5 files changed, 62 insertions, 14 deletions

diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 5b579b951503..863cd84eb1a2 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -64,6 +64,7 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 {
         return (dma_addr_t)__virt_to_bus((unsigned long)(addr));
 }
+
 #else
 static inline dma_addr_t pfn_to_dma(struct device *dev, unsigned long pfn)
 {
@@ -86,6 +87,13 @@ static inline dma_addr_t virt_to_dma(struct device *dev, void *addr)
 }
 #endif
 
+/* The ARM override for dma_max_pfn() */
+static inline unsigned long dma_max_pfn(struct device *dev)
+{
+        return PHYS_PFN_OFFSET + dma_to_pfn(dev, *dev->dma_mask);
+}
+#define dma_max_pfn(dev) dma_max_pfn(dev)
+
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
  */
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1272ed202dde..644d91f73b00 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -159,7 +159,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static u64 get_coherent_dma_mask(struct device *dev)
 {
-        u64 mask = (u64)arm_dma_limit;
+        u64 mask = (u64)DMA_BIT_MASK(32);
 
         if (dev) {
                 mask = dev->coherent_dma_mask;
@@ -173,10 +173,30 @@ static u64 get_coherent_dma_mask(struct device *dev)
                         return 0;
                 }
 
-                if ((~mask) & (u64)arm_dma_limit) {
-                        dev_warn(dev, "coherent DMA mask %#llx is smaller "
-                                 "than system GFP_DMA mask %#llx\n",
-                                 mask, (u64)arm_dma_limit);
+                /*
+                 * If the mask allows for more memory than we can address,
+                 * and we actually have that much memory, then fail the
+                 * allocation.
+                 */
+                if (sizeof(mask) != sizeof(dma_addr_t) &&
+                    mask > (dma_addr_t)~0 &&
+                    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit) {
+                        dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
+                                 mask);
+                        dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
+                        return 0;
+                }
+
+                /*
+                 * Now check that the mask, when translated to a PFN,
+                 * fits within the allowable addresses which we can
+                 * allocate.
+                 */
+                if (dma_to_pfn(dev, mask) < arm_dma_pfn_limit) {
+                        dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
+                                 mask,
+                                 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
+                                 arm_dma_pfn_limit + 1);
                         return 0;
                 }
         }
@@ -1007,8 +1027,27 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
  */
 int dma_supported(struct device *dev, u64 mask)
 {
-        if (mask < (u64)arm_dma_limit)
+        unsigned long limit;
+
+        /*
+         * If the mask allows for more memory than we can address,
+         * and we actually have that much memory, then we must
+         * indicate that DMA to this device is not supported.
+         */
+        if (sizeof(mask) != sizeof(dma_addr_t) &&
+            mask > (dma_addr_t)~0 &&
+            dma_to_pfn(dev, ~0) > arm_dma_pfn_limit)
+                return 0;
+
+        /*
+         * Translate the device's DMA mask to a PFN limit.  This
+         * PFN number includes the page which we can DMA to.
+         */
+        limit = dma_to_pfn(dev, mask);
+
+        if (limit < arm_dma_pfn_limit)
                 return 0;
+
         return 1;
 }
 EXPORT_SYMBOL(dma_supported);
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index ca907f805c57..3e8f106ee5fe 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -209,6 +209,7 @@ EXPORT_SYMBOL(arm_dma_zone_size);
  * so a successful GFP_DMA allocation will always satisfy this.
  */
 phys_addr_t arm_dma_limit;
+unsigned long arm_dma_pfn_limit;
 
 static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
         unsigned long dma_size)
@@ -231,6 +232,7 @@ void __init setup_dma_zone(const struct machine_desc *mdesc)
                 arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
         } else
                 arm_dma_limit = 0xffffffff;
+        arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;
 #endif
 }
 
@@ -418,12 +420,10 @@ void __init bootmem_init(void)
          * This doesn't seem to be used by the Linux memory manager any
          * more, but is used by ll_rw_block.  If we can get rid of it, we
          * also get rid of some of the stuff above as well.
-         *
-         * Note: max_low_pfn and max_pfn reflect the number of _pages_ in
-         * the system, not the maximum PFN.
          */
-        max_low_pfn = max_low - PHYS_PFN_OFFSET;
-        max_pfn = max_high - PHYS_PFN_OFFSET;
+        min_low_pfn = min;
+        max_low_pfn = max_low;
+        max_pfn = max_high;
 }
 
 /*
@@ -529,7 +529,7 @@ static inline void free_area_high(unsigned long pfn, unsigned long end)
 static void __init free_highpages(void)
 {
 #ifdef CONFIG_HIGHMEM
-        unsigned long max_low = max_low_pfn + PHYS_PFN_OFFSET;
+        unsigned long max_low = max_low_pfn;
         struct memblock_region *mem, *res;
 
         /* set highmem page free */
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index d5a4e9ad8f0f..d5a982d15a88 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -81,8 +81,10 @@ extern __init void add_static_vm_early(struct static_vm *svm);
 
 #ifdef CONFIG_ZONE_DMA
 extern phys_addr_t arm_dma_limit;
+extern unsigned long arm_dma_pfn_limit;
 #else
 #define arm_dma_limit ((phys_addr_t)~0)
+#define arm_dma_pfn_limit (~0ul >> PAGE_SHIFT)
 #endif
 
 extern phys_addr_t arm_lowmem_limit;
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index f99cefbd84e3..e7d0c88f621a 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1419,8 +1419,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 
                 /* needed to ensure proper operation of coherent allocations
                  * later, in case driver doesn't set it explicitly */
-                dma_set_mask(&viodev->dev, DMA_BIT_MASK(64));
-                dma_set_coherent_mask(&viodev->dev, DMA_BIT_MASK(64));
+                dma_set_mask_and_coherent(&viodev->dev, DMA_BIT_MASK(64));
         }
 
         /* register with generic device framework */