Merge tag 'iommu-updates-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - ARM-SMMU Updates from Will:

      - Continued SVM enablement, where page-table is shared with CPU

      - Groundwork to support integrated SMMU with Adreno GPU

      - Allow disabling of MSI-based polling on the kernel command-line

      - Minor driver fixes and cleanups (octal permissions, error
        messages, ...)

 - Secure Nested Paging Support for AMD IOMMU. The IOMMU will fault when
   a device tries DMA on memory owned by a guest. This needs new
   fault-types as well as a rewrite of the IOMMU memory semaphore for
   command completions.

 - Allow broken Intel IOMMUs (wrong address widths reported) to still be
   used for interrupt remapping.

 - IOMMU UAPI updates for supporting vSVA, where the IOMMU can access
   address spaces of processes running in a VM.

 - Support for the MT8167 IOMMU in the Mediatek IOMMU driver.

 - Device-tree updates for the Renesas driver to support r8a7742.

 - Several smaller fixes and cleanups all over the place.

* tag 'iommu-updates-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (57 commits)
  iommu/vt-d: Gracefully handle DMAR units with no supported address widths
  iommu/vt-d: Check UAPI data processed by IOMMU core
  iommu/uapi: Handle data and argsz filled by users
  iommu/uapi: Rename uapi functions
  iommu/uapi: Use named union for user data
  iommu/uapi: Add argsz for user filled data
  docs: IOMMU user API
  iommu/qcom: add missing put_device() call in qcom_iommu_of_xlate()
  iommu/arm-smmu-v3: Add SVA device feature
  iommu/arm-smmu-v3: Check for SVA features
  iommu/arm-smmu-v3: Seize private ASID
  iommu/arm-smmu-v3: Share process page tables
  iommu/arm-smmu-v3: Move definitions to a header
  iommu/io-pgtable-arm: Move some definitions to a header
  iommu/arm-smmu-v3: Ensure queue is read after updating prod pointer
  iommu/amd: Re-purpose Exclusion range registers to support SNP CWWB
  iommu/amd: Add support for RMP_PAGE_FAULT and RMP_HW_ERR
  iommu/amd: Use 4K page for completion wait write-back semaphore
  iommu/tegra-smmu: Allow to group clients in same swgroup
  iommu/tegra-smmu: Fix iova->phys translation
  ...

26 files changed, 1894 insertions, 900 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index bef5d75e306b..04878caf6da4 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -232,7 +232,7 @@ config IPMMU_VMSA
 	select ARM_DMA_USE_IOMMU
 	help
 	  Support for the Renesas VMSA-compatible IPMMU found in the R-Mobile
-	  APE6, R-Car Gen2, and R-Car Gen3 SoCs.
+	  APE6, R-Car Gen{2,3} and RZ/G{1,2} SoCs.
 
 	  If unsure, say N.
 
@@ -308,6 +308,16 @@ config ARM_SMMU_V3
 	  Say Y here if your system includes an IOMMU device implementing
 	  the ARM SMMUv3 architecture.
 
+config ARM_SMMU_V3_SVA
+	bool "Shared Virtual Addressing support for the ARM SMMUv3"
+	depends on ARM_SMMU_V3
+	help
+	  Support for sharing process address spaces with devices using the
+	  SMMUv3.
+
+	  Say Y here if your system supports SVA extensions such as PCIe PASID
+	  and PRI.
+
 config S390_IOMMU
 	def_bool y if S390 && PCI
 	depends on S390 && PCI
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 030ee90197a1..6b8cbdf71714 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -41,6 +41,15 @@ extern int amd_iommu_guest_ir;
 struct iommu_domain;
 
 extern bool amd_iommu_v2_supported(void);
+extern struct amd_iommu *get_amd_iommu(unsigned int idx);
+extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+extern bool amd_iommu_pc_supported(void);
+extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
+extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
+
 extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
 extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
 extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 30a5d412255a..f696ac7c5f89 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -93,6 +93,7 @@
 #define FEATURE_PC		(1ULL<<9)
 #define FEATURE_GAM_VAPIC	(1ULL<<21)
 #define FEATURE_EPHSUP		(1ULL<<50)
+#define FEATURE_SNP		(1ULL<<63)
 
 #define FEATURE_PASID_SHIFT	32
 #define FEATURE_PASID_MASK	(0x1fULL << FEATURE_PASID_SHIFT)
@@ -128,6 +129,8 @@
 #define EVENT_TYPE_IOTLB_INV_TO	0x7
 #define EVENT_TYPE_INV_DEV_REQ	0x8
 #define EVENT_TYPE_INV_PPR_REQ	0x9
+#define EVENT_TYPE_RMP_FAULT	0xd
+#define EVENT_TYPE_RMP_HW_ERR	0xe
 #define EVENT_DEVID_MASK	0xffff
 #define EVENT_DEVID_SHIFT	0
 #define EVENT_DOMID_MASK_LO	0xffff
@@ -595,7 +598,8 @@ struct amd_iommu {
 #endif
 
 	u32 flags;
-	volatile u64 __aligned(8) cmd_sem;
+	volatile u64 *cmd_sem;
+	u64 cmd_sem_val;
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 1ba6b4cc56e8..82e4af8f09bb 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -359,6 +359,29 @@ static void iommu_set_exclusion_range(struct amd_iommu *iommu)
 			&entry, sizeof(entry));
 }
 
+static void iommu_set_cwwb_range(struct amd_iommu *iommu)
+{
+	u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem);
+	u64 entry = start & PM_ADDR_MASK;
+
+	if (!iommu_feature(iommu, FEATURE_SNP))
+		return;
+
+	/* Note:
+	 * Re-purpose Exclusion base/limit registers for Completion wait
+	 * write-back base/limit.
+	 */
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* Note:
+	 * Default to 4 Kbytes, which can be specified by setting base
+	 * address equal to the limit address.
+	 */
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
+		    &entry, sizeof(entry));
+}
+
 /* Programs the physical address of the device table into the IOMMU hardware */
 static void iommu_set_device_table(struct amd_iommu *iommu)
 {
@@ -813,6 +836,19 @@ static int iommu_init_ga(struct amd_iommu *iommu)
 	return ret;
 }
 
+static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
+{
+	iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL);
+
+	return iommu->cmd_sem ? 0 : -ENOMEM;
+}
+
+static void __init free_cwwb_sem(struct amd_iommu *iommu)
+{
+	if (iommu->cmd_sem)
+		free_page((unsigned long)iommu->cmd_sem);
+}
+
 static void iommu_enable_xt(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
@@ -1376,6 +1412,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 
 static void __init free_iommu_one(struct amd_iommu *iommu)
 {
+	free_cwwb_sem(iommu);
 	free_command_buffer(iommu);
 	free_event_buffer(iommu);
 	free_ppr_log(iommu);
@@ -1462,6 +1499,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	int ret;
 
 	raw_spin_lock_init(&iommu->lock);
+	iommu->cmd_sem_val = 0;
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);
@@ -1539,6 +1577,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (!iommu->mmio_base)
 		return -ENOMEM;
 
+	if (alloc_cwwb_sem(iommu))
+		return -ENOMEM;
+
 	if (alloc_command_buffer(iommu))
 		return -ENOMEM;
 
@@ -1576,7 +1617,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 
 /**
  * get_highest_supported_ivhd_type - Look up the appropriate IVHD type
- * @ivrs          Pointer to the IVRS header
+ * @ivrs: Pointer to the IVRS header
  *
  * This function search through all IVDB of the maximum supported IVHD
  */
@@ -1864,6 +1905,9 @@ static int __init amd_iommu_init_pci(void)
 		ret = iommu_init_pci(iommu);
 		if (ret)
 			break;
+
+		/* Need to setup range after PCI init */
+		iommu_set_cwwb_range(iommu);
 	}
 
 	/*
@@ -1927,7 +1971,7 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 #define XT_INT_VEC(x)		(((x) & 0xFFULL) << 32)
 #define XT_INT_DEST_HI(x)	((((x) >> 24) & 0xFFULL) << 56)
 
-/**
+/*
  * Setup the IntCapXT registers with interrupt routing information
  * based on the PCI MSI capability block registers, accessed via
  * MMIO MSI address low/hi and MSI data registers.
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 9e231caa5012..4b1b02c80f55 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -486,6 +486,67 @@ static void dump_command(unsigned long phys_addr)
 		pr_err("CMD[%d]: %08x\n", i, cmd->data[i]);
 }
 
+static void amd_iommu_report_rmp_hw_error(volatile u32 *event)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	int devid, vmg_tag, flags;
+	struct pci_dev *pdev;
+	u64 spa;
+
+	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	vmg_tag = (event[1]) & 0xFFFF;
+	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	spa     = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8);
+
+	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data && __ratelimit(&dev_data->rs)) {
+		pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+			vmg_tag, spa, flags);
+	} else {
+		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			vmg_tag, spa, flags);
+	}
+
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
+static void amd_iommu_report_rmp_fault(volatile u32 *event)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	int devid, flags_rmp, vmg_tag, flags;
+	struct pci_dev *pdev;
+	u64 gpa;
+
+	devid     = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	flags_rmp = (event[0] >> EVENT_FLAGS_SHIFT) & 0xFF;
+	vmg_tag   = (event[1]) & 0xFFFF;
+	flags     = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	gpa       = ((u64)event[3] << 32) | event[2];
+
+	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data && __ratelimit(&dev_data->rs)) {
+		pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+			vmg_tag, gpa, flags_rmp, flags);
+	} else {
+		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			vmg_tag, gpa, flags_rmp, flags);
+	}
+
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
 static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 					u64 address, int flags)
 {
@@ -578,6 +639,12 @@ retry:
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
+	case EVENT_TYPE_RMP_FAULT:
+		amd_iommu_report_rmp_fault(event);
+		break;
+	case EVENT_TYPE_RMP_HW_ERR:
+		amd_iommu_report_rmp_hw_error(event);
+		break;
 	case EVENT_TYPE_INV_PPR_REQ:
 		pasid = PPR_PASID(*((u64 *)__evt));
 		tag = event[1] & 0x03FF;
@@ -807,11 +874,11 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
  *
  ****************************************************************************/
 
-static int wait_on_sem(volatile u64 *sem)
+static int wait_on_sem(struct amd_iommu *iommu, u64 data)
 {
 	int i = 0;
 
-	while (*sem == 0 && i < LOOP_TIMEOUT) {
+	while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) {
 		udelay(1);
 		i += 1;
 	}
@@ -842,16 +909,16 @@ static void copy_cmd_to_buffer(struct amd_iommu *iommu,
 	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 }
 
-static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
+static void build_completion_wait(struct iommu_cmd *cmd,
+				  struct amd_iommu *iommu,
+				  u64 data)
 {
-	u64 paddr = iommu_virt_to_phys((void *)address);
-
-	WARN_ON(address & 0x7ULL);
+	u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem);
 
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
 	cmd->data[1] = upper_32_bits(paddr);
-	cmd->data[2] = 1;
+	cmd->data[2] = data;
 	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
 }
 
@@ -1060,22 +1127,21 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	struct iommu_cmd cmd;
 	unsigned long flags;
 	int ret;
+	u64 data;
 
 	if (!iommu->need_sync)
 		return 0;
 
-
-	build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
-
 	raw_spin_lock_irqsave(&iommu->lock, flags);
 
-	iommu->cmd_sem = 0;
+	data = ++iommu->cmd_sem_val;
+	build_completion_wait(&cmd, iommu, data);
 
 	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_unlock;
 
-	ret = wait_on_sem(&iommu->cmd_sem);
+	ret = wait_on_sem(iommu, data);
 
 out_unlock:
 	raw_spin_unlock_irqrestore(&iommu->lock, flags);
diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile
index 569e24e9f162..54feb1ecccad 100644
--- a/drivers/iommu/arm/arm-smmu-v3/Makefile
+++ b/drivers/iommu/arm/arm-smmu-v3/Makefile
@@ -1,2 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
+obj-$(CONFIG_ARM_SMMU_V3) += arm_smmu_v3.o
+arm_smmu_v3-objs-y += arm-smmu-v3.o
+arm_smmu_v3-objs-$(CONFIG_ARM_SMMU_V3_SVA) += arm-smmu-v3-sva.o
+arm_smmu_v3-objs := $(arm_smmu_v3-objs-y)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
new file mode 100644
index 000000000000..9255c9600fb8
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of the IOMMU SVA API for the ARM SMMUv3
+ */
+
+#include <linux/mm.h>
+#include <linux/mmu_context.h>
+#include <linux/slab.h>
+
+#include "arm-smmu-v3.h"
+#include "../../io-pgtable-arm.h"
+
+static DEFINE_MUTEX(sva_lock);
+
+/*
+ * Check if the CPU ASID is available on the SMMU side. If a private context
+ * descriptor is using it, try to replace it.
+ */
+static struct arm_smmu_ctx_desc *
+arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
+{
+	int ret;
+	u32 new_asid;
+	struct arm_smmu_ctx_desc *cd;
+	struct arm_smmu_device *smmu;
+	struct arm_smmu_domain *smmu_domain;
+
+	cd = xa_load(&arm_smmu_asid_xa, asid);
+	if (!cd)
+		return NULL;
+
+	if (cd->mm) {
+		if (WARN_ON(cd->mm != mm))
+			return ERR_PTR(-EINVAL);
+		/* All devices bound to this mm use the same cd struct. */
+		refcount_inc(&cd->refs);
+		return cd;
+	}
+
+	smmu_domain = container_of(cd, struct arm_smmu_domain, s1_cfg.cd);
+	smmu = smmu_domain->smmu;
+
+	ret = xa_alloc(&arm_smmu_asid_xa, &new_asid, cd,
+		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
+	if (ret)
+		return ERR_PTR(-ENOSPC);
+	/*
+	 * Race with unmap: TLB invalidations will start targeting the new ASID,
+	 * which isn't assigned yet. We'll do an invalidate-all on the old ASID
+	 * later, so it doesn't matter.
+	 */
+	cd->asid = new_asid;
+	/*
+	 * Update ASID and invalidate CD in all associated masters. There will
+	 * be some overlap between use of both ASIDs, until we invalidate the
+	 * TLB.
+	 */
+	arm_smmu_write_ctx_desc(smmu_domain, 0, cd);
+
+	/* Invalidate TLB entries previously associated with that context */
+	arm_smmu_tlb_inv_asid(smmu, asid);
+
+	xa_erase(&arm_smmu_asid_xa, asid);
+	return NULL;
+}
+
+__maybe_unused
+static struct arm_smmu_ctx_desc *arm_smmu_alloc_shared_cd(struct mm_struct *mm)
+{
+	u16 asid;
+	int err = 0;
+	u64 tcr, par, reg;
+	struct arm_smmu_ctx_desc *cd;
+	struct arm_smmu_ctx_desc *ret = NULL;
+
+	asid = arm64_mm_context_get(mm);
+	if (!asid)
+		return ERR_PTR(-ESRCH);
+
+	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
+	if (!cd) {
+		err = -ENOMEM;
+		goto out_put_context;
+	}
+
+	refcount_set(&cd->refs, 1);
+
+	mutex_lock(&arm_smmu_asid_lock);
+	ret = arm_smmu_share_asid(mm, asid);
+	if (ret) {
+		mutex_unlock(&arm_smmu_asid_lock);
+		goto out_free_cd;
+	}
+
+	err = xa_insert(&arm_smmu_asid_xa, asid, cd, GFP_KERNEL);
+	mutex_unlock(&arm_smmu_asid_lock);
+
+	if (err)
+		goto out_free_asid;
+
+	tcr = FIELD_PREP(CTXDESC_CD_0_TCR_T0SZ, 64ULL - vabits_actual) |
+	      FIELD_PREP(CTXDESC_CD_0_TCR_IRGN0, ARM_LPAE_TCR_RGN_WBWA) |
+	      FIELD_PREP(CTXDESC_CD_0_TCR_ORGN0, ARM_LPAE_TCR_RGN_WBWA) |
+	      FIELD_PREP(CTXDESC_CD_0_TCR_SH0, ARM_LPAE_TCR_SH_IS) |
+	      CTXDESC_CD_0_TCR_EPD1 | CTXDESC_CD_0_AA64;
+
+	switch (PAGE_SIZE) {
+	case SZ_4K:
+		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_4K);
+		break;
+	case SZ_16K:
+		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_16K);
+		break;
+	case SZ_64K:
+		tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_TG0, ARM_LPAE_TCR_TG0_64K);
+		break;
+	default:
+		WARN_ON(1);
+		err = -EINVAL;
+		goto out_free_asid;
+	}
+
+	reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	par = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_PARANGE_SHIFT);
+	tcr |= FIELD_PREP(CTXDESC_CD_0_TCR_IPS, par);
+
+	cd->ttbr = virt_to_phys(mm->pgd);
+	cd->tcr = tcr;
+	/*
+	 * MAIR value is pretty much constant and global, so we can just get it
+	 * from the current CPU register
+	 */
+	cd->mair = read_sysreg(mair_el1);
+	cd->asid = asid;
+	cd->mm = mm;
+
+	return cd;
+
+out_free_asid:
+	arm_smmu_free_asid(cd);
+out_free_cd:
+	kfree(cd);
+out_put_context:
+	arm64_mm_context_put(mm);
+	return err < 0 ? ERR_PTR(err) : ret;
+}
+
+__maybe_unused
+static void arm_smmu_free_shared_cd(struct arm_smmu_ctx_desc *cd)
+{
+	if (arm_smmu_free_asid(cd)) {
+		/* Unpin ASID */
+		arm64_mm_context_put(cd->mm);
+		kfree(cd);
+	}
+}
+
+bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
+{
+	unsigned long reg, fld;
+	unsigned long oas;
+	unsigned long asid_bits;
+	u32 feat_mask = ARM_SMMU_FEAT_BTM | ARM_SMMU_FEAT_COHERENCY;
+
+	if (vabits_actual == 52)
+		feat_mask |= ARM_SMMU_FEAT_VAX;
+
+	if ((smmu->features & feat_mask) != feat_mask)
+		return false;
+
+	if (!(smmu->pgsize_bitmap & PAGE_SIZE))
+		return false;
+
+	/*
+	 * Get the smallest PA size of all CPUs (sanitized by cpufeature). We're
+	 * not even pretending to support AArch32 here. Abort if the MMU outputs
+	 * addresses larger than what we support.
+	 */
+	reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_PARANGE_SHIFT);
+	oas = id_aa64mmfr0_parange_to_phys_shift(fld);
+	if (smmu->oas < oas)
+		return false;
+
+	/* We can support bigger ASIDs than the CPU, but not smaller */
+	fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR0_ASID_SHIFT);
+	asid_bits = fld ? 16 : 8;
+	if (smmu->asid_bits < asid_bits)
+		return false;
+
+	/*
+	 * See max_pinned_asids in arch/arm64/mm/context.c. The following is
+	 * generally the maximum number of bindable processes.
+	 */
+	if (arm64_kernel_unmapped_at_el0())
+		asid_bits--;
+	dev_dbg(smmu->dev, "%d shared contexts\n", (1 << asid_bits) -
+		num_possible_cpus() - 2);
+
+	return true;
+}
+
+static bool arm_smmu_iopf_supported(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
+{
+	if (!(master->smmu->features & ARM_SMMU_FEAT_SVA))
+		return false;
+
+	/* SSID and IOPF support are mandatory for the moment */
+	return master->ssid_bits && arm_smmu_iopf_supported(master);
+}
+
+bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
+{
+	bool enabled;
+
+	mutex_lock(&sva_lock);
+	enabled = master->sva_enabled;
+	mutex_unlock(&sva_lock);
+	return enabled;
+}
+
+int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
+{
+	mutex_lock(&sva_lock);
+	master->sva_enabled = true;
+	mutex_unlock(&sva_lock);
+
+	return 0;
+}
+
+int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
+{
+	mutex_lock(&sva_lock);
+	if (!list_empty(&master->bonds)) {
+		dev_err(master->dev, "cannot disable SVA, device is bound\n");
+		mutex_unlock(&sva_lock);
+		return -EBUSY;
+	}
+	master->sva_enabled = false;
+	mutex_unlock(&sva_lock);
+
+	return 0;
+}
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
index c192544e874b..e634bbe60573 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -11,7 +11,6 @@
 
