1 files changed, 199 insertions, 54 deletions

diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index 62e23ff3c987..617fd81a80f0 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -10,11 +10,11 @@
 
 #include <linux/debugfs.h>
 #include <linux/dmar.h>
-#include <linux/intel-iommu.h>
 #include <linux/pci.h>
 
 #include <asm/irq_remapping.h>
 
+#include "iommu.h"
 #include "pasid.h"
 #include "perf.h"
 
@@ -62,8 +62,6 @@ static const struct iommu_regset iommu_regs_64[] = {
 	IOMMU_REGSET_ENTRY(CAP),
 	IOMMU_REGSET_ENTRY(ECAP),
 	IOMMU_REGSET_ENTRY(RTADDR),
-	IOMMU_REGSET_ENTRY(CCMD),
-	IOMMU_REGSET_ENTRY(AFLOG),
 	IOMMU_REGSET_ENTRY(PHMBASE),
 	IOMMU_REGSET_ENTRY(PHMLIMIT),
 	IOMMU_REGSET_ENTRY(IQH),
@@ -106,11 +104,10 @@ static const struct iommu_regset iommu_regs_64[] = {
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9),
 	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9),
-	IOMMU_REGSET_ENTRY(VCCAP),
-	IOMMU_REGSET_ENTRY(VCMD),
-	IOMMU_REGSET_ENTRY(VCRSP),
 };
 
+static struct dentry *intel_iommu_debug;
+
 static int iommu_regset_show(struct seq_file *m, void *unused)
 {
 	struct dmar_drhd_unit *drhd;
@@ -263,10 +260,9 @@ static void ctx_tbl_walk(struct seq_file *m, struct intel_iommu *iommu, u16 bus)
 
 static void root_tbl_walk(struct seq_file *m, struct intel_iommu *iommu)
 {
-	unsigned long flags;
 	u16 bus;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	spin_lock(&iommu->lock);
 	seq_printf(m, "IOMMU %s: Root Table Address: 0x%llx\n", iommu->name,
 		   (u64)virt_to_phys(iommu->root_entry));
 	seq_puts(m, "B.D.F\tRoot_entry\t\t\t\tContext_entry\t\t\t\tPASID\tPASID_table_entry\n");
@@ -278,8 +274,7 @@ static void root_tbl_walk(struct seq_file *m, struct intel_iommu *iommu)
 	 */
 	for (bus = 0; bus < 256; bus++)
 		ctx_tbl_walk(m, iommu, bus);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	spin_unlock(&iommu->lock);
 }
 
 static int dmar_translation_struct_show(struct seq_file *m, void *unused)
@@ -313,9 +308,14 @@ static inline unsigned long level_to_directory_size(int level)
 static inline void
 dump_page_info(struct seq_file *m, unsigned long iova, u64 *path)
 {
-	seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\t0x%016llx\n",
-		   iova >> VTD_PAGE_SHIFT, path[5], path[4],
-		   path[3], path[2], path[1]);
+	seq_printf(m, "0x%013lx |\t0x%016llx\t0x%016llx\t0x%016llx",
+		   iova >> VTD_PAGE_SHIFT, path[5], path[4], path[3]);
+	if (path[2]) {
+		seq_printf(m, "\t0x%016llx", path[2]);
+		if (path[1])
+			seq_printf(m, "\t0x%016llx", path[1]);
+	}
+	seq_putc(m, '\n');
 }
 
 static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
@@ -342,39 +342,153 @@ static void pgtable_walk_level(struct seq_file *m, struct dma_pte *pde,
 	}
 }
 
-static int show_device_domain_translation(struct device *dev, void *data)
+static int domain_translation_struct_show(struct seq_file *m,
+					  struct device_domain_info *info,
+					  ioasid_t pasid)
 {
-	struct dmar_domain *domain = find_domain(dev);
-	struct seq_file *m = data;
-	u64 path[6] = { 0 };
+	bool scalable, found = false;
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	u16 devfn, bus, seg;
 
