summaryrefslogtreecommitdiff
path: root/drivers/iommu/amd
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu/amd')
-rw-r--r--drivers/iommu/amd/Kconfig2
-rw-r--r--drivers/iommu/amd/amd_iommu.h9
-rw-r--r--drivers/iommu/amd/amd_iommu_types.h6
-rw-r--r--drivers/iommu/amd/init.c125
-rw-r--r--drivers/iommu/amd/iommu.c122
-rw-r--r--drivers/iommu/amd/iommu_v2.c7
6 files changed, 202 insertions, 69 deletions
diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
index 1f061d91e0b8..626b97d0dd21 100644
--- a/drivers/iommu/amd/Kconfig
+++ b/drivers/iommu/amd/Kconfig
@@ -10,7 +10,7 @@ config AMD_IOMMU
select IOMMU_API
select IOMMU_IOVA
select IOMMU_DMA
- depends on X86_64 && PCI && ACPI
+ depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
help
With this option you can enable support for AMD IOMMU hardware in
your system. An IOMMU is a hardware component which provides
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 57309716fd18..0781b7112467 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -41,6 +41,15 @@ extern int amd_iommu_guest_ir;
struct iommu_domain;
extern bool amd_iommu_v2_supported(void);
+extern struct amd_iommu *get_amd_iommu(unsigned int idx);
+extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+extern bool amd_iommu_pc_supported(void);
+extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+ u8 fxn, u64 *value);
+extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+ u8 fxn, u64 *value);
+
extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 30a5d412255a..f696ac7c5f89 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -93,6 +93,7 @@
#define FEATURE_PC (1ULL<<9)
#define FEATURE_GAM_VAPIC (1ULL<<21)
#define FEATURE_EPHSUP (1ULL<<50)
+#define FEATURE_SNP (1ULL<<63)
#define FEATURE_PASID_SHIFT 32
#define FEATURE_PASID_MASK (0x1fULL << FEATURE_PASID_SHIFT)
@@ -128,6 +129,8 @@
#define EVENT_TYPE_IOTLB_INV_TO 0x7
#define EVENT_TYPE_INV_DEV_REQ 0x8
#define EVENT_TYPE_INV_PPR_REQ 0x9
+#define EVENT_TYPE_RMP_FAULT 0xd
+#define EVENT_TYPE_RMP_HW_ERR 0xe
#define EVENT_DEVID_MASK 0xffff
#define EVENT_DEVID_SHIFT 0
#define EVENT_DOMID_MASK_LO 0xffff
@@ -595,7 +598,8 @@ struct amd_iommu {
#endif
u32 flags;
- volatile u64 __aligned(8) cmd_sem;
+ volatile u64 *cmd_sem;
+ u64 cmd_sem_val;
#ifdef CONFIG_AMD_IOMMU_DEBUGFS
/* DebugFS Info */
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index c652f16eb702..82e4af8f09bb 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -359,6 +359,29 @@ static void iommu_set_exclusion_range(struct amd_iommu *iommu)
&entry, sizeof(entry));
}
+static void iommu_set_cwwb_range(struct amd_iommu *iommu)
+{
+ u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem);
+ u64 entry = start & PM_ADDR_MASK;
+
+ if (!iommu_feature(iommu, FEATURE_SNP))
+ return;
+
+ /* Note:
+ * Re-purpose Exclusion base/limit registers for Completion wait
+ * write-back base/limit.
+ */
+ memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
+ &entry, sizeof(entry));
+
+ /* Note:
+ * Default to 4 Kbytes, which can be specified by setting base
+ * address equal to the limit address.