 #include <linux/acpi.h>
 #include <linux/acpi_iort.h>
-#include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/crash_dump.h>
 #include <linux/delay.h>
@@ -19,7 +18,6 @@
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io-pgtable.h>
-#include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/msi.h>
@@ -33,396 +31,17 @@
 
 #include <linux/amba/bus.h>
 
-/* MMIO registers */
-#define ARM_SMMU_IDR0			0x0
-#define IDR0_ST_LVL			GENMASK(28, 27)
-#define IDR0_ST_LVL_2LVL		1
-#define IDR0_STALL_MODEL		GENMASK(25, 24)
-#define IDR0_STALL_MODEL_STALL		0
-#define IDR0_STALL_MODEL_FORCE		2
-#define IDR0_TTENDIAN			GENMASK(22, 21)
-#define IDR0_TTENDIAN_MIXED		0
-#define IDR0_TTENDIAN_LE		2
-#define IDR0_TTENDIAN_BE		3
-#define IDR0_CD2L			(1 << 19)
-#define IDR0_VMID16			(1 << 18)
-#define IDR0_PRI			(1 << 16)
-#define IDR0_SEV			(1 << 14)
-#define IDR0_MSI			(1 << 13)
-#define IDR0_ASID16			(1 << 12)
-#define IDR0_ATS			(1 << 10)
-#define IDR0_HYP			(1 << 9)
-#define IDR0_COHACC			(1 << 4)
-#define IDR0_TTF			GENMASK(3, 2)
-#define IDR0_TTF_AARCH64		2
-#define IDR0_TTF_AARCH32_64		3
-#define IDR0_S1P			(1 << 1)
-#define IDR0_S2P			(1 << 0)
-
-#define ARM_SMMU_IDR1			0x4
-#define IDR1_TABLES_PRESET		(1 << 30)
-#define IDR1_QUEUES_PRESET		(1 << 29)
-#define IDR1_REL			(1 << 28)
-#define IDR1_CMDQS			GENMASK(25, 21)
-#define IDR1_EVTQS			GENMASK(20, 16)
-#define IDR1_PRIQS			GENMASK(15, 11)
-#define IDR1_SSIDSIZE			GENMASK(10, 6)
-#define IDR1_SIDSIZE			GENMASK(5, 0)
-
-#define ARM_SMMU_IDR3			0xc
-#define IDR3_RIL			(1 << 10)
-
-#define ARM_SMMU_IDR5			0x14
-#define IDR5_STALL_MAX			GENMASK(31, 16)
-#define IDR5_GRAN64K			(1 << 6)
-#define IDR5_GRAN16K			(1 << 5)
-#define IDR5_GRAN4K			(1 << 4)
-#define IDR5_OAS			GENMASK(2, 0)
-#define IDR5_OAS_32_BIT			0
-#define IDR5_OAS_36_BIT			1
-#define IDR5_OAS_40_BIT			2
-#define IDR5_OAS_42_BIT			3
-#define IDR5_OAS_44_BIT			4
-#define IDR5_OAS_48_BIT			5
-#define IDR5_OAS_52_BIT			6
-#define IDR5_VAX			GENMASK(11, 10)
-#define IDR5_VAX_52_BIT			1
-
-#define ARM_SMMU_CR0			0x20
-#define CR0_ATSCHK			(1 << 4)
-#define CR0_CMDQEN			(1 << 3)
-#define CR0_EVTQEN			(1 << 2)
-#define CR0_PRIQEN			(1 << 1)
-#define CR0_SMMUEN			(1 << 0)
-
-#define ARM_SMMU_CR0ACK			0x24
-
-#define ARM_SMMU_CR1			0x28
-#define CR1_TABLE_SH			GENMASK(11, 10)
-#define CR1_TABLE_OC			GENMASK(9, 8)
-#define CR1_TABLE_IC			GENMASK(7, 6)
-#define CR1_QUEUE_SH			GENMASK(5, 4)
-#define CR1_QUEUE_OC			GENMASK(3, 2)
-#define CR1_QUEUE_IC			GENMASK(1, 0)
-/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */
-#define CR1_CACHE_NC			0
-#define CR1_CACHE_WB			1
-#define CR1_CACHE_WT			2
-
-#define ARM_SMMU_CR2			0x2c
-#define CR2_PTM				(1 << 2)
-#define CR2_RECINVSID			(1 << 1)
-#define CR2_E2H				(1 << 0)
-
-#define ARM_SMMU_GBPA			0x44
-#define GBPA_UPDATE			(1 << 31)
-#define GBPA_ABORT			(1 << 20)
-
-#define ARM_SMMU_IRQ_CTRL		0x50
-#define IRQ_CTRL_EVTQ_IRQEN		(1 << 2)
-#define IRQ_CTRL_PRIQ_IRQEN		(1 << 1)
-#define IRQ_CTRL_GERROR_IRQEN		(1 << 0)
-
-#define ARM_SMMU_IRQ_CTRLACK		0x54
-
-#define ARM_SMMU_GERROR			0x60
-#define GERROR_SFM_ERR			(1 << 8)
-#define GERROR_MSI_GERROR_ABT_ERR	(1 << 7)
-#define GERROR_MSI_PRIQ_ABT_ERR		(1 << 6)
-#define GERROR_MSI_EVTQ_ABT_ERR		(1 << 5)
-#define GERROR_MSI_CMDQ_ABT_ERR		(1 << 4)
-#define GERROR_PRIQ_ABT_ERR		(1 << 3)
-#define GERROR_EVTQ_ABT_ERR		(1 << 2)
-#define GERROR_CMDQ_ERR			(1 << 0)
-#define GERROR_ERR_MASK			0xfd
-
-#define ARM_SMMU_GERRORN		0x64
-
-#define ARM_SMMU_GERROR_IRQ_CFG0	0x68
-#define ARM_SMMU_GERROR_IRQ_CFG1	0x70
-#define ARM_SMMU_GERROR_IRQ_CFG2	0x74
-
-#define ARM_SMMU_STRTAB_BASE		0x80
-#define STRTAB_BASE_RA			(1UL << 62)
-#define STRTAB_BASE_ADDR_MASK		GENMASK_ULL(51, 6)
-
-#define ARM_SMMU_STRTAB_BASE_CFG	0x88
-#define STRTAB_BASE_CFG_FMT		GENMASK(17, 16)
-#define STRTAB_BASE_CFG_FMT_LINEAR	0
-#define STRTAB_BASE_CFG_FMT_2LVL	1
-#define STRTAB_BASE_CFG_SPLIT		GENMASK(10, 6)
-#define STRTAB_BASE_CFG_LOG2SIZE	GENMASK(5, 0)
-
-#define ARM_SMMU_CMDQ_BASE		0x90
-#define ARM_SMMU_CMDQ_PROD		0x98
-#define ARM_SMMU_CMDQ_CONS		0x9c
-
-#define ARM_SMMU_EVTQ_BASE		0xa0
-#define ARM_SMMU_EVTQ_PROD		0x100a8
-#define ARM_SMMU_EVTQ_CONS		0x100ac
-#define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
-#define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
-#define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
-
-#define ARM_SMMU_PRIQ_BASE		0xc0
-#define ARM_SMMU_PRIQ_PROD		0x100c8
-#define ARM_SMMU_PRIQ_CONS		0x100cc
-#define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
-#define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
-#define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
-
-#define ARM_SMMU_REG_SZ			0xe00
-
-/* Common MSI config fields */
-#define MSI_CFG0_ADDR_MASK		GENMASK_ULL(51, 2)
-#define MSI_CFG2_SH			GENMASK(5, 4)
-#define MSI_CFG2_MEMATTR		GENMASK(3, 0)
-
-/* Common memory attribute values */
-#define ARM_SMMU_SH_NSH			0
-#define ARM_SMMU_SH_OSH			2
-#define ARM_SMMU_SH_ISH			3
-#define ARM_SMMU_MEMATTR_DEVICE_nGnRE	0x1
-#define ARM_SMMU_MEMATTR_OIWB		0xf
-
-#define Q_IDX(llq, p)			((p) & ((1 << (llq)->max_n_shift) - 1))
-#define Q_WRP(llq, p)			((p) & (1 << (llq)->max_n_shift))
-#define Q_OVERFLOW_FLAG			(1U << 31)
-#define Q_OVF(p)			((p) & Q_OVERFLOW_FLAG)
-#define Q_ENT(q, p)			((q)->base +			\
-					 Q_IDX(&((q)->llq), p) *	\
-					 (q)->ent_dwords)
-
-#define Q_BASE_RWA			(1UL << 62)
-#define Q_BASE_ADDR_MASK		GENMASK_ULL(51, 5)
-#define Q_BASE_LOG2SIZE			GENMASK(4, 0)
-
-/* Ensure DMA allocations are naturally aligned */
-#ifdef CONFIG_CMA_ALIGNMENT
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
-#else
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER - 1)
-#endif
-
-/*
- * Stream table.
- *
- * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
- * 2lvl: 128k L1 entries,
- *       256 lazy entries per table (each table covers a PCI bus)
- */
-#define STRTAB_L1_SZ_SHIFT		20
-#define STRTAB_SPLIT			8
-
-#define STRTAB_L1_DESC_DWORDS		1
-#define STRTAB_L1_DESC_SPAN		GENMASK_ULL(4, 0)
-#define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
-
-#define STRTAB_STE_DWORDS		8
-#define STRTAB_STE_0_V			(1UL << 0)
-#define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
-#define STRTAB_STE_0_CFG_ABORT		0
-#define STRTAB_STE_0_CFG_BYPASS		4
-#define STRTAB_STE_0_CFG_S1_TRANS	5
-#define STRTAB_STE_0_CFG_S2_TRANS	6
-
-#define STRTAB_STE_0_S1FMT		GENMASK_ULL(5, 4)
-#define STRTAB_STE_0_S1FMT_LINEAR	0
-#define STRTAB_STE_0_S1FMT_64K_L2	2
-#define STRTAB_STE_0_S1CTXPTR_MASK	GENMASK_ULL(51, 6)
-#define STRTAB_STE_0_S1CDMAX		GENMASK_ULL(63, 59)
-
-#define STRTAB_STE_1_S1DSS		GENMASK_ULL(1, 0)
-#define STRTAB_STE_1_S1DSS_TERMINATE	0x0
-#define STRTAB_STE_1_S1DSS_BYPASS	0x1
-#define STRTAB_STE_1_S1DSS_SSID0	0x2
-
-#define STRTAB_STE_1_S1C_CACHE_NC	0UL
-#define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
-#define STRTAB_STE_1_S1C_CACHE_WT	2UL
-#define STRTAB_STE_1_S1C_CACHE_WB	3UL
-#define STRTAB_STE_1_S1CIR		GENMASK_ULL(3, 2)
-#define STRTAB_STE_1_S1COR		GENMASK_ULL(5, 4)
-#define STRTAB_STE_1_S1CSH		GENMASK_ULL(7, 6)
-
-#define STRTAB_STE_1_S1STALLD		(1UL << 27)
-
-#define STRTAB_STE_1_EATS		GENMASK_ULL(29, 28)
-#define STRTAB_STE_1_EATS_ABT		0UL
-#define STRTAB_STE_1_EATS_TRANS		1UL
-#define STRTAB_STE_1_EATS_S1CHK		2UL
-
-#define STRTAB_STE_1_STRW		GENMASK_ULL(31, 30)
-#define STRTAB_STE_1_STRW_NSEL1		0UL
-#define STRTAB_STE_1_STRW_EL2		2UL
-
-#define STRTAB_STE_1_SHCFG		GENMASK_ULL(45, 44)
-#define STRTAB_STE_1_SHCFG_INCOMING	1UL
-
-#define STRTAB_STE_2_S2VMID		GENMASK_ULL(15, 0)
-#define STRTAB_STE_2_VTCR		GENMASK_ULL(50, 32)
-#define STRTAB_STE_2_VTCR_S2T0SZ	GENMASK_ULL(5, 0)
-#define STRTAB_STE_2_VTCR_S2SL0		GENMASK_ULL(7, 6)
-#define STRTAB_STE_2_VTCR_S2IR0		GENMASK_ULL(9, 8)
-#define STRTAB_STE_2_VTCR_S2OR0		GENMASK_ULL(11, 10)
-#define STRTAB_STE_2_VTCR_S2SH0		GENMASK_ULL(13, 12)
-#define STRTAB_STE_2_VTCR_S2TG		GENMASK_ULL(15, 14)
-#define STRTAB_STE_2_VTCR_S2PS		GENMASK_ULL(18, 16)
-#define STRTAB_STE_2_S2AA64		(1UL << 51)
-#define STRTAB_STE_2_S2ENDI		(1UL << 52)
-#define STRTAB_STE_2_S2PTW		(1UL << 54)
-#define STRTAB_STE_2_S2R		(1UL << 58)
-
-#define STRTAB_STE_3_S2TTB_MASK		GENMASK_ULL(51, 4)
-
-/*
- * Context descriptors.
- *
- * Linear: when less than 1024 SSIDs are supported
- * 2lvl: at most 1024 L1 entries,
- *       1024 lazy entries per table.
- */
-#define CTXDESC_SPLIT			10
-#define CTXDESC_L2_ENTRIES		(1 << CTXDESC_SPLIT)
-
-#define CTXDESC_L1_DESC_DWORDS		1
-#define CTXDESC_L1_DESC_V		(1UL << 0)
-#define CTXDESC_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 12)
-
-#define CTXDESC_CD_DWORDS		8
-#define CTXDESC_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
-#define CTXDESC_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
-#define CTXDESC_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
-#define CTXDESC_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
-#define CTXDESC_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
-#define CTXDESC_CD_0_TCR_EPD0		(1ULL << 14)
-#define CTXDESC_CD_0_TCR_EPD1		(1ULL << 30)
-
-#define CTXDESC_CD_0_ENDI		(1UL << 15)
-#define CTXDESC_CD_0_V			(1UL << 31)
-
-#define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
-#define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
-
-#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		(1UL << 47)
-#define CTXDESC_CD_0_ASID		GENMASK_ULL(63, 48)
-
-#define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
-
-/*
- * When the SMMU only supports linear context descriptor tables, pick a
- * reasonable size limit (64kB).
- */
-#define CTXDESC_LINEAR_CDMAX		ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3))
-
-/* Command queue */
-#define CMDQ_ENT_SZ_SHIFT		4
-#define CMDQ_ENT_DWORDS			((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
-#define CMDQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - CMDQ_ENT_SZ_SHIFT)
-
-#define CMDQ_CONS_ERR			GENMASK(30, 24)
-#define CMDQ_ERR_CERROR_NONE_IDX	0
-#define CMDQ_ERR_CERROR_ILL_IDX		1
-#define CMDQ_ERR_CERROR_ABT_IDX		2
-#define CMDQ_ERR_CERROR_ATC_INV_IDX	3
-
-#define CMDQ_PROD_OWNED_FLAG		Q_OVERFLOW_FLAG
-
-/*
- * This is used to size the command queue and therefore must be at least
- * BITS_PER_LONG so that the valid_map works correctly (it relies on the
- * total number of queue entries being a multiple of BITS_PER_LONG).
- */
-#define CMDQ_BATCH_ENTRIES		BITS_PER_LONG
-
-#define CMDQ_0_OP			GENMASK_ULL(7, 0)
-#define CMDQ_0_SSV			(1UL << 11)
-
-#define CMDQ_PREFETCH_0_SID		GENMASK_ULL(63, 32)
-#define CMDQ_PREFETCH_1_SIZE		GENMASK_ULL(4, 0)
-#define CMDQ_PREFETCH_1_ADDR_MASK	GENMASK_ULL(63, 12)
-
-#define CMDQ_CFGI_0_SSID		GENMASK_ULL(31, 12)
-#define CMDQ_CFGI_0_SID			GENMASK_ULL(63, 32)
-#define CMDQ_CFGI_1_LEAF		(1UL << 0)
-#define CMDQ_CFGI_1_RANGE		GENMASK_ULL(4, 0)
-
-#define CMDQ_TLBI_0_NUM			GENMASK_ULL(16, 12)
-#define CMDQ_TLBI_RANGE_NUM_MAX		31
-#define CMDQ_TLBI_0_SCALE		GENMASK_ULL(24, 20)
-#define CMDQ_TLBI_0_VMID		GENMASK_ULL(47, 32)
-#define CMDQ_TLBI_0_ASID		GENMASK_ULL(63, 48)
-#define CMDQ_TLBI_1_LEAF		(1UL << 0)
-#define CMDQ_TLBI_1_TTL			GENMASK_ULL(9, 8)
-#define CMDQ_TLBI_1_TG			GENMASK_ULL(11, 10)
-#define CMDQ_TLBI_1_VA_MASK		GENMASK_ULL(63, 12)
-#define CMDQ_TLBI_1_IPA_MASK		GENMASK_ULL(51, 12)
-
-#define CMDQ_ATC_0_SSID			GENMASK_ULL(31, 12)
-#define CMDQ_ATC_0_SID			GENMASK_ULL(63, 32)
-#define CMDQ_ATC_0_GLOBAL		(1UL << 9)
-#define CMDQ_ATC_1_SIZE			GENMASK_ULL(5, 0)
-#define CMDQ_ATC_1_ADDR_MASK		GENMASK_ULL(63, 12)
-
-#define CMDQ_PRI_0_SSID			GENMASK_ULL(31, 12)
-#define CMDQ_PRI_0_SID			GENMASK_ULL(63, 32)
-#define CMDQ_PRI_1_GRPID		GENMASK_ULL(8, 0)
-#define CMDQ_PRI_1_RESP			GENMASK_ULL(13, 12)
-
-#define CMDQ_SYNC_0_CS			GENMASK_ULL(13, 12)
-#define CMDQ_SYNC_0_CS_NONE		0
-#define CMDQ_SYNC_0_CS_IRQ		1
-#define CMDQ_SYNC_0_CS_SEV		2
-#define CMDQ_SYNC_0_MSH			GENMASK_ULL(23, 22)
-#define CMDQ_SYNC_0_MSIATTR		GENMASK_ULL(27, 24)
-#define CMDQ_SYNC_0_MSIDATA		GENMASK_ULL(63, 32)
-#define CMDQ_SYNC_1_MSIADDR_MASK	GENMASK_ULL(51, 2)
-
-/* Event queue */
-#define EVTQ_ENT_SZ_SHIFT		5
-#define EVTQ_ENT_DWORDS			((1 << EVTQ_ENT_SZ_SHIFT) >> 3)
-#define EVTQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT)
-
-#define EVTQ_0_ID			GENMASK_ULL(7, 0)
-
-/* PRI queue */
-#define PRIQ_ENT_SZ_SHIFT		4
-#define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
-#define PRIQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT)
-
-#define PRIQ_0_SID			GENMASK_ULL(31, 0)
-#define PRIQ_0_SSID			GENMASK_ULL(51, 32)
-#define PRIQ_0_PERM_PRIV		(1UL << 58)
-#define PRIQ_0_PERM_EXEC		(1UL << 59)
-#define PRIQ_0_PERM_READ		(1UL << 60)
-#define PRIQ_0_PERM_WRITE		(1UL << 61)
-#define PRIQ_0_PRG_LAST			(1UL << 62)
-#define PRIQ_0_SSID_V			(1UL << 63)
-
-#define PRIQ_1_PRG_IDX			GENMASK_ULL(8, 0)
-#define PRIQ_1_ADDR_MASK		GENMASK_ULL(63, 12)
-
-/* High-level queue structures */
-#define ARM_SMMU_POLL_TIMEOUT_US	1000000 /* 1s! */
-#define ARM_SMMU_POLL_SPIN_COUNT	10
-
-#define MSI_IOVA_BASE			0x8000000
-#define MSI_IOVA_LENGTH			0x100000
+#include "arm-smmu-v3.h"
 