-	if (!domain)
-		return 0;
+	bus = info->bus;
+	devfn = info->devfn;
+	seg = info->segment;
 
-	seq_printf(m, "Device %s with pasid %d @0x%llx\n",
-		   dev_name(dev), domain->default_pasid,
-		   (u64)virt_to_phys(domain->pgd));
-	seq_puts(m, "IOVA_PFN\t\tPML5E\t\t\tPML4E\t\t\tPDPE\t\t\tPDE\t\t\tPTE\n");
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		struct context_entry *context;
+		u64 pgd, path[6] = { 0 };
+		u32 sts, agaw;
 
-	pgtable_walk_level(m, domain->pgd, domain->agaw + 2, 0, path);
-	seq_putc(m, '\n');
+		if (seg != iommu->segment)
+			continue;
+
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (!(sts & DMA_GSTS_TES)) {
+			seq_printf(m, "DMA Remapping is not enabled on %s\n",
+				   iommu->name);
+			continue;
+		}
+		if (dmar_readq(iommu->reg + DMAR_RTADDR_REG) & DMA_RTADDR_SMT)
+			scalable = true;
+		else
+			scalable = false;
+
+		/*
+		 * The iommu->lock is held across the callback, which will
+		 * block calls to domain_attach/domain_detach. Hence,
+		 * the domain of the device will not change during traversal.
+		 *
+		 * Traversing page table possibly races with the iommu_unmap()
+		 * interface. This could be solved by RCU-freeing the page
+		 * table pages in the iommu_unmap() path.
+		 */
+		spin_lock(&iommu->lock);
+
+		context = iommu_context_addr(iommu, bus, devfn, 0);
+		if (!context || !context_present(context))
+			goto iommu_unlock;
+
+		if (scalable) {	/* scalable mode */
+			struct pasid_entry *pasid_tbl, *pasid_tbl_entry;
+			struct pasid_dir_entry *dir_tbl, *dir_entry;
+			u16 dir_idx, tbl_idx, pgtt;
+			u64 pasid_dir_ptr;
+
+			pasid_dir_ptr = context->lo & VTD_PAGE_MASK;
+
+			/* Dump specified device domain mappings with PASID. */
+			dir_idx = pasid >> PASID_PDE_SHIFT;
+			tbl_idx = pasid & PASID_PTE_MASK;
+
+			dir_tbl = phys_to_virt(pasid_dir_ptr);
+			dir_entry = &dir_tbl[dir_idx];
+
+			pasid_tbl = get_pasid_table_from_pde(dir_entry);
+			if (!pasid_tbl)
+				goto iommu_unlock;
+
+			pasid_tbl_entry = &pasid_tbl[tbl_idx];
+			if (!pasid_pte_is_present(pasid_tbl_entry))
+				goto iommu_unlock;
+
+			/*
+			 * According to PASID Granular Translation Type(PGTT),
+			 * get the page table pointer.
+			 */
+			pgtt = (u16)(pasid_tbl_entry->val[0] & GENMASK_ULL(8, 6)) >> 6;
+			agaw = (u8)(pasid_tbl_entry->val[0] & GENMASK_ULL(4, 2)) >> 2;
+
+			switch (pgtt) {
+			case PASID_ENTRY_PGTT_FL_ONLY:
+				pgd = pasid_tbl_entry->val[2];
+				break;
+			case PASID_ENTRY_PGTT_SL_ONLY:
+			case PASID_ENTRY_PGTT_NESTED:
+				pgd = pasid_tbl_entry->val[0];
+				break;
+			default:
+				goto iommu_unlock;
+			}
+			pgd &= VTD_PAGE_MASK;
+		} else { /* legacy mode */
+			u8 tt = (u8)(context->lo & GENMASK_ULL(3, 2)) >> 2;
+
+			/*
+			 * According to Translation Type(TT),
+			 * get the page table pointer(SSPTPTR).
+			 */
+			switch (tt) {
+			case CONTEXT_TT_MULTI_LEVEL:
+			case CONTEXT_TT_DEV_IOTLB:
+				pgd = context->lo & VTD_PAGE_MASK;
+				agaw = context->hi & 7;
+				break;
+			default:
+				goto iommu_unlock;
+			}
+		}
+
+		seq_printf(m, "Device %04x:%02x:%02x.%x ",
+			   iommu->segment, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+		if (scalable)
+			seq_printf(m, "with pasid %x @0x%llx\n", pasid, pgd);
+		else
+			seq_printf(m, "@0x%llx\n", pgd);
+
+		seq_printf(m, "%-17s\t%-18s\t%-18s\t%-18s\t%-18s\t%-s\n",
+			   "IOVA_PFN", "PML5E", "PML4E", "PDPE", "PDE", "PTE");
+		pgtable_walk_level(m, phys_to_virt(pgd), agaw + 2, 0, path);
+
+		found = true;
+iommu_unlock:
+		spin_unlock(&iommu->lock);
+		if (found)
+			break;
+	}
+	rcu_read_unlock();
 
