Merge branches 'arm/msm', 'arm/allwinner', 'arm/smmu', 'x86/vt-d', 'hyper-v',...

Merge branches 'arm/msm', 'arm/allwinner', 'arm/smmu', 'x86/vt-d', 'hyper-v', 'core' and 'x86/amd' into next

Documentation/devicetree/bindings/iommu/allwinner,sun50i-h6-iommu.yaml

+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/iommu/allwinner,sun50i-h6-iommu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Allwinner H6 IOMMU Device Tree Bindings
+
+maintainers:
+  - Chen-Yu Tsai <wens@csie.org>
+  - Maxime Ripard <mripard@kernel.org>
+
+properties:
+  "#iommu-cells":
+    const: 1
+    description:
+      The content of the cell is the master ID.
+
+  compatible:
+    const: allwinner,sun50i-h6-iommu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+required:
+  - "#iommu-cells"
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - resets
+
+additionalProperties: false
+
+examples:
+  - |
+      #include <dt-bindings/interrupt-controller/arm-gic.h>
+      #include <dt-bindings/interrupt-controller/irq.h>
+
+      #include <dt-bindings/clock/sun50i-h6-ccu.h>
+      #include <dt-bindings/reset/sun50i-h6-ccu.h>
+
+      iommu: iommu@30f0000 {
+          compatible = "allwinner,sun50i-h6-iommu";
+          reg = <0x030f0000 0x10000>;
+          interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>;
+          clocks = <&ccu CLK_BUS_IOMMU>;
+          resets = <&ccu RST_BUS_IOMMU>;
+          #iommu-cells = <1>;
+      };
+
+...

Documentation/devicetree/bindings/iommu/arm,smmu.yaml

@@ -41,7 +41,9 @@ properties:
           - const: arm,mmu-500
           - const: arm,smmu-v2
       - items:
-          - const: arm,mmu-401
+          - enum:
+              - arm,mmu-400
+              - arm,mmu-401
           - const: arm,smmu-v1
       - enum:
           - arm,smmu-v1

Documentation/devicetree/bindings/remoteproc/qcom,q6v5.txt

@@ -184,6 +184,9 @@ For the compatible strings below the following phandle references are required:
 		    followed by the offset within syscon for conn_box_spare0
 		    register.
 
+The Hexagon node must contain iommus property as described in ../iommu/iommu.txt
+on platforms which do not have TrustZone.
+
 = SUBNODES:
 The Hexagon node must contain two subnodes, named "mba" and "mpss" representing
 the memory regions used by the Hexagon firmware. Each sub-node must contain:

arch/arm64/boot/dts/qcom/sdm845-cheza.dtsi

@@ -631,6 +631,11 @@ ap_ts_i2c: &i2c14 {
 	status = "okay";
 };
 
+&mss_pil {
+	iommus = <&apps_smmu 0x780 0x1>,
+		 <&apps_smmu 0x724 0x3>;
+};
+
 &pm8998_pwrkey {
 	status = "disabled";
 };

drivers/iommu/Kconfig

@@ -303,6 +303,15 @@ config ROCKCHIP_IOMMU
 	  Say Y here if you are using a Rockchip SoC that includes an IOMMU
 	  device.
 
+config SUN50I_IOMMU
+	bool "Allwinner H6 IOMMU Support"
+	depends on ARCH_SUNXI || COMPILE_TEST
+	select ARM_DMA_USE_IOMMU
+	select IOMMU_API
+	select IOMMU_DMA
+	help
+	  Support for the IOMMU introduced in the Allwinner H6 SoCs.
+
 config TEGRA_IOMMU_GART
 	bool "Tegra GART IOMMU Support"
 	depends on ARCH_TEGRA_2x_SOC

drivers/iommu/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_MTK_IOMMU_V1) += mtk_iommu_v1.o
 obj-$(CONFIG_OMAP_IOMMU) += omap-iommu.o
 obj-$(CONFIG_OMAP_IOMMU_DEBUG) += omap-iommu-debug.o
 obj-$(CONFIG_ROCKCHIP_IOMMU) += rockchip-iommu.o
+obj-$(CONFIG_SUN50I_IOMMU) += sun50i-iommu.o
 obj-$(CONFIG_TEGRA_IOMMU_GART) += tegra-gart.o
 obj-$(CONFIG_TEGRA_IOMMU_SMMU) += tegra-smmu.o
 obj-$(CONFIG_EXYNOS_IOMMU) += exynos-iommu.o

drivers/iommu/amd_iommu.c

@@ -22,7 +22,6 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-iommu.h>
 #include <linux/iommu-helper.h>
-#include <linux/iommu.h>
 #include <linux/delay.h>
 #include <linux/amd-iommu.h>
 #include <linux/notifier.h>
@@ -43,8 +42,7 @@
 #include <asm/gart.h>
 #include <asm/dma.h>
 
-#include "amd_iommu_proto.h"
-#include "amd_iommu_types.h"
+#include "amd_iommu.h"
 #include "irq_remapping.h"
 
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
@@ -71,6 +69,8 @@
  */
 #define AMD_IOMMU_PGSIZES	((~0xFFFUL) & ~(2ULL << 38))
 
+#define DEFAULT_PGTABLE_LEVEL	PAGE_MODE_3_LEVEL
+
 static DEFINE_SPINLOCK(pd_bitmap_lock);
 
 /* List of all available dev_data structures */
@@ -99,7 +99,6 @@ struct iommu_cmd {
 struct kmem_cache *amd_iommu_irq_cache;
 
 static void update_domain(struct protection_domain *domain);
-static int protection_domain_init(struct protection_domain *domain);
 static void detach_device(struct device *dev);
 static void update_and_flush_device_table(struct protection_domain *domain,
 					  struct domain_pgtable *pgtable);
@@ -280,12 +279,6 @@ static struct iommu_dev_data *find_dev_data(u16 devid)
 	return dev_data;
 }
 
-struct iommu_dev_data *get_dev_data(struct device *dev)
-{
-	return dev->archdata.iommu;
-}
-EXPORT_SYMBOL(get_dev_data);
-
 /*
 * Find or create an IOMMU group for a acpihid device.
 */
@@ -314,16 +307,15 @@ static struct iommu_group *acpihid_device_group(struct device *dev)
 static bool pci_iommuv2_capable(struct pci_dev *pdev)
 {
 	static const int caps[] = {
-		PCI_EXT_CAP_ID_ATS,
 		PCI_EXT_CAP_ID_PRI,
 		PCI_EXT_CAP_ID_PASID,
 	};
 	int i, pos;
 
-	if (pci_ats_disabled())
+	if (!pci_ats_supported(pdev))
 		return false;
 
-	for (i = 0; i < 3; ++i) {
+	for (i = 0; i < 2; ++i) {
 		pos = pci_find_ext_capability(pdev, caps[i]);
 		if (pos == 0)
 			return false;
@@ -336,7 +328,7 @@ static bool pdev_pri_erratum(struct pci_dev *pdev, u32 erratum)
 {
 	struct iommu_dev_data *dev_data;
 
-	dev_data = get_dev_data(&pdev->dev);
+	dev_data = dev_iommu_priv_get(&pdev->dev);
 
 	return dev_data->errata & (1 << erratum) ? true : false;
 }
@@ -349,7 +341,7 @@ static bool check_device(struct device *dev)
 {
 	int devid;
 
-	if (!dev || !dev->dma_mask)
+	if (!dev)
 		return false;
 
 	devid = get_device_id(dev);
@@ -366,32 +358,18 @@ static bool check_device(struct device *dev)
 	return true;
 }
 
-static void init_iommu_group(struct device *dev)
-{
-	struct iommu_group *group;
-
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group))
-		return;
-
-	iommu_group_put(group);
-}
-
 static int iommu_init_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
-	struct amd_iommu *iommu;
 	int devid;
 
-	if (dev->archdata.iommu)
+	if (dev_iommu_priv_get(dev))
 		return 0;
 
 	devid = get_device_id(dev);
 	if (devid < 0)
 		return devid;
 
-	iommu = amd_iommu_rlookup_table[devid];
-
 	dev_data = find_dev_data(devid);
 	if (!dev_data)
 		return -ENOMEM;
@@ -412,9 +390,7 @@ static int iommu_init_device(struct device *dev)
 		dev_data->iommu_v2 = iommu->is_iommu_v2;
 	}
 
-	dev->archdata.iommu = dev_data;
-
-	iommu_device_link(&iommu->iommu, dev);
+	dev_iommu_priv_set(dev, dev_data);
 
 	return 0;
 }
@@ -433,31 +409,18 @@ static void iommu_ignore_device(struct device *dev)
 	setup_aliases(dev);
 }
 
-static void iommu_uninit_device(struct device *dev)
+static void amd_iommu_uninit_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
-	struct amd_iommu *iommu;
-	int devid;
 
-	devid = get_device_id(dev);
-	if (devid < 0)
-		return;
-
-	iommu = amd_iommu_rlookup_table[devid];
-
-	dev_data = search_dev_data(devid);
+	dev_data = dev_iommu_priv_get(dev);
 	if (!dev_data)
 		return;
 
 	if (dev_data->domain)
 		detach_device(dev);
 
-	iommu_device_unlink(&iommu->iommu, dev);
-
-	iommu_group_remove_device(dev);
-
-	/* Remove dma-ops */
-	dev->dma_ops = NULL;
+	dev_iommu_priv_set(dev, NULL);
 
 	/*
 	 * We keep dev_data around for unplugged devices and reuse it when the
@@ -521,7 +484,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
 					   devid & 0xff);
 	if (pdev)
-		dev_data = get_dev_data(&pdev->dev);
+		dev_data = dev_iommu_priv_get(&pdev->dev);
 
 	if (dev_data && __ratelimit(&dev_data->rs)) {
 		pci_err(pdev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
@@ -1418,20 +1381,19 @@ static struct page *free_sub_pt(unsigned long root, int mode,
 	return freelist;
 }
 
-static void free_pagetable(struct protection_domain *domain)
+static void free_pagetable(struct domain_pgtable *pgtable)
 {
-	struct domain_pgtable pgtable;
 	struct page *freelist = NULL;
 	unsigned long root;
 
-	amd_iommu_domain_get_pgtable(domain, &pgtable);
-	atomic64_set(&domain->pt_root, 0);
+	if (pgtable->mode == PAGE_MODE_NONE)
+		return;
 
-	BUG_ON(pgtable.mode < PAGE_MODE_NONE ||
-	       pgtable.mode > PAGE_MODE_6_LEVEL);
+	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
+	       pgtable->mode > PAGE_MODE_6_LEVEL);
 
-	root = (unsigned long)pgtable.root;
-	freelist = free_sub_pt(root, pgtable.mode, freelist);
+	root = (unsigned long)pgtable->root;
+	freelist = free_sub_pt(root, pgtable->mode, freelist);
 
 	free_page_list(freelist);
 }
@@ -1844,70 +1806,6 @@ static void free_gcr3_table(struct protection_domain *domain)
 	free_page((unsigned long)domain->gcr3_tbl);
 }
 
-/*
- * Free a domain, only used if something went wrong in the
- * allocation path and we need to free an already allocated page table
- */
-static void dma_ops_domain_free(struct protection_domain *domain)
-{
-	if (!domain)
-		return;
-
-	iommu_put_dma_cookie(&domain->domain);
-
-	free_pagetable(domain);
-
-	if (domain->id)
-		domain_id_free(domain->id);
-
-	kfree(domain);
-}
-
-/*
- * Allocates a new protection domain usable for the dma_ops functions.
- * It also initializes the page table and the address allocator data
- * structures required for the dma_ops interface
- */
-static struct protection_domain *dma_ops_domain_alloc(void)
-{
-	struct protection_domain *domain;
-	u64 *pt_root, root;
-
-	domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL);
-	if (!domain)
-		return NULL;
-
-	if (protection_domain_init(domain))
-		goto free_domain;
-
-	pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-	if (!pt_root)
-		goto free_domain;
-
-	root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL);
-	atomic64_set(&domain->pt_root, root);
-	domain->flags = PD_DMA_OPS_MASK;
-
-	if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM)
-		goto free_domain;
-
-	return domain;
-
-free_domain:
-	dma_ops_domain_free(domain);
-
-	return NULL;
-}
-
-/*
- * little helper function to check whether a given protection domain is a
- * dma_ops domain
- */
-static bool dma_ops_domain(struct protection_domain *domain)
-{
-	return domain->flags & PD_DMA_OPS_MASK;
-}
-
 static void set_dte_entry(u16 devid, struct protection_domain *domain,
 			  struct domain_pgtable *pgtable,
 			  bool ats, bool ppr)
@@ -2119,14 +2017,14 @@ static int pdev_iommuv2_enable(struct pci_dev *pdev)
 static int attach_device(struct device *dev,
 			 struct protection_domain *domain)
 {
-	struct pci_dev *pdev;
 	struct iommu_dev_data *dev_data;
+	struct pci_dev *pdev;
 	unsigned long flags;
 	int ret;
 
 	spin_lock_irqsave(&domain->lock, flags);
 
-	dev_data = get_dev_data(dev);
+	dev_data = dev_iommu_priv_get(dev);
 
 	spin_lock(&dev_data->lock);
 
@@ -2139,8 +2037,10 @@ static int attach_device(struct device *dev,
 
 	pdev = to_pci_dev(dev);
 	if (domain->flags & PD_IOMMUV2_MASK) {
+		struct iommu_domain *def_domain = iommu_get_dma_domain(dev);
+
 		ret = -EINVAL;
-		if (!dev_data->passthrough)
+		if (def_domain->type != IOMMU_DOMAIN_IDENTITY)
 			goto out;
 
 		if (dev_data->iommu_v2) {
@@ -2188,7 +2088,7 @@ static void detach_device(struct device *dev)
 	struct iommu_dev_data *dev_data;
 	unsigned long flags;
 
-	dev_data = get_dev_data(dev);
+	dev_data = dev_iommu_priv_get(dev);
 	domain   = dev_data->domain;
 
 	spin_lock_irqsave(&domain->lock, flags);
@@ -2222,68 +2122,60 @@ static void detach_device(struct device *dev)
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
 
-static int amd_iommu_add_device(struct device *dev)
+static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 {
-	struct iommu_dev_data *dev_data;
-	struct iommu_domain *domain;
+	struct iommu_device *iommu_dev;
 	struct amd_iommu *iommu;
 	int ret, devid;
 
-	if (!check_device(dev) || get_dev_data(dev))
-		return 0;
+	if (!check_device(dev))
+		return ERR_PTR(-ENODEV);
 
 	devid = get_device_id(dev);
 	if (devid < 0)
-		return devid;
+		return ERR_PTR(devid);
 
 	iommu = amd_iommu_rlookup_table[devid];
 
+	if (dev_iommu_priv_get(dev))
+		return &iommu->iommu;
+
 	ret = iommu_init_device(dev);
 	if (ret) {
 		if (ret != -ENOTSUPP)
 			dev_err(dev, "Failed to initialize - trying to proceed anyway\n");
-
+		iommu_dev = ERR_PTR(ret);
 		iommu_ignore_device(dev);
-		dev->dma_ops = NULL;
-		goto out;
+	} else {
+		iommu_dev = &iommu->iommu;
 	}
-	init_iommu_group(dev);
 