 static bool disable_bypass = 1;
-module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
+module_param(disable_bypass, bool, 0444);
 MODULE_PARM_DESC(disable_bypass,
 	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
 
-enum pri_resp {
-	PRI_RESP_DENY = 0,
-	PRI_RESP_FAIL = 1,
-	PRI_RESP_SUCC = 2,
-};
+static bool disable_msipolling;
+module_param(disable_msipolling, bool, 0444);
+MODULE_PARM_DESC(disable_msipolling,
+	"Disable MSI-based polling for CMD_SYNC completion.");
 
 enum arm_smmu_msi_index {
 	EVTQ_MSI_INDEX,
@@ -449,284 +68,13 @@ static phys_addr_t arm_smmu_msi_cfg[ARM_SMMU_MAX_MSIS][3] = {
 	},
 };
 
-struct arm_smmu_cmdq_ent {
-	/* Common fields */
-	u8				opcode;
-	bool				substream_valid;
-
-	/* Command-specific fields */
-	union {
-		#define CMDQ_OP_PREFETCH_CFG	0x1
-		struct {
-			u32			sid;
-			u8			size;
-			u64			addr;
-		} prefetch;
-
-		#define CMDQ_OP_CFGI_STE	0x3
-		#define CMDQ_OP_CFGI_ALL	0x4
-		#define CMDQ_OP_CFGI_CD		0x5
-		#define CMDQ_OP_CFGI_CD_ALL	0x6
-		struct {
-			u32			sid;
-			u32			ssid;
-			union {
-				bool		leaf;
-				u8		span;
-			};
-		} cfgi;
-
-		#define CMDQ_OP_TLBI_NH_ASID	0x11
-		#define CMDQ_OP_TLBI_NH_VA	0x12
-		#define CMDQ_OP_TLBI_EL2_ALL	0x20
-		#define CMDQ_OP_TLBI_S12_VMALL	0x28
-		#define CMDQ_OP_TLBI_S2_IPA	0x2a
-		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
-		struct {
-			u8			num;
-			u8			scale;
-			u16			asid;
-			u16			vmid;
-			bool			leaf;
-			u8			ttl;
-			u8			tg;
-			u64			addr;
-		} tlbi;
-
-		#define CMDQ_OP_ATC_INV		0x40
-		#define ATC_INV_SIZE_ALL	52
-		struct {
-			u32			sid;
-			u32			ssid;
-			u64			addr;
-			u8			size;
-			bool			global;
-		} atc;
-
-		#define CMDQ_OP_PRI_RESP	0x41
-		struct {
-			u32			sid;
-			u32			ssid;
-			u16			grpid;
-			enum pri_resp		resp;
-		} pri;
-
-		#define CMDQ_OP_CMD_SYNC	0x46
-		struct {
-			u64			msiaddr;
-		} sync;
-	};
-};
-
-struct arm_smmu_ll_queue {
-	union {
-		u64			val;
-		struct {
-			u32		prod;
-			u32		cons;
-		};
-		struct {
-			atomic_t	prod;
-			atomic_t	cons;
-		} atomic;
-		u8			__pad[SMP_CACHE_BYTES];
-	} ____cacheline_aligned_in_smp;
-	u32				max_n_shift;
-};
-
-struct arm_smmu_queue {
-	struct arm_smmu_ll_queue	llq;
-	int				irq; /* Wired interrupt */
-
-	__le64				*base;
-	dma_addr_t			base_dma;
-	u64				q_base;
-
-	size_t				ent_dwords;
-
-	u32 __iomem			*prod_reg;
-	u32 __iomem			*cons_reg;
-};
-
-struct arm_smmu_queue_poll {
-	ktime_t				timeout;
-	unsigned int			delay;
-	unsigned int			spin_cnt;
-	bool				wfe;
-};
-
-struct arm_smmu_cmdq {
-	struct arm_smmu_queue		q;
-	atomic_long_t			*valid_map;
-	atomic_t			owner_prod;
-	atomic_t			lock;
-};
-
-struct arm_smmu_cmdq_batch {
-	u64				cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS];
-	int				num;
-};
-
-struct arm_smmu_evtq {
-	struct arm_smmu_queue		q;
-	u32				max_stalls;
-};
-
-struct arm_smmu_priq {
-	struct arm_smmu_queue		q;
-};
-
-/* High-level stream table and context descriptor structures */
-struct arm_smmu_strtab_l1_desc {
-	u8				span;
-
-	__le64				*l2ptr;
-	dma_addr_t			l2ptr_dma;
-};
-
-struct arm_smmu_ctx_desc {
-	u16				asid;
-	u64				ttbr;
-	u64				tcr;
-	u64				mair;
-};
-
-struct arm_smmu_l1_ctx_desc {
-	__le64				*l2ptr;
-	dma_addr_t			l2ptr_dma;
-};
-
-struct arm_smmu_ctx_desc_cfg {
-	__le64				*cdtab;
-	dma_addr_t			cdtab_dma;
-	struct arm_smmu_l1_ctx_desc	*l1_desc;
-	unsigned int			num_l1_ents;
-};
-
-struct arm_smmu_s1_cfg {
-	struct arm_smmu_ctx_desc_cfg	cdcfg;
-	struct arm_smmu_ctx_desc	cd;
-	u8				s1fmt;
-	u8				s1cdmax;
-};
-
-struct arm_smmu_s2_cfg {
-	u16				vmid;
-	u64				vttbr;
-	u64				vtcr;
-};
-
-struct arm_smmu_strtab_cfg {
-	__le64				*strtab;
-	dma_addr_t			strtab_dma;
-	struct arm_smmu_strtab_l1_desc	*l1_desc;
-	unsigned int			num_l1_ents;
-
-	u64				strtab_base;
-	u32				strtab_base_cfg;
-};
-
-/* An SMMUv3 instance */
-struct arm_smmu_device {
-	struct device			*dev;
-	void __iomem			*base;
-	void __iomem			*page1;
-
-#define ARM_SMMU_FEAT_2_LVL_STRTAB	(1 << 0)
-#define ARM_SMMU_FEAT_2_LVL_CDTAB	(1 << 1)
-#define ARM_SMMU_FEAT_TT_LE		(1 << 2)
-#define ARM_SMMU_FEAT_TT_BE		(1 << 3)
-#define ARM_SMMU_FEAT_PRI		(1 << 4)
-#define ARM_SMMU_FEAT_ATS		(1 << 5)
-#define ARM_SMMU_FEAT_SEV		(1 << 6)
-#define ARM_SMMU_FEAT_MSI		(1 << 7)
-#define ARM_SMMU_FEAT_COHERENCY		(1 << 8)
-#define ARM_SMMU_FEAT_TRANS_S1		(1 << 9)
-#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)
-#define ARM_SMMU_FEAT_VAX		(1 << 14)
-#define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
-	u32				features;
-
-#define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
-#define ARM_SMMU_OPT_PAGE0_REGS_ONLY	(1 << 1)
-	u32				options;
-
-	struct arm_smmu_cmdq		cmdq;
-	struct arm_smmu_evtq		evtq;
-	struct arm_smmu_priq		priq;
-
-	int				gerr_irq;
-	int				combined_irq;
-
-	unsigned long			ias; /* IPA */
-	unsigned long			oas; /* PA */
-	unsigned long			pgsize_bitmap;
-
-#define ARM_SMMU_MAX_ASIDS		(1 << 16)
-	unsigned int			asid_bits;
-
-#define ARM_SMMU_MAX_VMIDS		(1 << 16)
-	unsigned int			vmid_bits;
-	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
-
-	unsigned int			ssid_bits;
-	unsigned int			sid_bits;
-
-	struct arm_smmu_strtab_cfg	strtab_cfg;
-
-	/* IOMMU core code handle */
-	struct iommu_device		iommu;
-};
-
-/* SMMU private data for each master */
-struct arm_smmu_master {
-	struct arm_smmu_device		*smmu;
-	struct device			*dev;
-	struct arm_smmu_domain		*domain;
-	struct list_head		domain_head;
-	u32				*sids;
-	unsigned int			num_sids;
-	bool				ats_enabled;
-	unsigned int			ssid_bits;
-};
-
-/* SMMU private data for an IOMMU domain */
-enum arm_smmu_domain_stage {
-	ARM_SMMU_DOMAIN_S1 = 0,
-	ARM_SMMU_DOMAIN_S2,
-	ARM_SMMU_DOMAIN_NESTED,
-	ARM_SMMU_DOMAIN_BYPASS,
-};
-
-struct arm_smmu_domain {
-	struct arm_smmu_device		*smmu;
-	struct mutex			init_mutex; /* Protects smmu pointer */
-
-	struct io_pgtable_ops		*pgtbl_ops;
-	bool				non_strict;
-	atomic_t			nr_ats_masters;
-
-	enum arm_smmu_domain_stage	stage;
-	union {
-		struct arm_smmu_s1_cfg	s1_cfg;
-		struct arm_smmu_s2_cfg	s2_cfg;
-	};
-
-	struct iommu_domain		domain;
-
-	struct list_head		devices;
-	spinlock_t			devices_lock;
-};
-
 struct arm_smmu_option_prop {
 	u32 opt;
 	const char *prop;
 };
 
-static DEFINE_XARRAY_ALLOC1(asid_xa);
+DEFINE_XARRAY_ALLOC1(arm_smmu_asid_xa);
+DEFINE_MUTEX(arm_smmu_asid_lock);
 
 static struct arm_smmu_option_prop arm_smmu_options[] = {
 	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
@@ -804,7 +152,7 @@ static void queue_sync_cons_out(struct arm_smmu_queue *q)
 	 * Ensure that all CPU accesses (reads and writes) to the queue
 	 * are complete before we update the cons pointer.
 	 */
-	mb();
+	__iomb();
 	writel_relaxed(q->llq.cons, q->cons_reg);
 }
 
@@ -816,8 +164,15 @@ static void queue_inc_cons(struct arm_smmu_ll_queue *q)
 
 static int queue_sync_prod_in(struct arm_smmu_queue *q)
 {
+	u32 prod;
 	int ret = 0;
-	u32 prod = readl_relaxed(q->prod_reg);
+
+	/*
+	 * We can't use the _relaxed() variant here, as we must prevent
+	 * speculative reads of the queue before we have determined that
+	 * prod has indeed moved.
+	 */
+	prod = readl(q->prod_reg);
 
 	if (Q_OVF(prod) != Q_OVF(q->llq.prod))
 		ret = -EOVERFLOW;
@@ -867,7 +222,7 @@ static void queue_write(__le64 *dst, u64 *src, size_t n_dwords)
 		*dst++ = cpu_to_le64(*src++);
 }
 
-static void queue_read(__le64 *dst, u64 *src, size_t n_dwords)
+static void queue_read(u64 *dst, __le64 *src, size_t n_dwords)
 {
 	int i;
 
@@ -992,8 +347,7 @@ static void arm_smmu_cmdq_build_sync_cmd(u64 *cmd, struct arm_smmu_device *smmu,
 	 * Beware that Hi16xx adds an extra 32 bits of goodness to its MSI
 	 * payload, so the write will zero the entire command on that platform.
 	 */
-	if (smmu->features & ARM_SMMU_FEAT_MSI &&
-	    smmu->features & ARM_SMMU_FEAT_COHERENCY) {
+	if (smmu->options & ARM_SMMU_OPT_MSIPOLL) {
 		ent.sync.msiaddr = q->base_dma + Q_IDX(&q->llq, prod) *
 				   q->ent_dwords * 8;
 	}
@@ -1331,8 +685,7 @@ static int __arm_smmu_cmdq_poll_until_consumed(struct arm_smmu_device *smmu,
 static int arm_smmu_cmdq_poll_until_sync(struct arm_smmu_device *smmu,
 					 struct arm_smmu_ll_queue *llq)
 {
-	if (smmu->features & ARM_SMMU_FEAT_MSI &&
-	    smmu->features & ARM_SMMU_FEAT_COHERENCY)
+	if (smmu->options & ARM_SMMU_OPT_MSIPOLL)
 		return __arm_smmu_cmdq_poll_until_msi(smmu, llq);
 
 	return __arm_smmu_cmdq_poll_until_consumed(smmu, llq);
@@ -1529,6 +882,17 @@ static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
 }
 
 /* Context descriptor manipulation functions */
+void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
+{
+	struct arm_smmu_cmdq_ent cmd = {
+		.opcode = CMDQ_OP_TLBI_NH_ASID,
+		.tlbi.asid = asid,
+	};
+
+	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+	arm_smmu_cmdq_issue_sync(smmu);
+}
+
 static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
 			     int ssid, bool leaf)
 {
@@ -1609,8 +973,8 @@ static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain,
 	return l1_desc->l2ptr + idx * CTXDESC_CD_DWORDS;
 }
 
-static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
-				   int ssid, struct arm_smmu_ctx_desc *cd)
+int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
+			    struct arm_smmu_ctx_desc *cd)
 {
 	/*
 	 * This function handles the following cases:
@@ -1661,7 +1025,8 @@ static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
 #ifdef __BIG_ENDIAN
 			CTXDESC_CD_0_ENDI |
 #endif
-			CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET |
+			CTXDESC_CD_0_R | CTXDESC_CD_0_A |
+			(cd->mm ? 0 : CTXDESC_CD_0_ASET) |
 			CTXDESC_CD_0_AA64 |
 			FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) |
 			CTXDESC_CD_0_V;
@@ -1765,12 +1130,20 @@ static void arm_smmu_free_cd_tables(struct arm_smmu_domain *smmu_domain)
 	cdcfg->cdtab = NULL;
 }
 
-static void arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd)
+bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd)
 {
+	bool free;
+	struct arm_smmu_ctx_desc *old_cd;
+
 	if (!cd->asid)
-		return;
+		return false;
 
-	xa_erase(&asid_xa, cd->asid);
+	free = refcount_dec_and_test(&cd->refs);
+	if (free) {
+		old_cd = xa_erase(&arm_smmu_asid_xa, cd->asid);
+		WARN_ON(old_cd != cd);
+	}
+	return free;
 }
 
