Merge tag 'iommu-updates-v4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU updates from Joerg Roedel:

 - Debugfs support for the Intel VT-d driver.

   When enabled, it now also exposes some of its internal data
   structures to user-space for debugging purposes.

 - ARM-SMMU driver now uses the generic deferred flushing and fast-path
   iova allocation code.

   This is expected to be a major performance improvement, as this
   allocation path scales a lot better.

 - Support for r8a7744 in the Renesas iommu driver

 - Couple of minor fixes and improvements all over the place

* tag 'iommu-updates-v4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (39 commits)
  iommu/arm-smmu-v3: Remove unnecessary wrapper function
  iommu/arm-smmu-v3: Add SPDX header
  iommu/amd: Add default branch in amd_iommu_capable()
  dt-bindings: iommu: ipmmu-vmsa: Add r8a7744 support
  iommu/amd: Move iommu_init_pci() to .init section
  iommu/arm-smmu: Support non-strict mode
  iommu/io-pgtable-arm-v7s: Add support for non-strict mode
  iommu/arm-smmu-v3: Add support for non-strict mode
  iommu/io-pgtable-arm: Add support for non-strict mode
  iommu: Add "iommu.strict" command line option
  iommu/dma: Add support for non-strict mode
  iommu/arm-smmu: Ensure that page-table updates are visible before TLBI
  iommu/arm-smmu-v3: Implement flush_iotlb_all hook
  iommu/arm-smmu-v3: Avoid back-to-back CMD_SYNC operations
  iommu/arm-smmu-v3: Fix unexpected CMD_SYNC timeout
  iommu/io-pgtable-arm: Fix race handling in split_blk_unmap()
  iommu/arm-smmu-v3: Fix a couple of minor comment typos
  iommu: Fix a typo
  iommu: Remove .domain_{get,set}_windows
  iommu: Tidy up window attributes
  ...

22 files changed, 825 insertions, 334 deletions

diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 4552b06fe601..439ba5c23693 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -127,6 +127,16 @@ static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
+static int fsl_mc_dma_configure(struct device *dev)
+{
+	struct device *dma_dev = dev;
+
+	while (dev_is_fsl_mc(dma_dev))
+		dma_dev = dma_dev->parent;
+
+	return of_dma_configure(dev, dma_dev->of_node, 0);
+}
+
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
@@ -148,6 +158,7 @@ struct bus_type fsl_mc_bus_type = {
 	.name = "fsl-mc",
 	.match = fsl_mc_bus_match,
 	.uevent = fsl_mc_bus_uevent,
+	.dma_configure  = fsl_mc_dma_configure,
 	.dev_groups = fsl_mc_dev_groups,
 };
 EXPORT_SYMBOL_GPL(fsl_mc_bus_type);
@@ -621,6 +632,7 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
 		mc_dev->icid = parent_mc_dev->icid;
 		mc_dev->dma_mask = FSL_MC_DEFAULT_DMA_MASK;
 		mc_dev->dev.dma_mask = &mc_dev->dma_mask;
+		mc_dev->dev.coherent_dma_mask = mc_dev->dma_mask;
 		dev_set_msi_domain(&mc_dev->dev,
 				   dev_get_msi_domain(&parent_mc_dev->dev));
 	}
@@ -638,10 +650,6 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
 			goto error_cleanup_dev;
 	}
 
-	/* Objects are coherent, unless 'no shareability' flag set. */
-	if (!(obj_desc->flags & FSL_MC_OBJ_FLAG_NO_MEM_SHAREABILITY))
-		arch_setup_dma_ops(&mc_dev->dev, 0, 0, NULL, true);
-
 	/*
 	 * The device-specific probe callback will get invoked by device_add()
 	 */
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 83e6d993fca5..d9a25715650e 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -186,6 +186,19 @@ config INTEL_IOMMU
 	  and include PCI device scope covered by these DMA
 	  remapping devices.
 
+config INTEL_IOMMU_DEBUGFS
+	bool "Export Intel IOMMU internals in Debugfs"
+	depends on INTEL_IOMMU && IOMMU_DEBUGFS
+	help
+	  !!!WARNING!!!
+
+	  DO NOT ENABLE THIS OPTION UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!!!
+
+	  Expose Intel IOMMU internals in Debugfs.
+
+	  This option is -NOT- intended for production environments, and should
+	  only be enabled for debugging Intel IOMMU.
+
 config INTEL_IOMMU_SVM
 	bool "Support for Shared Virtual Memory with Intel IOMMU"
 	depends on INTEL_IOMMU && X86
diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile
index ab5eba6edf82..a158a68c8ea8 100644
--- a/drivers/iommu/Makefile
+++ b/drivers/iommu/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
+obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel-iommu-debugfs.o
 obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o
 obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index bee0dfb7b93b..1167ff0416cf 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3083,6 +3083,8 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 		return (irq_remapping_enabled == 1);
 	case IOMMU_CAP_NOEXEC:
 		return false;
+	default:
+		break;
 	}
 
 	return false;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 3931c7de7c69..bb2cd29e1658 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1719,7 +1719,7 @@ static const struct attribute_group *amd_iommu_groups[] = {
 	NULL,
 };
 
-static int iommu_init_pci(struct amd_iommu *iommu)
+static int __init iommu_init_pci(struct amd_iommu *iommu)
 {
 	int cap_ptr = iommu->cap_ptr;
 	u32 range, misc, low, high;
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 5059d09f3202..6947ccf26512 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -1,18 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * IOMMU API for ARM architected SMMUv3 implementations.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
  * Copyright (C) 2015 ARM Limited
  *
  * Author: Will Deacon <will.deacon@arm.com>
@@ -567,7 +556,8 @@ struct arm_smmu_device {
 
 	int				gerr_irq;
 	int				combined_irq;
-	atomic_t			sync_nr;
+	u32				sync_nr;
+	u8				prev_cmd_opcode;
 
 	unsigned long			ias; /* IPA */
 	unsigned long			oas; /* PA */
@@ -611,6 +601,7 @@ struct arm_smmu_domain {
 	struct mutex			init_mutex; /* Protects smmu pointer */
 
 	struct io_pgtable_ops		*pgtbl_ops;
+	bool				non_strict;
 
 	enum arm_smmu_domain_stage	stage;
 	union {
@@ -708,7 +699,7 @@ 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
+ * Wait for the SMMU to consume items. If sync 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 sync, bool wfe)
@@ -901,6 +892,8 @@ 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);
 
+	smmu->prev_cmd_opcode = FIELD_GET(CMDQ_0_OP, cmd[0]);
+
 	while (queue_insert_raw(q, cmd) == -ENOSPC) {
 		if (queue_poll_cons(q, false, wfe))
 			dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
@@ -948,15 +941,21 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu)
 	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);
+
+	/* Piggy-back on the previous command if it's a SYNC */
+	if (smmu->prev_cmd_opcode == CMDQ_OP_CMD_SYNC) {
+		ent.sync.msidata = smmu->sync_nr;
+	} else {
+		ent.sync.msidata = ++smmu->sync_nr;
+		arm_smmu_cmdq_build_cmd(cmd, &ent);
+		arm_smmu_cmdq_insert_cmd(smmu, cmd);
+	}
+
 	spin_unlock_irqrestore(&smmu->cmdq.lock, flags);
 
 	return __arm_smmu_sync_poll_msi(smmu, ent.sync.msidata);
@@ -1372,15 +1371,11 @@ static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev)
 }
 