+ */
+ memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
+ &entry, sizeof(entry));
+}
+
/* Programs the physical address of the device table into the IOMMU hardware */
static void iommu_set_device_table(struct amd_iommu *iommu)
{
@@ -813,6 +836,19 @@ static int iommu_init_ga(struct amd_iommu *iommu)
return ret;
}
+static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
+{
+ iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL);
+
+ return iommu->cmd_sem ? 0 : -ENOMEM;
+}
+
+static void __init free_cwwb_sem(struct amd_iommu *iommu)
+{
+ if (iommu->cmd_sem)
+ free_page((unsigned long)iommu->cmd_sem);
+}
+
static void iommu_enable_xt(struct amd_iommu *iommu)
{
#ifdef CONFIG_IRQ_REMAP
@@ -1104,25 +1140,6 @@ static int __init add_early_maps(void)
}
/*
- * Reads the device exclusion range from ACPI and initializes the IOMMU with
- * it
- */
-static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
-{
- if (!(m->flags & IVMD_FLAG_EXCL_RANGE))
- return;
-
- /*
- * Treat per-device exclusion ranges as r/w unity-mapped regions
- * since some buggy BIOSes might lead to the overwritten exclusion
- * range (exclusion_start and exclusion_length members). This
- * happens when there are multiple exclusion ranges (IVMD entries)
- * defined in ACPI table.
- */
- m->flags = (IVMD_FLAG_IW | IVMD_FLAG_IR | IVMD_FLAG_UNITY_MAP);
-}
-
-/*
* Takes a pointer to an AMD IOMMU entry in the ACPI table and
* initializes the hardware and our data structures with it.
*/
@@ -1395,6 +1412,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
static void __init free_iommu_one(struct amd_iommu *iommu)
{
+ free_cwwb_sem(iommu);
free_command_buffer(iommu);
free_event_buffer(iommu);
free_ppr_log(iommu);
@@ -1481,6 +1499,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
int ret;
raw_spin_lock_init(&iommu->lock);
+ iommu->cmd_sem_val = 0;
/* Add IOMMU to internal data structures */
list_add_tail(&iommu->list, &amd_iommu_list);
@@ -1511,7 +1530,14 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
else
iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
- if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+
+ /*
+ * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+ * GAM also requires GA mode. Therefore, we need to
+ * check cmpxchg16b support before enabling it.
+ */
+ if (!boot_cpu_has(X86_FEATURE_CX16) ||
+ ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
break;
case 0x11:
@@ -1520,8 +1546,18 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
else
iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
- if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+
+ /*
+ * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+ * XT, GAM also requires GA mode. Therefore, we need to
+ * check cmpxchg16b support before enabling them.
+ */
+ if (!boot_cpu_has(X86_FEATURE_CX16) ||
+ ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+ break;
+ }
+
/*
* Note: Since iommu_update_intcapxt() leverages
* the IOMMU MMIO access to MSI capability block registers
@@ -1541,6 +1577,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
if (!iommu->mmio_base)
return -ENOMEM;
+ if (alloc_cwwb_sem(iommu))
+ return -ENOMEM;
+
if (alloc_command_buffer(iommu))
return -ENOMEM;
@@ -1578,7 +1617,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
/**
* get_highest_supported_ivhd_type - Look up the appropriate IVHD type
- * @ivrs Pointer to the IVRS header
+ * @ivrs: Pointer to the IVRS header
*
* This function search through all IVDB of the maximum supported IVHD
*/
@@ -1866,6 +1905,9 @@ static int __init amd_iommu_init_pci(void)
ret = iommu_init_pci(iommu);
if (ret)
break;
+
+ /* Need to setup range after PCI init */
+ iommu_set_cwwb_range(iommu);
}
/*
@@ -1929,7 +1971,7 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
#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.
@@ -2056,30 +2098,6 @@ static void __init free_unity_maps(void)
}
}
-/* called when we find an exclusion range definition in ACPI */
-static int __init init_exclusion_range(struct ivmd_header *m)
-{
- int i;
-
- switch (m->type) {
- case ACPI_IVMD_TYPE:
- set_device_exclusion_range(m->devid, m);
- break;
- case ACPI_IVMD_TYPE_ALL:
- for (i = 0; i <= amd_iommu_last_bdf; ++i)
- set_device_exclusion_range(i, m);
- break;
- case ACPI_IVMD_TYPE_RANGE:
- for (i = m->devid; i <= m->aux; ++i)
- set_device_exclusion_range(i, m);
- break;
- default:
- break;
- }
-
- return 0;
-}
-
/* called for unity map ACPI definition */
static int __init init_unity_map_range(struct ivmd_header *m)
{
@@ -2090,9 +2108,6 @@ static int __init init_unity_map_range(struct ivmd_header *m)
if (e == NULL)
return -ENOMEM;
- if (m->flags & IVMD_FLAG_EXCL_RANGE)
- init_exclusion_range(m);
-
switch (m->type) {
default:
kfree(e);
@@ -2116,6 +2131,16 @@ static int __init init_unity_map_range(struct ivmd_header *m)
e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
e->prot = m->flags >> 1;
+ /*
+ * Treat per-device exclusion ranges as r/w unity-mapped regions
+ * since some buggy BIOSes might lead to the overwritten exclusion
+ * range (exclusion_start and exclusion_length members). This
+ * happens when there are multiple exclusion ranges (IVMD entries)
+ * defined in ACPI table.
