Merge tag 'iommu-v4.15-rc1' of git://github.com/awilliam/linux-vfio

Pull IOMMU updates from Alex Williamson:
 "As Joerg mentioned[1], he's out on paternity leave through the end of
  the year and I'm filling in for him in the interim:

   - Enforce MSI multiple IRQ alignment in AMD IOMMU

   - VT-d PASID error handling fixes

   - Add r8a7795 IPMMU support

   - Manage runtime PM links on exynos at {add,remove}_device callbacks

   - Fix Mediatek driver name to avoid conflict

   - Add terminate support to qcom fault handler

   - 64-bit IOVA optimizations

   - Simplfy IOVA domain destruction, better use of rcache, and skip
     anchor nodes on copy

   - Convert to IOMMU TLB sync API in io-pgtable-arm{-v7s}

   - Drop command queue lock when waiting for CMD_SYNC completion on ARM
     SMMU implementations supporting MSI to cacheable memory

   - iomu-vmsa cleanup inspired by missed IOTLB sync callbacks

   - Fix sleeping lock with preemption disabled for RT

   - Dual MMU support for TI DRA7xx DSPs

   - Optional flush option on IOVA allocation avoiding overhead when
     caller can try other options

  [1] https://lkml.org/lkml/2017/10/22/72"

* tag 'iommu-v4.15-rc1' of git://github.com/awilliam/linux-vfio: (54 commits)
  iommu/iova: Use raw_cpu_ptr() instead of get_cpu_ptr() for ->fq
  iommu/mediatek: Fix driver name
  iommu/ipmmu-vmsa: Hook up r8a7795 DT matching code
  iommu/ipmmu-vmsa: Allow two bit SL0
  iommu/ipmmu-vmsa: Make IMBUSCTR setup optional
  iommu/ipmmu-vmsa: Write IMCTR twice
  iommu/ipmmu-vmsa: IPMMU device is 40-bit bus master
  iommu/ipmmu-vmsa: Make use of IOMMU_OF_DECLARE()
  iommu/ipmmu-vmsa: Enable multi context support
  iommu/ipmmu-vmsa: Add optional root device feature
  iommu/ipmmu-vmsa: Introduce features, break out alias
  iommu/ipmmu-vmsa: Unify ipmmu_ops
  iommu/ipmmu-vmsa: Clean up struct ipmmu_vmsa_iommu_priv
  iommu/ipmmu-vmsa: Simplify group allocation
  iommu/ipmmu-vmsa: Unify domain alloc/free
  iommu/ipmmu-vmsa: Fix return value check in ipmmu_find_group_dma()
  iommu/vt-d: Clear pasid table entry when memory unbound
  iommu/vt-d: Clear Page Request Overflow fault bit
  iommu/vt-d: Missing checks for pasid tables if allocation fails
  iommu/amd: Limit the IOVA page range to the specified addresses
  ...

17 files changed, 970 insertions, 615 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 9c848e36f209..7d5eb004091d 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -63,7 +63,6 @@
 /* IO virtual address start page frame number */
 #define IOVA_START_PFN		(1)
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
-#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
 
 /* Reserved IOVA ranges */
 #define MSI_RANGE_START		(0xfee00000)
@@ -1547,10 +1546,11 @@ static unsigned long dma_ops_alloc_iova(struct device *dev,
 
 	if (dma_mask > DMA_BIT_MASK(32))
 		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
-				      IOVA_PFN(DMA_BIT_MASK(32)));
+				      IOVA_PFN(DMA_BIT_MASK(32)), false);
 
 	if (!pfn)
-		pfn = alloc_iova_fast(&dma_dom->iovad, pages, IOVA_PFN(dma_mask));
+		pfn = alloc_iova_fast(&dma_dom->iovad, pages,
+				      IOVA_PFN(dma_mask), true);
 
 	return (pfn << PAGE_SHIFT);
 }
@@ -1788,8 +1788,7 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
 	if (!dma_dom->domain.pt_root)
 		goto free_dma_dom;
 
-	init_iova_domain(&dma_dom->iovad, PAGE_SIZE,
-			 IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&dma_dom->iovad, PAGE_SIZE, IOVA_START_PFN);
 
 	if (init_iova_flush_queue(&dma_dom->iovad, iova_domain_flush_tlb, NULL))
 		goto free_dma_dom;
@@ -2383,11 +2382,9 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 			   size_t size,
 			   int dir)
 {
-	dma_addr_t flush_addr;
 	dma_addr_t i, start;
 	unsigned int pages;
 
-	flush_addr = dma_addr;
 	pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
 	dma_addr &= PAGE_MASK;
 	start = dma_addr;
@@ -2696,8 +2693,7 @@ static int init_reserved_iova_ranges(void)
 	struct pci_dev *pdev = NULL;
 	struct iova *val;
 
-	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE,
-			 IOVA_START_PFN, DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_ranges, PAGE_SIZE, IOVA_START_PFN);
 
 	lockdep_set_class(&reserved_iova_ranges.iova_rbtree_lock,
 			  &reserved_rbtree_key);
@@ -3155,7 +3151,7 @@ static void amd_iommu_apply_resv_region(struct device *dev,
 	unsigned long start, end;
 
 	start = IOVA_PFN(region->start);
-	end   = IOVA_PFN(region->start + region->length);
+	end   = IOVA_PFN(region->start + region->length - 1);
 
 	WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL);
 }
@@ -3663,11 +3659,11 @@ out_unlock:
 	return table;
 }
 
-static int alloc_irq_index(u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count, bool align)
 {
 	struct irq_remap_table *table;
+	int index, c, alignment = 1;
 	unsigned long flags;
-	int index, c;
 	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
 	if (!iommu)
@@ -3677,16 +3673,21 @@ static int alloc_irq_index(u16 devid, int count)
 	if (!table)
 		return -ENODEV;
 
+	if (align)
+		alignment = roundup_pow_of_two(count);
+
 	spin_lock_irqsave(&table->lock, flags);
 
 	/* Scan table for free entries */
-	for (c = 0, index = table->min_index;
-	     index < MAX_IRQS_PER_TABLE;
-	     ++index) {
-		if (!iommu->irte_ops->is_allocated(table, index))
+	for (index = ALIGN(table->min_index, alignment), c = 0;
+	     index < MAX_IRQS_PER_TABLE;) {
+		if (!iommu->irte_ops->is_allocated(table, index)) {
 			c += 1;
-		else
-			c = 0;
+		} else {
+			c     = 0;
+			index = ALIGN(index + 1, alignment);
+			continue;
+		}
 
 		if (c == count)	{
 			for (; c != 0; --c)
@@ -3695,6 +3696,8 @@ static int alloc_irq_index(u16 devid, int count)
 			index -= count - 1;
 			goto out;
 		}
+
+		index++;
 	}
 
 	index = -ENOSPC;
@@ -4099,7 +4102,9 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		else
 			ret = -ENOMEM;
 	} else {
-		index = alloc_irq_index(devid, nr_irqs);
+		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
+
+		index = alloc_irq_index(devid, nr_irqs, align);
 	}
 	if (index < 0) {
 		pr_warn("Failed to allocate IRTE\n");
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index e67ba6c40faf..f122071688fd 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -316,6 +316,7 @@
 #define ARM64_TCR_TBI0_MASK		0x1UL
 
 #define CTXDESC_CD_0_AA64		(1UL << 41)
+#define CTXDESC_CD_0_S			(1UL << 44)
 #define CTXDESC_CD_0_R			(1UL << 45)
 #define CTXDESC_CD_0_A			(1UL << 46)
 #define CTXDESC_CD_0_ASET_SHIFT		47
@@ -377,7 +378,16 @@
 
 #define CMDQ_SYNC_0_CS_SHIFT		12
 #define CMDQ_SYNC_0_CS_NONE		(0UL << CMDQ_SYNC_0_CS_SHIFT)
+#define CMDQ_SYNC_0_CS_IRQ		(1UL << CMDQ_SYNC_0_CS_SHIFT)
 #define CMDQ_SYNC_0_CS_SEV		(2UL << CMDQ_SYNC_0_CS_SHIFT)
+#define CMDQ_SYNC_0_MSH_SHIFT		22
+#define CMDQ_SYNC_0_MSH_ISH		(3UL << CMDQ_SYNC_0_MSH_SHIFT)
+#define CMDQ_SYNC_0_MSIATTR_SHIFT	24
+#define CMDQ_SYNC_0_MSIATTR_OIWB	(0xfUL << CMDQ_SYNC_0_MSIATTR_SHIFT)
+#define CMDQ_SYNC_0_MSIDATA_SHIFT	32
+#define CMDQ_SYNC_0_MSIDATA_MASK	0xffffffffUL
+#define CMDQ_SYNC_1_MSIADDR_SHIFT	0
+#define CMDQ_SYNC_1_MSIADDR_MASK	0xffffffffffffcUL
 
 /* Event queue */
 #define EVTQ_ENT_DWORDS			4
@@ -408,20 +418,12 @@
 
 /* High-level queue structures */
 #define ARM_SMMU_POLL_TIMEOUT_US	100
-#define ARM_SMMU_CMDQ_DRAIN_TIMEOUT_US	1000000 /* 1s! */
+#define ARM_SMMU_CMDQ_SYNC_TIMEOUT_US	1000000 /* 1s! */
+#define ARM_SMMU_CMDQ_SYNC_SPIN_COUNT	10
 
 #define MSI_IOVA_BASE			0x8000000
 #define MSI_IOVA_LENGTH			0x100000
 
-/* Until ACPICA headers cover IORT rev. C */
-#ifndef ACPI_IORT_SMMU_HISILICON_HI161X
-#define ACPI_IORT_SMMU_HISILICON_HI161X		0x1
-#endif
-
-#ifndef ACPI_IORT_SMMU_V3_CAVIUM_CN99XX
-#define ACPI_IORT_SMMU_V3_CAVIUM_CN99XX		0x2
-#endif
-
 static bool disable_bypass;
 module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
@@ -504,6 +506,10 @@ struct arm_smmu_cmdq_ent {
 		} pri;
 
 		#define CMDQ_OP_CMD_SYNC	0x46
+		struct {
+			u32			msidata;
+			u64			msiaddr;
+		} sync;
 	};
 };
 
@@ -604,6 +610,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_TRANS_S2		(1 << 10)
 #define ARM_SMMU_FEAT_STALLS		(1 << 11)
 #define ARM_SMMU_FEAT_HYP		(1 << 12)
+#define ARM_SMMU_FEAT_STALL_FORCE	(1 << 13)
 	u32				features;
 
 #define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
@@ -616,6 +623,7 @@ struct arm_smmu_device {
 
 	int				gerr_irq;
 	int				combined_irq;
+	atomic_t			sync_nr;
 
 	unsigned long			ias; /* IPA */
 	unsigned long			oas; /* PA */
@@ -634,6 +642,8 @@ struct arm_smmu_device {
 
 	struct arm_smmu_strtab_cfg	strtab_cfg;
 
+	u32				sync_count;
+
 	/* IOMMU core code handle */
 	struct iommu_device		iommu;
 };
@@ -757,26 +767,29 @@ static void queue_inc_prod(struct arm_smmu_queue *q)
  * Wait for the SMMU to consume items. If drain is true, wait until the queue
  * is empty. Otherwise, wait until there is at least one free slot.
  */
-static int queue_poll_cons(struct arm_smmu_queue *q, bool drain, bool wfe)
+static int queue_poll_cons(struct arm_smmu_queue *q, bool sync, bool wfe)
 {
 	ktime_t timeout;
-	unsigned int delay = 1;
+	unsigned int delay = 1, spin_cnt = 0;
 
-	/* Wait longer if it's queue drain */
-	timeout = ktime_add_us(ktime_get(), drain ?
-					    ARM_SMMU_CMDQ_DRAIN_TIMEOUT_US :
+	/* Wait longer if it's a CMD_SYNC */
+	timeout = ktime_add_us(ktime_get(), sync ?
+					    ARM_SMMU_CMDQ_SYNC_TIMEOUT_US :
 					    ARM_SMMU_POLL_TIMEOUT_US);
 
-	while (queue_sync_cons(q), (drain ? !queue_empty(q) : queue_full(q))) {
+	while (queue_sync_cons(q), (sync ? !queue_empty(q) : queue_full(q))) {
 		if (ktime_compare(ktime_get(), timeout) > 0)
 			return -ETIMEDOUT;
 
 		if (wfe) {
 			wfe();
-		} else {
+		} else if (++spin_cnt < ARM_SMMU_CMDQ_SYNC_SPIN_COUNT) {
 			cpu_relax();
+			continue;
+		} else {
 			udelay(delay);
 			delay *= 2;
+			spin_cnt = 0;
 		}
 	}
 
@@ -878,7 +891,13 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		}
 		break;
 	case CMDQ_OP_CMD_SYNC:
-		cmd[0] |= CMDQ_SYNC_0_CS_SEV;
+		if (ent->sync.msiaddr)
+			cmd[0] |= CMDQ_SYNC_0_CS_IRQ;
+		else
+			cmd[0] |= CMDQ_SYNC_0_CS_SEV;
+		cmd[0] |= CMDQ_SYNC_0_MSH_ISH | CMDQ_SYNC_0_MSIATTR_OIWB;
+		cmd[0] |= (u64)ent->sync.msidata << CMDQ_SYNC_0_MSIDATA_SHIFT;
+		cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK;
 		break;
 	default:
 		return -ENOENT;
@@ -936,13 +955,22 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu)
 	queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
 }
 