 /* Stream table manipulation functions */
@@ -1939,7 +1312,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
-static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
+static void arm_smmu_init_bypass_stes(__le64 *strtab, unsigned int nent)
 {
 	unsigned int i;
 
@@ -2257,15 +1630,6 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	struct arm_smmu_cmdq_ent cmd;
 
-	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
-		cmd.opcode	= CMDQ_OP_TLBI_NH_ASID;
-		cmd.tlbi.asid	= smmu_domain->s1_cfg.cd.asid;
-		cmd.tlbi.vmid	= 0;
-	} else {
-		cmd.opcode	= CMDQ_OP_TLBI_S12_VMALL;
-		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
@@ -2273,8 +1637,14 @@ static void arm_smmu_tlb_inv_context(void *cookie)
 	 * insertion to guarantee those are observed before the TLBI. Do be
 	 * careful, 007.
 	 */
-	arm_smmu_cmdq_issue_cmd(smmu, &cmd);
-	arm_smmu_cmdq_issue_sync(smmu);
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+		arm_smmu_tlb_inv_asid(smmu, smmu_domain->s1_cfg.cd.asid);
+	} else {
+		cmd.opcode	= CMDQ_OP_TLBI_S12_VMALL;
+		cmd.tlbi.vmid	= smmu_domain->s2_cfg.vmid;
+		arm_smmu_cmdq_issue_cmd(smmu, &cmd);
+		arm_smmu_cmdq_issue_sync(smmu);
+	}
 	arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
 }
 
@@ -2458,9 +1828,12 @@ static void arm_smmu_domain_free(struct iommu_domain *domain)
 	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
 		struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
 
+		/* Prevent SVA from touching the CD while we're freeing it */
+		mutex_lock(&arm_smmu_asid_lock);
 		if (cfg->cdcfg.cdtab)
 			arm_smmu_free_cd_tables(smmu_domain);
 		arm_smmu_free_asid(&cfg->cd);
+		mutex_unlock(&arm_smmu_asid_lock);
 	} else {
 		struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
 		if (cfg->vmid)
@@ -2480,10 +1853,14 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	struct arm_smmu_s1_cfg *cfg = &smmu_domain->s1_cfg;
 	typeof(&pgtbl_cfg->arm_lpae_s1_cfg.tcr) tcr = &pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 
-	ret = xa_alloc(&asid_xa, &asid, &cfg->cd,
+	refcount_set(&cfg->cd.refs, 1);
+
+	/* Prevent SVA from modifying the ASID until it is written to the CD */
+	mutex_lock(&arm_smmu_asid_lock);
+	ret = xa_alloc(&arm_smmu_asid_xa, &asid, &cfg->cd,
 		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	cfg->s1cdmax = master->ssid_bits;
 
@@ -2511,12 +1888,15 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	if (ret)
 		goto out_free_cd_tables;
 
+	mutex_unlock(&arm_smmu_asid_lock);
 	return 0;
 
 out_free_cd_tables:
 	arm_smmu_free_cd_tables(smmu_domain);
 out_free_asid:
 	arm_smmu_free_asid(&cfg->cd);
+out_unlock:
+	mutex_unlock(&arm_smmu_asid_lock);
 	return ret;
 }
 
@@ -2796,6 +2176,16 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 	master = dev_iommu_priv_get(dev);
 	smmu = master->smmu;
 
+	/*
+	 * Checking that SVA is disabled ensures that this device isn't bound to
+	 * any mm, and can be safely detached from its old domain. Bonds cannot
+	 * be removed concurrently since we're holding the group mutex.
+	 */
+	if (arm_smmu_master_sva_enabled(master)) {
+		dev_err(dev, "cannot attach - SVA enabled\n");
+		return -EBUSY;
+	}
+
 	arm_smmu_detach_dev(master);
 
 	mutex_lock(&smmu_domain->init_mutex);
@@ -2943,6 +2333,7 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 	master->smmu = smmu;
 	master->sids = fwspec->ids;
 	master->num_sids = fwspec->num_ids;
+	INIT_LIST_HEAD(&master->bonds);
 	dev_iommu_priv_set(dev, master);
 
 	/* Check the SIDs are in range of the SMMU and our stream table */
@@ -2995,6 +2386,7 @@ static void arm_smmu_release_device(struct device *dev)
 		return;
 
 	master = dev_iommu_priv_get(dev);
+	WARN_ON(arm_smmu_master_sva_enabled(master));
 	arm_smmu_detach_dev(master);
 	arm_smmu_disable_pasid(master);
 	kfree(master);
@@ -3112,6 +2504,69 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 	iommu_dma_get_resv_regions(dev, head);
 }
 
+static bool arm_smmu_dev_has_feature(struct device *dev,
+				     enum iommu_dev_features feat)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	if (!master)
+		return false;
+
+	switch (feat) {
+	case IOMMU_DEV_FEAT_SVA:
+		return arm_smmu_master_sva_supported(master);
+	default:
+		return false;
+	}
+}
+
+static bool arm_smmu_dev_feature_enabled(struct device *dev,
+					 enum iommu_dev_features feat)
+{
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
+	if (!master)
+		return false;
+
+	switch (feat) {
+	case IOMMU_DEV_FEAT_SVA:
+		return arm_smmu_master_sva_enabled(master);
+	default:
+		return false;
+	}
+}
+
+static int arm_smmu_dev_enable_feature(struct device *dev,
+				       enum iommu_dev_features feat)
+{
+	if (!arm_smmu_dev_has_feature(dev, feat))
+		return -ENODEV;
+
+	if (arm_smmu_dev_feature_enabled(dev, feat))
+		return -EBUSY;
+
+	switch (feat) {
+	case IOMMU_DEV_FEAT_SVA:
+		return arm_smmu_master_enable_sva(dev_iommu_priv_get(dev));
+	default:
+		return -EINVAL;
+	}
+}
+
+static int arm_smmu_dev_disable_feature(struct device *dev,
+					enum iommu_dev_features feat)
+{
+	if (!arm_smmu_dev_feature_enabled(dev, feat))
+		return -EINVAL;
+
+	switch (feat) {
+	case IOMMU_DEV_FEAT_SVA:
+		return arm_smmu_master_disable_sva(dev_iommu_priv_get(dev));
+	default:
+		return -EINVAL;
+	}
+}
+
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -3130,6 +2585,10 @@ static struct iommu_ops arm_smmu_ops = {
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= generic_iommu_put_resv_regions,
+	.dev_has_feat		= arm_smmu_dev_has_feature,
+	.dev_feat_enabled	= arm_smmu_dev_feature_enabled,
+	.dev_enable_feat	= arm_smmu_dev_enable_feature,
+	.dev_disable_feat	= arm_smmu_dev_disable_feature,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -3280,7 +2739,7 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 	if (!strtab) {
 		dev_err(smmu->dev,
 			"failed to allocate l1 stream table (%u bytes)\n",
-			size);
+			l1size);
 		return -ENOMEM;
 	}
 	cfg->strtab = strtab;
@@ -3740,8 +3199,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	if (reg & IDR0_SEV)
 		smmu->features |= ARM_SMMU_FEAT_SEV;
 
-	if (reg & IDR0_MSI)
+	if (reg & IDR0_MSI) {
 		smmu->features |= ARM_SMMU_FEAT_MSI;
+		if (coherent && !disable_msipolling)
+			smmu->options |= ARM_SMMU_OPT_MSIPOLL;
+	}
 
 	if (reg & IDR0_HYP)
 		smmu->features |= ARM_SMMU_FEAT_HYP;
@@ -3891,6 +3353,9 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 
 	smmu->ias = max(smmu->ias, smmu->oas);
 
