use PPIs designated for specific cpus. The irq field is interpreted
like this::
- bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 |
+ bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 |
field: | vcpu2_index | irq_type | vcpu_index | irq_id |
The irq_type field has the following values:
Errors:
====== ============================================================
- ENOENT no such register
- EINVAL invalid register ID, or no such register or used with VMs in
+ ENOENT no such register
+ EINVAL invalid register ID, or no such register or used with VMs in
protected virtualization mode on s390
- EPERM (arm64) register access not allowed before vcpu finalization
+ EPERM (arm64) register access not allowed before vcpu finalization
====== ============================================================
(These error codes are indicative only: do not rely on a specific error
Errors include:
======== ============================================================
- ENOENT no such register
- EINVAL invalid register ID, or no such register or used with VMs in
+ ENOENT no such register
+ EINVAL invalid register ID, or no such register or used with VMs in
protected virtualization mode on s390
- EPERM (arm64) register access not allowed before vcpu finalization
+ EPERM (arm64) register access not allowed before vcpu finalization
======== ============================================================
(These error codes are indicative only: do not rely on a specific error
Errors:
====== =================================================================
- EINVAL the target is unknown, or the combination of features is invalid.
- ENOENT a features bit specified is unknown.
+ 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
+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.
The initial values are defined as:
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).
+ 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).
===== ==============================================================
::
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 |
+ 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
trap and emulate MSRs that are outside of the scope of KVM as well as
limit the attack surface on KVM's MSR emulation code.
-8.28 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
-----------------------------
Architectures: x86
will run faster if you say N here.
See also the SMP-HOWTO available at
- <http://www.tldp.org/docs.html#howto>.
+ <https://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
#include "ksize.h"
extern unsigned long switch_to_osf_pal(unsigned long nr,
- struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
+ struct pcb_struct *pcb_va, struct pcb_struct *pcb_pa,
unsigned long *vptb);
extern void move_stack(unsigned long new_stack);
START_ADDR KSEG address of the entry point of kernel code.
ZERO_PGE KSEG address of page full of zeroes, but
- upon entry to kerne cvan be expected
+ upon entry to kernel, it can be expected
to hold the parameter list and possible
INTRD information.
__attribute__ ((format (printf, 1, 2)));
/*
- * gzip delarations
+ * gzip declarations
*/
#define OF(args) args
#define STATIC static
CONFIG_ALPHA_LEGACY_START_ADDRESS=y
CONFIG_MATHEMU=y
CONFIG_CRYPTO_HMAC=y
+CONFIG_DEVTMPFS=y
#include <uapi/asm/compiler.h>
-/* Some idiots over in <linux/compiler.h> thought inline should imply
- always_inline. This breaks stuff. We'll include this file whenever
- we run into such problems. */
-
-#include <linux/compiler.h>
-#undef inline
-#undef __inline__
-#undef __inline
-#undef __always_inline
-#define __always_inline inline __attribute__((always_inline))
-
#endif /* __ALPHA_COMPILER_H */
return AUDIT_ARCH_ALPHA;
}
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->r0;
+}
+
#endif /* _ASM_ALPHA_SYSCALL_H */
return -EFAULT;
state = ¤t_thread_info()->ieee_state;
- /* Update softare trap enable bits. */
+ /* Update software trap enable bits. */
*state = (*state & ~IEEE_SW_MASK) | (swcr & IEEE_SW_MASK);
/* Update the real fpcr. */
state = ¤t_thread_info()->ieee_state;
exc &= IEEE_STATUS_MASK;
- /* Update softare trap enable bits. */
+ /* Update software trap enable bits. */
swcr = (*state & IEEE_SW_MASK) | exc;
*state |= exc;
* Check that CPU performance counters are supported.
* - currently support EV67 and later CPUs.
* - actually some later revisions of the EV6 have the same PMC model as the
- * EV67 but we don't do suffiently deep CPU detection to detect them.
+ * EV67 but we don't do sufficiently deep CPU detection to detect them.
* Bad luck to the very few people who might have one, I guess.
*/
static int supported_cpu(void)
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
childstack->r10 = kthread_arg;
- childregs->hae = alpha_mv.hae_cache,
+ childregs->hae = alpha_mv.hae_cache;
childti->pcb.usp = 0;
return 0;
}
i, cluster->usage, cluster->start_pfn,
cluster->start_pfn + cluster->numpages);
- /* Bit 0 is console/PALcode reserved. Bit 1 is
- non-volatile memory -- we might want to mark
- this for later. */
- if (cluster->usage & 3)
- continue;
-
end = cluster->start_pfn + cluster->numpages;
if (end > max_low_pfn)
max_low_pfn = end;
memblock_add(PFN_PHYS(cluster->start_pfn),
cluster->numpages << PAGE_SHIFT);
+
+ /* Bit 0 is console/PALcode reserved. Bit 1 is
+ non-volatile memory -- we might want to mark
+ this for later. */
+ if (cluster->usage & 3)
+ memblock_reserve(PFN_PHYS(cluster->start_pfn),
+ cluster->numpages << PAGE_SHIFT);
}
/*
smp_send_stop(void)
{
cpumask_t to_whom;
- cpumask_copy(&to_whom, cpu_possible_mask);
+ cpumask_copy(&to_whom, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &to_whom);
#ifdef DEBUG_IPI_MSG
if (hard_smp_processor_id() != boot_cpu_id)
/* Use default IO. */
pci_add_resource(&bridge->windows, &ioport_resource);
- /* Irongate PCI memory aperture, calculate requred size before
+ /* Irongate PCI memory aperture, calculate required size before
setting it up. */
pci_add_resource(&bridge->windows, &irongate_mem);
long error;
/* Check the UAC bits to decide what the user wants us to do
- with the unaliged access. */
+ with the unaligned access. */
if (!(current_thread_info()->status & TS_UAC_NOPRINT)) {
if (__ratelimit(&ratelimit)) {
long do_alpha_fp_emul_imprecise(struct pt_regs *, unsigned long);
long do_alpha_fp_emul(unsigned long);
-int init_module(void)
+static int alpha_fp_emul_init_module(void)
{
save_emul_imprecise = alpha_fp_emul_imprecise;
save_emul = alpha_fp_emul;
alpha_fp_emul = do_alpha_fp_emul;
return 0;
}
+module_init(alpha_fp_emul_init_module);
-void cleanup_module(void)
+static void alpha_fp_emul_cleanup_module(void)
{
alpha_fp_emul_imprecise = save_emul_imprecise;
alpha_fp_emul = save_emul;
}
+module_exit(alpha_fp_emul_cleanup_module);
#undef alpha_fp_emul_imprecise
#define alpha_fp_emul_imprecise do_alpha_fp_emul_imprecise
egress:
return si_code;
}
+
+EXPORT_SYMBOL(__udiv_qrnnd);
fallthrough; /* ??? */
case 256:
vram_size += PAGE_SIZE * 256;
+ break;
default:
break;
}
vma_shift = get_vma_page_shift(vma, hva);
}
- shared = (vma->vm_flags & VM_PFNMAP);
+ shared = (vma->vm_flags & VM_SHARED);
switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
DEFINE_CLK(sys, "sys.0", MCF_BUSCLK);
static struct clk_lookup m525x_clk_lookup[] = {
- CLKDEV_INIT(NULL, "pll.0", &pll),
+ CLKDEV_INIT(NULL, "pll.0", &clk_pll),
CLKDEV_INIT(NULL, "sys.0", &clk_sys),
CLKDEV_INIT("mcftmr.0", NULL, &clk_sys),
CLKDEV_INIT("mcftmr.1", NULL, &clk_sys),
u64 instruction_sigp_init_cpu_reset;
u64 instruction_sigp_cpu_reset;
u64 instruction_sigp_unknown;
- u64 diagnose_10;
- u64 diagnose_44;
- u64 diagnose_9c;
- u64 diagnose_9c_ignored;
- u64 diagnose_9c_forward;
- u64 diagnose_258;
- u64 diagnose_308;
- u64 diagnose_500;
- u64 diagnose_other;
+ u64 instruction_diagnose_10;
+ u64 instruction_diagnose_44;
+ u64 instruction_diagnose_9c;
+ u64 diag_9c_ignored;
+ u64 diag_9c_forward;
+ u64 instruction_diagnose_258;
+ u64 instruction_diagnose_308;
+ u64 instruction_diagnose_500;
+ u64 instruction_diagnose_other;
u64 pfault_sync;
};
start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + PAGE_SIZE;
- vcpu->stat.diagnose_10++;
+ vcpu->stat.instruction_diagnose_10++;
if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
|| start < 2 * PAGE_SIZE)
VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx",
vcpu->run->s.regs.gprs[rx]);
- vcpu->stat.diagnose_258++;
