Merge branches 'iommu/fixes', 'arm/qcom', 'arm/renesas', 'arm/rockchip',...

Merge branches 'iommu/fixes', 'arm/qcom', 'arm/renesas', 'arm/rockchip', 'arm/mediatek', 'arm/tegra', 'arm/smmu', 'x86/amd', 'x86/vt-d', 'virtio' and 'core' into next

Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt

@@ -15,6 +15,7 @@ Required Properties:
     - "renesas,ipmmu-r8a7744" for the R8A7744 (RZ/G1N) IPMMU.
     - "renesas,ipmmu-r8a7745" for the R8A7745 (RZ/G1E) IPMMU.
     - "renesas,ipmmu-r8a774a1" for the R8A774A1 (RZ/G2M) IPMMU.
+    - "renesas,ipmmu-r8a774b1" for the R8A774B1 (RZ/G2N) IPMMU.
     - "renesas,ipmmu-r8a774c0" for the R8A774C0 (RZ/G2E) IPMMU.
     - "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU.
     - "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU.

arch/ia64/include/asm/iommu.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_IA64_IOMMU_H
 #define _ASM_IA64_IOMMU_H 1
 
+#include <linux/acpi.h>
+
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT (((cycles_t) local_cpu_data->itc_freq)*10)
 
@@ -9,6 +11,9 @@ extern void no_iommu_init(void);
 #ifdef	CONFIG_INTEL_IOMMU
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+
+static inline int __init
+arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) { return 0; }
 #else
 #define no_iommu		(1)
 #define iommu_detected		(0)

arch/x86/include/asm/iommu.h

@@ -2,10 +2,28 @@
 #ifndef _ASM_X86_IOMMU_H
 #define _ASM_X86_IOMMU_H
 
+#include <linux/acpi.h>
+
+#include <asm/e820/api.h>
+
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
+static inline int __init
+arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
+{
+	u64 start = rmrr->base_address;
+	u64 end = rmrr->end_address + 1;
+
+	if (e820__mapped_all(start, end, E820_TYPE_RESERVED))
+		return 0;
+
+	pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n",
+	       start, end - 1);
+	return -EINVAL;
+}
+
 #endif /* _ASM_X86_IOMMU_H */

drivers/firmware/qcom_scm-32.c

@@ -614,3 +614,8 @@ int __qcom_scm_io_writel(struct device *dev, phys_addr_t addr, unsigned int val)
 	return qcom_scm_call_atomic2(QCOM_SCM_SVC_IO, QCOM_SCM_IO_WRITE,
 				     addr, val);
 }
+
+int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, bool enable)
+{
+	return -ENODEV;
+}

drivers/firmware/qcom_scm-64.c

@@ -62,32 +62,72 @@ static DEFINE_MUTEX(qcom_scm_lock);
 #define FIRST_EXT_ARG_IDX 3
 #define N_REGISTER_ARGS (MAX_QCOM_SCM_ARGS - N_EXT_QCOM_SCM_ARGS + 1)
 
-/**
- * qcom_scm_call() - Invoke a syscall in the secure world
- * @dev:	device
- * @svc_id:	service identifier
- * @cmd_id:	command identifier
- * @desc:	Descriptor structure containing arguments and return values
- *
- * Sends a command to the SCM and waits for the command to finish processing.
- * This should *only* be called in pre-emptible context.
-*/
-static int qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id,
-			 const struct qcom_scm_desc *desc,
-			 struct arm_smccc_res *res)
+static void __qcom_scm_call_do(const struct qcom_scm_desc *desc,
+			       struct arm_smccc_res *res, u32 fn_id,
+			       u64 x5, u32 type)
+{
+	u64 cmd;
+	struct arm_smccc_quirk quirk = { .id = ARM_SMCCC_QUIRK_QCOM_A6 };
+
+	cmd = ARM_SMCCC_CALL_VAL(type, qcom_smccc_convention,
+				 ARM_SMCCC_OWNER_SIP, fn_id);
+
+	quirk.state.a6 = 0;
+
+	do {
+		arm_smccc_smc_quirk(cmd, desc->arginfo, desc->args[0],
+				    desc->args[1], desc->args[2], x5,
+				    quirk.state.a6, 0, res, &quirk);
+
+		if (res->a0 == QCOM_SCM_INTERRUPTED)
+			cmd = res->a0;
+
+	} while (res->a0 == QCOM_SCM_INTERRUPTED);
+}
+
+static void qcom_scm_call_do(const struct qcom_scm_desc *desc,
+			     struct arm_smccc_res *res, u32 fn_id,
+			     u64 x5, bool atomic)
+{
+	int retry_count = 0;
+
+	if (atomic) {
+		__qcom_scm_call_do(desc, res, fn_id, x5, ARM_SMCCC_FAST_CALL);
+		return;
+	}
+
+	do {
+		mutex_lock(&qcom_scm_lock);
+
+		__qcom_scm_call_do(desc, res, fn_id, x5,
+				   ARM_SMCCC_STD_CALL);
+
+		mutex_unlock(&qcom_scm_lock);
+
+		if (res->a0 == QCOM_SCM_V2_EBUSY) {
+			if (retry_count++ > QCOM_SCM_EBUSY_MAX_RETRY)
+				break;
+			msleep(QCOM_SCM_EBUSY_WAIT_MS);
+		}
+	}  while (res->a0 == QCOM_SCM_V2_EBUSY);
+}
+
+static int ___qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id,
+			    const struct qcom_scm_desc *desc,
+			    struct arm_smccc_res *res, bool atomic)
 {
 	int arglen = desc->arginfo & 0xf;
-	int retry_count = 0, i;
+	int i;
 	u32 fn_id = QCOM_SCM_FNID(svc_id, cmd_id);
-	u64 cmd, x5 = desc->args[FIRST_EXT_ARG_IDX];
+	u64 x5 = desc->args[FIRST_EXT_ARG_IDX];
 	dma_addr_t args_phys = 0;
 	void *args_virt = NULL;
 	size_t alloc_len;
-	struct arm_smccc_quirk quirk = {.id = ARM_SMCCC_QUIRK_QCOM_A6};
+	gfp_t flag = atomic ? GFP_ATOMIC : GFP_KERNEL;
 
 	if (unlikely(arglen > N_REGISTER_ARGS)) {
 		alloc_len = N_EXT_QCOM_SCM_ARGS * sizeof(u64);
-		args_virt = kzalloc(PAGE_ALIGN(alloc_len), GFP_KERNEL);
+		args_virt = kzalloc(PAGE_ALIGN(alloc_len), flag);
 
 		if (!args_virt)
 			return -ENOMEM;
@@ -117,45 +157,55 @@ static int qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id,
 		x5 = args_phys;
 	}
 
-	do {
-		mutex_lock(&qcom_scm_lock);
-
-		cmd = ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL,
-					 qcom_smccc_convention,
-					 ARM_SMCCC_OWNER_SIP, fn_id);
-
-		quirk.state.a6 = 0;
-
-		do {
-			arm_smccc_smc_quirk(cmd, desc->arginfo, desc->args[0],
-				      desc->args[1], desc->args[2], x5,
-				      quirk.state.a6, 0, res, &quirk);
-
-			if (res->a0 == QCOM_SCM_INTERRUPTED)
-				cmd = res->a0;
-
-		} while (res->a0 == QCOM_SCM_INTERRUPTED);
-
-		mutex_unlock(&qcom_scm_lock);
-
-		if (res->a0 == QCOM_SCM_V2_EBUSY) {
-			if (retry_count++ > QCOM_SCM_EBUSY_MAX_RETRY)
-				break;
-			msleep(QCOM_SCM_EBUSY_WAIT_MS);
-		}
-	}  while (res->a0 == QCOM_SCM_V2_EBUSY);
+	qcom_scm_call_do(desc, res, fn_id, x5, atomic);
 
 	if (args_virt) {
 		dma_unmap_single(dev, args_phys, alloc_len, DMA_TO_DEVICE);
 		kfree(args_virt);
 	}
 