+static void arm_smmu_cmdq_insert_cmd(struct arm_smmu_device *smmu, u64 *cmd)
+{
+	struct arm_smmu_queue *q = &smmu->cmdq.q;
+	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+
+	while (queue_insert_raw(q, cmd) == -ENOSPC) {
+		if (queue_poll_cons(q, false, wfe))
+			dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
+	}
+}
+
 static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
 				    struct arm_smmu_cmdq_ent *ent)
 {
 	u64 cmd[CMDQ_ENT_DWORDS];
 	unsigned long flags;
-	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
-	struct arm_smmu_queue *q = &smmu->cmdq.q;
 
 	if (arm_smmu_cmdq_build_cmd(cmd, ent)) {
 		dev_warn(smmu->dev, "ignoring unknown CMDQ opcode 0x%x\n",
@@ -951,14 +979,76 @@ static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
 	}
 
 	spin_lock_irqsave(&smmu->cmdq.lock, flags);
-	while (queue_insert_raw(q, cmd) == -ENOSPC) {
-		if (queue_poll_cons(q, false, wfe))
-			dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
-	}
+	arm_smmu_cmdq_insert_cmd(smmu, cmd);
+	spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
+}
 
-	if (ent->opcode == CMDQ_OP_CMD_SYNC && queue_poll_cons(q, true, wfe))
-		dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
+/*
+ * The difference between val and sync_idx is bounded by the maximum size of
+ * a queue at 2^20 entries, so 32 bits is plenty for wrap-safe arithmetic.
+ */
+static int __arm_smmu_sync_poll_msi(struct arm_smmu_device *smmu, u32 sync_idx)
+{
+	ktime_t timeout;
+	u32 val;
+
+	timeout = ktime_add_us(ktime_get(), ARM_SMMU_CMDQ_SYNC_TIMEOUT_US);
+	val = smp_cond_load_acquire(&smmu->sync_count,
+				    (int)(VAL - sync_idx) >= 0 ||
+				    !ktime_before(ktime_get(), timeout));
+
+	return (int)(val - sync_idx) < 0 ? -ETIMEDOUT : 0;
+}
+
+static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
+{
+	u64 cmd[CMDQ_ENT_DWORDS];
+	unsigned long flags;
+	struct arm_smmu_cmdq_ent ent = {
+		.opcode = CMDQ_OP_CMD_SYNC,
+		.sync	= {
+			.msidata = atomic_inc_return_relaxed(&smmu->sync_nr),
+			.msiaddr = virt_to_phys(&smmu->sync_count),
+		},
+	};
+
+	arm_smmu_cmdq_build_cmd(cmd, &ent);
+
+	spin_lock_irqsave(&smmu->cmdq.lock, flags);
+	arm_smmu_cmdq_insert_cmd(smmu, cmd);
+	spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
+
+	return __arm_smmu_sync_poll_msi(smmu, ent.sync.msidata);
+}
+
+static int __arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
+{
+	u64 cmd[CMDQ_ENT_DWORDS];
+	unsigned long flags;
+	bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV);
+	struct arm_smmu_cmdq_ent ent = { .opcode = CMDQ_OP_CMD_SYNC };
+	int ret;
+
+	arm_smmu_cmdq_build_cmd(cmd, &ent);
+
+	spin_lock_irqsave(&smmu->cmdq.lock, flags);
+	arm_smmu_cmdq_insert_cmd(smmu, cmd);
+	ret = queue_poll_cons(&smmu->cmdq.q, true, wfe);
 	spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
+
+	return ret;
+}
+
+static void arm_smmu_cmdq_issue_sync(struct arm_smmu_device *smmu)
+{
+	int ret;
+	bool msi = (smmu->features & ARM_SMMU_FEAT_MSI) &&
+		   (smmu->features & ARM_SMMU_FEAT_COHERENCY);
+
+	ret = msi ? __arm_smmu_cmdq_issue_sync_msi(smmu)
+		  : __arm_smmu_cmdq_issue_sync(smmu);
+	if (ret)
+		dev_err_ratelimited(smmu->dev, "CMD_SYNC timeout\n");
 }
 
 /* Context descriptor manipulation functions */
@@ -996,6 +1086,11 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu,
 	      CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE |
 	      CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT |
 	      CTXDESC_CD_0_V;
+
+	/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
+	if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
+		val |= CTXDESC_CD_0_S;
+
 	cfg->cdptr[0] = cpu_to_le64(val);
 
 	val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT;
@@ -1029,8 +1124,7 @@ static void arm_smmu_sync_ste_for_sid(struct arm_smmu_device *smmu, u32 sid)
 	};
 
 	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
-	cmd.opcode = CMDQ_OP_CMD_SYNC;
-	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	arm_smmu_cmdq_issue_sync(smmu);
 }
 
 static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
@@ -1094,7 +1188,11 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 		dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING
 			 << STRTAB_STE_1_SHCFG_SHIFT);
 		dst[2] = 0; /* Nuke the VMID */
-		if (ste_live)
+		/*
+		 * The SMMU can perform negative caching, so we must sync
+		 * the STE regardless of whether the old value was live.
+		 */
+		if (smmu)
 			arm_smmu_sync_ste_for_sid(smmu, sid);
 		return;
 	}
@@ -1112,7 +1210,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 #endif
 			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
 
-		if (smmu->features & ARM_SMMU_FEAT_STALLS)
+		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
+		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
 			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
@@ -1275,12 +1374,6 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t arm_smmu_cmdq_sync_handler(int irq, void *dev)
-{
-	/* We don't actually use CMD_SYNC interrupts for anything */
-	return IRQ_HANDLED;
-}
-
 static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
 
 static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
@@ -1313,10 +1406,8 @@ static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
 	if (active & GERROR_MSI_EVTQ_ABT_ERR)
 		dev_warn(smmu->dev, "EVTQ MSI write aborted\n");
 
-	if (active & GERROR_MSI_CMDQ_ABT_ERR) {
+	if (active & GERROR_MSI_CMDQ_ABT_ERR)
 		dev_warn(smmu->dev, "CMDQ MSI write aborted\n");
-		arm_smmu_cmdq_sync_handler(irq, smmu->dev);
-	}
 
 	if (active & GERROR_PRIQ_ABT_ERR)
 		dev_err(smmu->dev, "PRIQ write aborted -- events may have been lost\n");
@@ -1345,17 +1436,13 @@ static irqreturn_t arm_smmu_combined_irq_thread(int irq, void *dev)
 static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev)
 {
 	arm_smmu_gerror_handler(irq, dev);
-	arm_smmu_cmdq_sync_handler(irq, dev);
 	return IRQ_WAKE_THREAD;
 }
 
 /* IO_PGTABLE API */
 static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
 {
-	struct arm_smmu_cmdq_ent cmd;
-
-	cmd.opcode = CMDQ_OP_CMD_SYNC;
-	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	arm_smmu_cmdq_issue_sync(smmu);
 }
 
 static void arm_smmu_tlb_sync(void *cookie)
@@ -1743,6 +1830,14 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu;
+
+	if (smmu)
+		__arm_smmu_tlb_sync(smmu);
+}
+
 static phys_addr_t
 arm_smmu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
@@ -1963,6 +2058,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
@@ -2147,6 +2244,7 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu)
 {
 	int ret;
 
+	atomic_set(&smmu->sync_nr, 0);
 	ret = arm_smmu_init_queues(smmu);
 	if (ret)
 		return ret;
@@ -2265,15 +2363,6 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu)
 			dev_warn(smmu->dev, "failed to enable evtq irq\n");
 	}
 
-	irq = smmu->cmdq.q.irq;
-	if (irq) {
-		ret = devm_request_irq(smmu->dev, irq,
-				       arm_smmu_cmdq_sync_handler, 0,
-				       "arm-smmu-v3-cmdq-sync", smmu);
-		if (ret < 0)
-			dev_warn(smmu->dev, "failed to enable cmdq-sync irq\n");
-	}
-
 	irq = smmu->gerr_irq;
 	if (irq) {
 		ret = devm_request_irq(smmu->dev, irq, arm_smmu_gerror_handler,
@@ -2399,8 +2488,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 	/* Invalidate any cached configuration */
 	cmd.opcode = CMDQ_OP_CFGI_ALL;
 	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
-	cmd.opcode = CMDQ_OP_CMD_SYNC;
-	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	arm_smmu_cmdq_issue_sync(smmu);
 
 	/* Invalidate any stale TLB entries */
 	if (smmu->features & ARM_SMMU_FEAT_HYP) {
@@ -2410,8 +2498,7 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass)
 
 	cmd.opcode = CMDQ_OP_TLBI_NSNH_ALL;
 	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
-	cmd.opcode = CMDQ_OP_CMD_SYNC;
-	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	arm_smmu_cmdq_issue_sync(smmu);
 
 	/* Event queue */
 	writeq_relaxed(smmu->evtq.q.q_base, smmu->base + ARM_SMMU_EVTQ_BASE);
@@ -2532,13 +2619,14 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	 * register, but warn on mismatch.
 	 */
 	if (!!(reg & IDR0_COHACC) != coherent)
-		dev_warn(smmu->dev, "IDR0.COHACC overridden by dma-coherent property (%s)\n",
+		dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n",
 			 coherent ? "true" : "false");
 
 	switch (reg & IDR0_STALL_MODEL_MASK << IDR0_STALL_MODEL_SHIFT) {
-	case IDR0_STALL_MODEL_STALL:
-		/* Fallthrough */
 	case IDR0_STALL_MODEL_FORCE:
+		smmu->features |= ARM_SMMU_FEAT_STALL_FORCE;
+		/* Fallthrough */
+	case IDR0_STALL_MODEL_STALL:
 		smmu->features |= ARM_SMMU_FEAT_STALLS;
 	}
 
@@ -2665,7 +2753,7 @@ static void acpi_smmu_get_options(u32 model, struct arm_smmu_device *smmu)
 	case ACPI_IORT_SMMU_V3_CAVIUM_CN99XX:
 		smmu->options |= ARM_SMMU_OPT_PAGE0_REGS_ONLY;
 		break;
-	case ACPI_IORT_SMMU_HISILICON_HI161X:
+	case ACPI_IORT_SMMU_V3_HISILICON_HI161X:
 		smmu->options |= ARM_SMMU_OPT_SKIP_PREFETCH;
 		break;
 	}
@@ -2783,10 +2871,6 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		if (irq > 0)
 			smmu->priq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "cmdq-sync");
-		if (irq > 0)
-			smmu->cmdq.q.irq = irq;
-
 		irq = platform_get_irq_byname(pdev, "gerror");
 		if (irq > 0)
 			smmu->gerr_irq = irq;
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 3bdb799d3b4b..78d4c6b8f1ba 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -59,6 +59,7 @@
 #define ARM_MMU500_ACTLR_CPRE		(1 << 1)
 
 #define ARM_MMU500_ACR_CACHE_LOCK	(1 << 26)
+#define ARM_MMU500_ACR_S2CRB_TLBEN	(1 << 10)
 #define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
 
 #define TLB_LOOP_TIMEOUT		1000000	/* 1s! */
@@ -119,14 +120,6 @@ enum arm_smmu_implementation {
 	CAVIUM_SMMUV2,
 };
 
-/* Until ACPICA headers cover IORT rev. C */
-#ifndef ACPI_IORT_SMMU_CORELINK_MMU401
-#define ACPI_IORT_SMMU_CORELINK_MMU401	0x4
-#endif
-#ifndef ACPI_IORT_SMMU_CAVIUM_THUNDERX
-#define ACPI_IORT_SMMU_CAVIUM_THUNDERX	0x5
-#endif
-
 struct arm_smmu_s2cr {
 	struct iommu_group		*group;
 	int				count;
@@ -250,6 +243,7 @@ enum arm_smmu_domain_stage {
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
+	const struct iommu_gather_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	struct mutex			init_mutex; /* Protects smmu pointer */
@@ -735,7 +729,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	enum io_pgtable_fmt fmt;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
-	const struct iommu_gather_ops *tlb_ops;
 
 	mutex_lock(&smmu_domain->init_mutex);
 	if (smmu_domain->smmu)
@@ -813,7 +806,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			ias = min(ias, 32UL);
 			oas = min(oas, 32UL);
 		}
-		tlb_ops = &arm_smmu_s1_tlb_ops;
+		smmu_domain->tlb_ops = &arm_smmu_s1_tlb_ops;
 		break;
 	case ARM_SMMU_DOMAIN_NESTED:
 		/*
@@ -833,9 +826,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 			oas = min(oas, 40UL);
 		}
 		if (smmu->version == ARM_SMMU_V2)
-			tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v2;
 		else
-			tlb_ops = &arm_smmu_s2_tlb_ops_v1;
+			smmu_domain->tlb_ops = &arm_smmu_s2_tlb_ops_v1;
 		break;
 	default:
 		ret = -EINVAL;
@@ -863,7 +856,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
 		.oas		= oas,
-		.tlb		= tlb_ops,
+		.tlb		= smmu_domain->tlb_ops,
 		.iommu_dev	= smmu->dev,
 	};
 
@@ -1259,6 +1252,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->tlb_ops)
+		smmu_domain->tlb_ops->tlb_sync(smmu_domain);
+}
+
 static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 					      dma_addr_t iova)
 {
@@ -1562,6 +1563,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
 	.map_sg			= default_iommu_map_sg,
+	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
@@ -1606,7 +1609,7 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 		 * Allow unmatched Stream IDs to allocate bypass
 		 * TLB entries for reduced latency.
 		 */
-		reg |= ARM_MMU500_ACR_SMTNMB_TLBEN;
+		reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN;
 		writel_relaxed(reg, gr0_base + ARM_SMMU_GR0_sACR);
 	}
 
