as
- * well.
+ * callback so the device driver can adjust to the situation.
*/
- if (nvecs > 1 && nvecs > affd->pre_vectors + affd->post_vectors)
+ if (nvecs > affd->pre_vectors + affd->post_vectors)
affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
else
affvecs = 0;
}
}
+static void irq_sysfs_del(struct irq_desc *desc)
+{
+ /*
+ * If irq_sysfs_init() has not yet been invoked (early boot), then
+ * irq_kobj_base is NULL and the descriptor was never added.
+ * kobject_del() complains about a object with no parent, so make
+ * it conditional.
+ */
+ if (irq_kobj_base)
+ kobject_del(&desc->kobj);
+}
+
static int __init irq_sysfs_init(void)
{
struct irq_desc *desc;
};
static void irq_sysfs_add(int irq, struct irq_desc *desc) {}
+static void irq_sysfs_del(struct irq_desc *desc) {}
#endif /* CONFIG_SYSFS */
* The sysfs entry must be serialized against a concurrent
* irq_sysfs_init() as well.
*/
- kobject_del(&desc->kobj);
+ irq_sysfs_del(desc);
delete_irq_desc(irq);
/*
{
char namebuf[KSYM_NAME_LEN];
- if (is_ksym_addr(addr))
- return !!get_symbol_pos(addr, symbolsize, offset);
+ if (is_ksym_addr(addr)) {
+ get_symbol_pos(addr, symbolsize, offset);
+ return 1;
+ }
return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
!!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
}
*/
static void do_optimize_kprobes(void)
{
+ lockdep_assert_held(&text_mutex);
/*
* The optimization/unoptimization refers online_cpus via
* stop_machine() and cpu-hotplug modifies online_cpus.
list_empty(&optimizing_list))
return;
- mutex_lock(&text_mutex);
arch_optimize_kprobes(&optimizing_list);
- mutex_unlock(&text_mutex);
}
/*
{
struct optimized_kprobe *op, *tmp;
+ lockdep_assert_held(&text_mutex);
/* See comment in do_optimize_kprobes() */
lockdep_assert_cpus_held();
if (list_empty(&unoptimizing_list))
return;
- mutex_lock(&text_mutex);
arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
/* Loop free_list for disarming */
list_for_each_entry_safe(op, tmp, &freeing_list, list) {
} else
list_del_init(&op->list);
}
- mutex_unlock(&text_mutex);
}
/* Reclaim all kprobes on the free_list */
{
mutex_lock(&kprobe_mutex);
cpus_read_lock();
+ mutex_lock(&text_mutex);
/* Lock modules while optimizing kprobes */
mutex_lock(&module_mutex);
do_free_cleaned_kprobes();
mutex_unlock(&module_mutex);
+ mutex_unlock(&text_mutex);
cpus_read_unlock();
mutex_unlock(&kprobe_mutex);
unsigned long nr_stack_trace_entries;
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+#ifdef CONFIG_PROVE_LOCKING
/*
* Stack-trace: tightly packed array of stack backtrace
* addresses. Protected by the graph_lock.
DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
#endif
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+#ifdef CONFIG_PROVE_LOCKING
/*
* Locking printouts:
*/
#endif
}
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+#ifdef CONFIG_PROVE_LOCKING
static int mark_lock(struct task_struct *curr, struct held_lock *this,
enum lock_usage_bit new_bit);
return ret;
}
-#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
+#else /* CONFIG_PROVE_LOCKING */
static inline int
mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
return 0;
}
-#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
+#endif /* CONFIG_PROVE_LOCKING */
/*
* Initialize a lock instance's lock-class mapping info:
*/
static void check_flags(unsigned long flags)
{
-#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \
- defined(CONFIG_TRACE_IRQFLAGS)
+#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP)
if (!debug_locks)
return;
static int lockdep_stats_show(struct seq_file *m, void *v)
{
- struct lock_class *class;
unsigned long nr_unused = 0, nr_uncategorized = 0,
nr_irq_safe = 0, nr_irq_unsafe = 0,
nr_softirq_safe = 0, nr_softirq_unsafe = 0,
sum_forward_deps = 0;
#ifdef CONFIG_PROVE_LOCKING
+ struct lock_class *class;
+
list_for_each_entry(class, &all_lock_classes, lock_entry) {
if (class->usage_mask == 0)
might_sleep();
+#ifdef CONFIG_DEBUG_MUTEXES
+ DEBUG_LOCKS_WARN_ON(lock->magic != lock);
+#endif
+
ww = container_of(lock, struct ww_mutex, base);
if (use_ww_ctx && ww_ctx) {
if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
*/
int __sched mutex_trylock(struct mutex *lock)
{
- bool locked = __mutex_trylock(lock);
+ bool locked;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+ DEBUG_LOCKS_WARN_ON(lock->magic != lock);
+#endif
+ locked = __mutex_trylock(lock);
if (locked)
mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
preempt_disable();
rcu_read_lock();
owner = rwsem_owner_flags(sem, &flags);
- if ((flags & nonspinnable) || (owner && !owner_on_cpu(owner)))
+ /*
+ * Don't check the read-owner as the entry may be stale.
+ */
+ if ((flags & nonspinnable) ||
+ (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner)))
ret = false;
rcu_read_unlock();
preempt_enable();
atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
adjustment = 0;
if (rwsem_optimistic_spin(sem, false)) {
+ /* rwsem_optimistic_spin() implies ACQUIRE on success */
/*
* Wake up other readers in the wait list if the front
* waiter is a reader.
}
return sem;
} else if (rwsem_reader_phase_trylock(sem, waiter.last_rowner)) {
+ /* rwsem_reader_phase_trylock() implies ACQUIRE on success */
return sem;
}
*/
if (adjustment && !(atomic_long_read(&sem->count) &
(RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+ /* Provide lock ACQUIRE */
+ smp_acquire__after_ctrl_dep();
raw_spin_unlock_irq(&sem->wait_lock);
rwsem_set_reader_owned(sem);
lockevent_inc(rwsem_rlock_fast);
wake_up_q(&wake_q);
/* wait to be given the lock */
- while (true) {
+ for (;;) {
set_current_state(state);
- if (!waiter.task)
+ if (!smp_load_acquire(&waiter.task)) {
+ /* Matches rwsem_mark_wake()'s smp_store_release(). */
break;
+ }
if (signal_pending_state(state, current)) {
raw_spin_lock_irq(&sem->wait_lock);
if (waiter.task)
goto out_nolock;
raw_spin_unlock_irq(&sem->wait_lock);
+ /* Ordered by sem->wait_lock against rwsem_mark_wake(). */
break;
}
schedule();
__set_current_state(TASK_RUNNING);
lockevent_inc(rwsem_rlock);
return sem;
+
out_nolock:
list_del(&waiter.list);
if (list_empty(&sem->wait_list)) {
/* do optimistic spinning and steal lock if possible */
if (rwsem_can_spin_on_owner(sem, RWSEM_WR_NONSPINNABLE) &&
- rwsem_optimistic_spin(sem, true))
+ rwsem_optimistic_spin(sem, true)) {
+ /* rwsem_optimistic_spin() implies ACQUIRE on success */
return sem;
+ }
/*
* Disable reader optimistic spinning for this rwsem after
wait:
/* wait until we successfully acquire the lock */
set_current_state(state);
- while (true) {
- if (rwsem_try_write_lock(sem, wstate))
+ for (;;) {
+ if (rwsem_try_write_lock(sem, wstate)) {
+ /* rwsem_try_write_lock() implies ACQUIRE on success */
break;
+ }
raw_spin_unlock_irq(&sem->wait_lock);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
-#include <linux/device.h>
-#include <linux/io.h>
-#include <linux/kasan.h>
-#include <linux/memory_hotplug.h>
-#include <linux/mm.h>
-#include <linux/pfn_t.h>
-#include <linux/swap.h>
-#include <linux/swapops.h>
-#include <linux/types.h>
-#include <linux/wait_bit.h>
-#include <linux/xarray.h>
-
-static DEFINE_XARRAY(pgmap_array);
-#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
-#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL(devmap_managed_key);
-static atomic_t devmap_managed_enable;
-
-static void devmap_managed_enable_put(void *data)
-{
- if (atomic_dec_and_test(&devmap_managed_enable))
- static_branch_disable(&devmap_managed_key);
-}
-
-static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
-{
- if (!pgmap->ops || !pgmap->ops->page_free) {
- WARN(1, "Missing page_free method\n");
- return -EINVAL;
- }
-
- if (atomic_inc_return(&devmap_managed_enable) == 1)
- static_branch_enable(&devmap_managed_key);
- return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
-}
-#else
-static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
-{
- return -EINVAL;
-}
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
-
-static void pgmap_array_delete(struct resource *res)
-{
- xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
- NULL, GFP_KERNEL);
- synchronize_rcu();
-}
-
-static unsigned long pfn_first(struct dev_pagemap *pgmap)
-{
- return PHYS_PFN(pgmap->res.start) +
- vmem_altmap_offset(pgmap_altmap(pgmap));
-}
-
-static unsigned long pfn_end(struct dev_pagemap *pgmap)
-{
- const struct resource *res = &pgmap->res;
-
- return (res->start + resource_size(res)) >> PAGE_SHIFT;
-}
-
-static unsigned long pfn_next(unsigned long pfn)
-{
- if (pfn % 1024 == 0)
- cond_resched();
- return pfn + 1;
-}
-
-#define for_each_device_pfn(pfn, map) \
- for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
-
-static void dev_pagemap_kill(struct dev_pagemap *pgmap)
-{
- if (pgmap->ops && pgmap->ops->kill)
- pgmap->ops->kill(pgmap);
- else
- percpu_ref_kill(pgmap->ref);
-}
-
-static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
- if (pgmap->ops && pgmap->ops->cleanup) {
- pgmap->ops->cleanup(pgmap);
- } else {
- wait_for_completion(&pgmap->done);
- percpu_ref_exit(pgmap->ref);
- }
-}
-
-static void devm_memremap_pages_release(void *data)
-{
- struct dev_pagemap *pgmap = data;
- struct device *dev = pgmap->dev;
- struct resource *res = &pgmap->res;
- unsigned long pfn;
- int nid;
-
- dev_pagemap_kill(pgmap);
- for_each_device_pfn(pfn, pgmap)
- put_page(pfn_to_page(pfn));
- dev_pagemap_cleanup(pgmap);
-
- /* pages are dead and unused, undo the arch mapping */
- nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
-
- mem_hotplug_begin();
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- pfn = PHYS_PFN(res->start);
- __remove_pages(page_zone(pfn_to_page(pfn)), pfn,
- PHYS_PFN(resource_size(res)), NULL);
- } else {
- arch_remove_memory(nid, res->start, resource_size(res),
- pgmap_altmap(pgmap));
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- }
- mem_hotplug_done();
-
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- pgmap_array_delete(res);
- dev_WARN_ONCE(dev, pgmap->altmap.alloc,
- "%s: failed to free all reserved pages\n", __func__);
-}
-
-static void dev_pagemap_percpu_release(struct percpu_ref *ref)
-{
- struct dev_pagemap *pgmap =
- container_of(ref, struct dev_pagemap, internal_ref);
-
- complete(&pgmap->done);
-}
-
-/**
- * devm_memremap_pages - remap and provide memmap backing for the given resource
- * @dev: hosting device for @res
- * @pgmap: pointer to a struct dev_pagemap
- *
- * Notes:
- * 1/ At a minimum the res and type members of @pgmap must be initialized
- * by the caller before passing it to this function
- *
- * 2/ The altmap field may optionally be initialized, in which case
- * PGMAP_ALTMAP_VALID must be set in pgmap->flags.
- *
- * 3/ The ref field may optionally be provided, in which pgmap->ref must be
- * 'live' on entry and will be killed and reaped at
- * devm_memremap_pages_release() time, or if this routine fails.
- *
- * 4/ res is expected to be a host memory range that could feasibly be
- * treated as a "System RAM" range, i.e. not a device mmio range, but
- * this is not enforced.
- */
-void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
-{
- struct resource *res = &pgmap->res;
- struct dev_pagemap *conflict_pgmap;
- struct mhp_restrictions restrictions = {
- /*
- * We do not want any optional features only our own memmap
- */
- .altmap = pgmap_altmap(pgmap),
- };
- pgprot_t pgprot = PAGE_KERNEL;
- int error, nid, is_ram;
- bool need_devmap_managed = true;
-
- switch (pgmap->type) {
- case MEMORY_DEVICE_PRIVATE:
- if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
- WARN(1, "Device private memory not supported\n");
- return ERR_PTR(-EINVAL);
- }
- if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
- WARN(1, "Missing migrate_to_ram method\n");
- return ERR_PTR(-EINVAL);
- }
- break;
- case MEMORY_DEVICE_FS_DAX:
- if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
- IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
- WARN(1, "File system DAX not supported\n");
- return ERR_PTR(-EINVAL);
- }
- break;
- case MEMORY_DEVICE_DEVDAX:
- case MEMORY_DEVICE_PCI_P2PDMA:
- need_devmap_managed = false;
- break;
- default:
- WARN(1, "Invalid pgmap type %d\n", pgmap->type);
- break;
- }
-
- if (!pgmap->ref) {
- if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
- return ERR_PTR(-EINVAL);
-
- init_completion(&pgmap->done);
- error = percpu_ref_init(&pgmap->internal_ref,
- dev_pagemap_percpu_release, 0, GFP_KERNEL);
- if (error)
- return ERR_PTR(error);
- pgmap->ref = &pgmap->internal_ref;
- } else {
- if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
- WARN(1, "Missing reference count teardown definition\n");
- return ERR_PTR(-EINVAL);
- }
- }
-
- if (need_devmap_managed) {
- error = devmap_managed_enable_get(dev, pgmap);
- if (error)
- return ERR_PTR(error);
- }
-
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
- if (conflict_pgmap) {
- dev_WARN(dev, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
- if (conflict_pgmap) {
- dev_WARN(dev, "Conflicting mapping in same section\n");
- put_dev_pagemap(conflict_pgmap);
- error = -ENOMEM;
- goto err_array;
- }
-
- is_ram = region_intersects(res->start, resource_size(res),
- IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
-
- if (is_ram != REGION_DISJOINT) {
- WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
- is_ram == REGION_MIXED ? "mixed" : "ram", res);
- error = -ENXIO;
- goto err_array;
- }
-
- pgmap->dev = dev;
-
- error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
- PHYS_PFN(res->end), pgmap, GFP_KERNEL));
- if (error)
- goto err_array;
-
- nid = dev_to_node(dev);
- if (nid < 0)
- nid = numa_mem_id();
-
- error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
- resource_size(res));
- if (error)
- goto err_pfn_remap;
-
- mem_hotplug_begin();
-
- /*
- * For device private memory we call add_pages() as we only need to
- * allocate and initialize struct page for the device memory. More-
- * over the device memory is un-accessible thus we do not want to
- * create a linear mapping for the memory like arch_add_memory()
- * would do.
- *
- * For all other device memory types, which are accessible by
- * the CPU, we do want the linear mapping and thus use
- * arch_add_memory().
- */
- if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
- error = add_pages(nid, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), &restrictions);
- } else {
- error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
- if (error) {
- mem_hotplug_done();
- goto err_kasan;
- }
-
- error = arch_add_memory(nid, res->start, resource_size(res),
- &restrictions);
- }
-
- if (!error) {
- struct zone *zone;
-
- zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
- move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), restrictions.altmap);
- }
-
- mem_hotplug_done();
- if (error)
- goto err_add_memory;
-
- /*
- * Initialization of the pages has been deferred until now in order
- * to allow us to do the work while not holding the hotplug lock.
- */
- memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
- PHYS_PFN(res->start),
- PHYS_PFN(resource_size(res)), pgmap);
- percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
-
- error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
- pgmap);
- if (error)
- return ERR_PTR(error);
-
- return __va(res->start);
-
- err_add_memory:
- kasan_remove_zero_shadow(__va(res->start), resource_size(res));
- err_kasan:
- untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
- err_pfn_remap:
- pgmap_array_delete(res);
- err_array:
- dev_pagemap_kill(pgmap);
- dev_pagemap_cleanup(pgmap);
- return ERR_PTR(error);
-}
-EXPORT_SYMBOL_GPL(devm_memremap_pages);
-
-void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
-{
- devm_release_action(dev, devm_memremap_pages_release, pgmap);
-}
-EXPORT_SYMBOL_GPL(devm_memunmap_pages);
-
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
- /* number of pfns from base where pfn_to_page() is valid */
- if (altmap)
- return altmap->reserve + altmap->free;
- return 0;
-}
-
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
-{
- altmap->alloc -= nr_pfns;
-}
-
-/**
- * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
- * @pfn: page frame number to lookup page_map
- * @pgmap: optional known pgmap that already has a reference
- *
- * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap
- * is non-NULL but does not cover @pfn the reference to it will be released.
- */
-struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
- struct dev_pagemap *pgmap)
-{
- resource_size_t phys = PFN_PHYS(pfn);
-
- /*
- * In the cached case we're already holding a live reference.
- */
- if (pgmap) {
- if (phys >= pgmap->res.start && phys <= pgmap->res.end)
- return pgmap;
- put_dev_pagemap(pgmap);
- }
-
- /* fall back to slow path lookup */
- rcu_read_lock();
- pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
- if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
- pgmap = NULL;
- rcu_read_unlock();
-
- return pgmap;
-}
-EXPORT_SYMBOL_GPL(get_dev_pagemap);
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-void __put_devmap_managed_page(struct page *page)
-{
- int count = page_ref_dec_return(page);
-
- /*
- * If refcount is 1 then page is freed and refcount is stable as nobody
- * holds a reference on the page.
- */
- if (count == 1) {
- /* Clear Active bit in case of parallel mark_page_accessed */
- __ClearPageActive(page);
- __ClearPageWaiters(page);
-
- mem_cgroup_uncharge(page);
-
- page->pgmap->ops->page_free(page);
- } else if (!count)
- __put_page(page);
-}
-EXPORT_SYMBOL(__put_devmap_managed_page);
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
/*
* Modules' sections will be aligned on page boundaries
* to ensure complete separation of code and data, but
- * only when CONFIG_STRICT_MODULE_RWX=y
+ * only when CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y
*/
-#ifdef CONFIG_STRICT_MODULE_RWX
+#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX
# define debug_align(X) ALIGN(X, PAGE_SIZE)
#else
# define debug_align(X) (X)
static inline void sched_submit_work(struct task_struct *tsk)
{
- if (!tsk->state || tsk_is_pi_blocked(tsk))
+ if (!tsk->state)
return;
/*
preempt_enable_no_resched();
}
+ if (tsk_is_pi_blocked(tsk))
+ return;
+
/*
* If we are going to sleep and we have plugged IO queued,
* make sure to submit it to avoid deadlocks.
return retval;
}
-static int sched_read_attr(struct sched_attr __user *uattr,
- struct sched_attr *attr,
- unsigned int usize)
+/*
+ * Copy the kernel size attribute structure (which might be larger
+ * than what user-space knows about) to user-space.
+ *
+ * Note that all cases are valid: user-space buffer can be larger or
+ * smaller than the kernel-space buffer. The usual case is that both
+ * have the same size.
+ */
+static int
+sched_attr_copy_to_user(struct sched_attr __user *uattr,
+ struct sched_attr *kattr,
+ unsigned int usize)
{
- int ret;
+ unsigned int ksize = sizeof(*kattr);
if (!access_ok(uattr, usize))
return -EFAULT;
/*
- * If we're handed a smaller struct than we know of,
- * ensure all the unknown bits are 0 - i.e. old
- * user-space does not get uncomplete information.
+ * sched_getattr() ABI forwards and backwards compatibility:
+ *
+ * If usize == ksize then we just copy everything to user-space and all is good.
+ *
+ * If usize < ksize then we only copy as much as user-space has space for,
+ * this keeps ABI compatibility as well. We skip the rest.
+ *
+ * If usize > ksize then user-space is using a newer version of the ABI,
+ * which part the kernel doesn't know about. Just ignore it - tooling can
+ * detect the kernel's knowledge of attributes from the attr->size value
+ * which is set to ksize in this case.
*/
- if (usize < sizeof(*attr)) {
- unsigned char *addr;
- unsigned char *end;
-
- addr = (void *)attr + usize;
- end = (void *)attr + sizeof(*attr);
+ kattr->size = min(usize, ksize);
- for (; addr < end; addr++) {
- if (*addr)
- return -EFBIG;
- }
-
- attr->size = usize;
- }
-
- ret = copy_to_user(uattr, attr, attr->size);
- if (ret)
+ if (copy_to_user(uattr, kattr, kattr->size))
return -EFAULT;
return 0;
* sys_sched_getattr - similar to sched_getparam, but with sched_attr
* @pid: the pid in question.
* @uattr: structure containing the extended parameters.
- * @size: sizeof(attr) for fwd/bwd comp.
+ * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility.
* @flags: for future extension.
*/
SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
- unsigned int, size, unsigned int, flags)
+ unsigned int, usize, unsigned int, flags)
{
- struct sched_attr attr = {
- .size = sizeof(struct sched_attr),
- };
+ struct sched_attr kattr = { };
struct task_struct *p;
int retval;
- if (!uattr || pid < 0 || size > PAGE_SIZE ||
- size < SCHED_ATTR_SIZE_VER0 || flags)
+ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
+ usize < SCHED_ATTR_SIZE_VER0 || flags)
return -EINVAL;
rcu_read_lock();
if (retval)
goto out_unlock;
- attr.sched_policy = p->policy;
+ kattr.sched_policy = p->policy;
if (p->sched_reset_on_fork)
- attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
if (task_has_dl_policy(p))
- __getparam_dl(p, &attr);
+ __getparam_dl(p, &kattr);
else if (task_has_rt_policy(p))
- attr.sched_priority = p->rt_priority;
+ kattr.sched_priority = p->rt_priority;
else
- attr.sched_nice = task_nice(p);
+ kattr.sched_nice = task_nice(p);
#ifdef CONFIG_UCLAMP_TASK
- attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
- attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif
rcu_read_unlock();
- retval = sched_read_attr(uattr, &attr, size);
- return retval;
+ return sched_attr_copy_to_user(uattr, &kattr, usize);
out_unlock:
rcu_read_unlock();
struct task_struct *thread;
bool work_in_progress;
+ bool limits_changed;
bool need_freq_update;
};
!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
- if (unlikely(sg_policy->need_freq_update))
+ if (unlikely(sg_policy->limits_changed)) {
+ sg_policy->limits_changed = false;
+ sg_policy->need_freq_update = true;
return true;
+ }
delta_ns = time - sg_policy->last_freq_update_time;
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
- sg_policy->need_freq_update = true;
+ sg_policy->limits_changed = true;
}
static void sugov_update_single(struct update_util_data *hook, u64 time,
if (!sugov_should_update_freq(sg_policy, time))
return;
- busy = sugov_cpu_is_busy(sg_cpu);
+ /* Limits may have changed, don't skip frequency update */
+ busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
util = sugov_get_util(sg_cpu);
max = sg_cpu->max;
sg_policy->last_freq_update_time = 0;
sg_policy->next_freq = 0;
sg_policy->work_in_progress = false;
+ sg_policy->limits_changed = false;
sg_policy->need_freq_update = false;
sg_policy->cached_raw_freq = 0;
mutex_unlock(&sg_policy->work_lock);
}
- sg_policy->need_freq_update = true;
+ sg_policy->limits_changed = true;
}
struct cpufreq_governor schedutil_gov = {
}
deactivate_task(rq, next_task, 0);
- sub_running_bw(&next_task->dl, &rq->dl);
- sub_rq_bw(&next_task->dl, &rq->dl);
set_task_cpu(next_task, later_rq->cpu);
- add_rq_bw(&next_task->dl, &later_rq->dl);
/*
* Update the later_rq clock here, because the clock is used
* by the cpufreq_update_util() inside __add_running_bw().
*/
update_rq_clock(later_rq);
- add_running_bw(&next_task->dl, &later_rq->dl);
activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
ret = 1;
resched = true;
deactivate_task(src_rq, p, 0);
- sub_running_bw(&p->dl, &src_rq->dl);
- sub_rq_bw(&p->dl, &src_rq->dl);
set_task_cpu(p, this_cpu);
- add_rq_bw(&p->dl, &this_rq->dl);
- add_running_bw(&p->dl, &this_rq->dl);
activate_task(this_rq, p, 0);
dmin = p->dl.deadline;
unsigned long faults[0];
};
+/*
+ * For functions that can be called in multiple contexts that permit reading
+ * ->numa_group (see struct task_struct for locking rules).
+ */
+static struct numa_group *deref_task_numa_group(struct task_struct *p)
+{
+ return rcu_dereference_check(p->numa_group, p == current ||
+ (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
+}
+
+static struct numa_group *deref_curr_numa_group(struct task_struct *p)
+{
+ return rcu_dereference_protected(p->numa_group, p == current);
+}
+
static inline unsigned long group_faults_priv(struct numa_group *ng);
static inline unsigned long group_faults_shared(struct numa_group *ng);
{
unsigned long smin = task_scan_min(p);
unsigned long period = smin;
+ struct numa_group *ng;
/* Scale the maximum scan period with the amount of shared memory. */
- if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
+ rcu_read_lock();
+ ng = rcu_dereference(p->numa_group);
+ if (ng) {
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);
period *= shared + 1;
period /= private + shared + 1;
}
+ rcu_read_unlock();
return max(smin, period);
}
{
unsigned long smin = task_scan_min(p);
unsigned long smax;
+ struct numa_group *ng;
/* Watch for min being lower than max due to floor calculations */
smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);
/* Scale the maximum scan period with the amount of shared memory. */
- if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
+ ng = deref_curr_numa_group(p);
+ if (ng) {
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);
unsigned long period = smax;
p->numa_scan_period = sysctl_numa_balancing_scan_delay;
p->numa_work.next = &p->numa_work;
p->numa_faults = NULL;
- p->numa_group = NULL;
+ RCU_INIT_POINTER(p->numa_group, NULL);
p->last_task_numa_placement = 0;
p->last_sum_exec_runtime = 0;
pid_t task_numa_group_id(struct task_struct *p)
{
- return p->numa_group ? p->numa_group->gid : 0;
+ struct numa_group *ng;
+ pid_t gid = 0;
+
+ rcu_read_lock();
+ ng = rcu_dereference(p->numa_group);
+ if (ng)
+ gid = ng->gid;
+ rcu_read_unlock();
+
+ return gid;
}
/*
static inline unsigned long group_faults(struct task_struct *p, int nid)
{
- if (!p->numa_group)
+ struct numa_group *ng = deref_task_numa_group(p);
+
+ if (!ng)
return 0;
- return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
- p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
+ return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+ ng->faults[task_faults_idx(NUMA_MEM, nid, 1)];
}
static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
static inline unsigned long group_weight(struct task_struct *p, int nid,
int dist)
{
+ struct numa_group *ng = deref_task_numa_group(p);
unsigned long faults, total_faults;
- if (!p->numa_group)
+ if (!ng)
return 0;
- total_faults = p->numa_group->total_faults;
+ total_faults = ng->total_faults;
if (!total_faults)
return 0;
bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int src_nid, int dst_cpu)
{
- struct numa_group *ng = p->numa_group;
+ struct numa_group *ng = deref_curr_numa_group(p);
int dst_nid = cpu_to_node(dst_cpu);
int last_cpupid, this_cpupid;
static void task_numa_compare(struct task_numa_env *env,
long taskimp, long groupimp, bool maymove)
{
+ struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
+ long imp = p_ng ? groupimp : taskimp;
struct task_struct *cur;
long src_load, dst_load;
- long load;
- long imp = env->p->numa_group ? groupimp : taskimp;
- long moveimp = imp;
int dist = env->dist;
+ long moveimp = imp;
+ long load;
if (READ_ONCE(dst_rq->numa_migrate_on))
return;
* If dst and source tasks are in the same NUMA group, or not
* in any group then look only at task weights.
*/
- if (cur->numa_group == env->p->numa_group) {
+ cur_ng = rcu_dereference(cur->numa_group);
+ if (cur_ng == p_ng) {
imp = taskimp + task_weight(cur, env->src_nid, dist) -
task_weight(cur, env->dst_nid, dist);
/*
* Add some hysteresis to prevent swapping the
* tasks within a group over tiny differences.
*/
- if (cur->numa_group)
+ if (cur_ng)
imp -= imp / 16;
} else {
/*
* Compare the group weights. If a task is all by itself
* (not part of a group), use the task weight instead.
*/
- if (cur->numa_group && env->p->numa_group)
+ if (cur_ng && p_ng)
imp += group_weight(cur, env->src_nid, dist) -
group_weight(cur, env->dst_nid, dist);
else
.best_imp = 0,
.best_cpu = -1,
};
+ unsigned long taskweight, groupweight;
struct sched_domain *sd;
+ long taskimp, groupimp;
+ struct numa_group *ng;
struct rq *best_rq;
- unsigned long taskweight, groupweight;
int nid, ret, dist;
- long taskimp, groupimp;
/*
* Pick the lowest SD_NUMA domain, as that would have the smallest
* multiple NUMA nodes; in order to better consolidate the group,
* we need to check other locations.
*/
- if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) {
+ ng = deref_curr_numa_group(p);
+ if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) {
for_each_online_node(nid) {
if (nid == env.src_nid || nid == p->numa_preferred_nid)
continue;
* A task that migrated to a second choice node will be better off
* trying for a better one later. Do not set the preferred node here.
*/
- if (p->numa_group) {
+ if (ng) {
if (env.best_cpu == -1)
nid = env.src_nid;
else
unsigned long total_faults;
u64 runtime, period;
spinlock_t *group_lock = NULL;
+ struct numa_group *ng;
/*
* The p->mm->numa_scan_seq field gets updated without
runtime = numa_get_avg_runtime(p, &period);
/* If the task is part of a group prevent parallel updates to group stats */
- if (p->numa_group) {
- group_lock = &p->numa_group->lock;
+ ng = deref_curr_numa_group(p);
+ if (ng) {
+ group_lock = &ng->lock;
spin_lock_irq(group_lock);
}
p->numa_faults[cpu_idx] += f_diff;
faults += p->numa_faults[mem_idx];
p->total_numa_faults += diff;
- if (p->numa_group) {
+ if (ng) {
/*
* safe because we can only change our own group
*
* nid and priv in a specific region because it
* is at the beginning of the numa_faults array.
*/
- p->numa_group->faults[mem_idx] += diff;
- p->numa_group->faults_cpu[mem_idx] += f_diff;
- p->numa_group->total_faults += diff;
- group_faults += p->numa_group->faults[mem_idx];
+ ng->faults[mem_idx] += diff;
+ ng->faults_cpu[mem_idx] += f_diff;
+ ng->total_faults += diff;
+ group_faults += ng->faults[mem_idx];
}
}
- if (!p->numa_group) {
+ if (!ng) {
if (faults > max_faults) {
max_faults = faults;
max_nid = nid;
}
}
- if (p->numa_group) {
- numa_group_count_active_nodes(p->numa_group);
+ if (ng) {
+ numa_group_count_active_nodes(ng);
spin_unlock_irq(group_lock);
max_nid = preferred_group_nid(p, max_nid);
}
int cpu = cpupid_to_cpu(cpupid);
int i;
- if (unlikely(!p->numa_group)) {
+ if (unlikely(!deref_curr_numa_group(p))) {
unsigned int size = sizeof(struct numa_group) +
4*nr_node_ids*sizeof(unsigned long);
if (!grp)
goto no_join;
- my_grp = p->numa_group;
+ my_grp = deref_curr_numa_group(p);
if (grp == my_grp)
goto no_join;
return;
}
-void task_numa_free(struct task_struct *p)
+/*
+ * Get rid of NUMA staticstics associated with a task (either current or dead).
+ * If @final is set, the task is dead and has reached refcount zero, so we can
+ * safely free all relevant data structures. Otherwise, there might be
+ * concurrent reads from places like load balancing and procfs, and we should
+ * reset the data back to default state without freeing ->numa_faults.
+ */
+void task_numa_free(struct task_struct *p, bool final)
{
- struct numa_group *grp = p->numa_group;
- void *numa_faults = p->numa_faults;
+ /* safe: p either is current or is being freed by current */
+ struct numa_group *grp = rcu_dereference_raw(p->numa_group);
+ unsigned long *numa_faults = p->numa_faults;
unsigned long flags;
int i;
+ if (!numa_faults)
+ return;
+
if (grp) {
spin_lock_irqsave(&grp->lock, flags);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
put_numa_group(grp);
}
- p->numa_faults = NULL;
- kfree(numa_faults);
+ if (final) {
+ p->numa_faults = NULL;
+ kfree(numa_faults);
+ } else {
+ p->total_numa_faults = 0;
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+ numa_faults[i] = 0;
+ }
}
/*
* actively using should be counted as local. This allows the
* scan rate to slow down when a workload has settled down.
*/
- ng = p->numa_group;
+ ng = deref_curr_numa_group(p);
if (!priv && !local && ng && ng->active_nodes > 1 &&
numa_is_active_node(cpu_node, ng) &&
numa_is_active_node(mem_node, ng))
if (likely(cfs_rq->runtime_remaining > 0))
return;
+ if (cfs_rq->throttled)
+ return;
/*
* if we're unable to extend our runtime we resched so that the active
* hierarchy can be throttled
if (!cfs_rq_throttled(cfs_rq))
goto next;
+ /* By the above check, this should never be true */
+ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
+
runtime = -cfs_rq->runtime_remaining + 1;
if (runtime > remaining)
runtime = remaining;
{
int node;
unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
+ struct numa_group *ng;
+ rcu_read_lock();
+ ng = rcu_dereference(p->numa_group);
for_each_online_node(node) {
if (p->numa_faults) {
tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
}
- if (p->numa_group) {
- gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
- gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
+ if (ng) {
+ gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)],
+ gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)];
}
print_numa_stats(m, node, tsf, tpf, gsf, gpf);
}
+ rcu_read_unlock();
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
if (!rcu_access_pointer(group->poll_kworker)) {
struct sched_param param = {
- .sched_priority = MAX_RT_PRIO - 1,
+ .sched_priority = 1,
};
struct kthread_worker *kworker;
mutex_unlock(&group->trigger_lock);
return ERR_CAST(kworker);
}
- sched_setscheduler(kworker->task, SCHED_FIFO, ¶m);
+ sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m);
kthread_init_delayed_work(&group->poll_work,
psi_poll_work);
rcu_assign_pointer(group->poll_kworker, kworker);
* deadlock while waiting for psi_poll_work to acquire trigger_lock
*/
if (kworker_to_destroy) {
+ /*
+ * After the RCU grace period has expired, the worker
+ * can no longer be found through group->poll_kworker.
+ * But it might have been already scheduled before
+ * that - deschedule it cleanly before destroying it.
+ */
kthread_cancel_delayed_work_sync(&group->poll_work);
+ atomic_set(&group->poll_scheduled, 0);
+
kthread_destroy_worker(kworker_to_destroy);
}
kfree(t);
handler == SIG_DFL && !(force && sig_kernel_only(sig)))
return true;
+ /* Only allow kernel generated signals to this kthread */
+ if (unlikely((t->flags & PF_KTHREAD) &&
+ (handler == SIG_KTHREAD_KERNEL) && !force))
+ return true;
+
return sig_handler_ignored(handler, sig);
}
* @task has %JOBCTL_STOP_PENDING set and is participating in a group stop.
* Group stop states are cleared and the group stop count is consumed if
* %JOBCTL_STOP_CONSUME was set. If the consumption completes the group
- * stop, the appropriate %SIGNAL_* flags are set.
+ * stop, the appropriate `SIGNAL_*` flags are set.
*
* CONTEXT:
* Must be called with @task->sighand->siglock held.
{
struct pid *pid;
+ WARN_ON(task->exit_state == 0);
pid = task_pid(task);
wake_up_all(&pid->wait_pidfd);
}
static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
{
tk->offs_boot = ktime_add(tk->offs_boot, delta);
+ /*
+ * Timespec representation for VDSO update to avoid 64bit division
+ * on every update.
+ */
+ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot);
}
/*
struct timekeeper *tk)
{
struct vdso_timestamp *vdso_ts;
- u64 nsec;
+ u64 nsec, sec;
vdata[CS_HRES_COARSE].cycle_last = tk->tkr_mono.cycle_last;
vdata[CS_HRES_COARSE].mask = tk->tkr_mono.mask;
}
vdso_ts->nsec = nsec;
- /* CLOCK_MONOTONIC_RAW */
- vdso_ts = &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
- vdso_ts->sec = tk->raw_sec;
- vdso_ts->nsec = tk->tkr_raw.xtime_nsec;
+ /* Copy MONOTONIC time for BOOTTIME */
+ sec = vdso_ts->sec;
+ /* Add the boot offset */
+ sec += tk->monotonic_to_boot.tv_sec;
+ nsec += (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift;
/* CLOCK_BOOTTIME */
vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME];
- vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
- nsec = tk->tkr_mono.xtime_nsec;
- nsec += ((u64)(tk->wall_to_monotonic.tv_nsec +
- ktime_to_ns(tk->offs_boot)) << tk->tkr_mono.shift);
+ vdso_ts->sec = sec;
+
while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift);
vdso_ts->sec++;
}
vdso_ts->nsec = nsec;
+ /* CLOCK_MONOTONIC_RAW */
+ vdso_ts = &vdata[CS_RAW].basetime[CLOCK_MONOTONIC_RAW];
+ vdso_ts->sec = tk->raw_sec;
+ vdso_ts->nsec = tk->tkr_raw.xtime_nsec;
+
/* CLOCK_TAI */
vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI];
vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset;
hnd = &iter->probe_entry->hlist;
hash = iter->probe->ops.func_hash->filter_hash;
+
+ /*
+ * A probe being registered may temporarily have an empty hash
+ * and it's at the end of the func_probes list.
+ */
+ if (!hash || hash == EMPTY_HASH)
+ return NULL;
+
size = 1 << hash->size_bits;
retry:
mutex_unlock(&ftrace_lock);
+ /*
+ * Note, there's a small window here that the func_hash->filter_hash
+ * may be NULL or empty. Need to be carefule when reading the loop.
+ */
mutex_lock(&probe->ops.func_hash->regex_lock);
orig_hash = &probe->ops.func_hash->filter_hash;
old_hash = *orig_hash;
hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash);
+ if (!hash) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
ret = ftrace_match_records(hash, glob, strlen(glob));
/* Nothing found? */
/**
* update_max_tr_single - only copy one trace over, and reset the rest
- * @tr - tracer
- * @tsk - task with the latency
- * @cpu - the cpu of the buffer to copy.
+ * @tr: tracer
+ * @tsk: task with the latency
+ * @cpu: the cpu of the buffer to copy.
*
* Flip the trace of a single CPU buffer between the @tr and the max_tr.
*/
/**
* register_tracer - register a tracer with the ftrace system.
- * @type - the plugin for the tracer
+ * @type: the plugin for the tracer
*
* Register a new plugin tracer.
*/
/**
* tracing_record_taskinfo - record the task info of a task
*
- * @task - task to record
- * @flags - TRACE_RECORD_CMDLINE for recording comm
- * - TRACE_RECORD_TGID for recording tgid
+ * @task: task to record
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ * TRACE_RECORD_TGID for recording tgid
*/
void tracing_record_taskinfo(struct task_struct *task, int flags)
{
/**
* tracing_record_taskinfo_sched_switch - record task info for sched_switch
*
- * @prev - previous task during sched_switch
- * @next - next task during sched_switch
- * @flags - TRACE_RECORD_CMDLINE for recording comm
- * TRACE_RECORD_TGID for recording tgid
+ * @prev: previous task during sched_switch
+ * @next: next task during sched_switch
+ * @flags: TRACE_RECORD_CMDLINE for recording comm
+ * TRACE_RECORD_TGID for recording tgid
*/
void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
struct task_struct *next, int flags)
/**
* trace_vbprintk - write binary msg to tracing buffer
- *
+ * @ip: The address of the caller
+ * @fmt: The string format to write to the buffer
+ * @args: Arguments for @fmt
*/
int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
{
return ret;
}
-static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
+int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
int ret;
if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT))
return 0;
+ /*
+ * Do not trace a function if it's filtered by set_graph_notrace.
+ * Make the index of ret stack negative to indicate that it should
+ * ignore further functions. But it needs its own ret stack entry
+ * to recover the original index in order to continue tracing after
+ * returning from the function.
+ */
if (ftrace_graph_notrace_addr(trace->func)) {
trace_recursion_set(TRACE_GRAPH_NOTRACE_BIT);
/*
if (ftrace_graph_ignore_irqs())
return 0;
- /*
- * Do not trace a function if it's filtered by set_graph_notrace.
- * Make the index of ret stack negative to indicate that it should
- * ignore further functions. But it needs its own ret stack entry
- * to recover the original index in order to continue tracing after
- * returning from the function.
- */
- if (ftrace_graph_notrace_addr(trace->func))
- return 1;
-
/*
* Stop here if tracing_threshold is set. We only write function return
* events to the ring buffer.
for (i = 0; i < tp->nr_args; i++)
traceprobe_free_probe_arg(&tp->args[i]);
- kfree(call->class->system);
+ if (call->class)
+ kfree(call->class->system);
kfree(call->name);
kfree(call->print_fmt);
}
config KASAN_STACK_ENABLE
bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
- default !(CLANG_VERSION < 90000)
depends on KASAN
help
The LLVM stack address sanitizer has a know problem that
Disabling asan-stack makes it safe to run kernels build
with clang-8 with KASAN enabled, though it loses some of
the functionality.
- This feature is always disabled when compile-testing with clang-8
- or earlier to avoid cluttering the output in stack overflow
- warnings, but clang-8 users can still enable it for builds without
- CONFIG_COMPILE_TEST. On gcc and later clang versions it is
- assumed to always be safe to use and enabled by default.
+ This feature is always disabled when compile-testing with clang
+ to avoid cluttering the output in stack overflow warnings,
+ but clang users can still enable it for builds without
+ CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe
+ to use and enabled by default.
config KASAN_STACK
int
obj-$(CONFIG_UBSAN) += ubsan.o
UBSAN_SANITIZE_ubsan.o := n
-CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+KASAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := $(call cc-option, -fno-stack-protector) $(DISABLE_STACKLEAK_PLUGIN)
obj-$(CONFIG_SBITMAP) += sbitmap.o
delta_us);
curr_stats->cpms = DIV_ROUND_UP(ncomps * USEC_PER_MSEC, delta_us);
if (curr_stats->epms != 0)
- curr_stats->cpe_ratio =
- (curr_stats->cpms * 100) / curr_stats->epms;
+ curr_stats->cpe_ratio = DIV_ROUND_DOWN_ULL(
+ curr_stats->cpms * 100, curr_stats->epms);
else
curr_stats->cpe_ratio = 0;
#include <linux/dim.h>
+/*
+ * Net DIM profiles:
+ * There are different set of profiles for each CQ period mode.
+ * There are different set of profiles for RX/TX CQs.
+ * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES
+ */
+#define NET_DIM_PARAMS_NUM_PROFILES 5
+#define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256
+#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128
+#define NET_DIM_DEF_PROFILE_CQE 1
+#define NET_DIM_DEF_PROFILE_EQE 1
+
+#define NET_DIM_RX_EQE_PROFILES { \
+ {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {128, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \
+}
+
+#define NET_DIM_RX_CQE_PROFILES { \
+ {2, 256}, \
+ {8, 128}, \
+ {16, 64}, \
+ {32, 64}, \
+ {64, 64} \
+}
+
+#define NET_DIM_TX_EQE_PROFILES { \
+ {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \
+ {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \
+}
+
+#define NET_DIM_TX_CQE_PROFILES { \
+ {5, 128}, \
+ {8, 64}, \
+ {16, 32}, \
+ {32, 32}, \
+ {64, 32} \
+}
+
+static const struct dim_cq_moder
+rx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+ NET_DIM_RX_EQE_PROFILES,
+ NET_DIM_RX_CQE_PROFILES,
+};
+
+static const struct dim_cq_moder
+tx_profile[DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = {
+ NET_DIM_TX_EQE_PROFILES,
+ NET_DIM_TX_CQE_PROFILES,
+};
+
struct dim_cq_moder
net_dim_get_rx_moderation(u8 cq_period_mode, int ix)
{
{
size /= esize;
- size = roundup_pow_of_two(size);
+ if (!is_power_of_2(size))
+ size = rounddown_pow_of_two(size);
fifo->in = 0;
fifo->out = 0;
struct logic_pio_hwaddr *range;
resource_size_t start;
resource_size_t end;
- resource_size_t mmio_sz = 0;
+ resource_size_t mmio_end = 0;
resource_size_t iio_sz = MMIO_UPPER_LIMIT;
int ret = 0;
end = new_range->hw_start + new_range->size;
mutex_lock(&io_range_mutex);
- list_for_each_entry_rcu(range, &io_range_list, list) {
+ list_for_each_entry(range, &io_range_list, list) {
if (range->fwnode == new_range->fwnode) {
/* range already there */
goto end_register;
/* for MMIO ranges we need to check for overlap */
if (start >= range->hw_start + range->size ||
end < range->hw_start) {
- mmio_sz += range->size;
+ mmio_end = range->io_start + range->size;
} else {
ret = -EFAULT;
goto end_register;
/* range not registered yet, check for available space */
if (new_range->flags == LOGIC_PIO_CPU_MMIO) {
- if (mmio_sz + new_range->size - 1 > MMIO_UPPER_LIMIT) {
+ if (mmio_end + new_range->size - 1 > MMIO_UPPER_LIMIT) {
/* if it's too big check if 64K space can be reserved */
- if (mmio_sz + SZ_64K - 1 > MMIO_UPPER_LIMIT) {
+ if (mmio_end + SZ_64K - 1 > MMIO_UPPER_LIMIT) {
ret = -E2BIG;
goto end_register;
}
new_range->size = SZ_64K;
pr_warn("Requested IO range too big, new size set to 64K\n");
}
- new_range->io_start = mmio_sz;
+ new_range->io_start = mmio_end;
} else if (new_range->flags == LOGIC_PIO_INDIRECT) {
if (iio_sz + new_range->size - 1 > IO_SPACE_LIMIT) {
ret = -E2BIG;
return ret;
}
+/**
+ * logic_pio_unregister_range - unregister a logical PIO range for a host
+ * @range: pointer to the IO range which has been already registered.
+ *
+ * Unregister a previously-registered IO range node.
+ */
+void logic_pio_unregister_range(struct logic_pio_hwaddr *range)
+{
+ mutex_lock(&io_range_mutex);
+ list_del_rcu(&range->list);
+ mutex_unlock(&io_range_mutex);
+ synchronize_rcu();
+}
+
/**
* find_io_range_by_fwnode - find logical PIO range for given FW node
* @fwnode: FW node handle associated with logical PIO range
*/
struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode)
{
- struct logic_pio_hwaddr *range;
+ struct logic_pio_hwaddr *range, *found_range = NULL;
+ rcu_read_lock();
list_for_each_entry_rcu(range, &io_range_list, list) {
- if (range->fwnode == fwnode)
- return range;
+ if (range->fwnode == fwnode) {
+ found_range = range;
+ break;
+ }
}
- return NULL;
+ rcu_read_unlock();
+
+ return found_range;
}
/* Return a registered range given an input PIO token */
static struct logic_pio_hwaddr *find_io_range(unsigned long pio)
{
- struct logic_pio_hwaddr *range;
+ struct logic_pio_hwaddr *range, *found_range = NULL;
+ rcu_read_lock();
list_for_each_entry_rcu(range, &io_range_list, list) {
- if (in_range(pio, range->io_start, range->size))
- return range;
+ if (in_range(pio, range->io_start, range->size)) {
+ found_range = range;
+ break;
+ }
}
- pr_err("PIO entry token %lx invalid\n", pio);
- return NULL;
+ rcu_read_unlock();
+
+ if (!found_range)
+ pr_err("PIO entry token 0x%lx invalid\n", pio);
+
+ return found_range;
}
/**
{
struct logic_pio_hwaddr *range;
+ rcu_read_lock();
list_for_each_entry_rcu(range, &io_range_list, list) {
if (range->flags != LOGIC_PIO_CPU_MMIO)
continue;
- if (in_range(addr, range->hw_start, range->size))
- return addr - range->hw_start + range->io_start;
+ if (in_range(addr, range->hw_start, range->size)) {
+ unsigned long cpuaddr;
+
+ cpuaddr = addr - range->hw_start + range->io_start;
+
+ rcu_read_unlock();
+ return cpuaddr;
+ }
}
- pr_err("addr %llx not registered in io_range_list\n",
- (unsigned long long) addr);
+ rcu_read_unlock();
+
+ pr_err("addr %pa not registered in io_range_list\n", &addr);
+
return ~0UL;
}
CFLAGS_vpermxor2.o += $(altivec_flags)
CFLAGS_vpermxor4.o += $(altivec_flags)
CFLAGS_vpermxor8.o += $(altivec_flags)
-targets += vpermxor1.o vpermxor2.o vpermxor4.o vpermxor8.o
+targets += vpermxor1.c vpermxor2.c vpermxor4.c vpermxor8.c
$(obj)/vpermxor%.c: $(src)/vpermxor.uc $(src)/unroll.awk FORCE
$(call if_changed,unroll)
return -ENOMEM;
rc = __test_firmware_config_init();
- if (rc)
+ if (rc) {
+ kfree(test_fw_config);
+ pr_err("could not init firmware test config: %d\n", rc);
return rc;
+ }
rc = misc_register(&test_fw_misc_device);
if (rc) {
* Copy the buffer to check that it's not wiped on
* free().
*/
- buf_copy = kmalloc(size, GFP_KERNEL);
+ buf_copy = kmalloc(size, GFP_ATOMIC);
if (buf_copy)
memcpy(buf_copy, buf, size);
ns = vdso_ts->nsec;
last = vd->cycle_last;
if (unlikely((s64)cycles < 0))
- return clock_gettime_fallback(clk, ts);
+ return -1;
ns += vdso_calc_delta(cycles, last, vd->mask, vd->mult);
ns >>= vd->shift;
}
static __maybe_unused int
-__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+__cvdso_clock_gettime_common(clockid_t clock, struct __kernel_timespec *ts)
{
const struct vdso_data *vd = __arch_get_vdso_data();
u32 msk;
/* Check for negative values or invalid clocks */
if (unlikely((u32) clock >= MAX_CLOCKS))
- goto fallback;
+ return -1;
/*
* Convert the clockid to a bitmask and use it to check which
} else if (msk & VDSO_RAW) {
return do_hres(&vd[CS_RAW], clock, ts);
}
+ return -1;
+}
+
+static __maybe_unused int
+__cvdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
+{
+ int ret = __cvdso_clock_gettime_common(clock, ts);
-fallback:
- return clock_gettime_fallback(clock, ts);
+ if (unlikely(ret))
+ return clock_gettime_fallback(clock, ts);
+ return 0;
}
static __maybe_unused int
struct __kernel_timespec ts;
int ret;
- if (res == NULL)
- goto fallback;
+ ret = __cvdso_clock_gettime_common(clock, &ts);
- ret = __cvdso_clock_gettime(clock, &ts);
+#ifdef VDSO_HAS_32BIT_FALLBACK
+ if (unlikely(ret))
+ return clock_gettime32_fallback(clock, res);
+#else
+ if (unlikely(ret))
+ ret = clock_gettime_fallback(clock, &ts);
+#endif
- if (ret == 0) {
+ if (likely(!ret)) {
res->tv_sec = ts.tv_sec;
res->tv_nsec = ts.tv_nsec;
}
-
return ret;
-
-fallback:
- return clock_gettime_fallback(clock, (struct __kernel_timespec *)res);
}
static __maybe_unused int
#ifdef VDSO_HAS_CLOCK_GETRES
static __maybe_unused
-int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
+int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
{
const struct vdso_data *vd = __arch_get_vdso_data();
- u64 ns;
+ u64 hrtimer_res;
u32 msk;
- u64 hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
+ u64 ns;
/* Check for negative values or invalid clocks */
if (unlikely((u32) clock >= MAX_CLOCKS))
- goto fallback;
+ return -1;
+ hrtimer_res = READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res);
/*
* Convert the clockid to a bitmask and use it to check which
* clocks are handled in the VDSO directly.
*/
ns = hrtimer_res;
} else {
- goto fallback;
+ return -1;
}
- if (res) {
- res->tv_sec = 0;
- res->tv_nsec = ns;
- }
+ res->tv_sec = 0;
+ res->tv_nsec = ns;
return 0;
+}
+
+int __cvdso_clock_getres(clockid_t clock, struct __kernel_timespec *res)
+{
+ int ret = __cvdso_clock_getres_common(clock, res);
-fallback:
- return clock_getres_fallback(clock, res);
+ if (unlikely(ret))
+ return clock_getres_fallback(clock, res);
+ return 0;
}
static __maybe_unused int
struct __kernel_timespec ts;
int ret;
- if (res == NULL)
- goto fallback;
+ ret = __cvdso_clock_getres_common(clock, &ts);
- ret = __cvdso_clock_getres(clock, &ts);
+#ifdef VDSO_HAS_32BIT_FALLBACK
+ if (unlikely(ret))
+ return clock_getres32_fallback(clock, res);
+#else
+ if (unlikely(ret))
+ ret = clock_getres_fallback(clock, &ts);
+#endif
- if (ret == 0) {
+ if (likely(!ret)) {
res->tv_sec = ts.tv_sec;
res->tv_nsec = ts.tv_nsec;
}
-
return ret;
-
-fallback:
- return clock_getres_fallback(clock, (struct __kernel_timespec *)res);
}
#endif /* VDSO_HAS_CLOCK_GETRES */
obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
+obj-$(CONFIG_ZONE_DEVICE) += memremap.o
obj-$(CONFIG_HMM_MIRROR) += hmm.o
obj-$(CONFIG_MEMFD_CREATE) += memfd.o
* memory corruption is possible and we should stop execution.
*/
BUG_ON(!trylock_page(page));
- list_del(&page->lru);
balloon_page_insert(b_dev_info, page);
unlock_page(page);
__count_vm_event(BALLOON_INFLATE);
* @b_dev_info: balloon device descriptor where we will insert a new page to
* @pages: pages to enqueue - allocated using balloon_page_alloc.
*
- * Driver must call it to properly enqueue a balloon pages before definitively
- * removing it from the guest system.
+ * Driver must call this function to properly enqueue balloon pages before
+ * definitively removing them from the guest system.
*
* Return: number of pages that were enqueued.
*/
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
list_for_each_entry_safe(page, tmp, pages, lru) {
+ list_del(&page->lru);
balloon_page_enqueue_one(b_dev_info, page);
n_pages++;
}
* @n_req_pages: number of requested pages.
*
* Driver must call this function to properly de-allocate a previous enlisted
- * balloon pages before definetively releasing it back to the guest system.
+ * balloon pages before definitively releasing it back to the guest system.
* This function tries to remove @n_req_pages from the ballooned pages and
* return them to the caller in the @pages list.
*
- * Note that this function may fail to dequeue some pages temporarily empty due
- * to compaction isolated pages.
+ * Note that this function may fail to dequeue some pages even if the balloon
+ * isn't empty - since the page list can be temporarily empty due to compaction
+ * of isolated pages.
*
* Return: number of pages that were added to the @pages list.
*/
/*
* balloon_page_alloc - allocates a new page for insertion into the balloon
- * page list.
+ * page list.
+ *
+ * Driver must call this function to properly allocate a new balloon page.
+ * Driver must call balloon_page_enqueue before definitively removing the page
+ * from the guest system.
*
- * Driver must call it to properly allocate a new enlisted balloon page.
- * Driver must call balloon_page_enqueue before definitively removing it from
- * the guest system. This function returns the page address for the recently
- * allocated page or NULL in the case we fail to allocate a new page this turn.
+ * Return: struct page for the allocated page or NULL on allocation failure.
*/
struct page *balloon_page_alloc(void)
{
struct page *page = alloc_page(balloon_mapping_gfp_mask() |
- __GFP_NOMEMALLOC | __GFP_NORETRY);
+ __GFP_NOMEMALLOC | __GFP_NORETRY |
+ __GFP_NOWARN);
return page;
}
EXPORT_SYMBOL_GPL(balloon_page_alloc);
/*
- * balloon_page_enqueue - allocates a new page and inserts it into the balloon
- * page list.
- * @b_dev_info: balloon device descriptor where we will insert a new page to
+ * balloon_page_enqueue - inserts a new page into the balloon page list.
+ *
+ * @b_dev_info: balloon device descriptor where we will insert a new page
* @page: new page to enqueue - allocated using balloon_page_alloc.
*
- * Driver must call it to properly enqueue a new allocated balloon page
- * before definitively removing it from the guest system.
- * This function returns the page address for the recently enqueued page or
- * NULL in the case we fail to allocate a new page this turn.
+ * Drivers must call this function to properly enqueue a new allocated balloon
+ * page before definitively removing the page from the guest system.
+ *
+ * Drivers must not call balloon_page_enqueue on pages that have been pushed to
+ * a list with balloon_page_push before removing them with balloon_page_pop. To
+ * enqueue a list of pages, use balloon_page_list_enqueue instead.
*/
void balloon_page_enqueue(struct balloon_dev_info *b_dev_info,
struct page *page)
/*
* balloon_page_dequeue - removes a page from balloon's page list and returns
- * the its address to allow the driver release the page.
+ * its address to allow the driver to release the page.
* @b_dev_info: balloon device decriptor where we will grab a page from.
*
- * Driver must call it to properly de-allocate a previous enlisted balloon page
- * before definetively releasing it back to the guest system.
- * This function returns the page address for the recently dequeued page or
- * NULL in the case we find balloon's page list temporarily empty due to
- * compaction isolated pages.
+ * Driver must call this function to properly dequeue a previously enqueued page
+ * before definitively releasing it back to the guest system.
+ *
+ * Caller must perform its own accounting to ensure that this
+ * function is called only if some pages are actually enqueued.
+ *
+ * Note that this function may fail to dequeue some pages even if there are
+ * some enqueued pages - since the page list can be temporarily empty due to
+ * the compaction of isolated pages.
+ *
+ * TODO: remove the caller accounting requirements, and allow caller to wait
+ * until all pages can be dequeued.
+ *
+ * Return: struct page for the dequeued page, or NULL if no page was dequeued.
*/
struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
{
if (n_pages != 1) {
/*
* If we are unable to dequeue a balloon page because the page
- * list is empty and there is no isolated pages, then something
+ * list is empty and there are no isolated pages, then something
* went out of track and some balloon pages are lost.
- * BUG() here, otherwise the balloon driver may get stuck into
+ * BUG() here, otherwise the balloon driver may get stuck in
* an infinite loop while attempting to release all its pages.
*/
spin_lock_irqsave(&b_dev_info->pages_lock, flags);
/*
* We can not easily support the no copy case here so ignore it as it
- * is unlikely to be use with ballon pages. See include/linux/hmm.h for
- * user of the MIGRATE_SYNC_NO_COPY mode.
+ * is unlikely to be used with balloon pages. See include/linux/hmm.h
+ * for a user of the MIGRATE_SYNC_NO_COPY mode.
*/
if (mode == MIGRATE_SYNC_NO_COPY)
return -EINVAL;
/*
* Periodically drop the lock (if held) regardless of its
- * contention, to give chance to IRQs. Abort async compaction
- * if contended.
