1 files changed, 1181 insertions, 394 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 98ba927aee1a..c92088855450 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -9,22 +9,33 @@
  */
 
 #include <linux/acpi_iort.h>
+#include <linux/atomic.h>
+#include <linux/crash_dump.h>
 #include <linux/device.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dma-iommu.h>
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
+#include <linux/iommu-dma.h>
 #include <linux/iova.h>
 #include <linux/irq.h>
+#include <linux/list_sort.h>
+#include <linux/memremap.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/msi.h>
+#include <linux/of_iommu.h>
 #include <linux/pci.h>
-#include <linux/swiotlb.h>
+#include <linux/pci-p2pdma.h>
 #include <linux/scatterlist.h>
+#include <linux/spinlock.h>
+#include <linux/swiotlb.h>
 #include <linux/vmalloc.h>
-#include <linux/crash_dump.h>
-#include <linux/dma-direct.h>
+#include <trace/events/swiotlb.h>
+
+#include "dma-iommu.h"
+#include "iommu-pages.h"
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -32,23 +43,42 @@ struct iommu_dma_msi_page {
 	phys_addr_t		phys;
 };
 
-enum iommu_dma_cookie_type {
-	IOMMU_DMA_IOVA_COOKIE,
-	IOMMU_DMA_MSI_COOKIE,
+enum iommu_dma_queue_type {
+	IOMMU_DMA_OPTS_PER_CPU_QUEUE,
+	IOMMU_DMA_OPTS_SINGLE_QUEUE,
+};
+
+struct iommu_dma_options {
+	enum iommu_dma_queue_type qt;
+	size_t		fq_size;
+	unsigned int	fq_timeout;
 };
 
 struct iommu_dma_cookie {
-	enum iommu_dma_cookie_type	type;
+	struct iova_domain iovad;
+	struct list_head msi_page_list;
+	/* Flush queue */
 	union {
-		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
-		struct iova_domain	iovad;
-		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
-		dma_addr_t		msi_iova;
+		struct iova_fq *single_fq;
+		struct iova_fq __percpu *percpu_fq;
 	};
-	struct list_head		msi_page_list;
-
+	/* Number of TLB flushes that have been started */
+	atomic64_t fq_flush_start_cnt;
+	/* Number of TLB flushes that have been finished */
+	atomic64_t fq_flush_finish_cnt;
+	/* Timer to regularily empty the flush queues */
+	struct timer_list fq_timer;
+	/* 1 when timer is active, 0 when not */
+	atomic_t fq_timer_on;
 	/* Domain for flush queue callback; NULL if flush queue not in use */
-	struct iommu_domain		*fq_domain;
+	struct iommu_domain *fq_domain;
+	/* Options for dma-iommu use */
+	struct iommu_dma_options options;
+};
+
+struct iommu_dma_msi_cookie {
+	dma_addr_t msi_iova;
+	struct list_head msi_page_list;
 };
 
 static DEFINE_STATIC_KEY_FALSE(iommu_deferred_attach_enabled);
@@ -64,56 +94,293 @@ static int __init iommu_dma_forcedac_setup(char *str)
 }
 early_param("iommu.forcedac", iommu_dma_forcedac_setup);
 
-static void iommu_dma_entry_dtor(unsigned long data)
+/* Number of entries per flush queue */
+#define IOVA_DEFAULT_FQ_SIZE	256
+#define IOVA_SINGLE_FQ_SIZE	32768
+
+/* Timeout (in ms) after which entries are flushed from the queue */
+#define IOVA_DEFAULT_FQ_TIMEOUT	10
+#define IOVA_SINGLE_FQ_TIMEOUT	1000
+
+/* Flush queue entry for deferred flushing */
+struct iova_fq_entry {
+	unsigned long iova_pfn;
+	unsigned long pages;
+	struct iommu_pages_list freelist;
+	u64 counter; /* Flush counter when this entry was added */
+};
+
+/* Per-CPU flush queue structure */
+struct iova_fq {
+	spinlock_t lock;
+	unsigned int head, tail;
+	unsigned int mod_mask;
+	struct iova_fq_entry entries[];
+};
+
+#define fq_ring_for_each(i, fq) \
+	for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) & (fq)->mod_mask)
+
+static inline bool fq_full(struct iova_fq *fq)
+{
+	assert_spin_locked(&fq->lock);
+	return (((fq->tail + 1) & fq->mod_mask) == fq->head);
+}
+
+static inline unsigned int fq_ring_add(struct iova_fq *fq)
 {
-	struct page *freelist = (struct page *)data;
+	unsigned int idx = fq->tail;
 
-	while (freelist) {
-		unsigned long p = (unsigned long)page_address(freelist);
+	assert_spin_locked(&fq->lock);
 
-		freelist = freelist->freelist;
-		free_page(p);
+	fq->tail = (idx + 1) & fq->mod_mask;
+
+	return idx;
+}
+
+static void fq_ring_free_locked(struct iommu_dma_cookie *cookie, struct iova_fq *fq)
+{
+	u64 counter = atomic64_read(&cookie->fq_flush_finish_cnt);
+	unsigned int idx;
+
+	assert_spin_locked(&fq->lock);
+
+	fq_ring_for_each(idx, fq) {
+
+		if (fq->entries[idx].counter >= counter)
+			break;
+
+		iommu_put_pages_list(&fq->entries[idx].freelist);
+		free_iova_fast(&cookie->iovad,
+			       fq->entries[idx].iova_pfn,
+			       fq->entries[idx].pages);
+
+		fq->entries[idx].freelist =
+			IOMMU_PAGES_LIST_INIT(fq->entries[idx].freelist);
+		fq->head = (fq->head + 1) & fq->mod_mask;
 	}
 }
 
-static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
+static void fq_ring_free(struct iommu_dma_cookie *cookie, struct iova_fq *fq)
 {
-	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
-		return cookie->iovad.granule;
-	return PAGE_SIZE;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fq->lock, flags);
+	fq_ring_free_locked(cookie, fq);
+	spin_unlock_irqrestore(&fq->lock, flags);
 }
 
-static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
+static void fq_flush_iotlb(struct iommu_dma_cookie *cookie)
 {
-	struct iommu_dma_cookie *cookie;
+	atomic64_inc(&cookie->fq_flush_start_cnt);
+	cookie->fq_domain->ops->flush_iotlb_all(cookie->fq_domain);
+	atomic64_inc(&cookie->fq_flush_finish_cnt);
+}
 
