Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 226 insertions, 230 deletions

diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
index 012cd2541a..f52fb39c96 100644
--- a/drivers/iommu/intel/Kconfig
+++ b/drivers/iommu/intel/Kconfig
@@ -51,6 +51,7 @@ config INTEL_IOMMU_SVM
 	depends on X86_64
 	select MMU_NOTIFIER
 	select IOMMU_SVA
+	select IOMMU_IOPF
 	help
 	  Shared Virtual Memory (SVM) provides a facility for devices
 	  to access DMA resources through process address space by
@@ -64,17 +65,6 @@ config INTEL_IOMMU_DEFAULT_ON
 	  one is found. If this option is not selected, DMAR support can
 	  be enabled by passing intel_iommu=on to the kernel.
 
-config INTEL_IOMMU_BROKEN_GFX_WA
-	bool "Workaround broken graphics drivers (going away soon)"
-	depends on BROKEN && X86
-	help
-	  Current Graphics drivers tend to use physical address
-	  for DMA and avoid using DMA APIs. Setting this config
-	  option permits the IOMMU driver to set a unity map for
-	  all the OS-visible memory. Hence the driver can continue
-	  to use physical addresses for DMA, at least until this
-	  option is removed in the 2.6.32 kernel.
-
 config INTEL_IOMMU_FLOPPY_WA
 	def_bool y
 	depends on X86
@@ -97,8 +87,8 @@ config INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON
 	  the default value.
 
 config INTEL_IOMMU_PERF_EVENTS
-	def_bool y
 	bool "Intel IOMMU performance events"
+	default y
 	depends on INTEL_IOMMU && PERF_EVENTS
 	help
 	  Selecting this option will enable the performance monitoring
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index d7e10f1311..e4a03588a8 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -27,7 +27,6 @@
 #include "iommu.h"
 #include "../dma-iommu.h"
 #include "../irq_remapping.h"
-#include "../iommu-sva.h"
 #include "pasid.h"
 #include "cap_audit.h"
 #include "perfmon.h"
@@ -222,12 +221,11 @@ int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON);
 int intel_iommu_enabled = 0;
 EXPORT_SYMBOL_GPL(intel_iommu_enabled);
 
-static int dmar_map_gfx = 1;
 static int intel_iommu_superpage = 1;
 static int iommu_identity_mapping;
 static int iommu_skip_te_disable;
+static int disable_igfx_iommu;
 
-#define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
 const struct iommu_ops intel_iommu_ops;
@@ -266,7 +264,7 @@ static int __init intel_iommu_setup(char *str)
 			no_platform_optin = 1;
 			pr_info("IOMMU disabled\n");
 		} else if (!strncmp(str, "igfx_off", 8)) {
-			dmar_map_gfx = 0;
+			disable_igfx_iommu = 1;
 			pr_info("Disable GFX device mapping\n");
 		} else if (!strncmp(str, "forcedac", 8)) {
 			pr_warn("intel_iommu=forcedac deprecated; use iommu.forcedac instead\n");
@@ -1851,34 +1849,17 @@ static void domain_exit(struct dmar_domain *domain)
 	kfree(domain);
 }
 
-/*
- * Get the PASID directory size for scalable mode context entry.
- * Value of X in the PDTS field of a scalable mode context entry
- * indicates PASID directory with 2^(X + 7) entries.
- */
-static unsigned long context_get_sm_pds(struct pasid_table *table)
-{
-	unsigned long pds, max_pde;
-
-	max_pde = table->max_pasid >> PASID_PDE_SHIFT;
-	pds = find_first_bit(&max_pde, MAX_NR_PASID_BITS);
-	if (pds < 7)
-		return 0;
-
-	return pds - 7;
-}
-
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
-				      struct pasid_table *table,
 				      u8 bus, u8 devfn)
 {
 	struct device_domain_info *info =
 			domain_lookup_dev_info(domain, iommu, bus, devfn);
 	u16 did = domain_id_iommu(domain, iommu);
 	int translation = CONTEXT_TT_MULTI_LEVEL;
+	struct dma_pte *pgd = domain->pgd;
 	struct context_entry *context;
-	int ret;
+	int agaw, ret;
 
 	if (hw_pass_through && domain_type_is_si(domain))
 		translation = CONTEXT_TT_PASS_THROUGH;
@@ -1921,65 +1902,37 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	}
 
 	context_clear_entry(context);
+	context_set_domain_id(context, did);
 
