diff options
author | Christoph Hellwig <hch@lst.de> | 2019-08-06 15:01:38 +0300 |
---|---|---|
committer | Christoph Hellwig <hch@lst.de> | 2019-09-04 11:13:19 +0200 |
commit | 249baa54790171438524ba97e8e0485dd6aa2762 (patch) | |
tree | cf5dc669ac064a93a37912f25aa7910d7e8db58d | |
parent | d9295532d5725e5926d76470acdfd239c8d2aad3 (diff) | |
download | linux-249baa54790171438524ba97e8e0485dd6aa2762.tar.bz2 |
dma-mapping: provide a better default ->get_required_mask
Most dma_map_ops instances are IOMMUs that work perfectly fine in 32-bits
of IOVA space, and the generic direct mapping code already provides its
own routines that is intelligent based on the amount of memory actually
present. Wire up the dma-direct routine for the ARM direct mapping code
as well, and otherwise default to the constant 32-bit mask. This way
we only need to override it for the occasional odd IOMMU that requires
64-bit IOVA support, or IOMMU drivers that are more efficient if they
can fall back to the direct mapping.
Signed-off-by: Christoph Hellwig <hch@lst.de>
-rw-r--r-- | arch/arm/mm/dma-mapping.c | 3 | ||||
-rw-r--r-- | arch/powerpc/platforms/ps3/system-bus.c | 7 | ||||
-rw-r--r-- | arch/x86/kernel/amd_gart_64.c | 1 | ||||
-rw-r--r-- | kernel/dma/mapping.c | 30 |
4 files changed, 14 insertions, 27 deletions
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 0189a757a8f2..eb903beef2ff 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -14,6 +14,7 @@ #include <linux/list.h> #include <linux/init.h> #include <linux/device.h> +#include <linux/dma-direct.h> #include <linux/dma-mapping.h> #include <linux/dma-noncoherent.h> #include <linux/dma-contiguous.h> @@ -192,6 +193,7 @@ const struct dma_map_ops arm_dma_ops = { .sync_sg_for_cpu = arm_dma_sync_sg_for_cpu, .sync_sg_for_device = arm_dma_sync_sg_for_device, .dma_supported = arm_dma_supported, + .get_required_mask = dma_direct_get_required_mask, }; EXPORT_SYMBOL(arm_dma_ops); @@ -212,6 +214,7 @@ const struct dma_map_ops arm_coherent_dma_ops = { .map_sg = arm_dma_map_sg, .map_resource = dma_direct_map_resource, .dma_supported = arm_dma_supported, + .get_required_mask = dma_direct_get_required_mask, }; EXPORT_SYMBOL(arm_coherent_dma_ops); diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index 70fcc9736a8c..3542b7bd6a46 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -686,18 +686,12 @@ static int ps3_dma_supported(struct device *_dev, u64 mask) return mask >= DMA_BIT_MASK(32); } -static u64 ps3_dma_get_required_mask(struct device *_dev) -{ - return DMA_BIT_MASK(32); -} - static const struct dma_map_ops ps3_sb_dma_ops = { .alloc = ps3_alloc_coherent, .free = ps3_free_coherent, .map_sg = ps3_sb_map_sg, .unmap_sg = ps3_sb_unmap_sg, .dma_supported = ps3_dma_supported, - .get_required_mask = ps3_dma_get_required_mask, .map_page = ps3_sb_map_page, .unmap_page = ps3_unmap_page, .mmap = dma_common_mmap, @@ -710,7 +704,6 @@ static const struct dma_map_ops ps3_ioc0_dma_ops = { .map_sg = ps3_ioc0_map_sg, .unmap_sg = ps3_ioc0_unmap_sg, .dma_supported = ps3_dma_supported, - .get_required_mask = ps3_dma_get_required_mask, .map_page = ps3_ioc0_map_page, .unmap_page = ps3_unmap_page, .mmap = dma_common_mmap, diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index f72c487d68a8..a6ac3712db8b 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -680,6 +680,7 @@ static const struct dma_map_ops gart_dma_ops = { .mmap = dma_common_mmap, .get_sgtable = dma_common_get_sgtable, .dma_supported = dma_direct_supported, + .get_required_mask = dma_direct_get_required_mask, }; static void gart_iommu_shutdown(void) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 285de5fbc8e9..64a3d294f4b4 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -271,25 +271,6 @@ int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, } EXPORT_SYMBOL(dma_mmap_attrs); -static u64 dma_default_get_required_mask(struct device *dev) -{ - u32 low_totalram = ((max_pfn - 1) << PAGE_SHIFT); - u32 high_totalram = ((max_pfn - 1) >> (32 - PAGE_SHIFT)); - u64 mask; - - if (!high_totalram) { - /* convert to mask just covering totalram */ - low_totalram = (1 << (fls(low_totalram) - 1)); - low_totalram += low_totalram - 1; - mask = low_totalram; - } else { - high_totalram = (1 << (fls(high_totalram) - 1)); - high_totalram += high_totalram - 1; - mask = (((u64)high_totalram) << 32) + 0xffffffff; - } - return mask; -} - u64 dma_get_required_mask(struct device *dev) { const struct dma_map_ops *ops = get_dma_ops(dev); @@ -298,7 +279,16 @@ u64 dma_get_required_mask(struct device *dev) return dma_direct_get_required_mask(dev); if (ops->get_required_mask) return ops->get_required_mask(dev); - return dma_default_get_required_mask(dev); + + /* + * We require every DMA ops implementation to at least support a 32-bit + * DMA mask (and use bounce buffering if that isn't supported in + * hardware). As the direct mapping code has its own routine to + * actually report an optimal mask we default to 32-bit here as that + * is the right thing for most IOMMUs, and at least not actively + * harmful in general. + */ + return DMA_BIT_MASK(32); } EXPORT_SYMBOL_GPL(dma_get_required_mask); |