-	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
-	if (cookie) {
-		INIT_LIST_HEAD(&cookie->msi_page_list);
-		cookie->type = type;
+static void fq_flush_timeout(struct timer_list *t)
+{
+	struct iommu_dma_cookie *cookie = timer_container_of(cookie, t,
+							     fq_timer);
+	int cpu;
+
+	atomic_set(&cookie->fq_timer_on, 0);
+	fq_flush_iotlb(cookie);
+
+	if (cookie->options.qt == IOMMU_DMA_OPTS_SINGLE_QUEUE) {
+		fq_ring_free(cookie, cookie->single_fq);
+	} else {
+		for_each_possible_cpu(cpu)
+			fq_ring_free(cookie, per_cpu_ptr(cookie->percpu_fq, cpu));
+	}
+}
+
+static void queue_iova(struct iommu_dma_cookie *cookie,
+		unsigned long pfn, unsigned long pages,
+		struct iommu_pages_list *freelist)
+{
+	struct iova_fq *fq;
+	unsigned long flags;
+	unsigned int idx;
+
+	/*
+	 * Order against the IOMMU driver's pagetable update from unmapping
+	 * @pte, to guarantee that fq_flush_iotlb() observes that if called
+	 * from a different CPU before we release the lock below. Full barrier
+	 * so it also pairs with iommu_dma_init_fq() to avoid seeing partially
+	 * written fq state here.
+	 */
+	smp_mb();
+
+	if (cookie->options.qt == IOMMU_DMA_OPTS_SINGLE_QUEUE)
+		fq = cookie->single_fq;
+	else
+		fq = raw_cpu_ptr(cookie->percpu_fq);
+
+	spin_lock_irqsave(&fq->lock, flags);
+
+	/*
+	 * First remove all entries from the flush queue that have already been
+	 * flushed out on another CPU. This makes the fq_full() check below less
+	 * likely to be true.
+	 */
+	fq_ring_free_locked(cookie, fq);
+
+	if (fq_full(fq)) {
+		fq_flush_iotlb(cookie);
+		fq_ring_free_locked(cookie, fq);
+	}
+
+	idx = fq_ring_add(fq);
+
+	fq->entries[idx].iova_pfn = pfn;
+	fq->entries[idx].pages    = pages;
+	fq->entries[idx].counter  = atomic64_read(&cookie->fq_flush_start_cnt);
+	iommu_pages_list_splice(freelist, &fq->entries[idx].freelist);
+
+	spin_unlock_irqrestore(&fq->lock, flags);
+
+	/* Avoid false sharing as much as possible. */
+	if (!atomic_read(&cookie->fq_timer_on) &&
+	    !atomic_xchg(&cookie->fq_timer_on, 1))
+		mod_timer(&cookie->fq_timer,
+			  jiffies + msecs_to_jiffies(cookie->options.fq_timeout));
+}
+
+static void iommu_dma_free_fq_single(struct iova_fq *fq)
+{
+	int idx;
+
+	fq_ring_for_each(idx, fq)
+		iommu_put_pages_list(&fq->entries[idx].freelist);
+	vfree(fq);
+}
+
+static void iommu_dma_free_fq_percpu(struct iova_fq __percpu *percpu_fq)
+{
+	int cpu, idx;
+
+	/* The IOVAs will be torn down separately, so just free our queued pages */
+	for_each_possible_cpu(cpu) {
+		struct iova_fq *fq = per_cpu_ptr(percpu_fq, cpu);
+
+		fq_ring_for_each(idx, fq)
+			iommu_put_pages_list(&fq->entries[idx].freelist);
 	}
-	return cookie;
+
+	free_percpu(percpu_fq);
+}
+
+static void iommu_dma_free_fq(struct iommu_dma_cookie *cookie)
+{
+	if (!cookie->fq_domain)
+		return;
+
+	timer_delete_sync(&cookie->fq_timer);
+	if (cookie->options.qt == IOMMU_DMA_OPTS_SINGLE_QUEUE)
+		iommu_dma_free_fq_single(cookie->single_fq);
+	else
+		iommu_dma_free_fq_percpu(cookie->percpu_fq);
+}
+
+static void iommu_dma_init_one_fq(struct iova_fq *fq, size_t fq_size)
+{
+	int i;
+
+	fq->head = 0;
+	fq->tail = 0;
+	fq->mod_mask = fq_size - 1;
+
+	spin_lock_init(&fq->lock);
+
+	for (i = 0; i < fq_size; i++)
+		fq->entries[i].freelist =
+			IOMMU_PAGES_LIST_INIT(fq->entries[i].freelist);
+}
+
+static int iommu_dma_init_fq_single(struct iommu_dma_cookie *cookie)
+{
+	size_t fq_size = cookie->options.fq_size;
+	struct iova_fq *queue;
+
+	queue = vmalloc(struct_size(queue, entries, fq_size));
+	if (!queue)
+		return -ENOMEM;
+	iommu_dma_init_one_fq(queue, fq_size);
+	cookie->single_fq = queue;
+
+	return 0;
+}
+
+static int iommu_dma_init_fq_percpu(struct iommu_dma_cookie *cookie)
+{
+	size_t fq_size = cookie->options.fq_size;
+	struct iova_fq __percpu *queue;
+	int cpu;
+
+	queue = __alloc_percpu(struct_size(queue, entries, fq_size),
+			       __alignof__(*queue));
+	if (!queue)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu)
+		iommu_dma_init_one_fq(per_cpu_ptr(queue, cpu), fq_size);
+	cookie->percpu_fq = queue;
+	return 0;
+}
+
+/* sysfs updates are serialised by the mutex of the group owning @domain */
+int iommu_dma_init_fq(struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	int rc;
+
+	if (cookie->fq_domain)
+		return 0;
+
+	atomic64_set(&cookie->fq_flush_start_cnt,  0);
+	atomic64_set(&cookie->fq_flush_finish_cnt, 0);
+
+	if (cookie->options.qt == IOMMU_DMA_OPTS_SINGLE_QUEUE)
+		rc = iommu_dma_init_fq_single(cookie);
+	else
+		rc = iommu_dma_init_fq_percpu(cookie);
+
+	if (rc) {
+		pr_warn("iova flush queue initialization failed\n");
+		return -ENOMEM;
+	}
+
+	timer_setup(&cookie->fq_timer, fq_flush_timeout, 0);
+	atomic_set(&cookie->fq_timer_on, 0);
+	/*
+	 * Prevent incomplete fq state being observable. Pairs with path from
+	 * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova()
+	 */
+	smp_wmb();
+	WRITE_ONCE(cookie->fq_domain, domain);
+	return 0;
 }
 
 /**
  * iommu_get_dma_cookie - Acquire DMA-API resources for a domain
  * @domain: IOMMU domain to prepare for DMA-API usage
- *
- * IOMMU drivers should normally call this from their domain_alloc
- * callback when domain->type == IOMMU_DOMAIN_DMA.
  */
 int iommu_get_dma_cookie(struct iommu_domain *domain)
 {
-	if (domain->iova_cookie)
+	struct iommu_dma_cookie *cookie;
+
+	if (domain->cookie_type != IOMMU_COOKIE_NONE)
 		return -EEXIST;
 
-	domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
-	if (!domain->iova_cookie)
+	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	if (!cookie)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&cookie->msi_page_list);
+	domain->cookie_type = IOMMU_COOKIE_DMA_IOVA;
+	domain->iova_cookie = cookie;
 	return 0;
 }
-EXPORT_SYMBOL(iommu_get_dma_cookie);
 
 /**
  * iommu_get_msi_cookie - Acquire just MSI remapping resources
@@ -129,50 +396,57 @@ EXPORT_SYMBOL(iommu_get_dma_cookie);
  */
 int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
 {
-	struct iommu_dma_cookie *cookie;
+	struct iommu_dma_msi_cookie *cookie;
 
 	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
 		return -EINVAL;
 
-	if (domain->iova_cookie)
+	if (domain->cookie_type != IOMMU_COOKIE_NONE)
 		return -EEXIST;
 
-	cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
+	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
 	if (!cookie)
 		return -ENOMEM;
 
 	cookie->msi_iova = base;
-	domain->iova_cookie = cookie;
+	INIT_LIST_HEAD(&cookie->msi_page_list);
+	domain->cookie_type = IOMMU_COOKIE_DMA_MSI;
+	domain->msi_cookie = cookie;
 	return 0;
 }
 EXPORT_SYMBOL(iommu_get_msi_cookie);
 
 /**
  * iommu_put_dma_cookie - Release a domain's DMA mapping resources
- * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
- *          iommu_get_msi_cookie()
- *
- * IOMMU drivers should normally call this from their domain_free callback.
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
  */
 void iommu_put_dma_cookie(struct iommu_domain *domain)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iommu_dma_msi_page *msi, *tmp;
 
-	if (!cookie)
-		return;
-
-	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
+	if (cookie->iovad.granule) {
+		iommu_dma_free_fq(cookie);
 		put_iova_domain(&cookie->iovad);
+	}
+	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list)
+		kfree(msi);
+	kfree(cookie);
+}
 
-	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
-		list_del(&msi->list);
+/**
+ * iommu_put_msi_cookie - Release a domain's MSI mapping resources
+ * @domain: IOMMU domain previously prepared by iommu_get_msi_cookie()
+ */
+void iommu_put_msi_cookie(struct iommu_domain *domain)
+{
+	struct iommu_dma_msi_cookie *cookie = domain->msi_cookie;
+	struct iommu_dma_msi_page *msi, *tmp;
+
+	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list)
 		kfree(msi);
-	}
 	kfree(cookie);
-	domain->iova_cookie = NULL;
 }
-EXPORT_SYMBOL(iommu_put_dma_cookie);
 
 /**
  * iommu_dma_get_resv_regions - Reserved region driver helper
@@ -188,8 +462,10 @@ void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
 {
 
 	if (!is_of_node(dev_iommu_fwspec_get(dev)->iommu_fwnode))
-		iort_iommu_msi_get_resv_regions(dev, list);
+		iort_iommu_get_resv_regions(dev, list);
 
+	if (dev->of_node)
+		of_iommu_get_resv_regions(dev, list);
 }
 EXPORT_SYMBOL(iommu_dma_get_resv_regions);
 
@@ -218,6 +494,15 @@ static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
 	return 0;
 }
 
+static int iommu_dma_ranges_sort(void *priv, const struct list_head *a,
+		const struct list_head *b)
+{
+	struct resource_entry *res_a = list_entry(a, typeof(*res_a), node);
+	struct resource_entry *res_b = list_entry(b, typeof(*res_b), node);
+
+	return res_a->res->start > res_b->res->start;
+}
+
 static int iova_reserve_pci_windows(struct pci_dev *dev,
 		struct iova_domain *iovad)
 {
@@ -236,6 +521,7 @@ static int iova_reserve_pci_windows(struct pci_dev *dev,
 	}
 