+ vcpu->stat.instruction_diagnose_258++;
if (vcpu->run->s.regs.gprs[rx] & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
- vcpu->stat.diagnose_44++;
+ vcpu->stat.instruction_diagnose_44++;
kvm_vcpu_on_spin(vcpu, true);
return 0;
}
int tid;
tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
- vcpu->stat.diagnose_9c++;
+ vcpu->stat.instruction_diagnose_9c++;
/* yield to self */
if (tid == vcpu->vcpu_id)
VCPU_EVENT(vcpu, 5,
"diag time slice end directed to %d: yield forwarded",
tid);
- vcpu->stat.diagnose_9c_forward++;
+ vcpu->stat.diag_9c_forward++;
return 0;
}
return 0;
no_yield:
VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid);
- vcpu->stat.diagnose_9c_ignored++;
+ vcpu->stat.diag_9c_ignored++;
return 0;
}
unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode);
- vcpu->stat.diagnose_308++;
+ vcpu->stat.instruction_diagnose_308++;
switch (subcode) {
case 3:
vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
{
int ret;
- vcpu->stat.diagnose_500++;
+ vcpu->stat.instruction_diagnose_500++;
/* No virtio-ccw notification? Get out quickly. */
if (!vcpu->kvm->arch.css_support ||
(vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
case 0x500:
return __diag_virtio_hypercall(vcpu);
default:
- vcpu->stat.diagnose_other++;
+ vcpu->stat.instruction_diagnose_other++;
return -EOPNOTSUPP;
}
}
STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset),
STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset),
STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown),
- STATS_DESC_COUNTER(VCPU, diagnose_10),
- STATS_DESC_COUNTER(VCPU, diagnose_44),
- STATS_DESC_COUNTER(VCPU, diagnose_9c),
- STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored),
- STATS_DESC_COUNTER(VCPU, diagnose_9c_forward),
- STATS_DESC_COUNTER(VCPU, diagnose_258),
- STATS_DESC_COUNTER(VCPU, diagnose_308),
- STATS_DESC_COUNTER(VCPU, diagnose_500),
- STATS_DESC_COUNTER(VCPU, diagnose_other),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_10),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_44),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_9c),
+ STATS_DESC_COUNTER(VCPU, diag_9c_ignored),
+ STATS_DESC_COUNTER(VCPU, diag_9c_forward),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_258),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_308),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_500),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_other),
STATS_DESC_COUNTER(VCPU, pfault_sync)
};
static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) ==
static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
{
ioapic->rtc_status.pending_eoi = 0;
- bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+ bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1);
}
static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
struct dest_map {
/* vcpu bitmap where IRQ has been sent */
- DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
+ DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);
/*
* Vector sent to a given vcpu, only valid when
* the vcpu's bit in map is set
*/
- u8 vectors[KVM_MAX_VCPU_ID];
+ u8 vectors[KVM_MAX_VCPU_ID + 1];
};
void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct vmcb *vmcb = svm->vmcb;
+ struct vmcb *vmcb = svm->vmcb01.ptr;
bool activated = kvm_vcpu_apicv_active(vcpu);
if (!enable_apicv)
* Also covers avic_vapic_bar, avic_backing_page, avic_logical_id,
* avic_physical_id.
*/
- WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK);
+ WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
/* Copied from vmcb01. msrpm_base can be overwritten later. */
svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl;
}
/* Copy state save area fields which are handled by VMRUN */
-void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
- struct vmcb_save_area *to_save)
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+ struct vmcb_save_area *from_save)
{
to_save->es = from_save->es;
to_save->cs = from_save->cs;
to_save->cpl = 0;
}
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
{
to_vmcb->save.fs = from_vmcb->save.fs;
to_vmcb->save.gs = from_vmcb->save.gs;
svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
- svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save);
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
nested_load_control_from_vmcb12(svm, ctl);
svm_switch_vmcb(svm, &svm->nested.vmcb02);
goto error_free_vmsa_page;
}
- svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
svm->vmcb01.ptr = page_address(vmcb01_page);
svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
svm_switch_vmcb(svm, &svm->vmcb01);
init_vmcb(vcpu);
+ svm_vcpu_init_msrpm(vcpu, svm->msrpm);
+
svm_init_osvw(vcpu);
vcpu->arch.microcode_version = 0x01000065;
{
struct vmcb_control_area *control;
- /* The following fields are ignored when AVIC is enabled */
- WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu));
+ /*
+ * The following fields are ignored when AVIC is enabled
+ */
+ WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
+
svm_set_intercept(svm, INTERCEPT_VINTR);
/*
ret = kvm_skip_emulated_instruction(vcpu);
if (vmload) {
- nested_svm_vmloadsave(vmcb12, svm->vmcb);
+ svm_copy_vmloadsave_state(svm->vmcb, vmcb12);
svm->sysenter_eip_hi = 0;
svm->sysenter_esp_hi = 0;
- } else
- nested_svm_vmloadsave(svm->vmcb, vmcb12);
+ } else {
+ svm_copy_vmloadsave_state(vmcb12, svm->vmcb);
+ }
kvm_vcpu_unmap(vcpu, &map, true);
BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
- svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
- map_save.hva + 0x400);
+ svm_copy_vmrun_state(map_save.hva + 0x400,
+ &svm->vmcb01.ptr->save);
kvm_vcpu_unmap(vcpu, &map_save, true);
}
&map_save) == -EINVAL)
return 1;
- svm_copy_vmrun_state(map_save.hva + 0x400,
- &svm->vmcb01.ptr->save);
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+ map_save.hva + 0x400);
kvm_vcpu_unmap(vcpu, &map_save, true);
}
void svm_free_nested(struct vcpu_svm *svm);
int svm_allocate_nested(struct vcpu_svm *svm);
int nested_svm_vmrun(struct kvm_vcpu *vcpu);
-void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
- struct vmcb_save_area *to_save);
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+ struct vmcb_save_area *from_save);
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
int nested_svm_vmexit(struct vcpu_svm *svm);
static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
* as we mark it dirty unconditionally towards end of vcpu
* init phase.
*/
- if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
+ if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
hve->hv_enlightenments_control.msr_bitmap)
vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
}
return 1;
break;
case MSR_KVM_ASYNC_PF_ACK:
- if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
return 1;
if (data & 0x1) {
vcpu->arch.apf.pageready_pending = false;
msr_info->data = vcpu->arch.apf.msr_int_val;
break;
case MSR_KVM_ASYNC_PF_ACK:
- if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
return 1;
msr_info->data = 0;
if (!chip_ctx)
return -ENOMEM;
chip_ctx->chip_num = bp->chip_num;
+ chip_ctx->hw_stats_size = bp->hw_ring_stats_size;
rdev->chip_ctx = chip_ctx;
/* rest members to follow eventually */
dma_addr_t dma_map,
u32 *fw_stats_ctx_id)
{
+ struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx;
struct hwrm_stat_ctx_alloc_output resp = {0};
struct hwrm_stat_ctx_alloc_input req = {0};
struct bnxt_en_dev *en_dev = rdev->en_dev;
bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1);
req.update_period_ms = cpu_to_le32(1000);
req.stats_dma_addr = cpu_to_le64(dma_map);
- req.stats_dma_length = cpu_to_le16(sizeof(struct ctx_hw_stats_ext));
+ req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size);
req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE;
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev,
struct bnxt_qplib_stats *stats);
static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+ struct bnxt_qplib_chip_ctx *cctx,
struct bnxt_qplib_stats *stats);
/* PBL */
goto fail;
stats_alloc:
/* Stats */
- rc = bnxt_qplib_alloc_stats_ctx(res->pdev, &ctx->stats);
+ rc = bnxt_qplib_alloc_stats_ctx(res->pdev, res->cctx, &ctx->stats);
if (rc)
goto fail;
}
static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+ struct bnxt_qplib_chip_ctx *cctx,
struct bnxt_qplib_stats *stats)
{
memset(stats, 0, sizeof(*stats));
stats->fw_id = -1;
- /* 128 byte aligned context memory is required only for 57500.