-	if (res->a0 < 0)
+	if ((long)res->a0 < 0)
 		return qcom_scm_remap_error(res->a0);
 
 	return 0;
 }
 
+/**
+ * qcom_scm_call() - Invoke a syscall in the secure world
+ * @dev:	device
+ * @svc_id:	service identifier
+ * @cmd_id:	command identifier
+ * @desc:	Descriptor structure containing arguments and return values
+ *
+ * Sends a command to the SCM and waits for the command to finish processing.
+ * This should *only* be called in pre-emptible context.
+ */
+static int qcom_scm_call(struct device *dev, u32 svc_id, u32 cmd_id,
+			 const struct qcom_scm_desc *desc,
+			 struct arm_smccc_res *res)
+{
+	might_sleep();
+	return ___qcom_scm_call(dev, svc_id, cmd_id, desc, res, false);
+}
+
+/**
+ * qcom_scm_call_atomic() - atomic variation of qcom_scm_call()
+ * @dev:	device
+ * @svc_id:	service identifier
+ * @cmd_id:	command identifier
+ * @desc:	Descriptor structure containing arguments and return values
+ * @res:	Structure containing results from SMC/HVC call
+ *
+ * Sends a command to the SCM and waits for the command to finish processing.
+ * This can be called in atomic context.
+ */
+static int qcom_scm_call_atomic(struct device *dev, u32 svc_id, u32 cmd_id,
+				const struct qcom_scm_desc *desc,
+				struct arm_smccc_res *res)
+{
+	return ___qcom_scm_call(dev, svc_id, cmd_id, desc, res, true);
+}
+
 /**
  * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
  * @entry: Entry point function for the cpus
@@ -502,3 +552,16 @@ int __qcom_scm_io_writel(struct device *dev, phys_addr_t addr, unsigned int val)
 	return qcom_scm_call(dev, QCOM_SCM_SVC_IO, QCOM_SCM_IO_WRITE,
 			     &desc, &res);
 }
+
+int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev, bool en)
+{
+	struct qcom_scm_desc desc = {0};
+	struct arm_smccc_res res;
+
+	desc.args[0] = QCOM_SCM_CONFIG_ERRATA1_CLIENT_ALL;
+	desc.args[1] = en;
+	desc.arginfo = QCOM_SCM_ARGS(2);
+
+	return qcom_scm_call_atomic(dev, QCOM_SCM_SVC_SMMU_PROGRAM,
+				    QCOM_SCM_CONFIG_ERRATA1, &desc, &res);
+}

drivers/firmware/qcom_scm.c

@@ -345,6 +345,12 @@ int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare)
 }
 EXPORT_SYMBOL(qcom_scm_iommu_secure_ptbl_init);
 
+int qcom_scm_qsmmu500_wait_safe_toggle(bool en)
+{
+	return __qcom_scm_qsmmu500_wait_safe_toggle(__scm->dev, en);
+}
+EXPORT_SYMBOL(qcom_scm_qsmmu500_wait_safe_toggle);
+
 int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val)
 {
 	return __qcom_scm_io_readl(__scm->dev, addr, val);

drivers/firmware/qcom_scm.h

@@ -91,10 +91,15 @@ extern int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id,
 				      u32 spare);
 #define QCOM_SCM_IOMMU_SECURE_PTBL_SIZE	3
 #define QCOM_SCM_IOMMU_SECURE_PTBL_INIT	4
+#define QCOM_SCM_SVC_SMMU_PROGRAM	0x15
+#define QCOM_SCM_CONFIG_ERRATA1		0x3
+#define QCOM_SCM_CONFIG_ERRATA1_CLIENT_ALL	0x2
 extern int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare,
 					     size_t *size);
 extern int __qcom_scm_iommu_secure_ptbl_init(struct device *dev, u64 addr,
 					     u32 size, u32 spare);
+extern int __qcom_scm_qsmmu500_wait_safe_toggle(struct device *dev,
+						bool enable);
 #define QCOM_MEM_PROT_ASSIGN_ID	0x16
 extern int  __qcom_scm_assign_mem(struct device *dev,
 				  phys_addr_t mem_region, size_t mem_sz,

drivers/iommu/Kconfig

@@ -3,6 +3,10 @@
 config IOMMU_IOVA
 	tristate
 
+# The IOASID library may also be used by non-IOMMU_API users
+config IOASID
+	tristate
+
 # IOMMU_API always gets selected by whoever wants it.
 config IOMMU_API
 	bool
@@ -138,6 +142,7 @@ config AMD_IOMMU
 	select PCI_PASID
 	select IOMMU_API
 	select IOMMU_IOVA
+	select IOMMU_DMA
 	depends on X86_64 && PCI && ACPI
 	---help---
 	  With this option you can enable support for AMD IOMMU hardware in

drivers/iommu/Makefile

@@ -7,13 +7,14 @@ obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o
 obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
+obj-$(CONFIG_IOASID) += ioasid.o
 obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
 obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o arm-smmu-qcom.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o

drivers/iommu/amd_iommu_types.h

@@ -468,7 +468,6 @@ struct protection_domain {
 	struct iommu_domain domain; /* generic domain handle used by
 				       iommu core code */
 	spinlock_t lock;	/* mostly used to lock the page table*/
-	struct mutex api_lock;	/* protect page tables in the iommu-api path */
 	u16 id;			/* the domain id written to the device table */
 	int mode;		/* paging mode (0-6 levels) */
 	u64 *pt_root;		/* page table root pointer */
@@ -639,8 +638,8 @@ struct iommu_dev_data {
 	struct list_head list;		  /* For domain->dev_list */
 	struct llist_node dev_data_list;  /* For global dev_data_list */
 	struct protection_domain *domain; /* Domain the device is bound to */
+	struct pci_dev *pdev;
 	u16 devid;			  /* PCI Device ID */
-	u16 alias;			  /* Alias Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
 	bool passthrough;		  /* Device is identity mapped */
 	struct {

drivers/iommu/arm-smmu-impl.c

@@ -109,7 +109,7 @@ static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smm
 #define ARM_MMU500_ACR_S2CRB_TLBEN	(1 << 10)
 #define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
 
-static int arm_mmu500_reset(struct arm_smmu_device *smmu)
+int arm_mmu500_reset(struct arm_smmu_device *smmu)
 {
 	u32 reg, major;
 	int i;
@@ -170,5 +170,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 				  "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
+	if (of_device_is_compatible(smmu->dev->of_node, "qcom,sdm845-smmu-500"))
+		return qcom_smmu_impl_init(smmu);
+
 	return smmu;
 }

drivers/iommu/arm-smmu-qcom.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2019, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/qcom_scm.h>
+
+#include "arm-smmu.h"
+
+struct qcom_smmu {
+	struct arm_smmu_device smmu;
+};
+
+static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu)
+{
+	int ret;
+
+	arm_mmu500_reset(smmu);
+
+	/*
+	 * To address performance degradation in non-real time clients,
+	 * such as USB and UFS, turn off wait-for-safe on sdm845 based boards,
+	 * such as MTP and db845, whose firmwares implement secure monitor
+	 * call handlers to turn on/off the wait-for-safe logic.
+	 */
+	ret = qcom_scm_qsmmu500_wait_safe_toggle(0);
+	if (ret)
+		dev_warn(smmu->dev, "Failed to turn off SAFE logic\n");
+
+	return ret;
+}
+
+static const struct arm_smmu_impl qcom_smmu_impl = {
+	.reset = qcom_sdm845_smmu500_reset,
+};
+
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	struct qcom_smmu *qsmmu;
+
+	qsmmu = devm_kzalloc(smmu->dev, sizeof(*qsmmu), GFP_KERNEL);
+	if (!qsmmu)
+		return ERR_PTR(-ENOMEM);
+
+	qsmmu->smmu = *smmu;
+
+	qsmmu->smmu.impl = &qcom_smmu_impl;
+	devm_kfree(smmu->dev, smmu);
+
+	return &qsmmu->smmu;
+}

drivers/iommu/arm-smmu-v3.c

@@ -2172,7 +2172,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 	cfg->cd.asid	= (u16)asid;
 	cfg->cd.ttbr	= pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
 	cfg->cd.tcr	= pgtbl_cfg->arm_lpae_s1_cfg.tcr;
-	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair[0];
+	cfg->cd.mair	= pgtbl_cfg->arm_lpae_s1_cfg.mair;
 	return 0;
 
 out_free_asid:
@@ -2448,7 +2448,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 }
 
 static int arm_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct io_pgtable_ops *ops = to_smmu_domain(domain)->pgtbl_ops;
 