+ * contention, to give chance to IRQs. Abort completely if
+ * a fatal signal is pending.
*/
if (!(low_pfn % SWAP_CLUSTER_MAX)
&& compact_unlock_should_abort(&pgdat->lru_lock,
- flags, &locked, cc))
- break;
+ flags, &locked, cc)) {
+ low_pfn = 0;
+ goto fatal_pending;
+ }
if (!pfn_valid_within(low_pfn))
goto isolate_fail;
trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn,
nr_scanned, nr_isolated);
+fatal_pending:
cc->total_migrate_scanned += nr_scanned;
if (nr_isolated)
count_compact_events(COMPACTISOLATED, nr_isolated);
* @range: range
* Return: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid
* permission (for instance asking for write and range is read only),
- * -EAGAIN if you need to retry, -EFAULT invalid (ie either no valid
+ * -EBUSY if you need to retry, -EFAULT invalid (ie either no valid
* vma or it is illegal to access that range), number of valid pages
* in range->pfns[] (from range start address).
*
do {
/* If range is no longer valid force retry. */
if (!range->valid)
- return -EAGAIN;
+ return -EBUSY;
vma = find_vma(hmm->mm, start);
if (vma == NULL || (vma->vm_flags & device_vma))
do {
/* If range is no longer valid force retry. */
- if (!range->valid) {
- up_read(&hmm->mm->mmap_sem);
- return -EAGAIN;
- }
+ if (!range->valid)
+ return -EBUSY;
vma = find_vma(hmm->mm, start);
if (vma == NULL || (vma->vm_flags & device_vma))
#include <linux/shmem_fs.h>
#include <linux/oom.h>
#include <linux/numa.h>
+#include <linux/page_owner.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
* available
* never: never stall for any thp allocation
*/
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
{
const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+ gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+ struct mempolicy *pol;
+ /*
+ * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+ * specified, to express a general desire to stay on the current
+ * node for optimistic allocation attempts. If the defrag mode
+ * and/or madvise hint requires the direct reclaim then we prefer
+ * to fallback to other node rather than node reclaim because that
+ * can lead to excessive reclaim even though there is free memory
+ * on other nodes. We expect that NUMA preferences are specified
+ * by memory policies.
+ */
+ pol = get_vma_policy(vma, addr);
+ if (pol->mode != MPOL_BIND)
+ this_node = __GFP_THISNODE;
+ mpol_cond_put(pol);
+#endif
- /* Always do synchronous compaction */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
-
- /* Kick kcompactd and fail quickly */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
-
- /* Synchronous compaction if madvised, otherwise kick kcompactd */
+ return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT |
- (vma_madvised ? __GFP_DIRECT_RECLAIM :
- __GFP_KSWAPD_RECLAIM);
-
- /* Only do synchronous compaction if madvised */
+ return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+ __GFP_KSWAPD_RECLAIM | this_node);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT |
- (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
-
- return GFP_TRANSHUGE_LIGHT;
+ return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
+ this_node);
+ return GFP_TRANSHUGE_LIGHT | this_node;
}
/* Caller must hold page table lock. */
pte_free(vma->vm_mm, pgtable);
return ret;
}
- gfp = alloc_hugepage_direct_gfpmask(vma);
- page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+ gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
alloc:
if (__transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
- huge_gfp = alloc_hugepage_direct_gfpmask(vma);
- new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+ huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+ haddr, numa_node_id());
} else
new_page = NULL;
}
ClearPageCompound(head);
+
+ split_page_owner(head, HPAGE_PMD_ORDER);
+
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
/* Additional pin to swap cache */
page = alloc_huge_page(vma, haddr, 0);
if (IS_ERR(page)) {
+ /*
+ * Returning error will result in faulting task being
+ * sent SIGBUS. The hugetlb fault mutex prevents two
+ * tasks from racing to fault in the same page which
+ * could result in false unable to allocate errors.
+ * Page migration does not take the fault mutex, but
+ * does a clear then write of pte's under page table
+ * lock. Page fault code could race with migration,
+ * notice the clear pte and try to allocate a page
+ * here. Before returning error, get ptl and make
+ * sure there really is no pte entry.
+ */
+ ptl = huge_pte_lock(h, mm, ptep);
+ if (!huge_pte_none(huge_ptep_get(ptep))) {
+ ret = 0;
+ spin_unlock(ptl);
+ goto out;
+ }
+ spin_unlock(ptl);
ret = vmf_error(PTR_ERR(page));
goto out;
}
if (IS_ENABLED(CONFIG_KASAN_GENERIC))
return shadow_byte < 0 ||
shadow_byte >= KASAN_SHADOW_SCALE_SIZE;
- else
- return tag != (u8)shadow_byte;
+
+ /* else CONFIG_KASAN_SW_TAGS: */
+ if ((u8)shadow_byte == KASAN_TAG_INVALID)
+ return true;
+ if ((tag != KASAN_TAG_KERNEL) && (tag != (u8)shadow_byte))
+ return true;
+
+ return false;
}
static bool __kasan_slab_free(struct kmem_cache *cache, void *object,
/* GFP bitmask for kmemleak internal allocations */
#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
__GFP_NORETRY | __GFP_NOMEMALLOC | \
- __GFP_NOWARN | __GFP_NOFAIL)
+ __GFP_NOWARN)
/* scanning area inside a memory block */
struct kmemleak_scan_area {
/* stop any memory operation tracing */
kmemleak_enabled = 0;
+ kmemleak_early_log = 0;
/* check whether it is too early for a kernel thread */
if (kmemleak_initialized)
#ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
if (!kmemleak_skip_disable) {
- kmemleak_early_log = 0;
kmemleak_disable();
return;
}
/* Update memcg */
__mod_memcg_state(memcg, idx, val);
+ /* Update lruvec */
+ __this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
struct mem_cgroup_per_node *pi;
- /*
- * Batch local counters to keep them in sync with
- * the hierarchical ones.
- */
- __this_cpu_add(pn->lruvec_stat_local->count[idx], x);
for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
atomic_long_add(x, &pi->lruvec_stat[idx]);
x = 0;
__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
}
+void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
+{
+ struct page *page = virt_to_head_page(p);
+ pg_data_t *pgdat = page_pgdat(page);
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+
+ rcu_read_lock();
+ memcg = memcg_from_slab_page(page);
+
+ /* Untracked pages have no memcg, no lruvec. Update only the node */
+ if (!memcg || memcg == root_mem_cgroup) {
+ __mod_node_page_state(pgdat, idx, val);
+ } else {
+ lruvec = mem_cgroup_lruvec(pgdat, memcg);
+ __mod_lruvec_state(lruvec, idx, val);
+ }
+ rcu_read_unlock();
+}
+
/**
* __count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
css_put(&prev->css);
}
-static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
+ struct mem_cgroup *dead_memcg)
{
- struct mem_cgroup *memcg = dead_memcg;
struct mem_cgroup_reclaim_iter *iter;
struct mem_cgroup_per_node *mz;
int nid;
int i;
- for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- for_each_node(nid) {
- mz = mem_cgroup_nodeinfo(memcg, nid);
- for (i = 0; i <= DEF_PRIORITY; i++) {
- iter = &mz->iter[i];
- cmpxchg(&iter->position,
- dead_memcg, NULL);
- }
+ for_each_node(nid) {
+ mz = mem_cgroup_nodeinfo(from, nid);
+ for (i = 0; i <= DEF_PRIORITY; i++) {
+ iter = &mz->iter[i];
+ cmpxchg(&iter->position,
+ dead_memcg, NULL);
}
}
}
+static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+{
+ struct mem_cgroup *memcg = dead_memcg;
+ struct mem_cgroup *last;
+
+ do {
+ __invalidate_reclaim_iterators(memcg, dead_memcg);
+ last = memcg;
+ } while ((memcg = parent_mem_cgroup(memcg)));
+
+ /*
+ * When cgruop1 non-hierarchy mode is used,
+ * parent_mem_cgroup() does not walk all the way up to the
+ * cgroup root (root_mem_cgroup). So we have to handle
+ * dead_memcg from cgroup root separately.
+ */
+ if (last != root_mem_cgroup)
+ __invalidate_reclaim_iterators(root_mem_cgroup,
+ dead_memcg);
+}
+
/**
* mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy
* @memcg: hierarchy root
}
}
+static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
+{
+ unsigned long stat[MEMCG_NR_STAT];
+ struct mem_cgroup *mi;
+ int node, cpu, i;
+ int min_idx, max_idx;
+
+ if (slab_only) {
+ min_idx = NR_SLAB_RECLAIMABLE;
+ max_idx = NR_SLAB_UNRECLAIMABLE;
+ } else {
+ min_idx = 0;
+ max_idx = MEMCG_NR_STAT;
+ }
+
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] = 0;
+
+ for_each_online_cpu(cpu)
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
+
+ for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+ for (i = min_idx; i < max_idx; i++)
+ atomic_long_add(stat[i], &mi->vmstats[i]);
+
+ if (!slab_only)
+ max_idx = NR_VM_NODE_STAT_ITEMS;
+
+ for_each_node(node) {
+ struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
+ struct mem_cgroup_per_node *pi;
+
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] = 0;
+
+ for_each_online_cpu(cpu)
+ for (i = min_idx; i < max_idx; i++)
+ stat[i] += per_cpu(
+ pn->lruvec_stat_cpu->count[i], cpu);
+
+ for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
+ for (i = min_idx; i < max_idx; i++)
+ atomic_long_add(stat[i], &pi->lruvec_stat[i]);
+ }
+}
+
+static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
+{
+ unsigned long events[NR_VM_EVENT_ITEMS];
+ struct mem_cgroup *mi;
+ int cpu, i;
+
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+ events[i] = 0;
+
+ for_each_online_cpu(cpu)
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+ events[i] += per_cpu(memcg->vmstats_percpu->events[i],
+ cpu);
+
+ for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+ for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+ atomic_long_add(events[i], &mi->vmevents[i]);
+}
+
#ifdef CONFIG_MEMCG_KMEM
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
if (!parent)
parent = root_mem_cgroup;
+ /*
+ * Deactivate and reparent kmem_caches. Then flush percpu
+ * slab statistics to have precise values at the parent and
+ * all ancestor levels. It's required to keep slab stats
+ * accurate after the reparenting of kmem_caches.
+ */
memcg_deactivate_kmem_caches(memcg, parent);
+ memcg_flush_percpu_vmstats(memcg, true);
kmemcg_id = memcg->kmemcg_id;
BUG_ON(kmemcg_id < 0);
{
int node;
+ /*
+ * Flush percpu vmstats and vmevents to guarantee the value correctness
+ * on parent's and all ancestor levels.
+ */
+ memcg_flush_percpu_vmstats(memcg, false);
+ memcg_flush_percpu_vmevents(memcg);
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->vmstats_percpu);
return;
release_resource(res);
kfree(res);
- return;
}
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
arch_refresh_nodedata(nid, NULL);
free_percpu(pgdat->per_cpu_nodestats);
arch_free_nodedata(pgdat);
- return;
}
},
};
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags);
struct queue_pages {
}
/*
- * queue_pages_pmd() has three possible return values:
- * 1 - pages are placed on the right node or queued successfully.
- * 0 - THP was split.
- * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
- * page was already on a node that does not follow the policy.
+ * queue_pages_pmd() has four possible return values:
+ * 0 - pages are placed on the right node or queued successfully.
+ * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
+ * specified.
+ * 2 - THP was split.
+ * -EIO - is migration entry or only MPOL_MF_STRICT was specified and an
+ * existing page was already on a node that does not follow the
+ * policy.
*/
static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
unsigned long end, struct mm_walk *walk)
if (is_huge_zero_page(page)) {
spin_unlock(ptl);
__split_huge_pmd(walk->vma, pmd, addr, false, NULL);
+ ret = 2;
goto out;
}
- if (!queue_pages_required(page, qp)) {
- ret = 1;
+ if (!queue_pages_required(page, qp))
goto unlock;
- }
- ret = 1;
flags = qp->flags;
/* go to thp migration */
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- if (!vma_migratable(walk->vma)) {
- ret = -EIO;
+ if (!vma_migratable(walk->vma) ||
+ migrate_page_add(page, qp->pagelist, flags)) {
+ ret = 1;
goto unlock;
}
-
- migrate_page_add(page, qp->pagelist, flags);
} else
ret = -EIO;
unlock:
/*
* Scan through pages checking if pages follow certain conditions,
* and move them to the pagelist if they do.
+ *
+ * queue_pages_pte_range() has three possible return values:
+ * 0 - pages are placed on the right node or queued successfully.
+ * 1 - there is unmovable page, and MPOL_MF_MOVE* & MPOL_MF_STRICT were
+ * specified.
+ * -EIO - only MPOL_MF_STRICT was specified and an existing page was already
+ * on a node that does not follow the policy.
*/
static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
struct queue_pages *qp = walk->private;
unsigned long flags = qp->flags;
int ret;
+ bool has_unmovable = false;
pte_t *pte;
spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
- if (ret > 0)
- return 0;
- else if (ret < 0)
+ if (ret != 2)
return ret;
}
+ /* THP was split, fall through to pte walk */
if (pmd_trans_unstable(pmd))
return 0;
if (!queue_pages_required(page, qp))
continue;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- if (!vma_migratable(vma))
+ /* MPOL_MF_STRICT must be specified if we get here */
+ if (!vma_migratable(vma)) {
+ has_unmovable = true;
break;
- migrate_page_add(page, qp->pagelist, flags);
+ }
+
+ /*
+ * Do not abort immediately since there may be
+ * temporary off LRU pages in the range. Still
+ * need migrate other LRU pages.
+ */
+ if (migrate_page_add(page, qp->pagelist, flags))
+ has_unmovable = true;
} else
break;
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
+
+ if (has_unmovable)
+ return 1;
+
return addr != end ? -EIO : 0;
}
*
* If pages found in a given range are on a set of nodes (determined by
* @nodes and @flags,) it's isolated and queued to the pagelist which is
- * passed via @private.)
+ * passed via @private.
+ *
+ * queue_pages_range() has three possible return values:
+ * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were
+ * specified.
+ * 0 - queue pages successfully or no misplaced page.
+ * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified.
*/
static int
queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
/*
* page migration, thp tail pages can be passed.
*/
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
struct page *head = compound_head(page);
mod_node_page_state(page_pgdat(head),
NR_ISOLATED_ANON + page_is_file_cache(head),
hpage_nr_pages(head));
+ } else if (flags & MPOL_MF_STRICT) {
+ /*
+ * Non-movable page may reach here. And, there may be
+ * temporary off LRU pages or non-LRU movable pages.
+ * Treat them as unmovable pages since they can't be
+ * isolated, so they can't be moved at the moment. It
+ * should return -EIO for this case too.
+ */
+ return -EIO;
}
}
+
+ return 0;
}
/* page allocation callback for NUMA node migration */
} else if (PageTransHuge(page)) {
struct page *thp;
- thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
- HPAGE_PMD_ORDER);
+ thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
+ address, numa_node_id());
if (!thp)
return NULL;
prep_transhuge_page(thp);
}
#else
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
+ return -EIO;
}
int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
struct mempolicy *new;
unsigned long end;
int err;
+ int ret;
LIST_HEAD(pagelist);
if (flags & ~(unsigned long)MPOL_MF_VALID)
if (err)
goto mpol_out;
- err = queue_pages_range(mm, start, end, nmask,
+ ret = queue_pages_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
- if (!err)
- err = mbind_range(mm, start, end, new);
+
+ if (ret < 0) {
+ err = -EIO;
+ goto up_out;
+ }
+
+ err = mbind_range(mm, start, end, new);
if (!err) {
int nr_failed = 0;
putback_movable_pages(&pagelist);
}
- if (nr_failed && (flags & MPOL_MF_STRICT))
+ if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
err = -EIO;
} else
putback_movable_pages(&pagelist);
+up_out:
up_write(&mm->mmap_sem);
- mpol_out:
+mpol_out:
mpol_put(new);
return err;
}
* freeing by another task. It is the caller's responsibility to free the
* extra reference for shared policies.
*/
-static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr)
{
struct mempolicy *pol = __get_vma_policy(vma, addr);
* @vma: Pointer to VMA or NULL if not available.
* @addr: Virtual Address of the allocation. Must be inside the VMA.
* @node: Which node to prefer for allocation (modulo policy).
- * @hugepage: for hugepages try only the preferred node if possible
*
* This function allocates a page from the kernel page pool and applies
* a NUMA policy associated with the VMA or the current process.
*/
struct page *
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
- unsigned long addr, int node, bool hugepage)
+ unsigned long addr, int node)
{
struct mempolicy *pol;
struct page *page;
goto out;
}
- if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
- int hpage_node = node;
-
- /*
- * For hugepage allocation and non-interleave policy which
- * allows the current node (or other explicitly preferred
- * node) we only try to allocate from the current/preferred
- * node and don't fall back to other nodes, as the cost of
- * remote accesses would likely offset THP benefits.
- *
- * If the policy is interleave, or does not allow the current
- * node in its nodemask, we allocate the standard way.
- */
- if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
- hpage_node = pol->v.preferred_node;
-
- nmask = policy_nodemask(gfp, pol);
- if (!nmask || node_isset(hpage_node, *nmask)) {
- mpol_cond_put(pol);
- page = __alloc_pages_node(hpage_node,
- gfp | __GFP_THISNODE, order);
- goto out;
- }
- }
-
nmask = policy_nodemask(gfp, pol);
preferred_nid = policy_node(gfp, pol, node);
page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2015 Intel Corporation. All rights reserved. */
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/kasan.h>
+#include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <linux/pfn_t.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/types.h>
+#include <linux/wait_bit.h>
+#include <linux/xarray.h>
+
+static DEFINE_XARRAY(pgmap_array);
+#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
+#define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
+static atomic_t devmap_managed_enable;
+
+static void devmap_managed_enable_put(void *data)
+{
+ if (atomic_dec_and_test(&devmap_managed_enable))
+ static_branch_disable(&devmap_managed_key);
+}
+
+static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
+{
+ if (!pgmap->ops || !pgmap->ops->page_free) {
+ WARN(1, "Missing page_free method\n");
+ return -EINVAL;
+ }
+
+ if (atomic_inc_return(&devmap_managed_enable) == 1)
+ static_branch_enable(&devmap_managed_key);
+ return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
+}
+#else
+static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
+
+static void pgmap_array_delete(struct resource *res)
+{
+ xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+ NULL, GFP_KERNEL);
+ synchronize_rcu();
+}
+
+static unsigned long pfn_first(struct dev_pagemap *pgmap)
+{
+ return PHYS_PFN(pgmap->res.start) +
+ vmem_altmap_offset(pgmap_altmap(pgmap));
+}
+
+static unsigned long pfn_end(struct dev_pagemap *pgmap)
+{
+ const struct resource *res = &pgmap->res;
+
+ return (res->start + resource_size(res)) >> PAGE_SHIFT;
+}
+
+static unsigned long pfn_next(unsigned long pfn)
+{
+ if (pfn % 1024 == 0)
+ cond_resched();
+ return pfn + 1;
+}
+
+#define for_each_device_pfn(pfn, map) \
+ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
+
+static void dev_pagemap_kill(struct dev_pagemap *pgmap)
+{
+ if (pgmap->ops && pgmap->ops->kill)
+ pgmap->ops->kill(pgmap);
+ else
+ percpu_ref_kill(pgmap->ref);
+}
+
+static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
+{
+ if (pgmap->ops && pgmap->ops->cleanup) {
+ pgmap->ops->cleanup(pgmap);
+ } else {
+ wait_for_completion(&pgmap->done);
+ percpu_ref_exit(pgmap->ref);
+ }
+ /*
+ * Undo the pgmap ref assignment for the internal case as the
+ * caller may re-enable the same pgmap.
+ */
+ if (pgmap->ref == &pgmap->internal_ref)
+ pgmap->ref = NULL;
+}
+
+static void devm_memremap_pages_release(void *data)
+{
+ struct dev_pagemap *pgmap = data;
+ struct device *dev = pgmap->dev;
+ struct resource *res = &pgmap->res;
+ unsigned long pfn;
+ int nid;
+
+ dev_pagemap_kill(pgmap);
+ for_each_device_pfn(pfn, pgmap)
+ put_page(pfn_to_page(pfn));
+ dev_pagemap_cleanup(pgmap);
+
+ /* pages are dead and unused, undo the arch mapping */
+ nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start)));
+
+ mem_hotplug_begin();
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ pfn = PHYS_PFN(res->start);
+ __remove_pages(page_zone(pfn_to_page(pfn)), pfn,
+ PHYS_PFN(resource_size(res)), NULL);
+ } else {
+ arch_remove_memory(nid, res->start, resource_size(res),
+ pgmap_altmap(pgmap));
+ kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+ }
+ mem_hotplug_done();
+
+ untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
+ pgmap_array_delete(res);
+ dev_WARN_ONCE(dev, pgmap->altmap.alloc,
+ "%s: failed to free all reserved pages\n", __func__);
+}
+
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+ struct dev_pagemap *pgmap =
+ container_of(ref, struct dev_pagemap, internal_ref);
+
+ complete(&pgmap->done);
+}
+
+/**
+ * devm_memremap_pages - remap and provide memmap backing for the given resource
+ * @dev: hosting device for @res
+ * @pgmap: pointer to a struct dev_pagemap
+ *
+ * Notes:
+ * 1/ At a minimum the res and type members of @pgmap must be initialized
+ * by the caller before passing it to this function
+ *
+ * 2/ The altmap field may optionally be initialized, in which case
+ * PGMAP_ALTMAP_VALID must be set in pgmap->flags.
+ *
+ * 3/ The ref field may optionally be provided, in which pgmap->ref must be
+ * 'live' on entry and will be killed and reaped at
+ * devm_memremap_pages_release() time, or if this routine fails.
+ *
+ * 4/ res is expected to be a host memory range that could feasibly be
+ * treated as a "System RAM" range, i.e. not a device mmio range, but
+ * this is not enforced.
+ */
+void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
+{
+ struct resource *res = &pgmap->res;
+ struct dev_pagemap *conflict_pgmap;
+ struct mhp_restrictions restrictions = {
+ /*
+ * We do not want any optional features only our own memmap
+ */
+ .altmap = pgmap_altmap(pgmap),
+ };
+ pgprot_t pgprot = PAGE_KERNEL;
+ int error, nid, is_ram;
+ bool need_devmap_managed = true;
+
+ switch (pgmap->type) {
+ case MEMORY_DEVICE_PRIVATE:
+ if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
+ WARN(1, "Device private memory not supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
+ WARN(1, "Missing migrate_to_ram method\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
+ case MEMORY_DEVICE_FS_DAX:
+ if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
+ IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
+ WARN(1, "File system DAX not supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+ break;
+ case MEMORY_DEVICE_DEVDAX:
+ case MEMORY_DEVICE_PCI_P2PDMA:
+ need_devmap_managed = false;
+ break;
+ default:
+ WARN(1, "Invalid pgmap type %d\n", pgmap->type);
+ break;
+ }
+
+ if (!pgmap->ref) {
+ if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+ return ERR_PTR(-EINVAL);
+
+ init_completion(&pgmap->done);
+ error = percpu_ref_init(&pgmap->internal_ref,
+ dev_pagemap_percpu_release, 0, GFP_KERNEL);
+ if (error)
+ return ERR_PTR(error);
+ pgmap->ref = &pgmap->internal_ref;
+ } else {
+ if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+ WARN(1, "Missing reference count teardown definition\n");
+ return ERR_PTR(-EINVAL);
+ }
+ }
+
+ if (need_devmap_managed) {
+ error = devmap_managed_enable_get(dev, pgmap);
+ if (error)
+ return ERR_PTR(error);
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->start), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ error = -ENOMEM;
+ goto err_array;
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(res->end), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ error = -ENOMEM;
+ goto err_array;
+ }
+
+ is_ram = region_intersects(res->start, resource_size(res),
+ IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
+
+ if (is_ram != REGION_DISJOINT) {
+ WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
+ is_ram == REGION_MIXED ? "mixed" : "ram", res);
+ error = -ENXIO;
+ goto err_array;
+ }
+
+ pgmap->dev = dev;
+
+ error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
+ PHYS_PFN(res->end), pgmap, GFP_KERNEL));
+ if (error)
+ goto err_array;
+
+ nid = dev_to_node(dev);
+ if (nid < 0)
+ nid = numa_mem_id();
+
+ error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(res->start), 0,
+ resource_size(res));
+ if (error)
+ goto err_pfn_remap;
+
+ mem_hotplug_begin();
+
+ /*
+ * For device private memory we call add_pages() as we only need to
+ * allocate and initialize struct page for the device memory. More-
+ * over the device memory is un-accessible thus we do not want to
+ * create a linear mapping for the memory like arch_add_memory()
+ * would do.
+ *
+ * For all other device memory types, which are accessible by
+ * the CPU, we do want the linear mapping and thus use
+ * arch_add_memory().
+ */
+ if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+ error = add_pages(nid, PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), &restrictions);
+ } else {
+ error = kasan_add_zero_shadow(__va(res->start), resource_size(res));
+ if (error) {
+ mem_hotplug_done();
+ goto err_kasan;
+ }
+
+ error = arch_add_memory(nid, res->start, resource_size(res),
+ &restrictions);
+ }
+
+ if (!error) {
+ struct zone *zone;
+
+ zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+ move_pfn_range_to_zone(zone, PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), restrictions.altmap);
+ }
+
+ mem_hotplug_done();
+ if (error)
+ goto err_add_memory;
+
+ /*
+ * Initialization of the pages has been deferred until now in order
+ * to allow us to do the work while not holding the hotplug lock.
+ */
+ memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+ PHYS_PFN(res->start),
+ PHYS_PFN(resource_size(res)), pgmap);
+ percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
+
+ error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+ pgmap);
+ if (error)
+ return ERR_PTR(error);
+
+ return __va(res->start);
+
+ err_add_memory:
+ kasan_remove_zero_shadow(__va(res->start), resource_size(res));
+ err_kasan:
+ untrack_pfn(NULL, PHYS_PFN(res->start), resource_size(res));
+ err_pfn_remap:
+ pgmap_array_delete(res);
+ err_array:
+ dev_pagemap_kill(pgmap);
+ dev_pagemap_cleanup(pgmap);
+ return ERR_PTR(error);
+}
+EXPORT_SYMBOL_GPL(devm_memremap_pages);
+
+void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
+{
+ devm_release_action(dev, devm_memremap_pages_release, pgmap);
+}
+EXPORT_SYMBOL_GPL(devm_memunmap_pages);
+
+unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
+{
+ /* number of pfns from base where pfn_to_page() is valid */
+ if (altmap)
+ return altmap->reserve + altmap->free;
+ return 0;
+}
+
+void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
+{
+ altmap->alloc -= nr_pfns;
+}
+
+/**
+ * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
+ * @pfn: page frame number to lookup page_map
+ * @pgmap: optional known pgmap that already has a reference
+ *
+ * If @pgmap is non-NULL and covers @pfn it will be returned as-is. If @pgmap
+ * is non-NULL but does not cover @pfn the reference to it will be released.
+ */
+struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
+ struct dev_pagemap *pgmap)
+{
+ resource_size_t phys = PFN_PHYS(pfn);
+
+ /*
+ * In the cached case we're already holding a live reference.
+ */
+ if (pgmap) {
+ if (phys >= pgmap->res.start && phys <= pgmap->res.end)
+ return pgmap;
+ put_dev_pagemap(pgmap);
+ }
+
+ /* fall back to slow path lookup */
+ rcu_read_lock();
+ pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
+ if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
+ pgmap = NULL;
+ rcu_read_unlock();
+
+ return pgmap;
+}
+EXPORT_SYMBOL_GPL(get_dev_pagemap);
+
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void __put_devmap_managed_page(struct page *page)
+{
+ int count = page_ref_dec_return(page);
+
+ /*
+ * If refcount is 1 then page is freed and refcount is stable as nobody
+ * holds a reference on the page.
+ */
+ if (count == 1) {
+ /* Clear Active bit in case of parallel mark_page_accessed */
+ __ClearPageActive(page);
+ __ClearPageWaiters(page);
+
+ mem_cgroup_uncharge(page);
+
+ /*
+ * When a device_private page is freed, the page->mapping field
+ * may still contain a (stale) mapping value. For example, the
+ * lower bits of page->mapping may still identify the page as
+ * an anonymous page. Ultimately, this entire field is just
+ * stale and wrong, and it will cause errors if not cleared.
+ * One example is:
+ *
+ * migrate_vma_pages()
+ * migrate_vma_insert_page()
+ * page_add_new_anon_rmap()
+ * __page_set_anon_rmap()
+ * ...checks page->mapping, via PageAnon(page) call,
+ * and incorrectly concludes that the page is an
+ * anonymous page. Therefore, it incorrectly,
+ * silently fails to set up the new anon rmap.
+ *
+ * For other types of ZONE_DEVICE pages, migration is either
+ * handled differently or not done at all, so there is no need
+ * to clear page->mapping.
+ */
+ if (is_device_private_page(page))
+ page->mapping = NULL;
+
+ page->pgmap->ops->page_free(page);
+ } else if (!count)
+ __put_page(page);
+}
+EXPORT_SYMBOL(__put_devmap_managed_page);
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
}
bh = bh->b_this_page;
} while (bh != head);
- spin_unlock(&mapping->private_lock);
if (busy) {
if (invalidated) {
rc = -EAGAIN;
goto unlock_buffers;
}
+ spin_unlock(&mapping->private_lock);
invalidate_bh_lrus();
invalidated = true;
goto recheck_buffers;
rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
+ if (check_refs)
+ spin_unlock(&mapping->private_lock);
bh = head;
do {
unlock_buffer(bh);
static void migrate_vma_collect(struct migrate_vma *migrate)
{
struct mmu_notifier_range range;
- struct mm_walk mm_walk;
-
- mm_walk.pmd_entry = migrate_vma_collect_pmd;
- mm_walk.pte_entry = NULL;
- mm_walk.pte_hole = migrate_vma_collect_hole;
- mm_walk.hugetlb_entry = NULL;
- mm_walk.test_walk = NULL;
- mm_walk.vma = migrate->vma;
- mm_walk.mm = migrate->vma->vm_mm;
- mm_walk.private = migrate;
+ struct mm_walk mm_walk = {
+ .pmd_entry = migrate_vma_collect_pmd,
+ .pte_hole = migrate_vma_collect_hole,
+ .vma = migrate->vma,
+ .mm = migrate->vma->vm_mm,
+ .private = migrate,
+ };
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm,
migrate->start,
unsigned int order;
int pages_moved = 0;
-#ifndef CONFIG_HOLES_IN_ZONE
- /*
- * page_zone is not safe to call in this context when
- * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
- * anyway as we check zone boundaries in move_freepages_block().
- * Remove at a later date when no bug reports exist related to
- * grouping pages by mobility
- */
- VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) &&
- pfn_valid(page_to_pfn(end_page)) &&
- page_zone(start_page) != page_zone(end_page));
-#endif
for (page = start_page; page <= end_page;) {
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
- /* Make sure we are not inadvertently changing nodes */
- VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
-
if (!PageBuddy(page)) {
/*
* We assume that pages that could be isolated for
continue;
}
+ /* Make sure we are not inadvertently changing nodes */
+ VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+ VM_BUG_ON_PAGE(page_zone(page) != zone, page);
+
order = page_order(page);
move_to_free_area(page, &zone->free_area[order], migratetype);
page += 1 << order;
/*
* No need to invalidate here it will synchronize on
* against the special swap migration pte.
+ *
+ * The assignment to subpage above was computed from a
+ * swap PTE which results in an invalid pointer.
+ * Since only PAGE_SIZE pages can currently be
+ * migrated, just set it to page. This will need to be
+ * changed when hugepage migrations to device private
+ * memory are supported.
*/
+ subpage = page;
goto discard;
}
shmem_pseudo_vma_init(&pvma, info, hindex);
page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
- HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
+ HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
shmem_pseudo_vma_destroy(&pvma);
if (page)
prep_transhuge_page(page);
void *old_tail = *tail ? *tail : *head;
int rsize;
- if (slab_want_init_on_free(s))
+ if (slab_want_init_on_free(s)) {
+ void *p = NULL;
+
do {
object = next;
next = get_freepointer(s, object);
: 0;
memset((char *)object + s->inuse, 0,
s->size - s->inuse - rsize);
- set_freepointer(s, object, next);
+ set_freepointer(s, object, p);
+ p = object;
} while (object != old_tail);
+ }
/*
* Compiler cannot detect this function can be removed if slab_free_hook()
bool to_user)
{
/* Reject if object wraps past end of memory. */
- if (ptr + n < ptr)
+ if (ptr + (n - 1) < ptr)
usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n);
/* Reject if NULL or ZERO-allocation. */
if (unlikely(valist == NULL))
return false;
+ /*
+ * First make sure the mappings are removed from all page-tables
+ * before they are freed.
+ */
+ vmalloc_sync_all();
+
/*
* TODO: to calculate a flush range without looping.
* The list can be up to lazy_max_pages() elements.
/*
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
* have one.
+ *
+ * The purpose of this function is to make sure the vmalloc area
+ * mappings are identical in all page-tables in the system.
*/
void __weak vmalloc_sync_all(void)
{
if (va == NULL)
goto overflow;
+ /*
+ * If required width exeeds current VA block, move
+ * base downwards and then recheck.
+ */
+ if (base + end > va->va_end) {
+ base = pvm_determine_end_from_reverse(&va, align) - end;
+ term_area = area;
+ continue;
+ }
+
/*
* If this VA does not fit, move base downwards and recheck.
*/
- if (base + start < va->va_start || base + end > va->va_end) {
+ if (base + start < va->va_start) {
va = node_to_va(rb_prev(&va->rb_node));
base = pvm_determine_end_from_reverse(&va, align) - end;
term_area = area;
/* Can pages be swapped as part of reclaim? */
unsigned int may_swap:1;
- /* e.g. boosted watermark reclaim leaves slabs alone */
- unsigned int may_shrinkslab:1;
-
/*
* Cgroups are not reclaimed below their configured memory.low,
* unless we threaten to OOM. If any cgroups are skipped due to
unsigned long ret, freed = 0;
struct shrinker *shrinker;
- if (!mem_cgroup_is_root(memcg))
+ /*
+ * The root memcg might be allocated even though memcg is disabled
+ * via "cgroup_disable=memory" boot parameter. This could make
+ * mem_cgroup_is_root() return false, then just run memcg slab
+ * shrink, but skip global shrink. This may result in premature
+ * oom.
+ */
+ if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
if (!down_read_trylock(&shrinker_rwsem))
shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
node_lru_pages += lru_pages;
- if (sc->may_shrinkslab) {
- shrink_slab(sc->gfp_mask, pgdat->node_id,
- memcg, sc->priority);
- }
+ shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
+ sc->priority);
/* Record the group's reclaim efficiency */
vmpressure(sc->gfp_mask, memcg, false,
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = 1,
- .may_shrinkslab = 1,
};
/*
#ifdef CONFIG_MEMCG
+/* Only used by soft limit reclaim. Do not reuse for anything else. */
unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
.may_unmap = 1,
.reclaim_idx = MAX_NR_ZONES - 1,
.may_swap = !noswap,
- .may_shrinkslab = 1,
};
unsigned long lru_pages;
- set_task_reclaim_state(current, &sc.reclaim_state);
+ WARN_ON_ONCE(!current->reclaim_state);
+
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
- set_task_reclaim_state(current, NULL);
*nr_scanned = sc.nr_scanned;
return sc.nr_reclaimed;
.may_writepage = !laptop_mode,
.may_unmap = 1,
.may_swap = may_swap,
- .may_shrinkslab = 1,
};
set_task_reclaim_state(current, &sc.reclaim_state);
*/
sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
sc.may_swap = !nr_boost_reclaim;
- sc.may_shrinkslab = !nr_boost_reclaim;
/*
* Do some background aging of the anon list, to give
if (node->count && node->count == node->nr_values) {
if (list_empty(&node->private_list)) {
list_lru_add(&shadow_nodes, &node->private_list);
- __inc_lruvec_page_state(virt_to_page(node),
- WORKINGSET_NODES);
+ __inc_lruvec_slab_state(node, WORKINGSET_NODES);
}
} else {
if (!list_empty(&node->private_list)) {
list_lru_del(&shadow_nodes, &node->private_list);
- __dec_lruvec_page_state(virt_to_page(node),
- WORKINGSET_NODES);
+ __dec_lruvec_slab_state(node, WORKINGSET_NODES);
}
}
}
}
list_lru_isolate(lru, item);
- __dec_lruvec_page_state(virt_to_page(node), WORKINGSET_NODES);
+ __dec_lruvec_slab_state(node, WORKINGSET_NODES);
spin_unlock(lru_lock);
* shadow entries we were tracking ...
*/
xas_store(&xas, NULL);
- __inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
+ __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);
out_invalid:
xa_unlock_irq(&mapping->i_pages);
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/wait.h>
#include <linux/zpool.h>
#include <linux/magic.h>
* @release_wq: workqueue for safe page release
* @work: work_struct for safe page release
* @inode: inode for z3fold pseudo filesystem
+ * @destroying: bool to stop migration once we start destruction
+ * @isolated: int to count the number of pages currently in isolation
*
* This structure is allocated at pool creation time and maintains metadata
* pertaining to a particular z3fold pool.
const struct zpool_ops *zpool_ops;
struct workqueue_struct *compact_wq;
struct workqueue_struct *release_wq;
+ struct wait_queue_head isolate_wait;
struct work_struct work;
struct inode *inode;
+ bool destroying;
+ int isolated;
};
/*
goto out_c;
spin_lock_init(&pool->lock);
spin_lock_init(&pool->stale_lock);
+ init_waitqueue_head(&pool->isolate_wait);
pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2);
if (!pool->unbuddied)
goto out_pool;
return NULL;
}
+static bool pool_isolated_are_drained(struct z3fold_pool *pool)
+{
+ bool ret;
+
+ spin_lock(&pool->lock);
+ ret = pool->isolated == 0;
+ spin_unlock(&pool->lock);
+ return ret;
+}
/**
* z3fold_destroy_pool() - destroys an existing z3fold pool
* @pool: the z3fold pool to be destroyed
static void z3fold_destroy_pool(struct z3fold_pool *pool)
{
kmem_cache_destroy(pool->c_handle);
- z3fold_unregister_migration(pool);
- destroy_workqueue(pool->release_wq);
+ /*
+ * We set pool-> destroying under lock to ensure that
+ * z3fold_page_isolate() sees any changes to destroying. This way we
+ * avoid the need for any memory barriers.
+ */
+
+ spin_lock(&pool->lock);
+ pool->destroying = true;
+ spin_unlock(&pool->lock);
+
+ /*
+ * We need to ensure that no pages are being migrated while we destroy
+ * these workqueues, as migration can queue work on either of the
+ * workqueues.
+ */
+ wait_event(pool->isolate_wait, !pool_isolated_are_drained(pool));
+
+ /*
+ * We need to destroy pool->compact_wq before pool->release_wq,
+ * as any pending work on pool->compact_wq will call
+ * queue_work(pool->release_wq, &pool->work).
+ *
+ * There are still outstanding pages until both workqueues are drained,
+ * so we cannot unregister migration until then.
+ */
+
destroy_workqueue(pool->compact_wq);
+ destroy_workqueue(pool->release_wq);
+ z3fold_unregister_migration(pool);
kfree(pool);
}
return atomic64_read(&pool->pages_nr);
}
+/*
+ * z3fold_dec_isolated() expects to be called while pool->lock is held.
+ */
+static void z3fold_dec_isolated(struct z3fold_pool *pool)
+{
+ assert_spin_locked(&pool->lock);
+ VM_BUG_ON(pool->isolated <= 0);
+ pool->isolated--;
+
+ /*
+ * If we have no more isolated pages, we have to see if
+ * z3fold_destroy_pool() is waiting for a signal.
+ */
+ if (pool->isolated == 0 && waitqueue_active(&pool->isolate_wait))
+ wake_up_all(&pool->isolate_wait);
+}
+
+static void z3fold_inc_isolated(struct z3fold_pool *pool)
+{
+ pool->isolated++;
+}
+
static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
{
struct z3fold_header *zhdr;
spin_lock(&pool->lock);
if (!list_empty(&page->lru))
list_del(&page->lru);
+ /*
+ * We need to check for destruction while holding pool->lock, as
+ * otherwise destruction could see 0 isolated pages, and
+ * proceed.
+ */
+ if (unlikely(pool->destroying)) {
+ spin_unlock(&pool->lock);
+ /*
+ * If this page isn't stale, somebody else holds a
+ * reference to it. Let't drop our refcount so that they
+ * can call the release logic.
+ */
+ if (unlikely(kref_put(&zhdr->refcount,
+ release_z3fold_page_locked))) {
+ /*
+ * If we get here we have kref problems, so we
+ * should freak out.
+ */
+ WARN(1, "Z3fold is experiencing kref problems\n");
+ z3fold_page_unlock(zhdr);
+ return false;
+ }
+ z3fold_page_unlock(zhdr);
+ return false;
+ }
+
+
+ z3fold_inc_isolated(pool);
spin_unlock(&pool->lock);
z3fold_page_unlock(zhdr);
return true;
queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work);
+ spin_lock(&pool->lock);
+ z3fold_dec_isolated(pool);
+ spin_unlock(&pool->lock);
+
page_mapcount_reset(page);
put_page(page);
return 0;
INIT_LIST_HEAD(&page->lru);
if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) {
atomic64_dec(&pool->pages_nr);
+ spin_lock(&pool->lock);
+ z3fold_dec_isolated(pool);
+ spin_unlock(&pool->lock);
return;
}
spin_lock(&pool->lock);
list_add(&page->lru, &pool->lru);
+ z3fold_dec_isolated(pool);
spin_unlock(&pool->lock);
z3fold_page_unlock(zhdr);
}
#include <linux/mount.h>
#include <linux/pseudo_fs.h>
#include <linux/migrate.h>
+#include <linux/wait.h>
#include <linux/pagemap.h>
#include <linux/fs.h>
#ifdef CONFIG_COMPACTION
struct inode *inode;
struct work_struct free_work;
+ /* A wait queue for when migration races with async_free_zspage() */
+ struct wait_queue_head migration_wait;
+ atomic_long_t isolated_pages;
+ bool destroying;
#endif
};
zspage->isolated--;
}
+static void putback_zspage_deferred(struct zs_pool *pool,
+ struct size_class *class,
+ struct zspage *zspage)
+{
+ enum fullness_group fg;
+
+ fg = putback_zspage(class, zspage);
+ if (fg == ZS_EMPTY)
+ schedule_work(&pool->free_work);
+
+}
+
+static inline void zs_pool_dec_isolated(struct zs_pool *pool)
+{
+ VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0);
+ atomic_long_dec(&pool->isolated_pages);
+ /*
+ * There's no possibility of racing, since wait_for_isolated_drain()
+ * checks the isolated count under &class->lock after enqueuing
+ * on migration_wait.
+ */
+ if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying)
+ wake_up_all(&pool->migration_wait);
+}
+
static void replace_sub_page(struct size_class *class, struct zspage *zspage,
struct page *newpage, struct page *oldpage)
{
*/
if (!list_empty(&zspage->list) && !is_zspage_isolated(zspage)) {
get_zspage_mapping(zspage, &class_idx, &fullness);
+ atomic_long_inc(&pool->isolated_pages);
remove_zspage(class, zspage, fullness);
}
* Page migration is done so let's putback isolated zspage to
* the list if @page is final isolated subpage in the zspage.
*/
- if (!is_zspage_isolated(zspage))
- putback_zspage(class, zspage);
+ if (!is_zspage_isolated(zspage)) {
+ /*
+ * We cannot race with zs_destroy_pool() here because we wait
+ * for isolation to hit zero before we start destroying.
+ * Also, we ensure that everyone can see pool->destroying before
+ * we start waiting.
+ */
+ putback_zspage_deferred(pool, class, zspage);
+ zs_pool_dec_isolated(pool);
+ }
reset_page(page);
put_page(page);
spin_lock(&class->lock);
dec_zspage_isolation(zspage);
if (!is_zspage_isolated(zspage)) {
- fg = putback_zspage(class, zspage);
/*
* Due to page_lock, we cannot free zspage immediately
* so let's defer.
*/
- if (fg == ZS_EMPTY)
- schedule_work(&pool->free_work);
+ putback_zspage_deferred(pool, class, zspage);
+ zs_pool_dec_isolated(pool);
}
spin_unlock(&class->lock);
}
return 0;
}
+static bool pool_isolated_are_drained(struct zs_pool *pool)
+{
+ return atomic_long_read(&pool->isolated_pages) == 0;
+}
+
+/* Function for resolving migration */
+static void wait_for_isolated_drain(struct zs_pool *pool)
+{
+
+ /*
+ * We're in the process of destroying the pool, so there are no
+ * active allocations. zs_page_isolate() fails for completely free
+ * zspages, so we need only wait for the zs_pool's isolated
+ * count to hit zero.
+ */
+ wait_event(pool->migration_wait,
+ pool_isolated_are_drained(pool));
+}
+
static void zs_unregister_migration(struct zs_pool *pool)
{
+ pool->destroying = true;
+ /*
+ * We need a memory barrier here to ensure global visibility of
+ * pool->destroying. Thus pool->isolated pages will either be 0 in which
+ * case we don't care, or it will be > 0 and pool->destroying will
+ * ensure that we wake up once isolation hits 0.
+ */
+ smp_mb();
+ wait_for_isolated_drain(pool); /* This can block */
flush_work(&pool->free_work);
iput(pool->inode);
}
if (!pool->name)
goto err;
+#ifdef CONFIG_COMPACTION
+ init_waitqueue_head(&pool->migration_wait);
+#endif
+
if (create_cache(pool))
goto err;
* batadv_iv_ogm_aggr_packet() - checks if there is another OGM attached
* @buff_pos: current position in the skb
* @packet_len: total length of the skb
- * @tvlv_len: tvlv length of the previously considered OGM
+ * @ogm_packet: potential OGM in buffer
*
* Return: true if there is enough space for another OGM, false otherwise.
*/
-static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
- __be16 tvlv_len)
+static bool
+batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
+ const struct batadv_ogm_packet *ogm_packet)
{
int next_buff_pos = 0;
- next_buff_pos += buff_pos + BATADV_OGM_HLEN;
- next_buff_pos += ntohs(tvlv_len);
+ /* check if there is enough space for the header */
+ next_buff_pos += buff_pos + sizeof(*ogm_packet);
+ if (next_buff_pos > packet_len)
+ return false;
+
+ /* check if there is enough space for the optional TVLV */
+ next_buff_pos += ntohs(ogm_packet->tvlv_len);
return (next_buff_pos <= packet_len) &&
(next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES);
/* adjust all flags and log packets */
while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len,
- batadv_ogm_packet->tvlv_len)) {
+ batadv_ogm_packet)) {
/* we might have aggregated direct link packets with an
* ordinary base packet
*/
/* unpack the aggregated packets and process them one by one */
while (batadv_iv_ogm_aggr_packet(ogm_offset, skb_headlen(skb),
- ogm_packet->tvlv_len)) {
+ ogm_packet)) {
batadv_iv_ogm_process(skb, ogm_offset, if_incoming);
ogm_offset += BATADV_OGM_HLEN;
* batadv_v_ogm_aggr_packet() - checks if there is another OGM aggregated
* @buff_pos: current position in the skb
* @packet_len: total length of the skb
- * @tvlv_len: tvlv length of the previously considered OGM
+ * @ogm2_packet: potential OGM2 in buffer
*
* Return: true if there is enough space for another OGM, false otherwise.
*/
-static bool batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
- __be16 tvlv_len)
+static bool
+batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
+ const struct batadv_ogm2_packet *ogm2_packet)
{
int next_buff_pos = 0;
- next_buff_pos += buff_pos + BATADV_OGM2_HLEN;
- next_buff_pos += ntohs(tvlv_len);
+ /* check if there is enough space for the header */
+ next_buff_pos += buff_pos + sizeof(*ogm2_packet);
+ if (next_buff_pos > packet_len)
+ return false;
+
+ /* check if there is enough space for the optional TVLV */
+ next_buff_pos += ntohs(ogm2_packet->tvlv_len);
return (next_buff_pos <= packet_len) &&
(next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES);
ogm_packet = (struct batadv_ogm2_packet *)skb->data;
while (batadv_v_ogm_aggr_packet(ogm_offset, skb_headlen(skb),
- ogm_packet->tvlv_len)) {
+ ogm_packet)) {
batadv_v_ogm_process(skb, ogm_offset, if_incoming);
ogm_offset += BATADV_OGM2_HLEN;
while (bucket_tmp < hash->size) {
if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash,
- *bucket, &idx_tmp))
+ bucket_tmp, &idx_tmp))
break;
bucket_tmp++;
batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
- batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_NO_FLAGS);
- batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_NO_FLAGS);
+ batadv_mcast_want_rtr4_update(bat_priv, orig,
+ BATADV_MCAST_WANT_NO_RTR4);
+ batadv_mcast_want_rtr6_update(bat_priv, orig,
+ BATADV_MCAST_WANT_NO_RTR6);
spin_unlock_bh(&orig->mcast_handler_lock);
}
{
struct nlattr *attr = nlmsg_find_attr(nlh, GENL_HDRLEN, attrtype);
- return attr ? nla_get_u32(attr) : 0;
+ return (attr && nla_len(attr) == sizeof(u32)) ? nla_get_u32(attr) : 0;
}
/**
hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE;
hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE;
hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT;
+ hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE;
mutex_init(&hdev->lock);
mutex_init(&hdev->req_lock);
return 0;
}
+static int min_encrypt_key_size_set(void *data, u64 val)
+{
+ struct hci_dev *hdev = data;
+
+ if (val < 1 || val > 16)
+ return -EINVAL;
+
+ hci_dev_lock(hdev);
+ hdev->min_enc_key_size = val;
+ hci_dev_unlock(hdev);
+
+ return 0;
+}
+
+static int min_encrypt_key_size_get(void *data, u64 *val)
+{
+ struct hci_dev *hdev = data;
+
+ hci_dev_lock(hdev);
+ *val = hdev->min_enc_key_size;
+ hci_dev_unlock(hdev);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(min_encrypt_key_size_fops,
+ min_encrypt_key_size_get,
+ min_encrypt_key_size_set, "%llu\n");
+
static int auto_accept_delay_get(void *data, u64 *val)
{
struct hci_dev *hdev = data;
if (lmp_ssp_capable(hdev)) {
debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs,
hdev, &ssp_debug_mode_fops);
+ debugfs_create_file("min_encrypt_key_size", 0644, hdev->debugfs,
+ hdev, &min_encrypt_key_size_fops);
debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs,
hdev, &auto_accept_delay_fops);
}
{
struct sk_buff *skb;
struct sock *sk = sock->sk;
+ int ret;
BT_DBG("session %p data %p size %d", session, data, size);
}
skb_put_u8(skb, hdr);
- if (data && size > 0)
+ if (data && size > 0) {
skb_put_data(skb, data, size);
+ ret = size;
+ } else {
+ ret = 0;
+ }
skb_queue_tail(transmit, skb);
wake_up_interruptible(sk_sleep(sk));
- return 0;
+ return ret;
}
static int hidp_send_ctrl_message(struct hidp_session *session,
* actually encrypted before enforcing a key size.
*/
return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) ||
- hcon->enc_key_size >= HCI_MIN_ENC_KEY_SIZE);
+ hcon->enc_key_size >= hcon->hdev->min_enc_key_size);
}
static void l2cap_do_start(struct l2cap_chan *chan)
int err;
if (dev->priv_flags & IFF_EBRIDGE) {
+ err = br_vlan_bridge_event(dev, event, ptr);
+ if (err)
+ return notifier_from_errno(err);
+
if (event == NETDEV_REGISTER) {
/* register of bridge completed, add sysfs entries */
br_sysfs_addbr(dev);
return NOTIFY_DONE;
}
- br_vlan_bridge_event(dev, event, ptr);
}
/* not a port of a bridge */
if (!br_port_group_equal(p, port, src))
continue;
+ if (p->flags & MDB_PG_FLAGS_PERMANENT)
+ break;
+
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
void br_vlan_get_stats(const struct net_bridge_vlan *v,
struct br_vlan_stats *stats);
void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
-void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
- void *ptr);
+int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
+ void *ptr);
static inline struct net_bridge_vlan_group *br_vlan_group(
const struct net_bridge *br)
{
}
-static inline void br_vlan_bridge_event(struct net_device *dev,
- unsigned long event, void *ptr)
+static inline int br_vlan_bridge_event(struct net_device *dev,
+ unsigned long event, void *ptr)
{
+ return 0;
}
#endif
{
struct net_bridge_vlan_group *vg;
int ret = -ENOMEM;
- bool changed;
vg = kzalloc(sizeof(*vg), GFP_KERNEL);
if (!vg)
br->vlan_proto = htons(ETH_P_8021Q);
br->default_pvid = 1;
rcu_assign_pointer(br->vlgrp, vg);
- ret = br_vlan_add(br, 1,
- BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED |
- BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
- if (ret)
- goto err_vlan_add;
out:
return ret;
-err_vlan_add:
- vlan_tunnel_deinit(vg);
err_tunnel_init:
rhashtable_destroy(&vg->vlan_hash);
err_rhtbl:
}
/* Must be protected by RTNL. */
-void br_vlan_bridge_event(struct net_device *dev, unsigned long event,
- void *ptr)
+int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr)
{
struct netdev_notifier_changeupper_info *info;
- struct net_bridge *br;
+ struct net_bridge *br = netdev_priv(dev);
+ bool changed;
+ int ret = 0;
switch (event) {
+ case NETDEV_REGISTER:
+ ret = br_vlan_add(br, br->default_pvid,
+ BRIDGE_VLAN_INFO_PVID |
+ BRIDGE_VLAN_INFO_UNTAGGED |
+ BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL);
+ break;
+ case NETDEV_UNREGISTER:
+ br_vlan_delete(br, br->default_pvid);
+ break;
case NETDEV_CHANGEUPPER:
info = ptr;
br_vlan_upper_change(dev, info->upper_dev, info->linking);
case NETDEV_CHANGE:
case NETDEV_UP:
- br = netdev_priv(dev);
if (!br_opt_get(br, BROPT_VLAN_BRIDGE_BINDING))
- return;
+ break;
br_vlan_link_state_change(dev, br);
break;
}
+
+ return ret;
}
/* Must be protected by RTNL. */
menuconfig NF_TABLES_BRIDGE
depends on BRIDGE && NETFILTER && NF_TABLES
select NETFILTER_FAMILY_BRIDGE
- bool "Ethernet Bridge nf_tables support"
+ tristate "Ethernet Bridge nf_tables support"
if NF_TABLES_BRIDGE
tristate "Bridge packet logging"
select NF_LOG_COMMON
+endif # NF_TABLES_BRIDGE
+
config NF_CONNTRACK_BRIDGE
tristate "IPv4/IPV6 bridge connection tracking support"
depends on NF_CONNTRACK
To compile it as a module, choose M here. If unsure, say N.
-endif # NF_TABLES_BRIDGE
-
menuconfig BRIDGE_NF_EBTABLES
tristate "Ethernet Bridge tables (ebtables) support"
depends on BRIDGE && NETFILTER && NETFILTER_XTABLES
return NF_DROP;
}
- ADD_COUNTER(*(counter_base + i), 1, skb->len);
+ ADD_COUNTER(*(counter_base + i), skb->len, 1);
/* these should only watch: not modify, nor tell us
* what to do with the packet
continue;
counter_base = COUNTER_BASE(oldcounters, nentries, cpu);
for (i = 0; i < nentries; i++)
- ADD_COUNTER(counters[i], counter_base[i].pcnt,
- counter_base[i].bcnt);
+ ADD_COUNTER(counters[i], counter_base[i].bcnt,
+ counter_base[i].pcnt);
}
}
/* we add to the counters of the first cpu */
for (i = 0; i < num_counters; i++)
- ADD_COUNTER(t->private->counters[i], tmp[i].pcnt, tmp[i].bcnt);
+ ADD_COUNTER(t->private->counters[i], tmp[i].bcnt, tmp[i].pcnt);
write_unlock_bh(&t->lock);
ret = 0;
return 0;
}
+static int ebt_compat_init_offsets(unsigned int number)
+{
+ if (number > INT_MAX)
+ return -EINVAL;
+
+ /* also count the base chain policies */
+ number += NF_BR_NUMHOOKS;
+
+ return xt_compat_init_offsets(NFPROTO_BRIDGE, number);
+}
static int compat_table_info(const struct ebt_table_info *info,
struct compat_ebt_replace *newinfo)
{
unsigned int size = info->entries_size;
const void *entries = info->entries;
+ int ret;
newinfo->entries_size = size;
- if (info->nentries) {
- int ret = xt_compat_init_offsets(NFPROTO_BRIDGE,
- info->nentries);
- if (ret)
- return ret;
- }
+ ret = ebt_compat_init_offsets(info->nentries);
+ if (ret)
+ return ret;
return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info,
entries, newinfo);
xt_compat_lock(NFPROTO_BRIDGE);
- if (tmp.nentries) {
- ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries);
- if (ret < 0)
- goto out_unlock;
- }
+ ret = ebt_compat_init_offsets(tmp.nentries);
+ if (ret < 0)
+ goto out_unlock;
ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
if (ret < 0)
state.buf_kern_len = size64;
ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state);
- if (WARN_ON(ret < 0))
+ if (WARN_ON(ret < 0)) {
+ vfree(entries_tmp);
goto out_unlock;
+ }
vfree(entries_tmp);
tmp.entries_size = size64;
switch (priv->key) {
case NFT_META_BRI_IIFNAME:
br_dev = nft_meta_get_bridge(in);
- if (!br_dev)
- goto err;
break;
case NFT_META_BRI_OIFNAME:
br_dev = nft_meta_get_bridge(out);
- if (!br_dev)
- goto err;
break;
case NFT_META_BRI_IIFPVID: {
u16 p_pvid;
goto err;
br_vlan_get_proto(br_dev, &p_proto);
- nft_reg_store16(dest, p_proto);
+ nft_reg_store16(dest, htons(p_proto));
return;
}
default:
- goto out;
+ return nft_meta_get_eval(expr, regs, pkt);
}
- strncpy((char *)dest, br_dev->name, IFNAMSIZ);
+ strncpy((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ);
return;
-out:
- return nft_meta_get_eval(expr, regs, pkt);
err:
regs->verdict.code = NFT_BREAK;
}
pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n",
max_hops);
- register_pernet_subsys(&cangw_pernet_ops);
+ ret = register_pernet_subsys(&cangw_pernet_ops);
+ if (ret)
+ return ret;
+
+ ret = -ENOMEM;
cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job),
0, 0, NULL);
-
if (!cgw_cache)
- return -ENOMEM;
+ goto out_cache_create;
/* set notifier */
notifier.notifier_call = cgw_notifier;
- register_netdevice_notifier(¬ifier);
+ ret = register_netdevice_notifier(¬ifier);
+ if (ret)
+ goto out_register_notifier;
ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_GETROUTE,
NULL, cgw_dump_jobs, 0);
- if (ret) {
- unregister_netdevice_notifier(¬ifier);
- kmem_cache_destroy(cgw_cache);
- return -ENOBUFS;
- }
-
- /* Only the first call to rtnl_register_module can fail */
- rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE,
- cgw_create_job, NULL, 0);
- rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE,
- cgw_remove_job, NULL, 0);
+ if (ret)
+ goto out_rtnl_register1;
+
+ ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_NEWROUTE,
+ cgw_create_job, NULL, 0);
+ if (ret)
+ goto out_rtnl_register2;
+ ret = rtnl_register_module(THIS_MODULE, PF_CAN, RTM_DELROUTE,
+ cgw_remove_job, NULL, 0);
+ if (ret)
+ goto out_rtnl_register3;
return 0;
+
+out_rtnl_register3:
+ rtnl_unregister(PF_CAN, RTM_NEWROUTE);
+out_rtnl_register2:
+ rtnl_unregister(PF_CAN, RTM_GETROUTE);
+out_rtnl_register1:
+ unregister_netdevice_notifier(¬ifier);
+out_register_notifier:
+ kmem_cache_destroy(cgw_cache);
+out_cache_create:
+ unregister_pernet_subsys(&cangw_pernet_ops);
+
+ return ret;
}
static __exit void cgw_module_exit(void)
if (key) {
kfree(key->key);
key->key = NULL;
- crypto_free_sync_skcipher(key->tfm);
- key->tfm = NULL;
+ if (key->tfm) {
+ crypto_free_sync_skcipher(key->tfm);
+ key->tfm = NULL;
+ }
}
}
struct ceph_osds up, acting;
bool force_resend = false;
bool unpaused = false;
- bool legacy_change;
+ bool legacy_change = false;
bool split = false;
bool sort_bitwise = ceph_osdmap_flag(osdc, CEPH_OSDMAP_SORTBITWISE);
bool recovery_deletes = ceph_osdmap_flag(osdc,
t->osd = acting.primary;
}
- if (unpaused || legacy_change || force_resend ||
- (split && con && CEPH_HAVE_FEATURE(con->peer_features,
- RESEND_ON_SPLIT)))
+ if (unpaused || legacy_change || force_resend || split)
ct_res = CALC_TARGET_NEED_RESEND;
else
ct_res = CALC_TARGET_NO_ACTION;
out:
- dout("%s t %p -> ct_res %d osd %d\n", __func__, t, ct_res, t->osd);
+ dout("%s t %p -> %d%d%d%d ct_res %d osd%d\n", __func__, t, unpaused,
+ legacy_change, force_resend, split, ct_res, t->osd);
return ct_res;
}
act = bpf_prog_run_xdp(xdp_prog, xdp);
+ /* check if bpf_xdp_adjust_head was used */
off = xdp->data - orig_data;
- if (off > 0)
- __skb_pull(skb, off);
- else if (off < 0)
- __skb_push(skb, -off);
- skb->mac_header += off;
+ if (off) {
+ if (off > 0)
+ __skb_pull(skb, off);
+ else if (off < 0)
+ __skb_push(skb, -off);
+
+ skb->mac_header += off;
+ skb_reset_network_header(skb);
+ }
/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
* pckt.
