#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/iova.h>
-#include <linux/intel-iommu.h>
#include <linux/timer.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/numa.h>
#include <linux/limits.h>
#include <asm/irq_remapping.h>
-#include <trace/events/intel_iommu.h>
+#include "iommu.h"
#include "../irq_remapping.h"
#include "perf.h"
+#include "trace.h"
+#include "perfmon.h"
typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
struct dmar_res_callback {
struct acpi_table_header * __initdata dmar_tbl;
static int dmar_dev_scope_status = 1;
-static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
+static DEFINE_IDA(dmar_seq_ids);
static int alloc_iommu(struct dmar_drhd_unit *drhd);
static void free_iommu(struct intel_iommu *iommu);
struct pci_dev *tmp;
struct dmar_pci_notify_info *info;
- BUG_ON(dev->is_virtfn);
-
/*
* Ignore devices that have a domain number higher than what can
* be looked up in DMAR, e.g. VMD subdevices with domain 0x10000
get_device(dev));
return 1;
}
- BUG_ON(i >= devices_cnt);
+ if (WARN_ON(i >= devices_cnt))
+ return -EINVAL;
}
return 0;
static struct notifier_block dmar_pci_bus_nb = {
.notifier_call = dmar_pci_bus_notifier,
- .priority = INT_MIN,
+ .priority = 1,
};
static struct dmar_drhd_unit *
memcpy(dmaru->hdr, header, header->length);
dmaru->reg_base_addr = drhd->address;
dmaru->segment = drhd->segment;
+ /* The size of the register set is 2 ^ N 4 KB pages. */
+ dmaru->reg_size = 1UL << (drhd->size + 12);
dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1),
((void *)drhd) + drhd->header.length,
info = dmar_alloc_pci_notify_info(dev,
BUS_NOTIFY_ADD_DEVICE);
if (!info) {
+ pci_dev_put(dev);
return dmar_dev_scope_status;
} else {
dmar_pci_bus_add_dev(info);
/**
* map_iommu: map the iommu's registers
* @iommu: the iommu to map
- * @phys_addr: the physical address of the base resgister
+ * @drhd: DMA remapping hardware definition structure
*
* Memory map the iommu's registers. Start w/ a single page, and
* possibly expand if that turns out to be insufficent.
*/
-static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
+static int map_iommu(struct intel_iommu *iommu, struct dmar_drhd_unit *drhd)
{
+ u64 phys_addr = drhd->reg_base_addr;
int map_size, err=0;
iommu->reg_phys = phys_addr;
- iommu->reg_size = VTD_PAGE_SIZE;
+ iommu->reg_size = drhd->reg_size;
if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) {
pr_err("Can't reserve memory\n");
warn_invalid_dmar(phys_addr, " returns all ones");
goto unmap;
}
- if (ecap_vcs(iommu->ecap))
- iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
/* the registers might be more than one page */
map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
goto release;
}
}
+
+ if (cap_ecmds(iommu->cap)) {
+ int i;
+
+ for (i = 0; i < DMA_MAX_NUM_ECMDCAP; i++) {
+ iommu->ecmdcap[i] = dmar_readq(iommu->reg + DMAR_ECCAP_REG +
+ i * DMA_ECMD_REG_STEP);
+ }
+ }
+
err = 0;
goto out;
return err;
}
-static int dmar_alloc_seq_id(struct intel_iommu *iommu)
-{
- iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
- DMAR_UNITS_SUPPORTED);
- if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
- iommu->seq_id = -1;
- } else {
- set_bit(iommu->seq_id, dmar_seq_ids);
- sprintf(iommu->name, "dmar%d", iommu->seq_id);
- }
-
- return iommu->seq_id;
-}
-
-static void dmar_free_seq_id(struct intel_iommu *iommu)
-{
- if (iommu->seq_id >= 0) {
- clear_bit(iommu->seq_id, dmar_seq_ids);
- iommu->seq_id = -1;
- }
-}
-
static int alloc_iommu(struct dmar_drhd_unit *drhd)
{
struct intel_iommu *iommu;
if (!iommu)
return -ENOMEM;
- if (dmar_alloc_seq_id(iommu) < 0) {
+ iommu->seq_id = ida_alloc_range(&dmar_seq_ids, 0,
+ DMAR_UNITS_SUPPORTED - 1, GFP_KERNEL);
+ if (iommu->seq_id < 0) {
pr_err("Failed to allocate seq_id\n");
- err = -ENOSPC;
+ err = iommu->seq_id;
goto error;
}
+ sprintf(iommu->name, "dmar%d", iommu->seq_id);
- err = map_iommu(iommu, drhd->reg_base_addr);
+ err = map_iommu(iommu, drhd);
if (err) {
pr_err("Failed to map %s\n", iommu->name);
goto error_free_seq_id;
}
err = -EINVAL;
- if (cap_sagaw(iommu->cap) == 0) {
+ if (!cap_sagaw(iommu->cap) &&
+ (!ecap_smts(iommu->ecap) || ecap_slts(iommu->ecap))) {
pr_info("%s: No supported address widths. Not attempting DMA translation.\n",
iommu->name);
drhd->ignored = 1;
iommu->agaw = agaw;
iommu->msagaw = msagaw;
iommu->segment = drhd->segment;
-
+ iommu->device_rbtree = RB_ROOT;
+ spin_lock_init(&iommu->device_rbtree_lock);
+ mutex_init(&iommu->iopf_lock);
iommu->node = NUMA_NO_NODE;
ver = readl(iommu->reg + DMAR_VER_REG);
if (sts & DMA_GSTS_QIES)
iommu->gcmd |= DMA_GCMD_QIE;
+ if (alloc_iommu_pmu(iommu))
+ pr_debug("Cannot alloc PMU for iommu (seq_id = %d)\n", iommu->seq_id);
+
raw_spin_lock_init(&iommu->register_lock);
+ /*
+ * A value of N in PSS field of eCap register indicates hardware
+ * supports PASID field of N+1 bits.