@@ -3611,19 +3611,19 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 
 	/* Interrupt lines */
 
-	irq = platform_get_irq_byname(pdev, "combined");
+	irq = platform_get_irq_byname_optional(pdev, "combined");
 	if (irq > 0)
 		smmu->combined_irq = irq;
 	else {
-		irq = platform_get_irq_byname(pdev, "eventq");
+		irq = platform_get_irq_byname_optional(pdev, "eventq");
 		if (irq > 0)
 			smmu->evtq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "priq");
+		irq = platform_get_irq_byname_optional(pdev, "priq");
 		if (irq > 0)
 			smmu->priq.q.irq = irq;
 
-		irq = platform_get_irq_byname(pdev, "gerror");
+		irq = platform_get_irq_byname_optional(pdev, "gerror");
 		if (irq > 0)
 			smmu->gerr_irq = irq;
 	}

drivers/iommu/arm-smmu.h

@@ -79,6 +79,8 @@
 #define ID7_MINOR			GENMASK(3, 0)
 
 #define ARM_SMMU_GR0_sGFSR		0x48
+#define sGFSR_USF			BIT(1)
+
 #define ARM_SMMU_GR0_sGFSYNR0		0x50
 #define ARM_SMMU_GR0_sGFSYNR1		0x54
 #define ARM_SMMU_GR0_sGFSYNR2		0x58
@@ -304,17 +306,10 @@ enum arm_smmu_domain_stage {
 	ARM_SMMU_DOMAIN_BYPASS,
 };
 
-struct arm_smmu_flush_ops {
-	struct iommu_flush_ops		tlb;
-	void (*tlb_inv_range)(unsigned long iova, size_t size, size_t granule,
-			      bool leaf, void *cookie);
-	void (*tlb_sync)(void *cookie);
-};
-
 struct arm_smmu_domain {
 	struct arm_smmu_device		*smmu;
 	struct io_pgtable_ops		*pgtbl_ops;
-	const struct arm_smmu_flush_ops	*flush_ops;
+	const struct iommu_flush_ops	*flush_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	bool				non_strict;
@@ -335,6 +330,8 @@ struct arm_smmu_impl {
 	int (*cfg_probe)(struct arm_smmu_device *smmu);
 	int (*reset)(struct arm_smmu_device *smmu);
 	int (*init_context)(struct arm_smmu_domain *smmu_domain);
+	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
+			 int status);
 };
 
 static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)
@@ -398,5 +395,8 @@ static inline void arm_smmu_writeq(struct arm_smmu_device *smmu, int page,
 	arm_smmu_writeq((s), ARM_SMMU_CB((s), (n)), (o), (v))
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu);
+struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu);
+
+int arm_mmu500_reset(struct arm_smmu_device *smmu);
 
 #endif /* _ARM_SMMU_H */

drivers/iommu/dma-iommu.c

@@ -22,6 +22,7 @@
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
+#include <linux/crash_dump.h>
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -353,6 +354,21 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	return iova_reserve_iommu_regions(dev, domain);
 }
 
+static int iommu_dma_deferred_attach(struct device *dev,
+		struct iommu_domain *domain)
+{
+	const struct iommu_ops *ops = domain->ops;
+
+	if (!is_kdump_kernel())
+		return 0;
+
+	if (unlikely(ops->is_attach_deferred &&
+			ops->is_attach_deferred(domain, dev)))
+		return iommu_attach_device(domain, dev);
+
+	return 0;
+}
+
 /**
  * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
  *                    page flags.
@@ -462,7 +478,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot)
+		size_t size, int prot, dma_addr_t dma_mask)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -470,13 +486,16 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	size_t iova_off = iova_offset(iovad, phys);
 	dma_addr_t iova;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return DMA_MAPPING_ERROR;
+
 	size = iova_align(iovad, size + iova_off);
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
-	if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
+	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
 		iommu_dma_free_iova(cookie, iova, size);
 		return DMA_MAPPING_ERROR;
 	}
@@ -579,6 +598,9 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 
 	*dma_handle = DMA_MAPPING_ERROR;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return NULL;
+
 	min_size = alloc_sizes & -alloc_sizes;
 	if (min_size < PAGE_SIZE) {
 		min_size = PAGE_SIZE;
@@ -611,7 +633,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
+	if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
 			< size)
 		goto out_free_sg;
 
@@ -711,7 +733,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dma_handle;
 
-	dma_handle =__iommu_dma_map(dev, phys, size, prot);
+	dma_handle = __iommu_dma_map(dev, phys, size, prot, dma_get_mask(dev));
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    dma_handle != DMA_MAPPING_ERROR)
 		arch_sync_dma_for_device(dev, phys, size, dir);
@@ -821,6 +843,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long mask = dma_get_seg_boundary(dev);
 	int i;
 
+	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
+		return 0;
+
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
 
@@ -871,7 +896,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	 * We'll leave any physical concatenation to the IOMMU driver's
 	 * implementation - it knows better than we do.
 	 */
-	if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len)
+	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
@@ -911,7 +936,8 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
+			dma_get_mask(dev));
 }
 
 static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
@@ -1017,7 +1043,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	if (!cpu_addr)
 		return NULL;
 
-	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot);
+	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot,
+			dev->coherent_dma_mask);
 	if (*handle == DMA_MAPPING_ERROR) {
 		__iommu_dma_free(dev, size, cpu_addr);
 		return NULL;

drivers/iommu/dmar.c

@@ -895,8 +895,11 @@ int __init detect_intel_iommu(void)
 	}
 
 #ifdef CONFIG_X86
-	if (!ret)
+	if (!ret) {
 		x86_init.iommu.iommu_init = intel_iommu_init;
+		x86_platform.iommu_shutdown = intel_iommu_shutdown;
+	}
+
 #endif
 
 	if (dmar_tbl) {

drivers/iommu/exynos-iommu.c

@@ -1073,7 +1073,7 @@ static int lv2set_page(sysmmu_pte_t *pent, phys_addr_t paddr, size_t size,
  */
 static int exynos_iommu_map(struct iommu_domain *iommu_domain,
 			    unsigned long l_iova, phys_addr_t paddr, size_t size,
-			    int prot)
+			    int prot, gfp_t gfp)
 {
 	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_pte_t *entry;

drivers/iommu/intel-iommu.c

@@ -2420,14 +2420,24 @@ static void domain_remove_dev_info(struct dmar_domain *domain)
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-/*
- * find_domain
- * Note: we use struct device->archdata.iommu stores the info
- */
 static struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
+	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO ||
+		     dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
+		return NULL;
+
+	/* No lock here, assumes no domain exit in normal case */
+	info = dev->archdata.iommu;
+	if (likely(info))
+		return info->domain;
+
+	return NULL;
+}
+
+static struct dmar_domain *deferred_attach_domain(struct device *dev)
+{
 	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
 		struct iommu_domain *domain;
 
