[PATCH 1/2] dma-mapping: add a dma_ops_bypass flag to struct device

[Christoph Hellwig]

Several IOMMU drivers have a bypass mode where they can use a direct
mapping if the devices DMA mask is large enough.  Add generic support
to the core dma-mapping code to do that to switch those drivers to
a common solution.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
 include/linux/device.h      |  4 ++++
 include/linux/dma-mapping.h | 30 ++++++++++++++++++------------
 kernel/dma/mapping.c        | 35 ++++++++++++++++++++++++++---------
 3 files changed, 48 insertions(+), 21 deletions(-)

diff --git a/include/linux/device.h b/include/linux/device.h
index 297239a08bb7..b8a3b4ec46bd 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1217,6 +1217,9 @@ struct dev_links_info {
  *              device.
  * @dma_coherent: this particular device is dma coherent, even if the
  *		architecture supports non-coherent devices.
+ * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the
+ *		streaming DMA operations (->map_* / ->unmap_* / ->sync_*).
+ *		This flag is managed by the dma_ops from ->dma_supported.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -1316,6 +1319,7 @@ struct device {
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	bool			dma_coherent:1;
 #endif
+	bool			dma_ops_bypass : 1;
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4d450672b7d6..22fe74179e02 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -191,9 +191,15 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
-static inline bool dma_is_direct(const struct dma_map_ops *ops)
+/*
+ * Check if the devices uses a direct mapping for streaming DMA operations.
+ * This allows IOMMU drivers to set a bypass mode if the DMA mask is large
+ * enough.
+ */
+static inline bool dma_map_direct(struct device *dev,
+		const struct dma_map_ops *ops)
 {
-	return likely(!ops);
+	return likely(!ops) || dev->dma_ops_bypass;
 }
 
 /*
@@ -282,7 +288,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
 	else
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
@@ -297,7 +303,7 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_unmap_page(dev, addr, size, dir, attrs);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, addr, size, dir, attrs);
@@ -316,7 +322,7 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
 		ents = ops->map_sg(dev, sg, nents, dir, attrs);
@@ -334,7 +340,7 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
 	else if (ops->unmap_sg)
 		ops->unmap_sg(dev, sg, nents, dir, attrs);
@@ -355,7 +361,7 @@ static inline dma_addr_t dma_map_resource(struct device *dev,
 	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
 		return DMA_MAPPING_ERROR;
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
 	else if (ops->map_resource)
 		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
@@ -371,7 +377,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (!dma_is_direct(ops) && ops->unmap_resource)
+	if (!dma_map_direct(dev, ops) && ops->unmap_resource)
 		ops->unmap_resource(dev, addr, size, dir, attrs);
 	debug_dma_unmap_resource(dev, addr, size, dir);
 }
@@ -383,7 +389,7 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 	else if (ops->sync_single_for_cpu)
 		ops->sync_single_for_cpu(dev, addr, size, dir);
@@ -397,7 +403,7 @@ static inline void dma_sync_single_for_device(struct device *dev,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_single_for_device(dev, addr, size, dir);
 	else if (ops->sync_single_for_device)
 		ops->sync_single_for_device(dev, addr, size, dir);
@@ -411,7 +417,7 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
 	else if (ops->sync_sg_for_cpu)
 		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
@@ -425,7 +431,7 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
 	else if (ops->sync_sg_for_device)
 		ops->sync_sg_for_device(dev, sg, nelems, dir);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 12ff766ec1fa..fdb6e16c1b00 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -105,6 +105,19 @@ void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 }
 EXPORT_SYMBOL(dmam_alloc_attrs);
 
+/*
+ * Check if the devices uses a direct mapping for DMA allocations.
+ * This allows IOMMU drivers to set a bypass mode if the DMA mask is large
+ * enough.
+ */
+static inline bool dma_alloc_direct(struct device *dev,
+		const struct dma_map_ops *ops)
+{
+	return likely(!ops) ||
+		(dev->dma_ops_bypass &&
+		 dma_direct_supported(dev, dev->coherent_dma_mask));
+}
+
 /*
  * Create scatter-list for the already allocated DMA buffer.
  */
@@ -138,7 +151,7 @@ int dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
 				size, attrs);
 	if (!ops->get_sgtable)
@@ -206,7 +219,7 @@ bool dma_can_mmap(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_can_mmap(dev);
 	return ops->mmap != NULL;
 }
@@ -231,7 +244,7 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
 				attrs);
 	if (!ops->mmap)
@@ -244,7 +257,7 @@ u64 dma_get_required_mask(struct device *dev)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		return dma_direct_get_required_mask(dev);
 	if (ops->get_required_mask)
 		return ops->get_required_mask(dev);
@@ -275,7 +288,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* let the implementation decide on the zone to allocate from: */
 	flag &= ~(__GFP_DMA | __GFP_DMA32 | __GFP_HIGHMEM);
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		cpu_addr = dma_direct_alloc(dev, size, dma_handle, flag, attrs);
 	else if (ops->alloc)
 		cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
@@ -307,7 +320,7 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 
 	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		dma_direct_free(dev, size, cpu_addr, dma_handle, attrs);
 	else if (ops->free)
 		ops->free(dev, size, cpu_addr, dma_handle, attrs);
@@ -318,7 +331,11 @@ int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
-	if (dma_is_direct(ops))
+	/*
+	 * Only call the dma-direct version if we really do not have any ops
+	 * set, as the dma_supported op will set the dma_ops_bypass flag.
+	 */
+	if (!ops)
 		return dma_direct_supported(dev, mask);
 	if (!ops->dma_supported)
 		return 1;
@@ -374,7 +391,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 
 	BUG_ON(!valid_dma_direction(dir));
 
-	if (dma_is_direct(ops))
+	if (dma_alloc_direct(dev, ops))
 		arch_dma_cache_sync(dev, vaddr, size, dir);
 	else if (ops->cache_sync)
 		ops->cache_sync(dev, vaddr, size, dir);
@@ -386,7 +403,7 @@ size_t dma_max_mapping_size(struct device *dev)
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	size_t size = SIZE_MAX;
 
-	if (dma_is_direct(ops))
+	if (dma_map_direct(dev, ops))
 		size = dma_direct_max_mapping_size(dev);
 	else if (ops && ops->max_mapping_size)
 		size = ops->max_mapping_size(dev);
-- 
2.20.1