+ */
+ if (m->flags & IVMD_FLAG_EXCL_RANGE)
+ e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1;
+
DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
" range_start: %016llx range_end: %016llx flags: %x\n", s,
PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start),
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..ea64fa8a9418 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -486,6 +486,67 @@ static void dump_command(unsigned long phys_addr)
pr_err("CMD[%d]: %08x\n", i, cmd->data[i]);
}
+static void amd_iommu_report_rmp_hw_error(volatile u32 *event)
+{
+ struct iommu_dev_data *dev_data = NULL;
+ int devid, vmg_tag, flags;
+ struct pci_dev *pdev;
+ u64 spa;
+
+ devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+ vmg_tag = (event[1]) & 0xFFFF;
+ flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+ spa = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8);
+
+ pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+ devid & 0xff);
+ if (pdev)
+ dev_data = dev_iommu_priv_get(&pdev->dev);
+
+ if (dev_data && __ratelimit(&dev_data->rs)) {
+ pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+ vmg_tag, spa, flags);
+ } else {
+ pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ vmg_tag, spa, flags);
+ }
+
+ if (pdev)
+ pci_dev_put(pdev);
+}
+
+static void amd_iommu_report_rmp_fault(volatile u32 *event)
+{
+ struct iommu_dev_data *dev_data = NULL;
+ int devid, flags_rmp, vmg_tag, flags;
+ struct pci_dev *pdev;
+ u64 gpa;
+
+ devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+ flags_rmp = (event[0] >> EVENT_FLAGS_SHIFT) & 0xFF;
+ vmg_tag = (event[1]) & 0xFFFF;
+ flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+ gpa = ((u64)event[3] << 32) | event[2];
+
+ pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+ devid & 0xff);
+ if (pdev)
+ dev_data = dev_iommu_priv_get(&pdev->dev);
+
+ if (dev_data && __ratelimit(&dev_data->rs)) {
+ pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+ vmg_tag, gpa, flags_rmp, flags);
+ } else {
+ pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+ PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+ vmg_tag, gpa, flags_rmp, flags);
+ }
+
+ if (pdev)
+ pci_dev_put(pdev);
+}
+
static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
u64 address, int flags)
{
@@ -577,6 +638,12 @@ retry:
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
pasid, address, flags);
break;
+ case EVENT_TYPE_RMP_FAULT:
+ amd_iommu_report_rmp_fault(event);
+ break;
+ case EVENT_TYPE_RMP_HW_ERR:
+ amd_iommu_report_rmp_hw_error(event);
+ break;
case EVENT_TYPE_INV_PPR_REQ:
pasid = PPR_PASID(*((u64 *)__evt));
tag = event[1] & 0x03FF;
@@ -792,11 +859,11 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
*
****************************************************************************/
-static int wait_on_sem(volatile u64 *sem)
+static int wait_on_sem(struct amd_iommu *iommu, u64 data)
{
int i = 0;
- while (*sem == 0 && i < LOOP_TIMEOUT) {
+ while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) {
udelay(1);
i += 1;
}
@@ -827,16 +894,16 @@ static void copy_cmd_to_buffer(struct amd_iommu *iommu,
writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
}
-static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
+static void build_completion_wait(struct iommu_cmd *cmd,
+ struct amd_iommu *iommu,
+ u64 data)
{
- u64 paddr = iommu_virt_to_phys((void *)address);
-
- WARN_ON(address & 0x7ULL);
+ u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem);
memset(cmd, 0, sizeof(*cmd));
cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
cmd->data[1] = upper_32_bits(paddr);