-	if (sm_supported(iommu)) {
-		unsigned long pds;
-
-		/* Setup the PASID DIR pointer: */
-		pds = context_get_sm_pds(table);
-		context->lo = (u64)virt_to_phys(table->table) |
-				context_pdts(pds);
-
-		/* Setup the RID_PASID field: */
-		context_set_sm_rid2pasid(context, IOMMU_NO_PASID);
-
+	if (translation != CONTEXT_TT_PASS_THROUGH) {
 		/*
-		 * Setup the Device-TLB enable bit and Page request
-		 * Enable bit:
+		 * Skip top levels of page tables for iommu which has
+		 * less agaw than default. Unnecessary for PT mode.
 		 */
-		if (info && info->ats_supported)
-			context_set_sm_dte(context);
-		if (info && info->pri_supported)
-			context_set_sm_pre(context);
-		if (info && info->pasid_supported)
-			context_set_pasid(context);
-	} else {
-		struct dma_pte *pgd = domain->pgd;
-		int agaw;
-
-		context_set_domain_id(context, did);
-
-		if (translation != CONTEXT_TT_PASS_THROUGH) {
-			/*
-			 * Skip top levels of page tables for iommu which has
-			 * less agaw than default. Unnecessary for PT mode.
-			 */
-			for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-				ret = -ENOMEM;
-				pgd = phys_to_virt(dma_pte_addr(pgd));
-				if (!dma_pte_present(pgd))
-					goto out_unlock;
-			}
-
-			if (info && info->ats_supported)
-				translation = CONTEXT_TT_DEV_IOTLB;
-			else
-				translation = CONTEXT_TT_MULTI_LEVEL;
-
-			context_set_address_root(context, virt_to_phys(pgd));
-			context_set_address_width(context, agaw);
-		} else {
-			/*
-			 * In pass through mode, AW must be programmed to
-			 * indicate the largest AGAW value supported by
-			 * hardware. And ASR is ignored by hardware.
-			 */
-			context_set_address_width(context, iommu->msagaw);
+		for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+			ret = -ENOMEM;
+			pgd = phys_to_virt(dma_pte_addr(pgd));
+			if (!dma_pte_present(pgd))
+				goto out_unlock;
 		}
 
-		context_set_translation_type(context, translation);
+		if (info && info->ats_supported)
+			translation = CONTEXT_TT_DEV_IOTLB;
+		else
+			translation = CONTEXT_TT_MULTI_LEVEL;
+
+		context_set_address_root(context, virt_to_phys(pgd));
+		context_set_address_width(context, agaw);
+	} else {
+		/*
+		 * In pass through mode, AW must be programmed to
+		 * indicate the largest AGAW value supported by
+		 * hardware. And ASR is ignored by hardware.
+		 */
+		context_set_address_width(context, iommu->msagaw);
 	}
 
+	context_set_translation_type(context, translation);
 	context_set_fault_enable(context);
 	context_set_present(context);
 	if (!ecap_coherent(iommu->ecap))
@@ -2009,43 +1962,29 @@ out_unlock:
 	return ret;
 }
 
-struct domain_context_mapping_data {
-	struct dmar_domain *domain;
-	struct intel_iommu *iommu;
-	struct pasid_table *table;
-};
-
 static int domain_context_mapping_cb(struct pci_dev *pdev,
 				     u16 alias, void *opaque)
 {
-	struct domain_context_mapping_data *data = opaque;
+	struct device_domain_info *info = dev_iommu_priv_get(&pdev->dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct dmar_domain *domain = opaque;
 
