1 files changed, 418 insertions, 137 deletions

diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index 11f0b856d74c..ac67a056b6c8 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -20,6 +20,7 @@
 
 #include "iommu.h"
 #include "pasid.h"
+#include "../iommu-pages.h"
 
 /*
  * Intel IOMMU system wide PASID name space:
@@ -38,7 +39,7 @@ int intel_pasid_alloc_table(struct device *dev)
 {
 	struct device_domain_info *info;
 	struct pasid_table *pasid_table;
-	struct page *pages;
+	struct pasid_dir_entry *dir;
 	u32 max_pasid = 0;
 	int order, size;
 
@@ -59,15 +60,14 @@ int intel_pasid_alloc_table(struct device *dev)
 
 	size = max_pasid >> (PASID_PDE_SHIFT - 3);
 	order = size ? get_order(size) : 0;
-	pages = alloc_pages_node(info->iommu->node,
-				 GFP_KERNEL | __GFP_ZERO, order);
-	if (!pages) {
+	dir = iommu_alloc_pages_node_sz(info->iommu->node, GFP_KERNEL,
+					1 << (order + PAGE_SHIFT));
+	if (!dir) {
 		kfree(pasid_table);
 		return -ENOMEM;
 	}
 
-	pasid_table->table = page_address(pages);
-	pasid_table->order = order;
+	pasid_table->table = dir;
 	pasid_table->max_pasid = 1 << (order + PAGE_SHIFT + 3);
 	info->pasid_table = pasid_table;
 
@@ -97,10 +97,10 @@ void intel_pasid_free_table(struct device *dev)
 	max_pde = pasid_table->max_pasid >> PASID_PDE_SHIFT;
 	for (i = 0; i < max_pde; i++) {
 		table = get_pasid_table_from_pde(&dir[i]);
-		free_pgtable_page(table);
+		iommu_free_pages(table);
 	}
 
-	free_pages((unsigned long)pasid_table->table, pasid_table->order);
+	iommu_free_pages(pasid_table->table);
 	kfree(pasid_table);
 }
 
@@ -146,7 +146,10 @@ static struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
 retry:
 	entries = get_pasid_table_from_pde(&dir[dir_index]);
 	if (!entries) {
-		entries = alloc_pgtable_page(info->iommu->node, GFP_ATOMIC);
+		u64 tmp;
+
+		entries = iommu_alloc_pages_node_sz(info->iommu->node,
+						    GFP_ATOMIC, SZ_4K);
 		if (!entries)
 			return NULL;
 
@@ -156,9 +159,10 @@ retry:
 		 * clear. However, this entry might be populated by others
 		 * while we are preparing it. Use theirs with a retry.
 		 */
-		if (cmpxchg64(&dir[dir_index].val, 0ULL,
-			      (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) {
-			free_pgtable_page(entries);
+		tmp = 0ULL;
+		if (!try_cmpxchg64(&dir[dir_index].val, &tmp,
+				   (u64)virt_to_phys(entries) | PASID_PTE_PRESENT)) {
+			iommu_free_pages(entries);
 			goto retry;
 		}
 		if (!ecap_coherent(info->iommu->ecap)) {
@@ -217,7 +221,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	if (pci_dev_is_disconnected(to_pci_dev(dev)))
 		return;
 
-	sid = info->bus << 8 | info->devfn;
+	sid = PCI_DEVID(info->bus, info->devfn);
 	qdep = info->ats_qdep;
 	pfsid = info->pfsid;
 
@@ -241,8 +245,28 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 
 	spin_lock(&iommu->lock);
 	pte = intel_pasid_get_entry(dev, pasid);
-	if (WARN_ON(!pte) || !pasid_pte_is_present(pte)) {
+	if (WARN_ON(!pte)) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		if (!pasid_pte_is_fault_disabled(pte)) {
+			WARN_ON(READ_ONCE(pte->val[0]) != 0);
+			spin_unlock(&iommu->lock);
+			return;
+		}
+
+		/*
+		 * When a PASID is used for SVA by a device, it's possible
+		 * that the pasid entry is non-present with the Fault
+		 * Processing Disabled bit set. Clear the pasid entry and
+		 * drain the PRQ for the PASID before return.
+		 */
+		pasid_clear_entry(pte);
 		spin_unlock(&iommu->lock);
+		intel_iommu_drain_pasid_prq(dev, pasid);
+
 		return;
 	}
 