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 9d1cebe7f6cb..25914d36c5ac 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -292,18 +292,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		/* ...then finally give it a kicking to make sure it fits */
 		base_pfn = max_t(unsigned long, base_pfn,
 				domain->geometry.aperture_start >> order);
-		end_pfn = min_t(unsigned long, end_pfn,
-				domain->geometry.aperture_end >> order);
 	}
-	/*
-	 * PCI devices may have larger DMA masks, but still prefer allocating
-	 * within a 32-bit mask to avoid DAC addressing. Such limitations don't
-	 * apply to the typical platform device, so for those we may as well
-	 * leave the cache limit at the top of their range to save an rb_last()
-	 * traversal on every allocation.
-	 */
-	if (dev && dev_is_pci(dev))
-		end_pfn &= DMA_BIT_MASK(32) >> order;
 
 	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
@@ -312,16 +301,11 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 			pr_warn("Incompatible range for DMA domain\n");
 			return -EFAULT;
 		}
-		/*
-		 * If we have devices with different DMA masks, move the free
-		 * area cache limit down for the benefit of the smaller one.
-		 */
-		iovad->dma_32bit_pfn = min(end_pfn + 1, iovad->dma_32bit_pfn);
 
 		return 0;
 	}
 
-	init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
+	init_iova_domain(iovad, 1UL << order, base_pfn);
 	if (!dev)
 		return 0;
 
@@ -386,10 +370,12 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 
 	/* Try to get PCI devices a SAC address */
 	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
-		iova = alloc_iova_fast(iovad, iova_len, DMA_BIT_MASK(32) >> shift);
+		iova = alloc_iova_fast(iovad, iova_len,
+				       DMA_BIT_MASK(32) >> shift, false);
 
 	if (!iova)
-		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift);
+		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
+				       true);
 
 	return (dma_addr_t)iova << shift;
 }
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 57c920c1372d..9a7ffd13c7f0 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -801,13 +801,16 @@ int __init dmar_dev_scope_init(void)
 				dmar_free_pci_notify_info(info);
 			}
 		}
-
-		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
 	}
 
 	return dmar_dev_scope_status;
 }
 
+void dmar_register_bus_notifier(void)
+{
+	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+}
+
 
 int __init dmar_table_init(void)
 {
@@ -1676,7 +1679,8 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		raw_spin_lock_irqsave(&iommu->register_lock, flag);
 	}
 
-	writel(DMA_FSTS_PFO | DMA_FSTS_PPF, iommu->reg + DMAR_FSTS_REG);
+	writel(DMA_FSTS_PFO | DMA_FSTS_PPF | DMA_FSTS_PRO,
+	       iommu->reg + DMAR_FSTS_REG);
 
 unlock_exit:
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 25c2c75f5332..79c45650f8de 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -263,6 +263,7 @@ struct exynos_iommu_domain {
 struct sysmmu_drvdata {
 	struct device *sysmmu;		/* SYSMMU controller device */
 	struct device *master;		/* master device (owner) */
+	struct device_link *link;	/* runtime PM link to master */
 	void __iomem *sfrbase;		/* our registers */
 	struct clk *clk;		/* SYSMMU's clock */
 	struct clk *aclk;		/* SYSMMU's aclk clock */
@@ -1250,6 +1251,8 @@ static struct iommu_group *get_device_iommu_group(struct device *dev)
 
 static int exynos_iommu_add_device(struct device *dev)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 	struct iommu_group *group;
 
 	if (!has_sysmmu(dev))
@@ -1260,6 +1263,15 @@ static int exynos_iommu_add_device(struct device *dev)
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
+	list_for_each_entry(data, &owner->controllers, owner_node) {
+		/*
+		 * SYSMMU will be runtime activated via device link
+		 * (dependency) to its master device, so there are no
+		 * direct calls to pm_runtime_get/put in this driver.
+		 */
+		data->link = device_link_add(dev, data->sysmmu,
+					     DL_FLAG_PM_RUNTIME);
+	}
 	iommu_group_put(group);
 
 	return 0;
@@ -1268,6 +1280,7 @@ static int exynos_iommu_add_device(struct device *dev)
 static void exynos_iommu_remove_device(struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+	struct sysmmu_drvdata *data;
 
 	if (!has_sysmmu(dev))
 		return;
@@ -1283,6 +1296,9 @@ static void exynos_iommu_remove_device(struct device *dev)
 		}
 	}
 	iommu_group_remove_device(dev);
+
+	list_for_each_entry(data, &owner->controllers, owner_node)
+		device_link_del(data->link);
 }
 
 static int exynos_iommu_of_xlate(struct device *dev,
@@ -1316,13 +1332,6 @@ static int exynos_iommu_of_xlate(struct device *dev,
 	list_add_tail(&data->owner_node, &owner->controllers);
 	data->master = dev;
 
-	/*
-	 * SYSMMU will be runtime activated via device link (dependency) to its
-	 * master device, so there are no direct calls to pm_runtime_get/put
-	 * in this driver.
-	 */
-	device_link_add(dev, data->sysmmu, DL_FLAG_PM_RUNTIME);
-
 	return 0;
 }
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 6784a05dd6b2..a0babdbf7146 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -82,8 +82,6 @@
 #define IOVA_START_PFN		(1)
 
 #define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
-#define DMA_32BIT_PFN		IOVA_PFN(DMA_BIT_MASK(32))
-#define DMA_64BIT_PFN		IOVA_PFN(DMA_BIT_MASK(64))
 
 /* page table handling */
 #define LEVEL_STRIDE		(9)
@@ -1878,8 +1876,7 @@ static int dmar_init_reserved_ranges(void)
 	struct iova *iova;
 	int i;
 
-	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN,
-			DMA_32BIT_PFN);
+	init_iova_domain(&reserved_iova_list, VTD_PAGE_SIZE, IOVA_START_PFN);
 
 	lockdep_set_class(&reserved_iova_list.iova_rbtree_lock,
 		&reserved_rbtree_key);
@@ -1938,8 +1935,7 @@ static int domain_init(struct dmar_domain *domain, struct intel_iommu *iommu,
 	unsigned long sagaw;
 	int err;
 
-	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
-			DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
 
 	err = init_iova_flush_queue(&domain->iovad,
 				    iommu_flush_iova, iova_entry_free);
@@ -2058,7 +2054,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	if (context_copied(context)) {
 		u16 did_old = context_domain_id(context);
 
-		if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) {
+		if (did_old < cap_ndoms(iommu->cap)) {
 			iommu->flush.flush_context(iommu, did_old,
 						   (((u16)bus) << 8) | devfn,
 						   DMA_CCMD_MASK_NOBIT,
@@ -3473,11 +3469,12 @@ static unsigned long intel_alloc_iova(struct device *dev,
 		 * from higher range
 		 */
 		iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
-					   IOVA_PFN(DMA_BIT_MASK(32)));
+					   IOVA_PFN(DMA_BIT_MASK(32)), false);
 		if (iova_pfn)
 			return iova_pfn;
 	}
-	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages, IOVA_PFN(dma_mask));
+	iova_pfn = alloc_iova_fast(&domain->iovad, nrpages,
+				   IOVA_PFN(dma_mask), true);
 	if (unlikely(!iova_pfn)) {
 		pr_err("Allocating %ld-page iova for %s failed",
 		       nrpages, dev_name(dev));
@@ -4752,6 +4749,16 @@ int __init intel_iommu_init(void)
 		goto out_free_dmar;
 	}
 
+	up_write(&dmar_global_lock);
+
+	/*
+	 * The bus notifier takes the dmar_global_lock, so lockdep will
+	 * complain later when we register it under the lock.
+	 */
+	dmar_register_bus_notifier();
+
+	down_write(&dmar_global_lock);
+
 	if (no_iommu || dmar_disabled) {
 		/*
 		 * We exit the function here to ensure IOMMU's remapping and
@@ -4897,8 +4904,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 {
 	int adjust_width;
 
-	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN,
-			DMA_32BIT_PFN);
+	init_iova_domain(&domain->iovad, VTD_PAGE_SIZE, IOVA_START_PFN);
 	domain_reserve_special_ranges(domain);
 
 	/* calculate AGAW */
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index f6697e55c2d4..ed1cf7c5a43b 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -292,7 +292,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 	int pasid_max;
 	int ret;
 
-	if (WARN_ON(!iommu))
+	if (WARN_ON(!iommu || !iommu->pasid_table))
 		return -EINVAL;
 
 	if (dev_is_pci(dev)) {
@@ -458,6 +458,8 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 				kfree_rcu(sdev, rcu);
 
 				if (list_empty(&svm->devs)) {
+					svm->iommu->pasid_table[svm->pasid].val = 0;
+					wmb();
 
 					idr_remove(&svm->iommu->pasid_idr, svm->pasid);
 					if (svm->mm)
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 6961fc393f0b..2ca08dc9331c 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -660,16 +660,11 @@ static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			 size_t size)
 {
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	size_t unmapped;
 
 	if (WARN_ON(upper_32_bits(iova)))
 		return 0;
 
-	unmapped = __arm_v7s_unmap(data, iova, size, 1, data->pgd);
-	if (unmapped)
-		io_pgtable_tlb_sync(&data->iop);
-
-	return unmapped;
+	return __arm_v7s_unmap(data, iova, size, 1, data->pgd);
 }
 
 static phys_addr_t arm_v7s_iova_to_phys(struct io_pgtable_ops *ops,
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index e8018a308868..51e5c43caed1 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -609,7 +609,6 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 			  size_t size)
 {
-	size_t unmapped;
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	arm_lpae_iopte *ptep = data->pgd;
 	int lvl = ARM_LPAE_START_LVL(data);
@@ -617,11 +616,7 @@ static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
 		return 0;
 
-	unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
-	if (unmapped)
-		io_pgtable_tlb_sync(&data->iop);
-
-	return unmapped;
+	return __arm_lpae_unmap(data, iova, size, lvl, ptep);
 }
 
 static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 33edfa794ae9..466aaa8ba841 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -24,6 +24,9 @@
 #include <linux/bitops.h>
 #include <linux/cpu.h>
 
+/* The anchor node sits above the top of the usable address space */
+#define IOVA_ANCHOR	~0UL
+
 static bool iova_rcache_insert(struct iova_domain *iovad,
 			       unsigned long pfn,
 			       unsigned long size);
@@ -37,7 +40,7 @@ static void fq_flush_timeout(unsigned long data);
 
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long granule,
-	unsigned long start_pfn, unsigned long pfn_32bit)
+	unsigned long start_pfn)
 {
 	/*
 	 * IOVA granularity will normally be equal to the smallest
@@ -48,12 +51,16 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 
 	spin_lock_init(&iovad->iova_rbtree_lock);
 	iovad->rbroot = RB_ROOT;
-	iovad->cached32_node = NULL;
+	iovad->cached_node = &iovad->anchor.node;
+	iovad->cached32_node = &iovad->anchor.node;
 	iovad->granule = granule;
 	iovad->start_pfn = start_pfn;
-	iovad->dma_32bit_pfn = pfn_32bit + 1;
+	iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
 	iovad->flush_cb = NULL;
 	iovad->fq = NULL;
+	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
+	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
+	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
 	init_iova_rcaches(iovad);
 }
 EXPORT_SYMBOL_GPL(init_iova_domain);
@@ -108,50 +115,36 @@ int init_iova_flush_queue(struct iova_domain *iovad,
 EXPORT_SYMBOL_GPL(init_iova_flush_queue);
 
 static struct rb_node *
-__get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
+__get_cached_rbnode(struct iova_domain *iovad, unsigned long limit_pfn)
 {
-	if ((*limit_pfn > iovad->dma_32bit_pfn) ||
-		(iovad->cached32_node == NULL))
-		return rb_last(&iovad->rbroot);
-	else {
-		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
-		struct iova *curr_iova =
-			rb_entry(iovad->cached32_node, struct iova, node);
-		*limit_pfn = curr_iova->pfn_lo;
-		return prev_node;
-	}
+	if (limit_pfn <= iovad->dma_32bit_pfn)
+		return iovad->cached32_node;
+
+	return iovad->cached_node;
 }
 
 static void
-__cached_rbnode_insert_update(struct iova_domain *iovad,
-	unsigned long limit_pfn, struct iova *new)
+__cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
 {
-	if (limit_pfn != iovad->dma_32bit_pfn)
-		return;
-	iovad->cached32_node = &new->node;
+	if (new->pfn_hi < iovad->dma_32bit_pfn)
+		iovad->cached32_node = &new->node;
+	else
+		iovad->cached_node = &new->node;
 }
 
 static void
 __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 {
 	struct iova *cached_iova;
-	struct rb_node *curr;
 
-	if (!iovad->cached32_node)
-		return;
-	curr = iovad->cached32_node;
-	cached_iova = rb_entry(curr, struct iova, node);
-
-	if (free->pfn_lo >= cached_iova->pfn_lo) {
-		struct rb_node *node = rb_next(&free->node);
-		struct iova *iova = rb_entry(node, struct iova, node);
+	cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
+	if (free->pfn_hi < iovad->dma_32bit_pfn &&
+	    free->pfn_lo >= cached_iova->pfn_lo)
+		iovad->cached32_node = rb_next(&free->node);
 