-	return domain_context_mapping_one(data->domain, data->iommu,
-					  data->table, PCI_BUS_NUM(alias),
-					  alias & 0xff);
+	return domain_context_mapping_one(domain, iommu,
+					  PCI_BUS_NUM(alias), alias & 0xff);
 }
 
 static int
 domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct domain_context_mapping_data data;
 	struct intel_iommu *iommu = info->iommu;
 	u8 bus = info->bus, devfn = info->devfn;
-	struct pasid_table *table;
-
-	table = intel_pasid_get_table(dev);
 
 	if (!dev_is_pci(dev))
-		return domain_context_mapping_one(domain, iommu, table,
-						  bus, devfn);
-
-	data.domain = domain;
-	data.iommu = iommu;
-	data.table = table;
+		return domain_context_mapping_one(domain, iommu, bus, devfn);
 
 	return pci_for_each_dma_alias(to_pci_dev(dev),
-				      &domain_context_mapping_cb, &data);
+				      domain_context_mapping_cb, domain);
 }
 
 /* Returns a number of VTD pages, but aligned to MM page size */
@@ -2235,9 +2174,6 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 	struct context_entry *context;
 	u16 did_old;
 
-	if (!iommu)
-		return;
-
 	spin_lock(&iommu->lock);
 	context = iommu_context_addr(iommu, bus, devfn, 0);
 	if (!context) {
@@ -2245,14 +2181,7 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 		return;
 	}
 
-	if (sm_supported(iommu)) {
-		if (hw_pass_through && domain_type_is_si(info->domain))
-			did_old = FLPT_DEFAULT_DID;
-		else
-			did_old = domain_id_iommu(info->domain, iommu);
-	} else {
-		did_old = context_domain_id(context);
-	}
+	did_old = context_domain_id(context);
 
 	context_clear_entry(context);
 	__iommu_flush_cache(iommu, context, sizeof(*context));
@@ -2263,9 +2192,6 @@ static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8
 				   DMA_CCMD_MASK_NOBIT,
 				   DMA_CCMD_DEVICE_INVL);
 
-	if (sm_supported(iommu))
-		qi_flush_pasid_cache(iommu, did_old, QI_PC_ALL_PASIDS, 0);
-
 	iommu->flush.flush_iotlb(iommu,
 				 did_old,
 				 0,
@@ -2405,28 +2331,19 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	list_add(&info->link, &domain->devices);
 	spin_unlock_irqrestore(&domain->lock, flags);
 
-	/* PASID table is mandatory for a PCI device in scalable mode. */
-	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
-		/* Setup the PASID entry for requests without PASID: */
-		if (hw_pass_through && domain_type_is_si(domain))
-			ret = intel_pasid_setup_pass_through(iommu,
-					dev, IOMMU_NO_PASID);
-		else if (domain->use_first_level)
-			ret = domain_setup_first_level(iommu, domain, dev,
-					IOMMU_NO_PASID);
-		else
-			ret = intel_pasid_setup_second_level(iommu, domain,
-					dev, IOMMU_NO_PASID);
-		if (ret) {
-			dev_err(dev, "Setup RID2PASID failed\n");
-			device_block_translation(dev);
-			return ret;
-		}
-	}
+	if (dev_is_real_dma_subdevice(dev))
+		return 0;
+
+	if (!sm_supported(iommu))
+		ret = domain_context_mapping(domain, dev);
+	else if (hw_pass_through && domain_type_is_si(domain))
+		ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
+	else if (domain->use_first_level)
+		ret = domain_setup_first_level(iommu, domain, dev, IOMMU_NO_PASID);
+	else
+		ret = intel_pasid_setup_second_level(iommu, domain, dev, IOMMU_NO_PASID);
 
