Merge tag 'iommu-updates-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - New DART IOMMU driver for Apple Silicon M1 chips

 - Optimizations for iommu_[map/unmap] performance

 - Selective TLB flush support for the AMD IOMMU driver to make it more
   efficient on emulated IOMMUs

 - Rework IOVA setup and default domain type setting to move more code
   out of IOMMU drivers and to support runtime switching between certain
   types of default domains

 - VT-d Updates from Lu Baolu:
      - Update the virtual command related registers
      - Enable Intel IOMMU scalable mode by default
      - Preset A/D bits for user space DMA usage
      - Allow devices to have more than 32 outstanding PRs
      - Various cleanups

 - ARM SMMU Updates from Will Deacon:
      SMMUv3:
       - Minor optimisation to avoid zeroing struct members on CMD submission
       - Increased use of batched commands to reduce submission latency
       - Refactoring in preparation for ECMDQ support
      SMMUv2:
       - Fix races when probing devices with identical StreamIDs
       - Optimise walk cache flushing for Qualcomm implementations
       - Allow deep sleep states for some Qualcomm SoCs with shared clocks

 - Various smaller optimizations, cleanups, and fixes

* tag 'iommu-updates-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (85 commits)
  iommu/io-pgtable: Abstract iommu_iotlb_gather access
  iommu/arm-smmu: Fix missing unlock on error in arm_smmu_device_group()
  iommu/vt-d: Add present bit check in pasid entry setup helpers
  iommu/vt-d: Use pasid_pte_is_present() helper function
  iommu/vt-d: Drop the kernel doc annotation
  iommu/vt-d: Allow devices to have more than 32 outstanding PRs
  iommu/vt-d: Preset A/D bits for user space DMA usage
  iommu/vt-d: Enable Intel IOMMU scalable mode by default
  iommu/vt-d: Refactor Kconfig a bit
  iommu/vt-d: Remove unnecessary oom message
  iommu/vt-d: Update the virtual command related registers
  iommu: Allow enabling non-strict mode dynamically
  iommu: Merge strictness and domain type configs
  iommu: Only log strictness for DMA domains
  iommu: Expose DMA domain strictness via sysfs
  iommu: Express DMA strictness via the domain type
  iommu/vt-d: Prepare for multiple DMA domain types
  iommu/arm-smmu: Prepare for multiple DMA domain types
  iommu/amd: Prepare for multiple DMA domain types
  iommu: Introduce explicit type for non-strict DMA domains
  ...

1 files changed, 143 insertions, 52 deletions

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 5a570d495f8d..3303d707bab4 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -7,7 +7,9 @@
 #define pr_fmt(fmt)    "iommu: " fmt
 
 #include <linux/device.h>
+#include <linux/dma-iommu.h>
 #include <linux/kernel.h>
+#include <linux/bits.h>
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -29,7 +31,7 @@ static struct kset *iommu_group_kset;
 static DEFINE_IDA(iommu_group_ida);
 
 static unsigned int iommu_def_domain_type __read_mostly;
-static bool iommu_dma_strict __read_mostly = true;
+static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT);
 static u32 iommu_cmd_line __read_mostly;
 
 struct iommu_group {
@@ -113,6 +115,7 @@ static const char *iommu_domain_type_str(unsigned int t)
 	case IOMMU_DOMAIN_UNMANAGED:
 		return "Unmanaged";
 	case IOMMU_DOMAIN_DMA:
+	case IOMMU_DOMAIN_DMA_FQ:
 		return "Translated";
 	default:
 		return "Unknown";
@@ -133,11 +136,20 @@ static int __init iommu_subsys_init(void)
 		}
 	}
 
+	if (!iommu_default_passthrough() && !iommu_dma_strict)
+		iommu_def_domain_type = IOMMU_DOMAIN_DMA_FQ;
+
 	pr_info("Default domain type: %s %s\n",
 		iommu_domain_type_str(iommu_def_domain_type),
 		(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ?
 			"(set via kernel command line)" : "");
 