@@ -2437,12 +2447,7 @@ static struct dmar_domain *find_domain(struct device *dev)
 			intel_iommu_attach_device(domain, dev);
 	}
 
-	/* No lock here, assumes no domain exit in normal case */
-	info = dev->archdata.iommu;
-
-	if (likely(info))
-		return info->domain;
-	return NULL;
+	return find_domain(dev);
 }
 
 static inline struct device_domain_info *
@@ -3512,7 +3517,7 @@ static dma_addr_t __intel_map_single(struct device *dev, phys_addr_t paddr,
 
 	BUG_ON(dir == DMA_NONE);
 
-	domain = find_domain(dev);
+	domain = deferred_attach_domain(dev);
 	if (!domain)
 		return DMA_MAPPING_ERROR;
 
@@ -3732,7 +3737,7 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 	if (!iommu_need_mapping(dev))
 		return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
 
-	domain = find_domain(dev);
+	domain = deferred_attach_domain(dev);
 	if (!domain)
 		return 0;
 
@@ -3827,7 +3832,7 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size,
 	int prot = 0;
 	int ret;
 
-	domain = find_domain(dev);
+	domain = deferred_attach_domain(dev);
 	if (WARN_ON(dir == DMA_NONE || !domain))
 		return DMA_MAPPING_ERROR;
 
@@ -4314,13 +4319,19 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
 	struct dmar_rmrr_unit *rmrru;
+	int ret;
+
+	rmrr = (struct acpi_dmar_reserved_memory *)header;
+	ret = arch_rmrr_sanity_check(rmrr);
+	if (ret)
+		return ret;
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
 		goto out;
 
 	rmrru->hdr = header;
-	rmrr = (struct acpi_dmar_reserved_memory *)header;
+
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
 
@@ -4759,6 +4770,26 @@ static void intel_disable_iommus(void)
 		iommu_disable_translation(iommu);
 }
 
+void intel_iommu_shutdown(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu = NULL;
+
+	if (no_iommu || dmar_disabled)
+		return;
+
+	down_write(&dmar_global_lock);
+
+	/* Disable PMRs explicitly here. */
+	for_each_iommu(iommu, drhd)
+		iommu_disable_protect_mem_regions(iommu);
+
+	/* Make sure the IOMMUs are switched off */
+	intel_disable_iommus();
+
+	up_write(&dmar_global_lock);
+}
+
 static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
 {
 	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);
@@ -5440,7 +5471,7 @@ static void intel_iommu_aux_detach_device(struct iommu_domain *domain,
 
 static int intel_iommu_map(struct iommu_domain *domain,
 			   unsigned long iova, phys_addr_t hpa,
-			   size_t size, int iommu_prot)
+			   size_t size, int iommu_prot, gfp_t gfp)
 {
 	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
 	u64 max_addr;

drivers/iommu/io-pgtable-arm-v7s.c

@@ -846,27 +846,28 @@ struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns = {
 
 #ifdef CONFIG_IOMMU_IO_PGTABLE_ARMV7S_SELFTEST
 
-static struct io_pgtable_cfg *cfg_cookie;
+static struct io_pgtable_cfg *cfg_cookie __initdata;
 
-static void dummy_tlb_flush_all(void *cookie)
+static void __init dummy_tlb_flush_all(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void dummy_tlb_flush(unsigned long iova, size_t size, size_t granule,
-			    void *cookie)
+static void __init dummy_tlb_flush(unsigned long iova, size_t size,
+				   size_t granule, void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
-			       unsigned long iova, size_t granule, void *cookie)
+static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+				      unsigned long iova, size_t granule,
+				      void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
 
-static const struct iommu_flush_ops dummy_tlb_ops = {
+static const struct iommu_flush_ops dummy_tlb_ops __initconst = {
 	.tlb_flush_all	= dummy_tlb_flush_all,
 	.tlb_flush_walk	= dummy_tlb_flush,
 	.tlb_flush_leaf	= dummy_tlb_flush,

drivers/iommu/iommu.c

@@ -1665,6 +1665,36 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(iommu_attach_device);
 
+int iommu_cache_invalidate(struct iommu_domain *domain, struct device *dev,
+			   struct iommu_cache_invalidate_info *inv_info)
+{
+	if (unlikely(!domain->ops->cache_invalidate))
+		return -ENODEV;
+
+	return domain->ops->cache_invalidate(domain, dev, inv_info);
+}
+EXPORT_SYMBOL_GPL(iommu_cache_invalidate);
+
+int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+			   struct device *dev, struct iommu_gpasid_bind_data *data)
+{
+	if (unlikely(!domain->ops->sva_bind_gpasid))
+		return -ENODEV;
+
+	return domain->ops->sva_bind_gpasid(domain, dev, data);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_bind_gpasid);
+
+int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid)
+{
+	if (unlikely(!domain->ops->sva_unbind_gpasid))
+		return -ENODEV;
+
+	return domain->ops->sva_unbind_gpasid(dev, pasid);
+}
+EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid);
+
 static void __iommu_detach_device(struct iommu_domain *domain,
 				  struct device *dev)
 {
@@ -1854,8 +1884,8 @@ static size_t iommu_pgsize(struct iommu_domain *domain,
 	return pgsize;
 }
 
-int iommu_map(struct iommu_domain *domain, unsigned long iova,
-	      phys_addr_t paddr, size_t size, int prot)
+int __iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	const struct iommu_ops *ops = domain->ops;
 	unsigned long orig_iova = iova;
@@ -1892,8 +1922,8 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
 			 iova, &paddr, pgsize);
+		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
 
-		ret = ops->map(domain, iova, paddr, pgsize, prot);
 		if (ret)
 			break;
 
@@ -1913,8 +1943,22 @@ int iommu_map(struct iommu_domain *domain, unsigned long iova,
 
 	return ret;
 }
+
+int iommu_map(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	might_sleep();
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map);
 
+int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+	      phys_addr_t paddr, size_t size, int prot)
+{
+	return __iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_atomic);
+
 static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
 			    struct iommu_iotlb_gather *iotlb_gather)
@@ -1991,8 +2035,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
-size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		    struct scatterlist *sg, unsigned int nents, int prot)
+size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot,
+		    gfp_t gfp)
 {
 	size_t len = 0, mapped = 0;
 	phys_addr_t start;
@@ -2003,7 +2048,9 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 		phys_addr_t s_phys = sg_phys(sg);
 
 		if (len && s_phys != start + len) {
-			ret = iommu_map(domain, iova + mapped, start, len, prot);
+			ret = __iommu_map(domain, iova + mapped, start,
+					len, prot, gfp);
+
 			if (ret)
 				goto out_err;
 
@@ -2031,8 +2078,22 @@ size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 	return 0;
 
 }
+
+size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	might_sleep();
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
+}
 EXPORT_SYMBOL_GPL(iommu_map_sg);
 
+size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
+		    struct scatterlist *sg, unsigned int nents, int prot)
+{
+	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
+}
+EXPORT_SYMBOL_GPL(iommu_map_sg_atomic);
+
 int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
 			       phys_addr_t paddr, u64 size, int prot)
 {

drivers/iommu/msm_iommu.c

@@ -504,7 +504,7 @@ static void msm_iommu_detach_dev(struct iommu_domain *domain,
 }
 
 static int msm_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t pa, size_t len, int prot)
+			 phys_addr_t pa, size_t len, int prot, gfp_t gfp)
 {
 	struct msm_priv *priv = to_msm_priv(domain);
 	unsigned long flags;

drivers/iommu/mtk_iommu.c

@@ -101,8 +101,6 @@
 #define MTK_M4U_TO_PORT(id)		((id) & 0x1f)
 
 struct mtk_iommu_domain {
-	spinlock_t			pgtlock; /* lock for page table */
-
 	struct io_pgtable_cfg		cfg;
 	struct io_pgtable_ops		*iop;
 