 /* IO_PGTABLE API */
-static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
-{
-	arm_smmu_cmdq_issue_sync(smmu);
-}
-
 static void arm_smmu_tlb_sync(void *cookie)
 {
 	struct arm_smmu_domain *smmu_domain = cookie;
-	__arm_smmu_tlb_sync(smmu_domain->smmu);
+
+	arm_smmu_cmdq_issue_sync(smmu_domain->smmu);
 }
 
 static void arm_smmu_tlb_inv_context(void *cookie)
@@ -1398,8 +1393,14 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
 	}
 
+	/*
+	 * NOTE: when io-pgtable is in non-strict mode, we may get here with
+	 * PTEs previously cleared by unmaps on the current CPU not yet visible
+	 * to the SMMU. We are relying on the DSB implicit in queue_inc_prod()
+	 * to guarantee those are observed before the TLBI. Do be careful, 007.
+	 */
 	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
-	__arm_smmu_tlb_sync(smmu);
+	arm_smmu_cmdq_issue_sync(smmu);
 }
 
 static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
@@ -1624,6 +1625,9 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain)
 	if (smmu->features & ARM_SMMU_FEAT_COHERENCY)
 		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;
 
+	if (smmu_domain->non_strict)
+		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
+
 	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
 	if (!pgtbl_ops)
 		return -ENOMEM;
@@ -1772,12 +1776,20 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size)
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->smmu)
+		arm_smmu_tlb_inv_context(smmu_domain);
+}
+
 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);
+		arm_smmu_cmdq_issue_sync(smmu);
 }
 
 static phys_addr_t
@@ -1917,15 +1929,27 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
-		return -EINVAL;
-
-	switch (attr) {
-	case DOMAIN_ATTR_NESTING:
-		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
-		return 0;
+	switch (domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		switch (attr) {
+		case DOMAIN_ATTR_NESTING:
+			*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+			return 0;
+		default:
+			return -ENODEV;
+		}
+		break;
+	case IOMMU_DOMAIN_DMA:
+		switch (attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			*(int *)data = smmu_domain->non_strict;
+			return 0;
+		default:
+			return -ENODEV;
+		}
+		break;
 	default:
-		return -ENODEV;
+		return -EINVAL;
 	}
 }
 
@@ -1935,26 +1959,37 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 	int ret = 0;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
-		return -EINVAL;
-
 	mutex_lock(&smmu_domain->init_mutex);
 
-	switch (attr) {
-	case DOMAIN_ATTR_NESTING:
-		if (smmu_domain->smmu) {
-			ret = -EPERM;
-			goto out_unlock;
+	switch (domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		switch (attr) {
+		case DOMAIN_ATTR_NESTING:
+			if (smmu_domain->smmu) {
+				ret = -EPERM;
+				goto out_unlock;
+			}
+
+			if (*(int *)data)
+				smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+			else
+				smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+			break;
+		default:
+			ret = -ENODEV;
+		}
+		break;
+	case IOMMU_DOMAIN_DMA:
+		switch(attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			smmu_domain->non_strict = *(int *)data;
+			break;
+		default:
+			ret = -ENODEV;
 		}
-
-		if (*(int *)data)
-			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
-		else
-			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
-
 		break;
 	default:
-		ret = -ENODEV;
+		ret = -EINVAL;
 	}
 
 out_unlock:
@@ -1999,7 +2034,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.attach_dev		= arm_smmu_attach_dev,
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
-	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
 	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
@@ -2180,7 +2215,6 @@ 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;
@@ -2353,8 +2387,8 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu)
 	irq = smmu->combined_irq;
 	if (irq) {
 		/*
-		 * Cavium ThunderX2 implementation doesn't not support unique
-		 * irq lines. Use single irq line for all the SMMUv3 interrupts.
+		 * Cavium ThunderX2 implementation doesn't support unique irq
+		 * lines. Use a single irq line for all the SMMUv3 interrupts.
 		 */
 		ret = devm_request_threaded_irq(smmu->dev, irq,
 					arm_smmu_combined_irq_handler,
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index fd1b80ef9490..5a28ae892504 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -52,6 +52,7 @@
 #include <linux/spinlock.h>
 
 #include <linux/amba/bus.h>
+#include <linux/fsl/mc.h>
 
 #include "io-pgtable.h"
 #include "arm-smmu-regs.h"
@@ -246,6 +247,7 @@ struct arm_smmu_domain {
 	const struct iommu_gather_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
+	bool				non_strict;
 	struct mutex			init_mutex; /* Protects smmu pointer */
 	spinlock_t			cb_lock; /* Serialises ATS1* ops and TLB syncs */
 	struct iommu_domain		domain;
@@ -447,7 +449,11 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie)
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	void __iomem *base = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
 
-	writel_relaxed(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID);
+	/*
+	 * NOTE: this is not a relaxed write; it needs to guarantee that PTEs
+	 * cleared by the current CPU are visible to the SMMU before the TLBI.
+	 */
+	writel(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID);
 	arm_smmu_tlb_sync_context(cookie);
 }
 
@@ -457,7 +463,8 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie)
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *base = ARM_SMMU_GR0(smmu);
 
-	writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
+	/* NOTE: see above */
+	writel(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
 	arm_smmu_tlb_sync_global(smmu);
 }
 
@@ -469,6 +476,9 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
 	void __iomem *reg = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
 
+	if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
+
 	if (stage1) {
 		reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
 
@@ -510,6 +520,9 @@ static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
 	struct arm_smmu_domain *smmu_domain = cookie;
 	void __iomem *base = ARM_SMMU_GR0(smmu_domain->smmu);
 
+	if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
+		wmb();
+
 	writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
 }
 
@@ -863,6 +876,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
 		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;
 
+	if (smmu_domain->non_strict)
+		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
+
 	smmu_domain->smmu = smmu;
 	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
 	if (!pgtbl_ops) {
@@ -1252,6 +1268,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->tlb_ops)
+		smmu_domain->tlb_ops->tlb_flush_all(smmu_domain);
+}
+
 static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -1459,6 +1483,8 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 
 	if (dev_is_pci(dev))
 		group = pci_device_group(dev);
+	else if (dev_is_fsl_mc(dev))
+		group = fsl_mc_device_group(dev);
 	else
 		group = generic_device_group(dev);
 
@@ -1470,15 +1496,27 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
-		return -EINVAL;
-
-	switch (attr) {
-	case DOMAIN_ATTR_NESTING:
-		*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
-		return 0;
+	switch(domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		switch (attr) {
+		case DOMAIN_ATTR_NESTING:
+			*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
+			return 0;
+		default:
+			return -ENODEV;
+		}
+		break;
+	case IOMMU_DOMAIN_DMA:
+		switch (attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			*(int *)data = smmu_domain->non_strict;
+			return 0;
+		default:
+			return -ENODEV;
+		}
+		break;
 	default:
-		return -ENODEV;
+		return -EINVAL;
 	}
 }
 
@@ -1488,28 +1526,38 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 	int ret = 0;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
-		return -EINVAL;
-
 	mutex_lock(&smmu_domain->init_mutex);
 
