[PATCH 6/8] iommu: allow the dma-iommu api to use bounce buffers

[Tom Murphy <murphyt7@tcd.ie>]

Allow the dma-iommu api to use bounce buffers for untrusted devices.
This is a copy of the intel bounce buffer code.

Signed-off-by: Tom Murphy <murphyt7@tcd.ie>
---
 drivers/iommu/dma-iommu.c | 93 ++++++++++++++++++++++++++++++++-------
 drivers/iommu/iommu.c     | 10 +++++
 include/linux/iommu.h     |  9 +++-
 3 files changed, 95 insertions(+), 17 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 4eac3cd35443..cf778db7d84d 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -20,9 +20,11 @@
 #include <linux/irq.h>
 #include <linux/mm.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;
@@ -505,29 +507,89 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 			iommu_tlb_sync(domain, &iotlb_gather);
 	}
 
+
 	iommu_dma_free_iova(cookie, dma_addr, size, 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;
+	size_t iova_off = iova_offset(iovad, dma_addr);
+	size_t aligned_size = iova_align(iovad, size + iova_off);
+	phys_addr_t phys;
+
+	phys = iommu_iova_to_phys(domain, dma_addr);
+	if (WARN_ON(!phys))
+		return;
+
+	__iommu_dma_unmap(dev, dma_addr, size);
+
+#ifdef CONFIG_SWIOTLB
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size,
+				aligned_size, dir, attrs);
+#endif
+}
+
 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 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 iova_off = iova_offset(iovad, phys);
+	size_t aligned_size = iova_align(iovad, org_size + iova_off);
 	dma_addr_t iova;
 
 	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
 		return DMA_MAPPING_ERROR;
 
-	size = iova_align(iovad, size + iova_off);
+#ifdef CONFIG_SWIOTLB
+	/*
+	 * If both the physical buffer start address and size are
+	 * page aligned, we don't need to use a bounce page.
+	 */
+	if (iommu_needs_bounce_buffer(dev)
+			&& !iova_offset(iovad, phys | org_size)) {
+		phys = swiotlb_tbl_map_single(dev,
+				__phys_to_dma(dev, io_tlb_start),
+				phys, org_size, aligned_size, dir, attrs);
+
+		if (phys == DMA_MAPPING_ERROR)
+			return DMA_MAPPING_ERROR;
+
+		/* Cleanup the padding area. */
+		void *padding_start = phys_to_virt(phys);
+		size_t 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;
+		}
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
+		memset(padding_start, 0, padding_size);
+	}
+#endif
+
+	iova = iommu_dma_alloc_iova(domain, aligned_size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
-	if (iommu_map_atomic(domain, iova, phys - iova_off, size, prot)) {
-		iommu_dma_free_iova(cookie, iova, size, NULL);
+	if (iommu_map_atomic(domain, iova, phys - iova_off, aligned_size,
+				prot)) {
+
+		if (unlikely(is_swiotlb_buffer(phys)))
+			swiotlb_tbl_unmap_single(dev, phys, aligned_size,
+					aligned_size, dir, attrs);
+		iommu_dma_free_iova(cookie, iova, aligned_size, NULL);
 		return DMA_MAPPING_ERROR;
 	}
 	return iova + iova_off;
@@ -761,10 +823,10 @@ 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(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);
@@ -776,7 +838,7 @@ 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);
 }
 
 /*
@@ -960,21 +1022,20 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		sg = tmp;
 	}
 	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(dev, start, end - start);
+	__iommu_dma_unmap_swiotlb(dev, start, end - start, dir, attrs);
 }
 
 static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	return __iommu_dma_map(dev, phys, size,
-			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
-			dma_get_mask(dev));
+	return __iommu_dma_map(dev, phys, size, dma_get_mask(dev), false, dir,
+			attrs);
 }
 
 static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_unmap_swiotlb(dev, handle, size, dir, attrs);
 }
 
 static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
@@ -1056,7 +1117,6 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
 {
 	bool coherent = dev_is_dma_coherent(dev);
-	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
 	struct page *page = NULL;
 	void *cpu_addr;
 
@@ -1074,8 +1134,9 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	if (!cpu_addr)
 		return NULL;
 
-	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot,
-			dev->coherent_dma_mask);
+	*handle = __iommu_dma_map(dev, page_to_phys(page), size,
+			dev->coherent_dma_mask, coherent, DMA_BIDIRECTIONAL,
+			attrs);
 	if (*handle == DMA_MAPPING_ERROR) {
 		__iommu_dma_free(dev, size, cpu_addr);
 		return NULL;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index cec728f40d9c..e5653cb20c83 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2236,6 +2236,16 @@ void iommu_get_resv_regions(struct device *dev, struct list_head *list)
 		ops->get_resv_regions(dev, list);
 }
 
+int iommu_needs_bounce_buffer(struct device *dev)
+{
+	const struct iommu_ops *ops = dev->bus->iommu_ops;
+
+	if (ops && ops->needs_bounce_buffer)
+		return ops->needs_bounce_buffer(dev);
+
+	return 0;
+}
+
 void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 61cac25410b5..d377ffa362a7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -280,6 +280,7 @@ struct iommu_ops {
 			       enum iommu_attr attr, void *data);
 	int (*domain_set_attr)(struct iommu_domain *domain,
 			       enum iommu_attr attr, void *data);
+	int (*needs_bounce_buffer)(struct device *dev);
 
 	/* Request/Free a list of reserved regions for a device */
 	void (*get_resv_regions)(struct device *dev, struct list_head *list);
@@ -460,6 +461,7 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
+extern int iommu_needs_bounce_buffer(struct device *dev);
 extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
 extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
@@ -530,7 +532,7 @@ static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
 		domain->ops->flush_iotlb_all(domain);
 }
 
-static inline void flush_iotlb_range(struct iommu_domain *domain,
+static inline void iommu_flush_iotlb_range(struct iommu_domain *domain,
 			unsigned long iova, size_t size,
 			struct page *freelist)
 {
@@ -764,6 +766,11 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 {
 }
 
+static inline int iommu_needs_bounce_buffer(struct device *dev)
+{
+	return 0;
+}
+
 static inline void iommu_get_resv_regions(struct device *dev,
 					struct list_head *list)
 {
-- 
2.20.1