-	ret = domain_context_mapping(domain, dev);
 	if (ret) {
-		dev_err(dev, "Domain context map failed\n");
 		device_block_translation(dev);
 		return ret;
 	}
@@ -2484,9 +2401,6 @@ static int device_def_domain_type(struct device *dev)
 
 		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
 			return IOMMU_DOMAIN_IDENTITY;
-
-		if ((iommu_identity_mapping & IDENTMAP_GFX) && IS_GFX_DEVICE(pdev))
-			return IOMMU_DOMAIN_IDENTITY;
 	}
 
 	return 0;
@@ -2787,13 +2701,6 @@ static int __init init_dmars(void)
 		iommu_set_root_entry(iommu);
 	}
 
-#ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
-	dmar_map_gfx = 0;
-#endif
-
-	if (!dmar_map_gfx)
-		iommu_identity_mapping |= IDENTMAP_GFX;
-
 	check_tylersburg_isoch();
 
 	ret = si_domain_init(hw_pass_through);
@@ -2884,7 +2791,7 @@ static void __init init_no_remapping_devices(void)
 		/* This IOMMU has *only* gfx devices. Either bypass it or
 		   set the gfx_mapped flag, as appropriate */
 		drhd->gfx_dedicated = 1;
-		if (!dmar_map_gfx)
+		if (disable_igfx_iommu)
 			drhd->ignored = 1;
 	}
 }
@@ -4078,6 +3985,10 @@ int prepare_domain_attach_device(struct iommu_domain *domain,
 		dmar_domain->agaw--;
 	}
 
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) &&
+	    context_copied(iommu, info->bus, info->devfn))
+		return intel_pasid_setup_sm_context(dev);
+
 	return 0;
 }
 
@@ -4393,11 +4304,19 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 			dev_err(dev, "PASID table allocation failed\n");
 			goto clear_rbtree;
 		}
+
+		if (!context_copied(iommu, info->bus, info->devfn)) {
+			ret = intel_pasid_setup_sm_context(dev);
+			if (ret)
+				goto free_table;
+		}
 	}
 
 	intel_iommu_debugfs_create_dev(info);
 
 	return &iommu->iommu;
+free_table:
+	intel_pasid_free_table(dev);
 clear_rbtree:
 	device_rbtree_remove(info);
 free:
@@ -4562,23 +4481,15 @@ static int intel_iommu_enable_iopf(struct device *dev)
 	if (ret)
 		return ret;
 
-	ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
-	if (ret)
-		goto iopf_remove_device;
-
 	ret = pci_enable_pri(pdev, PRQ_DEPTH);
-	if (ret)
-		goto iopf_unregister_handler;
+	if (ret) {
+		iopf_queue_remove_device(iommu->iopf_queue, dev);
+		return ret;
+	}
+
 	info->pri_enabled = 1;
 
 	return 0;
-
-iopf_unregister_handler:
-	iommu_unregister_device_fault_handler(dev);
-iopf_remove_device:
-	iopf_queue_remove_device(iommu->iopf_queue, dev);
-
-	return ret;
 }
 
 static int intel_iommu_disable_iopf(struct device *dev)
@@ -4599,14 +4510,7 @@ static int intel_iommu_disable_iopf(struct device *dev)
 	 */
 	pci_disable_pri(to_pci_dev(dev));
 	info->pri_enabled = 0;
-
-	/*
-	 * With PRI disabled and outstanding PRQs drained, unregistering
-	 * fault handler and removing device from iopf queue should never
-	 * fail.
-	 */
-	WARN_ON(iommu_unregister_device_fault_handler(dev));
-	WARN_ON(iopf_queue_remove_device(iommu->iopf_queue, dev));
+	iopf_queue_remove_device(iommu->iopf_queue, dev);
 
 	return 0;
 }
@@ -4964,7 +4868,7 @@ static void quirk_iommu_igfx(struct pci_dev *dev)
 		return;
 
 	pci_info(dev, "Disabling IOMMU for graphics on this chipset\n");
-	dmar_map_gfx = 0;
+	disable_igfx_iommu = 1;
 }
 
