Merging upstream version 6.8.9.

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

41 files changed, 1691 insertions, 1059 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index a66f7df7a2..9dbb55e745 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -160,6 +160,7 @@ config IOMMU_DMA
 
 # Shared Virtual Addressing
 config IOMMU_SVA
+	select IOMMU_MM_DATA
 	bool
 
 config FSL_PAMU
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 86be1edd50..8b3601f285 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -53,10 +53,16 @@ int amd_iommu_pdev_enable_cap_pri(struct pci_dev *pdev);
 void amd_iommu_pdev_disable_cap_pri(struct pci_dev *pdev);
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid, u64 address);
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu);
 void amd_iommu_update_and_flush_device_table(struct protection_domain *domain);
 void amd_iommu_domain_update(struct protection_domain *domain);
 void amd_iommu_domain_flush_complete(struct protection_domain *domain);
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain);
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size);
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
 int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 90b7d7950a..809d74faa1 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -902,12 +902,6 @@ extern int amd_iommu_max_glx_val;
 extern u64 amd_iommu_efr;
 extern u64 amd_iommu_efr2;
 
-/*
- * This function flushes all internal caches of
- * the IOMMU used by this driver.
- */
-void iommu_flush_all_caches(struct amd_iommu *iommu);
-
 static inline int get_ioapic_devid(int id)
 {
 	struct devid_map *entry;
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 7f65f3ecb2..40979b0f52 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -2226,7 +2226,7 @@ static int __init amd_iommu_init_pci(void)
 		init_device_table_dma(pci_seg);
 
 	for_each_iommu(iommu)
-		iommu_flush_all_caches(iommu);
+		amd_iommu_flush_all_caches(iommu);
 
 	print_iommu_info();
 
@@ -2776,7 +2776,7 @@ static void early_enable_iommu(struct amd_iommu *iommu)
 	iommu_enable_xt(iommu);
 	iommu_enable_irtcachedis(iommu);
 	iommu_enable(iommu);
-	iommu_flush_all_caches(iommu);
+	amd_iommu_flush_all_caches(iommu);
 }
 
 /*
@@ -2832,7 +2832,7 @@ static void early_enable_iommus(void)
 			iommu_enable_xt(iommu);
 			iommu_enable_irtcachedis(iommu);
 			iommu_set_device_table(iommu);
-			iommu_flush_all_caches(iommu);
+			amd_iommu_flush_all_caches(iommu);
 		}
 	}
 }
@@ -3296,7 +3296,7 @@ static int __init state_next(void)
 				uninit_device_table_dma(pci_seg);
 
 			for_each_iommu(iommu)
-				iommu_flush_all_caches(iommu);
+				amd_iommu_flush_all_caches(iommu);
 		}
 	}
 	return ret;
diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
index 6c0621f6f5..2a0d1e97e5 100644
--- a/drivers/iommu/amd/io_pgtable.c
+++ b/drivers/iommu/amd/io_pgtable.c
@@ -369,6 +369,8 @@ static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	bool updated = false;
 	u64 __pte, *pte;
 	int ret, i, count;
+	size_t size = pgcount << __ffs(pgsize);
+	unsigned long o_iova = iova;
 
 	BUG_ON(!IS_ALIGNED(iova, pgsize));
 	BUG_ON(!IS_ALIGNED(paddr, pgsize));
@@ -424,8 +426,7 @@ out:
 		 * Updates and flushing already happened in
 		 * increase_address_space().
 		 */
-		amd_iommu_domain_flush_tlb_pde(dom);
-		amd_iommu_domain_flush_complete(dom);
+		amd_iommu_domain_flush_pages(dom, o_iova, size);
 		spin_unlock_irqrestore(&dom->lock, flags);
 	}
 
diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
index f818a7e254..6d69ba6074 100644
--- a/drivers/iommu/amd/io_pgtable_v2.c
+++ b/drivers/iommu/amd/io_pgtable_v2.c
@@ -244,7 +244,6 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 	unsigned long mapped_size = 0;
 	unsigned long o_iova = iova;
 	size_t size = pgcount << __ffs(pgsize);
-	int count = 0;
 	int ret = 0;
 	bool updated = false;
 
@@ -265,19 +264,14 @@ static int iommu_v2_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
 
 		*pte = set_pte_attr(paddr, map_size, prot);
 
-		count++;
 		iova += map_size;
 		paddr += map_size;
 		mapped_size += map_size;
 	}
 
 out:
-	if (updated) {
-		if (count > 1)
-			amd_iommu_flush_tlb(&pdom->domain, 0);
-		else
-			amd_iommu_flush_page(&pdom->domain, 0, o_iova);
-	}
+	if (updated)
+		amd_iommu_domain_flush_pages(pdom, o_iova, size);
 
 	if (mapped)
 		*mapped += mapped_size;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index fcc987f5d4..4283dd8191 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -64,7 +64,7 @@ LIST_HEAD(hpet_map);
 LIST_HEAD(acpihid_map);
 
 const struct iommu_ops amd_iommu_ops;
-const struct iommu_dirty_ops amd_dirty_ops;
+static const struct iommu_dirty_ops amd_dirty_ops;
 
 int amd_iommu_max_glx_val = -1;
 
@@ -85,6 +85,11 @@ static void detach_device(struct device *dev);
  *
  ****************************************************************************/
 
+static inline bool pdom_is_v2_pgtbl_mode(struct protection_domain *pdom)
+{
+	return (pdom && (pdom->flags & PD_IOMMUV2_MASK));
+}
+
 static inline int get_acpihid_device_id(struct device *dev,
 					struct acpihid_map_entry **entry)
 {
@@ -551,8 +556,6 @@ static void amd_iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	dev_iommu_priv_set(dev, NULL);
-
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
 	 * device is re-plugged - not doing so would introduce a ton of races.
@@ -1124,68 +1127,44 @@ static inline u64 build_inv_address(u64 address, size_t size)
 }
 
 static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
-				  size_t size, u16 domid, int pde)
+				  size_t size, u16 domid,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[1] |= domid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
+	/* PDE bit - we want to flush everything, not only the PTEs */
+	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
+	if (gn) {
+		cmd->data[0] |= pasid;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-	if (pde) /* PDE bit - we want to flush everything, not only the PTEs */
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
 }
 
 static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
-				  u64 address, size_t size)
+				  u64 address, size_t size,
+				  ioasid_t pasid, bool gn)
 {
 	u64 inv_address = build_inv_address(address, size);
 
 	memset(cmd, 0, sizeof(*cmd));
+
 	cmd->data[0]  = devid;
 	cmd->data[0] |= (qdep & 0xff) << 24;
 	cmd->data[1]  = devid;
 	cmd->data[2]  = lower_32_bits(inv_address);
 	cmd->data[3]  = upper_32_bits(inv_address);
-	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
-}
-
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
-				  u64 address, bool size)
-{
-	memset(cmd, 0, sizeof(*cmd));
-
-	address &= ~(0xfffULL);
-
-	cmd->data[0]  = pasid;
-	cmd->data[1]  = domid;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[3]  = upper_32_bits(address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
-	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
-}
-
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
-				  int qdep, u64 address, bool size)
-{
-	memset(cmd, 0, sizeof(*cmd));
-
-	address &= ~(0xfffULL);
+	if (gn) {
+		cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
+		cmd->data[1] |= (pasid & 0xff) << 16;
+		cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
+	}
 
-	cmd->data[0]  = devid;
-	cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
-	cmd->data[0] |= (qdep  & 0xff) << 24;
-	cmd->data[1]  = devid;
-	cmd->data[1] |= (pasid & 0xff) << 16;
-	cmd->data[2]  = lower_32_bits(address);
-	cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
-	cmd->data[3]  = upper_32_bits(address);
-	if (size)
-		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
@@ -1341,7 +1320,7 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	for (dom_id = 0; dom_id <= last_bdf; ++dom_id) {
 		struct iommu_cmd cmd;
 		build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-				      dom_id, 1);
+				      dom_id, IOMMU_NO_PASID, false);
 		iommu_queue_command(iommu, &cmd);
 	}
 
@@ -1353,7 +1332,7 @@ static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
 	struct iommu_cmd cmd;
 
 	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			      dom_id, 1);
+			      dom_id, IOMMU_NO_PASID, false);
 	iommu_queue_command(iommu, &cmd);
 
 	iommu_completion_wait(iommu);
@@ -1392,7 +1371,7 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 	iommu_completion_wait(iommu);
 }
 
-void iommu_flush_all_caches(struct amd_iommu *iommu)
+void amd_iommu_flush_all_caches(struct amd_iommu *iommu)
 {
 	if (check_feature(FEATURE_IA)) {
 		amd_iommu_flush_all(iommu);
@@ -1406,8 +1385,8 @@ void iommu_flush_all_caches(struct amd_iommu *iommu)
 /*
  * Command send function for flushing on-device TLB
  */
-static int device_flush_iotlb(struct iommu_dev_data *dev_data,
-			      u64 address, size_t size)
+static int device_flush_iotlb(struct iommu_dev_data *dev_data, u64 address,
+			      size_t size, ioasid_t pasid, bool gn)
 {
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
@@ -1418,7 +1397,8 @@ static int device_flush_iotlb(struct iommu_dev_data *dev_data,
 	if (!iommu)
 		return -EINVAL;
 
-	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address, size);
+	build_inv_iotlb_pages(&cmd, dev_data->devid, qdep, address,
+			      size, pasid, gn);
 
 	return iommu_queue_command(iommu, &cmd);
 }
@@ -1464,8 +1444,11 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
 			return ret;
 	}
 
-	if (dev_data->ats_enabled)
-		ret = device_flush_iotlb(dev_data, 0, ~0UL);
+	if (dev_data->ats_enabled) {
+		/* Invalidate the entire contents of an IOTLB */
+		ret = device_flush_iotlb(dev_data, 0, ~0UL,
+					 IOMMU_NO_PASID, false);
+	}
 
 	return ret;
 }
@@ -1476,13 +1459,18 @@ static int device_flush_dte(struct iommu_dev_data *dev_data)
  * page. Otherwise it flushes the whole TLB of the IOMMU.
  */
 static void __domain_flush_pages(struct protection_domain *domain,
-				 u64 address, size_t size, int pde)
+				 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
 	int ret = 0, i;
+	ioasid_t pasid = IOMMU_NO_PASID;
+	bool gn = false;
+
+	if (pdom_is_v2_pgtbl_mode(domain))
+		gn = true;
 
-	build_inv_iommu_pages(&cmd, address, size, domain->id, pde);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, gn);
 
 	for (i = 0; i < amd_iommu_get_num_iommus(); ++i) {
 		if (!domain->dev_iommu[i])
@@ -1500,17 +1488,21 @@ static void __domain_flush_pages(struct protection_domain *domain,
 		if (!dev_data->ats_enabled)
 			continue;
 
-		ret |= device_flush_iotlb(dev_data, address, size);
+		ret |= device_flush_iotlb(dev_data, address, size, pasid, gn);
 	}
 
 	WARN_ON(ret);
 }
 
-static void domain_flush_pages(struct protection_domain *domain,
-			       u64 address, size_t size, int pde)
+void amd_iommu_domain_flush_pages(struct protection_domain *domain,
+				  u64 address, size_t size)
 {
 	if (likely(!amd_iommu_np_cache)) {
-		__domain_flush_pages(domain, address, size, pde);
+		__domain_flush_pages(domain, address, size);
+
+		/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+		amd_iommu_domain_flush_complete(domain);
+
 		return;
 	}
 
@@ -1543,16 +1535,20 @@ static void domain_flush_pages(struct protection_domain *domain,
 
 		flush_size = 1ul << min_alignment;
 
-		__domain_flush_pages(domain, address, flush_size, pde);
+		__domain_flush_pages(domain, address, flush_size);
 		address += flush_size;
 		size -= flush_size;
 	}
+
+	/* Wait until IOMMU TLB and all device IOTLB flushes are complete */
+	amd_iommu_domain_flush_complete(domain);
 }
 
 /* Flush the whole IO/TLB for a given protection domain - including PDE */
-void amd_iommu_domain_flush_tlb_pde(struct protection_domain *domain)
+static void amd_iommu_domain_flush_all(struct protection_domain *domain)
 {
-	domain_flush_pages(domain, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS, 1);
+	amd_iommu_domain_flush_pages(domain, 0,
+				     CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 void amd_iommu_domain_flush_complete(struct protection_domain *domain)
@@ -1579,8 +1575,7 @@ static void domain_flush_np_cache(struct protection_domain *domain,
 		unsigned long flags;
 
 		spin_lock_irqsave(&domain->lock, flags);
-		domain_flush_pages(domain, iova, size, 1);
-		amd_iommu_domain_flush_complete(domain);
+		amd_iommu_domain_flush_pages(domain, iova, size);
 		spin_unlock_irqrestore(&domain->lock, flags);
 	}
 }
@@ -1858,11 +1853,8 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
 
-	/* Flush IOTLB */
-	amd_iommu_domain_flush_tlb_pde(domain);
-
-	/* Wait for the flushes to finish */
-	amd_iommu_domain_flush_complete(domain);
+	/* Flush IOTLB and wait for the flushes to finish */
+	amd_iommu_domain_flush_all(domain);
 
 	/* decrease reference counters - needs to happen after the flushes */
 	domain->dev_iommu[iommu->index] -= 1;
@@ -1896,15 +1888,6 @@ static int attach_device(struct device *dev,
 
 	do_attach(dev_data, domain);
 
-	/*
-	 * We might boot into a crash-kernel here. The crashed kernel
-	 * left the caches in the IOMMU dirty. So we have to flush
-	 * here to evict all dirty stuff.
-	 */
-	amd_iommu_domain_flush_tlb_pde(domain);
-
-	amd_iommu_domain_flush_complete(domain);
-
 out:
 	spin_unlock(&dev_data->lock);
 
@@ -2048,8 +2031,7 @@ void amd_iommu_domain_update(struct protection_domain *domain)
 	amd_iommu_update_and_flush_device_table(domain);
 
 	/* Flush domain TLB(s) and wait for completion */
-	amd_iommu_domain_flush_tlb_pde(domain);
-	amd_iommu_domain_flush_complete(domain);
+	amd_iommu_domain_flush_all(domain);
 }
 
 /*****************************************************************************
@@ -2482,10 +2464,9 @@ static int amd_iommu_set_dirty_tracking(struct iommu_domain *domain,
 	}
 
 	/* Flush IOTLB to mark IOPTE dirty on the next translation(s) */
-	if (domain_flush) {
-		amd_iommu_domain_flush_tlb_pde(pdomain);
-		amd_iommu_domain_flush_complete(pdomain);
-	}
+	if (domain_flush)
+		amd_iommu_domain_flush_all(pdomain);
+
 	pdomain->dirty_tracking = enable;
 	spin_unlock_irqrestore(&pdomain->lock, flags);
 
@@ -2588,8 +2569,7 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	amd_iommu_domain_flush_tlb_pde(dom);
-	amd_iommu_domain_flush_complete(dom);
+	amd_iommu_domain_flush_all(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2600,8 +2580,8 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
-	amd_iommu_domain_flush_complete(dom);
+	amd_iommu_domain_flush_pages(dom, gather->start,
+				     gather->end - gather->start + 1);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
@@ -2635,7 +2615,7 @@ static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
 	return true;
 }
 
-const struct iommu_dirty_ops amd_dirty_ops = {
+static const struct iommu_dirty_ops amd_dirty_ops = {
 	.set_dirty_tracking = amd_iommu_set_dirty_tracking,
 	.read_and_clear_dirty = amd_iommu_read_and_clear_dirty,
 };
@@ -2666,7 +2646,7 @@ const struct iommu_ops amd_iommu_ops = {
 };
 
 static int __flush_pasid(struct protection_domain *domain, u32 pasid,
-			 u64 address, bool size)
+			 u64 address, size_t size)
 {
 	struct iommu_dev_data *dev_data;
 	struct iommu_cmd cmd;
@@ -2675,7 +2655,7 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 	if (!(domain->flags & PD_IOMMUV2_MASK))
 		return -EINVAL;
 
-	build_inv_iommu_pasid(&cmd, domain->id, pasid, address, size);
+	build_inv_iommu_pages(&cmd, address, size, domain->id, pasid, true);
 
 	/*
 	 * IOMMU TLB needs to be flushed before Device TLB to
@@ -2709,8 +2689,8 @@ static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 		iommu = rlookup_amd_iommu(dev_data->dev);
 		if (!iommu)
 			continue;
-		build_inv_iotlb_pasid(&cmd, dev_data->devid, pasid,
-				      qdep, address, size);
+		build_inv_iotlb_pages(&cmd, dev_data->devid, qdep,
+				      address, size, pasid, true);
 
 		ret = iommu_queue_command(iommu, &cmd);
 		if (ret != 0)
@@ -2730,7 +2710,7 @@ out:
 static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
-	return __flush_pasid(domain, pasid, address, false);
+	return __flush_pasid(domain, pasid, address, PAGE_SIZE);
 }
 
 int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
@@ -2749,8 +2729,7 @@ int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 
 static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
-	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
-			     true);
+	return __flush_pasid(domain, pasid, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
 }
 
 int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
@@ -3111,8 +3090,8 @@ out:
 	return index;
 }
 
-static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
-			  struct irte_ga *irte)
+static int __modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			    struct irte_ga *irte)
 {
 	struct irq_remap_table *table;
 	struct irte_ga *entry;
@@ -3139,6 +3118,18 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
+	return 0;
+}
+
+static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
+			  struct irte_ga *irte)
+{
+	bool ret;
+
+	ret = __modify_irte_ga(iommu, devid, index, irte);
+	if (ret)
+		return ret;
+
 	iommu_flush_irt_and_complete(iommu, devid);
 
 	return 0;
@@ -3357,7 +3348,7 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data,
 
 	data->irq_2_irte.devid = devid;
 	data->irq_2_irte.index = index + sub_handle;
-	iommu->irte_ops->prepare(data->entry, apic->delivery_mode,
+	iommu->irte_ops->prepare(data->entry, APIC_DELIVERY_MODE_FIXED,
 				 apic->dest_mode_logical, irq_cfg->vector,
 				 irq_cfg->dest_apicid, devid);
 
@@ -3634,7 +3625,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 
 	entry->lo.fields_remap.valid       = valid;
 	entry->lo.fields_remap.dm          = apic->dest_mode_logical;
-	entry->lo.fields_remap.int_type    = apic->delivery_mode;
+	entry->lo.fields_remap.int_type    = APIC_DELIVERY_MODE_FIXED;
 	entry->hi.fields.vector            = cfg->vector;
 	entry->lo.fields_remap.destination =
 				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
@@ -3822,8 +3813,8 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 	}
 	entry->lo.fields_vapic.is_run = is_run;
 