-	switch (attr) {
-	case DOMAIN_ATTR_NESTING:
-		if (smmu_domain->smmu) {
-			ret = -EPERM;
-			goto out_unlock;
+	switch(domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
+		switch (attr) {
+		case DOMAIN_ATTR_NESTING:
+			if (smmu_domain->smmu) {
+				ret = -EPERM;
+				goto out_unlock;
+			}
+
+			if (*(int *)data)
+				smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
+			else
+				smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
+			break;
+		default:
+			ret = -ENODEV;
+		}
+		break;
+	case IOMMU_DOMAIN_DMA:
+		switch (attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			smmu_domain->non_strict = *(int *)data;
+			break;
+		default:
+			ret = -ENODEV;
 		}
-
-		if (*(int *)data)
-			smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
-		else
-			smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
-
 		break;
 	default:
-		ret = -ENODEV;
+		ret = -EINVAL;
 	}
-
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);
 	return ret;
@@ -1562,7 +1610,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.attach_dev		= arm_smmu_attach_dev,
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
-	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
 	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
@@ -2036,6 +2084,10 @@ static void arm_smmu_bus_init(void)
 		bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
 	}
 #endif
+#ifdef CONFIG_FSL_MC_BUS
+	if (!iommu_present(&fsl_mc_bus_type))
+		bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops);
+#endif
 }
 
 static int arm_smmu_device_probe(struct platform_device *pdev)
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 511ff9a1d6d9..d1b04753b204 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -55,6 +55,9 @@ struct iommu_dma_cookie {
 	};
 	struct list_head		msi_page_list;
 	spinlock_t			msi_lock;
+
+	/* Domain for flush queue callback; NULL if flush queue not in use */
+	struct iommu_domain		*fq_domain;
 };
 
 static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
@@ -257,6 +260,20 @@ static int iova_reserve_iommu_regions(struct device *dev,
 	return ret;
 }
 
+static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad)
+{
+	struct iommu_dma_cookie *cookie;
+	struct iommu_domain *domain;
+
+	cookie = container_of(iovad, struct iommu_dma_cookie, iovad);
+	domain = cookie->fq_domain;
+	/*
+	 * The IOMMU driver supporting DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE
+	 * implies that ops->flush_iotlb_all must be non-NULL.
+	 */
+	domain->ops->flush_iotlb_all(domain);
+}
+
 /**
  * iommu_dma_init_domain - Initialise a DMA mapping domain
  * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
@@ -275,6 +292,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	unsigned long order, base_pfn, end_pfn;
+	int attr;
 
 	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
 		return -EINVAL;
@@ -308,6 +326,13 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	}
 
 	init_iova_domain(iovad, 1UL << order, base_pfn);
+
+	if (!cookie->fq_domain && !iommu_domain_get_attr(domain,
+			DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) {
+		cookie->fq_domain = domain;
+		init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, NULL);
+	}
+
 	if (!dev)
 		return 0;
 
@@ -393,6 +418,9 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 	/* The MSI case is only ever cleaning up its most recent allocation */
 	if (cookie->type == IOMMU_DMA_MSI_COOKIE)
 		cookie->msi_iova -= size;
+	else if (cookie->fq_domain)	/* non-strict mode */
+		queue_iova(iovad, iova_pfn(iovad, iova),
+				size >> iova_shift(iovad), 0);
 	else
 		free_iova_fast(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad));
@@ -408,7 +436,9 @@ static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr,
 	dma_addr -= iova_off;
 	size = iova_align(iovad, size + iova_off);
 
-	WARN_ON(iommu_unmap(domain, dma_addr, size) != size);
+	WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size);
+	if (!cookie->fq_domain)
+		iommu_tlb_sync(domain);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
@@ -491,7 +521,7 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count,
 void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
 		dma_addr_t *handle)
 {
-	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), *handle, size);
+	__iommu_dma_unmap(iommu_get_dma_domain(dev), *handle, size);
 	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
 	*handle = IOMMU_MAPPING_ERROR;
 }
@@ -518,7 +548,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
 		unsigned long attrs, int prot, dma_addr_t *handle,
 		void (*flush_page)(struct device *, const void *, phys_addr_t))
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	struct page **pages;
@@ -606,9 +636,8 @@ int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma)
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot)
+		size_t size, int prot, struct iommu_domain *domain)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	size_t iova_off = 0;
 	dma_addr_t iova;
@@ -632,13 +661,14 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, int prot)
 {
-	return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot);
+	return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot,
+			iommu_get_dma_domain(dev));
 }
 
 void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
 		enum dma_data_direction dir, unsigned long attrs)
 {
-	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle, size);
+	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
 }
 
 /*
@@ -726,7 +756,7 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		int nents, int prot)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	struct scatterlist *s, *prev = NULL;
@@ -811,20 +841,21 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 		sg = tmp;
 	}
 	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), start, end - start);
+	__iommu_dma_unmap(iommu_get_dma_domain(dev), start, end - start);
 }
 
 dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
+			iommu_get_dma_domain(dev));
 }
 
 void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle, size);
+	__iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size);
 }
 
 int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
@@ -850,7 +881,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!msi_page)
 		return NULL;
 
-	iova = __iommu_dma_map(dev, msi_addr, size, prot);
+	iova = __iommu_dma_map(dev, msi_addr, size, prot, domain);
 	if (iommu_dma_mapping_error(dev, iova))
 		goto out_free_page;
 
diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c
index f089136e9c3f..9b528cfcc6c3 100644
--- a/drivers/iommu/fsl_pamu_domain.c
+++ b/drivers/iommu/fsl_pamu_domain.c
@@ -814,6 +814,55 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en
 	return 0;
 }
 
+static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
+{
+	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dma_domain->domain_lock, flags);
+	/* Ensure domain is inactive i.e. DMA should be disabled for the domain */
+	if (dma_domain->enabled) {
+		pr_debug("Can't set geometry attributes as domain is active\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return  -EBUSY;
+	}
+
+	/* Ensure that the geometry has been set for the domain */
+	if (!dma_domain->geom_size) {
+		pr_debug("Please configure geometry before setting the number of windows\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	/*
+	 * Ensure we have valid window count i.e. it should be less than
+	 * maximum permissible limit and should be a power of two.
+	 */
+	if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) {
+		pr_debug("Invalid window count\n");
+		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+		return -EINVAL;
+	}
+
+	ret = pamu_set_domain_geometry(dma_domain, &domain->geometry,
+				       w_count > 1 ? w_count : 0);
+	if (!ret) {
+		kfree(dma_domain->win_arr);
+		dma_domain->win_arr = kcalloc(w_count,
+					      sizeof(*dma_domain->win_arr),
+					      GFP_ATOMIC);
+		if (!dma_domain->win_arr) {
+			spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+			return -ENOMEM;
+		}
+		dma_domain->win_cnt = w_count;
+	}
+	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
+
+	return ret;
+}
+
 static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
 				    enum iommu_attr attr_type, void *data)
 {
@@ -830,6 +879,9 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain,
 	case DOMAIN_ATTR_FSL_PAMU_ENABLE:
 		ret = configure_domain_dma_state(dma_domain, *(int *)data);
 		break;
+	case DOMAIN_ATTR_WINDOWS:
+		ret = fsl_pamu_set_windows(domain, *(u32 *)data);
+		break;
 	default:
 		pr_debug("Unsupported attribute type\n");
 		ret = -EINVAL;
@@ -856,6 +908,9 @@ static int fsl_pamu_get_domain_attr(struct iommu_domain *domain,
 	case DOMAIN_ATTR_FSL_PAMUV1:
 		*(int *)data = DOMAIN_ATTR_FSL_PAMUV1;
 		break;
+	case DOMAIN_ATTR_WINDOWS:
+		*(u32 *)data = dma_domain->win_cnt;
+		break;
 	default:
 		pr_debug("Unsupported attribute type\n");
 		ret = -EINVAL;
@@ -916,13 +971,13 @@ static struct iommu_group *get_shared_pci_device_group(struct pci_dev *pdev)
 static struct iommu_group *get_pci_device_group(struct pci_dev *pdev)
 {
 	struct pci_controller *pci_ctl;
-	bool pci_endpt_partioning;
+	bool pci_endpt_partitioning;
 	struct iommu_group *group = NULL;
 