 	return 0;
 }
 
-static int domain_translation_struct_show(struct seq_file *m, void *unused)
+static int dev_domain_translation_struct_show(struct seq_file *m, void *unused)
 {
-	unsigned long flags;
-	int ret;
+	struct device_domain_info *info = (struct device_domain_info *)m->private;
 
-	spin_lock_irqsave(&device_domain_lock, flags);
-	ret = bus_for_each_dev(&pci_bus_type, NULL, m,
-			       show_device_domain_translation);
-	spin_unlock_irqrestore(&device_domain_lock, flags);
+	return domain_translation_struct_show(m, info, IOMMU_NO_PASID);
+}
+DEFINE_SHOW_ATTRIBUTE(dev_domain_translation_struct);
 
-	return ret;
+static int pasid_domain_translation_struct_show(struct seq_file *m, void *unused)
+{
+	struct dev_pasid_info *dev_pasid = (struct dev_pasid_info *)m->private;
+	struct device_domain_info *info = dev_iommu_priv_get(dev_pasid->dev);
+
+	return domain_translation_struct_show(m, info, dev_pasid->pasid);
 }
-DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
+DEFINE_SHOW_ATTRIBUTE(pasid_domain_translation_struct);
 
 static void invalidation_queue_entry_show(struct seq_file *m,
 					  struct intel_iommu *iommu)
@@ -545,17 +659,11 @@ DEFINE_SHOW_ATTRIBUTE(ir_translation_struct);
 static void latency_show_one(struct seq_file *m, struct intel_iommu *iommu,
 			     struct dmar_drhd_unit *drhd)
 {
-	int ret;
-
 	seq_printf(m, "IOMMU: %s Register Base Address: %llx\n",
 		   iommu->name, drhd->reg_base_addr);
 
-	ret = dmar_latency_snapshot(iommu, debug_buf, DEBUG_BUFFER_SIZE);
-	if (ret < 0)
-		seq_puts(m, "Failed to get latency snapshot");
-	else
-		seq_puts(m, debug_buf);
-	seq_puts(m, "\n");
+	dmar_latency_snapshot(iommu, debug_buf, DEBUG_BUFFER_SIZE);
+	seq_printf(m, "%s\n", debug_buf);
 }
 
