switch xtensa over to the generic DMA remap / uncached segment code

switch xtensa over to the generic DMA remap / uncached segment code

[Christoph Hellwig]

Hi all,

this series switches over xtensa to use the generic DMA remap and
uncached code.  Xtensa is a little special because it uses an uncached
segment by default, but can still use page table bits for remapping
highmem.  To facilitate that there is some major refactoring in the
common DMA code that merges the remapping code into the main direct
mapping alloc / free routines.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 1/5] dma-direct: remove __dma_direct_free_pages

[Christoph Hellwig]

We can just call dma_free_contiguous directly instead of wrapping it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h |  1 -
 kernel/dma/direct.c        | 11 +++--------
 kernel/dma/remap.c         |  4 ++--
 3 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index adf993a3bd58..dec3b3bb121d 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -68,6 +68,5 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
-void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page);
 int dma_direct_supported(struct device *dev, u64 mask);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8402b29c280f..a7a2739fb747 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -153,7 +153,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		 * so log an error and fail.
 		 */
 		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		__dma_direct_free_pages(dev, size, page);
+		dma_free_contiguous(dev, page, size);
 		return NULL;
 	}
 
@@ -175,11 +175,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	return ret;
 }
 
-void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page)
-{
-	dma_free_contiguous(dev, page, size);
-}
-
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs)
 {
@@ -188,7 +183,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
 	    !force_dma_unencrypted(dev)) {
 		/* cpu_addr is a struct page cookie, not a kernel address */
-		__dma_direct_free_pages(dev, size, cpu_addr);
+		dma_free_contiguous(dev, cpu_addr, size);
 		return;
 	}
 
@@ -198,7 +193,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		cpu_addr = cached_kernel_address(cpu_addr);
-	__dma_direct_free_pages(dev, size, virt_to_page(cpu_addr));
+	dma_free_contiguous(dev, virt_to_page(cpu_addr), size);
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size,
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index c00b9258fa6a..fb1e50c2d48a 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -238,7 +238,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 			dma_pgprot(dev, PAGE_KERNEL, attrs),
 			__builtin_return_address(0));
 	if (!ret) {
-		__dma_direct_free_pages(dev, size, page);
+		dma_free_contiguous(dev, page, size);
 		return ret;
 	}
 
@@ -256,7 +256,7 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		struct page *page = pfn_to_page(__phys_to_pfn(phys));
 
 		vunmap(vaddr);
-		__dma_direct_free_pages(dev, size, page);
+		dma_free_contiguous(dev, page, size);
 	}
 }
 
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 2/5] dma-direct: remove the dma_handle argument to __dma_direct_alloc_pages

[Christoph Hellwig]

The argument isn't used anywhere, so stop passing it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-direct.h | 2 +-
 kernel/dma/direct.c        | 4 ++--
 kernel/dma/remap.c         | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index dec3b3bb121d..ff3d5edc44b9 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -67,6 +67,6 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
+		gfp_t gfp, unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index a7a2739fb747..724c282dd943 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -83,7 +83,7 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 }
 
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+		gfp_t gfp, unsigned long attrs)
 {
 	size_t alloc_size = PAGE_ALIGN(size);
 	int node = dev_to_node(dev);
@@ -131,7 +131,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	struct page *page;
 	void *ret;
 
-	page = __dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
+	page = __dma_direct_alloc_pages(dev, size, gfp, attrs);
 	if (!page)
 		return NULL;
 
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index fb1e50c2d48a..90d5ce77c189 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -226,7 +226,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		goto done;
 	}
 
-	page = __dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs);
+	page = __dma_direct_alloc_pages(dev, size, flags, attrs);
 	if (!page)
 		return NULL;
 
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 3/5] dma-direct: provide mmap and get_sgtable method overrides

[Christoph Hellwig]

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>
---
 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(-)

