ARM: another fix for the DMA mapping checks

Peter reports that OMAP audio broke with the recent fix for these
checks, caused by OMAP audio using a 64-bit DMA mask.  We should
allow 64-bit DMA masks even with 32-bit dma_addr_t if we can be sure
the amount of RAM we have won't allow the 32-bit dma_addr_t to
overflow.  Unfortunately, the checks to detect overflow were not
correct.

Tested-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f6b6bfa88ecff21ddde5646dfaafa0190792f247..c143a7bb681b305c044ecddcc4da6305d5494589 100644 (file)
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -185,7 +185,7 @@ static u64 get_coherent_dma_mask(struct device *dev)
                 */
                if (sizeof(mask) != sizeof(dma_addr_t) &&
                    mask > (dma_addr_t)~0 &&
-                   dma_to_pfn(dev, ~0) > max_dma_pfn) {
+                   dma_to_pfn(dev, ~0) < max_dma_pfn) {
                        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");
@@ -1041,7 +1041,7 @@ int dma_supported(struct device *dev, u64 mask)
         */
        if (sizeof(mask) != sizeof(dma_addr_t) &&
            mask > (dma_addr_t)~0 &&
-           dma_to_pfn(dev, ~0) > arm_dma_pfn_limit)
+           dma_to_pfn(dev, ~0) < min(max_pfn, arm_dma_pfn_limit))
                return 0;
 
        /*