-		/* only cache if it's below 32bit pfn */
-		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
-			iovad->cached32_node = node;
-		else
-			iovad->cached32_node = NULL;
-	}
+	cached_iova = rb_entry(iovad->cached_node, struct iova, node);
+	if (free->pfn_lo >= cached_iova->pfn_lo)
+		iovad->cached_node = rb_next(&free->node);
 }
 
 /* Insert the iova into domain rbtree by holding writer lock */
@@ -182,63 +175,43 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova,
 	rb_insert_color(&iova->node, root);
 }
 
-/*
- * Computes the padding size required, to make the start address
- * naturally aligned on the power-of-two order of its size
- */
-static unsigned int
-iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
-{
-	return (limit_pfn - size) & (__roundup_pow_of_two(size) - 1);
-}
-
 static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		unsigned long size, unsigned long limit_pfn,
 			struct iova *new, bool size_aligned)
 {
-	struct rb_node *prev, *curr = NULL;
+	struct rb_node *curr, *prev;
+	struct iova *curr_iova;
 	unsigned long flags;
-	unsigned long saved_pfn;
-	unsigned int pad_size = 0;
+	unsigned long new_pfn;
+	unsigned long align_mask = ~0UL;
+
+	if (size_aligned)
+		align_mask <<= fls_long(size - 1);
 
 	/* Walk the tree backwards */
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
-	saved_pfn = limit_pfn;
-	curr = __get_cached_rbnode(iovad, &limit_pfn);
-	prev = curr;
-	while (curr) {
-		struct iova *curr_iova = rb_entry(curr, struct iova, node);
-
-		if (limit_pfn <= curr_iova->pfn_lo) {
-			goto move_left;
-		} else if (limit_pfn > curr_iova->pfn_hi) {
-			if (size_aligned)
-				pad_size = iova_get_pad_size(size, limit_pfn);
-			if ((curr_iova->pfn_hi + size + pad_size) < limit_pfn)
-				break;	/* found a free slot */
-		}
-		limit_pfn = curr_iova->pfn_lo;
-move_left:
+	curr = __get_cached_rbnode(iovad, limit_pfn);
+	curr_iova = rb_entry(curr, struct iova, node);
+	do {
+		limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
+		new_pfn = (limit_pfn - size) & align_mask;
 		prev = curr;
 		curr = rb_prev(curr);
-	}
+		curr_iova = rb_entry(curr, struct iova, node);
+	} while (curr && new_pfn <= curr_iova->pfn_hi);
 
-	if (!curr) {
-		if (size_aligned)
-			pad_size = iova_get_pad_size(size, limit_pfn);
-		if ((iovad->start_pfn + size + pad_size) > limit_pfn) {
-			spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-			return -ENOMEM;
-		}
+	if (limit_pfn < size || new_pfn < iovad->start_pfn) {
+		spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+		return -ENOMEM;
 	}
 
 	/* pfn_lo will point to size aligned address if size_aligned is set */
-	new->pfn_lo = limit_pfn - (size + pad_size);
+	new->pfn_lo = new_pfn;
 	new->pfn_hi = new->pfn_lo + size - 1;
 
 	/* If we have 'prev', it's a valid place to start the insertion. */
 	iova_insert_rbtree(&iovad->rbroot, new, prev);
-	__cached_rbnode_insert_update(iovad, saved_pfn, new);
+	__cached_rbnode_insert_update(iovad, new);
 
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 
@@ -258,7 +231,8 @@ EXPORT_SYMBOL(alloc_iova_mem);
 
 void free_iova_mem(struct iova *iova)
 {
-	kmem_cache_free(iova_cache, iova);
+	if (iova->pfn_lo != IOVA_ANCHOR)
+		kmem_cache_free(iova_cache, iova);
 }
 EXPORT_SYMBOL(free_iova_mem);
 
@@ -342,15 +316,12 @@ private_find_iova(struct iova_domain *iovad, unsigned long pfn)
 	while (node) {
 		struct iova *iova = rb_entry(node, struct iova, node);
 
-		/* If pfn falls within iova's range, return iova */
-		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
-			return iova;
-		}
-
 		if (pfn < iova->pfn_lo)
 			node = node->rb_left;
-		else if (pfn > iova->pfn_lo)
+		else if (pfn > iova->pfn_hi)
 			node = node->rb_right;
+		else
+			return iova;	/* pfn falls within iova's range */
 	}
 
 	return NULL;
@@ -424,18 +395,19 @@ EXPORT_SYMBOL_GPL(free_iova);
  * @iovad: - iova domain in question
  * @size: - size of page frames to allocate
  * @limit_pfn: - max limit address
+ * @flush_rcache: - set to flush rcache on regular allocation failure
  * This function tries to satisfy an iova allocation from the rcache,
- * and falls back to regular allocation on failure.
+ * and falls back to regular allocation on failure. If regular allocation
+ * fails too and the flush_rcache flag is set then the rcache will be flushed.
 */
 unsigned long
 alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
-		unsigned long limit_pfn)
+		unsigned long limit_pfn, bool flush_rcache)
 {
-	bool flushed_rcache = false;
 	unsigned long iova_pfn;
 	struct iova *new_iova;
 
-	iova_pfn = iova_rcache_get(iovad, size, limit_pfn);
+	iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
 	if (iova_pfn)
 		return iova_pfn;
 
@@ -444,11 +416,11 @@ retry:
 	if (!new_iova) {
 		unsigned int cpu;
 
-		if (flushed_rcache)
+		if (!flush_rcache)
 			return 0;
 
 		/* Try replenishing IOVAs by flushing rcache. */
-		flushed_rcache = true;
+		flush_rcache = false;
 		for_each_online_cpu(cpu)
 			free_cpu_cached_iovas(cpu, iovad);
 		goto retry;
@@ -570,7 +542,7 @@ void queue_iova(struct iova_domain *iovad,
 		unsigned long pfn, unsigned long pages,
 		unsigned long data)
 {
-	struct iova_fq *fq = get_cpu_ptr(iovad->fq);
+	struct iova_fq *fq = raw_cpu_ptr(iovad->fq);
 	unsigned long flags;
 	unsigned idx;
 
@@ -600,8 +572,6 @@ void queue_iova(struct iova_domain *iovad,
 	if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
 		mod_timer(&iovad->fq_timer,
 			  jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
-
-	put_cpu_ptr(iovad->fq);
 }
 EXPORT_SYMBOL_GPL(queue_iova);
 
@@ -612,21 +582,12 @@ EXPORT_SYMBOL_GPL(queue_iova);
  */
 void put_iova_domain(struct iova_domain *iovad)
 {
-	struct rb_node *node;
-	unsigned long flags;
+	struct iova *iova, *tmp;
 
 	free_iova_flush_queue(iovad);
 	free_iova_rcaches(iovad);
-	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
-	node = rb_first(&iovad->rbroot);
-	while (node) {
-		struct iova *iova = rb_entry(node, struct iova, node);
-
-		rb_erase(node, &iovad->rbroot);
+	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
 		free_iova_mem(iova);
-		node = rb_first(&iovad->rbroot);
-	}
-	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 }
 EXPORT_SYMBOL_GPL(put_iova_domain);
 
@@ -695,6 +656,10 @@ reserve_iova(struct iova_domain *iovad,
 	struct iova *iova;
 	unsigned int overlap = 0;
 
+	/* Don't allow nonsensical pfns */
+	if (WARN_ON((pfn_hi | pfn_lo) > (ULLONG_MAX >> iova_shift(iovad))))
+		return NULL;
+
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
 		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
@@ -738,6 +703,9 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 		struct iova *iova = rb_entry(node, struct iova, node);
 		struct iova *new_iova;
 
+		if (iova->pfn_lo == IOVA_ANCHOR)
+			continue;
+
 		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
 		if (!new_iova)
 			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
@@ -855,12 +823,21 @@ static bool iova_magazine_empty(struct iova_magazine *mag)
 static unsigned long iova_magazine_pop(struct iova_magazine *mag,
 				       unsigned long limit_pfn)
 {
+	int i;
+	unsigned long pfn;
+
 	BUG_ON(iova_magazine_empty(mag));
 
-	if (mag->pfns[mag->size - 1] >= limit_pfn)
-		return 0;
+	/* Only fall back to the rbtree if we have no suitable pfns at all */
+	for (i = mag->size - 1; mag->pfns[i] > limit_pfn; i--)
+		if (i == 0)
+			return 0;
 
-	return mag->pfns[--mag->size];
+	/* Swap it to pop it */
+	pfn = mag->pfns[i];
+	mag->pfns[i] = mag->pfns[--mag->size];
+
+	return pfn;
 }
 
 static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
@@ -1011,27 +988,7 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 	if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
 		return 0;
 
-	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn);
-}
-
-/*
- * Free a cpu's rcache.
- */
-static void free_cpu_iova_rcache(unsigned int cpu, struct iova_domain *iovad,
-				 struct iova_rcache *rcache)
-{
-	struct iova_cpu_rcache *cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
-	unsigned long flags;
-
-	spin_lock_irqsave(&cpu_rcache->lock, flags);
-
-	iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
-	iova_magazine_free(cpu_rcache->loaded);
-
-	iova_magazine_free_pfns(cpu_rcache->prev, iovad);
-	iova_magazine_free(cpu_rcache->prev);
-
-	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
+	return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
 }
 
 /*
@@ -1040,21 +997,20 @@ static void free_cpu_iova_rcache(unsigned int cpu, struct iova_domain *iovad,
 static void free_iova_rcaches(struct iova_domain *iovad)
 {
 	struct iova_rcache *rcache;
-	unsigned long flags;
+	struct iova_cpu_rcache *cpu_rcache;
 	unsigned int cpu;
 	int i, j;
 
 	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
 		rcache = &iovad->rcaches[i];
-		for_each_possible_cpu(cpu)
-			free_cpu_iova_rcache(cpu, iovad, rcache);
-		spin_lock_irqsave(&rcache->lock, flags);
+		for_each_possible_cpu(cpu) {
+			cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
+			iova_magazine_free(cpu_rcache->loaded);
+			iova_magazine_free(cpu_rcache->prev);
+		}
 		free_percpu(rcache->cpu_rcaches);
-		for (j = 0; j < rcache->depot_size; ++j) {
-			iova_magazine_free_pfns(rcache->depot[j], iovad);
+		for (j = 0; j < rcache->depot_size; ++j)
 			iova_magazine_free(rcache->depot[j]);
-		}
-		spin_unlock_irqrestore(&rcache->lock, flags);
 	}
 }
 
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 195d6e93ac71..8dce3a9de9d8 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -19,30 +19,49 @@
 #include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_iommu.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
+#include <linux/sys_soc.h>
 
 #if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
 #include <asm/dma-iommu.h>
 #include <asm/pgalloc.h>
+#else
+#define arm_iommu_create_mapping(...)	NULL
+#define arm_iommu_attach_device(...)	-ENODEV
+#define arm_iommu_release_mapping(...)	do {} while (0)
+#define arm_iommu_detach_device(...)	do {} while (0)
 #endif
 
 #include "io-pgtable.h"
 
-#define IPMMU_CTX_MAX 1
+#define IPMMU_CTX_MAX 8
+
+struct ipmmu_features {
+	bool use_ns_alias_offset;
+	bool has_cache_leaf_nodes;
+	unsigned int number_of_contexts;
+	bool setup_imbuscr;
+	bool twobit_imttbcr_sl0;
+};
 
 struct ipmmu_vmsa_device {
 	struct device *dev;
 	void __iomem *base;
 	struct iommu_device iommu;
-
+	struct ipmmu_vmsa_device *root;
+	const struct ipmmu_features *features;
 	unsigned int num_utlbs;
+	unsigned int num_ctx;
 	spinlock_t lock;			/* Protects ctx and domains[] */
 	DECLARE_BITMAP(ctx, IPMMU_CTX_MAX);
 	struct ipmmu_vmsa_domain *domains[IPMMU_CTX_MAX];
 
+	struct iommu_group *group;
 	struct dma_iommu_mapping *mapping;
 };
 
@@ -57,18 +76,12 @@ struct ipmmu_vmsa_domain {
 	spinlock_t lock;			/* Protects mappings */
 };
 
-struct ipmmu_vmsa_iommu_priv {
-	struct ipmmu_vmsa_device *mmu;
-	struct device *dev;
-	struct list_head list;
-};
-
 static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct ipmmu_vmsa_domain, io_domain);
 }
 
-static struct ipmmu_vmsa_iommu_priv *to_priv(struct device *dev)
+static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev)
 {
 	return dev->iommu_fwspec ? dev->iommu_fwspec->iommu_priv : NULL;
 }
@@ -133,6 +146,10 @@ static struct ipmmu_vmsa_iommu_priv *to_priv(struct device *dev)
 #define IMTTBCR_TSZ0_MASK		(7 << 0)
 #define IMTTBCR_TSZ0_SHIFT		O
 
+#define IMTTBCR_SL0_TWOBIT_LVL_3	(0 << 6)
+#define IMTTBCR_SL0_TWOBIT_LVL_2	(1 << 6)
+#define IMTTBCR_SL0_TWOBIT_LVL_1	(2 << 6)
+
 #define IMBUSCR				0x000c
 #define IMBUSCR_DVM			(1 << 2)
 #define IMBUSCR_BUSSEL_SYS		(0 << 0)
@@ -194,6 +211,36 @@ static struct ipmmu_vmsa_iommu_priv *to_priv(struct device *dev)
 #define IMUASID_ASID0_SHIFT		0
 