-	dev_data = get_dev_data(dev);
+	iommu_completion_wait(iommu);
 
-	BUG_ON(!dev_data);
+	return iommu_dev;
+}
 
-	if (dev_data->iommu_v2)
-		iommu_request_dm_for_dev(dev);
+static void amd_iommu_probe_finalize(struct device *dev)
+{
+	struct iommu_domain *domain;
 
 	/* Domains are initialized for this device - have a look what we ended up with */
 	domain = iommu_get_domain_for_dev(dev);
-	if (domain->type == IOMMU_DOMAIN_IDENTITY)
-		dev_data->passthrough = true;
-	else if (domain->type == IOMMU_DOMAIN_DMA)
+	if (domain->type == IOMMU_DOMAIN_DMA)
 		iommu_setup_dma_ops(dev, IOVA_START_PFN << PAGE_SHIFT, 0);
-
-out:
-	iommu_completion_wait(iommu);
-
-	return 0;
 }
 
-static void amd_iommu_remove_device(struct device *dev)
+static void amd_iommu_release_device(struct device *dev)
 {
+	int devid = get_device_id(dev);
 	struct amd_iommu *iommu;
-	int devid;
 
 	if (!check_device(dev))
 		return;
 
-	devid = get_device_id(dev);
-	if (devid < 0)
-		return;
-
 	iommu = amd_iommu_rlookup_table[devid];
 
-	iommu_uninit_device(dev);
+	amd_iommu_uninit_device(dev);
 	iommu_completion_wait(iommu);
 }
 
@@ -2418,27 +2310,46 @@ static void cleanup_domain(struct protection_domain *domain)
 
 static void protection_domain_free(struct protection_domain *domain)
 {
+	struct domain_pgtable pgtable;
+
 	if (!domain)
 		return;
 
 	if (domain->id)
 		domain_id_free(domain->id);
 
+	amd_iommu_domain_get_pgtable(domain, &pgtable);
+	atomic64_set(&domain->pt_root, 0);
+	free_pagetable(&pgtable);
+
 	kfree(domain);
 }
 
-static int protection_domain_init(struct protection_domain *domain)
+static int protection_domain_init(struct protection_domain *domain, int mode)
 {
+	u64 *pt_root = NULL, root;
+
+	BUG_ON(mode < PAGE_MODE_NONE || mode > PAGE_MODE_6_LEVEL);
+
 	spin_lock_init(&domain->lock);
 	domain->id = domain_id_alloc();
 	if (!domain->id)
 		return -ENOMEM;
 	INIT_LIST_HEAD(&domain->dev_list);
 
+	if (mode != PAGE_MODE_NONE) {
+		pt_root = (void *)get_zeroed_page(GFP_KERNEL);
+		if (!pt_root)
+			return -ENOMEM;
+	}
+
+	root = amd_iommu_domain_encode_pgtable(pt_root, mode);
+	atomic64_set(&domain->pt_root, root);
+
 	return 0;
 }
 
-static struct protection_domain *protection_domain_alloc(void)
+static struct protection_domain *protection_domain_alloc(int mode)
 {
 	struct protection_domain *domain;
 
@@ -2446,7 +2357,7 @@ static struct protection_domain *protection_domain_alloc(void)
 	if (!domain)
 		return NULL;
 
-	if (protection_domain_init(domain))
+	if (protection_domain_init(domain, mode))
 		goto out_err;
 
 	return domain;
@@ -2459,54 +2370,35 @@ static struct protection_domain *protection_domain_alloc(void)
 
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
-	struct protection_domain *pdomain;
-	u64 *pt_root, root;
+	struct protection_domain *domain;
+	int mode = DEFAULT_PGTABLE_LEVEL;
 
-	switch (type) {
-	case IOMMU_DOMAIN_UNMANAGED:
-		pdomain = protection_domain_alloc();
-		if (!pdomain)
-			return NULL;
+	if (type == IOMMU_DOMAIN_IDENTITY)
+		mode = PAGE_MODE_NONE;
 
-		pt_root = (void *)get_zeroed_page(GFP_KERNEL);
-		if (!pt_root) {
-			protection_domain_free(pdomain);
-			return NULL;
-		}
+	domain = protection_domain_alloc(mode);
+	if (!domain)
+		return NULL;
 
-		root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL);
-		atomic64_set(&pdomain->pt_root, root);
+	domain->domain.geometry.aperture_start = 0;
+	domain->domain.geometry.aperture_end   = ~0ULL;
+	domain->domain.geometry.force_aperture = true;
 
-		pdomain->domain.geometry.aperture_start = 0;
-		pdomain->domain.geometry.aperture_end   = ~0ULL;
-		pdomain->domain.geometry.force_aperture = true;
+	if (type == IOMMU_DOMAIN_DMA &&
+	    iommu_get_dma_cookie(&domain->domain) == -ENOMEM)
+		goto free_domain;
 
-		break;
-	case IOMMU_DOMAIN_DMA:
-		pdomain = dma_ops_domain_alloc();
-		if (!pdomain) {
-			pr_err("Failed to allocate\n");
-			return NULL;
-		}
-		break;
-	case IOMMU_DOMAIN_IDENTITY:
-		pdomain = protection_domain_alloc();
-		if (!pdomain)
-			return NULL;
+	return &domain->domain;
 
-		atomic64_set(&pdomain->pt_root, PAGE_MODE_NONE);
-		break;
-	default:
-		return NULL;
-	}
+free_domain:
+	protection_domain_free(domain);
 
-	return &pdomain->domain;
+	return NULL;
 }
 
 static void amd_iommu_domain_free(struct iommu_domain *dom)
 {
 	struct protection_domain *domain;
-	struct domain_pgtable pgtable;
 
 	domain = to_pdomain(dom);
 
@@ -2518,29 +2410,19 @@ static void amd_iommu_domain_free(struct iommu_domain *dom)
 	if (!dom)
 		return;
 
-	switch (dom->type) {
-	case IOMMU_DOMAIN_DMA:
-		/* Now release the domain */
-		dma_ops_domain_free(domain);
-		break;
-	default:
-		amd_iommu_domain_get_pgtable(domain, &pgtable);
-
-		if (pgtable.mode != PAGE_MODE_NONE)
-			free_pagetable(domain);
+	if (dom->type == IOMMU_DOMAIN_DMA)
+		iommu_put_dma_cookie(&domain->domain);
 
-		if (domain->flags & PD_IOMMUV2_MASK)
-			free_gcr3_table(domain);
+	if (domain->flags & PD_IOMMUV2_MASK)
+		free_gcr3_table(domain);
 
-		protection_domain_free(domain);
-		break;
-	}
+	protection_domain_free(domain);
 }
 
 static void amd_iommu_detach_device(struct iommu_domain *dom,
 				    struct device *dev)
 {
-	struct iommu_dev_data *dev_data = dev->archdata.iommu;
+	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
 	struct amd_iommu *iommu;
 	int devid;
 
@@ -2578,7 +2460,7 @@ static int amd_iommu_attach_device(struct iommu_domain *dom,
 	if (!check_device(dev))
 		return -EINVAL;
 
-	dev_data = dev->archdata.iommu;
+	dev_data = dev_iommu_priv_get(dev);
 	dev_data->defer_attach = false;
 
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
@@ -2734,12 +2616,14 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 	list_add_tail(&region->list, head);
 }
 
-static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
-					 struct device *dev)
+bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
+				  struct device *dev)
 {
-	struct iommu_dev_data *dev_data = dev->archdata.iommu;
+	struct iommu_dev_data *dev_data = dev_iommu_priv_get(dev);
+
 	return dev_data->defer_attach;
 }
+EXPORT_SYMBOL_GPL(amd_iommu_is_attach_deferred);
 
 static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 {
@@ -2758,6 +2642,20 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	amd_iommu_flush_iotlb_all(domain);
 }
 
+static int amd_iommu_def_domain_type(struct device *dev)
+{
+	struct iommu_dev_data *dev_data;
+
+	dev_data = dev_iommu_priv_get(dev);
+	if (!dev_data)
+		return 0;
+
+	if (dev_data->iommu_v2)
+		return IOMMU_DOMAIN_IDENTITY;
+
+	return 0;
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -2767,8 +2665,9 @@ const struct iommu_ops amd_iommu_ops = {
 	.map = amd_iommu_map,
 	.unmap = amd_iommu_unmap,
 	.iova_to_phys = amd_iommu_iova_to_phys,
-	.add_device = amd_iommu_add_device,
-	.remove_device = amd_iommu_remove_device,
+	.probe_device = amd_iommu_probe_device,
+	.release_device = amd_iommu_release_device,
+	.probe_finalize = amd_iommu_probe_finalize,
 	.device_group = amd_iommu_device_group,
 	.domain_get_attr = amd_iommu_domain_get_attr,
 	.get_resv_regions = amd_iommu_get_resv_regions,
@@ -2777,6 +2676,7 @@ const struct iommu_ops amd_iommu_ops = {
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
 	.iotlb_sync = amd_iommu_iotlb_sync,
+	.def_domain_type = amd_iommu_def_domain_type,
 };
 
 /*****************************************************************************
@@ -2807,7 +2707,6 @@ void amd_iommu_domain_direct_map(struct iommu_domain *dom)
 	struct protection_domain *domain = to_pdomain(dom);
 	struct domain_pgtable pgtable;
 	unsigned long flags;
-	u64 pt_root;
 
 	spin_lock_irqsave(&domain->lock, flags);
 
@@ -2815,18 +2714,13 @@ void amd_iommu_domain_direct_map(struct iommu_domain *dom)
 	amd_iommu_domain_get_pgtable(domain, &pgtable);
 
 	/* Update data structure */
-	pt_root = amd_iommu_domain_encode_pgtable(NULL, PAGE_MODE_NONE);
-	atomic64_set(&domain->pt_root, pt_root);
+	atomic64_set(&domain->pt_root, 0);
 
 	/* Make changes visible to IOMMUs */
 	update_domain(domain);
 
-	/* Restore old pgtable in domain->ptroot to free page-table */
-	pt_root = amd_iommu_domain_encode_pgtable(pgtable.root, pgtable.mode);
-	atomic64_set(&domain->pt_root, pt_root);
-
 	/* Page-table is not visible to IOMMU anymore, so free it */
-	free_pagetable(domain);
+	free_pagetable(&pgtable);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -3085,7 +2979,7 @@ int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
 	struct amd_iommu *iommu;
 	struct iommu_cmd cmd;
 
-	dev_data = get_dev_data(&pdev->dev);
+	dev_data = dev_iommu_priv_get(&pdev->dev);
 	iommu    = amd_iommu_rlookup_table[dev_data->devid];
 
 	build_complete_ppr(&cmd, dev_data->devid, pasid, status,
@@ -3098,23 +2992,27 @@ EXPORT_SYMBOL(amd_iommu_complete_ppr);
 struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev)
 {
 	struct protection_domain *pdomain;
-	struct iommu_domain *io_domain;
+	struct iommu_dev_data *dev_data;
 	struct device *dev = &pdev->dev;
+	struct iommu_domain *io_domain;
 
 	if (!check_device(dev))
 		return NULL;
 
-	pdomain = get_dev_data(dev)->domain;
-	if (pdomain == NULL && get_dev_data(dev)->defer_attach) {
-		get_dev_data(dev)->defer_attach = false;
-		io_domain = iommu_get_domain_for_dev(dev);
+	dev_data  = dev_iommu_priv_get(&pdev->dev);
+	pdomain   = dev_data->domain;
+	io_domain = iommu_get_domain_for_dev(dev);
+
+	if (pdomain == NULL && dev_data->defer_attach) {
+		dev_data->defer_attach = false;
 		pdomain = to_pdomain(io_domain);
 		attach_device(dev, pdomain);
 	}
+
 	if (pdomain == NULL)
 		return NULL;
 
-	if (!dma_ops_domain(pdomain))
+	if (io_domain->type != IOMMU_DOMAIN_DMA)
 		return NULL;
 
 	/* Only return IOMMUv2 domains */
@@ -3132,7 +3030,7 @@ void amd_iommu_enable_device_erratum(struct pci_dev *pdev, u32 erratum)
 	if (!amd_iommu_v2_supported())
 		return;
 
-	dev_data = get_dev_data(&pdev->dev);
+	dev_data = dev_iommu_priv_get(&pdev->dev);
 	dev_data->errata |= (1 << erratum);
 }
 EXPORT_SYMBOL(amd_iommu_enable_device_erratum);
@@ -3151,11 +3049,8 @@ int amd_iommu_device_info(struct pci_dev *pdev,
 
 	memset(info, 0, sizeof(*info));
 
-	if (!pci_ats_disabled()) {
-		pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ATS);
-		if (pos)
-			info->flags |= AMD_IOMMU_DEVICE_FLAG_ATS_SUP;
-	}
+	if (pci_ats_supported(pdev))
+		info->flags |= AMD_IOMMU_DEVICE_FLAG_ATS_SUP;
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PRI);
 	if (pos)

drivers/iommu/amd_iommu.h

 /* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
 
 #ifndef AMD_IOMMU_H
 #define AMD_IOMMU_H
 
-int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line);
+#include <linux/iommu.h>
+
+#include "amd_iommu_types.h"
+
+extern int amd_iommu_get_num_iommus(void);
+extern int amd_iommu_init_dma_ops(void);
+extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
+extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+extern void amd_iommu_apply_erratum_63(u16 devid);
+extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
+extern int amd_iommu_init_devices(void);
+extern void amd_iommu_uninit_devices(void);
+extern void amd_iommu_init_notifier(void);
+extern int amd_iommu_init_api(void);
+
+#ifdef CONFIG_AMD_IOMMU_DEBUGFS
+void amd_iommu_debugfs_setup(struct amd_iommu *iommu);
+#else
+static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {}
+#endif
+
+/* Needed for interrupt remapping */
+extern int amd_iommu_prepare(void);
+extern int amd_iommu_enable(void);
+extern void amd_iommu_disable(void);
+extern int amd_iommu_reenable(int);
+extern int amd_iommu_enable_faulting(void);
+extern int amd_iommu_guest_ir;
+
+/* IOMMUv2 specific functions */
+struct iommu_domain;
+
+extern bool amd_iommu_v2_supported(void);
+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);
+extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
+extern int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+				u64 address);
+extern int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid);
+extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+				     unsigned long cr3);
+extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
+extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
+
+#ifdef CONFIG_IRQ_REMAP
+extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
+#else
+static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
+{
+	return 0;
+}
+#endif
+
+#define PPR_SUCCESS			0x0
+#define PPR_INVALID			0x1
+#define PPR_FAILURE			0xf
+
+extern int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+				  int status, int tag);
+
+static inline bool is_rd890_iommu(struct pci_dev *pdev)
+{
+	return (pdev->vendor == PCI_VENDOR_ID_ATI) &&
+	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
+}
+
+static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
+{
+	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+		return false;
+
+	return !!(iommu->features & f);
+}
+
+static inline u64 iommu_virt_to_phys(void *vaddr)
+{
+	return (u64)__sme_set(virt_to_phys(vaddr));
+}
+
+static inline void *iommu_phys_to_virt(unsigned long paddr)
+{
+	return phys_to_virt(__sme_clr(paddr));
+}
+
+extern bool translation_pre_enabled(struct amd_iommu *iommu);
+extern bool amd_iommu_is_attach_deferred(struct iommu_domain *domain,
+					 struct device *dev);
+extern int __init add_special_device(u8 type, u8 id, u16 *devid,
+				     bool cmd_line);
 