@@ -173,13 +171,16 @@ static void mtk_iommu_tlb_flush_all(void *cookie)
 	}
 }
 
-static void mtk_iommu_tlb_add_flush_nosync(unsigned long iova, size_t size,
-					   size_t granule, bool leaf,
-					   void *cookie)
+static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
+					   size_t granule, void *cookie)
 {
 	struct mtk_iommu_data *data = cookie;
+	unsigned long flags;
+	int ret;
+	u32 tmp;
 
 	for_each_m4u(data) {
+		spin_lock_irqsave(&data->tlb_lock, flags);
 		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
 			       data->base + REG_MMU_INV_SEL);
 
@@ -188,23 +189,10 @@ static void mtk_iommu_tlb_add_flush_nosync(unsigned long iova, size_t size,
 			       data->base + REG_MMU_INVLD_END_A);
 		writel_relaxed(F_MMU_INV_RANGE,
 			       data->base + REG_MMU_INVALIDATE);
-		data->tlb_flush_active = true;
-	}
-}
-
-static void mtk_iommu_tlb_sync(void *cookie)
-{
-	struct mtk_iommu_data *data = cookie;
-	int ret;
-	u32 tmp;
-
-	for_each_m4u(data) {
-		/* Avoid timing out if there's nothing to wait for */
-		if (!data->tlb_flush_active)
-			return;
 
+		/* tlb sync */
 		ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE,
-						tmp, tmp != 0, 10, 100000);
+						tmp, tmp != 0, 10, 1000);
 		if (ret) {
 			dev_warn(data->dev,
 				 "Partial TLB flush timed out, falling back to full flush\n");
@@ -212,35 +200,24 @@ static void mtk_iommu_tlb_sync(void *cookie)
 		}
 		/* Clear the CPE status */
 		writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
-		data->tlb_flush_active = false;
+		spin_unlock_irqrestore(&data->tlb_lock, flags);
 	}
 }
 
-static void mtk_iommu_tlb_flush_walk(unsigned long iova, size_t size,
-				     size_t granule, void *cookie)
-{
-	mtk_iommu_tlb_add_flush_nosync(iova, size, granule, false, cookie);
-	mtk_iommu_tlb_sync(cookie);
-}
-
-static void mtk_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
-				     size_t granule, void *cookie)
-{
-	mtk_iommu_tlb_add_flush_nosync(iova, size, granule, true, cookie);
-	mtk_iommu_tlb_sync(cookie);
-}
-
 static void mtk_iommu_tlb_flush_page_nosync(struct iommu_iotlb_gather *gather,
 					    unsigned long iova, size_t granule,
 					    void *cookie)
 {
-	mtk_iommu_tlb_add_flush_nosync(iova, granule, granule, true, cookie);
+	struct mtk_iommu_data *data = cookie;
+	struct iommu_domain *domain = &data->m4u_dom->domain;
+
+	iommu_iotlb_gather_add_page(domain, gather, iova, granule);
 }
 
 static const struct iommu_flush_ops mtk_iommu_flush_ops = {
 	.tlb_flush_all = mtk_iommu_tlb_flush_all,
-	.tlb_flush_walk = mtk_iommu_tlb_flush_walk,
-	.tlb_flush_leaf = mtk_iommu_tlb_flush_leaf,
+	.tlb_flush_walk = mtk_iommu_tlb_flush_range_sync,
+	.tlb_flush_leaf = mtk_iommu_tlb_flush_range_sync,
 	.tlb_add_page = mtk_iommu_tlb_flush_page_nosync,
 };
 
@@ -316,8 +293,6 @@ static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom)
 {
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
 
-	spin_lock_init(&dom->pgtlock);
-
 	dom->cfg = (struct io_pgtable_cfg) {
 		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
 			IO_PGTABLE_QUIRK_NO_PERMS |
@@ -412,22 +387,17 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot)
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
-	unsigned long flags;
-	int ret;
 
 	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
 	if (data->enable_4GB)
 		paddr |= BIT_ULL(32);
 
-	spin_lock_irqsave(&dom->pgtlock, flags);
-	ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
-	spin_unlock_irqrestore(&dom->pgtlock, flags);
-
-	return ret;
+	/* Synchronize with the tlb_lock */
+	return dom->iop->map(dom->iop, iova, paddr, size, prot);
 }
 
 static size_t mtk_iommu_unmap(struct iommu_domain *domain,
@@ -435,25 +405,26 @@ static size_t mtk_iommu_unmap(struct iommu_domain *domain,
 			      struct iommu_iotlb_gather *gather)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
-	unsigned long flags;
-	size_t unmapsz;
-
-	spin_lock_irqsave(&dom->pgtlock, flags);
-	unmapsz = dom->iop->unmap(dom->iop, iova, size, gather);
-	spin_unlock_irqrestore(&dom->pgtlock, flags);
 
-	return unmapsz;
+	return dom->iop->unmap(dom->iop, iova, size, gather);
 }
 
 static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
-	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+	mtk_iommu_tlb_flush_all(mtk_iommu_get_m4u_data());
 }
 
 static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
-	mtk_iommu_tlb_sync(mtk_iommu_get_m4u_data());
+	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
+	size_t length = gather->end - gather->start;
+
+	if (gather->start == ULONG_MAX)
+		return;
+
+	mtk_iommu_tlb_flush_range_sync(gather->start, length, gather->pgsize,
+				       data);
 }
 
 static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
@@ -461,13 +432,9 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	struct mtk_iommu_data *data = mtk_iommu_get_m4u_data();
-	unsigned long flags;
 	phys_addr_t pa;
 
-	spin_lock_irqsave(&dom->pgtlock, flags);
 	pa = dom->iop->iova_to_phys(dom->iop, iova);
-	spin_unlock_irqrestore(&dom->pgtlock, flags);
-
 	if (data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
 		pa &= ~BIT_ULL(32);
 
@@ -733,6 +700,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	spin_lock_init(&data->tlb_lock);
 	list_add_tail(&data->list, &m4ulist);
 
 	if (!iommu_present(&platform_bus_type))

drivers/iommu/mtk_iommu.h

@@ -57,7 +57,7 @@ struct mtk_iommu_data {
 	struct mtk_iommu_domain		*m4u_dom;
 	struct iommu_group		*m4u_group;
 	bool                            enable_4GB;
-	bool				tlb_flush_active;
+	spinlock_t			tlb_lock; /* lock for tlb range flush */
 
 	struct iommu_device		iommu;
 	const struct mtk_iommu_plat_data *plat_data;

drivers/iommu/mtk_iommu_v1.c

@@ -295,7 +295,7 @@ static void mtk_iommu_detach_device(struct iommu_domain *domain,
 }
 
 static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			 phys_addr_t paddr, size_t size, int prot)
+			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
 	unsigned int page_num = size >> MT2701_IOMMU_PAGE_SHIFT;

drivers/iommu/omap-iommu.c

@@ -1339,7 +1339,7 @@ static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz)
 }
 
 static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
-			  phys_addr_t pa, size_t bytes, int prot)
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
 {
 	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
 	struct device *dev = omap_domain->dev;

drivers/iommu/qcom_iommu.c

@@ -284,9 +284,9 @@ static int qcom_iommu_init_domain(struct iommu_domain *domain,
 
 		/* MAIRs (stage-1 only) */
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
-				pgtbl_cfg.arm_lpae_s1_cfg.mair[0]);
+				pgtbl_cfg.arm_lpae_s1_cfg.mair);
 		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1,
-				pgtbl_cfg.arm_lpae_s1_cfg.mair[1]);
+				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);
 