+	if (arm_smmu_sva_supported(smmu))
+		smmu->features |= ARM_SMMU_FEAT_SVA;
+
 	dev_info(smmu->dev, "ias %lu-bit, oas %lu-bit (features 0x%08x)\n",
 		 smmu->ias, smmu->oas, smmu->features);
 	return 0;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
new file mode 100644
index 000000000000..d4b7f40ccb02
--- /dev/null
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -0,0 +1,723 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IOMMU API for ARM architected SMMUv3 implementations.
+ *
+ * Copyright (C) 2015 ARM Limited
+ */
+
+#ifndef _ARM_SMMU_V3_H
+#define _ARM_SMMU_V3_H
+
+#include <linux/bitfield.h>
+#include <linux/iommu.h>
+#include <linux/kernel.h>
+#include <linux/mmzone.h>
+#include <linux/sizes.h>
+
+/* MMIO registers */
+#define ARM_SMMU_IDR0			0x0
+#define IDR0_ST_LVL			GENMASK(28, 27)
+#define IDR0_ST_LVL_2LVL		1
+#define IDR0_STALL_MODEL		GENMASK(25, 24)
+#define IDR0_STALL_MODEL_STALL		0
+#define IDR0_STALL_MODEL_FORCE		2
+#define IDR0_TTENDIAN			GENMASK(22, 21)
+#define IDR0_TTENDIAN_MIXED		0
+#define IDR0_TTENDIAN_LE		2
+#define IDR0_TTENDIAN_BE		3
+#define IDR0_CD2L			(1 << 19)
+#define IDR0_VMID16			(1 << 18)
+#define IDR0_PRI			(1 << 16)
+#define IDR0_SEV			(1 << 14)
+#define IDR0_MSI			(1 << 13)
+#define IDR0_ASID16			(1 << 12)
+#define IDR0_ATS			(1 << 10)
+#define IDR0_HYP			(1 << 9)
+#define IDR0_COHACC			(1 << 4)
+#define IDR0_TTF			GENMASK(3, 2)
+#define IDR0_TTF_AARCH64		2
+#define IDR0_TTF_AARCH32_64		3
+#define IDR0_S1P			(1 << 1)
+#define IDR0_S2P			(1 << 0)
+
+#define ARM_SMMU_IDR1			0x4
+#define IDR1_TABLES_PRESET		(1 << 30)
+#define IDR1_QUEUES_PRESET		(1 << 29)
+#define IDR1_REL			(1 << 28)
+#define IDR1_CMDQS			GENMASK(25, 21)
+#define IDR1_EVTQS			GENMASK(20, 16)
+#define IDR1_PRIQS			GENMASK(15, 11)
+#define IDR1_SSIDSIZE			GENMASK(10, 6)
+#define IDR1_SIDSIZE			GENMASK(5, 0)
+
+#define ARM_SMMU_IDR3			0xc
+#define IDR3_RIL			(1 << 10)
+
+#define ARM_SMMU_IDR5			0x14
+#define IDR5_STALL_MAX			GENMASK(31, 16)
+#define IDR5_GRAN64K			(1 << 6)
+#define IDR5_GRAN16K			(1 << 5)
+#define IDR5_GRAN4K			(1 << 4)
+#define IDR5_OAS			GENMASK(2, 0)
+#define IDR5_OAS_32_BIT			0
+#define IDR5_OAS_36_BIT			1
+#define IDR5_OAS_40_BIT			2
+#define IDR5_OAS_42_BIT			3
+#define IDR5_OAS_44_BIT			4
+#define IDR5_OAS_48_BIT			5
+#define IDR5_OAS_52_BIT			6
+#define IDR5_VAX			GENMASK(11, 10)
+#define IDR5_VAX_52_BIT			1
+
+#define ARM_SMMU_CR0			0x20
+#define CR0_ATSCHK			(1 << 4)
+#define CR0_CMDQEN			(1 << 3)
+#define CR0_EVTQEN			(1 << 2)
+#define CR0_PRIQEN			(1 << 1)
+#define CR0_SMMUEN			(1 << 0)
+
+#define ARM_SMMU_CR0ACK			0x24
+
+#define ARM_SMMU_CR1			0x28
+#define CR1_TABLE_SH			GENMASK(11, 10)
+#define CR1_TABLE_OC			GENMASK(9, 8)
+#define CR1_TABLE_IC			GENMASK(7, 6)
+#define CR1_QUEUE_SH			GENMASK(5, 4)
+#define CR1_QUEUE_OC			GENMASK(3, 2)
+#define CR1_QUEUE_IC			GENMASK(1, 0)
+/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */
+#define CR1_CACHE_NC			0
+#define CR1_CACHE_WB			1
+#define CR1_CACHE_WT			2
+
+#define ARM_SMMU_CR2			0x2c
+#define CR2_PTM				(1 << 2)
+#define CR2_RECINVSID			(1 << 1)
+#define CR2_E2H				(1 << 0)
+
+#define ARM_SMMU_GBPA			0x44
+#define GBPA_UPDATE			(1 << 31)
+#define GBPA_ABORT			(1 << 20)
+
+#define ARM_SMMU_IRQ_CTRL		0x50
+#define IRQ_CTRL_EVTQ_IRQEN		(1 << 2)
+#define IRQ_CTRL_PRIQ_IRQEN		(1 << 1)
+#define IRQ_CTRL_GERROR_IRQEN		(1 << 0)
+
+#define ARM_SMMU_IRQ_CTRLACK		0x54
+
+#define ARM_SMMU_GERROR			0x60
+#define GERROR_SFM_ERR			(1 << 8)
+#define GERROR_MSI_GERROR_ABT_ERR	(1 << 7)
+#define GERROR_MSI_PRIQ_ABT_ERR		(1 << 6)
+#define GERROR_MSI_EVTQ_ABT_ERR		(1 << 5)
+#define GERROR_MSI_CMDQ_ABT_ERR		(1 << 4)
+#define GERROR_PRIQ_ABT_ERR		(1 << 3)
+#define GERROR_EVTQ_ABT_ERR		(1 << 2)
+#define GERROR_CMDQ_ERR			(1 << 0)
+#define GERROR_ERR_MASK			0xfd
+
+#define ARM_SMMU_GERRORN		0x64
+
+#define ARM_SMMU_GERROR_IRQ_CFG0	0x68
+#define ARM_SMMU_GERROR_IRQ_CFG1	0x70
+#define ARM_SMMU_GERROR_IRQ_CFG2	0x74
+
+#define ARM_SMMU_STRTAB_BASE		0x80
+#define STRTAB_BASE_RA			(1UL << 62)
+#define STRTAB_BASE_ADDR_MASK		GENMASK_ULL(51, 6)
+
+#define ARM_SMMU_STRTAB_BASE_CFG	0x88
+#define STRTAB_BASE_CFG_FMT		GENMASK(17, 16)
+#define STRTAB_BASE_CFG_FMT_LINEAR	0
+#define STRTAB_BASE_CFG_FMT_2LVL	1
+#define STRTAB_BASE_CFG_SPLIT		GENMASK(10, 6)
+#define STRTAB_BASE_CFG_LOG2SIZE	GENMASK(5, 0)
+
+#define ARM_SMMU_CMDQ_BASE		0x90
+#define ARM_SMMU_CMDQ_PROD		0x98
+#define ARM_SMMU_CMDQ_CONS		0x9c
+
+#define ARM_SMMU_EVTQ_BASE		0xa0
+#define ARM_SMMU_EVTQ_PROD		0x100a8
+#define ARM_SMMU_EVTQ_CONS		0x100ac
+#define ARM_SMMU_EVTQ_IRQ_CFG0		0xb0
+#define ARM_SMMU_EVTQ_IRQ_CFG1		0xb8
+#define ARM_SMMU_EVTQ_IRQ_CFG2		0xbc
+
+#define ARM_SMMU_PRIQ_BASE		0xc0
+#define ARM_SMMU_PRIQ_PROD		0x100c8
+#define ARM_SMMU_PRIQ_CONS		0x100cc
+#define ARM_SMMU_PRIQ_IRQ_CFG0		0xd0
+#define ARM_SMMU_PRIQ_IRQ_CFG1		0xd8
+#define ARM_SMMU_PRIQ_IRQ_CFG2		0xdc
+
+#define ARM_SMMU_REG_SZ			0xe00
+
+/* Common MSI config fields */
+#define MSI_CFG0_ADDR_MASK		GENMASK_ULL(51, 2)
+#define MSI_CFG2_SH			GENMASK(5, 4)
+#define MSI_CFG2_MEMATTR		GENMASK(3, 0)
+
+/* Common memory attribute values */
+#define ARM_SMMU_SH_NSH			0
+#define ARM_SMMU_SH_OSH			2
+#define ARM_SMMU_SH_ISH			3
+#define ARM_SMMU_MEMATTR_DEVICE_nGnRE	0x1
+#define ARM_SMMU_MEMATTR_OIWB		0xf
+
+#define Q_IDX(llq, p)			((p) & ((1 << (llq)->max_n_shift) - 1))
+#define Q_WRP(llq, p)			((p) & (1 << (llq)->max_n_shift))
+#define Q_OVERFLOW_FLAG			(1U << 31)
+#define Q_OVF(p)			((p) & Q_OVERFLOW_FLAG)
+#define Q_ENT(q, p)			((q)->base +			\
+					 Q_IDX(&((q)->llq), p) *	\
+					 (q)->ent_dwords)
+
+#define Q_BASE_RWA			(1UL << 62)
+#define Q_BASE_ADDR_MASK		GENMASK_ULL(51, 5)
+#define Q_BASE_LOG2SIZE			GENMASK(4, 0)
+
+/* Ensure DMA allocations are naturally aligned */
+#ifdef CONFIG_CMA_ALIGNMENT
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
+#else
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER - 1)
+#endif
+
+/*
+ * Stream table.
+ *
+ * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
+ * 2lvl: 128k L1 entries,
+ *       256 lazy entries per table (each table covers a PCI bus)
+ */
+#define STRTAB_L1_SZ_SHIFT		20
+#define STRTAB_SPLIT			8
+
+#define STRTAB_L1_DESC_DWORDS		1
+#define STRTAB_L1_DESC_SPAN		GENMASK_ULL(4, 0)
+#define STRTAB_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 6)
+
+#define STRTAB_STE_DWORDS		8
+#define STRTAB_STE_0_V			(1UL << 0)
+#define STRTAB_STE_0_CFG		GENMASK_ULL(3, 1)
+#define STRTAB_STE_0_CFG_ABORT		0
+#define STRTAB_STE_0_CFG_BYPASS		4
+#define STRTAB_STE_0_CFG_S1_TRANS	5
+#define STRTAB_STE_0_CFG_S2_TRANS	6
+
+#define STRTAB_STE_0_S1FMT		GENMASK_ULL(5, 4)
+#define STRTAB_STE_0_S1FMT_LINEAR	0
+#define STRTAB_STE_0_S1FMT_64K_L2	2
+#define STRTAB_STE_0_S1CTXPTR_MASK	GENMASK_ULL(51, 6)
+#define STRTAB_STE_0_S1CDMAX		GENMASK_ULL(63, 59)
+
+#define STRTAB_STE_1_S1DSS		GENMASK_ULL(1, 0)
+#define STRTAB_STE_1_S1DSS_TERMINATE	0x0
+#define STRTAB_STE_1_S1DSS_BYPASS	0x1
+#define STRTAB_STE_1_S1DSS_SSID0	0x2
+
+#define STRTAB_STE_1_S1C_CACHE_NC	0UL
+#define STRTAB_STE_1_S1C_CACHE_WBRA	1UL
+#define STRTAB_STE_1_S1C_CACHE_WT	2UL
+#define STRTAB_STE_1_S1C_CACHE_WB	3UL
+#define STRTAB_STE_1_S1CIR		GENMASK_ULL(3, 2)
+#define STRTAB_STE_1_S1COR		GENMASK_ULL(5, 4)
+#define STRTAB_STE_1_S1CSH		GENMASK_ULL(7, 6)
+
+#define STRTAB_STE_1_S1STALLD		(1UL << 27)
+
+#define STRTAB_STE_1_EATS		GENMASK_ULL(29, 28)
+#define STRTAB_STE_1_EATS_ABT		0UL
+#define STRTAB_STE_1_EATS_TRANS		1UL
+#define STRTAB_STE_1_EATS_S1CHK		2UL
+
+#define STRTAB_STE_1_STRW		GENMASK_ULL(31, 30)
+#define STRTAB_STE_1_STRW_NSEL1		0UL
+#define STRTAB_STE_1_STRW_EL2		2UL
+
+#define STRTAB_STE_1_SHCFG		GENMASK_ULL(45, 44)
+#define STRTAB_STE_1_SHCFG_INCOMING	1UL
+
+#define STRTAB_STE_2_S2VMID		GENMASK_ULL(15, 0)
+#define STRTAB_STE_2_VTCR		GENMASK_ULL(50, 32)
+#define STRTAB_STE_2_VTCR_S2T0SZ	GENMASK_ULL(5, 0)
+#define STRTAB_STE_2_VTCR_S2SL0		GENMASK_ULL(7, 6)
+#define STRTAB_STE_2_VTCR_S2IR0		GENMASK_ULL(9, 8)
+#define STRTAB_STE_2_VTCR_S2OR0		GENMASK_ULL(11, 10)
+#define STRTAB_STE_2_VTCR_S2SH0		GENMASK_ULL(13, 12)
+#define STRTAB_STE_2_VTCR_S2TG		GENMASK_ULL(15, 14)
+#define STRTAB_STE_2_VTCR_S2PS		GENMASK_ULL(18, 16)
+#define STRTAB_STE_2_S2AA64		(1UL << 51)
+#define STRTAB_STE_2_S2ENDI		(1UL << 52)
+#define STRTAB_STE_2_S2PTW		(1UL << 54)
+#define STRTAB_STE_2_S2R		(1UL << 58)
+
+#define STRTAB_STE_3_S2TTB_MASK		GENMASK_ULL(51, 4)
+
+/*
+ * Context descriptors.
+ *
+ * Linear: when less than 1024 SSIDs are supported
+ * 2lvl: at most 1024 L1 entries,
+ *       1024 lazy entries per table.
+ */
+#define CTXDESC_SPLIT			10
+#define CTXDESC_L2_ENTRIES		(1 << CTXDESC_SPLIT)
+
+#define CTXDESC_L1_DESC_DWORDS		1
+#define CTXDESC_L1_DESC_V		(1UL << 0)
+#define CTXDESC_L1_DESC_L2PTR_MASK	GENMASK_ULL(51, 12)
+
+#define CTXDESC_CD_DWORDS		8
+#define CTXDESC_CD_0_TCR_T0SZ		GENMASK_ULL(5, 0)
+#define CTXDESC_CD_0_TCR_TG0		GENMASK_ULL(7, 6)
+#define CTXDESC_CD_0_TCR_IRGN0		GENMASK_ULL(9, 8)
+#define CTXDESC_CD_0_TCR_ORGN0		GENMASK_ULL(11, 10)
+#define CTXDESC_CD_0_TCR_SH0		GENMASK_ULL(13, 12)
+#define CTXDESC_CD_0_TCR_EPD0		(1ULL << 14)
+#define CTXDESC_CD_0_TCR_EPD1		(1ULL << 30)
+
+#define CTXDESC_CD_0_ENDI		(1UL << 15)
+#define CTXDESC_CD_0_V			(1UL << 31)
+
+#define CTXDESC_CD_0_TCR_IPS		GENMASK_ULL(34, 32)
+#define CTXDESC_CD_0_TCR_TBI0		(1ULL << 38)
+
+#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		(1UL << 47)
+#define CTXDESC_CD_0_ASID		GENMASK_ULL(63, 48)
+
+#define CTXDESC_CD_1_TTB0_MASK		GENMASK_ULL(51, 4)
+
+/*
+ * When the SMMU only supports linear context descriptor tables, pick a
+ * reasonable size limit (64kB).
+ */
+#define CTXDESC_LINEAR_CDMAX		ilog2(SZ_64K / (CTXDESC_CD_DWORDS << 3))
+
+/* Command queue */
+#define CMDQ_ENT_SZ_SHIFT		4
+#define CMDQ_ENT_DWORDS			((1 << CMDQ_ENT_SZ_SHIFT) >> 3)
+#define CMDQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - CMDQ_ENT_SZ_SHIFT)
+
+#define CMDQ_CONS_ERR			GENMASK(30, 24)
+#define CMDQ_ERR_CERROR_NONE_IDX	0
+#define CMDQ_ERR_CERROR_ILL_IDX		1
+#define CMDQ_ERR_CERROR_ABT_IDX		2
+#define CMDQ_ERR_CERROR_ATC_INV_IDX	3
+
+#define CMDQ_PROD_OWNED_FLAG		Q_OVERFLOW_FLAG
+
+/*
+ * This is used to size the command queue and therefore must be at least
+ * BITS_PER_LONG so that the valid_map works correctly (it relies on the
+ * total number of queue entries being a multiple of BITS_PER_LONG).
+ */
+#define CMDQ_BATCH_ENTRIES		BITS_PER_LONG
+
+#define CMDQ_0_OP			GENMASK_ULL(7, 0)
+#define CMDQ_0_SSV			(1UL << 11)
+
+#define CMDQ_PREFETCH_0_SID		GENMASK_ULL(63, 32)
+#define CMDQ_PREFETCH_1_SIZE		GENMASK_ULL(4, 0)
+#define CMDQ_PREFETCH_1_ADDR_MASK	GENMASK_ULL(63, 12)
+
+#define CMDQ_CFGI_0_SSID		GENMASK_ULL(31, 12)
+#define CMDQ_CFGI_0_SID			GENMASK_ULL(63, 32)
+#define CMDQ_CFGI_1_LEAF		(1UL << 0)
+#define CMDQ_CFGI_1_RANGE		GENMASK_ULL(4, 0)
+
+#define CMDQ_TLBI_0_NUM			GENMASK_ULL(16, 12)
+#define CMDQ_TLBI_RANGE_NUM_MAX		31
+#define CMDQ_TLBI_0_SCALE		GENMASK_ULL(24, 20)
+#define CMDQ_TLBI_0_VMID		GENMASK_ULL(47, 32)
+#define CMDQ_TLBI_0_ASID		GENMASK_ULL(63, 48)
+#define CMDQ_TLBI_1_LEAF		(1UL << 0)
+#define CMDQ_TLBI_1_TTL			GENMASK_ULL(9, 8)
+#define CMDQ_TLBI_1_TG			GENMASK_ULL(11, 10)
+#define CMDQ_TLBI_1_VA_MASK		GENMASK_ULL(63, 12)
+#define CMDQ_TLBI_1_IPA_MASK		GENMASK_ULL(51, 12)
+
+#define CMDQ_ATC_0_SSID			GENMASK_ULL(31, 12)
+#define CMDQ_ATC_0_SID			GENMASK_ULL(63, 32)
+#define CMDQ_ATC_0_GLOBAL		(1UL << 9)
+#define CMDQ_ATC_1_SIZE			GENMASK_ULL(5, 0)
+#define CMDQ_ATC_1_ADDR_MASK		GENMASK_ULL(63, 12)
+
+#define CMDQ_PRI_0_SSID			GENMASK_ULL(31, 12)
+#define CMDQ_PRI_0_SID			GENMASK_ULL(63, 32)
+#define CMDQ_PRI_1_GRPID		GENMASK_ULL(8, 0)
+#define CMDQ_PRI_1_RESP			GENMASK_ULL(13, 12)
+
+#define CMDQ_SYNC_0_CS			GENMASK_ULL(13, 12)
+#define CMDQ_SYNC_0_CS_NONE		0
+#define CMDQ_SYNC_0_CS_IRQ		1
+#define CMDQ_SYNC_0_CS_SEV		2
+#define CMDQ_SYNC_0_MSH			GENMASK_ULL(23, 22)
+#define CMDQ_SYNC_0_MSIATTR		GENMASK_ULL(27, 24)
+#define CMDQ_SYNC_0_MSIDATA		GENMASK_ULL(63, 32)
+#define CMDQ_SYNC_1_MSIADDR_MASK	GENMASK_ULL(51, 2)
+
+/* Event queue */
+#define EVTQ_ENT_SZ_SHIFT		5
+#define EVTQ_ENT_DWORDS			((1 << EVTQ_ENT_SZ_SHIFT) >> 3)
+#define EVTQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - EVTQ_ENT_SZ_SHIFT)
+
+#define EVTQ_0_ID			GENMASK_ULL(7, 0)
+
+/* PRI queue */
+#define PRIQ_ENT_SZ_SHIFT		4
+#define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
+#define PRIQ_MAX_SZ_SHIFT		(Q_MAX_SZ_SHIFT - PRIQ_ENT_SZ_SHIFT)
+
+#define PRIQ_0_SID			GENMASK_ULL(31, 0)
+#define PRIQ_0_SSID			GENMASK_ULL(51, 32)
+#define PRIQ_0_PERM_PRIV		(1UL << 58)
+#define PRIQ_0_PERM_EXEC		(1UL << 59)
+#define PRIQ_0_PERM_READ		(1UL << 60)
+#define PRIQ_0_PERM_WRITE		(1UL << 61)
+#define PRIQ_0_PRG_LAST			(1UL << 62)
+#define PRIQ_0_SSID_V			(1UL << 63)
+
+#define PRIQ_1_PRG_IDX			GENMASK_ULL(8, 0)
+#define PRIQ_1_ADDR_MASK		GENMASK_ULL(63, 12)
+
+/* High-level queue structures */
+#define ARM_SMMU_POLL_TIMEOUT_US	1000000 /* 1s! */
+#define ARM_SMMU_POLL_SPIN_COUNT	10
+
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
+enum pri_resp {
+	PRI_RESP_DENY = 0,
+	PRI_RESP_FAIL = 1,
+	PRI_RESP_SUCC = 2,
+};
+
+struct arm_smmu_cmdq_ent {
+	/* Common fields */
+	u8				opcode;
+	bool				substream_valid;
+
+	/* Command-specific fields */
+	union {
+		#define CMDQ_OP_PREFETCH_CFG	0x1
+		struct {
+			u32			sid;
+			u8			size;
+			u64			addr;
+		} prefetch;
+
+		#define CMDQ_OP_CFGI_STE	0x3
+		#define CMDQ_OP_CFGI_ALL	0x4
+		#define CMDQ_OP_CFGI_CD		0x5
+		#define CMDQ_OP_CFGI_CD_ALL	0x6
+		struct {
+			u32			sid;
+			u32			ssid;
+			union {
+				bool		leaf;
+				u8		span;
+			};
+		} cfgi;
+
+		#define CMDQ_OP_TLBI_NH_ASID	0x11
+		#define CMDQ_OP_TLBI_NH_VA	0x12
+		#define CMDQ_OP_TLBI_EL2_ALL	0x20
+		#define CMDQ_OP_TLBI_S12_VMALL	0x28
+		#define CMDQ_OP_TLBI_S2_IPA	0x2a
+		#define CMDQ_OP_TLBI_NSNH_ALL	0x30
+		struct {
+			u8			num;
+			u8			scale;
+			u16			asid;
+			u16			vmid;
+			bool			leaf;
+			u8			ttl;
+			u8			tg;
+			u64			addr;
+		} tlbi;
+
+		#define CMDQ_OP_ATC_INV		0x40
+		#define ATC_INV_SIZE_ALL	52
+		struct {
+			u32			sid;
+			u32			ssid;
+			u64			addr;
+			u8			size;
+			bool			global;
+		} atc;
+
+		#define CMDQ_OP_PRI_RESP	0x41
+		struct {
+			u32			sid;
+			u32			ssid;
+			u16			grpid;
+			enum pri_resp		resp;
+		} pri;
+
+		#define CMDQ_OP_CMD_SYNC	0x46
+		struct {
+			u64			msiaddr;
+		} sync;
+	};
+};
+
+struct arm_smmu_ll_queue {
+	union {
+		u64			val;
+		struct {
+			u32		prod;
+			u32		cons;
+		};
+		struct {
+			atomic_t	prod;
+			atomic_t	cons;
+		} atomic;
+		u8			__pad[SMP_CACHE_BYTES];
+	} ____cacheline_aligned_in_smp;
+	u32				max_n_shift;
+};
+
+struct arm_smmu_queue {
+	struct arm_smmu_ll_queue	llq;
+	int				irq; /* Wired interrupt */
+
+	__le64				*base;
+	dma_addr_t			base_dma;
+	u64				q_base;
+
+	size_t				ent_dwords;
+
+	u32 __iomem			*prod_reg;
+	u32 __iomem			*cons_reg;
+};
+
+struct arm_smmu_queue_poll {
+	ktime_t				timeout;
+	unsigned int			delay;
+	unsigned int			spin_cnt;
+	bool				wfe;
+};
+
+struct arm_smmu_cmdq {
+	struct arm_smmu_queue		q;
+	atomic_long_t			*valid_map;
+	atomic_t			owner_prod;
+	atomic_t			lock;
+};
+
+struct arm_smmu_cmdq_batch {
+	u64				cmds[CMDQ_BATCH_ENTRIES * CMDQ_ENT_DWORDS];
+	int				num;
+};
+
+struct arm_smmu_evtq {
+	struct arm_smmu_queue		q;
+	u32				max_stalls;
+};
+
+struct arm_smmu_priq {
+	struct arm_smmu_queue		q;
+};
+
+/* High-level stream table and context descriptor structures */
+struct arm_smmu_strtab_l1_desc {
+	u8				span;
+
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_ctx_desc {
+	u16				asid;
+	u64				ttbr;
+	u64				tcr;
+	u64				mair;
+
+	refcount_t			refs;
+	struct mm_struct		*mm;
+};
+
+struct arm_smmu_l1_ctx_desc {
+	__le64				*l2ptr;
+	dma_addr_t			l2ptr_dma;
+};
+
+struct arm_smmu_ctx_desc_cfg {
+	__le64				*cdtab;
+	dma_addr_t			cdtab_dma;
+	struct arm_smmu_l1_ctx_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+};
+
+struct arm_smmu_s1_cfg {
+	struct arm_smmu_ctx_desc_cfg	cdcfg;
+	struct arm_smmu_ctx_desc	cd;
+	u8				s1fmt;
+	u8				s1cdmax;
+};
+
+struct arm_smmu_s2_cfg {
+	u16				vmid;
+	u64				vttbr;
+	u64				vtcr;
+};
+
+struct arm_smmu_strtab_cfg {
+	__le64				*strtab;
+	dma_addr_t			strtab_dma;
+	struct arm_smmu_strtab_l1_desc	*l1_desc;
+	unsigned int			num_l1_ents;
+
+	u64				strtab_base;
+	u32				strtab_base_cfg;
+};
+
+/* An SMMUv3 instance */
+struct arm_smmu_device {
+	struct device			*dev;
+	void __iomem			*base;
+	void __iomem			*page1;
+
+#define ARM_SMMU_FEAT_2_LVL_STRTAB	(1 << 0)
+#define ARM_SMMU_FEAT_2_LVL_CDTAB	(1 << 1)
+#define ARM_SMMU_FEAT_TT_LE		(1 << 2)
+#define ARM_SMMU_FEAT_TT_BE		(1 << 3)
+#define ARM_SMMU_FEAT_PRI		(1 << 4)
+#define ARM_SMMU_FEAT_ATS		(1 << 5)
+#define ARM_SMMU_FEAT_SEV		(1 << 6)
+#define ARM_SMMU_FEAT_MSI		(1 << 7)
+#define ARM_SMMU_FEAT_COHERENCY		(1 << 8)
+#define ARM_SMMU_FEAT_TRANS_S1		(1 << 9)
+#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)
+#define ARM_SMMU_FEAT_VAX		(1 << 14)
+#define ARM_SMMU_FEAT_RANGE_INV		(1 << 15)
+#define ARM_SMMU_FEAT_BTM		(1 << 16)
+#define ARM_SMMU_FEAT_SVA		(1 << 17)
+	u32				features;
+
+#define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
+#define ARM_SMMU_OPT_PAGE0_REGS_ONLY	(1 << 1)
+#define ARM_SMMU_OPT_MSIPOLL		(1 << 2)
+	u32				options;
+
+	struct arm_smmu_cmdq		cmdq;
+	struct arm_smmu_evtq		evtq;
+	struct arm_smmu_priq		priq;
+
+	int				gerr_irq;
+	int				combined_irq;
+
+	unsigned long			ias; /* IPA */
+	unsigned long			oas; /* PA */
+	unsigned long			pgsize_bitmap;
+
+#define ARM_SMMU_MAX_ASIDS		(1 << 16)
+	unsigned int			asid_bits;
+
+#define ARM_SMMU_MAX_VMIDS		(1 << 16)
+	unsigned int			vmid_bits;
+	DECLARE_BITMAP(vmid_map, ARM_SMMU_MAX_VMIDS);
+
+	unsigned int			ssid_bits;
+	unsigned int			sid_bits;
+
+	struct arm_smmu_strtab_cfg	strtab_cfg;
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
+};
+
+/* SMMU private data for each master */
+struct arm_smmu_master {
+	struct arm_smmu_device		*smmu;
+	struct device			*dev;
+	struct arm_smmu_domain		*domain;
+	struct list_head		domain_head;
+	u32				*sids;
+	unsigned int			num_sids;
+	bool				ats_enabled;
+	bool				sva_enabled;
+	struct list_head		bonds;
+	unsigned int			ssid_bits;
+};
+
+/* SMMU private data for an IOMMU domain */
+enum arm_smmu_domain_stage {
+	ARM_SMMU_DOMAIN_S1 = 0,
+	ARM_SMMU_DOMAIN_S2,
+	ARM_SMMU_DOMAIN_NESTED,
+	ARM_SMMU_DOMAIN_BYPASS,
+};
+
+struct arm_smmu_domain {
+	struct arm_smmu_device		*smmu;
+	struct mutex			init_mutex; /* Protects smmu pointer */
+
+	struct io_pgtable_ops		*pgtbl_ops;
+	bool				non_strict;
+	atomic_t			nr_ats_masters;
+
+	enum arm_smmu_domain_stage	stage;
+	union {
+		struct arm_smmu_s1_cfg	s1_cfg;
+		struct arm_smmu_s2_cfg	s2_cfg;
+	};
+
+	struct iommu_domain		domain;
+
+	struct list_head		devices;
+	spinlock_t			devices_lock;
+};
+
+extern struct xarray arm_smmu_asid_xa;
+extern struct mutex arm_smmu_asid_lock;
+
+int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
+			    struct arm_smmu_ctx_desc *cd);
+void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
+bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd);
+
+#ifdef CONFIG_ARM_SMMU_V3_SVA
+bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
+bool arm_smmu_master_sva_supported(struct arm_smmu_master *master);
+bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
+int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
+int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
+#else /* CONFIG_ARM_SMMU_V3_SVA */
+static inline bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
+{
+	return false;
+}
+
+static inline bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
+{
+	return -ENODEV;
+}
+
+static inline int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_ARM_SMMU_V3_SVA */
+#endif /* _ARM_SMMU_V3_H */
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
index f4ff124a1967..88f17cc33023 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c
@@ -68,7 +68,8 @@ static int cavium_cfg_probe(struct arm_smmu_device *smmu)
 	return 0;
 }
 