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 8383155c8c82..4d7b671c8ff4 100644
--- 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
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8a50efb559f3..80e795aacd3a 100644
--- 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
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 7d042d5c43e3..f3cbeba7f9cb 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2346,12 +2346,6 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 			      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)
 {
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3f047afb982c..57606307fe34 100644
--- 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_FAST_MULTIPLIER
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 16714477eef4..bab7cd878464 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -33,7 +33,7 @@ config IA64
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_DMA_COHERENT_TO_PFN
+	select DMA_NONCOHERENT_MMAP
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
diff --git a/arch/ia64/kernel/dma-mapping.c b/arch/ia64/kernel/dma-mapping.c
index 4a3262795890..09ef9ce9988d 100644
--- a/arch/ia64/kernel/dma-mapping.c
+++ b/arch/ia64/kernel/dma-mapping.c
@@ -19,9 +19,3 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 {
 	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));
-}
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index c9c4be822456..261c26df1c9f 100644
--- 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_DMA_PREP_COHERENT
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a0bd9bdb5f83..248d39b8a160 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1134,9 +1134,9 @@ 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
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 1d4d57dd9acf..fcf6d3eaac66 100644
--- 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)
 {
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 12543e53fa96..303752f97c19 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -459,7 +459,6 @@ 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_DMA_PREP_COHERENT
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_HAS_SYNC_DMA_FOR_CPU
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index ff3d5edc44b9..bcd953fb1f5a 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -68,5 +68,12 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		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 */
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index dd3de6d88fc0..e30fca1f1b12 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -41,8 +41,6 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		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
 /*
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 73c5c2b8e824..4c103a24e380 100644
--- 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
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 724c282dd943..d8b612648a6b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -43,6 +43,12 @@ static inline dma_addr_t phys_to_dma_direct(struct device *dev,
 	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_to_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);
@@ -379,6 +385,59 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 }
 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_to_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
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index d9334f31a5af..12ff766ec1fa 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -112,24 +112,9 @@ int dma_common_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;
+	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 *dev, struct sg_table *sgt,
 	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, struct vm_area_struct *vma,
 	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, struct vm_area_struct *vma,
 	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, struct vm_area_struct *vma,
 	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;
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 90d5ce77c189..3c49499ee6b0 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -259,10 +259,4 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		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 */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 4/5] dma-mapping: merge the generic remapping helpers into dma-direct

[Christoph Hellwig]

Integrate the generic dma remapping implementation into the main flow.
This prepares for architectures like xtensa that use an uncached
segment for pages in the kernel mapping, but can also remap highmem
from CMA.  To simplify that implementation we now always deduct the
page from the physical address via the DMA address instead of the
virtual address.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/direct.c | 60 ++++++++++++++++++++++++++++++++++++---------
 kernel/dma/remap.c  | 49 ------------------------------------
 2 files changed, 48 insertions(+), 61 deletions(-)

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index d8b612648a6b..e37e7ab6e2ee 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -12,6 +12,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/dma-noncoherent.h>
 #include <linux/pfn.h>
+#include <linux/vmalloc.h>
 #include <linux/set_memory.h>
 #include <linux/swiotlb.h>
 
@@ -137,6 +138,15 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	struct page *page;
 	void *ret;
 
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_alloc_need_uncached(dev, attrs) &&
+	    !gfpflags_allow_blocking(gfp)) {
+		ret = dma_alloc_from_pool(PAGE_ALIGN(size), &page, gfp);
+		if (!ret)
+			return NULL;
+		goto done;
+	}
+
 	page = __dma_direct_alloc_pages(dev, size, gfp, attrs);
 	if (!page)
 		return NULL;
@@ -146,9 +156,28 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		/* remove any dirty cache lines on the kernel alias */
 		if (!PageHighMem(page))
 			arch_dma_prep_coherent(page, size);
-		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 		/* return the page pointer as the opaque cookie */
-		return page;
+		ret = page;
+		goto done;
+	}
+
+	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	     dma_alloc_need_uncached(dev, attrs)) ||
+	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
+		/* remove any dirty cache lines on the kernel alias */
+		arch_dma_prep_coherent(page, PAGE_ALIGN(size));
+
+		/* create a coherent mapping */
+		ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size),
+				dma_pgprot(dev, PAGE_KERNEL, attrs),
+				__builtin_return_address(0));
+		if (!ret) {
+			dma_free_contiguous(dev, page, size);
+			return ret;
+		}
+
+		memset(ret, 0, size);
+		goto done;
 	}
 
 	if (PageHighMem(page)) {
@@ -164,12 +193,9 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 	}
 
 	ret = page_address(page);
-	if (force_dma_unencrypted(dev)) {
+	if (force_dma_unencrypted(dev))
 		set_memory_decrypted((unsigned long)ret, 1 << get_order(size));
-		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
-	} else {
-		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-	}
+
 	memset(ret, 0, size);
 