 /* -----------------------------------------------------------------------------
+ * Root device handling
+ */
+
+static struct platform_driver ipmmu_driver;
+
+static bool ipmmu_is_root(struct ipmmu_vmsa_device *mmu)
+{
+	return mmu->root == mmu;
+}
+
+static int __ipmmu_check_device(struct device *dev, void *data)
+{
+	struct ipmmu_vmsa_device *mmu = dev_get_drvdata(dev);
+	struct ipmmu_vmsa_device **rootp = data;
+
+	if (ipmmu_is_root(mmu))
+		*rootp = mmu;
+
+	return 0;
+}
+
+static struct ipmmu_vmsa_device *ipmmu_find_root(void)
+{
+	struct ipmmu_vmsa_device *root = NULL;
+
+	return driver_for_each_device(&ipmmu_driver.driver, NULL, &root,
+				      __ipmmu_check_device) == 0 ? root : NULL;
+}
+
+/* -----------------------------------------------------------------------------
  * Read/Write Access
  */
 
@@ -208,15 +255,29 @@ static void ipmmu_write(struct ipmmu_vmsa_device *mmu, unsigned int offset,
 	iowrite32(data, mmu->base + offset);
 }
 
-static u32 ipmmu_ctx_read(struct ipmmu_vmsa_domain *domain, unsigned int reg)
+static u32 ipmmu_ctx_read_root(struct ipmmu_vmsa_domain *domain,
+			       unsigned int reg)
 {
-	return ipmmu_read(domain->mmu, domain->context_id * IM_CTX_SIZE + reg);
+	return ipmmu_read(domain->mmu->root,
+			  domain->context_id * IM_CTX_SIZE + reg);
 }
 
-static void ipmmu_ctx_write(struct ipmmu_vmsa_domain *domain, unsigned int reg,
-			    u32 data)
+static void ipmmu_ctx_write_root(struct ipmmu_vmsa_domain *domain,
+				 unsigned int reg, u32 data)
 {
-	ipmmu_write(domain->mmu, domain->context_id * IM_CTX_SIZE + reg, data);
+	ipmmu_write(domain->mmu->root,
+		    domain->context_id * IM_CTX_SIZE + reg, data);
+}
+
+static void ipmmu_ctx_write_all(struct ipmmu_vmsa_domain *domain,
+				unsigned int reg, u32 data)
+{
+	if (domain->mmu != domain->mmu->root)
+		ipmmu_write(domain->mmu,
+			    domain->context_id * IM_CTX_SIZE + reg, data);
+
+	ipmmu_write(domain->mmu->root,
+		    domain->context_id * IM_CTX_SIZE + reg, data);
 }
 
 /* -----------------------------------------------------------------------------
@@ -228,7 +289,7 @@ static void ipmmu_tlb_sync(struct ipmmu_vmsa_domain *domain)
 {
 	unsigned int count = 0;
 
-	while (ipmmu_ctx_read(domain, IMCTR) & IMCTR_FLUSH) {
+	while (ipmmu_ctx_read_root(domain, IMCTR) & IMCTR_FLUSH) {
 		cpu_relax();
 		if (++count == TLB_LOOP_TIMEOUT) {
 			dev_err_ratelimited(domain->mmu->dev,
@@ -243,9 +304,9 @@ static void ipmmu_tlb_invalidate(struct ipmmu_vmsa_domain *domain)
 {
 	u32 reg;
 
-	reg = ipmmu_ctx_read(domain, IMCTR);
+	reg = ipmmu_ctx_read_root(domain, IMCTR);
 	reg |= IMCTR_FLUSH;
-	ipmmu_ctx_write(domain, IMCTR, reg);
+	ipmmu_ctx_write_all(domain, IMCTR, reg);
 
 	ipmmu_tlb_sync(domain);
 }
@@ -313,11 +374,12 @@ static int ipmmu_domain_allocate_context(struct ipmmu_vmsa_device *mmu,
 
 	spin_lock_irqsave(&mmu->lock, flags);
 
-	ret = find_first_zero_bit(mmu->ctx, IPMMU_CTX_MAX);
-	if (ret != IPMMU_CTX_MAX) {
+	ret = find_first_zero_bit(mmu->ctx, mmu->num_ctx);
+	if (ret != mmu->num_ctx) {
 		mmu->domains[ret] = domain;
 		set_bit(ret, mmu->ctx);
-	}
+	} else
+		ret = -EBUSY;
 
 	spin_unlock_irqrestore(&mmu->lock, flags);
 
@@ -340,6 +402,7 @@ static void ipmmu_domain_free_context(struct ipmmu_vmsa_device *mmu,
 static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 {
 	u64 ttbr;
+	u32 tmp;
 	int ret;
 
 	/*
@@ -364,51 +427,59 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 	 * TODO: Add support for coherent walk through CCI with DVM and remove
 	 * cache handling. For now, delegate it to the io-pgtable code.
 	 */
-	domain->cfg.iommu_dev = domain->mmu->dev;
+	domain->cfg.iommu_dev = domain->mmu->root->dev;
 
 	/*
 	 * Find an unused context.
 	 */
-	ret = ipmmu_domain_allocate_context(domain->mmu, domain);
-	if (ret == IPMMU_CTX_MAX)
-		return -EBUSY;
+	ret = ipmmu_domain_allocate_context(domain->mmu->root, domain);
+	if (ret < 0)
+		return ret;
 
 	domain->context_id = ret;
 
 	domain->iop = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &domain->cfg,
 					   domain);
 	if (!domain->iop) {
-		ipmmu_domain_free_context(domain->mmu, domain->context_id);
+		ipmmu_domain_free_context(domain->mmu->root,
+					  domain->context_id);
 		return -EINVAL;
 	}
 
 	/* TTBR0 */
 	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
-	ipmmu_ctx_write(domain, IMTTLBR0, ttbr);
-	ipmmu_ctx_write(domain, IMTTUBR0, ttbr >> 32);
+	ipmmu_ctx_write_root(domain, IMTTLBR0, ttbr);
+	ipmmu_ctx_write_root(domain, IMTTUBR0, ttbr >> 32);
 
 	/*
 	 * TTBCR
 	 * We use long descriptors with inner-shareable WBWA tables and allocate
 	 * the whole 32-bit VA space to TTBR0.
 	 */
-	ipmmu_ctx_write(domain, IMTTBCR, IMTTBCR_EAE |
-			IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
-			IMTTBCR_IRGN0_WB_WA | IMTTBCR_SL0_LVL_1);
+	if (domain->mmu->features->twobit_imttbcr_sl0)
+		tmp = IMTTBCR_SL0_TWOBIT_LVL_1;
+	else
+		tmp = IMTTBCR_SL0_LVL_1;
+
+	ipmmu_ctx_write_root(domain, IMTTBCR, IMTTBCR_EAE |
+			     IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
+			     IMTTBCR_IRGN0_WB_WA | tmp);
 
 	/* MAIR0 */
-	ipmmu_ctx_write(domain, IMMAIR0, domain->cfg.arm_lpae_s1_cfg.mair[0]);
+	ipmmu_ctx_write_root(domain, IMMAIR0,
+			     domain->cfg.arm_lpae_s1_cfg.mair[0]);
 
 	/* IMBUSCR */
-	ipmmu_ctx_write(domain, IMBUSCR,
-			ipmmu_ctx_read(domain, IMBUSCR) &
-			~(IMBUSCR_DVM | IMBUSCR_BUSSEL_MASK));
+	if (domain->mmu->features->setup_imbuscr)
+		ipmmu_ctx_write_root(domain, IMBUSCR,
+				     ipmmu_ctx_read_root(domain, IMBUSCR) &
+				     ~(IMBUSCR_DVM | IMBUSCR_BUSSEL_MASK));
 
 	/*
 	 * IMSTR
 	 * Clear all interrupt flags.
 	 */
-	ipmmu_ctx_write(domain, IMSTR, ipmmu_ctx_read(domain, IMSTR));
+	ipmmu_ctx_write_root(domain, IMSTR, ipmmu_ctx_read_root(domain, IMSTR));
 
 	/*
 	 * IMCTR
@@ -417,7 +488,8 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 	 * software management as we have no use for it. Flush the TLB as
 	 * required when modifying the context registers.
 	 */
-	ipmmu_ctx_write(domain, IMCTR, IMCTR_INTEN | IMCTR_FLUSH | IMCTR_MMUEN);
+	ipmmu_ctx_write_all(domain, IMCTR,
+			    IMCTR_INTEN | IMCTR_FLUSH | IMCTR_MMUEN);
 
 	return 0;
 }
@@ -430,9 +502,9 @@ static void ipmmu_domain_destroy_context(struct ipmmu_vmsa_domain *domain)
 	 *
 	 * TODO: Is TLB flush really needed ?
 	 */
-	ipmmu_ctx_write(domain, IMCTR, IMCTR_FLUSH);
+	ipmmu_ctx_write_all(domain, IMCTR, IMCTR_FLUSH);
 	ipmmu_tlb_sync(domain);
-	ipmmu_domain_free_context(domain->mmu, domain->context_id);
+	ipmmu_domain_free_context(domain->mmu->root, domain->context_id);
 }
 
 /* -----------------------------------------------------------------------------
@@ -446,11 +518,11 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
 	u32 status;
 	u32 iova;
 
-	status = ipmmu_ctx_read(domain, IMSTR);
+	status = ipmmu_ctx_read_root(domain, IMSTR);
 	if (!(status & err_mask))
 		return IRQ_NONE;
 
-	iova = ipmmu_ctx_read(domain, IMEAR);
+	iova = ipmmu_ctx_read_root(domain, IMEAR);
 
 	/*
 	 * Clear the error status flags. Unlike traditional interrupt flag
@@ -458,7 +530,7 @@ static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
 	 * seems to require 0. The error address register must be read before,
 	 * otherwise its value will be 0.
 	 */
-	ipmmu_ctx_write(domain, IMSTR, 0);
+	ipmmu_ctx_write_root(domain, IMSTR, 0);
 
 	/* Log fatal errors. */
 	if (status & IMSTR_MHIT)
@@ -499,7 +571,7 @@ static irqreturn_t ipmmu_irq(int irq, void *dev)
 	/*
 	 * Check interrupts for all active contexts.
 	 */
-	for (i = 0; i < IPMMU_CTX_MAX; i++) {
+	for (i = 0; i < mmu->num_ctx; i++) {
 		if (!mmu->domains[i])
 			continue;
 		if (ipmmu_domain_irq(mmu->domains[i]) == IRQ_HANDLED)
@@ -528,6 +600,27 @@ static struct iommu_domain *__ipmmu_domain_alloc(unsigned type)
 	return &domain->io_domain;
 }
 
+static struct iommu_domain *ipmmu_domain_alloc(unsigned type)
+{
+	struct iommu_domain *io_domain = NULL;
+
+	switch (type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		io_domain = __ipmmu_domain_alloc(type);
+		break;
+
+	case IOMMU_DOMAIN_DMA:
+		io_domain = __ipmmu_domain_alloc(type);
+		if (io_domain && iommu_get_dma_cookie(io_domain)) {
+			kfree(io_domain);
+			io_domain = NULL;
+		}
+		break;
+	}
+
+	return io_domain;
+}
+
 static void ipmmu_domain_free(struct iommu_domain *io_domain)
 {
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
@@ -536,6 +629,7 @@ static void ipmmu_domain_free(struct iommu_domain *io_domain)
 	 * Free the domain resources. We assume that all devices have already
 	 * been detached.
 	 */
+	iommu_put_dma_cookie(io_domain);
 	ipmmu_domain_destroy_context(domain);
 	free_io_pgtable_ops(domain->iop);
 	kfree(domain);
@@ -544,15 +638,14 @@ static void ipmmu_domain_free(struct iommu_domain *io_domain)
 static int ipmmu_attach_device(struct iommu_domain *io_domain,
 			       struct device *dev)
 {
-	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);
 	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
-	struct ipmmu_vmsa_device *mmu = priv->mmu;
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
 	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
 	unsigned long flags;
 	unsigned int i;
 	int ret = 0;
 
-	if (!priv || !priv->mmu) {
+	if (!mmu) {
 		dev_err(dev, "Cannot attach to IPMMU\n");
 		return -ENXIO;
 	}
@@ -563,6 +656,13 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain,
 		/* The domain hasn't been used yet, initialize it. */
 		domain->mmu = mmu;
 		ret = ipmmu_domain_init_context(domain);
+		if (ret < 0) {
+			dev_err(dev, "Unable to initialize IPMMU context\n");
+			domain->mmu = NULL;
+		} else {
+			dev_info(dev, "Using IPMMU context %u\n",
+				 domain->context_id);
+		}
 	} else if (domain->mmu != mmu) {
 		/*
 		 * Something is wrong, we can't attach two devices using
@@ -619,6 +719,14 @@ static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
 	return domain->iop->unmap(domain->iop, iova, size);
 }
 