-static int cavium_init_context(struct arm_smmu_domain *smmu_domain)
+static int cavium_init_context(struct arm_smmu_domain *smmu_domain,
+		struct io_pgtable_cfg *pgtbl_cfg, struct device *dev)
 {
 	struct cavium_smmu *cs = container_of(smmu_domain->smmu,
 					      struct cavium_smmu, smmu);
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c
index 09c42af9f31e..dad7fa86fbd4 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c
@@ -65,41 +65,10 @@ module_param(disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
 	"Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU.");
 
-struct arm_smmu_s2cr {
-	struct iommu_group		*group;
-	int				count;
-	enum arm_smmu_s2cr_type		type;
-	enum arm_smmu_s2cr_privcfg	privcfg;
-	u8				cbndx;
-};
-
 #define s2cr_init_val (struct arm_smmu_s2cr){				\
 	.type = disable_bypass ? S2CR_TYPE_FAULT : S2CR_TYPE_BYPASS,	\
 }
 
-struct arm_smmu_smr {
-	u16				mask;
-	u16				id;
-	bool				valid;
-};
-
-struct arm_smmu_cb {
-	u64				ttbr[2];
-	u32				tcr[2];
-	u32				mair[2];
-	struct arm_smmu_cfg		*cfg;
-};
-
-struct arm_smmu_master_cfg {
-	struct arm_smmu_device		*smmu;
-	s16				smendx[];
-};
-#define INVALID_SMENDX			-1
-#define cfg_smendx(cfg, fw, i) \
-	(i >= fw->num_ids ? INVALID_SMENDX : cfg->smendx[i])
-#define for_each_cfg_sme(cfg, fw, i, idx) \
-	for (i = 0; idx = cfg_smendx(cfg, fw, i), i < fw->num_ids; ++i)
-
 static bool using_legacy_binding, using_generic_binding;
 
 static inline int arm_smmu_rpm_get(struct arm_smmu_device *smmu)
@@ -234,19 +203,6 @@ static int arm_smmu_register_legacy_master(struct device *dev,
 }
 #endif /* CONFIG_ARM_SMMU_LEGACY_DT_BINDINGS */
 
-static int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
-{
-	int idx;
-
-	do {
-		idx = find_next_zero_bit(map, end, start);
-		if (idx == end)
-			return -ENOSPC;
-	} while (test_and_set_bit(idx, map));
-
-	return idx;
-}
-
 static void __arm_smmu_free_bitmap(unsigned long *map, int idx)
 {
 	clear_bit(idx, map);
@@ -552,11 +508,15 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 			cb->ttbr[0] = pgtbl_cfg->arm_v7s_cfg.ttbr;
 			cb->ttbr[1] = 0;
 		} else {
-			cb->ttbr[0] = pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
-			cb->ttbr[0] |= FIELD_PREP(ARM_SMMU_TTBRn_ASID,
-						  cfg->asid);
+			cb->ttbr[0] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
+						 cfg->asid);
 			cb->ttbr[1] = FIELD_PREP(ARM_SMMU_TTBRn_ASID,
 						 cfg->asid);
+
+			if (pgtbl_cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1)
+				cb->ttbr[1] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
+			else
+				cb->ttbr[0] |= pgtbl_cfg->arm_lpae_s1_cfg.ttbr;
 		}
 	} else {
 		cb->ttbr[0] = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
@@ -574,7 +534,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 	}
 }
 
-static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
+void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
 {
 	u32 reg;
 	bool stage1;
@@ -660,8 +620,19 @@ static void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx)
 	arm_smmu_cb_write(smmu, idx, ARM_SMMU_CB_SCTLR, reg);
 }
 
+static int arm_smmu_alloc_context_bank(struct arm_smmu_domain *smmu_domain,
+				       struct arm_smmu_device *smmu,
+				       struct device *dev, unsigned int start)
+{
+	if (smmu->impl && smmu->impl->alloc_context_bank)
+		return smmu->impl->alloc_context_bank(smmu_domain, smmu, dev, start);
+
+	return __arm_smmu_alloc_bitmap(smmu->context_map, start, smmu->num_context_banks);
+}
+
 static int arm_smmu_init_domain_context(struct iommu_domain *domain,
-					struct arm_smmu_device *smmu)
+					struct arm_smmu_device *smmu,
+					struct device *dev)
 {
 	int irq, start, ret = 0;
 	unsigned long ias, oas;
@@ -776,10 +747,13 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		ret = -EINVAL;
 		goto out_unlock;
 	}
-	ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
-				      smmu->num_context_banks);
-	if (ret < 0)
+
+	ret = arm_smmu_alloc_context_bank(smmu_domain, smmu, dev, start);
+	if (ret < 0) {
 		goto out_unlock;
+	}
+
+	smmu_domain->smmu = smmu;
 
 	cfg->cbndx = ret;
 	if (smmu->version < ARM_SMMU_V2) {
@@ -794,13 +768,6 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	else
 		cfg->asid = cfg->cbndx;
 
-	smmu_domain->smmu = smmu;
-	if (smmu->impl && smmu->impl->init_context) {
-		ret = smmu->impl->init_context(smmu_domain);
-		if (ret)
-			goto out_unlock;
-	}
-
 	pgtbl_cfg = (struct io_pgtable_cfg) {
 		.pgsize_bitmap	= smmu->pgsize_bitmap,
 		.ias		= ias,
@@ -810,6 +777,12 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.iommu_dev	= smmu->dev,
 	};
 
+	if (smmu->impl && smmu->impl->init_context) {
+		ret = smmu->impl->init_context(smmu_domain, &pgtbl_cfg, dev);
+		if (ret)
+			goto out_clear_smmu;
+	}
+
 	if (smmu_domain->non_strict)
 		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
 
@@ -821,7 +794,14 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 
 	/* Update the domain's page sizes to reflect the page table format */
 	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
-	domain->geometry.aperture_end = (1UL << ias) - 1;
+
+	if (pgtbl_cfg.quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) {
+		domain->geometry.aperture_start = ~0UL << ias;
+		domain->geometry.aperture_end = ~0UL;
+	} else {
+		domain->geometry.aperture_end = (1UL << ias) - 1;
+	}
+
 	domain->geometry.force_aperture = true;
 
 	/* Initialise the context bank with our page table cfg */
@@ -1182,7 +1162,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 		return ret;
 
 	/* Ensure that the domain is finalised */
-	ret = arm_smmu_init_domain_context(domain, smmu);
+	ret = arm_smmu_init_domain_context(domain, smmu, dev);
 	if (ret < 0)
 		goto rpm_put;
 
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.h b/drivers/iommu/arm/arm-smmu/arm-smmu.h
index d890a4a968e8..1a746476927c 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu.h
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu.h
@@ -169,10 +169,12 @@ enum arm_smmu_cbar_type {
 #define ARM_SMMU_CB_TCR			0x30
 #define ARM_SMMU_TCR_EAE		BIT(31)
 #define ARM_SMMU_TCR_EPD1		BIT(23)
+#define ARM_SMMU_TCR_A1			BIT(22)
 #define ARM_SMMU_TCR_TG0		GENMASK(15, 14)
 #define ARM_SMMU_TCR_SH0		GENMASK(13, 12)
 #define ARM_SMMU_TCR_ORGN0		GENMASK(11, 10)
 #define ARM_SMMU_TCR_IRGN0		GENMASK(9, 8)
+#define ARM_SMMU_TCR_EPD0		BIT(7)
 #define ARM_SMMU_TCR_T0SZ		GENMASK(5, 0)
 
 #define ARM_SMMU_VTCR_RES1		BIT(31)
@@ -254,6 +256,21 @@ enum arm_smmu_implementation {
 	QCOM_SMMUV2,
 };
 
+struct arm_smmu_s2cr {
+	struct iommu_group		*group;
+	int				count;
+	enum arm_smmu_s2cr_type		type;
+	enum arm_smmu_s2cr_privcfg	privcfg;
+	u8				cbndx;
+};
+
+struct arm_smmu_smr {
+	u16				mask;
+	u16				id;
+	bool				valid;
+	bool				pinned;
+};
+
 struct arm_smmu_device {
 	struct device			*dev;
 
@@ -329,6 +346,13 @@ struct arm_smmu_cfg {
 };
 #define ARM_SMMU_INVALID_IRPTNDX	0xff
 
+struct arm_smmu_cb {
+	u64				ttbr[2];
+	u32				tcr[2];
+	u32				mair[2];
+	struct arm_smmu_cfg		*cfg;
+};
+
 enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_S1 = 0,
 	ARM_SMMU_DOMAIN_S2,
@@ -348,23 +372,39 @@ struct arm_smmu_domain {
 	struct iommu_domain		domain;
 };
 
-static inline u32 arm_smmu_lpae_tcr(struct io_pgtable_cfg *cfg)
+struct arm_smmu_master_cfg {
+	struct arm_smmu_device		*smmu;
+	s16				smendx[];
+};
+
+static inline u32 arm_smmu_lpae_tcr(const struct io_pgtable_cfg *cfg)
 {
-	return ARM_SMMU_TCR_EPD1 |
-	       FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
-	       FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
-	       FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
-	       FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
-	       FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+	u32 tcr = FIELD_PREP(ARM_SMMU_TCR_TG0, cfg->arm_lpae_s1_cfg.tcr.tg) |
+		FIELD_PREP(ARM_SMMU_TCR_SH0, cfg->arm_lpae_s1_cfg.tcr.sh) |
+		FIELD_PREP(ARM_SMMU_TCR_ORGN0, cfg->arm_lpae_s1_cfg.tcr.orgn) |
+		FIELD_PREP(ARM_SMMU_TCR_IRGN0, cfg->arm_lpae_s1_cfg.tcr.irgn) |
+		FIELD_PREP(ARM_SMMU_TCR_T0SZ, cfg->arm_lpae_s1_cfg.tcr.tsz);
+
+       /*
+	* When TTBR1 is selected shift the TCR fields by 16 bits and disable
+	* translation in TTBR0
+	*/
+	if (cfg->quirks & IO_PGTABLE_QUIRK_ARM_TTBR1) {
+		tcr = (tcr << 16) & ~ARM_SMMU_TCR_A1;
+		tcr |= ARM_SMMU_TCR_EPD0;
+	} else
+		tcr |= ARM_SMMU_TCR_EPD1;
+
+	return tcr;
 }
 
-static inline u32 arm_smmu_lpae_tcr2(struct io_pgtable_cfg *cfg)
+static inline u32 arm_smmu_lpae_tcr2(const struct io_pgtable_cfg *cfg)
 {
 	return FIELD_PREP(ARM_SMMU_TCR2_PASIZE, cfg->arm_lpae_s1_cfg.tcr.ips) |
 	       FIELD_PREP(ARM_SMMU_TCR2_SEP, ARM_SMMU_TCR2_SEP_UPSTREAM);
 }
 
-static inline u32 arm_smmu_lpae_vtcr(struct io_pgtable_cfg *cfg)
+static inline u32 arm_smmu_lpae_vtcr(const struct io_pgtable_cfg *cfg)
 {
 	return ARM_SMMU_VTCR_RES1 |
 	       FIELD_PREP(ARM_SMMU_VTCR_PS, cfg->arm_lpae_s2_cfg.vtcr.ps) |
@@ -386,14 +426,37 @@ struct arm_smmu_impl {
 			    u64 val);
 	int (*cfg_probe)(struct arm_smmu_device *smmu);
 	int (*reset)(struct arm_smmu_device *smmu);
-	int (*init_context)(struct arm_smmu_domain *smmu_domain);
+	int (*init_context)(struct arm_smmu_domain *smmu_domain,
+			struct io_pgtable_cfg *cfg, struct device *dev);
 	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
 			 int status);
 	int (*def_domain_type)(struct device *dev);
 	irqreturn_t (*global_fault)(int irq, void *dev);
 	irqreturn_t (*context_fault)(int irq, void *dev);
+	int (*alloc_context_bank)(struct arm_smmu_domain *smmu_domain,
+				  struct arm_smmu_device *smmu,
+				  struct device *dev, int start);
 };
 
+#define INVALID_SMENDX			-1
+#define cfg_smendx(cfg, fw, i) \
+	(i >= fw->num_ids ? INVALID_SMENDX : cfg->smendx[i])
+#define for_each_cfg_sme(cfg, fw, i, idx) \
+	for (i = 0; idx = cfg_smendx(cfg, fw, i), i < fw->num_ids; ++i)
+
+static inline int __arm_smmu_alloc_bitmap(unsigned long *map, int start, int end)
+{
+	int idx;
+
+	do {
+		idx = find_next_zero_bit(map, end, start);
+		if (idx == end)
+			return -ENOSPC;
+	} while (test_and_set_bit(idx, map));
+
+	return idx;
+}
+
 static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
 {
 	return smmu->base + (n << smmu->pgshift);
@@ -458,6 +521,7 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *nvidia_smmu_impl_init(struct arm_smmu_device *smmu);
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
 
+void arm_smmu_write_context_bank(struct arm_smmu_device *smmu, int idx);
 int arm_mmu500_reset(struct arm_smmu_device *smmu);
 
 #endif /* _ARM_SMMU_H */
diff --git a/drivers/iommu/arm/arm-smmu/qcom_iommu.c b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
index af6bec3ace00..b30d6c966e2c 100644
--- a/drivers/iommu/arm/arm-smmu/qcom_iommu.c
+++ b/drivers/iommu/arm/arm-smmu/qcom_iommu.c
@@ -584,8 +584,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	 * index into qcom_iommu->ctxs:
 	 */
 	if (WARN_ON(asid < 1) ||
-	    WARN_ON(asid > qcom_iommu->num_ctxs))
+	    WARN_ON(asid > qcom_iommu->num_ctxs)) {
+		put_device(&iommu_pdev->dev);
 		return -EINVAL;
+	}
 
 	if (!dev_iommu_priv_get(dev)) {
 		dev_iommu_priv_set(dev, qcom_iommu);
@@ -594,8 +596,10 @@ static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
 		 * multiple different iommu devices.  Multiple context
 		 * banks are ok, but multiple devices are not:
 		 */
-		if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev)))
+		if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev))) {
+			put_device(&iommu_pdev->dev);
 			return -EINVAL;
+		}
 	}
 
 	return iommu_fwspec_add_ids(dev, &asid, 1);
@@ -752,7 +756,7 @@ static const struct of_device_id ctx_of_match[] = {
 static struct platform_driver qcom_iommu_ctx_driver = {
 	.driver	= {
 		.name		= "qcom-iommu-ctx",
-		.of_match_table	= of_match_ptr(ctx_of_match),
+		.of_match_table	= ctx_of_match,
 	},
 	.probe	= qcom_iommu_ctx_probe,
 	.remove = qcom_iommu_ctx_remove,
@@ -915,7 +919,7 @@ static const struct of_device_id qcom_iommu_of_match[] = {
 static struct platform_driver qcom_iommu_driver = {
 	.driver	= {
 		.name		= "qcom-iommu",
-		.of_match_table	= of_match_ptr(qcom_iommu_of_match),
+		.of_match_table	= qcom_iommu_of_match,
 		.pm		= &qcom_iommu_pm_ops,
 	},
 	.probe	= qcom_iommu_device_probe,
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5141d49a046b..cd6e3c70ebb3 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -343,8 +343,11 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 
 	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 (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all,
+					NULL))
+			pr_warn("iova flush queue initialization failed\n");
+		else
+			cookie->fq_domain = domain;
 	}
 
 	if (!dev)
@@ -471,7 +474,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	WARN_ON(unmapped != size);
 
 	if (!cookie->fq_domain)
-		iommu_tlb_sync(domain, &iotlb_gather);
+		iommu_iotlb_sync(domain, &iotlb_gather);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 
@@ -524,6 +527,9 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	/* IOMMU can map any pages, so himem can also be used here */
 	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
 