-	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry);
+	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+				ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif
diff --git a/drivers/iommu/apple-dart.c b/drivers/iommu/apple-dart.c
index ee05f4824b..ef3ee95706 100644
--- a/drivers/iommu/apple-dart.c
+++ b/drivers/iommu/apple-dart.c
@@ -81,6 +81,7 @@
 #define DART_T8020_TCR_BYPASS_DAPF      BIT(12)
 
 #define DART_T8020_TTBR       0x200
+#define DART_T8020_USB4_TTBR  0x400
 #define DART_T8020_TTBR_VALID BIT(31)
 #define DART_T8020_TTBR_ADDR_FIELD_SHIFT 0
 #define DART_T8020_TTBR_SHIFT 12
@@ -368,12 +369,14 @@ apple_dart_t8020_hw_stream_command(struct apple_dart_stream_map *stream_map,
 			     u32 command)
 {
 	unsigned long flags;
-	int ret;
+	int ret, i;
 	u32 command_reg;
 
 	spin_lock_irqsave(&stream_map->dart->lock, flags);
 
-	writel(stream_map->sidmap[0], stream_map->dart->regs + DART_T8020_STREAM_SELECT);
+	for (i = 0; i < BITS_TO_U32(stream_map->dart->num_streams); i++)
+		writel(stream_map->sidmap[i],
+		       stream_map->dart->regs + DART_T8020_STREAM_SELECT + 4 * i);
 	writel(command, stream_map->dart->regs + DART_T8020_STREAM_COMMAND);
 
 	ret = readl_poll_timeout_atomic(
@@ -740,7 +743,6 @@ static void apple_dart_release_device(struct device *dev)
 {
 	struct apple_dart_master_cfg *cfg = dev_iommu_priv_get(dev);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
@@ -908,7 +910,7 @@ static struct iommu_group *apple_dart_device_group(struct device *dev)
 
 		ret = apple_dart_merge_master_cfg(group_master_cfg, cfg);
 		if (ret) {
-			dev_err(dev, "Failed to merge DART IOMMU grups.\n");
+			dev_err(dev, "Failed to merge DART IOMMU groups.\n");
 			iommu_group_put(group);
 			res = ERR_PTR(ret);
 			goto out;
@@ -1215,6 +1217,33 @@ static const struct apple_dart_hw apple_dart_hw_t8103 = {
 	.ttbr_shift = DART_T8020_TTBR_SHIFT,
 	.ttbr_count = 4,
 };
+
+static const struct apple_dart_hw apple_dart_hw_t8103_usb4 = {
+	.type = DART_T8020,
+	.irq_handler = apple_dart_t8020_irq,
+	.invalidate_tlb = apple_dart_t8020_hw_invalidate_tlb,
+	.oas = 36,
+	.fmt = APPLE_DART,
+	.max_sid_count = 64,
+
+	.enable_streams = DART_T8020_STREAMS_ENABLE,
+	.lock = DART_T8020_CONFIG,
+	.lock_bit = DART_T8020_CONFIG_LOCK,
+
+	.error = DART_T8020_ERROR,
+
+	.tcr = DART_T8020_TCR,
+	.tcr_enabled = DART_T8020_TCR_TRANSLATE_ENABLE,
+	.tcr_disabled = 0,
+	.tcr_bypass = 0,
+
+	.ttbr = DART_T8020_USB4_TTBR,
+	.ttbr_valid = DART_T8020_TTBR_VALID,
+	.ttbr_addr_field_shift = DART_T8020_TTBR_ADDR_FIELD_SHIFT,
+	.ttbr_shift = DART_T8020_TTBR_SHIFT,
+	.ttbr_count = 4,
+};
+
 static const struct apple_dart_hw apple_dart_hw_t6000 = {
 	.type = DART_T6000,
 	.irq_handler = apple_dart_t8020_irq,
@@ -1272,7 +1301,7 @@ static __maybe_unused int apple_dart_suspend(struct device *dev)
 	unsigned int sid, idx;
 
 	for (sid = 0; sid < dart->num_streams; sid++) {
-		dart->save_tcr[sid] = readl_relaxed(dart->regs + DART_TCR(dart, sid));
+		dart->save_tcr[sid] = readl(dart->regs + DART_TCR(dart, sid));
 		for (idx = 0; idx < dart->hw->ttbr_count; idx++)
 			dart->save_ttbr[sid][idx] =
 				readl(dart->regs + DART_TTBR(dart, sid, idx));
@@ -1307,6 +1336,7 @@ static DEFINE_SIMPLE_DEV_PM_OPS(apple_dart_pm_ops, apple_dart_suspend, apple_dar
 
 static const struct of_device_id apple_dart_of_match[] = {
 	{ .compatible = "apple,t8103-dart", .data = &apple_dart_hw_t8103 },
+	{ .compatible = "apple,t8103-usb4-dart", .data = &apple_dart_hw_t8103_usb4 },
 	{ .compatible = "apple,t8110-dart", .data = &apple_dart_hw_t8110 },
 	{ .compatible = "apple,t6000-dart", .data = &apple_dart_hw_t6000 },
 	{},
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index 7445454c2a..f3f2e47b6d 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -1063,6 +1063,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	bool cd_live;
 	__le64 *cdptr;
 	struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table;
+	struct arm_smmu_device *smmu = master->smmu;
 
 	if (WARN_ON(ssid >= (1 << cd_table->s1cdmax)))
 		return -E2BIG;
@@ -1077,6 +1078,8 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_master *master, int ssid,
 	if (!cd) { /* (5) */
 		val = 0;
 	} else if (cd == &quiet_cd) { /* (4) */
+		if (!(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
+			val &= ~(CTXDESC_CD_0_S | CTXDESC_CD_0_R);
 		val |= CTXDESC_CD_0_TCR_EPD0;
 	} else if (cd_live) { /* (3) */
 		val &= ~CTXDESC_CD_0_ASID;
@@ -1249,7 +1252,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
 }
 
 static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
-				      __le64 *dst)
+				      struct arm_smmu_ste *dst)
 {
 	/*
 	 * This is hideously complicated, but we only really care about
@@ -1267,12 +1270,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 	 * 2. Write everything apart from dword 0, sync, write dword 0, sync
 	 * 3. Update Config, sync
 	 */
-	u64 val = le64_to_cpu(dst[0]);
+	u64 val = le64_to_cpu(dst->data[0]);
 	bool ste_live = false;
-	struct arm_smmu_device *smmu = NULL;
+	struct arm_smmu_device *smmu = master->smmu;
 	struct arm_smmu_ctx_desc_cfg *cd_table = NULL;
 	struct arm_smmu_s2_cfg *s2_cfg = NULL;
-	struct arm_smmu_domain *smmu_domain = NULL;
+	struct arm_smmu_domain *smmu_domain = master->domain;
 	struct arm_smmu_cmdq_ent prefetch_cmd = {
 		.opcode		= CMDQ_OP_PREFETCH_CFG,
 		.prefetch	= {
@@ -1280,18 +1283,12 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		},
 	};
 
-	if (master) {
-		smmu_domain = master->domain;
-		smmu = master->smmu;
-	}
-
 	if (smmu_domain) {
 		switch (smmu_domain->stage) {
 		case ARM_SMMU_DOMAIN_S1:
 			cd_table = &master->cd_table;
 			break;
 		case ARM_SMMU_DOMAIN_S2:
-		case ARM_SMMU_DOMAIN_NESTED:
 			s2_cfg = &smmu_domain->s2_cfg;
 			break;
 		default:
@@ -1325,10 +1322,10 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		else
 			val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
-		dst[0] = cpu_to_le64(val);
-		dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
+		dst->data[0] = cpu_to_le64(val);
+		dst->data[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
 						STRTAB_STE_1_SHCFG_INCOMING));
-		dst[2] = 0; /* Nuke the VMID */
+		dst->data[2] = 0; /* Nuke the VMID */
 		/*
 		 * The SMMU can perform negative caching, so we must sync
 		 * the STE regardless of whether the old value was live.
@@ -1343,7 +1340,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			STRTAB_STE_1_STRW_EL2 : STRTAB_STE_1_STRW_NSEL1;
 
 		BUG_ON(ste_live);
-		dst[1] = cpu_to_le64(
+		dst->data[1] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) |
 			 FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) |
 			 FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) |
@@ -1352,7 +1349,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
 		    !master->stall_enabled)
-			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
+			dst->data[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (cd_table->cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
 			FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS) |
@@ -1362,7 +1359,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 
 	if (s2_cfg) {
 		BUG_ON(ste_live);
-		dst[2] = cpu_to_le64(
+		dst->data[2] = cpu_to_le64(
 			 FIELD_PREP(STRTAB_STE_2_S2VMID, s2_cfg->vmid) |
 			 FIELD_PREP(STRTAB_STE_2_VTCR, s2_cfg->vtcr) |
 #ifdef __BIG_ENDIAN
@@ -1371,18 +1368,18 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 |
 			 STRTAB_STE_2_S2R);
 
-		dst[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
+		dst->data[3] = cpu_to_le64(s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK);
 
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS);
 	}
 
 	if (master->ats_enabled)
-		dst[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
+		dst->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_EATS,
 						 STRTAB_STE_1_EATS_TRANS));
 
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 	/* See comment in arm_smmu_write_ctx_desc() */
-	WRITE_ONCE(dst[0], cpu_to_le64(val));
+	WRITE_ONCE(dst->data[0], cpu_to_le64(val));
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
@@ -1390,7 +1387,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool force)
+static void arm_smmu_init_bypass_stes(struct arm_smmu_ste *strtab,
+				      unsigned int nent, bool force)
 {
 	unsigned int i;
 	u64 val = STRTAB_STE_0_V;
@@ -1401,11 +1399,11 @@ static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent, bool fo
 		val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS);
 
 	for (i = 0; i < nent; ++i) {
-		strtab[0] = cpu_to_le64(val);
-		strtab[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG,
-						   STRTAB_STE_1_SHCFG_INCOMING));
-		strtab[2] = 0;
-		strtab += STRTAB_STE_DWORDS;
+		strtab->data[0] = cpu_to_le64(val);
+		strtab->data[1] = cpu_to_le64(FIELD_PREP(
+			STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING));
+		strtab->data[2] = 0;
+		strtab++;
 	}
 }
 
@@ -2171,7 +2169,6 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 		fmt = ARM_64_LPAE_S1;
 		finalise_stage_fn = arm_smmu_domain_finalise_s1;
 		break;
-	case ARM_SMMU_DOMAIN_NESTED:
 	case ARM_SMMU_DOMAIN_S2:
 		ias = smmu->ias;
 		oas = smmu->oas;
@@ -2209,26 +2206,23 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	return 0;
 }
 
-static __le64 *arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
+static struct arm_smmu_ste *
+arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid)
 {
-	__le64 *step;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	if (smmu->features & ARM_SMMU_FEAT_2_LVL_STRTAB) {
-		struct arm_smmu_strtab_l1_desc *l1_desc;
-		int idx;
+		unsigned int idx1, idx2;
 
 		/* Two-level walk */
-		idx = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
-		l1_desc = &cfg->l1_desc[idx];
-		idx = (sid & ((1 << STRTAB_SPLIT) - 1)) * STRTAB_STE_DWORDS;
-		step = &l1_desc->l2ptr[idx];
+		idx1 = (sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS;
+		idx2 = sid & ((1 << STRTAB_SPLIT) - 1);
+		return &cfg->l1_desc[idx1].l2ptr[idx2];
 	} else {
 		/* Simple linear lookup */
-		step = &cfg->strtab[sid * STRTAB_STE_DWORDS];
+		return (struct arm_smmu_ste *)&cfg
+			       ->strtab[sid * STRTAB_STE_DWORDS];
 	}
-
-	return step;
 }
 
 static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
@@ -2238,7 +2232,8 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 
 	for (i = 0; i < master->num_streams; ++i) {
 		u32 sid = master->streams[i].id;
-		__le64 *step = arm_smmu_get_step_for_sid(smmu, sid);
+		struct arm_smmu_ste *step =
+			arm_smmu_get_step_for_sid(smmu, sid);
 
 		/* Bridged PCI devices may end up with duplicated IDs */
 		for (j = 0; j < i; j++)
@@ -2403,8 +2398,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return -EBUSY;
 	}
 
-	arm_smmu_detach_dev(master);
-
 	mutex_lock(&smmu_domain->init_mutex);
 
 	if (!smmu_domain->smmu) {
@@ -2419,6 +2412,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	if (ret)
 		return ret;
 
+	/*
+	 * Prevent arm_smmu_share_asid() from trying to change the ASID
+	 * of either the old or new domain while we are working on it.
+	 * This allows the STE and the smmu_domain->devices list to
+	 * be inconsistent during this routine.
+	 */
+	mutex_lock(&arm_smmu_asid_lock);
+
+	arm_smmu_detach_dev(master);
+
 	master->domain = smmu_domain;
 
 	/*
@@ -2444,13 +2447,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 			}
 		}
 
-		/*
-		 * Prevent SVA from concurrently modifying the CD or writing to
-		 * the CD entry
-		 */
-		mutex_lock(&arm_smmu_asid_lock);
 		ret = arm_smmu_write_ctx_desc(master, IOMMU_NO_PASID, &smmu_domain->cd);
-		mutex_unlock(&arm_smmu_asid_lock);
 		if (ret) {
 			master->domain = NULL;
 			goto out_list_del;
@@ -2460,13 +2457,15 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	arm_smmu_install_ste_for_dev(master);
 
 	arm_smmu_enable_ats(master);
-	return 0;
+	goto out_unlock;
 
 out_list_del:
 	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
 	list_del(&master->domain_head);
 	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
 
+out_unlock:
+	mutex_unlock(&arm_smmu_asid_lock);
 	return ret;
 }
 
@@ -2649,9 +2648,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return ERR_PTR(-ENODEV);
-
 	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
 		return ERR_PTR(-EBUSY);
 
@@ -2698,7 +2694,6 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 
 err_free_master:
 	kfree(master);
-	dev_iommu_priv_set(dev, NULL);
 	return ERR_PTR(ret);
 }
 
@@ -2742,7 +2737,7 @@ static int arm_smmu_enable_nesting(struct iommu_domain *domain)
 	if (smmu_domain->smmu)
 		ret = -EPERM;
 	else
-		smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+		smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
 	mutex_unlock(&smmu_domain->init_mutex);
 
 	return ret;
@@ -3769,7 +3764,7 @@ static void arm_smmu_rmr_install_bypass_ste(struct arm_smmu_device *smmu)
 	iort_get_rmr_sids(dev_fwnode(smmu->dev), &rmr_list);
 
 	list_for_each_entry(e, &rmr_list, list) {
-		__le64 *step;
+		struct arm_smmu_ste *step;
 		struct iommu_iort_rmr_data *rmr;
 		int ret, i;
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 961205ba86..65fb388d51 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -188,7 +188,7 @@
 #ifdef CONFIG_CMA_ALIGNMENT
 #define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
 #else
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER)
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_PAGE_ORDER)
 #endif
 
 /*
@@ -206,6 +206,11 @@
 #define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
 
 #define STRTAB_STE_DWORDS		8
+
+struct arm_smmu_ste {
+	__le64 data[STRTAB_STE_DWORDS];
+};
+
 #define STRTAB_STE_0_V			(1UL << 0)
 #define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
 #define STRTAB_STE_0_CFG_ABORT		0
@@ -571,7 +576,7 @@ struct arm_smmu_priq {
 struct arm_smmu_strtab_l1_desc {
 	u8				span;
 
-	__le64				*l2ptr;
+	struct arm_smmu_ste		*l2ptr;
 	dma_addr_t			l2ptr_dma;
 };
 
@@ -710,7 +715,6 @@ struct arm_smmu_master {
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
-	ARM_SMMU_DOMAIN_NESTED,
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index d326fa230b..8b04ece004 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -246,6 +246,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,adreno-gmu" },
 	{ .compatible = "qcom,mdp4" },
 	{ .compatible = "qcom,mdss" },
+	{ .compatible = "qcom,qcm2290-mdss" },
 	{ .compatible = "qcom,sc7180-mdss" },
 	{ .compatible = "qcom,sc7180-mss-pil" },
 	{ .compatible = "qcom,sc7280-mdss" },
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index d6d1a2a55c..6317aaf7b3 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -82,6 +82,23 @@ static inline void arm_smmu_rpm_put(struct arm_smmu_device *smmu)
 		pm_runtime_put_autosuspend(smmu->dev);
 }
 
+static void arm_smmu_rpm_use_autosuspend(struct arm_smmu_device *smmu)
+{
+	/*
+	 * Setup an autosuspend delay to avoid bouncing runpm state.
+	 * Otherwise, if a driver for a suspended consumer device
+	 * unmaps buffers, it will runpm resume/suspend for each one.
+	 *
+	 * For example, when used by a GPU device, when an application
+	 * or game exits, it can trigger unmapping 100s or 1000s of
+	 * buffers.  With a runpm cycle for each buffer, that adds up
+	 * to 5-10sec worth of reprogramming the context bank, while
+	 * the system appears to be locked up to the user.
+	 */
+	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
+	pm_runtime_use_autosuspend(smmu->dev);
+}
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
@@ -392,8 +409,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 {
 	u32 fsr, fsynr, cbfrsynra;
 	unsigned long iova;
-	struct iommu_domain *domain = dev;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_domain *smmu_domain = dev;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	int idx = smmu_domain->cfg.cbndx;
 	int ret;
@@ -406,7 +422,7 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
 	iova = arm_smmu_cb_readq(smmu, idx, ARM_SMMU_CB_FAR);
 	cbfrsynra = arm_smmu_gr1_read(smmu, ARM_SMMU_GR1_CBFRSYNRA(idx));
 
-	ret = report_iommu_fault(domain, NULL, iova,
+	ret = report_iommu_fault(&smmu_domain->domain, NULL, iova,
 		fsynr & ARM_SMMU_FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ);
 
 	if (ret == -ENOSYS)
@@ -607,7 +623,7 @@ static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
 	return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks);
 }
 
-static int arm_smmu_init_domain_context(struct iommu_domain *domain,
+static int arm_smmu_init_domain_context(struct arm_smmu_domain *smmu_domain,
 					struct arm_smmu_device *smmu,
 					struct device *dev)
 {
@@ -616,7 +632,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	struct io_pgtable_ops *pgtbl_ops;
 	struct io_pgtable_cfg pgtbl_cfg;
 	enum io_pgtable_fmt fmt;
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct iommu_domain *domain = &smmu_domain->domain;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	irqreturn_t (*context_fault)(int irq, void *dev);
 
