x86: dma_alloc_coherent sets gfp flags properly

Non real IOMMU implemenations (which doesn't do virtual mappings,
e.g. swiotlb, pci-nommu, etc) need to use proper gfp flags and
dma_mask to allocate pages in their own dma_alloc_coherent()
(allocated page need to be suitable for device's coherent_dma_mask).

This patch makes dma_alloc_coherent do this job so that IOMMUs don't
need to take care of it any more.

Real IOMMU implemenataions can simply ignore the gfp flags.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Acked-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

2 files changed, 30 insertions, 21 deletions

diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index ada1c87cafc2..8e398b56f50b 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -80,26 +80,11 @@ nommu_alloc_coherent(struct device *hwdev, size_t size,
         int node;
         struct page *page;
 
-        gfp |= __GFP_ZERO;
-
-        dma_mask = hwdev->coherent_dma_mask;
-        if (!dma_mask)
-                dma_mask = *(hwdev->dma_mask);
+        dma_mask = dma_alloc_coherent_mask(hwdev, gfp);
 
-        if (dma_mask < DMA_24BIT_MASK)
-                return NULL;
+        gfp |= __GFP_ZERO;
 
         node = dev_to_node(hwdev);
-
-#ifdef CONFIG_X86_64
-        if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
-                gfp |= GFP_DMA32;
-#endif
-
-        /* No alloc-free penalty for ISA devices */
-        if (dma_mask == DMA_24BIT_MASK)
-                gfp |= GFP_DMA;
-
 again:
         page = alloc_pages_node(node, gfp, get_order(size));
         if (!page)
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index ad8b49032d18..0cc022b9a4a1 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -239,6 +239,29 @@ static inline int dma_get_cache_alignment(void)
         return boot_cpu_data.x86_clflush_size;
 }
 
+static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
+                                                    gfp_t gfp)
+{
+        unsigned long dma_mask = 0;
+
+        dma_mask = dev->coherent_dma_mask;
+        if (!dma_mask)
+                dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
+
+        return dma_mask;
+}
+
+static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
+{
+        unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
+
+#ifdef CONFIG_X86_64
+        if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+                gfp |= GFP_DMA32;
+#endif
+       return gfp;
+}
+
 static inline void *
 dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
                 gfp_t gfp)
@@ -259,10 +282,11 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
         if (!dev->dma_mask)
                 return NULL;
 
-        if (ops->alloc_coherent)
-                return ops->alloc_coherent(dev, size,
-                                dma_handle, gfp);
-        return NULL;
+        if (!ops->alloc_coherent)
+                return NULL;
+
+        return ops->alloc_coherent(dev, size, dma_handle,
+                                   dma_alloc_coherent_gfp_flags(dev, gfp));
 }
 
 static inline void dma_free_coherent(struct device *dev, size_t size,