 #ifdef CONFIG_DMI
 void amd_iommu_apply_ivrs_quirks(void);

drivers/iommu/amd_iommu_debugfs.c

@@ -8,10 +8,9 @@
  */
 
 #include <linux/debugfs.h>
-#include <linux/iommu.h>
 #include <linux/pci.h>
-#include "amd_iommu_proto.h"
-#include "amd_iommu_types.h"
+
+#include "amd_iommu.h"
 
 static struct dentry *amd_iommu_debugfs;
 static DEFINE_MUTEX(amd_iommu_debugfs_lock);

drivers/iommu/amd_iommu_init.c

@@ -18,7 +18,6 @@
 #include <linux/msi.h>
 #include <linux/amd-iommu.h>
 #include <linux/export.h>
-#include <linux/iommu.h>
 #include <linux/kmemleak.h>
 #include <linux/mem_encrypt.h>
 #include <asm/pci-direct.h>
@@ -32,9 +31,8 @@
 #include <asm/irq_remapping.h>
 
 #include <linux/crash_dump.h>
+
 #include "amd_iommu.h"
-#include "amd_iommu_proto.h"
-#include "amd_iommu_types.h"
 #include "irq_remapping.h"
 
 /*

drivers/iommu/amd_iommu_proto.h

-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <jroedel@suse.de>
- */
-
-#ifndef _ASM_X86_AMD_IOMMU_PROTO_H
-#define _ASM_X86_AMD_IOMMU_PROTO_H
-
-#include "amd_iommu_types.h"
-
-extern int amd_iommu_get_num_iommus(void);
-extern int amd_iommu_init_dma_ops(void);
-extern int amd_iommu_init_passthrough(void);
-extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
-extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_apply_erratum_63(u16 devid);
-extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
-extern int amd_iommu_init_devices(void);
-extern void amd_iommu_uninit_devices(void);
-extern void amd_iommu_init_notifier(void);
-extern int amd_iommu_init_api(void);
-
-#ifdef CONFIG_AMD_IOMMU_DEBUGFS
-void amd_iommu_debugfs_setup(struct amd_iommu *iommu);
-#else
-static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {}
-#endif
-
-/* Needed for interrupt remapping */
-extern int amd_iommu_prepare(void);
-extern int amd_iommu_enable(void);
-extern void amd_iommu_disable(void);
-extern int amd_iommu_reenable(int);
-extern int amd_iommu_enable_faulting(void);
-extern int amd_iommu_guest_ir;
-
-/* IOMMUv2 specific functions */
-struct iommu_domain;
-
-extern bool amd_iommu_v2_supported(void);
-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);
-extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
-extern int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
-				u64 address);
-extern int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid);
-extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
-				     unsigned long cr3);
-extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
-extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
-
-#ifdef CONFIG_IRQ_REMAP
-extern int amd_iommu_create_irq_domain(struct amd_iommu *iommu);
-#else
-static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
-{
-	return 0;
-}
-#endif
-
-#define PPR_SUCCESS			0x0
-#define PPR_INVALID			0x1
-#define PPR_FAILURE			0xf
-
-extern int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
-				  int status, int tag);
-
-static inline bool is_rd890_iommu(struct pci_dev *pdev)
-{
-	return (pdev->vendor == PCI_VENDOR_ID_ATI) &&
-	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
-}
-
-static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
-{
-	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
-		return false;
-
-	return !!(iommu->features & f);
-}
-
-static inline u64 iommu_virt_to_phys(void *vaddr)
-{
-	return (u64)__sme_set(virt_to_phys(vaddr));
-}
-
-static inline void *iommu_phys_to_virt(unsigned long paddr)
-{
-	return phys_to_virt(__sme_clr(paddr));
-}
-
-extern bool translation_pre_enabled(struct amd_iommu *iommu);
-extern struct iommu_dev_data *get_dev_data(struct device *dev);
-#endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */

drivers/iommu/amd_iommu_types.h

@@ -395,10 +395,10 @@
 #define PD_IOMMUV2_MASK		(1UL << 3) /* domain has gcr3 table */
 
 extern bool amd_iommu_dump;
-#define DUMP_printk(format, arg...)					\
-	do {								\
-		if (amd_iommu_dump)						\
-			printk(KERN_INFO "AMD-Vi: " format, ## arg);	\
+#define DUMP_printk(format, arg...)				\
+	do {							\
+		if (amd_iommu_dump)				\
+			pr_info("AMD-Vi: " format, ## arg);	\
 	} while(0);
 
 /* global flag if IOMMUs cache non-present entries */
@@ -645,7 +645,6 @@ struct iommu_dev_data {
 	struct pci_dev *pdev;
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
-	bool passthrough;		  /* Device is identity mapped */
 	struct {
 		bool enabled;
 		int qdep;

drivers/iommu/amd_iommu_v2.c

@@ -13,13 +13,11 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
-#include <linux/iommu.h>
 #include <linux/wait.h>
 #include <linux/pci.h>
 #include <linux/gfp.h>
 
-#include "amd_iommu_types.h"
-#include "amd_iommu_proto.h"
+#include "amd_iommu.h"
 
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Joerg Roedel <jroedel@suse.de>");
@@ -517,13 +515,12 @@ static int ppr_notifier(struct notifier_block *nb, unsigned long e, void *data)
 	struct amd_iommu_fault *iommu_fault;
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
+	struct pci_dev *pdev = NULL;
 	unsigned long flags;
 	struct fault *fault;
 	bool finish;
 	u16 tag, devid;
 	int ret;
-	struct iommu_dev_data *dev_data;
-	struct pci_dev *pdev = NULL;
 
 	iommu_fault = data;
 	tag         = iommu_fault->tag & 0x1ff;
@@ -534,12 +531,11 @@ static int ppr_notifier(struct notifier_block *nb, unsigned long e, void *data)
 					   devid & 0xff);
 	if (!pdev)
 		return -ENODEV;
-	dev_data = get_dev_data(&pdev->dev);
 
-	/* In kdump kernel pci dev is not initialized yet -> send INVALID */
 	ret = NOTIFY_DONE;
-	if (translation_pre_enabled(amd_iommu_rlookup_table[devid])
-		&& dev_data->defer_attach) {
+
+	/* In kdump kernel pci dev is not initialized yet -> send INVALID */
+	if (amd_iommu_is_attach_deferred(NULL, &pdev->dev)) {
 		amd_iommu_complete_ppr(pdev, iommu_fault->pasid,
 				       PPR_INVALID, tag);
 		goto out;

drivers/iommu/arm-smmu-impl.c

@@ -150,6 +150,8 @@ static const struct arm_smmu_impl arm_mmu500_impl = {
 
 struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 {
+	const struct device_node *np = smmu->dev->of_node;
+
 	/*
 	 * We will inevitably have to combine model-specific implementation
 	 * quirks with platform-specific integration quirks, but everything
@@ -166,11 +168,11 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
 		break;
 	}
 
-	if (of_property_read_bool(smmu->dev->of_node,
-				  "calxeda,smmu-secure-config-access"))
+	if (of_property_read_bool(np, "calxeda,smmu-secure-config-access"))
 		smmu->impl = &calxeda_impl;
 
-	if (of_device_is_compatible(smmu->dev->of_node, "qcom,sdm845-smmu-500"))
+	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500") ||
+	    of_device_is_compatible(np, "qcom,sc7180-smmu-500"))
 		return qcom_smmu_impl_init(smmu);
 
 	return smmu;

drivers/iommu/arm-smmu-qcom.c

@@ -3,6 +3,7 @@
  * Copyright (c) 2019, The Linux Foundation. All rights reserved.
  */
 
+#include <linux/of_device.h>
 #include <linux/qcom_scm.h>
 
 #include "arm-smmu.h"
@@ -11,12 +12,29 @@ struct qcom_smmu {
 	struct arm_smmu_device smmu;
 };
 
+static const struct of_device_id qcom_smmu_client_of_match[] = {
+	{ .compatible = "qcom,adreno" },
+	{ .compatible = "qcom,mdp4" },
+	{ .compatible = "qcom,mdss" },
+	{ .compatible = "qcom,sc7180-mdss" },
+	{ .compatible = "qcom,sc7180-mss-pil" },
+	{ .compatible = "qcom,sdm845-mdss" },
+	{ .compatible = "qcom,sdm845-mss-pil" },
+	{ }
+};
+
+static int qcom_smmu_def_domain_type(struct device *dev)
+{
+	const struct of_device_id *match =
+		of_match_device(qcom_smmu_client_of_match, dev);
+
+	return match ? IOMMU_DOMAIN_IDENTITY : 0;
+}
+
 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,
@@ -30,8 +48,21 @@ static int qcom_sdm845_smmu500_reset(struct arm_smmu_device *smmu)
 	return ret;
 }
 
+static int qcom_smmu500_reset(struct arm_smmu_device *smmu)
+{
+	const struct device_node *np = smmu->dev->of_node;
+
+	arm_mmu500_reset(smmu);
+
+	if (of_device_is_compatible(np, "qcom,sdm845-smmu-500"))
+		return qcom_sdm845_smmu500_reset(smmu);
+
+	return 0;
+}
+
 static const struct arm_smmu_impl qcom_smmu_impl = {
-	.reset = qcom_sdm845_smmu500_reset,
+	.def_domain_type = qcom_smmu_def_domain_type,
+	.reset = qcom_smmu500_reset,
 };
 
 struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)

drivers/iommu/arm-smmu-v3.c

@@ -171,6 +171,8 @@
 #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)
@@ -628,6 +630,7 @@ struct arm_smmu_strtab_cfg {
 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)
@@ -664,7 +667,6 @@ struct arm_smmu_device {
 
 #define ARM_SMMU_MAX_ASIDS		(1 << 16)
 	unsigned int			asid_bits;
-	DECLARE_BITMAP(asid_map, ARM_SMMU_MAX_ASIDS);
 
 #define ARM_SMMU_MAX_VMIDS		(1 << 16)
 	unsigned int			vmid_bits;
@@ -724,6 +726,8 @@ struct arm_smmu_option_prop {
 	const char *prop;
 };
 
+static DEFINE_XARRAY_ALLOC1(asid_xa);
+
 static struct arm_smmu_option_prop arm_smmu_options[] = {
 	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
 	{ ARM_SMMU_OPT_PAGE0_REGS_ONLY, "cavium,cn9900-broken-page1-regspace"},
@@ -733,9 +737,8 @@ static struct arm_smmu_option_prop arm_smmu_options[] = {
 static inline void __iomem *arm_smmu_page1_fixup(unsigned long offset,
 						 struct arm_smmu_device *smmu)
 {
-	if ((offset > SZ_64K) &&
-	    (smmu->options & ARM_SMMU_OPT_PAGE0_REGS_ONLY))
-		offset -= SZ_64K;
+	if (offset > SZ_64K)
+		return smmu->page1 + offset - SZ_64K;
 
 	return smmu->base + offset;
 }
@@ -1763,6 +1766,14 @@ 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)
+{
+	if (!cd->asid)
+		return;
+
+	xa_erase(&asid_xa, cd->asid);
+}
+
 /* Stream table manipulation functions */
 static void
 arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc)
@@ -2448,10 +2459,9 @@ 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;
 
-		if (cfg->cdcfg.cdtab) {
+		if (cfg->cdcfg.cdtab)
 			arm_smmu_free_cd_tables(smmu_domain);
-			arm_smmu_bitmap_free(smmu->asid_map, cfg->cd.asid);
-		}
+		arm_smmu_free_asid(&cfg->cd);
 	} else {
 		struct arm_smmu_s2_cfg *cfg = &smmu_domain->s2_cfg;
 		if (cfg->vmid)
@@ -2466,14 +2476,15 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	int ret;
-	int asid;
+	u32 asid;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	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;
 
-	asid = arm_smmu_bitmap_alloc(smmu->asid_map, smmu->asid_bits);
-	if (asid < 0)
-		return asid;
+	ret = xa_alloc(&asid_xa, &asid, &cfg->cd,
+		       XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL);
+	if (ret)
+		return ret;
 
 	cfg->s1cdmax = master->ssid_bits;
 
@@ -2506,7 +2517,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 out_free_cd_tables:
 	arm_smmu_free_cd_tables(smmu_domain);
 out_free_asid:
-	arm_smmu_bitmap_free(smmu->asid_map, asid);
+	arm_smmu_free_asid(&cfg->cd);
 	return ret;
 }
 
@@ -2652,26 +2663,20 @@ static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master)
 	}
 }
 
-#ifdef CONFIG_PCI_ATS
 static bool arm_smmu_ats_supported(struct arm_smmu_master *master)
 {
-	struct pci_dev *pdev;
+	struct device *dev = master->dev;
 	struct arm_smmu_device *smmu = master->smmu;
-	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(master->dev);
+	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 
-	if (!(smmu->features & ARM_SMMU_FEAT_ATS) || !dev_is_pci(master->dev) ||
-	    !(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS) || pci_ats_disabled())
+	if (!(smmu->features & ARM_SMMU_FEAT_ATS))
 		return false;
 
-	pdev = to_pci_dev(master->dev);
-	return !pdev->untrusted && pdev->ats_cap;
-}
-#else
-static bool arm_smmu_ats_supported(struct arm_smmu_master *master)
-{
-	return false;
+	if (!(fwspec->flags & IOMMU_FWSPEC_PCI_RC_ATS))
+		return false;
+
+	return dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev));
 }
-#endif
 
 static void arm_smmu_enable_ats(struct arm_smmu_master *master)
 {
@@ -2914,27 +2919,26 @@ static bool arm_smmu_sid_in_range(struct arm_smmu_device *smmu, u32 sid)
 
 static struct iommu_ops arm_smmu_ops;
 
-static int arm_smmu_add_device(struct device *dev)
+static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 {
 	int i, ret;
 	struct arm_smmu_device *smmu;
 	struct arm_smmu_master *master;
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
-	struct iommu_group *group;
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 
 	if (WARN_ON_ONCE(dev_iommu_priv_get(dev)))
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
 	smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	if (!smmu)
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 
 	master = kzalloc(sizeof(*master), GFP_KERNEL);
 	if (!master)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	master->dev = dev;
 	master->smmu = smmu;
@@ -2975,43 +2979,24 @@ static int arm_smmu_add_device(struct device *dev)
 		master->ssid_bits = min_t(u8, master->ssid_bits,
 					  CTXDESC_LINEAR_CDMAX);
 
-	ret = iommu_device_link(&smmu->iommu, dev);
-	if (ret)
-		goto err_disable_pasid;
-
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group)) {
-		ret = PTR_ERR(group);
-		goto err_unlink;
-	}
+	return &smmu->iommu;
 
