drivers/iommu/intel/iommu.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright © 2006-2014 Intel Corporation.
 *
 * Authors: David Woodhouse <dwmw2@infradead.org>,
 *          Ashok Raj <ashok.raj@intel.com>,
 *          Shaohua Li <shaohua.li@intel.com>,
 *          Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>,
 *          Fenghua Yu <fenghua.yu@intel.com>
 *          Joerg Roedel <jroedel@suse.de>
 */

#define pr_fmt(fmt)     "DMAR: " fmt
#define dev_fmt(fmt)    pr_fmt(fmt)

#include <linux/crash_dump.h>
#include <linux/dma-direct.h>
#include <linux/dmi.h>
#include <linux/memory.h>
#include <linux/pci.h>
#include <linux/pci-ats.h>
#include <linux/spinlock.h>
#include <linux/syscore_ops.h>
#include <linux/tboot.h>
#include <uapi/linux/iommufd.h>

#include "iommu.h"
#include "../dma-iommu.h"
#include "../irq_remapping.h"
#include "../iommu-pages.h"
#include "pasid.h"
#include "perfmon.h"

#define ROOT_SIZE		VTD_PAGE_SIZE
#define CONTEXT_SIZE		VTD_PAGE_SIZE

#define IS_GFX_DEVICE(pdev) pci_is_display(pdev)
#define IS_USB_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_SERIAL_USB)
#define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
#define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)

#define IOAPIC_RANGE_START	(0xfee00000)
#define IOAPIC_RANGE_END	(0xfeefffff)
#define IOVA_START_ADDR		(0x1000)

#define DEFAULT_DOMAIN_ADDRESS_WIDTH 57

static void __init check_tylersburg_isoch(void);
static int intel_iommu_set_dirty_tracking(struct iommu_domain *domain,
					  bool enable);
static int rwbf_quirk;

#define rwbf_required(iommu)	(rwbf_quirk || cap_rwbf((iommu)->cap))

/*
 * Skip forcing iommu on and avoid tboot-related kernel panics during
 * initialization when set to 1 (via intel_iommu=tboot_noforce).
 */
int intel_iommu_tboot_noforce;

#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))

/*
 * Take a root_entry and return the Lower Context Table Pointer (LCTP)
 * if marked present.
 */
static phys_addr_t root_entry_lctp(struct root_entry *re)
{
	if (!(re->lo & 1))
		return 0;

	return re->lo & VTD_PAGE_MASK;
}

/*
 * Take a root_entry and return the Upper Context Table Pointer (UCTP)
 * if marked present.
 */
static phys_addr_t root_entry_uctp(struct root_entry *re)
{
	if (!(re->hi & 1))
		return 0;

	return re->hi & VTD_PAGE_MASK;
}

static int device_rid_cmp_key(const void *key, const struct rb_node *node)
{
	struct device_domain_info *info =
		rb_entry(node, struct device_domain_info, node);
	const u16 *rid_lhs = key;

	if (*rid_lhs < PCI_DEVID(info->bus, info->devfn))
		return -1;

	if (*rid_lhs > PCI_DEVID(info->bus, info->devfn))
		return 1;

	return 0;
}

static int device_rid_cmp(struct rb_node *lhs, const struct rb_node *rhs)
{
	struct device_domain_info *info =
		rb_entry(lhs, struct device_domain_info, node);
	u16 key = PCI_DEVID(info->bus, info->devfn);

	return device_rid_cmp_key(&key, rhs);
}

/*
 * Looks up an IOMMU-probed device using its source ID.
 *
 * Returns the pointer to the device if there is a match. Otherwise,
 * returns NULL.
 *
 * Note that this helper doesn't guarantee that the device won't be
 * released by the iommu subsystem after being returned. The caller
 * should use its own synchronization mechanism to avoid the device
 * being released during its use if its possibly the case.
 */
struct device *device_rbtree_find(struct intel_iommu *iommu, u16 rid)
{
	struct device_domain_info *info = NULL;
	struct rb_node *node;
	unsigned long flags;

	spin_lock_irqsave(&iommu->device_rbtree_lock, flags);
	node = rb_find(&rid, &iommu->device_rbtree, device_rid_cmp_key);
	if (node)
		info = rb_entry(node, struct device_domain_info, node);
	spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags);

	return info ? info->dev : NULL;
}

static int device_rbtree_insert(struct intel_iommu *iommu,
				struct device_domain_info *info)
{
	struct rb_node *curr;
	unsigned long flags;

	spin_lock_irqsave(&iommu->device_rbtree_lock, flags);
	curr = rb_find_add(&info->node, &iommu->device_rbtree, device_rid_cmp);
	spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags);
	if (WARN_ON(curr))
		return -EEXIST;

	return 0;
}

static void device_rbtree_remove(struct device_domain_info *info)
{
	struct intel_iommu *iommu = info->iommu;
	unsigned long flags;

	spin_lock_irqsave(&iommu->device_rbtree_lock, flags);
	if (!RB_EMPTY_NODE(&info->node)) {
		rb_erase(&info->node, &iommu->device_rbtree);
		RB_CLEAR_NODE(&info->node);
	}
	spin_unlock_irqrestore(&iommu->device_rbtree_lock, flags);
}

struct dmar_rmrr_unit {
	struct list_head list;		/* list of rmrr units	*/
	struct acpi_dmar_header *hdr;	/* ACPI header		*/
	u64	base_address;		/* reserved base address*/
	u64	end_address;		/* reserved end address */
	struct dmar_dev_scope *devices;	/* target devices */
	int	devices_cnt;		/* target device count */
};

struct dmar_atsr_unit {
	struct list_head list;		/* list of ATSR units */
	struct acpi_dmar_header *hdr;	/* ACPI header */
	struct dmar_dev_scope *devices;	/* target devices */
	int devices_cnt;		/* target device count */
	u8 include_all:1;		/* include all ports */
};

struct dmar_satc_unit {
	struct list_head list;		/* list of SATC units */
	struct acpi_dmar_header *hdr;	/* ACPI header */
	struct dmar_dev_scope *devices;	/* target devices */
	struct intel_iommu *iommu;	/* the corresponding iommu */
	int devices_cnt;		/* target device count */
	u8 atc_required:1;		/* ATS is required */
};

static LIST_HEAD(dmar_atsr_units);
static LIST_HEAD(dmar_rmrr_units);
static LIST_HEAD(dmar_satc_units);

#define for_each_rmrr_units(rmrr) \
	list_for_each_entry(rmrr, &dmar_rmrr_units, list)

static void intel_iommu_domain_free(struct iommu_domain *domain);

#ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
int dmar_policy = DMAR_ON;
#else
int dmar_policy = DMAR_DEFAULT_OFF;
#endif
int intel_iommu_sm = IS_ENABLED(CONFIG_INTEL_IOMMU_SCALABLE_MODE_DEFAULT_ON);

int intel_iommu_enabled = 0;
EXPORT_SYMBOL_GPL(intel_iommu_enabled);

static int intel_iommu_superpage = 1;
static int iommu_identity_mapping;
static int iommu_skip_te_disable;
static int disable_igfx_iommu;

#define IDENTMAP_AZALIA		4

const struct iommu_ops intel_iommu_ops;

static bool translation_pre_enabled(struct intel_iommu *iommu)
{
	return (iommu->flags & VTD_FLAG_TRANS_PRE_ENABLED);
}

static void clear_translation_pre_enabled(struct intel_iommu *iommu)
{
	iommu->flags &= ~VTD_FLAG_TRANS_PRE_ENABLED;
}

static void init_translation_status(struct intel_iommu *iommu)
{
	u32 gsts;

	gsts = readl(iommu->reg + DMAR_GSTS_REG);
	if (gsts & DMA_GSTS_TES)
		iommu->flags |= VTD_FLAG_TRANS_PRE_ENABLED;
}

static int __init intel_iommu_setup(char *str)
{
	if (!str)
		return -EINVAL;

	while (*str) {
		if (!strncmp(str, "on", 2)) {
			dmar_policy = DMAR_ON;
			pr_info("IOMMU enabled\n");
		} else if (!strncmp(str, "off", 3)) {
			dmar_policy = DMAR_USER_OFF;
			pr_info("IOMMU disabled\n");
		} else if (!strncmp(str, "igfx_off", 8)) {
			disable_igfx_iommu = 1;
			pr_info("Disable GFX device mapping\n");
		} else if (!strncmp(str, "forcedac", 8)) {
			pr_warn("intel_iommu=forcedac deprecated; use iommu.forcedac instead\n");
			iommu_dma_forcedac = true;
		} else if (!strncmp(str, "strict", 6)) {
			pr_warn("intel_iommu=strict deprecated; use iommu.strict=1 instead\n");
			iommu_set_dma_strict();
		} else if (!strncmp(str, "sp_off", 6)) {
			pr_info("Disable supported super page\n");
			intel_iommu_superpage = 0;
		} else if (!strncmp(str, "sm_on", 5)) {
			pr_info("Enable scalable mode if hardware supports\n");
			intel_iommu_sm = 1;
		} else if (!strncmp(str, "sm_off", 6)) {
			pr_info("Scalable mode is disallowed\n");
			intel_iommu_sm = 0;
		} else if (!strncmp(str, "tboot_noforce", 13)) {
			pr_info("Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
			intel_iommu_tboot_noforce = 1;
		} else {
			pr_notice("Unknown option - '%s'\n", str);
		}

		str += strcspn(str, ",");
		while (*str == ',')
			str++;
	}

	return 1;
}
__setup("intel_iommu=", intel_iommu_setup);

/*
 * Calculate the Supported Adjusted Guest Address Widths of an IOMMU.
 * Refer to 11.4.2 of the VT-d spec for the encoding of each bit of
 * the returned SAGAW.
 */
static unsigned long __iommu_calculate_sagaw(struct intel_iommu *iommu)
{
	unsigned long fl_sagaw, sl_sagaw;

	fl_sagaw = BIT(2) | (cap_fl5lp_support(iommu->cap) ? BIT(3) : 0);
	sl_sagaw = cap_sagaw(iommu->cap);

	/* Second level only. */
	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
		return sl_sagaw;

	/* First level only. */
	if (!ecap_slts(iommu->ecap))
		return fl_sagaw;

	return fl_sagaw & sl_sagaw;
}

static int __iommu_calculate_agaw(struct intel_iommu *iommu, int max_gaw)
{
	unsigned long sagaw;
	int agaw;

	sagaw = __iommu_calculate_sagaw(iommu);
	for (agaw = width_to_agaw(max_gaw); agaw >= 0; agaw--) {
		if (test_bit(agaw, &sagaw))
			break;
	}

	return agaw;
}

/*
 * Calculate max SAGAW for each iommu.
 */
int iommu_calculate_max_sagaw(struct intel_iommu *iommu)
{
	return __iommu_calculate_agaw(iommu, MAX_AGAW_WIDTH);
}

/*
 * calculate agaw for each iommu.
 * "SAGAW" may be different across iommus, use a default agaw, and
 * get a supported less agaw for iommus that don't support the default agaw.
 */
int iommu_calculate_agaw(struct intel_iommu *iommu)
{
	return __iommu_calculate_agaw(iommu, DEFAULT_DOMAIN_ADDRESS_WIDTH);
}

static bool iommu_paging_structure_coherency(struct intel_iommu *iommu)
{
	return sm_supported(iommu) ?
			ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap);
}

struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus,
					 u8 devfn, int alloc)
{
	struct root_entry *root = &iommu->root_entry[bus];
	struct context_entry *context;
	u64 *entry;

	/*
	 * Except that the caller requested to allocate a new entry,
	 * returning a copied context entry makes no sense.
	 */
	if (!alloc && context_copied(iommu, bus, devfn))
		return NULL;

	entry = &root->lo;
	if (sm_supported(iommu)) {
		if (devfn >= 0x80) {
			devfn -= 0x80;
			entry = &root->hi;
		}
		devfn *= 2;
	}
	if (*entry & 1)
		context = phys_to_virt(*entry & VTD_PAGE_MASK);
	else {
		unsigned long phy_addr;
		if (!alloc)
			return NULL;

		context = iommu_alloc_pages_node_sz(iommu->node, GFP_ATOMIC,
						    SZ_4K);
		if (!context)
			return NULL;

		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
		phy_addr = virt_to_phys((void *)context);
		*entry = phy_addr | 1;
		__iommu_flush_cache(iommu, entry, sizeof(*entry));
	}
	return &context[devfn];
}

/**
 * is_downstream_to_pci_bridge - test if a device belongs to the PCI
 *				 sub-hierarchy of a candidate PCI-PCI bridge
 * @dev: candidate PCI device belonging to @bridge PCI sub-hierarchy
 * @bridge: the candidate PCI-PCI bridge
 *
 * Return: true if @dev belongs to @bridge PCI sub-hierarchy, else false.
 */
static bool
is_downstream_to_pci_bridge(struct device *dev, struct device *bridge)
{
	struct pci_dev *pdev, *pbridge;

	if (!dev_is_pci(dev) || !dev_is_pci(bridge))
		return false;

	pdev = to_pci_dev(dev);
	pbridge = to_pci_dev(bridge);

	if (pbridge->subordinate &&
	    pbridge->subordinate->number <= pdev->bus->number &&
	    pbridge->subordinate->busn_res.end >= pdev->bus->number)
		return true;

	return false;
}

static bool quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
{
	struct dmar_drhd_unit *drhd;
	u32 vtbar;
	int rc;

	/* We know that this device on this chipset has its own IOMMU.
	 * If we find it under a different IOMMU, then the BIOS is lying
	 * to us. Hope that the IOMMU for this device is actually
	 * disabled, and it needs no translation...
	 */
	rc = pci_bus_read_config_dword(pdev->bus, PCI_DEVFN(0, 0), 0xb0, &vtbar);
	if (rc) {
		/* "can't" happen */
		dev_info(&pdev->dev, "failed to run vt-d quirk\n");
		return false;
	}
	vtbar &= 0xffff0000;

	/* we know that the this iommu should be at offset 0xa000 from vtbar */
	drhd = dmar_find_matched_drhd_unit(pdev);
	if (!drhd || drhd->reg_base_addr - vtbar != 0xa000) {
		pr_warn_once(FW_BUG "BIOS assigned incorrect VT-d unit for Intel(R) QuickData Technology device\n");
		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
		return true;
	}

	return false;
}

static bool iommu_is_dummy(struct intel_iommu *iommu, struct device *dev)
{
	if (!iommu || iommu->drhd->ignored)
		return true;

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
		    pdev->device == PCI_DEVICE_ID_INTEL_IOAT_SNB &&
		    quirk_ioat_snb_local_iommu(pdev))
			return true;
	}

	return false;
}

static struct intel_iommu *device_lookup_iommu(struct device *dev, u8 *bus, u8 *devfn)
{
	struct dmar_drhd_unit *drhd = NULL;
	struct pci_dev *pdev = NULL;
	struct intel_iommu *iommu;
	struct device *tmp;
	u16 segment = 0;
	int i;

	if (!dev)
		return NULL;

	if (dev_is_pci(dev)) {
		struct pci_dev *pf_pdev;

		pdev = pci_real_dma_dev(to_pci_dev(dev));