@@ -261,9 +285,9 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
 	else
 		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
 
-	/* Device IOTLB doesn't need to be flushed in caching mode. */
-	if (!cap_caching_mode(iommu->cap))
-		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	if (!fault_ignore)
+		intel_iommu_drain_pasid_prq(dev, pasid);
 }
 
 /*
@@ -286,9 +310,68 @@ static void pasid_flush_caches(struct intel_iommu *iommu,
 }
 
 /*
+ * This function is supposed to be used after caller updates the fields
+ * except for the SSADE and P bit of a pasid table entry. It does the
+ * below:
+ * - Flush cacheline if needed
+ * - Flush the caches per Table 28 ”Guidance to Software for Invalidations“
+ *   of VT-d spec 5.0.
+ */
+static void intel_pasid_flush_present(struct intel_iommu *iommu,
+				      struct device *dev,
+				      u32 pasid, u16 did,
+				      struct pasid_entry *pte)
+{
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	/*
+	 * VT-d spec 5.0 table28 states guides for cache invalidation:
+	 *
+	 * - PASID-selective-within-Domain PASID-cache invalidation
+	 * - PASID-selective PASID-based IOTLB invalidation
+	 * - If (pasid is RID_PASID)
+	 *    - Global Device-TLB invalidation to affected functions
+	 *   Else
+	 *    - PASID-based Device-TLB invalidation (with S=1 and
+	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
+	 */
+	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+
+	devtlb_invalidation_with_pasid(iommu, dev, pasid);
+}
+
+/*
  * Set up the scalable mode pasid table entry for first only
  * translation type.
  */
+static void pasid_pte_config_first_level(struct intel_iommu *iommu,
+					 struct pasid_entry *pte,
+					 pgd_t *pgd, u16 did, int flags)
+{
+	lockdep_assert_held(&iommu->lock);
+
+	pasid_clear_entry(pte);
+
+	/* Setup the first level page table pointer: */
+	pasid_set_flptr(pte, (u64)__pa(pgd));
+
+	if (flags & PASID_FLAG_FL5LP)
+		pasid_set_flpm(pte, 1);
+
+	if (flags & PASID_FLAG_PAGE_SNOOP)
+		pasid_set_pgsnp(pte);
+
+	pasid_set_domain_id(pte, did);
+	pasid_set_address_width(pte, iommu->agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	/* Setup Present and PASID Granular Transfer Type: */
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
+	pasid_set_present(pte);
+}
+
 int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 				  struct device *dev, pgd_t *pgd,
 				  u32 pasid, u16 did, int flags)
@@ -319,54 +402,82 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 		return -EBUSY;
 	}
 
-	pasid_clear_entry(pte);
+	pasid_pte_config_first_level(iommu, pte, pgd, did, flags);
 
-	/* Setup the first level page table pointer: */
-	pasid_set_flptr(pte, (u64)__pa(pgd));
+	spin_unlock(&iommu->lock);
 
-	if (flags & PASID_FLAG_FL5LP)
-		pasid_set_flpm(pte, 1);
+	pasid_flush_caches(iommu, pte, pasid, did);
 
-	if (flags & PASID_FLAG_PAGE_SNOOP)
-		pasid_set_pgsnp(pte);
+	return 0;
+}
 
-	pasid_set_domain_id(pte, did);
-	pasid_set_address_width(pte, iommu->agaw);
-	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
-	pasid_set_nxe(pte);
+int intel_pasid_replace_first_level(struct intel_iommu *iommu,
+				    struct device *dev, pgd_t *pgd,
+				    u32 pasid, u16 did, u16 old_did,
+				    int flags)
+{
+	struct pasid_entry *pte, new_pte;
 
-	/* Setup Present and PASID Granular Transfer Type: */
-	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
-	pasid_set_present(pte);
+	if (!ecap_flts(iommu->ecap)) {
+		pr_err("No first level translation support on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	if ((flags & PASID_FLAG_FL5LP) && !cap_fl5lp_support(iommu->cap)) {
+		pr_err("No 5-level paging support for first-level on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	pasid_pte_config_first_level(iommu, &new_pte, pgd, did, flags);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
 	spin_unlock(&iommu->lock);
 