-	iommu_group_put(group);
-	return 0;
-
-err_unlink:
-	iommu_device_unlink(&smmu->iommu, dev);
-err_disable_pasid:
-	arm_smmu_disable_pasid(master);
 err_free_master:
 	kfree(master);
 	dev_iommu_priv_set(dev, NULL);
-	return ret;
+	return ERR_PTR(ret);
 }
 
-static void arm_smmu_remove_device(struct device *dev)
+static void arm_smmu_release_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct arm_smmu_master *master;
-	struct arm_smmu_device *smmu;
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return;
 
 	master = dev_iommu_priv_get(dev);
-	smmu = master->smmu;
 	arm_smmu_detach_dev(master);
-	iommu_group_remove_device(dev);
-	iommu_device_unlink(&smmu->iommu, dev);
 	arm_smmu_disable_pasid(master);
 	kfree(master);
 	iommu_fwspec_free(dev);
@@ -3138,8 +3123,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
 	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
-	.add_device		= arm_smmu_add_device,
-	.remove_device		= arm_smmu_remove_device,
+	.probe_device		= arm_smmu_probe_device,
+	.release_device		= arm_smmu_release_device,
 	.device_group		= arm_smmu_device_group,
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
@@ -4021,6 +4006,18 @@ err_reset_pci_ops: __maybe_unused;
 	return err;
 }
 
+static void __iomem *arm_smmu_ioremap(struct device *dev, resource_size_t start,
+				      resource_size_t size)
+{
+	struct resource res = {
+		.flags = IORESOURCE_MEM,
+		.start = start,
+		.end = start + size - 1,
+	};
+
+	return devm_ioremap_resource(dev, &res);
+}
+
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	int irq, ret;
@@ -4056,10 +4053,23 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 	}
 	ioaddr = res->start;
 
-	smmu->base = devm_ioremap_resource(dev, res);
+	/*
+	 * Don't map the IMPLEMENTATION DEFINED regions, since they may contain
+	 * the PMCG registers which are reserved by the PMU driver.
+	 */
+	smmu->base = arm_smmu_ioremap(dev, ioaddr, ARM_SMMU_REG_SZ);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
 
+	if (arm_smmu_resource_size(smmu) > SZ_64K) {
+		smmu->page1 = arm_smmu_ioremap(dev, ioaddr + SZ_64K,
+					       ARM_SMMU_REG_SZ);
+		if (IS_ERR(smmu->page1))
+			return PTR_ERR(smmu->page1);
+	} else {
+		smmu->page1 = smmu->base;
+	}
+
 	/* Interrupt lines */
 
 	irq = platform_get_irq_byname_optional(pdev, "combined");

drivers/iommu/arm-smmu.c

@@ -220,7 +220,7 @@ static int arm_smmu_register_legacy_master(struct device *dev,
  * With the legacy DT binding in play, we have no guarantees about
  * probe order, but then we're also not doing default domains, so we can
  * delay setting bus ops until we're sure every possible SMMU is ready,
- * and that way ensure that no add_device() calls get missed.
+ * and that way ensure that no probe_device() calls get missed.
  */
 static int arm_smmu_legacy_bus_init(void)
 {
@@ -1062,7 +1062,6 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
 	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
 	struct arm_smmu_device *smmu = cfg->smmu;
 	struct arm_smmu_smr *smrs = smmu->smrs;
-	struct iommu_group *group;
 	int i, idx, ret;
 
 	mutex_lock(&smmu->stream_map_mutex);
@@ -1090,18 +1089,9 @@ static int arm_smmu_master_alloc_smes(struct device *dev)
 		cfg->smendx[i] = (s16)idx;
 	}
 
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group)) {
-		ret = PTR_ERR(group);
-		goto out_err;
-	}
-	iommu_group_put(group);
-
 	/* It worked! Now, poke the actual hardware */
-	for_each_cfg_sme(cfg, fwspec, i, idx) {
+	for_each_cfg_sme(cfg, fwspec, i, idx)
 		arm_smmu_write_sme(smmu, idx);
-		smmu->s2crs[idx].group = group;
-	}
 
 	mutex_unlock(&smmu->stream_map_mutex);
 	return 0;
@@ -1172,7 +1162,7 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 
 	/*
 	 * FIXME: The arch/arm DMA API code tries to attach devices to its own
-	 * domains between of_xlate() and add_device() - we have no way to cope
+	 * domains between of_xlate() and probe_device() - we have no way to cope
 	 * with that, so until ARM gets converted to rely on groups and default
 	 * domains, just say no (but more politely than by dereferencing NULL).
 	 * This should be at least a WARN_ON once that's sorted.
@@ -1382,7 +1372,7 @@ struct arm_smmu_device *arm_smmu_get_by_fwnode(struct fwnode_handle *fwnode)
 	return dev ? dev_get_drvdata(dev) : NULL;
 }
 
-static int arm_smmu_add_device(struct device *dev)
+static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 {
 	struct arm_smmu_device *smmu = NULL;
 	struct arm_smmu_master_cfg *cfg;
@@ -1403,7 +1393,7 @@ static int arm_smmu_add_device(struct device *dev)
 	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
 		smmu = arm_smmu_get_by_fwnode(fwspec->iommu_fwnode);
 	} else {
-		return -ENODEV;
+		return ERR_PTR(-ENODEV);
 	}
 
 	ret = -EINVAL;
@@ -1444,21 +1434,19 @@ static int arm_smmu_add_device(struct device *dev)
 	if (ret)
 		goto out_cfg_free;
 
-	iommu_device_link(&smmu->iommu, dev);
-
 	device_link_add(dev, smmu->dev,
 			DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_SUPPLIER);
 
-	return 0;
+	return &smmu->iommu;
 
 out_cfg_free:
 	kfree(cfg);
 out_free:
 	iommu_fwspec_free(dev);
-	return ret;
+	return ERR_PTR(ret);
 }
 
-static void arm_smmu_remove_device(struct device *dev)
+static void arm_smmu_release_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
 	struct arm_smmu_master_cfg *cfg;
@@ -1475,13 +1463,11 @@ static void arm_smmu_remove_device(struct device *dev)
 	if (ret < 0)
 		return;
 
-	iommu_device_unlink(&smmu->iommu, dev);
 	arm_smmu_master_free_smes(cfg, fwspec);
 
 	arm_smmu_rpm_put(smmu);
 
 	dev_iommu_priv_set(dev, NULL);
-	iommu_group_remove_device(dev);
 	kfree(cfg);
 	iommu_fwspec_free(dev);
 }
@@ -1512,6 +1498,11 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
 	else
 		group = generic_device_group(dev);
 
+	/* Remember group for faster lookups */
+	if (!IS_ERR(group))
+		for_each_cfg_sme(cfg, fwspec, i, idx)
+			smmu->s2crs[idx].group = group;
+
 	return group;
 }
 
@@ -1618,6 +1609,17 @@ static void arm_smmu_get_resv_regions(struct device *dev,
 	iommu_dma_get_resv_regions(dev, head);
 }
 
+static int arm_smmu_def_domain_type(struct device *dev)
+{
+	struct arm_smmu_master_cfg *cfg = dev_iommu_priv_get(dev);
+	const struct arm_smmu_impl *impl = cfg->smmu->impl;
+
+	if (impl && impl->def_domain_type)
+		return impl->def_domain_type(dev);
+
+	return 0;
+}
+
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -1628,14 +1630,15 @@ static struct iommu_ops arm_smmu_ops = {
 	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
 	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
-	.add_device		= arm_smmu_add_device,
-	.remove_device		= arm_smmu_remove_device,
+	.probe_device		= arm_smmu_probe_device,
+	.release_device		= arm_smmu_release_device,
 	.device_group		= arm_smmu_device_group,
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
 	.get_resv_regions	= arm_smmu_get_resv_regions,
 	.put_resv_regions	= generic_iommu_put_resv_regions,
+	.def_domain_type	= arm_smmu_def_domain_type,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -2253,7 +2256,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
 		return -ENODEV;
 
 	if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS))
-		dev_err(&pdev->dev, "removing device with active domains!\n");
+		dev_notice(&pdev->dev, "disabling translation\n");
 
 	arm_smmu_bus_init(NULL);
 	iommu_device_unregister(&smmu->iommu);

drivers/iommu/arm-smmu.h

@@ -386,6 +386,7 @@ struct arm_smmu_impl {
 	int (*init_context)(struct arm_smmu_domain *smmu_domain);
 	void (*tlb_sync)(struct arm_smmu_device *smmu, int page, int sync,
 			 int status);
+	int (*def_domain_type)(struct device *dev);
 };
 
 static inline void __iomem *arm_smmu_page(struct arm_smmu_device *smmu, int n)

drivers/iommu/dmar.c

@@ -963,6 +963,7 @@ static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
 		warn_invalid_dmar(phys_addr, " returns all ones");
 		goto unmap;
 	}
+	iommu->vccap = dmar_readq(iommu->reg + DMAR_VCCAP_REG);
 
 	/* the registers might be more than one page */
 	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
@@ -1156,12 +1157,11 @@ static inline void reclaim_free_desc(struct q_inval *qi)
 	}
 }
 
-static int qi_check_fault(struct intel_iommu *iommu, int index)
+static int qi_check_fault(struct intel_iommu *iommu, int index, int wait_index)
 {
 	u32 fault;
 	int head, tail;
 	struct q_inval *qi = iommu->qi;
-	int wait_index = (index + 1) % QI_LENGTH;
 	int shift = qi_shift(iommu);
 
 	if (qi->desc_status[wait_index] == QI_ABORT)
@@ -1224,17 +1224,21 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
 }
 
 /*
- * Submit the queued invalidation descriptor to the remapping
- * hardware unit and wait for its completion.
+ * Function to submit invalidation descriptors of all types to the queued
+ * invalidation interface(QI). Multiple descriptors can be submitted at a
+ * time, a wait descriptor will be appended to each submission to ensure
+ * hardware has completed the invalidation before return. Wait descriptors
+ * can be part of the submission but it will not be polled for completion.
  */
-int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
+int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
+		   unsigned int count, unsigned long options)
 {
-	int rc;
 	struct q_inval *qi = iommu->qi;
-	int offset, shift, length;
 	struct qi_desc wait_desc;
 	int wait_index, index;
 	unsigned long flags;
+	int offset, shift;
+	int rc, i;
 
 	if (!qi)
 		return 0;
@@ -1243,32 +1247,41 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
 	rc = 0;
 
 	raw_spin_lock_irqsave(&qi->q_lock, flags);
-	while (qi->free_cnt < 3) {
+	/*
+	 * Check if we have enough empty slots in the queue to submit,
+	 * the calculation is based on:
+	 * # of desc + 1 wait desc + 1 space between head and tail
+	 */
+	while (qi->free_cnt < count + 2) {
 		raw_spin_unlock_irqrestore(&qi->q_lock, flags);
 		cpu_relax();
 		raw_spin_lock_irqsave(&qi->q_lock, flags);
 	}
 
 	index = qi->free_head;
-	wait_index = (index + 1) % QI_LENGTH;
+	wait_index = (index + count) % QI_LENGTH;
 	shift = qi_shift(iommu);
-	length = 1 << shift;
 
-	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
+	for (i = 0; i < count; i++) {
+		offset = ((index + i) % QI_LENGTH) << shift;
+		memcpy(qi->desc + offset, &desc[i], 1 << shift);
+		qi->desc_status[(index + i) % QI_LENGTH] = QI_IN_USE;
+	}
+	qi->desc_status[wait_index] = QI_IN_USE;
 
-	offset = index << shift;
-	memcpy(qi->desc + offset, desc, length);
 	wait_desc.qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
 			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
+	if (options & QI_OPT_WAIT_DRAIN)
+		wait_desc.qw0 |= QI_IWD_PRQ_DRAIN;
 	wait_desc.qw1 = virt_to_phys(&qi->desc_status[wait_index]);
 	wait_desc.qw2 = 0;
 	wait_desc.qw3 = 0;
 
 	offset = wait_index << shift;
-	memcpy(qi->desc + offset, &wait_desc, length);
+	memcpy(qi->desc + offset, &wait_desc, 1 << shift);
 
-	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
-	qi->free_cnt -= 2;
+	qi->free_head = (qi->free_head + count + 1) % QI_LENGTH;
+	qi->free_cnt -= count + 1;
 
 	/*
 	 * update the HW tail register indicating the presence of
@@ -1284,7 +1297,7 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
 		 * a deadlock where the interrupt context can wait indefinitely
 		 * for free slots in the queue.
 		 */
-		rc = qi_check_fault(iommu, index);
+		rc = qi_check_fault(iommu, index, wait_index);
 		if (rc)
 			break;
 
@@ -1293,7 +1306,8 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
 		raw_spin_lock(&qi->q_lock);
 	}
 
-	qi->desc_status[index] = QI_DONE;
+	for (i = 0; i < count; i++)
+		qi->desc_status[(index + i) % QI_LENGTH] = QI_DONE;
 
 	reclaim_free_desc(qi);
 	raw_spin_unlock_irqrestore(&qi->q_lock, flags);
@@ -1317,7 +1331,7 @@ void qi_global_iec(struct intel_iommu *iommu)
 	desc.qw3 = 0;
 
 	/* should never fail */
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
@@ -1331,7 +1345,7 @@ void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
@@ -1355,7 +1369,7 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
@@ -1377,7 +1391,7 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 /* PASID-based IOTLB invalidation */
@@ -1418,7 +1432,46 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr,
 				QI_EIOTLB_AM(mask);
 	}
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+/* PASID-based device IOTLB Invalidate */
+void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
+			      u32 pasid,  u16 qdep, u64 addr,
+			      unsigned int size_order, u64 granu)
+{
+	unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1);
+	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+
+	desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) |
+		QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE |
+		QI_DEV_IOTLB_PFSID(pfsid);
+	desc.qw1 = QI_DEV_EIOTLB_GLOB(granu);
+
+	/*
+	 * If S bit is 0, we only flush a single page. If S bit is set,
+	 * The least significant zero bit indicates the invalidation address
+	 * range. VT-d spec 6.5.2.6.
+	 * e.g. address bit 12[0] indicates 8KB, 13[0] indicates 16KB.
+	 * size order = 0 is PAGE_SIZE 4KB
+	 * Max Invs Pending (MIP) is set to 0 for now until we have DIT in
+	 * ECAP.
+	 */
+	desc.qw1 |= addr & ~mask;
+	if (size_order)
+		desc.qw1 |= QI_DEV_EIOTLB_SIZE;
+
+	qi_submit_sync(iommu, &desc, 1, 0);
+}
+
+void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did,
+			  u64 granu, int pasid)
+{
+	struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
+
+	desc.qw0 = QI_PC_PASID(pasid) | QI_PC_DID(did) |
+			QI_PC_GRAN(granu) | QI_PC_TYPE;
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 /*

drivers/iommu/exynos-iommu.c

@@ -1235,19 +1235,13 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain,
 	return phys;
 }
 