@@ -624,12 +640,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu_domain->smmu)
 		goto out_unlock;
 
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
-		smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
-		smmu_domain->smmu = smmu;
-		goto out_unlock;
-	}
-
 	/*
 	 * Mapping the requested stage onto what we support is surprisingly
 	 * complicated, mainly because the spec allows S1+S2 SMMUs without
@@ -796,8 +806,8 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	else
 		context_fault = arm_smmu_context_fault;
 
-	ret = devm_request_irq(smmu->dev, irq, context_fault,
-			       IRQF_SHARED, "arm-smmu-context-fault", domain);
+	ret = devm_request_irq(smmu->dev, irq, context_fault, IRQF_SHARED,
+			       "arm-smmu-context-fault", smmu_domain);
 	if (ret < 0) {
 		dev_err(smmu->dev, "failed to request context IRQ %d (%u)\n",
 			cfg->irptndx, irq);
@@ -818,14 +828,13 @@ out_unlock:
 	return ret;
 }
 
-static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
+static void arm_smmu_destroy_domain_context(struct arm_smmu_domain *smmu_domain)
 {
-	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	int ret, irq;
 
-	if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
+	if (!smmu)
 		return;
 
 	ret = arm_smmu_rpm_get(smmu);
@@ -841,7 +850,7 @@ static void arm_smmu_destroy_domain_context(struct iommu_domain *domain)
 
 	if (cfg->irptndx != ARM_SMMU_INVALID_IRPTNDX) {
 		irq = smmu->irqs[cfg->irptndx];
-		devm_free_irq(smmu->dev, irq, domain);
+		devm_free_irq(smmu->dev, irq, smmu_domain);
 	}
 
 	free_io_pgtable_ops(smmu_domain->pgtbl_ops);
@@ -854,7 +863,7 @@ static struct iommu_domain *arm_smmu_domain_alloc(unsigned type)
 {
 	struct arm_smmu_domain *smmu_domain;
 
-	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_IDENTITY) {
+	if (type != IOMMU_DOMAIN_UNMANAGED) {
 		if (using_legacy_binding || type != IOMMU_DOMAIN_DMA)
 			return NULL;
 	}
@@ -881,7 +890,7 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	 * Free the domain resources. We assume that all devices have
 	 * already been detached.
 	 */
-	arm_smmu_destroy_domain_context(domain);
+	arm_smmu_destroy_domain_context(smmu_domain);
 	kfree(smmu_domain);
 }
 
@@ -1081,21 +1090,14 @@ static void arm_smmu_master_free_smes(struct arm_smmu_master_cfg *cfg,
 	mutex_unlock(&smmu->stream_map_mutex);
 }
 
-static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
-				      struct arm_smmu_master_cfg *cfg,
-				      struct iommu_fwspec *fwspec)
+static void arm_smmu_master_install_s2crs(struct arm_smmu_master_cfg *cfg,
+					  enum arm_smmu_s2cr_type type,
+					  u8 cbndx, struct iommu_fwspec *fwspec)
 {
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
+	struct arm_smmu_device *smmu = cfg->smmu;
 	struct arm_smmu_s2cr *s2cr = smmu->s2crs;
-	u8 cbndx = smmu_domain->cfg.cbndx;
-	enum arm_smmu_s2cr_type type;
 	int i, idx;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
-		type = S2CR_TYPE_BYPASS;
-	else
-		type = S2CR_TYPE_TRANS;
-
 	for_each_cfg_sme(cfg, fwspec, i, idx) {
 		if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
 			continue;
@@ -1105,7 +1107,6 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 		s2cr[idx].cbndx = cbndx;
 		arm_smmu_write_s2cr(smmu, idx);
 	}
-	return 0;
 }
 
 static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
@@ -1116,11 +1117,6 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	struct arm_smmu_device *smmu;
 	int ret;
 
-	if (!fwspec || fwspec->ops != &arm_smmu_ops) {
-		dev_err(dev, "cannot attach to SMMU, is it on the same bus?\n");
-		return -ENXIO;
-	}
-
 	/*
 	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
 	 * domains between of_xlate() and probe_device() - we have no way to cope
@@ -1139,7 +1135,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return ret;
 
 	/* Ensure that the domain is finalised */
-	ret = arm_smmu_init_domain_context(domain, smmu, dev);
+	ret = arm_smmu_init_domain_context(smmu_domain, smmu, dev);
 	if (ret < 0)
 		goto rpm_put;
 
@@ -1153,27 +1149,66 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	}
 
 	/* Looks ok, so add the device to the domain */
-	ret = arm_smmu_domain_add_master(smmu_domain, cfg, fwspec);
-
-	/*
-	 * Setup an autosuspend delay to avoid bouncing runpm state.
-	 * Otherwise, if a driver for a suspended consumer device
-	 * unmaps buffers, it will runpm resume/suspend for each one.
-	 *
-	 * For example, when used by a GPU device, when an application
-	 * or game exits, it can trigger unmapping 100s or 1000s of
-	 * buffers.  With a runpm cycle for each buffer, that adds up
-	 * to 5-10sec worth of reprogramming the context bank, while
-	 * the system appears to be locked up to the user.
-	 */
-	pm_runtime_set_autosuspend_delay(smmu->dev, 20);
-	pm_runtime_use_autosuspend(smmu->dev);
-
+	arm_smmu_master_install_s2crs(cfg, S2CR_TYPE_TRANS,
+				      smmu_domain->cfg.cbndx, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
 rpm_put:
 	arm_smmu_rpm_put(smmu);
 	return ret;
 }
 
+static int arm_smmu_attach_dev_type(struct device *dev,
+				    enum arm_smmu_s2cr_type type)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
+	struct arm_smmu_device *smmu;
+	int ret;
+
+	if (!cfg)
+		return -ENODEV;
+	smmu = cfg->smmu;
+
+	ret = arm_smmu_rpm_get(smmu);
+	if (ret < 0)
+		return ret;
+
+	arm_smmu_master_install_s2crs(cfg, type, 0, fwspec);
+	arm_smmu_rpm_use_autosuspend(smmu);
+	arm_smmu_rpm_put(smmu);
+	return 0;
+}
+
+static int arm_smmu_attach_dev_identity(struct iommu_domain *domain,
+					struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_BYPASS);
+}
+
+static const struct iommu_domain_ops arm_smmu_identity_ops = {
+	.attach_dev = arm_smmu_attach_dev_identity,
+};
+
+static struct iommu_domain arm_smmu_identity_domain = {
+	.type = IOMMU_DOMAIN_IDENTITY,
+	.ops = &arm_smmu_identity_ops,
+};
+
+static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain,
+				       struct device *dev)
+{
+	return arm_smmu_attach_dev_type(dev, S2CR_TYPE_FAULT);
+}
+
+static const struct iommu_domain_ops arm_smmu_blocked_ops = {
+	.attach_dev = arm_smmu_attach_dev_blocked,
+};
+
+static struct iommu_domain arm_smmu_blocked_domain = {
+	.type = IOMMU_DOMAIN_BLOCKED,
+	.ops = &arm_smmu_blocked_ops,
+};
+
 static int arm_smmu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			      int prot, gfp_t gfp, size_t *mapped)
@@ -1357,10 +1392,8 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 		fwspec = dev_iommu_fwspec_get(dev);
 		if (ret)
 			goto out_free;
-	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
-		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	} else {
-		return ERR_PTR(-ENODEV);
+		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	}
 
 	ret = -EINVAL;
@@ -1427,7 +1460,6 @@ static void arm_smmu_release_device(struct device *dev)
 
 	arm_smmu_rpm_put(cfg->smmu);
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(cfg);
 }
 
@@ -1560,6 +1592,8 @@ static int arm_smmu_def_domain_type(struct device *dev)
 }
 
 static struct iommu_ops arm_smmu_ops = {
+	.identity_domain	= &arm_smmu_identity_domain,
+	.blocked_domain		= &arm_smmu_blocked_domain,
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
 	.probe_device		= arm_smmu_probe_device,
@@ -2161,7 +2195,8 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops, dev);
+	err = iommu_device_register(&smmu->iommu, &arm_smmu_ops,
+				    using_legacy_binding ? NULL : dev);
 	if (err) {
 		dev_err(dev, "Failed to register iommu\n");
 		iommu_device_sysfs_remove(&smmu->iommu);
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index 703fd5817e..836ed6799a 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -361,7 +361,6 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
 	ARM_SMMU_DOMAIN_NESTED,
-	ARM_SMMU_DOMAIN_BYPASS,
 };
 
 struct arm_smmu_domain {
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index 97b2122032..17a1c163fe 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -79,16 +79,6 @@ static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom)
 
 static const struct iommu_ops qcom_iommu_ops;
 
-static struct qcom_iommu_dev * to_iommu(struct device *dev)
-{
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-
-	if (!fwspec || fwspec->ops != &qcom_iommu_ops)
-		return NULL;
-
-	return dev_iommu_priv_get(dev);
-}
-
 static struct qcom_iommu_ctx * to_ctx(struct qcom_iommu_domain *d, unsigned asid)
 {
 	struct qcom_iommu_dev *qcom_iommu = d->iommu;
@@ -372,7 +362,7 @@ static void qcom_iommu_domain_free(struct iommu_domain *domain)
 
 static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	int ret;
 
@@ -404,7 +394,7 @@ static int qcom_iommu_identity_attach(struct iommu_domain *identity_domain,
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct qcom_iommu_domain *qcom_domain;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	unsigned int i;
 
 	if (domain == identity_domain || !domain)
@@ -535,7 +525,7 @@ static bool qcom_iommu_capable(struct device *dev, enum iommu_cap cap)
 
 static struct iommu_device *qcom_iommu_probe_device(struct device *dev)
 {
-	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
+	struct qcom_iommu_dev *qcom_iommu = dev_iommu_priv_get(dev);
 	struct device_link *link;
 
 	if (!qcom_iommu)
@@ -900,8 +890,16 @@ static void qcom_iommu_device_remove(struct platform_device *pdev)
 static int __maybe_unused qcom_iommu_resume(struct device *dev)
 {
 	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	if (ret < 0)
+		return ret;
+
+	if (dev->pm_domain)
+		return qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, 0);
 
-	return clk_bulk_prepare_enable(CLK_NUM, qcom_iommu->clks);
+	return ret;
 }
 
 static int __maybe_unused qcom_iommu_suspend(struct device *dev)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index a0767ce1bd..639efa0c40 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -885,7 +885,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	struct page **pages;
 	unsigned int i = 0, nid = dev_to_node(dev);
 
-	order_mask &= GENMASK(MAX_ORDER, 0);
+	order_mask &= GENMASK(MAX_PAGE_ORDER, 0);
 	if (!order_mask)
 		return NULL;
 
diff --git a/drivers/iommu/intel/debugfs.c b/drivers/iommu/intel/debugfs.c
index dee61e513b..86b506af7d 100644
--- a/drivers/iommu/intel/debugfs.c
+++ b/drivers/iommu/intel/debugfs.c
@@ -106,9 +106,6 @@ 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;
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 23cb80d62a..36d7427b12 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1095,7 +1095,9 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	iommu->agaw = agaw;
 	iommu->msagaw = msagaw;
 	iommu->segment = drhd->segment;
-
+	iommu->device_rbtree = RB_ROOT;
+	spin_lock_init(&iommu->device_rbtree_lock);
+	mutex_init(&iommu->iopf_lock);
 	iommu->node = NUMA_NO_NODE;
 
 	ver = readl(iommu->reg + DMAR_VER_REG);
@@ -1271,6 +1273,8 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 {
 	u32 fault;
 	int head, tail;
+	struct device *dev;
+	u64 iqe_err, ite_sid;
 	struct q_inval *qi = iommu->qi;
 	int shift = qi_shift(iommu);
 
@@ -1315,6 +1319,13 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 		tail = readl(iommu->reg + DMAR_IQT_REG);
 		tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
 
+		/*
+		 * SID field is valid only when the ITE field is Set in FSTS_REG
+		 * see Intel VT-d spec r4.1, section 11.4.9.9
+		 */
+		iqe_err = dmar_readq(iommu->reg + DMAR_IQER_REG);
+		ite_sid = DMAR_IQER_REG_ITESID(iqe_err);
+
 		writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
 		pr_info("Invalidation Time-out Error (ITE) cleared\n");
 
@@ -1324,6 +1335,19 @@ static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 			head = (head - 2 + QI_LENGTH) % QI_LENGTH;
 		} while (head != tail);
 
+		/*
+		 * If device was released or isn't present, no need to retry
+		 * the ATS invalidate request anymore.
+		 *
+		 * 0 value of ite_sid means old VT-d device, no ite_sid value.
+		 * see Intel VT-d spec r4.1, section 11.4.9.9
+		 */
+		if (ite_sid) {
+			dev = device_rbtree_find(iommu, ite_sid);
+			if (!dev || !dev_is_pci(dev) ||
+			    !pci_device_is_present(to_pci_dev(dev)))
+				return -ETIMEDOUT;
+		}
 		if (qi->desc_status[wait_index] == QI_ABORT)
 			return -EAGAIN;
 	}
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index a8366b1f4f..d7e10f1311 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -46,9 +46,6 @@
 
 #define DEFAULT_DOMAIN_ADDRESS_WIDTH 57
 
-#define MAX_AGAW_WIDTH 64
-#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
-
 #define __DOMAIN_MAX_PFN(gaw)  ((((uint64_t)1) << ((gaw) - VTD_PAGE_SHIFT)) - 1)
 #define __DOMAIN_MAX_ADDR(gaw) ((((uint64_t)1) << (gaw)) - 1)
 
@@ -63,74 +60,6 @@
 
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 
-/* page table handling */
-#define LEVEL_STRIDE		(9)
-#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
-
-static inline int agaw_to_level(int agaw)
-{
-	return agaw + 2;
-}
-
-static inline int agaw_to_width(int agaw)
-{
-	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
-}
-
-static inline int width_to_agaw(int width)
-{
-	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
-}
-
-static inline unsigned int level_to_offset_bits(int level)
-{
-	return (level - 1) * LEVEL_STRIDE;
-}
-
-static inline int pfn_level_offset(u64 pfn, int level)
-{
-	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
-}
-
-static inline u64 level_mask(int level)
-{
-	return -1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 level_size(int level)
-{
-	return 1ULL << level_to_offset_bits(level);
-}
-
-static inline u64 align_to_level(u64 pfn, int level)
-{
-	return (pfn + level_size(level) - 1) & level_mask(level);
-}
-
-static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
-{
-	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
-}
-
-/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
-   are never going to work. */
-static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
-{
-	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
-}
-static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
-{
-	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
-}
-static inline unsigned long page_to_dma_pfn(struct page *pg)
-{
-	return mm_to_dma_pfn_start(page_to_pfn(pg));
-}
-static inline unsigned long virt_to_dma_pfn(void *p)
-{
-	return page_to_dma_pfn(virt_to_page(p));
-}
-
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
@@ -168,76 +97,79 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 	return re->hi & VTD_PAGE_MASK;
 }
 
-static inline void context_set_present(struct context_entry *context)
+static int device_rid_cmp_key(const void *key, const struct rb_node *node)
 {
-	context->lo |= 1;
-}
+	struct device_domain_info *info =
+		rb_entry(node, struct device_domain_info, node);
+	const u16 *rid_lhs = key;
 
-static inline void context_set_fault_enable(struct context_entry *context)
-{
-	context->lo &= (((u64)-1) << 2) | 1;
-}
+	if (*rid_lhs < PCI_DEVID(info->bus, info->devfn))
+		return -1;
 
-static inline void context_set_translation_type(struct context_entry *context,
-						unsigned long value)
-{
-	context->lo &= (((u64)-1) << 4) | 3;
-	context->lo |= (value & 3) << 2;
-}
+	if (*rid_lhs > PCI_DEVID(info->bus, info->devfn))
+		return 1;
 
-static inline void context_set_address_root(struct context_entry *context,
-					    unsigned long value)
-{
-	context->lo &= ~VTD_PAGE_MASK;
-	context->lo |= value & VTD_PAGE_MASK;
+	return 0;
 }
 
-static inline void context_set_address_width(struct context_entry *context,
-					     unsigned long value)
+static int device_rid_cmp(struct rb_node *lhs, const struct rb_node *rhs)
 {
-	context->hi |= value & 7;
-}
+	struct device_domain_info *info =
+		rb_entry(lhs, struct device_domain_info, node);
+	u16 key = PCI_DEVID(info->bus, info->devfn);
 
-static inline void context_set_domain_id(struct context_entry *context,
-					 unsigned long value)
-{
-	context->hi |= (value & ((1 << 16) - 1)) << 8;
+	return device_rid_cmp_key(&key, rhs);
 }
 
-static inline void context_set_pasid(struct context_entry *context)
+/*
+ * Looks up an IOMMU-probed device using its source ID.
+ *
+ * Returns the pointer to the device if there is a match. Otherwise,
+ * returns NULL.
+ *
+ * Note that this helper doesn't guarantee that the device won't be
+ * released by the iommu subsystem after being returned. The caller
+ * should use its own synchronization mechanism to avoid the device
+ * being released during its use if its possibly the case.
+ */
+struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid)
 {
-	context->lo |= CONTEXT_PASIDE;
-}
+	struct device_domain_info *info = NULL;
+	struct rb_node *node;
+	unsigned long flags;
 
-static inline int context_domain_id(struct context_entry *c)
-{
-	return((c->hi >> 8) & 0xffff);
-}
+	spin_lock_irqsave(&iommu->device_rbtree_lock, flags);
+	node = rb_find(&rid, &iommu->device_rbtree, device_rid_cmp_key);
+	if (node)
+		info = rb_entry(node, struct device_domain_info, node);
+	spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags);
 
-static inline void context_clear_entry(struct context_entry *context)
-{
-	context->lo = 0;
-	context->hi = 0;
+	return info ? info->dev : NULL;
 }
 
-static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+static int device_rbtree_insert(struct intel_iommu *iommu,
+				struct device_domain_info *info)
 {
-	if (!iommu->copied_tables)
-		return false;
+	struct rb_node *curr;
+	unsigned long flags;
 
-	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
-}
+	spin_lock_irqsave(&iommu->device_rbtree_lock, flags);
+	curr = rb_find_add(&info->node, &iommu->device_rbtree, device_rid_cmp);
+	spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags);
+	if (WARN_ON(curr))
+		return -EEXIST;
 