 	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
@@ -177,7 +203,11 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size,
 		arch_dma_prep_coherent(page, size);
 		ret = uncached_kernel_address(ret);
 	}
-
+done:
+	if (force_dma_unencrypted(dev))
+		*dma_handle = __phys_to_dma(dev, page_to_phys(page));
+	else
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
 	return ret;
 }
 
@@ -193,19 +223,24 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
+	if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    dma_free_from_pool(cpu_addr, PAGE_ALIGN(size)))
+		return;
+
 	if (force_dma_unencrypted(dev))
 		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
-	    dma_alloc_need_uncached(dev, attrs))
-		cpu_addr = cached_kernel_address(cpu_addr);
-	dma_free_contiguous(dev, virt_to_page(cpu_addr), size);
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
+		vunmap(cpu_addr);
+
+	dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size);
 }
 
 void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
 	return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs);
@@ -215,6 +250,7 @@ void dma_direct_free(struct device *dev, size_t size,
 		void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs)
 {
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) &&
+	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
 	    dma_alloc_need_uncached(dev, attrs))
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
 	else
diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index 3c49499ee6b0..d47bd40fc0f5 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -210,53 +210,4 @@ bool dma_free_from_pool(void *start, size_t size)
 	gen_pool_free(atomic_pool, (unsigned long)start, size);
 	return true;
 }
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t flags, unsigned long attrs)
-{
-	struct page *page = NULL;
-	void *ret;
-
-	size = PAGE_ALIGN(size);
-
-	if (!gfpflags_allow_blocking(flags)) {
-		ret = dma_alloc_from_pool(size, &page, flags);
-		if (!ret)
-			return NULL;
-		goto done;
-	}
-
-	page = __dma_direct_alloc_pages(dev, size, flags, attrs);
-	if (!page)
-		return NULL;
-
-	/* remove any dirty cache lines on the kernel alias */
-	arch_dma_prep_coherent(page, size);
-
-	/* create a coherent mapping */
-	ret = dma_common_contiguous_remap(page, size,
-			dma_pgprot(dev, PAGE_KERNEL, attrs),
-			__builtin_return_address(0));
-	if (!ret) {
-		dma_free_contiguous(dev, page, size);
-		return ret;
-	}
-
-	memset(ret, 0, size);
-done:
-	*dma_handle = phys_to_dma(dev, page_to_phys(page));
-	return ret;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	if (!dma_free_from_pool(vaddr, PAGE_ALIGN(size))) {
-		phys_addr_t phys = dma_to_phys(dev, dma_handle);
-		struct page *page = pfn_to_page(__phys_to_pfn(phys));
-
-		vunmap(vaddr);
-		dma_free_contiguous(dev, page, size);
-	}
-}
 #endif /* CONFIG_DMA_DIRECT_REMAP */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

[PATCH 5/5] xtensa: use the generic uncached segment support

[Christoph Hellwig]

Switch xtensa over to use the generic uncached support, and thus the
generic implementations of dma_alloc_* and dma_alloc_*, which also
gains support for mmaping DMA memory.  The non-working nommu DMA
support has been disabled, but could be re-enabled easily if platforms
that actually have an uncached segment show up.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/xtensa/Kconfig                |   6 +-
 arch/xtensa/include/asm/platform.h |  27 -------
 arch/xtensa/kernel/Makefile        |   3 +-
 arch/xtensa/kernel/pci-dma.c       | 121 +++--------------------------
 4 files changed, 18 insertions(+), 139 deletions(-)

diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index a8e7beb6b7b5..c95a34702242 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -3,8 +3,10 @@ config XTENSA
 	def_bool y
 	select ARCH_32BIT_OFF_T
 	select ARCH_HAS_BINFMT_FLAT if !MMU
-	select ARCH_HAS_SYNC_DMA_FOR_CPU
-	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_DMA_PREP_COHERENT if MMU
+	select ARCH_HAS_SYNC_DMA_FOR_CPU if MMU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if MMU
+	select ARCH_HAS_UNCACHED_SEGMENT if MMU
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_FRAME_POINTERS
diff --git a/arch/xtensa/include/asm/platform.h b/arch/xtensa/include/asm/platform.h
index 913826dfa838..f2c48522c5a1 100644
--- a/arch/xtensa/include/asm/platform.h
+++ b/arch/xtensa/include/asm/platform.h
@@ -65,31 +65,4 @@ extern void platform_calibrate_ccount (void);
  */
 void cpu_reset(void) __attribute__((noreturn));
 
-/*
- * Memory caching is platform-dependent in noMMU xtensa configurations.
- * The following set of functions should be implemented in platform code
- * in order to enable coherent DMA memory operations when CONFIG_MMU is not
- * enabled. Default implementations do nothing and issue a warning.
- */
-
-/*
- * Check whether p points to a cached memory.
- */
-bool platform_vaddr_cached(const void *p);
-
-/*
- * Check whether p points to an uncached memory.
- */
-bool platform_vaddr_uncached(const void *p);
-
-/*
- * Return pointer to an uncached view of the cached sddress p.
- */
-void *platform_vaddr_to_uncached(void *p);
-
-/*
- * Return pointer to a cached view of the uncached sddress p.
- */
-void *platform_vaddr_to_cached(void *p);
-
 #endif	/* _XTENSA_PLATFORM_H */
diff --git a/arch/xtensa/kernel/Makefile b/arch/xtensa/kernel/Makefile
index 6f629027ac7d..d4082c6a121b 100644
--- a/arch/xtensa/kernel/Makefile
+++ b/arch/xtensa/kernel/Makefile
@@ -5,10 +5,11 @@
 
 extra-y := head.o vmlinux.lds
 
-obj-y := align.o coprocessor.o entry.o irq.o pci-dma.o platform.o process.o \
+obj-y := align.o coprocessor.o entry.o irq.o platform.o process.o \
 	 ptrace.o setup.o signal.o stacktrace.o syscall.o time.o traps.o \
 	 vectors.o
 
+obj-$(CONFIG_MMU) += pci-dma.o
 obj-$(CONFIG_PCI) += pci.o
 obj-$(CONFIG_MODULES) += xtensa_ksyms.o module.o
 obj-$(CONFIG_FUNCTION_TRACER) += mcount.o
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 154979d62b73..1c82e21de4f6 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -81,122 +81,25 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-#ifdef CONFIG_MMU
-bool platform_vaddr_cached(const void *p)
-{
-	unsigned long addr = (unsigned long)p;
-
-	return addr >= XCHAL_KSEG_CACHED_VADDR &&
-	       addr - XCHAL_KSEG_CACHED_VADDR < XCHAL_KSEG_SIZE;
-}
-
-bool platform_vaddr_uncached(const void *p)
-{
-	unsigned long addr = (unsigned long)p;
-
-	return addr >= XCHAL_KSEG_BYPASS_VADDR &&
-	       addr - XCHAL_KSEG_BYPASS_VADDR < XCHAL_KSEG_SIZE;
-}
-
-void *platform_vaddr_to_uncached(void *p)
-{
-	return p + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
-}
-
-void *platform_vaddr_to_cached(void *p)
-{
-	return p + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
-}
-#else
-bool __attribute__((weak)) platform_vaddr_cached(const void *p)
-{
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return true;
-}
-
-bool __attribute__((weak)) platform_vaddr_uncached(const void *p)
-{
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return false;
-}
-
-void __attribute__((weak)) *platform_vaddr_to_uncached(void *p)
+void arch_dma_prep_coherent(struct page *page, size_t size)
 {
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return p;
-}
-
-void __attribute__((weak)) *platform_vaddr_to_cached(void *p)
-{
-	WARN_ONCE(1, "Default %s implementation is used\n", __func__);
-	return p;
+	__invalidate_dcache_range((unsigned long)page_address(page), size);
 }
-#endif
 