+	/* It makes no sense to muck about with huge pages */
+	gfp &= ~__GFP_COMP;
+
 	while (count) {
 		struct page *page = NULL;
 		unsigned int order_size;
@@ -544,15 +550,9 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 			page = alloc_pages_node(nid, alloc_flags, order);
 			if (!page)
 				continue;
-			if (!order)
-				break;
-			if (!PageCompound(page)) {
+			if (order)
 				split_page(page, order);
-				break;
-			} else if (!split_huge_page(page)) {
-				break;
-			}
-			__free_pages(page, order);
+			break;
 		}
 		if (!page) {
 			__iommu_dma_free_pages(pages, i);
diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c
index 099a11a35fb9..b9a974d97831 100644
--- a/drivers/iommu/fsl_pamu.c
+++ b/drivers/iommu/fsl_pamu.c
@@ -1174,7 +1174,7 @@ error:
 	if (irq != NO_IRQ)
 		free_irq(irq, data);
 
-	kzfree(data);
+	kfree_sensitive(data);
 
 	if (pamu_regs)
 		iounmap(pamu_regs);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index df50a00ccfe8..2d70d56d8e0d 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -383,7 +383,7 @@ dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
 	return NULL;
 }
 
-/**
+/*
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
  * present in the platform
@@ -1027,8 +1027,8 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 {
 	struct intel_iommu *iommu;
 	u32 ver, sts;
-	int agaw = 0;
-	int msagaw = 0;
+	int agaw = -1;
+	int msagaw = -1;
 	int err;
 
 	if (!drhd->reg_base_addr) {
@@ -1053,17 +1053,28 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	}
 
 	err = -EINVAL;
-	agaw = iommu_calculate_agaw(iommu);
-	if (agaw < 0) {
-		pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n",
-			iommu->seq_id);
-		goto err_unmap;
-	}
-	msagaw = iommu_calculate_max_sagaw(iommu);
-	if (msagaw < 0) {
-		pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n",
-			iommu->seq_id);
-		goto err_unmap;
+	if (cap_sagaw(iommu->cap) == 0) {
+		pr_info("%s: No supported address widths. Not attempting DMA translation.\n",
+			iommu->name);
+		drhd->ignored = 1;
+	}
+
+	if (!drhd->ignored) {
+		agaw = iommu_calculate_agaw(iommu);
+		if (agaw < 0) {
+			pr_err("Cannot get a valid agaw for iommu (seq_id = %d)\n",
+			       iommu->seq_id);
+			drhd->ignored = 1;
+		}
+	}
+	if (!drhd->ignored) {
+		msagaw = iommu_calculate_max_sagaw(iommu);
+		if (msagaw < 0) {
+			pr_err("Cannot get a valid max agaw for iommu (seq_id = %d)\n",
+			       iommu->seq_id);
+			drhd->ignored = 1;
+			agaw = -1;
+		}
 	}
 	iommu->agaw = agaw;
 	iommu->msagaw = msagaw;
@@ -1090,7 +1101,12 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	raw_spin_lock_init(&iommu->register_lock);
 
-	if (intel_iommu_enabled) {
+	/*
+	 * This is only for hotplug; at boot time intel_iommu_enabled won't
+	 * be set yet. When intel_iommu_init() runs, it registers the units
+	 * present at boot time, then sets intel_iommu_enabled.
+	 */
+	if (intel_iommu_enabled && !drhd->ignored) {
 		err = iommu_device_sysfs_add(&iommu->iommu, NULL,
 					     intel_iommu_groups,
 					     "%s", iommu->name);
@@ -1120,7 +1136,7 @@ error:
 
 static void free_iommu(struct intel_iommu *iommu)
 {
-	if (intel_iommu_enabled) {
+	if (intel_iommu_enabled && iommu->iommu.ops) {
 		iommu_device_unregister(&iommu->iommu);
 		iommu_device_sysfs_remove(&iommu->iommu);
 	}
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 342e42e9c977..2e2ba294bb15 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -698,12 +698,47 @@ static int domain_update_iommu_superpage(struct dmar_domain *domain,
 	return fls(mask);
 }
 
+static int domain_update_device_node(struct dmar_domain *domain)
+{
+	struct device_domain_info *info;
+	int nid = NUMA_NO_NODE;
+
+	assert_spin_locked(&device_domain_lock);
+
+	if (list_empty(&domain->devices))
+		return NUMA_NO_NODE;
+
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->dev)
+			continue;
+
+		/*
+		 * There could possibly be multiple device numa nodes as devices
+		 * within the same domain may sit behind different IOMMUs. There
+		 * isn't perfect answer in such situation, so we select first
+		 * come first served policy.
+		 */
+		nid = dev_to_node(info->dev);
+		if (nid != NUMA_NO_NODE)
+			break;
+	}
+
+	return nid;
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
 	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
+
+	/*
+	 * If RHSA is missing, we should default to the device numa domain
+	 * as fall back.
+	 */
+	if (domain->nid == NUMA_NO_NODE)
+		domain->nid = domain_update_device_node(domain);
 }
 
 struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
@@ -5095,8 +5130,6 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type)
 		if (type == IOMMU_DOMAIN_DMA)
 			intel_init_iova_domain(dmar_domain);
 
-		domain_update_iommu_cap(dmar_domain);
-
 		domain = &dmar_domain->domain;
 		domain->geometry.aperture_start = 0;
 		domain->geometry.aperture_end   =
@@ -5408,8 +5441,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 	int ret = 0;
 	u64 size = 0;
 
-	if (!inv_info || !dmar_domain ||
-	    inv_info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+	if (!inv_info || !dmar_domain)
 		return -EINVAL;
 
 	if (!dev || !dev_is_pci(dev))
@@ -5434,8 +5466,8 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 
 	/* Size is only valid in address selective invalidation */
 	if (inv_info->granularity == IOMMU_INV_GRANU_ADDR)
-		size = to_vtd_size(inv_info->addr_info.granule_size,
-				   inv_info->addr_info.nb_granules);
+		size = to_vtd_size(inv_info->granu.addr_info.granule_size,
+				   inv_info->granu.addr_info.nb_granules);
 
 	for_each_set_bit(cache_type,
 			 (unsigned long *)&inv_info->cache,
@@ -5456,20 +5488,20 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 		 * granularity.
 		 */
 		if (inv_info->granularity == IOMMU_INV_GRANU_PASID &&
-		    (inv_info->pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
-			pasid = inv_info->pasid_info.pasid;
+		    (inv_info->granu.pasid_info.flags & IOMMU_INV_PASID_FLAGS_PASID))
+			pasid = inv_info->granu.pasid_info.pasid;
 		else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
-			 (inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
-			pasid = inv_info->addr_info.pasid;
+			 (inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_PASID))
+			pasid = inv_info->granu.addr_info.pasid;
 
 		switch (BIT(cache_type)) {
 		case IOMMU_CACHE_INV_TYPE_IOTLB:
 			/* HW will ignore LSB bits based on address mask */
 			if (inv_info->granularity == IOMMU_INV_GRANU_ADDR &&
 			    size &&
-			    (inv_info->addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
+			    (inv_info->granu.addr_info.addr & ((BIT(VTD_PAGE_SHIFT + size)) - 1))) {
 				pr_err_ratelimited("User address not aligned, 0x%llx, size order %llu\n",
-						   inv_info->addr_info.addr, size);
+						   inv_info->granu.addr_info.addr, size);
 			}
 
 			/*
@@ -5477,9 +5509,9 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 			 * We use npages = -1 to indicate that.
 			 */
 			qi_flush_piotlb(iommu, did, pasid,
-					mm_to_dma_pfn(inv_info->addr_info.addr),
+					mm_to_dma_pfn(inv_info->granu.addr_info.addr),
 					(granu == QI_GRAN_NONG_PASID) ? -1 : 1 << size,
-					inv_info->addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
+					inv_info->granu.addr_info.flags & IOMMU_INV_ADDR_FLAGS_LEAF);
 
 			if (!info->ats_enabled)
 				break;
@@ -5502,7 +5534,7 @@ intel_iommu_sva_invalidate(struct iommu_domain *domain, struct device *dev,
 				size = 64 - VTD_PAGE_SHIFT;
 				addr = 0;
 			} else if (inv_info->granularity == IOMMU_INV_GRANU_ADDR) {
-				addr = inv_info->addr_info.addr;
+				addr = inv_info->granu.addr_info.addr;
 			}
 
 			if (info->ats_enabled)
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 60ffe083b6d6..f1861fa3d0e4 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -285,8 +285,15 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	if (WARN_ON(!iommu) || !data)
 		return -EINVAL;
 
-	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
-	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+	if (data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+		return -EINVAL;
+
+	/* IOMMU core ensures argsz is more than the start of the union */
+	if (data->argsz < offsetofend(struct iommu_gpasid_bind_data, vendor.vtd))
+		return -EINVAL;
+
+	/* Make sure no undefined flags are used in vendor data */
+	if (data->vendor.vtd.flags & ~(IOMMU_SVA_VTD_GPASID_LAST - 1))
 		return -EINVAL;
 
 	if (!dev_is_pci(dev))
@@ -371,7 +378,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	spin_lock(&iommu->lock);
 	ret = intel_pasid_setup_nested(iommu, dev,
 				       (pgd_t *)(uintptr_t)data->gpgd,
-				       data->hpasid, &data->vtd, dmar_domain,
+				       data->hpasid, &data->vendor.vtd, dmar_domain,
 				       data->addr_width);
 	spin_unlock(&iommu->lock);
 	if (ret) {
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index dc7bcf858b6d..534810b6be77 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -20,6 +20,8 @@
 
 #include <asm/barrier.h>
 
+#include "io-pgtable-arm.h"
+
 #define ARM_LPAE_MAX_ADDR_BITS		52
 #define ARM_LPAE_S2_MAX_CONCAT_PAGES	16
 #define ARM_LPAE_MAX_LEVELS		4
@@ -100,23 +102,6 @@
 #define ARM_LPAE_PTE_MEMATTR_DEV	(((arm_lpae_iopte)0x1) << 2)
 
 /* Register bits */
-#define ARM_LPAE_TCR_TG0_4K		0
-#define ARM_LPAE_TCR_TG0_64K		1
-#define ARM_LPAE_TCR_TG0_16K		2
-
-#define ARM_LPAE_TCR_TG1_16K		1
-#define ARM_LPAE_TCR_TG1_4K		2
-#define ARM_LPAE_TCR_TG1_64K		3
-
-#define ARM_LPAE_TCR_SH_NS		0
-#define ARM_LPAE_TCR_SH_OS		2
-#define ARM_LPAE_TCR_SH_IS		3
-
-#define ARM_LPAE_TCR_RGN_NC		0
-#define ARM_LPAE_TCR_RGN_WBWA		1
-#define ARM_LPAE_TCR_RGN_WT		2
-#define ARM_LPAE_TCR_RGN_WB		3
-
 #define ARM_LPAE_VTCR_SL0_MASK		0x3
 
 #define ARM_LPAE_TCR_T0SZ_SHIFT		0
@@ -124,14 +109,6 @@
 #define ARM_LPAE_VTCR_PS_SHIFT		16
 #define ARM_LPAE_VTCR_PS_MASK		0x7
 
-#define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
-#define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
-#define ARM_LPAE_TCR_PS_40_BIT		0x2ULL
-#define ARM_LPAE_TCR_PS_42_BIT		0x3ULL
-#define ARM_LPAE_TCR_PS_44_BIT		0x4ULL
-#define ARM_LPAE_TCR_PS_48_BIT		0x5ULL
-#define ARM_LPAE_TCR_PS_52_BIT		0x6ULL
-
 #define ARM_LPAE_MAIR_ATTR_SHIFT(n)	((n) << 3)
 #define ARM_LPAE_MAIR_ATTR_MASK		0xff
 #define ARM_LPAE_MAIR_ATTR_DEVICE	0x04
diff --git a/drivers/iommu/io-pgtable-arm.h b/drivers/iommu/io-pgtable-arm.h
new file mode 100644
index 000000000000..ba7cfdf7afa0
--- /dev/null
+++ b/drivers/iommu/io-pgtable-arm.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef IO_PGTABLE_ARM_H_
+#define IO_PGTABLE_ARM_H_
+
+#define ARM_LPAE_TCR_TG0_4K		0
+#define ARM_LPAE_TCR_TG0_64K		1
+#define ARM_LPAE_TCR_TG0_16K		2
+
+#define ARM_LPAE_TCR_TG1_16K		1
+#define ARM_LPAE_TCR_TG1_4K		2
+#define ARM_LPAE_TCR_TG1_64K		3
+
+#define ARM_LPAE_TCR_SH_NS		0
+#define ARM_LPAE_TCR_SH_OS		2
+#define ARM_LPAE_TCR_SH_IS		3
+
+#define ARM_LPAE_TCR_RGN_NC		0
+#define ARM_LPAE_TCR_RGN_WBWA		1
+#define ARM_LPAE_TCR_RGN_WT		2
+#define ARM_LPAE_TCR_RGN_WB		3
+
+#define ARM_LPAE_TCR_PS_32_BIT		0x0ULL
+#define ARM_LPAE_TCR_PS_36_BIT		0x1ULL
+#define ARM_LPAE_TCR_PS_40_BIT		0x2ULL
+#define ARM_LPAE_TCR_PS_42_BIT		0x3ULL
+#define ARM_LPAE_TCR_PS_44_BIT		0x4ULL
+#define ARM_LPAE_TCR_PS_48_BIT		0x5ULL
+#define ARM_LPAE_TCR_PS_52_BIT		0x6ULL
+
+#endif /* IO_PGTABLE_ARM_H_ */
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0e4fbdc0f5e5..8c470f451a32 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -762,7 +762,7 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group,
 
 	}
 
-	iommu_flush_tlb_all(domain);
+	iommu_flush_iotlb_all(domain);
 
 out:
 	iommu_put_resv_regions(dev, &mappings);
@@ -1961,25 +1961,188 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
-int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
-			   struct iommu_cache_invalidate_info *inv_info)
+/*
+ * Check flags and other user provided data for valid combinations. We also
+ * make sure no reserved fields or unused flags are set. This is to ensure
+ * not breaking userspace in the future when these fields or flags are used.
+ */
+static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info)
 {
+	u32 mask;
+	int i;
+
+	if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1)
+		return -EINVAL;
+
+	mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1;
+	if (info->cache & ~mask)
+		return -EINVAL;
+
+	if (info->granularity >= IOMMU_INV_GRANU_NR)
+		return -EINVAL;
+
+	switch (info->granularity) {
+	case IOMMU_INV_GRANU_ADDR:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_PASID)
+			return -EINVAL;
+
+		mask = IOMMU_INV_ADDR_FLAGS_PASID |
+			IOMMU_INV_ADDR_FLAGS_ARCHID |
+			IOMMU_INV_ADDR_FLAGS_LEAF;
+
+		if (info->granu.addr_info.flags & ~mask)
+			return -EINVAL;
+		break;
+	case IOMMU_INV_GRANU_PASID:
+		mask = IOMMU_INV_PASID_FLAGS_PASID |
+			IOMMU_INV_PASID_FLAGS_ARCHID;
+		if (info->granu.pasid_info.flags & ~mask)
+			return -EINVAL;
+
+		break;
+	case IOMMU_INV_GRANU_DOMAIN:
+		if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(info->padding); i++) {
+		if (info->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+				void __user *uinfo)
+{
+	struct iommu_cache_invalidate_info inv_info = { 0 };
+	u32 minsz;
+	int ret;
+
 	if (unlikely(!domain->ops->cache_invalidate))
 		return -ENODEV;
 
-	return domain->ops->cache_invalidate(domain, dev, inv_info);
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_cache_invalidate_info, granu);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(&inv_info, uinfo, minsz))
+		return -EFAULT;
+
+	/* Fields before the variable size union are mandatory */
+	if (inv_info.argsz < minsz)
+		return -EINVAL;
+
+	/* PASID and address granu require additional info beyond minsz */
+	if (inv_info.granularity == IOMMU_INV_GRANU_PASID &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info))
+		return -EINVAL;
+
+	if (inv_info.granularity == IOMMU_INV_GRANU_ADDR &&
+	    inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info))
+		return -EINVAL;
+
+	/*
+	 * User might be using a newer UAPI header which has a larger data
+	 * size, we shall support the existing flags within the current
+	 * size. Copy the remaining user data _after_ minsz but not more
+	 * than the current kernel supported size.
+	 */
+	if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz,
+			   min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz))
+		return -EFAULT;
+
+	/* Now the argsz is validated, check the content */
+	ret = iommu_check_cache_invl_data(&inv_info);
+	if (ret)
+		return ret;
+
+	return domain->ops->cache_invalidate(domain, dev, &inv_info);
 }
-EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
-int iommu_sva_bind_gpasid(struct iommu_domain *domain,
-			   struct device *dev, struct iommu_gpasid_bind_data *data)
+static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
 {
+	u32 mask;
+	int i;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1)
+		return -EINVAL;
+
+	/* Check the range of supported formats */
+	if (data->format >= IOMMU_PASID_FORMAT_LAST)
+		return -EINVAL;
+
+	/* Check all flags */
+	mask = IOMMU_SVA_GPASID_VAL;
+	if (data->flags & ~mask)
+		return -EINVAL;
+
+	/* Check reserved padding fields */
+	for (i = 0; i < sizeof(data->padding); i++) {
+		if (data->padding[i])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int iommu_sva_prepare_bind_data(void __user *udata,
+				       struct iommu_gpasid_bind_data *data)
+{
+	u32 minsz;
+
+	/*
+	 * No new spaces can be added before the variable sized union, the
+	 * minimum size is the offset to the union.
+	 */
+	minsz = offsetof(struct iommu_gpasid_bind_data, vendor);
+
+	/* Copy minsz from user to get flags and argsz */
+	if (copy_from_user(data, udata, minsz))
+		return -EFAULT;
+
+	/* Fields before the variable size union are mandatory */
+	if (data->argsz < minsz)
+		return -EINVAL;
+	/*
+	 * User might be using a newer UAPI header, we shall let IOMMU vendor
+	 * driver decide on what size it needs. Since the guest PASID bind data
+	 * can be vendor specific, larger argsz could be the result of extension
+	 * for one vendor but it should not affect another vendor.
+	 * Copy the remaining user data _after_ minsz
+	 */
+	if (copy_from_user((void *)data + minsz, udata + minsz,
+			   min_t(u32, data->argsz, sizeof(*data)) - minsz))
+		return -EFAULT;
+
+	return iommu_check_bind_data(data);
+}
+
+int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			       void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
 	if (unlikely(!domain->ops->sva_bind_gpasid))
 		return -ENODEV;
 