-static inline void
-set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
-{
-	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+	return 0;
 }
 
-static inline void
-clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+static void device_rbtree_remove(struct device_domain_info *info)
 {
-	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+	struct intel_iommu *iommu = info->iommu;
+	unsigned long flags;
+
+	spin_lock_irqsave(&iommu->device_rbtree_lock, flags);
+	rb_erase(&info->node, &iommu->device_rbtree);
+	spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags);
 }
 
 /*
@@ -383,13 +315,12 @@ void free_pgtable_page(void *vaddr)
 	free_page((unsigned long)vaddr);
 }
 
-static inline int domain_type_is_si(struct dmar_domain *domain)
+static int domain_type_is_si(struct dmar_domain *domain)
 {
 	return domain->domain.type == IOMMU_DOMAIN_IDENTITY;
 }
 
-static inline int domain_pfn_supported(struct dmar_domain *domain,
-				       unsigned long pfn)
+static int domain_pfn_supported(struct dmar_domain *domain, unsigned long pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 
@@ -451,7 +382,7 @@ int iommu_calculate_agaw(struct intel_iommu *iommu)
 	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
 }
 
-static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
+static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
 {
 	return sm_supported(iommu) ?
 			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
@@ -701,7 +632,7 @@ static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
 	return false;
 }
 
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
+static struct intel_iommu *device_lookup_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	struct pci_dev *pdev = NULL;
@@ -1510,6 +1441,46 @@ static void domain_flush_pasid_iotlb(struct intel_iommu *iommu,
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
+static void __iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
+				    unsigned long pfn, unsigned int pages,
+				    int ih)
+{
+	unsigned int aligned_pages = __roundup_pow_of_two(pages);
+	unsigned long bitmask = aligned_pages - 1;
+	unsigned int mask = ilog2(aligned_pages);
+	u64 addr = (u64)pfn << VTD_PAGE_SHIFT;
+
+	/*
+	 * PSI masks the low order bits of the base address. If the
+	 * address isn't aligned to the mask, then compute a mask value
+	 * needed to ensure the target range is flushed.
+	 */
+	if (unlikely(bitmask & pfn)) {
+		unsigned long end_pfn = pfn + pages - 1, shared_bits;
+
+		/*
+		 * Since end_pfn <= pfn + bitmask, the only way bits
+		 * higher than bitmask can differ in pfn and end_pfn is
+		 * by carrying. This means after masking out bitmask,
+		 * high bits starting with the first set bit in
+		 * shared_bits are all equal in both pfn and end_pfn.
+		 */
+		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+		mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
+	}
+
+	/*
+	 * Fallback to domain selective flush if no PSI support or
+	 * the size is too big.
+	 */
+	if (!cap_pgsel_inv(iommu->cap) || mask > cap_max_amask_val(iommu->cap))
+		iommu->flush.flush_iotlb(iommu, did, 0, 0,
+					 DMA_TLB_DSI_FLUSH);
+	else
+		iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
+					 DMA_TLB_PSI_FLUSH);
+}
+
 static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 				  struct dmar_domain *domain,
 				  unsigned long pfn, unsigned int pages,
@@ -1526,42 +1497,10 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 	if (ih)
 		ih = 1 << 6;
 
-	if (domain->use_first_level) {
+	if (domain->use_first_level)
 		domain_flush_pasid_iotlb(iommu, domain, addr, pages, ih);
-	} else {
-		unsigned long bitmask = aligned_pages - 1;
-
-		/*
-		 * PSI masks the low order bits of the base address. If the
-		 * address isn't aligned to the mask, then compute a mask value
-		 * needed to ensure the target range is flushed.
-		 */
-		if (unlikely(bitmask & pfn)) {
-			unsigned long end_pfn = pfn + pages - 1, shared_bits;
-
-			/*
-			 * Since end_pfn <= pfn + bitmask, the only way bits
-			 * higher than bitmask can differ in pfn and end_pfn is
-			 * by carrying. This means after masking out bitmask,
-			 * high bits starting with the first set bit in
-			 * shared_bits are all equal in both pfn and end_pfn.
-			 */
-			shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
-			mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
-		}
-
-		/*
-		 * Fallback to domain selective flush if no PSI support or
-		 * the size is too big.
-		 */
-		if (!cap_pgsel_inv(iommu->cap) ||
-		    mask > cap_max_amask_val(iommu->cap))
-			iommu->flush.flush_iotlb(iommu, did, 0, 0,
-							DMA_TLB_DSI_FLUSH);
-		else
-			iommu->flush.flush_iotlb(iommu, did, addr | ih, mask,
-							DMA_TLB_PSI_FLUSH);
-	}
+	else
+		__iommu_flush_iotlb_psi(iommu, did, pfn, pages, ih);
 
 	/*
 	 * In caching mode, changes of pages from non-present to present require
@@ -1572,9 +1511,8 @@ static void iommu_flush_iotlb_psi(struct intel_iommu *iommu,
 }
 
 /* Notification for newly created mappings */
-static inline void __mapping_notify_one(struct intel_iommu *iommu,
-					struct dmar_domain *domain,
-					unsigned long pfn, unsigned int pages)
+static void __mapping_notify_one(struct intel_iommu *iommu, struct dmar_domain *domain,
+				 unsigned long pfn, unsigned int pages)
 {
 	/*
 	 * It's a non-present to present mapping. Only flush if caching mode
@@ -1586,6 +1524,46 @@ static inline void __mapping_notify_one(struct intel_iommu *iommu,
 		iommu_flush_write_buffer(iommu);
 }
 
+/*
+ * Flush the relevant caches in nested translation if the domain
+ * also serves as a parent
+ */
+static void parent_domain_flush(struct dmar_domain *domain,
+				unsigned long pfn,
+				unsigned long pages, int ih)
+{
+	struct dmar_domain *s1_domain;
+
+	spin_lock(&domain->s1_lock);
+	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
+		struct device_domain_info *device_info;
+		struct iommu_domain_info *info;
+		unsigned long flags;
+		unsigned long i;
+
+		xa_for_each(&s1_domain->iommu_array, i, info)
+			__iommu_flush_iotlb_psi(info->iommu, info->did,
+						pfn, pages, ih);
+
+		if (!s1_domain->has_iotlb_device)
+			continue;
+
+		spin_lock_irqsave(&s1_domain->lock, flags);
+		list_for_each_entry(device_info, &s1_domain->devices, link)
+			/*
+			 * Address translation cache in device side caches the
+			 * result of nested translation. There is no easy way
+			 * to identify the exact set of nested translations
+			 * affected by a change in S2. So just flush the entire
+			 * device cache.
+			 */
+			__iommu_flush_dev_iotlb(device_info, 0,
+						MAX_AGAW_PFN_WIDTH);
+		spin_unlock_irqrestore(&s1_domain->lock, flags);
+	}
+	spin_unlock(&domain->s1_lock);
+}
+
 static void intel_flush_iotlb_all(struct iommu_domain *domain)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
@@ -1605,6 +1583,9 @@ static void intel_flush_iotlb_all(struct iommu_domain *domain)
 		if (!cap_caching_mode(iommu->cap))
 			iommu_flush_dev_iotlb(dmar_domain, 0, MAX_AGAW_PFN_WIDTH);
 	}
+
+	if (dmar_domain->nested_parent)
+		parent_domain_flush(dmar_domain, 0, -1, 0);
 }
 
 static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
@@ -1841,7 +1822,7 @@ void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
 	spin_unlock(&iommu->lock);
 }
 
-static inline int guestwidth_to_adjustwidth(int gaw)
+static int guestwidth_to_adjustwidth(int gaw)
 {
 	int agaw;
 	int r = (gaw - 12) % 9;
@@ -1875,7 +1856,7 @@ static void domain_exit(struct dmar_domain *domain)
  * Value of X in the PDTS field of a scalable mode context entry
  * indicates PASID directory with 2^(X + 7) entries.
  */
-static inline unsigned long context_get_sm_pds(struct pasid_table *table)
+static unsigned long context_get_sm_pds(struct pasid_table *table)
 {
 	unsigned long pds, max_pde;
 
@@ -1887,38 +1868,6 @@ static inline unsigned long context_get_sm_pds(struct pasid_table *table)
 	return pds - 7;
 }
 
-/*
- * Set the RID_PASID field of a scalable mode context entry. The
- * IOMMU hardware will use the PASID value set in this field for
- * DMA translations of DMA requests without PASID.
- */
-static inline void
-context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
-{
-	context->hi |= pasid & ((1 << 20) - 1);
-}
-
-/*
- * Set the DTE(Device-TLB Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_dte(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(2);
-}
-
-/*
- * Set the PRE(Page Request Enable) field of a scalable mode context
- * entry.
- */
-static inline void context_set_sm_pre(struct context_entry *context)
-{
-	context->lo |= BIT_ULL(4);
-}
-
-/* Convert value to context PASID directory size field coding. */
-#define context_pdts(pds)	(((pds) & 0x7) << 9)
-
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
 				      struct pasid_table *table,
@@ -2079,14 +2028,11 @@ static int domain_context_mapping_cb(struct pci_dev *pdev,
 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;
-	struct intel_iommu *iommu;
-	u8 bus, devfn;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
 
 	table = intel_pasid_get_table(dev);
 
@@ -2103,18 +2049,15 @@ domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 }
 
 /* Returns a number of VTD pages, but aligned to MM page size */
-static inline unsigned long aligned_nrpages(unsigned long host_addr,
-					    size_t size)
+static unsigned long aligned_nrpages(unsigned long host_addr, size_t size)
 {
 	host_addr &= ~PAGE_MASK;
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
 /* Return largest possible superpage level for a given mapping */
-static inline int hardware_largepage_caps(struct dmar_domain *domain,
-					  unsigned long iov_pfn,
-					  unsigned long phy_pfn,
-					  unsigned long pages)
+static int hardware_largepage_caps(struct dmar_domain *domain, unsigned long iov_pfn,
+				   unsigned long phy_pfn, unsigned long pages)
 {
 	int support, level = 1;
 	unsigned long pfnmerge;
@@ -2166,6 +2109,9 @@ static void switch_to_super_page(struct dmar_domain *domain,
 				iommu_flush_iotlb_psi(info->iommu, domain,
 						      start_pfn, lvl_pages,
 						      0, 0);
+			if (domain->nested_parent)
+				parent_domain_flush(domain, start_pfn,
+						    lvl_pages, 0);
 		}
 
 		pte++;
@@ -2447,15 +2393,10 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	unsigned long flags;
-	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
 	ret = domain_attach_iommu(domain, iommu);
 	if (ret)
 		return ret;
@@ -2468,7 +2409,7 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	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, 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,
@@ -3613,7 +3554,7 @@ void intel_iommu_shutdown(void)
 	up_write(&dmar_global_lock);
 }
 
-static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
+static struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
 
@@ -3692,7 +3633,7 @@ const struct attribute_group *intel_iommu_groups[] = {
 	NULL,
 };
 
-static inline bool has_external_pci(void)
+static bool has_external_pci(void)
 {
 	struct pci_dev *pdev = NULL;
 
@@ -3933,30 +3874,6 @@ static void domain_context_clear(struct device_domain_info *info)
 			       &domain_context_clear_one_cb, info);
 }
 
-static void dmar_remove_one_dev_info(struct device *dev)
-{
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
-	struct dmar_domain *domain = info->domain;
-	struct intel_iommu *iommu = info->iommu;
-	unsigned long flags;
-
-	if (!dev_is_real_dma_subdevice(info->dev)) {
-		if (dev_is_pci(info->dev) && sm_supported(iommu))
-			intel_pasid_tear_down_entry(iommu, info->dev,
-					IOMMU_NO_PASID, false);
-
-		iommu_disable_pci_caps(info);
-		domain_context_clear(info);
-	}
-
-	spin_lock_irqsave(&domain->lock, flags);
-	list_del(&info->link);
-	spin_unlock_irqrestore(&domain->lock, flags);
-
-	domain_detach_iommu(domain, iommu);
-	info->domain = NULL;
-}
-
 /*
  * Clear the page table pointer in context or pasid table entries so that
  * all DMA requests without PASID from the device are blocked. If the page
@@ -4127,14 +4044,11 @@ static void intel_iommu_domain_free(struct iommu_domain *domain)
 int prepare_domain_attach_device(struct iommu_domain *domain,
 				 struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
-	struct intel_iommu *iommu;
+	struct intel_iommu *iommu = info->iommu;
 	int addr_width;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return -ENODEV;
-
 	if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap))
 		return -EINVAL;
 
@@ -4306,6 +4220,9 @@ static void intel_iommu_tlb_sync(struct iommu_domain *domain,
 				      start_pfn, nrpages,
 				      list_empty(&gather->freelist), 0);
 
+	if (dmar_domain->nested_parent)
+		parent_domain_flush(dmar_domain, start_pfn, nrpages,
+				    list_empty(&gather->freelist));
 	put_pages_list(&gather->freelist);
 }
 
@@ -4411,7 +4328,7 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	u8 bus, devfn;
 	int ret;
 
-	iommu = device_to_iommu(dev, &bus, &devfn);
+	iommu = device_lookup_iommu(dev, &bus, &devfn);
 	if (!iommu || !iommu->iommu.ops)
 		return ERR_PTR(-ENODEV);
 
@@ -4464,30 +4381,47 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev)
 	}
 
 	dev_iommu_priv_set(dev, info);
+	if (pdev && pci_ats_supported(pdev)) {
+		ret = device_rbtree_insert(iommu, info);
+		if (ret)
+			goto free;
+	}
 
 	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
 			dev_err(dev, "PASID table allocation failed\n");
-			dev_iommu_priv_set(dev, NULL);
-			kfree(info);
-			return ERR_PTR(ret);
+			goto clear_rbtree;
 		}
 	}
 
 	intel_iommu_debugfs_create_dev(info);
 
 	return &iommu->iommu;
+clear_rbtree:
+	device_rbtree_remove(info);
+free:
+	kfree(info);
+
+	return ERR_PTR(ret);
 }
 
 static void intel_iommu_release_device(struct device *dev)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+
+	mutex_lock(&iommu->iopf_lock);
+	if (dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev)))
+		device_rbtree_remove(info);
+	mutex_unlock(&iommu->iopf_lock);
+
+	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) &&
+	    !context_copied(iommu, info->bus, info->devfn))
+		intel_pasid_teardown_sm_context(dev);
 
-	dmar_remove_one_dev_info(dev);
 	intel_pasid_free_table(dev);
 	intel_iommu_debugfs_remove_dev(info);
-	dev_iommu_priv_set(dev, NULL);
 	kfree(info);
 	set_dma_ops(dev, NULL);
 }
@@ -4747,8 +4681,9 @@ static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 
 static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 {
-	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct dev_pasid_info *curr, *dev_pasid = NULL;
+	struct intel_iommu *iommu = info->iommu;
 	struct dmar_domain *dmar_domain;
 	struct iommu_domain *domain;
 	unsigned long flags;
@@ -4819,8 +4754,7 @@ static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
 		goto out_free;
 
 	if (domain_type_is_si(dmar_domain))
-		ret = intel_pasid_setup_pass_through(iommu, dmar_domain,
-						     dev, pasid);
+		ret = intel_pasid_setup_pass_through(iommu, dev, pasid);
 	else if (dmar_domain->use_first_level)
 		ret = domain_setup_first_level(iommu, dmar_domain,
 					       dev, pasid);
@@ -4991,6 +4925,7 @@ static const struct iommu_dirty_ops intel_dirty_ops = {
 
 const struct iommu_ops intel_iommu_ops = {
 	.blocked_domain		= &blocking_domain,
+	.release_domain		= &blocking_domain,
 	.capable		= intel_iommu_capable,
 	.hw_info		= intel_iommu_hw_info,
 	.domain_alloc		= intel_iommu_domain_alloc,
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index efc00d2b45..cd267ba64e 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -140,9 +140,6 @@
 #define DMAR_ECEO_REG		0x408
 #define DMAR_ECRSP_REG		0x410
 #define DMAR_ECCAP_REG		0x430
-#define DMAR_VCCAP_REG		0xe30 /* Virtual command capability register */
-#define DMAR_VCMD_REG		0xe00 /* Virtual command register */
-#define DMAR_VCRSP_REG		0xe10 /* Virtual command response register */
 
 #define DMAR_IQER_REG_IQEI(reg)		FIELD_GET(GENMASK_ULL(3, 0), reg)
 #define DMAR_IQER_REG_ITESID(reg)	FIELD_GET(GENMASK_ULL(47, 32), reg)
@@ -722,9 +719,16 @@ struct intel_iommu {
 #endif
 	struct iopf_queue *iopf_queue;
 	unsigned char iopfq_name[16];
+	/* Synchronization between fault report and iommu device release. */
+	struct mutex iopf_lock;
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 iommu_state[MAX_SR_DMAR_REGS]; /* Store iommu states between suspend and resume.*/
 
+	/* rb tree for all probed devices */
+	struct rb_root device_rbtree;
+	/* protect the device_rbtree */
+	spinlock_t device_rbtree_lock;
+
 #ifdef CONFIG_IRQ_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
 	struct irq_domain *ir_domain;
@@ -758,6 +762,8 @@ struct device_domain_info {
 	struct intel_iommu *iommu; /* IOMMU used by this device */
 	struct dmar_domain *domain; /* pointer to domain */
 	struct pasid_table *pasid_table; /* pasid table */
+	/* device tracking node(lookup by PCI RID) */
+	struct rb_node node;
 #ifdef CONFIG_INTEL_IOMMU_DEBUGFS
 	struct dentry *debugfs_dentry; /* pointer to device directory dentry */
 #endif
@@ -860,6 +866,181 @@ static inline bool context_present(struct context_entry *context)
 	return (context->lo & 1);
 }
 