+	if (!iommu_default_passthrough())
+		pr_info("DMA domain TLB invalidation policy: %s mode %s\n",
+			iommu_dma_strict ? "strict" : "lazy",
+			(iommu_cmd_line & IOMMU_CMD_LINE_STRICT) ?
+				"(set via kernel command line)" : "");
+
 	return 0;
 }
 subsys_initcall(iommu_subsys_init);
@@ -273,7 +285,9 @@ int iommu_probe_device(struct device *dev)
 	 * support default domains, so the return value is not yet
 	 * checked.
 	 */
+	mutex_lock(&group->mutex);
 	iommu_alloc_default_domain(group, dev);
+	mutex_unlock(&group->mutex);
 
 	if (group->default_domain) {
 		ret = __iommu_attach_device(group->default_domain, dev);
@@ -344,21 +358,13 @@ static int __init iommu_dma_setup(char *str)
 }
 early_param("iommu.strict", iommu_dma_setup);
 
-void iommu_set_dma_strict(bool strict)
+void iommu_set_dma_strict(void)
 {
-	if (strict || !(iommu_cmd_line & IOMMU_CMD_LINE_STRICT))
-		iommu_dma_strict = strict;
+	iommu_dma_strict = true;
+	if (iommu_def_domain_type == IOMMU_DOMAIN_DMA_FQ)
+		iommu_def_domain_type = IOMMU_DOMAIN_DMA;
 }
 
-bool iommu_get_dma_strict(struct iommu_domain *domain)
-{
-	/* only allow lazy flushing for DMA domains */
-	if (domain->type == IOMMU_DOMAIN_DMA)
-		return iommu_dma_strict;
-	return true;
-}
-EXPORT_SYMBOL_GPL(iommu_get_dma_strict);
-
 static ssize_t iommu_group_attr_show(struct kobject *kobj,
 				     struct attribute *__attr, char *buf)
 {
@@ -546,6 +552,9 @@ static ssize_t iommu_group_show_type(struct iommu_group *group,
 		case IOMMU_DOMAIN_DMA:
 			type = "DMA\n";
 			break;
+		case IOMMU_DOMAIN_DMA_FQ:
+			type = "DMA-FQ\n";
+			break;
 		}
 	}
 	mutex_unlock(&group->mutex);
@@ -759,7 +768,7 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group,
 	unsigned long pg_size;
 	int ret = 0;
 
-	if (!domain || domain->type != IOMMU_DOMAIN_DMA)
+	if (!domain || !iommu_is_dma_domain(domain))
 		return 0;
 
 	BUG_ON(!domain->pgsize_bitmap);
@@ -1944,6 +1953,11 @@ static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 	/* Assume all sizes by default; the driver may override this later */
 	domain->pgsize_bitmap  = bus->iommu_ops->pgsize_bitmap;
 
+	/* Temporarily avoid -EEXIST while drivers still get their own cookies */
+	if (iommu_is_dma_domain(domain) && !domain->iova_cookie && iommu_get_dma_cookie(domain)) {
+		iommu_domain_free(domain);
+		domain = NULL;
+	}
 	return domain;
 }
 
@@ -1955,6 +1969,7 @@ EXPORT_SYMBOL_GPL(iommu_domain_alloc);
 
 void iommu_domain_free(struct iommu_domain *domain)
 {
+	iommu_put_dma_cookie(domain);
 	domain->ops->domain_free(domain);
 }
 EXPORT_SYMBOL_GPL(iommu_domain_free);
@@ -2370,45 +2385,94 @@ EXPORT_SYMBOL_GPL(iommu_detach_group);
 
 phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova)
 {
-	if (unlikely(domain->ops->iova_to_phys == NULL))
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
+		return iova;
+
+	if (domain->type == IOMMU_DOMAIN_BLOCKED)
 		return 0;
 
 	return domain->ops->iova_to_phys(domain, iova);
 }
 EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
 
-static size_t iommu_pgsize(struct iommu_domain *domain,
-			   unsigned long addr_merge, size_t size)
+static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova,
+			   phys_addr_t paddr, size_t size, size_t *count)
 {
-	unsigned int pgsize_idx;
-	size_t pgsize;
+	unsigned int pgsize_idx, pgsize_idx_next;
+	unsigned long pgsizes;
+	size_t offset, pgsize, pgsize_next;
+	unsigned long addr_merge = paddr | iova;
 