		/* VFs aren't listed in scope tables; we need to look up
		 * the PF instead to find the IOMMU. */
		pf_pdev = pci_physfn(pdev);
		dev = &pf_pdev->dev;
		segment = pci_domain_nr(pdev->bus);
	} else if (has_acpi_companion(dev))
		dev = &ACPI_COMPANION(dev)->dev;

	rcu_read_lock();
	for_each_iommu(iommu, drhd) {
		if (pdev && segment != drhd->segment)
			continue;

		for_each_active_dev_scope(drhd->devices,
					  drhd->devices_cnt, i, tmp) {
			if (tmp == dev) {
				/* For a VF use its original BDF# not that of the PF
				 * which we used for the IOMMU lookup. Strictly speaking
				 * we could do this for all PCI devices; we only need to
				 * get the BDF# from the scope table for ACPI matches. */
				if (pdev && pdev->is_virtfn)
					goto got_pdev;

				if (bus && devfn) {
					*bus = drhd->devices[i].bus;
					*devfn = drhd->devices[i].devfn;
				}
				goto out;
			}

			if (is_downstream_to_pci_bridge(dev, tmp))
				goto got_pdev;
		}

		if (pdev && drhd->include_all) {
got_pdev:
			if (bus && devfn) {
				*bus = pdev->bus->number;
				*devfn = pdev->devfn;
			}
			goto out;
		}
	}
	iommu = NULL;
out:
	if (iommu_is_dummy(iommu, dev))
		iommu = NULL;

	rcu_read_unlock();

	return iommu;
}

static void free_context_table(struct intel_iommu *iommu)
{
	struct context_entry *context;
	int i;

	if (!iommu->root_entry)
		return;

	for (i = 0; i < ROOT_ENTRY_NR; i++) {
		context = iommu_context_addr(iommu, i, 0, 0);
		if (context)
			iommu_free_pages(context);

		if (!sm_supported(iommu))
			continue;

		context = iommu_context_addr(iommu, i, 0x80, 0);
		if (context)
			iommu_free_pages(context);
	}

	iommu_free_pages(iommu->root_entry);
	iommu->root_entry = NULL;
}

#ifdef CONFIG_DMAR_DEBUG
static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn,
			 u8 bus, u8 devfn, struct dma_pte *parent, int level)
{
	struct dma_pte *pte;
	int offset;

	while (1) {
		offset = pfn_level_offset(pfn, level);
		pte = &parent[offset];

		pr_info("pte level: %d, pte value: 0x%016llx\n", level, pte->val);

		if (!dma_pte_present(pte)) {
			pr_info("page table not present at level %d\n", level - 1);
			break;
		}

		if (level == 1 || dma_pte_superpage(pte))
			break;

		parent = phys_to_virt(dma_pte_addr(pte));
		level--;
	}
}

void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id,
			  unsigned long long addr, u32 pasid)
{
	struct pasid_dir_entry *dir, *pde;
	struct pasid_entry *entries, *pte;
	struct context_entry *ctx_entry;
	struct root_entry *rt_entry;
	int i, dir_index, index, level;
	u8 devfn = source_id & 0xff;
	u8 bus = source_id >> 8;
	struct dma_pte *pgtable;

	pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr);

	/* root entry dump */
	if (!iommu->root_entry) {
		pr_info("root table is not present\n");
		return;
	}
	rt_entry = &iommu->root_entry[bus];

	if (sm_supported(iommu))
		pr_info("scalable mode root entry: hi 0x%016llx, low 0x%016llx\n",
			rt_entry->hi, rt_entry->lo);
	else
		pr_info("root entry: 0x%016llx", rt_entry->lo);

	/* context entry dump */
	ctx_entry = iommu_context_addr(iommu, bus, devfn, 0);
	if (!ctx_entry) {
		pr_info("context table is not present\n");
		return;
	}

	pr_info("context entry: hi 0x%016llx, low 0x%016llx\n",
		ctx_entry->hi, ctx_entry->lo);

	/* legacy mode does not require PASID entries */
	if (!sm_supported(iommu)) {
		if (!context_present(ctx_entry)) {
			pr_info("legacy mode page table is not present\n");
			return;
		}
		level = agaw_to_level(ctx_entry->hi & 7);
		pgtable = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);
		goto pgtable_walk;
	}

	if (!context_present(ctx_entry)) {
		pr_info("pasid directory table is not present\n");
		return;
	}

	/* get the pointer to pasid directory entry */
	dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK);

	/* For request-without-pasid, get the pasid from context entry */
	if (intel_iommu_sm && pasid == IOMMU_PASID_INVALID)
		pasid = IOMMU_NO_PASID;

	dir_index = pasid >> PASID_PDE_SHIFT;
	pde = &dir[dir_index];
	pr_info("pasid dir entry: 0x%016llx\n", pde->val);

	/* get the pointer to the pasid table entry */
	entries = get_pasid_table_from_pde(pde);
	if (!entries) {
		pr_info("pasid table is not present\n");
		return;
	}
	index = pasid & PASID_PTE_MASK;
	pte = &entries[index];
	for (i = 0; i < ARRAY_SIZE(pte->val); i++)
		pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]);

	if (!pasid_pte_is_present(pte)) {
		pr_info("scalable mode page table is not present\n");
		return;
	}

	if (pasid_pte_get_pgtt(pte) == PASID_ENTRY_PGTT_FL_ONLY) {
		level = pte->val[2] & BIT_ULL(2) ? 5 : 4;
		pgtable = phys_to_virt(pte->val[2] & VTD_PAGE_MASK);
	} else {
		level = agaw_to_level((pte->val[0] >> 2) & 0x7);
		pgtable = phys_to_virt(pte->val[0] & VTD_PAGE_MASK);
	}

pgtable_walk:
	pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn, pgtable, level);
}
#endif

/* iommu handling */
static int iommu_alloc_root_entry(struct intel_iommu *iommu)
{
	struct root_entry *root;

	root = iommu_alloc_pages_node_sz(iommu->node, GFP_ATOMIC, SZ_4K);
	if (!root) {
		pr_err("Allocating root entry for %s failed\n",
			iommu->name);
		return -ENOMEM;
	}

	__iommu_flush_cache(iommu, root, ROOT_SIZE);
	iommu->root_entry = root;

	return 0;
}

static void iommu_set_root_entry(struct intel_iommu *iommu)
{
	u64 addr;
	u32 sts;
	unsigned long flag;

	addr = virt_to_phys(iommu->root_entry);
	if (sm_supported(iommu))
		addr |= DMA_RTADDR_SMT;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writeq(addr, iommu->reg + DMAR_RTADDR_REG);

	writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (sts & DMA_GSTS_RTPS), sts);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);

	/*
	 * Hardware invalidates all DMA remapping hardware translation
	 * caches as part of SRTP flow.
	 */
	if (cap_esrtps(iommu->cap))
		return;

	iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL);
	if (sm_supported(iommu))
		qi_flush_pasid_cache(iommu, 0, QI_PC_GLOBAL, 0);
	iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
}

void iommu_flush_write_buffer(struct intel_iommu *iommu)
{
	u32 val;
	unsigned long flag;

	if (!rwbf_quirk && !cap_rwbf(iommu->cap))
		return;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writel(iommu->gcmd | DMA_GCMD_WBF, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (!(val & DMA_GSTS_WBFS)), val);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

/* return value determine if we need a write buffer flush */
static void __iommu_flush_context(struct intel_iommu *iommu,
				  u16 did, u16 source_id, u8 function_mask,
				  u64 type)
{
	u64 val = 0;
	unsigned long flag;

	switch (type) {
	case DMA_CCMD_GLOBAL_INVL:
		val = DMA_CCMD_GLOBAL_INVL;
		break;
	case DMA_CCMD_DOMAIN_INVL:
		val = DMA_CCMD_DOMAIN_INVL|DMA_CCMD_DID(did);
		break;
	case DMA_CCMD_DEVICE_INVL:
		val = DMA_CCMD_DEVICE_INVL|DMA_CCMD_DID(did)
			| DMA_CCMD_SID(source_id) | DMA_CCMD_FM(function_mask);
		break;
	default:
		pr_warn("%s: Unexpected context-cache invalidation type 0x%llx\n",
			iommu->name, type);
		return;
	}
	val |= DMA_CCMD_ICC;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writeq(val, iommu->reg + DMAR_CCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_CCMD_REG,
		readq, (!(val & DMA_CCMD_ICC)), val);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
			 unsigned int size_order, u64 type)
{
	int tlb_offset = ecap_iotlb_offset(iommu->ecap);
	u64 val = 0, val_iva = 0;
	unsigned long flag;

	switch (type) {
	case DMA_TLB_GLOBAL_FLUSH:
		/* global flush doesn't need set IVA_REG */
		val = DMA_TLB_GLOBAL_FLUSH|DMA_TLB_IVT;
		break;
	case DMA_TLB_DSI_FLUSH:
		val = DMA_TLB_DSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
		break;
	case DMA_TLB_PSI_FLUSH:
		val = DMA_TLB_PSI_FLUSH|DMA_TLB_IVT|DMA_TLB_DID(did);
		/* IH bit is passed in as part of address */
		val_iva = size_order | addr;
		break;
	default:
		pr_warn("%s: Unexpected iotlb invalidation type 0x%llx\n",
			iommu->name, type);
		return;
	}

	if (cap_write_drain(iommu->cap))
		val |= DMA_TLB_WRITE_DRAIN;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	/* Note: Only uses first TLB reg currently */
	if (val_iva)
		writeq(val_iva, iommu->reg + tlb_offset);
	writeq(val, iommu->reg + tlb_offset + 8);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, tlb_offset + 8,
		readq, (!(val & DMA_TLB_IVT)), val);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);

	/* check IOTLB invalidation granularity */
	if (DMA_TLB_IAIG(val) == 0)
		pr_err("Flush IOTLB failed\n");
	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
		pr_debug("TLB flush request %Lx, actual %Lx\n",
			(unsigned long long)DMA_TLB_IIRG(type),
			(unsigned long long)DMA_TLB_IAIG(val));
}

static struct device_domain_info *
domain_lookup_dev_info(struct dmar_domain *domain,
		       struct intel_iommu *iommu, u8 bus, u8 devfn)
{
	struct device_domain_info *info;
	unsigned long flags;

	spin_lock_irqsave(&domain->lock, flags);
	list_for_each_entry(info, &domain->devices, link) {
		if (info->iommu == iommu && info->bus == bus &&
		    info->devfn == devfn) {
			spin_unlock_irqrestore(&domain->lock, flags);
			return info;
		}
	}
	spin_unlock_irqrestore(&domain->lock, flags);

	return NULL;
}

/*
 * The extra devTLB flush quirk impacts those QAT devices with PCI device
 * IDs ranging from 0x4940 to 0x4943. It is exempted from risky_device()
 * check because it applies only to the built-in QAT devices and it doesn't
 * grant additional privileges.
 */
#define BUGGY_QAT_DEVID_MASK 0x4940
static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev)
{
	if (pdev->vendor != PCI_VENDOR_ID_INTEL)
		return false;

	if ((pdev->device & 0xfffc) != BUGGY_QAT_DEVID_MASK)
		return false;

	return true;
}

static void iommu_enable_pci_ats(struct device_domain_info *info)
{
	struct pci_dev *pdev;

	if (!info->ats_supported)
		return;

	pdev = to_pci_dev(info->dev);
	if (!pci_ats_page_aligned(pdev))
		return;

	/*
	 * pci_enable_ats() should not fail here because earlier checks
	 * have already verified support and configuration.
	 */
	if (WARN_ON(pci_enable_ats(pdev, VTD_PAGE_SHIFT)))
		return;

	info->ats_enabled = 1;
}

static void iommu_disable_pci_ats(struct device_domain_info *info)
{
	if (!info->ats_enabled)
		return;

	pci_disable_ats(to_pci_dev(info->dev));
	info->ats_enabled = 0;
}

static void iommu_enable_pci_pri(struct device_domain_info *info)
{
	struct pci_dev *pdev;

	if (!info->ats_enabled || !info->pri_supported)
		return;

	pdev = to_pci_dev(info->dev);
	/* PASID is required in PRG Response Message. */
	if (info->pasid_enabled && !pci_prg_resp_pasid_required(pdev))
		return;

	if (pci_reset_pri(pdev))
		return;

	if (!pci_enable_pri(pdev, PRQ_DEPTH))
		info->pri_enabled = 1;
}

static void iommu_disable_pci_pri(struct device_domain_info *info)
{
	if (!info->pri_enabled)
		return;

	if (WARN_ON(info->iopf_refcount))
		iopf_queue_remove_device(info->iommu->iopf_queue, info->dev);

	pci_disable_pri(to_pci_dev(info->dev));
	info->pri_enabled = 0;
}

static void intel_flush_iotlb_all(struct iommu_domain *domain)
{
	cache_tag_flush_all(to_dmar_domain(domain));
}

static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
{
	u32 pmen;
	unsigned long flags;

	if (!cap_plmr(iommu->cap) && !cap_phmr(iommu->cap))
		return;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);
	pmen = readl(iommu->reg + DMAR_PMEN_REG);
	pmen &= ~DMA_PMEN_EPM;
	writel(pmen, iommu->reg + DMAR_PMEN_REG);

	/* wait for the protected region status bit to clear */
	IOMMU_WAIT_OP(iommu, DMAR_PMEN_REG,
		readl, !(pmen & DMA_PMEN_PRS), pmen);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static void iommu_enable_translation(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flags;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);
	iommu->gcmd |= DMA_GCMD_TE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (sts & DMA_GSTS_TES), sts);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static void iommu_disable_translation(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flag;

	if (iommu_skip_te_disable && iommu->drhd->gfx_dedicated &&
	    (cap_read_drain(iommu->cap) || cap_write_drain(iommu->cap)))
		return;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	iommu->gcmd &= ~DMA_GCMD_TE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (!(sts & DMA_GSTS_TES)), sts);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

static void disable_dmar_iommu(struct intel_iommu *iommu)
{
	/*
	 * All iommu domains must have been detached from the devices,
	 * hence there should be no domain IDs in use.
	 */
	if (WARN_ON(!ida_is_empty(&iommu->domain_ida)))
		return;

	if (iommu->gcmd & DMA_GCMD_TE)
		iommu_disable_translation(iommu);
}

static void free_dmar_iommu(struct intel_iommu *iommu)
{
	if (iommu->copied_tables) {
		bitmap_free(iommu->copied_tables);
		iommu->copied_tables = NULL;
	}

	/* free context mapping */
	free_context_table(iommu);

	if (ecap_prs(iommu->ecap))
		intel_iommu_finish_prq(iommu);
}

/*
 * Check and return whether first level is used by default for
 * DMA translation.
 */
static bool first_level_by_default(struct intel_iommu *iommu)
{
	/* Only SL is available in legacy mode */
	if (!sm_supported(iommu))
		return false;

	/* Only level (either FL or SL) is available, just use it */
	if (ecap_flts(iommu->ecap) ^ ecap_slts(iommu->ecap))
		return ecap_flts(iommu->ecap);

	return true;
}

int domain_attach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
{
	struct iommu_domain_info *info, *curr;
	int num, ret = -ENOSPC;

	if (domain->domain.type == IOMMU_DOMAIN_SVA)
		return 0;

	info = kzalloc_obj(*info);
	if (!info)
		return -ENOMEM;

	guard(mutex)(&iommu->did_lock);
	curr = xa_load(&domain->iommu_array, iommu->seq_id);
	if (curr) {
		curr->refcnt++;
		kfree(info);
		return 0;
	}

	num = ida_alloc_range(&iommu->domain_ida, IDA_START_DID,
			      iommu->max_domain_id - 1, GFP_KERNEL);
	if (num < 0) {
		pr_err("%s: No free domain ids\n", iommu->name);
		goto err_unlock;
	}

	info->refcnt	= 1;
	info->did	= num;
	info->iommu	= iommu;
	curr = xa_cmpxchg(&domain->iommu_array, iommu->seq_id,
			  NULL, info, GFP_KERNEL);
	if (curr) {
		ret = xa_err(curr) ? : -EBUSY;
		goto err_clear;
	}

	return 0;

err_clear:
	ida_free(&iommu->domain_ida, info->did);
err_unlock:
	kfree(info);
	return ret;
}

void domain_detach_iommu(struct dmar_domain *domain, struct intel_iommu *iommu)
{
	struct iommu_domain_info *info;

	if (domain->domain.type == IOMMU_DOMAIN_SVA)
		return;

	guard(mutex)(&iommu->did_lock);
	info = xa_load(&domain->iommu_array, iommu->seq_id);
	if (--info->refcnt == 0) {
		ida_free(&iommu->domain_ida, info->did);
		xa_erase(&domain->iommu_array, iommu->seq_id);
		kfree(info);
	}
}

