iommu/vt-d: Dump DMAR translation structure when DMA fault occurs

When the dmar translation fault happens, the kernel prints a single line
fault reason with corresponding hexadecimal code defined in the Intel VT-d
specification.

Currently, when user wants to debug the translation fault in detail,
debugfs is used for dumping the dmar_translation_struct, which is not
available when the kernel failed to boot.

Dump the DMAR translation structure, pagewalk the IO page table and print
the page table entry when the fault happens.

This takes effect only when CONFIG_DMAR_DEBUG is enabled.

Signed-off-by: Kyung Min Park <kyung.min.park@intel.com>
Link: https://lore.kernel.org/r/20210815203845.31287-1-kyung.min.park@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20211014053839.727419-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
index 0ddb77115be7d0f66dd06c11cfb0db80e1991424..247d0f2d5fdf77d6386d93bcd072850f88d921fa 100644 (file)
--- a/drivers/iommu/intel/Kconfig
+++ b/drivers/iommu/intel/Kconfig
@@ -6,6 +6,9 @@ config DMAR_TABLE
 config DMAR_PERF
        bool
 
+config DMAR_DEBUG
+       bool
+
 config INTEL_IOMMU
        bool "Support for Intel IOMMU using DMA Remapping Devices"
        depends on PCI_MSI && ACPI && (X86 || IA64)
@@ -31,6 +34,7 @@ config INTEL_IOMMU_DEBUGFS
        bool "Export Intel IOMMU internals in Debugfs"
        depends on IOMMU_DEBUGFS
        select DMAR_PERF
+       select DMAR_DEBUG
        help
          !!!WARNING!!!
 

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index b7708b93f3fa18819c956d81cf625aeaad1824b5..915bff76fe96585963a1a27ce3e38ba0a8c2b0a3 100644 (file)
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1941,12 +1941,16 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 
        reason = dmar_get_fault_reason(fault_reason, &fault_type);
 
-       if (fault_type == INTR_REMAP)
+       if (fault_type == INTR_REMAP) {
                pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n",
                       source_id >> 8, PCI_SLOT(source_id & 0xFF),
                       PCI_FUNC(source_id & 0xFF), addr >> 48,
                       fault_reason, reason);
-       else if (pasid == INVALID_IOASID)
+
+               return 0;
+       }
+
+       if (pasid == INVALID_IOASID)
                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),
@@ -1959,6 +1963,8 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
                       PCI_FUNC(source_id & 0xFF), addr,
                       fault_reason, reason);
 
+       dmar_fault_dump_ptes(iommu, source_id, addr, pasid);
+
        return 0;
 }
 

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 9a356075d345073848da1a0b3e2367fb89605cd2..abb2599998b1cfd33dc9223802d8e03f03b12dc8 100644 (file)
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -156,6 +156,8 @@ static struct intel_iommu **g_iommus;
 
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
+static inline struct device_domain_info *
+dmar_search_domain_by_dev_info(int segment, int bus, int devfn);
 
 /*
  * set to 1 to panic kernel if can't successfully enable VT-d
@@ -996,6 +998,117 @@ out:
        spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
+#ifdef CONFIG_DMAR_DEBUG
+static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn, u8 bus, u8 devfn)
+{
+       struct device_domain_info *info;
+       struct dma_pte *parent, *pte;
+       struct dmar_domain *domain;
+       int offset, level;
+
+       info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn);
+       if (!info || !info->domain) {
+               pr_info("device [%02x:%02x.%d] not probed\n",
+                       bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+               return;
+       }
+
+       domain = info->domain;
+       level = agaw_to_level(domain->agaw);
+       parent = domain->pgd;
+       if (!parent) {
+               pr_info("no page table setup\n");
+               return;
+       }
+
+       while (1) {
+               offset = pfn_level_offset(pfn, level);
+               pte = &parent[offset];
+               if (!pte || (dma_pte_superpage(pte) || !dma_pte_present(pte))) {
+                       pr_info("PTE not present at level %d\n", level);
+                       break;
+               }
+
+               pr_info("pte level: %d, pte value: 0x%016llx\n", level, pte->val);
+
+               if (level == 1)
+                       break;
+
+               parent = phys_to_virt(dma_pte_addr(pte));
+               level--;
+       }
+}
+
+void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+                         unsigned long long addr, u32 pasid)
+{
+       struct pasid_dir_entry *dir, *pde;
+       struct pasid_entry *entries, *pte;
+       struct context_entry *ctx_entry;
+       struct root_entry *rt_entry;
+       u8 devfn = source_id & 0xff;
+       u8 bus = source_id >> 8;
+       int i, dir_index, index;
+
+       pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr);
+
+       /* root entry dump */
+       rt_entry = &iommu->root_entry[bus];
+       if (!rt_entry) {
+               pr_info("root table entry is not present\n");
+               return;
+       }
+
+       if (sm_supported(iommu))
+               pr_info("scalable mode root entry: hi 0x%016llx, low 0x%016llx\n",
+                       rt_entry->hi, rt_entry->lo);
+       else
+               pr_info("root entry: 0x%016llx", rt_entry->lo);
+
+       /* context entry dump */
+       ctx_entry = iommu_context_addr(iommu, bus, devfn, 0);
+       if (!ctx_entry) {
+               pr_info("context table entry is not present\n");
+               return;
+       }
+
+       pr_info("context entry: hi 0x%016llx, low 0x%016llx\n",
+               ctx_entry->hi, ctx_entry->lo);
+
+       /* legacy mode does not require PASID entries */
+       if (!sm_supported(iommu))
+               goto pgtable_walk;
+
+       /* get the pointer to pasid directory entry */
+       dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
+       if (!dir) {
+               pr_info("pasid directory entry is not present\n");
+               return;
+       }
+       /* For request-without-pasid, get the pasid from context entry */
+       if (intel_iommu_sm && pasid == INVALID_IOASID)
+               pasid = PASID_RID2PASID;
+
+       dir_index = pasid >> PASID_PDE_SHIFT;
+       pde = &dir[dir_index];
+       pr_info("pasid dir entry: 0x%016llx\n", pde->val);
+
+       /* get the pointer to the pasid table entry */
+       entries = get_pasid_table_from_pde(pde);
+       if (!entries) {
+               pr_info("pasid table entry is not present\n");
+               return;
+       }
+       index = pasid & PASID_PTE_MASK;
+       pte = &entries[index];
+       for (i = 0; i < ARRAY_SIZE(pte->val); i++)
+               pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]);
+
+pgtable_walk:
+       pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn);
+}
+#endif
+
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
                                      unsigned long pfn, int *target_level)
 {

diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e04436a7ff271dfa9ca08c48dba341f60ed8c87e..45e903d8473355b85958896e357b924316db7a38 100644 (file)
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -131,6 +131,14 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
        return 0;
 }
 
+#ifdef CONFIG_DMAR_DEBUG
+void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+                         unsigned long long addr, u32 pasid);
+#else
+static inline void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
+                                       unsigned long long addr, u32 pasid) {}
+#endif
+
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);