 /* G4x/GM45 integrated gfx dmar support is totally busted. */
@@ -5045,8 +4949,8 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 
 	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
 		pci_info(dev, "BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
-		dmar_map_gfx = 0;
-	} else if (dmar_map_gfx) {
+		disable_igfx_iommu = 1;
+	} else if (!disable_igfx_iommu) {
 		/* we have to ensure the gfx device is idle before we flush */
 		pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n");
 		iommu_set_dma_strict();
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index cd267ba64e..404d2476a8 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -1096,8 +1096,8 @@ struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid);
 void intel_svm_check(struct intel_iommu *iommu);
 int intel_svm_enable_prq(struct intel_iommu *iommu);
 int intel_svm_finish_prq(struct intel_iommu *iommu);
-int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
-			    struct iommu_page_response *msg);
+void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
+			     struct iommu_page_response *msg);
 struct iommu_domain *intel_svm_domain_alloc(void);
 void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid);
 void intel_drain_pasid_prq(struct device *dev, u32 pasid);
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index a51e895d9a..11f0b856d7 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -734,3 +734,141 @@ void intel_pasid_teardown_sm_context(struct device *dev)
 
 	pci_for_each_dma_alias(to_pci_dev(dev), pci_pasid_table_teardown, dev);
 }
+
+/*
+ * Get the PASID directory size for scalable mode context entry.
+ * Value of X in the PDTS field of a scalable mode context entry
+ * indicates PASID directory with 2^(X + 7) entries.
+ */
+static unsigned long context_get_sm_pds(struct pasid_table *table)
+{
+	unsigned long pds, max_pde;
+
+	max_pde = table->max_pasid >> PASID_PDE_SHIFT;
+	pds = find_first_bit(&max_pde, MAX_NR_PASID_BITS);
+	if (pds < 7)
+		return 0;
+
+	return pds - 7;
+}
+
+static int context_entry_set_pasid_table(struct context_entry *context,
+					 struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct pasid_table *table = info->pasid_table;
+	struct intel_iommu *iommu = info->iommu;
+	unsigned long pds;
+
+	context_clear_entry(context);
+
+	pds = context_get_sm_pds(table);
+	context->lo = (u64)virt_to_phys(table->table) | context_pdts(pds);
+	context_set_sm_rid2pasid(context, IOMMU_NO_PASID);
+
+	if (info->ats_supported)
+		context_set_sm_dte(context);
+	if (info->pri_supported)
+		context_set_sm_pre(context);
+	if (info->pasid_supported)
+		context_set_pasid(context);
+
+	context_set_fault_enable(context);
+	context_set_present(context);
+	__iommu_flush_cache(iommu, context, sizeof(*context));
+
+	return 0;
+}
+
+static int device_pasid_table_setup(struct device *dev, u8 bus, u8 devfn)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct context_entry *context;
+
+	spin_lock(&iommu->lock);
+	context = iommu_context_addr(iommu, bus, devfn, true);
+	if (!context) {
+		spin_unlock(&iommu->lock);
+		return -ENOMEM;
+	}
+
+	if (context_present(context) && !context_copied(iommu, bus, devfn)) {
+		spin_unlock(&iommu->lock);
+		return 0;
+	}
+
+	if (context_copied(iommu, bus, devfn)) {
+		context_clear_entry(context);
+		__iommu_flush_cache(iommu, context, sizeof(*context));
+
+		/*
+		 * For kdump cases, old valid entries may be cached due to
+		 * the in-flight DMA and copied pgtable, but there is no