-	return domain->ops->sva_bind_gpasid(domain, dev, data);
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, &data);
 }
-EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid);
 
 int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
 			     ioasid_t pasid)
@@ -1991,6 +2154,23 @@ int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
 }
 EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
 
+int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+				 void __user *udata)
+{
+	struct iommu_gpasid_bind_data data = { 0 };
+	int ret;
+
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	ret = iommu_sva_prepare_bind_data(udata, &data);
+	if (ret)
+		return ret;
+
+	return iommu_sva_unbind_gpasid(domain, dev, data.hpasid);
+}
+EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid);
+
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
@@ -2316,7 +2496,7 @@ size_t iommu_unmap(struct iommu_domain *domain,
 
 	iommu_iotlb_gather_init(&iotlb_gather);
 	ret = __iommu_unmap(domain, iova, size, &iotlb_gather);
-	iommu_tlb_sync(domain, &iotlb_gather);
+	iommu_iotlb_sync(domain, &iotlb_gather);
 
 	return ret;
 }
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 45a251da5453..30d969a4c5fd 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -579,7 +579,7 @@ void queue_iova(struct iova_domain *iovad,
 
 	/* Avoid false sharing as much as possible. */
 	if (!atomic_read(&iovad->fq_timer_on) &&
-	    !atomic_cmpxchg(&iovad->fq_timer_on, 0, 1))
+	    !atomic_xchg(&iovad->fq_timer_on, 1))
 		mod_timer(&iovad->fq_timer,
 			  jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
 }
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 785b228d39a6..c072cee532c2 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -3,7 +3,6 @@
  * Copyright (c) 2015-2016 MediaTek Inc.
  * Author: Yong Wu <yong.wu@mediatek.com>
  */
-#include <linux/memblock.h>
 #include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/component.h>
@@ -15,13 +14,16 @@
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
 #include <linux/list.h>
+#include <linux/mfd/syscon.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/soc/mediatek/infracfg.h>
 #include <asm/barrier.h>
 #include <soc/mediatek/smi.h>
 
@@ -116,6 +118,7 @@
 #define OUT_ORDER_WR_EN			BIT(4)
 #define HAS_SUB_COMM			BIT(5)
 #define WR_THROT_EN			BIT(6)
+#define HAS_LEGACY_IVRP_PADDR		BIT(7)
 
 #define MTK_IOMMU_HAS_FLAG(pdata, _x) \
 		((((pdata)->flags) & (_x)) == (_x))
@@ -582,7 +585,7 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
 		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
 	writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);
 
-	if (data->plat_data->m4u_plat == M4U_MT8173)
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_LEGACY_IVRP_PADDR))
 		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
 	else
 		regval = lower_32_bits(data->protect_base) |
@@ -640,8 +643,11 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	struct resource         *res;
 	resource_size_t		ioaddr;
 	struct component_match  *match = NULL;
+	struct regmap		*infracfg;
 	void                    *protect;
 	int                     i, larb_nr, ret;
+	u32			val;
+	char                    *p;
 
 	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -655,10 +661,28 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);
 
-	/* Whether the current dram is over 4GB */
-	data->enable_4GB = !!(max_pfn > (BIT_ULL(32) >> PAGE_SHIFT));
-	if (!MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
-		data->enable_4GB = false;
+	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) {
+		switch (data->plat_data->m4u_plat) {
+		case M4U_MT2712:
+			p = "mediatek,mt2712-infracfg";
+			break;
+		case M4U_MT8173:
+			p = "mediatek,mt8173-infracfg";
+			break;
+		default:
+			p = NULL;
+		}
+
+		infracfg = syscon_regmap_lookup_by_compatible(p);
+
+		if (IS_ERR(infracfg))
+			return PTR_ERR(infracfg);
+
+		ret = regmap_read(infracfg, REG_INFRA_MISC, &val);
+		if (ret)
+			return ret;
+		data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN);
+	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	data->base = devm_ioremap_resource(dev, res);
@@ -816,9 +840,17 @@ static const struct mtk_iommu_plat_data mt6779_data = {
 	.larbid_remap  = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}},
 };
 
+static const struct mtk_iommu_plat_data mt8167_data = {
+	.m4u_plat     = M4U_MT8167,
+	.flags        = RESET_AXI | HAS_LEGACY_IVRP_PADDR,
+	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
+	.larbid_remap = {{0}, {1}, {2}}, /* Linear mapping. */
+};
+
 static const struct mtk_iommu_plat_data mt8173_data = {
 	.m4u_plat     = M4U_MT8173,
-	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI,
+	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI |
+			HAS_LEGACY_IVRP_PADDR,
 	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
 	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */
 };
@@ -833,6 +865,7 @@ static const struct mtk_iommu_plat_data mt8183_data = {
 static const struct of_device_id mtk_iommu_of_ids[] = {
 	{ .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
 	{ .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data},
+	{ .compatible = "mediatek,mt8167-m4u", .data = &mt8167_data},
 	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
 	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
 	{}
@@ -843,7 +876,7 @@ static struct platform_driver mtk_iommu_driver = {
 	.remove	= mtk_iommu_remove,
 	.driver	= {
 		.name = "mtk-iommu",
-		.of_match_table = of_match_ptr(mtk_iommu_of_ids),
+		.of_match_table = mtk_iommu_of_ids,
 		.pm = &mtk_iommu_pm_ops,
 	}
 };
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index 122925dbe547..df32b3e3408b 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -39,6 +39,7 @@ enum mtk_iommu_plat {
 	M4U_MT2701,
 	M4U_MT2712,
 	M4U_MT6779,
+	M4U_MT8167,
 	M4U_MT8173,
 	M4U_MT8183,
 };
diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
index 3b1bf2fb94f5..ea6db1341916 100644
--- a/drivers/iommu/sun50i-iommu.c
+++ b/drivers/iommu/sun50i-iommu.c
@@ -881,7 +881,6 @@ static phys_addr_t sun50i_iommu_handle_perm_irq(struct sun50i_iommu *iommu)
 static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id)
 {
 	struct sun50i_iommu *iommu = dev_id;
-	phys_addr_t iova;
 	u32 status;
 
 	spin_lock(&iommu->iommu_lock);
@@ -893,15 +892,15 @@ static irqreturn_t sun50i_iommu_irq(int irq, void *dev_id)
 	}
 
 	if (status & IOMMU_INT_INVALID_L2PG)
-		iova = sun50i_iommu_handle_pt_irq(iommu,
-						  IOMMU_INT_ERR_ADDR_L2_REG,
-						  IOMMU_L2PG_INT_REG);
+		sun50i_iommu_handle_pt_irq(iommu,
+					    IOMMU_INT_ERR_ADDR_L2_REG,
+					    IOMMU_L2PG_INT_REG);
 	else if (status & IOMMU_INT_INVALID_L1PG)
-		iova = sun50i_iommu_handle_pt_irq(iommu,
-						  IOMMU_INT_ERR_ADDR_L1_REG,
-						  IOMMU_L1PG_INT_REG);
+		sun50i_iommu_handle_pt_irq(iommu,
+					   IOMMU_INT_ERR_ADDR_L1_REG,
+					   IOMMU_L1PG_INT_REG);
 	else
-		iova = sun50i_iommu_handle_perm_irq(iommu);
+		sun50i_iommu_handle_perm_irq(iommu);
 
 	iommu_write(iommu, IOMMU_INT_CLR_REG, status);
 
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 124c8848ab7e..0becdbfea306 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -12,6 +12,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
 
 #include <soc/tegra/ahb.h>
@@ -19,8 +20,10 @@
 
 struct tegra_smmu_group {
 	struct list_head list;
+	struct tegra_smmu *smmu;
 	const struct tegra_smmu_group_soc *soc;
 	struct iommu_group *group;
+	unsigned int swgroup;
 };
 
 struct tegra_smmu {
@@ -49,6 +52,7 @@ struct tegra_smmu_as {
 	struct iommu_domain domain;
 	struct tegra_smmu *smmu;
 	unsigned int use_count;
+	spinlock_t lock;
 	u32 *count;
 	struct page **pts;
 	struct page *pd;
@@ -127,6 +131,11 @@ static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
 #define SMMU_PDE_SHIFT 22
 #define SMMU_PTE_SHIFT 12
 
+#define SMMU_PAGE_MASK		(~(SMMU_SIZE_PT-1))
+#define SMMU_OFFSET_IN_PAGE(x)	((unsigned long)(x) & ~SMMU_PAGE_MASK)
+#define SMMU_PFN_PHYS(x)	((phys_addr_t)(x) << SMMU_PTE_SHIFT)
+#define SMMU_PHYS_PFN(x)	((unsigned long)((x) >> SMMU_PTE_SHIFT))
+
 #define SMMU_PD_READABLE	(1 << 31)
 #define SMMU_PD_WRITABLE	(1 << 30)
 #define SMMU_PD_NONSECURE	(1 << 29)
@@ -308,6 +317,8 @@ static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type)
 		return NULL;
 	}
 
+	spin_lock_init(&as->lock);
+
 	/* setup aperture */
 	as->domain.geometry.aperture_start = 0;
 	as->domain.geometry.aperture_end = 0xffffffff;
@@ -569,19 +580,14 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
 }
 
 static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
-		       dma_addr_t *dmap)
+		       dma_addr_t *dmap, struct page *page)
 {
 	unsigned int pde = iova_pd_index(iova);
 	struct tegra_smmu *smmu = as->smmu;
 
 	if (!as->pts[pde]) {
-		struct page *page;
 		dma_addr_t dma;
 
-		page = alloc_page(GFP_KERNEL | __GFP_DMA | __GFP_ZERO);
-		if (!page)
-			return NULL;
-
 		dma = dma_map_page(smmu->dev, page, 0, SMMU_SIZE_PT,
 				   DMA_TO_DEVICE);
 		if (dma_mapping_error(smmu->dev, dma)) {
@@ -644,7 +650,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
 			       u32 *pte, dma_addr_t pte_dma, u32 val)
 {
 	struct tegra_smmu *smmu = as->smmu;
-	unsigned long offset = offset_in_page(pte);
+	unsigned long offset = SMMU_OFFSET_IN_PAGE(pte);
 
 	*pte = val;
 
@@ -655,15 +661,61 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
 	smmu_flush(smmu);
 }
 
-static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+static struct page *as_get_pde_page(struct tegra_smmu_as *as,
+				    unsigned long iova, gfp_t gfp,
+				    unsigned long *flags)
+{
+	unsigned int pde = iova_pd_index(iova);
+	struct page *page = as->pts[pde];
+
+	/* at first check whether allocation needs to be done at all */
+	if (page)
+		return page;
+
+	/*
+	 * In order to prevent exhaustion of the atomic memory pool, we
+	 * allocate page in a sleeping context if GFP flags permit. Hence
+	 * spinlock needs to be unlocked and re-locked after allocation.
+	 */
+	if (!(gfp & __GFP_ATOMIC))
+		spin_unlock_irqrestore(&as->lock, *flags);
+
+	page = alloc_page(gfp | __GFP_DMA | __GFP_ZERO);
+
+	if (!(gfp & __GFP_ATOMIC))
+		spin_lock_irqsave(&as->lock, *flags);
+
+	/*
+	 * In a case of blocking allocation, a concurrent mapping may win
+	 * the PDE allocation. In this case the allocated page isn't needed
+	 * if allocation succeeded and the allocation failure isn't fatal.
+	 */
+	if (as->pts[pde]) {
+		if (page)
+			__free_page(page);
+
+		page = as->pts[pde];
+	}
+
+	return page;
+}
+
+static int
+__tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
+		 phys_addr_t paddr, size_t size, int prot, gfp_t gfp,
+		 unsigned long *flags)
 {
 	struct tegra_smmu_as *as = to_smmu_as(domain);
 	dma_addr_t pte_dma;
+	struct page *page;
 	u32 pte_attrs;
 	u32 *pte;
 
-	pte = as_get_pte(as, iova, &pte_dma);
+	page = as_get_pde_page(as, iova, gfp, flags);
+	if (!page)
+		return -ENOMEM;
+
+	pte = as_get_pte(as, iova, &pte_dma, page);
 	if (!pte)
 		return -ENOMEM;
 
@@ -680,13 +732,14 @@ static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
 		pte_attrs |= SMMU_PTE_WRITABLE;
 
 	tegra_smmu_set_pte(as, iova, pte, pte_dma,
-			   __phys_to_pfn(paddr) | pte_attrs);
+			   SMMU_PHYS_PFN(paddr) | pte_attrs);
 
 	return 0;
 }
 
-static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
-			       size_t size, struct iommu_iotlb_gather *gather)
+static size_t
+__tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+		   size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct tegra_smmu_as *as = to_smmu_as(domain);
 	dma_addr_t pte_dma;
@@ -702,6 +755,33 @@ static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return size;
 }
 
+static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&as->lock, flags);
+	ret = __tegra_smmu_map(domain, iova, paddr, size, prot, gfp, &flags);
+	spin_unlock_irqrestore(&as->lock, flags);
+
+	return ret;
+}
+
+static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
+			       size_t size, struct iommu_iotlb_gather *gather)
+{
+	struct tegra_smmu_as *as = to_smmu_as(domain);
+	unsigned long flags;
+
+	spin_lock_irqsave(&as->lock, flags);
+	size = __tegra_smmu_unmap(domain, iova, size, gather);
+	spin_unlock_irqrestore(&as->lock, flags);
+
+	return size;
+}
+
 static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain,
 					   dma_addr_t iova)
 {
@@ -716,7 +796,7 @@ static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain,
 
 	pfn = *pte & as->smmu->pfn_mask;
 
-	return PFN_PHYS(pfn);
+	return SMMU_PFN_PHYS(pfn) + SMMU_OFFSET_IN_PAGE(iova);
 }
 
 static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
@@ -813,22 +893,34 @@ tegra_smmu_find_group(struct tegra_smmu *smmu, unsigned int swgroup)
 	return NULL;
 }
 
+static void tegra_smmu_group_release(void *iommu_data)
+{
+	struct tegra_smmu_group *group = iommu_data;
+	struct tegra_smmu *smmu = group->smmu;
+
+	mutex_lock(&smmu->lock);
+	list_del(&group->list);
+	mutex_unlock(&smmu->lock);
+}
+
 static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu,
 						unsigned int swgroup)
 {
 	const struct tegra_smmu_group_soc *soc;
 	struct tegra_smmu_group *group;
+	struct iommu_group *grp;
 
+	/* Find group_soc associating with swgroup */
 	soc = tegra_smmu_find_group(smmu, swgroup);
-	if (!soc)
-		return NULL;
 
 	mutex_lock(&smmu->lock);
 
+	/* Find existing iommu_group associating with swgroup or group_soc */
 	list_for_each_entry(group, &smmu->groups, list)
-		if (group->soc == soc) {
+		if ((group->swgroup == swgroup) || (soc && group->soc == soc)) {
+			grp = iommu_group_ref_get(group->group);
 			mutex_unlock(&smmu->lock);
-			return group->group;
+			return grp;
 		}
 
 	group = devm_kzalloc(smmu->dev, sizeof(*group), GFP_KERNEL);
@@ -838,6 +930,8 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu,
 	}
 
 	INIT_LIST_HEAD(&group->list);
+	group->swgroup = swgroup;
+	group->smmu = smmu;
 	group->soc = soc;
 
 	group->group = iommu_group_alloc();
@@ -847,6 +941,9 @@ static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu,
 		return NULL;
 	}
 
+	iommu_group_set_iommudata(group->group, group, tegra_smmu_group_release);
+	if (soc)
+		iommu_group_set_name(group->group, soc->name);
 	list_add_tail(&group->list, &smmu->groups);
 	mutex_unlock(&smmu->lock);
 
@@ -1019,10 +1116,11 @@ struct tegra_smmu *tegra_smmu_probe(struct device *dev,
 	smmu->dev = dev;
 	smmu->mc = mc;
 
-	smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1;
+	smmu->pfn_mask =
+		BIT_MASK(mc->soc->num_address_bits - SMMU_PTE_SHIFT) - 1;
 	dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n",
 		mc->soc->num_address_bits, smmu->pfn_mask);
-	smmu->tlb_mask = (smmu->soc->num_tlb_lines << 1) - 1;
+	smmu->tlb_mask = (1 << fls(smmu->soc->num_tlb_lines)) - 1;
 	dev_dbg(dev, "TLB lines: %u, mask: %#lx\n", smmu->soc->num_tlb_lines,
 		smmu->tlb_mask);