Merge tag 'dma-mapping-7.1-2026-04-16' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux

Pull dma-mapping updates from Marek Szyprowski:

 - added support for batched cache sync, what improves performance of
   dma_map/unmap_sg() operations on ARM64 architecture (Barry Song)

 - introduced DMA_ATTR_CC_SHARED attribute for explicitly shared memory
   used in confidential computing (Jiri Pirko)

 - refactored spaghetti-like code in drivers/of/of_reserved_mem.c and
   its clients (Marek Szyprowski, shared branch with device-tree updates
   to avoid merge conflicts)

 - prepared Contiguous Memory Allocator related code for making dma-buf
   drivers modularized (Maxime Ripard)

 - added support for benchmarking dma_map_sg() calls to tools/dma
   utility (Qinxin Xia)

* tag 'dma-mapping-7.1-2026-04-16' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux: (24 commits)
  dma-buf: heaps: system: document system_cc_shared heap
  dma-buf: heaps: system: add system_cc_shared heap for explicitly shared memory
  dma-mapping: introduce DMA_ATTR_CC_SHARED for shared memory
  mm: cma: Export cma_alloc(), cma_release() and cma_get_name()
  dma: contiguous: Export dev_get_cma_area()
  dma: contiguous: Make dma_contiguous_default_area static
  dma: contiguous: Make dev_get_cma_area() a proper function
  dma: contiguous: Turn heap registration logic around
  of: reserved_mem: rework fdt_init_reserved_mem_node()
  of: reserved_mem: clarify fdt_scan_reserved_mem*() functions
  of: reserved_mem: rearrange code a bit
  of: reserved_mem: replace CMA quirks by generic methods
  of: reserved_mem: switch to ops based OF_DECLARE()
  of: reserved_mem: use -ENODEV instead of -ENOENT
  of: reserved_mem: remove fdt node from the structure
  dma-mapping: fix false kernel-doc comment marker
  dma-mapping: Support batch mode for dma_direct_{map,unmap}_sg
  dma-mapping: Separate DMA sync issuing and completion waiting
  arm64: Provide dcache_inval_poc_nosync helper
  arm64: Provide dcache_clean_poc_nosync helper
  ...

7 files changed, 45 insertions, 48 deletions

diff --git a/include/linux/cma.h b/include/linux/cma.h
index d0793eaaadaa..8555d38a97b1 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -61,14 +61,4 @@ extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data)
 extern bool cma_intersects(struct cma *cma, unsigned long start, unsigned long end);
 
 extern void cma_reserve_pages_on_error(struct cma *cma);
-
-#ifdef CONFIG_DMA_CMA
-extern bool cma_skip_dt_default_reserved_mem(void);
-#else
-static inline bool cma_skip_dt_default_reserved_mem(void)
-{
-	return false;
-}
-#endif
-
 #endif
diff --git a/include/linux/dma-buf/heaps/cma.h b/include/linux/dma-buf/heaps/cma.h
deleted file mode 100644
index e751479e21e7..000000000000
--- a/include/linux/dma-buf/heaps/cma.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef DMA_BUF_HEAP_CMA_H_
-#define DMA_BUF_HEAP_CMA_H_
-
-struct cma;
-
-#ifdef CONFIG_DMABUF_HEAPS_CMA
-int dma_heap_cma_register_heap(struct cma *cma);
-#else
-static inline int dma_heap_cma_register_heap(struct cma *cma)
-{
-	return 0;
-}
-#endif // CONFIG_DMABUF_HEAPS_CMA
-
-#endif // DMA_BUF_HEAP_CMA_H_
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 60b63756df82..6a1832a73cad 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -91,14 +91,8 @@ static inline void set_dma_ops(struct device *dev,
 #endif /* CONFIG_ARCH_HAS_DMA_OPS */
 
 #ifdef CONFIG_DMA_CMA
-extern struct cma *dma_contiguous_default_area;
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	if (dev && dev->cma_area)
-		return dev->cma_area;
-	return dma_contiguous_default_area;
-}
+struct cma *dev_get_cma_area(struct device *dev);
+struct cma *dma_contiguous_get_area_by_idx(unsigned int idx);
 
 void dma_contiguous_reserve(phys_addr_t addr_limit);
 int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
@@ -117,6 +111,10 @@ static inline struct cma *dev_get_cma_area(struct device *dev)
 {
 	return NULL;
 }
+static inline struct cma *dma_contiguous_get_area_by_idx(unsigned int idx)
+{
+	return NULL;
+}
 static inline void dma_contiguous_reserve(phys_addr_t limit)
 {
 }
@@ -147,9 +145,6 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 {
 	__free_pages(page, get_order(size));
 }
-static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
-{
-}
 #endif /* CONFIG_DMA_CMA*/
 
 #ifdef CONFIG_DMA_DECLARE_COHERENT
@@ -361,6 +356,12 @@ static inline void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
 }
 #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
 
+#ifndef CONFIG_ARCH_HAS_BATCHED_DMA_SYNC
+static inline void arch_sync_dma_flush(void)
+{
+}
+#endif
+
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
 void arch_sync_dma_for_cpu_all(void);
 #else
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 99ef042ecdb4..db8ab24a54f4 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -9,7 +9,7 @@
 #include <linux/bug.h>
 #include <linux/cache.h>
 