+static void ipmmu_iotlb_sync(struct iommu_domain *io_domain)
+{
+	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
+
+	if (domain->mmu)
+		ipmmu_tlb_flush_all(domain);
+}
+
 static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
 				      dma_addr_t iova)
 {
@@ -633,62 +741,53 @@ static int ipmmu_init_platform_device(struct device *dev,
 				      struct of_phandle_args *args)
 {
 	struct platform_device *ipmmu_pdev;
-	struct ipmmu_vmsa_iommu_priv *priv;
 
 	ipmmu_pdev = of_find_device_by_node(args->np);
 	if (!ipmmu_pdev)
 		return -ENODEV;
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	priv->mmu = platform_get_drvdata(ipmmu_pdev);
-	priv->dev = dev;
-	dev->iommu_fwspec->iommu_priv = priv;
+	dev->iommu_fwspec->iommu_priv = platform_get_drvdata(ipmmu_pdev);
 	return 0;
 }
 
+static bool ipmmu_slave_whitelist(struct device *dev)
+{
+	/* By default, do not allow use of IPMMU */
+	return false;
+}
+
+static const struct soc_device_attribute soc_r8a7795[] = {
+	{ .soc_id = "r8a7795", },
+	{ /* sentinel */ }
+};
+
 static int ipmmu_of_xlate(struct device *dev,
 			  struct of_phandle_args *spec)
 {
+	/* For R-Car Gen3 use a white list to opt-in slave devices */
+	if (soc_device_match(soc_r8a7795) && !ipmmu_slave_whitelist(dev))
+		return -ENODEV;
+
 	iommu_fwspec_add_ids(dev, spec->args, 1);
 
 	/* Initialize once - xlate() will call multiple times */
-	if (to_priv(dev))
+	if (to_ipmmu(dev))
 		return 0;
 
 	return ipmmu_init_platform_device(dev, spec);
 }
 
-#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
-
-static struct iommu_domain *ipmmu_domain_alloc(unsigned type)
+static int ipmmu_init_arm_mapping(struct device *dev)
 {
-	if (type != IOMMU_DOMAIN_UNMANAGED)
-		return NULL;
-
-	return __ipmmu_domain_alloc(type);
-}
-
-static int ipmmu_add_device(struct device *dev)
-{
-	struct ipmmu_vmsa_device *mmu = NULL;
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
 	struct iommu_group *group;
 	int ret;
 
-	/*
-	 * Only let through devices that have been verified in xlate()
-	 */
-	if (!to_priv(dev))
-		return -ENODEV;
-
 	/* Create a device group and add the device to it. */
 	group = iommu_group_alloc();
 	if (IS_ERR(group)) {
 		dev_err(dev, "Failed to allocate IOMMU group\n");
-		ret = PTR_ERR(group);
-		goto error;
+		return PTR_ERR(group);
 	}
 
 	ret = iommu_group_add_device(group, dev);
@@ -696,8 +795,7 @@ static int ipmmu_add_device(struct device *dev)
 
 	if (ret < 0) {
 		dev_err(dev, "Failed to add device to IPMMU group\n");
-		group = NULL;
-		goto error;
+		return ret;
 	}
 
 	/*
@@ -709,7 +807,6 @@ static int ipmmu_add_device(struct device *dev)
 	 * - Make the mapping size configurable ? We currently use a 2GB mapping
 	 *   at a 1GB offset to ensure that NULL VAs will fault.
 	 */
-	mmu = to_priv(dev)->mmu;
 	if (!mmu->mapping) {
 		struct dma_iommu_mapping *mapping;
 
@@ -734,159 +831,73 @@ static int ipmmu_add_device(struct device *dev)
 	return 0;
 
 error:
-	if (mmu)
+	iommu_group_remove_device(dev);
+	if (mmu->mapping)
 		arm_iommu_release_mapping(mmu->mapping);
 
-	if (!IS_ERR_OR_NULL(group))
-		iommu_group_remove_device(dev);
-
 	return ret;
 }
 
-static void ipmmu_remove_device(struct device *dev)
-{
-	arm_iommu_detach_device(dev);
-	iommu_group_remove_device(dev);
-}
-
-static const struct iommu_ops ipmmu_ops = {
-	.domain_alloc = ipmmu_domain_alloc,
-	.domain_free = ipmmu_domain_free,
-	.attach_dev = ipmmu_attach_device,
-	.detach_dev = ipmmu_detach_device,
-	.map = ipmmu_map,
-	.unmap = ipmmu_unmap,
-	.map_sg = default_iommu_map_sg,
-	.iova_to_phys = ipmmu_iova_to_phys,
-	.add_device = ipmmu_add_device,
-	.remove_device = ipmmu_remove_device,
-	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
-	.of_xlate = ipmmu_of_xlate,
-};
-
-#endif /* !CONFIG_ARM && CONFIG_IOMMU_DMA */
-
-#ifdef CONFIG_IOMMU_DMA
-
-static DEFINE_SPINLOCK(ipmmu_slave_devices_lock);
-static LIST_HEAD(ipmmu_slave_devices);
-
-static struct iommu_domain *ipmmu_domain_alloc_dma(unsigned type)
-{
-	struct iommu_domain *io_domain = NULL;
-
-	switch (type) {
-	case IOMMU_DOMAIN_UNMANAGED:
-		io_domain = __ipmmu_domain_alloc(type);
-		break;
-
-	case IOMMU_DOMAIN_DMA:
-		io_domain = __ipmmu_domain_alloc(type);
-		if (io_domain)
-			iommu_get_dma_cookie(io_domain);
-		break;
-	}
-
-	return io_domain;
-}
-
-static void ipmmu_domain_free_dma(struct iommu_domain *io_domain)
-{
-	switch (io_domain->type) {
-	case IOMMU_DOMAIN_DMA:
-		iommu_put_dma_cookie(io_domain);
-		/* fall-through */
-	default:
-		ipmmu_domain_free(io_domain);
-		break;
-	}
-}
-
-static int ipmmu_add_device_dma(struct device *dev)
+static int ipmmu_add_device(struct device *dev)
 {
 	struct iommu_group *group;
 
 	/*
 	 * Only let through devices that have been verified in xlate()
 	 */
-	if (!to_priv(dev))
+	if (!to_ipmmu(dev))
 		return -ENODEV;
 
+	if (IS_ENABLED(CONFIG_ARM) && !IS_ENABLED(CONFIG_IOMMU_DMA))
+		return ipmmu_init_arm_mapping(dev);
+
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
 		return PTR_ERR(group);
 
-	spin_lock(&ipmmu_slave_devices_lock);
-	list_add(&to_priv(dev)->list, &ipmmu_slave_devices);
-	spin_unlock(&ipmmu_slave_devices_lock);
+	iommu_group_put(group);
 	return 0;
 }
 
-static void ipmmu_remove_device_dma(struct device *dev)
+static void ipmmu_remove_device(struct device *dev)
 {
-	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);
-
-	spin_lock(&ipmmu_slave_devices_lock);
-	list_del(&priv->list);
-	spin_unlock(&ipmmu_slave_devices_lock);
-
+	arm_iommu_detach_device(dev);
 	iommu_group_remove_device(dev);
 }
 
-static struct device *ipmmu_find_sibling_device(struct device *dev)
-{
-	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);
-	struct ipmmu_vmsa_iommu_priv *sibling_priv = NULL;
-	bool found = false;
-
-	spin_lock(&ipmmu_slave_devices_lock);
-
-	list_for_each_entry(sibling_priv, &ipmmu_slave_devices, list) {
-		if (priv == sibling_priv)
-			continue;
-		if (sibling_priv->mmu == priv->mmu) {
-			found = true;
-			break;
-		}
-	}
-
-	spin_unlock(&ipmmu_slave_devices_lock);
-
-	return found ? sibling_priv->dev : NULL;
-}
-
-static struct iommu_group *ipmmu_find_group_dma(struct device *dev)
+static struct iommu_group *ipmmu_find_group(struct device *dev)
 {
+	struct ipmmu_vmsa_device *mmu = to_ipmmu(dev);
 	struct iommu_group *group;
-	struct device *sibling;
 
-	sibling = ipmmu_find_sibling_device(dev);
-	if (sibling)
-		group = iommu_group_get(sibling);
-	if (!sibling || IS_ERR(group))
-		group = generic_device_group(dev);
+	if (mmu->group)
+		return iommu_group_ref_get(mmu->group);
+
+	group = iommu_group_alloc();
+	if (!IS_ERR(group))
+		mmu->group = group;
 
 	return group;
 }
 
 static const struct iommu_ops ipmmu_ops = {
-	.domain_alloc = ipmmu_domain_alloc_dma,
-	.domain_free = ipmmu_domain_free_dma,
+	.domain_alloc = ipmmu_domain_alloc,
+	.domain_free = ipmmu_domain_free,
 	.attach_dev = ipmmu_attach_device,
 	.detach_dev = ipmmu_detach_device,
 	.map = ipmmu_map,
 	.unmap = ipmmu_unmap,
+	.flush_iotlb_all = ipmmu_iotlb_sync,
+	.iotlb_sync = ipmmu_iotlb_sync,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = ipmmu_iova_to_phys,
-	.add_device = ipmmu_add_device_dma,
-	.remove_device = ipmmu_remove_device_dma,
-	.device_group = ipmmu_find_group_dma,
+	.add_device = ipmmu_add_device,
+	.remove_device = ipmmu_remove_device,
+	.device_group = ipmmu_find_group,
 	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
 	.of_xlate = ipmmu_of_xlate,
 };
 
-#endif /* CONFIG_IOMMU_DMA */
-
 /* -----------------------------------------------------------------------------
  * Probe/remove and init
  */
@@ -896,10 +907,40 @@ static void ipmmu_device_reset(struct ipmmu_vmsa_device *mmu)
 	unsigned int i;
 
 	/* Disable all contexts. */
-	for (i = 0; i < 4; ++i)
+	for (i = 0; i < mmu->num_ctx; ++i)
 		ipmmu_write(mmu, i * IM_CTX_SIZE + IMCTR, 0);
 }
 
+static const struct ipmmu_features ipmmu_features_default = {
+	.use_ns_alias_offset = true,
+	.has_cache_leaf_nodes = false,
+	.number_of_contexts = 1, /* software only tested with one context */
+	.setup_imbuscr = true,
+	.twobit_imttbcr_sl0 = false,
+};
+
+static const struct ipmmu_features ipmmu_features_r8a7795 = {
+	.use_ns_alias_offset = false,
+	.has_cache_leaf_nodes = true,
+	.number_of_contexts = 8,
+	.setup_imbuscr = false,
+	.twobit_imttbcr_sl0 = true,
+};
+
+static const struct of_device_id ipmmu_of_ids[] = {
+	{
+		.compatible = "renesas,ipmmu-vmsa",
+		.data = &ipmmu_features_default,
+	}, {
+		.compatible = "renesas,ipmmu-r8a7795",
+		.data = &ipmmu_features_r8a7795,
+	}, {
+		/* Terminator */
+	},
+};
+
+MODULE_DEVICE_TABLE(of, ipmmu_of_ids);
+
 static int ipmmu_probe(struct platform_device *pdev)
 {
 	struct ipmmu_vmsa_device *mmu;
@@ -917,6 +958,8 @@ static int ipmmu_probe(struct platform_device *pdev)
 	mmu->num_utlbs = 32;
 	spin_lock_init(&mmu->lock);
 	bitmap_zero(mmu->ctx, IPMMU_CTX_MAX);
+	mmu->features = of_device_get_match_data(&pdev->dev);
+	dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
 
 	/* Map I/O memory and request IRQ. */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -936,34 +979,71 @@ static int ipmmu_probe(struct platform_device *pdev)
 	 * Offset the registers base unconditionally to point to the non-secure
 	 * alias space for now.
 	 */
-	mmu->base += IM_NS_ALIAS_OFFSET;
+	if (mmu->features->use_ns_alias_offset)
+		mmu->base += IM_NS_ALIAS_OFFSET;
+
+	mmu->num_ctx = min_t(unsigned int, IPMMU_CTX_MAX,
+			     mmu->features->number_of_contexts);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev, "no IRQ found\n");
-		return irq;
-	}
 
-	ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0,
-			       dev_name(&pdev->dev), mmu);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to request IRQ %d\n", irq);
-		return ret;
-	}
+	/*
+	 * Determine if this IPMMU instance is a root device by checking for
+	 * the lack of has_cache_leaf_nodes flag or renesas,ipmmu-main property.
+	 */
+	if (!mmu->features->has_cache_leaf_nodes ||
+	    !of_find_property(pdev->dev.of_node, "renesas,ipmmu-main", NULL))
+		mmu->root = mmu;
+	else
+		mmu->root = ipmmu_find_root();
 
-	ipmmu_device_reset(mmu);
+	/*
+	 * Wait until the root device has been registered for sure.
+	 */
+	if (!mmu->root)
+		return -EPROBE_DEFER;
+
+	/* Root devices have mandatory IRQs */
+	if (ipmmu_is_root(mmu)) {
+		if (irq < 0) {
+			dev_err(&pdev->dev, "no IRQ found\n");
+			return irq;
+		}
 
-	ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL,
-				     dev_name(&pdev->dev));
-	if (ret)
-		return ret;
+		ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0,
+				       dev_name(&pdev->dev), mmu);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "failed to request IRQ %d\n", irq);
+			return ret;
+		}
 
-	iommu_device_set_ops(&mmu->iommu, &ipmmu_ops);
-	iommu_device_set_fwnode(&mmu->iommu, &pdev->dev.of_node->fwnode);
+		ipmmu_device_reset(mmu);
+	}
 