+#define LEVEL_STRIDE		(9)
+#define LEVEL_MASK		(((u64)1 << LEVEL_STRIDE) - 1)
+#define MAX_AGAW_WIDTH		(64)
+#define MAX_AGAW_PFN_WIDTH	(MAX_AGAW_WIDTH - VTD_PAGE_SHIFT)
+
+static inline int agaw_to_level(int agaw)
+{
+	return agaw + 2;
+}
+
+static inline int agaw_to_width(int agaw)
+{
+	return min_t(int, 30 + agaw * LEVEL_STRIDE, MAX_AGAW_WIDTH);
+}
+
+static inline int width_to_agaw(int width)
+{
+	return DIV_ROUND_UP(width - 30, LEVEL_STRIDE);
+}
+
+static inline unsigned int level_to_offset_bits(int level)
+{
+	return (level - 1) * LEVEL_STRIDE;
+}
+
+static inline int pfn_level_offset(u64 pfn, int level)
+{
+	return (pfn >> level_to_offset_bits(level)) & LEVEL_MASK;
+}
+
+static inline u64 level_mask(int level)
+{
+	return -1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 level_size(int level)
+{
+	return 1ULL << level_to_offset_bits(level);
+}
+
+static inline u64 align_to_level(u64 pfn, int level)
+{
+	return (pfn + level_size(level) - 1) & level_mask(level);
+}
+
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return 1UL << min_t(int, (lvl - 1) * LEVEL_STRIDE, MAX_AGAW_PFN_WIDTH);
+}
+
+/* VT-d pages must always be _smaller_ than MM pages. Otherwise things
+   are never going to work. */
+static inline unsigned long mm_to_dma_pfn_start(unsigned long mm_pfn)
+{
+	return mm_pfn << (PAGE_SHIFT - VTD_PAGE_SHIFT);
+}
+static inline unsigned long mm_to_dma_pfn_end(unsigned long mm_pfn)
+{
+	return ((mm_pfn + 1) << (PAGE_SHIFT - VTD_PAGE_SHIFT)) - 1;
+}
+static inline unsigned long page_to_dma_pfn(struct page *pg)
+{
+	return mm_to_dma_pfn_start(page_to_pfn(pg));
+}
+static inline unsigned long virt_to_dma_pfn(void *p)
+{
+	return page_to_dma_pfn(virt_to_page(p));
+}
+
+static inline void context_set_present(struct context_entry *context)
+{
+	context->lo |= 1;
+}
+
+static inline void context_set_fault_enable(struct context_entry *context)
+{
+	context->lo &= (((u64)-1) << 2) | 1;
+}
+
+static inline void context_set_translation_type(struct context_entry *context,
+						unsigned long value)
+{
+	context->lo &= (((u64)-1) << 4) | 3;
+	context->lo |= (value & 3) << 2;
+}
+
+static inline void context_set_address_root(struct context_entry *context,
+					    unsigned long value)
+{
+	context->lo &= ~VTD_PAGE_MASK;
+	context->lo |= value & VTD_PAGE_MASK;
+}
+
+static inline void context_set_address_width(struct context_entry *context,
+					     unsigned long value)
+{
+	context->hi |= value & 7;
+}
+
+static inline void context_set_domain_id(struct context_entry *context,
+					 unsigned long value)
+{
+	context->hi |= (value & ((1 << 16) - 1)) << 8;
+}
+
+static inline void context_set_pasid(struct context_entry *context)
+{
+	context->lo |= CONTEXT_PASIDE;
+}
+
+static inline int context_domain_id(struct context_entry *c)
+{
+	return((c->hi >> 8) & 0xffff);
+}
+
+static inline void context_clear_entry(struct context_entry *context)
+{
+	context->lo = 0;
+	context->hi = 0;
+}
+
+#ifdef CONFIG_INTEL_IOMMU
+static inline bool context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	if (!iommu->copied_tables)
+		return false;
+
+	return test_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+set_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	set_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+
+static inline void
+clear_context_copied(struct intel_iommu *iommu, u8 bus, u8 devfn)
+{
+	clear_bit(((long)bus << 8) | devfn, iommu->copied_tables);
+}
+#endif /* CONFIG_INTEL_IOMMU */
+
+/*
+ * Set the RID_PASID field of a scalable mode context entry. The
+ * IOMMU hardware will use the PASID value set in this field for
+ * DMA translations of DMA requests without PASID.
+ */
+static inline void
+context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
+{
+	context->hi |= pasid & ((1 << 20) - 1);
+}
+
+/*
+ * Set the DTE(Device-TLB Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_dte(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(2);
+}
+
+/*
+ * Set the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_pre(struct context_entry *context)
+{
+	context->lo |= BIT_ULL(4);
+}
+
+/* Convert value to context PASID directory size field coding. */
+#define context_pdts(pds)	(((pds) & 0x7) << 9)
+
 struct dmar_drhd_unit *dmar_find_matched_drhd_unit(struct pci_dev *dev);
 
 int dmar_enable_qi(struct intel_iommu *iommu);
@@ -907,9 +1088,9 @@ int dmar_ir_support(void);
 void *alloc_pgtable_page(int node, gfp_t gfp);
 void free_pgtable_page(void *vaddr);
 void iommu_flush_write_buffer(struct intel_iommu *iommu);
-struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn);
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
 					       const struct iommu_user_data *user_data);
+struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 void intel_svm_check(struct intel_iommu *iommu);
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index 29b9e55dcf..566297bc87 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1112,7 +1112,7 @@ static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 	 * irq migration in the presence of interrupt-remapping.
 	*/
 	irte->trigger_mode = 0;
-	irte->dlvry_mode = apic->delivery_mode;
+	irte->dlvry_mode = APIC_DELIVERY_MODE_FIXED;
 	irte->vector = vector;
 	irte->dest_id = IRTE_DEST(dest);
 	irte->redir_hint = 1;
diff --git a/drivers/iommu/intel/nested.c b/drivers/iommu/intel/nested.c
index 92e82b33ea..a7d68f3d51 100644
--- a/drivers/iommu/intel/nested.c
+++ b/drivers/iommu/intel/nested.c
@@ -81,9 +81,97 @@ static void intel_nested_domain_free(struct iommu_domain *domain)
 	kfree(dmar_domain);
 }
 
+static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
+				   unsigned int mask)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	u16 sid, qdep;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->ats_enabled)
+			continue;
+		sid = info->bus << 8 | info->devfn;
+		qdep = info->ats_qdep;
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				   qdep, addr, mask);
+		quirk_extra_dev_tlb_flush(info, addr, mask,
+					  IOMMU_NO_PASID, qdep);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr,
+				     u64 npages, bool ih)
+{
+	struct iommu_domain_info *info;
+	unsigned int mask;
+	unsigned long i;
+
+	xa_for_each(&domain->iommu_array, i, info)
+		qi_flush_piotlb(info->iommu,
+				domain_id_iommu(domain, info->iommu),
+				IOMMU_NO_PASID, addr, npages, ih);
+
+	if (!domain->has_iotlb_device)
+		return;
+
+	if (npages == U64_MAX)
+		mask = 64 - VTD_PAGE_SHIFT;
+	else
+		mask = ilog2(__roundup_pow_of_two(npages));
+
+	nested_flush_dev_iotlb(domain, addr, mask);
+}
+
+static int intel_nested_cache_invalidate_user(struct iommu_domain *domain,
+					      struct iommu_user_data_array *array)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct iommu_hwpt_vtd_s1_invalidate inv_entry;
+	u32 index, processed = 0;
+	int ret = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (index = 0; index < array->entry_num; index++) {
+		ret = iommu_copy_struct_from_user_array(&inv_entry, array,
+							IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+							index, __reserved);
+		if (ret)
+			break;
+
+		if ((inv_entry.flags & ~IOMMU_VTD_INV_FLAGS_LEAF) ||
+		    inv_entry.__reserved) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (!IS_ALIGNED(inv_entry.addr, VTD_PAGE_SIZE) ||
+		    ((inv_entry.npages == U64_MAX) && inv_entry.addr)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		intel_nested_flush_cache(dmar_domain, inv_entry.addr,
+					 inv_entry.npages,
+					 inv_entry.flags & IOMMU_VTD_INV_FLAGS_LEAF);
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return ret;
+}
+
 static const struct iommu_domain_ops intel_nested_domain_ops = {
 	.attach_dev		= intel_nested_attach_dev,
 	.free			= intel_nested_domain_free,
+	.cache_invalidate_user	= intel_nested_cache_invalidate_user,
 };
 
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index cc2490e5cf..a51e895d9a 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -26,63 +26,6 @@
  */
 u32 intel_pasid_max_id = PASID_MAX;
 
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	int ret = 0;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		*pasid = VCMD_VRSP_RESULT_PASID(res);
-		break;
-	case VCMD_VRSP_SC_NO_PASID_AVAIL:
-		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
-		ret = -ENOSPC;
-		break;
-	default:
-		ret = -ENODEV;
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-
-	return ret;
-}
-
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
-{
-	unsigned long flags;
-	u8 status_code;
-	u64 res;
-
-	raw_spin_lock_irqsave(&iommu->register_lock, flags);
-	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
-		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
-	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
-		      !(res & VCMD_VRSP_IP), res);
-	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
-
-	status_code = VCMD_VRSP_SC(res);
-	switch (status_code) {
-	case VCMD_VRSP_SC_SUCCESS:
-		break;
-	case VCMD_VRSP_SC_INVALID_PASID:
-		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
-		break;
-	default:
-		pr_warn("IOMMU: %s: Unexpected error code %d\n",
-			iommu->name, status_code);
-	}
-}
-
 /*
  * Per device pasid table management:
  */
@@ -230,30 +173,6 @@ retry:
 /*
  * Interfaces for PASID table entry manipulation:
  */
-static inline void pasid_clear_entry(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], 0);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
-static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
-{
-	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
-	WRITE_ONCE(pe->val[1], 0);
-	WRITE_ONCE(pe->val[2], 0);
-	WRITE_ONCE(pe->val[3], 0);
-	WRITE_ONCE(pe->val[4], 0);
-	WRITE_ONCE(pe->val[5], 0);
-	WRITE_ONCE(pe->val[6], 0);
-	WRITE_ONCE(pe->val[7], 0);
-}
-
 static void
 intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 {
@@ -269,192 +188,6 @@ intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
 		pasid_clear_entry(pe);
 }
 
-static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
-{
-	u64 old;
-
-	old = READ_ONCE(*ptr);
-	WRITE_ONCE(*ptr, (old & ~mask) | bits);
-}
-
-static inline u64 pasid_get_bits(u64 *ptr)
-{
-	return READ_ONCE(*ptr);
-}
-
-/*
- * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_domain_id(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
-}
-
-/*
- * Get domain ID value of a scalable mode PASID entry.
- */
-static inline u16
-pasid_get_domain_id(struct pasid_entry *pe)
-{
-	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
-}
-
-/*
- * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_slptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
- * entry.
- */
-static inline void
-pasid_set_address_width(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
-}
-
-/*
- * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_translation_type(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
-}
-
-/*
- * Enable fault processing by clearing the FPD(Fault Processing
- * Disable) field (Bit 1) of a scalable mode PASID entry.
- */
-static inline void pasid_set_fault_enable(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 1, 0);
-}
-
-/*
- * Enable second level A/D bits by setting the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
-}
-
-/*
- * Disable second level A/D bits by clearing the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_clear_ssade(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 9, 0);
-}
-
-/*
- * Checks if second level A/D bits specifically the SLADE (Second Level
- * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
- * entry is set.
- */
-static inline bool pasid_get_ssade(struct pasid_entry *pe)
-{
-	return pasid_get_bits(&pe->val[0]) & (1 << 9);
-}
-
-/*
- * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_sre(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 0, 1);
-}
-
-/*
- * Setup the WPE(Write Protect Enable) field (Bit 132) of a
- * scalable mode PASID entry.
- */
-static inline void pasid_set_wpe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
-}
-
-/*
- * Setup the P(Present) field (Bit 0) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_present(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[0], 1 << 0, 1);
-}
-
-/*
- * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
- * entry.
- */
-static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
-{
-	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
-}
-
-/*
- * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
- * entry. It is required when XD bit of the first level page table
- * entry is about to be set.
- */
-static inline void pasid_set_nxe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
-}
-
-/*
- * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
- * PASID entry.
- */
-static inline void
-pasid_set_pgsnp(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
-}
-
-/*
- * Setup the First Level Page table Pointer field (Bit 140~191)
- * of a scalable mode PASID entry.
- */
-static inline void
-pasid_set_flptr(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
-}
-
-/*
- * Setup the First Level Paging Mode field (Bit 130~131) of a
- * scalable mode PASID entry.
- */
-static inline void
-pasid_set_flpm(struct pasid_entry *pe, u64 value)
-{
-	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
-}
-
-/*
- * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
- * of a scalable mode PASID entry.
- */
-static inline void pasid_set_eafe(struct pasid_entry *pe)
-{
-	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
-}
-
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, u32 pasid)
@@ -616,9 +349,9 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
  * Skip top levels of page tables for iommu which has less agaw
  * than default. Unnecessary for PT mode.
  */
-static inline int iommu_skip_agaw(struct dmar_domain *domain,
-				  struct intel_iommu *iommu,
-				  struct dma_pte **pgd)
+static int iommu_skip_agaw(struct dmar_domain *domain,
+			   struct intel_iommu *iommu,
+			   struct dma_pte **pgd)
 {
 	int agaw;
 
@@ -769,7 +502,6 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
  * Set up the scalable mode pasid entry for passthrough translation type.
  */
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid)
 {
 	u16 did = FLPT_DEFAULT_DID;
@@ -938,3 +670,67 @@ int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 
 	return 0;
 }
+
+/*
+ * Interfaces to setup or teardown a pasid table to the scalable-mode
+ * context table entry:
+ */
+
+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;
+
+	spin_lock(&iommu->lock);
+	context = iommu_context_addr(iommu, bus, devfn, false);
+	if (!context) {
+		spin_unlock(&iommu->lock);
+		return;
+	}
+
+	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);
+}
+
+static int pci_pasid_table_teardown(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct device *dev = data;
+
+	if (dev == &pdev->dev)
+		device_pasid_table_teardown(dev, PCI_BUS_NUM(alias), alias & 0xff);
+
+	return 0;
+}
+
+void intel_pasid_teardown_sm_context(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+	if (!dev_is_pci(dev)) {
+		device_pasid_table_teardown(dev, info->bus, info->devfn);
+		return;
+	}
+
+	pci_for_each_dma_alias(to_pci_dev(dev), pci_pasid_table_teardown, dev);
+}
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index 3568adca1f..42fda97fd8 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -22,16 +22,6 @@
 #define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
 #define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
 
-/* Virtual command interface for enlightened pasid management. */
-#define VCMD_CMD_ALLOC			0x1
-#define VCMD_CMD_FREE			0x2
-#define VCMD_VRSP_IP			0x1
-#define VCMD_VRSP_SC(e)			(((e) & 0xff) >> 1)
-#define VCMD_VRSP_SC_SUCCESS		0
-#define VCMD_VRSP_SC_NO_PASID_AVAIL	16
-#define VCMD_VRSP_SC_INVALID_PASID	16
-#define VCMD_VRSP_RESULT_PASID(e)	(((e) >> 16) & 0xfffff)
-#define VCMD_CMD_OPERAND(e)		((e) << 16)
 /*
  * Domain ID reserved for pasid entries programmed for first-level
  * only and pass-through transfer modes.
@@ -96,6 +86,216 @@ static inline u16 pasid_pte_get_pgtt(struct pasid_entry *pte)
 	return (u16)((READ_ONCE(pte->val[0]) >> 6) & 0x7);
 }
 
+static inline void pasid_clear_entry(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], 0);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
+{
+	u64 old;
+
+	old = READ_ONCE(*ptr);
+	WRITE_ONCE(*ptr, (old & ~mask) | bits);
+}
+
+static inline u64 pasid_get_bits(u64 *ptr)
+{
+	return READ_ONCE(*ptr);
+}
+
+/*
+ * Setup the DID(Domain Identifier) field (Bit 64~79) of scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_domain_id(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[1], GENMASK_ULL(15, 0), value);
+}
+
+/*
+ * Get domain ID value of a scalable mode PASID entry.
+ */
+static inline u16
+pasid_get_domain_id(struct pasid_entry *pe)
+{
+	return (u16)(READ_ONCE(pe->val[1]) & GENMASK_ULL(15, 0));
+}
+
+/*
+ * Setup the SLPTPTR(Second Level Page Table Pointer) field (Bit 12~63)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_slptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the AW(Address Width) field (Bit 2~4) of a scalable mode PASID
+ * entry.
+ */
+static inline void
+pasid_set_address_width(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(4, 2), value << 2);
+}
+
+/*
+ * Setup the PGTT(PASID Granular Translation Type) field (Bit 6~8)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_translation_type(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[0], GENMASK_ULL(8, 6), value << 6);
+}
+
+/*
+ * Enable fault processing by clearing the FPD(Fault Processing
+ * Disable) field (Bit 1) of a scalable mode PASID entry.
+ */
+static inline void pasid_set_fault_enable(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 1, 0);
+}
+
+/*
+ * Enable second level A/D bits by setting the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 1 << 9);
+}
+
+/*
+ * Disable second level A/D bits by clearing the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_clear_ssade(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 9, 0);
+}
+
+/*
+ * Checks if second level A/D bits specifically the SLADE (Second Level
+ * Access Dirty Enable) field (Bit 9) of a scalable mode PASID
+ * entry is set.
+ */
+static inline bool pasid_get_ssade(struct pasid_entry *pe)
+{
+	return pasid_get_bits(&pe->val[0]) & (1 << 9);
+}
+
+/*
+ * Setup the SRE(Supervisor Request Enable) field (Bit 128) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_sre(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 0, 1);
+}
+
+/*
+ * Setup the WPE(Write Protect Enable) field (Bit 132) of a
+ * scalable mode PASID entry.
+ */
+static inline void pasid_set_wpe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 4, 1 << 4);
+}
+
+/*
+ * Setup the P(Present) field (Bit 0) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_present(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[0], 1 << 0, 1);
+}
+
+/*
+ * Setup Page Walk Snoop bit (Bit 87) of a scalable mode PASID
+ * entry.
+ */
+static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
+{
+	pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
+}
+
+/*
+ * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+ * entry. It is required when XD bit of the first level page table
+ * entry is about to be set.
+ */
+static inline void pasid_set_nxe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+}
+
+/*
+ * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
+ * PASID entry.
+ */
+static inline void
+pasid_set_pgsnp(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[1], 1ULL << 24, 1ULL << 24);
+}
+
+/*
+ * Setup the First Level Page table Pointer field (Bit 140~191)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the First Level Paging Mode field (Bit 130~131) of a
+ * scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flpm(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
+}
+
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
 extern unsigned int intel_pasid_max_id;
 int intel_pasid_alloc_table(struct device *dev);
 void intel_pasid_free_table(struct device *dev);
@@ -110,15 +310,13 @@ int intel_pasid_setup_dirty_tracking(struct intel_iommu *iommu,
 				     struct device *dev, u32 pasid,
 				     bool enabled);
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
-				   struct dmar_domain *domain,
 				   struct device *dev, u32 pasid);
 int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
 			     u32 pasid, struct dmar_domain *domain);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 				 struct device *dev, u32 pasid,
 				 bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
 void intel_pasid_setup_page_snoop_control(struct intel_iommu *iommu,
 					  struct device *dev, u32 pasid);
+void intel_pasid_teardown_sm_context(struct device *dev);
 #endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c
index cf43e798ec..44083d0185 100644
--- a/drivers/iommu/intel/perfmon.c
+++ b/drivers/iommu/intel/perfmon.c
@@ -438,7 +438,7 @@ static int iommu_pmu_assign_event(struct iommu_pmu *iommu_pmu,
 	iommu_pmu_set_filter(domain, event->attr.config1,
 			     IOMMU_PMU_FILTER_DOMAIN, idx,
 			     event->attr.config1);
-	iommu_pmu_set_filter(pasid, event->attr.config1,
+	iommu_pmu_set_filter(pasid, event->attr.config2,
 			     IOMMU_PMU_FILTER_PASID, idx,
 			     event->attr.config1);
 	iommu_pmu_set_filter(ats, event->attr.config2,
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index ac12f76c12..4d269df008 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -67,7 +67,7 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 	struct page *pages;
 	int irq, ret;
 