/* Push remaining network devices to init_net */
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
+ if (__dev_get_by_name(&init_net, fb_name))
+ snprintf(fb_name, IFNAMSIZ, "dev%%d");
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (err) {
pr_emerg("%s: failed to move %s to init_net: %d\n",
case offsetof(struct __sk_buff, gso_segs):
/* si->dst_reg = skb_shinfo(SKB); */
#ifdef NET_SKBUFF_DATA_USES_OFFSET
- *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
- si->dst_reg, si->src_reg,
- offsetof(struct sk_buff, head));
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
BPF_REG_AX, si->src_reg,
offsetof(struct sk_buff, end));
+ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head),
+ si->dst_reg, si->src_reg,
+ offsetof(struct sk_buff, head));
*insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX);
#else
*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end),
return size == size_default;
/* Fields that allow narrowing */
- case offsetof(struct sk_reuseport_md, eth_protocol):
+ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol):
if (size < FIELD_SIZEOF(struct sk_buff, protocol))
return false;
/* fall through */
- case offsetof(struct sk_reuseport_md, ip_protocol):
- case offsetof(struct sk_reuseport_md, bind_inany):
- case offsetof(struct sk_reuseport_md, len):
+ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol):
+ case bpf_ctx_range(struct sk_reuseport_md, bind_inany):
+ case bpf_ctx_range(struct sk_reuseport_md, len):
bpf_ctx_record_field_size(info, size_default);
return bpf_ctx_narrow_access_ok(off, size, size_default);
mutex_unlock(&flow_dissector_mutex);
return -ENOENT;
}
- bpf_prog_put(attached);
RCU_INIT_POINTER(net->flow_dissector_prog, NULL);
+ bpf_prog_put(attached);
mutex_unlock(&flow_dissector_mutex);
return 0;
}
}
EXPORT_SYMBOL(flow_rule_match_enc_opts);
-struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv))
{
if (!block_cb)
return ERR_PTR(-ENOMEM);
- block_cb->net = net;
block_cb->cb = cb;
block_cb->cb_ident = cb_ident;
block_cb->cb_priv = cb_priv;
}
EXPORT_SYMBOL(flow_block_cb_free);
-struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f,
- tc_setup_cb_t *cb, void *cb_ident)
+struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
+ flow_setup_cb_t *cb, void *cb_ident)
{
struct flow_block_cb *block_cb;
- list_for_each_entry(block_cb, f->driver_block_list, driver_list) {
- if (block_cb->net == f->net &&
- block_cb->cb == cb &&
+ list_for_each_entry(block_cb, &block->cb_list, list) {
+ if (block_cb->cb == cb &&
block_cb->cb_ident == cb_ident)
return block_cb;
}
}
EXPORT_SYMBOL(flow_block_cb_decref);
-bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
struct list_head *driver_block_list)
{
struct flow_block_cb *block_cb;
int flow_block_cb_setup_simple(struct flow_block_offload *f,
struct list_head *driver_block_list,
- tc_setup_cb_t *cb, void *cb_ident, void *cb_priv,
+ flow_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv,
bool ingress_only)
{
struct flow_block_cb *block_cb;
if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list))
return -EBUSY;
- block_cb = flow_block_cb_alloc(f->net, cb, cb_ident,
- cb_priv, NULL);
+ block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
list_add_tail(&block_cb->driver_list, driver_block_list);
return 0;
case FLOW_BLOCK_UNBIND:
- block_cb = flow_block_cb_lookup(f, cb, cb_ident);
+ block_cb = flow_block_cb_lookup(f->block, cb, cb_ident);
if (!block_cb)
return -ENOENT;
txq = netdev_get_tx_queue(dev, q_index);
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (netif_xmit_frozen_or_stopped(txq) ||
- netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+ !dev_xmit_complete(netpoll_start_xmit(skb, dev, txq))) {
skb_queue_head(&npinfo->txq, skb);
HARD_TX_UNLOCK(dev, txq);
local_irq_restore(flags);
HARD_TX_UNLOCK(dev, txq);
- if (status == NETDEV_TX_OK)
+ if (dev_xmit_complete(status))
break;
}
}
- if (status != NETDEV_TX_OK) {
+ if (!dev_xmit_complete(status)) {
skb_queue_tail(&npinfo->txq, skb);
schedule_delayed_work(&npinfo->tx_work,0);
}
void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
- rcu_assign_sk_user_data(sk, NULL);
sk_psock_cork_free(psock);
sk_psock_zap_ingress(psock);
- sk_psock_restore_proto(sk, psock);
write_lock_bh(&sk->sk_callback_lock);
+ sk_psock_restore_proto(sk, psock);
+ rcu_assign_sk_user_data(sk, NULL);
if (psock->progs.skb_parser)
sk_psock_stop_strp(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
}
EXPORT_SYMBOL(skb_set_owner_w);
+static bool can_skb_orphan_partial(const struct sk_buff *skb)
+{
+#ifdef CONFIG_TLS_DEVICE
+ /* Drivers depend on in-order delivery for crypto offload,
+ * partial orphan breaks out-of-order-OK logic.
+ */
+ if (skb->decrypted)
+ return false;
+#endif
+ return (skb->destructor == sock_wfree ||
+ (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
+}
+
/* This helper is used by netem, as it can hold packets in its
* delay queue. We want to allow the owner socket to send more
* packets, as if they were already TX completed by a typical driver.
if (skb_is_tcp_pure_ack(skb))
return;
- if (skb->destructor == sock_wfree
-#ifdef CONFIG_INET
- || skb->destructor == tcp_wfree
-#endif
- ) {
+ if (can_skb_orphan_partial(skb)) {
struct sock *sk = skb->sk;
if (refcount_inc_not_zero(&sk->sk_refcnt)) {
core_initcall(net_inuse_init);
-static void assign_proto_idx(struct proto *prot)
+static int assign_proto_idx(struct proto *prot)
{
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
pr_err("PROTO_INUSE_NR exhausted\n");
- return;
+ return -ENOSPC;
}
set_bit(prot->inuse_idx, proto_inuse_idx);
+ return 0;
}
static void release_proto_idx(struct proto *prot)
clear_bit(prot->inuse_idx, proto_inuse_idx);
}
#else
-static inline void assign_proto_idx(struct proto *prot)
+static inline int assign_proto_idx(struct proto *prot)
{
+ return 0;
}
static inline void release_proto_idx(struct proto *prot)
int proto_register(struct proto *prot, int alloc_slab)
{
+ int ret = -ENOBUFS;
+
if (alloc_slab) {
prot->slab = kmem_cache_create_usercopy(prot->name,
prot->obj_size, 0,
}
mutex_lock(&proto_list_mutex);
+ ret = assign_proto_idx(prot);
+ if (ret) {
+ mutex_unlock(&proto_list_mutex);
+ goto out_free_timewait_sock_slab_name;
+ }
list_add(&prot->node, &proto_list);
- assign_proto_idx(prot);
mutex_unlock(&proto_list_mutex);
- return 0;
+ return ret;
out_free_timewait_sock_slab_name:
- kfree(prot->twsk_prot->twsk_slab_name);
+ if (alloc_slab && prot->twsk_prot)
+ kfree(prot->twsk_prot->twsk_slab_name);
out_free_request_sock_slab:
- req_prot_cleanup(prot->rsk_prot);
+ if (alloc_slab) {
+ req_prot_cleanup(prot->rsk_prot);
- kmem_cache_destroy(prot->slab);
- prot->slab = NULL;
+ kmem_cache_destroy(prot->slab);
+ prot->slab = NULL;
+ }
out:
- return -ENOBUFS;
+ return ret;
}
EXPORT_SYMBOL(proto_register);
static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
static struct workqueue_struct *broadcast_wq;
+static atomic64_t cookie_gen;
u64 sock_gen_cookie(struct sock *sk)
{
if (res)
return res;
- res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
+ res = atomic64_inc_return(&cookie_gen);
atomic64_cmpxchg(&sk->sk_cookie, 0, res);
}
}
raw_spin_unlock_bh(&stab->lock);
rcu_read_unlock();
+ synchronize_rcu();
+
bpf_map_area_free(stab->sks);
kfree(stab);
}
struct sock **psk)
{
struct sock *sk;
+ int err = 0;
raw_spin_lock_bh(&stab->lock);
sk = *psk;
if (!sk_test || sk_test == sk)
- *psk = NULL;
+ sk = xchg(psk, NULL);
+
+ if (likely(sk))
+ sock_map_unref(sk, psk);
+ else
+ err = -EINVAL;
+
raw_spin_unlock_bh(&stab->lock);
- if (unlikely(!sk))
- return -EINVAL;
- sock_map_unref(sk, psk);
- return 0;
+ return err;
}
static void sock_map_delete_from_link(struct bpf_map *map, struct sock *sk,
struct sock *sk, u64 flags)
{
struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct sk_psock_link *link;
struct sk_psock *psock;
struct sock *osk;
return -EINVAL;
if (unlikely(idx >= map->max_entries))
return -E2BIG;
+ if (unlikely(icsk->icsk_ulp_data))
+ return -EINVAL;
link = sk_psock_init_link();
if (!link)
int err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
- bool noblock = (*timeo_p ? false : true);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
if (sk_stream_memory_free(sk))
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
- if (!*timeo_p) {
- if (noblock)
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- goto do_nonblock;
- }
+ if (!*timeo_p)
+ goto do_eagain;
if (signal_pending(current))
goto do_interrupted;
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
do_error:
err = -EPIPE;
goto out;
-do_nonblock:
+do_eagain:
+ /* Make sure that whenever EAGAIN is returned, EPOLLOUT event can
+ * be generated later.
+ * When TCP receives ACK packets that make room, tcp_check_space()
+ * only calls tcp_new_space() if SOCK_NOSPACE is set.
+ */
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
err = -EAGAIN;
goto out;
do_interrupted:
struct flow_block_offload *f)
{
struct flow_block_cb *block_cb;
- tc_setup_cb_t *cb;
+ flow_setup_cb_t *cb;
if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
cb = dsa_slave_setup_tc_block_cb_ig;
if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list))
return -EBUSY;
- block_cb = flow_block_cb_alloc(f->net, cb, dev, dev, NULL);
+ block_cb = flow_block_cb_alloc(cb, dev, dev, NULL);
if (IS_ERR(block_cb))
return PTR_ERR(block_cb);
list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list);
return 0;
case FLOW_BLOCK_UNBIND:
- block_cb = flow_block_cb_lookup(f, cb, dev);
+ block_cb = flow_block_cb_lookup(f->block, cb, dev);
if (!block_cb)
return -ENOENT;
{
int port;
+ if (!ds->ops->port_mdb_add)
+ return;
+
for_each_set_bit(port, bitmap, ds->num_ports)
ds->ops->port_mdb_add(ds, port, mdb);
}
*
* RSV - VID[9]:
* To be used for further expansion of SWITCH_ID or for other purposes.
+ * Must be transmitted as zero and ignored on receive.
*
* SWITCH_ID - VID[8:6]:
* Index of switch within DSA tree. Must be between 0 and
*
* RSV - VID[5:4]:
* To be used for further expansion of PORT or for other purposes.
+ * Must be transmitted as zero and ignored on receive.
*
* PORT - VID[3:0]:
* Index of switch port. Must be between 0 and DSA_MAX_PORTS - 1.
"Expected meta frame, is %12llx "
"in the DSA master multicast filter?\n",
SJA1105_META_DMAC);
+ kfree_skb(sp->data->stampable_skb);
}
/* Hold a reference to avoid dsa_switch_rcv
* for further processing up the network stack.
*/
kfree_skb(skb);
-
- skb = skb_copy(stampable_skb, GFP_ATOMIC);
- if (!skb) {
- dev_err_ratelimited(dp->ds->dev,
- "Failed to copy stampable skb\n");
- spin_unlock(&sp->data->meta_lock);
- return NULL;
- }
+ skb = stampable_skb;
sja1105_transfer_meta(skb, meta);
- /* The cached copy will be freed now */
- skb_unref(stampable_skb);
spin_unlock(&sp->data->meta_lock);
}
reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
if (!reasm_data)
goto out_oom;
- inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data, false);
skb->dev = ldev;
skb->tstamp = fq->q.stamp;
static int __init af_ieee802154_init(void)
{
- int rc = -EINVAL;
+ int rc;
rc = proto_register(&ieee802154_raw_prot, 1);
if (rc)
if (filter->dump_exceptions) {
err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi,
- &i_fa, s_fa);
+ &i_fa, s_fa, flags);
if (err < 0)
goto stop;
}
if (!rt)
goto out;
- net = dev_net(rt->dst.dev);
+
+ if (rt->dst.dev)
+ net = dev_net(rt->dst.dev);
+ else if (skb_in->dev)
+ net = dev_net(skb_in->dev);
+ else
+ goto out;
/*
* Find the original header. It is expected to be valid, of course.
return false;
}
- icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway);
+ icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway));
return true;
}
void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
{
- __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE);
+ __ip_mc_inc_group(in_dev, addr, GFP_KERNEL);
}
EXPORT_SYMBOL(ip_mc_inc_group);
iml->sflist = NULL;
iml->sfmode = mode;
rcu_assign_pointer(inet->mc_list, iml);
- __ip_mc_inc_group(in_dev, addr, mode);
+ ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL);
err = 0;
done:
return err;
prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params);
if (!prev)
fq = inet_frag_create(fqdir, key, &prev);
- if (prev && !IS_ERR(prev)) {
+ if (!IS_ERR_OR_NULL(prev)) {
fq = prev;
if (!refcount_inc_not_zero(&fq->refcnt))
fq = NULL;
EXPORT_SYMBOL(inet_frag_reasm_prepare);
void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
- void *reasm_data)
+ void *reasm_data, bool try_coalesce)
{
struct sk_buff **nextp = (struct sk_buff **)reasm_data;
struct rb_node *rbn;
struct sk_buff *fp;
+ int sum_truesize;
skb_push(head, head->data - skb_network_header(head));
fp = FRAG_CB(head)->next_frag;
rbn = rb_next(&head->rbnode);
rb_erase(&head->rbnode, &q->rb_fragments);
+
+ sum_truesize = head->truesize;
while (rbn || fp) {
/* fp points to the next sk_buff in the current run;
* rbn points to the next run.
*/
/* Go through the current run. */
while (fp) {
- *nextp = fp;
- nextp = &fp->next;
- fp->prev = NULL;
- memset(&fp->rbnode, 0, sizeof(fp->rbnode));
- fp->sk = NULL;
- head->data_len += fp->len;
- head->len += fp->len;
+ struct sk_buff *next_frag = FRAG_CB(fp)->next_frag;
+ bool stolen;
+ int delta;
+
+ sum_truesize += fp->truesize;
if (head->ip_summed != fp->ip_summed)
head->ip_summed = CHECKSUM_NONE;
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
- head->truesize += fp->truesize;
- fp = FRAG_CB(fp)->next_frag;
+
+ if (try_coalesce && skb_try_coalesce(head, fp, &stolen,
+ &delta)) {
+ kfree_skb_partial(fp, stolen);
+ } else {
+ fp->prev = NULL;
+ memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+ fp->sk = NULL;
+
+ head->data_len += fp->len;
+ head->len += fp->len;
+ head->truesize += fp->truesize;
+
+ *nextp = fp;
+ nextp = &fp->next;
+ }
+
+ fp = next_frag;
}
/* Move to the next run. */
if (rbn) {
rbn = rbnext;
}
}
- sub_frag_mem_limit(q->fqdir, head->truesize);
+ sub_frag_mem_limit(q->fqdir, sum_truesize);
*nextp = NULL;
skb_mark_not_on_list(head);
return err;
}
+static bool ip_frag_coalesce_ok(const struct ipq *qp)
+{
+ return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER;
+}
+
/* Build a new IP datagram from all its fragments. */
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
struct sk_buff *prev_tail, struct net_device *dev)
if (len > 65535)
goto out_oversize;
- inet_frag_reasm_finish(&qp->q, skb, reasm_data);
+ inet_frag_reasm_finish(&qp->q, skb, reasm_data,
+ ip_frag_coalesce_ok(qp));
skb->dev = dev;
IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
const struct iphdr *tiph = &tunnel->parms.iph;
u8 ipproto;
+ if (!pskb_inet_may_pull(skb))
+ goto tx_error;
+
switch (skb->protocol) {
case htons(ETH_P_IP):
ipproto = IPPROTO_IPIP;
ctinfo == IP_CT_RELATED_REPLY))
return XT_CONTINUE;
- /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO,
- * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here
+ /* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO,
+ * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here
* on, which all have an ID field [relevant for hashing]. */
hash = clusterip_hashfn(skb, cipinfo->config);
opts.options |= XT_SYNPROXY_OPT_ECN;
opts.options &= info->options;
+ opts.mss_encode = opts.mss;
+ opts.mss = info->mss;
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_init_timestamp_cookie(info, &opts);
else
flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
flow.flowi4_tos = RT_TOS(iph->tos);
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
+ flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
}
int ret;
rtp_exp->tuple.dst.u.udp.port = htons(nated_port);
- ret = nf_ct_expect_related(rtp_exp);
+ ret = nf_ct_expect_related(rtp_exp, 0);
if (ret == 0) {
rtcp_exp->tuple.dst.u.udp.port =
htons(nated_port + 1);
- ret = nf_ct_expect_related(rtcp_exp);
+ ret = nf_ct_expect_related(rtcp_exp, 0);
if (ret == 0)
break;
else if (ret == -EBUSY) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, 0);
if (ret == 0)
break;
else if (ret != -EBUSY) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, 0);
if (ret == 0)
break;
else if (ret != -EBUSY) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, 0);
if (ret == 0)
break;
else if (ret != -EBUSY) {
int ret;
exp->tuple.dst.u.tcp.port = htons(nated_port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, 0);
if (ret == 0)
break;
else if (ret != -EBUSY) {
/* called with rcu_read_lock held */
static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
struct rtable *rt, u32 table_id, struct flowi4 *fl4,
- struct sk_buff *skb, u32 portid, u32 seq)
+ struct sk_buff *skb, u32 portid, u32 seq,
+ unsigned int flags)
{
struct rtmsg *r;
struct nlmsghdr *nlh;
u32 error;
u32 metrics[RTAX_MAX];
- nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0);
+ nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags);
if (!nlh)
return -EMSGSIZE;
static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, u32 table_id,
struct fnhe_hash_bucket *bucket, int genid,
- int *fa_index, int fa_start)
+ int *fa_index, int fa_start, unsigned int flags)
{
int i;
err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt,
table_id, NULL, skb,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq);
+ cb->nlh->nlmsg_seq, flags);
if (err)
return err;
next:
int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb,
u32 table_id, struct fib_info *fi,
- int *fa_index, int fa_start)
+ int *fa_index, int fa_start, unsigned int flags)
{
struct net *net = sock_net(cb->skb->sk);
int nhsel, genid = fnhe_genid(net);
err = 0;
if (bucket)
err = fnhe_dump_bucket(net, skb, cb, table_id, bucket,
- genid, fa_index, fa_start);
+ genid, fa_index, fa_start,
+ flags);
rcu_read_unlock();
if (err)
return err;
fl4.flowi4_tos, res.fi, 0);
} else {
err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
- NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0);
}
if (err < 0)
goto errout_rcu;
return mss_now;
}
+/* In some cases, both sendpage() and sendmsg() could have added
+ * an skb to the write queue, but failed adding payload on it.
+ * We need to remove it to consume less memory, but more
+ * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
+ * users.
+ */
+static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+{
+ if (skb && !skb->len) {
+ tcp_unlink_write_queue(skb, sk);
+ if (tcp_write_queue_empty(sk))
+ tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
+ sk_wmem_free_skb(sk, skb);
+ }
+}
+
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
{
if (!skb)
goto wait_for_memory;
+#ifdef CONFIG_TLS_DEVICE
+ skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
skb_entail(sk, skb);
copy = size_goal;
}
return copied;
do_error:
+ tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk));
if (copied)
goto out;
out_err:
sock_zerocopy_put(uarg);
return copied + copied_syn;
+do_error:
+ skb = tcp_write_queue_tail(sk);
do_fault:
- if (!skb->len) {
- tcp_unlink_write_queue(skb, sk);
- /* It is the one place in all of TCP, except connection
- * reset, where we can be unlinking the send_head.
- */
- if (tcp_write_queue_empty(sk))
- tcp_chrono_stop(sk, TCP_CHRONO_BUSY);
- sk_wmem_free_skb(sk, skb);
- }
+ tcp_remove_empty_skb(sk, skb);
-do_error:
if (copied + copied_syn)
goto out;
out_err:
static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
struct sk_msg tmp, *msg_tx = NULL;
- int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
int copied = 0, err = 0;
struct sk_psock *psock;
long timeo;
+ int flags;
+
+ /* Don't let internal do_tcp_sendpages() flags through */
+ flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED);
+ flags |= MSG_NO_SHARED_FRAGS;
psock = sk_psock_get(sk);
if (unlikely(!psock))
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
int nsize, old_factor;
+ long limit;
int nlen;
u8 flags;
if (nsize < 0)
nsize = 0;
- if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf &&
- tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) {
+ /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
+ * We need some allowance to not penalize applications setting small
+ * SO_SNDBUF values.
+ * Also allow first and last skb in retransmit queue to be split.
+ */
+ limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+ if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
+ tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
+ skb != tcp_rtx_queue_head(sk) &&
+ skb != tcp_rtx_queue_tail(sk))) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
return -ENOMEM;
}
buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
if (!buff)
return -ENOMEM; /* We'll just try again later. */
+ skb_copy_decrypted(buff, skb);
sk->sk_wmem_queued += buff->truesize;
sk_mem_charge(sk, buff->truesize);
buff = sk_stream_alloc_skb(sk, 0, gfp, true);
if (unlikely(!buff))
return -ENOMEM;
+ skb_copy_decrypted(buff, skb);
sk->sk_wmem_queued += buff->truesize;
sk_mem_charge(sk, buff->truesize);
if (len <= skb->len)
break;
- if (unlikely(TCP_SKB_CB(skb)->eor))
+ if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb))
return false;
len -= skb->len;
sk_mem_charge(sk, nskb->truesize);
skb = tcp_send_head(sk);
+ skb_copy_decrypted(nskb, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
* we need to propagate it to the new skb.
*/
TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
+ tcp_skb_collapse_tstamp(nskb, skb);
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
} else {
rcu_read_unlock();
}
+void tcp_update_ulp(struct sock *sk, struct proto *proto)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (!icsk->icsk_ulp_ops) {
+ sk->sk_prot = proto;
+ return;
+ }
+
+ if (icsk->icsk_ulp_ops->update)
+ icsk->icsk_ulp_ops->update(sk, proto);
+}
+
void tcp_cleanup_ulp(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (!idev) {
idev = ipv6_add_dev(dev);
if (IS_ERR(idev))
- return NULL;
+ return idev;
}
if (dev->flags&IFF_UP)
int err = 0;
if (addr_type == IPV6_ADDR_ANY ||
- addr_type & IPV6_ADDR_MULTICAST ||
+ (addr_type & IPV6_ADDR_MULTICAST &&
+ !(cfg->ifa_flags & IFA_F_MCAUTOJOIN)) ||
(!(idev->dev->flags & IFF_LOOPBACK) &&
!netif_is_l3_master(idev->dev) &&
addr_type & IPV6_ADDR_LOOPBACK))
ASSERT_RTNL();
idev = ipv6_find_idev(dev);
- if (!idev)
- return ERR_PTR(-ENOBUFS);
+ if (IS_ERR(idev))
+ return idev;
if (idev->cnf.disable_ipv6)
return ERR_PTR(-EACCES);
ASSERT_RTNL();
idev = ipv6_find_idev(dev);
- if (!idev) {
+ if (IS_ERR(idev)) {
pr_debug("%s: add_dev failed\n", __func__);
return;
}
*/
idev = ipv6_find_idev(dev);
- if (!idev) {
+ if (IS_ERR(idev)) {
pr_debug("%s: add_dev failed\n", __func__);
return;
}
ASSERT_RTNL();
idev = ipv6_find_idev(dev);
- if (!idev) {
+ if (IS_ERR(idev)) {
pr_debug("%s: add_dev failed\n", __func__);
return;
}
IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC;
idev = ipv6_find_idev(dev);
- if (!idev)
- return -ENOBUFS;
+ if (IS_ERR(idev))
+ return PTR_ERR(idev);
if (!ipv6_allow_optimistic_dad(net, idev))
cfg.ifa_flags &= ~IFA_F_OPTIMISTIC;
struct flowi6 *fl6, __u8 *dsfield,
int *encap_limit)
{
- struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ struct ipv6hdr *ipv6h;
struct ip6_tnl *t = netdev_priv(dev);
__u16 offset;
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+ ipv6h = ipv6_hdr(skb);
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
}
fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+ dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
- dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
-
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
}
fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
+ dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
- dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
-
skb_set_inner_ipproto(skb, IPPROTO_IPV6);
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
if (pmc) {
im->idev = pmc->idev;
if (im->mca_sfmode == MCAST_INCLUDE) {
- im->mca_tomb = pmc->mca_tomb;
- im->mca_sources = pmc->mca_sources;
+ swap(im->mca_tomb, pmc->mca_tomb);
+ swap(im->mca_sources, pmc->mca_sources);
for (psf = im->mca_sources; psf; psf = psf->sf_next)
psf->sf_crcount = idev->mc_qrv;
} else {
im->mca_crcount = idev->mc_qrv;
}
in6_dev_put(pmc->idev);
+ ip6_mc_clear_src(pmc);
kfree(pmc);
}
spin_unlock_bh(&im->mca_lock);
opts.options |= XT_SYNPROXY_OPT_ECN;
opts.options &= info->options;
+ opts.mss_encode = opts.mss;
+ opts.mss = info->mss;
if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP)
synproxy_init_timestamp_cookie(info, &opts);
else
if (rpfilter_addr_linklocal(&iph->saddr)) {
lookup_flags |= RT6_LOOKUP_F_IFACE;
fl6.flowi6_oif = dev->ifindex;
- } else if ((flags & XT_RPFILTER_LOOSE) == 0)
+ /* Set flowi6_oif for vrf devices to lookup route in l3mdev domain. */
+ } else if (netif_is_l3_master(dev) || netif_is_l3_slave(dev) ||
+ (flags & XT_RPFILTER_LOOSE) == 0)
fl6.flowi6_oif = dev->ifindex;
rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags);
goto out;
}
- if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
+ if (rt->rt6i_idev->dev == dev ||
+ l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex ||
+ (flags & XT_RPFILTER_LOOSE))
ret = true;
out:
ip6_rt_put(rt);
skb_reset_transport_header(skb);
- inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data, false);
skb->ignore_df = 1;
skb->dev = dev;
skb_reset_transport_header(skb);
- inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+ inet_frag_reasm_finish(&fq->q, skb, reasm_data, true);
skb->dev = dev;
ipv6_hdr(skb)->payload_len = htons(payload_len);
nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg);
if (!arg.match)
- return;
+ goto unlock;
fib6_nh = arg.match;
} else {
fib6_nh = from->fib6_nh;
sk->sk_state = IUCV_DISCONN;
sk->sk_state_change(sk);
}
- case IUCV_DISCONN: /* fall through */
+ /* fall through */
+
+ case IUCV_DISCONN:
sk->sk_state = IUCV_CLOSING;
sk->sk_state_change(sk);
iucv_sock_in_state(sk, IUCV_CLOSED, 0),
timeo);
}
+ /* fall through */
- case IUCV_CLOSING: /* fall through */
+ case IUCV_CLOSING:
sk->sk_state = IUCV_CLOSED;
sk->sk_state_change(sk);
skb_queue_purge(&iucv->send_skb_q);
skb_queue_purge(&iucv->backlog_skb_q);
+ /* fall through */
- default: /* fall through */
+ default:
iucv_sever_path(sk, 1);
}
kfree_skb(skb);
break;
}
- /* fall through and receive non-zero length data */
+ /* fall through - and receive non-zero length data */
case (AF_IUCV_FLAG_SHT):
/* shutdown request */
- /* fall through and receive zero length data */
+ /* fall through - and receive zero length data */
case 0:
/* plain data frame */
IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class;
.recvmsg = pppol2tp_recvmsg,
.mmap = sock_no_mmap,
.ioctl = pppox_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = pppox_compat_ioctl,
+#endif
};
static const struct pppox_proto pppol2tp_proto = {
err = ieee80211_set_probe_resp(sdata, params->probe_resp,
params->probe_resp_len, csa);
- if (err < 0)
+ if (err < 0) {
+ kfree(new);
return err;
+ }
if (err == 0)
changed |= BSS_CHANGED_AP_PROBE_RESP;
params->civicloc,
params->civicloc_len);
- if (err < 0)
+ if (err < 0) {
+ kfree(new);
return err;
+ }
changed |= BSS_CHANGED_FTM_RESPONDER;
}
if (is_multicast_ether_addr(mac))
return -EINVAL;
+ if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER) &&
+ sdata->vif.type == NL80211_IFTYPE_STATION &&
+ !sdata->u.mgd.associated)
+ return -EINVAL;
+
sta = sta_info_alloc(sdata, mac, GFP_KERNEL);
if (!sta)
return -ENOMEM;
if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER))
sta->sta.tdls = true;
- if (sta->sta.tdls && sdata->vif.type == NL80211_IFTYPE_STATION &&
- !sdata->u.mgd.associated)
- return -EINVAL;
-
err = sta_apply_parameters(local, sta, params);
if (err) {
sta_info_free(local, sta);
if (!check_sdata_in_driver(sdata))
return -EIO;
- if (WARN_ONCE(params->cw_min == 0 ||
- params->cw_min > params->cw_max,
- "%s: invalid CW_min/CW_max: %d/%d\n",
- sdata->name, params->cw_min, params->cw_max))
+ if (params->cw_min == 0 || params->cw_min > params->cw_max) {
+ /*
+ * If we can't configure hardware anyway, don't warn. We may
+ * never have initialized the CW parameters.
+ */
+ WARN_ONCE(local->ops->conf_tx,
+ "%s: invalid CW_min/CW_max: %d/%d\n",
+ sdata->name, params->cw_min, params->cw_max);
return -EINVAL;
+ }
trace_drv_conf_tx(local, sdata, ac, params);
if (local->ops->conf_tx)
static void ieee80211_if_setup_no_queue(struct net_device *dev)
{
ieee80211_if_setup(dev);
- dev->features |= NETIF_F_LLTX;
dev->priv_flags |= IFF_NO_QUEUE;
}
ieee80211_regulatory_limit_wmm_params(sdata, ¶ms[ac], ac);
}
+ /* WMM specification requires all 4 ACIs. */
+ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+ if (params[ac].cw_min == 0) {
+ sdata_info(sdata,
+ "AP has invalid WMM params (missing AC %d), using defaults\n",
+ ac);
+ return false;
+ }
+ }
+
for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
mlme_dbg(sdata,
"WMM AC=%d acm=%d aifs=%d cWmin=%d cWmax=%d txop=%d uapsd=%d, downgraded=%d\n",
skb->protocol == cpu_to_be16(ETH_P_PREAUTH)) &&
sdata->control_port_over_nl80211)) {
struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
- bool noencrypt = status->flag & RX_FLAG_DECRYPTED;
+ bool noencrypt = !(status->flag & RX_FLAG_DECRYPTED);
cfg80211_rx_control_port(dev, skb, noencrypt);
dev_kfree_skb(skb);
} else {
+ memset(skb->cb, 0, sizeof(skb->cb));
+
/* deliver to local stack */
if (rx->napi)
napi_gro_receive(rx->napi, skb);
if (skb) {
skb->protocol = eth_type_trans(skb, dev);
- memset(skb->cb, 0, sizeof(skb->cb));
-
ieee80211_deliver_skb_to_local_stack(skb, rx);
}
}
/* Always allow software iftypes */
- if (local->hw.wiphy->software_iftypes & BIT(iftype) ||
- (iftype == NL80211_IFTYPE_AP_VLAN &&
- local->hw.wiphy->flags & WIPHY_FLAG_4ADDR_AP)) {
+ if (cfg80211_iftype_allowed(local->hw.wiphy, iftype, 0, 1)) {
if (radar_detect)
return -EINVAL;
return 0;
if (sdata_iter == sdata ||
!ieee80211_sdata_running(sdata_iter) ||
- local->hw.wiphy->software_iftypes & BIT(wdev_iter->iftype))
+ cfg80211_iftype_allowed(local->hw.wiphy,
+ wdev_iter->iftype, 0, 1))
continue;
params.iftype_num[wdev_iter->iftype]++;
mpls_stats_inc_outucastpkts(out_dev, skb);
if (rt) {
- if (rt->rt_gw_family == AF_INET)
- err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
- skb);
- else if (rt->rt_gw_family == AF_INET6)
+ if (rt->rt_gw_family == AF_INET6)
err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt->rt_gw6,
skb);
+ else
+ err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gw4,
+ skb);
} else if (rt6) {
if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
/* 6PE (RFC 4798) */
checksum = ncsi_calculate_checksum((unsigned char *)h,
sizeof(*h) + nca->payload);
pchecksum = (__be32 *)((void *)h + sizeof(struct ncsi_pkt_hdr) +
- nca->payload);
+ ALIGN(nca->payload, 4));
*pchecksum = htonl(checksum);
}
int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca)
{
+ struct ncsi_cmd_handler *nch = NULL;
struct ncsi_request *nr;
+ unsigned char type;
struct ethhdr *eh;
- struct ncsi_cmd_handler *nch = NULL;
int i, ret;
+ /* Use OEM generic handler for Netlink request */
+ if (nca->req_flags == NCSI_REQ_FLAG_NETLINK_DRIVEN)
+ type = NCSI_PKT_CMD_OEM;
+ else
+ type = nca->type;
+
/* Search for the handler */
for (i = 0; i < ARRAY_SIZE(ncsi_cmd_handlers); i++) {
- if (ncsi_cmd_handlers[i].type == nca->type) {
+ if (ncsi_cmd_handlers[i].type == type) {
if (ncsi_cmd_handlers[i].handler)
nch = &ncsi_cmd_handlers[i];
else
if (ntohs(h->code) != NCSI_PKT_RSP_C_COMPLETED ||
ntohs(h->reason) != NCSI_PKT_RSP_R_NO_ERROR) {
netdev_dbg(nr->ndp->ndev.dev,
- "NCSI: non zero response/reason code\n");
+ "NCSI: non zero response/reason code %04xh, %04xh\n",
+ ntohs(h->code), ntohs(h->reason));
return -EPERM;
}
* sender doesn't support checksum according to NCSI
* specification.
*/
- pchecksum = (__be32 *)((void *)(h + 1) + payload - 4);
+ pchecksum = (__be32 *)((void *)(h + 1) + ALIGN(payload, 4) - 4);
if (ntohl(*pchecksum) == 0)
return 0;
sizeof(*h) + payload - 4);
if (*pchecksum != htonl(checksum)) {
- netdev_dbg(nr->ndp->ndev.dev, "NCSI: checksum mismatched\n");
+ netdev_dbg(nr->ndp->ndev.dev,
+ "NCSI: checksum mismatched; recd: %08x calc: %08x\n",
+ *pchecksum, htonl(checksum));
return -EINVAL;
}
of Network Address Translation on them.
This is FTP support on Layer 3 independent connection tracking.
- Layer 3 independent connection tracking is experimental scheme
- which generalize ip_conntrack to support other layer 3 protocols.
To compile it as a module, choose M here. If unsure, say N.
help
SIP is an application-layer control protocol that can establish,
modify, and terminate multimedia sessions (conferences) such as
- Internet telephony calls. With the ip_conntrack_sip and
+ Internet telephony calls. With the nf_conntrack_sip and
the nf_nat_sip modules you can support the protocol on a connection
tracking/NATing firewall.
depends on NETFILTER_ADVANCED
help
Helper matching allows you to match packets in dynamic connections
- tracked by a conntrack-helper, ie. ip_conntrack_ftp
+ tracked by a conntrack-helper, ie. nf_conntrack_ftp
To compile it as a module, choose M here. If unsure, say Y.
e.id = ip_to_id(map, ip);
- if (opt->flags & IPSET_DIM_ONE_SRC)
+ if (opt->flags & IPSET_DIM_TWO_SRC)
ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
else
ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
return -ENOENT;
write_lock_bh(&ip_set_ref_lock);
- if (set->ref != 0) {
+ if (set->ref != 0 || set->ref_netlink != 0) {
ret = -IPSET_ERR_REFERENCED;
goto out;
}
struct hash_ipmac4_elem e = { .ip = 0, { .foo[0] = 0, .foo[1] = 0 } };
struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
- /* MAC can be src only */
- if (!(opt->flags & IPSET_DIM_TWO_SRC))
- return 0;
-
if (skb_mac_header(skb) < skb->head ||
(skb_mac_header(skb) + ETH_HLEN) > skb->data)
return -EINVAL;
- if (opt->flags & IPSET_DIM_ONE_SRC)
+ if (opt->flags & IPSET_DIM_TWO_SRC)
ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
else
ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
IP_VS_DBG_BUF(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n",
__func__, ct, ARG_TUPLE(&exp->tuple));
- nf_ct_expect_related(exp);
+ nf_ct_expect_related(exp, 0);
nf_ct_expect_put(exp);
}
EXPORT_SYMBOL(ip_vs_nfct_expect_related);
if (nf_nat_amanda && ct->status & IPS_NAT_MASK)
ret = nf_nat_amanda(skb, ctinfo, protoff,
off - dataoff, len, exp);
- else if (nf_ct_expect_related(exp) != 0) {
+ else if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
}
exp->class = NF_CT_EXPECT_CLASS_DEFAULT;
exp->helper = NULL;
- nf_ct_expect_related(exp);
+ nf_ct_expect_related(exp, 0);
nf_ct_expect_put(exp);
nf_ct_refresh(ct, skb, timeout * HZ);
* table location, we assume id gets exposed to userspace.
*
* Following nf_conn items do not change throughout lifetime
- * of the nf_conn after it has been committed to main hash table:
+ * of the nf_conn:
*
* 1. nf_conn address
- * 2. nf_conn->ext address
- * 3. nf_conn->master address (normally NULL)
- * 4. tuple
- * 5. the associated net namespace
+ * 2. nf_conn->master address (normally NULL)
+ * 3. the associated net namespace
+ * 4. the original direction tuple
*/
u32 nf_ct_get_id(const struct nf_conn *ct)
{
net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
a = (unsigned long)ct;
- b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
- c = (unsigned long)ct->ext;
- d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+ b = (unsigned long)ct->master;
+ c = (unsigned long)nf_ct_net(ct);
+ d = (unsigned long)siphash(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+ sizeof(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple),
&ct_id_seed);
#ifdef CONFIG_64BIT
return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
#include <linux/netfilter/nfnetlink_conntrack.h>
#include <linux/mutex.h>
-/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be
- * in ip_conntrack_core, since we don't want the protocols to autoload
- * or depend on ctnetlink */
+/* Generic function for tcp/udp/sctp/dccp and alike. */
int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
const struct nf_conntrack_tuple *tuple)
{
static inline int expect_matches(const struct nf_conntrack_expect *a,
const struct nf_conntrack_expect *b)
{
- return a->master == b->master &&
- nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
+ return nf_ct_tuple_equal(&a->tuple, &b->tuple) &&
nf_ct_tuple_mask_equal(&a->mask, &b->mask) &&
net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) &&
nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master));
}
+static bool master_matches(const struct nf_conntrack_expect *a,
+ const struct nf_conntrack_expect *b,
+ unsigned int flags)
+{
+ if (flags & NF_CT_EXP_F_SKIP_MASTER)
+ return true;
+
+ return a->master == b->master;
+}
+
/* Generally a bad idea to call this: could have matched already. */
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
{
nf_ct_remove_expect(last);
}
-static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
+static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect,
+ unsigned int flags)
{
const struct nf_conntrack_expect_policy *p;
struct nf_conntrack_expect *i;
}
h = nf_ct_expect_dst_hash(net, &expect->tuple);
hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) {
- if (expect_matches(i, expect)) {
- if (i->class != expect->class)
+ if (master_matches(i, expect, flags) &&
+ expect_matches(i, expect)) {
+ if (i->class != expect->class ||
+ i->master != expect->master)
return -EALREADY;
if (nf_ct_remove_expect(i))
}
int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
- u32 portid, int report)
+ u32 portid, int report, unsigned int flags)
{
int ret;
spin_lock_bh(&nf_conntrack_expect_lock);
- ret = __nf_ct_expect_check(expect);
+ ret = __nf_ct_expect_check(expect, flags);
if (ret < 0)
goto out;
i++;
}
- pr_debug("Skipped up to `%c'!\n", skip);
+ pr_debug("Skipped up to 0x%hhx delimiter!\n", skip);
*numoff = i;
*numlen = getnum(data + i, dlen - i, cmd, term, numoff);
protoff, matchoff, matchlen, exp);
else {
/* Can't expect this? Best to drop packet now. */
- if (nf_ct_expect_related(exp) != 0) {
+ if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
} else
// SPDX-License-Identifier: GPL-2.0-only
/*
- * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323
- * conntrack/NAT module.
+ * BER and PER decoding library for H.323 conntrack/NAT module.
*
* Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net>
*
- * See ip_conntrack_helper_h323_asn1.h for details.
+ * See nf_conntrack_helper_h323_asn1.h for details.
*/
#ifdef __KERNEL__
ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff,
taddr, port, rtp_port, rtp_exp, rtcp_exp);
} else { /* Conntrack only */
- if (nf_ct_expect_related(rtp_exp) == 0) {
- if (nf_ct_expect_related(rtcp_exp) == 0) {
+ if (nf_ct_expect_related(rtp_exp, 0) == 0) {
+ if (nf_ct_expect_related(rtcp_exp, 0) == 0) {
pr_debug("nf_ct_h323: expect RTP ");
nf_ct_dump_tuple(&rtp_exp->tuple);
pr_debug("nf_ct_h323: expect RTCP ");
ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr,
port, exp);
} else { /* Conntrack only */
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_h323: expect T.120 ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr,
port, exp);
} else { /* Conntrack only */
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_q931: expect H.245 ");
nf_ct_dump_tuple(&exp->tuple);
} else
protoff, data, dataoff,
taddr, port, exp);
} else { /* Conntrack only */
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_q931: expect Call Forwarding ");
nf_ct_dump_tuple(&exp->tuple);
} else
ret = nat_q931(skb, ct, ctinfo, protoff, data,
taddr, i, port, exp);
} else { /* Conntrack only */
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
nf_ct_dump_tuple(&exp->tuple);
IPPROTO_UDP, NULL, &port);
exp->helper = nf_conntrack_helper_ras;
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect RAS ");
nf_ct_dump_tuple(&exp->tuple);
} else
exp->flags = NF_CT_EXPECT_PERMANENT;
exp->helper = nf_conntrack_helper_q931;
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
nf_ct_dump_tuple(&exp->tuple);
} else
exp->flags = NF_CT_EXPECT_PERMANENT;
exp->helper = nf_conntrack_helper_q931;
- if (nf_ct_expect_related(exp) == 0) {
+ if (nf_ct_expect_related(exp, 0) == 0) {
pr_debug("nf_ct_ras: expect Q.931 ");
nf_ct_dump_tuple(&exp->tuple);
} else
addr_beg_p - ib_ptr,
addr_end_p - addr_beg_p,
exp);
- else if (nf_ct_expect_related(exp) != 0) {
+ else if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, ct,
"cannot add expectation");
ret = NF_DROP;
if (IS_ERR(exp))
return PTR_ERR(exp);
- err = nf_ct_expect_related_report(exp, portid, report);
+ err = nf_ct_expect_related_report(exp, portid, report, 0);
nf_ct_expect_put(exp);
return err;
}
goto err_rcu;
}
- err = nf_ct_expect_related_report(exp, portid, report);
+ err = nf_ct_expect_related_report(exp, portid, report, 0);
nf_ct_expect_put(exp);
err_rcu:
rcu_read_unlock();
nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre);
if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK)
nf_nat_pptp_exp_gre(exp_orig, exp_reply);
- if (nf_ct_expect_related(exp_orig) != 0)
+ if (nf_ct_expect_related(exp_orig, 0) != 0)
goto out_put_both;
- if (nf_ct_expect_related(exp_reply) != 0)
+ if (nf_ct_expect_related(exp_reply, 0) != 0)
goto out_unexpect_orig;
/* Add GRE keymap entries */
// SPDX-License-Identifier: GPL-2.0-only
/*
- * ip_conntrack_proto_gre.c - Version 3.0
- *
* Connection tracking protocol helper module for GRE.
*
* GRE is a generic encapsulation protocol, which is generally not very
return -NF_ACCEPT;
}
- /* See ip_conntrack_proto_tcp.c */
+ /* See nf_conntrack_proto_tcp.c */
if (state->net->ct.sysctl_checksum &&
state->hook == NF_INET_PRE_ROUTING &&
nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) {
struct ip_ct_tcp_state *receiver = &state->seen[!dir];
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
__u32 seq, ack, sack, end, win, swin;
+ u16 win_raw;
s32 receiver_offset;
bool res, in_recv_win;
*/
seq = ntohl(tcph->seq);
ack = sack = ntohl(tcph->ack_seq);
- win = ntohs(tcph->window);
+ win_raw = ntohs(tcph->window);
+ win = win_raw;
end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);
if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
&& state->last_seq == seq
&& state->last_ack == ack
&& state->last_end == end
- && state->last_win == win)
+ && state->last_win == win_raw)
state->retrans++;
else {
state->last_dir = dir;
state->last_seq = seq;
state->last_ack = ack;
state->last_end = end;
- state->last_win = win;
+ state->last_win = win_raw;
state->retrans = 0;
}
}
nf_ct_dump_tuple(&exp->tuple);
/* Can't expect this? Best to drop packet now. */
- if (nf_ct_expect_related(exp) != 0) {
+ if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
}
/* -EALREADY handling works around end-points that send
* SDP messages with identical port but different media type,
* we pretend expectation was set up.
+ * It also works in the case that SDP messages are sent with
+ * identical expect tuples but for different master conntracks.
*/
- int errp = nf_ct_expect_related(rtp_exp);
+ int errp = nf_ct_expect_related(rtp_exp,
+ NF_CT_EXP_F_SKIP_MASTER);
if (errp == 0 || errp == -EALREADY) {
- int errcp = nf_ct_expect_related(rtcp_exp);
+ int errcp = nf_ct_expect_related(rtcp_exp,
+ NF_CT_EXP_F_SKIP_MASTER);
if (errcp == 0 || errcp == -EALREADY)
ret = NF_ACCEPT;
ret = hooks->expect(skb, protoff, dataoff, dptr, datalen,
exp, matchoff, matchlen);
else {
- if (nf_ct_expect_related(exp) != 0) {
+ if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
} else
table[NF_SYSCTL_CT_COUNT].data = &net->ct.count;
table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum;
table[NF_SYSCTL_CT_LOG_INVALID].data = &net->ct.sysctl_log_invalid;
+ table[NF_SYSCTL_CT_ACCT].data = &net->ct.sysctl_acct;
+ table[NF_SYSCTL_CT_HELPER].data = &net->ct.sysctl_auto_assign_helper;
#ifdef CONFIG_NF_CONNTRACK_EVENTS
table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events;
+#endif
+#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP
+ table[NF_SYSCTL_CT_TIMESTAMP].data = &net->ct.sysctl_tstamp;
#endif
table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout;
table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout;
nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook);
if (nf_nat_tftp && ct->status & IPS_NAT_MASK)
ret = nf_nat_tftp(skb, ctinfo, exp);
- else if (nf_ct_expect_related(exp) != 0) {
+ else if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
}
#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ)
#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ)
-static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+static inline __s32 nf_flow_timeout_delta(unsigned int timeout)
+{
+ return (__s32)(timeout - (u32)jiffies);
+}
+
+static void flow_offload_fixup_ct_timeout(struct nf_conn *ct)
{
const struct nf_conntrack_l4proto *l4proto;
+ int l4num = nf_ct_protonum(ct);
unsigned int timeout;
- int l4num;
-
- l4num = nf_ct_protonum(ct);
- if (l4num == IPPROTO_TCP)
- flow_offload_fixup_tcp(&ct->proto.tcp);
l4proto = nf_ct_l4proto_find(l4num);
if (!l4proto)
else
return;
- ct->timeout = nfct_time_stamp + timeout;
+ if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
+ ct->timeout = nfct_time_stamp + timeout;
+}
+
+static void flow_offload_fixup_ct_state(struct nf_conn *ct)
+{
+ if (nf_ct_protonum(ct) == IPPROTO_TCP)
+ flow_offload_fixup_tcp(&ct->proto.tcp);
+}
+
+static void flow_offload_fixup_ct(struct nf_conn *ct)
+{
+ flow_offload_fixup_ct_state(ct);
+ flow_offload_fixup_ct_timeout(ct);
}
void flow_offload_free(struct flow_offload *flow)
}
EXPORT_SYMBOL_GPL(flow_offload_add);
+static inline bool nf_flow_has_expired(const struct flow_offload *flow)
+{
+ return nf_flow_timeout_delta(flow->timeout) <= 0;
+}
+
static void flow_offload_del(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
e = container_of(flow, struct flow_offload_entry, flow);
clear_bit(IPS_OFFLOAD_BIT, &e->ct->status);
+ if (nf_flow_has_expired(flow))
+ flow_offload_fixup_ct(e->ct);
+ else if (flow->flags & FLOW_OFFLOAD_TEARDOWN)
+ flow_offload_fixup_ct_timeout(e->ct);
+
flow_offload_free(flow);
}
return err;
}
-static inline bool nf_flow_has_expired(const struct flow_offload *flow)
-{
- return (__s32)(flow->timeout - (u32)jiffies) <= 0;
-}
-
static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
{
struct nf_flowtable *flow_table = data;
return true;
}
+static int nf_flow_offload_dst_check(struct dst_entry *dst)
+{
+ if (unlikely(dst_xfrm(dst)))
+ return dst_check(dst, 0) ? 0 : -1;
+
+ return 0;
+}
+
+static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
+ const struct nf_hook_state *state,
+ struct dst_entry *dst)
+{
+ skb_orphan(skb);
+ skb_dst_set_noref(skb, dst);
+ dst_output(state->net, state->sk, skb);
+ return NF_STOLEN;
+}
+
unsigned int
nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
return NF_ACCEPT;
+ if (nf_flow_offload_dst_check(&rt->dst)) {
+ flow_offload_teardown(flow);
+ return NF_ACCEPT;
+ }
+
if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
return NF_DROP;
flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
iph = ip_hdr(skb);
ip_decrease_ttl(iph);
+ skb->tstamp = 0;
+
+ if (unlikely(dst_xfrm(&rt->dst))) {
+ memset(skb->cb, 0, sizeof(struct inet_skb_parm));
+ IPCB(skb)->iif = skb->dev->ifindex;
+ IPCB(skb)->flags = IPSKB_FORWARDED;
+ return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+ }
skb->dev = outdev;
nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr);
sizeof(*ip6h)))
return NF_ACCEPT;
+ if (nf_flow_offload_dst_check(&rt->dst)) {
+ flow_offload_teardown(flow);
+ return NF_ACCEPT;
+ }
+
if (skb_try_make_writable(skb, sizeof(*ip6h)))
return NF_DROP;
flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
ip6h = ipv6_hdr(skb);
ip6h->hop_limit--;
+ skb->tstamp = 0;
+
+ if (unlikely(dst_xfrm(&rt->dst))) {
+ memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
+ IP6CB(skb)->iif = skb->dev->ifindex;
+ IP6CB(skb)->flags = IP6SKB_FORWARDED;
+ return nf_flow_xmit_xfrm(skb, state, &rt->dst);
+ }
skb->dev = outdev;
nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6);
int res;
exp->tuple.dst.u.tcp.port = htons(port);
- res = nf_ct_expect_related(exp);
+ res = nf_ct_expect_related(exp, 0);
if (res == 0)
break;
else if (res != -EBUSY) {
* and NF_INET_LOCAL_OUT, we change the destination to map into the
* range. It might not be possible to get a unique tuple, but we try.
