Merge branch 'for-next/iommu/vt-d' into for-next/iommu/core

Intel VT-D updates for 5.11. The main thing here is converting the code
over to the iommu-dma API, which required some improvements to the core
code to preserve existing functionality.

* for-next/iommu/vt-d:
  iommu/vt-d: Avoid GFP_ATOMIC where it is not needed
  iommu/vt-d: Remove set but not used variable
  iommu/vt-d: Cleanup after converting to dma-iommu ops
  iommu/vt-d: Convert intel iommu driver to the iommu ops
  iommu/vt-d: Update domain geometry in iommu_ops.at(de)tach_dev
  iommu: Add quirk for Intel graphic devices in map_sg
  iommu: Allow the dma-iommu api to use bounce buffers
  iommu: Add iommu_dma_free_cpu_cached_iovas()
  iommu: Handle freelists when using deferred flushing in iommu drivers
  iommu/vt-d: include conditionally on CONFIG_INTEL_IOMMU_SVM

Documentation/admin-guide/kernel-parameters.txt

@@ -1883,11 +1883,6 @@
 			Note that using this option lowers the security
 			provided by tboot because it makes the system
 			vulnerable to DMA attacks.
-		nobounce [Default off]
-			Disable bounce buffer for untrusted devices such as
-			the Thunderbolt devices. This will treat the untrusted
-			devices as the trusted ones, hence might expose security
-			risks of DMA attacks.
 
 	intel_idle.max_cstate=	[KNL,HW,ACPI,X86]
 			0	disables intel_idle and fall back on acpi_idle.

drivers/iommu/dma-iommu.c

@@ -20,9 +20,11 @@
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/swiotlb.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
 #include <linux/crash_dump.h>
+#include <linux/dma-direct.h>
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -49,6 +51,27 @@ struct iommu_dma_cookie {
 	struct iommu_domain		*fq_domain;
 };
 
+void iommu_dma_free_cpu_cached_iovas(unsigned int cpu,
+		struct iommu_domain *domain)
+{
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+
+	free_cpu_cached_iovas(cpu, iovad);
+}
+
+static void iommu_dma_entry_dtor(unsigned long data)
+{
+	struct page *freelist = (struct page *)data;
+
+	while (freelist) {
+		unsigned long p = (unsigned long)page_address(freelist);
+
+		freelist = freelist->freelist;
+		free_page(p);
+	}
+}
+
 static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
 {
 	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
@@ -343,7 +366,7 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 	if (!cookie->fq_domain && !iommu_domain_get_attr(domain,
 			DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) {
 		if (init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all,
-					NULL))
+					  iommu_dma_entry_dtor))
 			pr_warn("iova flush queue initialization failed\n");
 		else
 			cookie->fq_domain = domain;
@@ -440,7 +463,7 @@ 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)
+		dma_addr_t iova, size_t size, struct page *freelist)
 {
 	struct iova_domain *iovad = &cookie->iovad;
 
@@ -449,7 +472,8 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 		cookie->msi_iova -= size;
 	else if (cookie->fq_domain)	/* non-strict mode */
 		queue_iova(iovad, iova_pfn(iovad, iova),
-				size >> iova_shift(iovad), 0);
+				size >> iova_shift(iovad),
+				(unsigned long)freelist);
 	else
 		free_iova_fast(iovad, iova_pfn(iovad, iova),
 				size >> iova_shift(iovad));
@@ -474,7 +498,32 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 
 	if (!cookie->fq_domain)
 		iommu_iotlb_sync(domain, &iotlb_gather);
-	iommu_dma_free_iova(cookie, dma_addr, size);
+	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);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	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,
+				iova_align(iovad, size), dir, attrs);
+}
+
+static bool dev_is_untrusted(struct device *dev)
+{
+	return dev_is_pci(dev) && to_pci_dev(dev)->untrusted;
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
@@ -496,12 +545,60 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 		return DMA_MAPPING_ERROR;
 