 	pci_ctl = pci_bus_to_host(pdev->bus);
-	pci_endpt_partioning = check_pci_ctl_endpt_part(pci_ctl);
+	pci_endpt_partitioning = check_pci_ctl_endpt_part(pci_ctl);
 	/* We can partition PCIe devices so assign device group to the device */
-	if (pci_endpt_partioning) {
+	if (pci_endpt_partitioning) {
 		group = pci_device_group(&pdev->dev);
 
 		/*
@@ -994,62 +1049,6 @@ static void fsl_pamu_remove_device(struct device *dev)
 	iommu_group_remove_device(dev);
 }
 
-static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count)
-{
-	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&dma_domain->domain_lock, flags);
-	/* Ensure domain is inactive i.e. DMA should be disabled for the domain */
-	if (dma_domain->enabled) {
-		pr_debug("Can't set geometry attributes as domain is active\n");
-		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-		return  -EBUSY;
-	}
-
-	/* Ensure that the geometry has been set for the domain */
-	if (!dma_domain->geom_size) {
-		pr_debug("Please configure geometry before setting the number of windows\n");
-		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-		return -EINVAL;
-	}
-
-	/*
-	 * Ensure we have valid window count i.e. it should be less than
-	 * maximum permissible limit and should be a power of two.
-	 */
-	if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) {
-		pr_debug("Invalid window count\n");
-		spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-		return -EINVAL;
-	}
-
-	ret = pamu_set_domain_geometry(dma_domain, &domain->geometry,
-				       w_count > 1 ? w_count : 0);
-	if (!ret) {
-		kfree(dma_domain->win_arr);
-		dma_domain->win_arr = kcalloc(w_count,
-					      sizeof(*dma_domain->win_arr),
-					      GFP_ATOMIC);
-		if (!dma_domain->win_arr) {
-			spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-			return -ENOMEM;
-		}
-		dma_domain->win_cnt = w_count;
-	}
-	spin_unlock_irqrestore(&dma_domain->domain_lock, flags);
-
-	return ret;
-}
-
-static u32 fsl_pamu_get_windows(struct iommu_domain *domain)
-{
-	struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain);
-
-	return dma_domain->win_cnt;
-}
-
 static const struct iommu_ops fsl_pamu_ops = {
 	.capable	= fsl_pamu_capable,
 	.domain_alloc	= fsl_pamu_domain_alloc,
@@ -1058,8 +1057,6 @@ static const struct iommu_ops fsl_pamu_ops = {
 	.detach_dev	= fsl_pamu_detach_device,
 	.domain_window_enable = fsl_pamu_window_enable,
 	.domain_window_disable = fsl_pamu_window_disable,
-	.domain_get_windows = fsl_pamu_get_windows,
-	.domain_set_windows = fsl_pamu_set_windows,
 	.iova_to_phys	= fsl_pamu_iova_to_phys,
 	.domain_set_attr = fsl_pamu_set_domain_attr,
 	.domain_get_attr = fsl_pamu_get_domain_attr,
diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c
new file mode 100644
index 000000000000..7fabf9b1c2dc
--- /dev/null
+++ b/drivers/iommu/intel-iommu-debugfs.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2018 Intel Corporation.
+ *
+ * Authors: Gayatri Kammela <gayatri.kammela@intel.com>
+ *	    Sohil Mehta <sohil.mehta@intel.com>
+ *	    Jacob Pan <jacob.jun.pan@linux.intel.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/dmar.h>
+#include <linux/intel-iommu.h>
+#include <linux/pci.h>
+
+#include <asm/irq_remapping.h>
+
+struct iommu_regset {
+	int offset;
+	const char *regs;
+};
+
+#define IOMMU_REGSET_ENTRY(_reg_)					\
+	{ DMAR_##_reg_##_REG, __stringify(_reg_) }
+static const struct iommu_regset iommu_regs[] = {
+	IOMMU_REGSET_ENTRY(VER),
+	IOMMU_REGSET_ENTRY(CAP),
+	IOMMU_REGSET_ENTRY(ECAP),
+	IOMMU_REGSET_ENTRY(GCMD),
+	IOMMU_REGSET_ENTRY(GSTS),
+	IOMMU_REGSET_ENTRY(RTADDR),
+	IOMMU_REGSET_ENTRY(CCMD),
+	IOMMU_REGSET_ENTRY(FSTS),
+	IOMMU_REGSET_ENTRY(FECTL),
+	IOMMU_REGSET_ENTRY(FEDATA),
+	IOMMU_REGSET_ENTRY(FEADDR),
+	IOMMU_REGSET_ENTRY(FEUADDR),
+	IOMMU_REGSET_ENTRY(AFLOG),
+	IOMMU_REGSET_ENTRY(PMEN),
+	IOMMU_REGSET_ENTRY(PLMBASE),
+	IOMMU_REGSET_ENTRY(PLMLIMIT),
+	IOMMU_REGSET_ENTRY(PHMBASE),
+	IOMMU_REGSET_ENTRY(PHMLIMIT),
+	IOMMU_REGSET_ENTRY(IQH),
+	IOMMU_REGSET_ENTRY(IQT),
+	IOMMU_REGSET_ENTRY(IQA),
+	IOMMU_REGSET_ENTRY(ICS),
+	IOMMU_REGSET_ENTRY(IRTA),
+	IOMMU_REGSET_ENTRY(PQH),
+	IOMMU_REGSET_ENTRY(PQT),
+	IOMMU_REGSET_ENTRY(PQA),
+	IOMMU_REGSET_ENTRY(PRS),
+	IOMMU_REGSET_ENTRY(PECTL),
+	IOMMU_REGSET_ENTRY(PEDATA),
+	IOMMU_REGSET_ENTRY(PEADDR),
+	IOMMU_REGSET_ENTRY(PEUADDR),
+	IOMMU_REGSET_ENTRY(MTRRCAP),
+	IOMMU_REGSET_ENTRY(MTRRDEF),
+	IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX16K_80000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX16K_A0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_C0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_C8000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_D0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_D8000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_E0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_E8000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_F0000),
+	IOMMU_REGSET_ENTRY(MTRR_FIX4K_F8000),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE0),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK0),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE1),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK1),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE2),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK2),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE3),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK3),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE4),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK4),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE5),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK5),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE6),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK6),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE7),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK7),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE8),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9),
+	IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9),
+	IOMMU_REGSET_ENTRY(VCCAP),
+	IOMMU_REGSET_ENTRY(VCMD),
+	IOMMU_REGSET_ENTRY(VCRSP),
+};
