dma-mapping updates for 5.12:

- add support to emulate processing delays in the DMA API benchmark
    selftest (Barry Song)
  - remove support for non-contiguous noncoherent allocations,
    which aren't used and will be replaced by a different API
 -----BEGIN PGP SIGNATURE-----
 
 iQI/BAABCgApFiEEgdbnc3r/njty3Iq9D55TZVIEUYMFAmA2A7gLHGhjaEBsc3Qu
 ZGUACgkQD55TZVIEUYMebw//bkSZ1v1FvGgMd+AQKKnNz+iNHH0MJAlEDhPCynFM
 QCPg6OtU9IU/5nmyQlO3rgZ1IW+qABCF36TqjPZar6STuTv3dzfvv9xydyOqdPNA
 ekFzc9FnjvWt4wzL+1pXiB/EfjKDudGAjlMyLhghl653HcLnLvE3LxgpfBMrUHbH
 DfSBTXt4fTK4ck8ZO6FW2LXOtLgmJvk+qglO1vs9GQv/zcRHXYkIyvqMYTlHwBlh
 Ltfl+kJzFHQ3taIo3utCeS5Qzctd6tbxy/Me4OHl2VydNAi8awQz4HX4yZyWYxl5
 WpIGhHfD9ROKnGroaEhetUO4OczOXiqYdkt6tt5iAAUW2TFA+mgbvph3+Di/zxgl
 4IxOQyhdWA38IA00YmNsoPafuuqC7WwASUfCufg+30MgHR3bpM7GyY5X84DIh3tm
 wlPJBMl2RqWnfxmmvjPYxV2wtN3TkA8KJN/xVcUE8aWL2mV50l1/nDdlvCbmjg60
 pQt1cGP8A2hODYwLHTzadm67xc0cLrkC8nQbrnDo/FAKGmDD3aHhS95TAIr+ZoeK
 cgSFHNkJ1UcJ6nosCB3/MPlIJo1noAIeJnmuOIfhJn0uIof4CGQ5XQgWmJeHFLqO
 GlwtJAN3F3db4dxMQNn5br049wob7fgFWqMPfTGy51bZ5BClUKWGSpEonavpUMd1
 oKM=
 =papz
 -----END PGP SIGNATURE-----

Merge tag 'dma-mapping-5.12' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - add support to emulate processing delays in the DMA API benchmark
   selftest (Barry Song)

 - remove support for non-contiguous noncoherent allocations, which
   aren't used and will be replaced by a different API

* tag 'dma-mapping-5.12' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: remove the {alloc,free}_noncoherent methods
  dma-mapping: benchmark: pretend DMA is transmitting

Documentation/core-api/dma-api.rst

@@ -526,46 +526,6 @@ for the kernel vs the device.
 If you don't understand how cache line coherency works between a processor and
 an I/O device, you should not be using this part of the API.
 
-::
-
-	void *
-	dma_alloc_noncoherent(struct device *dev, size_t size,
-			dma_addr_t *dma_handle, enum dma_data_direction dir,
-			gfp_t gfp)
-
-This routine allocates a region of <size> bytes of consistent memory.  It
-returns a pointer to the allocated region (in the processor's virtual address
-space) or NULL if the allocation failed.  The returned memory may or may not
-be in the kernel direct mapping.  Drivers must not call virt_to_page on
-the returned memory region.
-
-It also returns a <dma_handle> which may be cast to an unsigned integer the
-same width as the bus and given to the device as the DMA address base of
-the region.
-
-The dir parameter specified if data is read and/or written by the device,
-see dma_map_single() for details.
-
-The gfp parameter allows the caller to specify the ``GFP_`` flags (see
-kmalloc()) for the allocation, but rejects flags used to specify a memory
-zone such as GFP_DMA or GFP_HIGHMEM.
-
-Before giving the memory to the device, dma_sync_single_for_device() needs
-to be called, and before reading memory written by the device,
-dma_sync_single_for_cpu(), just like for streaming DMA mappings that are
-reused.
-
-::
-
-	void
-	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
-			dma_addr_t dma_handle, enum dma_data_direction dir)
-
-Free a region of memory previously allocated using dma_alloc_noncoherent().
-dev, size and dma_handle and dir must all be the same as those passed into
-dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
-dma_alloc_noncoherent().
-
 ::
 
 	struct page *
@@ -600,9 +560,29 @@ reused.
 			dma_addr_t dma_handle, enum dma_data_direction dir)
 