-	ret = iommu_device_register(&mmu->iommu);
-	if (ret)
-		return ret;
+	/*
+	 * Register the IPMMU to the IOMMU subsystem in the following cases:
+	 * - R-Car Gen2 IPMMU (all devices registered)
+	 * - R-Car Gen3 IPMMU (leaf devices only - skip root IPMMU-MM device)
+	 */
+	if (!mmu->features->has_cache_leaf_nodes || !ipmmu_is_root(mmu)) {
+		ret = iommu_device_sysfs_add(&mmu->iommu, &pdev->dev, NULL,
+					     dev_name(&pdev->dev));
+		if (ret)
+			return ret;
+
+		iommu_device_set_ops(&mmu->iommu, &ipmmu_ops);
+		iommu_device_set_fwnode(&mmu->iommu,
+					&pdev->dev.of_node->fwnode);
+
+		ret = iommu_device_register(&mmu->iommu);
+		if (ret)
+			return ret;
+
+#if defined(CONFIG_IOMMU_DMA)
+		if (!iommu_present(&platform_bus_type))
+			bus_set_iommu(&platform_bus_type, &ipmmu_ops);
+#endif
+	}
 
 	/*
 	 * We can't create the ARM mapping here as it requires the bus to have
@@ -983,20 +1063,13 @@ static int ipmmu_remove(struct platform_device *pdev)
 	iommu_device_sysfs_remove(&mmu->iommu);
 	iommu_device_unregister(&mmu->iommu);
 
-#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
 	arm_iommu_release_mapping(mmu->mapping);
-#endif
 
 	ipmmu_device_reset(mmu);
 
 	return 0;
 }
 
-static const struct of_device_id ipmmu_of_ids[] = {
-	{ .compatible = "renesas,ipmmu-vmsa", },
-	{ }
-};
-
 static struct platform_driver ipmmu_driver = {
 	.driver = {
 		.name = "ipmmu-vmsa",
@@ -1008,15 +1081,22 @@ static struct platform_driver ipmmu_driver = {
 
 static int __init ipmmu_init(void)
 {
+	static bool setup_done;
 	int ret;
 
+	if (setup_done)
+		return 0;
+
 	ret = platform_driver_register(&ipmmu_driver);
 	if (ret < 0)
 		return ret;
 
+#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
 	if (!iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, &ipmmu_ops);
+#endif
 
+	setup_done = true;
 	return 0;
 }
 
@@ -1028,6 +1108,19 @@ static void __exit ipmmu_exit(void)
 subsys_initcall(ipmmu_init);
 module_exit(ipmmu_exit);
 
+#ifdef CONFIG_IOMMU_DMA
+static int __init ipmmu_vmsa_iommu_of_setup(struct device_node *np)
+{
+	ipmmu_init();
+	return 0;
+}
+
+IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa",
+		 ipmmu_vmsa_iommu_of_setup);
+IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795",
+		 ipmmu_vmsa_iommu_of_setup);
+#endif
+
 MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU");
 MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 16d33ac19db0..f227d73e7bf6 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -392,6 +392,11 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 	return unmapsz;
 }
 
+static void mtk_iommu_iotlb_sync(struct iommu_domain *domain)
+{
+	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+}
+
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 					  dma_addr_t iova)
 {
@@ -491,6 +496,8 @@ static struct iommu_ops mtk_iommu_ops = {
 	.map		= mtk_iommu_map,
 	.unmap		= mtk_iommu_unmap,
 	.map_sg		= default_iommu_map_sg,
+	.flush_iotlb_all = mtk_iommu_iotlb_sync,
+	.iotlb_sync	= mtk_iommu_iotlb_sync,
 	.iova_to_phys	= mtk_iommu_iova_to_phys,
 	.add_device	= mtk_iommu_add_device,
 	.remove_device	= mtk_iommu_remove_device,
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index bc1efbfb9ddf..542930cd183d 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -708,7 +708,7 @@ static struct platform_driver mtk_iommu_driver = {
 	.probe	= mtk_iommu_probe,
 	.remove	= mtk_iommu_remove,
 	.driver	= {
-		.name = "mtk-iommu",
+		.name = "mtk-iommu-v1",
 		.of_match_table = mtk_iommu_of_ids,
 		.pm = &mtk_iommu_pm_ops,
 	}
diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c
index bd67e1b2c64e..e135ab830ebf 100644
--- a/drivers/iommu/omap-iommu.c
+++ b/drivers/iommu/omap-iommu.c
@@ -2,6 +2,7 @@
  * omap iommu: tlb and pagetable primitives
  *
  * Copyright (C) 2008-2010 Nokia Corporation
+ * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
  *
  * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>,
  *		Paul Mundt and Toshihiro Kobayashi
@@ -71,13 +72,23 @@ static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom)
  **/
 void omap_iommu_save_ctx(struct device *dev)
 {
-	struct omap_iommu *obj = dev_to_omap_iommu(dev);
-	u32 *p = obj->ctx;
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu *obj;
+	u32 *p;
 	int i;
 
-	for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
-		p[i] = iommu_read_reg(obj, i * sizeof(u32));
-		dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]);
+	if (!arch_data)
+		return;
+
+	while (arch_data->iommu_dev) {
+		obj = arch_data->iommu_dev;
+		p = obj->ctx;
+		for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
+			p[i] = iommu_read_reg(obj, i * sizeof(u32));
+			dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i,
+				p[i]);
+		}
+		arch_data++;
 	}
 }
 EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
@@ -88,13 +99,23 @@ EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);
  **/
 void omap_iommu_restore_ctx(struct device *dev)
 {
-	struct omap_iommu *obj = dev_to_omap_iommu(dev);
-	u32 *p = obj->ctx;
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu *obj;
+	u32 *p;
 	int i;
 
-	for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
-		iommu_write_reg(obj, p[i], i * sizeof(u32));
-		dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i, p[i]);
+	if (!arch_data)
+		return;
+
+	while (arch_data->iommu_dev) {
+		obj = arch_data->iommu_dev;
+		p = obj->ctx;
+		for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
+			iommu_write_reg(obj, p[i], i * sizeof(u32));
+			dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i,
+				p[i]);
+		}
+		arch_data++;
 	}
 }
 EXPORT_SYMBOL_GPL(omap_iommu_restore_ctx);
@@ -805,7 +826,7 @@ static irqreturn_t iommu_fault_handler(int irq, void *data)
 	struct iommu_domain *domain = obj->domain;
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 
-	if (!omap_domain->iommu_dev)
+	if (!omap_domain->dev)
 		return IRQ_NONE;
 
 	errs = iommu_report_fault(obj, &da);
@@ -893,6 +914,24 @@ static void omap_iommu_detach(struct omap_iommu *obj)
 	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
 }
 
+static bool omap_iommu_can_register(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+
+	if (!of_device_is_compatible(np, "ti,dra7-dsp-iommu"))
+		return true;
+
+	/*
+	 * restrict IOMMU core registration only for processor-port MDMA MMUs
+	 * on DRA7 DSPs
+	 */
+	if ((!strcmp(dev_name(&pdev->dev), "40d01000.mmu")) ||
+	    (!strcmp(dev_name(&pdev->dev), "41501000.mmu")))
+		return true;
+
+	return false;
+}
+
 static int omap_iommu_dra7_get_dsp_system_cfg(struct platform_device *pdev,
 					      struct omap_iommu *obj)
 {
@@ -984,19 +1023,22 @@ static int omap_iommu_probe(struct platform_device *pdev)
 		return err;
 	platform_set_drvdata(pdev, obj);
 
-	obj->group = iommu_group_alloc();
-	if (IS_ERR(obj->group))
-		return PTR_ERR(obj->group);
+	if (omap_iommu_can_register(pdev)) {
+		obj->group = iommu_group_alloc();
+		if (IS_ERR(obj->group))
+			return PTR_ERR(obj->group);
 
-	err = iommu_device_sysfs_add(&obj->iommu, obj->dev, NULL, obj->name);
-	if (err)
-		goto out_group;
+		err = iommu_device_sysfs_add(&obj->iommu, obj->dev, NULL,
+					     obj->name);
+		if (err)
+			goto out_group;
 
-	iommu_device_set_ops(&obj->iommu, &omap_iommu_ops);
+		iommu_device_set_ops(&obj->iommu, &omap_iommu_ops);
 
-	err = iommu_device_register(&obj->iommu);
-	if (err)
-		goto out_sysfs;
+		err = iommu_device_register(&obj->iommu);
+		if (err)
+			goto out_sysfs;
+	}
 
 	pm_runtime_irq_safe(obj->dev);
 	pm_runtime_enable(obj->dev);
@@ -1018,11 +1060,13 @@ static int omap_iommu_remove(struct platform_device *pdev)
 {
 	struct omap_iommu *obj = platform_get_drvdata(pdev);
 
-	iommu_group_put(obj->group);
-	obj->group = NULL;
+	if (obj->group) {
+		iommu_group_put(obj->group);
+		obj->group = NULL;
 
-	iommu_device_sysfs_remove(&obj->iommu);
-	iommu_device_unregister(&obj->iommu);
+		iommu_device_sysfs_remove(&obj->iommu);
+		iommu_device_unregister(&obj->iommu);
+	}
 
 	omap_iommu_debugfs_remove(obj);
 
@@ -1068,11 +1112,13 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 			  phys_addr_t pa, size_t bytes, int prot)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu = omap_domain->iommu_dev;
-	struct device *dev = oiommu->dev;
+	struct device *dev = omap_domain->dev;
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
 	struct iotlb_entry e;
 	int omap_pgsz;
-	u32 ret;
+	u32 ret = -EINVAL;
+	int i;
 
 	omap_pgsz = bytes_to_iopgsz(bytes);
 	if (omap_pgsz < 0) {
@@ -1084,9 +1130,24 @@ static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
 
 	iotlb_init_entry(&e, da, pa, omap_pgsz);
 
-	ret = omap_iopgtable_store_entry(oiommu, &e);
-	if (ret)
-		dev_err(dev, "omap_iopgtable_store_entry failed: %d\n", ret);
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		ret = omap_iopgtable_store_entry(oiommu, &e);
+		if (ret) {
+			dev_err(dev, "omap_iopgtable_store_entry failed: %d\n",
+				ret);
+			break;
+		}
+	}
+
+	if (ret) {
+		while (i--) {
+			iommu--;
+			oiommu = iommu->iommu_dev;
+			iopgtable_clear_entry(oiommu, da);
+		}
+	}
 
 	return ret;
 }
@@ -1095,12 +1156,90 @@ static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
 			       size_t size)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu = omap_domain->iommu_dev;
-	struct device *dev = oiommu->dev;
+	struct device *dev = omap_domain->dev;
+	struct omap_iommu_device *iommu;
+	struct omap_iommu *oiommu;
+	bool error = false;
+	size_t bytes = 0;
+	int i;
 
 	dev_dbg(dev, "unmapping da 0x%lx size %u\n", da, size);
 
-	return iopgtable_clear_entry(oiommu, da);
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
+		oiommu = iommu->iommu_dev;
+		bytes = iopgtable_clear_entry(oiommu, da);
+		if (!bytes)
+			error = true;
+	}
+
+	/*
+	 * simplify return - we are only checking if any of the iommus
+	 * reported an error, but not if all of them are unmapping the
+	 * same number of entries. This should not occur due to the
+	 * mirror programming.
+	 */
+	return error ? 0 : bytes;
+}
+
+static int omap_iommu_count(struct device *dev)
+{
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	int count = 0;
+
+	while (arch_data->iommu_dev) {
+		count++;
+		arch_data++;
+	}
+
+	return count;
+}
+
+/* caller should call cleanup if this function fails */
+static int omap_iommu_attach_init(struct device *dev,
+				  struct omap_iommu_domain *odomain)
+{
+	struct omap_iommu_device *iommu;
+	int i;
+
+	odomain->num_iommus = omap_iommu_count(dev);
+	if (!odomain->num_iommus)
+		return -EINVAL;
+
+	odomain->iommus = kcalloc(odomain->num_iommus, sizeof(*iommu),
+				  GFP_ATOMIC);
+	if (!odomain->iommus)
+		return -ENOMEM;
+
+	iommu = odomain->iommus;
+	for (i = 0; i < odomain->num_iommus; i++, iommu++) {
+		iommu->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_ATOMIC);
+		if (!iommu->pgtable)
+			return -ENOMEM;
+
+		/*
+		 * should never fail, but please keep this around to ensure
+		 * we keep the hardware happy
+		 */
+		if (WARN_ON(!IS_ALIGNED((long)iommu->pgtable,
+					IOPGD_TABLE_SIZE)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void omap_iommu_detach_fini(struct omap_iommu_domain *odomain)
+{
+	int i;
+	struct omap_iommu_device *iommu = odomain->iommus;
+
+	for (i = 0; iommu && i < odomain->num_iommus; i++, iommu++)
+		kfree(iommu->pgtable);
+
+	kfree(odomain->iommus);
+	odomain->num_iommus = 0;
+	odomain->iommus = NULL;
 }
 
 static int
@@ -1108,8 +1247,10 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu_device *iommu;
 	struct omap_iommu *oiommu;
 	int ret = 0;
+	int i;
 
 	if (!arch_data || !arch_data->iommu_dev) {
 		dev_err(dev, "device doesn't have an associated iommu\n");
@@ -1118,26 +1259,49 @@ omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	spin_lock(&omap_domain->lock);
 
-	/* only a single device is supported per domain for now */
-	if (omap_domain->iommu_dev) {
+	/* only a single client device can be attached to a domain */
+	if (omap_domain->dev) {
 		dev_err(dev, "iommu domain is already attached\n");
 		ret = -EBUSY;
 		goto out;
 	}
 