+
+static int iommu_regset_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	unsigned long flag;
+	int i, ret = 0;
+	u64 value;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!drhd->reg_base_addr) {
+			seq_puts(m, "IOMMU: Invalid base address\n");
+			ret = -EINVAL;
+			goto out;
+		}
+
+		seq_printf(m, "IOMMU: %s Register Base Address: %llx\n",
+			   iommu->name, drhd->reg_base_addr);
+		seq_puts(m, "Name\t\t\tOffset\t\tContents\n");
+		/*
+		 * Publish the contents of the 64-bit hardware registers
+		 * by adding the offset to the pointer (virtual address).
+		 */
+		raw_spin_lock_irqsave(&iommu->register_lock, flag);
+		for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) {
+			value = dmar_readq(iommu->reg + iommu_regs[i].offset);
+			seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n",
+				   iommu_regs[i].regs, iommu_regs[i].offset,
+				   value);
+		}
+		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
+		seq_putc(m, '\n');
+	}
+out:
+	rcu_read_unlock();
+
+	return ret;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_regset);
+
+static void ctx_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu,
+			       int bus)
+{
+	struct context_entry *context;
+	int devfn;
+
+	seq_printf(m, " Context Table Entries for Bus: %d\n", bus);
+	seq_puts(m, "  Entry\tB:D.F\tHigh\tLow\n");
+
+	for (devfn = 0; devfn < 256; devfn++) {
+		context = iommu_context_addr(iommu, bus, devfn, 0);
+		if (!context)
+			return;
+
+		if (!context_present(context))
+			continue;
+
+		seq_printf(m, "  %-5d\t%02x:%02x.%x\t%-6llx\t%llx\n", devfn,
+			   bus, PCI_SLOT(devfn), PCI_FUNC(devfn),
+			   context[0].hi, context[0].lo);
+	}
+}
+
+static void root_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu)
+{
+	unsigned long flags;
+	int bus;
+
+	spin_lock_irqsave(&iommu->lock, flags);
+	seq_printf(m, "IOMMU %s: Root Table Address:%llx\n", iommu->name,
+		   (u64)virt_to_phys(iommu->root_entry));
+	seq_puts(m, "Root Table Entries:\n");
+
+	for (bus = 0; bus < 256; bus++) {
+		if (!(iommu->root_entry[bus].lo & 1))
+			continue;
+
+		seq_printf(m, " Bus: %d H: %llx L: %llx\n", bus,
+			   iommu->root_entry[bus].hi,
+			   iommu->root_entry[bus].lo);
+
+		ctx_tbl_entry_show(m, iommu, bus);
+		seq_putc(m, '\n');
+	}
+	spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
+static int dmar_translation_struct_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		root_tbl_entry_show(m, iommu);
+		seq_putc(m, '\n');
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dmar_translation_struct);
+
+#ifdef CONFIG_IRQ_REMAP
+static void ir_tbl_remap_entry_show(struct seq_file *m,
+				    struct intel_iommu *iommu)
+{
+	struct irte *ri_entry;
+	unsigned long flags;
+	int idx;
+
+	seq_puts(m, " Entry SrcID   DstID    Vct IRTE_high\t\tIRTE_low\n");
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+	for (idx = 0; idx < INTR_REMAP_TABLE_ENTRIES; idx++) {
+		ri_entry = &iommu->ir_table->base[idx];
+		if (!ri_entry->present || ri_entry->p_pst)
+			continue;
+
+		seq_printf(m, " %-5d %02x:%02x.%01x %08x %02x  %016llx\t%016llx\n",
+			   idx, PCI_BUS_NUM(ri_entry->sid),
+			   PCI_SLOT(ri_entry->sid), PCI_FUNC(ri_entry->sid),
+			   ri_entry->dest_id, ri_entry->vector,
+			   ri_entry->high, ri_entry->low);
+	}
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+}
+
+static void ir_tbl_posted_entry_show(struct seq_file *m,
+				     struct intel_iommu *iommu)
+{
+	struct irte *pi_entry;
+	unsigned long flags;
+	int idx;
+
+	seq_puts(m, " Entry SrcID   PDA_high PDA_low  Vct IRTE_high\t\tIRTE_low\n");
+
+	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
+	for (idx = 0; idx < INTR_REMAP_TABLE_ENTRIES; idx++) {
+		pi_entry = &iommu->ir_table->base[idx];
+		if (!pi_entry->present || !pi_entry->p_pst)
+			continue;
+
+		seq_printf(m, " %-5d %02x:%02x.%01x %08x %08x %02x  %016llx\t%016llx\n",
+			   idx, PCI_BUS_NUM(pi_entry->sid),
+			   PCI_SLOT(pi_entry->sid), PCI_FUNC(pi_entry->sid),
+			   pi_entry->pda_h, pi_entry->pda_l << 6,
+			   pi_entry->vector, pi_entry->high,
+			   pi_entry->low);
+	}
+	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+}
+
+/*
+ * For active IOMMUs go through the Interrupt remapping
+ * table and print valid entries in a table format for
+ * Remapped and Posted Interrupts.
+ */
+static int ir_translation_struct_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	u64 irta;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!ecap_ir_support(iommu->ecap))
+			continue;
+
+		seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n",
+			   iommu->name);
+
+		if (iommu->ir_table) {
+			irta = virt_to_phys(iommu->ir_table->base);
+			seq_printf(m, " IR table address:%llx\n", irta);
+			ir_tbl_remap_entry_show(m, iommu);
+		} else {
+			seq_puts(m, "Interrupt Remapping is not enabled\n");
+		}
+		seq_putc(m, '\n');
+	}
+
+	seq_puts(m, "****\n\n");
+
+	for_each_active_iommu(iommu, drhd) {
+		if (!cap_pi_support(iommu->cap))
+			continue;
+
+		seq_printf(m, "Posted Interrupt supported on IOMMU: %s\n",
+			   iommu->name);
+
+		if (iommu->ir_table) {
+			irta = virt_to_phys(iommu->ir_table->base);
+			seq_printf(m, " IR table address:%llx\n", irta);
+			ir_tbl_posted_entry_show(m, iommu);
+		} else {
+			seq_puts(m, "Interrupt Remapping is not enabled\n");
+		}
+		seq_putc(m, '\n');
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ir_translation_struct);
+#endif
+
+void __init intel_iommu_debugfs_init(void)
+{
+	struct dentry *intel_iommu_debug = debugfs_create_dir("intel",
+						iommu_debugfs_dir);
+
+	debugfs_create_file("iommu_regset", 0444, intel_iommu_debug, NULL,
+			    &iommu_regset_fops);
+	debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug,
+			    NULL, &dmar_translation_struct_fops);
+#ifdef CONFIG_IRQ_REMAP
+	debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug,
+			    NULL, &ir_translation_struct_fops);
+#endif
+}
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 76f0a5d16ed3..f3ccf025108b 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -185,16 +185,6 @@ static int rwbf_quirk;
 static int force_on = 0;
 int intel_iommu_tboot_noforce;
 