 		/* SCTLR */
 		reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_AFE | SCTLR_TRE |
@@ -423,7 +423,7 @@ static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *de
 }
 
 static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	int ret;
 	unsigned long flags;
@@ -539,8 +539,8 @@ static int qcom_iommu_add_device(struct device *dev)
 	}
 
 	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR_OR_NULL(group))
-		return PTR_ERR_OR_ZERO(group);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
 
 	iommu_group_put(group);
 	iommu_device_link(&qcom_iommu->iommu, dev);

drivers/iommu/rockchip-iommu.c

@@ -527,7 +527,7 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
 	int i, err;
 
 	err = pm_runtime_get_if_in_use(iommu->dev);
-	if (WARN_ON_ONCE(err <= 0))
+	if (!err || WARN_ON_ONCE(err < 0))
 		return ret;
 
 	if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)))
@@ -758,7 +758,7 @@ static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
 }
 
 static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
-			phys_addr_t paddr, size_t size, int prot)
+			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
 	unsigned long flags;
@@ -980,13 +980,13 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 	if (!dma_dev)
 		return NULL;
 
-	rk_domain = devm_kzalloc(dma_dev, sizeof(*rk_domain), GFP_KERNEL);
+	rk_domain = kzalloc(sizeof(*rk_domain), GFP_KERNEL);
 	if (!rk_domain)
 		return NULL;
 
 	if (type == IOMMU_DOMAIN_DMA &&
 	    iommu_get_dma_cookie(&rk_domain->domain))
-		return NULL;
+		goto err_free_domain;
 
 	/*
 	 * rk32xx iommus use a 2 level pagetable.
@@ -1021,6 +1021,8 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
 err_put_cookie:
 	if (type == IOMMU_DOMAIN_DMA)
 		iommu_put_dma_cookie(&rk_domain->domain);
+err_free_domain:
+	kfree(rk_domain);
 
 	return NULL;
 }
@@ -1049,6 +1051,7 @@ static void rk_iommu_domain_free(struct iommu_domain *domain)
 
 	if (domain->type == IOMMU_DOMAIN_DMA)
 		iommu_put_dma_cookie(&rk_domain->domain);
+	kfree(rk_domain);
 }
 
 static int rk_iommu_add_device(struct device *dev)

drivers/iommu/s390-iommu.c

@@ -265,7 +265,7 @@ static int s390_iommu_update_trans(struct s390_domain *s390_domain,
 }
 
 static int s390_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct s390_domain *s390_domain = to_s390_domain(domain);
 	int flags = ZPCI_PTE_VALID, rc = 0;

drivers/iommu/tegra-gart.c

@@ -178,7 +178,7 @@ static inline int __gart_iommu_map(struct gart_device *gart, unsigned long iova,
 }
 
 static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t pa, size_t bytes, int prot)
+			  phys_addr_t pa, size_t bytes, int prot, gfp_t gfp)
 {
 	struct gart_device *gart = gart_handle;
 	int ret;

drivers/iommu/tegra-smmu.c

@@ -159,9 +159,9 @@ static bool smmu_dma_addr_valid(struct tegra_smmu *smmu, dma_addr_t addr)
 	return (addr & smmu->pfn_mask) == addr;
 }
 
-static dma_addr_t smmu_pde_to_dma(u32 pde)
+static dma_addr_t smmu_pde_to_dma(struct tegra_smmu *smmu, u32 pde)
 {
-	return pde << 12;
+	return (dma_addr_t)(pde & smmu->pfn_mask) << 12;
 }
 
 static void smmu_flush_ptc_all(struct tegra_smmu *smmu)
@@ -240,7 +240,7 @@ static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu,
 
 static inline void smmu_flush(struct tegra_smmu *smmu)
 {
-	smmu_readl(smmu, SMMU_CONFIG);
+	smmu_readl(smmu, SMMU_PTB_ASID);
 }
 
 static int tegra_smmu_alloc_asid(struct tegra_smmu *smmu, unsigned int *idp)
@@ -351,6 +351,20 @@ static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
 	unsigned int i;
 	u32 value;
 
+	group = tegra_smmu_find_swgroup(smmu, swgroup);
+	if (group) {
+		value = smmu_readl(smmu, group->reg);
+		value &= ~SMMU_ASID_MASK;
+		value |= SMMU_ASID_VALUE(asid);
+		value |= SMMU_ASID_ENABLE;
+		smmu_writel(smmu, value, group->reg);
+	} else {
+		pr_warn("%s group from swgroup %u not found\n", __func__,
+				swgroup);
+		/* No point moving ahead if group was not found */
+		return;
+	}
+
 	for (i = 0; i < smmu->soc->num_clients; i++) {
 		const struct tegra_mc_client *client = &smmu->soc->clients[i];
 
@@ -361,15 +375,6 @@ static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
 		value |= BIT(client->smmu.bit);
 		smmu_writel(smmu, value, client->smmu.reg);
 	}
-
-	group = tegra_smmu_find_swgroup(smmu, swgroup);
-	if (group) {
-		value = smmu_readl(smmu, group->reg);
-		value &= ~SMMU_ASID_MASK;
-		value |= SMMU_ASID_VALUE(asid);
-		value |= SMMU_ASID_ENABLE;
-		smmu_writel(smmu, value, group->reg);
-	}
 }
 
 static void tegra_smmu_disable(struct tegra_smmu *smmu, unsigned int swgroup,
@@ -549,6 +554,7 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
 				  dma_addr_t *dmap)
 {
 	unsigned int pd_index = iova_pd_index(iova);
+	struct tegra_smmu *smmu = as->smmu;
 	struct page *pt_page;
 	u32 *pd;
 
@@ -557,7 +563,7 @@ static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
 		return NULL;
 
 	pd = page_address(as->pd);
-	*dmap = smmu_pde_to_dma(pd[pd_index]);
+	*dmap = smmu_pde_to_dma(smmu, pd[pd_index]);
 
 	return tegra_smmu_pte_offset(pt_page, iova);
 }
@@ -599,7 +605,7 @@ static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
 	} else {
 		u32 *pd = page_address(as->pd);
 
-		*dmap = smmu_pde_to_dma(pd[pde]);
+		*dmap = smmu_pde_to_dma(smmu, pd[pde]);
 	}
 
 	return tegra_smmu_pte_offset(as->pts[pde], iova);
@@ -624,7 +630,7 @@ static void tegra_smmu_pte_put_use(struct tegra_smmu_as *as, unsigned long iova)
 	if (--as->count[pde] == 0) {
 		struct tegra_smmu *smmu = as->smmu;
 		u32 *pd = page_address(as->pd);
-		dma_addr_t pte_dma = smmu_pde_to_dma(pd[pde]);
+		dma_addr_t pte_dma = smmu_pde_to_dma(smmu, pd[pde]);
 
 		tegra_smmu_set_pde(as, iova, 0);
 
@@ -650,7 +656,7 @@ static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
 }
 
 static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
-			  phys_addr_t paddr, size_t size, int prot)
+			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	struct tegra_smmu_as *as = to_smmu_as(domain);
 	dma_addr_t pte_dma;

drivers/iommu/virtio-iommu.c

@@ -153,7 +153,6 @@ static off_t viommu_get_write_desc_offset(struct viommu_dev *viommu,
  */
 static int __viommu_sync_req(struct viommu_dev *viommu)
 {
-	int ret = 0;
 	unsigned int len;
 	size_t write_len;
 	struct viommu_request *req;
@@ -182,7 +181,7 @@ static int __viommu_sync_req(struct viommu_dev *viommu)
 		kfree(req);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int viommu_sync_req(struct viommu_dev *viommu)
@@ -713,7 +712,7 @@ static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 }
 
 static int viommu_map(struct iommu_domain *domain, unsigned long iova,
-		      phys_addr_t paddr, size_t size, int prot)
+		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
 	int ret;
 	u32 flags;

drivers/memory/mtk-smi.c

@@ -366,6 +366,8 @@ static int __maybe_unused mtk_smi_larb_suspend(struct device *dev)
 
 static const struct dev_pm_ops smi_larb_pm_ops = {
 	SET_RUNTIME_PM_OPS(mtk_smi_larb_suspend, mtk_smi_larb_resume, NULL)
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static struct platform_driver mtk_smi_larb_driver = {
@@ -507,6 +509,8 @@ static int __maybe_unused mtk_smi_common_suspend(struct device *dev)
 
 static const struct dev_pm_ops smi_common_pm_ops = {
 	SET_RUNTIME_PM_OPS(mtk_smi_common_suspend, mtk_smi_common_resume, NULL)
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static struct platform_driver mtk_smi_common_driver = {

include/linux/dmar.h

@@ -129,6 +129,7 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg)
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
 extern int intel_iommu_init(void);
+extern void intel_iommu_shutdown(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header, void *arg);
 extern int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg);
@@ -137,6 +138,7 @@ extern int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
+static inline void intel_iommu_shutdown(void) { }
 