- * However making this unconditional, it does not harm previous
- * generation.
- */
- stats->size = ALIGN(sizeof(struct ctx_hw_stats), 128);
+ stats->size = cctx->hw_stats_size;
stats->dma = dma_alloc_coherent(&pdev->dev, stats->size,
&stats->dma_map, GFP_KERNEL);
if (!stats->dma) {
u16 chip_num;
u8 chip_rev;
u8 chip_metal;
+ u16 hw_stats_size;
struct bnxt_qplib_drv_modes modes;
};
* parses fpm commit info and copy base value
* of hmc objects in hmc_info
*/
-static enum irdma_status_code
+static void
irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf,
struct irdma_hmc_obj_info *info, u32 *sd)
{
else
*sd = (u32)(size >> 21);
- return 0;
}
/**
* @dev: sc device struct
* @count: allocate count
*/
-enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count)
+void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count)
{
writel(count, dev->hw_regs[IRDMA_AEQALLOC]);
-
- return 0;
}
/**
ret_code = irdma_sc_commit_fpm_val(dev->cqp, 0, hmc_info->hmc_fn_id,
&commit_fpm_mem, true, wait_type);
if (!ret_code)
- ret_code = irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf,
- hmc_info->hmc_obj,
- &hmc_info->sd_table.sd_cnt);
+ irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf,
+ hmc_info->hmc_obj,
+ &hmc_info->sd_table.sd_cnt);
print_hex_dump_debug("HMC: COMMIT FPM BUFFER", DUMP_PREFIX_OFFSET, 16,
8, commit_fpm_mem.va, IRDMA_COMMIT_FPM_BUF_SIZE,
false);
* irdma_set_hw_rsrc - set hw memory resources.
* @rf: RDMA PCI function
*/
-static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf)
+static void irdma_set_hw_rsrc(struct irdma_pci_f *rf)
{
rf->allocated_qps = (void *)(rf->mem_rsrc +
(sizeof(struct irdma_arp_entry) * rf->arp_table_size));
spin_lock_init(&rf->arp_lock);
spin_lock_init(&rf->qptable_lock);
spin_lock_init(&rf->qh_list_lock);
-
- return 0;
}
/**
rf->arp_table = (struct irdma_arp_entry *)rf->mem_rsrc;
- ret = irdma_set_hw_rsrc(rf);
- if (ret)
- goto set_hw_rsrc_fail;
+ irdma_set_hw_rsrc(rf);
set_bit(0, rf->allocated_mrs);
set_bit(0, rf->allocated_qps);
return 0;
-set_hw_rsrc_fail:
- kfree(rf->mem_rsrc);
- rf->mem_rsrc = NULL;
mem_rsrc_kzalloc_fail:
kfree(rf->allocated_ws_nodes);
rf->allocated_ws_nodes = NULL;
pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
}
-static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf)
+static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf,
+ struct ice_vsi *vsi)
{
struct irdma_pci_f *rf = iwdev->rf;
- struct ice_vsi *vsi = ice_get_main_vsi(pf);
rf->cdev = pf;
rf->gen_ops.register_qset = irdma_lan_register_qset;
struct iidc_auxiliary_dev,
adev);
struct ice_pf *pf = iidc_adev->pf;
+ struct ice_vsi *vsi = ice_get_main_vsi(pf);
struct iidc_qos_params qos_info = {};
struct irdma_device *iwdev;
struct irdma_pci_f *rf;
struct irdma_l2params l2params = {};
int err;
+ if (!vsi)
+ return -EIO;
iwdev = ib_alloc_device(irdma_device, ibdev);
if (!iwdev)
return -ENOMEM;
return -ENOMEM;
}
- irdma_fill_device_info(iwdev, pf);
+ irdma_fill_device_info(iwdev, pf, vsi);
rf = iwdev->rf;
if (irdma_ctrl_init_hw(rf)) {
struct irdma_aeq_init_info *info);
enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq,
struct irdma_aeqe_info *info);
-enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev,
- u32 count);
+void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count);
void irdma_sc_pd_init(struct irdma_sc_dev *dev, struct irdma_sc_pd *pd, u32 pd_id,
int abi_ver);
enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp,
struct irdma_post_rq_info *info)
{
- u32 total_size = 0, wqe_idx, i, byte_off;
+ u32 wqe_idx, i, byte_off;
u32 addl_frag_cnt;
__le64 *wqe;
u64 hdr;
if (qp->max_rq_frag_cnt < info->num_sges)
return IRDMA_ERR_INVALID_FRAG_COUNT;
- for (i = 0; i < info->num_sges; i++)
- total_size += info->sg_list[i].len;
-
wqe = irdma_qp_get_next_recv_wqe(qp, &wqe_idx);
if (!wqe)
return IRDMA_ERR_QP_TOOMANY_WRS_POSTED;
* @iwqp: qp ptr
* @init_info: initialize info to return
*/
-static int irdma_setup_virt_qp(struct irdma_device *iwdev,
+static void irdma_setup_virt_qp(struct irdma_device *iwdev,
struct irdma_qp *iwqp,
struct irdma_qp_init_info *init_info)
{
init_info->sq_pa = qpmr->sq_pbl.addr;
init_info->rq_pa = qpmr->rq_pbl.addr;
}
-
- return 0;
}
/**
}
}
init_info.qp_uk_init_info.abi_ver = iwpd->sc_pd.abi_ver;
- err_code = irdma_setup_virt_qp(iwdev, iwqp, &init_info);
+ irdma_setup_virt_qp(iwdev, iwqp, &init_info);
} else {
init_info.qp_uk_init_info.abi_ver = IRDMA_ABI_VER;
err_code = irdma_setup_kmode_qp(iwdev, iwqp, &init_info, init_attr);
int num_buf;
void *vaddr;
int err;
+ int i;
umem = ib_umem_get(pd->ibpd.device, start, length, access);
if (IS_ERR(umem)) {
- pr_warn("err %d from rxe_umem_get\n",
- (int)PTR_ERR(umem));
+ pr_warn("%s: Unable to pin memory region err = %d\n",
+ __func__, (int)PTR_ERR(umem));
err = PTR_ERR(umem);
- goto err1;
+ goto err_out;
}
mr->umem = umem;
err = rxe_mr_alloc(mr, num_buf);
if (err) {
- pr_warn("err %d from rxe_mr_alloc\n", err);
- ib_umem_release(umem);
- goto err1;
+ pr_warn("%s: Unable to allocate memory for map\n",
+ __func__);
+ goto err_release_umem;
}
mr->page_shift = PAGE_SHIFT;
vaddr = page_address(sg_page_iter_page(&sg_iter));
if (!vaddr) {
- pr_warn("null vaddr\n");
- ib_umem_release(umem);
+ pr_warn("%s: Unable to get virtual address\n",
+ __func__);
err = -ENOMEM;
- goto err1;
+ goto err_cleanup_map;
}
buf->addr = (uintptr_t)vaddr;
return 0;
-err1:
+err_cleanup_map:
+ for (i = 0; i < mr->num_map; i++)
+ kfree(mr->map[i]);
+ kfree(mr->map);
+err_release_umem:
+ ib_umem_release(umem);
+err_out:
return err;
}
#define AMD_PMC_RESULT_CMD_UNKNOWN 0xFE
#define AMD_PMC_RESULT_FAILED 0xFF
+/* FCH SSC Registers */
+#define FCH_S0I3_ENTRY_TIME_L_OFFSET 0x30
+#define FCH_S0I3_ENTRY_TIME_H_OFFSET 0x34
+#define FCH_S0I3_EXIT_TIME_L_OFFSET 0x38
+#define FCH_S0I3_EXIT_TIME_H_OFFSET 0x3C
+#define FCH_SSC_MAPPING_SIZE 0x800
+#define FCH_BASE_PHY_ADDR_LOW 0xFED81100
+#define FCH_BASE_PHY_ADDR_HIGH 0x00000000
+
+/* SMU Message Definations */
+#define SMU_MSG_GETSMUVERSION 0x02
+#define SMU_MSG_LOG_GETDRAM_ADDR_HI 0x04
+#define SMU_MSG_LOG_GETDRAM_ADDR_LO 0x05
+#define SMU_MSG_LOG_START 0x06
+#define SMU_MSG_LOG_RESET 0x07
+#define SMU_MSG_LOG_DUMP_DATA 0x08
+#define SMU_MSG_GET_SUP_CONSTRAINTS 0x09
/* List of supported CPU ids */
#define AMD_CPU_ID_RV 0x15D0
#define AMD_CPU_ID_RN 0x1630
#define AMD_CPU_ID_PCO AMD_CPU_ID_RV
#define AMD_CPU_ID_CZN AMD_CPU_ID_RN
+#define AMD_CPU_ID_YC 0x14B5
-#define AMD_SMU_FW_VERSION 0x0
#define PMC_MSG_DELAY_MIN_US 100
#define RESPONSE_REGISTER_LOOP_MAX 200
+#define SOC_SUBSYSTEM_IP_MAX 12
+#define DELAY_MIN_US 2000
+#define DELAY_MAX_US 3000
enum amd_pmc_def {
MSG_TEST = 0x01,