/*
 * For kdump cases, old valid entries may be cached due to the
 * in-flight DMA and copied pgtable, but there is no unmapping
 * behaviour for them, thus we need an explicit cache flush for
 * the newly-mapped device. For kdump, at this point, the device
 * is supposed to finish reset at its driver probe stage, so no
 * in-flight DMA will exist, and we don't need to worry anymore
 * hereafter.
 */
static void copied_context_tear_down(struct intel_iommu *iommu,
				     struct context_entry *context,
				     u8 bus, u8 devfn)
{
	u16 did_old;

	if (!context_copied(iommu, bus, devfn))
		return;

	assert_spin_locked(&iommu->lock);

	did_old = context_domain_id(context);
	context_clear_present(context);
	__iommu_flush_cache(iommu, context, sizeof(*context));

	if (did_old < iommu->max_domain_id) {
		iommu->flush.flush_context(iommu, did_old,
					   PCI_DEVID(bus, devfn),
					   DMA_CCMD_MASK_NOBIT,
					   DMA_CCMD_DEVICE_INVL);
		iommu->flush.flush_iotlb(iommu, did_old, 0, 0,
					 DMA_TLB_DSI_FLUSH);
	}

	context_clear_entry(context);
	__iommu_flush_cache(iommu, context, sizeof(*context));

	clear_context_copied(iommu, bus, devfn);
}

/*
 * It's a non-present to present mapping. If hardware doesn't cache
 * non-present entry we only need to flush the write-buffer. If the
 * _does_ cache non-present entries, then it does so in the special
 * domain #0, which we have to flush:
 */
static void context_present_cache_flush(struct intel_iommu *iommu, u16 did,
					u8 bus, u8 devfn)
{
	if (cap_caching_mode(iommu->cap)) {
		iommu->flush.flush_context(iommu, 0,
					   PCI_DEVID(bus, devfn),
					   DMA_CCMD_MASK_NOBIT,
					   DMA_CCMD_DEVICE_INVL);
		iommu->flush.flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH);
	} else {
		iommu_flush_write_buffer(iommu);
	}
}

static int domain_context_mapping_one(struct dmar_domain *domain,
				      struct intel_iommu *iommu,
				      u8 bus, u8 devfn)
{
	struct device_domain_info *info =
			domain_lookup_dev_info(domain, iommu, bus, devfn);
	u16 did = domain_id_iommu(domain, iommu);
	int translation = CONTEXT_TT_MULTI_LEVEL;
	struct pt_iommu_vtdss_hw_info pt_info;
	struct context_entry *context;
	int ret;

	if (WARN_ON(!intel_domain_is_ss_paging(domain)))
		return -EINVAL;

	pt_iommu_vtdss_hw_info(&domain->sspt, &pt_info);

	pr_debug("Set context mapping for %02x:%02x.%d\n",
		bus, PCI_SLOT(devfn), PCI_FUNC(devfn));

	spin_lock(&iommu->lock);
	ret = -ENOMEM;
	context = iommu_context_addr(iommu, bus, devfn, 1);
	if (!context)
		goto out_unlock;

	ret = 0;
	if (context_present(context) && !context_copied(iommu, bus, devfn))
		goto out_unlock;

	copied_context_tear_down(iommu, context, bus, devfn);
	context_clear_entry(context);
	context_set_domain_id(context, did);

	if (info && info->ats_supported)
		translation = CONTEXT_TT_DEV_IOTLB;
	else
		translation = CONTEXT_TT_MULTI_LEVEL;

	context_set_address_root(context, pt_info.ssptptr);
	context_set_address_width(context, pt_info.aw);
	context_set_translation_type(context, translation);
	context_set_fault_enable(context);
	context_set_present(context);
	if (!ecap_coherent(iommu->ecap))
		clflush_cache_range(context, sizeof(*context));
	context_present_cache_flush(iommu, did, bus, devfn);
	ret = 0;

out_unlock:
	spin_unlock(&iommu->lock);

	return ret;
}

static int domain_context_mapping_cb(struct pci_dev *pdev,
				     u16 alias, void *opaque)
{
	struct device_domain_info *info = dev_iommu_priv_get(&pdev->dev);
	struct intel_iommu *iommu = info->iommu;
	struct dmar_domain *domain = opaque;

	return domain_context_mapping_one(domain, iommu,
					  PCI_BUS_NUM(alias), alias & 0xff);
}

static int
domain_context_mapping(struct dmar_domain *domain, struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	u8 bus = info->bus, devfn = info->devfn;
	int ret;

	if (!dev_is_pci(dev))
		return domain_context_mapping_one(domain, iommu, bus, devfn);

	ret = pci_for_each_dma_alias(to_pci_dev(dev),
				     domain_context_mapping_cb, domain);
	if (ret)
		return ret;

	iommu_enable_pci_ats(info);

	return 0;
}

static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 devfn)
{
	struct intel_iommu *iommu = info->iommu;
	struct context_entry *context;
	u16 did;

	spin_lock(&iommu->lock);
	context = iommu_context_addr(iommu, bus, devfn, 0);
	if (!context) {
		spin_unlock(&iommu->lock);
		return;
	}

	did = context_domain_id(context);
	context_clear_present(context);
	__iommu_flush_cache(iommu, context, sizeof(*context));
	spin_unlock(&iommu->lock);
	intel_context_flush_no_pasid(info, context, did, PCI_DEVID(bus, devfn));
	context_clear_entry(context);
	__iommu_flush_cache(iommu, context, sizeof(*context));
}

int __domain_setup_first_level(struct intel_iommu *iommu, struct device *dev,
			       ioasid_t pasid, u16 did, phys_addr_t fsptptr,
			       int flags, struct iommu_domain *old)
{
	if (old)
		intel_pasid_tear_down_entry(iommu, dev, pasid, false);

	return intel_pasid_setup_first_level(iommu, dev, fsptptr, pasid, did, flags);
}

static int domain_setup_second_level(struct intel_iommu *iommu,
				     struct dmar_domain *domain,
				     struct device *dev, ioasid_t pasid,
				     struct iommu_domain *old)
{
	if (old)
		intel_pasid_tear_down_entry(iommu, dev, pasid, false);

	return intel_pasid_setup_second_level(iommu, domain, dev, pasid);
}

static int domain_setup_passthrough(struct intel_iommu *iommu,
				    struct device *dev, ioasid_t pasid,
				    struct iommu_domain *old)
{
	if (old)
		intel_pasid_tear_down_entry(iommu, dev, pasid, false);

	return intel_pasid_setup_pass_through(iommu, dev, pasid);
}

static int domain_setup_first_level(struct intel_iommu *iommu,
				    struct dmar_domain *domain,
				    struct device *dev,
				    u32 pasid, struct iommu_domain *old)
{
	struct pt_iommu_x86_64_hw_info pt_info;
	unsigned int flags = 0;

	pt_iommu_x86_64_hw_info(&domain->fspt, &pt_info);
	if (WARN_ON(pt_info.levels != 4 && pt_info.levels != 5))
		return -EINVAL;

	if (pt_info.levels == 5)
		flags |= PASID_FLAG_FL5LP;

	if (domain->force_snooping)
		flags |= PASID_FLAG_PAGE_SNOOP;

	if (!(domain->fspt.x86_64_pt.common.features &
	      BIT(PT_FEAT_DMA_INCOHERENT)))
		flags |= PASID_FLAG_PWSNP;

	return __domain_setup_first_level(iommu, dev, pasid,
					  domain_id_iommu(domain, iommu),
					  pt_info.gcr3_pt, flags, old);
}

static int dmar_domain_attach_device(struct dmar_domain *domain,
				     struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	unsigned long flags;
	int ret;

	ret = domain_attach_iommu(domain, iommu);
	if (ret)
		return ret;

	info->domain = domain;
	info->domain_attached = true;
	spin_lock_irqsave(&domain->lock, flags);
	list_add(&info->link, &domain->devices);
	spin_unlock_irqrestore(&domain->lock, flags);

	if (dev_is_real_dma_subdevice(dev))
		return 0;

	if (!sm_supported(iommu))
		ret = domain_context_mapping(domain, dev);
	else if (intel_domain_is_fs_paging(domain))
		ret = domain_setup_first_level(iommu, domain, dev,
					       IOMMU_NO_PASID, NULL);
	else if (intel_domain_is_ss_paging(domain))
		ret = domain_setup_second_level(iommu, domain, dev,
						IOMMU_NO_PASID, NULL);
	else if (WARN_ON(true))
		ret = -EINVAL;

	if (ret)
		goto out_block_translation;

	ret = cache_tag_assign_domain(domain, dev, IOMMU_NO_PASID);
	if (ret)
		goto out_block_translation;

	return 0;

out_block_translation:
	device_block_translation(dev);
	return ret;
}

/**
 * device_rmrr_is_relaxable - Test whether the RMRR of this device
 * is relaxable (ie. is allowed to be not enforced under some conditions)
 * @dev: device handle
 *
 * We assume that PCI USB devices with RMRRs have them largely
 * for historical reasons and that the RMRR space is not actively used post
 * boot.  This exclusion may change if vendors begin to abuse it.
 *
 * The same exception is made for graphics devices, with the requirement that
 * any use of the RMRR regions will be torn down before assigning the device
 * to a guest.
 *
 * Return: true if the RMRR is relaxable, false otherwise
 */
static bool device_rmrr_is_relaxable(struct device *dev)
{
	struct pci_dev *pdev;

	if (!dev_is_pci(dev))
		return false;

	pdev = to_pci_dev(dev);
	if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
		return true;
	else
		return false;
}

static int device_def_domain_type(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;

	/*
	 * Hardware does not support the passthrough translation mode.
	 * Always use a dynamaic mapping domain.
	 */
	if (!ecap_pass_through(iommu->ecap))
		return IOMMU_DOMAIN_DMA;

	if (dev_is_pci(dev)) {
		struct pci_dev *pdev = to_pci_dev(dev);

		if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev))
			return IOMMU_DOMAIN_IDENTITY;
	}

	return 0;
}

static void intel_iommu_init_qi(struct intel_iommu *iommu)
{
	/*
	 * Start from the sane iommu hardware state.
	 * If the queued invalidation is already initialized by us
	 * (for example, while enabling interrupt-remapping) then
	 * we got the things already rolling from a sane state.
	 */
	if (!iommu->qi) {
		/*
		 * Clear any previous faults.
		 */
		dmar_fault(-1, iommu);
		/*
		 * Disable queued invalidation if supported and already enabled
		 * before OS handover.
		 */
		dmar_disable_qi(iommu);
	}

	if (dmar_enable_qi(iommu)) {
		/*
		 * Queued Invalidate not enabled, use Register Based Invalidate
		 */
		iommu->flush.flush_context = __iommu_flush_context;
		iommu->flush.flush_iotlb = __iommu_flush_iotlb;
		pr_info("%s: Using Register based invalidation\n",
			iommu->name);
	} else {
		iommu->flush.flush_context = qi_flush_context;
		iommu->flush.flush_iotlb = qi_flush_iotlb;
		pr_info("%s: Using Queued invalidation\n", iommu->name);
	}
}

static int copy_context_table(struct intel_iommu *iommu,
			      struct root_entry *old_re,
			      struct context_entry **tbl,
			      int bus, bool ext)
{
	int tbl_idx, tbl_slot = 0, idx, devfn, ret = 0, did;
	struct context_entry *new_ce = NULL, ce;
	struct context_entry *old_ce = NULL;
	struct root_entry re;
	phys_addr_t old_ce_phys;

	tbl_idx = ext ? bus * 2 : bus;
	memcpy(&re, old_re, sizeof(re));

	for (devfn = 0; devfn < 256; devfn++) {
		/* First calculate the correct index */
		idx = (ext ? devfn * 2 : devfn) % 256;

		if (idx == 0) {
			/* First save what we may have and clean up */
			if (new_ce) {
				tbl[tbl_idx + tbl_slot] = new_ce;
				__iommu_flush_cache(iommu, new_ce,
						    VTD_PAGE_SIZE);
			}

			if (old_ce)
				memunmap(old_ce);

			ret = 0;
			if (devfn < 0x80)
				old_ce_phys = root_entry_lctp(&re);
			else
				old_ce_phys = root_entry_uctp(&re);

			if (!old_ce_phys) {
				if (ext && devfn == 0) {
					/* No LCTP, try UCTP */
					devfn = 0x7f;
					continue;
				} else {
					goto out;
				}
			}

			/* Track if saving UCTP or LCTP entries in scalable mode */
			tbl_slot = ext && devfn >= 0x80 ? 1 : 0;

			ret = -ENOMEM;
			old_ce = memremap(old_ce_phys, PAGE_SIZE,
					MEMREMAP_WB);
			if (!old_ce)
				goto out;

			new_ce = iommu_alloc_pages_node_sz(iommu->node,
							   GFP_KERNEL, SZ_4K);
			if (!new_ce)
				goto out_unmap;

			ret = 0;
		}

		/* Now copy the context entry */
		memcpy(&ce, old_ce + idx, sizeof(ce));

		if (!context_present(&ce))
			continue;

		did = context_domain_id(&ce);
		if (did >= 0 && did < iommu->max_domain_id)
			ida_alloc_range(&iommu->domain_ida, did, did, GFP_KERNEL);

		set_context_copied(iommu, bus, devfn);
		new_ce[idx] = ce;
	}

	tbl[tbl_idx + tbl_slot] = new_ce;

	__iommu_flush_cache(iommu, new_ce, VTD_PAGE_SIZE);

out_unmap:
	memunmap(old_ce);

out:
	return ret;
}

static int copy_translation_tables(struct intel_iommu *iommu)
{
	struct context_entry **ctxt_tbls;
	struct root_entry *old_rt;
	phys_addr_t old_rt_phys;
	int ctxt_table_entries;
	u64 rtaddr_reg;
	int bus, ret;
	bool new_ext, ext;

	rtaddr_reg = readq(iommu->reg + DMAR_RTADDR_REG);
	ext        = !!(rtaddr_reg & DMA_RTADDR_SMT);
	new_ext    = !!sm_supported(iommu);

	/*
	 * The RTT bit can only be changed when translation is disabled,
	 * but disabling translation means to open a window for data
	 * corruption. So bail out and don't copy anything if we would
	 * have to change the bit.
	 */
	if (new_ext != ext)
		return -EINVAL;

	iommu->copied_tables = bitmap_zalloc(BIT_ULL(16), GFP_KERNEL);
	if (!iommu->copied_tables)
		return -ENOMEM;

	old_rt_phys = rtaddr_reg & VTD_PAGE_MASK;
	if (!old_rt_phys) {
		ret = -EINVAL;
		goto err_free_bitmap;
	}

	old_rt = memremap(old_rt_phys, PAGE_SIZE, MEMREMAP_WB);
	if (!old_rt) {
		ret = -ENOMEM;
		goto err_free_bitmap;
	}

	/* This is too big for the stack - allocate it from slab */
	ctxt_table_entries = ext ? 512 : 256;
	ret = -ENOMEM;
	ctxt_tbls = kcalloc(ctxt_table_entries, sizeof(void *), GFP_KERNEL);
	if (!ctxt_tbls)
		goto out_unmap;

	for (bus = 0; bus < 256; bus++) {
		ret = copy_context_table(iommu, &old_rt[bus],
					 ctxt_tbls, bus, ext);
		if (ret) {
			pr_err("%s: Failed to copy context table for bus %d\n",
				iommu->name, bus);
			continue;
		}
	}

	spin_lock(&iommu->lock);

