From 75bebb7f0c2a709812cccb4d3151a21b012c5cad Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 23 Oct 2008 20:46:55 +0900 Subject: x86: use GFP_DMA for 24bit coherent_dma_mask dma_alloc_coherent (include/asm-x86/dma-mapping.h) avoids GFP_DMA allocation first and if the allocated address is not fit for the device's coherent_dma_mask, then dma_alloc_coherent does GFP_DMA allocation. This is because dma_alloc_coherent avoids precious GFP_DMA zone if possible. This is also how the old dma_alloc_coherent (arch/x86/kernel/pci-dma.c) works. However, if the coherent_dma_mask of a device is 24bit, there is no point to go into the above GFP_DMA retry mechanism. We had better use GFP_DMA in the first place. Signed-off-by: FUJITA Tomonori Tested-by: Takashi Iwai Signed-off-by: Ingo Molnar --- arch/x86/include/asm/dma-mapping.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 4a5397bfce2..7f225a4b2a2 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -255,9 +255,11 @@ static inline unsigned long dma_alloc_coherent_mask(struct device *dev, static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) { -#ifdef CONFIG_X86_64 unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp); + if (dma_mask <= DMA_24BIT_MASK) + gfp |= GFP_DMA; +#ifdef CONFIG_X86_64 if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) gfp |= GFP_DMA32; #endif -- cgit v1.2.3 From 03967c5267b0e7312d1d55dc814d94cf190ca573 Mon Sep 17 00:00:00 2001 From: FUJITA Tomonori Date: Thu, 23 Oct 2008 23:14:29 +0900 Subject: x86: restore the old swiotlb alloc_coherent behavior This restores the old swiotlb alloc_coherent behavior (before the alloc_coherent rewrite): http://lkml.org/lkml/2008/8/12/200 The old alloc_coherent avoids GFP_DMA allocation first and if the allocated address is not fit for the device's coherent_dma_mask, then dma_alloc_coherent does GFP_DMA allocation. If it fails, alloc_coherent calls swiotlb_alloc_coherent (in short, we rarely used swiotlb_alloc_coherent). After the alloc_coherent rewrite, dma_alloc_coherent (include/asm-x86/dma-mapping.h) directly calls swiotlb_alloc_coherent. It means that we possibly can't handle a device having dma_masks > 24bit < 32bits since swiotlb_alloc_coherent doesn't have the above GFP_DMA retry mechanism. This patch fixes x86's swiotlb alloc_coherent to use the GFP_DMA retry mechanism, which dma_generic_alloc_coherent() provides now (pci-nommu.c and GART IOMMU driver also use dma_generic_alloc_coherent). Signed-off-by: FUJITA Tomonori Signed-off-by: Ingo Molnar --- arch/x86/kernel/pci-swiotlb_64.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index c4ce0332759..3c539d111ab 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -18,9 +18,21 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); } +static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags) +{ + void *vaddr; + + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags); + if (vaddr) + return vaddr; + + return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); +} + struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, - .alloc_coherent = swiotlb_alloc_coherent, + .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, .map_single = swiotlb_map_single_phys, .unmap_single = swiotlb_unmap_single, -- cgit v1.2.3