-	pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, PRQ_ORDER);
+	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO, PRQ_ORDER);
 	if (!pages) {
 		pr_warn("IOMMU: %s: Failed to allocate page request queue\n",
 			iommu->name);
@@ -316,21 +316,22 @@ out:
 }
 
 static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
-			     struct mm_struct *mm)
+			     struct iommu_domain *domain, ioasid_t pasid)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct mm_struct *mm = domain->mm;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm;
 	unsigned long sflags;
 	int ret = 0;
 
-	svm = pasid_private_find(mm->pasid);
+	svm = pasid_private_find(pasid);
 	if (!svm) {
 		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
 		if (!svm)
 			return -ENOMEM;
 
-		svm->pasid = mm->pasid;
+		svm->pasid = pasid;
 		svm->mm = mm;
 		INIT_LIST_HEAD_RCU(&svm->devs);
 
@@ -368,7 +369,7 @@ static int intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev,
 
 	/* Setup the pasid table: */
 	sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0;
-	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid,
+	ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, pasid,
 					    FLPT_DEFAULT_DID, sflags);
 	if (ret)
 		goto free_sdev;
@@ -382,7 +383,7 @@ free_sdev:
 free_svm:
 	if (list_empty(&svm->devs)) {
 		mmu_notifier_unregister(&svm->notifier, mm);
-		pasid_private_remove(mm->pasid);
+		pasid_private_remove(pasid);
 		kfree(svm);
 	}
 
@@ -392,14 +393,9 @@ free_svm:
 void intel_svm_remove_dev_pasid(struct device *dev, u32 pasid)
 {
 	struct intel_svm_dev *sdev;
-	struct intel_iommu *iommu;
 	struct intel_svm *svm;
 	struct mm_struct *mm;
 
-	iommu = device_to_iommu(dev, NULL, NULL);
-	if (!iommu)
-		return;
-
 	if (pasid_to_svm_sdev(dev, pasid, &svm, &sdev))
 		return;
 	mm = svm->mm;
@@ -654,7 +650,7 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 	struct intel_iommu *iommu = d;
 	struct page_req_dsc *req;
 	int head, tail, handled;
-	struct pci_dev *pdev;
+	struct device *dev;
 	u64 address;
 
 	/*
@@ -700,23 +696,24 @@ bad_req:
 		if (unlikely(req->lpig && !req->rd_req && !req->wr_req))
 			goto prq_advance;
 
-		pdev = pci_get_domain_bus_and_slot(iommu->segment,
-						   PCI_BUS_NUM(req->rid),
-						   req->rid & 0xff);
 		/*
 		 * If prq is to be handled outside iommu driver via receiver of
 		 * the fault notifiers, we skip the page response here.
 		 */
-		if (!pdev)
+		mutex_lock(&iommu->iopf_lock);
+		dev = device_rbtree_find(iommu, req->rid);
+		if (!dev) {
+			mutex_unlock(&iommu->iopf_lock);
 			goto bad_req;
+		}
 
-		if (intel_svm_prq_report(iommu, &pdev->dev, req))
+		if (intel_svm_prq_report(iommu, dev, req))
 			handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
 		else
-			trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1,
+			trace_prq_report(iommu, dev, req->qw_0, req->qw_1,
 					 req->priv_data[0], req->priv_data[1],
 					 iommu->prq_seq_number++);
-		pci_dev_put(pdev);
+		mutex_unlock(&iommu->iopf_lock);
 prq_advance:
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
@@ -750,25 +747,16 @@ int intel_svm_page_response(struct device *dev,
 			    struct iommu_fault_event *evt,
 			    struct iommu_page_response *msg)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	u8 bus = info->bus, devfn = info->devfn;
 	struct iommu_fault_page_request *prm;
-	struct intel_iommu *iommu;
 	bool private_present;
 	bool pasid_present;
 	bool last_page;
-	u8 bus, devfn;
 	int ret = 0;
 	u16 sid;
 
-	if (!dev || !dev_is_pci(dev))
-		return -ENODEV;
-
-	iommu = device_to_iommu(dev, &bus, &devfn);
-	if (!iommu)
-		return -ENODEV;
-
-	if (!msg || !evt)
-		return -EINVAL;
-
 	prm = &evt->fault.prm;
 	sid = PCI_DEVID(bus, devfn);
 	pasid_present = prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
@@ -822,9 +810,8 @@ static int intel_svm_set_dev_pasid(struct iommu_domain *domain,
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
-	struct mm_struct *mm = domain->mm;
 
-	return intel_svm_bind_mm(iommu, dev, mm);
+	return intel_svm_bind_mm(iommu, dev, domain, pasid);
 }
 
 static void intel_svm_domain_free(struct iommu_domain *domain)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 72dcdd468c..f7828a7aad 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -188,20 +188,28 @@ static dma_addr_t __arm_lpae_dma_addr(void *pages)
 }
 
 static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
-				    struct io_pgtable_cfg *cfg)
+				    struct io_pgtable_cfg *cfg,
+				    void *cookie)
 {
 	struct device *dev = cfg->iommu_dev;
 	int order = get_order(size);
-	struct page *p;
 	dma_addr_t dma;
 	void *pages;
 
 	VM_BUG_ON((gfp & __GFP_HIGHMEM));
-	p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
-	if (!p)
+
+	if (cfg->alloc) {
+		pages = cfg->alloc(cookie, size, gfp);
+	} else {
+		struct page *p;
+
+		p = alloc_pages_node(dev_to_node(dev), gfp | __GFP_ZERO, order);
+		pages = p ? page_address(p) : NULL;
+	}
+
+	if (!pages)
 		return NULL;
 
-	pages = page_address(p);
 	if (!cfg->coherent_walk) {
 		dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -220,18 +228,28 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 out_unmap:
 	dev_err(dev, "Cannot accommodate DMA translation for IOMMU page tables\n");
 	dma_unmap_single(dev, dma, size, DMA_TO_DEVICE);
+
 out_free:
-	__free_pages(p, order);
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, order);
+
 	return NULL;
 }
 
 static void __arm_lpae_free_pages(void *pages, size_t size,
-				  struct io_pgtable_cfg *cfg)
+				  struct io_pgtable_cfg *cfg,
+				  void *cookie)
 {
 	if (!cfg->coherent_walk)
 		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
-	free_pages((unsigned long)pages, get_order(size));
+
+	if (cfg->free)
+		cfg->free(cookie, pages, size);
+	else
+		free_pages((unsigned long)pages, get_order(size));
 }
 
 static void __arm_lpae_sync_pte(arm_lpae_iopte *ptep, int num_entries,
@@ -373,13 +391,13 @@ static int __arm_lpae_map(struct arm_lpae_io_pgtable *data, unsigned long iova,
 	/* Grab a pointer to the next level */
 	pte = READ_ONCE(*ptep);
 	if (!pte) {
-		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg);
+		cptep = __arm_lpae_alloc_pages(tblsz, gfp, cfg, data->iop.cookie);
 		if (!cptep)
 			return -ENOMEM;
 
 		pte = arm_lpae_install_table(cptep, ptep, 0, data);
 		if (pte)
-			__arm_lpae_free_pages(cptep, tblsz, cfg);
+			__arm_lpae_free_pages(cptep, tblsz, cfg, data->iop.cookie);
 	} else if (!cfg->coherent_walk && !(pte & ARM_LPAE_PTE_SW_SYNC)) {
 		__arm_lpae_sync_pte(ptep, 1, cfg);
 	}
@@ -524,7 +542,7 @@ static void __arm_lpae_free_pgtable(struct arm_lpae_io_pgtable *data, int lvl,
 		__arm_lpae_free_pgtable(data, lvl + 1, iopte_deref(pte, data));
 	}
 
-	__arm_lpae_free_pages(start, table_size, &data->iop.cfg);
+	__arm_lpae_free_pages(start, table_size, &data->iop.cfg, data->iop.cookie);
 }
 
 static void arm_lpae_free_pgtable(struct io_pgtable *iop)
@@ -552,7 +570,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 	if (WARN_ON(lvl == ARM_LPAE_MAX_LEVELS))
 		return 0;
 
-	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg);
+	tablep = __arm_lpae_alloc_pages(tablesz, GFP_ATOMIC, cfg, data->iop.cookie);
 	if (!tablep)
 		return 0; /* Bytes unmapped */
 
@@ -575,7 +593,7 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 
 	pte = arm_lpae_install_table(tablep, ptep, blk_pte, data);
 	if (pte != blk_pte) {
-		__arm_lpae_free_pages(tablep, tablesz, cfg);
+		__arm_lpae_free_pages(tablep, tablesz, cfg, data->iop.cookie);
 		/*
 		 * We may race against someone unmapping another part of this
 		 * block, but anything else is invalid. We can't misinterpret
@@ -882,7 +900,7 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Looking good; allocate a pgd */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -984,7 +1002,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 
 	/* Allocate pgd pages */
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data),
-					   GFP_KERNEL, cfg);
+					   GFP_KERNEL, cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1059,7 +1077,7 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 		 << ARM_LPAE_MAIR_ATTR_SHIFT(ARM_LPAE_MAIR_ATTR_IDX_DEV));
 
 	data->pgd = __arm_lpae_alloc_pages(ARM_LPAE_PGD_SIZE(data), GFP_KERNEL,
-					   cfg);
+					   cfg, cookie);
 	if (!data->pgd)
 		goto out_free_data;
 
@@ -1080,26 +1098,31 @@ out_free_data:
 }
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_64_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_64_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s1,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s2_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_32_lpae_alloc_pgtable_s2,
 	.free	= arm_lpae_free_pgtable,
 };
 
 struct io_pgtable_init_fns io_pgtable_arm_mali_lpae_init_fns = {
+	.caps	= IO_PGTABLE_CAP_CUSTOM_ALLOCATOR,
 	.alloc	= arm_mali_lpae_alloc_pgtable,
 	.free	= arm_lpae_free_pgtable,
 };
diff --git a/drivers/iommu/io-pgtable.c b/drivers/iommu/io-pgtable.c
index b843fcd365..8841c1487f 100644
--- a/drivers/iommu/io-pgtable.c
+++ b/drivers/iommu/io-pgtable.c
@@ -34,6 +34,26 @@ io_pgtable_init_table[IO_PGTABLE_NUM_FMTS] = {
 #endif
 };
 
+static int check_custom_allocator(enum io_pgtable_fmt fmt,
+				  struct io_pgtable_cfg *cfg)
+{
+	/* No custom allocator, no need to check the format. */
+	if (!cfg->alloc && !cfg->free)
+		return 0;
+
+	/* When passing a custom allocator, both the alloc and free
+	 * functions should be provided.
+	 */
+	if (!cfg->alloc || !cfg->free)
+		return -EINVAL;
+
+	/* Make sure the format supports custom allocators. */
+	if (io_pgtable_init_table[fmt]->caps & IO_PGTABLE_CAP_CUSTOM_ALLOCATOR)
+		return 0;
+
+	return -EINVAL;
+}
+
 struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 					    struct io_pgtable_cfg *cfg,
 					    void *cookie)
@@ -44,6 +64,9 @@ struct io_pgtable_ops *alloc_io_pgtable_ops(enum io_pgtable_fmt fmt,
 	if (fmt >= IO_PGTABLE_NUM_FMTS)
 		return NULL;
 
+	if (check_custom_allocator(fmt, cfg))
+		return NULL;
+
 	fns = io_pgtable_init_table[fmt];
 	if (!fns)
 		return NULL;
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 4a2f569974..65814cbc84 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -12,32 +12,43 @@
 static DEFINE_MUTEX(iommu_sva_lock);
 
 /* Allocate a PASID for the mm within range (inclusive) */
-static int iommu_sva_alloc_pasid(struct mm_struct *mm, struct device *dev)
+static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct device *dev)
 {
+	struct iommu_mm_data *iommu_mm;
 	ioasid_t pasid;
-	int ret = 0;
+
+	lockdep_assert_held(&iommu_sva_lock);
 
 	if (!arch_pgtable_dma_compat(mm))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
-	mutex_lock(&iommu_sva_lock);
+	iommu_mm = mm->iommu_mm;
 	/* Is a PASID already associated with this mm? */
-	if (mm_valid_pasid(mm)) {
-		if (mm->pasid >= dev->iommu->max_pasids)
-			ret = -EOVERFLOW;
-		goto out;
+	if (iommu_mm) {
+		if (iommu_mm->pasid >= dev->iommu->max_pasids)
+			return ERR_PTR(-EOVERFLOW);
+		return iommu_mm;
 	}
 
+	iommu_mm = kzalloc(sizeof(struct iommu_mm_data), GFP_KERNEL);
+	if (!iommu_mm)
+		return ERR_PTR(-ENOMEM);
+
 	pasid = iommu_alloc_global_pasid(dev);
 	if (pasid == IOMMU_PASID_INVALID) {
-		ret = -ENOSPC;
-		goto out;
+		kfree(iommu_mm);
+		return ERR_PTR(-ENOSPC);
 	}
-	mm->pasid = pasid;
-	ret = 0;
-out:
-	mutex_unlock(&iommu_sva_lock);
-	return ret;
+	iommu_mm->pasid = pasid;
+	INIT_LIST_HEAD(&iommu_mm->sva_domains);
+	INIT_LIST_HEAD(&iommu_mm->sva_handles);
+	/*
+	 * Make sure the write to mm->iommu_mm is not reordered in front of
+	 * initialization to iommu_mm fields. If it does, readers may see a
+	 * valid iommu_mm with uninitialized values.
+	 */
+	smp_store_release(&mm->iommu_mm, iommu_mm);
+	return iommu_mm;
 }
 
 /**
@@ -58,57 +69,70 @@ out:
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
 	int ret;
 
+	mutex_lock(&iommu_sva_lock);
+
 	/* Allocate mm->pasid if necessary. */
-	ret = iommu_sva_alloc_pasid(mm, dev);
-	if (ret)
-		return ERR_PTR(ret);
+	iommu_mm = iommu_alloc_mm_data(mm, dev);
+	if (IS_ERR(iommu_mm)) {
+		ret = PTR_ERR(iommu_mm);
+		goto out_unlock;
+	}
 
-	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return ERR_PTR(-ENOMEM);
+	list_for_each_entry(handle, &mm->iommu_mm->sva_handles, handle_item) {
+		if (handle->dev == dev) {
+			refcount_inc(&handle->users);
+			mutex_unlock(&iommu_sva_lock);
+			return handle;
+		}
+	}
 
-	mutex_lock(&iommu_sva_lock);
-	/* Search for an existing domain. */
-	domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid,
-						IOMMU_DOMAIN_SVA);
-	if (IS_ERR(domain)) {
-		ret = PTR_ERR(domain);
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle) {
+		ret = -ENOMEM;
 		goto out_unlock;
 	}
 
-	if (domain) {
-		domain->users++;
-		goto out;
+	/* Search for an existing domain. */
+	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+		if (!ret) {
+			domain->users++;
+			goto out;
+		}
 	}
 
 	/* Allocate a new domain and set it on device pasid. */
 	domain = iommu_sva_domain_alloc(dev, mm);
 	if (!domain) {
 		ret = -ENOMEM;
-		goto out_unlock;
+		goto out_free_handle;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
+	list_add(&domain->next, &mm->iommu_mm->sva_domains);
+
 out:
+	refcount_set(&handle->users, 1);
+	list_add(&handle->handle_item, &mm->iommu_mm->sva_handles);
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
 	handle->domain = domain;
-
 	return handle;
 
 out_free_domain:
 	iommu_domain_free(domain);
+out_free_handle:
+	kfree(handle);
 out_unlock:
 	mutex_unlock(&iommu_sva_lock);
-	kfree(handle);
-
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
@@ -124,12 +148,19 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
 	struct iommu_domain *domain = handle->domain;
-	ioasid_t pasid = domain->mm->pasid;
+	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
 	mutex_lock(&iommu_sva_lock);
+	if (!refcount_dec_and_test(&handle->users)) {
+		mutex_unlock(&iommu_sva_lock);
+		return;
+	}
+	list_del(&handle->handle_item);
+
+	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
-		iommu_detach_device_pasid(domain, dev, pasid);
+		list_del(&domain->next);
 		iommu_domain_free(domain);
 	}
 	mutex_unlock(&iommu_sva_lock);
@@ -205,8 +236,11 @@ out_put_mm:
 
 void mm_pasid_drop(struct mm_struct *mm)
 {
-	if (likely(!mm_valid_pasid(mm)))
+	struct iommu_mm_data *iommu_mm = mm->iommu_mm;
+
+	if (!iommu_mm)
 		return;
 
-	iommu_free_global_pasid(mm->pasid);
+	iommu_free_global_pasid(iommu_mm->pasid);
+	kfree(iommu_mm);
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 33e2a9b5d3..ad33161f23 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -148,7 +148,7 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 static LIST_HEAD(iommu_device_list);
 static DEFINE_SPINLOCK(iommu_device_lock);
 