-/*
- * 0: Present
- * 1-11: Reserved
- * 12-63: Context Ptr (12 - (haw-1))
- * 64-127: Reserved
- */
-struct root_entry {
-	u64	lo;
-	u64	hi;
-};
 #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
 
 /*
@@ -220,21 +210,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re)
 
 	return re->hi & VTD_PAGE_MASK;
 }
-/*
- * low 64 bits:
- * 0: present
- * 1: fault processing disable
- * 2-3: translation type
- * 12-63: address space root
- * high 64 bits:
- * 0-2: address width
- * 3-6: aval
- * 8-23: domain id
- */
-struct context_entry {
-	u64 lo;
-	u64 hi;
-};
 
 static inline void context_clear_pasid_enable(struct context_entry *context)
 {
@@ -261,7 +236,7 @@ static inline bool __context_present(struct context_entry *context)
 	return (context->lo & 1);
 }
 
-static inline bool context_present(struct context_entry *context)
+bool context_present(struct context_entry *context)
 {
 	return context_pasid_enabled(context) ?
 	     __context_present(context) :
@@ -788,8 +763,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 	domain->iommu_superpage = domain_update_iommu_superpage(NULL);
 }
 
-static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu,
-						       u8 bus, u8 devfn, int alloc)
+struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
+					 u8 devfn, int alloc)
 {
 	struct root_entry *root = &iommu->root_entry[bus];
 	struct context_entry *context;
@@ -4860,6 +4835,7 @@ int __init intel_iommu_init(void)
 	cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL,
 			  intel_iommu_cpu_dead);
 	intel_iommu_enabled = 1;
+	intel_iommu_debugfs_init();
 
 	return 0;
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index 967450bd421a..c2d6c11431de 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -76,7 +76,7 @@ static struct hpet_scope ir_hpet[MAX_HPET_TBS];
  * in single-threaded environment with interrupt disabled, so no need to tabke
  * the dmar_global_lock.
  */
-static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
+DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
 static const struct irq_domain_ops intel_ir_domain_ops;
 
 static void iommu_disable_irq_remapping(struct intel_iommu *iommu);
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index b5948ba6b3b3..445c3bde0480 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -587,6 +587,7 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data,
 	}
 
 	io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
+	io_pgtable_tlb_sync(&data->iop);
 	return size;
 }
 
@@ -642,6 +643,13 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data,
 				io_pgtable_tlb_sync(iop);
 				ptep = iopte_deref(pte[i], lvl);
 				__arm_v7s_free_table(ptep, lvl + 1, data);
+			} else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
+				/*
+				 * Order the PTE update against queueing the IOVA, to
+				 * guarantee that a flush callback from a different CPU
+				 * has observed it before the TLBIALL can be issued.
+				 */
+				smp_wmb();
 			} else {
 				io_pgtable_tlb_add_flush(iop, iova, blk_size,
 							 blk_size, true);
@@ -712,7 +720,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 			    IO_PGTABLE_QUIRK_NO_PERMS |
 			    IO_PGTABLE_QUIRK_TLBI_ON_MAP |
 			    IO_PGTABLE_QUIRK_ARM_MTK_4GB |
-			    IO_PGTABLE_QUIRK_NO_DMA))
+			    IO_PGTABLE_QUIRK_NO_DMA |
+			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
 	/* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 88641b4560bc..237cacd4a62b 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -574,13 +574,13 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data,
 			return 0;
 
 		tablep = iopte_deref(pte, data);
+	} else if (unmap_idx >= 0) {
+		io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
+		io_pgtable_tlb_sync(&data->iop);
+		return size;
 	}
 
-	if (unmap_idx < 0)
-		return __arm_lpae_unmap(data, iova, size, lvl, tablep);
-
-	io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true);
-	return size;
+	return __arm_lpae_unmap(data, iova, size, lvl, tablep);
 }
 
 static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
@@ -610,6 +610,13 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data,
 			io_pgtable_tlb_sync(iop);
 			ptep = iopte_deref(pte, data);
 			__arm_lpae_free_pgtable(data, lvl + 1, ptep);
+		} else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) {
+			/*
+			 * Order the PTE update against queueing the IOVA, to
+			 * guarantee that a flush callback from a different CPU
+			 * has observed it before the TLBIALL can be issued.
+			 */
+			smp_wmb();
 		} else {
 			io_pgtable_tlb_add_flush(iop, iova, size, size, true);
 		}
@@ -772,7 +779,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie)
 	u64 reg;
 	struct arm_lpae_io_pgtable *data;
 
-	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA))
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA |
+			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
@@ -864,7 +872,8 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie)
 	struct arm_lpae_io_pgtable *data;
 
 	/* The NS quirk doesn't apply at stage 2 */
-	if (cfg->quirks & ~IO_PGTABLE_QUIRK_NO_DMA)
+	if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NO_DMA |
+			    IO_PGTABLE_QUIRK_NON_STRICT))
 		return NULL;
 
 	data = arm_lpae_alloc_pgtable(cfg);
diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h
index 2df79093cad9..47d5ae559329 100644
--- a/drivers/iommu/io-pgtable.h
+++ b/drivers/iommu/io-pgtable.h
@@ -71,12 +71,17 @@ struct io_pgtable_cfg {
 	 *	be accessed by a fully cache-coherent IOMMU or CPU (e.g. for a
 	 *	software-emulated IOMMU), such that pagetable updates need not
 	 *	be treated as explicit DMA data.
+	 *
+	 * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs
+	 *	on unmap, for DMA domains using the flush queue mechanism for
+	 *	delayed invalidation.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS		BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS	BIT(1)
 	#define IO_PGTABLE_QUIRK_TLBI_ON_MAP	BIT(2)
 	#define IO_PGTABLE_QUIRK_ARM_MTK_4GB	BIT(3)
 	#define IO_PGTABLE_QUIRK_NO_DMA		BIT(4)
+	#define IO_PGTABLE_QUIRK_NON_STRICT	BIT(5)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8c15c5980299..edbdf5d6962c 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -32,6 +32,7 @@
 #include <linux/pci.h>
 #include <linux/bitops.h>
 #include <linux/property.h>
+#include <linux/fsl/mc.h>
 #include <trace/events/iommu.h>
 
 static struct kset *iommu_group_kset;
@@ -41,6 +42,7 @@ static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY;
 #else
 static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
 #endif
+static bool iommu_dma_strict __read_mostly = true;
 
 struct iommu_callback_data {
 	const struct iommu_ops *ops;
@@ -131,6 +133,12 @@ static int __init iommu_set_def_domain_type(char *str)
 }
 early_param("iommu.passthrough", iommu_set_def_domain_type);
 
+static int __init iommu_dma_setup(char *str)
+{
+	return kstrtobool(str, &iommu_dma_strict);
+}
+early_param("iommu.strict", iommu_dma_setup);
+
 static ssize_t iommu_group_attr_show(struct kobject *kobj,
 				     struct attribute *__attr, char *buf)
 {
@@ -1024,6 +1032,18 @@ struct iommu_group *pci_device_group(struct device *dev)
 	return iommu_group_alloc();
 }
 