	/* Context tables are copied, now write them to the root_entry table */
	for (bus = 0; bus < 256; bus++) {
		int idx = ext ? bus * 2 : bus;
		u64 val;

		if (ctxt_tbls[idx]) {
			val = virt_to_phys(ctxt_tbls[idx]) | 1;
			iommu->root_entry[bus].lo = val;
		}

		if (!ext || !ctxt_tbls[idx + 1])
			continue;

		val = virt_to_phys(ctxt_tbls[idx + 1]) | 1;
		iommu->root_entry[bus].hi = val;
	}

	spin_unlock(&iommu->lock);

	kfree(ctxt_tbls);

	__iommu_flush_cache(iommu, iommu->root_entry, PAGE_SIZE);

	memunmap(old_rt);
	return 0;

out_unmap:
	memunmap(old_rt);
err_free_bitmap:
	bitmap_free(iommu->copied_tables);
	iommu->copied_tables = NULL;
	return ret;
}

static int __init init_dmars(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	int ret;

	for_each_iommu(iommu, drhd) {
		if (drhd->ignored) {
			iommu_disable_translation(iommu);
			continue;
		}

		/*
		 * Find the max pasid size of all IOMMU's in the system.
		 * We need to ensure the system pasid table is no bigger
		 * than the smallest supported.
		 */
		if (pasid_supported(iommu)) {
			u32 temp = 2 << ecap_pss(iommu->ecap);

			intel_pasid_max_id = min_t(u32, temp,
						   intel_pasid_max_id);
		}

		intel_iommu_init_qi(iommu);
		init_translation_status(iommu);

		if (translation_pre_enabled(iommu) && !is_kdump_kernel()) {
			iommu_disable_translation(iommu);
			clear_translation_pre_enabled(iommu);
			pr_warn("Translation was enabled for %s but we are not in kdump mode\n",
				iommu->name);
		}

		/*
		 * TBD:
		 * we could share the same root & context tables
		 * among all IOMMU's. Need to Split it later.
		 */
		ret = iommu_alloc_root_entry(iommu);
		if (ret)
			goto free_iommu;

		if (translation_pre_enabled(iommu)) {
			pr_info("Translation already enabled - trying to copy translation structures\n");

			ret = copy_translation_tables(iommu);
			if (ret) {
				/*
				 * We found the IOMMU with translation
				 * enabled - but failed to copy over the
				 * old root-entry table. Try to proceed
				 * by disabling translation now and
				 * allocating a clean root-entry table.
				 * This might cause DMAR faults, but
				 * probably the dump will still succeed.
				 */
				pr_err("Failed to copy translation tables from previous kernel for %s\n",
				       iommu->name);
				iommu_disable_translation(iommu);
				clear_translation_pre_enabled(iommu);
			} else {
				pr_info("Copied translation tables from previous kernel for %s\n",
					iommu->name);
			}
		}

		intel_svm_check(iommu);
	}

	/*
	 * Now that qi is enabled on all iommus, set the root entry and flush
	 * caches. This is required on some Intel X58 chipsets, otherwise the
	 * flush_context function will loop forever and the boot hangs.
	 */
	for_each_active_iommu(iommu, drhd) {
		iommu_flush_write_buffer(iommu);
		iommu_set_root_entry(iommu);
	}

	check_tylersburg_isoch();

	/*
	 * for each drhd
	 *   enable fault log
	 *   global invalidate context cache
	 *   global invalidate iotlb
	 *   enable translation
	 */
	for_each_iommu(iommu, drhd) {
		if (drhd->ignored) {
			/*
			 * we always have to disable PMRs or DMA may fail on
			 * this device
			 */
			if (dmar_policy_force_on())
				iommu_disable_protect_mem_regions(iommu);
			continue;
		}

		iommu_flush_write_buffer(iommu);

		if (ecap_prs(iommu->ecap)) {
			/*
			 * Call dmar_alloc_hwirq() with dmar_global_lock held,
			 * could cause possible lock race condition.
			 */
			up_write(&dmar_global_lock);
			ret = intel_iommu_enable_prq(iommu);
			down_write(&dmar_global_lock);
			if (ret)
				goto free_iommu;
		}

		ret = dmar_set_interrupt(iommu);
		if (ret)
			goto free_iommu;
	}

	return 0;

free_iommu:
	for_each_active_iommu(iommu, drhd) {
		disable_dmar_iommu(iommu);
		free_dmar_iommu(iommu);
	}

	return ret;
}

static void __init init_no_remapping_devices(void)
{
	struct dmar_drhd_unit *drhd;
	struct device *dev;
	int i;

	for_each_drhd_unit(drhd) {
		if (!drhd->include_all) {
			for_each_active_dev_scope(drhd->devices,
						  drhd->devices_cnt, i, dev)
				break;
			/* ignore DMAR unit if no devices exist */
			if (i == drhd->devices_cnt)
				drhd->ignored = 1;
		}
	}

	for_each_active_drhd_unit(drhd) {
		if (drhd->include_all)
			continue;

		for_each_active_dev_scope(drhd->devices,
					  drhd->devices_cnt, i, dev)
			if (!dev_is_pci(dev) || !IS_GFX_DEVICE(to_pci_dev(dev)))
				break;
		if (i < drhd->devices_cnt)
			continue;

		/* This IOMMU has *only* gfx devices. Either bypass it or
		   set the gfx_mapped flag, as appropriate */
		drhd->gfx_dedicated = 1;
		if (disable_igfx_iommu)
			drhd->ignored = 1;
	}
}

#ifdef CONFIG_SUSPEND
static int init_iommu_hw(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;
	int ret;

	for_each_active_iommu(iommu, drhd) {
		if (iommu->qi) {
			ret = dmar_reenable_qi(iommu);
			if (ret)
				return ret;
		}
	}

	for_each_iommu(iommu, drhd) {
		if (drhd->ignored) {
			/*
			 * we always have to disable PMRs or DMA may fail on
			 * this device
			 */
			if (dmar_policy_force_on())
				iommu_disable_protect_mem_regions(iommu);
			continue;
		}

		iommu_flush_write_buffer(iommu);
		iommu_set_root_entry(iommu);
		iommu_enable_translation(iommu);
		iommu_disable_protect_mem_regions(iommu);
	}

	return 0;
}

static void iommu_flush_all(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;

	for_each_active_iommu(iommu, drhd) {
		iommu->flush.flush_context(iommu, 0, 0, 0,
					   DMA_CCMD_GLOBAL_INVL);
		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
					 DMA_TLB_GLOBAL_FLUSH);
	}
}

static int iommu_suspend(void *data)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;
	unsigned long flag;

	iommu_flush_all();

	for_each_active_iommu(iommu, drhd) {
		iommu_disable_translation(iommu);

		raw_spin_lock_irqsave(&iommu->register_lock, flag);

		iommu->iommu_state[SR_DMAR_FECTL_REG] =
			readl(iommu->reg + DMAR_FECTL_REG);
		iommu->iommu_state[SR_DMAR_FEDATA_REG] =
			readl(iommu->reg + DMAR_FEDATA_REG);
		iommu->iommu_state[SR_DMAR_FEADDR_REG] =
			readl(iommu->reg + DMAR_FEADDR_REG);
		iommu->iommu_state[SR_DMAR_FEUADDR_REG] =
			readl(iommu->reg + DMAR_FEUADDR_REG);

		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
	}
	return 0;
}

static void iommu_resume(void *data)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;
	unsigned long flag;

	if (init_iommu_hw()) {
		if (dmar_policy_force_on())
			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
		else
			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
		return;
	}

	for_each_active_iommu(iommu, drhd) {

		raw_spin_lock_irqsave(&iommu->register_lock, flag);

		writel(iommu->iommu_state[SR_DMAR_FECTL_REG],
			iommu->reg + DMAR_FECTL_REG);
		writel(iommu->iommu_state[SR_DMAR_FEDATA_REG],
			iommu->reg + DMAR_FEDATA_REG);
		writel(iommu->iommu_state[SR_DMAR_FEADDR_REG],
			iommu->reg + DMAR_FEADDR_REG);
		writel(iommu->iommu_state[SR_DMAR_FEUADDR_REG],
			iommu->reg + DMAR_FEUADDR_REG);

		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
	}
}

static const struct syscore_ops iommu_syscore_ops = {
	.resume		= iommu_resume,
	.suspend	= iommu_suspend,
};

static struct syscore iommu_syscore = {
	.ops = &iommu_syscore_ops,
};

static void __init init_iommu_pm_ops(void)
{
	register_syscore(&iommu_syscore);
}

#else
static inline void init_iommu_pm_ops(void) {}
#endif	/* CONFIG_PM */

static int __init rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
{
	if (!IS_ALIGNED(rmrr->base_address, PAGE_SIZE) ||
	    !IS_ALIGNED(rmrr->end_address + 1, PAGE_SIZE) ||
	    rmrr->end_address <= rmrr->base_address ||
	    arch_rmrr_sanity_check(rmrr))
		return -EINVAL;

	return 0;
}

int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
{
	struct acpi_dmar_reserved_memory *rmrr;
	struct dmar_rmrr_unit *rmrru;

	rmrr = (struct acpi_dmar_reserved_memory *)header;
	if (rmrr_sanity_check(rmrr)) {
		pr_warn(FW_BUG
			   "Your BIOS is broken; bad RMRR [%#018Lx-%#018Lx]\n"
			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
			   rmrr->base_address, rmrr->end_address,
			   dmi_get_system_info(DMI_BIOS_VENDOR),
			   dmi_get_system_info(DMI_BIOS_VERSION),
			   dmi_get_system_info(DMI_PRODUCT_VERSION));
		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
	}

	rmrru = kzalloc_obj(*rmrru);
	if (!rmrru)
		goto out;

	rmrru->hdr = header;

	rmrru->base_address = rmrr->base_address;
	rmrru->end_address = rmrr->end_address;

	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
				((void *)rmrr) + rmrr->header.length,
				&rmrru->devices_cnt);
	if (rmrru->devices_cnt && rmrru->devices == NULL)
		goto free_rmrru;

	list_add(&rmrru->list, &dmar_rmrr_units);

	return 0;
free_rmrru:
	kfree(rmrru);
out:
	return -ENOMEM;
}

static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
{
	struct dmar_atsr_unit *atsru;
	struct acpi_dmar_atsr *tmp;

	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list,
				dmar_rcu_check()) {
		tmp = (struct acpi_dmar_atsr *)atsru->hdr;
		if (atsr->segment != tmp->segment)
			continue;
		if (atsr->header.length != tmp->header.length)
			continue;
		if (memcmp(atsr, tmp, atsr->header.length) == 0)
			return atsru;
	}

	return NULL;
}

int dmar_parse_one_atsr(struct acpi_dmar_header *hdr, void *arg)
{
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled)
		return 0;

	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
	atsru = dmar_find_atsr(atsr);
	if (atsru)
		return 0;

	atsru = kzalloc(sizeof(*atsru) + hdr->length, GFP_KERNEL);
	if (!atsru)
		return -ENOMEM;

	/*
	 * If memory is allocated from slab by ACPI _DSM method, we need to
	 * copy the memory content because the memory buffer will be freed
	 * on return.
	 */
	atsru->hdr = (void *)(atsru + 1);
	memcpy(atsru->hdr, hdr, hdr->length);
	atsru->include_all = atsr->flags & 0x1;
	if (!atsru->include_all) {
		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
				(void *)atsr + atsr->header.length,
				&atsru->devices_cnt);
		if (atsru->devices_cnt && atsru->devices == NULL) {
			kfree(atsru);
			return -ENOMEM;
		}
	}

	list_add_rcu(&atsru->list, &dmar_atsr_units);

	return 0;
}

static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
{
	dmar_free_dev_scope(&atsru->devices, &atsru->devices_cnt);
	kfree(atsru);
}

int dmar_release_one_atsr(struct acpi_dmar_header *hdr, void *arg)
{
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
	atsru = dmar_find_atsr(atsr);
	if (atsru) {
		list_del_rcu(&atsru->list);
		synchronize_rcu();
		intel_iommu_free_atsr(atsru);
	}

	return 0;
}

int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg)
{
	int i;
	struct device *dev;
	struct acpi_dmar_atsr *atsr;
	struct dmar_atsr_unit *atsru;

	atsr = container_of(hdr, struct acpi_dmar_atsr, header);
	atsru = dmar_find_atsr(atsr);
	if (!atsru)
		return 0;

	if (!atsru->include_all && atsru->devices && atsru->devices_cnt) {
		for_each_active_dev_scope(atsru->devices, atsru->devices_cnt,
					  i, dev)
			return -EBUSY;
	}

	return 0;
}

static struct dmar_satc_unit *dmar_find_satc(struct acpi_dmar_satc *satc)
{
	struct dmar_satc_unit *satcu;
	struct acpi_dmar_satc *tmp;

	list_for_each_entry_rcu(satcu, &dmar_satc_units, list,
				dmar_rcu_check()) {
		tmp = (struct acpi_dmar_satc *)satcu->hdr;
		if (satc->segment != tmp->segment)
			continue;
		if (satc->header.length != tmp->header.length)
			continue;
		if (memcmp(satc, tmp, satc->header.length) == 0)
			return satcu;
	}

	return NULL;
}

int dmar_parse_one_satc(struct acpi_dmar_header *hdr, void *arg)
{
	struct acpi_dmar_satc *satc;
	struct dmar_satc_unit *satcu;

	if (system_state >= SYSTEM_RUNNING && !intel_iommu_enabled)
		return 0;

	satc = container_of(hdr, struct acpi_dmar_satc, header);
	satcu = dmar_find_satc(satc);
	if (satcu)
		return 0;

	satcu = kzalloc(sizeof(*satcu) + hdr->length, GFP_KERNEL);
	if (!satcu)
		return -ENOMEM;

	satcu->hdr = (void *)(satcu + 1);
	memcpy(satcu->hdr, hdr, hdr->length);
	satcu->atc_required = satc->flags & 0x1;
	satcu->devices = dmar_alloc_dev_scope((void *)(satc + 1),
					      (void *)satc + satc->header.length,
					      &satcu->devices_cnt);
	if (satcu->devices_cnt && !satcu->devices) {
		kfree(satcu);
		return -ENOMEM;
	}
	list_add_rcu(&satcu->list, &dmar_satc_units);

	return 0;
}

static int intel_iommu_add(struct dmar_drhd_unit *dmaru)
{
	struct intel_iommu *iommu = dmaru->iommu;
	int ret;

	/*
	 * Disable translation if already enabled prior to OS handover.
	 */
	if (iommu->gcmd & DMA_GCMD_TE)
		iommu_disable_translation(iommu);

	ret = iommu_alloc_root_entry(iommu);
	if (ret)
		goto out;

	intel_svm_check(iommu);

	if (dmaru->ignored) {
		/*
		 * we always have to disable PMRs or DMA may fail on this device
		 */
		if (dmar_policy_force_on())
			iommu_disable_protect_mem_regions(iommu);
		return 0;
	}

	intel_iommu_init_qi(iommu);
	iommu_flush_write_buffer(iommu);

	if (ecap_prs(iommu->ecap)) {
		ret = intel_iommu_enable_prq(iommu);
		if (ret)
			goto disable_iommu;
	}

	ret = dmar_set_interrupt(iommu);
	if (ret)
		goto disable_iommu;

	iommu_set_root_entry(iommu);
	iommu_enable_translation(iommu);

	iommu_disable_protect_mem_regions(iommu);
	return 0;

disable_iommu:
	disable_dmar_iommu(iommu);
out:
	free_dmar_iommu(iommu);
	return ret;
}

int dmar_iommu_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
{
	int ret = 0;
	struct intel_iommu *iommu = dmaru->iommu;

	if (!intel_iommu_enabled)
		return 0;
	if (iommu == NULL)
		return -EINVAL;

	if (insert) {
		ret = intel_iommu_add(dmaru);
	} else {
		disable_dmar_iommu(iommu);
		free_dmar_iommu(iommu);
	}

	return ret;
}

static void intel_iommu_free_dmars(void)
{
	struct dmar_rmrr_unit *rmrru, *rmrr_n;
	struct dmar_atsr_unit *atsru, *atsr_n;
	struct dmar_satc_unit *satcu, *satc_n;