-static struct bus_type * const iommu_buses[] = {
+static const struct bus_type * const iommu_buses[] = {
 	&platform_bus_type,
 #ifdef CONFIG_PCI
 	&pci_bus_type,
@@ -257,13 +257,6 @@ int iommu_device_register(struct iommu_device *iommu,
 	/* We need to be able to take module references appropriately */
 	if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner))
 		return -EINVAL;
-	/*
-	 * Temporarily enforce global restriction to a single driver. This was
-	 * already the de-facto behaviour, since any possible combination of
-	 * existing drivers would compete for at least the PCI or platform bus.
-	 */
-	if (iommu_buses[0]->iommu_ops && iommu_buses[0]->iommu_ops != ops)
-		return -EBUSY;
 
 	iommu->ops = ops;
 	if (hwdev)
@@ -273,10 +266,8 @@ int iommu_device_register(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) {
-		iommu_buses[i]->iommu_ops = ops;
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++)
 		err = bus_iommu_probe(iommu_buses[i]);
-	}
 	if (err)
 		iommu_device_unregister(iommu);
 	return err;
@@ -329,7 +320,6 @@ int iommu_device_register_bus(struct iommu_device *iommu,
 	list_add_tail(&iommu->list, &iommu_device_list);
 	spin_unlock(&iommu_device_lock);
 
-	bus->iommu_ops = ops;
 	err = bus_iommu_probe(bus);
 	if (err) {
 		iommu_device_unregister_bus(iommu, bus, nb);
@@ -344,6 +334,8 @@ static struct dev_iommu *dev_iommu_get(struct device *dev)
 {
 	struct dev_iommu *param = dev->iommu;
 
+	lockdep_assert_held(&iommu_probe_device_lock);
+
 	if (param)
 		return param;
 
@@ -368,6 +360,15 @@ static void dev_iommu_free(struct device *dev)
 	kfree(param);
 }
 
+/*
+ * Internal equivalent of device_iommu_mapped() for when we care that a device
+ * actually has API ops, and don't want false positives from VFIO-only groups.
+ */
+static bool dev_has_iommu(struct device *dev)
+{
+	return dev->iommu && dev->iommu->iommu_dev;
+}
+
 static u32 dev_iommu_get_max_pasids(struct device *dev)
 {
 	u32 max_pasids = 0, bits = 0;
@@ -386,6 +387,15 @@ static u32 dev_iommu_get_max_pasids(struct device *dev)
 	return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids);
 }
 
+void dev_iommu_priv_set(struct device *dev, void *priv)
+{
+	/* FSL_PAMU does something weird */
+	if (!IS_ENABLED(CONFIG_FSL_PAMU))
+		lockdep_assert_held(&iommu_probe_device_lock);
+	dev->iommu->priv = priv;
+}
+EXPORT_SYMBOL_GPL(dev_iommu_priv_set);
+
 /*
  * Init the dev->iommu and dev->iommu_group in the struct device and get the
  * driver probed
@@ -453,13 +463,24 @@ static void iommu_deinit_device(struct device *dev)
 
 	/*
 	 * release_device() must stop using any attached domain on the device.
-	 * If there are still other devices in the group they are not effected
+	 * If there are still other devices in the group, they are not affected
 	 * by this callback.
 	 *
-	 * The IOMMU driver must set the device to either an identity or
-	 * blocking translation and stop using any domain pointer, as it is
-	 * going to be freed.
+	 * If the iommu driver provides release_domain, the core code ensures
+	 * that domain is attached prior to calling release_device. Drivers can
+	 * use this to enforce a translation on the idle iommu. Typically, the
+	 * global static blocked_domain is a good choice.
+	 *
+	 * Otherwise, the iommu driver must set the device to either an identity
+	 * or a blocking translation in release_device() and stop using any
+	 * domain pointer, as it is going to be freed.
+	 *
+	 * Regardless, if a delayed attach never occurred, then the release
+	 * should still avoid touching any hardware configuration either.
 	 */
+	if (!dev->iommu->attach_deferred && ops->release_domain)
+		ops->release_domain->ops->attach_dev(ops->release_domain, dev);
+
 	if (ops->release_device)
 		ops->release_device(dev);
 
@@ -489,11 +510,26 @@ DEFINE_MUTEX(iommu_probe_device_lock);
 
 static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
-	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	const struct iommu_ops *ops;
+	struct iommu_fwspec *fwspec;
 	struct iommu_group *group;
 	struct group_device *gdev;
 	int ret;
 
+	/*
+	 * For FDT-based systems and ACPI IORT/VIOT, drivers register IOMMU
+	 * instances with non-NULL fwnodes, and client devices should have been
+	 * identified with a fwspec by this point. Otherwise, we can currently
+	 * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can
+	 * be present, and that any of their registered instances has suitable
+	 * ops for probing, and thus cheekily co-opt the same mechanism.
+	 */
+	fwspec = dev_iommu_fwspec_get(dev);
+	if (fwspec && fwspec->ops)
+		ops = fwspec->ops;
+	else
+		ops = iommu_ops_from_fwnode(NULL);
+
 	if (!ops)
 		return -ENODEV;
 	/*
@@ -618,7 +654,7 @@ static void __iommu_group_remove_device(struct device *dev)
 
 		list_del(&device->list);
 		__iommu_group_free_device(group, device);
-		if (dev->iommu && dev->iommu->iommu_dev)
+		if (dev_has_iommu(dev))
 			iommu_deinit_device(dev);
 		else
 			dev->iommu_group = NULL;
@@ -817,7 +853,7 @@ int iommu_get_group_resv_regions(struct iommu_group *group,
 		 * Non-API groups still expose reserved_regions in sysfs,
 		 * so filter out calls that get here that way.
 		 */
-		if (!device->dev->iommu)
+		if (!dev_has_iommu(device->dev))
 			break;
 
 		INIT_LIST_HEAD(&dev_resv_regions);
@@ -1223,6 +1259,12 @@ void iommu_group_remove_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
+static struct device *iommu_group_first_dev(struct iommu_group *group)
+{
+	lockdep_assert_held(&group->mutex);
+	return list_first_entry(&group->devices, struct group_device, list)->dev;
+}
+
 /**
  * iommu_group_for_each_dev - iterate over each device in the group
  * @group: the group
@@ -1751,30 +1793,13 @@ __iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 }
 
 /*
- * Returns the iommu_ops for the devices in an iommu group.
- *
- * It is assumed that all devices in an iommu group are managed by a single
- * IOMMU unit. Therefore, this returns the dev_iommu_ops of the first device
- * in the group.
- */
-static const struct iommu_ops *group_iommu_ops(struct iommu_group *group)
-{
-	struct group_device *device =
-		list_first_entry(&group->devices, struct group_device, list);
-
-	lockdep_assert_held(&group->mutex);
-
-	return dev_iommu_ops(device->dev);
-}
-
-/*
  * req_type of 0 means "auto" which means to select a domain based on
  * iommu_def_domain_type or what the driver actually supports.
  */
 static struct iommu_domain *
 iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(iommu_group_first_dev(group));
 	struct iommu_domain *dom;
 
 	lockdep_assert_held(&group->mutex);
@@ -1785,7 +1810,7 @@ iommu_group_alloc_default_domain(struct iommu_group *group, int req_type)
 	 * domain. Do not use in new drivers.
 	 */
 	if (ops->default_domain) {
-		if (req_type)
+		if (req_type != ops->default_domain->type)
 			return ERR_PTR(-EINVAL);
 		return ops->default_domain;
 	}
@@ -1854,13 +1879,21 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 static int iommu_get_def_domain_type(struct iommu_group *group,
 				     struct device *dev, int cur_type)
 {
-	const struct iommu_ops *ops = group_iommu_ops(group);
+	const struct iommu_ops *ops = dev_iommu_ops(dev);
 	int type;
 
-	if (!ops->def_domain_type)
-		return cur_type;
-
-	type = ops->def_domain_type(dev);
+	if (ops->default_domain) {
+		/*
+		 * Drivers that declare a global static default_domain will
+		 * always choose that.
+		 */
+		type = ops->default_domain->type;
+	} else {
+		if (ops->def_domain_type)
+			type = ops->def_domain_type(dev);
+		else
+			return cur_type;
+	}
 	if (!type || cur_type == type)
 		return cur_type;
 	if (!cur_type)
@@ -2003,9 +2036,28 @@ int bus_iommu_probe(const struct bus_type *bus)
 	return 0;
 }
 
+/**
+ * iommu_present() - make platform-specific assumptions about an IOMMU
+ * @bus: bus to check
+ *
+ * Do not use this function. You want device_iommu_mapped() instead.
+ *
+ * Return: true if some IOMMU is present and aware of devices on the given bus;
+ * in general it may not be the only IOMMU, and it may not have anything to do
+ * with whatever device you are ultimately interested in.
+ */
 bool iommu_present(const struct bus_type *bus)
 {
-	return bus->iommu_ops != NULL;
+	bool ret = false;
+
+	for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) {
+		if (iommu_buses[i] == bus) {
+			spin_lock(&iommu_device_lock);
+			ret = !list_empty(&iommu_device_list);
+			spin_unlock(&iommu_device_lock);
+		}
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_present);
 
@@ -2021,7 +2073,7 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 {
 	const struct iommu_ops *ops;
 
-	if (!dev->iommu || !dev->iommu->iommu_dev)
+	if (!dev_has_iommu(dev))
 		return false;
 
 	ops = dev_iommu_ops(dev);
@@ -2107,6 +2159,7 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 		return ERR_PTR(-ENOMEM);
 
 	domain->type = type;
+	domain->owner = ops;
 	/*
 	 * If not already set, assume all sizes by default; the driver
 	 * may override this later
@@ -2132,21 +2185,37 @@ static struct iommu_domain *__iommu_domain_alloc(const struct iommu_ops *ops,
 static struct iommu_domain *
 __iommu_group_domain_alloc(struct iommu_group *group, unsigned int type)
 {
-	struct device *dev =
-		list_first_entry(&group->devices, struct group_device, list)
-			->dev;
+	struct device *dev = iommu_group_first_dev(group);
+
+	return __iommu_domain_alloc(dev_iommu_ops(dev), dev, type);
+}
+
+static int __iommu_domain_alloc_dev(struct device *dev, void *data)
+{
+	const struct iommu_ops **ops = data;
 
-	return __iommu_domain_alloc(group_iommu_ops(group), dev, type);
+	if (!dev_has_iommu(dev))
+		return 0;
+
+	if (WARN_ONCE(*ops && *ops != dev_iommu_ops(dev),
+		      "Multiple IOMMU drivers present for bus %s, which the public IOMMU API can't fully support yet. You will still need to disable one or more for this to work, sorry!\n",
+		      dev_bus_name(dev)))
+		return -EBUSY;
+
+	*ops = dev_iommu_ops(dev);
+	return 0;
 }
 
 struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
 {
+	const struct iommu_ops *ops = NULL;
+	int err = bus_for_each_dev(bus, NULL, &ops, __iommu_domain_alloc_dev);
 	struct iommu_domain *domain;
 
-	if (bus == NULL || bus->iommu_ops == NULL)
+	if (err || !ops)
 		return NULL;
-	domain = __iommu_domain_alloc(bus->iommu_ops, NULL,
-				    IOMMU_DOMAIN_UNMANAGED);
+
+	domain = __iommu_domain_alloc(ops, NULL, IOMMU_DOMAIN_UNMANAGED);
 	if (IS_ERR(domain))
 		return NULL;
 	return domain;
@@ -2284,10 +2353,16 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev)
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group)
 {
+	struct device *dev;
+
 	if (group->domain && group->domain != group->default_domain &&
 	    group->domain != group->blocking_domain)
 		return -EBUSY;
 
+	dev = iommu_group_first_dev(group);
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner)
+		return -EINVAL;
+
 	return __iommu_group_set_domain(group, domain);
 }
 
@@ -3004,8 +3079,8 @@ EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
  */
 int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+	if (dev_has_iommu(dev)) {
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_enable_feat)
 			return ops->dev_enable_feat(dev, feat);
@@ -3020,8 +3095,8 @@ EXPORT_SYMBOL_GPL(iommu_dev_enable_feature);
  */
 int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
 {
-	if (dev->iommu && dev->iommu->iommu_dev) {
-		const struct iommu_ops *ops = dev->iommu->iommu_dev->ops;
+	if (dev_has_iommu(dev)) {
+		const struct iommu_ops *ops = dev_iommu_ops(dev);
 
 		if (ops->dev_disable_feat)
 			return ops->dev_disable_feat(dev, feat);
@@ -3472,6 +3547,7 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 {
 	/* Caller must be a probed driver on dev */
 	struct iommu_group *group = dev->iommu_group;
+	struct group_device *device;
 	void *curr;
 	int ret;
 
@@ -3481,7 +3557,18 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	if (!group)
 		return -ENODEV;
 
+	if (!dev_has_iommu(dev) || dev_iommu_ops(dev) != domain->owner ||
+	    pasid == IOMMU_NO_PASID)
+		return -EINVAL;
+
 	mutex_lock(&group->mutex);
+	for_each_group_device(group, device) {
+		if (pasid >= device->dev->iommu->max_pasids) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+	}
+
 	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
 	if (curr) {
 		ret = xa_err(curr) ? : -EBUSY;
@@ -3569,6 +3656,7 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
 	domain->type = IOMMU_DOMAIN_SVA;
 	mmgrab(mm);
 	domain->mm = mm;
+	domain->owner = ops;
 	domain->iopf_handler = iommu_sva_handle_iopf;
 	domain->fault_data = mm;
 
diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig
index 99d4b075df..76656fe047 100644
--- a/drivers/iommu/iommufd/Kconfig
+++ b/drivers/iommu/iommufd/Kconfig
@@ -37,6 +37,7 @@ config IOMMUFD_TEST
 	depends on DEBUG_KERNEL
 	depends on FAULT_INJECTION
 	depends on RUNTIME_TESTING_MENU
+	select IOMMUFD_DRIVER
 	default n
 	help
 	  This is dangerous, do not enable unless running
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 6f680959b2..33d142f805 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -135,6 +135,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			hwpt->domain = NULL;
 			goto out_abort;
 		}
+		hwpt->domain->owner = ops;
 	} else {
 		hwpt->domain = iommu_domain_alloc(idev->dev->bus);
 		if (!hwpt->domain) {
@@ -233,6 +234,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 		hwpt->domain = NULL;
 		goto out_abort;
 	}
+	hwpt->domain->owner = ops;
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;
@@ -372,3 +374,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
+
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
+	struct iommu_user_data_array data_array = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.entry_len = cmd->entry_len,
+		.entry_num = cmd->entry_num,
+	};
+	struct iommufd_hw_pagetable *hwpt;
+	u32 done_num = 0;
+	int rc;
+
+	if (cmd->__reserved) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt)) {
+		rc = PTR_ERR(hwpt);
+		goto out;
+	}
+
+	rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain,
+						      &data_array);
+	done_num = data_array.entry_num;
+
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+out:
+	cmd->entry_num = done_num;
+	if (iommufd_ucmd_respond(ucmd, sizeof(*cmd)))
+		return -EFAULT;
+	return rc;
+}
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index abae041e25..991f864d1f 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
 					       IOMMUFD_OBJ_HWPT_PAGING),
 			    struct iommufd_hwpt_paging, common.obj);
 }
+
+static inline struct iommufd_hw_pagetable *
+iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_NESTED),
+			    struct iommufd_hw_pagetable, obj);
+}
+
 int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
 int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
 
@@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
 void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
 void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)
diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 7910fbe196..e854d3f672 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -21,6 +21,7 @@ enum {
 	IOMMU_TEST_OP_ACCESS_REPLACE_IOAS,
 	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
 	IOMMU_TEST_OP_DIRTY,
+	IOMMU_TEST_OP_MD_CHECK_IOTLB,
 };
 
 enum {
@@ -44,6 +45,7 @@ enum {
 
 enum {
 	MOCK_FLAGS_DEVICE_NO_DIRTY = 1 << 0,
+	MOCK_FLAGS_DEVICE_HUGE_IOVA = 1 << 1,
 };
 
 enum {
@@ -121,6 +123,10 @@ struct iommu_test_cmd {
 			__aligned_u64 uptr;
 			__aligned_u64 out_nr_dirty;
 		} dirty;
+		struct {
+			__u32 id;
+			__u32 iotlb;
+		} check_iotlb;
 	};
 	__u32 last;
 };
@@ -148,4 +154,22 @@ struct iommu_hwpt_selftest {
 	__u32 iotlb;
 };
 
+/* Should not be equal to any defined value in enum iommu_hwpt_invalidate_data_type */
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST 0xdeadbeef
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef
+
+/**
+ * struct iommu_hwpt_invalidate_selftest - Invalidation data for Mock driver
+ *                                         (IOMMU_HWPT_INVALIDATE_DATA_SELFTEST)
+ * @flags: Invalidate flags
+ * @iotlb_id: Invalidate iotlb entry index
+ *
+ * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @iotlb_id will be ignored
+ */
+struct iommu_hwpt_invalidate_selftest {
+#define IOMMU_TEST_INVALIDATE_FLAG_ALL	(1 << 0)
+	__u32 flags;
+	__u32 iotlb_id;
+};
+
 #endif
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index c9091e46d2..39b32932c6 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -322,6 +322,7 @@ union ucmd_buffer {
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_invalidate cache;
 	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
@@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
+		 struct iommu_hwpt_invalidate, __reserved),
 	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
 		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index d437ffb715..7a2199470f 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -25,9 +25,23 @@ static struct iommu_domain_ops domain_nested_ops;
 
 size_t iommufd_test_memory_limit = 65536;
 
+struct mock_bus_type {
+	struct bus_type bus;
+	struct notifier_block nb;
+};
+
+static struct mock_bus_type iommufd_mock_bus_type = {
+	.bus = {
+		.name = "iommufd_mock",
+	},
+};
+
+static DEFINE_IDA(mock_dev_ida);
+
 enum {
 	MOCK_DIRTY_TRACK = 1,
 	MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2,
+	MOCK_HUGE_PAGE_SIZE = 512 * MOCK_IO_PAGE_SIZE,
 
 	/*
 	 * Like a real page table alignment requires the low bits of the address
@@ -40,6 +54,7 @@ enum {
 	MOCK_PFN_START_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_LAST_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1,
+	MOCK_PFN_HUGE_IOVA = _MOCK_PFN_START << 2,
 };
 
 /*
@@ -123,6 +138,7 @@ enum selftest_obj_type {
 struct mock_dev {
 	struct device dev;
 	unsigned long flags;
+	int id;
 };
 
 struct selftest_obj {
@@ -193,6 +209,34 @@ static int mock_domain_set_dirty_tracking(struct iommu_domain *domain,
 	return 0;
 }
 
