Merge tag 'iommu-fixes-v5.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU fixes from Joerg Roedel:

 - Intel VT-d fixes:
    - RCU list handling fixes
    - Replace WARN_TAINT with pr_warn + add_taint for reporting firmware
      issues
    - DebugFS fixes
    - Fix for hugepage handling in iova_to_phys implementation
    - Fix for handling VMD devices, which have a domain number which
      doesn't fit into 16 bits
    - Warning message fix

 - MSI allocation fix for iommu-dma code

 - Sign-extension fix for io page-table code

 - Fix for AMD-Vi to properly update the is-running bit when AVIC is
   used

* tag 'iommu-fixes-v5.6-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/vt-d: Populate debugfs if IOMMUs are detected
  iommu/amd: Fix IOMMU AVIC not properly update the is_run bit in IRTE
  iommu/vt-d: Ignore devices with out-of-spec domain number
  iommu/vt-d: Fix the wrong printing in RHSA parsing
  iommu/vt-d: Fix debugfs register reads
  iommu/vt-d: quirk_ioat_snb_local_iommu: replace WARN_TAINT with pr_warn + add_taint
  iommu/vt-d: dmar_parse_one_rmrr: replace WARN_TAINT with pr_warn + add_taint
  iommu/vt-d: dmar: replace WARN_TAINT with pr_warn + add_taint
  iommu/vt-d: Silence RCU-list debugging warnings
  iommu/vt-d: Fix RCU-list bugs in intel_iommu_init()
  iommu/dma: Fix MSI reservation allocation
  iommu/io-pgtable-arm: Fix IOVA validation for 32-bit
  iommu/vt-d: Fix a bug in intel_iommu_iova_to_phys() for huge page
  iommu/vt-d: Fix RCU list debugging warnings

8 files changed, 94 insertions, 49 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index aac132bd1ef0..20cce366e951 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3826,7 +3826,7 @@ int amd_iommu_activate_guest_mode(void *data)
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
 	return modify_irte_ga(ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, NULL);
+			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
 
@@ -3852,7 +3852,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
 
 	return modify_irte_ga(ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, NULL);
+			      ir_data->irq_2_irte.index, entry, ir_data);
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a2e96a5fd9a7..ba128d1cdaee 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -177,15 +177,15 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
 	start -= iova_offset(iovad, start);
 	num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);
 
-	msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL);
-	if (!msi_page)
-		return -ENOMEM;
-
 	for (i = 0; i < num_pages; i++) {
-		msi_page[i].phys = start;
-		msi_page[i].iova = start;
-		INIT_LIST_HEAD(&msi_page[i].list);
-		list_add(&msi_page[i].list, &cookie->msi_page_list);
+		msi_page = kmalloc(sizeof(*msi_page), GFP_KERNEL);
+		if (!msi_page)
+			return -ENOMEM;
+
+		msi_page->phys = start;
+		msi_page->iova = start;
+		INIT_LIST_HEAD(&msi_page->list);
+		list_add(&msi_page->list, &cookie->msi_page_list);
 		start += iovad->granule;
 	}
 
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 071bb42bbbc5..f77dae7ba7d4 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/iommu.h>
 #include <linux/numa.h>
+#include <linux/limits.h>
 #include <asm/irq_remapping.h>
 #include <asm/iommu_table.h>
 
@@ -128,6 +129,13 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 
 	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
+	 */
+	if (pci_domain_nr(dev->bus) > U16_MAX)
+		return NULL;
+
 	/* Only generate path[] for device addition event */
 	if (event == BUS_NOTIFY_ADD_DEVICE)
 		for (tmp = dev; tmp; tmp = tmp->bus->self)
@@ -363,7 +371,8 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
 {
 	struct dmar_drhd_unit *dmaru;
 
-	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
+	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list,
+				dmar_rcu_check())
 		if (dmaru->segment == drhd->segment &&
 		    dmaru->reg_base_addr == drhd->address)
 			return dmaru;
@@ -440,12 +449,13 @@ static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
 
 	/* Check for NUL termination within the designated length */
 	if (strnlen(andd->device_name, header->length - 8) == header->length - 8) {
-		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+		pr_warn(FW_BUG
 			   "Your BIOS is broken; ANDD object name is not NUL-terminated\n"
 			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
 			   dmi_get_system_info(DMI_BIOS_VENDOR),
 			   dmi_get_system_info(DMI_BIOS_VERSION),
 			   dmi_get_system_info(DMI_PRODUCT_VERSION));
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		return -EINVAL;
 	}
 	pr_info("ANDD device: %x name: %s\n", andd->device_number,
@@ -471,14 +481,14 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
 			return 0;
 		}
 	}
-	WARN_TAINT(
-		1, TAINT_FIRMWARE_WORKAROUND,
+	pr_warn(FW_BUG
 		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
 		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
-		drhd->reg_base_addr,
+		rhsa->base_address,
 		dmi_get_system_info(DMI_BIOS_VENDOR),
 		dmi_get_system_info(DMI_BIOS_VERSION),
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 
 	return 0;
 }
@@ -827,14 +837,14 @@ int __init dmar_table_init(void)
 
