diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-19 13:27:23 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-19 13:27:23 -0700 |
commit | 671df189537883f36cf9c7d4f9495bfac0f86627 (patch) | |
tree | 22e5f598ed1f5d9b2218d85d4426140f804d61e6 /arch/arm64 | |
parent | c9fe5630dae1df2328d82042602e2c4d1add8d57 (diff) | |
parent | c7d9eccb3c1e802c5cbb2a764eb0eb9807d9f12e (diff) |
Merge tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping updates from Christoph Hellwig:
- add dma-mapping and block layer helpers to take care of IOMMU merging
for mmc plus subsequent fixups (Yoshihiro Shimoda)
- rework handling of the pgprot bits for remapping (me)
- take care of the dma direct infrastructure for swiotlb-xen (me)
- improve the dma noncoherent remapping infrastructure (me)
- better defaults for ->mmap, ->get_sgtable and ->get_required_mask
(me)
- cleanup mmaping of coherent DMA allocations (me)
- various misc cleanups (Andy Shevchenko, me)
* tag 'dma-mapping-5.4' of git://git.infradead.org/users/hch/dma-mapping: (41 commits)
mmc: renesas_sdhi_internal_dmac: Add MMC_CAP2_MERGE_CAPABLE
mmc: queue: Fix bigger segments usage
arm64: use asm-generic/dma-mapping.h
swiotlb-xen: merge xen_unmap_single into xen_swiotlb_unmap_page
swiotlb-xen: simplify cache maintainance
swiotlb-xen: use the same foreign page check everywhere
swiotlb-xen: remove xen_swiotlb_dma_mmap and xen_swiotlb_dma_get_sgtable
xen: remove the exports for xen_{create,destroy}_contiguous_region
xen/arm: remove xen_dma_ops
xen/arm: simplify dma_cache_maint
xen/arm: use dev_is_dma_coherent
xen/arm: consolidate page-coherent.h
xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance
arm: remove wrappers for the generic dma remap helpers
dma-mapping: introduce a dma_common_find_pages helper
dma-mapping: always use VM_DMA_COHERENT for generic DMA remap
vmalloc: lift the arm flag for coherent mappings to common code
dma-mapping: provide a better default ->get_required_mask
dma-mapping: remove the dma_declare_coherent_memory export
remoteproc: don't allow modular build
...
Diffstat (limited to 'arch/arm64')
-rw-r--r-- | arch/arm64/Kconfig | 1 | ||||
-rw-r--r-- | arch/arm64/include/asm/Kbuild | 1 | ||||
-rw-r--r-- | arch/arm64/include/asm/dma-mapping.h | 28 | ||||
-rw-r--r-- | arch/arm64/include/asm/pgtable.h | 12 | ||||
-rw-r--r-- | arch/arm64/include/asm/xen/page-coherent.h | 75 | ||||
-rw-r--r-- | arch/arm64/mm/dma-mapping.c | 16 |
6 files changed, 16 insertions, 117 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 6ae6ad8a4db0..835a1509882b 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -13,7 +13,6 @@ config ARM64 select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_DMA_COHERENT_TO_PFN - select ARCH_HAS_DMA_MMAP_PGPROT select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ELF_RANDOMIZE diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index c52e151afab0..98a5405c8558 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += delay.h generic-y += div64.h generic-y += dma.h generic-y += dma-contiguous.h +generic-y += dma-mapping.h generic-y += early_ioremap.h generic-y += emergency-restart.h generic-y += hw_irq.h diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h deleted file mode 100644 index fb3e5044f473..000000000000 --- a/arch/arm64/include/asm/dma-mapping.h +++ /dev/null @@ -1,28 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012 ARM Ltd. - */ -#ifndef __ASM_DMA_MAPPING_H -#define __ASM_DMA_MAPPING_H - -#include <linux/types.h> -#include <linux/vmalloc.h> - -#include <xen/xen.h> -#include <asm/xen/hypervisor.h> - -static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) -{ - return NULL; -} - -/* - * Do not use this function in a driver, it is only provided for - * arch/arm/mm/xen.c, which is used by arm64 as well. - */ -static inline bool is_device_dma_coherent(struct device *dev) -{ - return dev->dma_coherent; -} - -#endif /* __ASM_DMA_MAPPING_H */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 470ba7ae8821..57427d17580e 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -437,6 +437,18 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define pgprot_device(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) +/* + * DMA allocations for non-coherent devices use what the Arm architecture calls + * "Normal non-cacheable" memory, which permits speculation, unaligned accesses + * and merging of writes. This is different from "Device-nGnR[nE]" memory which + * is intended for MMIO and thus forbids speculation, preserves access size, + * requires strict alignment and can also force write responses to come from the + * endpoint. + */ +#define pgprot_dmacoherent(prot) \ + __pgprot_modify(prot, PTE_ATTRINDX_MASK, \ + PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) + #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h index d88e56b90b93..27e984977402 100644 --- a/arch/arm64/include/asm/xen/page-coherent.h +++ b/arch/arm64/include/asm/xen/page-coherent.h @@ -1,77 +1,2 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H -#define _ASM_ARM64_XEN_PAGE_COHERENT_H - -#include <linux/dma-mapping.h> -#include <asm/page.h> #include <xen/arm/page-coherent.h> - -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) -{ - return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs); -} - -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) -{ - dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs); -} - -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - - if (pfn_valid(pfn)) - dma_direct_sync_single_for_cpu(hwdev, handle, size, dir); - else - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir); -} - -static inline void xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - if (pfn_valid(pfn)) - dma_direct_sync_single_for_device(hwdev, handle, size, dir); - else - __xen_dma_sync_single_for_device(hwdev, handle, size, dir); -} - -static inline void xen_dma_map_page(struct device *hwdev, struct page *page, - dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long page_pfn = page_to_xen_pfn(page); - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); - unsigned long compound_pages = - (1<<compound_order(page)) * XEN_PFN_PER_PAGE; - bool local = (page_pfn <= dev_pfn) && - (dev_pfn - page_pfn < compound_pages); - - if (local) - dma_direct_map_page(hwdev, page, offset, size, dir, attrs); - else - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs); -} - -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long pfn = PFN_DOWN(handle); - /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a - * foreign mfn will always return false. If the page is local we can - * safely call the native dma_ops function, otherwise we call the xen - * specific function. - */ - if (pfn_valid(pfn)) - dma_direct_unmap_page(hwdev, handle, size, dir, attrs); - else - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs); -} - -#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */ diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index bd2b039f43a6..9239416e93d4 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -8,15 +8,11 @@ #include <linux/cache.h> #include <linux/dma-noncoherent.h> #include <linux/dma-iommu.h> +#include <xen/xen.h> +#include <xen/swiotlb-xen.h> #include <asm/cacheflush.h> -pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, - unsigned long attrs) -{ - return pgprot_writecombine(prot); -} - void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { @@ -34,12 +30,6 @@ void arch_dma_prep_coherent(struct page *page, size_t size) __dma_flush_area(page_address(page), size); } -static int __init arm64_dma_init(void) -{ - return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC)); -} -arch_initcall(arm64_dma_init); - #ifdef CONFIG_IOMMU_DMA void arch_teardown_dma_ops(struct device *dev) { @@ -64,6 +54,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, #ifdef CONFIG_XEN if (xen_initial_domain()) - dev->dma_ops = xen_dma_ops; + dev->dma_ops = &xen_swiotlb_dma_ops; #endif } |