	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
		list_del(&rmrru->list);
		dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
		kfree(rmrru);
	}

	list_for_each_entry_safe(atsru, atsr_n, &dmar_atsr_units, list) {
		list_del(&atsru->list);
		intel_iommu_free_atsr(atsru);
	}
	list_for_each_entry_safe(satcu, satc_n, &dmar_satc_units, list) {
		list_del(&satcu->list);
		dmar_free_dev_scope(&satcu->devices, &satcu->devices_cnt);
		kfree(satcu);
	}
}

static struct dmar_satc_unit *dmar_find_matched_satc_unit(struct pci_dev *dev)
{
	struct dmar_satc_unit *satcu;
	struct acpi_dmar_satc *satc;
	struct device *tmp;
	int i;

	rcu_read_lock();

	list_for_each_entry_rcu(satcu, &dmar_satc_units, list) {
		satc = container_of(satcu->hdr, struct acpi_dmar_satc, header);
		if (satc->segment != pci_domain_nr(dev->bus))
			continue;
		for_each_dev_scope(satcu->devices, satcu->devices_cnt, i, tmp)
			if (to_pci_dev(tmp) == dev)
				goto out;
	}
	satcu = NULL;
out:
	rcu_read_unlock();
	return satcu;
}

static bool dmar_ats_supported(struct pci_dev *dev, struct intel_iommu *iommu)
{
	struct pci_dev *bridge = NULL;
	struct dmar_atsr_unit *atsru;
	struct dmar_satc_unit *satcu;
	struct acpi_dmar_atsr *atsr;
	bool supported = true;
	struct pci_bus *bus;
	struct device *tmp;
	int i;

	dev = pci_physfn(dev);
	satcu = dmar_find_matched_satc_unit(dev);
	if (satcu)
		/*
		 * This device supports ATS as it is in SATC table.
		 * When IOMMU is in legacy mode, enabling ATS is done
		 * automatically by HW for the device that requires
		 * ATS, hence OS should not enable this device ATS
		 * to avoid duplicated TLB invalidation.
		 */
		return !(satcu->atc_required && !sm_supported(iommu));

	for (bus = dev->bus; bus; bus = bus->parent) {
		bridge = bus->self;
		/* If it's an integrated device, allow ATS */
		if (!bridge)
			return true;
		/* Connected via non-PCIe: no ATS */
		if (!pci_is_pcie(bridge) ||
		    pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE)
			return false;
		/* If we found the root port, look it up in the ATSR */
		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT)
			break;
	}

	rcu_read_lock();
	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
		if (atsr->segment != pci_domain_nr(dev->bus))
			continue;

		for_each_dev_scope(atsru->devices, atsru->devices_cnt, i, tmp)
			if (tmp == &bridge->dev)
				goto out;

		if (atsru->include_all)
			goto out;
	}
	supported = false;
out:
	rcu_read_unlock();

	return supported;
}

int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
{
	int ret;
	struct dmar_rmrr_unit *rmrru;
	struct dmar_atsr_unit *atsru;
	struct dmar_satc_unit *satcu;
	struct acpi_dmar_atsr *atsr;
	struct acpi_dmar_reserved_memory *rmrr;
	struct acpi_dmar_satc *satc;

	if (!intel_iommu_enabled && system_state >= SYSTEM_RUNNING)
		return 0;

	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
		rmrr = container_of(rmrru->hdr,
				    struct acpi_dmar_reserved_memory, header);
		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
			ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1),
				((void *)rmrr) + rmrr->header.length,
				rmrr->segment, rmrru->devices,
				rmrru->devices_cnt);
			if (ret < 0)
				return ret;
		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
			dmar_remove_dev_scope(info, rmrr->segment,
				rmrru->devices, rmrru->devices_cnt);
		}
	}

	list_for_each_entry(atsru, &dmar_atsr_units, list) {
		if (atsru->include_all)
			continue;

		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
			ret = dmar_insert_dev_scope(info, (void *)(atsr + 1),
					(void *)atsr + atsr->header.length,
					atsr->segment, atsru->devices,
					atsru->devices_cnt);
			if (ret > 0)
				break;
			else if (ret < 0)
				return ret;
		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
			if (dmar_remove_dev_scope(info, atsr->segment,
					atsru->devices, atsru->devices_cnt))
				break;
		}
	}
	list_for_each_entry(satcu, &dmar_satc_units, list) {
		satc = container_of(satcu->hdr, struct acpi_dmar_satc, header);
		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
			ret = dmar_insert_dev_scope(info, (void *)(satc + 1),
					(void *)satc + satc->header.length,
					satc->segment, satcu->devices,
					satcu->devices_cnt);
			if (ret > 0)
				break;
			else if (ret < 0)
				return ret;
		} else if (info->event == BUS_NOTIFY_REMOVED_DEVICE) {
			if (dmar_remove_dev_scope(info, satc->segment,
					satcu->devices, satcu->devices_cnt))
				break;
		}
	}

	return 0;
}

static void intel_disable_iommus(void)
{
	struct intel_iommu *iommu = NULL;
	struct dmar_drhd_unit *drhd;

	for_each_iommu(iommu, drhd)
		iommu_disable_translation(iommu);
}

void intel_iommu_shutdown(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;

	if (dmar_policy_off())
		return;

	/*
	 * All other CPUs were brought down, hotplug interrupts were disabled,
	 * no lock and RCU checking needed anymore
	 */
	list_for_each_entry(drhd, &dmar_drhd_units, list) {
		iommu = drhd->iommu;

		/* Disable PMRs explicitly here. */
		iommu_disable_protect_mem_regions(iommu);

		/* Make sure the IOMMUs are switched off */
		iommu_disable_translation(iommu);
	}
}

static struct intel_iommu *dev_to_intel_iommu(struct device *dev)
{
	struct iommu_device *iommu_dev = dev_to_iommu_device(dev);

	return container_of(iommu_dev, struct intel_iommu, iommu);
}

static ssize_t version_show(struct device *dev,
			    struct device_attribute *attr, char *buf)
{
	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
	u32 ver = readl(iommu->reg + DMAR_VER_REG);
	return sysfs_emit(buf, "%d:%d\n",
			  DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver));
}
static DEVICE_ATTR_RO(version);

static ssize_t address_show(struct device *dev,
			    struct device_attribute *attr, char *buf)
{
	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
	return sysfs_emit(buf, "%llx\n", iommu->reg_phys);
}
static DEVICE_ATTR_RO(address);

static ssize_t cap_show(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
	return sysfs_emit(buf, "%llx\n", iommu->cap);
}
static DEVICE_ATTR_RO(cap);

static ssize_t ecap_show(struct device *dev,
			 struct device_attribute *attr, char *buf)
{
	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
	return sysfs_emit(buf, "%llx\n", iommu->ecap);
}
static DEVICE_ATTR_RO(ecap);

static ssize_t domains_supported_show(struct device *dev,
				      struct device_attribute *attr, char *buf)
{
	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
	return sysfs_emit(buf, "%ld\n", iommu->max_domain_id);
}
static DEVICE_ATTR_RO(domains_supported);

static ssize_t domains_used_show(struct device *dev,
				 struct device_attribute *attr, char *buf)
{
	struct intel_iommu *iommu = dev_to_intel_iommu(dev);
	unsigned int count = 0;
	int id;

	for (id = 0; id < iommu->max_domain_id; id++)
		if (ida_exists(&iommu->domain_ida, id))
			count++;

	return sysfs_emit(buf, "%d\n", count);
}
static DEVICE_ATTR_RO(domains_used);

static struct attribute *intel_iommu_attrs[] = {
	&dev_attr_version.attr,
	&dev_attr_address.attr,
	&dev_attr_cap.attr,
	&dev_attr_ecap.attr,
	&dev_attr_domains_supported.attr,
	&dev_attr_domains_used.attr,
	NULL,
};

static struct attribute_group intel_iommu_group = {
	.name = "intel-iommu",
	.attrs = intel_iommu_attrs,
};

const struct attribute_group *intel_iommu_groups[] = {
	&intel_iommu_group,
	NULL,
};

static bool has_external_pci(void)
{
	struct pci_dev *pdev = NULL;

	for_each_pci_dev(pdev)
		if (pdev->external_facing) {
			pci_dev_put(pdev);
			return true;
		}

	return false;
}

static void __init platform_optin_force_iommu(void)
{
	if (!dmar_platform_optin() || !dmar_can_force_on(DMAR_FORCEON_PLATFORM))
		return;

	if (!has_external_pci())
		return;

	/*
	 * If Intel-IOMMU is disabled by default, we will apply identity
	 * map for all devices except those marked as being untrusted.
	 */
	if (dmar_policy_off()) {
		pr_info("Intel-IOMMU force enabled due to platform opt in\n");
		iommu_set_default_passthrough(false);
	}

	/* No concurrent access to dmar_policy at this point. */
	dmar_policy = DMAR_FORCE_ON;
}

static int __init probe_acpi_namespace_devices(void)
{
	struct dmar_drhd_unit *drhd;
	/* To avoid a -Wunused-but-set-variable warning. */
	struct intel_iommu *iommu __maybe_unused;
	struct device *dev;
	int i, ret = 0;

	for_each_active_iommu(iommu, drhd) {
		for_each_active_dev_scope(drhd->devices,
					  drhd->devices_cnt, i, dev) {
			struct acpi_device_physical_node *pn;
			struct acpi_device *adev;

			if (dev->bus != &acpi_bus_type)
				continue;

			up_read(&dmar_global_lock);
			adev = to_acpi_device(dev);
			mutex_lock(&adev->physical_node_lock);
			list_for_each_entry(pn,
					    &adev->physical_node_list, node) {
				ret = iommu_probe_device(pn->dev);
				if (ret)
					break;
			}
			mutex_unlock(&adev->physical_node_lock);
			down_read(&dmar_global_lock);

			if (ret)
				return ret;
		}
	}

	return 0;
}

static __init void tboot_force_iommu(void)
{
	if (!tboot_enabled() || intel_iommu_tboot_noforce)
		return;

	if (!dmar_can_force_on(DMAR_FORCEON_TBOOT))
		panic("tboot: Failed to force IOMMU on\n");

	if (dmar_policy_off())
		pr_warn("Forcing Intel-IOMMU to enabled\n");

	/* No concurrent access to dmar_policy at this point. */
	dmar_policy = DMAR_FORCE_ON;
	no_iommu = 0;
}

int __init intel_iommu_init(void)
{
	int ret = -ENODEV;
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;

	/*
	 * Intel IOMMU is required for a TXT/tboot launch or platform
	 * opt in, so enforce that.
	 */
	tboot_force_iommu();
	if (!dmar_policy_force_on())
		platform_optin_force_iommu();

	down_write(&dmar_global_lock);
	if (dmar_table_init()) {
		if (dmar_policy_force_on())
			panic("tboot: Failed to initialize DMAR table\n");
		goto out_free_dmar;
	}

	if (dmar_dev_scope_init() < 0) {
		if (dmar_policy_force_on())
			panic("tboot: Failed to initialize DMAR device scope\n");
		goto out_free_dmar;
	}

	up_write(&dmar_global_lock);

	/*
	 * The bus notifier takes the dmar_global_lock, so lockdep will
	 * complain later when we register it under the lock.
	 */
	dmar_register_bus_notifier();

	down_write(&dmar_global_lock);

	if (!no_iommu)
		intel_iommu_debugfs_init();

	if (dmar_policy_off()) {
		/*
		 * We exit the function here to ensure IOMMU's remapping and
		 * mempool aren't setup, which means that the IOMMU's PMRs
		 * won't be disabled via the call to init_dmars(). So disable
		 * it explicitly here. The PMRs were setup by tboot prior to
		 * calling SENTER, but the kernel is expected to reset/tear
		 * down the PMRs.
		 */
		if (intel_iommu_tboot_noforce) {
			for_each_iommu(iommu, drhd)
				iommu_disable_protect_mem_regions(iommu);
		}

		/*
		 * Make sure the IOMMUs are switched off, even when we
		 * boot into a kexec kernel and the previous kernel left
		 * them enabled
		 */
		intel_disable_iommus();
		goto out_free_dmar;
	}

	if (list_empty(&dmar_rmrr_units))
		pr_info("No RMRR found\n");

	if (list_empty(&dmar_atsr_units))
		pr_info("No ATSR found\n");

	if (list_empty(&dmar_satc_units))
		pr_info("No SATC found\n");

	init_no_remapping_devices();

	ret = init_dmars();
	if (ret) {
		if (dmar_policy_force_on())
			panic("tboot: Failed to initialize DMARs\n");
		pr_err("Initialization failed\n");
		goto out_free_dmar;
	}
	up_write(&dmar_global_lock);

	init_iommu_pm_ops();

	down_read(&dmar_global_lock);
	for_each_active_iommu(iommu, drhd) {
		/*
		 * The flush queue implementation does not perform
		 * page-selective invalidations that are required for efficient
		 * TLB flushes in virtual environments.  The benefit of batching
		 * is likely to be much lower than the overhead of synchronizing
		 * the virtual and physical IOMMU page-tables.
		 */
		if (cap_caching_mode(iommu->cap) &&
		    !first_level_by_default(iommu)) {
			pr_info_once("IOMMU batching disallowed due to virtualization\n");
			iommu_set_dma_strict();
		}
		iommu_device_sysfs_add(&iommu->iommu, NULL,
				       intel_iommu_groups,
				       "%s", iommu->name);
		/*
		 * The iommu device probe is protected by the iommu_probe_device_lock.
		 * Release the dmar_global_lock before entering the device probe path
		 * to avoid unnecessary lock order splat.
		 */
		up_read(&dmar_global_lock);
		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
		down_read(&dmar_global_lock);

		iommu_pmu_register(iommu);
	}

	if (probe_acpi_namespace_devices())
		pr_warn("ACPI name space devices didn't probe correctly\n");

	/* Finally, we enable the DMA remapping hardware. */
	for_each_iommu(iommu, drhd) {
		if (!drhd->ignored && !translation_pre_enabled(iommu))
			iommu_enable_translation(iommu);

		iommu_disable_protect_mem_regions(iommu);
	}
	up_read(&dmar_global_lock);

	pr_info("Intel(R) Virtualization Technology for Directed I/O\n");

	intel_iommu_enabled = 1;

	return 0;

out_free_dmar:
	intel_iommu_free_dmars();
	up_write(&dmar_global_lock);
	return ret;
}

static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct device_domain_info *info = opaque;

	domain_context_clear_one(info, PCI_BUS_NUM(alias), alias & 0xff);
	return 0;
}

/*
 * NB - intel-iommu lacks any sort of reference counting for the users of
 * dependent devices.  If multiple endpoints have intersecting dependent
 * devices, unbinding the driver from any one of them will possibly leave
 * the others unable to operate.
 */
static void domain_context_clear(struct device_domain_info *info)
{
	if (!dev_is_pci(info->dev)) {
		domain_context_clear_one(info, info->bus, info->devfn);
		return;
	}

	pci_for_each_dma_alias(to_pci_dev(info->dev),
			       &domain_context_clear_one_cb, info);
	iommu_disable_pci_ats(info);
}

/*
 * Clear the page table pointer in context or pasid table entries so that
 * all DMA requests without PASID from the device are blocked. If the page
 * table has been set, clean up the data structures.
 */
void device_block_translation(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	unsigned long flags;

