From b3d53f5fce5d07b4981f0f4f93e579e389a99b07 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 29 Oct 2019 14:34:23 -0700
Subject: usb: core: Remove redundant vmap checks

Now that the vmap area checks are being performed in the DMA
infrastructure directly, there is no need to repeat them in USB.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/usb/core/hcd.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

(limited to 'drivers')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index f225eaa98ff8..281568d464f9 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1410,10 +1410,7 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 		if (hcd->self.uses_pio_for_control)
 			return ret;
 		if (hcd_uses_dma(hcd)) {
-			if (is_vmalloc_addr(urb->setup_packet)) {
-				WARN_ONCE(1, "setup packet is not dma capable\n");
-				return -EAGAIN;
-			} else if (object_is_on_stack(urb->setup_packet)) {
+			if (object_is_on_stack(urb->setup_packet)) {
 				WARN_ONCE(1, "setup packet is on stack\n");
 				return -EAGAIN;
 			}
@@ -1479,9 +1476,6 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 					ret = -EAGAIN;
 				else
 					urb->transfer_flags |= URB_DMA_MAP_PAGE;
-			} else if (is_vmalloc_addr(urb->transfer_buffer)) {
-				WARN_ONCE(1, "transfer buffer not dma capable\n");
-				ret = -EAGAIN;
 			} else if (object_is_on_stack(urb->transfer_buffer)) {
 				WARN_ONCE(1, "transfer buffer is on stack\n");
 				ret = -EAGAIN;
-- 
cgit v1.3.1


From 56e35f9c5b87ec1ae93e483284e189c84388de16 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 7 Nov 2019 18:03:11 +0100
Subject: dma-mapping: drop the dev argument to arch_sync_dma_for_*

These are pure cache maintainance routines, so drop the unused
struct device argument.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 arch/arc/mm/dma.c                 |  8 ++++----
 arch/arm/mm/dma-mapping.c         |  8 ++++----
 arch/arm/xen/mm.c                 | 12 ++++++------
 arch/arm64/mm/dma-mapping.c       |  8 ++++----
 arch/c6x/mm/dma-coherent.c        | 14 +++++++-------
 arch/csky/mm/dma-mapping.c        |  8 ++++----
 arch/hexagon/kernel/dma.c         |  4 ++--
 arch/ia64/mm/init.c               |  4 ++--
 arch/m68k/kernel/dma.c            |  4 ++--
 arch/microblaze/kernel/dma.c      | 14 +++++++-------
 arch/mips/bmips/dma.c             |  2 +-
 arch/mips/jazz/jazzdma.c          | 17 ++++++++---------
 arch/mips/mm/dma-noncoherent.c    | 12 ++++++------
 arch/nds32/kernel/dma.c           |  8 ++++----
 arch/nios2/mm/dma-mapping.c       |  8 ++++----
 arch/openrisc/kernel/dma.c        |  2 +-
 arch/parisc/kernel/pci-dma.c      |  8 ++++----
 arch/powerpc/mm/dma-noncoherent.c |  8 ++++----
 arch/sh/kernel/dma-coherent.c     |  6 +++---
 arch/sparc/kernel/ioport.c        |  4 ++--
 arch/xtensa/kernel/pci-dma.c      |  8 ++++----
 drivers/iommu/dma-iommu.c         | 10 +++++-----
 drivers/xen/swiotlb-xen.c         |  8 ++++----
 include/linux/dma-noncoherent.h   | 20 ++++++++++----------
 include/xen/swiotlb-xen.h         |  8 ++++----
 kernel/dma/direct.c               | 14 +++++++-------
 26 files changed, 113 insertions(+), 114 deletions(-)

(limited to 'drivers')

diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 73a7e88a1e92..e947572a521e 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -48,8 +48,8 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
  * upper layer functions (in include/linux/dma-mapping.h)
  */
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
@@ -69,8 +69,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f3cbeba7f9cb..da1a32b5e192 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2332,15 +2332,15 @@ void arch_teardown_dma_ops(struct device *dev)
 }
 
 #ifdef CONFIG_SWIOTLB
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
 			      size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
 			      size, dir);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 38fa917c8585..a6a2514e5fe8 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -70,20 +70,20 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op)
  * pfn_valid returns true the pages is local and we can use the native
  * dma-direct functions, otherwise we call the Xen specific version.
  */
-void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	if (pfn_valid(PFN_DOWN(handle)))
-		arch_sync_dma_for_cpu(dev, paddr, size, dir);
+		arch_sync_dma_for_cpu(paddr, size, dir);
 	else if (dir != DMA_TO_DEVICE)
 		dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
 }
 