 	/* Get reserved DMA windows from host bridge */
+	list_sort(NULL, &bridge->dma_ranges, iommu_dma_ranges_sort);
 	resource_list_for_each_entry(window, &bridge->dma_ranges) {
 		end = window->res->start - window->offset;
 resv_iova:
@@ -244,7 +530,7 @@ resv_iova:
 			hi = iova_pfn(iovad, end);
 			reserve_iova(iovad, lo, hi);
 		} else if (end < start) {
-			/* dma_ranges list should be sorted */
+			/* DMA ranges should be non-overlapping */
 			dev_err(&dev->dev,
 				"Failed to reserve IOVA [%pa-%pa]\n",
 				&start, &end);
@@ -301,61 +587,104 @@ static int iova_reserve_iommu_regions(struct device *dev,
 	return ret;
 }
 
-static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad)
+static bool dev_is_untrusted(struct device *dev)
 {
-	struct iommu_dma_cookie *cookie;
-	struct iommu_domain *domain;
+	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
+}
+
+static bool dev_use_swiotlb(struct device *dev, size_t size,
+			    enum dma_data_direction dir)
+{
+	return IS_ENABLED(CONFIG_SWIOTLB) &&
+		(dev_is_untrusted(dev) ||
+		 dma_kmalloc_needs_bounce(dev, size, dir));
+}
+
+static bool dev_use_sg_swiotlb(struct device *dev, struct scatterlist *sg,
+			       int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *s;
+	int i;
 
-	cookie = container_of(iovad, struct iommu_dma_cookie, iovad);
-	domain = cookie->fq_domain;
+	if (!IS_ENABLED(CONFIG_SWIOTLB))
+		return false;
 
-	domain->ops->flush_iotlb_all(domain);
+	if (dev_is_untrusted(dev))
+		return true;
+
+	/*
+	 * If kmalloc() buffers are not DMA-safe for this device and
+	 * direction, check the individual lengths in the sg list. If any
+	 * element is deemed unsafe, use the swiotlb for bouncing.
+	 */
+	if (!dma_kmalloc_safe(dev, dir)) {
+		for_each_sg(sg, s, nents, i)
+			if (!dma_kmalloc_size_aligned(s->length))
+				return true;
+	}
+
+	return false;
 }
 
-static bool dev_is_untrusted(struct device *dev)
+/**
+ * iommu_dma_init_options - Initialize dma-iommu options
+ * @options: The options to be initialized
+ * @dev: Device the options are set for
+ *
+ * This allows tuning dma-iommu specific to device properties
+ */
+static void iommu_dma_init_options(struct iommu_dma_options *options,
+				   struct device *dev)
 {
-	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
+	/* Shadowing IOTLB flushes do better with a single large queue */
+	if (dev->iommu->shadow_on_flush) {
+		options->qt = IOMMU_DMA_OPTS_SINGLE_QUEUE;
+		options->fq_timeout = IOVA_SINGLE_FQ_TIMEOUT;
+		options->fq_size = IOVA_SINGLE_FQ_SIZE;
+	} else {
+		options->qt = IOMMU_DMA_OPTS_PER_CPU_QUEUE;
+		options->fq_size = IOVA_DEFAULT_FQ_SIZE;
+		options->fq_timeout = IOVA_DEFAULT_FQ_TIMEOUT;
+	}
 }
 
 /**
  * iommu_dma_init_domain - Initialise a DMA mapping domain
  * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
- * @base: IOVA at which the mappable address space starts
- * @limit: Last address of the IOVA space
  * @dev: Device the domain is being initialised for
  *
- * @base and @limit + 1 should be exact multiples of IOMMU page granularity to
- * avoid rounding surprises. If necessary, we reserve the page at address 0
+ * If the geometry and dma_range_map include address 0, we reserve that page
  * to ensure it is an invalid IOVA. It is safe to reinitialise a domain, but
  * any change which could make prior IOVAs invalid will fail.
  */
-static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
-				 dma_addr_t limit, struct device *dev)
+static int iommu_dma_init_domain(struct iommu_domain *domain, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	const struct bus_dma_region *map = dev->dma_range_map;
 	unsigned long order, base_pfn;
 	struct iova_domain *iovad;
+	int ret;
 
-	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
+	if (!cookie || domain->cookie_type != IOMMU_COOKIE_DMA_IOVA)
 		return -EINVAL;
 
 	iovad = &cookie->iovad;
 
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
-	base_pfn = max_t(unsigned long, 1, base >> order);
+	base_pfn = 1;
 
 	/* Check the domain allows at least some access to the device... */
-	if (domain->geometry.force_aperture) {
-		if (base > domain->geometry.aperture_end ||
-		    limit < domain->geometry.aperture_start) {
+	if (map) {
+		if (dma_range_map_min(map) > domain->geometry.aperture_end ||
+		    dma_range_map_max(map) < domain->geometry.aperture_start) {
 			pr_warn("specified DMA range outside IOMMU capability\n");
 			return -EFAULT;
 		}
-		/* ...then finally give it a kicking to make sure it fits */
-		base_pfn = max_t(unsigned long, base_pfn,
-				domain->geometry.aperture_start >> order);
 	}
+	/* ...then finally give it a kicking to make sure it fits */
+	base_pfn = max_t(unsigned long, base_pfn,
+			 domain->geometry.aperture_start >> order);
 
 	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
@@ -369,18 +698,16 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	}
 
 	init_iova_domain(iovad, 1UL << order, base_pfn);
+	ret = iova_domain_init_rcaches(iovad);
+	if (ret)
+		return ret;
 
-	if (!cookie->fq_domain && (!dev || !dev_is_untrusted(dev)) &&
-	    domain->ops->flush_iotlb_all && !iommu_get_dma_strict(domain)) {
-		if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all,
-					  iommu_dma_entry_dtor))
-			pr_warn("iova flush queue initialization failed\n");
-		else
-			cookie->fq_domain = domain;
-	}
+	iommu_dma_init_options(&cookie->options, dev);
 
-	if (!dev)
-		return 0;
+	/* If the FQ fails we can simply fall back to strict mode */
+	if (domain->type == IOMMU_DOMAIN_DMA_FQ &&
+	    (!device_iommu_capable(dev, IOMMU_CAP_DEFERRED_FLUSH) || iommu_dma_init_fq(domain)))
+		domain->type = IOMMU_DOMAIN_DMA;
 
 	return iova_reserve_iommu_regions(dev, domain);
 }
@@ -397,7 +724,12 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
 		     unsigned long attrs)
 {
-	int prot = coherent ? IOMMU_CACHE : 0;
+	int prot;
+
+	if (attrs & DMA_ATTR_MMIO)
+		prot = IOMMU_MMIO;
+	else
+		prot = coherent ? IOMMU_CACHE : 0;
 
 	if (attrs & DMA_ATTR_PRIVILEGED)
 		prot |= IOMMU_PRIV;
@@ -419,53 +751,59 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
-	unsigned long shift, iova_len, iova = 0;
+	unsigned long shift, iova_len, iova;
 
-	if (cookie->type == IOMMU_DMA_MSI_COOKIE) {
-		cookie->msi_iova += size;
-		return cookie->msi_iova - size;
+	if (domain->cookie_type == IOMMU_COOKIE_DMA_MSI) {
+		domain->msi_cookie->msi_iova += size;
+		return domain->msi_cookie->msi_iova - size;
 	}
 
 	shift = iova_shift(iovad);
 	iova_len = size >> shift;
-	/*
-	 * Freeing non-power-of-two-sized allocations back into the IOVA caches
-	 * will come back to bite us badly, so we have to waste a bit of space
-	 * rounding up anything cacheable to make sure that can't happen. The
-	 * order of the unadjusted size will still match upon freeing.
-	 */
-	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
-		iova_len = roundup_pow_of_two(iova_len);
 
 	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, (u64)domain->geometry.aperture_end);
 
-	/* Try to get PCI devices a SAC address */
-	if (dma_limit > DMA_BIT_MASK(32) && !iommu_dma_forcedac && dev_is_pci(dev))
+	/*
+	 * Try to use all the 32-bit PCI addresses first. The original SAC vs.
+	 * DAC reasoning loses relevance with PCIe, but enough hardware and
+	 * firmware bugs are still lurking out there that it's safest not to
+	 * venture into the 64-bit space until necessary.
+	 *
+	 * If your device goes wrong after seeing the notice then likely either
+	 * its driver is not setting DMA masks accurately, the hardware has
+	 * some inherent bug in handling >32-bit addresses, or not all the
+	 * expected address bits are wired up between the device and the IOMMU.
+	 */
+	if (dma_limit > DMA_BIT_MASK(32) && dev->iommu->pci_32bit_workaround) {
 		iova = alloc_iova_fast(iovad, iova_len,
 				       DMA_BIT_MASK(32) >> shift, false);
+		if (iova)
+			goto done;
 
