mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 23:56:50 +07:00
af7ddd8a62
A huge update this time, but a lot of that is just consolidating or removing code: - provide a common DMA_MAPPING_ERROR definition and avoid indirect calls for dma_map_* error checking - use direct calls for the DMA direct mapping case, avoiding huge retpoline overhead for high performance workloads - merge the swiotlb dma_map_ops into dma-direct - provide a generic remapping DMA consistent allocator for architectures that have devices that perform DMA that is not cache coherent. Based on the existing arm64 implementation and also used for csky now. - improve the dma-debug infrastructure, including dynamic allocation of entries (Robin Murphy) - default to providing chaining scatterlist everywhere, with opt-outs for the few architectures (alpha, parisc, most arm32 variants) that can't cope with it - misc sparc32 dma-related cleanups - remove the dma_mark_clean arch hook used by swiotlb on ia64 and replace it with the generic noncoherent infrastructure - fix the return type of dma_set_max_seg_size (Niklas Söderlund) - move the dummy dma ops for not DMA capable devices from arm64 to common code (Robin Murphy) - ensure dma_alloc_coherent returns zeroed memory to avoid kernel data leaks through userspace. We already did this for most common architectures, but this ensures we do it everywhere. dma_zalloc_coherent has been deprecated and can hopefully be removed after -rc1 with a coccinelle script. -----BEGIN PGP SIGNATURE----- iQI/BAABCgApFiEEgdbnc3r/njty3Iq9D55TZVIEUYMFAlwctQgLHGhjaEBsc3Qu ZGUACgkQD55TZVIEUYMxgQ//dBpAfS4/J76CdAbYry2zqgcOUU9hIrD6NHiEMWov ltJxyvEl3LsUmIdEj3aCrYL9jZN0qsnCzn5BVj2c3jDIVgD64fAr7HDf/PbEEfKb j6/GgEnVLPZV+sQMvhNA5jOzHrkseaqPa4/pNLFZ/l8jnuZ2d+btusDWJpMoVDer TXVwtIfgeIu0gTygYOShLYXd5qptWKWsZEpbTZOO2sE6+x+ZJX7yQYUxYDTlcOIj JWVO2l5QNHPc5T9o2at+6L5aNUvnZOxT79sWgyZLn0Kc+FagKAVwfLqUEl0v7foG 8k/xca5/8p3afB1DfrIrtplJqis7cVgdyGxriwuuoO8X4F0nPyWwpGmxsBhrWwwl xTqC4UorEJ7QwoP6Azopk/vYI2QXIUBLjuCJCuFXZj9+2BGf4IfvBY1S2cLM9qLs HMcxQonuXJii044KEFS96ePEuiT+igVINweIFBKWcgNCEG0UQtyL6RQ1U5297ipF JiWZAqD+p9X52UdKS+oKfAiZEekMXn6Xyo97+YCiNpfOo0GP5eEcwhL+JpY4AiRq apPXtsRy2o1s8yfjdraUIM2Mc2n62vFKb35oUbGCd/QO9piPrFQHl6T0HHcHk4YR XrUXcHieFZBCYqh7ZVa4RL8Msq1wvGuTL4Dxl43mXdsMoUFRR6eSNWLoAV4IpOLZ WgA= =in72 -----END PGP SIGNATURE----- Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping Pull DMA mapping updates from Christoph Hellwig: "A huge update this time, but a lot of that is just consolidating or removing code: - provide a common DMA_MAPPING_ERROR definition and avoid indirect calls for dma_map_* error checking - use direct calls for the DMA direct mapping case, avoiding huge retpoline overhead for high performance workloads - merge the swiotlb dma_map_ops into dma-direct - provide a generic remapping DMA consistent allocator for architectures that have devices that perform DMA that is not cache coherent. Based on the existing arm64 implementation and also used for csky now. - improve the dma-debug infrastructure, including dynamic allocation of entries (Robin Murphy) - default to providing chaining scatterlist everywhere, with opt-outs for the few architectures (alpha, parisc, most arm32 variants) that can't cope with it - misc sparc32 dma-related cleanups - remove the dma_mark_clean arch hook used by swiotlb on ia64 and replace it with the generic noncoherent infrastructure - fix the return type of dma_set_max_seg_size (Niklas Söderlund) - move the dummy dma ops for not DMA capable devices from arm64 to common code (Robin Murphy) - ensure dma_alloc_coherent returns zeroed memory to avoid kernel data leaks through userspace. We already did this for most common architectures, but this ensures we do it everywhere. dma_zalloc_coherent has been deprecated and can hopefully be removed after -rc1 with a coccinelle script" * tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits) dma-mapping: fix inverted logic in dma_supported dma-mapping: deprecate dma_zalloc_coherent dma-mapping: zero memory returned from dma_alloc_* sparc/iommu: fix ->map_sg return value sparc/io-unit: fix ->map_sg return value arm64: default to the direct mapping in get_arch_dma_ops PCI: Remove unused attr variable in pci_dma_configure ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled dma-mapping: bypass indirect calls for dma-direct vmd: use the proper dma_* APIs instead of direct methods calls dma-direct: merge swiotlb_dma_ops into the dma_direct code dma-direct: use dma_direct_map_page to implement dma_direct_map_sg dma-direct: improve addressability error reporting swiotlb: remove dma_mark_clean swiotlb: remove SWIOTLB_MAP_ERROR ACPI / scan: Refactor _CCA enforcement dma-mapping: factor out dummy DMA ops dma-mapping: always build the direct mapping code dma-mapping: move dma_cache_sync out of line dma-mapping: move various slow path functions out of line ...