-void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	if (pfn_valid(PFN_DOWN(handle)))
-		arch_sync_dma_for_device(dev, paddr, size, dir);
+		arch_sync_dma_for_device(paddr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
 		dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL);
 	else
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 9239416e93d4..6c45350e33aa 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -13,14 +13,14 @@
 
 #include <asm/cacheflush.h>
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_map_area(phys_to_virt(paddr), size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_unmap_area(phys_to_virt(paddr), size, dir);
 }
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index b319808e8f6b..a5909091cb14 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -140,7 +140,7 @@ void __init coherent_mem_init(phys_addr_t start, u32 size)
 		      sizeof(long));
 }
 
-static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+static void c6x_dma_sync(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
 	BUG_ON(!valid_dma_direction(dir));
@@ -160,14 +160,14 @@ static void c6x_dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
 	}
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	return c6x_dma_sync(dev, paddr, size, dir);
+	return c6x_dma_sync(paddr, size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	return c6x_dma_sync(dev, paddr, size, dir);
+	return c6x_dma_sync(paddr, size, dir);
 }
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 06e85b565454..8f6571ae27c8 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -58,8 +58,8 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 	cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-			      size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
@@ -74,8 +74,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-			   size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index f561b127c4b4..25f388d9cfcc 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -55,8 +55,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	gen_pool_free(coherent_pool, (unsigned long) vaddr, size);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *addr = phys_to_virt(paddr);
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index bf9df2625bc8..58fd67068bac 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -73,8 +73,8 @@ __ia64_sync_icache_dcache (pte_t pte)
  * DMA can be marked as "clean" so that lazy_mmu_prot_update() doesn't have to
  * flush them when they get mapped into an executable vm-area.
  */
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	unsigned long pfn = PHYS_PFN(paddr);
 
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 3fab684cc0db..871a0e11da34 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -61,8 +61,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t handle, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index a89c2d4ed5ff..d7bebd04247b 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -15,7 +15,7 @@
 #include <linux/bug.h>
 #include <asm/cacheflush.h>
 
-static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
+static void __dma_sync(phys_addr_t paddr, size_t size,
 		enum dma_data_direction direction)
 {
 	switch (direction) {
@@ -31,14 +31,14 @@ static void __dma_sync(struct device *dev, phys_addr_t paddr, size_t size,
 	}
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	__dma_sync(dev, paddr, size, dir);
+	__dma_sync(paddr, size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	__dma_sync(dev, paddr, size, dir);
+	__dma_sync(paddr, size, dir);
 }
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index 3d13c77c125f..df56bf4179e3 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -64,7 +64,7 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr;
 }
 
-void arch_sync_dma_for_cpu_all(struct device *dev)
+void arch_sync_dma_for_cpu_all(void)
 {
 	void __iomem *cbr = BMIPS_GET_CBR();
 	u32 cfg;
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index a01e14955187..c64a297e82b3 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -592,7 +592,7 @@ static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
 	phys_addr_t phys = page_to_phys(page) + offset;
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return vdma_alloc(phys, size);
 }
 
@@ -600,7 +600,7 @@ static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir);
+		arch_sync_dma_for_cpu(vdma_log2phys(dma_addr), size, dir);
 	vdma_free(dma_addr);
 }
 
@@ -612,7 +612,7 @@ static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+			arch_sync_dma_for_device(sg_phys(sg), sg->length,
 				dir);
 		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
@@ -631,8 +631,7 @@ static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length,
-				dir);
+			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 		vdma_free(sg->dma_address);
 	}
 }
@@ -640,13 +639,13 @@ static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 static void jazz_dma_sync_single_for_device(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir);
+	arch_sync_dma_for_device(vdma_log2phys(addr), size, dir);
 }
 
 static void jazz_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
-	arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir);
+	arch_sync_dma_for_cpu(vdma_log2phys(addr), size, dir);
 }
 