-static int exynos_iommu_add_device(struct device *dev)
+static struct iommu_device *exynos_iommu_probe_device(struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	struct sysmmu_drvdata *data;
-	struct iommu_group *group;
 
 	if (!has_sysmmu(dev))
-		return -ENODEV;
-
-	group = iommu_group_get_for_dev(dev);
-
-	if (IS_ERR(group))
-		return PTR_ERR(group);
+		return ERR_PTR(-ENODEV);
 
 	list_for_each_entry(data, &owner->controllers, owner_node) {
 		/*
@@ -1259,12 +1253,15 @@ static int exynos_iommu_add_device(struct device *dev)
 					     DL_FLAG_STATELESS |
 					     DL_FLAG_PM_RUNTIME);
 	}
-	iommu_group_put(group);
 
-	return 0;
+	/* There is always at least one entry, see exynos_iommu_of_xlate() */
+	data = list_first_entry(&owner->controllers,
+				struct sysmmu_drvdata, owner_node);
+
+	return &data->iommu;
 }
 
-static void exynos_iommu_remove_device(struct device *dev)
+static void exynos_iommu_release_device(struct device *dev)
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	struct sysmmu_drvdata *data;
@@ -1282,7 +1279,6 @@ static void exynos_iommu_remove_device(struct device *dev)
 			iommu_group_put(group);
 		}
 	}
-	iommu_group_remove_device(dev);
 
 	list_for_each_entry(data, &owner->controllers, owner_node)
 		device_link_del(data->link);
@@ -1331,8 +1327,8 @@ static const struct iommu_ops exynos_iommu_ops = {
 	.unmap = exynos_iommu_unmap,
 	.iova_to_phys = exynos_iommu_iova_to_phys,
 	.device_group = generic_device_group,
-	.add_device = exynos_iommu_add_device,
-	.remove_device = exynos_iommu_remove_device,
+	.probe_device = exynos_iommu_probe_device,
+	.release_device = exynos_iommu_release_device,
 	.pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE,
 	.of_xlate = exynos_iommu_of_xlate,
 };

drivers/iommu/fsl_pamu_domain.c

@@ -1016,25 +1016,13 @@ static struct iommu_group *fsl_pamu_device_group(struct device *dev)
 	return group;
 }
 
-static int fsl_pamu_add_device(struct device *dev)
+static struct iommu_device *fsl_pamu_probe_device(struct device *dev)
 {
-	struct iommu_group *group;
-
-	group = iommu_group_get_for_dev(dev);
-	if (IS_ERR(group))
-		return PTR_ERR(group);
-
-	iommu_group_put(group);
-
-	iommu_device_link(&pamu_iommu, dev);
-
-	return 0;
+	return &pamu_iommu;
 }
 
-static void fsl_pamu_remove_device(struct device *dev)
+static void fsl_pamu_release_device(struct device *dev)
 {
-	iommu_device_unlink(&pamu_iommu, dev);
-	iommu_group_remove_device(dev);
 }
 
 static const struct iommu_ops fsl_pamu_ops = {
@@ -1048,8 +1036,8 @@ static const struct iommu_ops fsl_pamu_ops = {
 	.iova_to_phys	= fsl_pamu_iova_to_phys,
 	.domain_set_attr = fsl_pamu_set_domain_attr,
 	.domain_get_attr = fsl_pamu_get_domain_attr,
-	.add_device	= fsl_pamu_add_device,
-	.remove_device	= fsl_pamu_remove_device,
+	.probe_device	= fsl_pamu_probe_device,
+	.release_device	= fsl_pamu_release_device,
 	.device_group   = fsl_pamu_device_group,
 };
 

drivers/iommu/hyperv-iommu.c

@@ -131,7 +131,7 @@ static int hyperv_irq_remapping_activate(struct irq_domain *domain,
 	return 0;
 }
 
-static struct irq_domain_ops hyperv_ir_domain_ops = {
+static const struct irq_domain_ops hyperv_ir_domain_ops = {
 	.alloc = hyperv_irq_remapping_alloc,
 	.free = hyperv_irq_remapping_free,
 	.activate = hyperv_irq_remapping_activate,

drivers/iommu/intel-iommu-debugfs.c

@@ -372,6 +372,66 @@ static int domain_translation_struct_show(struct seq_file *m, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(domain_translation_struct);
 
+static void invalidation_queue_entry_show(struct seq_file *m,
+					  struct intel_iommu *iommu)
+{
+	int index, shift = qi_shift(iommu);
+	struct qi_desc *desc;
+	int offset;
+
+	if (ecap_smts(iommu->ecap))
+		seq_puts(m, "Index\t\tqw0\t\t\tqw1\t\t\tqw2\t\t\tqw3\t\t\tstatus\n");
+	else
+		seq_puts(m, "Index\t\tqw0\t\t\tqw1\t\t\tstatus\n");
+
+	for (index = 0; index < QI_LENGTH; index++) {
+		offset = index << shift;
+		desc = iommu->qi->desc + offset;
+		if (ecap_smts(iommu->ecap))
+			seq_printf(m, "%5d\t%016llx\t%016llx\t%016llx\t%016llx\t%016x\n",
+				   index, desc->qw0, desc->qw1,
+				   desc->qw2, desc->qw3,
+				   iommu->qi->desc_status[index]);
+		else
+			seq_printf(m, "%5d\t%016llx\t%016llx\t%016x\n",
+				   index, desc->qw0, desc->qw1,
+				   iommu->qi->desc_status[index]);
+	}
+}
+
+static int invalidation_queue_show(struct seq_file *m, void *unused)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	unsigned long flags;
+	struct q_inval *qi;
+	int shift;
+
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		qi = iommu->qi;
+		shift = qi_shift(iommu);
+
+		if (!qi || !ecap_qis(iommu->ecap))
+			continue;
+
+		seq_printf(m, "Invalidation queue on IOMMU: %s\n", iommu->name);
+
+		raw_spin_lock_irqsave(&qi->q_lock, flags);
+		seq_printf(m, " Base: 0x%llx\tHead: %lld\tTail: %lld\n",
+			   (u64)virt_to_phys(qi->desc),
+			   dmar_readq(iommu->reg + DMAR_IQH_REG) >> shift,
+			   dmar_readq(iommu->reg + DMAR_IQT_REG) >> shift);
+		invalidation_queue_entry_show(m, iommu);
+		raw_spin_unlock_irqrestore(&qi->q_lock, flags);
+		seq_putc(m, '\n');
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(invalidation_queue);
+
 #ifdef CONFIG_IRQ_REMAP
 static void ir_tbl_remap_entry_show(struct seq_file *m,
 				    struct intel_iommu *iommu)
@@ -490,6 +550,8 @@ void __init intel_iommu_debugfs_init(void)
 	debugfs_create_file("domain_translation_struct", 0444,
 			    intel_iommu_debug, NULL,
 			    &domain_translation_struct_fops);
+	debugfs_create_file("invalidation_queue", 0444, intel_iommu_debug,
+			    NULL, &invalidation_queue_fops);
 #ifdef CONFIG_IRQ_REMAP
 	debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug,
 			    NULL, &ir_translation_struct_fops);

drivers/iommu/intel-pasid.c

@@ -27,6 +27,63 @@
 static DEFINE_SPINLOCK(pasid_lock);
 u32 intel_pasid_max_id = PASID_MAX;
 
+int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
+{
+	unsigned long flags;
+	u8 status_code;
+	int ret = 0;
+	u64 res;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	dmar_writeq(iommu->reg + DMAR_VCMD_REG, VCMD_CMD_ALLOC);
+	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
+		      !(res & VCMD_VRSP_IP), res);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	status_code = VCMD_VRSP_SC(res);
+	switch (status_code) {
+	case VCMD_VRSP_SC_SUCCESS:
+		*pasid = VCMD_VRSP_RESULT_PASID(res);
+		break;
+	case VCMD_VRSP_SC_NO_PASID_AVAIL:
+		pr_info("IOMMU: %s: No PASID available\n", iommu->name);
+		ret = -ENOSPC;
+		break;
+	default:
+		ret = -ENODEV;
+		pr_warn("IOMMU: %s: Unexpected error code %d\n",
+			iommu->name, status_code);
+	}
+
+	return ret;
+}
+
+void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid)
+{
+	unsigned long flags;
+	u8 status_code;
+	u64 res;
+
+	raw_spin_lock_irqsave(&iommu->register_lock, flags);
+	dmar_writeq(iommu->reg + DMAR_VCMD_REG,
+		    VCMD_CMD_OPERAND(pasid) | VCMD_CMD_FREE);
+	IOMMU_WAIT_OP(iommu, DMAR_VCRSP_REG, dmar_readq,
+		      !(res & VCMD_VRSP_IP), res);
+	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
+
+	status_code = VCMD_VRSP_SC(res);
+	switch (status_code) {
+	case VCMD_VRSP_SC_SUCCESS:
+		break;
+	case VCMD_VRSP_SC_INVALID_PASID:
+		pr_info("IOMMU: %s: Invalid PASID\n", iommu->name);
+		break;
+	default:
+		pr_warn("IOMMU: %s: Unexpected error code %d\n",
+			iommu->name, status_code);
+	}
+}
+
 /*
  * Per device pasid table management:
  */
@@ -94,7 +151,7 @@ int intel_pasid_alloc_table(struct device *dev)
 	int size;
 
 	might_sleep();
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table))
 		return -EINVAL;
 
@@ -141,7 +198,7 @@ void intel_pasid_free_table(struct device *dev)
 	struct pasid_entry *table;
 	int i, max_pde;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info || !dev_is_pci(dev) || !info->pasid_table)
 		return;
 
@@ -167,7 +224,7 @@ struct pasid_table *intel_pasid_get_table(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info)
 		return NULL;
 
@@ -178,7 +235,7 @@ int intel_pasid_get_dev_max_id(struct device *dev)
 {
 	struct device_domain_info *info;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info || !info->pasid_table)
 		return 0;
 
@@ -199,7 +256,7 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
 		return NULL;
 
 	dir = pasid_table->table;
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	dir_index = pasid >> PASID_PDE_SHIFT;
 	index = pasid & PASID_PTE_MASK;
 
@@ -235,7 +292,20 @@ static inline void pasid_clear_entry(struct pasid_entry *pe)
 	WRITE_ONCE(pe->val[7], 0);
 }
 
-static void intel_pasid_clear_entry(struct device *dev, int pasid)
+static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
+{
+	WRITE_ONCE(pe->val[0], PASID_PTE_FPD);
+	WRITE_ONCE(pe->val[1], 0);
+	WRITE_ONCE(pe->val[2], 0);
+	WRITE_ONCE(pe->val[3], 0);
+	WRITE_ONCE(pe->val[4], 0);
+	WRITE_ONCE(pe->val[5], 0);
+	WRITE_ONCE(pe->val[6], 0);
+	WRITE_ONCE(pe->val[7], 0);
+}
+
+static void
+intel_pasid_clear_entry(struct device *dev, int pasid, bool fault_ignore)
 {
 	struct pasid_entry *pe;
 
@@ -243,7 +313,10 @@ static void intel_pasid_clear_entry(struct device *dev, int pasid)
 	if (WARN_ON(!pe))
 		return;
 
-	pasid_clear_entry(pe);
+	if (fault_ignore && pasid_pte_is_present(pe))
+		pasid_clear_entry_with_fpd(pe);
+	else
+		pasid_clear_entry(pe);
 }
 
 static inline void pasid_set_bits(u64 *ptr, u64 mask, u64 bits)
@@ -359,18 +432,29 @@ pasid_set_flpm(struct pasid_entry *pe, u64 value)
 	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
 }
 
+/*
+ * Setup the Extended Access Flag Enable (EAFE) field (Bit 135)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_eafe(struct pasid_entry *pe)
+{
+	pasid_set_bits(&pe->val[2], 1 << 7, 1 << 7);
+}
+
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, int pasid)
 {
 	struct qi_desc desc;
 
-	desc.qw0 = QI_PC_DID(did) | QI_PC_PASID_SEL | QI_PC_PASID(pasid);
+	desc.qw0 = QI_PC_DID(did) | QI_PC_GRAN(QI_PC_PASID_SEL) |
+		QI_PC_PASID(pasid) | QI_PC_TYPE;
 	desc.qw1 = 0;
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 static void
@@ -384,7 +468,7 @@ iotlb_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid)
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	qi_submit_sync(&desc, iommu);
+	qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 static void
@@ -394,7 +478,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	struct device_domain_info *info;
 	u16 sid, qdep, pfsid;
 
-	info = dev->archdata.iommu;
+	info = get_domain_info(dev);
 	if (!info || !info->ats_enabled)
 		return;
 
@@ -405,8 +489,8 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
 	qi_flush_dev_iotlb(iommu, sid, pfsid, qdep, 0, 64 - VTD_PAGE_SHIFT);
 }
 
-void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
-				 struct device *dev, int pasid)
+void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
+				 int pasid, bool fault_ignore)
 {
 	struct pasid_entry *pte;
 	u16 did;
@@ -416,7 +500,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 		return;
 
 	did = pasid_get_domain_id(pte);
-	intel_pasid_clear_entry(dev, pasid);
+	intel_pasid_clear_entry(dev, pasid, fault_ignore);
 
 	if (!ecap_coherent(iommu->ecap))
 		clflush_cache_range(pte, sizeof(*pte));
@@ -492,13 +576,32 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
 	/* Setup Present and PASID Granular Transfer Type: */
-	pasid_set_translation_type(pte, 1);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
 	pasid_set_present(pte);
 	pasid_flush_caches(iommu, pte, pasid, did);
 
 	return 0;
 }
 
+/*
+ * Skip top levels of page tables for iommu which has less agaw
+ * than default. Unnecessary for PT mode.
+ */
+static inline int iommu_skip_agaw(struct dmar_domain *domain,
+				  struct intel_iommu *iommu,
+				  struct dma_pte **pgd)
+{
+	int agaw;
+
+	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+		*pgd = phys_to_virt(dma_pte_addr(*pgd));
+		if (!dma_pte_present(*pgd))
+			return -EINVAL;
+	}
+
+	return agaw;
+}
+
 /*
  * Set up the scalable mode pasid entry for second only translation type.
  */
@@ -522,17 +625,11 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 		return -EINVAL;
 	}
 
-	/*
-	 * Skip top levels of page tables for iommu which has less agaw
-	 * than default. Unnecessary for PT mode.
-	 */
 	pgd = domain->pgd;
-	for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-		pgd = phys_to_virt(dma_pte_addr(pgd));
-		if (!dma_pte_present(pgd)) {
-			dev_err(dev, "Invalid domain page table\n");
-			return -EINVAL;
-		}
+	agaw = iommu_skip_agaw(domain, iommu, &pgd);
+	if (agaw < 0) {
+		dev_err(dev, "Invalid domain page table\n");
+		return -EINVAL;
 	}
 
 	pgd_val = virt_to_phys(pgd);
@@ -548,7 +645,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 	pasid_set_domain_id(pte, did);
 	pasid_set_slptr(pte, pgd_val);
 	pasid_set_address_width(pte, agaw);
-	pasid_set_translation_type(pte, 2);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_SL_ONLY);
 	pasid_set_fault_enable(pte);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
@@ -582,7 +679,7 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 	pasid_clear_entry(pte);
 	pasid_set_domain_id(pte, did);
 	pasid_set_address_width(pte, iommu->agaw);
-	pasid_set_translation_type(pte, 4);
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_PT);
 	pasid_set_fault_enable(pte);
 	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
 
