diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index d9da766719c8..cbe6a890a93a 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -23,8 +23,7 @@ config IOMMU_IO_PGTABLE
 config IOMMU_IO_PGTABLE_LPAE
 	bool "ARMv7/v8 Long Descriptor Format"
 	select IOMMU_IO_PGTABLE
-	# SWIOTLB guarantees a dma_to_phys() implementation
-	depends on ARM || ARM64 || (COMPILE_TEST && SWIOTLB)
+	depends on HAS_DMA && (ARM || ARM64 || COMPILE_TEST)
 	help
 	  Enable support for the ARM long descriptor pagetable format.
 	  This allocator supports 4K/2M/1G, 16K/32M and 64K/512M page
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index f82060e778a2..08d2775887f7 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2006,6 +2006,15 @@ static void do_detach(struct iommu_dev_data *dev_data)
 {
 	struct amd_iommu *iommu;
 
+	/*
+	 * First check if the device is still attached. It might already
+	 * be detached from its domain because the generic
+	 * iommu_detach_group code detached it and we try again here in
+	 * our alias handling.
+	 */
+	if (!dev_data->domain)
+		return;
+
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
 
 	/* decrease reference counters */
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 5ef347a13cb5..1b066e7d144d 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1256,6 +1256,9 @@ static int iommu_init_pci(struct amd_iommu *iommu)
 	if (!iommu->dev)
 		return -ENODEV;
 
+	/* Prevent binding other PCI device drivers to IOMMU devices */
+	iommu->dev->match_driver = false;
+
 	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
 			      &iommu->cap);
 	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET,
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index dafaf59dc3b8..286e890e7d64 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -56,6 +56,7 @@
 #define IDR0_TTF_SHIFT			2
 #define IDR0_TTF_MASK			0x3
 #define IDR0_TTF_AARCH64		(2 << IDR0_TTF_SHIFT)
+#define IDR0_TTF_AARCH32_64		(3 << IDR0_TTF_SHIFT)
 #define IDR0_S1P			(1 << 1)
 #define IDR0_S2P			(1 << 0)
 
@@ -342,7 +343,8 @@
 #define CMDQ_TLBI_0_VMID_SHIFT		32
 #define CMDQ_TLBI_0_ASID_SHIFT		48
 #define CMDQ_TLBI_1_LEAF		(1UL << 0)
-#define CMDQ_TLBI_1_ADDR_MASK		~0xfffUL
+#define CMDQ_TLBI_1_VA_MASK		~0xfffUL
+#define CMDQ_TLBI_1_IPA_MASK		0xfffffffff000UL
 
 #define CMDQ_PRI_0_SSID_SHIFT		12
 #define CMDQ_PRI_0_SSID_MASK		0xfffffUL
@@ -770,11 +772,13 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		break;
 	case CMDQ_OP_TLBI_NH_VA:
 		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
-		/* Fallthrough */
+		cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
+		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK;
+		break;
 	case CMDQ_OP_TLBI_S2_IPA:
 		cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT;
 		cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0;
-		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_ADDR_MASK;
+		cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK;
 		break;
 	case CMDQ_OP_TLBI_NH_ASID:
 		cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT;
@@ -2460,7 +2464,13 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
 	}
 
 	/* We only support the AArch64 table format at present */
-	if ((reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) < IDR0_TTF_AARCH64) {
+	switch (reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) {
+	case IDR0_TTF_AARCH32_64:
+		smmu->ias = 40;
+		/* Fallthrough */
+	case IDR0_TTF_AARCH64:
+		break;
+	default:
 		dev_err(smmu->dev, "AArch64 table format not supported!\n");
 		return -ENXIO;
 	}
@@ -2541,8 +2551,7 @@ static int arm_smmu_device_probe(struct arm_smmu_device *smmu)
 		dev_warn(smmu->dev,
 			 "failed to set DMA mask for table walker\n");
 
-	if (!smmu->ias)
-		smmu->ias = smmu->oas;
+	smmu->ias = max(smmu->ias, smmu->oas);
 
 	dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
 		 smmu->ias, smmu->oas, smmu->features);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 041bc1810a86..35365f046923 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2301,6 +2301,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 
 	if (ret) {
 		spin_unlock_irqrestore(&device_domain_lock, flags);
+		free_devinfo_mem(info);
 		return NULL;
 	}
 
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 73c07482f487..7df97777662d 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -202,9 +202,9 @@ typedef u64 arm_lpae_iopte;
 
 static bool selftest_running = false;
 
-static dma_addr_t __arm_lpae_dma_addr(struct device *dev, void *pages)
+static dma_addr_t __arm_lpae_dma_addr(void *pages)
 {
-	return phys_to_dma(dev, virt_to_phys(pages));
+	return (dma_addr_t)virt_to_phys(pages);
 }
 
 static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
@@ -223,10 +223,10 @@ static void *__arm_lpae_alloc_pages(size_t size, gfp_t gfp,
 			goto out_free;
 		/*
 		 * We depend on the IOMMU being able to work with any physical
-		 * address directly, so if the DMA layer suggests it can't by
-		 * giving us back some translation, that bodes very badly...
+		 * address directly, so if the DMA layer suggests otherwise by
+		 * translating or truncating them, that bodes very badly...
 		 */
-		if (dma != __arm_lpae_dma_addr(dev, pages))
+		if (dma != virt_to_phys(pages))
 			goto out_unmap;
 	}
 
@@ -243,10 +243,8 @@ out_free:
 static void __arm_lpae_free_pages(void *pages, size_t size,
 				  struct io_pgtable_cfg *cfg)
 {
-	struct device *dev = cfg->iommu_dev;
-
 	if (!selftest_running)
-		dma_unmap_single(dev, __arm_lpae_dma_addr(dev, pages),
+		dma_unmap_single(cfg->iommu_dev, __arm_lpae_dma_addr(pages),
 				 size, DMA_TO_DEVICE);
 	free_pages_exact(pages, size);
 }
@@ -254,12 +252,11 @@ static void __arm_lpae_free_pages(void *pages, size_t size,
 static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte,
 			       struct io_pgtable_cfg *cfg)
 {
-	struct device *dev = cfg->iommu_dev;
-
 	*ptep = pte;
 
 	if (!selftest_running)
-		dma_sync_single_for_device(dev, __arm_lpae_dma_addr(dev, ptep),
+		dma_sync_single_for_device(cfg->iommu_dev,
+					   __arm_lpae_dma_addr(ptep),
 					   sizeof(pte), DMA_TO_DEVICE);
 }
 
@@ -629,6 +626,11 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 	if (cfg->oas > ARM_LPAE_MAX_ADDR_BITS)
 		return NULL;
 
+	if (!selftest_running && cfg->iommu_dev->dma_pfn_offset) {
+		dev_err(cfg->iommu_dev, "Cannot accommodate DMA offset for IOMMU page tables\n");
+		return NULL;
+	}
+
 	data = kmalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return NULL;