 static int latency_show(struct seq_file *m, void *v)
@@ -603,7 +711,6 @@ static ssize_t dmar_perf_latency_write(struct file *filp,
 			dmar_latency_disable(iommu, DMAR_LATENCY_INV_IOTLB);
 			dmar_latency_disable(iommu, DMAR_LATENCY_INV_DEVTLB);
 			dmar_latency_disable(iommu, DMAR_LATENCY_INV_IEC);
-			dmar_latency_disable(iommu, DMAR_LATENCY_PRQ);
 		}
 		rcu_read_unlock();
 		break;
@@ -625,12 +732,6 @@ static ssize_t dmar_perf_latency_write(struct file *filp,
 			dmar_latency_enable(iommu, DMAR_LATENCY_INV_IEC);
 		rcu_read_unlock();
 		break;
-	case 4:
-		rcu_read_lock();
-		for_each_active_iommu(iommu, drhd)
-			dmar_latency_enable(iommu, DMAR_LATENCY_PRQ);
-		rcu_read_unlock();
-		break;
 	default:
 		return -EINVAL;
 	}
@@ -649,16 +750,12 @@ static const struct file_operations dmar_perf_latency_fops = {
 
 void __init intel_iommu_debugfs_init(void)
 {
-	struct dentry *intel_iommu_debug = debugfs_create_dir("intel",
-						iommu_debugfs_dir);
+	intel_iommu_debug = debugfs_create_dir("intel", iommu_debugfs_dir);
 
 	debugfs_create_file("iommu_regset", 0444, intel_iommu_debug, NULL,
 			    &iommu_regset_fops);
 	debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug,
 			    NULL, &dmar_translation_struct_fops);
-	debugfs_create_file("domain_translation_struct", 0444,
-			    intel_iommu_debug, NULL,
-			    &domain_translation_struct_fops);
 	debugfs_create_file("invalidation_queue", 0444, intel_iommu_debug,
 			    NULL, &invalidation_queue_fops);
 #ifdef CONFIG_IRQ_REMAP
@@ -668,3 +765,51 @@ void __init intel_iommu_debugfs_init(void)
 	debugfs_create_file("dmar_perf_latency", 0644, intel_iommu_debug,
 			    NULL, &dmar_perf_latency_fops);
 }
+
+/*
+ * Create a debugfs directory for each device, and then create a
+ * debugfs file in this directory for users to dump the page table
+ * of the default domain. e.g.
+ * /sys/kernel/debug/iommu/intel/0000:00:01.0/domain_translation_struct
+ */
+void intel_iommu_debugfs_create_dev(struct device_domain_info *info)
+{
+	info->debugfs_dentry = debugfs_create_dir(dev_name(info->dev), intel_iommu_debug);
+
+	debugfs_create_file("domain_translation_struct", 0444, info->debugfs_dentry,
+			    info, &dev_domain_translation_struct_fops);
+}
+
+/* Remove the device debugfs directory. */
+void intel_iommu_debugfs_remove_dev(struct device_domain_info *info)
+{
+	debugfs_remove_recursive(info->debugfs_dentry);
+}
+
+/*
+ * Create a debugfs directory per pair of {device, pasid}, then create the
+ * corresponding debugfs file in this directory for users to dump its page
+ * table. e.g.
+ * /sys/kernel/debug/iommu/intel/0000:00:01.0/1/domain_translation_struct
+ *
+ * The debugfs only dumps the page tables whose mappings are created and
+ * destroyed by the iommu_map/unmap() interfaces. Check the mapping type
+ * of the domain before creating debugfs directory.
+ */
+void intel_iommu_debugfs_create_dev_pasid(struct dev_pasid_info *dev_pasid)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev_pasid->dev);
+	char dir_name[10];
+
+	sprintf(dir_name, "%x", dev_pasid->pasid);
+	dev_pasid->debugfs_dentry = debugfs_create_dir(dir_name, info->debugfs_dentry);
+
+	debugfs_create_file("domain_translation_struct", 0444, dev_pasid->debugfs_dentry,
+			    dev_pasid, &pasid_domain_translation_struct_fops);
+}
+
+/* Remove the device pasid debugfs directory. */
+void intel_iommu_debugfs_remove_dev_pasid(struct dev_pasid_info *dev_pasid)
+{
+	debugfs_remove_recursive(dev_pasid->debugfs_dentry);
+}