119 lines
3.5 KiB
C
119 lines
3.5 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
|
|
*
|
|
* Provide default implementations of the DMA mapping callbacks for
|
|
* busses using the iommu infrastructure
|
|
*/
|
|
|
|
#include <asm/iommu.h>
|
|
|
|
/*
|
|
* Generic iommu implementation
|
|
*/
|
|
|
|
/* Allocates a contiguous real buffer and creates mappings over it.
|
|
* Returns the virtual address of the buffer and sets dma_handle
|
|
* to the dma address (mapping) of the first page.
|
|
*/
|
|
static void *dma_iommu_alloc_coherent(struct device *dev, size_t size,
|
|
dma_addr_t *dma_handle, gfp_t flag,
|
|
unsigned long attrs)
|
|
{
|
|
return iommu_alloc_coherent(dev, get_iommu_table_base(dev), size,
|
|
dma_handle, dev->coherent_dma_mask, flag,
|
|
dev_to_node(dev));
|
|
}
|
|
|
|
static void dma_iommu_free_coherent(struct device *dev, size_t size,
|
|
void *vaddr, dma_addr_t dma_handle,
|
|
unsigned long attrs)
|
|
{
|
|
iommu_free_coherent(get_iommu_table_base(dev), size, vaddr, dma_handle);
|
|
}
|
|
|
|
/* Creates TCEs for a user provided buffer. The user buffer must be
|
|
* contiguous real kernel storage (not vmalloc). The address passed here
|
|
* comprises a page address and offset into that page. The dma_addr_t
|
|
* returned will point to the same byte within the page as was passed in.
|
|
*/
|
|
static dma_addr_t dma_iommu_map_page(struct device *dev, struct page *page,
|
|
unsigned long offset, size_t size,
|
|
enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
return iommu_map_page(dev, get_iommu_table_base(dev), page, offset,
|
|
size, device_to_mask(dev), direction, attrs);
|
|
}
|
|
|
|
|
|
static void dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
|
|
size_t size, enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
iommu_unmap_page(get_iommu_table_base(dev), dma_handle, size, direction,
|
|
attrs);
|
|
}
|
|
|
|
|
|
static int dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
|
|
int nelems, enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
return ppc_iommu_map_sg(dev, get_iommu_table_base(dev), sglist, nelems,
|
|
device_to_mask(dev), direction, attrs);
|
|
}
|
|
|
|
static void dma_iommu_unmap_sg(struct device *dev, struct scatterlist *sglist,
|
|
int nelems, enum dma_data_direction direction,
|
|
unsigned long attrs)
|
|
{
|
|
ppc_iommu_unmap_sg(get_iommu_table_base(dev), sglist, nelems,
|
|
direction, attrs);
|
|
}
|
|
|
|
/* We support DMA to/from any memory page via the iommu */
|
|
int dma_iommu_dma_supported(struct device *dev, u64 mask)
|
|
{
|
|
struct iommu_table *tbl = get_iommu_table_base(dev);
|
|
|
|
if (!tbl) {
|
|
dev_info(dev, "Warning: IOMMU dma not supported: mask 0x%08llx"
|
|
", table unavailable\n", mask);
|
|
return 0;
|
|
}
|
|
|
|
if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
|
|
dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
|
|
dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
|
|
mask, tbl->it_offset << tbl->it_page_shift);
|
|
return 0;
|
|
} else
|
|
return 1;
|
|
}
|
|
|
|
static u64 dma_iommu_get_required_mask(struct device *dev)
|
|
{
|
|
struct iommu_table *tbl = get_iommu_table_base(dev);
|
|
u64 mask;
|
|
if (!tbl)
|
|
return 0;
|
|
|
|
mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1);
|
|
mask += mask - 1;
|
|
|
|
return mask;
|
|
}
|
|
|
|
struct dma_map_ops dma_iommu_ops = {
|
|
.alloc = dma_iommu_alloc_coherent,
|
|
.free = dma_iommu_free_coherent,
|
|
.mmap = dma_nommu_mmap_coherent,
|
|
.map_sg = dma_iommu_map_sg,
|
|
.unmap_sg = dma_iommu_unmap_sg,
|
|
.dma_supported = dma_iommu_dma_supported,
|
|
.map_page = dma_iommu_map_page,
|
|
.unmap_page = dma_iommu_unmap_page,
|
|
.get_required_mask = dma_iommu_get_required_mask,
|
|
};
|