 static void jazz_dma_sync_sg_for_device(struct device *dev,
@@ -656,7 +655,7 @@ static void jazz_dma_sync_sg_for_device(struct device *dev,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
 static void jazz_dma_sync_sg_for_cpu(struct device *dev,
@@ -666,7 +665,7 @@ static void jazz_dma_sync_sg_for_cpu(struct device *dev,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
 const struct dma_map_ops jazz_dma_ops = {
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index fcf6d3eaac66..dc42ffc83825 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -27,7 +27,7 @@
  * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
  * SGI IP32 aka O2.
  */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
+static inline bool cpu_needs_post_dma_flush(void)
 {
 	switch (boot_cpu_type()) {
 	case CPU_R10000:
@@ -112,17 +112,17 @@ static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
 	} while (left);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	dma_sync_phys(paddr, size, dir);
 }
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
-	if (cpu_needs_post_dma_flush(dev))
+	if (cpu_needs_post_dma_flush())
 		dma_sync_phys(paddr, size, dir);
 }
 #endif
diff --git a/arch/nds32/kernel/dma.c b/arch/nds32/kernel/dma.c
index 4206d4b6c8ce..69d762182d49 100644
--- a/arch/nds32/kernel/dma.c
+++ b/arch/nds32/kernel/dma.c
@@ -46,8 +46,8 @@ static inline void cache_op(phys_addr_t paddr, size_t size,
 	} while (left);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_FROM_DEVICE:
@@ -61,8 +61,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 9cb238664584..0ed711e37902 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -18,8 +18,8 @@
 #include <linux/cache.h>
 #include <asm/cacheflush.h>
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *vaddr = phys_to_virt(paddr);
 
@@ -42,8 +42,8 @@ void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *vaddr = phys_to_virt(paddr);
 
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 4d5b8bd1d795..adec711ad39d 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -125,7 +125,7 @@ arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	free_pages_exact(vaddr, size);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t addr, size_t size,
+void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
 		enum dma_data_direction dir)
 {
 	unsigned long cl;
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index ca35d9a76e50..a60d47fd4d55 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -439,14 +439,14 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	free_pages((unsigned long)__va(dma_handle), order);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index 2a82984356f8..5ab4f868e919 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -104,14 +104,14 @@ static void __dma_sync_page(phys_addr_t paddr, size_t size, int dir)
 #endif
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_sync_page(paddr, size, dir);
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	__dma_sync_page(paddr, size, dir);
 }
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index b17514619b7e..eeb25a4fa55f 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -25,7 +25,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	 * Pages from the page allocator may have data present in
 	 * cache. So flush the cache before using uncached memory.
 	 */
-	arch_sync_dma_for_device(dev, virt_to_phys(ret), size,
+	arch_sync_dma_for_device(virt_to_phys(ret), size,
 			DMA_BIDIRECTIONAL);
 
 	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
@@ -59,8 +59,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 	iounmap(vaddr);
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	void *addr = sh_cacheop_vaddr(phys_to_virt(paddr));
 
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index f89603855f1e..e59461d03b9a 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -366,8 +366,8 @@ void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 
 /* IIep is write-through, not flushing on cpu to device transfer. */
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	if (dir != PCI_DMA_TODEVICE)
 		dma_make_coherent(paddr, PAGE_ALIGN(size));
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 1c82e21de4f6..72b6222daa0b 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -44,8 +44,8 @@ static void do_cache_op(phys_addr_t paddr, size_t size,
 		}
 }
 
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -62,8 +62,8 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 	}
 }
 
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index f321279baf9e..0fa8c1d818b7 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -659,7 +659,7 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_cpu(dev, phys, size, dir);
+	arch_sync_dma_for_cpu(phys, size, dir);
 }
 
 static void iommu_dma_sync_single_for_device(struct device *dev,
@@ -671,7 +671,7 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 		return;
 
 	phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dma_handle);
-	arch_sync_dma_for_device(dev, phys, size, dir);
+	arch_sync_dma_for_device(phys, size, dir);
 }
 
 static void iommu_dma_sync_sg_for_cpu(struct device *dev,
@@ -685,7 +685,7 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
 static void iommu_dma_sync_sg_for_device(struct device *dev,
@@ -699,7 +699,7 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
-		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+		arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
 static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
@@ -714,7 +714,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	dma_handle =__iommu_dma_map(dev, phys, size, prot);
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    dma_handle != DMA_MAPPING_ERROR)
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return dma_handle;
 }
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index bd3a10dfac15..3f8b2cdb4acb 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -405,7 +405,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 
 done:
 	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		xen_dma_sync_for_device(dev, dev_addr, phys, size, dir);
+		xen_dma_sync_for_device(dev_addr, phys, size, dir);
 	return dev_addr;
 }
 