	/* Device in DMA blocking state. Noting to do. */
	if (!info->domain_attached)
		return;

	if (info->domain)
		cache_tag_unassign_domain(info->domain, dev, IOMMU_NO_PASID);

	if (!dev_is_real_dma_subdevice(dev)) {
		if (sm_supported(iommu))
			intel_pasid_tear_down_entry(iommu, dev,
						    IOMMU_NO_PASID, false);
		else
			domain_context_clear(info);
	}

	/* Device now in DMA blocking state. */
	info->domain_attached = false;

	if (!info->domain)
		return;

	spin_lock_irqsave(&info->domain->lock, flags);
	list_del(&info->link);
	spin_unlock_irqrestore(&info->domain->lock, flags);

	domain_detach_iommu(info->domain, iommu);
	info->domain = NULL;
}

static int blocking_domain_attach_dev(struct iommu_domain *domain,
				      struct device *dev,
				      struct iommu_domain *old)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);

	iopf_for_domain_remove(info->domain ? &info->domain->domain : NULL, dev);
	device_block_translation(dev);
	return 0;
}

static int blocking_domain_set_dev_pasid(struct iommu_domain *domain,
					 struct device *dev, ioasid_t pasid,
					 struct iommu_domain *old);

static struct iommu_domain blocking_domain = {
	.type = IOMMU_DOMAIN_BLOCKED,
	.ops = &(const struct iommu_domain_ops) {
		.attach_dev	= blocking_domain_attach_dev,
		.set_dev_pasid	= blocking_domain_set_dev_pasid,
	}
};

static struct dmar_domain *paging_domain_alloc(void)
{
	struct dmar_domain *domain;

	domain = kzalloc_obj(*domain);
	if (!domain)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&domain->devices);
	INIT_LIST_HEAD(&domain->dev_pasids);
	INIT_LIST_HEAD(&domain->cache_tags);
	spin_lock_init(&domain->lock);
	spin_lock_init(&domain->cache_lock);
	xa_init(&domain->iommu_array);
	INIT_LIST_HEAD(&domain->s1_domains);
	spin_lock_init(&domain->s1_lock);

	return domain;
}

static unsigned int compute_vasz_lg2_fs(struct intel_iommu *iommu,
					unsigned int *top_level)
{
	unsigned int mgaw = cap_mgaw(iommu->cap);

	/*
	 * Spec 3.6 First-Stage Translation:
	 *
	 * Software must limit addresses to less than the minimum of MGAW
	 * and the lower canonical address width implied by FSPM (i.e.,
	 * 47-bit when FSPM is 4-level and 56-bit when FSPM is 5-level).
	 */
	if (mgaw > 48 && cap_fl5lp_support(iommu->cap)) {
		*top_level = 4;
		return min(57, mgaw);
	}

	/* Four level is always supported */
	*top_level = 3;
	return min(48, mgaw);
}

static struct iommu_domain *
intel_iommu_domain_alloc_first_stage(struct device *dev,
				     struct intel_iommu *iommu, u32 flags)
{
	struct pt_iommu_x86_64_cfg cfg = {};
	struct dmar_domain *dmar_domain;
	int ret;

	if (flags & ~IOMMU_HWPT_ALLOC_PASID)
		return ERR_PTR(-EOPNOTSUPP);

	/* Only SL is available in legacy mode */
	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
		return ERR_PTR(-EOPNOTSUPP);

	dmar_domain = paging_domain_alloc();
	if (IS_ERR(dmar_domain))
		return ERR_CAST(dmar_domain);

	cfg.common.hw_max_vasz_lg2 =
		compute_vasz_lg2_fs(iommu, &cfg.top_level);
	cfg.common.hw_max_oasz_lg2 = 52;
	cfg.common.features = BIT(PT_FEAT_SIGN_EXTEND) |
			      BIT(PT_FEAT_FLUSH_RANGE);
	/* First stage always uses scalable mode */
	if (!ecap_smpwc(iommu->ecap))
		cfg.common.features |= BIT(PT_FEAT_DMA_INCOHERENT);
	dmar_domain->iommu.iommu_device = dev;
	dmar_domain->iommu.nid = dev_to_node(dev);
	dmar_domain->domain.ops = &intel_fs_paging_domain_ops;
	/*
	 * iotlb sync for map is only needed for legacy implementations that
	 * explicitly require flushing internal write buffers to ensure memory
	 * coherence.
	 */
	if (rwbf_required(iommu))
		dmar_domain->iotlb_sync_map = true;

	ret = pt_iommu_x86_64_init(&dmar_domain->fspt, &cfg, GFP_KERNEL);
	if (ret) {
		kfree(dmar_domain);
		return ERR_PTR(ret);
	}

	if (!cap_fl1gp_support(iommu->cap))
		dmar_domain->domain.pgsize_bitmap &= ~(u64)SZ_1G;
	if (!intel_iommu_superpage)
		dmar_domain->domain.pgsize_bitmap = SZ_4K;

	return &dmar_domain->domain;
}

static unsigned int compute_vasz_lg2_ss(struct intel_iommu *iommu,
					unsigned int *top_level)
{
	unsigned int sagaw = cap_sagaw(iommu->cap);
	unsigned int mgaw = cap_mgaw(iommu->cap);

	/*
	 * Find the largest table size that both the mgaw and sagaw support.
	 * This sets the valid range of IOVA and the top starting level.
	 * Some HW may only support a 4 or 5 level walk but must limit IOVA to
	 * 3 levels.
	 */
	if (mgaw > 48 && sagaw >= BIT(3)) {
		*top_level = 4;
		return min(57, mgaw);
	} else if (mgaw > 39 && sagaw >= BIT(2)) {
		*top_level = 3 + ffs(sagaw >> 3);
		return min(48, mgaw);
	} else if (mgaw > 30 && sagaw >= BIT(1)) {
		*top_level = 2 + ffs(sagaw >> 2);
		return min(39, mgaw);
	}
	return 0;
}

static const struct iommu_dirty_ops intel_second_stage_dirty_ops = {
	IOMMU_PT_DIRTY_OPS(vtdss),
	.set_dirty_tracking = intel_iommu_set_dirty_tracking,
};

static struct iommu_domain *
intel_iommu_domain_alloc_second_stage(struct device *dev,
				      struct intel_iommu *iommu, u32 flags)
{
	struct pt_iommu_vtdss_cfg cfg = {};
	struct dmar_domain *dmar_domain;
	unsigned int sslps;
	int ret;

	if (flags &
	    (~(IOMMU_HWPT_ALLOC_NEST_PARENT | IOMMU_HWPT_ALLOC_DIRTY_TRACKING |
	       IOMMU_HWPT_ALLOC_PASID)))
		return ERR_PTR(-EOPNOTSUPP);

	if (((flags & IOMMU_HWPT_ALLOC_NEST_PARENT) &&
	     !nested_supported(iommu)) ||
	    ((flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING) &&
	     !ssads_supported(iommu)))
		return ERR_PTR(-EOPNOTSUPP);

	/* Legacy mode always supports second stage */
	if (sm_supported(iommu) && !ecap_slts(iommu->ecap))
		return ERR_PTR(-EOPNOTSUPP);

	dmar_domain = paging_domain_alloc();
	if (IS_ERR(dmar_domain))
		return ERR_CAST(dmar_domain);

	cfg.common.hw_max_vasz_lg2 = compute_vasz_lg2_ss(iommu, &cfg.top_level);
	cfg.common.hw_max_oasz_lg2 = 52;
	cfg.common.features = BIT(PT_FEAT_FLUSH_RANGE);

	/*
	 * Read-only mapping is disallowed on the domain which serves as the
	 * parent in a nested configuration, due to HW errata
	 * (ERRATA_772415_SPR17)
	 */
	if (flags & IOMMU_HWPT_ALLOC_NEST_PARENT)
		cfg.common.features |= BIT(PT_FEAT_VTDSS_FORCE_WRITEABLE);

	if (!iommu_paging_structure_coherency(iommu))
		cfg.common.features |= BIT(PT_FEAT_DMA_INCOHERENT);
	dmar_domain->iommu.iommu_device = dev;
	dmar_domain->iommu.nid = dev_to_node(dev);
	dmar_domain->domain.ops = &intel_ss_paging_domain_ops;
	dmar_domain->nested_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;

	if (flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING)
		dmar_domain->domain.dirty_ops = &intel_second_stage_dirty_ops;

	ret = pt_iommu_vtdss_init(&dmar_domain->sspt, &cfg, GFP_KERNEL);
	if (ret) {
		kfree(dmar_domain);
		return ERR_PTR(ret);
	}

	/* Adjust the supported page sizes to HW capability */
	sslps = cap_super_page_val(iommu->cap);
	if (!(sslps & BIT(0)))
		dmar_domain->domain.pgsize_bitmap &= ~(u64)SZ_2M;
	if (!(sslps & BIT(1)))
		dmar_domain->domain.pgsize_bitmap &= ~(u64)SZ_1G;
	if (!intel_iommu_superpage)
		dmar_domain->domain.pgsize_bitmap = SZ_4K;

	/*
	 * Besides the internal write buffer flush, the caching mode used for
	 * legacy nested translation (which utilizes shadowing page tables)
	 * also requires iotlb sync on map.
	 */
	if (rwbf_required(iommu) || cap_caching_mode(iommu->cap))
		dmar_domain->iotlb_sync_map = true;

	return &dmar_domain->domain;
}

static struct iommu_domain *
intel_iommu_domain_alloc_paging_flags(struct device *dev, u32 flags,
				      const struct iommu_user_data *user_data)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	struct iommu_domain *domain;

	if (user_data)
		return ERR_PTR(-EOPNOTSUPP);

	/* Prefer first stage if possible by default. */
	domain = intel_iommu_domain_alloc_first_stage(dev, iommu, flags);
	if (domain != ERR_PTR(-EOPNOTSUPP))
		return domain;
	return intel_iommu_domain_alloc_second_stage(dev, iommu, flags);
}

static void intel_iommu_domain_free(struct iommu_domain *domain)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);

	if (WARN_ON(dmar_domain->nested_parent &&
		    !list_empty(&dmar_domain->s1_domains)))
		return;

	if (WARN_ON(!list_empty(&dmar_domain->devices)))
		return;

	pt_iommu_deinit(&dmar_domain->iommu);

	kfree(dmar_domain->qi_batch);
	kfree(dmar_domain);
}

static int paging_domain_compatible_first_stage(struct dmar_domain *dmar_domain,
						struct intel_iommu *iommu)
{
	if (WARN_ON(dmar_domain->domain.dirty_ops ||
		    dmar_domain->nested_parent))
		return -EINVAL;

	/* Only SL is available in legacy mode */
	if (!sm_supported(iommu) || !ecap_flts(iommu->ecap))
		return -EINVAL;

	if (!ecap_smpwc(iommu->ecap) &&
	    !(dmar_domain->fspt.x86_64_pt.common.features &
	      BIT(PT_FEAT_DMA_INCOHERENT)))
		return -EINVAL;

	/* Supports the number of table levels */
	if (!cap_fl5lp_support(iommu->cap) &&
	    dmar_domain->fspt.x86_64_pt.common.max_vasz_lg2 > 48)
		return -EINVAL;

	/* Same page size support */
	if (!cap_fl1gp_support(iommu->cap) &&
	    (dmar_domain->domain.pgsize_bitmap & SZ_1G))
		return -EINVAL;

	/* iotlb sync on map requirement */
	if ((rwbf_required(iommu)) && !dmar_domain->iotlb_sync_map)
		return -EINVAL;

	return 0;
}

static int
paging_domain_compatible_second_stage(struct dmar_domain *dmar_domain,
				      struct intel_iommu *iommu)
{
	unsigned int vasz_lg2 = dmar_domain->sspt.vtdss_pt.common.max_vasz_lg2;
	unsigned int sslps = cap_super_page_val(iommu->cap);
	struct pt_iommu_vtdss_hw_info pt_info;

	pt_iommu_vtdss_hw_info(&dmar_domain->sspt, &pt_info);

	if (dmar_domain->domain.dirty_ops && !ssads_supported(iommu))
		return -EINVAL;
	if (dmar_domain->nested_parent && !nested_supported(iommu))
		return -EINVAL;

	/* Legacy mode always supports second stage */
	if (sm_supported(iommu) && !ecap_slts(iommu->ecap))
		return -EINVAL;

	if (!iommu_paging_structure_coherency(iommu) &&
	    !(dmar_domain->sspt.vtdss_pt.common.features &
	      BIT(PT_FEAT_DMA_INCOHERENT)))
		return -EINVAL;

	/* Address width falls within the capability */
	if (cap_mgaw(iommu->cap) < vasz_lg2)
		return -EINVAL;

	/* Page table level is supported. */
	if (!(cap_sagaw(iommu->cap) & BIT(pt_info.aw)))
		return -EINVAL;

	/* Same page size support */
	if (!(sslps & BIT(0)) && (dmar_domain->domain.pgsize_bitmap & SZ_2M))
		return -EINVAL;
	if (!(sslps & BIT(1)) && (dmar_domain->domain.pgsize_bitmap & SZ_1G))
		return -EINVAL;

	/* iotlb sync on map requirement */
	if ((rwbf_required(iommu) || cap_caching_mode(iommu->cap)) &&
	    !dmar_domain->iotlb_sync_map)
		return -EINVAL;

	/*
	 * FIXME this is locked wrong, it needs to be under the
	 * dmar_domain->lock
	 */
	if ((dmar_domain->sspt.vtdss_pt.common.features &
	     BIT(PT_FEAT_VTDSS_FORCE_COHERENCE)) &&
	    !ecap_sc_support(iommu->ecap))
		return -EINVAL;
	return 0;
}

int paging_domain_compatible(struct iommu_domain *domain, struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct intel_iommu *iommu = info->iommu;
	int ret = -EINVAL;

	if (intel_domain_is_fs_paging(dmar_domain))
		ret = paging_domain_compatible_first_stage(dmar_domain, iommu);
	else if (intel_domain_is_ss_paging(dmar_domain))
		ret = paging_domain_compatible_second_stage(dmar_domain, iommu);
	else if (WARN_ON(true))
		ret = -EINVAL;
	if (ret)
		return ret;

	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) &&
	    context_copied(iommu, info->bus, info->devfn))
		return intel_pasid_setup_sm_context(dev);

	return 0;
}

static int intel_iommu_attach_device(struct iommu_domain *domain,
				     struct device *dev,
				     struct iommu_domain *old)
{
	int ret;

	device_block_translation(dev);

	ret = paging_domain_compatible(domain, dev);
	if (ret)
		return ret;

	ret = iopf_for_domain_replace(domain, old, dev);
	if (ret)
		return ret;

	ret = dmar_domain_attach_device(to_dmar_domain(domain), dev);
	if (ret)
		iopf_for_domain_replace(old, domain, dev);

	return ret;
}

static void intel_iommu_tlb_sync(struct iommu_domain *domain,
				 struct iommu_iotlb_gather *gather)
{
	cache_tag_flush_range(to_dmar_domain(domain), gather->start,
			      gather->end,
			      iommu_pages_list_empty(&gather->freelist));
	iommu_put_pages_list(&gather->freelist);
}

static bool domain_support_force_snooping(struct dmar_domain *domain)
{
	struct device_domain_info *info;
	bool support = true;

	assert_spin_locked(&domain->lock);
	list_for_each_entry(info, &domain->devices, link) {
		if (!ecap_sc_support(info->iommu->ecap)) {
			support = false;
			break;
		}
	}

	return support;
}

static bool intel_iommu_enforce_cache_coherency_fs(struct iommu_domain *domain)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct device_domain_info *info;

	guard(spinlock_irqsave)(&dmar_domain->lock);

	if (dmar_domain->force_snooping)
		return true;

	if (!domain_support_force_snooping(dmar_domain))
		return false;

	dmar_domain->force_snooping = true;
	list_for_each_entry(info, &dmar_domain->devices, link)
		intel_pasid_setup_page_snoop_control(info->iommu, info->dev,
						     IOMMU_NO_PASID);
	return true;
}

static bool intel_iommu_enforce_cache_coherency_ss(struct iommu_domain *domain)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);

	guard(spinlock_irqsave)(&dmar_domain->lock);
	if (!domain_support_force_snooping(dmar_domain))
		return false;