-	oiommu = arch_data->iommu_dev;
-
-	/* get a handle to and enable the omap iommu */
-	ret = omap_iommu_attach(oiommu, omap_domain->pgtable);
+	ret = omap_iommu_attach_init(dev, omap_domain);
 	if (ret) {
-		dev_err(dev, "can't get omap iommu: %d\n", ret);
-		goto out;
+		dev_err(dev, "failed to allocate required iommu data %d\n",
+			ret);
+		goto init_fail;
+	}
+
+	iommu = omap_domain->iommus;
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu++, arch_data++) {
+		/* configure and enable the omap iommu */
+		oiommu = arch_data->iommu_dev;
+		ret = omap_iommu_attach(oiommu, iommu->pgtable);
+		if (ret) {
+			dev_err(dev, "can't get omap iommu: %d\n", ret);
+			goto attach_fail;
+		}
+
+		oiommu->domain = domain;
+		iommu->iommu_dev = oiommu;
 	}
 
-	omap_domain->iommu_dev = oiommu;
 	omap_domain->dev = dev;
-	oiommu->domain = domain;
 
+	goto out;
+
+attach_fail:
+	while (i--) {
+		iommu--;
+		arch_data--;
+		oiommu = iommu->iommu_dev;
+		omap_iommu_detach(oiommu);
+		iommu->iommu_dev = NULL;
+		oiommu->domain = NULL;
+	}
+init_fail:
+	omap_iommu_detach_fini(omap_domain);
 out:
 	spin_unlock(&omap_domain->lock);
 	return ret;
@@ -1146,21 +1310,40 @@ out:
 static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
 				   struct device *dev)
 {
-	struct omap_iommu *oiommu = dev_to_omap_iommu(dev);
+	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+	struct omap_iommu_device *iommu = omap_domain->iommus;
+	struct omap_iommu *oiommu;
+	int i;
+
+	if (!omap_domain->dev) {
+		dev_err(dev, "domain has no attached device\n");
+		return;
+	}
 
 	/* only a single device is supported per domain for now */
-	if (omap_domain->iommu_dev != oiommu) {
-		dev_err(dev, "invalid iommu device\n");
+	if (omap_domain->dev != dev) {
+		dev_err(dev, "invalid attached device\n");
 		return;
 	}
 
-	iopgtable_clear_entry_all(oiommu);
+	/*
+	 * cleanup in the reverse order of attachment - this addresses
+	 * any h/w dependencies between multiple instances, if any
+	 */
+	iommu += (omap_domain->num_iommus - 1);
+	arch_data += (omap_domain->num_iommus - 1);
+	for (i = 0; i < omap_domain->num_iommus; i++, iommu--, arch_data--) {
+		oiommu = iommu->iommu_dev;
+		iopgtable_clear_entry_all(oiommu);
+
+		omap_iommu_detach(oiommu);
+		iommu->iommu_dev = NULL;
+		oiommu->domain = NULL;
+	}
 
-	omap_iommu_detach(oiommu);
+	omap_iommu_detach_fini(omap_domain);
 
-	omap_domain->iommu_dev = NULL;
 	omap_domain->dev = NULL;
-	oiommu->domain = NULL;
 }
 
 static void omap_iommu_detach_dev(struct iommu_domain *domain,
@@ -1182,18 +1365,7 @@ static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 
 	omap_domain = kzalloc(sizeof(*omap_domain), GFP_KERNEL);
 	if (!omap_domain)
-		goto out;
-
-	omap_domain->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_KERNEL);
-	if (!omap_domain->pgtable)
-		goto fail_nomem;
-
-	/*
-	 * should never fail, but please keep this around to ensure
-	 * we keep the hardware happy
-	 */
-	if (WARN_ON(!IS_ALIGNED((long)omap_domain->pgtable, IOPGD_TABLE_SIZE)))
-		goto fail_align;
+		return NULL;
 
 	spin_lock_init(&omap_domain->lock);
 
@@ -1202,13 +1374,6 @@ static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
 	omap_domain->domain.geometry.force_aperture = true;
 
 	return &omap_domain->domain;
-
-fail_align:
-	kfree(omap_domain->pgtable);
-fail_nomem:
-	kfree(omap_domain);
-out:
-	return NULL;
 }
 
 static void omap_iommu_domain_free(struct iommu_domain *domain)
@@ -1219,10 +1384,9 @@ static void omap_iommu_domain_free(struct iommu_domain *domain)
 	 * An iommu device is still attached
 	 * (currently, only one device can be attached) ?
 	 */
-	if (omap_domain->iommu_dev)
+	if (omap_domain->dev)
 		_omap_iommu_detach_dev(omap_domain, omap_domain->dev);
 
-	kfree(omap_domain->pgtable);
 	kfree(omap_domain);
 }
 
@@ -1230,11 +1394,16 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t da)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
-	struct omap_iommu *oiommu = omap_domain->iommu_dev;
+	struct omap_iommu_device *iommu = omap_domain->iommus;
+	struct omap_iommu *oiommu = iommu->iommu_dev;
 	struct device *dev = oiommu->dev;
 	u32 *pgd, *pte;
 	phys_addr_t ret = 0;
 
+	/*
+	 * all the iommus within the domain will have identical programming,
+	 * so perform the lookup using just the first iommu
+	 */
 	iopgtable_lookup_entry(oiommu, da, &pgd, &pte);
 
 	if (pte) {
@@ -1260,11 +1429,12 @@ static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static int omap_iommu_add_device(struct device *dev)
 {
-	struct omap_iommu_arch_data *arch_data;
+	struct omap_iommu_arch_data *arch_data, *tmp;
 	struct omap_iommu *oiommu;
 	struct iommu_group *group;
 	struct device_node *np;
 	struct platform_device *pdev;
+	int num_iommus, i;
 	int ret;
 
 	/*
@@ -1276,36 +1446,57 @@ static int omap_iommu_add_device(struct device *dev)
 	if (!dev->of_node)
 		return 0;
 
-	np = of_parse_phandle(dev->of_node, "iommus", 0);
-	if (!np)
+	/*
+	 * retrieve the count of IOMMU nodes using phandle size as element size
+	 * since #iommu-cells = 0 for OMAP
+	 */
+	num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus",
+						     sizeof(phandle));
+	if (num_iommus < 0)
 		return 0;
 
-	pdev = of_find_device_by_node(np);
-	if (WARN_ON(!pdev)) {
-		of_node_put(np);
-		return -EINVAL;
-	}
+	arch_data = kzalloc((num_iommus + 1) * sizeof(*arch_data), GFP_KERNEL);
+	if (!arch_data)
+		return -ENOMEM;
 
-	oiommu = platform_get_drvdata(pdev);
-	if (!oiommu) {
-		of_node_put(np);
-		return -EINVAL;
-	}
+	for (i = 0, tmp = arch_data; i < num_iommus; i++, tmp++) {
+		np = of_parse_phandle(dev->of_node, "iommus", i);
+		if (!np) {
+			kfree(arch_data);
+			return -EINVAL;
+		}
+
+		pdev = of_find_device_by_node(np);
+		if (WARN_ON(!pdev)) {
+			of_node_put(np);
+			kfree(arch_data);
+			return -EINVAL;
+		}
+
+		oiommu = platform_get_drvdata(pdev);
+		if (!oiommu) {
+			of_node_put(np);
+			kfree(arch_data);
+			return -EINVAL;
+		}
+
+		tmp->iommu_dev = oiommu;
 
-	arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL);
-	if (!arch_data) {
 		of_node_put(np);
-		return -ENOMEM;
 	}
 
+	/*
+	 * use the first IOMMU alone for the sysfs device linking.
+	 * TODO: Evaluate if a single iommu_group needs to be
+	 * maintained for both IOMMUs
+	 */
+	oiommu = arch_data->iommu_dev;
 	ret = iommu_device_link(&oiommu->iommu, dev);
 	if (ret) {
 		kfree(arch_data);
-		of_node_put(np);
 		return ret;
 	}
 
-	arch_data->iommu_dev = oiommu;
 	dev->archdata.iommu = arch_data;
 
 	/*
@@ -1321,8 +1512,6 @@ static int omap_iommu_add_device(struct device *dev)
 	}
 	iommu_group_put(group);
 
-	of_node_put(np);
-
 	return 0;
 }
 
diff --git a/drivers/iommu/omap-iommu.h b/drivers/iommu/omap-iommu.h
index a675af29a6ec..1703159ef5af 100644
--- a/drivers/iommu/omap-iommu.h
+++ b/drivers/iommu/omap-iommu.h
@@ -29,17 +29,26 @@ struct iotlb_entry {
 };
 
 /**
+ * struct omap_iommu_device - omap iommu device data
+ * @pgtable:	page table used by an omap iommu attached to a domain
+ * @iommu_dev:	pointer to store an omap iommu instance attached to a domain
+ */
+struct omap_iommu_device {
+	u32 *pgtable;
+	struct omap_iommu *iommu_dev;
+};
+
+/**
  * struct omap_iommu_domain - omap iommu domain
- * @pgtable:	the page table
- * @iommu_dev:	an omap iommu device attached to this domain. only a single
- *		iommu device can be attached for now.
+ * @num_iommus: number of iommus in this domain
+ * @iommus:	omap iommu device data for all iommus in this domain
  * @dev:	Device using this domain.
  * @lock:	domain lock, should be taken when attaching/detaching
  * @domain:	generic domain handle used by iommu core code
  */
 struct omap_iommu_domain {
-	u32 *pgtable;
-	struct omap_iommu *iommu_dev;
+	u32 num_iommus;
+	struct omap_iommu_device *iommus;
 	struct device *dev;
 	spinlock_t lock;
 	struct iommu_domain domain;
@@ -97,17 +106,6 @@ struct iotlb_lock {
 	short vict;
 };
 
-/**
- * dev_to_omap_iommu() - retrieves an omap iommu object from a user device
- * @dev: iommu client device
- */
-static inline struct omap_iommu *dev_to_omap_iommu(struct device *dev)
-{
-	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
-
-	return arch_data->iommu_dev;
-}
-
 /*
  * MMU Register offsets
  */
diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c
index c8a587d034b0..e07f02d00c68 100644
--- a/drivers/iommu/qcom_iommu.c
+++ b/drivers/iommu/qcom_iommu.c
@@ -66,6 +66,7 @@ struct qcom_iommu_ctx {
 	void __iomem		*base;
 	bool			 secure_init;
 	u8			 asid;      /* asid and ctx bank # are 1:1 */
+	struct iommu_domain	*domain;
 };
 
 struct qcom_iommu_domain {
@@ -194,12 +195,15 @@ static irqreturn_t qcom_iommu_fault(int irq, void *dev)
 	fsynr = iommu_readl(ctx, ARM_SMMU_CB_FSYNR0);
 	iova = iommu_readq(ctx, ARM_SMMU_CB_FAR);
 
-	dev_err_ratelimited(ctx->dev,
-			    "Unhandled context fault: fsr=0x%x, "
-			    "iova=0x%016llx, fsynr=0x%x, cb=%d\n",
-			    fsr, iova, fsynr, ctx->asid);
+	if (!report_iommu_fault(ctx->domain, ctx->dev, iova, 0)) {
+		dev_err_ratelimited(ctx->dev,
+				    "Unhandled context fault: fsr=0x%x, "
+				    "iova=0x%016llx, fsynr=0x%x, cb=%d\n",
+				    fsr, iova, fsynr, ctx->asid);
+	}
 
 	iommu_writel(ctx, ARM_SMMU_CB_FSR, fsr);
+	iommu_writel(ctx, ARM_SMMU_CB_RESUME, RESUME_TERMINATE);
 
 	return IRQ_HANDLED;
 }
@@ -274,12 +278,14 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* SCTLR */
 		reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
-			SCTLR_M | SCTLR_S1_ASIDPNE;
+			SCTLR_M | SCTLR_S1_ASIDPNE | SCTLR_CFCFG;
 
 		if (IS_ENABLED(CONFIG_BIG_ENDIAN))
 			reg |= SCTLR_E;
 
 		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg);
+
+		ctx->domain = domain;
 	}
 
 	mutex_unlock(&qcom_domain->init_mutex);
@@ -395,6 +401,8 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de
 
 		/* Disable the context bank: */
 		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0);
+
+		ctx->domain = NULL;
 	}
 	pm_runtime_put_sync(qcom_iommu->dev);
 
@@ -443,6 +451,19 @@ static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ret;
 }
 
+static void qcom_iommu_iotlb_sync(struct iommu_domain *domain)
+{
+	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
+	struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
+						  struct io_pgtable, ops);
+	if (!qcom_domain->pgtbl_ops)
+		return;
+
+	pm_runtime_get_sync(qcom_domain->iommu->dev);
+	qcom_iommu_tlb_sync(pgtable->cookie);
+	pm_runtime_put_sync(qcom_domain->iommu->dev);
+}
+
 static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
@@ -570,6 +591,8 @@ static const struct iommu_ops qcom_iommu_ops = {
 	.map		= qcom_iommu_map,
 	.unmap		= qcom_iommu_unmap,
 	.map_sg		= default_iommu_map_sg,
+	.flush_iotlb_all = qcom_iommu_iotlb_sync,
+	.iotlb_sync	= qcom_iommu_iotlb_sync,
 	.iova_to_phys	= qcom_iommu_iova_to_phys,
 	.add_device	= qcom_iommu_add_device,
 	.remove_device	= qcom_iommu_remove_device,