@@ -425,7 +425,7 @@ static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 	BUG_ON(dir == DMA_NONE);
 
 	if (!dev_is_dma_coherent(hwdev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		xen_dma_sync_for_cpu(hwdev, dev_addr, paddr, size, dir);
+		xen_dma_sync_for_cpu(dev_addr, paddr, size, dir);
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr))
@@ -439,7 +439,7 @@ xen_swiotlb_sync_single_for_cpu(struct device *dev, dma_addr_t dma_addr,
 	phys_addr_t paddr = xen_bus_to_phys(dma_addr);
 
 	if (!dev_is_dma_coherent(dev))
-		xen_dma_sync_for_cpu(dev, dma_addr, paddr, size, dir);
+		xen_dma_sync_for_cpu(dma_addr, paddr, size, dir);
 
 	if (is_xen_swiotlb_buffer(dma_addr))
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
@@ -455,7 +455,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
 
 	if (!dev_is_dma_coherent(dev))
-		xen_dma_sync_for_device(dev, dma_addr, paddr, size, dir);
+		xen_dma_sync_for_device(dma_addr, paddr, size, dir);
 }
 
 /*
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index e30fca1f1b12..ca9b5770caee 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -73,29 +73,29 @@ static inline void arch_dma_cache_sync(struct device *dev, void *vaddr,
 #endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE
-void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir);
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
 #else
-static inline void arch_sync_dma_for_device(struct device *dev,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+static inline void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 }
 #endif /* ARCH_HAS_SYNC_DMA_FOR_DEVICE */
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
-void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir);
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
 #else
-static inline void arch_sync_dma_for_cpu(struct device *dev,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir)
+static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
 {
 }
 #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
-void arch_sync_dma_for_cpu_all(struct device *dev);
+void arch_sync_dma_for_cpu_all(void);
 #else
-static inline void arch_sync_dma_for_cpu_all(struct device *dev)
+static inline void arch_sync_dma_for_cpu_all(void)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index d71380f6ed0b..ffc0d3902b71 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -4,10 +4,10 @@
 
 #include <linux/swiotlb.h>
 
-void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir);
-void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle,
-		phys_addr_t paddr, size_t size, enum dma_data_direction dir);
+void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
+void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir);
 
 extern int xen_swiotlb_init(int verbose, bool early);
 extern const struct dma_map_ops xen_swiotlb_dma_ops;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 22a2e0833862..077876ae5c74 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -268,7 +268,7 @@ void dma_direct_sync_single_for_device(struct device *dev,
 		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
 
 	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_device(dev, paddr, size, dir);
+		arch_sync_dma_for_device(paddr, size, dir);
 }
 EXPORT_SYMBOL(dma_direct_sync_single_for_device);
 
@@ -286,7 +286,7 @@ void dma_direct_sync_sg_for_device(struct device *dev,
 					dir, SYNC_FOR_DEVICE);
 
 		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_device(dev, paddr, sg->length,
+			arch_sync_dma_for_device(paddr, sg->length,
 					dir);
 	}
 }
@@ -302,8 +302,8 @@ void dma_direct_sync_single_for_cpu(struct device *dev,
 	phys_addr_t paddr = dma_to_phys(dev, addr);
 
 	if (!dev_is_dma_coherent(dev)) {
-		arch_sync_dma_for_cpu(dev, paddr, size, dir);
-		arch_sync_dma_for_cpu_all(dev);
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
 	}
 
 	if (unlikely(is_swiotlb_buffer(paddr)))
@@ -321,7 +321,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 		phys_addr_t paddr = dma_to_phys(dev, sg_dma_address(sg));
 
 		if (!dev_is_dma_coherent(dev))
-			arch_sync_dma_for_cpu(dev, paddr, sg->length, dir);
+			arch_sync_dma_for_cpu(paddr, sg->length, dir);
 
 		if (unlikely(is_swiotlb_buffer(paddr)))
 			swiotlb_tbl_sync_single(dev, paddr, sg->length, dir,
@@ -329,7 +329,7 @@ void dma_direct_sync_sg_for_cpu(struct device *dev,
 	}
 
 	if (!dev_is_dma_coherent(dev))
-		arch_sync_dma_for_cpu_all(dev);
+		arch_sync_dma_for_cpu_all();
 }
 EXPORT_SYMBOL(dma_direct_sync_sg_for_cpu);
 
@@ -380,7 +380,7 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
 	}
 
 	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(dev, phys, size, dir);
+		arch_sync_dma_for_device(phys, size, dir);
 	return dma_addr;
 }
 EXPORT_SYMBOL(dma_direct_map_page);
-- 
cgit v1.3.1


From 68a33b1794665ba8a1d1ef1d3bfcc7c587d380a6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Nov 2019 17:38:58 +0100
Subject: dma-direct: exclude dma_direct_map_resource from the min_low_pfn
 check

The valid memory address check in dma_capable only makes sense when mapping
normal memory, not when using dma_map_resource to map a device resource.
Add a new boolean argument to dma_capable to exclude that check for the
dma_map_resource case.

