Merge tag 'dma-mapping-5.6' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping fixes from Christoph Hellwig:

 - give command line cma= precedence over the CONFIG_ option (Nicolas
   Saenz Julienne)

 - always allow 32-bit DMA, even for weirdly placed ZONE_DMA

 - improve the debug printks when memory is not addressable, to help
   find problems with swiotlb initialization

* tag 'dma-mapping-5.6' of git://git.infradead.org/users/hch/dma-mapping:
  dma-direct: improve DMA mask overflow reporting
  dma-direct: improve swiotlb error reporting
  dma-direct: relax addressability checks in dma_direct_supported
  dma-contiguous: CMA: give precedence to cmdline

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/contiguous.c

@@ -302,9 +302,16 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
 	phys_addr_t mask = align - 1;
 	unsigned long node = rmem->fdt_node;
+	bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL);
 	struct cma *cma;
 	int err;
 
+	if (size_cmdline != -1 && default_cma) {
+		pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n",
+			rmem->name);
+		return -EBUSY;
+	}
+
 	if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
 	    of_get_flat_dt_prop(node, "no-map", NULL))
 		return -EINVAL;
@@ -322,7 +329,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem)
 	/* Architecture specific contiguous memory fixup. */
 	dma_contiguous_early_fixup(rmem->base, rmem->size);
 
-	if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+	if (default_cma)
 		dma_contiguous_set_default(cma);
 
 	rmem->ops = &rmem_cma_ops;

kernel/dma/direct.c

@@ -23,18 +23,6 @@
  */
 unsigned int zone_dma_bits __ro_after_init = 24;
 
-static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
-{
-	if (!dev->dma_mask) {
-		dev_err_once(dev, "DMA map on device without dma_mask\n");
-	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) {
-		dev_err_once(dev,
-			"overflow %pad+%zu of DMA mask %llx bus limit %llx\n",
-			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-	}
-	WARN_ON_ONCE(1);
-}
-
 static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 		phys_addr_t phys)
 {
@@ -357,13 +345,6 @@ 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)
@@ -371,9 +352,16 @@ 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)) {
-		report_addr(dev, dma_addr, size);
+	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);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -411,7 +399,10 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 	dma_addr_t dma_addr = paddr;
 
 	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		report_addr(dev, dma_addr, size);
+		dev_err_once(dev,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		WARN_ON_ONCE(1);
 		return DMA_MAPPING_ERROR;
 	}
 
@@ -472,28 +463,26 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 }
 #endif /* CONFIG_MMU */
 
-/*
- * Because 32-bit DMA masks are so common we expect every architecture to be
- * able to satisfy them - either by not supporting more physical memory, or by
- * providing a ZONE_DMA32.  If neither is the case, the architecture needs to
- * use an IOMMU instead of the direct mapping.
- */
 int dma_direct_supported(struct device *dev, u64 mask)
 {
-	u64 min_mask;
+	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		min_mask = DMA_BIT_MASK(zone_dma_bits);
-	else
-		min_mask = DMA_BIT_MASK(32);
-
-	min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);
+	/*
+	 * Because 32-bit DMA masks are so common we expect every architecture
+	 * to be able to satisfy them - either by not supporting more physical
+	 * memory, or by providing a ZONE_DMA32.  If neither is the case, the
+	 * architecture needs to use an IOMMU instead of the direct mapping.
+	 */
+	if (mask >= DMA_BIT_MASK(32))
+		return 1;
 
 	/*
 	 * This check needs to be against the actual bit mask value, so
 	 * use __phys_to_dma() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
 	return mask >= __phys_to_dma(dev, min_mask);
 }
 

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)