MSG_OS_HINT_PCO,
MSG_OS_HINT_RN,
};
+struct amd_pmc_bit_map {
+ const char *name;
+ u32 bit_mask;
+};
+
+static const struct amd_pmc_bit_map soc15_ip_blk[] = {
+ {"DISPLAY", BIT(0)},
+ {"CPU", BIT(1)},
+ {"GFX", BIT(2)},
+ {"VDD", BIT(3)},
+ {"ACP", BIT(4)},
+ {"VCN", BIT(5)},
+ {"ISP", BIT(6)},
+ {"NBIO", BIT(7)},
+ {"DF", BIT(8)},
+ {"USB0", BIT(9)},
+ {"USB1", BIT(10)},
+ {"LAPIC", BIT(11)},
+ {}
+};
+
struct amd_pmc_dev {
void __iomem *regbase;
- void __iomem *smu_base;
+ void __iomem *smu_virt_addr;
+ void __iomem *fch_virt_addr;
u32 base_addr;
u32 cpu_id;
+ u32 active_ips;
struct device *dev;
+ struct mutex lock; /* generic mutex lock */
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbgfs_dir;
#endif /* CONFIG_DEBUG_FS */
};
static struct amd_pmc_dev pmc;
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret);
static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset)
{
iowrite32(val, dev->regbase + reg_offset);
}
+struct smu_metrics {
+ u32 table_version;
+ u32 hint_count;
+ u32 s0i3_cyclecount;
+ u32 timein_s0i2;
+ u64 timeentering_s0i3_lastcapture;
+ u64 timeentering_s0i3_totaltime;
+ u64 timeto_resume_to_os_lastcapture;
+ u64 timeto_resume_to_os_totaltime;
+ u64 timein_s0i3_lastcapture;
+ u64 timein_s0i3_totaltime;
+ u64 timein_swdrips_lastcapture;
+ u64 timein_swdrips_totaltime;
+ u64 timecondition_notmet_lastcapture[SOC_SUBSYSTEM_IP_MAX];
+ u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX];
+} __packed;
+
#ifdef CONFIG_DEBUG_FS
static int smu_fw_info_show(struct seq_file *s, void *unused)
{
struct amd_pmc_dev *dev = s->private;
- u32 value;
+ struct smu_metrics table;
+ int idx;
+
+ if (dev->cpu_id == AMD_CPU_ID_PCO)
+ return -EINVAL;
+
+ memcpy_fromio(&table, dev->smu_virt_addr, sizeof(struct smu_metrics));
+
+ seq_puts(s, "\n=== SMU Statistics ===\n");
+ seq_printf(s, "Table Version: %d\n", table.table_version);
+ seq_printf(s, "Hint Count: %d\n", table.hint_count);
+ seq_printf(s, "S0i3 Cycle Count: %d\n", table.s0i3_cyclecount);
+ seq_printf(s, "Time (in us) to S0i3: %lld\n", table.timeentering_s0i3_lastcapture);
+ seq_printf(s, "Time (in us) in S0i3: %lld\n", table.timein_s0i3_lastcapture);
+
+ seq_puts(s, "\n=== Active time (in us) ===\n");
+ for (idx = 0 ; idx < SOC_SUBSYSTEM_IP_MAX ; idx++) {
+ if (soc15_ip_blk[idx].bit_mask & dev->active_ips)
+ seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name,
+ table.timecondition_notmet_lastcapture[idx]);
+ }
- value = ioread32(dev->smu_base + AMD_SMU_FW_VERSION);
- seq_printf(s, "SMU FW Info: %x\n", value);
return 0;
}
DEFINE_SHOW_ATTRIBUTE(smu_fw_info);
+static int s0ix_stats_show(struct seq_file *s, void *unused)
+{
+ struct amd_pmc_dev *dev = s->private;
+ u64 entry_time, exit_time, residency;
+
+ entry_time = ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_H_OFFSET);
+ entry_time = entry_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_L_OFFSET);
+
+ exit_time = ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_H_OFFSET);
+ exit_time = exit_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_L_OFFSET);
+
+ /* It's in 48MHz. We need to convert it */
+ residency = exit_time - entry_time;
+ do_div(residency, 48);
+
+ seq_puts(s, "=== S0ix statistics ===\n");
+ seq_printf(s, "S0ix Entry Time: %lld\n", entry_time);
+ seq_printf(s, "S0ix Exit Time: %lld\n", exit_time);
+ seq_printf(s, "Residency Time: %lld\n", residency);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(s0ix_stats);
+
static void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev)
{
debugfs_remove_recursive(dev->dbgfs_dir);
dev->dbgfs_dir = debugfs_create_dir("amd_pmc", NULL);
debugfs_create_file("smu_fw_info", 0644, dev->dbgfs_dir, dev,
&smu_fw_info_fops);
+ debugfs_create_file("s0ix_stats", 0644, dev->dbgfs_dir, dev,
+ &s0ix_stats_fops);
}
#else
static inline void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev)
}
#endif /* CONFIG_DEBUG_FS */
+static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
+{
+ u32 phys_addr_low, phys_addr_hi;
+ u64 smu_phys_addr;
+
+ if (dev->cpu_id == AMD_CPU_ID_PCO)
+ return -EINVAL;
+
+ /* Get Active devices list from SMU */
+ amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1);
+
+ /* Get dram address */
+ amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1);
+ amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1);
+ smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low);
+
+ dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics));
+ if (!dev->smu_virt_addr)
+ return -ENOMEM;
+
+ /* Start the logging */
+ amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0);
+
+ return 0;
+}
+
static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
{
u32 value;
dev_dbg(dev->dev, "AMD_PMC_REGISTER_MESSAGE:%x\n", value);
}
-static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret)
{
int rc;
- u8 msg;
u32 val;
+ mutex_lock(&dev->lock);
/* Wait until we get a valid response */
rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
- val, val > 0, PMC_MSG_DELAY_MIN_US,
+ val, val != 0, PMC_MSG_DELAY_MIN_US,
PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX);
if (rc) {
dev_err(dev->dev, "failed to talk to SMU\n");
- return rc;
+ goto out_unlock;
}
/* Write zero to response register */
amd_pmc_reg_write(dev, AMD_PMC_REGISTER_ARGUMENT, set);
/* Write message ID to message ID register */
- msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO;
amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg);
- return 0;
+
+ /* Wait until we get a valid response */
+ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
+ val, val != 0, PMC_MSG_DELAY_MIN_US,
+ PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX);
+ if (rc) {
+ dev_err(dev->dev, "SMU response timed out\n");
+ goto out_unlock;
+ }
+
+ switch (val) {
+ case AMD_PMC_RESULT_OK:
+ if (ret) {
+ /* PMFW may take longer time to return back the data */
+ usleep_range(DELAY_MIN_US, 10 * DELAY_MAX_US);
+ *data = amd_pmc_reg_read(dev, AMD_PMC_REGISTER_ARGUMENT);
+ }
+ break;
+ case AMD_PMC_RESULT_CMD_REJECT_BUSY:
+ dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val);
+ rc = -EBUSY;
+ goto out_unlock;
+ case AMD_PMC_RESULT_CMD_UNKNOWN:
+ dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val);
+ rc = -EINVAL;
+ goto out_unlock;
+ case AMD_PMC_RESULT_CMD_REJECT_PREREQ:
+ case AMD_PMC_RESULT_FAILED:
+ default:
+ dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val);
+ rc = -EIO;
+ goto out_unlock;
+ }
+
+out_unlock:
+ mutex_unlock(&dev->lock);
+ amd_pmc_dump_registers(dev);
+ return rc;
+}
+
+static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
+{
+ switch (dev->cpu_id) {
+ case AMD_CPU_ID_PCO:
+ return MSG_OS_HINT_PCO;
+ case AMD_CPU_ID_RN:
+ case AMD_CPU_ID_YC:
+ return MSG_OS_HINT_RN;
+ }
+ return -EINVAL;
}
static int __maybe_unused amd_pmc_suspend(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
int rc;
+ u8 msg;
+
+ /* Reset and Start SMU logging - to monitor the s0i3 stats */
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0);
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0);
- rc = amd_pmc_send_cmd(pdev, 1);
+ msg = amd_pmc_get_os_hint(pdev);
+ rc = amd_pmc_send_cmd(pdev, 1, NULL, msg, 0);
if (rc)
dev_err(pdev->dev, "suspend failed\n");
- amd_pmc_dump_registers(pdev);
- return 0;
+ return rc;
}
static int __maybe_unused amd_pmc_resume(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
int rc;
+ u8 msg;
+
+ /* Let SMU know that we are looking for stats */
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_DUMP_DATA, 0);
- rc = amd_pmc_send_cmd(pdev, 0);
+ msg = amd_pmc_get_os_hint(pdev);
+ rc = amd_pmc_send_cmd(pdev, 0, NULL, msg, 0);
if (rc)
dev_err(pdev->dev, "resume failed\n");
- amd_pmc_dump_registers(pdev);
return 0;
}
};
static const struct pci_device_id pmc_pci_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CZN) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RN) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PCO) },
{
struct amd_pmc_dev *dev = &pmc;
struct pci_dev *rdev;
- u32 base_addr_lo;
- u32 base_addr_hi;
- u64 base_addr;
+ u32 base_addr_lo, base_addr_hi;
+ u64 base_addr, fch_phys_addr;
int err;
u32 val;
pci_dev_put(rdev);
base_addr = ((u64)base_addr_hi << 32 | base_addr_lo);
- dev->smu_base = devm_ioremap(dev->dev, base_addr, AMD_PMC_MAPPING_SIZE);
- if (!dev->smu_base)
- return -ENOMEM;
-
dev->regbase = devm_ioremap(dev->dev, base_addr + AMD_PMC_BASE_ADDR_OFFSET,
AMD_PMC_MAPPING_SIZE);
if (!dev->regbase)
return -ENOMEM;
- amd_pmc_dump_registers(dev);
+ mutex_init(&dev->lock);
+
+ /* Use FCH registers to get the S0ix stats */
+ base_addr_lo = FCH_BASE_PHY_ADDR_LOW;
+ base_addr_hi = FCH_BASE_PHY_ADDR_HIGH;
+ fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo);
+ dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE);
+ if (!dev->fch_virt_addr)
+ return -ENOMEM;
+
+ /* Use SMU to get the s0i3 debug stats */
+ err = amd_pmc_setup_smu_logging(dev);
+ if (err)
+ dev_err(dev->dev, "SMU debugging info not supported on this platform\n");
platform_set_drvdata(pdev, dev);
amd_pmc_dbgfs_register(dev);
struct amd_pmc_dev *dev = platform_get_drvdata(pdev);
amd_pmc_dbgfs_unregister(dev);
+ mutex_destroy(&dev->lock);
return 0;
}
static const struct acpi_device_id amd_pmc_acpi_ids[] = {
{"AMDI0005", 0},
+ {"AMDI0006", 0},
+ {"AMDI0007", 0},
{"AMD0004", 0},
{ }
};
static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"),
+ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"),
{"INT33D5", 0},
{"INTC1051", 0},
{"INTC1054", 0},
+ {"INTC1070", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
else
ret = tlmi_save_bios_settings("");
+ if (!ret && !tlmi_priv.pending_changes) {
+ tlmi_priv.pending_changes = true;
+ /* let userland know it may need to check reboot pending again */
+ kobject_uevent(&tlmi_priv.class_dev->kobj, KOBJ_CHANGE);
+ }
out:
kfree(auth_str);
kfree(set_str);
.sysfs_ops = &tlmi_kobj_sysfs_ops,
};
+static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", tlmi_priv.pending_changes);
+}
+
+static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot);
+
/* ---- Initialisation --------------------------------------------------------- */
static void tlmi_release_attr(void)
{
kobject_put(&tlmi_priv.setting[i]->kobj);
}
}
+ sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
kset_unregister(tlmi_priv.attribute_kset);
/* Authentication structures */
/* Build attribute */
tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset;
- ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype,
- NULL, "%s", tlmi_priv.setting[i]->display_name);
+ ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL,
+ "%s", tlmi_priv.setting[i]->display_name);
if (ret)
goto fail_create_attr;
goto fail_create_attr;
}
+ ret = sysfs_create_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
+ if (ret)
+ goto fail_create_attr;
+
/* Create authentication entries */
tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
&tlmi_priv.class_dev->kobj);
goto fail_create_attr;
}
tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset;
- ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype,
- NULL, "%s", "Admin");
+ ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin");
if (ret)
goto fail_create_attr;
goto fail_create_attr;
tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset;
- ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype,
- NULL, "%s", "System");
+ ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "System");
if (ret)
goto fail_create_attr;
pr_info("Error retrieving possible values for %d : %s\n",
i, setting->display_name);
}
+ kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
tlmi_priv.setting[i] = setting;
tlmi_priv.settings_count++;
kfree(item);
if (pwdcfg.password_state & TLMI_PAP_PWD)
tlmi_priv.pwd_admin->valid = true;
+ kobject_init(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype);
+
tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL);
if (!tlmi_priv.pwd_power) {
ret = -ENOMEM;
- goto fail_clear_attr;
+ goto fail_free_pwd_admin;
}
strscpy(tlmi_priv.pwd_power->kbdlang, "us", TLMI_LANG_MAXLEN);
tlmi_priv.pwd_power->encoding = TLMI_ENCODING_ASCII;
if (pwdcfg.password_state & TLMI_POP_PWD)
tlmi_priv.pwd_power->valid = true;
+ kobject_init(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype);
+
return 0;
+fail_free_pwd_admin:
+ kfree(tlmi_priv.pwd_admin);
fail_clear_attr:
- for (i = 0; i < TLMI_SETTINGS_COUNT; ++i)
- kfree(tlmi_priv.setting[i]);
+ for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) {
+ if (tlmi_priv.setting[i]) {
+ kfree(tlmi_priv.setting[i]->possible_values);
+ kfree(tlmi_priv.setting[i]);
+ }
+ }
return ret;
}
bool can_get_bios_selections;
bool can_set_bios_password;
bool can_get_password_settings;
+ bool pending_changes;
struct tlmi_attr_setting *setting[TLMI_SETTINGS_COUNT];
struct device *class_dev;
err = wireless_input_setup();
if (err)
- pr_err("Failed to setup hp wireless hotkeys\n");
+ pr_err("Failed to setup wireless hotkeys\n");
return err;
}
//#endif
clear_bit(SCpnt->device->id * 8 +
(u8)(SCpnt->device->lun & 0x7), host->busyluns);
+ fallthrough;
/*
* We found the command, and cleared it out. Either
case IS_COMPLETE:
break;
}
+ break;
default:
break;
with v4 shared libraries freely available from Compaq. If you're
going to use shared libraries from Tru64 version 5.0 or later, say N.