* At worst (or if we race), we will end up with a final duplicate in
- * __ip_conntrack_confirm and drop the packet. */
+ * __nf_conntrack_confirm and drop the packet. */
static void
get_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_conntrack_tuple *orig_tuple,
int ret;
exp->tuple.dst.u.tcp.port = htons(port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, 0);
if (ret == 0)
break;
else if (ret != -EBUSY) {
int ret;
exp->tuple.dst.u.tcp.port = htons(port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, 0);
if (ret == 0)
break;
else if (ret != -EBUSY) {
int ret;
exp->tuple.dst.u.udp.port = htons(port);
- ret = nf_ct_expect_related(exp);
+ ret = nf_ct_expect_related(exp, NF_CT_EXP_F_SKIP_MASTER);
if (ret == 0)
break;
else if (ret != -EBUSY) {
int ret;
rtp_exp->tuple.dst.u.udp.port = htons(port);
- ret = nf_ct_expect_related(rtp_exp);
+ ret = nf_ct_expect_related(rtp_exp,
+ NF_CT_EXP_F_SKIP_MASTER);
if (ret == -EBUSY)
continue;
else if (ret < 0) {
break;
}
rtcp_exp->tuple.dst.u.udp.port = htons(port + 1);
- ret = nf_ct_expect_related(rtcp_exp);
+ ret = nf_ct_expect_related(rtcp_exp,
+ NF_CT_EXP_F_SKIP_MASTER);
if (ret == 0)
break;
else if (ret == -EBUSY) {
= ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
exp->dir = IP_CT_DIR_REPLY;
exp->expectfn = nf_nat_follow_master;
- if (nf_ct_expect_related(exp) != 0) {
+ if (nf_ct_expect_related(exp, 0) != 0) {
nf_ct_helper_log(skb, exp->master, "cannot add expectation");
return NF_DROP;
}
struct iphdr *iph, *niph;
struct tcphdr *nth;
unsigned int tcp_hdr_size;
- u16 mss = opts->mss;
+ u16 mss = opts->mss_encode;
iph = ip_hdr(skb);
state = &ct->proto.tcp;
switch (state->state) {
case TCP_CONNTRACK_CLOSE:
- if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
+ if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
ntohl(th->seq) + 1);
break;
struct ipv6hdr *iph, *niph;
struct tcphdr *nth;
unsigned int tcp_hdr_size;
- u16 mss = opts->mss;
+ u16 mss = opts->mss_encode;
iph = ipv6_hdr(skb);
state = &ct->proto.tcp;
switch (state->state) {
case TCP_CONNTRACK_CLOSE:
- if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
+ if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
nf_ct_seqadj_init(ct, ctinfo, synproxy->isn -
ntohl(th->seq) + 1);
break;
return;
list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
- if (trans->msg_type == NFT_MSG_NEWSET &&
- nft_trans_set(trans) == set) {
- set->bound = true;
+ switch (trans->msg_type) {
+ case NFT_MSG_NEWSET:
+ if (nft_trans_set(trans) == set)
+ nft_trans_set_bound(trans) = true;
+ break;
+ case NFT_MSG_NEWSETELEM:
+ if (nft_trans_elem_set(trans) == set)
+ nft_trans_elem_set_bound(trans) = true;
break;
}
}
chain->flags |= NFT_BASE_CHAIN | flags;
basechain->policy = NF_ACCEPT;
- INIT_LIST_HEAD(&basechain->cb_list);
+ if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
+ nft_chain_offload_priority(basechain) < 0)
+ return -EOPNOTSUPP;
+
+ flow_block_init(&basechain->flow_block);
} else {
chain = kzalloc(sizeof(*chain), GFP_KERNEL);
if (chain == NULL)
if (nla[NFTA_CHAIN_FLAGS])
flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS]));
+ else if (chain)
+ flags = chain->flags;
nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
break;
case NFT_MSG_NEWSET:
trans->ctx.table->use--;
- if (nft_trans_set(trans)->bound) {
+ if (nft_trans_set_bound(trans)) {
nft_trans_destroy(trans);
break;
}
nft_trans_destroy(trans);
break;
case NFT_MSG_NEWSETELEM:
- if (nft_trans_elem_set(trans)->bound) {
+ if (nft_trans_elem_set_bound(trans)) {
nft_trans_destroy(trans);
break;
}
}
static void nft_flow_offload_common_init(struct flow_cls_common_offload *common,
- __be16 proto,
- struct netlink_ext_ack *extack)
+ __be16 proto, int priority,
+ struct netlink_ext_ack *extack)
{
common->protocol = proto;
+ common->prio = priority;
common->extack = extack;
}
struct flow_block_cb *block_cb;
int err;
- list_for_each_entry(block_cb, &basechain->cb_list, list) {
+ list_for_each_entry(block_cb, &basechain->flow_block.cb_list, list) {
err = block_cb->cb(type, type_data, block_cb->cb_priv);
if (err < 0)
return err;
return 0;
}
+int nft_chain_offload_priority(struct nft_base_chain *basechain)
+{
+ if (basechain->ops.priority <= 0 ||
+ basechain->ops.priority > USHRT_MAX)
+ return -1;
+
+ return 0;
+}
+
static int nft_flow_offload_rule(struct nft_trans *trans,
enum flow_cls_command command)
{
if (flow)
proto = flow->proto;
- nft_flow_offload_common_init(&cls_flow.common, proto, &extack);
+ nft_flow_offload_common_init(&cls_flow.common, proto,
+ basechain->ops.priority, &extack);
cls_flow.command = command;
cls_flow.cookie = (unsigned long) rule;
if (flow)
static int nft_flow_offload_bind(struct flow_block_offload *bo,
struct nft_base_chain *basechain)
{
- list_splice(&bo->cb_list, &basechain->cb_list);
+ list_splice(&bo->cb_list, &basechain->flow_block.cb_list);
return 0;
}
return -EOPNOTSUPP;
bo.command = cmd;
+ bo.block = &basechain->flow_block;
bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
bo.extack = &extack;
INIT_LIST_HEAD(&bo.cb_list);
ss = nfnetlink_get_subsys(type << 8);
rcu_read_unlock();
if (!ss)
- request_module("nfnetlink-subsys-%d", type);
+ request_module_nowait("nfnetlink-subsys-%d", type);
return 0;
}
#endif
static inline void nft_chain_filter_inet_fini(void) {}
#endif /* CONFIG_NF_TABLES_IPV6 */
-#ifdef CONFIG_NF_TABLES_BRIDGE
+#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE)
static unsigned int
nft_do_chain_bridge(void *priv,
struct sk_buff *skb,
#ifdef CONFIG_NF_TABLES_IPV6
MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat");
#endif
+#ifdef CONFIG_NF_TABLES_INET
+MODULE_ALIAS_NFT_CHAIN(1, "nat"); /* NFPROTO_INET */
+#endif
priv->l4proto, NULL, &priv->dport);
exp->timeout.expires = jiffies + priv->timeout * HZ;
- if (nf_ct_expect_related(exp) != 0)
+ if (nf_ct_expect_related(exp, 0) != 0)
regs->verdict.code = NF_DROP;
}
{
struct nft_flow_offload *priv = nft_expr_priv(expr);
struct nf_flowtable *flowtable = &priv->flowtable->data;
+ struct tcphdr _tcph, *tcph = NULL;
enum ip_conntrack_info ctinfo;
struct nf_flow_route route;
struct flow_offload *flow;
enum ip_conntrack_dir dir;
- bool is_tcp = false;
struct nf_conn *ct;
int ret;
switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
case IPPROTO_TCP:
- is_tcp = true;
+ tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff,
+ sizeof(_tcph), &_tcph);
+ if (unlikely(!tcph || tcph->fin || tcph->rst))
+ goto out;
break;
case IPPROTO_UDP:
break;
if (!flow)
goto err_flow_alloc;
- if (is_tcp) {
+ if (tcph) {
ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
}
return nft_chain_validate_hooks(ctx->chain, hook_mask);
}
+static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = {
+ [NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING,
+ .len = NFT_NAME_MAXLEN - 1 },
+};
+
static int nft_flow_offload_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
static struct nft_expr_type nft_flow_offload_type __read_mostly = {
.name = "flow_offload",
.ops = &nft_flow_offload_ops,
+ .policy = nft_flow_offload_policy,
.maxattr = NFTA_FLOW_MAX,
.owner = THIS_MODULE,
};
priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]);
priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS]));
- if (priv->modulus <= 1)
+ if (priv->modulus < 1)
return -ERANGE;
if (priv->offset + priv->modulus - 1 < priv->offset)
*dest = skb->mark;
break;
case NFT_META_IIF:
- if (in == NULL)
- goto err;
- *dest = in->ifindex;
+ *dest = in ? in->ifindex : 0;
break;
case NFT_META_OIF:
- if (out == NULL)
- goto err;
- *dest = out->ifindex;
+ *dest = out ? out->ifindex : 0;
break;
case NFT_META_IIFNAME:
- if (in == NULL)
- goto err;
- strncpy((char *)dest, in->name, IFNAMSIZ);
+ strncpy((char *)dest, in ? in->name : "", IFNAMSIZ);
break;
case NFT_META_OIFNAME:
- if (out == NULL)
- goto err;
- strncpy((char *)dest, out->name, IFNAMSIZ);
+ strncpy((char *)dest, out ? out->name : "", IFNAMSIZ);
break;
case NFT_META_IIFTYPE:
if (in == NULL)
if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG])
return ERR_PTR(-EINVAL);
-#ifdef CONFIG_NF_TABLES_BRIDGE
+#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META)
if (ctx->family == NFPROTO_BRIDGE)
return ERR_PTR(-EAGAIN);
#endif
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
-MODULE_ALIAS_NFT_EXPR("nat");
+MODULE_ALIAS_NFT_EXPR("redir");
opts->options |= NF_SYNPROXY_OPT_ECN;
opts->options &= priv->info.options;
+ opts->mss_encode = opts->mss;
+ opts->mss = info->mss;
if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP)
synproxy_init_timestamp_cookie(info, opts);
else
nfnl_acct_put(info->nfacct);
}
-static struct xt_match nfacct_mt_reg __read_mostly = {
- .name = "nfacct",
- .family = NFPROTO_UNSPEC,
- .checkentry = nfacct_mt_checkentry,
- .match = nfacct_mt,
- .destroy = nfacct_mt_destroy,
- .matchsize = sizeof(struct xt_nfacct_match_info),
- .usersize = offsetof(struct xt_nfacct_match_info, nfacct),
- .me = THIS_MODULE,
+static struct xt_match nfacct_mt_reg[] __read_mostly = {
+ {
+ .name = "nfacct",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .checkentry = nfacct_mt_checkentry,
+ .match = nfacct_mt,
+ .destroy = nfacct_mt_destroy,
+ .matchsize = sizeof(struct xt_nfacct_match_info),
+ .usersize = offsetof(struct xt_nfacct_match_info, nfacct),
+ .me = THIS_MODULE,
+ },
+ {
+ .name = "nfacct",
+ .revision = 1,
+ .family = NFPROTO_UNSPEC,
+ .checkentry = nfacct_mt_checkentry,
+ .match = nfacct_mt,
+ .destroy = nfacct_mt_destroy,
+ .matchsize = sizeof(struct xt_nfacct_match_info_v1),
+ .usersize = offsetof(struct xt_nfacct_match_info_v1, nfacct),
+ .me = THIS_MODULE,
+ },
};
static int __init nfacct_mt_init(void)
{
- return xt_register_match(&nfacct_mt_reg);
+ return xt_register_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg));
}
static void __exit nfacct_mt_exit(void)
{
- xt_unregister_match(&nfacct_mt_reg);
+ xt_unregister_matches(nfacct_mt_reg, ARRAY_SIZE(nfacct_mt_reg));
}
module_init(nfacct_mt_init);
if (info->bitmask & (XT_PHYSDEV_OP_OUT | XT_PHYSDEV_OP_ISOUT) &&
(!(info->bitmask & XT_PHYSDEV_OP_BRIDGED) ||
info->invert & XT_PHYSDEV_OP_BRIDGED) &&
- par->hook_mask & ((1 << NF_INET_LOCAL_OUT) |
- (1 << NF_INET_FORWARD) | (1 << NF_INET_POST_ROUTING))) {
+ par->hook_mask & (1 << NF_INET_LOCAL_OUT)) {
pr_info_ratelimited("--physdev-out and --physdev-is-out only supported in the FORWARD and POSTROUTING chains with bridged traffic\n");
- if (par->hook_mask & (1 << NF_INET_LOCAL_OUT))
- return -EINVAL;
+ return -EINVAL;
}
if (!brnf_probed) {
window = skb->data[20];
+ sock_hold(make);
skb->sk = make;
skb->destructor = sock_efree;
make->sk_state = TCP_ESTABLISHED;
struct md_mark mark;
struct md_labels labels;
char timeout[CTNL_TIMEOUT_NAME_MAX];
+ struct nf_ct_timeout *nf_ct_timeout;
#if IS_ENABLED(CONFIG_NF_NAT)
struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */
#endif
return -EPFNOSUPPORT;
}
+ /* The key extracted from the fragment that completed this datagram
+ * likely didn't have an L4 header, so regenerate it.
+ */
+ ovs_flow_key_update_l3l4(skb, key);
+
key->ip.frag = OVS_FRAG_TYPE_NONE;
skb_clear_hash(skb);
skb->ignore_df = 1;
if (help && rcu_access_pointer(help->helper) != info->helper)
return false;
}
+ if (info->nf_ct_timeout) {
+ struct nf_conn_timeout *timeout_ext;
+
+ timeout_ext = nf_ct_timeout_find(ct);
+ if (!timeout_ext || info->nf_ct_timeout !=
+ rcu_dereference(timeout_ext->timeout))
+ return false;
+ }
/* Force conntrack entry direction to the current packet? */
if (info->force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
/* Delete the conntrack entry if confirmed, else just release
case OVS_CT_ATTR_TIMEOUT:
memcpy(info->timeout, nla_data(a), nla_len(a));
if (!memchr(info->timeout, '\0', nla_len(a))) {
- OVS_NLERR(log, "Invalid conntrack helper");
+ OVS_NLERR(log, "Invalid conntrack timeout");
return -EINVAL;
}
break;
ct_info.timeout))
pr_info_ratelimited("Failed to associated timeout "
"policy `%s'\n", ct_info.timeout);
+ else
+ ct_info.nf_ct_timeout = rcu_dereference(
+ nf_ct_timeout_find(ct_info.ct)->timeout);
+
}
if (helper) {
}
/* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
-static struct sw_flow_actions *get_flow_actions(struct net *net,
+static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net,
const struct nlattr *a,
const struct sw_flow_key *key,
const struct sw_flow_mask *mask,
* we should not to return match object with dangling reference
* to mask.
* */
-static int ovs_nla_init_match_and_action(struct net *net,
- struct sw_flow_match *match,
- struct sw_flow_key *key,
- struct nlattr **a,
- struct sw_flow_actions **acts,
- bool log)
+static noinline_for_stack int
+ovs_nla_init_match_and_action(struct net *net,
+ struct sw_flow_match *match,
+ struct sw_flow_key *key,
+ struct nlattr **a,
+ struct sw_flow_actions **acts,
+ bool log)
{
struct sw_flow_mask mask;
int error = 0;
void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
const struct sk_buff *skb)
{
- struct flow_stats *stats;
+ struct sw_flow_stats *stats;
unsigned int cpu = smp_processor_id();
int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
if (likely(flow->stats_last_writer != -1) &&
likely(!rcu_access_pointer(flow->stats[cpu]))) {
/* Try to allocate CPU-specific stats. */
- struct flow_stats *new_stats;
+ struct sw_flow_stats *new_stats;
new_stats =
kmem_cache_alloc_node(flow_stats_cache,
/* We open code this to make sure cpu 0 is always considered */
for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
- struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
+ struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
if (stats) {
/* Local CPU may write on non-local stats, so we must
/* We open code this to make sure cpu 0 is always considered */
for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
- struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
+ struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
if (stats) {
spin_lock_bh(&stats->lock);
}
/**
- * key_extract - extracts a flow key from an Ethernet frame.
+ * key_extract_l3l4 - extracts L3/L4 header information.
* @skb: sk_buff that contains the frame, with skb->data pointing to the
- * Ethernet header
+ * L3 header
* @key: output flow key
*
- * The caller must ensure that skb->len >= ETH_HLEN.
- *
- * Returns 0 if successful, otherwise a negative errno value.
- *
- * Initializes @skb header fields as follows:
- *
- * - skb->mac_header: the L2 header.
- *
- * - skb->network_header: just past the L2 header, or just past the
- * VLAN header, to the first byte of the L2 payload.
- *
- * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
- * on output, then just past the IP header, if one is present and
- * of a correct length, otherwise the same as skb->network_header.
- * For other key->eth.type values it is left untouched.
- *
- * - skb->protocol: the type of the data starting at skb->network_header.
- * Equals to key->eth.type.
*/
-static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+static int key_extract_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
{
int error;
- struct ethhdr *eth;
-
- /* Flags are always used as part of stats */
- key->tp.flags = 0;
-
- skb_reset_mac_header(skb);
-
- /* Link layer. */
- clear_vlan(key);
- if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
- if (unlikely(eth_type_vlan(skb->protocol)))
- return -EINVAL;
-
- skb_reset_network_header(skb);
- key->eth.type = skb->protocol;
- } else {
- eth = eth_hdr(skb);
- ether_addr_copy(key->eth.src, eth->h_source);
- ether_addr_copy(key->eth.dst, eth->h_dest);
-
- __skb_pull(skb, 2 * ETH_ALEN);
- /* We are going to push all headers that we pull, so no need to
- * update skb->csum here.
- */
-
- if (unlikely(parse_vlan(skb, key)))
- return -ENOMEM;
-
- key->eth.type = parse_ethertype(skb);
- if (unlikely(key->eth.type == htons(0)))
- return -ENOMEM;
-
- /* Multiple tagged packets need to retain TPID to satisfy
- * skb_vlan_pop(), which will later shift the ethertype into
- * skb->protocol.
- */
- if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
- skb->protocol = key->eth.cvlan.tpid;
- else
- skb->protocol = key->eth.type;
-
- skb_reset_network_header(skb);
- __skb_push(skb, skb->data - skb_mac_header(skb));
- }
- skb_reset_mac_len(skb);
/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
offset = nh->frag_off & htons(IP_OFFSET);
if (offset) {
key->ip.frag = OVS_FRAG_TYPE_LATER;
+ memset(&key->tp, 0, sizeof(key->tp));
return 0;
}
if (nh->frag_off & htons(IP_MF) ||
return error;
}
- if (key->ip.frag == OVS_FRAG_TYPE_LATER)
+ if (key->ip.frag == OVS_FRAG_TYPE_LATER) {
+ memset(&key->tp, 0, sizeof(key->tp));
return 0;
+ }
if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
return 0;
}
+/**
+ * key_extract - extracts a flow key from an Ethernet frame.
+ * @skb: sk_buff that contains the frame, with skb->data pointing to the
+ * Ethernet header
+ * @key: output flow key
+ *
+ * The caller must ensure that skb->len >= ETH_HLEN.
+ *
+ * Returns 0 if successful, otherwise a negative errno value.
+ *
+ * Initializes @skb header fields as follows:
+ *
+ * - skb->mac_header: the L2 header.
+ *
+ * - skb->network_header: just past the L2 header, or just past the
+ * VLAN header, to the first byte of the L2 payload.
+ *
+ * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6
+ * on output, then just past the IP header, if one is present and
+ * of a correct length, otherwise the same as skb->network_header.
+ * For other key->eth.type values it is left untouched.
+ *
+ * - skb->protocol: the type of the data starting at skb->network_header.
+ * Equals to key->eth.type.
+ */
+static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ struct ethhdr *eth;
+
+ /* Flags are always used as part of stats */
+ key->tp.flags = 0;
+
+ skb_reset_mac_header(skb);
+
+ /* Link layer. */
+ clear_vlan(key);
+ if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
+ if (unlikely(eth_type_vlan(skb->protocol)))
+ return -EINVAL;
+
+ skb_reset_network_header(skb);
+ key->eth.type = skb->protocol;
+ } else {
+ eth = eth_hdr(skb);
+ ether_addr_copy(key->eth.src, eth->h_source);
+ ether_addr_copy(key->eth.dst, eth->h_dest);
+
+ __skb_pull(skb, 2 * ETH_ALEN);
+ /* We are going to push all headers that we pull, so no need to
+ * update skb->csum here.
+ */
+
+ if (unlikely(parse_vlan(skb, key)))
+ return -ENOMEM;
+
+ key->eth.type = parse_ethertype(skb);
+ if (unlikely(key->eth.type == htons(0)))
+ return -ENOMEM;
+
+ /* Multiple tagged packets need to retain TPID to satisfy
+ * skb_vlan_pop(), which will later shift the ethertype into
+ * skb->protocol.
+ */
+ if (key->eth.cvlan.tci & htons(VLAN_CFI_MASK))
+ skb->protocol = key->eth.cvlan.tpid;
+ else
+ skb->protocol = key->eth.type;
+
+ skb_reset_network_header(skb);
+ __skb_push(skb, skb->data - skb_mac_header(skb));
+ }
+
+ skb_reset_mac_len(skb);
+
+ /* Fill out L3/L4 key info, if any */
+ return key_extract_l3l4(skb, key);
+}
+
+/* In the case of conntrack fragment handling it expects L3 headers,
+ * add a helper.
+ */
+int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key)
+{
+ return key_extract_l3l4(skb, key);
+}
+
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
{
int res;
struct nlattr actions[];
};
-struct flow_stats {
+struct sw_flow_stats {
u64 packet_count; /* Number of packets matched. */
u64 byte_count; /* Number of bytes matched. */
unsigned long used; /* Last used time (in jiffies). */
struct cpumask cpu_used_mask;
struct sw_flow_mask *mask;
struct sw_flow_actions __rcu *sf_acts;
- struct flow_stats __rcu *stats[]; /* One for each CPU. First one
+ struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one
* is allocated at flow creation time,
* the rest are allocated on demand
* while holding the 'stats[0].lock'.
u64 ovs_flow_used_time(unsigned long flow_jiffies);
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_update_l3l4(struct sk_buff *skb, struct sw_flow_key *key);
int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
struct sk_buff *skb,
struct sw_flow_key *key);
struct sw_flow *ovs_flow_alloc(void)
{
struct sw_flow *flow;
- struct flow_stats *stats;
+ struct sw_flow_stats *stats;
flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);
if (!flow)
for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
if (flow->stats[cpu])
kmem_cache_free(flow_stats_cache,
- (struct flow_stats __force *)flow->stats[cpu]);
+ (struct sw_flow_stats __force *)flow->stats[cpu]);
kmem_cache_free(flow_cache, flow);
}
flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
+ (nr_cpu_ids
- * sizeof(struct flow_stats *)),
+ * sizeof(struct sw_flow_stats *)),
0, 0, NULL);
if (flow_cache == NULL)
return -ENOMEM;
flow_stats_cache
- = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+ = kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats),
0, SLAB_HWCACHE_ALIGN, NULL);
if (flow_stats_cache == NULL) {
kmem_cache_destroy(flow_cache);
mutex_lock(&po->pg_vec_lock);
+ /* packet_sendmsg() check on tx_ring.pg_vec was lockless,
+ * we need to confirm it under protection of pg_vec_lock.
+ */
+ if (unlikely(!po->tx_ring.pg_vec)) {
+ err = -EBUSY;
+ goto out;
+ }
if (likely(saddr == NULL)) {
dev = packet_cached_dev_get(po);
proto = po->num;
{
psample_group_notify(group, PSAMPLE_CMD_DEL_GROUP);
list_del(&group->list);
- kfree(group);
+ kfree_rcu(group, rcu);
}
static struct psample_group *
void *buffer)
{
struct rds_info_rdma_connection *iinfo = buffer;
- struct rds_ib_connection *ic;
+ struct rds_ib_connection *ic = conn->c_transport_data;
/* We will only ever look at IB transports */
if (conn->c_trans != &rds_ib_transport)
iinfo->src_addr = conn->c_laddr.s6_addr32[3];
iinfo->dst_addr = conn->c_faddr.s6_addr32[3];
- iinfo->tos = conn->c_tos;
+ if (ic) {
+ iinfo->tos = conn->c_tos;
+ iinfo->sl = ic->i_sl;
+ }
memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid));
memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid));
if (rds_conn_state(conn) == RDS_CONN_UP) {
struct rds_ib_device *rds_ibdev;
- ic = conn->c_transport_data;
-
rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo->src_gid,
(union ib_gid *)&iinfo->dst_gid);
void *buffer)
{
struct rds6_info_rdma_connection *iinfo6 = buffer;
- struct rds_ib_connection *ic;
+ struct rds_ib_connection *ic = conn->c_transport_data;
/* We will only ever look at IB transports */
if (conn->c_trans != &rds_ib_transport)
iinfo6->src_addr = conn->c_laddr;
iinfo6->dst_addr = conn->c_faddr;
+ if (ic) {
+ iinfo6->tos = conn->c_tos;
+ iinfo6->sl = ic->i_sl;
+ }
memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid));
memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid));
if (rds_conn_state(conn) == RDS_CONN_UP) {
struct rds_ib_device *rds_ibdev;
- ic = conn->c_transport_data;
rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid,
(union ib_gid *)&iinfo6->dst_gid);
rds_ibdev = ic->rds_ibdev;
/* Send/Recv vectors */
int i_scq_vector;
int i_rcq_vector;
+ u8 i_sl;
};
/* This assumes that atomic_t is at least 32 bits */
RDS_PROTOCOL_MINOR(conn->c_version),
ic->i_flowctl ? ", flow control" : "");
+ /* receive sl from the peer */
+ ic->i_sl = ic->i_cm_id->route.path_rec->sl;
+
atomic_set(&ic->i_cq_quiesce, 0);
/* Init rings and fill recv. this needs to wait until protocol
static struct rdma_cm_id *rds6_rdma_listen_id;
#endif
+/* Per IB specification 7.7.3, service level is a 4-bit field. */
+#define TOS_TO_SL(tos) ((tos) & 0xF)
+
static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event,
bool isv6)
struct rds_ib_connection *ibic;
ibic = conn->c_transport_data;
- if (ibic && ibic->i_cm_id == cm_id)
+ if (ibic && ibic->i_cm_id == cm_id) {
+ cm_id->route.path_rec[0].sl =
+ TOS_TO_SL(conn->c_tos);
ret = trans->cm_initiate_connect(cm_id, isv6);
- else
+ } else {
rds_conn_drop(conn);
+ }
}
break;
case RDMA_CM_EVENT_ESTABLISHED:
- trans->cm_connect_complete(conn, event);
+ if (conn)
+ trans->cm_connect_complete(conn, event);
break;
case RDMA_CM_EVENT_REJECTED:
break;
case RDMA_CM_EVENT_DISCONNECTED:
+ if (!conn)
+ break;
rdsdebug("DISCONNECT event - dropping connection "
"%pI6c->%pI6c\n", &conn->c_laddr,
&conn->c_faddr);
/*
- * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2019 Oracle and/or its affiliates. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence);
minfo6.len = be32_to_cpu(inc->i_hdr.h_len);
+ minfo6.tos = inc->i_conn->c_tos;
if (flip) {
minfo6.laddr = *daddr;
minfo6.fport = inc->i_hdr.h_dport;
}
+ minfo6.flags = 0;
+
rds_info_copy(iter, &minfo6, sizeof(minfo6));
}
#endif
service_in_use:
write_unlock(&local->services_lock);
- rxrpc_put_local(local);
+ rxrpc_unuse_local(local);
ret = -EADDRINUSE;
error_unlock:
release_sock(&rx->sk);
*/
void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call)
{
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
rxrpc_propose_ack_ping_for_check_life);
rxrpc_send_ack_packet(call, true, NULL);
}
static int rxrpc_release_sock(struct sock *sk)
{
struct rxrpc_sock *rx = rxrpc_sk(sk);
- struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
_enter("%p{%d,%d}", sk, sk->sk_state, refcount_read(&sk->sk_refcnt));
rxrpc_release_calls_on_socket(rx);
flush_workqueue(rxrpc_workqueue);
rxrpc_purge_queue(&sk->sk_receive_queue);
- rxrpc_queue_work(&rxnet->service_conn_reaper);
- rxrpc_queue_work(&rxnet->client_conn_reaper);
- rxrpc_put_local(rx->local);
+ rxrpc_unuse_local(rx->local);
rx->local = NULL;
key_put(rx->key);
rx->key = NULL;
* - max 48 bytes (struct sk_buff::cb)
*/
struct rxrpc_skb_priv {
- union {
- u8 nr_jumbo; /* Number of jumbo subpackets */
- };
+ atomic_t nr_ring_pins; /* Number of rxtx ring pins */
+ u8 nr_subpackets; /* Number of subpackets */
+ u8 rx_flags; /* Received packet flags */
+#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */
+#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */
union {
int remain; /* amount of space remaining for next write */
+
+ /* List of requested ACKs on subpackets */
+ unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) /
+ BITS_PER_LONG];
};
struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */
*/
struct rxrpc_local {
struct rcu_head rcu;
- atomic_t usage;
+ atomic_t active_users; /* Number of users of the local endpoint */
+ atomic_t usage; /* Number of references to the structure */
struct rxrpc_net *rxnet; /* The network ns in which this resides */
struct list_head link;
struct socket *socket; /* my UDP socket */
#define RXRPC_TX_ANNO_LAST 0x04
#define RXRPC_TX_ANNO_RESENT 0x08
-#define RXRPC_RX_ANNO_JUMBO 0x3f /* Jumbo subpacket number + 1 if not zero */
-#define RXRPC_RX_ANNO_JLAST 0x40 /* Set if last element of a jumbo packet */
+#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */
#define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */
rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but
* not hard-ACK'd packet follows this.
/* receive-phase ACK management */
u8 ackr_reason; /* reason to ACK */
- u16 ackr_skew; /* skew on packet being ACK'd */
rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */
rxrpc_serial_t ackr_first_seq; /* first sequence number received */
rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */
/*
* call_event.c
*/
-void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool,
+void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool,
enum rxrpc_propose_ack_trace);
void rxrpc_process_call(struct work_struct *);
void rxrpc_put_client_conn(struct rxrpc_connection *);
void rxrpc_discard_expired_client_conns(struct work_struct *);
void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
+void rxrpc_clean_up_local_conns(struct rxrpc_local *);
/*
* conn_event.c
struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *);
struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *);
void rxrpc_put_local(struct rxrpc_local *);
+struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *);
+void rxrpc_unuse_local(struct rxrpc_local *);
void rxrpc_queue_local(struct rxrpc_local *);
void rxrpc_destroy_all_locals(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
void rxrpc_put_peer(struct rxrpc_peer *);
+void rxrpc_put_peer_locked(struct rxrpc_peer *);
/*
* proc.c
void rxrpc_packet_destructor(struct sk_buff *);
void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace);
+void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_get_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace);
void rxrpc_purge_queue(struct sk_buff_head *);
* propose an ACK be sent
*/
static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
- u16 skew, u32 serial, bool immediate,
- bool background,
+ u32 serial, bool immediate, bool background,
enum rxrpc_propose_ack_trace why)
{
enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) {
outcome = rxrpc_propose_ack_update;
call->ackr_serial = serial;
- call->ackr_skew = skew;
}
if (!immediate)
goto trace;
} else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
call->ackr_reason = ack_reason;
call->ackr_serial = serial;
- call->ackr_skew = skew;
} else {
outcome = rxrpc_propose_ack_subsume;
}
* propose an ACK be sent, locking the call structure
*/
void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
- u16 skew, u32 serial, bool immediate, bool background,
+ u32 serial, bool immediate, bool background,
enum rxrpc_propose_ack_trace why)
{
spin_lock_bh(&call->lock);
- __rxrpc_propose_ACK(call, ack_reason, skew, serial,
+ __rxrpc_propose_ACK(call, ack_reason, serial,
immediate, background, why);
spin_unlock_bh(&call->lock);
}
continue;
skb = call->rxtx_buffer[ix];
- rxrpc_see_skb(skb, rxrpc_skb_tx_seen);
+ rxrpc_see_skb(skb, rxrpc_skb_seen);
if (anno_type == RXRPC_TX_ANNO_UNACK) {
if (ktime_after(skb->tstamp, max_age)) {
ack_ts = ktime_sub(now, call->acks_latest_ts);
if (ktime_to_ns(ack_ts) < call->peer->rtt)
goto out;
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
rxrpc_send_ack_packet(call, true, NULL);
goto out;
continue;
skb = call->rxtx_buffer[ix];
- rxrpc_get_skb(skb, rxrpc_skb_tx_got);
+ rxrpc_get_skb(skb, rxrpc_skb_got);
spin_unlock_bh(&call->lock);
if (rxrpc_send_data_packet(call, skb, true) < 0) {
- rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
return;
}
if (rxrpc_is_client_call(call))
rxrpc_expose_client_call(call);
- rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
spin_lock_bh(&call->lock);
/* We need to clear the retransmit state, but there are two
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true,
rxrpc_propose_ack_ping_for_keepalive);
set_bit(RXRPC_CALL_EV_PING, &call->events);
}
send_ack = NULL;
if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) {
call->acks_lost_top = call->tx_top;
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
send_ack = &call->acks_lost_ping;
}
trace_rxrpc_call(call, op, n, here, NULL);
}
+/*
+ * Clean up the RxTx skb ring.
+ */
+static void rxrpc_cleanup_ring(struct rxrpc_call *call)
+{
+ int i;
+
+ for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) {
+ rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned);
+ call->rxtx_buffer[i] = NULL;
+ }
+}
+
/*
* Detach a call from its owning socket.
*/
const void *here = __builtin_return_address(0);
struct rxrpc_connection *conn = call->conn;
bool put = false;
- int i;
_enter("{%d,%d}", call->debug_id, atomic_read(&call->usage));
if (conn)
rxrpc_disconnect_call(call);
- for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) {
- rxrpc_free_skb(call->rxtx_buffer[i],
- (call->tx_phase ? rxrpc_skb_tx_cleaned :
- rxrpc_skb_rx_cleaned));
- call->rxtx_buffer[i] = NULL;
- }
-
+ rxrpc_cleanup_ring(call);
_leave("");
}
*/
void rxrpc_cleanup_call(struct rxrpc_call *call)
{
- int i;
-
_net("DESTROY CALL %d", call->debug_id);
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
ASSERTCMP(call->conn, ==, NULL);
- /* Clean up the Rx/Tx buffer */
- for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++)
- rxrpc_free_skb(call->rxtx_buffer[i],
- (call->tx_phase ? rxrpc_skb_tx_cleaned :
- rxrpc_skb_rx_cleaned));
-
- rxrpc_free_skb(call->tx_pending, rxrpc_skb_tx_cleaned);
+ rxrpc_cleanup_ring(call);
+ rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned);
call_rcu(&call->rcu, rxrpc_rcu_destroy_call);
}
_leave("");
}
+
+/*
+ * Clean up the client connections on a local endpoint.
+ */
+void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
+{
+ struct rxrpc_connection *conn, *tmp;
+ struct rxrpc_net *rxnet = local->rxnet;
+ unsigned int nr_active;
+ LIST_HEAD(graveyard);
+
+ _enter("");
+
+ spin_lock(&rxnet->client_conn_cache_lock);
+ nr_active = rxnet->nr_active_client_conns;
+
+ list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
+ cache_link) {
+ if (conn->params.local == local) {
+ ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE);
+
+ trace_rxrpc_client(conn, -1, rxrpc_client_discard);
+ if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags))
+ BUG();
+ conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
+ list_move(&conn->cache_link, &graveyard);
+ nr_active--;
+ }
+ }
+
+ rxnet->nr_active_client_conns = nr_active;
+ spin_unlock(&rxnet->client_conn_cache_lock);
+ ASSERTCMP(nr_active, >=, 0);
+
+ while (!list_empty(&graveyard)) {
+ conn = list_entry(graveyard.next,
+ struct rxrpc_connection, cache_link);
+ list_del_init(&conn->cache_link);
+
+ rxrpc_put_connection(conn);
+ }
+
+ _leave(" [culled]");
+}
/* go through the conn-level event packets, releasing the ref on this
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
- rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
+ rxrpc_see_skb(skb, rxrpc_skb_seen);
ret = rxrpc_process_event(conn, skb, &abort_code);
switch (ret) {
case -EPROTO:
goto requeue_and_leave;
case -ECONNABORTED:
default:
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
break;
}
}
protocol_error:
if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
goto requeue_and_leave;
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
goto out;
}
if (conn->state == RXRPC_CONN_SERVICE_PREALLOC)
continue;
- if (rxnet->live) {
+ if (rxnet->live && !conn->params.local->dead) {
idle_timestamp = READ_ONCE(conn->idle_timestamp);
expire_at = idle_timestamp + rxrpc_connection_expiry * HZ;
if (conn->params.local->service_closed)
* Ping the other end to fill our RTT cache and to retrieve the rwind
* and MTU parameters.
*/
-static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb,
- int skew)
+static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
ktime_t now = skb->tstamp;
if (call->peer->rtt_usage < 3 ||
ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
true, true,
rxrpc_propose_ack_ping_for_params);
}
ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK;
skb = call->rxtx_buffer[ix];
annotation = call->rxtx_annotations[ix];
- rxrpc_see_skb(skb, rxrpc_skb_tx_rotated);
+ rxrpc_see_skb(skb, rxrpc_skb_rotated);
call->rxtx_buffer[ix] = NULL;
call->rxtx_annotations[ix] = 0;
skb->next = list;
skb = list;
list = skb->next;
skb_mark_not_on_list(skb);
- rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
}
return rot_last;
}
/*
- * Scan a jumbo packet to validate its structure and to work out how many
+ * Scan a data packet to validate its structure and to work out how many
* subpackets it contains.
*
* A jumbo packet is a collection of consecutive packets glued together with
* the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any
* size.
*/
-static bool rxrpc_validate_jumbo(struct sk_buff *skb)
+static bool rxrpc_validate_data(struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned int offset = sizeof(struct rxrpc_wire_header);
unsigned int len = skb->len;
- int nr_jumbo = 1;
u8 flags = sp->hdr.flags;
- do {
- nr_jumbo++;
+ for (;;) {
+ if (flags & RXRPC_REQUEST_ACK)
+ __set_bit(sp->nr_subpackets, sp->rx_req_ack);
+ sp->nr_subpackets++;
+
+ if (!(flags & RXRPC_JUMBO_PACKET))
+ break;
+
if (len - offset < RXRPC_JUMBO_SUBPKTLEN)
goto protocol_error;
if (flags & RXRPC_LAST_PACKET)
if (skb_copy_bits(skb, offset, &flags, 1) < 0)
goto protocol_error;
offset += sizeof(struct rxrpc_jumbo_header);
- } while (flags & RXRPC_JUMBO_PACKET);
+ }
- sp->nr_jumbo = nr_jumbo;
+ if (flags & RXRPC_LAST_PACKET)
+ sp->rx_flags |= RXRPC_SKB_INCL_LAST;
return true;
protocol_error:
* (that information is encoded in the ACK packet).
*/
static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq,
- u8 annotation, bool *_jumbo_bad)
+ bool is_jumbo, bool *_jumbo_bad)
{
/* Discard normal packets that are duplicates. */
- if (annotation == 0)
+ if (is_jumbo)
return;
/* Skip jumbo subpackets that are duplicates. When we've had three or
}
/*
- * Process a DATA packet, adding the packet to the Rx ring.
+ * Process a DATA packet, adding the packet to the Rx ring. The caller's
+ * packet ref must be passed on or discarded.
*/
-static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb,
- u16 skew)
+static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
enum rxrpc_call_state state;
- unsigned int offset = sizeof(struct rxrpc_wire_header);
- unsigned int ix;
+ unsigned int j;
rxrpc_serial_t serial = sp->hdr.serial, ack_serial = 0;
- rxrpc_seq_t seq = sp->hdr.seq, hard_ack;
- bool immediate_ack = false, jumbo_bad = false, queued;
- u16 len;
- u8 ack = 0, flags, annotation = 0;
+ rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack;
+ bool immediate_ack = false, jumbo_bad = false;
+ u8 ack = 0;
_enter("{%u,%u},{%u,%u}",
- call->rx_hard_ack, call->rx_top, skb->len, seq);
+ call->rx_hard_ack, call->rx_top, skb->len, seq0);
- _proto("Rx DATA %%%u { #%u f=%02x }",
- sp->hdr.serial, seq, sp->hdr.flags);
+ _proto("Rx DATA %%%u { #%u f=%02x n=%u }",
+ sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets);
state = READ_ONCE(call->state);
- if (state >= RXRPC_CALL_COMPLETE)
+ if (state >= RXRPC_CALL_COMPLETE) {
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
return;
+ }
if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
unsigned long timo = READ_ONCE(call->next_req_timo);
!rxrpc_receiving_reply(call))
goto unlock;
- call->ackr_prev_seq = seq;
-
+ call->ackr_prev_seq = seq0;
hard_ack = READ_ONCE(call->rx_hard_ack);
- if (after(seq, hard_ack + call->rx_winsize)) {
- ack = RXRPC_ACK_EXCEEDS_WINDOW;
- ack_serial = serial;
- goto ack;
- }
- flags = sp->hdr.flags;
- if (flags & RXRPC_JUMBO_PACKET) {
+ if (sp->nr_subpackets > 1) {
if (call->nr_jumbo_bad > 3) {
ack = RXRPC_ACK_NOSPACE;
ack_serial = serial;
goto ack;
}
- annotation = 1;
}
-next_subpacket:
- queued = false;
- ix = seq & RXRPC_RXTX_BUFF_MASK;
- len = skb->len;
- if (flags & RXRPC_JUMBO_PACKET)
- len = RXRPC_JUMBO_DATALEN;
-
- if (flags & RXRPC_LAST_PACKET) {
- if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- seq != call->rx_top) {
- rxrpc_proto_abort("LSN", call, seq);
- goto unlock;
- }
- } else {
- if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
- after_eq(seq, call->rx_top)) {
- rxrpc_proto_abort("LSA", call, seq);
- goto unlock;
+ for (j = 0; j < sp->nr_subpackets; j++) {
+ rxrpc_serial_t serial = sp->hdr.serial + j;
+ rxrpc_seq_t seq = seq0 + j;
+ unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK;
+ bool terminal = (j == sp->nr_subpackets - 1);
+ bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST);
+ u8 flags, annotation = j;
+
+ _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }",
+ j, serial, seq, terminal, last);
+
+ if (last) {
+ if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
+ seq != call->rx_top) {
+ rxrpc_proto_abort("LSN", call, seq);
+ goto unlock;
+ }
+ } else {
+ if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) &&
+ after_eq(seq, call->rx_top)) {
+ rxrpc_proto_abort("LSA", call, seq);
+ goto unlock;
+ }
}
- }
-
- trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation);
- if (before_eq(seq, hard_ack)) {
- ack = RXRPC_ACK_DUPLICATE;
- ack_serial = serial;
- goto skip;
- }
- if (flags & RXRPC_REQUEST_ACK && !ack) {
- ack = RXRPC_ACK_REQUESTED;
- ack_serial = serial;
- }
+ flags = 0;
+ if (last)
+ flags |= RXRPC_LAST_PACKET;
+ if (!terminal)
+ flags |= RXRPC_JUMBO_PACKET;
+ if (test_bit(j, sp->rx_req_ack))
+ flags |= RXRPC_REQUEST_ACK;
+ trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation);
- if (call->rxtx_buffer[ix]) {
- rxrpc_input_dup_data(call, seq, annotation, &jumbo_bad);
- if (ack != RXRPC_ACK_DUPLICATE) {
+ if (before_eq(seq, hard_ack)) {
ack = RXRPC_ACK_DUPLICATE;
ack_serial = serial;
+ continue;
}
- immediate_ack = true;
- goto skip;
- }
-
- /* Queue the packet. We use a couple of memory barriers here as need
- * to make sure that rx_top is perceived to be set after the buffer
- * pointer and that the buffer pointer is set after the annotation and
- * the skb data.
- *
- * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window()
- * and also rxrpc_fill_out_ack().
- */
- rxrpc_get_skb(skb, rxrpc_skb_rx_got);
- call->rxtx_annotations[ix] = annotation;
- smp_wmb();
- call->rxtx_buffer[ix] = skb;
- if (after(seq, call->rx_top)) {
- smp_store_release(&call->rx_top, seq);
- } else if (before(seq, call->rx_top)) {
- /* Send an immediate ACK if we fill in a hole */
- if (!ack) {
- ack = RXRPC_ACK_DELAY;
- ack_serial = serial;
- }
- immediate_ack = true;
- }
- if (flags & RXRPC_LAST_PACKET) {
- set_bit(RXRPC_CALL_RX_LAST, &call->flags);
- trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq);
- } else {
- trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq);
- }
- queued = true;
- if (after_eq(seq, call->rx_expect_next)) {
- if (after(seq, call->rx_expect_next)) {
- _net("OOS %u > %u", seq, call->rx_expect_next);
- ack = RXRPC_ACK_OUT_OF_SEQUENCE;
- ack_serial = serial;
+ if (call->rxtx_buffer[ix]) {
+ rxrpc_input_dup_data(call, seq, sp->nr_subpackets > 1,
+ &jumbo_bad);
+ if (ack != RXRPC_ACK_DUPLICATE) {
+ ack = RXRPC_ACK_DUPLICATE;
+ ack_serial = serial;
+ }
+ immediate_ack = true;
+ continue;
}
- call->rx_expect_next = seq + 1;
- }
-skip:
- offset += len;
- if (flags & RXRPC_JUMBO_PACKET) {
- if (skb_copy_bits(skb, offset, &flags, 1) < 0) {
- rxrpc_proto_abort("XJF", call, seq);
- goto unlock;
- }
- offset += sizeof(struct rxrpc_jumbo_header);
- seq++;
- serial++;
- annotation++;
- if (flags & RXRPC_JUMBO_PACKET)
- annotation |= RXRPC_RX_ANNO_JLAST;
if (after(seq, hard_ack + call->rx_winsize)) {
ack = RXRPC_ACK_EXCEEDS_WINDOW;
ack_serial = serial;
- if (!jumbo_bad) {
- call->nr_jumbo_bad++;
- jumbo_bad = true;
+ if (flags & RXRPC_JUMBO_PACKET) {
+ if (!jumbo_bad) {
+ call->nr_jumbo_bad++;
+ jumbo_bad = true;
+ }
}
+
goto ack;
}
- _proto("Rx DATA Jumbo %%%u", serial);
- goto next_subpacket;
- }
+ if (flags & RXRPC_REQUEST_ACK && !ack) {
+ ack = RXRPC_ACK_REQUESTED;
+ ack_serial = serial;
+ }
+
+ /* Queue the packet. We use a couple of memory barriers here as need
+ * to make sure that rx_top is perceived to be set after the buffer
+ * pointer and that the buffer pointer is set after the annotation and
+ * the skb data.
+ *
+ * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window()
+ * and also rxrpc_fill_out_ack().
+ */
+ if (!terminal)
+ rxrpc_get_skb(skb, rxrpc_skb_got);
+ call->rxtx_annotations[ix] = annotation;
+ smp_wmb();
+ call->rxtx_buffer[ix] = skb;
+ if (after(seq, call->rx_top)) {
+ smp_store_release(&call->rx_top, seq);
+ } else if (before(seq, call->rx_top)) {
+ /* Send an immediate ACK if we fill in a hole */
+ if (!ack) {
+ ack = RXRPC_ACK_DELAY;
+ ack_serial = serial;
+ }
+ immediate_ack = true;
+ }
- if (queued && flags & RXRPC_LAST_PACKET && !ack) {
- ack = RXRPC_ACK_DELAY;
- ack_serial = serial;
+ if (terminal) {
+ /* From this point on, we're not allowed to touch the
+ * packet any longer as its ref now belongs to the Rx
+ * ring.
+ */
+ skb = NULL;
+ }
+
+ if (last) {
+ set_bit(RXRPC_CALL_RX_LAST, &call->flags);
+ if (!ack) {
+ ack = RXRPC_ACK_DELAY;
+ ack_serial = serial;
+ }
+ trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq);
+ } else {
+ trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq);
+ }
+
+ if (after_eq(seq, call->rx_expect_next)) {
+ if (after(seq, call->rx_expect_next)) {
+ _net("OOS %u > %u", seq, call->rx_expect_next);
+ ack = RXRPC_ACK_OUT_OF_SEQUENCE;
+ ack_serial = serial;
+ }
+ call->rx_expect_next = seq + 1;
+ }
}
ack:
if (ack)
- rxrpc_propose_ACK(call, ack, skew, ack_serial,
+ rxrpc_propose_ACK(call, ack, ack_serial,
immediate_ack, true,
rxrpc_propose_ack_input_data);
else
- rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial,
+ rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
false, true,
rxrpc_propose_ack_input_data);
- if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) {
+ if (seq0 == READ_ONCE(call->rx_hard_ack) + 1) {
trace_rxrpc_notify_socket(call->debug_id, serial);
rxrpc_notify_socket(call);
}
unlock:
spin_unlock(&call->input_lock);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
_leave(" [queued]");
}
* soft-ACK means that the packet may be discarded and retransmission
* requested. A phase is complete when all packets are hard-ACK'd.
*/
-static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
- u16 skew)
+static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb)
{
struct rxrpc_ack_summary summary = { 0 };
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
if (buf.ack.reason == RXRPC_ACK_PING) {
_proto("Rx ACK %%%u PING Request", sp->hdr.serial);
rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE,
- skew, sp->hdr.serial, true, true,
+ sp->hdr.serial, true, true,
rxrpc_propose_ack_respond_to_ping);
} else if (sp->hdr.flags & RXRPC_REQUEST_ACK) {
rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED,
- skew, sp->hdr.serial, true, true,
+ sp->hdr.serial, true, true,
rxrpc_propose_ack_respond_to_ack);
}
RXRPC_TX_ANNO_LAST &&
summary.nr_acks == call->tx_top - hard_ack &&
rxrpc_is_client_call(call))
- rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial,
+ rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
false, true,
rxrpc_propose_ack_ping_for_lost_reply);
* Process an incoming call packet.
*/
static void rxrpc_input_call_packet(struct rxrpc_call *call,
- struct sk_buff *skb, u16 skew)
+ struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned long timo;
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
- rxrpc_input_data(call, skb, skew);
- break;
+ rxrpc_input_data(call, skb);
+ goto no_free;
case RXRPC_PACKET_TYPE_ACK:
- rxrpc_input_ack(call, skb, skew);
+ rxrpc_input_ack(call, skb);
break;
case RXRPC_PACKET_TYPE_BUSY:
break;
}
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
+no_free:
_leave("");
}
{
_enter("%p,%p", local, skb);
- skb_queue_tail(&local->event_queue, skb);
- rxrpc_queue_local(local);
+ if (rxrpc_get_local_maybe(local)) {
+ skb_queue_tail(&local->event_queue, skb);
+ rxrpc_queue_local(local);
+ } else {
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
+ }
}
/*
{
CHECK_SLAB_OKAY(&local->usage);
- skb_queue_tail(&local->reject_queue, skb);
- rxrpc_queue_local(local);
+ if (rxrpc_get_local_maybe(local)) {
+ skb_queue_tail(&local->reject_queue, skb);
+ rxrpc_queue_local(local);
+ } else {
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
+ }
}
/*
struct rxrpc_peer *peer = NULL;
struct rxrpc_sock *rx = NULL;
unsigned int channel;
- int skew = 0;
_enter("%p", udp_sk);
if (skb->tstamp == 0)
skb->tstamp = ktime_get_real();
- rxrpc_new_skb(skb, rxrpc_skb_rx_received);
+ rxrpc_new_skb(skb, rxrpc_skb_received);
skb_pull(skb, sizeof(struct udphdr));
static int lose;
if ((lose++ & 7) == 7) {
trace_rxrpc_rx_lose(sp);
- rxrpc_free_skb(skb, rxrpc_skb_rx_lost);
+ rxrpc_free_skb(skb, rxrpc_skb_lost);
return 0;
}
}
if (sp->hdr.callNumber == 0 ||
sp->hdr.seq == 0)
goto bad_message;
- if (sp->hdr.flags & RXRPC_JUMBO_PACKET &&
- !rxrpc_validate_jumbo(skb))
+ if (!rxrpc_validate_data(skb))
goto bad_message;
+
+ /* Unshare the packet so that it can be modified for in-place
+ * decryption.
+ */
+ if (sp->hdr.securityIndex != 0) {
+ struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC);
+ if (!nskb) {
+ rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem);
+ goto out;
+ }
+
+ if (nskb != skb) {
+ rxrpc_eaten_skb(skb, rxrpc_skb_received);
+ rxrpc_new_skb(skb, rxrpc_skb_unshared);
+ skb = nskb;
+ sp = rxrpc_skb(skb);
+ }
+ }
break;
case RXRPC_PACKET_TYPE_CHALLENGE:
goto out;
}
- /* Note the serial number skew here */
- skew = (int)sp->hdr.serial - (int)conn->hi_serial;
- if (skew >= 0) {
- if (skew > 0)
- conn->hi_serial = sp->hdr.serial;
- } else {
- skew = -skew;
- skew = min(skew, 65535);
- }
+ if ((int)sp->hdr.serial - (int)conn->hi_serial > 0)
+ conn->hi_serial = sp->hdr.serial;
/* Call-bound packets are routed by connection channel. */
channel = sp->hdr.cid & RXRPC_CHANNELMASK;
call = rxrpc_new_incoming_call(local, rx, skb);
if (!call)
goto reject_packet;
- rxrpc_send_ping(call, skb, skew);
+ rxrpc_send_ping(call, skb);
mutex_unlock(&call->user_mutex);
}
- rxrpc_input_call_packet(call, skb, skew);
- goto discard;
+ /* Process a call packet; this either discards or passes on the ref
+ * elsewhere.
+ */
+ rxrpc_input_call_packet(call, skb);
+ goto out;
discard:
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
out:
trace_rxrpc_rx_done(0, 0);
return 0;
if (skb) {
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
+ rxrpc_see_skb(skb, rxrpc_skb_seen);
_debug("{%d},{%u}", local->debug_id, sp->hdr.type);
switch (sp->hdr.type) {
break;
}
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
}
_leave("");
local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
if (local) {
atomic_set(&local->usage, 1);
+ atomic_set(&local->active_users, 1);
local->rxnet = rxnet;
INIT_LIST_HEAD(&local->link);
INIT_WORK(&local->processor, rxrpc_local_processor);
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
memcpy(&local->srx, srx, sizeof(*srx));
local->srx.srx_service = 0;
- trace_rxrpc_local(local, rxrpc_local_new, 1, NULL);
+ trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL);
}
_leave(" = %p", local);
* bind the transport socket may still fail if we're attempting
* to use a local address that the dying object is still using.
*/
- if (!rxrpc_get_local_maybe(local)) {
- cursor = cursor->next;
- list_del_init(&local->link);
+ if (!rxrpc_use_local(local))
break;
- }
age = "old";
goto found;
if (ret < 0)
goto sock_error;
- list_add_tail(&local->link, cursor);
+ if (cursor != &rxnet->local_endpoints)
+ list_replace_init(cursor, &local->link);
+ else
+ list_add_tail(&local->link, cursor);
age = "new";
found:
int n;
n = atomic_inc_return(&local->usage);
- trace_rxrpc_local(local, rxrpc_local_got, n, here);
+ trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here);
return local;
}
if (local) {
int n = atomic_fetch_add_unless(&local->usage, 1, 0);
if (n > 0)
- trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
+ trace_rxrpc_local(local->debug_id, rxrpc_local_got,
+ n + 1, here);
else
local = NULL;
}
}
/*
- * Queue a local endpoint.
+ * Queue a local endpoint and pass the caller's reference to the work item.
*/
void rxrpc_queue_local(struct rxrpc_local *local)
{
const void *here = __builtin_return_address(0);
+ unsigned int debug_id = local->debug_id;
+ int n = atomic_read(&local->usage);
if (rxrpc_queue_work(&local->processor))
- trace_rxrpc_local(local, rxrpc_local_queued,
- atomic_read(&local->usage), here);
-}
-
-/*
- * A local endpoint reached its end of life.
- */
-static void __rxrpc_put_local(struct rxrpc_local *local)
-{
- _enter("%d", local->debug_id);
- rxrpc_queue_work(&local->processor);
+ trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here);
+ else
+ rxrpc_put_local(local);
}
/*
if (local) {
n = atomic_dec_return(&local->usage);
- trace_rxrpc_local(local, rxrpc_local_put, n, here);
+ trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
if (n == 0)
- __rxrpc_put_local(local);
+ call_rcu(&local->rcu, rxrpc_local_rcu);
+ }
+}
+
+/*
+ * Start using a local endpoint.
+ */
+struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
+{
+ unsigned int au;
+
+ local = rxrpc_get_local_maybe(local);
+ if (!local)
+ return NULL;
+
+ au = atomic_fetch_add_unless(&local->active_users, 1, 0);
+ if (au == 0) {
+ rxrpc_put_local(local);
+ return NULL;
+ }
+
+ return local;
+}
+
+/*
+ * Cease using a local endpoint. Once the number of active users reaches 0, we
+ * start the closure of the transport in the work processor.
+ */
+void rxrpc_unuse_local(struct rxrpc_local *local)
+{
+ unsigned int au;
+
+ if (local) {
+ au = atomic_dec_return(&local->active_users);
+ if (au == 0)
+ rxrpc_queue_local(local);
+ else
+ rxrpc_put_local(local);
}
}
_enter("%d", local->debug_id);
- /* We can get a race between an incoming call packet queueing the
- * processor again and the work processor starting the destruction
- * process which will shut down the UDP socket.
- */
- if (local->dead) {
- _leave(" [already dead]");
- return;
- }
local->dead = true;
mutex_lock(&rxnet->local_mutex);
list_del_init(&local->link);
mutex_unlock(&rxnet->local_mutex);
- ASSERT(RB_EMPTY_ROOT(&local->client_conns));
+ rxrpc_clean_up_local_conns(local);
+ rxrpc_service_connection_reaper(&rxnet->service_conn_reaper);
ASSERT(!local->service);
if (socket) {
*/
rxrpc_purge_queue(&local->reject_queue);
rxrpc_purge_queue(&local->event_queue);
-
- _debug("rcu local %d", local->debug_id);
- call_rcu(&local->rcu, rxrpc_local_rcu);
}
/*
- * Process events on an endpoint
+ * Process events on an endpoint. The work item carries a ref which
+ * we must release.
*/
static void rxrpc_local_processor(struct work_struct *work)
{
container_of(work, struct rxrpc_local, processor);
bool again;
- trace_rxrpc_local(local, rxrpc_local_processing,
+ trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
atomic_read(&local->usage), NULL);
do {
again = false;
- if (atomic_read(&local->usage) == 0)
- return rxrpc_local_destroyer(local);
+ if (atomic_read(&local->active_users) == 0) {
+ rxrpc_local_destroyer(local);
+ break;
+ }
if (!skb_queue_empty(&local->reject_queue)) {
rxrpc_reject_packets(local);
again = true;
}
} while (again);
+
+ rxrpc_put_local(local);
}
/*
*_top = top;
pkt->ack.bufferSpace = htons(8);
- pkt->ack.maxSkew = htons(call->ackr_skew);
+ pkt->ack.maxSkew = htons(0);
pkt->ack.firstPacket = htonl(hard_ack + 1);
pkt->ack.previousPacket = htonl(call->ackr_prev_seq);
pkt->ack.serial = htonl(serial);
if (ping)
clear_bit(RXRPC_CALL_PINGING, &call->flags);
rxrpc_propose_ACK(call, pkt->ack.reason,
- ntohs(pkt->ack.maxSkew),
ntohl(pkt->ack.serial),
false, true,
rxrpc_propose_ack_retry_tx);
memset(&whdr, 0, sizeof(whdr));
while ((skb = skb_dequeue(&local->reject_queue))) {
- rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
+ rxrpc_see_skb(skb, rxrpc_skb_seen);
sp = rxrpc_skb(skb);
switch (skb->mark) {
ioc = 2;
break;
default:
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
continue;
}
rxrpc_tx_point_reject);
}
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
}
_leave("");
_leave("UDP socket errqueue empty");
return;
}
- rxrpc_new_skb(skb, rxrpc_skb_rx_received);
+ rxrpc_new_skb(skb, rxrpc_skb_received);
serr = SKB_EXT_ERR(skb);
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
_leave("UDP empty message");
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
return;
}
peer = NULL;
if (!peer) {
rcu_read_unlock();
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
_leave(" [no peer]");
return;
}
serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
rxrpc_adjust_mtu(peer, serr);
rcu_read_unlock();
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
rxrpc_put_peer(peer);
_leave(" [MTU update]");
return;
rxrpc_store_error(peer, serr);
rcu_read_unlock();
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
rxrpc_put_peer(peer);
_leave("");
spin_lock_bh(&rxnet->peer_hash_lock);
list_add_tail(&peer->keepalive_link,
&rxnet->peer_keepalive[slot & mask]);
- rxrpc_put_peer(peer);
+ rxrpc_put_peer_locked(peer);
}
spin_unlock_bh(&rxnet->peer_hash_lock);
}
}
+/*
+ * Drop a ref on a peer record where the caller already holds the
+ * peer_hash_lock.
+ */
+void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
+{
+ const void *here = __builtin_return_address(0);
+ int n;
+
+ n = atomic_dec_return(&peer->usage);
+ trace_rxrpc_peer(peer, rxrpc_peer_put, n, here);
+ if (n == 0) {
+ hash_del_rcu(&peer->hash_link);
+ list_del_init(&peer->keepalive_link);
+ kfree_rcu(peer, rcu);
+ }
+}
+
/*
* Make sure all peer records have been discarded.
*/
#define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */
#define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header))
+/*
+ * The maximum number of subpackets that can possibly fit in a UDP packet is:
+ *
+ * ((max_IP - IP_hdr - UDP_hdr) / RXRPC_JUMBO_SUBPKTLEN) + 1
+ * = ((65535 - 28 - 28) / 1416) + 1
+ * = 46 non-terminal packets and 1 terminal packet.
+ */
+#define RXRPC_MAX_NR_JUMBO 47
+
/*****************************************************************************/
/*
* on-the-wire Rx ACK packet data payload
ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
- rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true,
+ rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true,
rxrpc_propose_ack_terminal_ack);
//rxrpc_send_ack_packet(call, false, NULL);
}
call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
write_unlock_bh(&call->state_lock);
- rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true,
+ rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true,
rxrpc_propose_ack_processing_op);
break;
default:
struct sk_buff *skb;
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
- u8 flags;
+ bool last = false;
+ u8 subpacket;
int ix;
_enter("%d", call->debug_id);
hard_ack++;
ix = hard_ack & RXRPC_RXTX_BUFF_MASK;
skb = call->rxtx_buffer[ix];
- rxrpc_see_skb(skb, rxrpc_skb_rx_rotated);
+ rxrpc_see_skb(skb, rxrpc_skb_rotated);
sp = rxrpc_skb(skb);
- flags = sp->hdr.flags;
- serial = sp->hdr.serial;
- if (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO)
- serial += (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - 1;
+
+ subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET;
+ serial = sp->hdr.serial + subpacket;
+
+ if (subpacket == sp->nr_subpackets - 1 &&
+ sp->rx_flags & RXRPC_SKB_INCL_LAST)
+ last = true;
call->rxtx_buffer[ix] = NULL;
call->rxtx_annotations[ix] = 0;
/* Barrier against rxrpc_input_data(). */
smp_store_release(&call->rx_hard_ack, hard_ack);
- rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
- _debug("%u,%u,%02x", hard_ack, top, flags);
trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack);
- if (flags & RXRPC_LAST_PACKET) {
+ if (last) {
rxrpc_end_rx_phase(call, serial);
} else {
/* Check to see if there's an ACK that needs sending. */
if (after_eq(hard_ack, call->ackr_consumed + 2) ||
after_eq(top, call->ackr_seen + 2) ||
(hard_ack == top && after(hard_ack, call->ackr_consumed)))
- rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial,
+ rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial,
true, true,
rxrpc_propose_ack_rotate_rx);
if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY)
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
rxrpc_seq_t seq = sp->hdr.seq;
u16 cksum = sp->hdr.cksum;
+ u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET;
_enter("");
/* For all but the head jumbo subpacket, the security checksum is in a
* jumbo header immediately prior to the data.