 	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
-		iommu_dma_free_iova(cookie, iova, size);
+		iommu_dma_free_iova(cookie, 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,
+				aligned_size, dir, attrs);
+
+	return iova;
+}
+
 static void __iommu_dma_free_pages(struct page **pages, int count)
 {
 	while (count--)
@@ -649,7 +746,7 @@ out_unmap:
 out_free_sg:
 	sg_free_table(&sgt);
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size);
+	iommu_dma_free_iova(cookie, iova, size, NULL);
 out_free_pages:
 	__iommu_dma_free_pages(pages, count);
 	return NULL;
@@ -675,11 +772,15 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev))
+	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_cpu(phys, size, dir);
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_cpu(phys, size, dir);
+
+	if (is_swiotlb_buffer(phys))
+		swiotlb_tbl_sync_single(dev, phys, size, dir, SYNC_FOR_CPU);
 }
 
 static void iommu_dma_sync_single_for_device(struct device *dev,
@@ -687,11 +788,15 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 {
 	phys_addr_t phys;
 
-	if (dev_is_dma_coherent(dev))
+	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_device(phys, size, dir);
+	if (is_swiotlb_buffer(phys))
+		swiotlb_tbl_sync_single(dev, phys, size, dir, SYNC_FOR_DEVICE);
+
+	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,
@@ -701,11 +806,17 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
+	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
 		return;
 
-	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
+	for_each_sg(sgl, sg, nelems, i) {
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
+
+		if (is_swiotlb_buffer(sg_phys(sg)))
+			swiotlb_tbl_sync_single(dev, sg_phys(sg), sg->length,
+						dir, SYNC_FOR_CPU);
+	}
 }
 
 static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -715,11 +826,17 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (dev_is_dma_coherent(dev))
+	if (dev_is_dma_coherent(dev) && !dev_is_untrusted(dev))
 		return;
 
-	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_tbl_sync_single(dev, sg_phys(sg), sg->length,
+						dir, SYNC_FOR_DEVICE);
+
+		if (!dev_is_dma_coherent(dev))
+			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
+	}
 }
 
 static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
@@ -728,10 +845,10 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
-	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dma_handle;
 
-	dma_handle = __iommu_dma_map(dev, phys, size, prot, dma_get_mask(dev));
+	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)
 		arch_sync_dma_for_device(phys, size, dir);
@@ -743,7 +860,7 @@ static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 {
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_single_for_cpu(dev, dma_handle, size, dir);
-	__iommu_dma_unmap(dev, dma_handle, size);
+	__iommu_dma_unmap_swiotlb(dev, dma_handle, size, dir, attrs);
 }
 
 /*
@@ -761,6 +878,33 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
 	int i, count = 0;
 
+	/*
+	 * The Intel graphic driver is used to assume that the returned
+	 * sg list is not combound. This blocks the efforts of converting
+	 * Intel IOMMU driver to dma-iommu api's. Add this quirk to make the
+	 * device driver work and should be removed once it's fixed in i915
+	 * driver.
+	 */
+	if (IS_ENABLED(CONFIG_DRM_I915) && dev_is_pci(dev) &&
+	    to_pci_dev(dev)->vendor == PCI_VENDOR_ID_INTEL &&
+	    (to_pci_dev(dev)->class >> 16) == PCI_BASE_CLASS_DISPLAY) {
+		for_each_sg(sg, s, nents, i) {
+			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_addr + s_iova_off;
+			sg_dma_len(s) = s_length;
+			dma_addr += s_iova_len;
+
+			pr_info_once("sg combining disabled due to i915 driver\n");
+		}
+
+		return nents;
+	}
+
 	for_each_sg(sg, s, nents, i) {
 		/* Restore this segment's original unaligned fields first */
 		unsigned int s_iova_off = sg_dma_address(s);
@@ -821,6 +965,39 @@ static void __invalidate_sg(struct scatterlist *sg, int nents)
 	}
 }
 