-	if (!iova)
-		iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift,
-				       true);
+		dev->iommu->pci_32bit_workaround = false;
+		dev_notice(dev, "Using %d-bit DMA addresses\n", bits_per(dma_limit));
+	}
 
+	iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift, true);
+done:
 	return (dma_addr_t)iova << shift;
 }
 
-static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
-		dma_addr_t iova, size_t size, struct page *freelist)
+static void iommu_dma_free_iova(struct iommu_domain *domain, dma_addr_t iova,
+				size_t size, struct iommu_iotlb_gather *gather)
 {
-	struct iova_domain *iovad = &cookie->iovad;
+	struct iova_domain *iovad = &domain->iova_cookie->iovad;
 
 	/* The MSI case is only ever cleaning up its most recent allocation */
-	if (cookie->type == IOMMU_DMA_MSI_COOKIE)
-		cookie->msi_iova -= size;
-	else if (cookie->fq_domain)	/* non-strict mode */
-		queue_iova(iovad, iova_pfn(iovad, iova),
+	if (domain->cookie_type == IOMMU_COOKIE_DMA_MSI)
+		domain->msi_cookie->msi_iova -= size;
+	else if (gather && gather->queued)
+		queue_iova(domain->iova_cookie, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad),
-				(unsigned long)freelist);
+				&gather->freelist);
 	else
 		free_iova_fast(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad));
@@ -484,30 +822,14 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	dma_addr -= iova_off;
 	size = iova_align(iovad, size + iova_off);
 	iommu_iotlb_gather_init(&iotlb_gather);
+	iotlb_gather.queued = READ_ONCE(cookie->fq_domain);
 
 	unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather);
 	WARN_ON(unmapped != size);
 
-	if (!cookie->fq_domain)
+	if (!iotlb_gather.queued)
 		iommu_iotlb_sync(domain, &iotlb_gather);
-	iommu_dma_free_iova(cookie, dma_addr, size, iotlb_gather.freelist);
-}
-
-static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	phys_addr_t phys;
-
-	phys = iommu_iova_to_phys(domain, dma_addr);
-	if (WARN_ON(!phys))
-		return;
-
-	__iommu_dma_unmap(dev, dma_addr, size);
-
-	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+	iommu_dma_free_iova(domain, dma_addr, size, &iotlb_gather);
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
@@ -523,65 +845,24 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	    iommu_deferred_attach(dev, domain))
 		return DMA_MAPPING_ERROR;
 
+	/* If anyone ever wants this we'd need support in the IOVA allocator */
+	if (dev_WARN_ONCE(dev, dma_get_min_align_mask(dev) > iova_mask(iovad),
+	    "Unsupported alignment constraint\n"))
+		return DMA_MAPPING_ERROR;
+
 	size = iova_align(iovad, size + iova_off);
 
 	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
-	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
-		iommu_dma_free_iova(cookie, iova, size, NULL);
+	if (iommu_map(domain, iova, phys - iova_off, size, prot, GFP_ATOMIC)) {
+		iommu_dma_free_iova(domain, iova, size, NULL);
 		return DMA_MAPPING_ERROR;
 	}
 	return iova + iova_off;
 }
 
-static dma_addr_t __iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
-		size_t org_size, dma_addr_t dma_mask, bool coherent,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	int prot = dma_info_to_prot(dir, coherent, attrs);
-	struct iommu_domain *domain = iommu_get_dma_domain(dev);
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	struct iova_domain *iovad = &cookie->iovad;
-	size_t aligned_size = org_size;
-	void *padding_start;
-	size_t padding_size;
-	dma_addr_t iova;
-
-	/*
-	 * If both the physical buffer start address and size are
-	 * page aligned, we don't need to use a bounce page.
-	 */
-	if (IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev) &&
-	    iova_offset(iovad, phys | org_size)) {
-		aligned_size = iova_align(iovad, org_size);
-		phys = swiotlb_tbl_map_single(dev, phys, org_size,
-					      aligned_size, dir, attrs);
-
-		if (phys == DMA_MAPPING_ERROR)
-			return DMA_MAPPING_ERROR;
-
-		/* Cleanup the padding area. */
-		padding_start = phys_to_virt(phys);
-		padding_size = aligned_size;
-
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    (dir == DMA_TO_DEVICE ||
-		     dir == DMA_BIDIRECTIONAL)) {
-			padding_start += org_size;
-			padding_size -= org_size;
-		}
-
-		memset(padding_start, 0, padding_size);
-	}
-
-	iova = __iommu_dma_map(dev, phys, aligned_size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(phys))
-		swiotlb_tbl_unmap_single(dev, phys, org_size, dir, attrs);
-	return iova;
-}
-
 static void __iommu_dma_free_pages(struct page **pages, int count)
 {
 	while (count--)
@@ -595,20 +876,17 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	struct page **pages;
 	unsigned int i = 0, nid = dev_to_node(dev);
 
-	order_mask &= (2U << MAX_ORDER) - 1;
+	order_mask &= GENMASK(MAX_PAGE_ORDER, 0);
 	if (!order_mask)
 		return NULL;
 
-	pages = kvzalloc(count * sizeof(*pages), GFP_KERNEL);
+	pages = kvcalloc(count, sizeof(*pages), GFP_KERNEL);
 	if (!pages)
 		return NULL;
 
 	/* IOMMU can map any pages, so himem can also be used here */
 	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
 
-	/* It makes no sense to muck about with huge pages */
-	gfp &= ~__GFP_COMP;
-
 	while (count) {
 		struct page *page = NULL;
 		unsigned int order_size;
@@ -618,7 +896,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 		 * than a necessity, hence using __GFP_NORETRY until
 		 * falling back to minimum-order allocations.
 		 */
-		for (order_mask &= (2U << __fls(count)) - 1;
+		for (order_mask &= GENMASK(__fls(count), 0);
 		     order_mask; order_mask &= ~order_size) {
 			unsigned int order = __fls(order_mask);
 			gfp_t alloc_flags = gfp;
@@ -649,8 +927,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
  * but an IOMMU which supports smaller pages might not map the whole thing.
  */
 static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
-		size_t size, struct sg_table *sgt, gfp_t gfp, pgprot_t prot,
-		unsigned long attrs)
+		size_t size, struct sg_table *sgt, gfp_t gfp, unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -660,6 +937,7 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
 	dma_addr_t iova;
+	ssize_t ret;
 
 	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
 	    iommu_deferred_attach(dev, domain))
@@ -686,7 +964,14 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 	if (!iova)
 		goto out_free_pages;
 
-	if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, GFP_KERNEL))
+	/*
+	 * Remove the zone/policy flags from the GFP - these are applied to the
+	 * __iommu_dma_alloc_pages() but are not used for the supporting
+	 * internal allocations that follow.
+	 */
+	gfp &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM | __GFP_COMP);
+
+	if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, gfp))
 		goto out_free_iova;
 
 	if (!(ioprot & IOMMU_CACHE)) {
@@ -697,8 +982,9 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot)
-			< size)
+	ret = iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, ioprot,
+			   gfp);
+	if (ret < 0 || ret < size)
 		goto out_free_sg;
 
 	sgt->sgl->dma_address = iova;
@@ -708,22 +994,21 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 out_free_sg:
 	sg_free_table(sgt);
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size, NULL);
+	iommu_dma_free_iova(domain, iova, size, NULL);
 out_free_pages:
 	__iommu_dma_free_pages(pages, count);
 	return NULL;
 }
 
 static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot,
-		unsigned long attrs)
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	struct page **pages;
 	struct sg_table sgt;
 	void *vaddr;
+	pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 
-	pages = __iommu_dma_alloc_noncontiguous(dev, size, &sgt, gfp, prot,
-						attrs);
+	pages = __iommu_dma_alloc_noncontiguous(dev, size, &sgt, gfp, attrs);
 	if (!pages)
 		return NULL;
 	*dma_handle = sgt.sgl->dma_address;
@@ -740,10 +1025,23 @@ out_unmap:
 	return NULL;
 }
 
-#ifdef CONFIG_DMA_REMAP
-static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
-		size_t size, enum dma_data_direction dir, gfp_t gfp,
-		unsigned long attrs)
+/*
+ * This is the actual return value from the iommu_dma_alloc_noncontiguous.
+ *
+ * The users of the DMA API should only care about the sg_table, but to make
+ * the DMA-API internal vmaping and freeing easier we stash away the page
+ * array as well (except for the fallback case).  This can go away any time,
+ * e.g. when a vmap-variant that takes a scatterlist comes along.
+ */
+struct dma_sgt_handle {
+	struct sg_table sgt;
+	struct page **pages;
+};
+#define sgt_handle(sgt) \
+	container_of((sgt), struct dma_sgt_handle, sgt)
+
+struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size,
+	       enum dma_data_direction dir, gfp_t gfp, unsigned long attrs)
 {
 	struct dma_sgt_handle *sh;
 