*/
- if ((annotation & RXRPC_RX_ANNO_JUMBO) > 1) {
+ if (subpacket > 0) {
__be16 tmp;
if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0)
BUG();
cksum = ntohs(tmp);
- seq += (annotation & RXRPC_RX_ANNO_JUMBO) - 1;
+ seq += subpacket;
}
return call->conn->security->verify_packet(call, skb, offset, len,
u8 *_annotation,
unsigned int *_offset, unsigned int *_len)
{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
unsigned int offset = sizeof(struct rxrpc_wire_header);
unsigned int len;
int ret;
u8 annotation = *_annotation;
+ u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET;
/* Locate the subpacket */
+ offset += subpacket * RXRPC_JUMBO_SUBPKTLEN;
len = skb->len - offset;
- if ((annotation & RXRPC_RX_ANNO_JUMBO) > 0) {
- offset += (((annotation & RXRPC_RX_ANNO_JUMBO) - 1) *
- RXRPC_JUMBO_SUBPKTLEN);
- len = (annotation & RXRPC_RX_ANNO_JLAST) ?
- skb->len - offset : RXRPC_JUMBO_SUBPKTLEN;
- }
+ if (subpacket < sp->nr_subpackets - 1)
+ len = RXRPC_JUMBO_DATALEN;
if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) {
ret = rxrpc_verify_packet(call, skb, annotation, offset, len);
{
struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
+ rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top, seq;
size_t remain;
bool last;
break;
}
smp_rmb();
- rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
+ rxrpc_see_skb(skb, rxrpc_skb_seen);
sp = rxrpc_skb(skb);
- if (!(flags & MSG_PEEK))
+ if (!(flags & MSG_PEEK)) {
+ serial = sp->hdr.serial;
+ serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET;
trace_rxrpc_receive(call, rxrpc_receive_front,
- sp->hdr.serial, seq);
+ serial, seq);
+ }
if (msg)
sock_recv_timestamp(msg, sock->sk, skb);
struct rxrpc_skb_priv *sp;
struct rxrpc_crypt iv;
struct scatterlist sg[16];
- struct sk_buff *trailer;
unsigned int len;
u16 check;
- int nsg;
int err;
sp = rxrpc_skb(skb);
crypto_skcipher_encrypt(req);
/* we want to encrypt the skbuff in-place */
- nsg = skb_cow_data(skb, 0, &trailer);
- err = -ENOMEM;
- if (nsg < 0 || nsg > 16)
+ err = -EMSGSIZE;
+ if (skb_shinfo(skb)->nr_frags > 16)
goto out;
len = data_size + call->conn->size_align - 1;
len &= ~(call->conn->size_align - 1);
- sg_init_table(sg, nsg);
+ sg_init_table(sg, ARRAY_SIZE(sg));
err = skb_to_sgvec(skb, sg, 0, len);
if (unlikely(err < 0))
goto out;
struct rxkad_level1_hdr sechdr;
struct rxrpc_crypt iv;
struct scatterlist sg[16];
- struct sk_buff *trailer;
bool aborted;
u32 data_size, buf;
u16 check;
- int nsg, ret;
+ int ret;
_enter("");
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
*/
- nsg = skb_cow_data(skb, 0, &trailer);
- if (nsg < 0 || nsg > 16)
- goto nomem;
-
- sg_init_table(sg, nsg);
+ sg_init_table(sg, ARRAY_SIZE(sg));
ret = skb_to_sgvec(skb, sg, offset, 8);
if (unlikely(ret < 0))
return ret;
if (aborted)
rxrpc_send_abort_packet(call);
return -EPROTO;
-
-nomem:
- _leave(" = -ENOMEM");
- return -ENOMEM;
}
/*
struct rxkad_level2_hdr sechdr;
struct rxrpc_crypt iv;
struct scatterlist _sg[4], *sg;
- struct sk_buff *trailer;
bool aborted;
u32 data_size, buf;
u16 check;
/* Decrypt the skbuff in-place. TODO: We really want to decrypt
* directly into the target buffer.
*/
- nsg = skb_cow_data(skb, 0, &trailer);
- if (nsg < 0)
- goto nomem;
-
sg = _sg;
- if (unlikely(nsg > 4)) {
+ nsg = skb_shinfo(skb)->nr_frags;
+ if (nsg <= 4) {
+ nsg = 4;
+ } else {
sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO);
if (!sg)
goto nomem;
skb->tstamp = ktime_get_real();
ix = seq & RXRPC_RXTX_BUFF_MASK;
- rxrpc_get_skb(skb, rxrpc_skb_tx_got);
+ rxrpc_get_skb(skb, rxrpc_skb_got);
call->rxtx_annotations[ix] = annotation;
smp_wmb();
call->rxtx_buffer[ix] = skb;
rxrpc_set_call_completion(call,
RXRPC_CALL_LOCAL_ERROR,
0, ret);
+ rxrpc_notify_socket(call);
goto out;
}
_debug("need instant resend %d", ret);
}
out:
- rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
_leave(" = %d", ret);
return ret;
}
skb = call->tx_pending;
call->tx_pending = NULL;
- rxrpc_see_skb(skb, rxrpc_skb_tx_seen);
+ rxrpc_see_skb(skb, rxrpc_skb_seen);
copied = 0;
do {
if (!skb)
goto maybe_error;
- rxrpc_new_skb(skb, rxrpc_skb_tx_new);
+ sp = rxrpc_skb(skb);
+ sp->rx_flags |= RXRPC_SKB_TX_BUFFER;
+ rxrpc_new_skb(skb, rxrpc_skb_new);
_debug("ALLOC SEND %p", skb);
skb_reserve(skb, call->conn->security_size);
skb->len += call->conn->security_size;
- sp = rxrpc_skb(skb);
sp->remain = chunk;
if (sp->remain > skb_tailroom(skb))
sp->remain = skb_tailroom(skb);
return ret;
call_terminated:
- rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
+ rxrpc_free_skb(skb, rxrpc_skb_freed);
_leave(" = %d", call->error);
return call->error;
#include <net/af_rxrpc.h>
#include "ar-internal.h"
-#define select_skb_count(op) (op >= rxrpc_skb_tx_cleaned ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs)
+#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER)
+#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs)
/*
* Note the allocation or reception of a socket buffer.
void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
- int n = atomic_inc_return(select_skb_count(op));
- trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
+ int n = atomic_inc_return(select_skb_count(skb));
+ trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n,
+ rxrpc_skb(skb)->rx_flags, here);
}
/*
{
const void *here = __builtin_return_address(0);
if (skb) {
- int n = atomic_read(select_skb_count(op));
- trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
+ int n = atomic_read(select_skb_count(skb));
+ trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n,
+ rxrpc_skb(skb)->rx_flags, here);
}
}
void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
- int n = atomic_inc_return(select_skb_count(op));
- trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
+ int n = atomic_inc_return(select_skb_count(skb));
+ trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n,
+ rxrpc_skb(skb)->rx_flags, here);
skb_get(skb);
}
+/*
+ * Note the dropping of a ref on a socket buffer by the core.
+ */
+void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
+{
+ const void *here = __builtin_return_address(0);
+ int n = atomic_inc_return(&rxrpc_n_rx_skbs);
+ trace_rxrpc_skb(skb, op, 0, n, 0, here);
+}
+
/*
* Note the destruction of a socket buffer.
*/
if (skb) {
int n;
CHECK_SLAB_OKAY(&skb->users);
- n = atomic_dec_return(select_skb_count(op));
- trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
+ n = atomic_dec_return(select_skb_count(skb));
+ trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n,
+ rxrpc_skb(skb)->rx_flags, here);
kfree_skb(skb);
}
}
const void *here = __builtin_return_address(0);
struct sk_buff *skb;
while ((skb = skb_dequeue((list))) != NULL) {
- int n = atomic_dec_return(select_skb_count(rxrpc_skb_rx_purged));
- trace_rxrpc_skb(skb, rxrpc_skb_rx_purged,
- refcount_read(&skb->users), n, here);
+ int n = atomic_dec_return(select_skb_count(skb));
+ trace_rxrpc_skb(skb, rxrpc_skb_purged,
+ refcount_read(&skb->users), n,
+ rxrpc_skb(skb)->rx_flags, here);
kfree_skb(skb);
}
}
struct tcf_bpf *prog;
bool is_bpf, is_ebpf;
int ret, res = 0;
+ u32 index;
if (!nla)
return -EINVAL;
return -EINVAL;
parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
-
- ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+ index = parm->index;
+ ret = tcf_idr_check_alloc(tn, &index, act, bind);
if (!ret) {
- ret = tcf_idr_create(tn, parm->index, est, act,
+ ret = tcf_idr_create(tn, index, est, act,
&act_bpf_ops, bind, true);
if (ret < 0) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, bpf_net_id);
- return tc_action_net_init(tn, &act_bpf_ops);
+ return tc_action_net_init(net, tn, &act_bpf_ops);
}
static void __net_exit bpf_exit_net(struct list_head *net_list)
struct tcf_connmark_info *ci;
struct tc_connmark *parm;
int ret = 0, err;
+ u32 index;
if (!nla)
return -EINVAL;
return -EINVAL;
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
-
- ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ ret = tcf_idr_check_alloc(tn, &index, a, bind);
if (!ret) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_connmark_ops, bind, false);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
- return tc_action_net_init(tn, &act_connmark_ops);
+ return tc_action_net_init(net, tn, &act_connmark_ops);
}
static void __net_exit connmark_exit_net(struct list_head *net_list)
struct tc_csum *parm;
struct tcf_csum *p;
int ret = 0, err;
+ u32 index;
if (nla == NULL)
return -EINVAL;
if (tb[TCA_CSUM_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_CSUM_PARMS]);
-
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_csum_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, csum_net_id);
- return tc_action_net_init(tn, &act_csum_ops);
+ return tc_action_net_init(net, tn, &act_csum_ops);
}
static void __net_exit csum_exit_net(struct list_head *net_list)
struct tc_ct *parm;
struct tcf_ct *c;
int err, res = 0;
+ u32 index;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed");
return -EINVAL;
}
parm = nla_data(tb[TCA_CT_PARMS]);
-
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
if (!err) {
- err = tcf_idr_create(tn, parm->index, est, a,
+ err = tcf_idr_create(tn, index, est, a,
&act_ct_ops, bind, true);
if (err) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return err;
}
res = ACT_P_CREATED;
tn->labels = true;
}
- return tc_action_net_init(&tn->tn, &act_ct_ops);
+ return tc_action_net_init(net, &tn->tn, &act_ct_ops);
}
static void __net_exit ct_exit_net(struct list_head *net_list)
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, ctinfo_net_id);
+ u32 dscpmask = 0, dscpstatemask, index;
struct nlattr *tb[TCA_CTINFO_MAX + 1];
struct tcf_ctinfo_params *cp_new;
struct tcf_chain *goto_ch = NULL;
- u32 dscpmask = 0, dscpstatemask;
struct tc_ctinfo *actparm;
struct tcf_ctinfo *ci;
u8 dscpmaskshift;
}
/* done the validation:now to the actual action allocation */
- err = tcf_idr_check_alloc(tn, &actparm->index, a, bind);
+ index = actparm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
- ret = tcf_idr_create(tn, actparm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_ctinfo_ops, bind, false);
if (ret) {
- tcf_idr_cleanup(tn, actparm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, ctinfo_net_id);
- return tc_action_net_init(tn, &act_ctinfo_ops);
+ return tc_action_net_init(net, tn, &act_ctinfo_ops);
}
static void __net_exit ctinfo_exit_net(struct list_head *net_list)
struct tc_gact *parm;
struct tcf_gact *gact;
int ret = 0;
+ u32 index;
int err;
#ifdef CONFIG_GACT_PROB
struct tc_gact_p *p_parm = NULL;
if (tb[TCA_GACT_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_GACT_PARMS]);
+ index = parm->index;
#ifndef CONFIG_GACT_PROB
if (tb[TCA_GACT_PROB] != NULL)
}
#endif
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_gact_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, gact_net_id);
- return tc_action_net_init(tn, &act_gact_ops);
+ return tc_action_net_init(net, tn, &act_gact_ops);
}
static void __net_exit gact_exit_net(struct list_head *net_list)
u8 *saddr = NULL;
bool exists = false;
int ret = 0;
+ u32 index;
int err;
+ if (!nla) {
+ NL_SET_ERR_MSG_MOD(extack, "IFE requires attributes to be passed");
+ return -EINVAL;
+ }
+
err = nla_parse_nested_deprecated(tb, TCA_IFE_MAX, nla, ife_policy,
NULL);
if (err < 0)
if (!p)
return -ENOMEM;
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0) {
kfree(p);
return err;
}
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
+ ret = tcf_idr_create(tn, index, est, a, &act_ife_ops,
bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
kfree(p);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, ife_net_id);
- return tc_action_net_init(tn, &act_ife_ops);
+ return tc_action_net_init(net, tn, &act_ife_ops);
}
static void __net_exit ife_exit_net(struct list_head *net_list)
return 0;
}
-static void ipt_destroy_target(struct xt_entry_target *t)
+static void ipt_destroy_target(struct xt_entry_target *t, struct net *net)
{
struct xt_tgdtor_param par = {
.target = t->u.kernel.target,
.targinfo = t->data,
.family = NFPROTO_IPV4,
+ .net = net,
};
if (par.target->destroy != NULL)
par.target->destroy(&par);
struct tcf_ipt *ipt = to_ipt(a);
if (ipt->tcfi_t) {
- ipt_destroy_target(ipt->tcfi_t);
+ ipt_destroy_target(ipt->tcfi_t, a->idrinfo->net);
kfree(ipt->tcfi_t);
}
kfree(ipt->tcfi_tname);
spin_lock_bh(&ipt->tcf_lock);
if (ret != ACT_P_CREATED) {
- ipt_destroy_target(ipt->tcfi_t);
+ ipt_destroy_target(ipt->tcfi_t, net);
kfree(ipt->tcfi_tname);
kfree(ipt->tcfi_t);
}
{
struct tc_action_net *tn = net_generic(net, ipt_net_id);
- return tc_action_net_init(tn, &act_ipt_ops);
+ return tc_action_net_init(net, tn, &act_ipt_ops);
}
static void __net_exit ipt_exit_net(struct list_head *net_list)
{
struct tc_action_net *tn = net_generic(net, xt_net_id);
- return tc_action_net_init(tn, &act_xt_ops);
+ return tc_action_net_init(net, tn, &act_xt_ops);
}
static void __net_exit xt_exit_net(struct list_head *net_list)
struct net_device *dev;
bool exists = false;
int ret, err;
+ u32 index;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
return -EINVAL;
}
parm = nla_data(tb[TCA_MIRRED_PARMS]);
-
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
return -EINVAL;
}
if (!exists) {
if (!parm->ifindex) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
return -EINVAL;
}
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_mirred_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, mirred_net_id);
- return tc_action_net_init(tn, &act_mirred_ops);
+ return tc_action_net_init(net, tn, &act_mirred_ops);
}
static void __net_exit mirred_exit_net(struct list_head *net_list)
struct tcf_mpls *m;
int ret = 0, err;
u8 mpls_ttl = 0;
+ u32 index;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes");
return -EINVAL;
}
parm = nla_data(tb[TCA_MPLS_PARMS]);
+ index = parm->index;
/* Verify parameters against action type. */
switch (parm->m_action) {
return -EINVAL;
}
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
return 0;
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_mpls_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, mpls_net_id);
- return tc_action_net_init(tn, &act_mpls_ops);
+ return tc_action_net_init(net, tn, &act_mpls_ops);
}
static void __net_exit mpls_exit_net(struct list_head *net_list)
struct tc_nat *parm;
int ret = 0, err;
struct tcf_nat *p;
+ u32 index;
if (nla == NULL)
return -EINVAL;
if (tb[TCA_NAT_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_NAT_PARMS]);
-
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_nat_ops, bind, false);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, nat_net_id);
- return tc_action_net_init(tn, &act_nat_ops);
+ return tc_action_net_init(net, tn, &act_nat_ops);
}
static void __net_exit nat_exit_net(struct list_head *net_list)
struct tcf_pedit *p;
int ret = 0, err;
int ksize;
+ u32 index;
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
if (IS_ERR(keys_ex))
return PTR_ERR(keys_ex);
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (!err) {
if (!parm->nkeys) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
ret = -EINVAL;
goto out_free;
}
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_pedit_ops, bind, false);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
goto out_free;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, pedit_net_id);
- return tc_action_net_init(tn, &act_pedit_ops);
+ return tc_action_net_init(net, tn, &act_pedit_ops);
}
static void __net_exit pedit_exit_net(struct list_head *net_list)
struct tc_action_net *tn = net_generic(net, police_net_id);
struct tcf_police_params *new;
bool exists = false;
+ u32 index;
if (nla == NULL)
return -EINVAL;
return -EINVAL;
parm = nla_data(tb[TCA_POLICE_TBF]);
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
return 0;
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, NULL, a,
+ ret = tcf_idr_create(tn, index, NULL, a,
&act_police_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
{
struct tc_action_net *tn = net_generic(net, police_net_id);
- return tc_action_net_init(tn, &act_police_ops);
+ return tc_action_net_init(net, tn, &act_police_ops);
}
static void __net_exit police_exit_net(struct list_head *net_list)
struct tc_action_net *tn = net_generic(net, sample_net_id);
struct nlattr *tb[TCA_SAMPLE_MAX + 1];
struct psample_group *psample_group;
+ u32 psample_group_num, rate, index;
struct tcf_chain *goto_ch = NULL;
- u32 psample_group_num, rate;
struct tc_sample *parm;
struct tcf_sample *s;
bool exists = false;
return -EINVAL;
parm = nla_data(tb[TCA_SAMPLE_PARMS]);
-
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
return 0;
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_sample_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
s->rate = rate;
s->psample_group_num = psample_group_num;
- RCU_INIT_POINTER(s->psample_group, psample_group);
+ rcu_swap_protected(s->psample_group, psample_group,
+ lockdep_is_held(&s->tcf_lock));
if (tb[TCA_SAMPLE_TRUNC_SIZE]) {
s->truncate = true;
s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
}
spin_unlock_bh(&s->tcf_lock);
+
+ if (psample_group)
+ psample_group_put(psample_group);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
{
struct tc_action_net *tn = net_generic(net, sample_net_id);
- return tc_action_net_init(tn, &act_sample_ops);
+ return tc_action_net_init(net, tn, &act_sample_ops);
}
static void __net_exit sample_exit_net(struct list_head *net_list)
struct tcf_defact *d;
bool exists = false;
int ret = 0, err;
+ u32 index;
if (nla == NULL)
return -EINVAL;
return -EINVAL;
parm = nla_data(tb[TCA_DEF_PARMS]);
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_simp_ops, bind, false);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, simp_net_id);
- return tc_action_net_init(tn, &act_simp_ops);
+ return tc_action_net_init(net, tn, &act_simp_ops);
}
static void __net_exit simp_exit_net(struct list_head *net_list)
u16 *queue_mapping = NULL, *ptype = NULL;
bool exists = false;
int ret = 0, err;
+ u32 index;
if (nla == NULL)
return -EINVAL;
}
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
-
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_skbedit_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
return tcf_idr_search(tn, a, index);
}
+static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
+{
+ return nla_total_size(sizeof(struct tc_skbedit))
+ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
+ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
+ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
+ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
+ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */
+ + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */
+}
+
static struct tc_action_ops act_skbedit_ops = {
.kind = "skbedit",
.id = TCA_ID_SKBEDIT,
.init = tcf_skbedit_init,
.cleanup = tcf_skbedit_cleanup,
.walk = tcf_skbedit_walker,
+ .get_fill_size = tcf_skbedit_get_fill_size,
.lookup = tcf_skbedit_search,
.size = sizeof(struct tcf_skbedit),
};
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
- return tc_action_net_init(tn, &act_skbedit_ops);
+ return tc_action_net_init(net, tn, &act_skbedit_ops);
}
static void __net_exit skbedit_exit_net(struct list_head *net_list)
struct tcf_skbmod_params *p, *p_old;
struct tcf_chain *goto_ch = NULL;
struct tc_skbmod *parm;
+ u32 lflags = 0, index;
struct tcf_skbmod *d;
bool exists = false;
u8 *daddr = NULL;
u8 *saddr = NULL;
u16 eth_type = 0;
- u32 lflags = 0;
int ret = 0, err;
if (!nla)
}
parm = nla_data(tb[TCA_SKBMOD_PARMS]);
+ index = parm->index;
if (parm->flags & SKBMOD_F_SWAPMAC)
lflags = SKBMOD_F_SWAPMAC;
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_skbmod_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, skbmod_net_id);
- return tc_action_net_init(tn, &act_skbmod_ops);
+ return tc_action_net_init(net, tn, &act_skbmod_ops);
}
static void __net_exit skbmod_exit_net(struct list_head *net_list)
__be16 flags = 0;
u8 tos, ttl;
int ret = 0;
+ u32 index;
int err;
if (!nla) {
}
parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
}
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_tunnel_key_ops, bind, true);
if (ret) {
NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
{
struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
- return tc_action_net_init(tn, &act_tunnel_key_ops);
+ return tc_action_net_init(net, tn, &act_tunnel_key_ops);
}
static void __net_exit tunnel_key_exit_net(struct list_head *net_list)
u8 push_prio = 0;
bool exists = false;
int ret = 0, err;
+ u32 index;
if (!nla)
return -EINVAL;
if (!tb[TCA_VLAN_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_VLAN_PARMS]);
- err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+ index = parm->index;
+ err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -ERANGE;
}
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -EPROTONOSUPPORT;
}
} else {
if (exists)
tcf_idr_release(*a, bind);
else
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return -EINVAL;
}
action = parm->v_action;
if (!exists) {
- ret = tcf_idr_create(tn, parm->index, est, a,
+ ret = tcf_idr_create(tn, index, est, a,
&act_vlan_ops, bind, true);
if (ret) {
- tcf_idr_cleanup(tn, parm->index);
+ tcf_idr_cleanup(tn, index);
return ret;
}
return tcf_idr_search(tn, a, index);
}
+static size_t tcf_vlan_get_fill_size(const struct tc_action *act)
+{
+ return nla_total_size(sizeof(struct tc_vlan))
+ + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_ID */
+ + nla_total_size(sizeof(u16)) /* TCA_VLAN_PUSH_VLAN_PROTOCOL */
+ + nla_total_size(sizeof(u8)); /* TCA_VLAN_PUSH_VLAN_PRIORITY */
+}
+
static struct tc_action_ops act_vlan_ops = {
.kind = "vlan",
.id = TCA_ID_VLAN,
.init = tcf_vlan_init,
.cleanup = tcf_vlan_cleanup,
.walk = tcf_vlan_walker,
+ .get_fill_size = tcf_vlan_get_fill_size,
.lookup = tcf_vlan_search,
.size = sizeof(struct tcf_vlan),
};
{
struct tc_action_net *tn = net_generic(net, vlan_net_id);
- return tc_action_net_init(tn, &act_vlan_ops);
+ return tc_action_net_init(net, tn, &act_vlan_ops);
}
static void __net_exit vlan_exit_net(struct list_head *net_list)
if (!indr_dev->block)
return;
+ bo.block = &indr_dev->block->flow_block;
+
indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
&bo);
tcf_block_setup(indr_dev->block, &bo);
.command = command,
.binder_type = ei->binder_type,
.net = dev_net(dev),
+ .block = &block->flow_block,
.block_shared = tcf_block_shared(block),
.extack = extack,
};
bo.net = dev_net(dev);
bo.command = command;
bo.binder_type = ei->binder_type;
+ bo.block = &block->flow_block;
bo.block_shared = tcf_block_shared(block);
bo.extack = extack;
INIT_LIST_HEAD(&bo.cb_list);
return ERR_PTR(-ENOMEM);
}
mutex_init(&block->lock);
+ flow_block_init(&block->flow_block);
INIT_LIST_HEAD(&block->chain_list);
- INIT_LIST_HEAD(&block->cb_list);
INIT_LIST_HEAD(&block->owner_list);
INIT_LIST_HEAD(&block->chain0.filter_chain_list);
EXPORT_SYMBOL(tcf_block_put);
static int
-tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
+tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
void *cb_priv, bool add, bool offload_in_use,
struct netlink_ext_ack *extack)
{
i++;
}
- list_splice(&bo->cb_list, &block->cb_list);
+ list_splice(&bo->cb_list, &block->flow_block.cb_list);
return 0;
tfilter_notify(net, skb, n, tp, block, q, parent, fh,
RTM_NEWTFILTER, false, rtnl_held);
tfilter_put(tp, fh);
- q->flags &= ~TCQ_F_CAN_BYPASS;
+ /* q pointer is NULL for shared blocks */
+ if (q)
+ q->flags &= ~TCQ_F_CAN_BYPASS;
}
errout:
if (block->nooffloaddevcnt && err_stop)
return -EOPNOTSUPP;
- list_for_each_entry(block_cb, &block->cb_list, list) {
+ list_for_each_entry(block_cb, &block->flow_block.cb_list, list) {
err = block_cb->cb(type, type_data, block_cb->cb_priv);
if (err) {
if (err_stop)
}
}
-static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
void *cb_priv, struct netlink_ext_ack *extack)
{
struct cls_bpf_head *head = rtnl_dereference(tp->root);
return NULL;
}
-static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
void *cb_priv, struct netlink_ext_ack *extack)
{
struct tcf_block *block = tp->chain->block;
arg->count++;
}
-static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
void *cb_priv, struct netlink_ext_ack *extack)
{
struct cls_mall_head *head = rtnl_dereference(tp->root);
}
static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
- bool add, tc_setup_cb_t *cb, void *cb_priv,
+ bool add, flow_setup_cb_t *cb, void *cb_priv,
struct netlink_ext_ack *extack)
{
struct tc_cls_u32_offload cls_u32 = {};
}
static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
- bool add, tc_setup_cb_t *cb, void *cb_priv,
+ bool add, flow_setup_cb_t *cb, void *cb_priv,
struct netlink_ext_ack *extack)
{
struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
return 0;
}
-static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
void *cb_priv, struct netlink_ext_ack *extack)
{
struct tc_u_common *tp_c = tp->data;
s64 credits;
int len;
- if (atomic64_read(&q->port_rate) == -1) {
- WARN_ONCE(1, "cbs: dequeue() called with unknown port rate.");
- return NULL;
- }
-
if (q->credits < 0) {
credits = timediff_to_credits(now - q->last, q->idleslope);
static void cbs_set_port_rate(struct net_device *dev, struct cbs_sched_data *q)
{
struct ethtool_link_ksettings ecmd;
+ int speed = SPEED_10;
int port_rate = -1;
+ int err;
+
+ err = __ethtool_get_link_ksettings(dev, &ecmd);
+ if (err < 0)
+ goto skip;
+
+ if (ecmd.base.speed != SPEED_UNKNOWN)
+ speed = ecmd.base.speed;
- if (!__ethtool_get_link_ksettings(dev, &ecmd) &&
- ecmd.base.speed != SPEED_UNKNOWN)
- port_rate = ecmd.base.speed * 1000 * BYTES_PER_KBIT;
+skip:
+ port_rate = speed * 1000 * BYTES_PER_KBIT;
atomic64_set(&q->port_rate, port_rate);
netdev_dbg(dev, "cbs: set %s's port_rate to: %lld, linkspeed: %d\n",
struct Qdisc *sch = ctx;
struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
- if (skb)
+ if (skb) {
sch->qstats.backlog -= qdisc_pkt_len(skb);
-
- prefetch(&skb->end); /* we'll need skb_shinfo() */
+ prefetch(&skb->end); /* we'll need skb_shinfo() */
+ }
return skb;
}
err = skb_array_produce(q, skb);
- if (unlikely(err))
- return qdisc_drop_cpu(skb, qdisc, to_free);
+ if (unlikely(err)) {
+ if (qdisc_is_percpu_stats(qdisc))
+ return qdisc_drop_cpu(skb, qdisc, to_free);
+ else
+ return qdisc_drop(skb, qdisc, to_free);
+ }
qdisc_update_stats_at_enqueue(qdisc, pkt_len);
return NET_XMIT_SUCCESS;
kfree_skb(skb);
}
- for_each_possible_cpu(i) {
- struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
+ if (qdisc_is_percpu_stats(qdisc)) {
+ for_each_possible_cpu(i) {
+ struct gnet_stats_queue *q;
- q->backlog = 0;
- q->qlen = 0;
+ q = per_cpu_ptr(qdisc->cpu_qstats, i);
+ q->backlog = 0;
+ q->qlen = 0;
+ }
}
}
u32 gate_mask;
int i;
- if (atomic64_read(&q->picos_per_byte) == -1) {
- WARN_ONCE(1, "taprio: dequeue() called with unknown picos per byte.");
- return NULL;
- }
-
rcu_read_lock();
entry = rcu_dereference(q->current_entry);
/* if there's no entry, it means that the schedule didn't
struct taprio_sched *q)
{
struct ethtool_link_ksettings ecmd;
- int picos_per_byte = -1;
+ int speed = SPEED_10;
+ int picos_per_byte;
+ int err;
- if (!__ethtool_get_link_ksettings(dev, &ecmd) &&
- ecmd.base.speed != SPEED_UNKNOWN)
- picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
- ecmd.base.speed * 1000 * 1000);
+ err = __ethtool_get_link_ksettings(dev, &ecmd);
+ if (err < 0)
+ goto skip;
+
+ if (ecmd.base.speed != SPEED_UNKNOWN)
+ speed = ecmd.base.speed;
+
+skip:
+ picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8,
+ speed * 1000 * 1000);
atomic64_set(&q->picos_per_byte, picos_per_byte);
netdev_dbg(dev, "taprio: set %s's picos_per_byte to: %lld, linkspeed: %d\n",
spin_unlock_bh(qdisc_lock(sch));
free_sched:
- kfree(new_admin);
+ if (new_admin)
+ call_rcu(&new_admin->rcu, taprio_free_sched_cb);
return err;
}
*/
q->clockid = -1;
+ spin_lock(&taprio_list_lock);
+ list_add(&q->taprio_list, &taprio_list);
+ spin_unlock(&taprio_list_lock);
+
if (sch->parent != TC_H_ROOT)
return -EOPNOTSUPP;
if (!opt)
return -EINVAL;
- spin_lock(&taprio_list_lock);
- list_add(&q->taprio_list, &taprio_list);
- spin_unlock(&taprio_list_lock);
-
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *dev_queue;
struct Qdisc *qdisc;
*/
if (net->sctp.pf_enable &&
(transport->state == SCTP_ACTIVE) &&
- (asoc->pf_retrans < transport->pathmaxrxt) &&
+ (transport->error_count < transport->pathmaxrxt) &&
(transport->error_count > asoc->pf_retrans)) {
sctp_assoc_control_transport(asoc, transport,
return -EINVAL;
kaddrs = memdup_user(addrs, addrs_size);
- if (unlikely(IS_ERR(kaddrs)))
+ if (IS_ERR(kaddrs))
return PTR_ERR(kaddrs);
/* Walk through the addrs buffer and count the number of addresses. */
return -EINVAL;
kaddrs = memdup_user(addrs, addrs_size);
- if (unlikely(IS_ERR(kaddrs)))
+ if (IS_ERR(kaddrs))
return PTR_ERR(kaddrs);
/* Allow security module to validate connectx addresses. */
nstr_list[i] = htons(str_list[i]);
if (out && !sctp_stream_outq_is_empty(stream, str_nums, nstr_list)) {
+ kfree(nstr_list);
retval = -EAGAIN;
goto out;
}
/* Check if socket is already active */
rc = -EINVAL;
- if (sk->sk_state != SMC_INIT)
+ if (sk->sk_state != SMC_INIT || smc->connect_nonblock)
goto out_rel;
smc->clcsock->sk->sk_reuse = sk->sk_reuse;
lock_sock(sk);
rc = -EINVAL;
- if ((sk->sk_state != SMC_INIT) && (sk->sk_state != SMC_LISTEN))
+ if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) ||
+ smc->connect_nonblock)
goto out;
rc = 0;
goto out;
if (msg->msg_flags & MSG_FASTOPEN) {
- if (sk->sk_state == SMC_INIT) {
+ if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) {
smc_switch_to_fallback(smc);
smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
} else {
}
break;
case TCP_NODELAY:
- if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (sk->sk_state != SMC_INIT &&
+ sk->sk_state != SMC_LISTEN &&
+ sk->sk_state != SMC_CLOSED) {
if (val && !smc->use_fallback)
mod_delayed_work(system_wq, &smc->conn.tx_work,
0);
}
break;
case TCP_CORK:
- if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) {
+ if (sk->sk_state != SMC_INIT &&
+ sk->sk_state != SMC_LISTEN &&
+ sk->sk_state != SMC_CLOSED) {
if (!val && !smc->use_fallback)
mod_delayed_work(system_wq, &smc->conn.tx_work,
0);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
- bool noblock;
long timeo;
int rc = 0;
/* similar to sk_stream_wait_memory */
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
- noblock = timeo ? false : true;
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
break;
}
if (!timeo) {
- if (noblock)
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ /* ensure EPOLLOUT is subsequently generated */
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
rc = -EAGAIN;
break;
}
static void
call_bind_status(struct rpc_task *task)
{
+ struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt;
int status = -EIO;
if (rpc_task_transmitted(task)) {
return;
}
- if (task->tk_status >= 0) {
- dprint_status(task);
+ dprint_status(task);
+ trace_rpc_bind_status(task);
+ if (task->tk_status >= 0)
+ goto out_next;
+ if (xprt_bound(xprt)) {
task->tk_status = 0;
- task->tk_action = call_connect;
- return;
+ goto out_next;
}
- trace_rpc_bind_status(task);
switch (task->tk_status) {
case -ENOMEM:
dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid);
task->tk_rebind_retry--;
rpc_delay(task, 3*HZ);
goto retry_timeout;
+ case -ENOBUFS:
+ rpc_delay(task, HZ >> 2);
+ goto retry_timeout;
case -EAGAIN:
goto retry_timeout;
case -ETIMEDOUT:
case -ENETDOWN:
case -EHOSTUNREACH:
case -ENETUNREACH:
- case -ENOBUFS:
case -EPIPE:
dprintk("RPC: %5u remote rpcbind unreachable: %d\n",
task->tk_pid, task->tk_status);
rpc_call_rpcerror(task, status);
return;
-
+out_next:
+ task->tk_action = call_connect;
+ return;
retry_timeout:
task->tk_status = 0;
task->tk_action = call_bind;
static void
call_connect_status(struct rpc_task *task)
{
+ struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt;
struct rpc_clnt *clnt = task->tk_client;
int status = task->tk_status;
}
dprint_status(task);
-
trace_rpc_connect_status(task);
+
+ if (task->tk_status == 0) {
+ clnt->cl_stats->netreconn++;
+ goto out_next;
+ }
+ if (xprt_connected(xprt)) {
+ task->tk_status = 0;
+ goto out_next;
+ }
+
task->tk_status = 0;
switch (status) {
case -ECONNREFUSED:
case -ENETDOWN:
case -ENETUNREACH:
case -EHOSTUNREACH:
- case -EADDRINUSE:
- case -ENOBUFS:
case -EPIPE:
xprt_conditional_disconnect(task->tk_rqstp->rq_xprt,
task->tk_rqstp->rq_connect_cookie);
/* retry with existing socket, after a delay */
rpc_delay(task, 3*HZ);
/* fall through */
+ case -EADDRINUSE:
case -ENOTCONN:
case -EAGAIN:
case -ETIMEDOUT:
goto out_retry;
- case 0:
- clnt->cl_stats->netreconn++;
- task->tk_action = call_transmit;
- return;
+ case -ENOBUFS:
+ rpc_delay(task, HZ >> 2);
+ goto out_retry;
}
rpc_call_rpcerror(task, status);
return;
+out_next:
+ task->tk_action = call_transmit;
+ return;
out_retry:
/* Check for timeouts before looping back to call_bind */
task->tk_action = call_bind;
case -ECONNABORTED:
case -ENOTCONN:
rpc_force_rebind(clnt);
- /* fall through */
+ break;
case -EADDRINUSE:
rpc_delay(task, 3*HZ);
/* fall through */
status = -EBADMSG;
goto out_dequeue;
}
- if (task->tk_ops->rpc_call_prepare_transmit) {
- task->tk_ops->rpc_call_prepare_transmit(task,
- task->tk_calldata);
- status = task->tk_status;
- if (status < 0)
- goto out_dequeue;
- }
if (RPC_SIGNALLED(task)) {
status = -ERESTARTSYS;
goto out_dequeue;
tipc_set_node_id(net, node_id);
}
tn->trial_addr = addr;
+ tn->addr_trial_end = jiffies;
pr_info("32-bit node address hash set to %x\n", addr);
}
* @transmitq: queue for sent, non-acked messages
* @backlogq: queue for messages waiting to be sent
* @snt_nxt: next sequence number to use for outbound messages
- * @prev_from: sequence number of most previous retransmission request
- * @stale_limit: time when repeated identical retransmits must force link reset
* @ackers: # of peers that needs to ack each packet before it can be released
* @acked: # last packet acked by a certain peer. Used for broadcast.
* @rcv_nxt: next sequence number to expect for inbound messages
u16 limit;
} backlog[5];
u16 snd_nxt;
- u16 prev_from;
u16 window;
- unsigned long stale_limit;
/* Reception */
u16 rcv_nxt;
* link_retransmit_failure() - Detect repeated retransmit failures
* @l: tipc link sender
* @r: tipc link receiver (= l in case of unicast)
- * @from: seqno of the 1st packet in retransmit request
* @rc: returned code
*
* Return: true if the repeated retransmit failures happens, otherwise
* false
*/
static bool link_retransmit_failure(struct tipc_link *l, struct tipc_link *r,
- u16 from, int *rc)
+ int *rc)
{
struct sk_buff *skb = skb_peek(&l->transmq);
struct tipc_msg *hdr;
if (!skb)
return false;
- hdr = buf_msg(skb);
- /* Detect repeated retransmit failures on same packet */
- if (r->prev_from != from) {
- r->prev_from = from;
- r->stale_limit = jiffies + msecs_to_jiffies(r->tolerance);
- } else if (time_after(jiffies, r->stale_limit)) {
- pr_warn("Retransmission failure on link <%s>\n", l->name);
- link_print(l, "State of link ");
- pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
- msg_user(hdr), msg_type(hdr), msg_size(hdr),
- msg_errcode(hdr));
- pr_info("sqno %u, prev: %x, src: %x\n",
- msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
-
- trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
- trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
- trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
+ if (!TIPC_SKB_CB(skb)->retr_cnt)
+ return false;
- if (link_is_bc_sndlink(l))
- *rc = TIPC_LINK_DOWN_EVT;
+ if (!time_after(jiffies, TIPC_SKB_CB(skb)->retr_stamp +
+ msecs_to_jiffies(r->tolerance)))
+ return false;
+
+ hdr = buf_msg(skb);
+ if (link_is_bc_sndlink(l) && !less(r->acked, msg_seqno(hdr)))
+ return false;
+ pr_warn("Retransmission failure on link <%s>\n", l->name);
+ link_print(l, "State of link ");
+ pr_info("Failed msg: usr %u, typ %u, len %u, err %u\n",
+ msg_user(hdr), msg_type(hdr), msg_size(hdr), msg_errcode(hdr));
+ pr_info("sqno %u, prev: %x, dest: %x\n",
+ msg_seqno(hdr), msg_prevnode(hdr), msg_destnode(hdr));
+ pr_info("retr_stamp %d, retr_cnt %d\n",
+ jiffies_to_msecs(TIPC_SKB_CB(skb)->retr_stamp),
+ TIPC_SKB_CB(skb)->retr_cnt);
+
+ trace_tipc_list_dump(&l->transmq, true, "retrans failure!");
+ trace_tipc_link_dump(l, TIPC_DUMP_NONE, "retrans failure!");
+ trace_tipc_link_dump(r, TIPC_DUMP_NONE, "retrans failure!");
+
+ if (link_is_bc_sndlink(l)) {
+ r->state = LINK_RESET;
+ *rc = TIPC_LINK_DOWN_EVT;
+ } else {
*rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
- return true;
}
- return false;
+ return true;
}
/* tipc_link_bc_retrans() - retransmit zero or more packets
trace_tipc_link_retrans(r, from, to, &l->transmq);
- if (link_retransmit_failure(l, r, from, &rc))
+ if (link_retransmit_failure(l, r, &rc))
return rc;
skb_queue_walk(&l->transmq, skb) {
continue;
if (more(msg_seqno(hdr), to))
break;
- if (link_is_bc_sndlink(l)) {
- if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
- continue;
- TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
- }
+
+ if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
+ continue;
+ TIPC_SKB_CB(skb)->nxt_retr = TIPC_BC_RETR_LIM;
_skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE, GFP_ATOMIC);
if (!_skb)
return 0;
_skb->priority = TC_PRIO_CONTROL;
__skb_queue_tail(xmitq, _skb);
l->stats.retransmitted++;
+
+ /* Increase actual retrans counter & mark first time */
+ if (!TIPC_SKB_CB(skb)->retr_cnt++)
+ TIPC_SKB_CB(skb)->retr_stamp = jiffies;
}
return 0;
}
struct tipc_msg *hdr;
u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
u16 ack = l->rcv_nxt - 1;
+ bool passed = false;
u16 seqno, n = 0;
int rc = 0;
- if (gap && link_retransmit_failure(l, l, acked + 1, &rc))
- return rc;
-
skb_queue_walk_safe(&l->transmq, skb, tmp) {
seqno = buf_seqno(skb);
__skb_unlink(skb, &l->transmq);
kfree_skb(skb);
} else if (less_eq(seqno, acked + gap)) {
- /* retransmit skb */
+ /* First, check if repeated retrans failures occurs? */
+ if (!passed && link_retransmit_failure(l, l, &rc))
+ return rc;
+ passed = true;
+
+ /* retransmit skb if unrestricted*/
if (time_before(jiffies, TIPC_SKB_CB(skb)->nxt_retr))
continue;
TIPC_SKB_CB(skb)->nxt_retr = TIPC_UC_RETR_TIME;
-
- _skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
+ _skb = __pskb_copy(skb, LL_MAX_HEADER + MIN_H_SIZE,
+ GFP_ATOMIC);
if (!_skb)
continue;
hdr = buf_msg(_skb);
_skb->priority = TC_PRIO_CONTROL;
__skb_queue_tail(xmitq, _skb);
l->stats.retransmitted++;
+
+ /* Increase actual retrans counter & mark first time */
+ if (!TIPC_SKB_CB(skb)->retr_cnt++)
+ TIPC_SKB_CB(skb)->retr_stamp = jiffies;
} else {
/* retry with Gap ACK blocks if any */
if (!ga || n >= ga->gack_cnt)
i += scnprintf(buf + i, sz - i, " %x", l->peer_caps);
i += scnprintf(buf + i, sz - i, " %u", l->silent_intv_cnt);
i += scnprintf(buf + i, sz - i, " %u", l->rst_cnt);
- i += scnprintf(buf + i, sz - i, " %u", l->prev_from);
+ i += scnprintf(buf + i, sz - i, " %u", 0);
i += scnprintf(buf + i, sz - i, " %u", 0);
i += scnprintf(buf + i, sz - i, " %u", l->acked);
#define TIPC_MEDIA_INFO_OFFSET 5
struct tipc_skb_cb {
- u32 bytes_read;
- u32 orig_member;
struct sk_buff *tail;
unsigned long nxt_retr;
- bool validated;
+ unsigned long retr_stamp;
+ u32 bytes_read;
+ u32 orig_member;
u16 chain_imp;
u16 ackers;
+ u16 retr_cnt;
+ bool validated;
};
#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0]))
int rep_type;
int rep_size;
int req_type;
+ int req_size;
struct net *net;
struct sk_buff *rep;
struct tlv_desc *req;
int err;
struct sk_buff *arg;
- if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+ if (msg->req_type && (!msg->req_size ||
+ !TLV_CHECK_TYPE(msg->req, msg->req_type)))
return -EINVAL;
msg->rep = tipc_tlv_alloc(msg->rep_size);
{
int err;
- if (msg->req_type && !TLV_CHECK_TYPE(msg->req, msg->req_type))
+ if (msg->req_type && (!msg->req_size ||
+ !TLV_CHECK_TYPE(msg->req, msg->req_type)))
return -EINVAL;
err = __tipc_nl_compat_doit(cmd, msg);
goto send;
}
- len = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
- if (!len || !TLV_OK(msg.req, len)) {
+ msg.req_size = nlmsg_attrlen(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN);
+ if (msg.req_size && !TLV_OK(msg.req, msg.req_size)) {
msg.rep = tipc_get_err_tlv(TIPC_CFG_NOT_SUPPORTED);
err = -EOPNOTSUPP;
goto send;
tsk_set_unreturnable(tsk, true);
if (sock->type == SOCK_DGRAM)
tsk_set_unreliable(tsk, true);
- __skb_queue_head_init(&tsk->mc_method.deferredq);
}
-
+ __skb_queue_head_init(&tsk->mc_method.deferredq);
trace_tipc_sk_create(sk, NULL, TIPC_DUMP_NONE, " ");
return 0;
}
}
}
-/* tipc_toprsv_listener_data_ready - interrupt callback with connection request
+/* tipc_topsrv_listener_data_ready - interrupt callback with connection request
* The queued job is launched into tipc_topsrv_accept()
*/
static void tipc_topsrv_listener_data_ready(struct sock *sk)
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_prot_info *prot = &tls_ctx->prot_info;
struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
- int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
struct tls_record_info *record = ctx->open_record;
+ int tls_push_record_flags;
struct page_frag *pfrag;
size_t orig_size = size;
u32 max_open_record_len;
if (sk->sk_err)
return -sk->sk_err;
+ flags |= MSG_SENDPAGE_DECRYPTED;
+ tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
if (tls_is_partially_sent_record(tls_ctx)) {
rc = tls_push_partial_record(sk, tls_ctx, flags);
gfp_t sk_allocation = sk->sk_allocation;
sk->sk_allocation = GFP_ATOMIC;
- tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL);
+ tls_push_partial_record(sk, ctx,
+ MSG_DONTWAIT | MSG_NOSIGNAL |
+ MSG_SENDPAGE_DECRYPTED);
sk->sk_allocation = sk_allocation;
}
}
kfree(ctx);
}
-static void tls_sk_proto_close(struct sock *sk, long timeout)
+static void tls_sk_proto_cleanup(struct sock *sk,
+ struct tls_context *ctx, long timeo)
{
- struct tls_context *ctx = tls_get_ctx(sk);
- long timeo = sock_sndtimeo(sk, 0);
- void (*sk_proto_close)(struct sock *sk, long timeout);
- bool free_ctx = false;
-
- lock_sock(sk);
- sk_proto_close = ctx->sk_proto_close;
-
- if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD)
- goto skip_tx_cleanup;
-
- if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) {
- free_ctx = true;
- goto skip_tx_cleanup;
- }
-
if (unlikely(sk->sk_write_pending) &&
!wait_on_pending_writer(sk, &timeo))
tls_handle_open_record(sk, 0);
if (ctx->tx_conf == TLS_SW) {
kfree(ctx->tx.rec_seq);
kfree(ctx->tx.iv);
- tls_sw_free_resources_tx(sk);
+ tls_sw_release_resources_tx(sk);
#ifdef CONFIG_TLS_DEVICE
} else if (ctx->tx_conf == TLS_HW) {
tls_device_free_resources_tx(sk);
}
if (ctx->rx_conf == TLS_SW)
- tls_sw_free_resources_rx(sk);
+ tls_sw_release_resources_rx(sk);
#ifdef CONFIG_TLS_DEVICE
if (ctx->rx_conf == TLS_HW)
tls_device_offload_cleanup_rx(sk);
-
- if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) {
-#else
- {
#endif
- tls_ctx_free(ctx);
- ctx = NULL;
- }
+}
-skip_tx_cleanup:
+static void tls_sk_proto_close(struct sock *sk, long timeout)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tls_context *ctx = tls_get_ctx(sk);
+ long timeo = sock_sndtimeo(sk, 0);
+ bool free_ctx;
+
+ if (ctx->tx_conf == TLS_SW)
+ tls_sw_cancel_work_tx(ctx);
+
+ lock_sock(sk);
+ free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW;
+
+ if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE)
+ tls_sk_proto_cleanup(sk, ctx, timeo);
+
+ write_lock_bh(&sk->sk_callback_lock);
+ if (free_ctx)
+ icsk->icsk_ulp_data = NULL;
+ sk->sk_prot = ctx->sk_proto;
+ if (sk->sk_write_space == tls_write_space)
+ sk->sk_write_space = ctx->sk_write_space;
+ write_unlock_bh(&sk->sk_callback_lock);
release_sock(sk);
- sk_proto_close(sk, timeout);
- /* free ctx for TLS_HW_RECORD, used by tcp_set_state
- * for sk->sk_prot->unhash [tls_hw_unhash]
- */
+ if (ctx->tx_conf == TLS_SW)
+ tls_sw_free_ctx_tx(ctx);
+ if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW)
+ tls_sw_strparser_done(ctx);
+ if (ctx->rx_conf == TLS_SW)
+ tls_sw_free_ctx_rx(ctx);
+ ctx->sk_proto_close(sk, timeout);
+
if (free_ctx)
tls_ctx_free(ctx);
}
{
#endif
rc = tls_set_sw_offload(sk, ctx, 1);
+ if (rc)
+ goto err_crypto_info;
conf = TLS_SW;
}
} else {
{
#endif
rc = tls_set_sw_offload(sk, ctx, 0);
+ if (rc)
+ goto err_crypto_info;
conf = TLS_SW;
}
+ tls_sw_strparser_arm(sk, ctx);
}
- if (rc)
- goto err_crypto_info;
-
if (tx)
ctx->tx_conf = conf;
else
ctx->setsockopt = sk->sk_prot->setsockopt;
ctx->getsockopt = sk->sk_prot->getsockopt;
ctx->sk_proto_close = sk->sk_prot->close;
+ ctx->unhash = sk->sk_prot->unhash;
return ctx;
}
prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash;
prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash;
- prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close;
}
static int tls_init(struct sock *sk)
int rc = 0;
if (tls_hw_prot(sk))
- goto out;
+ return 0;
/* The TLS ulp is currently supported only for TCP sockets
* in ESTABLISHED state.
if (sk->sk_state != TCP_ESTABLISHED)
return -ENOTSUPP;
+ tls_build_proto(sk);
+
/* allocate tls context */
+ write_lock_bh(&sk->sk_callback_lock);
ctx = create_ctx(sk);
if (!ctx) {
rc = -ENOMEM;
goto out;
}
- tls_build_proto(sk);
ctx->tx_conf = TLS_BASE;
ctx->rx_conf = TLS_BASE;
+ ctx->sk_proto = sk->sk_prot;
update_sk_prot(sk, ctx);
out:
+ write_unlock_bh(&sk->sk_callback_lock);
return rc;
}
+static void tls_update(struct sock *sk, struct proto *p)
+{
+ struct tls_context *ctx;
+
+ ctx = tls_get_ctx(sk);
+ if (likely(ctx)) {
+ ctx->sk_proto_close = p->close;
+ ctx->sk_proto = p;
+ } else {
+ sk->sk_prot = p;
+ }
+}
+
void tls_register_device(struct tls_device *device)
{
spin_lock_bh(&device_spinlock);
.name = "tls",
.owner = THIS_MODULE,
.init = tls_init,
+ .update = tls_update,
};
static int __init tls_register(void)
}
}
-void tls_sw_free_resources_tx(struct sock *sk)
+void tls_sw_cancel_work_tx(struct tls_context *tls_ctx)
+{
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
+
+ set_bit(BIT_TX_CLOSING, &ctx->tx_bitmask);
+ set_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask);
+ cancel_delayed_work_sync(&ctx->tx_work.work);
+}
+
+void tls_sw_release_resources_tx(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
if (atomic_read(&ctx->encrypt_pending))
crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
- release_sock(sk);
- cancel_delayed_work_sync(&ctx->tx_work.work);
- lock_sock(sk);
-
- /* Tx whatever records we can transmit and abandon the rest */
tls_tx_records(sk, -1);
/* Free up un-sent records in tx_list. First, free
crypto_free_aead(ctx->aead_send);
tls_free_open_rec(sk);
+}
+
+void tls_sw_free_ctx_tx(struct tls_context *tls_ctx)
+{
+ struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
kfree(ctx);
}
skb_queue_purge(&ctx->rx_list);
crypto_free_aead(ctx->aead_recv);
strp_stop(&ctx->strp);
- write_lock_bh(&sk->sk_callback_lock);
- sk->sk_data_ready = ctx->saved_data_ready;
- write_unlock_bh(&sk->sk_callback_lock);
- release_sock(sk);
- strp_done(&ctx->strp);
- lock_sock(sk);
+ /* If tls_sw_strparser_arm() was not called (cleanup paths)
+ * we still want to strp_stop(), but sk->sk_data_ready was
+ * never swapped.
+ */
+ if (ctx->saved_data_ready) {
+ write_lock_bh(&sk->sk_callback_lock);
+ sk->sk_data_ready = ctx->saved_data_ready;
+ write_unlock_bh(&sk->sk_callback_lock);
+ }
}
}
-void tls_sw_free_resources_rx(struct sock *sk)
+void tls_sw_strparser_done(struct tls_context *tls_ctx)
{
- struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- tls_sw_release_resources_rx(sk);
+ strp_done(&ctx->strp);
+}
+
+void tls_sw_free_ctx_rx(struct tls_context *tls_ctx)
+{
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
kfree(ctx);
}
+void tls_sw_free_resources_rx(struct sock *sk)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+ tls_sw_release_resources_rx(sk);
+ tls_sw_free_ctx_rx(tls_ctx);
+}
+
/* The work handler to transmitt the encrypted records in tx_list */
static void tx_work_handler(struct work_struct *work)
{
struct tx_work, work);
struct sock *sk = tx_work->sk;
struct tls_context *tls_ctx = tls_get_ctx(sk);
- struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
+ struct tls_sw_context_tx *ctx;
- if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
+ if (unlikely(!tls_ctx))
return;
+ ctx = tls_sw_ctx_tx(tls_ctx);
+ if (test_bit(BIT_TX_CLOSING, &ctx->tx_bitmask))
+ return;
+
+ if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
+ return;
lock_sock(sk);
tls_tx_records(sk, -1);
release_sock(sk);
}
}
+void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx)
+{
+ struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(tls_ctx);
+
+ write_lock_bh(&sk->sk_callback_lock);
+ rx_ctx->saved_data_ready = sk->sk_data_ready;
+ sk->sk_data_ready = tls_data_ready;
+ write_unlock_bh(&sk->sk_callback_lock);
+
+ strp_check_rcv(&rx_ctx->strp);
+}
+
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
cb.parse_msg = tls_read_size;
strp_init(&sw_ctx_rx->strp, sk, &cb);
-
- write_lock_bh(&sk->sk_callback_lock);
- sw_ctx_rx->saved_data_ready = sk->sk_data_ready;
- sk->sk_data_ready = tls_data_ready;
- write_unlock_bh(&sk->sk_callback_lock);
-
- strp_check_rcv(&sw_ctx_rx->strp);
}
goto out;
lock_sock(sk);
hvs_do_close_lock_held(vsock_sk(sk), true);
release_sock(sk);
+
+ /* Release the refcnt for the channel that's opened in
+ * hvs_open_connection().
+ */
+ sock_put(sk);
}
static void hvs_open_connection(struct vmbus_channel *chan)
}
set_per_channel_state(chan, conn_from_host ? new : sk);
+
+ /* This reference will be dropped by hvs_close_connection(). */
+ sock_hold(conn_from_host ? new : sk);
vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
/* Set the pending send size to max packet size to always get
}
break;
case NETDEV_PRE_UP:
- if (!(wdev->wiphy->interface_modes & BIT(wdev->iftype)) &&
- !(wdev->iftype == NL80211_IFTYPE_AP_VLAN &&
- rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP &&
- wdev->use_4addr))
+ if (!cfg80211_iftype_allowed(wdev->wiphy, wdev->iftype,
+ wdev->use_4addr, 0))
return notifier_from_errno(-EOPNOTSUPP);
if (rfkill_blocked(rdev->rfkill))
return err;
}
- if (!(rdev->wiphy.interface_modes & (1 << type)) &&
- !(type == NL80211_IFTYPE_AP_VLAN && params.use_4addr &&
- rdev->wiphy.flags & WIPHY_FLAG_4ADDR_AP))
+ if (!cfg80211_iftype_allowed(&rdev->wiphy, type, params.use_4addr, 0))
return -EOPNOTSUPP;
err = nl80211_parse_mon_options(rdev, type, info, ¶ms);
/* When last_request->processed becomes true this will be rescheduled */
if (lr && !lr->processed) {
- reg_process_hint(lr);
+ pr_debug("Pending regulatory request, waiting for it to be processed...\n");
return;
}
switch (params->cipher) {
case WLAN_CIPHER_SUITE_TKIP:
+ /* Extended Key ID can only be used with CCMP/GCMP ciphers */
+ if ((pairwise && key_idx) ||
+ params->mode != NL80211_KEY_RX_TX)
+ return -EINVAL;
+ break;
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
case WLAN_CIPHER_SUITE_GCMP:
case WLAN_CIPHER_SUITE_GCMP_256:
- /* IEEE802.11-2016 allows only 0 and - when using Extended Key
- * ID - 1 as index for pairwise keys.
+ /* IEEE802.11-2016 allows only 0 and - when supporting
+ * Extended Key ID - 1 as index for pairwise keys.
* @NL80211_KEY_NO_TX is only allowed for pairwise keys when
* the driver supports Extended Key ID.
* @NL80211_KEY_SET_TX can't be set when installing and
* validating a key.