@@ -596,3 +693,161 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 
 	return 0;
 }
+
+static int
+intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
+			    struct iommu_gpasid_bind_data_vtd *pasid_data)
+{
+	/*
+	 * Not all guest PASID table entry fields are passed down during bind,
+	 * here we only set up the ones that are dependent on guest settings.
+	 * Execution related bits such as NXE, SMEP are not supported.
+	 * Other fields, such as snoop related, are set based on host needs
+	 * regardless of guest settings.
+	 */
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_SRE) {
+		if (!ecap_srs(iommu->ecap)) {
+			pr_err_ratelimited("No supervisor request support on %s\n",
+					   iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_sre(pte);
+	}
+
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_EAFE) {
+		if (!ecap_eafs(iommu->ecap)) {
+			pr_err_ratelimited("No extended access flag support on %s\n",
+					   iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_eafe(pte);
+	}
+
+	/*
+	 * Memory type is only applicable to devices inside processor coherent
+	 * domain. Will add MTS support once coherent devices are available.
+	 */
+	if (pasid_data->flags & IOMMU_SVA_VTD_GPASID_MTS_MASK) {
+		pr_warn_ratelimited("No memory type support %s\n",
+				    iommu->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * intel_pasid_setup_nested() - Set up PASID entry for nested translation.
+ * This could be used for guest shared virtual address. In this case, the
+ * first level page tables are used for GVA-GPA translation in the guest,
+ * second level page tables are used for GPA-HPA translation.
+ *
+ * @iommu:      IOMMU which the device belong to
+ * @dev:        Device to be set up for translation
+ * @gpgd:       FLPTPTR: First Level Page translation pointer in GPA
+ * @pasid:      PASID to be programmed in the device PASID table
+ * @pasid_data: Additional PASID info from the guest bind request
+ * @domain:     Domain info for setting up second level page tables
+ * @addr_width: Address width of the first level (guest)
+ */
+int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
+			     pgd_t *gpgd, int pasid,
+			     struct iommu_gpasid_bind_data_vtd *pasid_data,
+			     struct dmar_domain *domain, int addr_width)
+{
+	struct pasid_entry *pte;
+	struct dma_pte *pgd;
+	int ret = 0;
+	u64 pgd_val;
+	int agaw;
+	u16 did;
+
+	if (!ecap_nest(iommu->ecap)) {
+		pr_err_ratelimited("IOMMU: %s: No nested translation support\n",
+				   iommu->name);
+		return -EINVAL;
+	}
+
+	if (!(domain->flags & DOMAIN_FLAG_NESTING_MODE)) {
+		pr_err_ratelimited("Domain is not in nesting mode, %x\n",
+				   domain->flags);
+		return -EINVAL;
+	}
+
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte))
+		return -EINVAL;
+
+	/*
+	 * Caller must ensure PASID entry is not in use, i.e. not bind the
+	 * same PASID to the same device twice.
+	 */
+	if (pasid_pte_is_present(pte))
+		return -EBUSY;
+
+	pasid_clear_entry(pte);
+
+	/* Sanity checking performed by caller to make sure address
+	 * width matching in two dimensions:
+	 * 1. CPU vs. IOMMU
+	 * 2. Guest vs. Host.
+	 */
+	switch (addr_width) {
+#ifdef CONFIG_X86
+	case ADDR_WIDTH_5LEVEL:
+		if (!cpu_feature_enabled(X86_FEATURE_LA57) ||
+		    !cap_5lp_support(iommu->cap)) {
+			dev_err_ratelimited(dev,
+					    "5-level paging not supported\n");
+			return -EINVAL;
+		}
+
+		pasid_set_flpm(pte, 1);
+		break;
+#endif
+	case ADDR_WIDTH_4LEVEL:
+		pasid_set_flpm(pte, 0);
+		break;
+	default:
+		dev_err_ratelimited(dev, "Invalid guest address width %d\n",
+				    addr_width);
+		return -EINVAL;
+	}
+
+	/* First level PGD is in GPA, must be supported by the second level */
+	if ((uintptr_t)gpgd > domain->max_addr) {
+		dev_err_ratelimited(dev,
+				    "Guest PGD %lx not supported, max %llx\n",
+				    (uintptr_t)gpgd, domain->max_addr);
+		return -EINVAL;
+	}
+	pasid_set_flptr(pte, (uintptr_t)gpgd);
+
+	ret = intel_pasid_setup_bind_data(iommu, pte, pasid_data);
+	if (ret)
+		return ret;
+
+	/* Setup the second level based on the given domain */
+	pgd = domain->pgd;
+
+	agaw = iommu_skip_agaw(domain, iommu, &pgd);
+	if (agaw < 0) {
+		dev_err_ratelimited(dev, "Invalid domain page table\n");
+		return -EINVAL;
+	}
+	pgd_val = virt_to_phys(pgd);
+	pasid_set_slptr(pte, pgd_val);
+	pasid_set_fault_enable(pte);
+
+	did = domain->iommu_did[iommu->seq_id];
+	pasid_set_domain_id(pte, did);
+
+	pasid_set_address_width(pte, agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	pasid_set_translation_type(pte, PASID_ENTRY_PGTT_NESTED);
+	pasid_set_present(pte);
+	pasid_flush_caches(iommu, pte, pasid, did);
+
+	return ret;
+}

drivers/iommu/intel-pasid.h

@@ -15,6 +15,7 @@
 #define PASID_MAX			0x100000
 #define PASID_PTE_MASK			0x3F
 #define PASID_PTE_PRESENT		1
+#define PASID_PTE_FPD			2
 #define PDE_PFN_MASK			PAGE_MASK
 #define PASID_PDE_SHIFT			6
 #define MAX_NR_PASID_BITS		20
@@ -23,6 +24,16 @@
 #define is_pasid_enabled(entry)		(((entry)->lo >> 3) & 0x1)
 #define get_pasid_dir_size(entry)	(1 << ((((entry)->lo >> 9) & 0x7) + 7))
 
+/* Virtual command interface for enlightened pasid management. */
+#define VCMD_CMD_ALLOC			0x1
+#define VCMD_CMD_FREE			0x2
+#define VCMD_VRSP_IP			0x1
+#define VCMD_VRSP_SC(e)			(((e) >> 1) & 0x3)
+#define VCMD_VRSP_SC_SUCCESS		0
+#define VCMD_VRSP_SC_NO_PASID_AVAIL	1
+#define VCMD_VRSP_SC_INVALID_PASID	1
+#define VCMD_VRSP_RESULT_PASID(e)	(((e) >> 8) & 0xfffff)
+#define VCMD_CMD_OPERAND(e)		((e) << 8)
 /*
  * Domain ID reserved for pasid entries programmed for first-level
  * only and pass-through transfer modes.
@@ -36,6 +47,7 @@
  * to vmalloc or even module mappings.
  */
 #define PASID_FLAG_SUPERVISOR_MODE	BIT(0)
+#define PASID_FLAG_NESTED		BIT(1)
 
 /*
  * The PASID_FLAG_FL5LP flag Indicates using 5-level paging for first-
@@ -51,6 +63,11 @@ struct pasid_entry {
 	u64 val[8];
 };
 
+#define PASID_ENTRY_PGTT_FL_ONLY	(1)
+#define PASID_ENTRY_PGTT_SL_ONLY	(2)
+#define PASID_ENTRY_PGTT_NESTED		(3)
+#define PASID_ENTRY_PGTT_PT		(4)
+
 /* The representative of a PASID table */
 struct pasid_table {
 	void			*table;		/* pasid table pointer */
@@ -99,7 +116,13 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, int pasid);
+int intel_pasid_setup_nested(struct intel_iommu *iommu,
+			     struct device *dev, pgd_t *pgd, int pasid,
+			     struct iommu_gpasid_bind_data_vtd *pasid_data,
+			     struct dmar_domain *domain, int addr_width);
 void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
-				 struct device *dev, int pasid);
-
+				 struct device *dev, int pasid,
+				 bool fault_ignore);
+int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid);
+void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid);
 #endif /* __INTEL_PASID_H */

drivers/iommu/intel-svm.c

@@ -23,6 +23,7 @@
 #include "intel-pasid.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
+static void intel_svm_drain_prq(struct device *dev, int pasid);
 
 #define PRQ_ORDER 0
 
@@ -66,6 +67,8 @@ int intel_svm_enable_prq(struct intel_iommu *iommu)
 	dmar_writeq(iommu->reg + DMAR_PQT_REG, 0ULL);
 	dmar_writeq(iommu->reg + DMAR_PQA_REG, virt_to_phys(iommu->prq) | PRQ_ORDER);
 
+	init_completion(&iommu->prq_complete);
+
 	return 0;
 }
 
@@ -138,7 +141,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 	}
 	desc.qw2 = 0;
 	desc.qw3 = 0;
-	qi_submit_sync(&desc, svm->iommu);
+	qi_submit_sync(svm->iommu, &desc, 1, 0);
 
 	if (sdev->dev_iotlb) {
 		desc.qw0 = QI_DEV_EIOTLB_PASID(svm->pasid) |
@@ -162,7 +165,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 		}
 		desc.qw2 = 0;
 		desc.qw3 = 0;
-		qi_submit_sync(&desc, svm->iommu);
+		qi_submit_sync(svm->iommu, &desc, 1, 0);
 	}
 }
 
@@ -206,10 +209,9 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	 * *has* to handle gracefully without affecting other processes.
 	 */
 	rcu_read_lock();
-	list_for_each_entry_rcu(sdev, &svm->devs, list) {
-		intel_pasid_tear_down_entry(svm->iommu, sdev->dev, svm->pasid);
-		intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
-	}
+	list_for_each_entry_rcu(sdev, &svm->devs, list)
+		intel_pasid_tear_down_entry(svm->iommu, sdev->dev,
+					    svm->pasid, true);
 	rcu_read_unlock();
 
 }
@@ -226,13 +228,212 @@ static LIST_HEAD(global_svm_list);
 	list_for_each_entry((sdev), &(svm)->devs, list)	\
 		if ((d) != (sdev)->dev) {} else
 
-int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops)
+int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
+			  struct iommu_gpasid_bind_data *data)
+{
+	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct dmar_domain *dmar_domain;
+	struct intel_svm_dev *sdev;
+	struct intel_svm *svm;
+	int ret = 0;
+
+	if (WARN_ON(!iommu) || !data)
+		return -EINVAL;
+
+	if (data->version != IOMMU_GPASID_BIND_VERSION_1 ||
+	    data->format != IOMMU_PASID_FORMAT_INTEL_VTD)
+		return -EINVAL;
+
+	if (!dev_is_pci(dev))
+		return -ENOTSUPP;
+
+	/* VT-d supports devices with full 20 bit PASIDs only */
+	if (pci_max_pasids(to_pci_dev(dev)) != PASID_MAX)
+		return -EINVAL;
+
+	/*
+	 * We only check host PASID range, we have no knowledge to check
+	 * guest PASID range.
+	 */
+	if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
+		return -EINVAL;
+
+	dmar_domain = to_dmar_domain(domain);
+
+	mutex_lock(&pasid_mutex);
+	svm = ioasid_find(NULL, data->hpasid, NULL);
+	if (IS_ERR(svm)) {
+		ret = PTR_ERR(svm);
+		goto out;
+	}
+
+	if (svm) {
+		/*
+		 * If we found svm for the PASID, there must be at
+		 * least one device bond, otherwise svm should be freed.
+		 */
+		if (WARN_ON(list_empty(&svm->devs))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		for_each_svm_dev(sdev, svm, dev) {
+			/*
+			 * For devices with aux domains, we should allow
+			 * multiple bind calls with the same PASID and pdev.
+			 */
+			if (iommu_dev_feature_enabled(dev,
+						      IOMMU_DEV_FEAT_AUX)) {
+				sdev->users++;
+			} else {
+				dev_warn_ratelimited(dev,
+						     "Already bound with PASID %u\n",
+						     svm->pasid);
+				ret = -EBUSY;
+			}
+			goto out;
+		}
+	} else {
+		/* We come here when PASID has never been bond to a device. */
+		svm = kzalloc(sizeof(*svm), GFP_KERNEL);
+		if (!svm) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		/* REVISIT: upper layer/VFIO can track host process that bind
+		 * the PASID. ioasid_set = mm might be sufficient for vfio to
+		 * check pasid VMM ownership. We can drop the following line
+		 * once VFIO and IOASID set check is in place.
+		 */
+		svm->mm = get_task_mm(current);
+		svm->pasid = data->hpasid;
+		if (data->flags & IOMMU_SVA_GPASID_VAL) {
+			svm->gpasid = data->gpasid;
+			svm->flags |= SVM_FLAG_GUEST_PASID;
+		}
+		ioasid_set_data(data->hpasid, svm);
+		INIT_LIST_HEAD_RCU(&svm->devs);
+		mmput(svm->mm);
+	}
+	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+	if (!sdev) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	sdev->dev = dev;
+
+	/* Only count users if device has aux domains */
+	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
+		sdev->users = 1;
+
+	/* Set up device context entry for PASID if not enabled already */
+	ret = intel_iommu_enable_pasid(iommu, sdev->dev);
+	if (ret) {
+		dev_err_ratelimited(dev, "Failed to enable PASID capability\n");
+		kfree(sdev);
+		goto out;
+	}
+
+	/*
+	 * PASID table is per device for better security. Therefore, for
+	 * each bind of a new device even with an existing PASID, we need to
+	 * call the nested mode setup function here.
+	 */
+	spin_lock(&iommu->lock);
+	ret = intel_pasid_setup_nested(iommu, dev,
+				       (pgd_t *)(uintptr_t)data->gpgd,
+				       data->hpasid, &data->vtd, dmar_domain,
+				       data->addr_width);
+	spin_unlock(&iommu->lock);
+	if (ret) {
+		dev_err_ratelimited(dev, "Failed to set up PASID %llu in nested mode, Err %d\n",
+				    data->hpasid, ret);
+		/*
+		 * PASID entry should be in cleared state if nested mode
+		 * set up failed. So we only need to clear IOASID tracking
+		 * data such that free call will succeed.
+		 */
+		kfree(sdev);
+		goto out;
+	}
+
+	svm->flags |= SVM_FLAG_GUEST_MODE;
+
+	init_rcu_head(&sdev->rcu);
+	list_add_rcu(&sdev->list, &svm->devs);
+ out:
+	if (!IS_ERR_OR_NULL(svm) && list_empty(&svm->devs)) {
+		ioasid_set_data(data->hpasid, NULL);
+		kfree(svm);
+	}
+
+	mutex_unlock(&pasid_mutex);
+	return ret;
+}
+
+int intel_svm_unbind_gpasid(struct device *dev, int pasid)
+{
+	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
+	struct intel_svm_dev *sdev;
+	struct intel_svm *svm;
+	int ret = -EINVAL;
+
+	if (WARN_ON(!iommu))
+		return -EINVAL;
+
+	mutex_lock(&pasid_mutex);
+	svm = ioasid_find(NULL, pasid, NULL);
+	if (!svm) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (IS_ERR(svm)) {
+		ret = PTR_ERR(svm);
+		goto out;
+	}
+
+	for_each_svm_dev(sdev, svm, dev) {
+		ret = 0;
+		if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
+			sdev->users--;
+		if (!sdev->users) {
+			list_del_rcu(&sdev->list);
+			intel_pasid_tear_down_entry(iommu, dev,
+						    svm->pasid, false);
+			intel_svm_drain_prq(dev, svm->pasid);
+			kfree_rcu(sdev, rcu);
+
+			if (list_empty(&svm->devs)) {
+				/*
+				 * We do not free the IOASID here in that
+				 * IOMMU driver did not allocate it.
+				 * Unlike native SVM, IOASID for guest use was
+				 * allocated prior to the bind call.
+				 * In any case, if the free call comes before
+				 * the unbind, IOMMU driver will get notified
+				 * and perform cleanup.
+				 */
+				ioasid_set_data(pasid, NULL);
+				kfree(svm);
+			}
+		}
+		break;
+	}
+out:
+	mutex_unlock(&pasid_mutex);
+	return ret;
+}
+
+/* Caller must hold pasid_mutex, mm reference */
+static int
+intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
+		  struct mm_struct *mm, struct intel_svm_dev **sd)
 {
 	struct intel_iommu *iommu = intel_svm_device_to_iommu(dev);
 	struct device_domain_info *info;
 	struct intel_svm_dev *sdev;
 	struct intel_svm *svm = NULL;
-	struct mm_struct *mm = NULL;
 	int pasid_max;
 	int ret;
 