@@ -751,8 +1049,7 @@ static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
 	if (!sh)
 		return NULL;
 
-	sh->pages = __iommu_dma_alloc_noncontiguous(dev, size, &sh->sgt, gfp,
-						    PAGE_KERNEL, attrs);
+	sh->pages = __iommu_dma_alloc_noncontiguous(dev, size, &sh->sgt, gfp, attrs);
 	if (!sh->pages) {
 		kfree(sh);
 		return NULL;
@@ -760,7 +1057,7 @@ static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
 	return &sh->sgt;
 }
 
-static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
 		struct sg_table *sgt, enum dma_data_direction dir)
 {
 	struct dma_sgt_handle *sh = sgt_handle(sgt);
@@ -768,103 +1065,189 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
 	__iommu_dma_unmap(dev, sgt->sgl->dma_address, size);
 	__iommu_dma_free_pages(sh->pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
 	sg_free_table(&sh->sgt);
+	kfree(sh);
+}
+
+void *iommu_dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt)
+{
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL);
+}
+
+int iommu_dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct sg_table *sgt)
+{
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (vma->vm_pgoff >= count || vma_pages(vma) > count - vma->vm_pgoff)
+		return -ENXIO;
+	return vm_map_pages(vma, sgt_handle(sgt)->pages, count);
 }
-#endif /* CONFIG_DMA_REMAP */
 
-static void iommu_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev) && !dev_use_swiotlb(dev, size, dir))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_cpu(phys, size, dir);
 
-	if (is_swiotlb_buffer(phys))
-		swiotlb_sync_single_for_cpu(dev, phys, size, dir);
+	swiotlb_sync_single_for_cpu(dev, phys, size, dir);
 }
 
-static void iommu_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
+	if (dev_is_dma_coherent(dev) && !dev_use_swiotlb(dev, size, dir))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	if (is_swiotlb_buffer(phys))
-		swiotlb_sync_single_for_device(dev, phys, size, dir);
+	swiotlb_sync_single_for_device(dev, phys, size, dir);
 
 	if (!dev_is_dma_coherent(dev))
 		arch_sync_dma_for_device(phys, size, dir);
 }
 
-static void iommu_dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nelems,
-		enum dma_data_direction dir)
+void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
-		return;
-
-	for_each_sg(sgl, sg, nelems, i) {
-		if (!dev_is_dma_coherent(dev))
+	if (sg_dma_is_swiotlb(sgl))
+		for_each_sg(sgl, sg, nelems, i)
+			iommu_dma_sync_single_for_cpu(dev, sg_dma_address(sg),
+						      sg->length, dir);
+	else if (!dev_is_dma_coherent(dev))
+		for_each_sg(sgl, sg, nelems, i)
 			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
-
-		if (is_swiotlb_buffer(sg_phys(sg)))
-			swiotlb_sync_single_for_cpu(dev, sg_phys(sg),
-						    sg->length, dir);
-	}
 }
 
-static void iommu_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nelems,
-		enum dma_data_direction dir)
+void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
-		return;
+	if (sg_dma_is_swiotlb(sgl))
+		for_each_sg(sgl, sg, nelems, i)
+			iommu_dma_sync_single_for_device(dev,
+							 sg_dma_address(sg),
+							 sg->length, dir);
+	else if (!dev_is_dma_coherent(dev))
+		for_each_sg(sgl, sg, nelems, i)
+			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
+}
 
-	for_each_sg(sgl, sg, nelems, i) {
-		if (is_swiotlb_buffer(sg_phys(sg)))
-			swiotlb_sync_single_for_device(dev, sg_phys(sg),
-						       sg->length, dir);
+static phys_addr_t iommu_dma_map_swiotlb(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iova_domain *iovad = &domain->iova_cookie->iovad;
 
-		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
+	if (!is_swiotlb_active(dev)) {
+		dev_warn_once(dev, "DMA bounce buffers are inactive, unable to map unaligned transaction.\n");
+		return (phys_addr_t)DMA_MAPPING_ERROR;
 	}
+
+	trace_swiotlb_bounced(dev, phys, size);
+
+	phys = swiotlb_tbl_map_single(dev, phys, size, iova_mask(iovad), dir,
+			attrs);
+
+	/*
+	 * Untrusted devices should not see padding areas with random leftover
+	 * kernel data, so zero the pre- and post-padding.
+	 * swiotlb_tbl_map_single() has initialized the bounce buffer proper to
+	 * the contents of the original memory buffer.
+	 */
+	if (phys != (phys_addr_t)DMA_MAPPING_ERROR && dev_is_untrusted(dev)) {
+		size_t start, virt = (size_t)phys_to_virt(phys);
+
+		/* Pre-padding */
+		start = iova_align_down(iovad, virt);
+		memset((void *)start, 0, virt - start);
+
+		/* Post-padding */
+		start = virt + size;
+		memset((void *)start, 0, iova_align(iovad, start) - start);
+	}
+
+	return phys;
 }
 
-static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+/*
+ * Checks if a physical buffer has unaligned boundaries with respect to
+ * the IOMMU granule. Returns non-zero if either the start or end
+ * address is not aligned to the granule boundary.
+ */
+static inline size_t iova_unaligned(struct iova_domain *iovad, phys_addr_t phys,
+				    size_t size)
+{
+	return iova_offset(iovad, phys | size);
+}
+
+dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
-	dma_addr_t dma_handle;
+	int prot = dma_info_to_prot(dir, coherent, attrs);
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t iova, dma_mask = dma_get_mask(dev);
+
+	/*
+	 * If both the physical buffer start address and size are page aligned,
+	 * we don't need to use a bounce page.
+	 */
+	if (dev_use_swiotlb(dev, size, dir) &&
+	    iova_unaligned(iovad, phys, size)) {
+		if (attrs & DMA_ATTR_MMIO)
+			return DMA_MAPPING_ERROR;
+
+		phys = iommu_dma_map_swiotlb(dev, phys, size, dir, attrs);
+		if (phys == (phys_addr_t)DMA_MAPPING_ERROR)
+			return DMA_MAPPING_ERROR;
+	}
 
-	dma_handle = __iommu_dma_map_swiotlb(dev, phys, size, dma_get_mask(dev),
-			coherent, dir, attrs);
-	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-	    dma_handle != DMA_MAPPING_ERROR)
+	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
 		arch_sync_dma_for_device(phys, size, dir);
-	return dma_handle;
+
+	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
+	if (iova == DMA_MAPPING_ERROR && !(attrs & DMA_ATTR_MMIO))
+		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+	return iova;
 }
 
-static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
-	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);
+	phys_addr_t phys;
+
+	if (attrs & DMA_ATTR_MMIO) {
+		__iommu_dma_unmap(dev, dma_handle, size);
+		return;
+	}
+
+	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
+	if (WARN_ON(!phys))
+		return;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && !dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu(phys, size, dir);
+
+	__iommu_dma_unmap(dev, dma_handle, size);
+
+	swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 
 /*
@@ -884,15 +1267,30 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 	for_each_sg(sg, s, nents, i) {
 		/* Restore this segment's original unaligned fields first */
+		dma_addr_t s_dma_addr = sg_dma_address(s);
 		unsigned int s_iova_off = sg_dma_address(s);
 		unsigned int s_length = sg_dma_len(s);
 		unsigned int s_iova_len = s->length;
 
-		s->offset += s_iova_off;
-		s->length = s_length;
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 
+		if (sg_dma_is_bus_address(s)) {
+			if (i > 0)
+				cur = sg_next(cur);
+
+			sg_dma_unmark_bus_address(s);
+			sg_dma_address(cur) = s_dma_addr;
+			sg_dma_len(cur) = s_length;
+			sg_dma_mark_bus_address(cur);
+			count++;
+			cur_len = 0;
+			continue;
+		}
+
+		s->offset += s_iova_off;
+		s->length = s_length;
+
 		/*
 		 * Now fill in the real DMA data. If...
 		 * - there is a valid output segment to append to
@@ -933,10 +1331,14 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 	int i;
 
 	for_each_sg(sg, s, nents, i) {
-		if (sg_dma_address(s) != DMA_MAPPING_ERROR)
-			s->offset += sg_dma_address(s);
-		if (sg_dma_len(s))
-			s->length = sg_dma_len(s);
+		if (sg_dma_is_bus_address(s)) {
+			sg_dma_unmark_bus_address(s);
+		} else {
+			if (sg_dma_address(s) != DMA_MAPPING_ERROR)
+				s->offset += sg_dma_address(s);
+			if (sg_dma_len(s))
+				s->length = sg_dma_len(s);
+		}
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 	}
@@ -949,7 +1351,7 @@ static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *s
 	int i;
 
 	for_each_sg(sg, s, nents, i)
-		__iommu_dma_unmap_swiotlb(dev, sg_dma_address(s),
+		iommu_dma_unmap_phys(dev, sg_dma_address(s),
 				sg_dma_len(s), dir, attrs);
 }
 
