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, 34 insertions, 17 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 174b2b309fde..896bea04c347 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -317,6 +317,30 @@ static bool dev_is_untrusted(struct device *dev)
 	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
 }
 
+/* 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 ret;
+
+	if (cookie->fq_domain)
+		return 0;
+
+	ret = init_iova_flush_queue(&cookie->iovad, iommu_dma_flush_iotlb_all,
+				    iommu_dma_entry_dtor);
+	if (ret) {
+		pr_warn("iova flush queue initialization failed\n");
+		return ret;
+	}
+	/*
+	 * Prevent incomplete iovad->fq 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_dma_init_domain - Initialise a DMA mapping domain
  * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
@@ -370,17 +394,9 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 
 	init_iova_domain(iovad, 1UL << order, base_pfn);
 
-	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;
-	}
-
-	if (!dev)
-		return 0;
+	/* If the FQ fails we can simply fall back to strict mode */
+	if (domain->type == IOMMU_DOMAIN_DMA_FQ && iommu_dma_init_fq(domain))
+		domain->type = IOMMU_DOMAIN_DMA;
 
 	return iova_reserve_iommu_regions(dev, domain);
 }
@@ -455,17 +471,17 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 }
 
 static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
-		dma_addr_t iova, size_t size, struct page *freelist)
+		dma_addr_t iova, size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct iova_domain *iovad = &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 */
+	else if (gather && gather->queued)
 		queue_iova(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad),
-				(unsigned long)freelist);
+				(unsigned long)gather->freelist);
 	else
 		free_iova_fast(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad));
@@ -484,13 +500,14 @@ 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);
+	iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
 }
 
 static void __iommu_dma_unmap_swiotlb(struct device *dev, dma_addr_t dma_addr,
@@ -1330,7 +1347,7 @@ void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit)
 	 * The IOMMU core code allocates the default DMA domain, which the
 	 * underlying IOMMU driver needs to support via the dma-iommu layer.
 	 */
-	if (domain->type == IOMMU_DOMAIN_DMA) {
+	if (iommu_is_dma_domain(domain)) {
 		if (iommu_dma_init_domain(domain, dma_base, dma_limit, dev))
 			goto out_err;
 		dev->dma_ops = &iommu_dma_ops;