@@ -249,16 +450,15 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 	} else
 		pasid_max = 1 << 20;
 
+	/* Bind supervisor PASID shuld have mm = NULL */
 	if (flags & SVM_FLAG_SUPERVISOR_MODE) {
-		if (!ecap_srs(iommu->ecap))
+		if (!ecap_srs(iommu->ecap) || mm) {
+			pr_err("Supervisor PASID with user provided mm.\n");
 			return -EINVAL;
-	} else if (pasid) {
-		mm = get_task_mm(current);
-		BUG_ON(!mm);
+		}
 	}
 
-	mutex_lock(&pasid_mutex);
-	if (pasid && !(flags & SVM_FLAG_PRIVATE_PASID)) {
+	if (!(flags & SVM_FLAG_PRIVATE_PASID)) {
 		struct intel_svm *t;
 
 		list_for_each_entry(t, &global_svm_list, list) {
@@ -296,19 +496,12 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 	sdev->dev = dev;
 
 	ret = intel_iommu_enable_pasid(iommu, dev);
-	if (ret || !pasid) {
-		/* If they don't actually want to assign a PASID, this is
-		 * just an enabling check/preparation. */
-		kfree(sdev);
-		goto out;
-	}
-
-	info = dev->archdata.iommu;
-	if (!info || !info->pasid_supported) {
+	if (ret) {
 		kfree(sdev);
 		goto out;
 	}
 
+	info = get_domain_info(dev);
 	sdev->did = FLPT_DEFAULT_DID;
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
 	if (info->ats_enabled) {
@@ -397,26 +590,24 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 		}
 	}
 	list_add_rcu(&sdev->list, &svm->devs);
-
- success:
-	*pasid = svm->pasid;
+success:
+	sdev->pasid = svm->pasid;
+	sdev->sva.dev = dev;
+	if (sd)
+		*sd = sdev;
 	ret = 0;
  out:
-	mutex_unlock(&pasid_mutex);
-	if (mm)
-		mmput(mm);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(intel_svm_bind_mm);
 
-int intel_svm_unbind_mm(struct device *dev, int pasid)
+/* Caller must hold pasid_mutex */
+static int intel_svm_unbind_mm(struct device *dev, int pasid)
 {
 	struct intel_svm_dev *sdev;
 	struct intel_iommu *iommu;
 	struct intel_svm *svm;
 	int ret = -EINVAL;
 
-	mutex_lock(&pasid_mutex);
 	iommu = intel_svm_device_to_iommu(dev);
 	if (!iommu)
 		goto out;
@@ -442,8 +633,9 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 			 * to use. We have a *shared* PASID table, because it's
 			 * large and has to be physically contiguous. So it's
 			 * hard to be as defensive as we might like. */
-			intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
-			intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
+			intel_pasid_tear_down_entry(iommu, dev,
+						    svm->pasid, false);
+			intel_svm_drain_prq(dev, svm->pasid);
 			kfree_rcu(sdev, rcu);
 
 			if (list_empty(&svm->devs)) {
@@ -462,45 +654,9 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 		break;
 	}
  out:
-	mutex_unlock(&pasid_mutex);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(intel_svm_unbind_mm);
-
-int intel_svm_is_pasid_valid(struct device *dev, int pasid)
-{
-	struct intel_iommu *iommu;
-	struct intel_svm *svm;
-	int ret = -EINVAL;
-
-	mutex_lock(&pasid_mutex);
-	iommu = intel_svm_device_to_iommu(dev);
-	if (!iommu)
-		goto out;
-
-	svm = ioasid_find(NULL, pasid, NULL);
-	if (!svm)
-		goto out;
-
-	if (IS_ERR(svm)) {
-		ret = PTR_ERR(svm);
-		goto out;
-	}
-	/* init_mm is used in this case */
-	if (!svm->mm)
-		ret = 1;
-	else if (atomic_read(&svm->mm->mm_users) > 0)
-		ret = 1;
-	else
-		ret = 0;
-
- out:
-	mutex_unlock(&pasid_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(intel_svm_is_pasid_valid);
 
 /* Page request queue descriptor */
 struct page_req_dsc {
@@ -557,6 +713,93 @@ static bool is_canonical_address(u64 addr)
 	return (((saddr << shift) >> shift) == saddr);
 }
 
+/**
+ * intel_svm_drain_prq - Drain page requests and responses for a pasid
+ * @dev: target device
+ * @pasid: pasid for draining
+ *
+ * Drain all pending page requests and responses related to @pasid in both
+ * software and hardware. This is supposed to be called after the device
+ * driver has stopped DMA, the pasid entry has been cleared, and both IOTLB
+ * and DevTLB have been invalidated.
+ *
+ * It waits until all pending page requests for @pasid in the page fault
+ * queue are completed by the prq handling thread. Then follow the steps
+ * described in VT-d spec CH7.10 to drain all page requests and page
+ * responses pending in the hardware.
+ */
+static void intel_svm_drain_prq(struct device *dev, int pasid)
+{
+	struct device_domain_info *info;
+	struct dmar_domain *domain;
+	struct intel_iommu *iommu;
+	struct qi_desc desc[3];
+	struct pci_dev *pdev;
+	int head, tail;
+	u16 sid, did;
+	int qdep;
+
+	info = get_domain_info(dev);
+	if (WARN_ON(!info || !dev_is_pci(dev)))
+		return;
+
+	if (!info->pri_enabled)
+		return;
+
+	iommu = info->iommu;
+	domain = info->domain;
+	pdev = to_pci_dev(dev);
+	sid = PCI_DEVID(info->bus, info->devfn);
+	did = domain->iommu_did[iommu->seq_id];
+	qdep = pci_ats_queue_depth(pdev);
+
+	/*
+	 * Check and wait until all pending page requests in the queue are
+	 * handled by the prq handling thread.
+	 */
+prq_retry:
+	reinit_completion(&iommu->prq_complete);
+	tail = dmar_readq(iommu->reg + DMAR_PQT_REG) & PRQ_RING_MASK;
+	head = dmar_readq(iommu->reg + DMAR_PQH_REG) & PRQ_RING_MASK;
+	while (head != tail) {
+		struct page_req_dsc *req;
+
+		req = &iommu->prq[head / sizeof(*req)];
+		if (!req->pasid_present || req->pasid != pasid) {
+			head = (head + sizeof(*req)) & PRQ_RING_MASK;
+			continue;
+		}
+
+		wait_for_completion(&iommu->prq_complete);
+		goto prq_retry;
+	}
+
+	/*
+	 * Perform steps described in VT-d spec CH7.10 to drain page
+	 * requests and responses in hardware.
+	 */
+	memset(desc, 0, sizeof(desc));
+	desc[0].qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
+			QI_IWD_FENCE |
+			QI_IWD_TYPE;
+	desc[1].qw0 = QI_EIOTLB_PASID(pasid) |
+			QI_EIOTLB_DID(did) |
+			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+			QI_EIOTLB_TYPE;
+	desc[2].qw0 = QI_DEV_EIOTLB_PASID(pasid) |
+			QI_DEV_EIOTLB_SID(sid) |
+			QI_DEV_EIOTLB_QDEP(qdep) |
+			QI_DEIOTLB_TYPE |
+			QI_DEV_IOTLB_PFSID(info->pfsid);
+qi_retry:
+	reinit_completion(&iommu->prq_complete);
+	qi_submit_sync(iommu, desc, 3, QI_OPT_WAIT_DRAIN);
+	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO) {
+		wait_for_completion(&iommu->prq_complete);
+		goto qi_retry;
+	}
+}
+
 static irqreturn_t prq_event_thread(int irq, void *d)
 {
 	struct intel_iommu *iommu = d;
@@ -685,12 +928,75 @@ static irqreturn_t prq_event_thread(int irq, void *d)
 				       sizeof(req->priv_data));
 			resp.qw2 = 0;
 			resp.qw3 = 0;
-			qi_submit_sync(&resp, iommu);
+			qi_submit_sync(iommu, &resp, 1, 0);
 		}
 		head = (head + sizeof(*req)) & PRQ_RING_MASK;
 	}
 
 	dmar_writeq(iommu->reg + DMAR_PQH_REG, tail);
 
+	/*
+	 * Clear the page request overflow bit and wake up all threads that
+	 * are waiting for the completion of this handling.
+	 */
+	if (readl(iommu->reg + DMAR_PRS_REG) & DMA_PRS_PRO)
+		writel(DMA_PRS_PRO, iommu->reg + DMAR_PRS_REG);
+
+	if (!completion_done(&iommu->prq_complete))
+		complete(&iommu->prq_complete);
+
 	return IRQ_RETVAL(handled);
 }
+
+#define to_intel_svm_dev(handle) container_of(handle, struct intel_svm_dev, sva)
+struct iommu_sva *
+intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
+{
+	struct iommu_sva *sva = ERR_PTR(-EINVAL);
+	struct intel_svm_dev *sdev = NULL;
+	int flags = 0;
+	int ret;
+
+	/*
+	 * TODO: Consolidate with generic iommu-sva bind after it is merged.
+	 * It will require shared SVM data structures, i.e. combine io_mm
+	 * and intel_svm etc.
+	 */
+	if (drvdata)
+		flags = *(int *)drvdata;
+	mutex_lock(&pasid_mutex);
+	ret = intel_svm_bind_mm(dev, flags, NULL, mm, &sdev);
+	if (ret)
+		sva = ERR_PTR(ret);
+	else if (sdev)
+		sva = &sdev->sva;
+	else
+		WARN(!sdev, "SVM bind succeeded with no sdev!\n");
+
+	mutex_unlock(&pasid_mutex);
+
+	return sva;
+}
+
+void intel_svm_unbind(struct iommu_sva *sva)
+{
+	struct intel_svm_dev *sdev;
+
+	mutex_lock(&pasid_mutex);
+	sdev = to_intel_svm_dev(sva);
+	intel_svm_unbind_mm(sdev->dev, sdev->pasid);
+	mutex_unlock(&pasid_mutex);
+}
+
+int intel_svm_get_pasid(struct iommu_sva *sva)
+{
+	struct intel_svm_dev *sdev;
+	int pasid;
+
+	mutex_lock(&pasid_mutex);
+	sdev = to_intel_svm_dev(sva);
+	pasid = sdev->pasid;
+	mutex_unlock(&pasid_mutex);
+
+	return pasid;
+}

drivers/iommu/intel_irq_remapping.c

@@ -151,7 +151,7 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 	desc.qw2 = 0;
 	desc.qw3 = 0;
 
-	return qi_submit_sync(&desc, iommu);
+	return qi_submit_sync(iommu, &desc, 1, 0);
 }
 
 static int modify_irte(struct irq_2_iommu *irq_iommu,

drivers/iommu/iommu.c

@@ -44,6 +44,7 @@ struct iommu_group {
 	int id;
 	struct iommu_domain *default_domain;
 	struct iommu_domain *domain;
+	struct list_head entry;
 };
 
 struct group_device {
@@ -79,6 +80,20 @@ static bool iommu_cmd_line_dma_api(void)
 	return !!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API);
 }
 
+static int iommu_alloc_default_domain(struct iommu_group *group,
+				      struct device *dev);
+static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
+						 unsigned type);
+static int __iommu_attach_device(struct iommu_domain *domain,
+				 struct device *dev);
+static int __iommu_attach_group(struct iommu_domain *domain,
+				struct iommu_group *group);
+static void __iommu_detach_group(struct iommu_domain *domain,
+				 struct iommu_group *group);
+static int iommu_create_device_direct_mappings(struct iommu_group *group,
+					       struct device *dev);
+static struct iommu_group *iommu_group_get_for_dev(struct device *dev);
+
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
 	__ATTR(_name, _mode, _show, _store)
@@ -175,57 +190,118 @@ static void dev_iommu_free(struct device *dev)
 	dev->iommu = NULL;
 }
 
-int iommu_probe_device(struct device *dev)
+static int __iommu_probe_device(struct device *dev, struct list_head *group_list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	struct iommu_device *iommu_dev;
+	struct iommu_group *group;
 	int ret;
 
-	WARN_ON(dev->iommu_group);
 	if (!ops)
-		return -EINVAL;
+		return -ENODEV;
 
 	if (!dev_iommu_get(dev))
 		return -ENOMEM;
 
 	if (!try_module_get(ops->owner)) {
 		ret = -EINVAL;
-		goto err_free_dev_param;
+		goto err_free;
 	}
 
-	ret = ops->add_device(dev);
-	if (ret)
-		goto err_module_put;
+	iommu_dev = ops->probe_device(dev);
+	if (IS_ERR(iommu_dev)) {
+		ret = PTR_ERR(iommu_dev);
+		goto out_module_put;
+	}
+
+	dev->iommu->iommu_dev = iommu_dev;
+
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group)) {
+		ret = PTR_ERR(group);
+		goto out_release;
+	}
+	iommu_group_put(group);
+
+	if (group_list && !group->default_domain && list_empty(&group->entry))
+		list_add_tail(&group->entry, group_list);
+
+	iommu_device_link(iommu_dev, dev);
 
 	return 0;
 
-err_module_put:
+out_release:
+	ops->release_device(dev);
+
+out_module_put:
 	module_put(ops->owner);
-err_free_dev_param:
+
+err_free:
 	dev_iommu_free(dev);
+
 	return ret;
 }
 
-void iommu_release_device(struct device *dev)
+int iommu_probe_device(struct device *dev)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	struct iommu_group *group;
+	int ret;
 