-	/* Max page size that still fits into 'size' */
-	pgsize_idx = __fls(size);
+	/* Page sizes supported by the hardware and small enough for @size */
+	pgsizes = domain->pgsize_bitmap & GENMASK(__fls(size), 0);
 
-	/* need to consider alignment requirements ? */
-	if (likely(addr_merge)) {
-		/* Max page size allowed by address */
-		unsigned int align_pgsize_idx = __ffs(addr_merge);
-		pgsize_idx = min(pgsize_idx, align_pgsize_idx);
-	}
+	/* Constrain the page sizes further based on the maximum alignment */
+	if (likely(addr_merge))
+		pgsizes &= GENMASK(__ffs(addr_merge), 0);
 
-	/* build a mask of acceptable page sizes */
-	pgsize = (1UL << (pgsize_idx + 1)) - 1;
+	/* Make sure we have at least one suitable page size */
+	BUG_ON(!pgsizes);
 
-	/* throw away page sizes not supported by the hardware */
-	pgsize &= domain->pgsize_bitmap;
+	/* Pick the biggest page size remaining */
+	pgsize_idx = __fls(pgsizes);
+	pgsize = BIT(pgsize_idx);
+	if (!count)
+		return pgsize;
 
-	/* make sure we're still sane */
-	BUG_ON(!pgsize);
+	/* Find the next biggest support page size, if it exists */
+	pgsizes = domain->pgsize_bitmap & ~GENMASK(pgsize_idx, 0);
+	if (!pgsizes)
+		goto out_set_count;
 
-	/* pick the biggest page */
-	pgsize_idx = __fls(pgsize);
-	pgsize = 1UL << pgsize_idx;
+	pgsize_idx_next = __ffs(pgsizes);
+	pgsize_next = BIT(pgsize_idx_next);
 
+	/*
+	 * There's no point trying a bigger page size unless the virtual
+	 * and physical addresses are similarly offset within the larger page.
+	 */
+	if ((iova ^ paddr) & (pgsize_next - 1))
+		goto out_set_count;
+
+	/* Calculate the offset to the next page size alignment boundary */
+	offset = pgsize_next - (addr_merge & (pgsize_next - 1));
+
+	/*
+	 * If size is big enough to accommodate the larger page, reduce
+	 * the number of smaller pages.
+	 */
+	if (offset + pgsize_next <= size)
+		size = offset;
+
+out_set_count:
+	*count = size >> pgsize_idx;
 	return pgsize;
 }
 
+static int __iommu_map_pages(struct iommu_domain *domain, unsigned long iova,
+			     phys_addr_t paddr, size_t size, int prot,
+			     gfp_t gfp, size_t *mapped)
+{
+	const struct iommu_ops *ops = domain->ops;
+	size_t pgsize, count;
+	int ret;
+
+	pgsize = iommu_pgsize(domain, iova, paddr, size, &count);
+
+	pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx count %zu\n",
+		 iova, &paddr, pgsize, count);
+
+	if (ops->map_pages) {
+		ret = ops->map_pages(domain, iova, paddr, pgsize, count, prot,
+				     gfp, mapped);
+	} else {
+		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
+		*mapped = ret ? 0 : pgsize;
+	}
+
+	return ret;
+}
+
 static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 		       phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
 {
@@ -2419,7 +2483,7 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	phys_addr_t orig_paddr = paddr;
 	int ret = 0;
 
-	if (unlikely(ops->map == NULL ||
+	if (unlikely(!(ops->map || ops->map_pages) ||
 		     domain->pgsize_bitmap == 0UL))
 		return -ENODEV;
 
@@ -2443,18 +2507,21 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova,
 	pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size);
 
 	while (size) {
-		size_t pgsize = iommu_pgsize(domain, iova | paddr, size);
+		size_t mapped = 0;
 
-		pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n",
-			 iova, &paddr, pgsize);
-		ret = ops->map(domain, iova, paddr, pgsize, prot, gfp);
+		ret = __iommu_map_pages(domain, iova, paddr, size, prot, gfp,
+					&mapped);
+		/*
+		 * Some pages may have been mapped, even if an error occurred,
+		 * so we should account for those so they can be unmapped.
+		 */
+		size -= mapped;
 
 		if (ret)
 			break;
 
