1 files changed, 79 insertions, 19 deletions

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index efa6cd2500b9..778f167be2d3 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -139,10 +139,14 @@ static struct lock_class_key reserved_rbtree_key;
 static inline int match_hid_uid(struct device *dev,
 				struct acpihid_map_entry *entry)
 {
+	struct acpi_device *adev = ACPI_COMPANION(dev);
 	const char *hid, *uid;
 
-	hid = acpi_device_hid(ACPI_COMPANION(dev));
-	uid = acpi_device_uid(ACPI_COMPANION(dev));
+	if (!adev)
+		return -ENODEV;
+
+	hid = acpi_device_hid(adev);
+	uid = acpi_device_uid(adev);
 
 	if (!hid || !(*hid))
 		return -ENODEV;
@@ -442,7 +446,14 @@ static int iommu_init_device(struct device *dev)
 
 	dev_data->alias = get_alias(dev);
 
-	if (dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
+	/*
+	 * By default we use passthrough mode for IOMMUv2 capable device.
+	 * But if amd_iommu=force_isolation is set (e.g. to debug DMA to
+	 * invalid address), we ignore the capability for the device so
+	 * it'll be forced to go into translation mode.
+	 */
+	if ((iommu_pass_through || !amd_iommu_force_isolation) &&
+	    dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
 		struct amd_iommu *iommu;
 
 		iommu = amd_iommu_rlookup_table[dev_data->devid];
@@ -1143,6 +1154,17 @@ static void amd_iommu_flush_tlb_all(struct amd_iommu *iommu)
 	iommu_completion_wait(iommu);
 }
 
+static void amd_iommu_flush_tlb_domid(struct amd_iommu *iommu, u32 dom_id)
+{
+	struct iommu_cmd cmd;
+
+	build_inv_iommu_pages(&cmd, 0, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
+			      dom_id, 1);
+	iommu_queue_command(iommu, &cmd);
+
+	iommu_completion_wait(iommu);
+}
+
 static void amd_iommu_flush_all(struct amd_iommu *iommu)
 {
 	struct iommu_cmd cmd;
@@ -1319,18 +1341,21 @@ static void domain_flush_devices(struct protection_domain *domain)
  * another level increases the size of the address space by 9 bits to a size up
  * to 64 bits.
  */
-static bool increase_address_space(struct protection_domain *domain,
+static void increase_address_space(struct protection_domain *domain,
 				   gfp_t gfp)
 {
+	unsigned long flags;
 	u64 *pte;
 
-	if (domain->mode == PAGE_MODE_6_LEVEL)
+	spin_lock_irqsave(&domain->lock, flags);
+
+	if (WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL))
 		/* address space already 64 bit large */
-		return false;
+		goto out;
 
 	pte = (void *)get_zeroed_page(gfp);
 	if (!pte)
-		return false;
+		goto out;
 
 	*pte             = PM_LEVEL_PDE(domain->mode,
 					iommu_virt_to_phys(domain->pt_root));
@@ -1338,7 +1363,10 @@ static bool increase_address_space(struct protection_domain *domain,
 	domain->mode    += 1;
 	domain->updated  = true;
 
-	return true;
+out:
+	spin_unlock_irqrestore(&domain->lock, flags);
+
+	return;
 }
 
 static u64 *alloc_pte(struct protection_domain *domain,
@@ -1828,6 +1856,7 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 {
 	u64 pte_root = 0;
 	u64 flags = 0;
+	u32 old_domid;
 
 	if (domain->mode != PAGE_MODE_NONE)
 		pte_root = iommu_virt_to_phys(domain->pt_root);
@@ -1870,8 +1899,20 @@ static void set_dte_entry(u16 devid, struct protection_domain *domain, bool ats)
 	flags &= ~DEV_DOMID_MASK;
 	flags |= domain->id;
 