-config BINFMT_EM86
- tristate "Kernel support for Linux/Intel ELF binaries"
- depends on ALPHA
- help
- Say Y here if you want to be able to execute Linux/Intel ELF
- binaries just like native Alpha binaries on your Alpha machine. For
- this to work, you need to have the emulator /usr/bin/em86 in place.
-
- You can get the same functionality by saying N here and saying Y to
- "Kernel support for MISC binaries".
-
- You may answer M to compile the emulation support as a module and
- later load the module when you want to use a Linux/Intel binary. The
- module will be called binfmt_em86. If unsure, say Y.
-
config BINFMT_MISC
tristate "Kernel support for MISC binaries"
help
obj-$(CONFIG_FS_VERITY) += verity/
obj-$(CONFIG_FILE_LOCKING) += locks.o
obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o
-obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o
obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o
obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o
obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/fs/binfmt_em86.c
- *
- * Based on linux/fs/binfmt_script.c
- * Copyright (C) 1996 Martin von Löwis
- * original #!-checking implemented by tytso.
- *
- * em86 changes Copyright (C) 1997 Jim Paradis
- */
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/binfmts.h>
-#include <linux/elf.h>
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/errno.h>
-
-
-#define EM86_INTERP "/usr/bin/em86"
-#define EM86_I_NAME "em86"
-
-static int load_em86(struct linux_binprm *bprm)
-{
- const char *i_name, *i_arg;
- char *interp;
- struct file * file;
- int retval;
- struct elfhdr elf_ex;
-
- /* Make sure this is a Linux/Intel ELF executable... */
- elf_ex = *((struct elfhdr *)bprm->buf);
-
- if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
- return -ENOEXEC;
-
- /* First of all, some simple consistency checks */
- if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) ||
- (!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) ||
- !bprm->file->f_op->mmap) {
- return -ENOEXEC;
- }
-
- /* Need to be able to load the file after exec */
- if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
- return -ENOENT;
-
- /* Unlike in the script case, we don't have to do any hairy
- * parsing to find our interpreter... it's hardcoded!
- */
- interp = EM86_INTERP;
- i_name = EM86_I_NAME;
- i_arg = NULL; /* We reserve the right to add an arg later */
-
- /*
- * Splice in (1) the interpreter's name for argv[0]
- * (2) (optional) argument to interpreter
- * (3) filename of emulated file (replace argv[0])
- *
- * This is done in reverse order, because of how the
- * user environment and arguments are stored.
- */
- remove_arg_zero(bprm);
- retval = copy_string_kernel(bprm->filename, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
- if (i_arg) {
- retval = copy_string_kernel(i_arg, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
- }
- retval = copy_string_kernel(i_name, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
-
- /*
- * OK, now restart the process with the interpreter's inode.
- * Note that we use open_exec() as the name is now in kernel
- * space, and we don't need to copy it.
- */
- file = open_exec(interp);
- if (IS_ERR(file))
- return PTR_ERR(file);
-
- bprm->interpreter = file;
- return 0;
-}
-
-static struct linux_binfmt em86_format = {
- .module = THIS_MODULE,
- .load_binary = load_em86,
-};
-
-static int __init init_em86_binfmt(void)
-{
- register_binfmt(&em86_format);
- return 0;
-}
-
-static void __exit exit_em86_binfmt(void)
-{
- unregister_binfmt(&em86_format);
-}
-
-core_initcall(init_em86_binfmt);
-module_exit(exit_em86_binfmt);
-MODULE_LICENSE("GPL");
return err;
}
-static bool ext2_check_page(struct page *page, int quiet)
+static bool ext2_check_page(struct page *page, int quiet, char *kaddr)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
unsigned chunk_size = ext2_chunk_size(dir);
- char *kaddr = page_address(page);
u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
unsigned offs, rec_len;
unsigned limit = PAGE_SIZE;
if (!IS_ERR(page)) {
*page_addr = kmap_local_page(page);
if (unlikely(!PageChecked(page))) {
- if (PageError(page) || !ext2_check_page(page, quiet))
+ if (PageError(page) || !ext2_check_page(page, quiet,
+ *page_addr))
goto fail;
}
}
* ext2_delete_entry deletes a directory entry by merging it with the
* previous entry. Page is up-to-date.
*/
-int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
+int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page,
+ char *kaddr)
{
struct inode *inode = page->mapping->host;
- char *kaddr = page_address(page);
unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
unsigned to = ((char *)dir - kaddr) +
ext2_rec_len_from_disk(dir->rec_len);
de = ext2_next_entry(de);
}
if (pde)
- from = (char*)pde - (char*)page_address(page);
+ from = (char *)pde - kaddr;
pos = page_offset(page) + from;
lock_page(page);
err = ext2_prepare_chunk(page, pos, to - from);
extern int ext2_make_empty(struct inode *, struct inode *);
extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *,
struct page **, void **res_page_addr);
-extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
+extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page,
+ char *kaddr);
extern int ext2_empty_dir (struct inode *);
extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa);
extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *,
goto out;
}
- err = ext2_delete_entry (de, page);
+ err = ext2_delete_entry (de, page, page_addr);
ext2_put_page(page, page_addr);
if (err)
goto out;
old_inode->i_ctime = current_time(old_inode);
mark_inode_dirty(old_inode);
- ext2_delete_entry(old_de, old_page);
+ ext2_delete_entry(old_de, old_page, old_page_addr);
if (dir_de) {
if (old_dir != new_dir)
*/
extern const struct fs_context_operations legacy_fs_context_ops;
extern int parse_monolithic_mount_data(struct fs_context *, void *);
-extern void fc_drop_locked(struct fs_context *);
extern void vfs_clean_context(struct fs_context *fc);
extern int finish_clean_context(struct fs_context *fc);
search_path->path_length = ILLEGAL_PATH_ELEMENT_OFFSET;
}
+static int has_valid_deh_location(struct buffer_head *bh, struct item_head *ih)
+{
+ struct reiserfs_de_head *deh;
+ int i;
+
+ deh = B_I_DEH(bh, ih);
+ for (i = 0; i < ih_entry_count(ih); i++) {
+ if (deh_location(&deh[i]) > ih_item_len(ih)) {
+ reiserfs_warning(NULL, "reiserfs-5094",
+ "directory entry location seems wrong %h",
+ &deh[i]);
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
{
struct block_head *blkh;
"(second one): %h", ih);
return 0;
}
- if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) {
- reiserfs_warning(NULL, "reiserfs-5093",
- "item entry count seems wrong %h",
- ih);
- return 0;
+ if (is_direntry_le_ih(ih)) {
+ if (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE)) {
+ reiserfs_warning(NULL, "reiserfs-5093",
+ "item entry count seems wrong %h",
+ ih);
+ return 0;
+ }
+ return has_valid_deh_location(bh, ih);
}
prev_location = ih_location(ih);
}
unlock_new_inode(root_inode);
}
+ if (!S_ISDIR(root_inode->i_mode) || !inode_get_bytes(root_inode) ||
+ !root_inode->i_size) {
+ SWARN(silent, s, "", "corrupt root inode, run fsck");
+ iput(root_inode);
+ errval = -EUCLEAN;
+ goto error;
+ }
+
s->s_root = d_make_root(root_inode);
if (!s->s_root)
goto error;
extern void put_fs_context(struct fs_context *fc);
extern int vfs_parse_fs_param_source(struct fs_context *fc,
struct fs_parameter *param);
+extern void fc_drop_locked(struct fs_context *fc);
/*
* sget() wrappers to be called from the ->get_tree() op.
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */
/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
#ifndef _USR_IDXD_H_
#define _USR_IDXD_H_
-/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB */
/*
* Copyright (c) 2006 - 2021 Intel Corporation. All rights reserved.
