From: Christoph Hellwig <hch@lst.de>
Date: Tue, 29 Oct 2019 11:01:37 +0100
Subject: dma-direct: provide mmap and get_sgtable method overrides
Git-commit: 34dc0ea6bc960f1f57b2148f01a3f4da23f87013
Patch-mainline: v5.5-rc1
References: bsc#1175713
For dma-direct we know that the DMA address is an encoding of the
physical address that we can trivially decode. Use that fact to
provide implementations that do not need the arch_dma_coherent_to_pfn
architecture hook. Note that we still can only support mmap of
non-coherent memory only if the architecture provides a way to set an
uncached bit in the page tables. This must be true for architectures
that use the generic remap helpers, but other architectures can also
manually select it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Max Filippov <jcmvbkbc@gmail.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
---
arch/arc/Kconfig | 1
arch/arm/Kconfig | 1
arch/arm/mm/dma-mapping.c | 6 ---
arch/arm64/Kconfig | 1
arch/ia64/Kconfig | 2 -
arch/ia64/kernel/dma-mapping.c | 6 ---
arch/microblaze/Kconfig | 1
arch/mips/Kconfig | 4 +-
arch/mips/mm/dma-noncoherent.c | 6 ---
arch/powerpc/platforms/Kconfig.cputype | 1
include/linux/dma-direct.h | 7 +++
include/linux/dma-noncoherent.h | 2 -
kernel/dma/Kconfig | 12 +++++-
kernel/dma/direct.c | 59 +++++++++++++++++++++++++++++++++
kernel/dma/mapping.c | 45 +++----------------------
kernel/dma/remap.c | 6 ---
16 files changed, 85 insertions(+), 75 deletions(-)
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -6,7 +6,6 @@
config ARC
def_bool y
select ARC_TIMERS
- select ARCH_HAS_DMA_COHERENT_TO_PFN
select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_SETUP_DMA_OPS
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -7,7 +7,6 @@ config ARM
select ARCH_HAS_BINFMT_FLAT
select ARCH_HAS_DEBUG_VIRTUAL if MMU
select ARCH_HAS_DEVMEM_IS_ALLOWED
- select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2373,12 +2373,6 @@ void arch_sync_dma_for_cpu(struct device
size, dir);
}
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
- dma_addr_t dma_addr)
-{
- return dma_to_pfn(dev, dma_addr);
-}
-
void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
gfp_t gfp, unsigned long attrs)
{
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -12,7 +12,6 @@ config ARM64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEVMEM_IS_ALLOWED
- select ARCH_HAS_DMA_COHERENT_TO_PFN
select ARCH_HAS_DMA_PREP_COHERENT
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ELF_RANDOMIZE
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -30,7 +30,7 @@ config IA64
select HAVE_ARCH_TRACEHOOK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_VIRT_CPU_ACCOUNTING
- select ARCH_HAS_DMA_COHERENT_TO_PFN if SWIOTLB
+ select DMA_NONCOHERENT_MMAP
select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB
select VIRT_TO_BUS
select GENERIC_IRQ_PROBE
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -28,12 +28,6 @@ void arch_dma_free(struct device *dev, s
dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs);
}
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
- dma_addr_t dma_addr)
-{
- return page_to_pfn(virt_to_page(cpu_addr));
-}
-
void __init swiotlb_dma_init(void)
{
swiotlb_init(1);
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -4,7 +4,6 @@ config MICROBLAZE
select ARCH_32BIT_OFF_T
select ARCH_NO_SWAP
select ARCH_HAS_BINFMT_FLAT if !MMU
- select ARCH_HAS_DMA_COHERENT_TO_PFN if MMU
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_SYNC_DMA_FOR_CPU
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1122,9 +1122,9 @@ config DMA_NONCOHERENT
select ARCH_HAS_DMA_WRITE_COMBINE
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_HAS_UNCACHED_SEGMENT
- select NEED_DMA_MAP_STATE
- select ARCH_HAS_DMA_COHERENT_TO_PFN
+ select DMA_NONCOHERENT_MMAP
select DMA_NONCOHERENT_CACHE_SYNC
+ select NEED_DMA_MAP_STATE
config SYS_HAS_EARLY_PRINTK
bool
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -59,12 +59,6 @@ void *cached_kernel_address(void *addr)
return __va(addr) - UNCAC_BASE;
}
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
- dma_addr_t dma_addr)
-{
- return page_to_pfn(virt_to_page(cached_kernel_address(cpu_addr)));
-}
-
static inline void dma_sync_virt(void *addr, size_t size,
enum dma_data_direction dir)
{
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -449,7 +449,6 @@ config NOT_COHERENT_CACHE
bool
depends on 4xx || PPC_8xx || E200 || PPC_MPC512x || \
GAMECUBE_COMMON || AMIGAONE
- select ARCH_HAS_DMA_COHERENT_TO_PFN
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select ARCH_HAS_SYNC_DMA_FOR_CPU
default n if PPC_47x
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -70,5 +70,12 @@ void dma_direct_free_pages(struct device
dma_addr_t dma_addr, unsigned long attrs);
struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
gfp_t gfp, unsigned long attrs);
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
+bool dma_direct_can_mmap(struct device *dev);
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs);
int dma_direct_supported(struct device *dev, u64 mask);
#endif /* _LINUX_DMA_DIRECT_H */
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -41,8 +41,6 @@ void *arch_dma_alloc(struct device *dev,
gfp_t gfp, unsigned long attrs);
void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
dma_addr_t dma_addr, unsigned long attrs);
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
- dma_addr_t dma_addr);
#ifdef CONFIG_MMU
/*
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -51,9 +51,6 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
config ARCH_HAS_DMA_PREP_COHERENT
bool
-config ARCH_HAS_DMA_COHERENT_TO_PFN
- bool
-
config ARCH_HAS_FORCE_DMA_UNENCRYPTED
bool
@@ -68,9 +65,18 @@ config SWIOTLB
bool
select NEED_DMA_MAP_STATE
+#
+# Should be selected if we can mmap non-coherent mappings to userspace.