+static bool mock_test_and_clear_dirty(struct mock_iommu_domain *mock,
+				      unsigned long iova, size_t page_size,
+				      unsigned long flags)
+{
+	unsigned long cur, end = iova + page_size - 1;
+	bool dirty = false;
+	void *ent, *old;
+
+	for (cur = iova; cur < end; cur += MOCK_IO_PAGE_SIZE) {
+		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
+		if (!ent || !(xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA))
+			continue;
+
+		dirty = true;
+		/* Clear dirty */
+		if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
+			unsigned long val;
+
+			val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
+			old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE,
+				       xa_mk_value(val), GFP_KERNEL);
+			WARN_ON_ONCE(ent != old);
+		}
+	}
+
+	return dirty;
+}
+
 static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 					    unsigned long iova, size_t size,
 					    unsigned long flags,
@@ -200,31 +244,31 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 {
 	struct mock_iommu_domain *mock =
 		container_of(domain, struct mock_iommu_domain, domain);
-	unsigned long i, max = size / MOCK_IO_PAGE_SIZE;
-	void *ent, *old;
+	unsigned long end = iova + size;
+	void *ent;
 
 	if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap)
 		return -EINVAL;
 
-	for (i = 0; i < max; i++) {
-		unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE;
+	do {
+		unsigned long pgsize = MOCK_IO_PAGE_SIZE;
+		unsigned long head;
 
-		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
-		if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) {
-			/* Clear dirty */
-			if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
-				unsigned long val;
-
-				val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
-				old = xa_store(&mock->pfns,
-					       cur / MOCK_IO_PAGE_SIZE,
-					       xa_mk_value(val), GFP_KERNEL);
-				WARN_ON_ONCE(ent != old);
-			}
-			iommu_dirty_bitmap_record(dirty, cur,
-						  MOCK_IO_PAGE_SIZE);
+		ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE);
+		if (!ent) {
+			iova += pgsize;
+			continue;
 		}
-	}
+
+		if (xa_to_value(ent) & MOCK_PFN_HUGE_IOVA)
+			pgsize = MOCK_HUGE_PAGE_SIZE;
+		head = iova & ~(pgsize - 1);
+
+		/* Clear dirty */
+		if (mock_test_and_clear_dirty(mock, head, pgsize, flags))
+			iommu_dirty_bitmap_record(dirty, head, pgsize);
+		iova = head + pgsize;
+	} while (iova < end);
 
 	return 0;
 }
@@ -236,6 +280,7 @@ const struct iommu_dirty_ops dirty_ops = {
 
 static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
 {
+	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 	struct mock_iommu_domain *mock;
 
 	mock = kzalloc(sizeof(*mock), GFP_KERNEL);
@@ -244,6 +289,8 @@ static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
 	mock->domain.geometry.aperture_start = MOCK_APERTURE_START;
 	mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST;
 	mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE;
+	if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA)
+		mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE;
 	mock->domain.ops = mock_ops.default_domain_ops;
 	mock->domain.type = IOMMU_DOMAIN_UNMANAGED;
 	xa_init(&mock->pfns);
@@ -289,7 +336,7 @@ mock_domain_alloc_user(struct device *dev, u32 flags,
 			return ERR_PTR(-EOPNOTSUPP);
 		if (user_data || (has_dirty_flag && no_dirty_ops))
 			return ERR_PTR(-EOPNOTSUPP);
-		domain = mock_domain_alloc_paging(NULL);
+		domain = mock_domain_alloc_paging(dev);
 		if (!domain)
 			return ERR_PTR(-ENOMEM);
 		if (has_dirty_flag)
@@ -352,6 +399,9 @@ static int mock_domain_map_pages(struct iommu_domain *domain,
 
 			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
 				flags = MOCK_PFN_LAST_IOVA;
+			if (pgsize != MOCK_IO_PAGE_SIZE) {
+				flags |= MOCK_PFN_HUGE_IOVA;
+			}
 			old = xa_store(&mock->pfns, iova / MOCK_IO_PAGE_SIZE,
 				       xa_mk_value((paddr / MOCK_IO_PAGE_SIZE) |
 						   flags),
@@ -396,20 +446,27 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 
 			/*
 			 * iommufd generates unmaps that must be a strict
-			 * superset of the map's performend So every starting
-			 * IOVA should have been an iova passed to map, and the
+			 * superset of the map's performend So every
+			 * starting/ending IOVA should have been an iova passed
+			 * to map.
 			 *
-			 * First IOVA must be present and have been a first IOVA
-			 * passed to map_pages
+			 * This simple logic doesn't work when the HUGE_PAGE is
+			 * turned on since the core code will automatically
+			 * switch between the two page sizes creating a break in
+			 * the unmap calls. The break can land in the middle of
+			 * contiguous IOVA.
 			 */
-			if (first) {
-				WARN_ON(ent && !(xa_to_value(ent) &
-						 MOCK_PFN_START_IOVA));
-				first = false;
+			if (!(domain->pgsize_bitmap & MOCK_HUGE_PAGE_SIZE)) {
+				if (first) {
+					WARN_ON(ent && !(xa_to_value(ent) &
+							 MOCK_PFN_START_IOVA));
+					first = false;
+				}
+				if (pgcount == 1 &&
+				    cur + MOCK_IO_PAGE_SIZE == pgsize)
+					WARN_ON(ent && !(xa_to_value(ent) &
+							 MOCK_PFN_LAST_IOVA));
 			}
-			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
-				WARN_ON(ent && !(xa_to_value(ent) &
-						 MOCK_PFN_LAST_IOVA));
 
 			iova += MOCK_IO_PAGE_SIZE;
 			ret += MOCK_IO_PAGE_SIZE;
@@ -452,6 +509,8 @@ static struct iommu_device mock_iommu_device = {
 
 static struct iommu_device *mock_probe_device(struct device *dev)
 {
+	if (dev->bus != &iommufd_mock_bus_type.bus)
+		return ERR_PTR(-ENODEV);
 	return &mock_iommu_device;
 }
 
@@ -488,9 +547,59 @@ static void mock_domain_free_nested(struct iommu_domain *domain)
 	kfree(mock_nested);
 }
 
+static int
+mock_domain_cache_invalidate_user(struct iommu_domain *domain,
+				  struct iommu_user_data_array *array)
+{
+	struct mock_iommu_domain_nested *mock_nested =
+		container_of(domain, struct mock_iommu_domain_nested, domain);
+	struct iommu_hwpt_invalidate_selftest inv;
+	u32 processed = 0;
+	int i = 0, j;
+	int rc = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	for ( ; i < array->entry_num; i++) {
+		rc = iommu_copy_struct_from_user_array(&inv, array,
+						       IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+						       i, iotlb_id);
+		if (rc)
+			break;
+
+		if (inv.flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			rc = -EOPNOTSUPP;
+			break;
+		}
+
+		if (inv.iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX) {
+			rc = -EINVAL;
+			break;
+		}
+
+		if (inv.flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			/* Invalidate all mock iotlb entries and ignore iotlb_id */
+			for (j = 0; j < MOCK_NESTED_DOMAIN_IOTLB_NUM; j++)
+				mock_nested->iotlb[j] = 0;
+		} else {
+			mock_nested->iotlb[inv.iotlb_id] = 0;
+		}
+
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return rc;
+}
+
 static struct iommu_domain_ops domain_nested_ops = {
 	.free = mock_domain_free_nested,
 	.attach_dev = mock_domain_nop_attach,
+	.cache_invalidate_user = mock_domain_cache_invalidate_user,
 };
 
 static inline struct iommufd_hw_pagetable *
@@ -541,24 +650,11 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 	return hwpt;
 }
 
-struct mock_bus_type {
-	struct bus_type bus;
-	struct notifier_block nb;
-};
-
-static struct mock_bus_type iommufd_mock_bus_type = {
-	.bus = {
-		.name = "iommufd_mock",
-	},
-};
-
-static atomic_t mock_dev_num;
-
 static void mock_dev_release(struct device *dev)
 {
 	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 
-	atomic_dec(&mock_dev_num);
+	ida_free(&mock_dev_ida, mdev->id);
 	kfree(mdev);
 }
 
@@ -567,7 +663,8 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 	struct mock_dev *mdev;
 	int rc;
 
-	if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY))
+	if (dev_flags &
+	    ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA))
 		return ERR_PTR(-EINVAL);
 
 	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
@@ -579,8 +676,12 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 	mdev->dev.release = mock_dev_release;
 	mdev->dev.bus = &iommufd_mock_bus_type.bus;
 
-	rc = dev_set_name(&mdev->dev, "iommufd_mock%u",
-			  atomic_inc_return(&mock_dev_num));
+	rc = ida_alloc(&mock_dev_ida, GFP_KERNEL);
+	if (rc < 0)
+		goto err_put;
+	mdev->id = rc;
+
+	rc = dev_set_name(&mdev->dev, "iommufd_mock%u", mdev->id);
 	if (rc)
 		goto err_put;
 
@@ -808,6 +909,28 @@ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd,
 	return 0;
 }
 
+static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd,
+				       u32 mockpt_id, unsigned int iotlb_id,
+				       u32 iotlb)
+{
+	struct mock_iommu_domain_nested *mock_nested;
+	struct iommufd_hw_pagetable *hwpt;
+	int rc = 0;
+
+	hwpt = get_md_pagetable_nested(ucmd, mockpt_id, &mock_nested);
+	if (IS_ERR(hwpt))
+		return PTR_ERR(hwpt);
+
+	mock_nested = container_of(hwpt->domain,
+				   struct mock_iommu_domain_nested, domain);
+
+	if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX ||
+	    mock_nested->iotlb[iotlb_id] != iotlb)
+		rc = -EINVAL;
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+	return rc;
+}
+
 struct selftest_access {
 	struct iommufd_access *access;
 	struct file *file;
@@ -1289,6 +1412,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 		return iommufd_test_md_check_refs(
 			ucmd, u64_to_user_ptr(cmd->check_refs.uptr),
 			cmd->check_refs.length, cmd->check_refs.refs);
+	case IOMMU_TEST_OP_MD_CHECK_IOTLB:
+		return iommufd_test_md_check_iotlb(ucmd, cmd->id,
+						   cmd->check_iotlb.id,
+						   cmd->check_iotlb.iotlb);
 	case IOMMU_TEST_OP_CREATE_ACCESS:
 		return iommufd_test_create_access(ucmd, cmd->id,
 						  cmd->create_access.flags);
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 75279500a4..7abe9e85a5 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -863,16 +863,11 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct mtk_iommu_data *data;
+	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
 	struct device_link *link;
 	struct device *larbdev;
 	unsigned int larbid, larbidx, i;
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
-	data = dev_iommu_priv_get(dev);
-
 	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
 		return &data->iommu;
 
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 67e044c1a7..25b41222ab 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -481,9 +481,6 @@ static struct iommu_device *mtk_iommu_v1_probe_device(struct device *dev)
 		idx++;
 	}
 
-	if (!fwspec || fwspec->ops != &mtk_iommu_v1_ops)
-		return ERR_PTR(-ENODEV); /* Not a iommu client device */
-
 	data = dev_iommu_priv_get(dev);
 
 	/* Link the consumer device with the smi-larb device(supplier) */
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 42cffb0ee5..719652b608 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -17,8 +17,6 @@
 #include <linux/slab.h>
 #include <linux/fsl/mc.h>
 
-#define NO_IOMMU	1
-
 static int of_iommu_xlate(struct device *dev,
 			  struct of_phandle_args *iommu_spec)
 {
@@ -29,7 +27,7 @@ static int of_iommu_xlate(struct device *dev,
 	ops = iommu_ops_from_fwnode(fwnode);
 	if ((ops && !ops->of_xlate) ||
 	    !of_device_is_available(iommu_spec->np))
-		return NO_IOMMU;
+		return -ENODEV;
 
 	ret = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
 	if (ret)
@@ -61,7 +59,7 @@ static int of_iommu_configure_dev_id(struct device_node *master_np,
 			 "iommu-map-mask", &iommu_spec.np,
 			 iommu_spec.args);
 	if (err)
-		return err == -ENODEV ? NO_IOMMU : err;
+		return err;
 
 	err = of_iommu_xlate(dev, &iommu_spec);
 	of_node_put(iommu_spec.np);
@@ -72,7 +70,7 @@ static int of_iommu_configure_dev(struct device_node *master_np,
 				  struct device *dev)
 {
 	struct of_phandle_args iommu_spec;
-	int err = NO_IOMMU, idx = 0;
+	int err = -ENODEV, idx = 0;
 
 	while (!of_parse_phandle_with_args(master_np, "iommus",
 					   "#iommu-cells",
@@ -107,16 +105,21 @@ static int of_iommu_configure_device(struct device_node *master_np,
 		      of_iommu_configure_dev(master_np, dev);
 }
 
-const struct iommu_ops *of_iommu_configure(struct device *dev,
-					   struct device_node *master_np,
-					   const u32 *id)
+/*
+ * Returns:
+ *  0 on success, an iommu was configured
+ *  -ENODEV if the device does not have any IOMMU
+ *  -EPROBEDEFER if probing should be tried again
+ *  -errno fatal errors
+ */
+int of_iommu_configure(struct device *dev, struct device_node *master_np,
+		       const u32 *id)
 {
-	const struct iommu_ops *ops = NULL;
 	struct iommu_fwspec *fwspec;
-	int err = NO_IOMMU;
+	int err;
 
 	if (!master_np)
-		return NULL;
+		return -ENODEV;
 
 	/* Serialise to make dev->iommu stable under our potential fwspec */
 	mutex_lock(&iommu_probe_device_lock);
@@ -124,7 +127,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	if (fwspec) {
 		if (fwspec->ops) {
 			mutex_unlock(&iommu_probe_device_lock);
-			return fwspec->ops;
+			return 0;
 		}
 		/* In the deferred case, start again from scratch */
 		iommu_fwspec_free(dev);
@@ -147,36 +150,21 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 	} else {
 		err = of_iommu_configure_device(master_np, dev, id);
 	}
-
-	/*
-	 * Two success conditions can be represented by non-negative err here:
-	 * >0 : there is no IOMMU, or one was unavailable for non-fatal reasons
-	 *  0 : we found an IOMMU, and dev->fwspec is initialised appropriately
-	 * <0 : any actual error
-	 */
-	if (!err) {
-		/* The fwspec pointer changed, read it again */
-		fwspec = dev_iommu_fwspec_get(dev);
-		ops    = fwspec->ops;
-	}
 	mutex_unlock(&iommu_probe_device_lock);
 
-	/*
-	 * If we have reason to believe the IOMMU driver missed the initial
-	 * probe for dev, replay it to get things in order.
-	 */
-	if (!err && dev->bus)
-		err = iommu_probe_device(dev);
-
-	/* Ignore all other errors apart from EPROBE_DEFER */
-	if (err == -EPROBE_DEFER) {
-		ops = ERR_PTR(err);
-	} else if (err < 0) {
-		dev_dbg(dev, "Adding to IOMMU failed: %d\n", err);
-		ops = NULL;
-	}
+	if (err == -ENODEV || err == -EPROBE_DEFER)
+		return err;
+	if (err)
+		goto err_log;
+
+	err = iommu_probe_device(dev);
+	if (err)
+		goto err_log;
+	return 0;
 
-	return ops;
+err_log:
+	dev_dbg(dev, "Adding to IOMMU failed: %pe\n", ERR_PTR(err));
+	return err;
 }
 
 static enum iommu_resv_type __maybe_unused
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index c66b070841..c9528065a5 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -1719,7 +1719,6 @@ static void omap_iommu_release_device(struct device *dev)
 	if (!dev->of_node || !arch_data)
 		return;
 
-	dev_iommu_priv_set(dev, NULL);
 	kfree(arch_data);
 
 }
diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
index 2eb9fb4670..537359f109 100644
--- a/drivers/iommu/sprd-iommu.c
+++ b/drivers/iommu/sprd-iommu.c
@@ -385,13 +385,7 @@ static phys_addr_t sprd_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static struct iommu_device *sprd_iommu_probe_device(struct device *dev)
 {
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct sprd_iommu_device *sdev;
-
-	if (!fwspec || fwspec->ops != &sprd_iommu_ops)
-		return ERR_PTR(-ENODEV);
-
-	sdev = dev_iommu_priv_get(dev);
+	struct sprd_iommu_device *sdev = dev_iommu_priv_get(dev);
 
 	return &sdev->iommu;
 }
diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c
index 379ebe03ef..34db37fd96 100644
--- a/drivers/iommu/virtio-iommu.c
+++ b/drivers/iommu/virtio-iommu.c
@@ -843,7 +843,7 @@ static int viommu_map_pages(struct iommu_domain *domain, unsigned long iova,
 			.flags		= cpu_to_le32(flags),
 		};
 
-		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
+		ret = viommu_add_req(vdomain->viommu, &map, sizeof(map));
 		if (ret) {
 			viommu_del_mappings(vdomain, iova, end);
 			return ret;
@@ -912,6 +912,33 @@ static void viommu_iotlb_sync(struct iommu_domain *domain,
 	viommu_sync_req(vdomain->viommu);
 }
 
+static int viommu_iotlb_sync_map(struct iommu_domain *domain,
+				 unsigned long iova, size_t size)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return 0;
+	return viommu_sync_req(vdomain->viommu);
+}
+
+static void viommu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct viommu_domain *vdomain = to_viommu_domain(domain);
+
+	/*
+	 * May be called before the viommu is initialized including
+	 * while creating direct mapping
+	 */
+	if (!vdomain->nr_endpoints)
+		return;
+	viommu_sync_req(vdomain->viommu);
+}
+
 static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
 {
 	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
@@ -969,9 +996,6 @@ static struct iommu_device *viommu_probe_device(struct device *dev)
 	struct viommu_dev *viommu = NULL;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!fwspec || fwspec->ops != &viommu_ops)
-		return ERR_PTR(-ENODEV);
-
 	viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode);
 	if (!viommu)
 		return ERR_PTR(-ENODEV);
@@ -1037,6 +1061,8 @@ static bool viommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
+	case IOMMU_CAP_DEFERRED_FLUSH:
+		return true;
 	default:
 		return false;
 	}
@@ -1057,7 +1083,9 @@ static struct iommu_ops viommu_ops = {
 		.map_pages		= viommu_map_pages,
 		.unmap_pages		= viommu_unmap_pages,
 		.iova_to_phys		= viommu_iova_to_phys,
+		.flush_iotlb_all	= viommu_flush_iotlb_all,
 		.iotlb_sync		= viommu_iotlb_sync,
+		.iotlb_sync_map		= viommu_iotlb_sync_map,
 		.free			= viommu_domain_free,
 	}
 };