* Copyright (c) 2005 Topspin Communications. All rights reserved.
ret = cgroup_do_get_tree(fc);
if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) {
- struct super_block *sb = fc->root->d_sb;
- dput(fc->root);
- deactivate_locked_super(sb);
+ fc_drop_locked(fc);
ret = 1;
}
unbound_release_work);
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
- bool is_last;
+ bool is_last = false;
- if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
- return;
+ /*
+ * when @pwq is not linked, it doesn't hold any reference to the
+ * @wq, and @wq is invalid to access.
+ */
+ if (!list_empty(&pwq->pwqs_node)) {
+ if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
+ return;
- mutex_lock(&wq->mutex);
- list_del_rcu(&pwq->pwqs_node);
- is_last = list_empty(&wq->pwqs);
- mutex_unlock(&wq->mutex);
+ mutex_lock(&wq->mutex);
+ list_del_rcu(&pwq->pwqs_node);
+ is_last = list_empty(&wq->pwqs);
+ mutex_unlock(&wq->mutex);
+ }
mutex_lock(&wq_pool_mutex);
put_unbound_pool(pool);
return err;
}
+static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+
+ /*
+ * Garbage collection of unix sockets starts by selecting a set of
+ * candidate sockets which have reference only from being in flight
+ * (total_refs == inflight_refs). This condition is checked once during
+ * the candidate collection phase, and candidates are marked as such, so
+ * that non-candidates can later be ignored. While inflight_refs is
+ * protected by unix_gc_lock, total_refs (file count) is not, hence this
+ * is an instantaneous decision.
+ *
+ * Once a candidate, however, the socket must not be reinstalled into a
+ * file descriptor while the garbage collection is in progress.
+ *
+ * If the above conditions are met, then the directed graph of
+ * candidates (*) does not change while unix_gc_lock is held.
+ *
+ * Any operations that changes the file count through file descriptors
+ * (dup, close, sendmsg) does not change the graph since candidates are
+ * not installed in fds.
+ *
+ * Dequeing a candidate via recvmsg would install it into an fd, but
+ * that takes unix_gc_lock to decrement the inflight count, so it's
+ * serialized with garbage collection.
+ *
+ * MSG_PEEK is special in that it does not change the inflight count,
+ * yet does install the socket into an fd. The following lock/unlock
+ * pair is to ensure serialization with garbage collection. It must be
+ * done between incrementing the file count and installing the file into
+ * an fd.
+ *
+ * If garbage collection starts after the barrier provided by the
+ * lock/unlock, then it will see the elevated refcount and not mark this
+ * as a candidate. If a garbage collection is already in progress
+ * before the file count was incremented, then the lock/unlock pair will
+ * ensure that garbage collection is finished before progressing to
+ * installing the fd.
+ *
+ * (*) A -> B where B is on the queue of A or B is on the queue of C
+ * which is on the queue of listening socket A.
+ */
+ spin_lock(&unix_gc_lock);
+ spin_unlock(&unix_gc_lock);
+}
+
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
sk_peek_offset_fwd(sk, size);
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
}
err = (flags & MSG_TRUNC) ? skb->len - skip : size;
/* It is questionable, see note in unix_dgram_recvmsg.
*/
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
sk_peek_offset_fwd(sk, chunk);
/x86_64/xen_vmcall_test
/x86_64/xss_msr_test
/x86_64/vmx_pmu_msrs_test
+/access_tracking_perf_test
/demand_paging_test
/dirty_log_test
/dirty_log_perf_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
+TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
#define VREGS_SUBLIST \
{ "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), }
#define PMU_SUBLIST \
- { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
+ { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \
+ .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
#define SVE_SUBLIST \
{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
.regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * access_tracking_perf_test
+ *
+ * Copyright (C) 2021, Google, Inc.
+ *
+ * This test measures the performance effects of KVM's access tracking.
+ * Access tracking is driven by the MMU notifiers test_young, clear_young, and
+ * clear_flush_young. These notifiers do not have a direct userspace API,
+ * however the clear_young notifier can be triggered by marking a pages as idle
+ * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to
+ * enable access tracking on guest memory.
+ *
+ * To measure performance this test runs a VM with a configurable number of
+ * vCPUs that each touch every page in disjoint regions of memory. Performance
+ * is measured in the time it takes all vCPUs to finish touching their
+ * predefined region.
+ *
+ * Note that a deterministic correctness test of access tracking is not possible
+ * by using page_idle as it exists today. This is for a few reasons:
+ *
+ * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This
+ * means subsequent guest accesses are not guaranteed to see page table
+ * updates made by KVM until some time in the future.
+ *
+ * 2. page_idle only operates on LRU pages. Newly allocated pages are not
+ * immediately allocated to LRU lists. Instead they are held in a "pagevec",
+ * which is drained to LRU lists some time in the future. There is no
+ * userspace API to force this drain to occur.
+ *
+ * These limitations are worked around in this test by using a large enough
+ * region of memory for each vCPU such that the number of translations cached in
+ * the TLB and the number of pages held in pagevecs are a small fraction of the
+ * overall workload. And if either of those conditions are not true this test
+ * will fail rather than silently passing.
+ */
+#include <inttypes.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
+
+/* Global variable used to synchronize all of the vCPU threads. */
+static int iteration = -1;
+
+/* Defines what vCPU threads should do during a given iteration. */
+static enum {
+ /* Run the vCPU to access all its memory. */
+ ITERATION_ACCESS_MEMORY,
+ /* Mark the vCPU's memory idle in page_idle. */
+ ITERATION_MARK_IDLE,
+} iteration_work;
+
+/* Set to true when vCPU threads should exit. */
+static bool done;
+
+/* The iteration that was last completed by each vCPU. */
+static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
+
+/* Whether to overlap the regions of memory vCPUs access. */
+static bool overlap_memory_access;
+
+struct test_params {
+ /* The backing source for the region of memory. */
+ enum vm_mem_backing_src_type backing_src;
+
+ /* The amount of memory to allocate for each vCPU. */
+ uint64_t vcpu_memory_bytes;
+
+ /* The number of vCPUs to create in the VM. */
+ int vcpus;
+};
+
+static uint64_t pread_uint64(int fd, const char *filename, uint64_t index)
+{
+ uint64_t value;
+ off_t offset = index * sizeof(value);
+
+ TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value),
+ "pread from %s offset 0x%" PRIx64 " failed!",
+ filename, offset);
+
+ return value;
+
+}
+
+#define PAGEMAP_PRESENT (1ULL << 63)
+#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1)
+
+static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva)
+{
+ uint64_t hva = (uint64_t) addr_gva2hva(vm, gva);
+ uint64_t entry;
+ uint64_t pfn;
+
+ entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize());
+ if (!(entry & PAGEMAP_PRESENT))
+ return 0;
+
+ pfn = entry & PAGEMAP_PFN_MASK;
+ if (!pfn) {
+ print_skip("Looking up PFNs requires CAP_SYS_ADMIN");
+ exit(KSFT_SKIP);
+ }
+
+ return pfn;
+}
+
+static bool is_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64);
+
+ return !!((bits >> (pfn % 64)) & 1);
+}
+
+static void mark_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = 1ULL << (pfn % 64);
+
+ TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8,
+ "Set page_idle bits for PFN 0x%" PRIx64, pfn);
+}
+
+static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id)
+{
+ uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva;
+ uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages;
+ uint64_t page;
+ uint64_t still_idle = 0;
+ uint64_t no_pfn = 0;
+ int page_idle_fd;
+ int pagemap_fd;
+
+ /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */
+ if (overlap_memory_access && vcpu_id)
+ return;
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle.");
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap.");
+
+ for (page = 0; page < pages; page++) {
+ uint64_t gva = base_gva + page * perf_test_args.guest_page_size;
+ uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva);
+
+ if (!pfn) {
+ no_pfn++;
+ continue;
+ }
+
+ if (is_page_idle(page_idle_fd, pfn)) {
+ still_idle++;
+ continue;
+ }
+
+ mark_page_idle(page_idle_fd, pfn);
+ }
+
+ /*
+ * Assumption: Less than 1% of pages are going to be swapped out from
+ * under us during this test.