+# The only thing that is really required is a way to set an uncached bit
+# in the pagetables
+#
+config DMA_NONCOHERENT_MMAP
+ bool
+
config DMA_REMAP
depends on MMU
select GENERIC_ALLOCATOR
+ select DMA_NONCOHERENT_MMAP
bool
config DMA_DIRECT_REMAP
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -42,6 +42,12 @@ static inline dma_addr_t phys_to_dma_dir
return phys_to_dma(dev, phys);
}
+static inline struct page *dma_direct_to_page(struct device *dev,
+ dma_addr_t dma_addr)
+{
+ return pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_addr)));
+}
+
u64 dma_direct_get_required_mask(struct device *dev)
{
u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT);
@@ -378,6 +384,59 @@ dma_addr_t dma_direct_map_resource(struc
}
EXPORT_SYMBOL(dma_direct_map_resource);
+int dma_direct_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ struct page *page = dma_direct_to_page(dev, dma_addr);
+ int ret;
+
+ ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+ if (!ret)
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+ return ret;
+}
+
+#ifdef CONFIG_MMU
+bool dma_direct_can_mmap(struct device *dev)
+{
+ return dev_is_dma_coherent(dev) ||
+ IS_ENABLED(CONFIG_DMA_NONCOHERENT_MMAP);
+}
+
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ unsigned long user_count = vma_pages(vma);
+ unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long pfn = PHYS_PFN(dma_to_phys(dev, dma_addr));
+ int ret = -ENXIO;
+
+ vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
+
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff)
+ return -ENXIO;
+ return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
+ user_count << PAGE_SHIFT, vma->vm_page_prot);
+}
+#else /* CONFIG_MMU */
+bool dma_direct_can_mmap(struct device *dev)
+{
+ return false;
+}
+
+int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ return -ENXIO;
+}
+#endif /* CONFIG_MMU */
+
/*
* Because 32-bit DMA masks are so common we expect every architecture to be
* able to satisfy them - either by not supporting more physical memory, or by
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -112,24 +112,9 @@ int dma_common_get_sgtable(struct device
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
- struct page *page;
+ struct page *page = virt_to_page(cpu_addr);
int ret;
- if (!dev_is_dma_coherent(dev)) {
- unsigned long pfn;
-
- if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
- return -ENXIO;
-
- /* If the PFN is not valid, we do not have a struct page */
- pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
- if (!pfn_valid(pfn))
- return -ENXIO;
- page = pfn_to_page(pfn);
- } else {
- page = virt_to_page(cpu_addr);
- }
-
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
if (!ret)
sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
@@ -154,7 +139,7 @@ int dma_get_sgtable_attrs(struct device
const struct dma_map_ops *ops = get_dma_ops(dev);
if (dma_is_direct(ops))
- return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr,
+ return dma_direct_get_sgtable(dev, sgt, cpu_addr, dma_addr,
size, attrs);
if (!ops->get_sgtable)
return -ENXIO;
@@ -192,7 +177,6 @@ int dma_common_mmap(struct device *dev,
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
- unsigned long pfn;
int ret = -ENXIO;
vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
@@ -203,19 +187,8 @@ int dma_common_mmap(struct device *dev,
if (off >= count || user_count > count - off)
return -ENXIO;
- if (!dev_is_dma_coherent(dev)) {
- if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN))
- return -ENXIO;
-
- /* If the PFN is not valid, we do not have a struct page */
- pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr);
- if (!pfn_valid(pfn))
- return -ENXIO;
- } else {
- pfn = page_to_pfn(virt_to_page(cpu_addr));
- }
-
- return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff,
+ return remap_pfn_range(vma, vma->vm_start,
+ page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
user_count << PAGE_SHIFT, vma->vm_page_prot);
#else
return -ENXIO;
@@ -233,12 +206,8 @@ bool dma_can_mmap(struct device *dev)
{
const struct dma_map_ops *ops = get_dma_ops(dev);
- if (dma_is_direct(ops)) {
- return IS_ENABLED(CONFIG_MMU) &&
- (dev_is_dma_coherent(dev) ||
- IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN));
- }
-
+ if (dma_is_direct(ops))
+ return dma_direct_can_mmap(dev);
return ops->mmap != NULL;
}
EXPORT_SYMBOL_GPL(dma_can_mmap);
@@ -263,7 +232,7 @@ int dma_mmap_attrs(struct device *dev, s
const struct dma_map_ops *ops = get_dma_ops(dev);
if (dma_is_direct(ops))
- return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size,
+ return dma_direct_mmap(dev, vma, cpu_addr, dma_addr, size,
attrs);
if (!ops->mmap)
return -ENXIO;
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -259,10 +259,4 @@ void arch_dma_free(struct device *dev, s
dma_free_contiguous(dev, page, size);
}
}
-
-long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
- dma_addr_t dma_addr)
-{
- return __phys_to_pfn(dma_to_phys(dev, dma_addr));
-}
#endif /* CONFIG_DMA_DIRECT_REMAP */