Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux; tag 'dma-mapping-5.5' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - improve dma-debug scalability (Eric Dumazet)

 - tiny dma-debug cleanup (Dan Carpenter)

 - check for vmap memory in dma_map_single (Kees Cook)

 - check for dma_addr_t overflows in dma-direct when using DMA offsets
   (Nicolas Saenz Julienne)

 - switch the x86 sta2x11 SOC to use more generic DMA code (Nicolas
   Saenz Julienne)

 - fix arm-nommu dma-ranges handling (Vladimir Murzin)

 - use __initdata in CMA (Shyam Saini)

 - replace the bus dma mask with a limit (Nicolas Saenz Julienne)

 - merge the remapping helpers into the main dma-direct flow (me)

 - switch xtensa to the generic dma remap handling (me)

 - various cleanups around dma_capable (me)

 - remove unused dev arguments to various dma-noncoherent helpers (me)

* 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux:

* tag 'dma-mapping-5.5' of git://git.infradead.org/users/hch/dma-mapping: (22 commits)
  dma-mapping: treat dev->bus_dma_mask as a DMA limit
  dma-direct: exclude dma_direct_map_resource from the min_low_pfn check
  dma-direct: don't check swiotlb=force in dma_direct_map_resource
  dma-debug: clean up put_hash_bucket()
  powerpc: remove support for NULL dev in __phys_to_dma / __dma_to_phys
  dma-direct: avoid a forward declaration for phys_to_dma
  dma-direct: unify the dma_capable definitions
  dma-mapping: drop the dev argument to arch_sync_dma_for_*
  x86/PCI: sta2x11: use default DMA address translation
  dma-direct: check for overflows on 32 bit DMA addresses
  dma-debug: increase HASH_SIZE
  dma-debug: reorder struct dma_debug_entry fields
  xtensa: use the generic uncached segment support
  dma-mapping: merge the generic remapping helpers into dma-direct
  dma-direct: provide mmap and get_sgtable method overrides
  dma-direct: remove the dma_handle argument to __dma_direct_alloc_pages
  dma-direct: remove __dma_direct_free_pages
  usb: core: Remove redundant vmap checks
  kernel: dma-contiguous: mark CMA parameters __initdata/__initconst
  dma-debug: add a schedule point in debug_dma_dump_mappings()
  ...

5 files changed, 48 insertions, 33 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index f05c5b92e61f..e226030c1df3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1213,8 +1213,8 @@ 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.
@@ -1300,7 +1300,7 @@ 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 d03af3605460..24b8684aa21d 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -3,6 +3,7 @@
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
+#include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
 
 extern unsigned int zone_dma_bits;
@@ -23,15 +24,6 @@ static inline phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dev_addr)
 
 	return paddr + ((phys_addr_t)dev->dma_pfn_offset << PAGE_SHIFT);
 }
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <=
-		min_not_zero(*dev->dma_mask, dev->bus_dma_mask);
-}
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
 #ifdef CONFIG_ARCH_HAS_FORCE_DMA_UNENCRYPTED
@@ -59,6 +51,21 @@ 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,
+		bool is_ram)
+{
+	dma_addr_t end = addr + size - 1;
+
+	if (!dev->dma_mask)
+		return false;
+
+	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;
+
+	return end <= min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
+}
+
 u64 dma_direct_get_required_mask(struct device *dev);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
@@ -69,7 +76,13 @@ 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);
-void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page);
+		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-mapping.h b/include/linux/dma-mapping.h
index 8023071d6903..330ad58fbf4d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -159,7 +159,7 @@ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
 int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
 			    void *cpu_addr, size_t size, int *ret);
 
-void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle);
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size, dma_addr_t *dma_handle);
 int dma_release_from_global_coherent(int order, void *vaddr);
 int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
 				  size_t size, int *ret);
@@ -169,7 +169,7 @@ int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
 #define dma_release_from_dev_coherent(dev, order, vaddr) (0)
 #define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
 
-static inline void *dma_alloc_from_global_coherent(ssize_t size,
+static inline void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
 						   dma_addr_t *dma_handle)
 {
 	return NULL;
@@ -580,6 +580,10 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
+	/* DMA must never operate on areas that might be remapped. */
+	if (dev_WARN_ONCE(dev, is_vmalloc_addr(ptr),
+			  "rejecting DMA map of vmalloc memory\n"))
+		return DMA_MAPPING_ERROR;
 	debug_dma_map_single(dev, ptr, size);
 	return dma_map_page_attrs(dev, virt_to_page(ptr), offset_in_page(ptr),
 			size, dir, attrs);
@@ -690,7 +694,7 @@ 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/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index dd3de6d88fc0..ca9b5770caee 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
 /*
@@ -75,29 +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;