+static void iommu_dma_unmap_sg_swiotlb(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		__iommu_dma_unmap_swiotlb(dev, sg_dma_address(s),
+				sg_dma_len(s), dir, attrs);
+}
+
+static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	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);
+		if (sg_dma_address(s) == DMA_MAPPING_ERROR)
+			goto out_unmap;
+		sg_dma_len(s) = s->length;
+	}
+
+	return nents;
+
+out_unmap:
+	iommu_dma_unmap_sg_swiotlb(dev, sg, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
+	return 0;
+}
+
 /*
  * The DMA API client is passing in a scatterlist which could describe
  * any old buffer layout, but the IOMMU API requires everything to be
@@ -847,6 +1024,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	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
@@ -900,7 +1080,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	return __finalise_sg(dev, sg, nents, iova);
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, iova_len);
+	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
 out_restore_sg:
 	__invalidate_sg(sg, nents);
 	return 0;
@@ -916,6 +1096,11 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_cpu(dev, sg, nents, dir);
 
+	if (dev_is_untrusted(dev)) {
+		iommu_dma_unmap_sg_swiotlb(dev, sg, nents, dir, attrs);
+		return;
+	}
+
 	/*
 	 * The scatterlist segments are mapped into a single
 	 * contiguous IOVA allocation, so this is incredibly easy.
@@ -1228,7 +1413,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size);
+	iommu_dma_free_iova(cookie, iova, size, NULL);
 out_free_page:
 	kfree(msi_page);
 	return NULL;

drivers/iommu/intel/Kconfig

@@ -13,6 +13,7 @@ config INTEL_IOMMU
 	select DMAR_TABLE
 	select SWIOTLB
 	select IOASID
+	select IOMMU_DMA
 	help
 	  DMA remapping (DMAR) devices support enables independent address
 	  translations for Direct Memory Access (DMA) from devices.

drivers/xen/swiotlb-xen.c

@@ -395,8 +395,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 */
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
-	map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start),
-				     phys, size, size, dir, attrs);
+	map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs);
 	if (map == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;
 

include/linux/dma-iommu.h

@@ -37,6 +37,9 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc,
 
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
+void iommu_dma_free_cpu_cached_iovas(unsigned int cpu,
+		struct iommu_domain *domain);
+
 #else /* CONFIG_IOMMU_DMA */
 
 struct iommu_domain;
@@ -78,5 +81,10 @@ static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_he
 {
 }
 
+static inline void iommu_dma_free_cpu_cached_iovas(unsigned int cpu,
+		struct iommu_domain *domain)
+{
+}
+
 #endif	/* CONFIG_IOMMU_DMA */
 #endif	/* __DMA_IOMMU_H */

include/linux/iommu.h

@@ -181,6 +181,7 @@ struct iommu_iotlb_gather {
 	unsigned long		start;
 	unsigned long		end;
 	size_t			pgsize;
+	struct page		*freelist;
 };
 
 /**

include/linux/swiotlb.h

@@ -45,13 +45,9 @@ enum dma_sync_target {
 	SYNC_FOR_DEVICE = 1,
 };
 
-extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-					  dma_addr_t tbl_dma_addr,
-					  phys_addr_t phys,
-					  size_t mapping_size,
-					  size_t alloc_size,
-					  enum dma_data_direction dir,
-					  unsigned long attrs);
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,

kernel/dma/swiotlb.c

@@ -229,6 +229,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	if (verbose)
 		swiotlb_print_info();
@@ -260,9 +261,11 @@ swiotlb_init(int verbose)
 	if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
 		return;
 
-	if (io_tlb_start)
+	if (io_tlb_start) {
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+		io_tlb_start = 0;
+	}
 	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
@@ -360,6 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 		io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
 	}
 	io_tlb_index = 0;
+	no_iotlb_memory = false;
 
 	swiotlb_print_info();
 
@@ -441,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 	}
 }
 
-phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
-				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr,
-				   size_t mapping_size,
-				   size_t alloc_size,
-				   enum dma_data_direction dir,
-				   unsigned long attrs)
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr,
+		size_t mapping_size, size_t alloc_size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
+	dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start);
 	unsigned long flags;
 	phys_addr_t tlb_addr;
 	unsigned int nslots, stride, index, wrap;
@@ -667,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
 	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
 			      swiotlb_force);
 
-	swiotlb_addr = swiotlb_tbl_map_single(dev,
-			phys_to_dma_unencrypted(dev, io_tlb_start),
-			paddr, size, size, dir, attrs);
+	swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir,
+			attrs);
 	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
 		return DMA_MAPPING_ERROR;