 #define	dmar_parse_one_rmrr		dmar_res_noop
 #define	dmar_parse_one_atsr		dmar_res_noop

include/linux/io-pgtable.h

@@ -102,7 +102,7 @@ struct io_pgtable_cfg {
 		struct {
 			u64	ttbr[2];
 			u64	tcr;
-			u64	mair[2];
+			u64	mair;
 		} arm_lpae_s1_cfg;
 
 		struct {

include/linux/ioasid.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_IOASID_H
+#define __LINUX_IOASID_H
+
+#include <linux/types.h>
+#include <linux/errno.h>
+
+#define INVALID_IOASID ((ioasid_t)-1)
+typedef unsigned int ioasid_t;
+typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data);
+typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data);
+
+struct ioasid_set {
+	int dummy;
+};
+
+/**
+ * struct ioasid_allocator_ops - IOASID allocator helper functions and data
+ *
+ * @alloc:	helper function to allocate IOASID
+ * @free:	helper function to free IOASID
+ * @list:	for tracking ops that share helper functions but not data
+ * @pdata:	data belong to the allocator, provided when calling alloc()
+ */
+struct ioasid_allocator_ops {
+	ioasid_alloc_fn_t alloc;
+	ioasid_free_fn_t free;
+	struct list_head list;
+	void *pdata;
+};
+
+#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 }
+
+#if IS_ENABLED(CONFIG_IOASID)
+ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max,
+		      void *private);
+void ioasid_free(ioasid_t ioasid);
+void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
+		  bool (*getter)(void *));
+int ioasid_register_allocator(struct ioasid_allocator_ops *allocator);
+void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator);
+int ioasid_set_data(ioasid_t ioasid, void *data);
+
+#else /* !CONFIG_IOASID */
+static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min,
+				    ioasid_t max, void *private)
+{
+	return INVALID_IOASID;
+}
+
+static inline void ioasid_free(ioasid_t ioasid)
+{
+}
+
+static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid,
+				bool (*getter)(void *))
+{
+	return NULL;
+}
+
+static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator)
+{
+	return -ENOTSUPP;
+}
+
+static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator)
+{
+}
+
+static inline int ioasid_set_data(ioasid_t ioasid, void *data)
+{
+	return -ENOTSUPP;
+}
+
+#endif /* CONFIG_IOASID */
+#endif /* __LINUX_IOASID_H */

include/linux/iommu.h

@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/of.h>
+#include <linux/ioasid.h>
 #include <uapi/linux/iommu.h>
 
 #define IOMMU_READ	(1 << 0)
@@ -31,11 +32,11 @@
  */
 #define IOMMU_PRIV	(1 << 5)
 /*
- * Non-coherent masters on few Qualcomm SoCs can use this page protection flag
- * to set correct cacheability attributes to use an outer level of cache -
- * last level cache, aka system cache.
+ * Non-coherent masters can use this page protection flag to set cacheable
+ * memory attributes for only a transparent outer level of cache, also known as
+ * the last-level or system cache.
  */
-#define IOMMU_QCOM_SYS_CACHE	(1 << 6)
+#define IOMMU_SYS_CACHE_ONLY	(1 << 6)
 
 struct iommu_ops;
 struct iommu_group;
@@ -244,7 +245,10 @@ struct iommu_iotlb_gather {
  * @sva_unbind: Unbind process address space from device
  * @sva_get_pasid: Get PASID associated to a SVA handle
  * @page_response: handle page request response
+ * @cache_invalidate: invalidate translation caches
  * @pgsize_bitmap: bitmap of all possible supported page sizes
+ * @sva_bind_gpasid: bind guest pasid and mm
+ * @sva_unbind_gpasid: unbind guest pasid and mm
  */
 struct iommu_ops {
 	bool (*capable)(enum iommu_cap);
@@ -256,7 +260,7 @@ struct iommu_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot);
+		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
 	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
 		     size_t size, struct iommu_iotlb_gather *iotlb_gather);
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
@@ -306,6 +310,12 @@ struct iommu_ops {
 	int (*page_response)(struct device *dev,
 			     struct iommu_fault_event *evt,
 			     struct iommu_page_response *msg);
+	int (*cache_invalidate)(struct iommu_domain *domain, struct device *dev,
+				struct iommu_cache_invalidate_info *inv_info);
+	int (*sva_bind_gpasid)(struct iommu_domain *domain,
+			struct device *dev, struct iommu_gpasid_bind_data *data);
+
+	int (*sva_unbind_gpasid)(struct device *dev, int pasid);
 
 	unsigned long pgsize_bitmap;
 };
@@ -417,10 +427,19 @@ extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
+extern int iommu_cache_invalidate(struct iommu_domain *domain,
+				  struct device *dev,
+				  struct iommu_cache_invalidate_info *inv_info);
+extern int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+		struct device *dev, struct iommu_gpasid_bind_data *data);
+extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+				struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot);
+extern int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
+			    phys_addr_t paddr, size_t size, int prot);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
@@ -428,6 +447,9 @@ extern size_t iommu_unmap_fast(struct iommu_domain *domain,
 			       struct iommu_iotlb_gather *iotlb_gather);
 extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
 			   struct scatterlist *sg,unsigned int nents, int prot);
+extern size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
@@ -662,6 +684,13 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova,
 	return -ENODEV;
 }
 
+static inline int iommu_map_atomic(struct iommu_domain *domain,
+				   unsigned long iova, phys_addr_t paddr,
+				   size_t size, int prot)
+{
+	return -ENODEV;
+}
+
 static inline size_t iommu_unmap(struct iommu_domain *domain,
 				 unsigned long iova, size_t size)
 {
@@ -682,6 +711,13 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain,
 	return 0;
 }
 
+static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				  unsigned long iova, struct scatterlist *sg,
+				  unsigned int nents, int prot)
+{
+	return 0;
+}
+
 static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 {
 }
@@ -1005,6 +1041,25 @@ static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
 	return IOMMU_PASID_INVALID;
 }
 
+static inline int
+iommu_cache_invalidate(struct iommu_domain *domain,
+		       struct device *dev,
+		       struct iommu_cache_invalidate_info *inv_info)
+{
+	return -ENODEV;
+}
+static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
+				struct device *dev, struct iommu_gpasid_bind_data *data)
+{
+	return -ENODEV;
+}
+
+static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
+					   struct device *dev, int pasid)
+{
+	return -ENODEV;
+}
+
 #endif /* CONFIG_IOMMU_API */
 