+	old_domid = amd_iommu_dev_table[devid].data[1] & DEV_DOMID_MASK;
 	amd_iommu_dev_table[devid].data[1]  = flags;
 	amd_iommu_dev_table[devid].data[0]  = pte_root;
+
+	/*
+	 * A kdump kernel might be replacing a domain ID that was copied from
+	 * the previous kernel--if so, it needs to flush the translation cache
+	 * entries for the old domain ID that is being overwritten
+	 */
+	if (old_domid) {
+		struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
+
+		amd_iommu_flush_tlb_domid(iommu, old_domid);
+	}
 }
 
 static void clear_dte_entry(u16 devid)
@@ -1912,6 +1953,7 @@ static void do_attach(struct iommu_dev_data *dev_data,
 
 static void do_detach(struct iommu_dev_data *dev_data)
 {
+	struct protection_domain *domain = dev_data->domain;
 	struct amd_iommu *iommu;
 	u16 alias;
 
@@ -1927,10 +1969,6 @@ static void do_detach(struct iommu_dev_data *dev_data)
 	iommu = amd_iommu_rlookup_table[dev_data->devid];
 	alias = dev_data->alias;
 
-	/* decrease reference counters */
-	dev_data->domain->dev_iommu[iommu->index] -= 1;
-	dev_data->domain->dev_cnt                 -= 1;
-
 	/* Update data structures */
 	dev_data->domain = NULL;
 	list_del(&dev_data->list);
@@ -1940,6 +1978,16 @@ static void do_detach(struct iommu_dev_data *dev_data)
 
 	/* Flush the DTE entry */
 	device_flush_dte(dev_data);
+
+	/* Flush IOTLB */
+	domain_flush_tlb_pde(domain);
+
+	/* Wait for the flushes to finish */
+	domain_flush_complete(domain);
+
+	/* decrease reference counters - needs to happen after the flushes */
+	domain->dev_iommu[iommu->index] -= 1;
+	domain->dev_cnt                 -= 1;
 }
 
 /*
@@ -2112,6 +2160,8 @@ skip_ats_check:
 	 */
 	domain_flush_tlb_pde(domain);
 
+	domain_flush_complete(domain);
+
 	return ret;
 }
 
@@ -2524,7 +2574,9 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 
 			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
 			phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
-			ret = iommu_map_page(domain, bus_addr, phys_addr, PAGE_SIZE, prot, GFP_ATOMIC);
+			ret = iommu_map_page(domain, bus_addr, phys_addr,
+					     PAGE_SIZE, prot,
+					     GFP_ATOMIC | __GFP_NOWARN);
 			if (ret)
 				goto out_unmap;
 
@@ -2534,7 +2586,12 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 
 	/* Everything is mapped - write the right values into s->dma_address */
 	for_each_sg(sglist, s, nelems, i) {
-		s->dma_address += address + s->offset;
+		/*
+		 * Add in the remaining piece of the scatter-gather offset that
+		 * was masked out when we were determining the physical address
+		 * via (sg_phys(s) & PAGE_MASK) earlier.
+		 */
+		s->dma_address += address + (s->offset & ~PAGE_MASK);
 		s->dma_length   = s->length;
 	}
 
@@ -2553,13 +2610,13 @@ out_unmap:
 			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
 			iommu_unmap_page(domain, bus_addr, PAGE_SIZE);
 
-			if (--mapped_pages)
+			if (--mapped_pages == 0)
 				goto out_free_iova;
 		}
 	}
 
 out_free_iova:
-	free_iova_fast(&dma_dom->iovad, address, npages);
+	free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages);
 
 out_err:
 	return 0;
@@ -3108,21 +3165,24 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 		return;
 
 	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+		int type, prot = 0;
 		size_t length;
-		int prot = 0;
 
 		if (devid < entry->devid_start || devid > entry->devid_end)
 			continue;
 
+		type   = IOMMU_RESV_DIRECT;
 		length = entry->address_end - entry->address_start;
 		if (entry->prot & IOMMU_PROT_IR)
 			prot |= IOMMU_READ;
 		if (entry->prot & IOMMU_PROT_IW)
 			prot |= IOMMU_WRITE;
+		if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE)
+			/* Exclusion range */
+			type = IOMMU_RESV_RESERVED;
 
 		region = iommu_alloc_resv_region(entry->address_start,
-						 length, prot,
-						 IOMMU_RESV_DIRECT);
+						 length, prot, type);
 		if (!region) {
 			pr_err("Out of memory allocating dm-regions for %s\n",
 				dev_name(dev));