-	pasid_flush_caches(iommu, pte, pasid, did);
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
 
 	return 0;
 }
 
 /*
- * Skip top levels of page tables for iommu which has less agaw
- * than default. Unnecessary for PT mode.
+ * Set up the scalable mode pasid entry for second only translation type.
  */
-static int iommu_skip_agaw(struct dmar_domain *domain,
-			   struct intel_iommu *iommu,
-			   struct dma_pte **pgd)
+static void pasid_pte_config_second_level(struct intel_iommu *iommu,
+					  struct pasid_entry *pte,
+					  u64 pgd_val, int agaw, u16 did,
+					  bool dirty_tracking)
 {
-	int agaw;
+	lockdep_assert_held(&iommu->lock);
 
-	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-		*pgd = phys_to_virt(dma_pte_addr(*pgd));
-		if (!dma_pte_present(*pgd))
-			return -EINVAL;
-	}
+	pasid_clear_entry(pte);
+	pasid_set_domain_id(pte, did);
+	pasid_set_slptr(pte, pgd_val);
+	pasid_set_address_width(pte, agaw);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
+	pasid_set_fault_enable(pte);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	if (dirty_tracking)
+		pasid_set_ssade(pte);
 
-	return agaw;
+	pasid_set_present(pte);
 }
 
-/*
- * Set up the scalable mode pasid entry for second only translation type.
- */
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid)
@@ -374,7 +485,6 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	struct pasid_entry *pte;
 	struct dma_pte *pgd;
 	u64 pgd_val;
-	int agaw;
 	u16 did;
 
 	/*
@@ -388,15 +498,58 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	}
 
 	pgd = domain->pgd;
-	agaw = iommu_skip_agaw(domain, iommu, &pgd);
-	if (agaw < 0) {
-		dev_err(dev, "Invalid domain page table\n");
+	pgd_val = virt_to_phys(pgd);
+	did = domain_id_iommu(domain, iommu);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EBUSY;
+	}
+
+	pasid_pte_config_second_level(iommu, pte, pgd_val, domain->agaw,
+				      did, domain->dirty_tracking);
+	spin_unlock(&iommu->lock);
+
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return 0;
+}
+
+int intel_pasid_replace_second_level(struct intel_iommu *iommu,
+				     struct dmar_domain *domain,
+				     struct device *dev, u16 old_did,
+				     u32 pasid)
+{
+	struct pasid_entry *pte, new_pte;
+	struct dma_pte *pgd;
+	u64 pgd_val;
+	u16 did;
+
+	/*
+	 * If hardware advertises no support for second level
+	 * translation, return directly.
+	 */
+	if (!ecap_slts(iommu->ecap)) {
+		pr_err("No second level translation support on %s\n",
+		       iommu->name);
 		return -EINVAL;
 	}
 
+	pgd = domain->pgd;
 	pgd_val = virt_to_phys(pgd);
 	did = domain_id_iommu(domain, iommu);
 
+	pasid_pte_config_second_level(iommu, &new_pte, pgd_val,
+				      domain->agaw, did,
+				      domain->dirty_tracking);
+
 	spin_lock(&iommu->lock);
 	pte = intel_pasid_get_entry(dev, pasid);
 	if (!pte) {
@@ -404,25 +557,18 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 		return -ENODEV;
 	}
 
-	if (pasid_pte_is_present(pte)) {
+	if (!pasid_pte_is_present(pte)) {
 		spin_unlock(&iommu->lock);
-		return -EBUSY;
+		return -EINVAL;
 	}
 
-	pasid_clear_entry(pte);
-	pasid_set_domain_id(pte, did);
-	pasid_set_slptr(pte, pgd_val);
-	pasid_set_address_width(pte, agaw);
-	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
-	pasid_set_fault_enable(pte);
-	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
-	if (domain->dirty_tracking)
-		pasid_set_ssade(pte);
+	WARN_ON(old_did != pasid_get_domain_id(pte));
 
-	pasid_set_present(pte);
+	*pte = new_pte;
 	spin_unlock(&iommu->lock);
 
-	pasid_flush_caches(iommu, pte, pasid, did);
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
 
 	return 0;
 }
@@ -491,9 +637,7 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 
 	iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
 