+ */
+ TEST_ASSERT(no_pfn < pages / 100,
+ "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.",
+ vcpu_id, no_pfn, pages);
+
+ /*
+ * Test that at least 90% of memory has been marked idle (the rest might
+ * not be marked idle because the pages have not yet made it to an LRU
+ * list or the translations are still cached in the TLB). 90% is
+ * arbitrary; high enough that we ensure most memory access went through
+ * access tracking but low enough as to not make the test too brittle
+ * over time and across architectures.
+ */
+ TEST_ASSERT(still_idle < pages / 10,
+ "vCPU%d: Too many pages still idle (%"PRIu64 " out of %"
+ PRIu64 ").\n",
+ vcpu_id, still_idle, pages);
+
+ close(page_idle_fd);
+ close(pagemap_fd);
+}
+
+static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id,
+ uint64_t expected_ucall)
+{
+ struct ucall uc;
+ uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc);
+
+ TEST_ASSERT(expected_ucall == actual_ucall,
+ "Guest exited unexpectedly (expected ucall %" PRIu64
+ ", got %" PRIu64 ")",
+ expected_ucall, actual_ucall);
+}
+
+static bool spin_wait_for_next_iteration(int *current_iteration)
+{
+ int last_iteration = *current_iteration;
+
+ do {
+ if (READ_ONCE(done))
+ return false;
+
+ *current_iteration = READ_ONCE(iteration);
+ } while (last_iteration == *current_iteration);
+
+ return true;
+}
+
+static void *vcpu_thread_main(void *arg)
+{
+ struct perf_test_vcpu_args *vcpu_args = arg;
+ struct kvm_vm *vm = perf_test_args.vm;
+ int vcpu_id = vcpu_args->vcpu_id;
+ int current_iteration = -1;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+ while (spin_wait_for_next_iteration(¤t_iteration)) {
+ switch (READ_ONCE(iteration_work)) {
+ case ITERATION_ACCESS_MEMORY:
+ vcpu_run(vm, vcpu_id);
+ assert_ucall(vm, vcpu_id, UCALL_SYNC);
+ break;
+ case ITERATION_MARK_IDLE:
+ mark_vcpu_memory_idle(vm, vcpu_id);
+ break;
+ };
+
+ vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+ }
+
+ return NULL;
+}
+
+static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
+{
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) !=
+ target_iteration) {
+ continue;
+ }
+}
+
+/* The type of memory accesses to perform in the VM. */
+enum access_type {
+ ACCESS_READ,
+ ACCESS_WRITE,
+};
+
+static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
+{
+ struct timespec ts_start;
+ struct timespec ts_elapsed;
+ int next_iteration;
+ int vcpu_id;
+
+ /* Kick off the vCPUs by incrementing iteration. */
+ next_iteration = ++iteration;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+ /* Wait for all vCPUs to finish the iteration. */
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+ spin_wait_for_vcpu(vcpu_id, next_iteration);
+
+ ts_elapsed = timespec_elapsed(ts_start);
+ pr_info("%-30s: %ld.%09lds\n",
+ description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec);
+}
+
+static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
+ const char *description)
+{
+ perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
+ sync_global_to_guest(vm, perf_test_args);
+ iteration_work = ITERATION_ACCESS_MEMORY;
+ run_iteration(vm, vcpus, description);
+}
+
+static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
+{
+ /*
+ * Even though this parallelizes the work across vCPUs, this is still a
+ * very slow operation because page_idle forces the test to mark one pfn
+ * at a time and the clear_young notifier serializes on the KVM MMU
+ * lock.
+ */
+ pr_debug("Marking VM memory idle (slow)...\n");
+ iteration_work = ITERATION_MARK_IDLE;
+ run_iteration(vm, vcpus, "Mark memory idle");
+}
+
+static pthread_t *create_vcpu_threads(int vcpus)
+{
+ pthread_t *vcpu_threads;
+ int i;
+
+ vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
+ TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
+
+ for (i = 0; i < vcpus; i++) {
+ vcpu_last_completed_iteration[i] = iteration;
+ pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
+ &perf_test_args.vcpu_args[i]);
+ }
+
+ return vcpu_threads;
+}
+
+static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
+{
+ int i;
+
+ /* Set done to signal the vCPU threads to exit */
+ done = true;
+
+ for (i = 0; i < vcpus; i++)
+ pthread_join(vcpu_threads[i], NULL);
+}
+
+static void run_test(enum vm_guest_mode mode, void *arg)
+{
+ struct test_params *params = arg;
+ struct kvm_vm *vm;
+ pthread_t *vcpu_threads;
+ int vcpus = params->vcpus;
+
+ vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes,
+ params->backing_src);
+
+ perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
+ !overlap_memory_access);
+
+ vcpu_threads = create_vcpu_threads(vcpus);
+
+ pr_info("\n");
+ access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
+
+ /* As a control, read and write to the populated memory first. */
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory");
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory");
+
+ /* Repeat on memory that has been marked as idle. */
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory");
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
+
+ terminate_vcpu_threads(vcpu_threads, vcpus);
+ free(vcpu_threads);
+ perf_test_destroy_vm(vm);
+}
+
+static void help(char *name)
+{
+ puts("");
+ printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n",
+ name);
+ puts("");
+ printf(" -h: Display this help message.");
+ guest_modes_help();
+ printf(" -b: specify the size of the memory region which should be\n"
+ " dirtied by each vCPU. e.g. 10M or 3G.\n"
+ " (default: 1G)\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ printf(" -o: Overlap guest memory accesses instead of partitioning\n"
+ " them into a separate region of memory for each vCPU.\n");
+ printf(" -s: specify the type of memory that should be used to\n"
+ " back the guest data region.\n\n");
+ backing_src_help();
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct test_params params = {
+ .backing_src = VM_MEM_SRC_ANONYMOUS,
+ .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
+ .vcpus = 1,
+ };
+ int page_idle_fd;
+ int opt;
+
+ guest_modes_append_default();
+
+ while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+ switch (opt) {
+ case 'm':
+ guest_modes_cmdline(optarg);
+ break;
+ case 'b':
+ params.vcpu_memory_bytes = parse_size(optarg);
+ break;
+ case 'v':
+ params.vcpus = atoi(optarg);
+ break;
+ case 'o':
+ overlap_memory_access = true;
+ break;
+ case 's':
+ params.backing_src = parse_backing_src_type(optarg);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ if (page_idle_fd < 0) {
+ print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled");
+ exit(KSFT_SKIP);
+ }
+ close(page_idle_fd);
+
+ for_each_guest_mode(run_test, ¶ms);
+
+ return 0;
+}
break;
case 'o':
p.partition_vcpu_memory_access = false;
+ break;
case 's':
p.backing_src = parse_backing_src_type(optarg);
break;
run_delay = get_run_delay();
pthread_create(&thread, &attr, do_steal_time, NULL);
do
- pthread_yield();
+ sched_yield();
while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS);
pthread_join(thread, NULL);
run_delay = get_run_delay() - run_delay;
++vcpu->stat.generic.halt_poll_invalid;
goto out;
}
+ cpu_relax();
poll_end = cur = ktime_get();
} while (kvm_vcpu_can_poll(cur, stop));
}
};
};
+struct compat_kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ compat_uptr_t dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
static long kvm_vm_compat_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
if (kvm->mm != current->mm)
return -EIO;
switch (ioctl) {
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ case KVM_CLEAR_DIRTY_LOG: {
+ struct compat_kvm_clear_dirty_log compat_log;
+ struct kvm_clear_dirty_log log;
+
+ if (copy_from_user(&compat_log, (void __user *)arg,
+ sizeof(compat_log)))
+ return -EFAULT;
+ log.slot = compat_log.slot;
+ log.num_pages = compat_log.num_pages;
+ log.first_page = compat_log.first_page;
+ log.padding2 = compat_log.padding2;
+ log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
+
+ r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
+ break;
+ }
+#endif
case KVM_GET_DIRTY_LOG: {
struct compat_kvm_dirty_log compat_log;
struct kvm_dirty_log log;
projects / linux-2.6-microblaze.git / commitdiff