+		 * unmapping behaviour for them, thus we need explicit cache
+		 * flushes for all affected domain IDs and PASIDs used in
+		 * the copied PASID table. Given that we have no idea about
+		 * which domain IDs and PASIDs were used in the copied tables,
+		 * upgrade them to global PASID and IOTLB cache invalidation.
+		 */
+		iommu->flush.flush_context(iommu, 0,
+					   PCI_DEVID(bus, devfn),
+					   DMA_CCMD_MASK_NOBIT,
+					   DMA_CCMD_DEVICE_INVL);
+		qi_flush_pasid_cache(iommu, 0, QI_PC_GLOBAL, 0);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
+		devtlb_invalidation_with_pasid(iommu, dev, IOMMU_NO_PASID);
+
+		/*
+		 * At this point, the device is supposed to finish reset at
+		 * its driver probe stage, so no in-flight DMA will exist,
+		 * and we don't need to worry anymore hereafter.
+		 */
+		clear_context_copied(iommu, bus, devfn);
+	}
+
+	context_entry_set_pasid_table(context, dev);
+	spin_unlock(&iommu->lock);
+
+	/*
+	 * It's a non-present to present mapping. If hardware doesn't cache
+	 * non-present entry we don't need to flush the caches. If it does
+	 * cache non-present entries, then it does so in the special
+	 * domain #0, which we have to flush:
+	 */
+	if (cap_caching_mode(iommu->cap)) {
+		iommu->flush.flush_context(iommu, 0,
+					   PCI_DEVID(bus, devfn),
+					   DMA_CCMD_MASK_NOBIT,
+					   DMA_CCMD_DEVICE_INVL);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH);
+	}
+
+	return 0;
+}
+
+static int pci_pasid_table_setup(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct device *dev = data;
+
+	if (dev != &pdev->dev)
+		return 0;
+
+	return device_pasid_table_setup(dev, PCI_BUS_NUM(alias), alias & 0xff);
+}
+
+/*
+ * Set the device's PASID table to its context table entry.
+ *
+ * The PASID table is set to the context entries of both device itself
+ * and its alias requester ID for DMA.
+ */
+int intel_pasid_setup_sm_context(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+	if (!dev_is_pci(dev))
+		return device_pasid_table_setup(dev, info->bus, info->devfn);
+
+	return pci_for_each_dma_alias(to_pci_dev(dev), pci_pasid_table_setup, dev);
+}
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index 42fda97fd8..da9978fef7 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -318,5 +318,6 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 bool fault_ignore);
 void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 					  struct device *dev, u32 pasid);
+int intel_pasid_setup_sm_context(struct device *dev);
 void intel_pasid_teardown_sm_context(struct device *dev);
 #endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/perf.c b/drivers/iommu/intel/perf.c
index 94ee70ac38..adc4de6bbd 100644
--- a/drivers/iommu/intel/perf.c
+++ b/drivers/iommu/intel/perf.c
@@ -33,7 +33,7 @@ int dmar_latency_enable(struct intel_iommu *iommu, enum latency_type type)
 
 	spin_lock_irqsave(&latency_lock, flags);
 	if (!iommu->perf_statistic) {
-		iommu->perf_statistic = kzalloc(sizeof(*lstat) * DMAR_LATENCY_NUM,
+		iommu->perf_statistic = kcalloc(DMAR_LATENCY_NUM, sizeof(*lstat),
 						GFP_ATOMIC);
 		if (!iommu->perf_statistic) {
 			ret = -ENOMEM;
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 4d269df008..ee3b469e2d 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -22,7 +22,6 @@
 #include "iommu.h"
 #include "pasid.h"
 #include "perf.h"
-#include "../iommu-sva.h"
 #include "trace.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
@@ -315,10 +314,11 @@ out:
 	return 0;
 }
 