*/
- if (params->mode == NL80211_KEY_NO_TX) {
- if (!wiphy_ext_feature_isset(&rdev->wiphy,
- NL80211_EXT_FEATURE_EXT_KEY_ID))
- return -EINVAL;
- else if (!pairwise || key_idx < 0 || key_idx > 1)
+ if ((params->mode == NL80211_KEY_NO_TX && !pairwise) ||
+ params->mode == NL80211_KEY_SET_TX)
+ return -EINVAL;
+ if (wiphy_ext_feature_isset(&rdev->wiphy,
+ NL80211_EXT_FEATURE_EXT_KEY_ID)) {
+ if (pairwise && (key_idx < 0 || key_idx > 1))
return -EINVAL;
- } else if ((pairwise && key_idx) ||
- params->mode == NL80211_KEY_SET_TX) {
+ } else if (pairwise && key_idx) {
return -EINVAL;
}
break;
for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
num_interfaces += params->iftype_num[iftype];
if (params->iftype_num[iftype] > 0 &&
- !(wiphy->software_iftypes & BIT(iftype)))
+ !cfg80211_iftype_allowed(wiphy, iftype, 0, 1))
used_iftypes |= BIT(iftype);
}
return -ENOMEM;
for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) {
- if (wiphy->software_iftypes & BIT(iftype))
+ if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1))
continue;
for (j = 0; j < c->n_limits; j++) {
all_iftypes |= limits[j].types;
return max_vht_nss;
}
EXPORT_SYMBOL(ieee80211_get_vht_max_nss);
+
+bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype,
+ bool is_4addr, u8 check_swif)
+
+{
+ bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN;
+
+ switch (check_swif) {
+ case 0:
+ if (is_vlan && is_4addr)
+ return wiphy->flags & WIPHY_FLAG_4ADDR_AP;
+ return wiphy->interface_modes & BIT(iftype);
+ case 1:
+ if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan)
+ return wiphy->flags & WIPHY_FLAG_4ADDR_AP;
+ return wiphy->software_iftypes & BIT(iftype);
+ default:
+ break;
+ }
+
+ return false;
+}
+EXPORT_SYMBOL(cfg80211_iftype_allowed);
umem->pages = kcalloc(umem->npgs, sizeof(*umem->pages), GFP_KERNEL);
if (!umem->pages) {
err = -ENOMEM;
- goto out_account;
+ goto out_pin;
}
for (i = 0; i < umem->npgs; i++)
return 0;
+out_pin:
+ xdp_umem_unpin_pages(umem);
out_account:
xdp_umem_unaccount_pages(umem);
return err;
struct flowi4 *fl4 = &fl->u.ip4;
int oif = 0;
- if (skb_dst(skb))
+ if (skb_dst(skb) && skb_dst(skb)->dev)
oif = skb_dst(skb)->dev->ifindex;
memset(fl4, 0, sizeof(struct flowi4));
nexthdr = nh[nhoff];
- if (skb_dst(skb))
+ if (skb_dst(skb) && skb_dst(skb)->dev)
oif = skb_dst(skb)->dev->ifindex;
memset(fl6, 0, sizeof(struct flowi6));
if (argc != 2) {
printf(
- "Sintax: %s fbdev\n"
+ "Syntax: %s fbdev\n"
"Usually: /dev/fb0, /dev/fb1...\n", argv[0]);
return -1;
}
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Simple pci display device.
*
# printing commands
cmd = @set -e; $(echo-cmd) $(cmd_$(1))
-# Add $(obj)/ for paths that are not absolute
-objectify = $(foreach o,$(1),$(if $(filter /%,$(o)),$(o),$(obj)/$(o)))
-
###
# if_changed - execute command if any prerequisite is newer than
# target, or command line has changed
# $(cc-option,<flag>)
# Return y if the compiler supports <flag>, n otherwise
-cc-option = $(success,$(CC) -Werror $(1) -E -x c /dev/null -o /dev/null)
+cc-option = $(success,$(CC) -Werror $(CLANG_FLAGS) $(1) -E -x c /dev/null -o /dev/null)
# $(ld-option,<flag>)
# Return y if the linker supports <flag>, n otherwise
$(warning kbuild: Makefile.build is included improperly)
endif
+ifeq ($(MAKECMDGOALS)$(need-modorder),)
+ifneq ($(obj-m),)
+$(warning $(patsubst %.o,'%.ko',$(obj-m)) will not be built even though obj-m is specified.)
+$(warning You cannot use subdir-y/m to visit a module Makefile. Use obj-y/m instead.)
+endif
+endif
+
# ===========================================================================
ifneq ($(strip $(lib-y) $(lib-m) $(lib-)),)
PHONY += $(subdir-ym)
$(subdir-ym):
- $(Q)$(MAKE) $(build)=$@ need-builtin=$(if $(findstring $@,$(subdir-obj-y)),1)
+ $(Q)$(MAKE) $(build)=$@ \
+ need-builtin=$(if $(filter $@/built-in.a, $(subdir-obj-y)),1) \
+ need-modorder=$(if $(need-modorder),$(if $(filter $@/modules.order, $(modorder)),1))
# Add FORCE to the prequisites of a target to force it to be always rebuilt.
# ---------------------------------------------------------------------------
multi-used-y := $(sort $(foreach m,$(obj-y), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y))), $(m))))
multi-used-m := $(sort $(foreach m,$(obj-m), $(if $(strip $($(m:.o=-objs)) $($(m:.o=-y)) $($(m:.o=-m))), $(m))))
multi-used := $(multi-used-y) $(multi-used-m)
-single-used-m := $(sort $(filter-out $(multi-used-m),$(obj-m)))
# $(subdir-obj-y) is the list of objects in $(obj-y) which uses dir/ to
# tell kbuild to descend
subdir-obj-y := $(addprefix $(obj)/,$(subdir-obj-y))
real-obj-y := $(addprefix $(obj)/,$(real-obj-y))
real-obj-m := $(addprefix $(obj)/,$(real-obj-m))
-single-used-m := $(addprefix $(obj)/,$(single-used-m))
multi-used-m := $(addprefix $(obj)/,$(multi-used-m))
subdir-ym := $(addprefix $(obj)/,$(subdir-ym))
# symbols in the final module linking stage
# KBUILD_MODPOST_NOFINAL can be set to skip the final link of modules.
# This is solely useful to speed up test compiles
-PHONY := _modpost
-_modpost: __modpost
+
+PHONY := __modpost
+__modpost:
include include/config/auto.conf
include scripts/Kbuild.include
+kernelsymfile := $(objtree)/Module.symvers
+modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers
+
+MODPOST = scripts/mod/modpost \
+ $(if $(CONFIG_MODVERSIONS),-m) \
+ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \
+ $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \
+ $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \
+ $(if $(KBUILD_EXTMOD),$(addprefix -e ,$(KBUILD_EXTRA_SYMBOLS))) \
+ $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \
+ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \
+ $(if $(KBUILD_MODPOST_WARN),-w)
+
+ifdef MODPOST_VMLINUX
+
+__modpost: vmlinux.o
+
+quiet_cmd_modpost = MODPOST $@
+ cmd_modpost = $(MODPOST) $@
+
+PHONY += vmlinux.o
+vmlinux.o:
+ $(call cmd,modpost)
+
+else
+
# When building external modules load the Kbuild file to retrieve EXTRA_SYMBOLS info
ifneq ($(KBUILD_EXTMOD),)
include scripts/Makefile.lib
-kernelsymfile := $(objtree)/Module.symvers
-modulesymfile := $(firstword $(KBUILD_EXTMOD))/Module.symvers
-
-modorder := $(if $(KBUILD_EXTMOD),$(KBUILD_EXTMOD)/)modules.order
-
-# Step 1), find all modules listed in modules.order
-ifdef CONFIG_MODULES
-modules := $(sort $(shell cat $(modorder)))
-endif
+# find all modules listed in modules.order
+modules := $(sort $(shell cat $(MODORDER)))
# Stop after building .o files if NOFINAL is set. Makes compile tests quicker
-_modpost: $(if $(KBUILD_MODPOST_NOFINAL), $(modules:.ko:.o),$(modules))
-
-# Step 2), invoke modpost
-# Includes step 3,4
-modpost = scripts/mod/modpost \
- $(if $(CONFIG_MODVERSIONS),-m) \
- $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a,) \
- $(if $(KBUILD_EXTMOD),-i,-o) $(kernelsymfile) \
- $(if $(KBUILD_EXTMOD),-I $(modulesymfile)) \
- $(if $(KBUILD_EXTRA_SYMBOLS), $(patsubst %, -e %,$(KBUILD_EXTRA_SYMBOLS))) \
- $(if $(KBUILD_EXTMOD),-o $(modulesymfile)) \
- $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \
- $(if $(KBUILD_MODPOST_WARN),-w)
-
-MODPOST_OPT=$(subst -i,-n,$(filter -i,$(MAKEFLAGS)))
+__modpost: $(if $(KBUILD_MODPOST_NOFINAL), $(modules:.ko:.o),$(modules))
+ @:
-# We can go over command line length here, so be careful.
-quiet_cmd_modpost = MODPOST $(words $(filter-out vmlinux FORCE, $^)) modules
- cmd_modpost = sed 's/ko$$/o/' $(modorder) | $(modpost) $(MODPOST_OPT) -s -T -
-
-PHONY += __modpost
-__modpost: $(modules:.ko=.o) FORCE
- $(call cmd,modpost) $(wildcard vmlinux)
+MODPOST += $(subst -i,-n,$(filter -i,$(MAKEFLAGS))) -s -T - $(wildcard vmlinux)
-quiet_cmd_kernel-mod = MODPOST $@
- cmd_kernel-mod = $(modpost) $@
+# We can go over command line length here, so be careful.
+quiet_cmd_modpost = MODPOST $(words $(modules)) modules
+ cmd_modpost = sed 's/ko$$/o/' $(MODORDER) | $(MODPOST)
-vmlinux.o: FORCE
- $(call cmd,kernel-mod)
+PHONY += modules-modpost
+modules-modpost:
+ $(call cmd,modpost)
# Declare generated files as targets for modpost
-$(modules:.ko=.mod.c): __modpost ;
-
+$(modules:.ko=.mod.c): modules-modpost
# Step 5), compile all *.mod.c files
# optimization, we don't need to read them if the target does not
# exist, we will rebuild anyway in that case.
-cmd_files := $(wildcard $(foreach f,$(sort $(targets)),$(dir $(f)).$(notdir $(f)).cmd))
+existing-targets := $(wildcard $(sort $(targets)))
+
+-include $(foreach f,$(existing-targets),$(dir $(f)).$(notdir $(f)).cmd)
-ifneq ($(cmd_files),)
- include $(cmd_files)
endif
.PHONY: $(PHONY)
+// SPDX-License-Identifier: GPL-2.0-only
// Check if refcount_t type and API should be used
// instead of atomic_t type when dealing with refcounters
//
_VALID_LOG_LEVELS = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
# A kernel build generally has over 2000 entries in its compile_commands.json
-# database. If this code finds 500 or fewer, then warn the user that they might
+# database. If this code finds 300 or fewer, then warn the user that they might
# not have all the .cmd files, and they might need to compile the kernel.
-_LOW_COUNT_THRESHOLD = 500
+_LOW_COUNT_THRESHOLD = 300
def parse_arguments():
trap 'rm -f $OUTFILE $TMPFILE' EXIT
+# SPDX-License-Identifier with GPL variants must have "WITH Linux-syscall-note"
+if [ -n "$(sed -n -e "/SPDX-License-Identifier:.*GPL-/{/WITH Linux-syscall-note/!p}" $INFILE)" ]; then
+ echo "error: $INFILE: missing \"WITH Linux-syscall-note\" for SPDX-License-Identifier" >&2
+ exit 1
+fi
+
sed -E -e '
s/([[:space:](])(__user|__force|__iomem)[[:space:]]/\1/g
s/__attribute_const__([[:space:]]|$)/\1/g
const char *str;
char tmpname[PATH_MAX + 1], oldname[PATH_MAX + 1];
char *env;
+ int i;
bool need_newline = false;
if (!name)
}
fclose(out);
+ for_all_symbols(i, sym)
+ sym->flags &= ~SYMBOL_WRITTEN;
+
if (*tmpname) {
if (is_same(name, tmpname)) {
conf_message("No change to %s", name);
modpost_link vmlinux.o
# modpost vmlinux.o to check for section mismatches
-${MAKE} -f "${srctree}/scripts/Makefile.modpost" vmlinux.o
+${MAKE} -f "${srctree}/scripts/Makefile.modpost" MODPOST_VMLINUX=1
info MODINFO modules.builtin.modinfo
${OBJCOPY} -j .modinfo -O binary vmlinux.o modules.builtin.modinfo
foreach my $prog (sort keys %missing) {
my $is_optional = $missing{$prog};
+ # At least on some LTS distros like CentOS 7, texlive doesn't
+ # provide all packages we need. When such distros are
+ # detected, we have to disable PDF output.
+ #
+ # So, we need to ignore the packages that distros would
+ # need for LaTeX to work
+ if ($is_optional == 2 && !$pdf) {
+ $optional--;
+ next;
+ }
+
if ($is_optional) {
print "Warning: better to also install \"$prog\".\n";
} else {
if ($pdf) {
check_missing_file("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
- "fonts-dejavu", 1);
+ "fonts-dejavu", 2);
+
+ check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc",
+ "fonts-noto-cjk", 2);
}
- check_program("dvipng", 1) if ($pdf);
+ check_program("dvipng", 2) if ($pdf);
check_missing(\%map);
return if (!$need && !$optional);
my @fedora_tex_pkgs = (
"texlive-collection-fontsrecommended",
"texlive-collection-latex",
+ "texlive-xecjk",
"dejavu-sans-fonts",
"dejavu-serif-fonts",
"dejavu-sans-mono-fonts",
#
# Checks valid for RHEL/CentOS version 7.x.
#
- if (! $system_release =~ /Fedora/) {
+ my $old = 0;
+ my $rel;
+ $rel = $1 if ($system_release =~ /release\s+(\d+)/);
+
+ if (!($system_release =~ /Fedora/)) {
$map{"virtualenv"} = "python-virtualenv";
- }
- my $release;
+ if ($rel && $rel < 8) {
+ $old = 1;
+ $pdf = 0;
+
+ printf("Note: texlive packages on RHEL/CENTOS <= 7 are incomplete. Can't support PDF output\n");
+ printf("If you want to build PDF, please read:\n");
+ printf("\thttps://www.systutorials.com/241660/how-to-install-tex-live-on-centos-7-linux/\n");
+ }
+ } else {
+ if ($rel && $rel < 26) {
+ $old = 1;
+ }
+ }
+ if (!$rel) {
+ printf("Couldn't identify release number\n");
+ $old = 1;
+ $pdf = 0;
+ }
- $release = $1 if ($system_release =~ /Fedora\s+release\s+(\d+)/);
+ if ($pdf) {
+ check_missing_file("/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc",
+ "google-noto-sans-cjk-ttc-fonts", 2);
+ }
- check_rpm_missing(\@fedora26_opt_pkgs, 1) if ($pdf && $release >= 26);
- check_rpm_missing(\@fedora_tex_pkgs, 1) if ($pdf);
- check_missing_tex(1) if ($pdf);
+ check_rpm_missing(\@fedora26_opt_pkgs, 2) if ($pdf && !$old);
+ check_rpm_missing(\@fedora_tex_pkgs, 2) if ($pdf);
+ check_missing_tex(2) if ($pdf);
check_missing(\%map);
return if (!$need && !$optional);
- if ($release >= 18) {
+ if (!$old) {
# dnf, for Fedora 18+
printf("You should run:\n\n\tsudo dnf install -y $install\n");
} else {
"texlive-zapfding",
);
- check_rpm_missing(\@suse_tex_pkgs, 1) if ($pdf);
- check_missing_tex(1) if ($pdf);
+ $map{"latexmk"} = "texlive-latexmk-bin";
+
+ # FIXME: add support for installing CJK fonts
+ #
+ # I tried hard, but was unable to find a way to install
+ # "Noto Sans CJK SC" on openSUSE
+
+ check_rpm_missing(\@suse_tex_pkgs, 2) if ($pdf);
+ check_missing_tex(2) if ($pdf);
check_missing(\%map);
return if (!$need && !$optional);
"texlive-fontsextra",
);
- check_rpm_missing(\@tex_pkgs, 1) if ($pdf);
+ $map{"latexmk"} = "texlive-collection-basic";
+
+ if ($pdf) {
+ check_missing_file("/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc",
+ "google-noto-sans-cjk-ttc-fonts", 2);
+ }
+
+ check_rpm_missing(\@tex_pkgs, 2) if ($pdf);
check_missing(\%map);
return if (!$need && !$optional);
"texlive-latexextra",
"ttf-dejavu",
);
- check_pacman_missing(\@archlinux_tex_pkgs, 1) if ($pdf);
+ check_pacman_missing(\@archlinux_tex_pkgs, 2) if ($pdf);
+
+ if ($pdf) {
+ check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc",
+ "noto-fonts-cjk", 2);
+ }
+
check_missing(\%map);
return if (!$need && !$optional);
);
check_missing_file("/usr/share/fonts/dejavu/DejaVuSans.ttf",
- "media-fonts/dejavu", 1) if ($pdf);
+ "media-fonts/dejavu", 2) if ($pdf);
+
+ if ($pdf) {
+ check_missing_file("/usr/share/fonts/noto-cjk/NotoSansCJKsc-Regular.otf",
+ "media-fonts/noto-cjk", 2);
+ }
check_missing(\%map);
return if (!$need && !$optional);
printf("You should run:\n\n");
- printf("\tsudo su -c 'echo \"media-gfx/imagemagick svg png\" > /etc/portage/package.use/imagemagick'\n");
- printf("\tsudo su -c 'echo \"media-gfx/graphviz cairo pdf\" > /etc/portage/package.use/graphviz'\n");
+
+ my $imagemagick = "media-gfx/imagemagick svg png";
+ my $cairo = "media-gfx/graphviz cairo pdf";
+ my $portage_imagemagick = "/etc/portage/package.use/imagemagick";
+ my $portage_cairo = "/etc/portage/package.use/graphviz";
+
+ if (qx(cat $portage_imagemagick) ne "$imagemagick\n") {
+ printf("\tsudo su -c 'echo \"$imagemagick\" > $portage_imagemagick'\n")
+ }
+ if (qx(cat $portage_cairo) ne "$cairo\n") {
+ printf("\tsudo su -c 'echo \"$cairo\" > $portage_cairo'\n");
+ }
+
printf("\tsudo emerge --ask $install\n");
}
my %map = (
"sphinx-build" => "sphinx"
);
- check_missing_tex(1) if ($pdf);
+ check_missing_tex(2) if ($pdf);
check_missing(\%map);
print "I don't know distro $system_release.\n";
print "So, I can't provide you a hint with the install procedure.\n";
check_program("make", 0);
check_program("gcc", 0);
check_python_module("sphinx_rtd_theme", 1) if (!$virtualenv);
- check_program("xelatex", 1) if ($pdf);
check_program("dot", 1);
check_program("convert", 1);
- check_program("rsvg-convert", 1) if ($pdf);
- check_program("latexmk", 1) if ($pdf);
+
+ # Extra PDF files - should use 2 for is_optional
+ check_program("xelatex", 2) if ($pdf);
+ check_program("rsvg-convert", 2) if ($pdf);
+ check_program("latexmk", 2) if ($pdf);
check_distros();
config GCC_PLUGIN_STRUCTLEAK_BYREF
bool "zero-init structs passed by reference (strong)"
depends on GCC_PLUGINS
+ depends on !(KASAN && KASAN_STACK=1)
select GCC_PLUGIN_STRUCTLEAK
help
Zero-initialize any structures on the stack that may
exposures, like CVE-2017-1000410:
https://git.kernel.org/linus/06e7e776ca4d3654
+ As a side-effect, this keeps a lot of variables on the
+ stack that can otherwise be optimized out, so combining
+ this with CONFIG_KASAN_STACK can lead to a stack overflow
+ and is disallowed.
+
config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL
bool "zero-init anything passed by reference (very strong)"
depends on GCC_PLUGINS
+ depends on !(KASAN && KASAN_STACK=1)
select GCC_PLUGIN_STRUCTLEAK
help
Zero-initialize any stack variables that may be passed
key = check_cached_key(&ctx);
if (key)
- return key;
+ goto error_free;
/* search all the process keyrings for a key */
rcu_read_lock();
{
struct request_key_auth *rka = dereference_key_rcu(key);
+ if (!rka)
+ return;
+
seq_puts(m, "key:");
seq_puts(m, key->description);
if (key_is_positive(key))
size_t datalen;
long ret;
+ if (!rka)
+ return -EKEYREVOKED;
+
datalen = rka->callout_len;
ret = datalen;
static int __init init_digests(void)
{
- u8 digest[TPM_MAX_DIGEST_SIZE];
- int ret;
- int i;
-
- ret = tpm_get_random(chip, digest, TPM_MAX_DIGEST_SIZE);
- if (ret < 0)
- return ret;
- if (ret < TPM_MAX_DIGEST_SIZE)
- return -EFAULT;
-
digests = kcalloc(chip->nr_allocated_banks, sizeof(*digests),
GFP_KERNEL);
if (!digests)
return -ENOMEM;
- for (i = 0; i < chip->nr_allocated_banks; i++)
- memcpy(digests[i].digest, digest, TPM_MAX_DIGEST_SIZE);
-
return 0;
}
return v;
}
+static int (*destroy_f[SYM_NUM]) (void *key, void *datum, void *datap);
+
/*
* Initialize a policy database structure.
*/
out:
hashtab_destroy(p->filename_trans);
hashtab_destroy(p->range_tr);
- for (i = 0; i < SYM_NUM; i++)
+ for (i = 0; i < SYM_NUM; i++) {
+ hashtab_map(p->symtab[i].table, destroy_f[i], NULL);
hashtab_destroy(p->symtab[i].table);
+ }
return rc;
}
++count;
}
+ /* bail out if we already reached max entries */
+ rc = -EOVERFLOW;
+ if (count >= SIDTAB_MAX)
+ goto out_unlock;
+
/* insert context into new entry */
rc = -ENOMEM;
dst = sidtab_do_lookup(s, count, 1);
vendor_id);
ret = device_add(&codec->dev);
- if (ret)
- goto err_free_codec;
+ if (ret) {
+ put_device(&codec->dev);
+ return ret;
+ }
return 0;
-err_free_codec:
- of_node_put(codec->dev.of_node);
- put_device(&codec->dev);
- kfree(codec);
- ac97_ctrl->codecs[idx] = NULL;
-
- return ret;
}
unsigned int snd_ac97_bus_scan_one(struct ac97_controller *adrv,
stream->metadata_set = false;
stream->next_track = false;
- if (stream->direction == SND_COMPRESS_PLAYBACK)
- stream->runtime->state = SNDRV_PCM_STATE_SETUP;
- else
- stream->runtime->state = SNDRV_PCM_STATE_PREPARED;
+ stream->runtime->state = SNDRV_PCM_STATE_SETUP;
} else {
return -EPERM;
}
{
int retval;
- if (stream->runtime->state != SNDRV_PCM_STATE_PREPARED)
+ switch (stream->runtime->state) {
+ case SNDRV_PCM_STATE_SETUP:
+ if (stream->direction != SND_COMPRESS_CAPTURE)
+ return -EPERM;
+ break;
+ case SNDRV_PCM_STATE_PREPARED:
+ break;
+ default:
return -EPERM;
+ }
+
retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_START);
if (!retval)
stream->runtime->state = SNDRV_PCM_STATE_RUNNING;
{
int retval;
- if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
- stream->runtime->state == SNDRV_PCM_STATE_SETUP)
+ switch (stream->runtime->state) {
+ case SNDRV_PCM_STATE_OPEN:
+ case SNDRV_PCM_STATE_SETUP:
+ case SNDRV_PCM_STATE_PREPARED:
return -EPERM;
+ default:
+ break;
+ }
+
retval = stream->ops->trigger(stream, SNDRV_PCM_TRIGGER_STOP);
if (!retval) {
snd_compr_drain_notify(stream);
{
int retval;
- if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
- stream->runtime->state == SNDRV_PCM_STATE_SETUP)
+ switch (stream->runtime->state) {
+ case SNDRV_PCM_STATE_OPEN:
+ case SNDRV_PCM_STATE_SETUP:
+ case SNDRV_PCM_STATE_PREPARED:
+ case SNDRV_PCM_STATE_PAUSED:
return -EPERM;
+ case SNDRV_PCM_STATE_XRUN:
+ return -EPIPE;
+ default:
+ break;
+ }
retval = stream->ops->trigger(stream, SND_COMPR_TRIGGER_DRAIN);
if (retval) {
if (stream->runtime->state != SNDRV_PCM_STATE_RUNNING)
return -EPERM;
+ /* next track doesn't have any meaning for capture streams */
+ if (stream->direction == SND_COMPRESS_CAPTURE)
+ return -EPERM;
+
/* you can signal next track if this is intended to be a gapless stream
* and current track metadata is set
*/
static int snd_compr_partial_drain(struct snd_compr_stream *stream)
{
int retval;
- if (stream->runtime->state == SNDRV_PCM_STATE_PREPARED ||
- stream->runtime->state == SNDRV_PCM_STATE_SETUP)
+
+ switch (stream->runtime->state) {
+ case SNDRV_PCM_STATE_OPEN:
+ case SNDRV_PCM_STATE_SETUP:
+ case SNDRV_PCM_STATE_PREPARED:
+ case SNDRV_PCM_STATE_PAUSED:
+ return -EPERM;
+ case SNDRV_PCM_STATE_XRUN:
+ return -EPIPE;
+ default:
+ break;
+ }
+
+ /* partial drain doesn't have any meaning for capture streams */
+ if (stream->direction == SND_COMPRESS_CAPTURE)
return -EPERM;
+
/* stream can be drained only when next track has been signalled */
if (stream->next_track == false)
return -EPERM;
spin_lock_init(&group->lock);
mutex_init(&group->mutex);
INIT_LIST_HEAD(&group->substreams);
- refcount_set(&group->refs, 0);
+ refcount_set(&group->refs, 1);
}
/* define group lock helpers */
if (!group)
return;
- do_free = refcount_dec_and_test(&group->refs) &&
- list_empty(&group->substreams);
+ do_free = refcount_dec_and_test(&group->refs);
snd_pcm_group_unlock(group, substream->pcm->nonatomic);
if (do_free)
kfree(group);
if (!to_check)
break; /* all drained */
init_waitqueue_entry(&wait, current);
+ set_current_state(TASK_INTERRUPTIBLE);
add_wait_queue(&to_check->sleep, &wait);
snd_pcm_stream_unlock_irq(substream);
if (runtime->no_period_wakeup)
}
tout = msecs_to_jiffies(tout * 1000);
}
- tout = schedule_timeout_interruptible(tout);
+ tout = schedule_timeout(tout);
snd_pcm_stream_lock_irq(substream);
group = snd_pcm_stream_group_ref(substream);
snd_pcm_group_lock_irq(target_group, nonatomic);
snd_pcm_stream_lock(substream1);
snd_pcm_group_assign(substream1, target_group);
+ refcount_inc(&target_group->refs);
snd_pcm_stream_unlock(substream1);
snd_pcm_group_unlock_irq(target_group, nonatomic);
_end:
snd_pcm_group_lock_irq(group, nonatomic);
relink_to_local(substream);
+ refcount_dec(&group->refs);
/* detach the last stream, too */
if (list_is_singular(&group->substreams)) {
relink_to_local(list_first_entry(&group->substreams,
struct snd_pcm_substream,
link_list));
- do_free = !refcount_read(&group->refs);
+ do_free = refcount_dec_and_test(&group->refs);
}
snd_pcm_group_unlock_irq(group, nonatomic);
if (cptr->type == USER_CLIENT) {
info->input_pool = cptr->data.user.fifo_pool_size;
info->input_free = info->input_pool;
- if (cptr->data.user.fifo)
- info->input_free = snd_seq_unused_cells(cptr->data.user.fifo->pool);
+ info->input_free = snd_seq_fifo_unused_cells(cptr->data.user.fifo);
} else {
info->input_pool = 0;
info->input_free = 0;
return 0;
}
+
+/* get the number of unused cells safely */
+int snd_seq_fifo_unused_cells(struct snd_seq_fifo *f)
+{
+ unsigned long flags;
+ int cells;
+
+ if (!f)
+ return 0;
+
+ snd_use_lock_use(&f->use_lock);
+ spin_lock_irqsave(&f->lock, flags);
+ cells = snd_seq_unused_cells(f->pool);
+ spin_unlock_irqrestore(&f->lock, flags);
+ snd_use_lock_free(&f->use_lock);
+ return cells;
+}
/* resize pool in fifo */
int snd_seq_fifo_resize(struct snd_seq_fifo *f, int poolsize);
+/* get the number of unused cells safely */
+int snd_seq_fifo_unused_cells(struct snd_seq_fifo *f);
#endif
unsigned int channels = params_channels(hw_params);
mutex_lock(&oxfw->mutex);
- err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->tx_stream,
+ err = snd_oxfw_stream_reserve_duplex(oxfw, &oxfw->rx_stream,
rate, channels);
if (err >= 0)
++oxfw->substreams_count;
packets_per_page = PAGE_SIZE / packet_size;
if (WARN_ON(!packets_per_page)) {
err = -EINVAL;
- goto error;
+ goto err_packets;
}
pages = DIV_ROUND_UP(count, packets_per_page);
if (!acomp)
return -ENODEV;
if (!acomp->ops) {
- request_module("i915");
- /* 60s timeout */
- wait_for_completion_timeout(&bind_complete,
- msecs_to_jiffies(60 * 1000));
+ if (!IS_ENABLED(CONFIG_MODULES) ||
+ !request_module("i915")) {
+ /* 60s timeout */
+ wait_for_completion_timeout(&bind_complete,
+ msecs_to_jiffies(60 * 1000));
+ }
}
if (!acomp->ops) {
dev_info(bus->dev, "couldn't bind with audio component\n");
while (id >= 0) {
const struct hda_fixup *fix = codec->fixup_list + id;
+ if (++depth > 10)
+ break;
if (fix->chained_before)
apply_fixup(codec, fix->chain_id, action, depth + 1);
}
if (!fix->chained || fix->chained_before)
break;
- if (++depth > 10)
- break;
id = fix->chain_id;
}
}
static int hda_codec_force_resume(struct device *dev)
{
struct hda_codec *codec = dev_to_hda_codec(dev);
- bool forced_resume = !codec->relaxed_resume;
+ bool forced_resume = !codec->relaxed_resume && codec->jacktbl.used;
int ret;
/* The get/put pair below enforces the runtime resume even if the
}
runtime->private_data = azx_dev;
- if (chip->gts_present)
- azx_pcm_hw.info = azx_pcm_hw.info |
- SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME;
-
runtime->hw = azx_pcm_hw;
+ if (chip->gts_present)
+ runtime->hw.info |= SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME;
runtime->hw.channels_min = hinfo->channels_min;
runtime->hw.channels_max = hinfo->channels_max;
runtime->hw.formats = hinfo->formats;
20,
178000000);
+ /* by some reason, the playback stream stalls on PulseAudio with
+ * tsched=1 when a capture stream triggers. Until we figure out the
+ * real cause, disable tsched mode by telling the PCM info flag.
+ */
+ if (chip->driver_caps & AZX_DCAPS_AMD_WORKAROUND)
+ runtime->hw.info |= SNDRV_PCM_INFO_BATCH;
+
if (chip->align_buffer_size)
/* constrain buffer sizes to be multiple of 128
bytes. This is more efficient in terms of memory
/* 14 unused */
#define AZX_DCAPS_CTX_WORKAROUND (1 << 15) /* X-Fi workaround */
#define AZX_DCAPS_POSFIX_LPIB (1 << 16) /* Use LPIB as default */
-/* 17 unused */
+#define AZX_DCAPS_AMD_WORKAROUND (1 << 17) /* AMD-specific workaround */
#define AZX_DCAPS_NO_64BIT (1 << 18) /* No 64bit address */
#define AZX_DCAPS_SYNC_WRITE (1 << 19) /* sync each cmd write */
#define AZX_DCAPS_OLD_SSYNC (1 << 20) /* Old SSYNC reg for ICH */
if (spec->init_hook)
spec->init_hook(codec);
- snd_hda_apply_verbs(codec);
+ if (!spec->skip_verbs)
+ snd_hda_apply_verbs(codec);
init_multi_out(codec);
init_extra_out(codec);
}
EXPORT_SYMBOL_GPL(snd_hda_gen_free);
+/**
+ * snd_hda_gen_reboot_notify - Make codec enter D3 before rebooting
+ * @codec: the HDA codec
+ *
+ * This can be put as patch_ops reboot_notify function.
+ */
+void snd_hda_gen_reboot_notify(struct hda_codec *codec)
+{
+ /* Make the codec enter D3 to avoid spurious noises from the internal
+ * speaker during (and after) reboot
+ */
+ snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3);
+ snd_hda_codec_write(codec, codec->core.afg, 0,
+ AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
+ msleep(10);
+}
+EXPORT_SYMBOL_GPL(snd_hda_gen_reboot_notify);
+
#ifdef CONFIG_PM
/**
* snd_hda_gen_check_power_status - check the loopback power save state
.init = snd_hda_gen_init,
.free = snd_hda_gen_free,
.unsol_event = snd_hda_jack_unsol_event,
+ .reboot_notify = snd_hda_gen_reboot_notify,
#ifdef CONFIG_PM
.check_power_status = snd_hda_gen_check_power_status,
#endif
err = snd_hda_parse_pin_defcfg(codec, &spec->autocfg, NULL, 0);
if (err < 0)
- return err;
+ goto error;
err = snd_hda_gen_parse_auto_config(codec, &spec->autocfg);
if (err < 0)
unsigned int indep_hp_enabled:1; /* independent HP enabled */
unsigned int have_aamix_ctl:1;
unsigned int hp_mic_jack_modes:1;
+ unsigned int skip_verbs:1; /* don't apply verbs at snd_hda_gen_init() */
/* additional mute flags (only effective with auto_mute_via_amp=1) */
u64 mute_bits;
struct auto_pin_cfg *cfg);
int snd_hda_gen_build_controls(struct hda_codec *codec);
int snd_hda_gen_build_pcms(struct hda_codec *codec);
+void snd_hda_gen_reboot_notify(struct hda_codec *codec);
/* standard jack event callbacks */
void snd_hda_gen_hp_automute(struct hda_codec *codec,
POS_FIX_VIACOMBO,
POS_FIX_COMBO,
POS_FIX_SKL,
+ POS_FIX_FIFO,
};
/* Defines for ATI HD Audio support in SB450 south bridge */
MODULE_PARM_DESC(model, "Use the given board model.");
module_param_array(position_fix, int, NULL, 0444);
MODULE_PARM_DESC(position_fix, "DMA pointer read method."
- "(-1 = system default, 0 = auto, 1 = LPIB, 2 = POSBUF, 3 = VIACOMBO, 4 = COMBO, 5 = SKL+).");
+ "(-1 = system default, 0 = auto, 1 = LPIB, 2 = POSBUF, 3 = VIACOMBO, 4 = COMBO, 5 = SKL+, 6 = FIFO).");
module_param_array(bdl_pos_adj, int, NULL, 0644);
MODULE_PARM_DESC(bdl_pos_adj, "BDL position adjustment offset.");
module_param_array(probe_mask, int, NULL, 0444);
#define AZX_DCAPS_INTEL_SKYLAKE \
(AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
+ AZX_DCAPS_SYNC_WRITE |\
AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT)
-#define AZX_DCAPS_INTEL_BROXTON \
- (AZX_DCAPS_INTEL_PCH_BASE | AZX_DCAPS_PM_RUNTIME |\
- AZX_DCAPS_SEPARATE_STREAM_TAG | AZX_DCAPS_I915_COMPONENT)
+#define AZX_DCAPS_INTEL_BROXTON AZX_DCAPS_INTEL_SKYLAKE
/* quirks for ATI SB / AMD Hudson */
#define AZX_DCAPS_PRESET_ATI_SB \
#define AZX_DCAPS_PRESET_ATI_HDMI_NS \
(AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_SNOOP_OFF)
+/* quirks for AMD SB */
+#define AZX_DCAPS_PRESET_AMD_SB \
+ (AZX_DCAPS_NO_TCSEL | AZX_DCAPS_SYNC_WRITE | AZX_DCAPS_AMD_WORKAROUND |\
+ AZX_DCAPS_SNOOP_TYPE(ATI) | AZX_DCAPS_PM_RUNTIME)
+
/* quirks for Nvidia */
#define AZX_DCAPS_PRESET_NVIDIA \
(AZX_DCAPS_NO_MSI | AZX_DCAPS_CORBRP_SELF_CLEAR |\
return bound_pos + mod_dma_pos;
}
+#define AMD_FIFO_SIZE 32
+
+/* get the current DMA position with FIFO size correction */
+static unsigned int azx_get_pos_fifo(struct azx *chip, struct azx_dev *azx_dev)
+{
+ struct snd_pcm_substream *substream = azx_dev->core.substream;
+ struct snd_pcm_runtime *runtime = substream->runtime;
+ unsigned int pos, delay;
+
+ pos = snd_hdac_stream_get_pos_lpib(azx_stream(azx_dev));
+ if (!runtime)
+ return pos;
+
+ runtime->delay = AMD_FIFO_SIZE;
+ delay = frames_to_bytes(runtime, AMD_FIFO_SIZE);
+ if (azx_dev->insufficient) {
+ if (pos < delay) {
+ delay = pos;
+ runtime->delay = bytes_to_frames(runtime, pos);
+ } else {
+ azx_dev->insufficient = 0;
+ }
+ }
+
+ /* correct the DMA position for capture stream */
+ if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+ if (pos < delay)
+ pos += azx_dev->core.bufsize;
+ pos -= delay;
+ }
+
+ return pos;
+}
+
+static int azx_get_delay_from_fifo(struct azx *chip, struct azx_dev *azx_dev,
+ unsigned int pos)
+{
+ struct snd_pcm_substream *substream = azx_dev->core.substream;
+
+ /* just read back the calculated value in the above */
+ return substream->runtime->delay;
+}
+
static unsigned int azx_skl_get_dpib_pos(struct azx *chip,
struct azx_dev *azx_dev)
{
case POS_FIX_VIACOMBO:
case POS_FIX_COMBO:
case POS_FIX_SKL:
+ case POS_FIX_FIFO:
return fix;
}
dev_dbg(chip->card->dev, "Using VIACOMBO position fix\n");
return POS_FIX_VIACOMBO;
}
+ if (chip->driver_caps & AZX_DCAPS_AMD_WORKAROUND) {
+ dev_dbg(chip->card->dev, "Using FIFO position fix\n");
+ return POS_FIX_FIFO;
+ }
if (chip->driver_caps & AZX_DCAPS_POSFIX_LPIB) {
dev_dbg(chip->card->dev, "Using LPIB position fix\n");
return POS_FIX_LPIB;
[POS_FIX_VIACOMBO] = azx_via_get_position,
[POS_FIX_COMBO] = azx_get_pos_lpib,
[POS_FIX_SKL] = azx_get_pos_skl,
+ [POS_FIX_FIFO] = azx_get_pos_fifo,
};
chip->get_position[0] = chip->get_position[1] = callbacks[fix];
azx_get_delay_from_lpib;
}
+ if (fix == POS_FIX_FIFO)
+ chip->get_delay[0] = chip->get_delay[1] =
+ azx_get_delay_from_fifo;
}
/*
/* AMD Hudson */
{ PCI_DEVICE(0x1022, 0x780d),
.driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
+ /* AMD, X370 & co */
+ { PCI_DEVICE(0x1022, 0x1457),
+ .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB },
+ /* AMD, X570 & co */
+ { PCI_DEVICE(0x1022, 0x1487),
+ .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_AMD_SB },
/* AMD Stoney */
{ PCI_DEVICE(0x1022, 0x157a),
.driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB |
SND_PCI_QUIRK(0x1028, 0x0708, "Alienware 15 R2 2016", QUIRK_ALIENWARE),
SND_PCI_QUIRK(0x1102, 0x0010, "Sound Blaster Z", QUIRK_SBZ),
SND_PCI_QUIRK(0x1102, 0x0023, "Sound Blaster Z", QUIRK_SBZ),
+ SND_PCI_QUIRK(0x1102, 0x0027, "Sound Blaster Z", QUIRK_SBZ),
SND_PCI_QUIRK(0x1102, 0x0033, "Sound Blaster ZxR", QUIRK_SBZ),
SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI),
{
struct conexant_spec *spec = codec->spec;
- switch (codec->core.vendor_id) {
- case 0x14f12008: /* CX8200 */
- case 0x14f150f2: /* CX20722 */
- case 0x14f150f4: /* CX20724 */
- break;
- default:
- return;
- }
-
/* Turn the problematic codec into D3 to avoid spurious noises
from the internal speaker during (and after) reboot */
cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, false);
-
- snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3);
- snd_hda_codec_write(codec, codec->core.afg, 0,
- AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
- msleep(10);
+ snd_hda_gen_reboot_notify(codec);
}
static void cx_auto_free(struct hda_codec *codec)
/* update LED status via GPIO */
static void cxt_update_gpio_led(struct hda_codec *codec, unsigned int mask,
- bool enabled)
+ bool led_on)
{
struct conexant_spec *spec = codec->spec;
unsigned int oldval = spec->gpio_led;
if (spec->mute_led_polarity)
- enabled = !enabled;
+ led_on = !led_on;
- if (enabled)
- spec->gpio_led &= ~mask;
- else
+ if (led_on)
spec->gpio_led |= mask;
+ else
+ spec->gpio_led &= ~mask;
+ codec_dbg(codec, "mask:%d enabled:%d gpio_led:%d\n",
+ mask, led_on, spec->gpio_led);
if (spec->gpio_led != oldval)
snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
spec->gpio_led);
{
struct hda_codec *codec = private_data;
struct conexant_spec *spec = codec->spec;
-
- cxt_update_gpio_led(codec, spec->gpio_mute_led_mask, enabled);
+ /* muted -> LED on */
+ cxt_update_gpio_led(codec, spec->gpio_mute_led_mask, !enabled);
}
/* turn on/off mic-mute LED via GPIO per capture hook */
{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x03 },
{}
};
- codec_info(codec, "action: %d gpio_led: %d\n", action, spec->gpio_led);
if (action == HDA_FIXUP_ACT_PRE_PROBE) {
spec->gen.vmaster_mute.hook = cxt_fixup_gpio_mute_hook;
*/
static const struct hda_device_id snd_hda_id_conexant[] = {
+ HDA_CODEC_ENTRY(0x14f11f86, "CX8070", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f12008, "CX8200", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15045, "CX20549 (Venice)", patch_conexant_auto),
HDA_CODEC_ENTRY(0x14f15047, "CX20551 (Waikiki)", patch_conexant_auto),
if (spec->init_hook)
spec->init_hook(codec);
+ spec->gen.skip_verbs = 1; /* applied in below */
snd_hda_gen_init(codec);
alc_fix_pll(codec);
alc_auto_init_amp(codec, spec->init_amp);
+ snd_hda_apply_verbs(codec); /* apply verbs here after own init */
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT);
alc_shutup(codec);
}
-/* power down codec to D3 at reboot/shutdown; set as reboot_notify ops */
-static void alc_d3_at_reboot(struct hda_codec *codec)
-{
- snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3);
- snd_hda_codec_write(codec, codec->core.afg, 0,
- AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
- msleep(10);
-}
-
#define alc_free snd_hda_gen_free
#ifdef CONFIG_PM
struct alc_spec *spec = codec->spec;
if (action == HDA_FIXUP_ACT_PRE_PROBE) {
- spec->reboot_notify = alc_d3_at_reboot; /* reduce noise */
+ spec->reboot_notify = snd_hda_gen_reboot_notify; /* reduce noise */
spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
codec->power_save_node = 0; /* avoid click noises */
snd_hda_apply_pincfgs(codec, pincfgs);
ALC286_FIXUP_ACER_AIO_HEADSET_MIC,
ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
ALC299_FIXUP_PREDATOR_SPK,
+ ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC,
};
static const struct hda_fixup alc269_fixups[] = {
{ }
}
},
+ [ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x14, 0x411111f0 }, /* disable confusing internal speaker */
+ { 0x19, 0x04a11150 }, /* use as headset mic, without its own jack detect */
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x82bf, "HP G3 mini", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x82c0, "HP G3 mini premium", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
+ SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
+ SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
+ SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_INTSPK_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
static const struct hda_device_id snd_hda_id_realtek[] = {
HDA_CODEC_ENTRY(0x10ec0215, "ALC215", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0221, "ALC221", patch_alc269),
+ HDA_CODEC_ENTRY(0x10ec0222, "ALC222", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0225, "ALC225", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0231, "ALC231", patch_alc269),
HDA_CODEC_ENTRY(0x10ec0233, "ALC233", patch_alc269),
select SND_SOC_MAX98357A
select SND_SOC_ADAU7002
select REGULATOR
- depends on SND_SOC_AMD_ACP && I2C
+ depends on SND_SOC_AMD_ACP && I2C && GPIOLIB
help
This option enables machine driver for DA7219 and MAX9835.
dev->channels = channels;
ret = regmap_write(dev->regmap, MCHP_I2SMCC_MRA, mra);
- if (ret < 0)
+ if (ret < 0) {
+ if (dev->gclk_use) {
+ clk_unprepare(dev->gclk);
+ dev->gclk_use = 0;
+ }
return ret;
+ }
return regmap_write(dev->regmap, MCHP_I2SMCC_MRB, mrb);
}
err = wait_event_interruptible_timeout(dev->wq_txrdy,
dev->tx_rdy,
msecs_to_jiffies(500));
+ if (err == 0) {
+ dev_warn_once(dev->dev,
+ "Timeout waiting for Tx ready\n");
+ regmap_write(dev->regmap, MCHP_I2SMCC_IDRA,
+ MCHP_I2SMCC_INT_TXRDY_MASK(dev->channels));
+ dev->tx_rdy = 1;
+ }
} else {
err = wait_event_interruptible_timeout(dev->wq_rxrdy,
dev->rx_rdy,
msecs_to_jiffies(500));
- }
-
- if (err == 0) {
- u32 idra;
-
- dev_warn_once(dev->dev, "Timeout waiting for %s\n",
- is_playback ? "Tx ready" : "Rx ready");
- if (is_playback)
- idra = MCHP_I2SMCC_INT_TXRDY_MASK(dev->channels);
- else
- idra = MCHP_I2SMCC_INT_RXRDY_MASK(dev->channels);
- regmap_write(dev->regmap, MCHP_I2SMCC_IDRA, idra);
+ if (err == 0) {
+ dev_warn_once(dev->dev,
+ "Timeout waiting for Rx ready\n");
+ regmap_write(dev->regmap, MCHP_I2SMCC_IDRA,
+ MCHP_I2SMCC_INT_RXRDY_MASK(dev->channels));
+ dev->rx_rdy = 1;
+ }
}
if (!mchp_i2s_mcc_is_running(dev)) {
regmap_write(dev->regmap, MCHP_I2SMCC_CR, MCHP_I2SMCC_CR_CKDIS);
if (dev->gclk_running) {
- clk_disable_unprepare(dev->gclk);
+ clk_disable(dev->gclk);
dev->gclk_running = 0;
}
+ if (dev->gclk_use) {
+ clk_unprepare(dev->gclk);
+ dev->gclk_use = 0;
+ }
}
return 0;
init_waitqueue_head(&dev->wq_txrdy);
init_waitqueue_head(&dev->wq_rxrdy);
+ dev->tx_rdy = 1;
+ dev->rx_rdy = 1;
snd_soc_dai_init_dma_data(dai, &dev->playback, &dev->capture);
static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(alc_max_gain_tlv, -650, 150, 0);
static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(alc_min_gain_tlv, -1200, 150, 0);
static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(alc_target_tlv, -1650, 150, 0);
-static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(hpmixer_gain_tlv, -1200, 150, 0);
+static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(hpmixer_gain_tlv,
+ 0, 4, TLV_DB_SCALE_ITEM(-1200, 150, 0),
+ 8, 11, TLV_DB_SCALE_ITEM(-450, 150, 0),
+);
static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(adc_pga_gain_tlv,
0, 0, TLV_DB_SCALE_ITEM(-350, 0, 0),
SOC_DOUBLE_TLV("Headphone Playback Volume", ES8316_CPHP_ICAL_VOL,
4, 0, 3, 1, hpout_vol_tlv),
SOC_DOUBLE_TLV("Headphone Mixer Volume", ES8316_HPMIX_VOL,
- 0, 4, 7, 0, hpmixer_gain_tlv),
+ 4, 0, 11, 0, hpmixer_gain_tlv),
SOC_ENUM("Playback Polarity", dacpol),
SOC_DOUBLE_R_TLV("DAC Playback Volume", ES8316_DAC_VOLL,
static int rt1011_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
{
struct snd_soc_component *component = dai->component;
+ struct snd_soc_dapm_context *dapm =
+ snd_soc_component_get_dapm(component);
unsigned int reg_val = 0, reg_bclk_inv = 0;
+ int ret = 0;
+ snd_soc_dapm_mutex_lock(dapm);
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBS_CFS:
reg_val |= RT1011_I2S_TDM_MS_S;
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
reg_bclk_inv |= RT1011_TDM_INV_BCLK;
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
reg_val |= RT1011_I2S_TDM_DF_PCM_B;
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
switch (dai->id) {
break;
default:
dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
- return -EINVAL;
+ ret = -EINVAL;
}
- return 0;
+
+ snd_soc_dapm_mutex_unlock(dapm);
+ return ret;
}
static int rt1011_set_component_sysclk(struct snd_soc_component *component,
unsigned int tx_mask, unsigned int rx_mask, int slots, int slot_width)
{
struct snd_soc_component *component = dai->component;
+ struct snd_soc_dapm_context *dapm =
+ snd_soc_component_get_dapm(component);
unsigned int val = 0, tdm_en = 0;
+ int ret = 0;
+ snd_soc_dapm_mutex_lock(dapm);
if (rx_mask || tx_mask)
tdm_en = RT1011_TDM_I2S_DOCK_EN_1;
case 2:
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
switch (slot_width) {
case 16:
break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
snd_soc_component_update_bits(component, RT1011_TDM1_SET_1,
RT1011_ADCDAT1_PIN_CONFIG | RT1011_ADCDAT2_PIN_CONFIG,
RT1011_ADCDAT1_OUTPUT | RT1011_ADCDAT2_OUTPUT);
- return 0;
+ snd_soc_dapm_mutex_unlock(dapm);
+ return ret;
}
static int rt1011_probe(struct snd_soc_component *component)
u32 wl = SSI_SxCCR_WL(sample_size);
int ret;
- /*
- * SSI is properly configured if it is enabled and running in
- * the synchronous mode; Note that AC97 mode is an exception
- * that should set separate configurations for STCCR and SRCCR
- * despite running in the synchronous mode.
- */
- if (ssi->streams && ssi->synchronous)
- return 0;
-
if (fsl_ssi_is_i2s_master(ssi)) {
ret = fsl_ssi_set_bclk(substream, dai, hw_params);
if (ret)
}
}
+ /*
+ * SSI is properly configured if it is enabled and running in
+ * the synchronous mode; Note that AC97 mode is an exception
+ * that should set separate configurations for STCCR and SRCCR
+ * despite running in the synchronous mode.
+ */
+ if (ssi->streams && ssi->synchronous)
+ return 0;
+
if (!fsl_ssi_is_ac97(ssi)) {
/*
* Keep the ssi->i2s_net intact while having a local variable
break;
case SNDRV_PCM_TRIGGER_SUSPEND:
pdata->restore_stream = false;
+ /* fallthrough */
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
sst_byt_stream_pause(byt, pcm_data->stream);
break;
if (ipc->ops.reply_msg_match != NULL)
header = ipc->ops.reply_msg_match(header, &mask);
+ else
+ mask = (u64)-1;
if (list_empty(&ipc->rx_list)) {
dev_err(ipc->dev, "error: rx list empty but received 0x%llx\n",
memset(d->fw_read_buff, 0, FW_REG_BUF);
if (w0_stat_sz > 0)
- __iowrite32_copy(d->fw_read_buff, fw_reg_addr, w0_stat_sz >> 2);
+ __ioread32_copy(d->fw_read_buff, fw_reg_addr, w0_stat_sz >> 2);
for (offset = 0; offset < FW_REG_SIZE; offset += 16) {
ret += snprintf(tmp + ret, FW_REG_BUF - ret, "%#.4x: ", offset);
struct hdac_bus *bus = skl_to_bus(skl);
struct device *dev = bus->dev;
- dev_dbg(dev, "oem_id %.6s, oem_table_id %8s oem_revision %d\n",
+ dev_dbg(dev, "oem_id %.6s, oem_table_id %.8s oem_revision %d\n",
nhlt->header.oem_id, nhlt->header.oem_table_id,
nhlt->header.oem_revision);
struct mtk_base_afe *afe = snd_soc_dai_get_drvdata(dai);
struct mtk_base_afe_memif *memif = &afe->memif[rtd->cpu_dai->id];
int hd_audio = 0;
- int hd_align = 1;
+ int hd_align = 0;
/* set hd mode */
switch (substream->runtime->format) {
break;
case SNDRV_PCM_FORMAT_S24_LE:
hd_audio = 1;
- hd_align = 0;
break;
default:
dev_err(afe->dev, "%s() error: unsupported format %d\n",
if (!dmaengine_pcm_can_report_residue(dev, pcm->chan[i]))
pcm->flags |= SND_DMAENGINE_PCM_FLAG_NO_RESIDUE;
+
+ if (rtd->pcm->streams[i].pcm->name[0] == '\0') {
+ strncpy(rtd->pcm->streams[i].pcm->name,
+ rtd->pcm->streams[i].pcm->id,
+ sizeof(rtd->pcm->streams[i].pcm->name));
+ }
}
return 0;
static int soc_tplg_process_headers(struct soc_tplg *tplg);
static void soc_tplg_complete(struct soc_tplg *tplg);
-struct snd_soc_dapm_widget *
-snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm,
- const struct snd_soc_dapm_widget *widget);
-struct snd_soc_dapm_widget *
-snd_soc_dapm_new_control(struct snd_soc_dapm_context *dapm,
- const struct snd_soc_dapm_widget *widget);
static void soc_tplg_denum_remove_texts(struct soc_enum *se);
static void soc_tplg_denum_remove_values(struct soc_enum *se);
#include "omap-mcbsp.h"
#include "../codecs/cx20442.h"
+static struct gpio_desc *handset_mute;
+static struct gpio_desc *handsfree_mute;
+
+static int ams_delta_event_handset(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *k, int event)
+{
+ gpiod_set_value_cansleep(handset_mute, !SND_SOC_DAPM_EVENT_ON(event));
+ return 0;
+}
+
+static int ams_delta_event_handsfree(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *k, int event)
+{
+ gpiod_set_value_cansleep(handsfree_mute, !SND_SOC_DAPM_EVENT_ON(event));
+ return 0;
+}
+
/* Board specific DAPM widgets */
static const struct snd_soc_dapm_widget ams_delta_dapm_widgets[] = {
/* Handset */
SND_SOC_DAPM_MIC("Mouthpiece", NULL),
- SND_SOC_DAPM_HP("Earpiece", NULL),
+ SND_SOC_DAPM_HP("Earpiece", ams_delta_event_handset),
/* Handsfree/Speakerphone */
SND_SOC_DAPM_MIC("Microphone", NULL),
- SND_SOC_DAPM_SPK("Speaker", NULL),
+ SND_SOC_DAPM_SPK("Speaker", ams_delta_event_handsfree),
};
/* How they are connected to codec pins */
card->dev = &pdev->dev;
+ handset_mute = devm_gpiod_get(card->dev, "handset_mute",
+ GPIOD_OUT_HIGH);
+ if (IS_ERR(handset_mute))
+ return PTR_ERR(handset_mute);
+
+ handsfree_mute = devm_gpiod_get(card->dev, "handsfree_mute",
+ GPIOD_OUT_HIGH);
+ if (IS_ERR(handsfree_mute))
+ return PTR_ERR(handsfree_mute);
+
ret = snd_soc_register_card(card);
if (ret) {
dev_err(&pdev->dev, "snd_soc_register_card failed (%d)\n", ret);
static void davinci_mcbsp_start(struct davinci_mcbsp_dev *dev,
struct snd_pcm_substream *substream)
{
- struct snd_soc_pcm_runtime *rtd = substream->private_data;
- struct snd_soc_component *component = snd_soc_rtdcom_lookup(rtd, DRV_NAME);
int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
u32 spcr;
u32 mask = playback ? DAVINCI_MCBSP_SPCR_XRST : DAVINCI_MCBSP_SPCR_RRST;
- spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
- if (spcr & mask) {
- /* start off disabled */
- davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG,
- spcr & ~mask);
- toggle_clock(dev, playback);
- }
- if (dev->pcr & (DAVINCI_MCBSP_PCR_FSXM | DAVINCI_MCBSP_PCR_FSRM |
- DAVINCI_MCBSP_PCR_CLKXM | DAVINCI_MCBSP_PCR_CLKRM)) {
- /* Start the sample generator */
- spcr |= DAVINCI_MCBSP_SPCR_GRST;
- davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
- }
-
- if (playback) {
- /* Stop the DMA to avoid data loss */
- /* while the transmitter is out of reset to handle XSYNCERR */
- if (component->driver->ops->trigger) {
- int ret = component->driver->ops->trigger(substream,
- SNDRV_PCM_TRIGGER_STOP);
- if (ret < 0)
- printk(KERN_DEBUG "Playback DMA stop failed\n");
- }
-
- /* Enable the transmitter */
- spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
- spcr |= DAVINCI_MCBSP_SPCR_XRST;
- davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
-
- /* wait for any unexpected frame sync error to occur */
- udelay(100);
-
- /* Disable the transmitter to clear any outstanding XSYNCERR */
- spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
- spcr &= ~DAVINCI_MCBSP_SPCR_XRST;
- davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
- toggle_clock(dev, playback);
-
- /* Restart the DMA */
- if (component->driver->ops->trigger) {
- int ret = component->driver->ops->trigger(substream,
- SNDRV_PCM_TRIGGER_START);
- if (ret < 0)
- printk(KERN_DEBUG "Playback DMA start failed\n");
- }
- }
/* Enable transmitter or receiver */
spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
{
struct davinci_mcbsp_dev *dev = snd_soc_dai_get_drvdata(dai);
int playback = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK);
+ u32 spcr;
+ u32 mask = playback ? DAVINCI_MCBSP_SPCR_XRST : DAVINCI_MCBSP_SPCR_RRST;
+
davinci_mcbsp_stop(dev, playback);
+
+ spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+ if (spcr & mask) {
+ /* start off disabled */
+ davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG,
+ spcr & ~mask);
+ toggle_clock(dev, playback);
+ }
+ if (dev->pcr & (DAVINCI_MCBSP_PCR_FSXM | DAVINCI_MCBSP_PCR_FSRM |
+ DAVINCI_MCBSP_PCR_CLKXM | DAVINCI_MCBSP_PCR_CLKRM)) {
+ /* Start the sample generator */
+ spcr |= DAVINCI_MCBSP_SPCR_GRST;
+ davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+ }
+
+ if (playback) {
+ /* Enable the transmitter */
+ spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+ spcr |= DAVINCI_MCBSP_SPCR_XRST;
+ davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+
+ /* wait for any unexpected frame sync error to occur */
+ udelay(100);
+
+ /* Disable the transmitter to clear any outstanding XSYNCERR */
+ spcr = davinci_mcbsp_read_reg(dev, DAVINCI_MCBSP_SPCR_REG);
+ spcr &= ~DAVINCI_MCBSP_SPCR_XRST;
+ davinci_mcbsp_write_reg(dev, DAVINCI_MCBSP_SPCR_REG, spcr);
+ toggle_clock(dev, playback);
+ }
+
return 0;
}
goto retry;
}
spin_unlock(&sound_loader_lock);
- return -EBUSY;
+ r = -EBUSY;
+ goto fail;
}
}
struct usb_host_endpoint *ep;
ep = usb_pipe_endpoint(dev, pipe);
- if (usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
+ if (!ep || usb_pipetype(pipe) != pipetypes[usb_endpoint_type(&ep->desc)])
return -EINVAL;
return 0;
}
ret = hiface_pcm_init_urb(&rt->out_urbs[i], chip, OUT_EP,
hiface_pcm_out_urb_handler);
if (ret < 0)
- return ret;
+ goto error;
}
ret = snd_pcm_new(chip->card, "USB-SPDIF Audio", 0, 1, 0, &pcm);
if (ret < 0) {
- kfree(rt);
dev_err(&chip->dev->dev, "Cannot create pcm instance\n");
- return ret;
+ goto error;
}
pcm->private_data = rt;
chip->pcm = rt;
return 0;
+
+error:
+ for (i = 0; i < PCM_N_URBS; i++)
+ kfree(rt->out_urbs[i].buffer);
+ kfree(rt);
+ return ret;
}
line6pcm->volume_monitor = 255;
line6pcm->line6 = line6;
+ spin_lock_init(&line6pcm->out.lock);
+ spin_lock_init(&line6pcm->in.lock);
+ line6pcm->impulse_period = LINE6_IMPULSE_DEFAULT_PERIOD;
+
+ line6->line6pcm = line6pcm;
+
+ pcm->private_data = line6pcm;
+ pcm->private_free = line6_cleanup_pcm;
+
line6pcm->max_packet_size_in =
usb_maxpacket(line6->usbdev,
usb_rcvisocpipe(line6->usbdev, ep_read), 0);
return -EINVAL;
}
- spin_lock_init(&line6pcm->out.lock);
- spin_lock_init(&line6pcm->in.lock);
- line6pcm->impulse_period = LINE6_IMPULSE_DEFAULT_PERIOD;
-
- line6->line6pcm = line6pcm;
-
- pcm->private_data = line6pcm;
- pcm->private_free = line6_cleanup_pcm;
-
err = line6_create_audio_out_urbs(line6pcm);
if (err < 0)
return err;
.name = "POD HD500",
.capabilities = LINE6_CAP_PCM
| LINE6_CAP_HWMON,
- .altsetting = 1,
+ .altsetting = 0,
.ep_ctrl_r = 0x81,
.ep_ctrl_w = 0x01,
.ep_audio_r = 0x86,
module_usb_driver(variax_driver);
-MODULE_DESCRIPTION("Vairax Workbench USB driver");
+MODULE_DESCRIPTION("Variax Workbench USB driver");
MODULE_LICENSE("GPL");
unsigned char *buffer;
unsigned int buflen;
DECLARE_BITMAP(unitbitmap, MAX_ID_ELEMS);
+ DECLARE_BITMAP(termbitmap, MAX_ID_ELEMS);
struct usb_audio_term oterm;
const struct usbmix_name_map *map;
const struct usbmix_selector_map *selector_map;
struct uac_mixer_unit_descriptor *desc)
{
int mu_channels;
- void *c;
if (desc->bLength < sizeof(*desc))
return -EINVAL;
if (!desc->bNrInPins)
return -EINVAL;
+ if (desc->bLength < sizeof(*desc) + desc->bNrInPins)
+ return -EINVAL;
switch (state->mixer->protocol) {
case UAC_VERSION_1:
break;
}
- if (!mu_channels)
- return 0;
-
- c = uac_mixer_unit_bmControls(desc, state->mixer->protocol);
- if (c - (void *)desc + (mu_channels - 1) / 8 >= desc->bLength)
- return 0; /* no bmControls -> skip */
-
return mu_channels;
}
* parse the source unit recursively until it reaches to a terminal
* or a branched unit.