@@ -959,10 +1361,11 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
 	struct scatterlist *s;
 	int i;
 
+	sg_dma_mark_swiotlb(sg);
+
 	for_each_sg(sg, s, nents, i) {
-		sg_dma_address(s) = __iommu_dma_map_swiotlb(dev, sg_phys(s),
-				s->length, dma_get_mask(dev),
-				dev_is_dma_coherent(dev), dir, attrs);
+		sg_dma_address(s) = iommu_dma_map_phys(dev, sg_phys(s),
+				s->length, dir, attrs);
 		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
 			goto out_unmap;
 		sg_dma_len(s) = s->length;
@@ -972,7 +1375,7 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
 
 out_unmap:
 	iommu_dma_unmap_sg_swiotlb(dev, sg, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return 0;
+	return -EIO;
 }
 
 /*
@@ -982,29 +1385,33 @@ out_unmap:
  * impedance-matching, to be able to hand off a suitably-aligned list,
  * but still preserve the original offsets and sizes for the caller.
  */
-static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
+int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	struct scatterlist *s, *prev = NULL;
 	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
+	struct pci_p2pdma_map_state p2pdma_state = {};
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
+	ssize_t ret;
 	int i;
 
-	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
-	    iommu_deferred_attach(dev, domain))
-		return 0;
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled)) {
+		ret = iommu_deferred_attach(dev, domain);
+		if (ret)
+			goto out;
+	}
+
+	if (dev_use_sg_swiotlb(dev, sg, nents, dir))
+		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
 
-	if (dev_is_untrusted(dev))
-		return iommu_dma_map_sg_swiotlb(dev, sg, nents, dir, attrs);
-
 	/*
 	 * Work out how much IOVA space we need, and align the segments to
 	 * IOVA granules for the IOMMU driver to handle. With some clever
@@ -1016,6 +1423,32 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		size_t s_length = s->length;
 		size_t pad_len = (mask - iova_len + 1) & mask;
 
+		switch (pci_p2pdma_state(&p2pdma_state, dev, sg_page(s))) {
+		case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+			/*
+			 * Mapping through host bridge should be mapped with
+			 * regular IOVAs, thus we do nothing here and continue
+			 * below.
+			 */
+			break;
+		case PCI_P2PDMA_MAP_NONE:
+			break;
+		case PCI_P2PDMA_MAP_BUS_ADDR:
+			/*
+			 * iommu_map_sg() will skip this segment as it is marked
+			 * as a bus address, __finalise_sg() will copy the dma
+			 * address into the output segment.
+			 */
+			s->dma_address = pci_p2pdma_bus_addr_map(
+				p2pdma_state.mem, sg_phys(s));
+			sg_dma_len(s) = sg->length;
+			sg_dma_mark_bus_address(s);
+			continue;
+		default:
+			ret = -EREMOTEIO;
+			goto out_restore_sg;
+		}
+
 		sg_dma_address(s) = s_iova_off;
 		sg_dma_len(s) = s_length;
 		s->offset -= s_iova_off;
@@ -1044,67 +1477,83 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		prev = s;
 	}
 
+	if (!iova_len)
+		return __finalise_sg(dev, sg, nents, 0);
+
 	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
-	if (!iova)
+	if (!iova) {
+		ret = -ENOMEM;
 		goto out_restore_sg;
+	}
 
 	/*
 	 * We'll leave any physical concatenation to the IOMMU driver's
 	 * implementation - it knows better than we do.
 	 */
-	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
+	ret = iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
+	if (ret < 0 || ret < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
+	iommu_dma_free_iova(domain, iova, iova_len, NULL);
 out_restore_sg:
 	__invalidate_sg(sg, nents);
-	return 0;
+out:
+	if (ret != -ENOMEM && ret != -EREMOTEIO)
+		return -EINVAL;
+	return ret;
 }
 
-static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
+void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t start, end;
+	dma_addr_t end = 0, start;
 	struct scatterlist *tmp;
 	int i;
 
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
-
-	if (dev_is_untrusted(dev)) {
+	if (sg_dma_is_swiotlb(sg)) {
 		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
 		return;
 	}
 
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
+
 	/*
 	 * The scatterlist segments are mapped into a single
-	 * contiguous IOVA allocation, so this is incredibly easy.
+	 * contiguous IOVA allocation, the start and end points
+	 * just have to be determined.
 	 */
-	start = sg_dma_address(sg);
-	for_each_sg(sg_next(sg), tmp, nents - 1, i) {
+	for_each_sg(sg, tmp, nents, i) {
+		if (sg_dma_is_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
+
 		if (sg_dma_len(tmp) == 0)
 			break;
-		sg = tmp;
+
+		start = sg_dma_address(tmp);
+		break;
 	}
-	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(dev, start, end - start);
-}
 
-static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
-			dma_get_mask(dev));
-}
+	nents -= i;
+	for_each_sg(tmp, tmp, nents, i) {
+		if (sg_dma_is_bus_address(tmp)) {
+			sg_dma_unmark_bus_address(tmp);
+			continue;
+		}
 
-static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	__iommu_dma_unmap(dev, handle, size);
+		if (sg_dma_len(tmp) == 0)
+			break;
+
+		end = sg_dma_address(tmp) + sg_dma_len(tmp);
+	}
+
+	if (end)
+		__iommu_dma_unmap(dev, start, end - start);
 }
 
 static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
@@ -1118,7 +1567,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 	    dma_free_from_pool(dev, cpu_addr, alloc_size))
 		return;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		/*
 		 * If it the address is remapped, then it's either non-coherent
 		 * or highmem CMA, or an iommu_dma_alloc_remap() construction.
@@ -1138,7 +1587,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 		dma_free_contiguous(dev, page, alloc_size);
 }
 
-static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t handle, unsigned long attrs)
 {
 	__iommu_dma_unmap(dev, handle, size);
@@ -1160,7 +1609,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && (!coherent || PageHighMem(page))) {
+	if (!coherent || PageHighMem(page)) {
 		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
 
 		cpu_addr = dma_common_contiguous_remap(page, alloc_size,
@@ -1182,8 +1631,8 @@ out_free_pages:
 	return NULL;
 }
 
-static void *iommu_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
+void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	bool coherent = dev_is_dma_coherent(dev);
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
@@ -1192,10 +1641,9 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 
 	gfp |= __GFP_ZERO;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && gfpflags_allow_blocking(gfp) &&
+	if (gfpflags_allow_blocking(gfp) &&
 	    !(attrs & DMA_ATTR_FORCE_CONTIGUOUS)) {
-		return iommu_dma_alloc_remap(dev, size, handle, gfp,
-				dma_pgprot(dev, PAGE_KERNEL, attrs), attrs);
+		return iommu_dma_alloc_remap(dev, size, handle, gfp, attrs);
 	}
 
 	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
@@ -1217,7 +1665,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	return cpu_addr;
 }
 
-static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
 {
@@ -1233,7 +1681,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	if (off >= nr_pages || vma_pages(vma) > nr_pages - off)
 		return -ENXIO;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages)
@@ -1248,14 +1696,14 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 			       vma->vm_page_prot);
 }
 
-static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
 {
 	struct page *page;
 	int ret;
 
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
+	if (is_vmalloc_addr(cpu_addr)) {
 		struct page **pages = dma_common_find_pages(cpu_addr);
 
 		if (pages) {
@@ -1275,76 +1723,439 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
-static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
+unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
-static const struct dma_map_ops iommu_dma_ops = {
-	.alloc			= iommu_dma_alloc,
-	.free			= iommu_dma_free,
-	.alloc_pages		= dma_common_alloc_pages,
-	.free_pages		= dma_common_free_pages,
-#ifdef CONFIG_DMA_REMAP
-	.alloc_noncontiguous	= iommu_dma_alloc_noncontiguous,
-	.free_noncontiguous	= iommu_dma_free_noncontiguous,
-#endif
-	.mmap			= iommu_dma_mmap,
-	.get_sgtable		= iommu_dma_get_sgtable,
-	.map_page		= iommu_dma_map_page,
-	.unmap_page		= iommu_dma_unmap_page,
-	.map_sg			= iommu_dma_map_sg,
-	.unmap_sg		= iommu_dma_unmap_sg,
-	.sync_single_for_cpu	= iommu_dma_sync_single_for_cpu,
-	.sync_single_for_device	= iommu_dma_sync_single_for_device,
-	.sync_sg_for_cpu	= iommu_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= iommu_dma_sync_sg_for_device,
-	.map_resource		= iommu_dma_map_resource,
-	.unmap_resource		= iommu_dma_unmap_resource,
-	.get_merge_boundary	= iommu_dma_get_merge_boundary,
-};
+size_t iommu_dma_opt_mapping_size(void)
+{
+	return iova_rcache_range();
+}
 