+/* Get the IOMMU group for device on fsl-mc bus */
+struct iommu_group *fsl_mc_device_group(struct device *dev)
+{
+	struct device *cont_dev = fsl_mc_cont_dev(dev);
+	struct iommu_group *group;
+
+	group = iommu_group_get(cont_dev);
+	if (!group)
+		group = iommu_group_alloc();
+	return group;
+}
+
 /**
  * iommu_group_get_for_dev - Find or create the IOMMU group for a device
  * @dev: target device
@@ -1072,6 +1092,13 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 		group->default_domain = dom;
 		if (!group->domain)
 			group->domain = dom;
+
+		if (dom && !iommu_dma_strict) {
+			int attr = 1;
+			iommu_domain_set_attr(dom,
+					      DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
+					      &attr);
+		}
 	}
 
 	ret = iommu_group_add_device(group, dev);
@@ -1416,7 +1443,16 @@ struct iommu_domain *iommu_get_domain_for_dev(struct device *dev)
 EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev);
 
 /*
- * IOMMU groups are really the natrual working unit of the IOMMU, but
+ * For IOMMU_DOMAIN_DMA implementations which already provide their own
+ * guarantees that the group and its default domain are valid and correct.
+ */
+struct iommu_domain *iommu_get_dma_domain(struct device *dev)
+{
+	return dev->iommu_group->default_domain;
+}
+
+/*
+ * IOMMU groups are really the natural working unit of the IOMMU, but
  * the IOMMU API works on domains and devices.  Bridge that gap by
  * iterating over the devices in a group.  Ideally we'd have a single
  * device which represents the requestor ID of the group, but we also
@@ -1796,7 +1832,6 @@ int iommu_domain_get_attr(struct iommu_domain *domain,
 	struct iommu_domain_geometry *geometry;
 	bool *paging;
 	int ret = 0;
-	u32 *count;
 
 	switch (attr) {
 	case DOMAIN_ATTR_GEOMETRY:
@@ -1808,15 +1843,6 @@ int iommu_domain_get_attr(struct iommu_domain *domain,
 		paging  = data;
 		*paging = (domain->pgsize_bitmap != 0UL);
 		break;
-	case DOMAIN_ATTR_WINDOWS:
-		count = data;
-
-		if (domain->ops->domain_get_windows != NULL)
-			*count = domain->ops->domain_get_windows(domain);
-		else
-			ret = -ENODEV;
-
-		break;
 	default:
 		if (!domain->ops->domain_get_attr)
 			return -EINVAL;
@@ -1832,18 +1858,8 @@ int iommu_domain_set_attr(struct iommu_domain *domain,
 			  enum iommu_attr attr, void *data)
 {
 	int ret = 0;
-	u32 *count;
 
 	switch (attr) {
-	case DOMAIN_ATTR_WINDOWS:
-		count = data;
-
-		if (domain->ops->domain_set_windows != NULL)
-			ret = domain->ops->domain_set_windows(domain, *count);
-		else
-			ret = -ENODEV;
-
-		break;
 	default:
 		if (domain->ops->domain_set_attr == NULL)
 			return -EINVAL;
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 83fe2621effe..f8d3ba247523 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -56,6 +56,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	iovad->granule = granule;
 	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
+	iovad->max32_alloc_size = iovad->dma_32bit_pfn;
 	iovad->flush_cb = NULL;
 	iovad->fq = NULL;
 	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
@@ -139,8 +140,10 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 
 	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)
+	    free->pfn_lo >= cached_iova->pfn_lo) {
 		iovad->cached32_node = rb_next(&free->node);
+		iovad->max32_alloc_size = iovad->dma_32bit_pfn;
+	}
 
 	cached_iova = rb_entry(iovad->cached_node, struct iova, node);
 	if (free->pfn_lo >= cached_iova->pfn_lo)
@@ -190,6 +193,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 
 	/* Walk the tree backwards */
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	if (limit_pfn <= iovad->dma_32bit_pfn &&
+			size >= iovad->max32_alloc_size)
+		goto iova32_full;
+
 	curr = __get_cached_rbnode(iovad, limit_pfn);
 	curr_iova = rb_entry(curr, struct iova, node);
 	do {
@@ -200,10 +207,8 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		curr_iova = rb_entry(curr, struct iova, node);
 	} while (curr && new_pfn <= curr_iova->pfn_hi);
 
-	if (limit_pfn < size || new_pfn < iovad->start_pfn) {
-		spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-		return -ENOMEM;
-	}
+	if (limit_pfn < size || new_pfn < iovad->start_pfn)
+		goto iova32_full;
 
 	/* pfn_lo will point to size aligned address if size_aligned is set */
 	new->pfn_lo = new_pfn;
@@ -214,9 +219,12 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	__cached_rbnode_insert_update(iovad, new);
 
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-
-
 	return 0;
+
+iova32_full:
+	iovad->max32_alloc_size = size;
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	return -ENOMEM;
 }
 
 static struct kmem_cache *iova_cache;
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 22b94f8a9a04..b98a03189580 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * IPMMU VMSA
  *
  * Copyright (C) 2014 Renesas Electronics Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
  */
 
 #include <linux/bitmap.h>
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index f7787e757244..c5dd63072529 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -24,6 +24,7 @@
 #include <linux/of_iommu.h>
 #include <linux/of_pci.h>
 #include <linux/slab.h>
+#include <linux/fsl/mc.h>
 
 #define NO_IOMMU	1
 
@@ -132,9 +133,8 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
 	struct of_phandle_args iommu_spec = { .args_count = 1 };
 	int err;
 
-	err = of_pci_map_rid(info->np, alias, "iommu-map",
-			     "iommu-map-mask", &iommu_spec.np,
-			     iommu_spec.args);
+	err = of_map_rid(info->np, alias, "iommu-map", "iommu-map-mask",
+			 &iommu_spec.np, iommu_spec.args);
 	if (err)
 		return err == -ENODEV ? NO_IOMMU : err;
 
@@ -143,6 +143,23 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
 	return err;
 }
 
+static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev,
+				struct device_node *master_np)
+{
+	struct of_phandle_args iommu_spec = { .args_count = 1 };
+	int err;
+
+	err = of_map_rid(master_np, mc_dev->icid, "iommu-map",
+			 "iommu-map-mask", &iommu_spec.np,
+			 iommu_spec.args);
+	if (err)
+		return err == -ENODEV ? NO_IOMMU : err;
+
+	err = of_iommu_xlate(&mc_dev->dev, &iommu_spec);
+	of_node_put(iommu_spec.np);
+	return err;
+}
+
 const struct iommu_ops *of_iommu_configure(struct device *dev,
 					   struct device_node *master_np)
 {
@@ -174,6 +191,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 
 		err = pci_for_each_dma_alias(to_pci_dev(dev),
 					     of_pci_iommu_init, &info);
+	} else if (dev_is_fsl_mc(dev)) {
+		err = of_fsl_mc_iommu_init(to_fsl_mc_device(dev), master_np);
 	} else {
 		struct of_phandle_args iommu_spec;
 		int idx = 0;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 74eaedd5b860..90bf7d9fa17b 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -2045,3 +2045,105 @@ int of_find_last_cache_level(unsigned int cpu)
 