*/
-static int check_input_term(struct mixer_build *state, int id,
+static int __check_input_term(struct mixer_build *state, int id,
struct usb_audio_term *term)
{
int protocol = state->mixer->protocol;
int err;
void *p1;
+ unsigned char *hdr;
memset(term, 0, sizeof(*term));
- while ((p1 = find_audio_control_unit(state, id)) != NULL) {
- unsigned char *hdr = p1;
+ for (;;) {
+ /* a loop in the terminal chain? */
+ if (test_and_set_bit(id, state->termbitmap))
+ return -EINVAL;
+
+ p1 = find_audio_control_unit(state, id);
+ if (!p1)
+ break;
+
+ hdr = p1;
term->id = id;
if (protocol == UAC_VERSION_1 || protocol == UAC_VERSION_2) {
/* call recursively to verify that the
* referenced clock entity is valid */
- err = check_input_term(state, d->bCSourceID, term);
+ err = __check_input_term(state, d->bCSourceID, term);
if (err < 0)
return err;
case UAC2_CLOCK_SELECTOR: {
struct uac_selector_unit_descriptor *d = p1;
/* call recursively to retrieve the channel info */
- err = check_input_term(state, d->baSourceID[0], term);
+ err = __check_input_term(state, d->baSourceID[0], term);
if (err < 0)
return err;
term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */
/* call recursively to verify that the
* referenced clock entity is valid */
- err = check_input_term(state, d->bCSourceID, term);
+ err = __check_input_term(state, d->bCSourceID, term);
if (err < 0)
return err;
case UAC3_CLOCK_SELECTOR: {
struct uac_selector_unit_descriptor *d = p1;
/* call recursively to retrieve the channel info */
- err = check_input_term(state, d->baSourceID[0], term);
+ err = __check_input_term(state, d->baSourceID[0], term);
if (err < 0)
return err;
term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */
return -EINVAL;
/* call recursively to retrieve the channel info */
- err = check_input_term(state, d->baSourceID[0], term);
+ err = __check_input_term(state, d->baSourceID[0], term);
if (err < 0)
return err;
return -ENODEV;
}
+
+static int check_input_term(struct mixer_build *state, int id,
+ struct usb_audio_term *term)
+{
+ memset(term, 0, sizeof(*term));
+ memset(state->termbitmap, 0, sizeof(state->termbitmap));
+ return __check_input_term(state, id, term);
+}
+
/*
* Feature Unit
*/
* Mixer Unit
*/
+/* check whether the given in/out overflows bmMixerControls matrix */
+static bool mixer_bitmap_overflow(struct uac_mixer_unit_descriptor *desc,
+ int protocol, int num_ins, int num_outs)
+{
+ u8 *hdr = (u8 *)desc;
+ u8 *c = uac_mixer_unit_bmControls(desc, protocol);
+ size_t rest; /* remaining bytes after bmMixerControls */
+
+ switch (protocol) {
+ case UAC_VERSION_1:
+ default:
+ rest = 1; /* iMixer */
+ break;
+ case UAC_VERSION_2:
+ rest = 2; /* bmControls + iMixer */
+ break;
+ case UAC_VERSION_3:
+ rest = 6; /* bmControls + wMixerDescrStr */
+ break;
+ }
+
+ /* overflow? */
+ return c + (num_ins * num_outs + 7) / 8 + rest > hdr + hdr[0];
+}
+
/*
* build a mixer unit control
*
if (err < 0)
return err;
num_ins += iterm.channels;
+ if (mixer_bitmap_overflow(desc, state->mixer->protocol,
+ num_ins, num_outs))
+ break;
for (; ich < num_ins; ich++) {
int och, ich_has_controls = 0;
{
struct usb_mixer_interface *mixer;
struct usb_mixer_elem_info *cval;
- int unitid = 12; /* SamleRate ExtensionUnit ID */
+ int unitid = 12; /* SampleRate ExtensionUnit ID */
list_for_each_entry(mixer, &chip->mixer_list, list) {
- cval = mixer_elem_list_to_info(mixer->id_elems[unitid]);
- if (cval) {
+ if (mixer->id_elems[unitid]) {
+ cval = mixer_elem_list_to_info(mixer->id_elems[unitid]);
snd_usb_mixer_set_ctl_value(cval, UAC_SET_CUR,
cval->control << 8,
samplerate_id);
snd_usb_mixer_notify_id(mixer, unitid);
+ break;
}
- break;
}
}
ep = 0x81;
ifnum = 2;
goto add_sync_ep_from_ifnum;
+ case USB_ID(0x1397, 0x0001): /* Behringer UFX1604 */
case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */
ep = 0x81;
ifnum = 1;
pd = kzalloc(sizeof(*pd), GFP_KERNEL);
if (!pd) {
+ kfree(fp->chmap);
kfree(fp->rate_table);
kfree(fp);
return NULL;
#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \
KVM_REG_ARM_FW | ((r) & 0xffff))
#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
+ /* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
+ /* Higher values mean better protection. */
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
KVM_REG_ARM_FW | ((r) & 0xffff))
#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 KVM_REG_ARM_FW_REG(1)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 KVM_REG_ARM_FW_REG(2)
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL 0
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN 1
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL 2
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3
+#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4)
/* SVE registers */
#define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT)
#define MAP_DENYWRITE 0x0800
#define MAP_EXECUTABLE 0x1000
#define MAP_GROWSDOWN 0x0100
-#define MAP_HUGETLB 0x40000
#define MAP_LOCKED 0x80
-#define MAP_NONBLOCK 0x10000
#define MAP_NORESERVE 0x40
-#define MAP_POPULATE 0x8000
-#define MAP_STACK 0x20000
#include <uapi/asm-generic/mman-common.h>
/* MAP_32BIT is undefined on powerpc, fix it for perf */
#define MAP_32BIT 0
#define MAP_DENYWRITE 0x0800
#define MAP_EXECUTABLE 0x1000
#define MAP_GROWSDOWN 0x0200
-#define MAP_HUGETLB 0x40000
#define MAP_LOCKED 0x100
-#define MAP_NONBLOCK 0x10000
#define MAP_NORESERVE 0x40
-#define MAP_POPULATE 0x8000
-#define MAP_STACK 0x20000
#include <uapi/asm-generic/mman-common.h>
/* MAP_32BIT is undefined on sparc, fix it for perf */
#define MAP_32BIT 0
struct kvm_vcpu_events events;
};
-#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
-#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
-#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
-#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
+#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3)
+#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
} data;
};
+/* for KVM_CAP_PMU_EVENT_FILTER */
+struct kvm_pmu_event_filter {
+ __u32 action;
+ __u32 nevents;
+ __u32 fixed_counter_bitmap;
+ __u32 flags;
+ __u32 pad[4];
+ __u64 events[0];
+};
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
#endif /* _ASM_X86_KVM_H */
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
-#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
if (err)
return err;
- return bpf_obj_pin(fd, name);
+ err = bpf_obj_pin(fd, name);
+ if (err)
+ p_err("can't pin the object (%s): %s", name, strerror(errno));
+
+ return err;
}
int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
fd = get_fd_by_id(id);
if (fd < 0) {
- p_err("can't get prog by id (%u): %s", id, strerror(errno));
+ p_err("can't open object by id (%u): %s", id, strerror(errno));
return -1;
}
if (fd < 0)
return -1;
- return show_prog(fd);
+ err = show_prog(fd);
+ close(fd);
+ return err;
}
if (argc)
# the script prints the string "Disabled" to stdout.
#
# Each Distro is expected to implement this script in a distro specific
-# fashion. For instance on Distros that ship with Network Manager enabled,
+# fashion. For instance, on Distros that ship with Network Manager enabled,
# this script can be based on the Network Manager APIs for retrieving DHCP
# information.
/*
- * Gather the DNS state.
+ * Gather the DNS state.
* Since there is no standard way to get this information
* across various distributions of interest; we just invoke
* an external script that needs to be ported across distros
int sn_offset = 0;
int error = 0;
char *buffer;
- struct hv_kvp_ipaddr_value *ip_buffer;
+ struct hv_kvp_ipaddr_value *ip_buffer = NULL;
char cidr_mask[5]; /* /xyz */
int weight;
int i;
char *start;
/*
- * in_buf has sequence of characters that are seperated by
+ * in_buf has sequence of characters that are separated by
* the character ';'. The last sequence does not have the
* terminating ";" character.
*/
daemonize = 0;
break;
case 'h':
+ print_usage(argv);
+ exit(0);
default:
print_usage(argv);
exit(EXIT_FAILURE);
case KVP_OP_GET_IP_INFO:
kvp_ip_val = &hv_msg->body.kvp_ip_val;
- error = kvp_mac_to_ip(kvp_ip_val);
+ error = kvp_mac_to_ip(kvp_ip_val);
if (error)
hv_msg->error = error;
# be used to configure the interface.
#
# Each Distro is expected to implement this script in a distro specific
-# fashion. For instance on Distros that ship with Network Manager enabled,
+# fashion. For instance, on Distros that ship with Network Manager enabled,
# this script can be based on the Network Manager APIs for configuring the
# interface.
#
* If a partition is mounted more than once, only the first
* FREEZE/THAW can succeed and the later ones will get
* EBUSY/EINVAL respectively: there could be 2 cases:
- * 1) a user may mount the same partition to differnt directories
+ * 1) a user may mount the same partition to different directories
* by mistake or on purpose;
* 2) The subvolume of btrfs appears to have the same partition
* mounted more than once.
daemonize = 0;
break;
case 'h':
+ print_usage(argv);
+ exit(0);
default:
print_usage(argv);
exit(EXIT_FAILURE);
import os
from optparse import OptionParser
+help_msg = "print verbose messages. Try -vv, -vvv for more verbose messages"
parser = OptionParser()
-parser.add_option("-v", "--verbose", dest="verbose",
- help="print verbose messages. Try -vv, -vvv for \
- more verbose messages", action="count")
+parser.add_option(
+ "-v", "--verbose", dest="verbose", help=help_msg, action="count")
(options, args) = parser.parse_args()
exit(-1)
vmbus_dev_dict = {
- '{0e0b6031-5213-4934-818b-38d90ced39db}' : '[Operating system shutdown]',
- '{9527e630-d0ae-497b-adce-e80ab0175caf}' : '[Time Synchronization]',
- '{57164f39-9115-4e78-ab55-382f3bd5422d}' : '[Heartbeat]',
- '{a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}' : '[Data Exchange]',
- '{35fa2e29-ea23-4236-96ae-3a6ebacba440}' : '[Backup (volume checkpoint)]',
- '{34d14be3-dee4-41c8-9ae7-6b174977c192}' : '[Guest services]',
- '{525074dc-8985-46e2-8057-a307dc18a502}' : '[Dynamic Memory]',
- '{cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}' : 'Synthetic mouse',
- '{f912ad6d-2b17-48ea-bd65-f927a61c7684}' : 'Synthetic keyboard',
- '{da0a7802-e377-4aac-8e77-0558eb1073f8}' : 'Synthetic framebuffer adapter',
- '{f8615163-df3e-46c5-913f-f2d2f965ed0e}' : 'Synthetic network adapter',
- '{32412632-86cb-44a2-9b5c-50d1417354f5}' : 'Synthetic IDE Controller',
- '{ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}' : 'Synthetic SCSI Controller',
- '{2f9bcc4a-0069-4af3-b76b-6fd0be528cda}' : 'Synthetic fiber channel adapter',
- '{8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}' : 'Synthetic RDMA adapter',
- '{44c4f61d-4444-4400-9d52-802e27ede19f}' : 'PCI Express pass-through',
- '{276aacf4-ac15-426c-98dd-7521ad3f01fe}' : '[Reserved system device]',
- '{f8e65716-3cb3-4a06-9a60-1889c5cccab5}' : '[Reserved system device]',
- '{3375baf4-9e15-4b30-b765-67acb10d607b}' : '[Reserved system device]',
+ '{0e0b6031-5213-4934-818b-38d90ced39db}': '[Operating system shutdown]',
+ '{9527e630-d0ae-497b-adce-e80ab0175caf}': '[Time Synchronization]',
+ '{57164f39-9115-4e78-ab55-382f3bd5422d}': '[Heartbeat]',
+ '{a9a0f4e7-5a45-4d96-b827-8a841e8c03e6}': '[Data Exchange]',
+ '{35fa2e29-ea23-4236-96ae-3a6ebacba440}': '[Backup (volume checkpoint)]',
+ '{34d14be3-dee4-41c8-9ae7-6b174977c192}': '[Guest services]',
+ '{525074dc-8985-46e2-8057-a307dc18a502}': '[Dynamic Memory]',
+ '{cfa8b69e-5b4a-4cc0-b98b-8ba1a1f3f95a}': 'Synthetic mouse',
+ '{f912ad6d-2b17-48ea-bd65-f927a61c7684}': 'Synthetic keyboard',
+ '{da0a7802-e377-4aac-8e77-0558eb1073f8}': 'Synthetic framebuffer adapter',
+ '{f8615163-df3e-46c5-913f-f2d2f965ed0e}': 'Synthetic network adapter',
+ '{32412632-86cb-44a2-9b5c-50d1417354f5}': 'Synthetic IDE Controller',
+ '{ba6163d9-04a1-4d29-b605-72e2ffb1dc7f}': 'Synthetic SCSI Controller',
+ '{2f9bcc4a-0069-4af3-b76b-6fd0be528cda}': 'Synthetic fiber channel adapter',
+ '{8c2eaf3d-32a7-4b09-ab99-bd1f1c86b501}': 'Synthetic RDMA adapter',
+ '{44c4f61d-4444-4400-9d52-802e27ede19f}': 'PCI Express pass-through',
+ '{276aacf4-ac15-426c-98dd-7521ad3f01fe}': '[Reserved system device]',
+ '{f8e65716-3cb3-4a06-9a60-1889c5cccab5}': '[Reserved system device]',
+ '{3375baf4-9e15-4b30-b765-67acb10d607b}': '[Reserved system device]',
}
+
def get_vmbus_dev_attr(dev_name, attr):
try:
f = open('%s/%s/%s' % (vmbus_sys_path, dev_name, attr), 'r')
return lines
+
class VMBus_Dev:
pass
chn_vp_mapping = get_vmbus_dev_attr(f, 'channel_vp_mapping')
chn_vp_mapping = [c.strip() for c in chn_vp_mapping]
- chn_vp_mapping = sorted(chn_vp_mapping,
- key = lambda c : int(c.split(':')[0]))
+ chn_vp_mapping = sorted(
+ chn_vp_mapping, key=lambda c: int(c.split(':')[0]))
- chn_vp_mapping = ['\tRel_ID=%s, target_cpu=%s' %
- (c.split(':')[0], c.split(':')[1])
- for c in chn_vp_mapping]
+ chn_vp_mapping = [
+ '\tRel_ID=%s, target_cpu=%s' %
+ (c.split(':')[0], c.split(':')[1]) for c in chn_vp_mapping
+ ]
d = VMBus_Dev()
d.sysfs_path = '%s/%s' % (vmbus_sys_path, f)
d.vmbus_id = vmbus_id
vmbus_dev_list.append(d)
-vmbus_dev_list = sorted(vmbus_dev_list, key = lambda d : int(d.vmbus_id))
+vmbus_dev_list = sorted(vmbus_dev_list, key=lambda d: int(d.vmbus_id))
format0 = '%2s: %s'
format1 = '%2s: Class_ID = %s - %s\n%s'
if verbose == 0:
print(('VMBUS ID ' + format0) % (d.vmbus_id, d.dev_desc))
elif verbose == 1:
- print (('VMBUS ID ' + format1) % \
- (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping))
+ print(
+ ('VMBUS ID ' + format1) %
+ (d.vmbus_id, d.class_id, d.dev_desc, d.chn_vp_mapping)
+ )
else:
- print (('VMBUS ID ' + format2) % \
- (d.vmbus_id, d.class_id, d.dev_desc, \
- d.device_id, d.sysfs_path, d.chn_vp_mapping))
+ print(
+ ('VMBUS ID ' + format2) %
+ (
+ d.vmbus_id, d.class_id, d.dev_desc,
+ d.device_id, d.sysfs_path, d.chn_vp_mapping
+ )
+ )
#define MAP_TYPE 0x0f /* Mask for type of mapping */
#define MAP_FIXED 0x10 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x20 /* don't use a file */
-#ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED
-# define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be uninitialized */
-#else
-# define MAP_UNINITIALIZED 0x0 /* Don't support this flag */
-#endif
-/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */
+/* 0x0100 - 0x4000 flags are defined in asm-generic/mman.h */
+#define MAP_POPULATE 0x008000 /* populate (prefault) pagetables */
+#define MAP_NONBLOCK 0x010000 /* do not block on IO */
+#define MAP_STACK 0x020000 /* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB 0x040000 /* create a huge page mapping */
+#define MAP_SYNC 0x080000 /* perform synchronous page faults for the mapping */
#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */
+#define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be
+ * uninitialized */
+
/*
* Flags for mlock
*/
#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
#define MAP_LOCKED 0x2000 /* pages are locked */
#define MAP_NORESERVE 0x4000 /* don't check for reservations */
-#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
-#define MAP_NONBLOCK 0x10000 /* do not block on IO */
-#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */
-#define MAP_HUGETLB 0x40000 /* create a huge page mapping */
-#define MAP_SYNC 0x80000 /* perform synchronous page faults for the mapping */
-/* Bits [26:31] are reserved, see mman-common.h for MAP_HUGETLB usage */
+/*
+ * Bits [26:31] are reserved, see asm-generic/hugetlb_encode.h
+ * for MAP_HUGETLB usage
+ */
#define MCL_CURRENT 1 /* lock all current mappings */
#define MCL_FUTURE 2 /* lock all future mappings */
__SYSCALL(__NR_fsmount, sys_fsmount)
#define __NR_fspick 433
__SYSCALL(__NR_fspick, sys_fspick)
+#define __NR_pidfd_open 434
+__SYSCALL(__NR_pidfd_open, sys_pidfd_open)
+#ifdef __ARCH_WANT_SYS_CLONE3
+#define __NR_clone3 435
+__SYSCALL(__NR_clone3, sys_clone3)
+#endif
#undef __NR_syscalls
-#define __NR_syscalls 434
+#define __NR_syscalls 436
/*
* 32 bit systems traditionally used different
#else /* One of the BSDs */
+#include <stdint.h>
#include <sys/ioccom.h>
#include <sys/types.h>
typedef int8_t __s8;
struct i915_engine_class_instance {
__u16 engine_class; /* see enum drm_i915_gem_engine_class */
__u16 engine_instance;
+#define I915_ENGINE_CLASS_INVALID_NONE -1
+#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
};
/**
#define DRM_I915_PERF_ADD_CONFIG 0x37
#define DRM_I915_PERF_REMOVE_CONFIG 0x38
#define DRM_I915_QUERY 0x39
+#define DRM_I915_GEM_VM_CREATE 0x3a
+#define DRM_I915_GEM_VM_DESTROY 0x3b
/* Must be kept compact -- no holes */
#define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
#define DRM_IOCTL_I915_QUERY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
+#define DRM_IOCTL_I915_GEM_VM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
+#define DRM_IOCTL_I915_GEM_VM_DESTROY DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
/* Allow drivers to submit batchbuffers directly to hardware, relying
* on the security mechanisms provided by hardware.
*/
#define I915_PARAM_MMAP_GTT_COHERENT 52
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
+ * execution through use of explicit fence support.
+ * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
+ */
+#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
/* Must be kept compact -- no holes and well documented */
typedef struct drm_i915_getparam {
*/
#define I915_EXEC_FENCE_ARRAY (1<<19)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
+/*
+ * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_SUBMIT (1 << 20)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
__u32 ctx_id; /* output: id of new context*/
__u32 flags;
#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS (1u << 0)
+#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE (1u << 1)
#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
- (-(I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS << 1))
+ (-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
__u64 extensions;
};
* On creation, all new contexts are marked as recoverable.
*/
#define I915_CONTEXT_PARAM_RECOVERABLE 0x8
+
+ /*
+ * The id of the associated virtual memory address space (ppGTT) of
+ * this context. Can be retrieved and passed to another context
+ * (on the same fd) for both to use the same ppGTT and so share
+ * address layouts, and avoid reloading the page tables on context
+ * switches between themselves.
+ *
+ * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
+ */
+#define I915_CONTEXT_PARAM_VM 0x9
+
+/*
+ * I915_CONTEXT_PARAM_ENGINES:
+ *
+ * Bind this context to operate on this subset of available engines. Henceforth,
+ * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
+ * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
+ * and upwards. Slots 0...N are filled in using the specified (class, instance).
+ * Use
+ * engine_class: I915_ENGINE_CLASS_INVALID,
+ * engine_instance: I915_ENGINE_CLASS_INVALID_NONE
+ * to specify a gap in the array that can be filled in later, e.g. by a
+ * virtual engine used for load balancing.
+ *
+ * Setting the number of engines bound to the context to 0, by passing a zero
+ * sized argument, will revert back to default settings.
+ *
+ * See struct i915_context_param_engines.
+ *
+ * Extensions:
+ * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
+ * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ */
+#define I915_CONTEXT_PARAM_ENGINES 0xa
/* Must be kept compact -- no holes and well documented */
__u64 value;
struct i915_engine_class_instance engine;
/*
- * Unused for now. Must be cleared to zero.
+ * Unknown flags must be cleared to zero.
*/
__u32 flags;
+#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
/*
* Mask of slices to enable for the context. Valid values are a subset
__u32 rsvd;
};
+/*
+ * i915_context_engines_load_balance:
+ *
+ * Enable load balancing across this set of engines.
+ *
+ * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
+ * used will proxy the execbuffer request onto one of the set of engines
+ * in such a way as to distribute the load evenly across the set.
+ *
+ * The set of engines must be compatible (e.g. the same HW class) as they
+ * will share the same logical GPU context and ring.
+ *
+ * To intermix rendering with the virtual engine and direct rendering onto
+ * the backing engines (bypassing the load balancing proxy), the context must
+ * be defined to use a single timeline for all engines.
+ */
+struct i915_context_engines_load_balance {
+ struct i915_user_extension base;
+
+ __u16 engine_index;
+ __u16 num_siblings;
+ __u32 flags; /* all undefined flags must be zero */
+
+ __u64 mbz64; /* reserved for future use; must be zero */
+
+ struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
+ struct i915_user_extension base; \
+ __u16 engine_index; \
+ __u16 num_siblings; \
+ __u32 flags; \
+ __u64 mbz64; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/*
+ * i915_context_engines_bond:
+ *
+ * Constructed bonded pairs for execution within a virtual engine.
+ *
+ * All engines are equal, but some are more equal than others. Given
+ * the distribution of resources in the HW, it may be preferable to run
+ * a request on a given subset of engines in parallel to a request on a
+ * specific engine. We enable this selection of engines within a virtual
+ * engine by specifying bonding pairs, for any given master engine we will
+ * only execute on one of the corresponding siblings within the virtual engine.
+ *
+ * To execute a request in parallel on the master engine and a sibling requires
+ * coordination with a I915_EXEC_FENCE_SUBMIT.
+ */
+struct i915_context_engines_bond {
+ struct i915_user_extension base;
+
+ struct i915_engine_class_instance master;
+
+ __u16 virtual_index; /* index of virtual engine in ctx->engines[] */
+ __u16 num_bonds;
+
+ __u64 flags; /* all undefined flags must be zero */
+ __u64 mbz64[4]; /* reserved for future use; must be zero */
+
+ struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
+ struct i915_user_extension base; \
+ struct i915_engine_class_instance master; \
+ __u16 virtual_index; \
+ __u16 num_bonds; \
+ __u64 flags; \
+ __u64 mbz64[4]; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+struct i915_context_param_engines {
+ __u64 extensions; /* linked chain of extension blocks, 0 terminates */
+#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
+#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+ struct i915_engine_class_instance engines[0];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
+ __u64 extensions; \
+ struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
struct drm_i915_gem_context_create_ext_setparam {
#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
struct i915_user_extension base;
struct drm_i915_gem_context_param param;
};
+struct drm_i915_gem_context_create_ext_clone {
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
+ struct i915_user_extension base;
+ __u32 clone_id;
+ __u32 flags;
+#define I915_CONTEXT_CLONE_ENGINES (1u << 0)
+#define I915_CONTEXT_CLONE_FLAGS (1u << 1)
+#define I915_CONTEXT_CLONE_SCHEDATTR (1u << 2)
+#define I915_CONTEXT_CLONE_SSEU (1u << 3)
+#define I915_CONTEXT_CLONE_TIMELINE (1u << 4)
+#define I915_CONTEXT_CLONE_VM (1u << 5)
+#define I915_CONTEXT_CLONE_UNKNOWN -(I915_CONTEXT_CLONE_VM << 1)
+ __u64 rsvd;
+};
+
struct drm_i915_gem_context_destroy {
__u32 ctx_id;
__u32 pad;
struct drm_i915_query_item {
__u64 query_id;
#define DRM_I915_QUERY_TOPOLOGY_INFO 1
+#define DRM_I915_QUERY_ENGINE_INFO 2
/* Must be kept compact -- no holes and well documented */
/*
__u8 data[];
};
+/**
+ * struct drm_i915_engine_info
+ *
+ * Describes one engine and it's capabilities as known to the driver.
+ */
+struct drm_i915_engine_info {
+ /** Engine class and instance. */
+ struct i915_engine_class_instance engine;
+
+ /** Reserved field. */
+ __u32 rsvd0;
+
+ /** Engine flags. */
+ __u64 flags;
+
+ /** Capabilities of this engine. */
+ __u64 capabilities;
+#define I915_VIDEO_CLASS_CAPABILITY_HEVC (1 << 0)
+#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC (1 << 1)
+
+ /** Reserved fields. */
+ __u64 rsvd1[4];
+};
+
+/**
+ * struct drm_i915_query_engine_info
+ *
+ * Engine info query enumerates all engines known to the driver by filling in
+ * an array of struct drm_i915_engine_info structures.
+ */
+struct drm_i915_query_engine_info {
+ /** Number of struct drm_i915_engine_info structs following. */
+ __u32 num_engines;
+
+ /** MBZ */
+ __u32 rsvd[3];
+
+ /** Marker for drm_i915_engine_info structures. */
+ struct drm_i915_engine_info engines[];
+};
+
#if defined(__cplusplus)
}
#endif
* If no cookie has been set yet, generate a new cookie. Once
* generated, the socket cookie remains stable for the life of the
* socket. This helper can be useful for monitoring per socket
- * networking traffic statistics as it provides a unique socket
- * identifier per namespace.
+ * networking traffic statistics as it provides a global socket
+ * identifier that can be assumed unique.
* Return
* A 8-byte long non-decreasing number on success, or 0 if the
* socket field is missing inside *skb*.
* but this is only implemented for native XDP (with driver
* support) as of this writing).
*
- * All values for *flags* are reserved for future usage, and must
- * be left at zero.
+ * The lower two bits of *flags* are used as the return code if
+ * the map lookup fails. This is so that the return value can be
+ * one of the XDP program return codes up to XDP_TX, as chosen by
+ * the caller. Any higher bits in the *flags* argument must be
+ * unset.
*
* When used to redirect packets to net devices, this helper
* provides a high performance increase over **bpf_redirect**\ ().
IFLA_VF_IB_NODE_GUID, /* VF Infiniband node GUID */
IFLA_VF_IB_PORT_GUID, /* VF Infiniband port GUID */
IFLA_VF_VLAN_LIST, /* nested list of vlans, option for QinQ */
+ IFLA_VF_BROADCAST, /* VF broadcast */
__IFLA_VF_MAX,
};
__u8 mac[32]; /* MAX_ADDR_LEN */
};
+struct ifla_vf_broadcast {
+ __u8 broadcast[32];
+};
+
struct ifla_vf_vlan {
__u32 vf;
__u32 vlan; /* 0 - 4095, 0 disables VLAN filter */
* ACPI gsi notion of irq.
* For IA-64 (APIC model) IOAPIC0: irq 0-23; IOAPIC1: irq 24-47..
* For X86 (standard AT mode) PIC0/1: irq 0-15. IOAPIC0: 0-23..
- * For ARM: See Documentation/virtual/kvm/api.txt
+ * For ARM: See Documentation/virt/kvm/api.txt
*/
union {
__u32 irq;
#define KVM_CAP_ARM_SVE 170
#define KVM_CAP_ARM_PTRAUTH_ADDRESS 171
#define KVM_CAP_ARM_PTRAUTH_GENERIC 172
+#define KVM_CAP_PMU_EVENT_FILTER 173
#ifdef KVM_CAP_IRQ_ROUTING
*
* KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
* the irqfd to operate in resampling mode for level triggered interrupt
- * emulation. See Documentation/virtual/kvm/api.txt.
+ * emulation. See Documentation/virt/kvm/api.txt.
*/
#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info)
/* Available with KVM_CAP_PPC_GET_CPU_CHAR */
#define KVM_PPC_GET_CPU_CHAR _IOR(KVMIO, 0xb1, struct kvm_ppc_cpu_char)
+/* Available with KVM_CAP_PMU_EVENT_FILTER */
+#define KVM_SET_PMU_EVENT_FILTER _IOW(KVMIO, 0xb2, struct kvm_pmu_event_filter)
/* ioctl for vm fd */
#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device)
#ifndef _UAPI_LINUX_SCHED_H
#define _UAPI_LINUX_SCHED_H
+#include <linux/types.h>
+
/*
* cloning flags:
*/
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
+/*
+ * Arguments for the clone3 syscall
+ */
+struct clone_args {
+ __aligned_u64 flags;
+ __aligned_u64 pidfd;
+ __aligned_u64 child_tid;
+ __aligned_u64 parent_tid;
+ __aligned_u64 exit_signal;
+ __aligned_u64 stack;
+ __aligned_u64 stack_size;
+ __aligned_u64 tls;
+};
+
/*
* Scheduling policies
*/
#define SCHED_FLAG_RESET_ON_FORK 0x01
#define SCHED_FLAG_RECLAIM 0x02
#define SCHED_FLAG_DL_OVERRUN 0x04
+#define SCHED_FLAG_KEEP_POLICY 0x08
+#define SCHED_FLAG_KEEP_PARAMS 0x10
+#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
+#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+
+#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
+ SCHED_FLAG_KEEP_PARAMS)
+
+#define SCHED_FLAG_UTIL_CLAMP (SCHED_FLAG_UTIL_CLAMP_MIN | \
+ SCHED_FLAG_UTIL_CLAMP_MAX)
#define SCHED_FLAG_ALL (SCHED_FLAG_RESET_ON_FORK | \
SCHED_FLAG_RECLAIM | \
- SCHED_FLAG_DL_OVERRUN)
+ SCHED_FLAG_DL_OVERRUN | \
+ SCHED_FLAG_KEEP_ALL | \
+ SCHED_FLAG_UTIL_CLAMP)
#endif /* _UAPI_LINUX_SCHED_H */
unsigned char slow;
};
+struct usbdevfs_conninfo_ex {
+ __u32 size; /* Size of the structure from the kernel's */
+ /* point of view. Can be used by userspace */
+ /* to determine how much data can be */
+ /* used/trusted. */
+ __u32 busnum; /* USB bus number, as enumerated by the */
+ /* kernel, the device is connected to. */
+ __u32 devnum; /* Device address on the bus. */
+ __u32 speed; /* USB_SPEED_* constants from ch9.h */
+ __u8 num_ports; /* Number of ports the device is connected */
+ /* to on the way to the root hub. It may */
+ /* be bigger than size of 'ports' array so */
+ /* userspace can detect overflows. */
+ __u8 ports[7]; /* List of ports on the way from the root */
+ /* hub to the device. Current limit in */
+ /* USB specification is 7 tiers (root hub, */
+ /* 5 intermediate hubs, device), which */
+ /* gives at most 6 port entries. */
+};
+
#define USBDEVFS_URB_SHORT_NOT_OK 0x01
#define USBDEVFS_URB_ISO_ASAP 0x02
#define USBDEVFS_URB_BULK_CONTINUATION 0x04
#define USBDEVFS_CAP_REAP_AFTER_DISCONNECT 0x10
#define USBDEVFS_CAP_MMAP 0x20
#define USBDEVFS_CAP_DROP_PRIVILEGES 0x40
+#define USBDEVFS_CAP_CONNINFO_EX 0x80
/* USBDEVFS_DISCONNECT_CLAIM flags & struct */
#define USBDEVFS_FREE_STREAMS _IOR('U', 29, struct usbdevfs_streams)
#define USBDEVFS_DROP_PRIVILEGES _IOW('U', 30, __u32)
#define USBDEVFS_GET_SPEED _IO('U', 31)
+/*
+ * Returns struct usbdevfs_conninfo_ex; length is variable to allow
+ * extending size of the data returned.
+ */
+#define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len)
#endif /* _UAPI_LINUX_USBDEVICE_FS_H */
// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
/* Copyright (c) 2018 Facebook */
+#include <endian.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
static bool btf_check_endianness(const GElf_Ehdr *ehdr)
{
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#if __BYTE_ORDER == __LITTLE_ENDIAN
return ehdr->e_ident[EI_DATA] == ELFDATA2LSB;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#elif __BYTE_ORDER == __BIG_ENDIAN
return ehdr->e_ident[EI_DATA] == ELFDATA2MSB;
#else
# error "Unrecognized __BYTE_ORDER__"
#include <stdbool.h>
#include <stddef.h>
+#ifdef __GLIBC__
+#include <bits/wordsize.h>
+#else
+#include <bits/reg.h>
+#endif
#include "libbpf_internal.h"
static inline size_t hash_bits(size_t h, int bits)
#include <inttypes.h>
#include <string.h>
#include <unistd.h>
+#include <endian.h>
#include <fcntl.h>
#include <errno.h>
#include <asm/unistd.h>
bpf_program_clear_priv_t clear_priv;
enum bpf_attach_type expected_attach_type;
- int btf_fd;
void *func_info;
__u32 func_info_rec_size;
__u32 func_info_cnt;
prog->instances.nr = -1;
zfree(&prog->instances.fds);
- zclose(prog->btf_fd);
zfree(&prog->func_info);
zfree(&prog->line_info);
}
prog->instances.fds = NULL;
prog->instances.nr = -1;
prog->type = BPF_PROG_TYPE_UNSPEC;
- prog->btf_fd = -1;
return 0;
errout:
static int bpf_object__check_endianness(struct bpf_object *obj)
{
-#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+#if __BYTE_ORDER == __LITTLE_ENDIAN
if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
return 0;
-#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+#elif __BYTE_ORDER == __BIG_ENDIAN
if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
return 0;
#else
if (!has_datasec && kind == BTF_KIND_VAR) {
/* replace VAR with INT */
t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
- t->size = sizeof(int);
- *(int *)(t+1) = BTF_INT_ENC(0, 0, 32);
+ /*
+ * using size = 1 is the safest choice, 4 will be too
+ * big and cause kernel BTF validation failure if
+ * original variable took less than 4 bytes
+ */
+ t->size = 1;
+ *(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
} else if (!has_datasec && kind == BTF_KIND_DATASEC) {
/* replace DATASEC with STRUCT */
struct btf_var_secinfo *v = (void *)(t + 1);
BTF_ELF_SEC, err);
btf__free(obj->btf);
obj->btf = NULL;
+ /* btf_ext can't exist without btf, so free it as well */
+ if (obj->btf_ext) {
+ btf_ext__free(obj->btf_ext);
+ obj->btf_ext = NULL;
+ }
+
if (bpf_object__is_btf_mandatory(obj))
return err;
}
prog->line_info_rec_size = btf_ext__line_info_rec_size(obj->btf_ext);
}
- if (!insn_offset)
- prog->btf_fd = btf__fd(obj->btf);
-
return 0;
}
char *cp, errmsg[STRERR_BUFSIZE];
int log_buf_size = BPF_LOG_BUF_SIZE;
char *log_buf;
- int ret;
+ int btf_fd, ret;
if (!insns || !insns_cnt)
return -EINVAL;
load_attr.license = license;
load_attr.kern_version = kern_version;
load_attr.prog_ifindex = prog->prog_ifindex;
- load_attr.prog_btf_fd = prog->btf_fd >= 0 ? prog->btf_fd : 0;
+ /* if .BTF.ext was loaded, kernel supports associated BTF for prog */
+ if (prog->obj->btf_ext)
+ btf_fd = bpf_object__btf_fd(prog->obj);
+ else
+ btf_fd = -1;
+ load_attr.prog_btf_fd = btf_fd >= 0 ? btf_fd : 0;
load_attr.func_info = prog->func_info;
load_attr.func_info_rec_size = prog->func_info_rec_size;
load_attr.func_info_cnt = prog->func_info_cnt;
const struct perf_buffer_opts *opts)
{
struct perf_buffer_params p = {};
- struct perf_event_attr attr = {
- .config = PERF_COUNT_SW_BPF_OUTPUT,
- .type = PERF_TYPE_SOFTWARE,
- .sample_type = PERF_SAMPLE_RAW,
- .sample_period = 1,
- .wakeup_events = 1,
- };
+ struct perf_event_attr attr = { 0, };
+
+ attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.sample_type = PERF_SAMPLE_RAW;
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
p.attr = &attr;
p.sample_cb = opts ? opts->sample_cb : NULL;
static const char *fcpu = "/sys/devices/system/cpu/possible";
int len = 0, n = 0, il = 0, ir = 0;
unsigned int start = 0, end = 0;
+ int tmp_cpus = 0;
static int cpus;
char buf[128];
int error = 0;
int fd = -1;
- if (cpus > 0)
- return cpus;
+ tmp_cpus = READ_ONCE(cpus);
+ if (tmp_cpus > 0)
+ return tmp_cpus;
fd = open(fcpu, O_RDONLY);
if (fd < 0) {
}
buf[len] = '\0';
- for (ir = 0, cpus = 0; ir <= len; ir++) {
+ for (ir = 0, tmp_cpus = 0; ir <= len; ir++) {
/* Each sub string separated by ',' has format \d+-\d+ or \d+ */
if (buf[ir] == ',' || buf[ir] == '\0') {
buf[ir] = '\0';
} else if (n == 1) {
end = start;
}
- cpus += end - start + 1;
+ tmp_cpus += end - start + 1;
il = ir + 1;
}
}
- if (cpus <= 0) {
- pr_warning("Invalid #CPUs %d from %s\n", cpus, fcpu);
+ if (tmp_cpus <= 0) {
+ pr_warning("Invalid #CPUs %d from %s\n", tmp_cpus, fcpu);
return -EINVAL;
}
- return cpus;
+
+ WRITE_ONCE(cpus, tmp_cpus);
+ return tmp_cpus;
}
static int xsk_get_max_queues(struct xsk_socket *xsk)
{
- struct ethtool_channels channels;
- struct ifreq ifr;
+ struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS };
+ struct ifreq ifr = {};
int fd, err, ret;
fd = socket(AF_INET, SOCK_DGRAM, 0);
if (fd < 0)
return -errno;
- channels.cmd = ETHTOOL_GCHANNELS;
ifr.ifr_data = (void *)&channels;
- strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
+ memcpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1);
ifr.ifr_name[IFNAMSIZ - 1] = '\0';
err = ioctl(fd, SIOCETHTOOL, &ifr);
if (err && errno != EOPNOTSUPP) {
goto out;
}
- if (channels.max_combined == 0 || errno == EOPNOTSUPP)
+ if (err || channels.max_combined == 0)
/* If the device says it has no channels, then all traffic
* is sent to a single stream, so max queues = 1.
*/
err = -errno;
goto out_socket;
}
- strncpy(xsk->ifname, ifname, IFNAMSIZ - 1);
+ memcpy(xsk->ifname, ifname, IFNAMSIZ - 1);
xsk->ifname[IFNAMSIZ - 1] = '\0';
err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
struct alternative *alt;
struct instruction *insn, *next_insn;
struct section *sec;
+ u8 visited;
int ret;
insn = first;
return 1;
}
+ visited = 1 << state.uaccess;
if (insn->visited) {
if (!insn->hint && !insn_state_match(insn, &state))
return 1;
- /* If we were here with AC=0, but now have AC=1, go again */
- if (insn->state.uaccess || !state.uaccess)
+ if (insn->visited & visited)
return 0;
}
} else
insn->state = state;
- insn->visited = true;
+ insn->visited |= visited;
if (!insn->ignore_alts) {
bool skip_orig = false;
unsigned int len;
enum insn_type type;
unsigned long immediate;
- bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts;
+ bool alt_group, dead_end, ignore, hint, save, restore, ignore_alts;
bool retpoline_safe;
+ u8 visited;
struct symbol *call_dest;
struct instruction *jump_dest;
struct instruction *first_jump_src;
$(PERL_PATH) ./build-docdep.perl >$@+ $(QUIET_STDERR) && \
mv $@+ $@
--include $(OUPTUT)doc.dep
+-include $(OUTPUT)doc.dep
_cmds_txt = cmds-ancillaryinterrogators.txt \
cmds-ancillarymanipulators.txt \
With the metric option perf script can compute metrics for
sampling periods, similar to perf stat. This requires
- specifying a group with multiple metrics with the :S option
+ specifying a group with multiple events defining metrics with the :S option
for perf record. perf will sample on the first event, and
- compute metrics for all the events in the group. Please note
+ print computed metrics for all the events in the group. Please note
that the metric computed is averaged over the whole sampling
- period, not just for the sample point.
+ period (since the last sample), not just for the sample point.
For sample events it's possible to display misc field with -F +misc option,
following letters are displayed for each bit:
perf script --time 0%-10%,30%-40%
--max-blocks::
- Set the maximum number of program blocks to print with brstackasm for
+ Set the maximum number of program blocks to print with brstackinsn for
each sample.
--reltime::
HEADER_TOTAL_MEM = 10,
-An uint64_t with the total memory in bytes.
+An uint64_t with the total memory in kilobytes.
HEADER_CMDLINE = 11,
#include "machine.h"
#include "api/fs/fs.h"
#include "debug.h"
+#include "symbol.h"
-int arch__fix_module_text_start(u64 *start, const char *name)
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
{
u64 m_start = *start;
char path[PATH_MAX];
if (sysfs__read_ull(path, (unsigned long long *)start) < 0) {
pr_debug2("Using module %s start:%#lx\n", path, m_start);
*start = m_start;
+ } else {
+ /* Successful read of the modules segment text start address.
+ * Calculate difference between module start address
+ * in memory and module text segment start address.
+ * For example module load address is 0x3ff8011b000
+ * (from /proc/modules) and module text segment start
+ * address is 0x3ff8011b870 (from file above).
+ *
+ * Adjust the module size and subtract the GOT table
+ * size located at the beginning of the module.
+ */
+ *size -= (*start - m_start);
}
return 0;
}
+
+/* On s390 kernel text segment start is located at very low memory addresses,
+ * for example 0x10000. Modules are located at very high memory addresses,
+ * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
+ * and beginning of first module's text segment is very big.
+ * Therefore do not fill this gap and do not assign it to the kernel dso map.
+ */
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+ if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
+ /* Last kernel symbol mapped to end of page */
+ p->end = roundup(p->end, page_size);
+ else
+ p->end = c->start;
+ pr_debug4("%s sym:%s end:%#lx\n", __func__, p->name, p->end);
+}
431 common fsconfig __x64_sys_fsconfig
432 common fsmount __x64_sys_fsmount
433 common fspick __x64_sys_fspick
+434 common pidfd_open __x64_sys_pidfd_open
+435 common clone3 __x64_sys_clone3/ptregs
#
# x32-specific system call numbers start at 512 to avoid cache impact
/* Allocate and initialize all memory on CPU#0: */
if (init_cpu0) {
- orig_mask = bind_to_node(0);
- bind_to_memnode(0);
+ int node = numa_node_of_cpu(0);
+
+ orig_mask = bind_to_node(node);
+ bind_to_memnode(node);
}
bytes = bytes0 + HPSIZE;
int last_cpu;
last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
- mask_size = (last_cpu + 3) / 4 + 1;
+ mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
cpumask = malloc(mask_size);
ret = perf_add_probe_events(params.events, params.nevents);
if (ret < 0) {
+
+ /*
+ * When perf_add_probe_events() fails it calls
+ * cleanup_perf_probe_events(pevs, npevs), i.e.
+ * cleanup_perf_probe_events(params.events, params.nevents), which
+ * will call clear_perf_probe_event(), so set nevents to zero
+ * to avoid cleanup_params() to call clear_perf_probe_event() again
+ * on the same pevs.
+ */
+ params.nevents = 0;
pr_err_with_code(" Error: Failed to add events.", ret);
return ret;
}
printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp);
if (ip == end) {
- printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp,
+ printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, ++insn, fp,
&total_cycles);
if (PRINT_FIELD(SRCCODE))
printed += print_srccode(thread, x.cpumode, ip);
* group leaders.
*/
read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
- perf_evlist__close(evsel_list);
+
+ /*
+ * We need to keep evsel_list alive, because it's processed
+ * later the evsel_list will be closed after.
+ */
+ if (!STAT_RECORD)
+ perf_evlist__close(evsel_list);
return WEXITSTATUS(status);
}
perf_session__write_header(perf_stat.session, evsel_list, fd, true);
}
+ perf_evlist__close(evsel_list);
perf_session__delete(perf_stat.session);
}
{ "inst_retired.any_p", "event=0xc0" },
{ "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
{ "cpu_clk_unhalted.thread", "event=0x3c" },
+ { "cpu_clk_unhalted.core", "event=0x3c" },
{ "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
{ NULL, NULL},
};
[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+# also as:
+# #define USBDEVFS_CONNINFO_EX(len) _IOC(_IOC_READ, 'U', 32, len)
+
printf "static const char *usbdevfs_ioctl_cmds[] = {\n"
-regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-egrep $regex ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \
- sed -r "s/$regex/\2 \1/g" | \
+regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
+egrep "$regex" ${header_dir}/usbdevice_fs.h | egrep -v 'USBDEVFS_\w+32[[:space:]]' | \
+ sed -r "s/$regex/\4 \1/g" | \
sort | xargs printf "\t[%s] = \"%s\",\n"
printf "};\n\n"
printf "#if 0\n"
// SPDX-License-Identifier: GPL-2.0
-#include "../string2.h"
-#include "../config.h"
-#include "../../perf.h"
+#include "../util/util.h"
+#include "../util/string2.h"
+#include "../util/config.h"
+#include "../perf.h"
#include "libslang.h"
#include "ui.h"
#include "util.h"
#include "browser.h"
#include "helpline.h"
#include "keysyms.h"
-#include "../color.h"
+#include "../util/color.h"
#include <linux/ctype.h>
#include <linux/zalloc.h>
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
-#include "../cache.h"
+#include "../../util/cache.h"
#include "../progress.h"
#include "../libslang.h"
#include "../ui.h"
goto out;
(*rawp)[0] = tmp;
- *rawp = skip_spaces(*rawp);
+ *rawp = strim(*rawp);
return 0;
unsigned char *bitmap;
int last_cpu = cpu_map__cpu(map, map->nr - 1);
- bitmap = zalloc((last_cpu + 7) / 8);
+ if (buf == NULL)
+ return 0;
+
+ bitmap = zalloc(last_cpu / 8 + 1);
if (bitmap == NULL) {
buf[0] = '\0';
return 0;
xyarray__delete(evsel->sample_id);
evsel->sample_id = NULL;
zfree(&evsel->id);
+ evsel->ids = 0;
}
static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
perf_evsel__close_fd(evsel);
perf_evsel__free_fd(evsel);
+ perf_evsel__free_id(evsel);
}
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
data->file.path);
}
+ if (f_header.attr_size == 0) {
+ pr_err("ERROR: The %s file's attr size field is 0 which is unexpected.\n"
+ "Was the 'perf record' command properly terminated?\n",
+ data->file.path);
+ return -EINVAL;
+ }
+
nr_attrs = f_header.attrs.size / f_header.attr_size;
lseek(fd, f_header.attrs.offset, SEEK_SET);
size += sizeof(struct perf_event_header);
size += ids * sizeof(u64);
- ev = malloc(size);
+ ev = zalloc(size);
if (ev == NULL)
return -ENOMEM;
return 0;
ff.buf = (void *)fe->data;
- ff.size = event->header.size - sizeof(event->header);
+ ff.size = event->header.size - sizeof(*fe);
ff.ph = &session->header;
if (feat_ops[feat].process(&ff, NULL))
return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
}
int __weak arch__fix_module_text_start(u64 *start __maybe_unused,
+ u64 *size __maybe_unused,
const char *name __maybe_unused)
{
return 0;
struct machine *machine = arg;
struct map *map;
- if (arch__fix_module_text_start(&start, name) < 0)
+ if (arch__fix_module_text_start(&start, &size, name) < 0)
return -1;
map = machine__findnew_module_map(machine, start, name);
struct map *machine__findnew_module_map(struct machine *machine, u64 start,
const char *filename);
-int arch__fix_module_text_start(u64 *start, const char *name);
+int arch__fix_module_text_start(u64 *start, u64 *size, const char *name);
int machine__load_kallsyms(struct machine *machine, const char *filename);
field = next;
}
}
+ pev->nargs = 0;
zfree(&pev->args);
}
void *src;
size_t decomp_size, src_size;
u64 decomp_last_rem = 0;
- size_t decomp_len = session->header.env.comp_mmap_len;
+ size_t mmap_len, decomp_len = session->header.env.comp_mmap_len;
struct decomp *decomp, *decomp_last = session->decomp_last;
- decomp = mmap(NULL, sizeof(struct decomp) + decomp_len, PROT_READ|PROT_WRITE,
+ if (decomp_last) {
+ decomp_last_rem = decomp_last->size - decomp_last->head;
+ decomp_len += decomp_last_rem;
+ }
+
+ mmap_len = sizeof(struct decomp) + decomp_len;
+ decomp = mmap(NULL, mmap_len, PROT_READ|PROT_WRITE,
MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
if (decomp == MAP_FAILED) {
pr_err("Couldn't allocate memory for decompression\n");
}
decomp->file_pos = file_offset;
+ decomp->mmap_len = mmap_len;
decomp->head = 0;
- if (decomp_last) {
- decomp_last_rem = decomp_last->size - decomp_last->head;
+ if (decomp_last_rem) {
memcpy(decomp->data, &(decomp_last->data[decomp_last->head]), decomp_last_rem);
decomp->size = decomp_last_rem;
}
decomp_size = zstd_decompress_stream(&(session->zstd_data), src, src_size,
&(decomp->data[decomp_last_rem]), decomp_len - decomp_last_rem);
if (!decomp_size) {
- munmap(decomp, sizeof(struct decomp) + decomp_len);
+ munmap(decomp, mmap_len);
pr_err("Couldn't decompress data\n");
return -1;
}
static void perf_session__release_decomp_events(struct perf_session *session)
{
struct decomp *next, *decomp;
- size_t decomp_len;
+ size_t mmap_len;
next = session->decomp;
- decomp_len = session->header.env.comp_mmap_len;
do {
decomp = next;
if (decomp == NULL)
break;
next = decomp->next;
- munmap(decomp, decomp_len + sizeof(struct decomp));
+ mmap_len = decomp->mmap_len;
+ munmap(decomp, mmap_len);
} while (1);
}
struct decomp {
struct decomp *next;
u64 file_pos;
+ size_t mmap_len;
u64 head;
size_t size;
char data[];
"stalled cycles per insn",
ratio);
} else if (have_frontend_stalled) {
- print_metric(config, ctxp, NULL, NULL,
+ out->new_line(config, ctxp);
+ print_metric(config, ctxp, NULL, "%7.2f ",
"stalled cycles per insn", 0);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
return tail - str;
}
+void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
+{
+ p->end = c->start;
+}
+
const char * __weak arch__normalize_symbol_name(const char *name)
{
return name;
curr = rb_entry(nd, struct symbol, rb_node);
if (prev->end == prev->start && prev->end != curr->start)
- prev->end = curr->start;
+ arch__symbols__fixup_end(prev, curr);
}
/* Last entry */
#define SYMBOL_A 0
#define SYMBOL_B 1
+void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
int arch__compare_symbol_names(const char *namea, const char *nameb);
int arch__compare_symbol_names_n(const char *namea, const char *nameb,
unsigned int n);
struct comm *thread__exec_comm(const struct thread *thread)
{
- struct comm *comm, *last = NULL;
+ struct comm *comm, *last = NULL, *second_last = NULL;
list_for_each_entry(comm, &thread->comm_list, list) {
if (comm->exec)
return comm;
+ second_last = last;
last = comm;
}
+ /*
+ * 'last' with no start time might be the parent's comm of a synthesized
+ * thread (created by processing a synthesized fork event). For a main
+ * thread, that is very probably wrong. Prefer a later comm to avoid
+ * that case.