-/*
- * The IOMMU core code allocates the default DMA domain, which the underlying
- * IOMMU driver needs to support via the dma-iommu layer.
+size_t iommu_dma_max_mapping_size(struct device *dev)
+{
+	if (dev_is_untrusted(dev))
+		return swiotlb_max_mapping_size(dev);
+
+	return SIZE_MAX;
+}
+
+/**
+ * dma_iova_try_alloc - Try to allocate an IOVA space
+ * @dev: Device to allocate the IOVA space for
+ * @state: IOVA state
+ * @phys: physical address
+ * @size: IOVA size
+ *
+ * Check if @dev supports the IOVA-based DMA API, and if yes allocate IOVA space
+ * for the given base address and size.
+ *
+ * Note: @phys is only used to calculate the IOVA alignment. Callers that always
+ * do PAGE_SIZE aligned transfers can safely pass 0 here.
+ *
+ * Returns %true if the IOVA-based DMA API can be used and IOVA space has been
+ * allocated, or %false if the regular DMA API should be used.
  */
-void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit)
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_dma_cookie *cookie;
+	struct iommu_domain *domain;
+	struct iova_domain *iovad;
+	size_t iova_off;
+	dma_addr_t addr;
 
-	if (!domain)
-		goto out_err;
+	memset(state, 0, sizeof(*state));
+	if (!use_dma_iommu(dev))
+		return false;
+
+	domain = iommu_get_dma_domain(dev);
+	cookie = domain->iova_cookie;
+	iovad = &cookie->iovad;
+	iova_off = iova_offset(iovad, phys);
+
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
+	    iommu_deferred_attach(dev, iommu_get_domain_for_dev(dev)))
+		return false;
+
+	if (WARN_ON_ONCE(!size))
+		return false;
 
 	/*
-	 * The IOMMU core code allocates the default DMA domain, which the
-	 * underlying IOMMU driver needs to support via the dma-iommu layer.
+	 * DMA_IOVA_USE_SWIOTLB is flag which is set by dma-iommu
+	 * internals, make sure that caller didn't set it and/or
+	 * didn't use this interface to map SIZE_MAX.
 	 */
-	if (domain->type == IOMMU_DOMAIN_DMA) {
-		if (iommu_dma_init_domain(domain, dma_base, dma_limit, dev))
-			goto out_err;
-		dev->dma_ops = &iommu_dma_ops;
+	if (WARN_ON_ONCE((u64)size & DMA_IOVA_USE_SWIOTLB))
+		return false;
+
+	addr = iommu_dma_alloc_iova(domain,
+			iova_align(iovad, size + iova_off),
+			dma_get_mask(dev), dev);
+	if (!addr)
+		return false;
+
+	state->addr = addr + iova_off;
+	state->__size = size;
+	return true;
+}
+EXPORT_SYMBOL_GPL(dma_iova_try_alloc);
+
+/**
+ * dma_iova_free - Free an IOVA space
+ * @dev: Device to free the IOVA space for
+ * @state: IOVA state
+ *
+ * Undoes a successful dma_try_iova_alloc().
+ *
+ * Note that all dma_iova_link() calls need to be undone first.  For callers
+ * that never call dma_iova_unlink(), dma_iova_destroy() can be used instead
+ * which unlinks all ranges and frees the IOVA space in a single efficient
+ * operation.
+ */
+void dma_iova_free(struct device *dev, struct dma_iova_state *state)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, state->addr);
+	size_t size = dma_iova_size(state);
+
+	iommu_dma_free_iova(domain, state->addr - iova_start_pad,
+			iova_align(iovad, size + iova_start_pad), NULL);
+}
+EXPORT_SYMBOL_GPL(dma_iova_free);
+
+static int __dma_iova_link(struct device *dev, dma_addr_t addr,
+		phys_addr_t phys, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	bool coherent = dev_is_dma_coherent(dev);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
+
+	if (!coherent && !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
+		arch_sync_dma_for_device(phys, size, dir);
+
+	return iommu_map_nosync(iommu_get_dma_domain(dev), addr, phys, size,
+			prot, GFP_ATOMIC);
+}
+
+static int iommu_dma_iova_bounce_and_link(struct device *dev, dma_addr_t addr,
+		phys_addr_t phys, size_t bounce_len,
+		enum dma_data_direction dir, unsigned long attrs,
+		size_t iova_start_pad)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iova_domain *iovad = &domain->iova_cookie->iovad;
+	phys_addr_t bounce_phys;
+	int error;
+
+	bounce_phys = iommu_dma_map_swiotlb(dev, phys, bounce_len, dir, attrs);
+	if (bounce_phys == DMA_MAPPING_ERROR)
+		return -ENOMEM;
+
+	error = __dma_iova_link(dev, addr - iova_start_pad,
+			bounce_phys - iova_start_pad,
+			iova_align(iovad, bounce_len), dir, attrs);
+	if (error)
+		swiotlb_tbl_unmap_single(dev, bounce_phys, bounce_len, dir,
+				attrs);
+	return error;
+}
+
+static int iommu_dma_iova_link_swiotlb(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t offset,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, phys);
+	size_t iova_end_pad = iova_offset(iovad, phys + size);
+	dma_addr_t addr = state->addr + offset;
+	size_t mapped = 0;
+	int error;
+
+	if (iova_start_pad) {
+		size_t bounce_len = min(size, iovad->granule - iova_start_pad);
+
+		error = iommu_dma_iova_bounce_and_link(dev, addr, phys,
+				bounce_len, dir, attrs, iova_start_pad);
+		if (error)
+			return error;
+		state->__size |= DMA_IOVA_USE_SWIOTLB;
+
+		mapped += bounce_len;
+		size -= bounce_len;
+		if (!size)
+			return 0;
+	}
+
+	size -= iova_end_pad;
+	error = __dma_iova_link(dev, addr + mapped, phys + mapped, size, dir,
+			attrs);
+	if (error)
+		goto out_unmap;
+	mapped += size;
+
+	if (iova_end_pad) {
+		error = iommu_dma_iova_bounce_and_link(dev, addr + mapped,
+				phys + mapped, iova_end_pad, dir, attrs, 0);
+		if (error)
+			goto out_unmap;
+		state->__size |= DMA_IOVA_USE_SWIOTLB;
 	}
 