 	return cache_level;
 }
+
+/**
+ * of_map_rid - Translate a requester ID through a downstream mapping.
+ * @np: root complex device node.
+ * @rid: device requester ID to map.
+ * @map_name: property name of the map to use.
+ * @map_mask_name: optional property name of the mask to use.
+ * @target: optional pointer to a target device node.
+ * @id_out: optional pointer to receive the translated ID.
+ *
+ * Given a device requester ID, look up the appropriate implementation-defined
+ * platform ID and/or the target device which receives transactions on that
+ * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
+ * @id_out may be NULL if only the other is required. If @target points to
+ * a non-NULL device node pointer, only entries targeting that node will be
+ * matched; if it points to a NULL value, it will receive the device node of
+ * the first matching target phandle, with a reference held.
+ *
+ * Return: 0 on success or a standard error code on failure.
+ */
+int of_map_rid(struct device_node *np, u32 rid,
+	       const char *map_name, const char *map_mask_name,
+	       struct device_node **target, u32 *id_out)
+{
+	u32 map_mask, masked_rid;
+	int map_len;
+	const __be32 *map = NULL;
+
+	if (!np || !map_name || (!target && !id_out))
+		return -EINVAL;
+
+	map = of_get_property(np, map_name, &map_len);
+	if (!map) {
+		if (target)
+			return -ENODEV;
+		/* Otherwise, no map implies no translation */
+		*id_out = rid;
+		return 0;
+	}
+
+	if (!map_len || map_len % (4 * sizeof(*map))) {
+		pr_err("%pOF: Error: Bad %s length: %d\n", np,
+			map_name, map_len);
+		return -EINVAL;
+	}
+
+	/* The default is to select all bits. */
+	map_mask = 0xffffffff;
+
+	/*
+	 * Can be overridden by "{iommu,msi}-map-mask" property.
+	 * If of_property_read_u32() fails, the default is used.
+	 */
+	if (map_mask_name)
+		of_property_read_u32(np, map_mask_name, &map_mask);
+
+	masked_rid = map_mask & rid;
+	for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
+		struct device_node *phandle_node;
+		u32 rid_base = be32_to_cpup(map + 0);
+		u32 phandle = be32_to_cpup(map + 1);
+		u32 out_base = be32_to_cpup(map + 2);
+		u32 rid_len = be32_to_cpup(map + 3);
+
+		if (rid_base & ~map_mask) {
+			pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
+				np, map_name, map_name,
+				map_mask, rid_base);
+			return -EFAULT;
+		}
+
+		if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
+			continue;
+
+		phandle_node = of_find_node_by_phandle(phandle);
+		if (!phandle_node)
+			return -ENODEV;
+
+		if (target) {
+			if (*target)
+				of_node_put(phandle_node);
+			else
+				*target = phandle_node;
+
+			if (*target != phandle_node)
+				continue;
+		}
+
+		if (id_out)
+			*id_out = masked_rid - rid_base + out_base;
+
+		pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
+			np, map_name, map_mask, rid_base, out_base,
+			rid_len, rid, masked_rid - rid_base + out_base);
+		return 0;
+	}
+
+	pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n",
+		np, map_name, rid, target && *target ? *target : NULL);
+	return -EFAULT;
+}
+EXPORT_SYMBOL_GPL(of_map_rid);
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 02ad93a304a4..e1f6f392a4c0 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -22,7 +22,6 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include <linux/of_pci.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 
@@ -588,8 +587,8 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
 	 * "msi-map" property.
 	 */
 	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
-		if (!of_pci_map_rid(parent_dev->of_node, rid_in, "msi-map",
-				    "msi-map-mask", np, &rid_out))
+		if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map",
+				"msi-map-mask", np, &rid_out))
 			break;
 	return rid_out;
 }
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index 1836b8ddf292..4c4217d0c3f1 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -355,107 +355,6 @@ failed:
 EXPORT_SYMBOL_GPL(devm_of_pci_get_host_bridge_resources);
 #endif /* CONFIG_OF_ADDRESS */
 
-/**
- * of_pci_map_rid - Translate a requester ID through a downstream mapping.
- * @np: root complex device node.
- * @rid: PCI requester ID to map.
- * @map_name: property name of the map to use.
- * @map_mask_name: optional property name of the mask to use.
- * @target: optional pointer to a target device node.
- * @id_out: optional pointer to receive the translated ID.
- *
- * Given a PCI requester ID, look up the appropriate implementation-defined
- * platform ID and/or the target device which receives transactions on that
- * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
- * @id_out may be NULL if only the other is required. If @target points to
- * a non-NULL device node pointer, only entries targeting that node will be
- * matched; if it points to a NULL value, it will receive the device node of
- * the first matching target phandle, with a reference held.
- *
- * Return: 0 on success or a standard error code on failure.
- */
-int of_pci_map_rid(struct device_node *np, u32 rid,
-		   const char *map_name, const char *map_mask_name,
-		   struct device_node **target, u32 *id_out)
-{
-	u32 map_mask, masked_rid;
-	int map_len;
-	const __be32 *map = NULL;
-
-	if (!np || !map_name || (!target && !id_out))
-		return -EINVAL;
-
-	map = of_get_property(np, map_name, &map_len);
-	if (!map) {
-		if (target)
-			return -ENODEV;
-		/* Otherwise, no map implies no translation */
-		*id_out = rid;
-		return 0;
-	}
-
-	if (!map_len || map_len % (4 * sizeof(*map))) {
-		pr_err("%pOF: Error: Bad %s length: %d\n", np,
-			map_name, map_len);
-		return -EINVAL;
-	}
-
-	/* The default is to select all bits. */
-	map_mask = 0xffffffff;
-
-	/*
-	 * Can be overridden by "{iommu,msi}-map-mask" property.
-	 * If of_property_read_u32() fails, the default is used.
-	 */
-	if (map_mask_name)
-		of_property_read_u32(np, map_mask_name, &map_mask);
-
-	masked_rid = map_mask & rid;
-	for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
-		struct device_node *phandle_node;
-		u32 rid_base = be32_to_cpup(map + 0);
-		u32 phandle = be32_to_cpup(map + 1);
-		u32 out_base = be32_to_cpup(map + 2);
-		u32 rid_len = be32_to_cpup(map + 3);
-
-		if (rid_base & ~map_mask) {
-			pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
-				np, map_name, map_name,
-				map_mask, rid_base);
-			return -EFAULT;
-		}
-
-		if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
-			continue;
-
-		phandle_node = of_find_node_by_phandle(phandle);
-		if (!phandle_node)
-			return -ENODEV;
-
-		if (target) {
-			if (*target)
-				of_node_put(phandle_node);
-			else
-				*target = phandle_node;
-
-			if (*target != phandle_node)
-				continue;
-		}
-
-		if (id_out)
-			*id_out = masked_rid - rid_base + out_base;
-
-		pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
-			np, map_name, map_mask, rid_base, out_base,
-			rid_len, rid, masked_rid - rid_base + out_base);
-		return 0;
-	}
-
-	pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n",
-		np, map_name, rid, target && *target ? *target : NULL);
-	return -EFAULT;
-}
-
 #if IS_ENABLED(CONFIG_OF_IRQ)
 /**
  * of_irq_parse_pci - Resolve the interrupt for a PCI device