Fixes: b12d66278dd6 ("dma-direct: check for overflows on 32 bit DMA addresses")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 arch/x86/kernel/amd_gart_64.c | 4 ++--
 drivers/xen/swiotlb-xen.c     | 4 ++--
 include/linux/dma-direct.h    | 5 +++--
 kernel/dma/direct.c           | 4 ++--
 kernel/dma/swiotlb.c          | 2 +-
 5 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'drivers')

diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index a6ac3712db8b..5cfab41e8509 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -185,13 +185,13 @@ static void iommu_full(struct device *dev, size_t size, int dir)
 static inline int
 need_iommu(struct device *dev, unsigned long addr, size_t size)
 {
-	return force_iommu || !dma_capable(dev, addr, size);
+	return force_iommu || !dma_capable(dev, addr, size, true);
 }
 
 static inline int
 nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
 {
-	return !dma_capable(dev, addr, size);
+	return !dma_capable(dev, addr, size, true);
 }
 
 /* Map a single continuous physical area into the IOMMU.
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 3f8b2cdb4acb..b6d27762c6f8 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -375,7 +375,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (dma_capable(dev, dev_addr, size) &&
+	if (dma_capable(dev, dev_addr, size, true) &&
 	    !range_straddles_page_boundary(phys, size) &&
 		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
 		swiotlb_force != SWIOTLB_FORCE)
@@ -397,7 +397,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (unlikely(!dma_capable(dev, dev_addr, size))) {
+	if (unlikely(!dma_capable(dev, dev_addr, size, true))) {
 		swiotlb_tbl_unmap_single(dev, map, size, size, dir,
 				attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return DMA_MAPPING_ERROR;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index f8959f75e496..99b77dd5f79b 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -49,14 +49,15 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return __sme_clr(__dma_to_phys(dev, daddr));
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
+		bool is_ram)
 {
 	dma_addr_t end = addr + size - 1;
 
 	if (!dev->dma_mask)
 		return false;
 
-	if (!IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
+	if (is_ram && !IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) &&
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index a479bd2d1e8b..40f1f0aac4b1 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -363,7 +363,7 @@ static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr,
 		size_t size)
 {
 	return swiotlb_force != SWIOTLB_FORCE &&
-		dma_capable(dev, dma_addr, size);
+		dma_capable(dev, dma_addr, size, true);
 }
 
 dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
@@ -412,7 +412,7 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
 {
 	dma_addr_t dma_addr = paddr;
 
-	if (unlikely(!dma_capable(dev, dma_addr, size))) {
+	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
 		report_addr(dev, dma_addr, size);
 		return DMA_MAPPING_ERROR;
 	}
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 673a2cdb2656..9280d6f8271e 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -678,7 +678,7 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 
 	/* Ensure that the address returned is DMA'ble */
 	*dma_addr = __phys_to_dma(dev, *phys);
-	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
+	if (unlikely(!dma_capable(dev, *dma_addr, size, true))) {
 		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return false;
-- 
cgit v1.3.1


From a7ba70f1787f977f970cd116076c6fce4b9e01cc Mon Sep 17 00:00:00 2001
From: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Date: Thu, 21 Nov 2019 10:26:44 +0100
Subject: dma-mapping: treat dev->bus_dma_mask as a DMA limit

Using a mask to represent bus DMA constraints has a set of limitations.
The biggest one being it can only hold a power of two (minus one). The
DMA mapping code is already aware of this and treats dev->bus_dma_mask
as a limit. This quirk is already used by some architectures although
still rare.

With the introduction of the Raspberry Pi 4 we've found a new contender
for the use of bus DMA limits, as its PCIe bus can only address the
lower 3GB of memory (of a total of 4GB). This is impossible to represent
with a mask. To make things worse the device-tree code rounds non power
of two bus DMA limits to the next power of two, which is unacceptable in
this case.