-	/* Device IOTLB doesn't need to be flushed in caching mode. */
-	if (!cap_caching_mode(iommu->cap))
-		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	devtlb_invalidation_with_pasid(iommu, dev, pasid);
 
 	return 0;
 }
@@ -501,6 +645,20 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 /*
  * Set up the scalable mode pasid entry for passthrough translation type.
  */
+static void pasid_pte_config_pass_through(struct intel_iommu *iommu,
+					  struct pasid_entry *pte, u16 did)
+{
+	lockdep_assert_held(&iommu->lock);
+
+	pasid_clear_entry(pte);
+	pasid_set_domain_id(pte, did);
+	pasid_set_address_width(pte, iommu->agaw);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT);
+	pasid_set_fault_enable(pte);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	pasid_set_present(pte);
+}
+
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct device *dev, u32 pasid)
 {
@@ -519,13 +677,7 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 		return -EBUSY;
 	}
 
-	pasid_clear_entry(pte);
-	pasid_set_domain_id(pte, did);
-	pasid_set_address_width(pte, iommu->agaw);
-	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT);
-	pasid_set_fault_enable(pte);
-	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
-	pasid_set_present(pte);
+	pasid_pte_config_pass_through(iommu, pte, did);
 	spin_unlock(&iommu->lock);
 
 	pasid_flush_caches(iommu, pte, pasid, did);
@@ -533,6 +685,38 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 	return 0;
 }
 
+int intel_pasid_replace_pass_through(struct intel_iommu *iommu,
+				     struct device *dev, u16 old_did,
+				     u32 pasid)
+{
+	struct pasid_entry *pte, new_pte;
+	u16 did = FLPT_DEFAULT_DID;
+
+	pasid_pte_config_pass_through(iommu, &new_pte, did);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
+	spin_unlock(&iommu->lock);
+
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
+
+	return 0;
+}
+
 /*
  * Set the page snoop control for a pasid entry which has been set up.
  */
@@ -553,26 +737,47 @@ void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 	did = pasid_get_domain_id(pte);
 	spin_unlock(&iommu->lock);
 
-	if (!ecap_coherent(iommu->ecap))
-		clflush_cache_range(pte, sizeof(*pte));
+	intel_pasid_flush_present(iommu, dev, pasid, did, pte);
+}
 
-	/*
-	 * VT-d spec 3.4 table23 states guides for cache invalidation:
-	 *
-	 * - PASID-selective-within-Domain PASID-cache invalidation
-	 * - PASID-selective PASID-based IOTLB invalidation
-	 * - If (pasid is RID_PASID)
-	 *    - Global Device-TLB invalidation to affected functions
-	 *   Else
-	 *    - PASID-based Device-TLB invalidation (with S=1 and
-	 *      Addr[63:12]=0x7FFFFFFF_FFFFF) to affected functions
-	 */
-	pasid_cache_invalidation_with_pasid(iommu, did, pasid);
-	qi_flush_piotlb(iommu, did, pasid, 0, -1, 0);
+static void pasid_pte_config_nestd(struct intel_iommu *iommu,
+				   struct pasid_entry *pte,
+				   struct iommu_hwpt_vtd_s1 *s1_cfg,
+				   struct dmar_domain *s2_domain,
+				   u16 did)
+{
+	struct dma_pte *pgd = s2_domain->pgd;
+
+	lockdep_assert_held(&iommu->lock);
 
-	/* Device IOTLB doesn't need to be flushed in caching mode. */
-	if (!cap_caching_mode(iommu->cap))
-		devtlb_invalidation_with_pasid(iommu, dev, pasid);
+	pasid_clear_entry(pte);
+
+	if (s1_cfg->addr_width == ADDR_WIDTH_5LEVEL)
+		pasid_set_flpm(pte, 1);
+
+	pasid_set_flptr(pte, s1_cfg->pgtbl_addr);
+
+	if (s1_cfg->flags & IOMMU_VTD_S1_SRE) {
+		pasid_set_sre(pte);
+		if (s1_cfg->flags & IOMMU_VTD_S1_WPE)
+			pasid_set_wpe(pte);
+	}
+
+	if (s1_cfg->flags & IOMMU_VTD_S1_EAFE)
+		pasid_set_eafe(pte);
+
+	if (s2_domain->force_snooping)
+		pasid_set_pgsnp(pte);
+
+	pasid_set_slptr(pte, virt_to_phys(pgd));
+	pasid_set_fault_enable(pte);
+	pasid_set_domain_id(pte, did);
+	pasid_set_address_width(pte, s2_domain->agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+	if (s2_domain->dirty_tracking)
+		pasid_set_ssade(pte);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
+	pasid_set_present(pte);
 }
 