 #ifdef CONFIG_IOMMU_DEBUGFS

include/linux/qcom_scm.h

@@ -58,6 +58,7 @@ extern int qcom_scm_set_remote_state(u32 state, u32 id);
 extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
 extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
 extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
+extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en);
 extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val);
 extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val);
 #else
@@ -97,6 +98,7 @@ qcom_scm_set_remote_state(u32 state,u32 id) { return -ENODEV; }
 static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) { return -ENODEV; }
 static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) { return -ENODEV; }
 static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) { return -ENODEV; }
+static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) { return -ENODEV; }
 static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) { return -ENODEV; }
 static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) { return -ENODEV; }
 #endif

include/uapi/linux/iommu.h

@@ -152,4 +152,173 @@ struct iommu_page_response {
 	__u32	code;
 };
 
+/* defines the granularity of the invalidation */
+enum iommu_inv_granularity {
+	IOMMU_INV_GRANU_DOMAIN,	/* domain-selective invalidation */
+	IOMMU_INV_GRANU_PASID,	/* PASID-selective invalidation */
+	IOMMU_INV_GRANU_ADDR,	/* page-selective invalidation */
+	IOMMU_INV_GRANU_NR,	/* number of invalidation granularities */
+};
+
+/**
+ * struct iommu_inv_addr_info - Address Selective Invalidation Structure
+ *
+ * @flags: indicates the granularity of the address-selective invalidation
+ * - If the PASID bit is set, the @pasid field is populated and the invalidation
+ *   relates to cache entries tagged with this PASID and matching the address
+ *   range.
+ * - If ARCHID bit is set, @archid is populated and the invalidation relates
+ *   to cache entries tagged with this architecture specific ID and matching
+ *   the address range.
+ * - Both PASID and ARCHID can be set as they may tag different caches.
+ * - If neither PASID or ARCHID is set, global addr invalidation applies.
+ * - The LEAF flag indicates whether only the leaf PTE caching needs to be
+ *   invalidated and other paging structure caches can be preserved.
+ * @pasid: process address space ID
+ * @archid: architecture-specific ID
+ * @addr: first stage/level input address
+ * @granule_size: page/block size of the mapping in bytes
+ * @nb_granules: number of contiguous granules to be invalidated
+ */
+struct iommu_inv_addr_info {
+#define IOMMU_INV_ADDR_FLAGS_PASID	(1 << 0)
+#define IOMMU_INV_ADDR_FLAGS_ARCHID	(1 << 1)
+#define IOMMU_INV_ADDR_FLAGS_LEAF	(1 << 2)
+	__u32	flags;
+	__u32	archid;
+	__u64	pasid;
+	__u64	addr;
+	__u64	granule_size;
+	__u64	nb_granules;
+};
+
+/**
+ * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure
+ *
+ * @flags: indicates the granularity of the PASID-selective invalidation
+ * - If the PASID bit is set, the @pasid field is populated and the invalidation
+ *   relates to cache entries tagged with this PASID and matching the address
+ *   range.
+ * - If the ARCHID bit is set, the @archid is populated and the invalidation
+ *   relates to cache entries tagged with this architecture specific ID and
+ *   matching the address range.
+ * - Both PASID and ARCHID can be set as they may tag different caches.
+ * - At least one of PASID or ARCHID must be set.
+ * @pasid: process address space ID
+ * @archid: architecture-specific ID
+ */
+struct iommu_inv_pasid_info {
+#define IOMMU_INV_PASID_FLAGS_PASID	(1 << 0)
+#define IOMMU_INV_PASID_FLAGS_ARCHID	(1 << 1)
+	__u32	flags;
+	__u32	archid;
+	__u64	pasid;
+};
+
+/**
+ * struct iommu_cache_invalidate_info - First level/stage invalidation
+ *     information
+ * @version: API version of this structure
+ * @cache: bitfield that allows to select which caches to invalidate
+ * @granularity: defines the lowest granularity used for the invalidation:
+ *     domain > PASID > addr
+ * @padding: reserved for future use (should be zero)
+ * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID
+ * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR
+ *
+ * Not all the combinations of cache/granularity are valid:
+ *
+ * +--------------+---------------+---------------+---------------+
+ * | type /       |   DEV_IOTLB   |     IOTLB     |      PASID    |
+ * | granularity  |               |               |      cache    |
+ * +==============+===============+===============+===============+
+ * | DOMAIN       |       N/A     |       Y       |       Y       |
+ * +--------------+---------------+---------------+---------------+
+ * | PASID        |       Y       |       Y       |       Y       |
+ * +--------------+---------------+---------------+---------------+
+ * | ADDR         |       Y       |       Y       |       N/A     |
+ * +--------------+---------------+---------------+---------------+
+ *
+ * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than
+ * @version and @cache.
+ *
+ * If multiple cache types are invalidated simultaneously, they all
+ * must support the used granularity.
+ */
+struct iommu_cache_invalidate_info {
+#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
+	__u32	version;
+/* IOMMU paging structure cache */
+#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /* IOMMU IOTLB */
+#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /* Device IOTLB */
+#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /* PASID cache */
+#define IOMMU_CACHE_INV_TYPE_NR		(3)
+	__u8	cache;
+	__u8	granularity;
+	__u8	padding[2];
+	union {
+		struct iommu_inv_pasid_info pasid_info;
+		struct iommu_inv_addr_info addr_info;
+	};
+};
+
+/**
+ * struct iommu_gpasid_bind_data_vtd - Intel VT-d specific data on device and guest
+ * SVA binding.
+ *
+ * @flags:	VT-d PASID table entry attributes
+ * @pat:	Page attribute table data to compute effective memory type
+ * @emt:	Extended memory type
+ *
+ * Only guest vIOMMU selectable and effective options are passed down to
+ * the host IOMMU.
+ */
+struct iommu_gpasid_bind_data_vtd {
+#define IOMMU_SVA_VTD_GPASID_SRE	(1 << 0) /* supervisor request */
+#define IOMMU_SVA_VTD_GPASID_EAFE	(1 << 1) /* extended access enable */
+#define IOMMU_SVA_VTD_GPASID_PCD	(1 << 2) /* page-level cache disable */
+#define IOMMU_SVA_VTD_GPASID_PWT	(1 << 3) /* page-level write through */
+#define IOMMU_SVA_VTD_GPASID_EMTE	(1 << 4) /* extended mem type enable */
+#define IOMMU_SVA_VTD_GPASID_CD		(1 << 5) /* PASID-level cache disable */
+	__u64 flags;
+	__u32 pat;
+	__u32 emt;
+};
+
+/**
+ * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
+ * @version:	Version of this data structure
+ * @format:	PASID table entry format
+ * @flags:	Additional information on guest bind request
+ * @gpgd:	Guest page directory base of the guest mm to bind
+ * @hpasid:	Process address space ID used for the guest mm in host IOMMU
+ * @gpasid:	Process address space ID used for the guest mm in guest IOMMU
+ * @addr_width:	Guest virtual address width
+ * @padding:	Reserved for future use (should be zero)
+ * @vtd:	Intel VT-d specific data
+ *
+ * Guest to host PASID mapping can be an identity or non-identity, where guest
+ * has its own PASID space. For non-identify mapping, guest to host PASID lookup
+ * is needed when VM programs guest PASID into an assigned device. VMM may
+ * trap such PASID programming then request host IOMMU driver to convert guest
+ * PASID to host PASID based on this bind data.
+ */
+struct iommu_gpasid_bind_data {
+#define IOMMU_GPASID_BIND_VERSION_1	1
+	__u32 version;
+#define IOMMU_PASID_FORMAT_INTEL_VTD	1
+	__u32 format;
+#define IOMMU_SVA_GPASID_VAL	(1 << 0) /* guest PASID valid */
+	__u64 flags;
+	__u64 gpgd;
+	__u64 hpasid;
+	__u64 gpasid;
+	__u32 addr_width;
+	__u8  padding[12];
+	/* Vendor specific data */
+	union {
+		struct iommu_gpasid_bind_data_vtd vtd;
+	};
+};
+
 #endif /* _UAPI_IOMMU_H */