+ */
+ if (pasid_supported(iommu))
+ iommu->iommu.max_pasids = 2UL << ecap_pss(iommu->ecap);
+
/*
* This is only for hotplug; at boot time intel_iommu_enabled won't
* be set yet. When intel_iommu_init() runs, it registers the units
err = iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
if (err)
goto err_sysfs;
+
+ iommu_pmu_register(iommu);
}
drhd->iommu = iommu;
err_sysfs:
iommu_device_sysfs_remove(&iommu->iommu);
err_unmap:
+ free_iommu_pmu(iommu);
unmap_iommu(iommu);
error_free_seq_id:
- dmar_free_seq_id(iommu);
+ ida_free(&dmar_seq_ids, iommu->seq_id);
error:
kfree(iommu);
return err;
static void free_iommu(struct intel_iommu *iommu)
{
if (intel_iommu_enabled && !iommu->drhd->ignored) {
+ iommu_pmu_unregister(iommu);
iommu_device_unregister(&iommu->iommu);
iommu_device_sysfs_remove(&iommu->iommu);
}
+ free_iommu_pmu(iommu);
+
if (iommu->irq) {
if (iommu->pr_irq) {
free_irq(iommu->pr_irq, iommu);
if (iommu->reg)
unmap_iommu(iommu);
- dmar_free_seq_id(iommu);
+ ida_free(&dmar_seq_ids, iommu->seq_id);
kfree(iommu);
}
{
u32 fault;
int head, tail;
+ struct device *dev;
+ u64 iqe_err, ite_sid;
struct q_inval *qi = iommu->qi;
int shift = qi_shift(iommu);
tail = readl(iommu->reg + DMAR_IQT_REG);
tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
+ /*
+ * SID field is valid only when the ITE field is Set in FSTS_REG
+ * see Intel VT-d spec r4.1, section 11.4.9.9
+ */
+ iqe_err = dmar_readq(iommu->reg + DMAR_IQER_REG);
+ ite_sid = DMAR_IQER_REG_ITESID(iqe_err);
+
writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
pr_info("Invalidation Time-out Error (ITE) cleared\n");
head = (head - 2 + QI_LENGTH) % QI_LENGTH;
} while (head != tail);
+ /*
+ * If device was released or isn't present, no need to retry
+ * the ATS invalidate request anymore.
+ *
+ * 0 value of ite_sid means old VT-d device, no ite_sid value.
+ * see Intel VT-d spec r4.1, section 11.4.9.9
+ */
+ if (ite_sid) {
+ dev = device_rbtree_find(iommu, ite_sid);
+ if (!dev || !dev_is_pci(dev) ||
+ !pci_device_is_present(to_pci_dev(dev)))
+ return -ETIMEDOUT;
+ }
if (qi->desc_status[wait_index] == QI_ABORT)
return -EAGAIN;
}
{
struct qi_desc desc;
+ /*
+ * VT-d spec, section 4.3:
+ *
+ * Software is recommended to not submit any Device-TLB invalidation
+ * requests while address remapping hardware is disabled.
+ */
+ if (!(iommu->gcmd & DMA_GCMD_TE))
+ return;
+
if (mask) {
addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+ /*
+ * VT-d spec, section 4.3:
+ *
+ * Software is recommended to not submit any Device-TLB invalidation
+ * requests while address remapping hardware is disabled.
+ */
+ if (!(iommu->gcmd & DMA_GCMD_TE))
+ return;
+
desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
QI_DEV_IOTLB_PFSID(pfsid);
* is present.
*/
if (ecap_smts(iommu->ecap))
- val |= (1 << 11) | 1;
+ val |= BIT_ULL(11) | BIT_ULL(0);
raw_spin_lock_irqsave(&iommu->register_lock, flags);
return DMAR_FECTL_REG;
else if (iommu->pr_irq == irq)
return DMAR_PECTL_REG;
+ else if (iommu->perf_irq == irq)
+ return DMAR_PERFINTRCTL_REG;
else
BUG();
}
return 0;
}
- if (pasid == INVALID_IOASID)
+ if (pasid == IOMMU_PASID_INVALID)
pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n",
type ? "DMA Read" : "DMA Write",
source_id >> 8, PCI_SLOT(source_id & 0xFF),
if (!ratelimited)
/* Using pasid -1 if pasid is not present */
dmar_fault_do_one(iommu, type, fault_reason,
- pasid_present ? pasid : INVALID_IOASID,
+ pasid_present ? pasid : IOMMU_PASID_INVALID,
source_id, guest_addr);
fault_index++;