+ */
+ if (second_last && !last->start && thread->pid_ == thread->tid)
+ return second_last;
+
return last;
}
while (input.pos < input.size) {
ret = ZSTD_decompressStream(data->dstream, &output, &input);
if (ZSTD_isError(ret)) {
- pr_err("failed to decompress (B): %ld -> %ld : %s\n",
- src_size, output.size, ZSTD_getErrorName(ret));
+ pr_err("failed to decompress (B): %ld -> %ld, dst_size %ld : %s\n",
+ src_size, output.size, dst_size, ZSTD_getErrorName(ret));
break;
}
output.dst = dst + output.pos;
endif
turbostat : turbostat.c
-override CFLAGS += -Wall -I../../../include
+override CFLAGS += -O2 -Wall -I../../../include
override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
+override CFLAGS += -D_FORTIFY_SOURCE=2
%: %.c
@mkdir -p $(BUILD_OUTPUT)
int *fd_percpu;
struct timeval interval_tv = {5, 0};
struct timespec interval_ts = {5, 0};
-struct timespec one_msec = {0, 1000000};
unsigned int num_iterations;
unsigned int debug;
unsigned int quiet;
unsigned int units = 1000000; /* MHz etc */
unsigned int genuine_intel;
unsigned int authentic_amd;
+unsigned int hygon_genuine;
unsigned int max_level, max_extended_level;
unsigned int has_invariant_tsc;
unsigned int do_nhm_platform_info;
unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */
unsigned int has_misc_feature_control;
unsigned int first_counter_read = 1;
+int ignore_stdin;
#define RAPL_PKG (1 << 0)
/* 0x610 MSR_PKG_POWER_LIMIT */
struct thread_data {
struct timeval tv_begin;
struct timeval tv_end;
+ struct timeval tv_delta;
unsigned long long tsc;
unsigned long long aperf;
unsigned long long mperf;
unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME)
#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
- outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
if (DO_BIC(BIC_TOD))
outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec);
- interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
+ interval_float = t->tv_delta.tv_sec + t->tv_delta.tv_usec/1000000.0;
tsc = t->tsc * tsc_tweak;
}
}
+int soft_c1_residency_display(int bic)
+{
+ if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr)
+ return 0;
+
+ return DO_BIC_READ(bic);
+}
+
/*
* old = new - old
*/
* over-write old w/ new so we can print end of interval values
*/
+ timersub(&new->tv_begin, &old->tv_begin, &old->tv_delta);
old->tv_begin = new->tv_begin;
old->tv_end = new->tv_end;
old->c1 = new->c1 - old->c1;
- if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
+ if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) ||
+ soft_c1_residency_display(BIC_Avg_MHz)) {
if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) {
old->aperf = new->aperf - old->aperf;
old->mperf = new->mperf - old->mperf;
t->tv_begin.tv_usec = 0;
t->tv_end.tv_sec = 0;
t->tv_end.tv_usec = 0;
+ t->tv_delta.tv_sec = 0;
+ t->tv_delta.tv_usec = 0;
t->tsc = 0;
t->aperf = 0;
for_all_cpus(sum_counters, t, c, p);
+ /* Use the global time delta for the average. */
+ average.threads.tv_delta = tv_delta;
+
average.threads.tsc /= topo.num_cpus;
average.threads.aperf /= topo.num_cpus;
average.threads.mperf /= topo.num_cpus;
if (!DO_BIC(BIC_X2APIC))
return;
- if (authentic_amd) {
+ if (authentic_amd || hygon_genuine) {
unsigned int topology_extensions;
if (max_extended_level < 0x8000001e)
struct msr_counter *mp;
int i;
- gettimeofday(&t->tv_begin, (struct timezone *)NULL);
-
if (cpu_migrate(cpu)) {
fprintf(outf, "Could not migrate to CPU %d\n", cpu);
return -1;
}
+ gettimeofday(&t->tv_begin, (struct timezone *)NULL);
+
if (first_counter_read)
get_apic_id(t);
retry:
t->tsc = rdtsc(); /* we are running on local CPU of interest */
- if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) {
+ if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) ||
+ soft_c1_residency_display(BIC_Avg_MHz)) {
unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
/*
if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
goto done;
- if (DO_BIC(BIC_CPU_c3)) {
+ if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
}
- if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) {
+ if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) {
if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6))
return -7;
- } else if (do_knl_cstates) {
+ } else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) {
if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6))
return -7;
}
- if (DO_BIC(BIC_CPU_c7))
+ if (DO_BIC(BIC_CPU_c7) || soft_c1_residency_display(BIC_CPU_c7))
if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7))
return -8;
if (retval != 1) {
fprintf(stderr, "Disabling Low Power Idle CPU output\n");
BIC_NOT_PRESENT(BIC_CPU_LPI);
+ fclose(fp);
return -1;
}
if (retval != 1) {
fprintf(stderr, "Disabling Low Power Idle System output\n");
BIC_NOT_PRESENT(BIC_SYS_LPI);
+ fclose(fp);
return -1;
}
fclose(fp);
fprintf(stderr, "SIGUSR1\n");
break;
}
- /* make sure this manually-invoked interval is at least 1ms long */
- nanosleep(&one_msec, NULL);
}
void setup_signal_handler(void)
void do_sleep(void)
{
- struct timeval select_timeout;
+ struct timeval tout;
+ struct timespec rest;
fd_set readfds;
int retval;
FD_ZERO(&readfds);
FD_SET(0, &readfds);
- if (!isatty(fileno(stdin))) {
+ if (ignore_stdin) {
nanosleep(&interval_ts, NULL);
return;
}
- select_timeout = interval_tv;
- retval = select(1, &readfds, NULL, NULL, &select_timeout);
+ tout = interval_tv;
+ retval = select(1, &readfds, NULL, NULL, &tout);
if (retval == 1) {
switch (getc(stdin)) {
case 'q':
exit_requested = 1;
break;
+ case EOF:
+ /*
+ * 'stdin' is a pipe closed on the other end. There
+ * won't be any further input.
+ */
+ ignore_stdin = 1;
+ /* Sleep the rest of the time */
+ rest.tv_sec = (tout.tv_sec + tout.tv_usec / 1000000);
+ rest.tv_nsec = (tout.tv_usec % 1000000) * 1000;
+ nanosleep(&rest, NULL);
}
- /* make sure this manually-invoked interval is at least 1ms long */
- nanosleep(&one_msec, NULL);
}
}
break;
case INTEL_FAM6_HASWELL_CORE: /* HSW */
case INTEL_FAM6_HASWELL_X: /* HSX */
+ case INTEL_FAM6_HASWELL_ULT: /* HSW */
case INTEL_FAM6_HASWELL_GT3E: /* HSW */
case INTEL_FAM6_BROADWELL_CORE: /* BDW */
case INTEL_FAM6_BROADWELL_GT3E: /* BDW */
case INTEL_FAM6_IVYBRIDGE: /* IVB */
case INTEL_FAM6_HASWELL_CORE: /* HSW */
case INTEL_FAM6_HASWELL_X: /* HSX */
+ case INTEL_FAM6_HASWELL_ULT: /* HSW */
case INTEL_FAM6_HASWELL_GT3E: /* HSW */
case INTEL_FAM6_BROADWELL_CORE: /* BDW */
case INTEL_FAM6_BROADWELL_GT3E: /* BDW */
{
switch (family) {
case 0x17:
+ case 0x18:
default:
/* This is the max stock TDP of HEDT/Server Fam17h chips */
return 250.0;
case INTEL_FAM6_SANDYBRIDGE:
case INTEL_FAM6_IVYBRIDGE:
case INTEL_FAM6_HASWELL_CORE: /* HSW */
+ case INTEL_FAM6_HASWELL_ULT: /* HSW */
case INTEL_FAM6_HASWELL_GT3E: /* HSW */
case INTEL_FAM6_BROADWELL_CORE: /* BDW */
case INTEL_FAM6_BROADWELL_GT3E: /* BDW */
switch (family) {
case 0x17: /* Zen, Zen+ */
+ case 0x18: /* Hygon Dhyana */
do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
if (rapl_joules) {
BIC_PRESENT(BIC_Pkg_J);
rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
rapl_power_units = ldexp(1.0, -(msr & 0xf));
- tdp = get_tdp_amd(model);
+ tdp = get_tdp_amd(family);
rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
if (!quiet)
{
if (genuine_intel)
rapl_probe_intel(family, model);
- if (authentic_amd)
+ if (authentic_amd || hygon_genuine)
rapl_probe_amd(family, model);
}
switch (model) {
case INTEL_FAM6_HASWELL_CORE: /* HSW */
+ case INTEL_FAM6_HASWELL_ULT: /* HSW */
case INTEL_FAM6_HASWELL_GT3E: /* HSW */
do_gfx_perf_limit_reasons = 1;
case INTEL_FAM6_HASWELL_X: /* HSX */
case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */
case INTEL_FAM6_HASWELL_CORE: /* HSW */
case INTEL_FAM6_HASWELL_X: /* HSW */
+ case INTEL_FAM6_HASWELL_ULT: /* HSW */
case INTEL_FAM6_HASWELL_GT3E: /* HSW */
case INTEL_FAM6_BROADWELL_CORE: /* BDW */
case INTEL_FAM6_BROADWELL_GT3E: /* BDW */
}
/*
- * HSW adds support for additional MSRs:
+ * HSW ULT added support for C8/C9/C10 MSRs:
*
* MSR_PKG_C8_RESIDENCY 0x00000630
* MSR_PKG_C9_RESIDENCY 0x00000631
* MSR_PKGC10_IRTL 0x00000635
*
*/
-int has_hsw_msrs(unsigned int family, unsigned int model)
+int has_c8910_msrs(unsigned int family, unsigned int model)
{
if (!genuine_intel)
return 0;
switch (model) {
- case INTEL_FAM6_HASWELL_CORE:
+ case INTEL_FAM6_HASWELL_ULT: /* HSW */
case INTEL_FAM6_BROADWELL_CORE: /* BDW */
case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */
case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
case INTEL_FAM6_XEON_PHI_KNM:
return INTEL_FAM6_XEON_PHI_KNL;
- case INTEL_FAM6_HASWELL_ULT:
- return INTEL_FAM6_HASWELL_CORE;
-
case INTEL_FAM6_BROADWELL_X:
case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */
return INTEL_FAM6_BROADWELL_X;
return INTEL_FAM6_SKYLAKE_MOBILE;
case INTEL_FAM6_ICELAKE_MOBILE:
+ case INTEL_FAM6_ICELAKE_NNPI:
return INTEL_FAM6_CANNONLAKE_MOBILE;
+
+ case INTEL_FAM6_ATOM_TREMONT_X:
+ return INTEL_FAM6_ATOM_GOLDMONT_X;
}
return model;
}
genuine_intel = 1;
else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65)
authentic_amd = 1;
+ else if (ebx == 0x6f677948 && ecx == 0x656e6975 && edx == 0x6e65476e)
+ hygon_genuine = 1;
if (!quiet)
fprintf(outf, "CPUID(0): %.4s%.4s%.4s ",
BIC_NOT_PRESENT(BIC_CPU_c7);
BIC_NOT_PRESENT(BIC_Pkgpc7);
}
- if (has_hsw_msrs(family, model)) {
+ if (has_c8910_msrs(family, model)) {
BIC_PRESENT(BIC_Pkgpc8);
BIC_PRESENT(BIC_Pkgpc9);
BIC_PRESENT(BIC_Pkgpc10);
}
- do_irtl_hsw = has_hsw_msrs(family, model);
+ do_irtl_hsw = has_c8910_msrs(family, model);
if (has_skl_msrs(family, model)) {
BIC_PRESENT(BIC_Totl_c0);
BIC_PRESENT(BIC_Any_c0);
void allocate_output_buffer()
{
- output_buffer = calloc(1, (1 + topo.num_cpus) * 1024);
+ output_buffer = calloc(1, (1 + topo.num_cpus) * 2048);
outp = output_buffer;
if (outp == NULL)
err(-1, "calloc output buffer");
}
void print_version() {
- fprintf(outf, "turbostat version 19.03.20"
+ fprintf(outf, "turbostat version 19.08.31"
" - Len Brown <lenb@kernel.org>\n");
}
endif
x86_energy_perf_policy : x86_energy_perf_policy.c
-override CFLAGS += -Wall -I../../../include
+override CFLAGS += -O2 -Wall -I../../../include
override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
+override CFLAGS += -D_FORTIFY_SOURCE=2
%: %.c
@mkdir -p $(BUILD_OUTPUT)
Hardware P-States (HWP) are effectively an expansion of hardware
P-state control from the opportunistic turbo-mode P-state range
to include the entire range of available P-states.
-On Broadwell Xeon, the initial HWP implementation, EBP influenced HWP.
+On Broadwell Xeon, the initial HWP implementation, EPB influenced HWP.
That influence was removed in subsequent generations,
where it was moved to the
Energy_Performance_Preference (EPP) field in
progname = argv[0];
- while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw",
+ while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw:",
long_options, &option_index)) != -1) {
switch (opt) {
case 'a':
if (system("/sbin/modprobe msr > /dev/null 2>&1"))
err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
}
+
+static void get_cpuid_or_exit(unsigned int leaf,
+ unsigned int *eax, unsigned int *ebx,
+ unsigned int *ecx, unsigned int *edx)
+{
+ if (!__get_cpuid(leaf, eax, ebx, ecx, edx))
+ errx(1, "Processor not supported\n");
+}
+
/*
* early_cpuid()
* initialize turbo_is_enabled, has_hwp, has_epb
*/
void early_cpuid(void)
{
- unsigned int eax, ebx, ecx, edx, max_level;
+ unsigned int eax, ebx, ecx, edx;
unsigned int fms, family, model;
- __get_cpuid(0, &max_level, &ebx, &ecx, &edx);
-
- if (max_level < 6)
- errx(1, "Processor not supported\n");
-
- __get_cpuid(1, &fms, &ebx, &ecx, &edx);
+ get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx);
family = (fms >> 8) & 0xf;
model = (fms >> 4) & 0xf;
if (family == 6 || family == 0xf)
bdx_highest_ratio = msr & 0xFF;
}
- __get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+ get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx);
turbo_is_enabled = (eax >> 1) & 1;
has_hwp = (eax >> 7) & 1;
has_epb = (ecx >> 3) & 1;
eax = ebx = ecx = edx = 0;
- __get_cpuid(0, &max_level, &ebx, &ecx, &edx);
+ get_cpuid_or_exit(0, &max_level, &ebx, &ecx, &edx);
if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
genuine_intel = 1;
fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
(char *)&ebx, (char *)&edx, (char *)&ecx);
- __get_cpuid(1, &fms, &ebx, &ecx, &edx);
+ get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx);
family = (fms >> 8) & 0xf;
model = (fms >> 4) & 0xf;
stepping = fms & 0xf;
errx(1, "CPUID: no MSR");
- __get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
+ get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx);
/* turbo_is_enabled already set */
/* has_hwp already set */
has_hwp_notify = eax & (1 << 8);
EXTRA_WARNINGS += -Wold-style-definition
EXTRA_WARNINGS += -Wpacked
EXTRA_WARNINGS += -Wredundant-decls
-EXTRA_WARNINGS += -Wshadow
EXTRA_WARNINGS += -Wstrict-prototypes
EXTRA_WARNINGS += -Wswitch-default
EXTRA_WARNINGS += -Wswitch-enum
# will do for now and keep the above -Wstrict-aliasing=3 in place
# in newer systems.
# Needed for the __raw_cmpxchg in tools/arch/x86/include/asm/cmpxchg.h
+#
+# See https://lkml.org/lkml/2006/11/28/253 and https://gcc.gnu.org/gcc-4.8/changes.html,
+# that takes into account Linus's comments (search for Wshadow) for the reasoning about
+# -Wshadow not being interesting before gcc 4.8.
+
ifneq ($(filter 3.%,$(MAKE_VERSION)),) # make-3
EXTRA_WARNINGS += -fno-strict-aliasing
+EXTRA_WARNINGS += -Wno-shadow
+else
+EXTRA_WARNINGS += -Wshadow
endif
ifneq ($(findstring $(MAKEFLAGS), w),w)
}
else {
- die "Unknow option $opt\n";
+ die "Unknown option $opt\n";
}
}
}
}
run_command "cp $good_start $good" or die "failed to copy to $good\n";
- run_command "cp $bad_start $bad" or die "faield to copy to $bad\n";
+ run_command "cp $bad_start $bad" or die "failed to copy to $bad\n";
} else {
if ( ! -f $good ) {
die "Can not find file $good\n";
BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c)))
TEST_GEN_FILES = $(BPF_OBJ_FILES)
+BTF_C_FILES = $(wildcard progs/btf_dump_test_case_*.c)
+TEST_FILES = $(BTF_C_FILES)
+
# Also test sub-register code-gen if LLVM has eBPF v3 processor support which
# contains both ALU32 and JMP32 instructions.
SUBREG_CODEGEN := $(shell echo "int cal(int a) { return a > 0; }" | \
test_lirc_mode2.sh \
test_skb_cgroup_id.sh \
test_flow_dissector.sh \
- test_xdp_vlan.sh \
+ test_xdp_vlan_mode_generic.sh \
+ test_xdp_vlan_mode_native.sh \
test_lwt_ip_encap.sh \
test_tcp_check_syncookie.sh \
test_tc_tunnel.sh \
TEST_PROGS_EXTENDED := with_addr.sh \
with_tunnels.sh \
tcp_client.py \
- tcp_server.py
+ tcp_server.py \
+ test_xdp_vlan.sh
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
CONFIG_MPLS_ROUTING=m
CONFIG_MPLS_IPTUNNEL=m
CONFIG_IPV6_SIT=m
+CONFIG_BPF_JIT=y
}
/* Rewrite destination. */
- if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) &&
- ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) {
+ if (ctx->user_ip6[0] == bpf_htonl(0xFACEB00C)) {
ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1);
ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);
}
snprintf(test_file, sizeof(test_file), "progs/%s.c", test_case->name);
+ if (access(test_file, R_OK) == -1)
+ /*
+ * When the test is run with O=, kselftest copies TEST_FILES
+ * without preserving the directory structure.
+ */
+ snprintf(test_file, sizeof(test_file), "%s.c",
+ test_case->name);
/*
* Diff test output and expected test output, contained between
* START-EXPECTED-OUTPUT and END-EXPECTED-OUTPUT lines in test case.
BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_get_local_storage),
- BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
- BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
BPF_FUNC_get_local_storage),
BPF_MOV64_IMM(BPF_REG_1, 1),
BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
- BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
+#include "bpf_endian.h"
#include "bpf_rlimit.h"
#include "bpf_util.h"
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip6[3])),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x01000000, 4),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
+ __bpf_constant_ntohl(0x00000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2),
/* if (ip == expected && port == expected) */
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x0100007F, 4),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_7,
+ __bpf_constant_ntohl(0x7F000001), 4),
BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
offsetof(struct bpf_sock, src_port)),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2),
#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Author: Jesper Dangaard Brouer <hawk@kernel.org>
-TESTNAME=xdp_vlan
+# Allow wrapper scripts to name test
+if [ -z "$TESTNAME" ]; then
+ TESTNAME=xdp_vlan
+fi
+
+# Default XDP mode
+XDP_MODE=xdpgeneric
usage() {
echo "Testing XDP + TC eBPF VLAN manipulations: $TESTNAME"
echo " -v | --verbose : Verbose"
echo " --flush : Flush before starting (e.g. after --interactive)"
echo " --interactive : Keep netns setup running after test-run"
+ echo " --mode=XXX : Choose XDP mode (xdp | xdpgeneric | xdpdrv)"
echo ""
}
+valid_xdp_mode()
+{
+ local mode=$1
+
+ case "$mode" in
+ xdpgeneric | xdpdrv | xdp)
+ return 0
+ ;;
+ *)
+ return 1
+ esac
+}
+
cleanup()
{
local status=$?
# Using external program "getopt" to get --long-options
OPTIONS=$(getopt -o hvfi: \
- --long verbose,flush,help,interactive,debug -- "$@")
+ --long verbose,flush,help,interactive,debug,mode: -- "$@")
if (( $? != 0 )); then
usage
echo "selftests: $TESTNAME [FAILED] Error calling getopt, unknown option?"
cleanup
shift
;;
+ --mode )
+ shift
+ XDP_MODE=$1
+ shift
+ ;;
-- )
shift
break
exit 1
fi
-ip link set dev lo xdp off 2>/dev/null > /dev/null
-if [ $? -ne 0 ];then
+valid_xdp_mode $XDP_MODE
+if [ $? -ne 0 ]; then
+ echo "selftests: $TESTNAME [FAILED] unknown XDP mode ($XDP_MODE)"
+ exit 1
+fi
+
+ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
+if [ $? -ne 0 ]; then
echo "selftests: $TESTNAME [SKIP] need ip xdp support"
exit 0
fi
# At this point, the hosts cannot reach each-other,
# because ns2 are using VLAN tags on the packets.
-ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Okay ping fails"'
+ip netns exec ns2 sh -c 'ping -W 1 -c 1 100.64.41.1 || echo "Success: First ping must fail"'
# Now we can use the test_xdp_vlan.c program to pop/push these VLAN tags
# First test: Remove VLAN by setting VLAN ID 0, using "xdp_vlan_change"
export XDP_PROG=xdp_vlan_change
-ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
# In ns1: egress use TC to add back VLAN tag 4011
# (del cmd)
prio 1 handle 1 bpf da obj $FILE sec tc_vlan_push
# Now the namespaces can reach each-other, test with ping:
-ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1
+ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2
# Second test: Replace xdp prog, that fully remove vlan header
#
# ETH_P_8021Q indication, and this cause overwriting of our changes.
#
export XDP_PROG=xdp_vlan_remove_outer2
-ip netns exec ns1 ip link set $DEVNS1 xdp off
-ip netns exec ns1 ip link set $DEVNS1 xdp object $FILE section $XDP_PROG
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE off
+ip netns exec ns1 ip link set $DEVNS1 $XDP_MODE object $FILE section $XDP_PROG
# Now the namespaces should still be able reach each-other, test with ping:
-ip netns exec ns2 ping -W 2 -c 3 $IPADDR1
-ip netns exec ns1 ping -W 2 -c 3 $IPADDR2
+ip netns exec ns2 ping -i 0.2 -W 2 -c 2 $IPADDR1
+ip netns exec ns1 ping -i 0.2 -W 2 -c 2 $IPADDR2
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Exit on failure
+set -e
+
+# Wrapper script to test generic-XDP
+export TESTNAME=xdp_vlan_mode_generic
+./test_xdp_vlan.sh --mode=xdpgeneric
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Exit on failure
+set -e
+
+# Wrapper script to test native-XDP
+export TESTNAME=xdp_vlan_mode_native
+./test_xdp_vlan.sh --mode=xdpdrv
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
},
+{
+ "read gso_segs from CGROUP_SKB",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_1,
+ offsetof(struct __sk_buff, gso_segs)),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
{
"write gso_segs from CGROUP_SKB",
.insns = {
.errstr = "loop detected",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
+{
+ "not-taken loop with back jump to 1st insn",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 123),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 4, -2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .retval = 123,
+},
+{
+ "taken loop with back jump to 1st insn",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, -3),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .retval = 55,
+},
strtok(NULL, delim);
strtok(NULL, delim);
- if (strcmp(fs, "cgroup") == 0 &&
- strcmp(type, "cgroup2") == 0) {
+ if (strcmp(type, "cgroup2") == 0) {
strncpy(root, mount, len);
return 0;
}
stop_traffic
- log_test "UC performace under MC overload"
+ log_test "UC performance under MC overload"
echo "UC-only throughput $(humanize $ucth1)"
echo "UC+MC throughput $(humanize $ucth2)"
stop_traffic
- log_test "MC performace under UC overload"
+ log_test "MC performance under UC overload"
echo " ingress UC throughput $(humanize ${uc_ir})"
echo " egress UC throughput $(humanize ${uc_er})"
echo " sent $attempts BC ARPs, got $passes responses"
# override by exporting to your environment prior running this script.
# For instance this script assumes you do not have xfs loaded upon boot.
# If this is false, export DEFAULT_KMOD_FS="ext4" prior to running this
-# script if the filesyste module you don't have loaded upon bootup
+# script if the filesystem module you don't have loaded upon bootup
# is ext4 instead. Refer to allow_user_defaults() for a list of user
# override variables possible.
#
config_reset()
{
if ! echo -n "1" >"$DIR"/reset; then
- echo "$0: reset shuld have worked" >&2
+ echo "$0: reset should have worked" >&2
exit 1
fi
}
echo Example uses:
echo
echo "${TEST_NAME}.sh -- executes all tests"
- echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recomended"
+ echo "${TEST_NAME}.sh -t 0008 -- Executes test ID 0008 number of times is recommended"
echo "${TEST_NAME}.sh -w 0008 -- Watch test ID 0008 run until an error occurs"
echo "${TEST_NAME}.sh -s 0008 -- Run test ID 0008 once"
echo "${TEST_NAME}.sh -c 0008 3 -- Run test ID 0008 three times"
#ifndef __KSELFTEST_H
#define __KSELFTEST_H
+#include <errno.h>
#include <stdlib.h>
#include <unistd.h>
#include <stdarg.h>
static inline void ksft_print_msg(const char *msg, ...)
{
+ int saved_errno = errno;
va_list args;
va_start(args, msg);
printf("# ");
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
}
static inline void ksft_test_result_pass(const char *msg, ...)
{
+ int saved_errno = errno;
va_list args;
ksft_cnt.ksft_pass++;
va_start(args, msg);
printf("ok %d ", ksft_test_num());
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
}
static inline void ksft_test_result_fail(const char *msg, ...)
{
+ int saved_errno = errno;
va_list args;
ksft_cnt.ksft_fail++;
va_start(args, msg);
printf("not ok %d ", ksft_test_num());
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
}
static inline void ksft_test_result_skip(const char *msg, ...)
{
+ int saved_errno = errno;
va_list args;
ksft_cnt.ksft_xskip++;
va_start(args, msg);
printf("not ok %d # SKIP ", ksft_test_num());
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
}
static inline void ksft_test_result_error(const char *msg, ...)
{
+ int saved_errno = errno;
va_list args;
ksft_cnt.ksft_error++;
va_start(args, msg);
printf("not ok %d # error ", ksft_test_num());
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
}
static inline int ksft_exit_fail_msg(const char *msg, ...)
{
+ int saved_errno = errno;
va_list args;
va_start(args, msg);
printf("Bail out! ");
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
static inline int ksft_exit_skip(const char *msg, ...)
{
if (msg) {
+ int saved_errno = errno;
va_list args;
va_start(args, msg);
printf("not ok %d # SKIP ", 1 + ksft_test_num());
+ errno = saved_errno;
vprintf(msg, args);
va_end(args);
} else {
+/s390x/sync_regs_test
/x86_64/cr4_cpuid_sync_test
/x86_64/evmcs_test
/x86_64/hyperv_cpuid
-/x86_64/kvm_create_max_vcpus
/x86_64/mmio_warning_test
/x86_64/platform_info_test
/x86_64/set_sregs_test
/x86_64/vmx_tsc_adjust_test
/clear_dirty_log_test
/dirty_log_test
+/kvm_create_max_vcpus
--- /dev/null
+CONFIG_KVM=y
+CONFIG_KVM_INTEL=y
+CONFIG_KVM_AMD=y
struct hv_enlightened_vmcs *current_evmcs;
struct hv_vp_assist_page *current_vp_assist;
+int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id);
+
static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist)
{
u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XSAVE, r: %i",
r);
- r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
- r);
+ if (kvm_check_cap(KVM_CAP_XCRS)) {
+ r = ioctl(vcpu->fd, KVM_GET_XCRS, &state->xcrs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_XCRS, r: %i",
+ r);
+ }
r = ioctl(vcpu->fd, KVM_GET_SREGS, &state->sregs);
TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
r);
- r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
- TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
- r);
+ if (kvm_check_cap(KVM_CAP_XCRS)) {
+ r = ioctl(vcpu->fd, KVM_SET_XCRS, &state->xcrs);
+ TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XCRS, r: %i",
+ r);
+ }
r = ioctl(vcpu->fd, KVM_SET_SREGS, &state->sregs);
TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
bool enable_evmcs;
+int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id)
+{
+ uint16_t evmcs_ver;
+
+ struct kvm_enable_cap enable_evmcs_cap = {
+ .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
+ .args[0] = (unsigned long)&evmcs_ver
+ };
+
+ vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+ /* KVM should return supported EVMCS version range */
+ TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
+ (evmcs_ver & 0xff) > 0,
+ "Incorrect EVMCS version range: %x:%x\n",
+ evmcs_ver & 0xff, evmcs_ver >> 8);
+
+ return evmcs_ver;
+}
+
/* Allocate memory regions for nested VMX tests.
*
* Input Args:
struct kvm_x86_state *state;
struct ucall uc;
int stage;
- uint16_t evmcs_ver;
- struct kvm_enable_cap enable_evmcs_cap = {
- .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
- .args[0] = (unsigned long)&evmcs_ver
- };
/* Create VM */
vm = vm_create_default(VCPU_ID, 0, guest_code);
exit(KSFT_SKIP);
}
- vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
-
- /* KVM should return supported EVMCS version range */
- TEST_ASSERT(((evmcs_ver >> 8) >= (evmcs_ver & 0xff)) &&
- (evmcs_ver & 0xff) > 0,
- "Incorrect EVMCS version range: %x:%x\n",
- evmcs_ver & 0xff, evmcs_ver >> 8);
+ vcpu_enable_evmcs(vm, VCPU_ID);
run = vcpu_state(vm, VCPU_ID);
kvm_vm_restart(vm, O_RDWR);
vm_vcpu_add(vm, VCPU_ID);
vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
- vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+ vcpu_enable_evmcs(vm, VCPU_ID);
vcpu_load_state(vm, VCPU_ID, state);
run = vcpu_state(vm, VCPU_ID);
free(state);
#include "test_util.h"
#include "kvm_util.h"
#include "processor.h"
+#include "vmx.h"
#define VCPU_ID 0
{
struct kvm_vm *vm;
int rv;
- uint16_t evmcs_ver;
struct kvm_cpuid2 *hv_cpuid_entries;
- struct kvm_enable_cap enable_evmcs_cap = {
- .cap = KVM_CAP_HYPERV_ENLIGHTENED_VMCS,
- .args[0] = (unsigned long)&evmcs_ver
- };
/* Tell stdout not to buffer its content */
setbuf(stdout, NULL);
free(hv_cpuid_entries);
- rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
-
- if (rv) {
+ if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
fprintf(stderr,
"Enlightened VMCS is unsupported, skip related test\n");
goto vm_free;
}
+ vcpu_enable_evmcs(vm, VCPU_ID);
+
hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
if (!hv_cpuid_entries)
return 1;
msr_platform_info = vcpu_get_msr(vm, VCPU_ID, MSR_PLATFORM_INFO);
vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO,
msr_platform_info | MSR_PLATFORM_INFO_MAX_TURBO_RATIO);
- test_msr_platform_info_disabled(vm);
test_msr_platform_info_enabled(vm);
+ test_msr_platform_info_disabled(vm);
vcpu_set_msr(vm, VCPU_ID, MSR_PLATFORM_INFO, msr_platform_info);
kvm_vm_free(vm);
#define VMCS12_REVISION 0x11e57ed0
#define VCPU_ID 5
+bool have_evmcs;
+
void test_nested_state(struct kvm_vm *vm, struct kvm_nested_state *state)
{
- volatile struct kvm_run *run;
-
vcpu_nested_state_set(vm, VCPU_ID, state, false);
- run = vcpu_state(vm, VCPU_ID);
- vcpu_run(vm, VCPU_ID);
- TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
- "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n",
- run->exit_reason,
- exit_reason_str(run->exit_reason));
}
void test_nested_state_expect_errno(struct kvm_vm *vm,
struct kvm_nested_state *state,
int expected_errno)
{
- volatile struct kvm_run *run;
int rv;
rv = vcpu_nested_state_set(vm, VCPU_ID, state, true);
"Expected %s (%d) from vcpu_nested_state_set but got rv: %i errno: %s (%d)",
strerror(expected_errno), expected_errno, rv, strerror(errno),
errno);
- run = vcpu_state(vm, VCPU_ID);
- vcpu_run(vm, VCPU_ID);
- TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
- "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s),\n",
- run->exit_reason,
- exit_reason_str(run->exit_reason));
}
void test_nested_state_expect_einval(struct kvm_vm *vm,
{
memset(state, 0, size);
state->flags = KVM_STATE_NESTED_GUEST_MODE |
- KVM_STATE_NESTED_RUN_PENDING |
- KVM_STATE_NESTED_EVMCS;
+ KVM_STATE_NESTED_RUN_PENDING;
+ if (have_evmcs)
+ state->flags |= KVM_STATE_NESTED_EVMCS;
state->format = 0;
state->size = size;
state->hdr.vmx.vmxon_pa = 0x1000;
/*
* Setting vmxon_pa == -1ull and vmcs_pa == -1ull exits early without
* setting the nested state but flags other than eVMCS must be clear.
+ * The eVMCS flag can be set if the enlightened VMCS capability has
+ * been enabled.
*/
set_default_vmx_state(state, state_sz);
state->hdr.vmx.vmxon_pa = -1ull;
state->hdr.vmx.vmcs12_pa = -1ull;
test_nested_state_expect_einval(vm, state);
- state->flags = KVM_STATE_NESTED_EVMCS;
+ state->flags &= KVM_STATE_NESTED_EVMCS;
+ if (have_evmcs) {
+ test_nested_state_expect_einval(vm, state);
+ vcpu_enable_evmcs(vm, VCPU_ID);
+ }
test_nested_state(vm, state);
/* It is invalid to have vmxon_pa == -1ull and SMM flags non-zero. */
struct kvm_nested_state state;
struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+ have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS);
+
if (!kvm_check_cap(KVM_CAP_NESTED_STATE)) {
printf("KVM_CAP_NESTED_STATE not available, skipping test\n");
exit(KSFT_SKIP);
echo "$1" > /dev/kmsg
}
+# skip(msg) - testing can't proceed
+# msg - explanation
+function skip() {
+ log "SKIP: $1"
+ echo "SKIP: $1" >&2
+ exit 4
+}
+
# die(msg) - game over, man
# msg - dying words
function die() {
exit 1
}
-# set_dynamic_debug() - setup kernel dynamic debug
-# TODO - push and pop this config?
+function push_dynamic_debug() {
+ DYNAMIC_DEBUG=$(grep '^kernel/livepatch' /sys/kernel/debug/dynamic_debug/control | \
+ awk -F'[: ]' '{print "file " $1 " line " $2 " " $4}')
+}
+
+function pop_dynamic_debug() {
+ if [[ -n "$DYNAMIC_DEBUG" ]]; then
+ echo -n "$DYNAMIC_DEBUG" > /sys/kernel/debug/dynamic_debug/control
+ fi
+}
+
+# set_dynamic_debug() - save the current dynamic debug config and tweak
+# it for the self-tests. Set a script exit trap
+# that restores the original config.
function set_dynamic_debug() {
- cat << EOF > /sys/kernel/debug/dynamic_debug/control
-file kernel/livepatch/* +p
-func klp_try_switch_task -p
-EOF
+ push_dynamic_debug
+ trap pop_dynamic_debug EXIT INT TERM HUP
+ cat <<-EOF > /sys/kernel/debug/dynamic_debug/control
+ file kernel/livepatch/* +p
+ func klp_try_switch_task -p
+ EOF
}
# loop_until(cmd) - loop a command until it is successful or $MAX_RETRIES,
done
}
+function assert_mod() {
+ local mod="$1"
+
+ modprobe --dry-run "$mod" &>/dev/null
+}
+
function is_livepatch_mod() {
local mod="$1"
function load_mod() {
local mod="$1"; shift
+ assert_mod "$mod" ||
+ skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
+
is_livepatch_mod "$mod" &&
die "use load_lp() to load the livepatch module $mod"
function load_lp_nowait() {
local mod="$1"; shift
+ assert_mod "$mod" ||
+ skip "unable to load module ${mod}, verify CONFIG_TEST_LIVEPATCH=m and run self-tests as root"
+
is_livepatch_mod "$mod" ||
die "module $mod is not a livepatch"
tls
txring_overwrite
ip_defrag
+ipv6_flowlabel
+ipv6_flowlabel_mgr
so_txtime
-flowlabel
-flowlabel_mgr
tcp_fastopen_backup_key
ip route add vrf v$ol1 192.0.2.16/28 \
nexthop dev g1a \
nexthop dev g1b
-
- tc qdisc add dev $ul1 clsact
- tc filter add dev $ul1 egress pref 111 prot ipv4 \
- flower dst_ip 192.0.2.66 action pass
- tc filter add dev $ul1 egress pref 222 prot ipv4 \
- flower dst_ip 192.0.2.82 action pass
}
sw1_destroy()
{
- tc qdisc del dev $ul1 clsact
-
ip route del vrf v$ol1 192.0.2.16/28
ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
ip route add vrf v$ol2 192.0.2.0/28 \
nexthop dev g2a \
nexthop dev g2b
+
+ tc qdisc add dev $ul2 clsact
+ tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+ flower vlan_id 111 action pass
+ tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+ flower vlan_id 222 action pass
}
sw2_destroy()
{
+ tc qdisc del dev $ul2 clsact
+
ip route del vrf v$ol2 192.0.2.0/28
ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
sw1_create
sw2_create
h2_create
+
+ forwarding_enable
}
cleanup()
{
pre_cleanup
+ forwarding_restore
+
h2_destroy
sw2_destroy
sw1_destroy
nexthop dev g1a weight $weight1 \
nexthop dev g1b weight $weight2
- local t0_111=$(tc_rule_stats_get $ul1 111 egress)
- local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
ip vrf exec v$h1 \
$MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
-d 1msec -t udp "sp=1024,dp=0-32768"
- local t1_111=$(tc_rule_stats_get $ul1 111 egress)
- local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
local d111=$((t1_111 - t0_111))
local d222=$((t1_222 - t0_222))
ip netns exec "${NETNS}" ./tcp_fastopen_backup_key "$1"
val=$(ip netns exec "${NETNS}" nstat -az | \
grep TcpExtTCPFastOpenPassiveFail | awk '{print $2}')
- if [ $val -ne 0 ]; then
+ if [ "$val" != 0 ]; then
echo "FAIL: TcpExtTCPFastOpenPassiveFail non-zero"
return 1
fi
#define TLS_PAYLOAD_MAX_LEN 16384
#define SOL_TLS 282
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
+FIXTURE(tls_basic)
+{
+ int fd, cfd;
+ bool notls;
+};
+
+FIXTURE_SETUP(tls_basic)
+{
+ struct sockaddr_in addr;
+ socklen_t len;
+ int sfd, ret;
+
+ self->notls = false;
+ len = sizeof(addr);
+
+ addr.sin_family = AF_INET;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+
+ self->fd = socket(AF_INET, SOCK_STREAM, 0);
+ sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+ ret = bind(sfd, &addr, sizeof(addr));
+ ASSERT_EQ(ret, 0);
+ ret = listen(sfd, 10);
+ ASSERT_EQ(ret, 0);
+
+ ret = getsockname(sfd, &addr, &len);
+ ASSERT_EQ(ret, 0);
+
+ ret = connect(self->fd, &addr, sizeof(addr));
+ ASSERT_EQ(ret, 0);
+
+ self->cfd = accept(sfd, &addr, &len);
+ ASSERT_GE(self->cfd, 0);
+
+ close(sfd);
+
+ ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ if (ret != 0) {
+ ASSERT_EQ(errno, ENOENT);
+ self->notls = true;
+ printf("Failure setting TCP_ULP, testing without tls\n");
+ return;
+ }
+
+ ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ ASSERT_EQ(ret, 0);
+}
+
+FIXTURE_TEARDOWN(tls_basic)
+{
+ close(self->fd);
+ close(self->cfd);
+}
+
+/* Send some data through with ULP but no keys */
+TEST_F(tls_basic, base_base)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+ char buf[10];
+
+ ASSERT_EQ(strlen(test_str) + 1, send_len);
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+};
+
FIXTURE(tls)
{
int fd, cfd;
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
+TEST_F(tls, msg_more_unsent)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+ char buf[10];
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+ EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
+}
+
TEST_F(tls, sendmsg_single)
{
struct msghdr msg;
EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0);
}
+TEST_F(tls, bidir)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+ char buf[10];
+ int ret;
+
+ if (!self->notls) {
+ struct tls12_crypto_info_aes_gcm_128 tls12;
+
+ memset(&tls12, 0, sizeof(tls12));
+ tls12.info.version = TLS_1_3_VERSION;
+ tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+ ret = setsockopt(self->fd, SOL_TLS, TLS_RX, &tls12,
+ sizeof(tls12));
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(self->cfd, SOL_TLS, TLS_TX, &tls12,
+ sizeof(tls12));
+ ASSERT_EQ(ret, 0);
+ }
+
+ ASSERT_EQ(strlen(test_str) + 1, send_len);
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+
+ memset(buf, 0, sizeof(buf));
+
+ EXPECT_EQ(send(self->cfd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->fd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+};
+
TEST_F(tls, pollin)
{
char const *test_str = "test_poll";
EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
}
+TEST_F(tls, shutdown)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+ char buf[10];
+
+ ASSERT_EQ(strlen(test_str) + 1, send_len);
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+ EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+ EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+
+ shutdown(self->fd, SHUT_RDWR);
+ shutdown(self->cfd, SHUT_RDWR);
+}
+
+TEST_F(tls, shutdown_unsent)
+{
+ char const *test_str = "test_read";
+ int send_len = 10;
+
+ EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+
+ shutdown(self->fd, SHUT_RDWR);
+ shutdown(self->cfd, SHUT_RDWR);
+}
+
+TEST_F(tls, shutdown_reuse)
+{
+ struct sockaddr_in addr;
+ int ret;
+
+ shutdown(self->fd, SHUT_RDWR);
+ shutdown(self->cfd, SHUT_RDWR);
+ close(self->cfd);
+
+ addr.sin_family = AF_INET;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+
+ ret = bind(self->fd, &addr, sizeof(addr));
+ EXPECT_EQ(ret, 0);
+ ret = listen(self->fd, 10);
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EINVAL);
+
+ ret = connect(self->fd, &addr, sizeof(addr));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EISCONN);
+}
+
+TEST(non_established) {
+ struct tls12_crypto_info_aes_gcm_256 tls12;
+ struct sockaddr_in addr;
+ int sfd, ret, fd;
+ socklen_t len;
+
+ len = sizeof(addr);
+
+ memset(&tls12, 0, sizeof(tls12));
+ tls12.info.version = TLS_1_2_VERSION;
+ tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256;
+
+ addr.sin_family = AF_INET;
+ addr.sin_addr.s_addr = htonl(INADDR_ANY);
+ addr.sin_port = 0;
+
+ fd = socket(AF_INET, SOCK_STREAM, 0);
+ sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+ ret = bind(sfd, &addr, sizeof(addr));
+ ASSERT_EQ(ret, 0);
+ ret = listen(sfd, 10);
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ EXPECT_EQ(ret, -1);
+ /* TLS ULP not supported */
+ if (errno == ENOENT)
+ return;
+ EXPECT_EQ(errno, ENOTSUPP);
+
+ ret = setsockopt(sfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, ENOTSUPP);
+
+ ret = getsockname(sfd, &addr, &len);
+ ASSERT_EQ(ret, 0);
+
+ ret = connect(fd, &addr, sizeof(addr));
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ ASSERT_EQ(ret, 0);
+
+ ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EEXIST);
+
+ close(fd);
+ close(sfd);
+}
+
TEST(keysizes) {
struct tls12_crypto_info_aes_gcm_256 tls12;
struct sockaddr_in addr;
ip netns exec nsr1 nft list ruleset
fi
+KEY_SHA="0x"$(ps -xaf | sha1sum | cut -d " " -f 1)
+KEY_AES="0x"$(ps -xaf | md5sum | cut -d " " -f 1)
+SPI1=$RANDOM
+SPI2=$RANDOM
+
+if [ $SPI1 -eq $SPI2 ]; then
+ SPI2=$((SPI2+1))
+fi
+
+do_esp() {
+ local ns=$1
+ local me=$2
+ local remote=$3
+ local lnet=$4
+ local rnet=$5
+ local spi_out=$6
+ local spi_in=$7
+
+ ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet
+ ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet
+
+ # to encrypt packets as they go out (includes forwarded packets that need encapsulation)
+ ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 1 action allow
+ # to fwd decrypted packets after esp processing:
+ ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 1 action allow
+
+}
+
+do_esp nsr1 192.168.10.1 192.168.10.2 10.0.1.0/24 10.0.2.0/24 $SPI1 $SPI2
+
+do_esp nsr2 192.168.10.2 192.168.10.1 10.0.2.0/24 10.0.1.0/24 $SPI2 $SPI1
+
+ip netns exec nsr1 nft delete table ip nat
+
+# restore default routes
+ip -net ns2 route del 192.168.10.1 via 10.0.2.1
+ip -net ns2 route add default via 10.0.2.1
+ip -net ns2 route add default via dead:2::1
+
+test_tcp_forwarding ns1 ns2
+if [ $? -eq 0 ] ;then
+ echo "PASS: ipsec tunnel mode for ns1/ns2"
+else
+ echo "FAIL: ipsec tunnel mode for ns1/ns2"
+ ip netns exec nsr1 nft list ruleset 1>&2
+ ip netns exec nsr1 cat /proc/net/xfrm_stat 1>&2
+fi
+
exit $ret
ret = sys_pidfd_send_signal(pidfd, 0, NULL, 0);
if (ret < 0) {
- /*
- * pidfd_send_signal() will currently return ENOSYS when
- * CONFIG_PROC_FS is not set.
- */
if (errno == ENOSYS)
ksft_exit_skip(
- "%s test: pidfd_send_signal() syscall not supported (Ensure that CONFIG_PROC_FS=y is set)\n",
+ "%s test: pidfd_send_signal() syscall not supported\n",
test_name);
ksft_exit_fail_msg("%s test: Failed to send signal\n",
cmdlist.insert(0, self.args.NAMES['NS'])
cmdlist.insert(0, 'exec')
cmdlist.insert(0, 'netns')
- cmdlist.insert(0, 'ip')
+ cmdlist.insert(0, self.args.NAMES['IP'])
else:
pass
return command
def _ports_create(self):
- cmd = 'ip link add $DEV0 type veth peer name $DEV1'
+ cmd = '$IP link add $DEV0 type veth peer name $DEV1'
self._exec_cmd('pre', cmd)
- cmd = 'ip link set $DEV0 up'
+ cmd = '$IP link set $DEV0 up'
self._exec_cmd('pre', cmd)
if not self.args.namespace:
- cmd = 'ip link set $DEV1 up'
+ cmd = '$IP link set $DEV1 up'
self._exec_cmd('pre', cmd)
def _ports_destroy(self):
- cmd = 'ip link del $DEV0'
+ cmd = '$IP link del $DEV0'
self._exec_cmd('post', cmd)
def _ns_create(self):
'''
self._ports_create()
if self.args.namespace:
- cmd = 'ip netns add {}'.format(self.args.NAMES['NS'])
+ cmd = '$IP netns add {}'.format(self.args.NAMES['NS'])
self._exec_cmd('pre', cmd)
- cmd = 'ip link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
+ cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS'])
self._exec_cmd('pre', cmd)
- cmd = 'ip -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
+ cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS'])
self._exec_cmd('pre', cmd)
if self.args.device:
- cmd = 'ip link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
+ cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS'])
self._exec_cmd('pre', cmd)
- cmd = 'ip -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
+ cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS'])
self._exec_cmd('pre', cmd)
def _ns_destroy(self):
devices as well)
'''
if self.args.namespace:
- cmd = 'ip netns delete {}'.format(self.args.NAMES['NS'])
+ cmd = '$IP netns delete {}'.format(self.args.NAMES['NS'])
self._exec_cmd('post', cmd)
def _exec_cmd(self, stage, command):
"teardown": [
"$TC actions flush action skbedit"
]
+ },
+ {
+ "id": "630c",
+ "name": "Add batch of 32 skbedit actions with all parameters and cookie",
+ "category": [
+ "actions",
+ "skbedit"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action skbedit",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action skbedit",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "32",
+ "teardown": [
+ "$TC actions flush action skbedit"
+ ]
+ },
+ {
+ "id": "706d",
+ "name": "Delete batch of 32 skbedit actions with all parameters",
+ "category": [
+ "actions",
+ "skbedit"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action skbedit",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit queue_mapping 2 priority 10 mark 7/0xaabbccdd ptype host inheritdsfield index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action skbedit index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action skbedit",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
}
]
"teardown": [
"$TC actions flush action vlan"
]
+ },
+ {
+ "id": "294e",
+ "name": "Add batch of 32 vlan push actions with cookie",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "32",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "56f7",
+ "name": "Delete batch of 32 vlan push actions",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan push protocol 802.1q id 4094 priority 7 pipe index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "759f",
+ "name": "Add batch of 32 vlan pop actions with cookie",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop continue index \\$i cookie aabbccddeeff112233445566778800a1 \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "32",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "c84a",
+ "name": "Delete batch of 32 vlan pop actions",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan pop index \\$i \\\"; args=\\\"\\$args\\$cmd\\\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action vlan index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
}
]
printf("[OK]\tExecuting the vsyscall page failed: #PF(0x%lx)\n",
segv_err);
} else {
- printf("[FAILT]\tExecution failed with the wrong error: #PF(0x%lx)\n",
+ printf("[FAIL]\tExecution failed with the wrong error: #PF(0x%lx)\n",
segv_err);
return 1;
}
header-test- += linux/bpf_perf_event.h
endif
-ifeq ($(SRCARCH),s390)
-header-test- += asm/zcrypt.h
-endif
-
ifeq ($(SRCARCH),sparc)
header-test- += asm/stat.h
header-test- += asm/uctx.h
return ret;
}
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return false;
-}
-
int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
return 0;
void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
+ /*
+ * If we're about to block (most likely because we've just hit a
+ * WFI), we need to sync back the state of the GIC CPU interface
+ * so that we have the lastest PMR and group enables. This ensures
+ * that kvm_arch_vcpu_runnable has up-to-date data to decide
+ * whether we have pending interrupts.
+ */
+ preempt_disable();
+ kvm_vgic_vmcr_sync(vcpu);
+ preempt_enable();
+
kvm_vgic_v4_enable_doorbell(vcpu);
}
/* Set up the timer */
kvm_timer_vcpu_init(vcpu);
+ kvm_pmu_vcpu_init(vcpu);
+
kvm_arm_reset_debug_ptr(vcpu);
return kvm_vgic_vcpu_init(vcpu);
* Ensure we set mode to IN_GUEST_MODE after we disable
* interrupts and before the final VCPU requests check.
* See the comment in kvm_vcpu_exiting_guest_mode() and
- * Documentation/virtual/kvm/vcpu-requests.rst
+ * Documentation/virt/kvm/vcpu-requests.rst
*/
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
case 7:
cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3);
cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2);
+ /* Fall through */
case 6:
cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1);
+ /* Fall through */
default:
cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0);
}
case 7:
cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3);
cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2);
+ /* Fall through */
case 6:
cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1);
+ /* Fall through */
default:
cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0);
}
case 7:
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3);
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2);
+ /* Fall through */
case 6:
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1);
+ /* Fall through */
default:
__vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0);
}
case 7:
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3);
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2);
+ /* Fall through */
case 6:
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1);
+ /* Fall through */
default:
__vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0);
}
unsigned int len;
int mask;
+ /* Detect an already handled MMIO return */
+ if (unlikely(!vcpu->mmio_needed))
+ return 0;
+
+ vcpu->mmio_needed = 0;
+
if (!run->mmio.is_write) {
len = run->mmio.len;
if (len > sizeof(unsigned long))
run->mmio.is_write = is_write;
run->mmio.phys_addr = fault_ipa;
run->mmio.len = len;
+ vcpu->mmio_needed = 1;
if (!ret) {
/* We handled the access successfully in the kernel. */
kvm_pmu_release_perf_event(pmc);
}
+/**
+ * kvm_pmu_vcpu_init - assign pmu counter idx for cpu
+ * @vcpu: The vcpu pointer
+ *
+ */
+void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ int i;
+ struct kvm_pmu *pmu = &vcpu->arch.pmu;
+
+ for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+ pmu->pmc[i].idx = i;
+}
+
/**
* kvm_pmu_vcpu_reset - reset pmu state for cpu
* @vcpu: The vcpu pointer
int i;
struct kvm_pmu *pmu = &vcpu->arch.pmu;
- for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+ for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
- pmu->pmc[i].idx = i;
- }
bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
}
#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <kvm/arm_vgic.h>
+#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
#include "vgic.h"
irq->vcpu = NULL;
irq->target_vcpu = vcpu0;
kref_init(&irq->refcount);
- if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+ switch (dist->vgic_model) {
+ case KVM_DEV_TYPE_ARM_VGIC_V2:
irq->targets = 0;
irq->group = 0;
- } else {
+ break;
+ case KVM_DEV_TYPE_ARM_VGIC_V3:
irq->mpidr = 0;
irq->group = 1;
+ break;
+ default:
+ kfree(dist->spis);
+ return -EINVAL;
}
}
return 0;
irq->intid = i;
irq->vcpu = NULL;
irq->target_vcpu = vcpu;
- irq->targets = 1U << vcpu->vcpu_id;
kref_init(&irq->refcount);
if (vgic_irq_is_sgi(i)) {
/* SGIs */
/* PPIs */
irq->config = VGIC_CONFIG_LEVEL;
}
-
- if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
- irq->group = 1;
- else
- irq->group = 0;
}
if (!irqchip_in_kernel(vcpu->kvm))
for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
struct vgic_irq *irq = &vgic_cpu->private_irqs[i];
- if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ switch (dist->vgic_model) {
+ case KVM_DEV_TYPE_ARM_VGIC_V3:
irq->group = 1;
- else
+ irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
+ break;
+ case KVM_DEV_TYPE_ARM_VGIC_V2:
irq->group = 0;
+ irq->targets = 1U << idx;
+ break;
+ default:
+ ret = -EINVAL;
+ goto out;
+ }
}
}
* pending state of interrupt is latched in pending_latch variable.
* Userspace will save and restore pending state and line_level
* separately.
- * Refer to Documentation/virtual/kvm/devices/arm-vgic-v3.txt
+ * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.txt
* for handling of ISPENDR and ICPENDR.
*/
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
raw_spin_lock_irqsave(&irq->irq_lock, flags);
+ if (vgic_irq_is_mapped_level(irq)) {
+ bool was_high = irq->line_level;
+
+ /*
+ * We need to update the state of the interrupt because
+ * the guest might have changed the state of the device
+ * while the interrupt was disabled at the VGIC level.
+ */
+ irq->line_level = vgic_get_phys_line_level(irq);
+ /*
+ * Deactivate the physical interrupt so the GIC will let
+ * us know when it is asserted again.
+ */
+ if (!irq->active && was_high && !irq->line_level)
+ vgic_irq_set_phys_active(irq, false);
+ }
irq->enabled = true;
vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
vgic_irq_set_phys_active(irq, true);
}
+static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
+{
+ return (vgic_irq_is_sgi(irq->intid) &&
+ vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2);
+}
+
void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+ /* GICD_ISPENDR0 SGI bits are WI */
+ if (is_vgic_v2_sgi(vcpu, irq)) {
+ vgic_put_irq(vcpu->kvm, irq);
+ continue;
+ }
+
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw)
vgic_hw_irq_spending(vcpu, irq, is_uaccess);
for_each_set_bit(i, &val, len * 8) {
struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
+ /* GICD_ICPENDR0 SGI bits are WI */
+ if (is_vgic_v2_sgi(vcpu, irq)) {
+ vgic_put_irq(vcpu->kvm, irq);
+ continue;
+ }
+
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw)
if (vgic_irq_is_sgi(irq->intid)) {
u32 src = ffs(irq->source);
- BUG_ON(!src);
+ if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n",
+ irq->intid))
+ return;
+
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
if (irq->source) {
kvm_vgic_global_state.vctrl_base + GICH_APR);
}
-void vgic_v2_put(struct kvm_vcpu *vcpu)
+void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
cpu_if->vgic_vmcr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_VMCR);
+}
+
+void vgic_v2_put(struct kvm_vcpu *vcpu)
+{
+ struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
+
+ vgic_v2_vmcr_sync(vcpu);
cpu_if->vgic_apr = readl_relaxed(kvm_vgic_global_state.vctrl_base + GICH_APR);
}
model == KVM_DEV_TYPE_ARM_VGIC_V2) {
u32 src = ffs(irq->source);
- BUG_ON(!src);
+ if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n",
+ irq->intid))
+ return;
+
val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT;
irq->source &= ~(1 << (src - 1));
if (irq->source) {
__vgic_v3_activate_traps(vcpu);
}
-void vgic_v3_put(struct kvm_vcpu *vcpu)
+void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu)
{
struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
if (likely(cpu_if->vgic_sre))
cpu_if->vgic_vmcr = kvm_call_hyp_ret(__vgic_v3_read_vmcr);
+}
+
+void vgic_v3_put(struct kvm_vcpu *vcpu)
+{
+ vgic_v3_vmcr_sync(vcpu);
kvm_call_hyp(__vgic_v3_save_aprs, vcpu);
bool penda, pendb;
int ret;
+ /*
+ * list_sort may call this function with the same element when
+ * the list is fairly long.
+ */
+ if (unlikely(irqa == irqb))
+ return 0;
+
raw_spin_lock(&irqa->irq_lock);
raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING);
vgic_v3_put(vcpu);
}
+void kvm_vgic_vmcr_sync(struct kvm_vcpu *vcpu)
+{
+ if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
+ return;
+
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_vmcr_sync(vcpu);
+ else
+ vgic_v3_vmcr_sync(vcpu);
+}
+
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
VGIC_AFFINITY_LEVEL(val, 3))
/*
- * As per Documentation/virtual/kvm/devices/arm-vgic-v3.txt,
+ * As per Documentation/virt/kvm/devices/arm-vgic-v3.txt,
* below macros are defined for CPUREG encoding.
*/
#define KVM_REG_ARM_VGIC_SYSREG_OP0_MASK 0x000000000000c000
KVM_REG_ARM_VGIC_SYSREG_OP2_MASK)
/*
- * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt,
+ * As per Documentation/virt/kvm/devices/arm-vgic-its.txt,
* below macros are defined for ITS table entry encoding.
*/
#define KVM_ITS_CTE_VALID_SHIFT 63
void vgic_v2_init_lrs(void);
void vgic_v2_load(struct kvm_vcpu *vcpu);
void vgic_v2_put(struct kvm_vcpu *vcpu);
+void vgic_v2_vmcr_sync(struct kvm_vcpu *vcpu);
void vgic_v2_save_state(struct kvm_vcpu *vcpu);
void vgic_v2_restore_state(struct kvm_vcpu *vcpu);
void vgic_v3_load(struct kvm_vcpu *vcpu);
void vgic_v3_put(struct kvm_vcpu *vcpu);
+void vgic_v3_vmcr_sync(struct kvm_vcpu *vcpu);
bool vgic_has_its(struct kvm *kvm);
int kvm_vgic_register_its_device(void);
if (!kvm_is_reserved_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
- if (!PageReserved(page))
- SetPageDirty(page);
+ SetPageDirty(page);
}
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
#endif
}
+/*
+ * Unlike kvm_arch_vcpu_runnable, this function is called outside
+ * a vcpu_load/vcpu_put pair. However, for most architectures
+ * kvm_arch_vcpu_runnable does not require vcpu_load.
+ */
+bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ return kvm_arch_vcpu_runnable(vcpu);
+}
+
+static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ if (kvm_arch_dy_runnable(vcpu))
+ return true;
+
+#ifdef CONFIG_KVM_ASYNC_PF
+ if (!list_empty_careful(&vcpu->async_pf.done))
+ return true;
+#endif
+
+ return false;
+}
+
void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
{
struct kvm *kvm = me->kvm;
continue;
if (vcpu == me)
continue;
- if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+ if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
continue;
- if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
+ if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
+ !kvm_arch_vcpu_in_kernel(vcpu))
continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;
return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
}
-static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
+#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
char dir_name[ITOA_MAX_LEN * 2];
- int ret;
-
- if (!kvm_arch_has_vcpu_debugfs())
- return 0;
if (!debugfs_initialized())
- return 0;
+ return;
snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
vcpu->debugfs_dentry = debugfs_create_dir(dir_name,
- vcpu->kvm->debugfs_dentry);
- if (!vcpu->debugfs_dentry)
- return -ENOMEM;
-
- ret = kvm_arch_create_vcpu_debugfs(vcpu);
- if (ret < 0) {
- debugfs_remove_recursive(vcpu->debugfs_dentry);
- return ret;
- }
+ vcpu->kvm->debugfs_dentry);
- return 0;
+ kvm_arch_create_vcpu_debugfs(vcpu);
+#endif
}
/*
if (r)
goto vcpu_destroy;
- r = kvm_create_vcpu_debugfs(vcpu);
- if (r)
- goto vcpu_destroy;
+ kvm_create_vcpu_debugfs(vcpu);
mutex_lock(&kvm->lock);
if (kvm_get_vcpu_by_id(kvm, id)) {
{
struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
- vcpu->preempted = false;
+ WRITE_ONCE(vcpu->preempted, false);
WRITE_ONCE(vcpu->ready, false);
kvm_arch_sched_in(vcpu, cpu);
struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
if (current->state == TASK_RUNNING) {
- vcpu->preempted = true;
+ WRITE_ONCE(vcpu->preempted, true);
WRITE_ONCE(vcpu->ready, true);
}
kvm_arch_vcpu_put(vcpu);
projects / linux-2.6-microblaze.git / commitdiff