-static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
-			     struct iommu_domain *domain, ioasid_t pasid)
+static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
+				   struct device *dev, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
 	struct mm_struct *mm = domain->mm;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
@@ -360,7 +360,6 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 	sdev->iommu = iommu;
 	sdev->did = FLPT_DEFAULT_DID;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
-	init_rcu_head(&sdev->rcu);
 	if (info->ats_enabled) {
 		sdev->qdep = info->ats_qdep;
 		if (sdev->qdep >= QI_DEV_EIOTLB_MAX_INVS)
@@ -408,13 +407,6 @@ void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
 			if (svm->notifier.ops)
 				mmu_notifier_unregister(&svm->notifier, mm);
 			pasid_private_remove(svm->pasid);
-			/*
-			 * We mandate that no page faults may be outstanding
-			 * for the PASID when intel_svm_unbind_mm() is called.
-			 * If that is not obeyed, subtle errors will happen.
-			 * Let's make them less subtle...
-			 */
-			memset(svm, 0x6b, sizeof(*svm));
 			kfree(svm);
 		}
 	}
@@ -562,16 +554,12 @@ static int prq_to_iommu_prot(struct page_req_dsc *req)
 	return prot;
 }
 
-static int intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
-				struct page_req_dsc *desc)
+static void intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
+				 struct page_req_dsc *desc)
 {
-	struct iommu_fault_event event;
-
-	if (!dev || !dev_is_pci(dev))
-		return -ENODEV;
+	struct iopf_fault event = { };
 
 	/* Fill in event data for device specific processing */
-	memset(&event, 0, sizeof(struct iommu_fault_event));
 	event.fault.type = IOMMU_FAULT_PAGE_REQ;
 	event.fault.prm.addr = (u64)desc->addr << VTD_PAGE_SHIFT;
 	event.fault.prm.pasid = desc->pasid;
@@ -603,7 +591,7 @@ static int intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
 		event.fault.prm.private_data[0] = ktime_to_ns(ktime_get());
 	}
 
-	return iommu_report_device_fault(dev, &event);
+	iommu_report_device_fault(dev, &event);
 }
 
 static void handle_bad_prq_event(struct intel_iommu *iommu,
@@ -707,12 +695,10 @@ bad_req:
 			goto bad_req;
 		}
 
-		if (intel_svm_prq_report(iommu, dev, req))
-			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
-		else
-			trace_prq_report(iommu, dev, req->qw_0, req->qw_1,
-					 req->priv_data[0], req->priv_data[1],
-					 iommu->prq_seq_number++);
+		intel_svm_prq_report(iommu, dev, req);
+		trace_prq_report(iommu, dev, req->qw_0, req->qw_1,
+				 req->priv_data[0], req->priv_data[1],
+				 iommu->prq_seq_number++);
 		mutex_unlock(&iommu->iopf_lock);
 prq_advance:
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
@@ -743,9 +729,8 @@ prq_advance:
 	return IRQ_RETVAL(handled);
 }
 
-int intel_svm_page_response(struct device *dev,
-			    struct iommu_fault_event *evt,
-			    struct iommu_page_response *msg)
+void intel_svm_page_response(struct device *dev, struct iopf_fault *evt,
+			     struct iommu_page_response *msg)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
@@ -754,7 +739,6 @@ int intel_svm_page_response(struct device *dev,
 	bool private_present;
 	bool pasid_present;
 	bool last_page;
-	int ret = 0;
 	u16 sid;
 
 	prm = &evt->fault.prm;
@@ -763,16 +747,6 @@ int intel_svm_page_response(struct device *dev,
 	private_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
 	last_page = prm->flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
 
-	if (!pasid_present) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (prm->pasid == 0 || prm->pasid >= PASID_MAX) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	/*
 	 * Per VT-d spec. v3.0 ch7.7, system software must respond
 	 * with page group response if private data is present (PDP)
@@ -801,17 +775,6 @@ int intel_svm_page_response(struct device *dev,
 
 		qi_submit_sync(iommu, &desc, 1, 0);
 	}
-out:
-	return ret;
-}
-
-static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
-				   struct device *dev, ioasid_t pasid)
-{
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu = info->iommu;
-
-	return intel_svm_bind_mm(iommu, dev, domain, pasid);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)