	/*
	 * Second level page table supports per-PTE snoop control. The
	 * iommu_map() interface will handle this by setting SNP bit.
	 */
	dmar_domain->sspt.vtdss_pt.common.features |=
		BIT(PT_FEAT_VTDSS_FORCE_COHERENCE);
	dmar_domain->force_snooping = true;
	return true;
}

static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);

	switch (cap) {
	case IOMMU_CAP_CACHE_COHERENCY:
		return true;
	case IOMMU_CAP_PRE_BOOT_PROTECTION:
		return dmar_platform_optin();
	case IOMMU_CAP_ENFORCE_CACHE_COHERENCY:
		return ecap_sc_support(info->iommu->ecap);
	case IOMMU_CAP_DIRTY_TRACKING:
		return ssads_supported(info->iommu);
	case IOMMU_CAP_PCI_ATS_SUPPORTED:
		return info->ats_supported;
	default:
		return false;
	}
}

static struct iommu_device *intel_iommu_probe_device(struct device *dev)
{
	struct pci_dev *pdev = dev_is_pci(dev) ? to_pci_dev(dev) : NULL;
	struct device_domain_info *info;
	struct intel_iommu *iommu;
	u8 bus, devfn;
	int ret;

	iommu = device_lookup_iommu(dev, &bus, &devfn);
	if (!iommu || !iommu->iommu.ops)
		return ERR_PTR(-ENODEV);

	info = kzalloc_obj(*info);
	if (!info)
		return ERR_PTR(-ENOMEM);

	if (dev_is_real_dma_subdevice(dev)) {
		info->bus = pdev->bus->number;
		info->devfn = pdev->devfn;
		info->segment = pci_domain_nr(pdev->bus);
	} else {
		info->bus = bus;
		info->devfn = devfn;
		info->segment = iommu->segment;
	}

	info->dev = dev;
	info->iommu = iommu;
	RB_CLEAR_NODE(&info->node);
	if (dev_is_pci(dev)) {
		if (ecap_dev_iotlb_support(iommu->ecap) &&
		    pci_ats_supported(pdev) &&
		    dmar_ats_supported(pdev, iommu)) {
			info->ats_supported = 1;
			info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev);

			/*
			 * For IOMMU that supports device IOTLB throttling
			 * (DIT), we assign PFSID to the invalidation desc
			 * of a VF such that IOMMU HW can gauge queue depth
			 * at PF level. If DIT is not set, PFSID will be
			 * treated as reserved, which should be set to 0.
			 */
			if (ecap_dit(iommu->ecap))
				info->pfsid = pci_dev_id(pci_physfn(pdev));
			info->ats_qdep = pci_ats_queue_depth(pdev);
		}
		if (sm_supported(iommu)) {
			if (pasid_supported(iommu)) {
				int features = pci_pasid_features(pdev);

				if (features >= 0)
					info->pasid_supported = features | 1;
			}

			if (info->ats_supported && ecap_prs(iommu->ecap) &&
			    ecap_pds(iommu->ecap) && pci_pri_supported(pdev))
				info->pri_supported = 1;
		}
	}

	dev_iommu_priv_set(dev, info);
	if (pdev && pci_ats_supported(pdev)) {
		ret = pci_prepare_ats(pdev, VTD_PAGE_SHIFT);
		if (ret)
			goto free;

		ret = device_rbtree_insert(iommu, info);
		if (ret)
			goto free;
	}

	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
		ret = intel_pasid_alloc_table(dev);
		if (ret) {
			dev_err(dev, "PASID table allocation failed\n");
			goto clear_rbtree;
		}

		if (!context_copied(iommu, info->bus, info->devfn)) {
			ret = intel_pasid_setup_sm_context(dev);
			if (ret)
				goto free_table;
		}
	}

	intel_iommu_debugfs_create_dev(info);

	return &iommu->iommu;
free_table:
	intel_pasid_teardown_sm_context(dev);
	intel_pasid_free_table(dev);
clear_rbtree:
	device_rbtree_remove(info);
free:
	kfree(info);

	return ERR_PTR(ret);
}

static void intel_iommu_probe_finalize(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;

	/*
	 * The PCIe spec, in its wisdom, declares that the behaviour of the
	 * device is undefined if you enable PASID support after ATS support.
	 * So always enable PASID support on devices which have it, even if
	 * we can't yet know if we're ever going to use it.
	 */
	if (info->pasid_supported &&
	    !pci_enable_pasid(to_pci_dev(dev), info->pasid_supported & ~1))
		info->pasid_enabled = 1;

	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) {
		iommu_enable_pci_ats(info);
		/* Assign a DEVTLB cache tag to the default domain. */
		if (info->ats_enabled && info->domain) {
			u16 did = domain_id_iommu(info->domain, iommu);

			if (cache_tag_assign(info->domain, did, dev,
					     IOMMU_NO_PASID, CACHE_TAG_DEVTLB))
				iommu_disable_pci_ats(info);
		}
	}
	iommu_enable_pci_pri(info);
}

static void intel_iommu_release_device(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;

	iommu_disable_pci_pri(info);
	iommu_disable_pci_ats(info);

	if (info->pasid_enabled) {
		pci_disable_pasid(to_pci_dev(dev));
		info->pasid_enabled = 0;
	}

	mutex_lock(&iommu->iopf_lock);
	if (dev_is_pci(dev) && pci_ats_supported(to_pci_dev(dev)))
		device_rbtree_remove(info);
	mutex_unlock(&iommu->iopf_lock);

	if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev) &&
	    !context_copied(iommu, info->bus, info->devfn))
		intel_pasid_teardown_sm_context(dev);

	intel_pasid_free_table(dev);
	intel_iommu_debugfs_remove_dev(info);
	kfree(info);
}

static void intel_iommu_get_resv_regions(struct device *device,
					 struct list_head *head)
{
	int prot = DMA_PTE_READ | DMA_PTE_WRITE;
	struct iommu_resv_region *reg;
	struct dmar_rmrr_unit *rmrr;
	struct device *i_dev;
	int i;

	rcu_read_lock();
	for_each_rmrr_units(rmrr) {
		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
					  i, i_dev) {
			struct iommu_resv_region *resv;
			enum iommu_resv_type type;
			size_t length;

			if (i_dev != device &&
			    !is_downstream_to_pci_bridge(device, i_dev))
				continue;

			length = rmrr->end_address - rmrr->base_address + 1;

			type = device_rmrr_is_relaxable(device) ?
				IOMMU_RESV_DIRECT_RELAXABLE : IOMMU_RESV_DIRECT;

			resv = iommu_alloc_resv_region(rmrr->base_address,
						       length, prot, type,
						       GFP_ATOMIC);
			if (!resv)
				break;

			list_add_tail(&resv->list, head);
		}
	}
	rcu_read_unlock();

#ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA
	if (dev_is_pci(device)) {
		struct pci_dev *pdev = to_pci_dev(device);

		if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) {
			reg = iommu_alloc_resv_region(0, 1UL << 24, prot,
					IOMMU_RESV_DIRECT_RELAXABLE,
					GFP_KERNEL);
			if (reg)
				list_add_tail(&reg->list, head);
		}
	}
#endif /* CONFIG_INTEL_IOMMU_FLOPPY_WA */

	reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
				      IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
				      0, IOMMU_RESV_MSI, GFP_KERNEL);
	if (!reg)
		return;
	list_add_tail(&reg->list, head);
}

static struct iommu_group *intel_iommu_device_group(struct device *dev)
{
	if (dev_is_pci(dev))
		return pci_device_group(dev);
	return generic_device_group(dev);
}

int intel_iommu_enable_iopf(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	int ret;

	if (!info->pri_enabled)
		return -ENODEV;

	/* pri_enabled is protected by the group mutex. */
	iommu_group_mutex_assert(dev);
	if (info->iopf_refcount) {
		info->iopf_refcount++;
		return 0;
	}

	ret = iopf_queue_add_device(iommu->iopf_queue, dev);
	if (ret)
		return ret;

	info->iopf_refcount = 1;

	return 0;
}

void intel_iommu_disable_iopf(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;

	if (WARN_ON(!info->pri_enabled || !info->iopf_refcount))
		return;

	iommu_group_mutex_assert(dev);
	if (--info->iopf_refcount)
		return;

	iopf_queue_remove_device(iommu->iopf_queue, dev);
}

static bool intel_iommu_is_attach_deferred(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);

	return translation_pre_enabled(info->iommu) && !info->domain;
}

/*
 * Check that the device does not live on an external facing PCI port that is
 * marked as untrusted. Such devices should not be able to apply quirks and
 * thus not be able to bypass the IOMMU restrictions.
 */
static bool risky_device(struct pci_dev *pdev)
{
	if (pdev->untrusted) {
		pci_info(pdev,
			 "Skipping IOMMU quirk for dev [%04X:%04X] on untrusted PCI link\n",
			 pdev->vendor, pdev->device);
		pci_info(pdev, "Please check with your BIOS/Platform vendor about this\n");
		return true;
	}
	return false;
}

static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
				      unsigned long iova, size_t size)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);

	if (dmar_domain->iotlb_sync_map)
		cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1);

	return 0;
}

void domain_remove_dev_pasid(struct iommu_domain *domain,
			     struct device *dev, ioasid_t pasid)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct dev_pasid_info *curr, *dev_pasid = NULL;
	struct intel_iommu *iommu = info->iommu;
	struct dmar_domain *dmar_domain;
	unsigned long flags;

	if (!domain)
		return;

	/* Identity domain and blocked domain have no meta data for pasid. */
	if (domain->type == IOMMU_DOMAIN_IDENTITY || domain->type == IOMMU_DOMAIN_BLOCKED)
		return;

	dmar_domain = to_dmar_domain(domain);
	spin_lock_irqsave(&dmar_domain->lock, flags);
	list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
		if (curr->dev == dev && curr->pasid == pasid) {
			list_del(&curr->link_domain);
			dev_pasid = curr;
			break;
		}
	}
	spin_unlock_irqrestore(&dmar_domain->lock, flags);

	if (WARN_ON_ONCE(!dev_pasid))
		return;

	cache_tag_unassign_domain(dmar_domain, dev, pasid);
	domain_detach_iommu(dmar_domain, iommu);
	intel_iommu_debugfs_remove_dev_pasid(dev_pasid);
	kfree(dev_pasid);
}

static int blocking_domain_set_dev_pasid(struct iommu_domain *domain,
					 struct device *dev, ioasid_t pasid,
					 struct iommu_domain *old)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);

	intel_pasid_tear_down_entry(info->iommu, dev, pasid, false);
	iopf_for_domain_remove(old, dev);
	domain_remove_dev_pasid(old, dev, pasid);

	return 0;
}

struct dev_pasid_info *
domain_add_dev_pasid(struct iommu_domain *domain,
		     struct device *dev, ioasid_t pasid)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct intel_iommu *iommu = info->iommu;
	struct dev_pasid_info *dev_pasid;
	unsigned long flags;
	int ret;

	dev_pasid = kzalloc_obj(*dev_pasid);
	if (!dev_pasid)
		return ERR_PTR(-ENOMEM);

	ret = domain_attach_iommu(dmar_domain, iommu);
	if (ret)
		goto out_free;

	ret = cache_tag_assign_domain(dmar_domain, dev, pasid);
	if (ret)
		goto out_detach_iommu;

	dev_pasid->dev = dev;
	dev_pasid->pasid = pasid;
	spin_lock_irqsave(&dmar_domain->lock, flags);
	list_add(&dev_pasid->link_domain, &dmar_domain->dev_pasids);
	spin_unlock_irqrestore(&dmar_domain->lock, flags);

	return dev_pasid;
out_detach_iommu:
	domain_detach_iommu(dmar_domain, iommu);
out_free:
	kfree(dev_pasid);
	return ERR_PTR(ret);
}

static int intel_iommu_set_dev_pasid(struct iommu_domain *domain,
				     struct device *dev, ioasid_t pasid,
				     struct iommu_domain *old)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	struct intel_iommu *iommu = info->iommu;
	struct dev_pasid_info *dev_pasid;
	int ret;

	if (WARN_ON_ONCE(!(domain->type & __IOMMU_DOMAIN_PAGING)))
		return -EINVAL;

	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
		return -EOPNOTSUPP;

	if (context_copied(iommu, info->bus, info->devfn))
		return -EBUSY;

	ret = paging_domain_compatible(domain, dev);
	if (ret)
		return ret;

	dev_pasid = domain_add_dev_pasid(domain, dev, pasid);
	if (IS_ERR(dev_pasid))
		return PTR_ERR(dev_pasid);

	ret = iopf_for_domain_replace(domain, old, dev);
	if (ret)
		goto out_remove_dev_pasid;

	if (intel_domain_is_fs_paging(dmar_domain))
		ret = domain_setup_first_level(iommu, dmar_domain,
					       dev, pasid, old);
	else if (intel_domain_is_ss_paging(dmar_domain))
		ret = domain_setup_second_level(iommu, dmar_domain,
						dev, pasid, old);
	else if (WARN_ON(true))
		ret = -EINVAL;

	if (ret)
		goto out_unwind_iopf;

	domain_remove_dev_pasid(old, dev, pasid);

	intel_iommu_debugfs_create_dev_pasid(dev_pasid);

	return 0;

out_unwind_iopf:
	iopf_for_domain_replace(old, domain, dev);
out_remove_dev_pasid:
	domain_remove_dev_pasid(domain, dev, pasid);
	return ret;
}

static void *intel_iommu_hw_info(struct device *dev, u32 *length,
				 enum iommu_hw_info_type *type)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	struct iommu_hw_info_vtd *vtd;

	if (*type != IOMMU_HW_INFO_TYPE_DEFAULT &&
	    *type != IOMMU_HW_INFO_TYPE_INTEL_VTD)
		return ERR_PTR(-EOPNOTSUPP);

	vtd = kzalloc_obj(*vtd);
	if (!vtd)
		return ERR_PTR(-ENOMEM);

	vtd->flags = IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17;
	vtd->cap_reg = iommu->cap;
	vtd->ecap_reg = iommu->ecap;
	*length = sizeof(*vtd);
	*type = IOMMU_HW_INFO_TYPE_INTEL_VTD;
	return vtd;
}