In the light of this, rename dev->bus_dma_mask to dev->bus_dma_limit all
over the tree and treat it as such. Note that dev->bus_dma_limit should
contain the higher accessible DMA address.

Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/mips/pci/fixup-sb1250.c  | 16 ++++++++--------
 arch/powerpc/sysdev/fsl_pci.c |  6 +++---
 arch/x86/kernel/pci-dma.c     |  2 +-
 arch/x86/mm/mem_encrypt.c     |  2 +-
 arch/x86/pci/sta2x11-fixup.c  |  2 +-
 drivers/acpi/arm64/iort.c     | 20 +++++++-------------
 drivers/ata/ahci.c            |  2 +-
 drivers/iommu/dma-iommu.c     |  3 +--
 drivers/of/device.c           |  9 +++++----
 include/linux/device.h        |  6 +++---
 include/linux/dma-direct.h    |  2 +-
 include/linux/dma-mapping.h   |  2 +-
 kernel/dma/direct.c           | 27 +++++++++++++--------------
 13 files changed, 46 insertions(+), 53 deletions(-)

(limited to 'drivers')

diff --git a/arch/mips/pci/fixup-sb1250.c b/arch/mips/pci/fixup-sb1250.c
index 8a41b359cf90..40efc990cdce 100644
--- a/arch/mips/pci/fixup-sb1250.c
+++ b/arch/mips/pci/fixup-sb1250.c
@@ -21,22 +21,22 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI,
 
 /*
  * The BCM1250, etc. PCI host bridge does not support DAC on its 32-bit
- * bus, so we set the bus's DMA mask accordingly.  However the HT link
+ * bus, so we set the bus's DMA limit accordingly.  However the HT link
  * down the artificial PCI-HT bridge supports 40-bit addressing and the
  * SP1011 HT-PCI bridge downstream supports both DAC and a 64-bit bus
  * width, so we record the PCI-HT bridge's secondary and subordinate bus
- * numbers and do not set the mask for devices present in the inclusive
+ * numbers and do not set the limit for devices present in the inclusive
  * range of those.
  */
-struct sb1250_bus_dma_mask_exclude {
+struct sb1250_bus_dma_limit_exclude {
 	bool set;
 	unsigned char start;
 	unsigned char end;
 };
 
-static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data)
+static int sb1250_bus_dma_limit(struct pci_dev *dev, void *data)
 {
-	struct sb1250_bus_dma_mask_exclude *exclude = data;
+	struct sb1250_bus_dma_limit_exclude *exclude = data;
 	bool exclude_this;
 	bool ht_bridge;
 
@@ -55,7 +55,7 @@ static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data)
 			exclude->start, exclude->end);
 	} else {
 		dev_dbg(&dev->dev, "disabling DAC for device");
-		dev->dev.bus_dma_mask = DMA_BIT_MASK(32);
+		dev->dev.bus_dma_limit = DMA_BIT_MASK(32);
 	}
 
 	return 0;
@@ -63,9 +63,9 @@ static int sb1250_bus_dma_mask(struct pci_dev *dev, void *data)
 
 static void quirk_sb1250_pci_dac(struct pci_dev *dev)
 {
-	struct sb1250_bus_dma_mask_exclude exclude = { .set = false };
+	struct sb1250_bus_dma_limit_exclude exclude = { .set = false };
 
-	pci_walk_bus(dev->bus, sb1250_bus_dma_mask, &exclude);
+	pci_walk_bus(dev->bus, sb1250_bus_dma_limit, &exclude);
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI,
 			quirk_sb1250_pci_dac);
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index ff0e2b156cb5..617a443d673d 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -115,8 +115,8 @@ static void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 
-	pdev->dev.bus_dma_mask =
-		hose->dma_window_base_cur + hose->dma_window_size;
+	pdev->dev.bus_dma_limit =
+		hose->dma_window_base_cur + hose->dma_window_size - 1;
 }
 
 static void setup_swiotlb_ops(struct pci_controller *hose)
@@ -135,7 +135,7 @@ static void fsl_pci_dma_set_mask(struct device *dev, u64 dma_mask)
 	 * mapping that allows addressing any RAM address from across PCI.
 	 */
 	if (dev_is_pci(dev) && dma_mask >= pci64_dma_offset * 2 - 1) {
-		dev->bus_dma_mask = 0;
+		dev->bus_dma_limit = 0;
 		dev->archdata.dma_offset = pci64_dma_offset;
 	}
 }
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index fa4352dce491..3a75d665d43c 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -146,7 +146,7 @@ rootfs_initcall(pci_iommu_init);
 