-		iova += pgsize;
-		paddr += pgsize;
-		size -= pgsize;
+		iova += mapped;
+		paddr += mapped;
 	}
 
 	/* unroll mapping in case something went wrong */
@@ -2494,6 +2561,19 @@ int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova,
 }
 EXPORT_SYMBOL_GPL(iommu_map_atomic);
 
+static size_t __iommu_unmap_pages(struct iommu_domain *domain,
+				  unsigned long iova, size_t size,
+				  struct iommu_iotlb_gather *iotlb_gather)
+{
+	const struct iommu_ops *ops = domain->ops;
+	size_t pgsize, count;
+
+	pgsize = iommu_pgsize(domain, iova, iova, size, &count);
+	return ops->unmap_pages ?
+	       ops->unmap_pages(domain, iova, pgsize, count, iotlb_gather) :
+	       ops->unmap(domain, iova, pgsize, iotlb_gather);
+}
+
 static size_t __iommu_unmap(struct iommu_domain *domain,
 			    unsigned long iova, size_t size,
 			    struct iommu_iotlb_gather *iotlb_gather)
@@ -2503,7 +2583,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 	unsigned long orig_iova = iova;
 	unsigned int min_pagesz;
 
-	if (unlikely(ops->unmap == NULL ||
+	if (unlikely(!(ops->unmap || ops->unmap_pages) ||
 		     domain->pgsize_bitmap == 0UL))
 		return 0;
 
@@ -2531,9 +2611,9 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
 	 * or we hit an area that isn't mapped.
 	 */
 	while (unmapped < size) {
-		size_t pgsize = iommu_pgsize(domain, iova, size - unmapped);
-
-		unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather);
+		unmapped_page = __iommu_unmap_pages(domain, iova,
+						    size - unmapped,
+						    iotlb_gather);
 		if (!unmapped_page)
 			break;
 
@@ -3128,6 +3208,14 @@ static int iommu_change_dev_def_domain(struct iommu_group *group,
 		goto out;
 	}
 
+	/* We can bring up a flush queue without tearing down the domain */
+	if (type == IOMMU_DOMAIN_DMA_FQ && prev_dom->type == IOMMU_DOMAIN_DMA) {
+		ret = iommu_dma_init_fq(prev_dom);
+		if (!ret)
+			prev_dom->type = IOMMU_DOMAIN_DMA_FQ;
+		goto out;
+	}
+
 	/* Sets group->default_domain to the newly allocated domain */
 	ret = iommu_group_alloc_default_domain(dev->bus, group, type);
 	if (ret)
@@ -3168,9 +3256,9 @@ out:
 }
 
 /*
- * Changing the default domain through sysfs requires the users to ubind the
- * drivers from the devices in the iommu group. Return failure if this doesn't
- * meet.
+ * Changing the default domain through sysfs requires the users to unbind the
+ * drivers from the devices in the iommu group, except for a DMA -> DMA-FQ
+ * transition. Return failure if this isn't met.
  *
  * We need to consider the race between this and the device release path.
  * device_lock(dev) is used here to guarantee that the device release path
@@ -3193,6 +3281,8 @@ static ssize_t iommu_group_store_type(struct iommu_group *group,
 		req_type = IOMMU_DOMAIN_IDENTITY;
 	else if (sysfs_streq(buf, "DMA"))
 		req_type = IOMMU_DOMAIN_DMA;
+	else if (sysfs_streq(buf, "DMA-FQ"))
+		req_type = IOMMU_DOMAIN_DMA_FQ;
 	else if (sysfs_streq(buf, "auto"))
 		req_type = 0;
 	else
@@ -3244,7 +3334,8 @@ static ssize_t iommu_group_store_type(struct iommu_group *group,
 
 	/* Check if the device in the group still has a driver bound to it */
 	device_lock(dev);
-	if (device_is_bound(dev)) {
+	if (device_is_bound(dev) && !(req_type == IOMMU_DOMAIN_DMA_FQ &&
+	    group->default_domain->type == IOMMU_DOMAIN_DMA)) {
 		pr_err_ratelimited("Device is still bound to driver\n");
 		ret = -EBUSY;
 		goto out;