Merge tag 'iommu-fixes-v5.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu fixes from Joerg Roedel:

 - Fix kmemleak warning in IOVA code

 - Fix compile warnings on ARM32/64 in dma-iommu code due to dma_mask
   type mismatches

 - Make ISA reserved regions relaxable, so that VFIO can assign devices
   which have such regions defined

 - Fix mapping errors resulting in IO page-faults in the VT-d driver

 - Make sure direct mappings for a domain are created after the default
   domain is updated

 - Map ISA reserved regions in the VT-d driver with correct permissions

 - Remove unneeded check for PSI capability in the IOTLB flush code of
   the VT-d driver

 - Lockdep fix iommu_dma_prepare_msi()

* tag 'iommu-fixes-v5.5-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/dma: Relax locking in iommu_dma_prepare_msi()
  iommu/vt-d: Remove incorrect PSI capability check
  iommu/vt-d: Allocate reserved region for ISA with correct permission
  iommu: set group default domain before creating direct mappings
  iommu/vt-d: Fix dmar pte read access not set error
  iommu/vt-d: Set ISA bridge reserved region as relaxable
  iommu/dma: Rationalise types for DMA masks
  iommu/iova: Init the struct iova to fix the possible memleak

drivers/iommu/dma-iommu.c

@@ -19,6 +19,7 @@
 #include <linux/iova.h>
 #include <linux/irq.h>
 #include <linux/mm.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
@@ -44,7 +45,6 @@ struct iommu_dma_cookie {
 		dma_addr_t		msi_iova;
 	};
 	struct list_head		msi_page_list;
-	spinlock_t			msi_lock;
 
 	/* Domain for flush queue callback; NULL if flush queue not in use */
 	struct iommu_domain		*fq_domain;
@@ -63,7 +63,6 @@ static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
 
 	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
 	if (cookie) {
-		spin_lock_init(&cookie->msi_lock);
 		INIT_LIST_HEAD(&cookie->msi_page_list);
 		cookie->type = type;
 	}
@@ -399,7 +398,7 @@ static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
 }
 
 static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
-		size_t size, dma_addr_t dma_limit, struct device *dev)
+		size_t size, u64 dma_limit, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
@@ -424,7 +423,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
 	if (domain->geometry.force_aperture)
-		dma_limit = min(dma_limit, domain->geometry.aperture_end);
+		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) && dev_is_pci(dev))
@@ -477,7 +476,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot, dma_addr_t dma_mask)
+		size_t size, int prot, u64 dma_mask)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -1176,7 +1175,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 		if (msi_page->phys == msi_addr)
 			return msi_page;
 
-	msi_page = kzalloc(sizeof(*msi_page), GFP_ATOMIC);
+	msi_page = kzalloc(sizeof(*msi_page), GFP_KERNEL);
 	if (!msi_page)
 		return NULL;
 
@@ -1206,7 +1205,7 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	struct iommu_dma_cookie *cookie;
 	struct iommu_dma_msi_page *msi_page;
-	unsigned long flags;
+	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
 
 	if (!domain || !domain->iova_cookie) {
 		desc->iommu_cookie = NULL;
@@ -1216,13 +1215,13 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 	cookie = domain->iova_cookie;
 
 	/*
-	 * We disable IRQs to rule out a possible inversion against
-	 * irq_desc_lock if, say, someone tries to retarget the affinity
-	 * of an MSI from within an IPI handler.
+	 * 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...
 	 */
-	spin_lock_irqsave(&cookie->msi_lock, flags);
+	mutex_lock(&msi_prepare_lock);
 	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
-	spin_unlock_irqrestore(&cookie->msi_lock, flags);
+	mutex_unlock(&msi_prepare_lock);
 
 	msi_desc_set_iommu_cookie(desc, msi_page);
 

drivers/iommu/intel-iommu.c

@@ -5478,9 +5478,6 @@ static int intel_iommu_map(struct iommu_domain *domain,
 	int prot = 0;
 	int ret;
 
-	if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
-		return -EINVAL;
-
 	if (iommu_prot & IOMMU_READ)
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
@@ -5523,8 +5520,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain,
 	/* Cope with horrid API which requires us to unmap more than the
 	   size argument if it happens to be a large-page mapping. */
 	BUG_ON(!pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level));
-	if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
-		return 0;
 
 	if (size < VTD_PAGE_SIZE << level_to_offset_bits(level))
 		size = VTD_PAGE_SIZE << level_to_offset_bits(level);
@@ -5556,9 +5551,6 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	int level = 0;
 	u64 phys = 0;
 
-	if (dmar_domain->flags & DOMAIN_FLAG_LOSE_CHILDREN)
-		return 0;
-
 	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, &level);
 	if (pte)
 		phys = dma_pte_addr(pte);
@@ -5736,8 +5728,8 @@ static void intel_iommu_get_resv_regions(struct device *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, 0,
-						      IOMMU_RESV_DIRECT);
+			reg = iommu_alloc_resv_region(0, 1UL << 24, prot,
+						   IOMMU_RESV_DIRECT_RELAXABLE);
 			if (reg)
 				list_add_tail(&reg->list, head);
 		}

drivers/iommu/intel-svm.c

@@ -104,11 +104,7 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 {
 	struct qi_desc desc;
 
-	/*
-	 * Do PASID granu IOTLB invalidation if page selective capability is
-	 * not available.
-	 */
-	if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) {
+	if (pages == -1) {
 		desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
 			QI_EIOTLB_DID(sdev->did) |
 			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |

drivers/iommu/iommu.c

@@ -2282,13 +2282,13 @@ request_default_domain_for_dev(struct device *dev, unsigned long type)
 		goto out;
 	}
 
-	iommu_group_create_direct_mappings(group, dev);
-
 	/* Make the domain the default for this group */
 	if (group->default_domain)
 		iommu_domain_free(group->default_domain);
 	group->default_domain = domain;
 
+	iommu_group_create_direct_mappings(group, dev);
+
 	dev_info(dev, "Using iommu %s mapping\n",
 		 type == IOMMU_DOMAIN_DMA ? "dma" : "direct");
 

drivers/iommu/iova.c

@@ -233,7 +233,7 @@ static DEFINE_MUTEX(iova_cache_mutex);
 
 struct iova *alloc_iova_mem(void)
 {
-	return kmem_cache_alloc(iova_cache, GFP_ATOMIC);
+	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC);
 }
 EXPORT_SYMBOL(alloc_iova_mem);