 static int via_no_dac_cb(struct pci_dev *pdev, void *data)
 {
-	pdev->dev.bus_dma_mask = DMA_BIT_MASK(32);
+	pdev->dev.bus_dma_limit = DMA_BIT_MASK(32);
 	return 0;
 }
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9268c12458c8..a03614bd3e1a 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -367,7 +367,7 @@ bool force_dma_unencrypted(struct device *dev)
 	if (sme_active()) {
 		u64 dma_enc_mask = DMA_BIT_MASK(__ffs64(sme_me_mask));
 		u64 dma_dev_mask = min_not_zero(dev->coherent_dma_mask,
-						dev->bus_dma_mask);
+						dev->bus_dma_limit);
 
 		if (dma_dev_mask <= dma_enc_mask)
 			return true;
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
index 4a631264b809..c313d784efab 100644
--- a/arch/x86/pci/sta2x11-fixup.c
+++ b/arch/x86/pci/sta2x11-fixup.c
@@ -143,7 +143,7 @@ static void sta2x11_map_ep(struct pci_dev *pdev)
 
 	dev->dma_pfn_offset = PFN_DOWN(-amba_base);
 
-	dev->bus_dma_mask = max_amba_addr;
+	dev->bus_dma_limit = max_amba_addr;
 	pci_set_consistent_dma_mask(pdev, max_amba_addr);
 	pci_set_dma_mask(pdev, max_amba_addr);
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 5a7551d060f2..33f71983e001 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1057,8 +1057,8 @@ static int rc_dma_get_range(struct device *dev, u64 *size)
  */
 void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 {
-	u64 mask, dmaaddr = 0, size = 0, offset = 0;
-	int ret, msb;
+	u64 end, mask, dmaaddr = 0, size = 0, offset = 0;
+	int ret;
 
 	/*
 	 * If @dev is expected to be DMA-capable then the bus code that created
@@ -1085,19 +1085,13 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	}
 
 	if (!ret) {
-		msb = fls64(dmaaddr + size - 1);
 		/*
-		 * Round-up to the power-of-two mask or set
-		 * the mask to the whole 64-bit address space
-		 * in case the DMA region covers the full
-		 * memory window.
+		 * Limit coherent and dma mask based on size retrieved from
+		 * firmware.
 		 */
-		mask = msb == 64 ? U64_MAX : (1ULL << msb) - 1;
-		/*
-		 * Limit coherent and dma mask based on size
-		 * retrieved from firmware.
-		 */
-		dev->bus_dma_mask = mask;
+		end = dmaaddr + size - 1;
+		mask = DMA_BIT_MASK(ilog2(end) + 1);
+		dev->bus_dma_limit = end;
 		dev->coherent_dma_mask = mask;
 		*dev->dma_mask = mask;
 	}
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 05c2b32dcc4d..7c6d06ffb586 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -897,7 +897,7 @@ static int ahci_configure_dma_masks(struct pci_dev *pdev, int using_dac)
 	 * value, don't extend it here. This happens on STA2X11, for example.
 	 *
 	 * XXX: manipulating the DMA mask from platform code is completely
-	 * bogus, platform code should use dev->bus_dma_mask instead..
+	 * bogus, platform code should use dev->bus_dma_limit instead..
 	 */
 	if (pdev->dma_mask && pdev->dma_mask < DMA_BIT_MASK(32))
 		return 0;
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 0fa8c1d818b7..646332fbf3d7 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -405,8 +405,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
-	if (dev->bus_dma_mask)
-		dma_limit &= dev->bus_dma_mask;
+	dma_limit = min_not_zero(dma_limit, dev->bus_dma_limit);
 
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
diff --git a/drivers/of/device.c b/drivers/of/device.c
index da8158392010..e9127db7b067 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -93,7 +93,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	bool coherent;
 	unsigned long offset;
 	const struct iommu_ops *iommu;
-	u64 mask;
+	u64 mask, end;
 