 /*
- * Note: We assume that the full memory space is always mapped to 'kseg'
- *	 Otherwise we have to use page attributes (not implemented).
+ * Memory caching is platform-dependent in noMMU xtensa configurations.
+ * The following two functions should be implemented in platform code
+ * in order to enable coherent DMA memory operations when CONFIG_MMU is not
+ * enabled.
  */
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-		gfp_t flag, unsigned long attrs)
-{
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = NULL;
-
-	/* ignore region speicifiers */
-
-	flag &= ~(__GFP_DMA | __GFP_HIGHMEM);
-
-	if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
-		flag |= GFP_DMA;
-
-	if (gfpflags_allow_blocking(flag))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 flag & __GFP_NOWARN);
-
-	if (!page)
-		page = alloc_pages(flag | __GFP_ZERO, get_order(size));
-
-	if (!page)
-		return NULL;
-
-	*handle = phys_to_dma(dev, page_to_phys(page));
-
 #ifdef CONFIG_MMU
-	if (PageHighMem(page)) {
-		void *p;
-
-		p = dma_common_contiguous_remap(page, size,
-						pgprot_noncached(PAGE_KERNEL),
-						__builtin_return_address(0));
-		if (!p) {
-			if (!dma_release_from_contiguous(dev, page, count))
-				__free_pages(page, get_order(size));
-		}
-		return p;
-	}
-#endif
-	BUG_ON(!platform_vaddr_cached(page_address(page)));
-	__invalidate_dcache_range((unsigned long)page_address(page), size);
-	return platform_vaddr_to_uncached(page_address(page));
+void *uncached_kernel_address(void *p)
+{
+	return p + XCHAL_KSEG_BYPASS_VADDR - XCHAL_KSEG_CACHED_VADDR;
 }
 
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
+void *cached_kernel_address(void *p)
 {
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page;
-
-	if (platform_vaddr_uncached(vaddr)) {
-		page = virt_to_page(platform_vaddr_to_cached(vaddr));
-	} else {
-#ifdef CONFIG_MMU
-		dma_common_free_remap(vaddr, size);
-#endif
-		page = pfn_to_page(PHYS_PFN(dma_to_phys(dev, dma_handle)));
-	}
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
+	return p + XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
 }
+#endif /* CONFIG_MMU */
-- 
2.20.1

_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: switch xtensa over to the generic DMA remap / uncached segment code

[Max Filippov]

On Fri, Nov 1, 2019 at 3:02 PM Christoph Hellwig <hch@lst.de> wrote:
> this series switches over xtensa to use the generic DMA remap and
> uncached code.  Xtensa is a little special because it uses an uncached
> segment by default, but can still use page table bits for remapping
> highmem.  To facilitate that there is some major refactoring in the
> common DMA code that merges the remapping code into the main direct
> mapping alloc / free routines.

For the whole series:
Reviewed-by: Max Filippov <jcmvbkbc@gmail.com>
For the xtensa bits:
Tested-by: Max Filippov <jcmvbkbc@gmail.com>

-- 
Thanks.
-- Max
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu

Re: switch xtensa over to the generic DMA remap / uncached segment code

[Christoph Hellwig]

On Fri, Nov 01, 2019 at 08:18:49PM -0700, Max Filippov wrote:
> On Fri, Nov 1, 2019 at 3:02 PM Christoph Hellwig <hch@lst.de> wrote:
> > this series switches over xtensa to use the generic DMA remap and
> > uncached code.  Xtensa is a little special because it uses an uncached
> > segment by default, but can still use page table bits for remapping
> > highmem.  To facilitate that there is some major refactoring in the
> > common DMA code that merges the remapping code into the main direct
> > mapping alloc / free routines.
> 
> For the whole series:
> Reviewed-by: Max Filippov <jcmvbkbc@gmail.com>
> For the xtensa bits:
> Tested-by: Max Filippov <jcmvbkbc@gmail.com>

Thanks,

I've pulled this into the dma-mapping tree for 5.5.
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu