dma-direct: improve swiotlb error reporting

Untangle the way how dma_direct_map_page calls into swiotlb to be able
to properly report errors where the swiotlb DMA address overflows the
mask separately from overflows in the !swiotlb case.  This means that
siotlb_map now has to do a little more work that duplicates
dma_direct_map_page, but doing so greatly simplifies the calling
convention.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

include/linux/swiotlb.h

@@ -64,6 +64,9 @@ extern void swiotlb_tbl_sync_single(struct device *hwdev,
 				    size_t size, enum dma_data_direction dir,
 				    enum dma_sync_target target);
 
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+
 #ifdef CONFIG_SWIOTLB
 extern enum swiotlb_force swiotlb_force;
 extern phys_addr_t io_tlb_start, io_tlb_end;
@@ -73,8 +76,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr)
 	return paddr >= io_tlb_start && paddr < io_tlb_end;
 }
 
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void __init swiotlb_exit(void);
 unsigned int swiotlb_max_segment(void);
 size_t swiotlb_max_mapping_size(struct device *dev);
@@ -85,12 +86,6 @@ static inline bool is_swiotlb_buffer(phys_addr_t paddr)
 {
 	return false;
 }
-static inline bool swiotlb_map(struct device *dev, phys_addr_t *phys,
-		dma_addr_t *dma_addr, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	return false;
-}
 static inline void swiotlb_exit(void)
 {
 }

kernel/dma/direct.c

@@ -357,13 +357,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
 EXPORT_SYMBOL(dma_direct_unmap_sg);
 #endif
 
-static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
-		size_t size)
-{
-	return swiotlb_force != SWIOTLB_FORCE &&
-		dma_capable(dev, dma_addr, size, true);
-}
-
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 		unsigned long offset, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -371,8 +364,13 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	phys_addr_t phys = page_to_phys(page) + offset;
 	dma_addr_t dma_addr = phys_to_dma(dev, phys);
 
-	if (unlikely(!dma_direct_possible(dev, dma_addr, size)) &&
-	    !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) {
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
 		report_addr(dev, dma_addr, size);
 		return DMA_MAPPING_ERROR;
 	}

kernel/dma/swiotlb.c

@@ -22,6 +22,7 @@
 
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
@@ -656,35 +657,38 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
 }
 
 /*
- * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing
+ * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing
  * to the device copy the data into it as well.
  */
-bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
+dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
 {
-	trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force);
+	phys_addr_t swiotlb_addr;
+	dma_addr_t dma_addr;
 
-	if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) {
-		dev_warn_ratelimited(dev,
-			"Cannot do DMA to address %pa\n", phys);
-		return false;
-	}
+	trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size,
+			      swiotlb_force);
 
-	/* Oh well, have to allocate and map a bounce buffer. */
-	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, size, dir, attrs);
-	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
-		return false;
+	swiotlb_addr = swiotlb_tbl_map_single(dev,
+			__phys_to_dma(dev, io_tlb_start),
+			paddr, size, size, dir, attrs);
+	if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
+		return DMA_MAPPING_ERROR;
 
 	/* Ensure that the address returned is DMA'ble */
-	*dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, *dma_addr, size, true))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
+	dma_addr = __phys_to_dma(dev, swiotlb_addr);
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
-		return false;
+		dev_WARN_ONCE(dev, 1,
+			"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
 	}
 
-	return true;
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(swiotlb_addr, size, dir);
+	return dma_addr;
 }
 
 size_t swiotlb_max_mapping_size(struct device *dev)