+	return 0;
+
+out_unmap:
+	dma_iova_unlink(dev, state, 0, mapped, dir, attrs);
+	return error;
+}
+
+/**
+ * dma_iova_link - Link a range of IOVA space
+ * @dev: DMA device
+ * @state: IOVA state
+ * @phys: physical address to link
+ * @offset: offset into the IOVA state to map into
+ * @size: size of the buffer
+ * @dir: DMA direction
+ * @attrs: attributes of mapping properties
+ *
+ * Link a range of IOVA space for the given IOVA state without IOTLB sync.
+ * This function is used to link multiple physical addresses in contiguous
+ * IOVA space without performing costly IOTLB sync.
+ *
+ * The caller is responsible to call to dma_iova_sync() to sync IOTLB at
+ * the end of linkage.
+ */
+int dma_iova_link(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, phys);
+
+	if (WARN_ON_ONCE(iova_start_pad && offset > 0))
+		return -EIO;
+
+	if (dev_use_swiotlb(dev, size, dir) &&
+	    iova_unaligned(iovad, phys, size)) {
+		if (attrs & DMA_ATTR_MMIO)
+			return -EPERM;
+
+		return iommu_dma_iova_link_swiotlb(dev, state, phys, offset,
+				size, dir, attrs);
+	}
+
+	return __dma_iova_link(dev, state->addr + offset - iova_start_pad,
+			phys - iova_start_pad,
+			iova_align(iovad, size + iova_start_pad), dir, attrs);
+}
+EXPORT_SYMBOL_GPL(dma_iova_link);
+
+/**
+ * dma_iova_sync - Sync IOTLB
+ * @dev: DMA device
+ * @state: IOVA state
+ * @offset: offset into the IOVA state to sync
+ * @size: size of the buffer
+ *
+ * Sync IOTLB for the given IOVA state. This function should be called on
+ * the IOVA-contiguous range created by one ore more dma_iova_link() calls
+ * to sync the IOTLB.
+ */
+int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t addr = state->addr + offset;
+	size_t iova_start_pad = iova_offset(iovad, addr);
+
+	return iommu_sync_map(domain, addr - iova_start_pad,
+		      iova_align(iovad, size + iova_start_pad));
+}
+EXPORT_SYMBOL_GPL(dma_iova_sync);
+
+static void iommu_dma_iova_unlink_range_slow(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_start_pad = iova_offset(iovad, addr);
+	dma_addr_t end = addr + size;
+
+	do {
+		phys_addr_t phys;
+		size_t len;
+
+		phys = iommu_iova_to_phys(domain, addr);
+		if (WARN_ON(!phys))
+			/* Something very horrible happen here */
+			return;
+
+		len = min_t(size_t,
+			end - addr, iovad->granule - iova_start_pad);
+
+		if (!dev_is_dma_coherent(dev) &&
+		    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
+			arch_sync_dma_for_cpu(phys, len, dir);
+
+		swiotlb_tbl_unmap_single(dev, phys, len, dir, attrs);
+
+		addr += len;
+		iova_start_pad = 0;
+	} while (addr < end);
+}
+
+static void __iommu_dma_iova_unlink(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs,
+		bool free_iova)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t addr = state->addr + offset;
+	size_t iova_start_pad = iova_offset(iovad, addr);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t unmapped;
+
+	if ((state->__size & DMA_IOVA_USE_SWIOTLB) ||
+	    (!dev_is_dma_coherent(dev) &&
+	     !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))))
+		iommu_dma_iova_unlink_range_slow(dev, addr, size, dir, attrs);
+
+	iommu_iotlb_gather_init(&iotlb_gather);
+	iotlb_gather.queued = free_iova && READ_ONCE(cookie->fq_domain);
+
+	size = iova_align(iovad, size + iova_start_pad);
+	addr -= iova_start_pad;
+	unmapped = iommu_unmap_fast(domain, addr, size, &iotlb_gather);
+	WARN_ON(unmapped != size);
+
+	if (!iotlb_gather.queued)
+		iommu_iotlb_sync(domain, &iotlb_gather);
+	if (free_iova)
+		iommu_dma_free_iova(domain, addr, size, &iotlb_gather);
+}
+
+/**
+ * dma_iova_unlink - Unlink a range of IOVA space
+ * @dev: DMA device
+ * @state: IOVA state
+ * @offset: offset into the IOVA state to unlink
+ * @size: size of the buffer
+ * @dir: DMA direction
+ * @attrs: attributes of mapping properties
+ *
+ * Unlink a range of IOVA space for the given IOVA state.
+ */
+void dma_iova_unlink(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	 __iommu_dma_iova_unlink(dev, state, offset, size, dir, attrs, false);
+}
+EXPORT_SYMBOL_GPL(dma_iova_unlink);
+
+/**
+ * dma_iova_destroy - Finish a DMA mapping transaction
+ * @dev: DMA device
+ * @state: IOVA state
+ * @mapped_len: number of bytes to unmap
+ * @dir: DMA direction
+ * @attrs: attributes of mapping properties
+ *
+ * Unlink the IOVA range up to @mapped_len and free the entire IOVA space. The
+ * range of IOVA from dma_addr to @mapped_len must all be linked, and be the
+ * only linked IOVA in state.
+ */
+void dma_iova_destroy(struct device *dev, struct dma_iova_state *state,
+		size_t mapped_len, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	if (mapped_len)
+		__iommu_dma_iova_unlink(dev, state, 0, mapped_len, dir, attrs,
+				true);
+	else
+		/*
+		 * We can be here if first call to dma_iova_link() failed and
+		 * there is nothing to unlink, so let's be more clear.
+		 */
+		dma_iova_free(dev, state);
+}
+EXPORT_SYMBOL_GPL(dma_iova_destroy);
+
+void iommu_setup_dma_ops(struct device *dev)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+
+	if (dev_is_pci(dev))
+		dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac;
+
+	dev->dma_iommu = iommu_is_dma_domain(domain);
+	if (dev->dma_iommu && iommu_dma_init_domain(domain, dev))
+		goto out_err;
+
 	return;
 out_err:
-	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
-		 dev_name(dev));
+	pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+		dev_name(dev));
+	dev->dma_iommu = false;
+}
+
+static bool has_msi_cookie(const struct iommu_domain *domain)
+{
+	return domain && (domain->cookie_type == IOMMU_COOKIE_DMA_IOVA ||
+			  domain->cookie_type == IOMMU_COOKIE_DMA_MSI);
+}
+
+static size_t cookie_msi_granule(const struct iommu_domain *domain)
+{
+	switch (domain->cookie_type) {
+	case IOMMU_COOKIE_DMA_IOVA:
+		return domain->iova_cookie->iovad.granule;
+	case IOMMU_COOKIE_DMA_MSI:
+		return PAGE_SIZE;
+	default:
+		BUG();
+	}
+}
+
+static struct list_head *cookie_msi_pages(const struct iommu_domain *domain)
+{
+	switch (domain->cookie_type) {
+	case IOMMU_COOKIE_DMA_IOVA:
+		return &domain->iova_cookie->msi_page_list;
+	case IOMMU_COOKIE_DMA_MSI:
+		return &domain->msi_cookie->msi_page_list;
+	default:
+		BUG();
+	}
 }
-EXPORT_SYMBOL_GPL(iommu_setup_dma_ops);
 
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 		phys_addr_t msi_addr, struct iommu_domain *domain)
 {
-	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct list_head *msi_page_list = cookie_msi_pages(domain);
 	struct iommu_dma_msi_page *msi_page;
 	dma_addr_t iova;
 	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
-	size_t size = cookie_msi_granule(cookie);
+	size_t size = cookie_msi_granule(domain);
 
 	msi_addr &= ~(phys_addr_t)(size - 1);
-	list_for_each_entry(msi_page, &cookie->msi_page_list, list)
+	list_for_each_entry(msi_page, msi_page_list, list)
 		if (msi_page->phys == msi_addr)
 			return msi_page;
 
@@ -1356,65 +2167,41 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!iova)
 		goto out_free_page;
 
-	if (iommu_map(domain, iova, msi_addr, size, prot))
+	if (iommu_map(domain, iova, msi_addr, size, prot, GFP_KERNEL))
 		goto out_free_iova;
 
 	INIT_LIST_HEAD(&msi_page->list);
 	msi_page->phys = msi_addr;
 	msi_page->iova = iova;
-	list_add(&msi_page->list, &cookie->msi_page_list);
+	list_add(&msi_page->list, msi_page_list);
 	return msi_page;
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size, NULL);
+	iommu_dma_free_iova(domain, iova, size, NULL);
 out_free_page:
 	kfree(msi_page);
 	return NULL;
 }
 
-int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
+int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+		     phys_addr_t msi_addr)
 {
 	struct device *dev = msi_desc_to_dev(desc);
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	struct iommu_dma_msi_page *msi_page;
-	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
+	const struct iommu_dma_msi_page *msi_page;
 
-	if (!domain || !domain->iova_cookie) {
-		desc->iommu_cookie = NULL;
+	if (!has_msi_cookie(domain)) {
+		msi_desc_set_iommu_msi_iova(desc, 0, 0);
 		return 0;
 	}
 
-	/*
-	 * In fact the whole prepare operation should already be serialised by
-	 * irq_domain_mutex further up the callchain, but that's pretty subtle
-	 * on its own, so consider this locking as failsafe documentation...
-	 */
-	mutex_lock(&msi_prepare_lock);
+	iommu_group_mutex_assert(dev);
 	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
-	mutex_unlock(&msi_prepare_lock);
-
-	msi_desc_set_iommu_cookie(desc, msi_page);
-
 	if (!msi_page)
 		return -ENOMEM;
-	return 0;
-}
 
-void iommu_dma_compose_msi_msg(struct msi_desc *desc,
-			       struct msi_msg *msg)
-{
-	struct device *dev = msi_desc_to_dev(desc);
-	const struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	const struct iommu_dma_msi_page *msi_page;
-
-	msi_page = msi_desc_get_iommu_cookie(desc);
-
-	if (!domain || !domain->iova_cookie || WARN_ON(!msi_page))
-		return;
-
-	msg->address_hi = upper_32_bits(msi_page->iova);
-	msg->address_lo &= cookie_msi_granule(domain->iova_cookie) - 1;
-	msg->address_lo += lower_32_bits(msi_page->iova);
+	msi_desc_set_iommu_msi_iova(desc, msi_page->iova,
+				    ilog2(cookie_msi_granule(domain)));
+	return 0;
 }
 
 static int iommu_dma_init(void)