/* Set dirty tracking for the devices that the domain has been attached. */
static int domain_set_dirty_tracking(struct dmar_domain *domain, bool enable)
{
	struct device_domain_info *info;
	struct dev_pasid_info *dev_pasid;
	int ret = 0;

	lockdep_assert_held(&domain->lock);

	list_for_each_entry(info, &domain->devices, link) {
		ret = intel_pasid_setup_dirty_tracking(info->iommu, info->dev,
						       IOMMU_NO_PASID, enable);
		if (ret)
			return ret;
	}

	list_for_each_entry(dev_pasid, &domain->dev_pasids, link_domain) {
		info = dev_iommu_priv_get(dev_pasid->dev);
		ret = intel_pasid_setup_dirty_tracking(info->iommu, info->dev,
						       dev_pasid->pasid, enable);
		if (ret)
			break;
	}

	return ret;
}

static int parent_domain_set_dirty_tracking(struct dmar_domain *domain,
					    bool enable)
{
	struct dmar_domain *s1_domain;
	unsigned long flags;
	int ret;

	spin_lock(&domain->s1_lock);
	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
		spin_lock_irqsave(&s1_domain->lock, flags);
		ret = domain_set_dirty_tracking(s1_domain, enable);
		spin_unlock_irqrestore(&s1_domain->lock, flags);
		if (ret)
			goto err_unwind;
	}
	spin_unlock(&domain->s1_lock);
	return 0;

err_unwind:
	list_for_each_entry(s1_domain, &domain->s1_domains, s2_link) {
		spin_lock_irqsave(&s1_domain->lock, flags);
		domain_set_dirty_tracking(s1_domain, domain->dirty_tracking);
		spin_unlock_irqrestore(&s1_domain->lock, flags);
	}
	spin_unlock(&domain->s1_lock);
	return ret;
}

static int intel_iommu_set_dirty_tracking(struct iommu_domain *domain,
					  bool enable)
{
	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
	int ret;

	spin_lock(&dmar_domain->lock);
	if (dmar_domain->dirty_tracking == enable)
		goto out_unlock;

	ret = domain_set_dirty_tracking(dmar_domain, enable);
	if (ret)
		goto err_unwind;

	if (dmar_domain->nested_parent) {
		ret = parent_domain_set_dirty_tracking(dmar_domain, enable);
		if (ret)
			goto err_unwind;
	}

	dmar_domain->dirty_tracking = enable;
out_unlock:
	spin_unlock(&dmar_domain->lock);

	return 0;

err_unwind:
	domain_set_dirty_tracking(dmar_domain, dmar_domain->dirty_tracking);
	spin_unlock(&dmar_domain->lock);
	return ret;
}

static int context_setup_pass_through(struct device *dev, u8 bus, u8 devfn)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	struct context_entry *context;

	spin_lock(&iommu->lock);
	context = iommu_context_addr(iommu, bus, devfn, 1);
	if (!context) {
		spin_unlock(&iommu->lock);
		return -ENOMEM;
	}

	if (context_present(context) && !context_copied(iommu, bus, devfn)) {
		spin_unlock(&iommu->lock);
		return 0;
	}

	copied_context_tear_down(iommu, context, bus, devfn);
	context_clear_entry(context);
	context_set_domain_id(context, FLPT_DEFAULT_DID);

	/*
	 * In pass through mode, AW must be programmed to indicate the largest
	 * AGAW value supported by hardware. And ASR is ignored by hardware.
	 */
	context_set_address_width(context, iommu->msagaw);
	context_set_translation_type(context, CONTEXT_TT_PASS_THROUGH);
	context_set_fault_enable(context);
	context_set_present(context);
	if (!ecap_coherent(iommu->ecap))
		clflush_cache_range(context, sizeof(*context));
	context_present_cache_flush(iommu, FLPT_DEFAULT_DID, bus, devfn);
	spin_unlock(&iommu->lock);

	return 0;
}

static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *data)
{
	struct device *dev = data;

	return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
}

static int device_setup_pass_through(struct device *dev)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);

	if (!dev_is_pci(dev))
		return context_setup_pass_through(dev, info->bus, info->devfn);

	return pci_for_each_dma_alias(to_pci_dev(dev),
				      context_setup_pass_through_cb, dev);
}

static int identity_domain_attach_dev(struct iommu_domain *domain,
				      struct device *dev,
				      struct iommu_domain *old)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	int ret;

	device_block_translation(dev);

	if (dev_is_real_dma_subdevice(dev))
		return 0;

	/*
	 * The identity domain has no iopf_handler, so no IOPF reference is
	 * taken for it.  The reference held by the old domain must still be
	 * released here; putting the device in the blocking state above does
	 * not affect the IOPF reference count.
	 */
	iopf_for_domain_remove(old, dev);

	if (sm_supported(iommu))
		ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
	else
		ret = device_setup_pass_through(dev);

	if (!ret)
		info->domain_attached = true;

	return ret;
}

static int identity_domain_set_dev_pasid(struct iommu_domain *domain,
					 struct device *dev, ioasid_t pasid,
					 struct iommu_domain *old)
{
	struct device_domain_info *info = dev_iommu_priv_get(dev);
	struct intel_iommu *iommu = info->iommu;
	int ret;

	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
		return -EOPNOTSUPP;

	ret = iopf_for_domain_replace(domain, old, dev);
	if (ret)
		return ret;

	ret = domain_setup_passthrough(iommu, dev, pasid, old);
	if (ret) {
		iopf_for_domain_replace(old, domain, dev);
		return ret;
	}

	domain_remove_dev_pasid(old, dev, pasid);
	return 0;
}

static struct iommu_domain identity_domain = {
	.type = IOMMU_DOMAIN_IDENTITY,
	.ops = &(const struct iommu_domain_ops) {
		.attach_dev	= identity_domain_attach_dev,
		.set_dev_pasid	= identity_domain_set_dev_pasid,
	},
};

const struct iommu_domain_ops intel_fs_paging_domain_ops = {
	IOMMU_PT_DOMAIN_OPS(x86_64),
	.attach_dev = intel_iommu_attach_device,
	.set_dev_pasid = intel_iommu_set_dev_pasid,
	.iotlb_sync_map = intel_iommu_iotlb_sync_map,
	.flush_iotlb_all = intel_flush_iotlb_all,
	.iotlb_sync = intel_iommu_tlb_sync,
	.free = intel_iommu_domain_free,
	.enforce_cache_coherency = intel_iommu_enforce_cache_coherency_fs,
};

const struct iommu_domain_ops intel_ss_paging_domain_ops = {
	IOMMU_PT_DOMAIN_OPS(vtdss),
	.attach_dev = intel_iommu_attach_device,
	.set_dev_pasid = intel_iommu_set_dev_pasid,
	.iotlb_sync_map = intel_iommu_iotlb_sync_map,
	.flush_iotlb_all = intel_flush_iotlb_all,
	.iotlb_sync = intel_iommu_tlb_sync,
	.free = intel_iommu_domain_free,
	.enforce_cache_coherency = intel_iommu_enforce_cache_coherency_ss,
};

const struct iommu_ops intel_iommu_ops = {
	.blocked_domain		= &blocking_domain,
	.release_domain		= &blocking_domain,
	.identity_domain	= &identity_domain,
	.capable		= intel_iommu_capable,
	.hw_info		= intel_iommu_hw_info,
	.domain_alloc_paging_flags = intel_iommu_domain_alloc_paging_flags,
	.domain_alloc_sva	= intel_svm_domain_alloc,
	.domain_alloc_nested	= intel_iommu_domain_alloc_nested,
	.probe_device		= intel_iommu_probe_device,
	.probe_finalize		= intel_iommu_probe_finalize,
	.release_device		= intel_iommu_release_device,
	.get_resv_regions	= intel_iommu_get_resv_regions,
	.device_group		= intel_iommu_device_group,
	.is_attach_deferred	= intel_iommu_is_attach_deferred,
	.def_domain_type	= device_def_domain_type,
	.page_response		= intel_iommu_page_response,
};

static void quirk_iommu_igfx(struct pci_dev *dev)
{
	if (risky_device(dev))
		return;

	pci_info(dev, "Disabling IOMMU for graphics on this chipset\n");
	disable_igfx_iommu = 1;
}

/* Q35 integrated gfx dmar support is totally busted. */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x29b2, quirk_iommu_igfx);

/* G4x/GM45 integrated gfx dmar support is totally busted. */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_igfx);

/* QM57/QS57 integrated gfx malfunctions with dmar */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0044, quirk_iommu_igfx);

/* Broadwell igfx malfunctions with dmar */
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1606, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160B, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160E, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1602, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160A, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x160D, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1616, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161B, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161E, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1612, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161A, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x161D, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1626, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162B, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162E, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1622, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162A, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x162D, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1636, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163B, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163E, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1632, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163A, quirk_iommu_igfx);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x163D, quirk_iommu_igfx);

static void quirk_iommu_rwbf(struct pci_dev *dev)
{
	if (risky_device(dev))
		return;

	/*
	 * Mobile 4 Series Chipset neglects to set RWBF capability,
	 * but needs it. Same seems to hold for the desktop versions.
	 */
	pci_info(dev, "Forcing write-buffer flush capability\n");
	rwbf_quirk = 1;
}

DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e00, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e10, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e20, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e30, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e40, quirk_iommu_rwbf);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e90, quirk_iommu_rwbf);

#define GGC 0x52
#define GGC_MEMORY_SIZE_MASK	(0xf << 8)
#define GGC_MEMORY_SIZE_NONE	(0x0 << 8)
#define GGC_MEMORY_SIZE_1M	(0x1 << 8)
#define GGC_MEMORY_SIZE_2M	(0x3 << 8)
#define GGC_MEMORY_VT_ENABLED	(0x8 << 8)
#define GGC_MEMORY_SIZE_2M_VT	(0x9 << 8)
#define GGC_MEMORY_SIZE_3M_VT	(0xa << 8)
#define GGC_MEMORY_SIZE_4M_VT	(0xb << 8)

static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
{
	unsigned short ggc;

	if (risky_device(dev))
		return;

	if (pci_read_config_word(dev, GGC, &ggc))
		return;

	if (!(ggc & GGC_MEMORY_VT_ENABLED)) {
		pci_info(dev, "BIOS has allocated no shadow GTT; disabling IOMMU for graphics\n");
		disable_igfx_iommu = 1;
	} else if (!disable_igfx_iommu) {
		/* we have to ensure the gfx device is idle before we flush */
		pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n");
		iommu_set_dma_strict();
	}
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0062, quirk_calpella_no_shadow_gtt);
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x006a, quirk_calpella_no_shadow_gtt);

static void quirk_igfx_skip_te_disable(struct pci_dev *dev)
{
	unsigned short ver;

	if (!IS_GFX_DEVICE(dev))
		return;

	ver = (dev->device >> 8) & 0xff;
	if (ver != 0x45 && ver != 0x46 && ver != 0x4c &&
	    ver != 0x4e && ver != 0x8a && ver != 0x98 &&
	    ver != 0x9a && ver != 0xa7 && ver != 0x7d)
		return;

	if (risky_device(dev))
		return;

	pci_info(dev, "Skip IOMMU disabling for graphics\n");
	iommu_skip_te_disable = 1;
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, quirk_igfx_skip_te_disable);

/* On Tylersburg chipsets, some BIOSes have been known to enable the
   ISOCH DMAR unit for the Azalia sound device, but not give it any
   TLB entries, which causes it to deadlock. Check for that.  We do
   this in a function called from init_dmars(), instead of in a PCI
   quirk, because we don't want to print the obnoxious "BIOS broken"
   message if VT-d is actually disabled.
*/
static void __init check_tylersburg_isoch(void)
{
	struct pci_dev *pdev;
	uint32_t vtisochctrl;

	/* If there's no Azalia in the system anyway, forget it. */
	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x3a3e, NULL);
	if (!pdev)
		return;

	if (risky_device(pdev)) {
		pci_dev_put(pdev);
		return;
	}

	pci_dev_put(pdev);

	/* System Management Registers. Might be hidden, in which case
	   we can't do the sanity check. But that's OK, because the
	   known-broken BIOSes _don't_ actually hide it, so far. */
	pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x342e, NULL);
	if (!pdev)
		return;

	if (risky_device(pdev)) {
		pci_dev_put(pdev);
		return;
	}

	if (pci_read_config_dword(pdev, 0x188, &vtisochctrl)) {
		pci_dev_put(pdev);
		return;
	}

	pci_dev_put(pdev);

	/* If Azalia DMA is routed to the non-isoch DMAR unit, fine. */
	if (vtisochctrl & 1)
		return;

	/* Drop all bits other than the number of TLB entries */
	vtisochctrl &= 0x1c;

	/* If we have the recommended number of TLB entries (16), fine. */
	if (vtisochctrl == 0x10)
		return;

	/* Zero TLB entries? You get to ride the short bus to school. */
	if (!vtisochctrl) {
		WARN(1, "Your BIOS is broken; DMA routed to ISOCH DMAR unit but no TLB space.\n"
		     "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
		     dmi_get_system_info(DMI_BIOS_VENDOR),
		     dmi_get_system_info(DMI_BIOS_VERSION),
		     dmi_get_system_info(DMI_PRODUCT_VERSION));
		iommu_identity_mapping |= IDENTMAP_AZALIA;
		return;
	}

	pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n",
	       vtisochctrl);
}

/*
 * Here we deal with a device TLB defect where device may inadvertently issue ATS
 * invalidation completion before posted writes initiated with translated address
 * that utilized translations matching the invalidation address range, violating
 * the invalidation completion ordering.
 * Therefore, any use cases that cannot guarantee DMA is stopped before unmap is
 * vulnerable to this defect. In other words, any dTLB invalidation initiated not
 * under the control of the trusted/privileged host device driver must use this
 * quirk.
 * Device TLBs are invalidated under the following six conditions:
 * 1. Device driver does DMA API unmap IOVA
 * 2. Device driver unbind a PASID from a process, sva_unbind_device()
 * 3. PASID is torn down, after PASID cache is flushed. e.g. process
 *    exit_mmap() due to crash
 * 4. Under SVA usage, called by mmu_notifier.invalidate_range() where
 *    VM has to free pages that were unmapped
 * 5. Userspace driver unmaps a DMA buffer
 * 6. Cache invalidation in vSVA usage (upcoming)
 *
 * For #1 and #2, device drivers are responsible for stopping DMA traffic
 * before unmap/unbind. For #3, iommu driver gets mmu_notifier to
 * invalidate TLB the same way as normal user unmap which will use this quirk.
 * The dTLB invalidation after PASID cache flush does not need this quirk.
 *
 * As a reminder, #6 will *NEED* this quirk as we enable nested translation.
 */
void quirk_extra_dev_tlb_flush(struct device_domain_info *info,
			       unsigned long address, unsigned long mask,
			       u32 pasid, u16 qdep)
{
	u16 sid;

	if (likely(!info->dtlb_extra_inval))
		return;

	sid = PCI_DEVID(info->bus, info->devfn);
	if (pasid == IOMMU_NO_PASID) {
		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
				   qdep, address, mask);
	} else {
		qi_flush_dev_iotlb_pasid(info->iommu, sid, info->pfsid,
					 pasid, qdep, address, mask);
	}
}

#define ecmd_get_status_code(res)	(((res) & 0xff) >> 1)

/*
 * Function to submit a command to the enhanced command interface. The
 * valid enhanced command descriptions are defined in Table 47 of the
 * VT-d spec. The VT-d hardware implementation may support some but not
 * all commands, which can be determined by checking the Enhanced
 * Command Capability Register.
 *
 * Return values:
 *  - 0: Command successful without any error;
 *  - Negative: software error value;
 *  - Nonzero positive: failure status code defined in Table 48.
 */
int ecmd_submit_sync(struct intel_iommu *iommu, u8 ecmd, u64 oa, u64 ob)
{
	unsigned long flags;
	u64 res;
	int ret;

	if (!cap_ecmds(iommu->cap))
		return -ENODEV;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);

	res = readq(iommu->reg + DMAR_ECRSP_REG);
	if (res & DMA_ECMD_ECRSP_IP) {
		ret = -EBUSY;
		goto err;
	}

	/*
	 * Unconditionally write the operand B, because
	 * - There is no side effect if an ecmd doesn't require an
	 *   operand B, but we set the register to some value.
	 * - It's not invoked in any critical path. The extra MMIO
	 *   write doesn't bring any performance concerns.
	 */
	writeq(ob, iommu->reg + DMAR_ECEO_REG);
	writeq(ecmd | (oa << DMA_ECMD_OA_SHIFT), iommu->reg + DMAR_ECMD_REG);

	IOMMU_WAIT_OP(iommu, DMAR_ECRSP_REG, readq,
		      !(res & DMA_ECMD_ECRSP_IP), res);

	if (res & DMA_ECMD_ECRSP_IP) {
		ret = -ETIMEDOUT;
		goto err;
	}

	ret = ecmd_get_status_code(res);
err:
	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);

	return ret;
}

MODULE_IMPORT_NS("GENERIC_PT_IOMMU");