-	if (dev->iommu_group)
-		ops->remove_device(dev);
+	ret = __iommu_probe_device(dev, NULL);
+	if (ret)
+		goto err_out;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		goto err_release;
+
+	/*
+	 * Try to allocate a default domain - needs support from the
+	 * IOMMU driver. There are still some drivers which don't
+	 * support default domains, so the return value is not yet
+	 * checked.
+	 */
+	iommu_alloc_default_domain(group, dev);
+
+	if (group->default_domain)
+		ret = __iommu_attach_device(group->default_domain, dev);
+
+	iommu_create_device_direct_mappings(group, dev);
+
+	iommu_group_put(group);
+
+	if (ret)
+		goto err_release;
+
+	if (ops->probe_finalize)
+		ops->probe_finalize(dev);
+
+	return 0;
+
+err_release:
+	iommu_release_device(dev);
+
+err_out:
+	return ret;
 
-	if (dev->iommu) {
-		module_put(ops->owner);
-		dev_iommu_free(dev);
-	}
 }
 
-static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
-						 unsigned type);
-static int __iommu_attach_device(struct iommu_domain *domain,
-				 struct device *dev);
-static int __iommu_attach_group(struct iommu_domain *domain,
-				struct iommu_group *group);
-static void __iommu_detach_group(struct iommu_domain *domain,
-				 struct iommu_group *group);
+void iommu_release_device(struct device *dev)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (!dev->iommu)
+		return;
+
+	iommu_device_unlink(dev->iommu->iommu_dev, dev);
+	iommu_group_remove_device(dev);
+
+	ops->release_device(dev);
+
+	module_put(ops->owner);
+	dev_iommu_free(dev);
+}
 
 static int __init iommu_set_def_domain_type(char *str)
 {
@@ -497,6 +573,7 @@ struct iommu_group *iommu_group_alloc(void)
 	group->kobj.kset = iommu_group_kset;
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
+	INIT_LIST_HEAD(&group->entry);
 	BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
 
 	ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL);
@@ -638,8 +715,8 @@ int iommu_group_set_name(struct iommu_group *group, const char *name)
 }
 EXPORT_SYMBOL_GPL(iommu_group_set_name);
 
-static int iommu_group_create_direct_mappings(struct iommu_group *group,
-					      struct device *dev)
+static int iommu_create_device_direct_mappings(struct iommu_group *group,
+					       struct device *dev)
 {
 	struct iommu_domain *domain = group->default_domain;
 	struct iommu_resv_region *entry;
@@ -752,8 +829,6 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 
 	dev->iommu_group = group;
 
-	iommu_group_create_direct_mappings(group, dev);
-
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
 	if (group->domain  && !iommu_is_attach_deferred(group->domain, dev))
@@ -1371,6 +1446,61 @@ struct iommu_group *fsl_mc_device_group(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(fsl_mc_device_group);
 
+static int iommu_get_def_domain_type(struct device *dev)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	unsigned int type = 0;
+
+	if (ops->def_domain_type)
+		type = ops->def_domain_type(dev);
+
+	return (type == 0) ? iommu_def_domain_type : type;
+}
+
+static int iommu_group_alloc_default_domain(struct bus_type *bus,
+					    struct iommu_group *group,
+					    unsigned int type)
+{
+	struct iommu_domain *dom;
+
+	dom = __iommu_domain_alloc(bus, type);
+	if (!dom && type != IOMMU_DOMAIN_DMA) {
+		dom = __iommu_domain_alloc(bus, IOMMU_DOMAIN_DMA);
+		if (dom)
+			pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA",
+				type, group->name);
+	}
+
+	if (!dom)
+		return -ENOMEM;
+
+	group->default_domain = dom;
+	if (!group->domain)
+		group->domain = dom;
+
+	if (!iommu_dma_strict) {
+		int attr = 1;
+		iommu_domain_set_attr(dom,
+				      DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
+				      &attr);
+	}
+
+	return 0;
+}
+
+static int iommu_alloc_default_domain(struct iommu_group *group,
+				      struct device *dev)
+{
+	unsigned int type;
+
+	if (group->default_domain)
+		return 0;
+
+	type = iommu_get_def_domain_type(dev);
+
+	return iommu_group_alloc_default_domain(dev->bus, group, type);
+}
+
 /**
  * iommu_group_get_for_dev - Find or create the IOMMU group for a device
  * @dev: target device
@@ -1381,7 +1511,7 @@ EXPORT_SYMBOL_GPL(fsl_mc_device_group);
  * to the returned IOMMU group, which will already include the provided
  * device.  The reference should be released with iommu_group_put().
  */
-struct iommu_group *iommu_group_get_for_dev(struct device *dev)
+static struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 	struct iommu_group *group;
@@ -1401,59 +1531,37 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 	if (IS_ERR(group))
 		return group;
 
-	/*
-	 * Try to allocate a default domain - needs support from the
-	 * IOMMU driver.
-	 */
-	if (!group->default_domain) {
-		struct iommu_domain *dom;
-
-		dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
-		if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
-			dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
-			if (dom) {
-				dev_warn(dev,
-					 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
-					 iommu_def_domain_type);
-			}
-		}
-
-		group->default_domain = dom;
-		if (!group->domain)
-			group->domain = dom;
-
-		if (dom && !iommu_dma_strict) {
-			int attr = 1;
-			iommu_domain_set_attr(dom,
-					      DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE,
-					      &attr);
-		}
-	}
-
 	ret = iommu_group_add_device(group, dev);
-	if (ret) {
-		iommu_group_put(group);
-		return ERR_PTR(ret);
-	}
+	if (ret)
+		goto out_put_group;
 
 	return group;
+
+out_put_group:
+	iommu_group_put(group);
+
+	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(iommu_group_get_for_dev);
 
 struct iommu_domain *iommu_group_default_domain(struct iommu_group *group)
 {
 	return group->default_domain;
 }
 
-static int add_iommu_group(struct device *dev, void *data)
+static int probe_iommu_group(struct device *dev, void *data)
 {
-	int ret = iommu_probe_device(dev);
+	struct list_head *group_list = data;
+	struct iommu_group *group;
+	int ret;
 
-	/*
-	 * We ignore -ENODEV errors for now, as they just mean that the
-	 * device is not translated by an IOMMU. We still care about
-	 * other errors and fail to initialize when they happen.
-	 */
+	/* Device is probed already if in a group */
+	group = iommu_group_get(dev);
+	if (group) {
+		iommu_group_put(group);
+		return 0;
+	}
+
+	ret = __iommu_probe_device(dev, group_list);
 	if (ret == -ENODEV)
 		ret = 0;
 
@@ -1519,10 +1627,148 @@ static int iommu_bus_notifier(struct notifier_block *nb,
 	return 0;
 }
 
+struct __group_domain_type {
+	struct device *dev;
+	unsigned int type;
+};
+
+static int probe_get_default_domain_type(struct device *dev, void *data)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+	struct __group_domain_type *gtype = data;
+	unsigned int type = 0;
+
+	if (ops->def_domain_type)
+		type = ops->def_domain_type(dev);
+
+	if (type) {
+		if (gtype->type && gtype->type != type) {
+			dev_warn(dev, "Device needs domain type %s, but device %s in the same iommu group requires type %s - using default\n",
+				 iommu_domain_type_str(type),
+				 dev_name(gtype->dev),
+				 iommu_domain_type_str(gtype->type));
+			gtype->type = 0;
+		}
+
+		if (!gtype->dev) {
+			gtype->dev  = dev;
+			gtype->type = type;
+		}
+	}
+
+	return 0;
+}
+
+static void probe_alloc_default_domain(struct bus_type *bus,
+				       struct iommu_group *group)
+{
+	struct __group_domain_type gtype;
+
+	memset(&gtype, 0, sizeof(gtype));
+
+	/* Ask for default domain requirements of all devices in the group */
+	__iommu_group_for_each_dev(group, &gtype,
+				   probe_get_default_domain_type);
+
+	if (!gtype.type)
+		gtype.type = iommu_def_domain_type;
+
+	iommu_group_alloc_default_domain(bus, group, gtype.type);
+
+}
+
+static int iommu_group_do_dma_attach(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+
+	return __iommu_attach_device(domain, dev);
+}
+
+static int __iommu_group_dma_attach(struct iommu_group *group)
+{
+	return __iommu_group_for_each_dev(group, group->default_domain,
+					  iommu_group_do_dma_attach);
+}
+
+static int iommu_group_do_probe_finalize(struct device *dev, void *data)
+{
+	struct iommu_domain *domain = data;
+
+	if (domain->ops->probe_finalize)
+		domain->ops->probe_finalize(dev);
+
+	return 0;
+}
+
+static void __iommu_group_dma_finalize(struct iommu_group *group)
+{
+	__iommu_group_for_each_dev(group, group->default_domain,
+				   iommu_group_do_probe_finalize);
+}
+
+static int iommu_do_create_direct_mappings(struct device *dev, void *data)
+{
+	struct iommu_group *group = data;
+
+	iommu_create_device_direct_mappings(group, dev);
+
+	return 0;
+}
+
+static int iommu_group_create_direct_mappings(struct iommu_group *group)
+{
+	return __iommu_group_for_each_dev(group, group,
+					  iommu_do_create_direct_mappings);
+}
+
+int bus_iommu_probe(struct bus_type *bus)
+{
+	struct iommu_group *group, *next;
+	LIST_HEAD(group_list);
+	int ret;
+
+	/*
+	 * This code-path does not allocate the default domain when
+	 * creating the iommu group, so do it after the groups are
+	 * created.
+	 */
+	ret = bus_for_each_dev(bus, NULL, &group_list, probe_iommu_group);
+	if (ret)
+		return ret;
+
+	list_for_each_entry_safe(group, next, &group_list, entry) {
+		/* Remove item from the list */
+		list_del_init(&group->entry);
+
+		mutex_lock(&group->mutex);
+
+		/* Try to allocate default domain */
+		probe_alloc_default_domain(bus, group);
+
+		if (!group->default_domain) {
+			mutex_unlock(&group->mutex);
+			continue;
+		}
+
+		iommu_group_create_direct_mappings(group);
+
+		ret = __iommu_group_dma_attach(group);
+
+		mutex_unlock(&group->mutex);
+
+		if (ret)
+			break;
+
+		__iommu_group_dma_finalize(group);
+	}
+
+	return ret;
+}
+
 static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
 {
-	int err;
 	struct notifier_block *nb;
+	int err;
 
 	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
 	if (!nb)
@@ -1534,7 +1780,7 @@ static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops)
 	if (err)
 		goto out_free;
 
-	err = bus_for_each_dev(bus, NULL, NULL, add_iommu_group);
+	err = bus_iommu_probe(bus);
 	if (err)
 		goto out_err;
 
@@ -2301,71 +2547,6 @@ struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
 }
 EXPORT_SYMBOL_GPL(iommu_alloc_resv_region);
 
-static int
-request_default_domain_for_dev(struct device *dev, unsigned long type)
-{
-	struct iommu_domain *domain;
-	struct iommu_group *group;
-	int ret;
-
-	/* Device must already be in a group before calling this function */
-	group = iommu_group_get(dev);
-	if (!group)
-		return -EINVAL;
-
-	mutex_lock(&group->mutex);
-
-	ret = 0;
-	if (group->default_domain && group->default_domain->type == type)
-		goto out;
-
-	/* Don't change mappings of existing devices */
-	ret = -EBUSY;
-	if (iommu_group_device_count(group) != 1)
-		goto out;
-
-	ret = -ENOMEM;
-	domain = __iommu_domain_alloc(dev->bus, type);
-	if (!domain)
-		goto out;
-
-	/* Attach the device to the domain */
-	ret = __iommu_attach_group(domain, group);
-	if (ret) {
-		iommu_domain_free(domain);
-		goto out;
-	}
-
-	/* Make the domain the default for this group */
-	if (group->default_domain)
-		iommu_domain_free(group->default_domain);
-	group->default_domain = domain;
-
-	iommu_group_create_direct_mappings(group, dev);
-
-	dev_info(dev, "Using iommu %s mapping\n",
-		 type == IOMMU_DOMAIN_DMA ? "dma" : "direct");
-
-	ret = 0;
-out:
-	mutex_unlock(&group->mutex);
-	iommu_group_put(group);
-
-	return ret;
-}
-
-/* Request that a device is direct mapped by the IOMMU */
-int iommu_request_dm_for_dev(struct device *dev)
-{
-	return request_default_domain_for_dev(dev, IOMMU_DOMAIN_IDENTITY);
-}
-
-/* Request that a device can't be direct mapped by the IOMMU */
-int iommu_request_dma_domain_for_dev(struct device *dev)
-{
-	return request_default_domain_for_dev(dev, IOMMU_DOMAIN_DMA);
-}
-
 void iommu_set_default_passthrough(bool cmd_line)
 {
 	if (cmd_line)
@@ -2643,17 +2824,6 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 }
 EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
 
-int iommu_sva_set_ops(struct iommu_sva *handle,
-		      const struct iommu_sva_ops *sva_ops)
-{
-	if (handle->ops && handle->ops != sva_ops)
-		return -EEXIST;
-
-	handle->ops = sva_ops;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(iommu_sva_set_ops);
-
 int iommu_sva_get_pasid(struct iommu_sva *handle)
 {
 	const struct iommu_ops *ops = handle->dev->bus->iommu_ops;

drivers/iommu/iova.c

@@ -253,7 +253,7 @@ int iova_cache_get(void)
 			SLAB_HWCACHE_ALIGN, NULL);
 		if (!iova_cache) {
 			mutex_unlock(&iova_cache_mutex);
-			printk(KERN_ERR "Couldn't create iova cache\n");
+			pr_err("Couldn't create iova cache\n");
 			return -ENOMEM;
 		}
 	}
@@ -718,8 +718,8 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 
 		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
 		if (!new_iova)
-			printk(KERN_ERR "Reserve iova range %lx@%lx failed\n",
-				iova->pfn_lo, iova->pfn_lo);
+			pr_err("Reserve iova range %lx@%lx failed\n",
+			       iova->pfn_lo, iova->pfn_lo);
 	}
 	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
 }

include/linux/pci-ats.h

@@ -6,11 +6,14 @@
 
 #ifdef CONFIG_PCI_ATS
 /* Address Translation Service */
+bool pci_ats_supported(struct pci_dev *dev);
 int pci_enable_ats(struct pci_dev *dev, int ps);
 void pci_disable_ats(struct pci_dev *dev);
 int pci_ats_queue_depth(struct pci_dev *dev);
 int pci_ats_page_aligned(struct pci_dev *dev);
 #else /* CONFIG_PCI_ATS */
+static inline bool pci_ats_supported(struct pci_dev *d)
+{ return false; }
 static inline int pci_enable_ats(struct pci_dev *d, int ps)
 { return -ENODEV; }
 static inline void pci_disable_ats(struct pci_dev *d) { }

include/uapi/linux/iommu.h

@@ -285,6 +285,11 @@ struct iommu_gpasid_bind_data_vtd {
 	__u32 emt;
 };
 
+#define IOMMU_SVA_VTD_GPASID_MTS_MASK	(IOMMU_SVA_VTD_GPASID_CD | \
+					 IOMMU_SVA_VTD_GPASID_EMTE | \
+					 IOMMU_SVA_VTD_GPASID_PCD |  \
+					 IOMMU_SVA_VTD_GPASID_PWT)
+
 /**
  * struct iommu_gpasid_bind_data - Information about device and guest PASID binding
  * @version:	Version of this data structure