 static void warn_invalid_dmar(u64 addr, const char *message)
 {
-	WARN_TAINT_ONCE(
-		1, TAINT_FIRMWARE_WORKAROUND,
+	pr_warn_once(FW_BUG
 		"Your BIOS is broken; DMAR reported at address %llx%s!\n"
 		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
 		addr, message,
 		dmi_get_system_info(DMI_BIOS_VENDOR),
 		dmi_get_system_info(DMI_BIOS_VERSION),
 		dmi_get_system_info(DMI_PRODUCT_VERSION));
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 }
 
 static int __ref
diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
index c1257bef553c..3eb1fe240fb0 100644
--- a/drivers/iommu/intel-iommu-debugfs.c
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -33,38 +33,42 @@ struct iommu_regset {
 
 #define IOMMU_REGSET_ENTRY(_reg_)					\
 	{ DMAR_##_reg_##_REG, __stringify(_reg_) }
-static const struct iommu_regset iommu_regs[] = {
+
+static const struct iommu_regset iommu_regs_32[] = {
 	IOMMU_REGSET_ENTRY(VER),
-	IOMMU_REGSET_ENTRY(CAP),
-	IOMMU_REGSET_ENTRY(ECAP),
 	IOMMU_REGSET_ENTRY(GCMD),
 	IOMMU_REGSET_ENTRY(GSTS),
-	IOMMU_REGSET_ENTRY(RTADDR),
-	IOMMU_REGSET_ENTRY(CCMD),
 	IOMMU_REGSET_ENTRY(FSTS),
 	IOMMU_REGSET_ENTRY(FECTL),
 	IOMMU_REGSET_ENTRY(FEDATA),
 	IOMMU_REGSET_ENTRY(FEADDR),
 	IOMMU_REGSET_ENTRY(FEUADDR),
-	IOMMU_REGSET_ENTRY(AFLOG),
 	IOMMU_REGSET_ENTRY(PMEN),
 	IOMMU_REGSET_ENTRY(PLMBASE),
 	IOMMU_REGSET_ENTRY(PLMLIMIT),
+	IOMMU_REGSET_ENTRY(ICS),
+	IOMMU_REGSET_ENTRY(PRS),
+	IOMMU_REGSET_ENTRY(PECTL),
+	IOMMU_REGSET_ENTRY(PEDATA),
+	IOMMU_REGSET_ENTRY(PEADDR),
+	IOMMU_REGSET_ENTRY(PEUADDR),
+};
+
+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),
 	IOMMU_REGSET_ENTRY(IQT),
 	IOMMU_REGSET_ENTRY(IQA),
-	IOMMU_REGSET_ENTRY(ICS),
 	IOMMU_REGSET_ENTRY(IRTA),
 	IOMMU_REGSET_ENTRY(PQH),
 	IOMMU_REGSET_ENTRY(PQT),
 	IOMMU_REGSET_ENTRY(PQA),
-	IOMMU_REGSET_ENTRY(PRS),
-	IOMMU_REGSET_ENTRY(PECTL),
-	IOMMU_REGSET_ENTRY(PEDATA),
-	IOMMU_REGSET_ENTRY(PEADDR),
-	IOMMU_REGSET_ENTRY(PEUADDR),
 	IOMMU_REGSET_ENTRY(MTRRCAP),
 	IOMMU_REGSET_ENTRY(MTRRDEF),
 	IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000),
@@ -127,10 +131,16 @@ static int iommu_regset_show(struct seq_file *m, void *unused)
 		 * by adding the offset to the pointer (virtual address).
 		 */
 		raw_spin_lock_irqsave(&iommu->register_lock, flag);
-		for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) {
-			value = dmar_readq(iommu->reg + iommu_regs[i].offset);
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_32); i++) {
+			value = dmar_readl(iommu->reg + iommu_regs_32[i].offset);
+			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
+				   iommu_regs_32[i].regs, iommu_regs_32[i].offset,
+				   value);
+		}
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs_64); i++) {
+			value = dmar_readq(iommu->reg + iommu_regs_64[i].offset);
 			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
-				   iommu_regs[i].regs, iommu_regs[i].offset,
+				   iommu_regs_64[i].regs, iommu_regs_64[i].offset,
 				   value);
 		}
 		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
@@ -272,9 +282,16 @@ static int dmar_translation_struct_show(struct seq_file *m, void *unused)
 {
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
+	u32 sts;
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
+		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;
+		}
 		root_tbl_walk(m, iommu);
 		seq_putc(m, '\n');
 	}
@@ -415,6 +432,7 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused)
 	struct dmar_drhd_unit *drhd;
 	struct intel_iommu *iommu;
 	u64 irta;
+	u32 sts;
 
 	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
@@ -424,7 +442,8 @@ static int ir_translation_struct_show(struct seq_file *m, void *unused)
 		seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n",
 			   iommu->name);
 