 	ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
 	if (ret < 0) {
@@ -148,12 +148,13 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * Limit coherent and dma mask based on size and default mask
 	 * set by the driver.
 	 */
-	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
+	end = dma_addr + size - 1;
+	mask = DMA_BIT_MASK(ilog2(end) + 1);
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
-	/* ...but only set bus mask if we found valid dma-ranges earlier */
+	/* ...but only set bus limit if we found valid dma-ranges earlier */
 	if (!ret)
-		dev->bus_dma_mask = mask;
+		dev->bus_dma_limit = end;
 
 	coherent = of_dma_is_coherent(np);
 	dev_dbg(dev, "device is%sdma coherent\n",
diff --git a/include/linux/device.h b/include/linux/device.h
index 297239a08bb7..e396de656f20 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1186,8 +1186,8 @@ struct dev_links_info {
  * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
  * 		hardware supports 64-bit addresses for consistent allocations
  * 		such descriptors.
- * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA
- *		limit than the device itself supports.
+ * @bus_dma_limit: Limit of an upstream bridge or bus which imposes a smaller
+ *		DMA limit than the device itself supports.
  * @dma_pfn_offset: offset of DMA memory range relatively of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
@@ -1270,7 +1270,7 @@ struct device {
 					     not all hardware supports
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
-	u64		bus_dma_mask;	/* upstream dma_mask constraint */
+	u64		bus_dma_limit;	/* upstream dma constraint */
 	unsigned long	dma_pfn_offset;
 
 	struct device_dma_parameters *dma_parms;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 452f5280cde3..24b8684aa21d 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -63,7 +63,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 	    min(addr, end) < phys_to_dma(dev, PFN_PHYS(min_low_pfn)))
 		return false;
 
-	return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_mask);
+	return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
 }
 
 u64 dma_direct_get_required_mask(struct device *dev);
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 4d450672b7d6..c4d8741264bd 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -697,7 +697,7 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
  */
 static inline bool dma_addressing_limited(struct device *dev)
 {
-	return min_not_zero(dma_get_mask(dev), dev->bus_dma_mask) <
+	return min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
 			    dma_get_required_mask(dev);
 }
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 267b23a13b69..6af7ae83c4ad 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -27,10 +27,10 @@ static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
 {
 	if (!dev->dma_mask) {
 		dev_err_once(dev, "DMA map on device without dma_mask\n");
-	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) {
+	} else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) {
 		dev_err_once(dev,
-			"overflow %pad+%zu of DMA mask %llx bus mask %llx\n",
-			&dma_addr, size, *dev->dma_mask, dev->bus_dma_mask);
+			"overflow %pad+%zu of DMA mask %llx bus limit %llx\n",
+			&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
 	}
 	WARN_ON_ONCE(1);
 }
@@ -57,15 +57,14 @@ u64 dma_direct_get_required_mask(struct device *dev)
 }
 
 static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
-		u64 *phys_mask)
+		u64 *phys_limit)
 {
-	if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask)
-		dma_mask = dev->bus_dma_mask;
+	u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit);
 
 	if (force_dma_unencrypted(dev))
-		*phys_mask = __dma_to_phys(dev, dma_mask);
+		*phys_limit = __dma_to_phys(dev, dma_limit);
 	else
-		*phys_mask = dma_to_phys(dev, dma_mask);
+		*phys_limit = dma_to_phys(dev, dma_limit);
 
 	/*
 	 * Optimistically try the zone that the physical address mask falls
@@ -75,9 +74,9 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	 * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
 	 * zones.
 	 */
-	if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits))
+	if (*phys_limit <= DMA_BIT_MASK(zone_dma_bits))
 		return GFP_DMA;
-	if (*phys_mask <= DMA_BIT_MASK(32))
+	if (*phys_limit <= DMA_BIT_MASK(32))
 		return GFP_DMA32;
 	return 0;
 }
@@ -85,7 +84,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
-			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask);
+			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
@@ -94,7 +93,7 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	size_t alloc_size = PAGE_ALIGN(size);
 	int node = dev_to_node(dev);
 	struct page *page = NULL;
-	u64 phys_mask;
+	u64 phys_limit;
 
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
@@ -102,7 +101,7 @@ struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	/* we always manually zero the memory once we are done: */
 	gfp &= ~__GFP_ZERO;
 	gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
-			&phys_mask);
+			&phys_limit);
 	page = dma_alloc_contiguous(dev, alloc_size, gfp);
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		dma_free_contiguous(dev, page, alloc_size);
@@ -116,7 +115,7 @@ again:
 		page = NULL;
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
-		    phys_mask < DMA_BIT_MASK(64) &&
+		    phys_limit < DMA_BIT_MASK(64) &&
 		    !(gfp & (GFP_DMA32 | GFP_DMA))) {
 			gfp |= GFP_DMA32;
 			goto again;
-- 
cgit v1.3.1