 Free a region of memory previously allocated using dma_alloc_pages().
-dev, size and dma_handle and dir must all be the same as those passed into
-dma_alloc_noncoherent().  page must be the pointer returned by
-dma_alloc_pages().
+dev, size, dma_handle and dir must all be the same as those passed into
+dma_alloc_pages().  page must be the pointer returned by dma_alloc_pages().
+
+::
+
+	void *
+	dma_alloc_noncoherent(struct device *dev, size_t size,
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp)
+
+This routine is a convenient wrapper around dma_alloc_pages that returns the
+kernel virtual address for the allocated memory instead of the page structure.
+
+::
+
+	void
+	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
+			dma_addr_t dma_handle, enum dma_data_direction dir)
+
+Free a region of memory previously allocated using dma_alloc_noncoherent().
+dev, size, dma_handle and dir must all be the same as those passed into
+dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
+dma_alloc_noncoherent().
 
 ::
 

drivers/iommu/dma-iommu.c

@@ -1187,34 +1187,6 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	return cpu_addr;
 }
 
-#ifdef CONFIG_DMA_REMAP
-static void *iommu_dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *handle, enum dma_data_direction dir, gfp_t gfp)
-{
-	if (!gfpflags_allow_blocking(gfp)) {
-		struct page *page;
-
-		page = dma_common_alloc_pages(dev, size, handle, dir, gfp);
-		if (!page)
-			return NULL;
-		return page_address(page);
-	}
-
-	return iommu_dma_alloc_remap(dev, size, handle, gfp | __GFP_ZERO,
-				     PAGE_KERNEL, 0);
-}
-
-static void iommu_dma_free_noncoherent(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t handle, enum dma_data_direction dir)
-{
-	__iommu_dma_unmap(dev, handle, size);
-	__iommu_dma_free(dev, size, cpu_addr);
-}
-#else
-#define iommu_dma_alloc_noncoherent		NULL
-#define iommu_dma_free_noncoherent		NULL
-#endif /* CONFIG_DMA_REMAP */
-
 static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs)
@@ -1285,8 +1257,6 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
 	.free_pages		= dma_common_free_pages,
-	.alloc_noncoherent	= iommu_dma_alloc_noncoherent,
-	.free_noncoherent	= iommu_dma_free_noncoherent,
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,

include/linux/dma-map-ops.h

@@ -22,11 +22,6 @@ struct dma_map_ops {
 			gfp_t gfp);
 	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
 			dma_addr_t dma_handle, enum dma_data_direction dir);
-	void *(*alloc_noncoherent)(struct device *dev, size_t size,
-			dma_addr_t *dma_handle, enum dma_data_direction dir,
-			gfp_t gfp);
-	void (*free_noncoherent)(struct device *dev, size_t size, void *vaddr,
-			dma_addr_t dma_handle, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			void *, dma_addr_t, size_t, unsigned long attrs);
 

include/linux/dma-mapping.h

@@ -263,10 +263,19 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
 void dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir);
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
-void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, enum dma_data_direction dir);
+
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
+	return page ? page_address(page) : NULL;
+}
+
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
+}
 
 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)

kernel/dma/map_benchmark.c

@@ -21,6 +21,7 @@
 #define DMA_MAP_BENCHMARK	_IOWR('d', 1, struct map_benchmark)
 #define DMA_MAP_MAX_THREADS	1024
 #define DMA_MAP_MAX_SECONDS	300
+#define DMA_MAP_MAX_TRANS_DELAY	(10 * NSEC_PER_MSEC)
 
 #define DMA_MAP_BIDIRECTIONAL	0
 #define DMA_MAP_TO_DEVICE	1
@@ -36,7 +37,8 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u8 expansion[84];	/* For future use */
+	__u32 dma_trans_ns; /* time for DMA transmission in ns */
+	__u8 expansion[80];	/* For future use */
 };
 
 struct map_benchmark_data {
@@ -87,6 +89,9 @@ static int map_benchmark_thread(void *data)
 		map_etime = ktime_get();
 		map_delta = ktime_sub(map_etime, map_stime);
 
+		/* Pretend DMA is transmitting */
+		ndelay(map->bparam.dma_trans_ns);
+
 		unmap_stime = ktime_get();
 		dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);
 		unmap_etime = ktime_get();
@@ -218,6 +223,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		}
 
+		if (map->bparam.dma_trans_ns > DMA_MAP_MAX_TRANS_DELAY) {
+			pr_err("invalid transmission delay\n");
+			return -EINVAL;
+		}
+
 		if (map->bparam.node != NUMA_NO_NODE &&
 		    !node_possible(map->bparam.node)) {
 			pr_err("invalid numa node\n");

kernel/dma/mapping.c

@@ -517,46 +517,6 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page,
 }
 EXPORT_SYMBOL_GPL(dma_free_pages);
 
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	void *vaddr;
-
-	if (!ops || !ops->alloc_noncoherent) {
-		struct page *page;
-
-		page = dma_alloc_pages(dev, size, dma_handle, dir, gfp);
-		if (!page)
-			return NULL;
-		return page_address(page);
-	}
-
-	size = PAGE_ALIGN(size);
-	vaddr = ops->alloc_noncoherent(dev, size, dma_handle, dir, gfp);
-	if (vaddr)
-		debug_dma_map_page(dev, virt_to_page(vaddr), 0, size, dir,
-				   *dma_handle);
-	return vaddr;
-}
-EXPORT_SYMBOL_GPL(dma_alloc_noncoherent);
-
-void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (!ops || !ops->free_noncoherent) {
-		dma_free_pages(dev, size, virt_to_page(vaddr), dma_handle, dir);
-		return;
-	}
-
-	size = PAGE_ALIGN(size);
-	debug_dma_unmap_page(dev, dma_handle, size, dir);
-	ops->free_noncoherent(dev, size, vaddr, dma_handle, dir);
-}
-EXPORT_SYMBOL_GPL(dma_free_noncoherent);
-
 int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);

tools/testing/selftests/dma/dma_map_benchmark.c

@@ -12,9 +12,12 @@
 #include <sys/mman.h>
 #include <linux/types.h>
 
+#define NSEC_PER_MSEC	1000000L
+
 #define DMA_MAP_BENCHMARK	_IOWR('d', 1, struct map_benchmark)
 #define DMA_MAP_MAX_THREADS	1024
 #define DMA_MAP_MAX_SECONDS     300
+#define DMA_MAP_MAX_TRANS_DELAY	(10 * NSEC_PER_MSEC)
 
 #define DMA_MAP_BIDIRECTIONAL	0
 #define DMA_MAP_TO_DEVICE	1
@@ -36,7 +39,8 @@ struct map_benchmark {
 	__s32 node; /* which numa node this benchmark will run on */
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
-	__u8 expansion[84];	/* For future use */
+	__u32 dma_trans_ns; /* time for DMA transmission in ns */
+	__u8 expansion[80];	/* For future use */
 };
 
 int main(int argc, char **argv)
@@ -46,12 +50,12 @@ int main(int argc, char **argv)
 	/* default single thread, run 20 seconds on NUMA_NO_NODE */
 	int threads = 1, seconds = 20, node = -1;
 	/* default dma mask 32bit, bidirectional DMA */
-	int bits = 32, dir = DMA_MAP_BIDIRECTIONAL;
+	int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
 
 	int cmd = DMA_MAP_BENCHMARK;
 	char *p;
 
-	while ((opt = getopt(argc, argv, "t:s:n:b:d:")) != -1) {
+	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) {
 		switch (opt) {
 		case 't':
 			threads = atoi(optarg);
@@ -68,6 +72,9 @@ int main(int argc, char **argv)
 		case 'd':
 			dir = atoi(optarg);
 			break;
+		case 'x':
+			xdelay = atoi(optarg);
+			break;
 		default:
 			return -1;
 		}
@@ -85,6 +92,12 @@ int main(int argc, char **argv)
 		exit(1);
 	}
 
+	if (xdelay < 0 || xdelay > DMA_MAP_MAX_TRANS_DELAY) {
+		fprintf(stderr, "invalid transmit delay, must be in 0-%ld\n",
+			DMA_MAP_MAX_TRANS_DELAY);
+		exit(1);
+	}
+
 	/* suppose the mininum DMA zone is 1MB in the world */
 	if (bits < 20 || bits > 64) {
 		fprintf(stderr, "invalid dma mask bit, must be in 20-64\n");
@@ -109,6 +122,8 @@ int main(int argc, char **argv)
 	map.node = node;
 	map.dma_bits = bits;
 	map.dma_dir = dir;
+	map.dma_trans_ns = xdelay;
+
 	if (ioctl(fd, cmd, &map)) {
 		perror("ioctl");
 		exit(1);