- cmd->data[2] = 1;
+ cmd->data[2] = data;
CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
}
@@ -1045,22 +1112,21 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
struct iommu_cmd cmd;
unsigned long flags;
int ret;
+ u64 data;
if (!iommu->need_sync)
return 0;
-
- build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
-
raw_spin_lock_irqsave(&iommu->lock, flags);
- iommu->cmd_sem = 0;
+ data = ++iommu->cmd_sem_val;
+ build_completion_wait(&cmd, iommu, data);
ret = __iommu_queue_command_sync(iommu, &cmd, false);
if (ret)
goto out_unlock;
- ret = wait_on_sem(&iommu->cmd_sem);
+ ret = wait_on_sem(iommu, data);
out_unlock:
raw_spin_unlock_irqrestore(&iommu->lock, flags);
@@ -2659,7 +2725,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
if (!dev_data)
return 0;
- if (dev_data->iommu_v2)
+ /*
+ * Do not identity map IOMMUv2 capable devices when memory encryption is
+ * active, because some of those devices (AMD GPUs) don't have the
+ * encryption bit in their DMA-mask and require remapping.
+ */
+ if (!mem_encrypt_active() && dev_data->iommu_v2)
return IOMMU_DOMAIN_IDENTITY;
return 0;
@@ -3292,6 +3363,7 @@ out:
static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
struct amd_ir_data *data)
{
+ bool ret;
struct irq_remap_table *table;
struct amd_iommu *iommu;
unsigned long flags;
@@ -3309,10 +3381,18 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
entry = (struct irte_ga *)table->table;
entry = &entry[index];
- entry->lo.fields_remap.valid = 0;
- entry->hi.val = irte->hi.val;
- entry->lo.val = irte->lo.val;
- entry->lo.fields_remap.valid = 1;
+
+ ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+ entry->lo.val, entry->hi.val,
+ irte->lo.val, irte->hi.val);
+ /*
+ * We use cmpxchg16 to atomically update the 128-bit IRTE,
+ * and it cannot be updated by the hardware or other processors
+ * behind us, so the return value of cmpxchg16 should be the
+ * same as the old value.
+ */
+ WARN_ON(!ret);
+
if (data)
data->ref = entry;
@@ -3826,14 +3906,18 @@ int amd_iommu_activate_guest_mode(void *data)
{
struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+ u64 valid;
if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
!entry || entry->lo.fields_vapic.guest_mode)
return 0;
+ valid = entry->lo.fields_vapic.valid;
+
entry->lo.val = 0;
entry->hi.val = 0;
+ entry->lo.fields_vapic.valid = valid;
entry->lo.fields_vapic.guest_mode = 1;
entry->lo.fields_vapic.ga_log_intr = 1;
entry->hi.fields.ga_root_ptr = ir_data->ga_root_ptr;
@@ -3850,14 +3934,18 @@ int amd_iommu_deactivate_guest_mode(void *data)
struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
struct irq_cfg *cfg = ir_data->cfg;
+ u64 valid;
if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
!entry || !entry->lo.fields_vapic.guest_mode)
return 0;
+ valid = entry->lo.fields_remap.valid;
+
entry->lo.val = 0;
entry->hi.val = 0;
+ entry->lo.fields_remap.valid = valid;
entry->lo.fields_remap.dm = apic->irq_dest_mode;
entry->lo.fields_remap.int_type = apic->irq_delivery_mode;
entry->hi.fields.vector = cfg->vector;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index c259108ab6dd..0d175aed1d92 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -737,6 +737,13 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
might_sleep();
+ /*
+ * When memory encryption is active the device is likely not in a
+ * direct-mapped domain. Forbid using IOMMUv2 functionality for now.
+ */
+ if (mem_encrypt_active())
+ return -ENODEV;
+
if (!amd_iommu_v2_supported())
return -ENODEV;
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-25 19:49:51 +0300