-		if (iommu->ir_table) {
+		sts = dmar_readl(iommu->reg + DMAR_GSTS_REG);
+		if (iommu->ir_table && (sts & DMA_GSTS_IRES)) {
 			irta = virt_to_phys(iommu->ir_table->base);
 			seq_printf(m, " IR table address:%llx\n", irta);
 			ir_tbl_remap_entry_show(m, iommu);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6fa6de2b6ad5..4be549478691 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -4261,10 +4261,11 @@ static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
 
 	/* we know that the this iommu should be at offset 0xa000 from vtbar */
 	drhd = dmar_find_matched_drhd_unit(pdev);
-	if (WARN_TAINT_ONCE(!drhd || drhd->reg_base_addr - vtbar != 0xa000,
-			    TAINT_FIRMWARE_WORKAROUND,
-			    "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n"))
+	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
+		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
 		pdev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+	}
 }
 DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quirk_ioat_snb_local_iommu);
 
@@ -4460,14 +4461,16 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 	struct dmar_rmrr_unit *rmrru;
 
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
-	if (rmrr_sanity_check(rmrr))
-		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
+	if (rmrr_sanity_check(rmrr)) {
+		pr_warn(FW_BUG
 			   "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
 			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
 			   rmrr->base_address, rmrr->end_address,
 			   dmi_get_system_info(DMI_BIOS_VENDOR),
 			   dmi_get_system_info(DMI_BIOS_VERSION),
 			   dmi_get_system_info(DMI_PRODUCT_VERSION));
+		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+	}
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
@@ -5130,6 +5133,9 @@ int __init intel_iommu_init(void)
 
 	down_write(&dmar_global_lock);
 
+	if (!no_iommu)
+		intel_iommu_debugfs_init();
+
 	if (no_iommu || dmar_disabled) {
 		/*
 		 * We exit the function here to ensure IOMMU's remapping and
@@ -5193,6 +5199,7 @@ int __init intel_iommu_init(void)
 
 	init_iommu_pm_ops();
 
+	down_read(&dmar_global_lock);
 	for_each_active_iommu(iommu, drhd) {
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
@@ -5200,6 +5207,7 @@ int __init intel_iommu_init(void)
 		iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
 		iommu_device_register(&iommu->iommu);
 	}
+	up_read(&dmar_global_lock);
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	if (si_domain && !hw_pass_through)
@@ -5210,7 +5218,6 @@ int __init intel_iommu_init(void)
 	down_read(&dmar_global_lock);
 	if (probe_acpi_namespace_devices())
 		pr_warn("ACPI name space devices didn't probe correctly\n");
-	up_read(&dmar_global_lock);
 
 	/* Finally, we enable the DMA remapping hardware. */
 	for_each_iommu(iommu, drhd) {
@@ -5219,10 +5226,11 @@ int __init intel_iommu_init(void)
 
 		iommu_disable_protect_mem_regions(iommu);
 	}
+	up_read(&dmar_global_lock);
+
 	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");
 
 	intel_iommu_enabled = 1;
-	intel_iommu_debugfs_init();
 
 	return 0;
 
@@ -5700,8 +5708,10 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	u64 phys = 0;
 
 	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
-	if (pte)
-		phys = dma_pte_addr(pte);
+	if (pte && dma_pte_present(pte))
+		phys = dma_pte_addr(pte) +
+			(iova & (BIT_MASK(level_to_offset_bits(level) +
+						VTD_PAGE_SHIFT) - 1));
 
 	return phys;
 }
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 983b08477e64..04fbd4bf0ff9 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -468,7 +468,7 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	arm_lpae_iopte *ptep = data->pgd;
 	int ret, lvl = data->start_level;
 	arm_lpae_iopte prot;
-	long iaext = (long)iova >> cfg->ias;
+	long iaext = (s64)iova >> cfg->ias;
 
 	/* If no access, then nothing to do */
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
@@ -645,7 +645,7 @@ static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	arm_lpae_iopte *ptep = data->pgd;
-	long iaext = (long)iova >> cfg->ias;
+	long iaext = (s64)iova >> cfg->ias;
 
 	if (WARN_ON(!size || (size & cfg->pgsize_bitmap) != size))
 		return 0;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index f64ca27dc210..d7bf029df737 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -69,19 +69,23 @@ struct dmar_pci_notify_info {
 extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
-#define for_each_drhd_unit(drhd) \
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)
+#define for_each_drhd_unit(drhd)					\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())
 
 #define for_each_active_drhd_unit(drhd)					\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (drhd->ignored) {} else
 
 #define for_each_active_iommu(i, drhd)					\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (i=drhd->iommu, drhd->ignored) {} else
 
 #define for_each_iommu(i, drhd)						\
-	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list,		\
+				dmar_rcu_check())			\
 		if (i=drhd->iommu, 0) {} else 
 
 static inline bool dmar_rcu_check(void)
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 4a16b39ae353..980234ae0312 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -123,6 +123,8 @@
 
 #define dmar_readq(a) readq(a)
 #define dmar_writeq(a,v) writeq(v,a)
+#define dmar_readl(a) readl(a)
+#define dmar_writel(a, v) writel(v, a)
 
 #define DMAR_VER_MAJOR(v)		(((v) & 0xf0) >> 4)
 #define DMAR_VER_MINOR(v)		((v) & 0x0f)