-/**
+/*
  * List of possible attributes associated with a DMA mapping. The semantics
  * of each attribute should be defined in Documentation/core-api/dma-attributes.rst.
  */
@@ -92,6 +92,16 @@
  * flushing.
  */
 #define DMA_ATTR_REQUIRE_COHERENT	(1UL << 12)
+/*
+ * DMA_ATTR_CC_SHARED: Indicates the DMA mapping is shared (decrypted) for
+ * confidential computing guests. For normal system memory the caller must have
+ * called set_memory_decrypted(), and pgprot_decrypted must be used when
+ * creating CPU PTEs for the mapping. The same shared semantic may be passed
+ * to the vIOMMU when it sets up the IOPTE. For MMIO use together with
+ * DMA_ATTR_MMIO to indicate shared MMIO. Unless DMA_ATTR_MMIO is provided
+ * a struct page is required.
+ */
+#define DMA_ATTR_CC_SHARED	(1UL << 13)
 
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index f573423359f4..e8b20b29fa68 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -11,7 +11,6 @@ struct resource;
 
 struct reserved_mem {
 	const char			*name;
-	unsigned long			fdt_node;
 	const struct reserved_mem_ops	*ops;
 	phys_addr_t			base;
 	phys_addr_t			size;
@@ -19,18 +18,20 @@ struct reserved_mem {
 };
 
 struct reserved_mem_ops {
+	int	(*node_validate)(unsigned long fdt_node, phys_addr_t *align);
+	int	(*node_fixup)(unsigned long fdt_node, phys_addr_t base,
+			      phys_addr_t size);
+	int	(*node_init)(unsigned long fdt_node, struct reserved_mem *rmem);
 	int	(*device_init)(struct reserved_mem *rmem,
 			       struct device *dev);
 	void	(*device_release)(struct reserved_mem *rmem,
 				  struct device *dev);
 };
 
-typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem);
-
 #ifdef CONFIG_OF_RESERVED_MEM
 
-#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
-	_OF_DECLARE(reservedmem, name, compat, init, reservedmem_of_init_fn)
+#define RESERVEDMEM_OF_DECLARE(name, compat, ops)			\
+	_OF_DECLARE(reservedmem, name, compat, ops, struct reserved_mem_ops *)
 
 int of_reserved_mem_device_init_by_idx(struct device *dev,
 				       struct device_node *np, int idx);
@@ -48,8 +49,9 @@ int of_reserved_mem_region_count(const struct device_node *np);
 
 #else
 
-#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
-	_OF_DECLARE_STUB(reservedmem, name, compat, init, reservedmem_of_init_fn)
+#define RESERVEDMEM_OF_DECLARE(name, compat, ops)			\
+	_OF_DECLARE_STUB(reservedmem, name, compat, ops,		\
+			 struct reserved_mem_ops *)
 
 static inline int of_reserved_mem_device_init_by_idx(struct device *dev,
 					struct device_node *np, int idx)
diff --git a/include/trace/events/dma.h b/include/trace/events/dma.h
index 63597b004424..31c9ddf72c9d 100644
--- a/include/trace/events/dma.h
+++ b/include/trace/events/dma.h
@@ -34,7 +34,8 @@ TRACE_DEFINE_ENUM(DMA_NONE);
 		{ DMA_ATTR_PRIVILEGED, "PRIVILEGED" }, \
 		{ DMA_ATTR_MMIO, "MMIO" }, \
 		{ DMA_ATTR_DEBUGGING_IGNORE_CACHELINES, "CACHELINES_OVERLAP" }, \
-		{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" })
+		{ DMA_ATTR_REQUIRE_COHERENT, "REQUIRE_COHERENT" }, \
+		{ DMA_ATTR_CC_SHARED, "CC_SHARED" })
 
 DECLARE_EVENT_CLASS(dma_map,
 	TP_PROTO(struct device *dev, phys_addr_t phys_addr, dma_addr_t dma_addr,
diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.h
index c2d91088a40d..4b17829a9f17 100644
--- a/include/uapi/linux/map_benchmark.h
+++ b/include/uapi/linux/map_benchmark.h
@@ -17,6 +17,12 @@
 #define DMA_MAP_TO_DEVICE       1
 #define DMA_MAP_FROM_DEVICE     2
 
+enum {
+	DMA_MAP_BENCH_SINGLE_MODE,
+	DMA_MAP_BENCH_SG_MODE,
+	DMA_MAP_BENCH_MODE_MAX
+};
+
 struct map_benchmark {
 	__u64 avg_map_100ns; /* average map latency in 100ns */
 	__u64 map_stddev; /* standard deviation of map latency */
@@ -28,8 +34,11 @@ struct map_benchmark {
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
 	__u32 dma_trans_ns; /* time for DMA transmission in ns */
-	__u32 granule;  /* how many PAGE_SIZE will do map/unmap once a time */
-	__u8 expansion[76]; /* For future use */
+	__u32 granule;  /* - SINGLE_MODE: number of pages mapped/unmapped per operation
+			 * - SG_MODE: number of scatterlist entries (each maps one page)
+			 */
+	__u8 map_mode;  /* the mode of dma map */
+	__u8 expansion[75]; /* For future use */
 };
 
 #endif /* _UAPI_DMA_BENCHMARK_H */