 /**
@@ -590,10 +795,8 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain)
 {
 	struct iommu_hwpt_vtd_s1 *s1_cfg = &domain->s1_cfg;
-	pgd_t *s1_gpgd = (pgd_t *)(uintptr_t)domain->s1_pgtbl;
 	struct dmar_domain *s2_domain = domain->s2_domain;
 	u16 did = domain_id_iommu(domain, iommu);
-	struct dma_pte *pgd = s2_domain->pgd;
 	struct pasid_entry *pte;
 
 	/* Address width should match the address width supported by hardware */
@@ -636,37 +839,73 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 		return -EBUSY;
 	}
 
-	pasid_clear_entry(pte);
+	pasid_pte_config_nestd(iommu, pte, s1_cfg, s2_domain, did);
+	spin_unlock(&iommu->lock);
 
-	if (s1_cfg->addr_width == ADDR_WIDTH_5LEVEL)
-		pasid_set_flpm(pte, 1);
+	pasid_flush_caches(iommu, pte, pasid, did);
 
-	pasid_set_flptr(pte, (uintptr_t)s1_gpgd);
+	return 0;
+}
 
-	if (s1_cfg->flags & IOMMU_VTD_S1_SRE) {
-		pasid_set_sre(pte);
-		if (s1_cfg->flags & IOMMU_VTD_S1_WPE)
-			pasid_set_wpe(pte);
+int intel_pasid_replace_nested(struct intel_iommu *iommu,
+			       struct device *dev, u32 pasid,
+			       u16 old_did, struct dmar_domain *domain)
+{
+	struct iommu_hwpt_vtd_s1 *s1_cfg = &domain->s1_cfg;
+	struct dmar_domain *s2_domain = domain->s2_domain;
+	u16 did = domain_id_iommu(domain, iommu);
+	struct pasid_entry *pte, new_pte;
+
+	/* Address width should match the address width supported by hardware */
+	switch (s1_cfg->addr_width) {
+	case ADDR_WIDTH_4LEVEL:
+		break;
+	case ADDR_WIDTH_5LEVEL:
+		if (!cap_fl5lp_support(iommu->cap)) {
+			dev_err_ratelimited(dev,
+					    "5-level paging not supported\n");
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err_ratelimited(dev, "Invalid stage-1 address width %d\n",
+				    s1_cfg->addr_width);
+		return -EINVAL;
 	}
 
-	if (s1_cfg->flags & IOMMU_VTD_S1_EAFE)
-		pasid_set_eafe(pte);
+	if ((s1_cfg->flags & IOMMU_VTD_S1_SRE) && !ecap_srs(iommu->ecap)) {
+		pr_err_ratelimited("No supervisor request support on %s\n",
+				   iommu->name);
+		return -EINVAL;
+	}
 
-	if (s2_domain->force_snooping)
-		pasid_set_pgsnp(pte);
+	if ((s1_cfg->flags & IOMMU_VTD_S1_EAFE) && !ecap_eafs(iommu->ecap)) {
+		pr_err_ratelimited("No extended access flag support on %s\n",
+				   iommu->name);
+		return -EINVAL;
+	}
 
-	pasid_set_slptr(pte, virt_to_phys(pgd));
-	pasid_set_fault_enable(pte);
-	pasid_set_domain_id(pte, did);
-	pasid_set_address_width(pte, s2_domain->agaw);
-	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
-	if (s2_domain->dirty_tracking)
-		pasid_set_ssade(pte);
-	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
-	pasid_set_present(pte);
+	pasid_pte_config_nestd(iommu, &new_pte, s1_cfg, s2_domain, did);
+
+	spin_lock(&iommu->lock);
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (!pte) {
+		spin_unlock(&iommu->lock);
+		return -ENODEV;
+	}
+
+	if (!pasid_pte_is_present(pte)) {
+		spin_unlock(&iommu->lock);
+		return -EINVAL;
+	}
+
+	WARN_ON(old_did != pasid_get_domain_id(pte));
+
+	*pte = new_pte;
 	spin_unlock(&iommu->lock);
 
-	pasid_flush_caches(iommu, pte, pasid, did);
+	intel_pasid_flush_present(iommu, dev, pasid, old_did, pte);
+	intel_iommu_drain_pasid_prq(dev, pasid);
 
 	return 0;
 }
@@ -681,6 +920,7 @@ static void device_pasid_table_teardown(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;
+	u16 did;
 
 	spin_lock(&iommu->lock);
 	context = iommu_context_addr(iommu, bus, devfn, false);
@@ -689,28 +929,11 @@ static void device_pasid_table_teardown(struct device *dev, u8 bus, u8 devfn)
 		return;
 	}
 
+	did = context_domain_id(context);
 	context_clear_entry(context);
 	__iommu_flush_cache(iommu, context, sizeof(*context));
 	spin_unlock(&iommu->lock);
-
-	/*
-	 * Cache invalidation for changes to a scalable-mode context table
-	 * entry.
-	 *
-	 * Section 6.5.3.3 of the VT-d spec:
-	 * - Device-selective context-cache invalidation;
-	 * - Domain-selective PASID-cache invalidation to affected domains
-	 *   (can be skipped if all PASID entries were not-present);
-	 * - Domain-selective IOTLB invalidation to affected domains;
-	 * - Global Device-TLB invalidation to affected functions.
-	 *
-	 * The iommu has been parked in the blocking state. All domains have
-	 * been detached from the device or PASID. The PASID and IOTLB caches
-	 * have been invalidated during the domain detach path.
-	 */
-	iommu->flush.flush_context(iommu, 0, PCI_DEVID(bus, devfn),
-				   DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL);
-	devtlb_invalidation_with_pasid(iommu, dev, IOMMU_NO_PASID);
+	intel_context_flush_no_pasid(info, context, did);
 }
 
 static int pci_pasid_table_teardown(struct pci_dev *pdev, u16 alias, void *data)
@@ -768,10 +991,10 @@ static int context_entry_set_pasid_table(struct context_entry *context,
 
 	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);
+	if (info->pri_supported)
+		context_set_sm_pre(context);
 
 	context_set_fault_enable(context);
 	context_set_present(context);
@@ -872,3 +1095,61 @@ int intel_pasid_setup_sm_context(struct device *dev)
 
 	return pci_for_each_dma_alias(to_pci_dev(dev), pci_pasid_table_setup, dev);
 }
+
+/*
+ * Global Device-TLB invalidation following changes in a context entry which
+ * was present.
+ */
+static void __context_flush_dev_iotlb(struct device_domain_info *info)
+{
+	if (!info->ats_enabled)
+		return;
+
+	qi_flush_dev_iotlb(info->iommu, PCI_DEVID(info->bus, info->devfn),
+			   info->pfsid, info->ats_qdep, 0, MAX_AGAW_PFN_WIDTH);
+
+	/*
+	 * There is no guarantee that the device DMA is stopped when it reaches
+	 * here. Therefore, always attempt the extra device TLB invalidation
+	 * quirk. The impact on performance is acceptable since this is not a
+	 * performance-critical path.
+	 */
+	quirk_extra_dev_tlb_flush(info, 0, MAX_AGAW_PFN_WIDTH, IOMMU_NO_PASID,
+				  info->ats_qdep);
+}
+
+/*
+ * Cache invalidations after change in a context table entry that was present
+ * according to the Spec 6.5.3.3 (Guidance to Software for Invalidations).
+ * This helper can only be used when IOMMU is working in the legacy mode or
+ * IOMMU is in scalable mode but all PASID table entries of the device are
+ * non-present.
+ */
+void intel_context_flush_no_pasid(struct device_domain_info *info,
+				  struct context_entry *context, u16 did)
+{
+	struct intel_iommu *iommu = info->iommu;
+
+	/*
+	 * Device-selective context-cache invalidation. The Domain-ID field
+	 * of the Context-cache Invalidate Descriptor is ignored by hardware
+	 * when operating in scalable mode. Therefore the @did value doesn't
+	 * matter in scalable mode.
+	 */
+	iommu->flush.flush_context(iommu, did, PCI_DEVID(info->bus, info->devfn),
+				   DMA_CCMD_MASK_NOBIT, DMA_CCMD_DEVICE_INVL);
+
+	/*
+	 * For legacy mode:
+	 * - Domain-selective IOTLB invalidation
+	 * - Global Device-TLB invalidation to all affected functions
+	 */
+	if (!sm_supported(iommu)) {
+		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
+		__context_flush_dev_iotlb(info);
+
+		return;
+	}
+
+	__context_flush_dev_iotlb(info);
+}