Merge tag 'dma-mapping-5.13' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - add a new dma_alloc_noncontiguous API (me, Ricardo Ribalda)

 - fix a copyright notice (Hao Fang)

 - add an unlikely annotation to dma_mapping_error (Heiner Kallweit)

 - remove a pointless empty line (Wang Qing)

 - add support for multi-pages map/unmap bencharking (Xiang Chen)

* tag 'dma-mapping-5.13' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: add unlikely hint to error path in dma_mapping_error
  dma-mapping: benchmark: Add support for multi-pages map/unmap
  dma-mapping: benchmark: use the correct HiSilicon copyright
  dma-mapping: remove a pointless empty line in dma_alloc_coherent
  media: uvcvideo: Use dma_alloc_noncontiguous API
  dma-iommu: implement ->alloc_noncontiguous
  dma-iommu: refactor iommu_dma_alloc_remap
  dma-mapping: add a dma_alloc_noncontiguous API
  dma-mapping: refactor dma_{alloc,free}_pages
  dma-mapping: add a dma_mmap_pages helper

2 files changed, 153 insertions, 18 deletions

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index e0e64f8b0739..9b9af1bd6be3 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020 Hisilicon Limited.
+ * Copyright (C) 2020 HiSilicon Limited.
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
@@ -38,7 +38,8 @@ 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 */
-	__u8 expansion[80];	/* For future use */
+	__u32 granule;	/* how many PAGE_SIZE will do map/unmap once a time */
+	__u8 expansion[76];	/* For future use */
 };
 
 struct map_benchmark_data {
@@ -58,9 +59,11 @@ static int map_benchmark_thread(void *data)
 	void *buf;
 	dma_addr_t dma_addr;
 	struct map_benchmark_data *map = data;
+	int npages = map->bparam.granule;
+	u64 size = npages * PAGE_SIZE;
 	int ret = 0;
 
-	buf = (void *)__get_free_page(GFP_KERNEL);
+	buf = alloc_pages_exact(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -76,10 +79,10 @@ static int map_benchmark_thread(void *data)
 		 * 66 means evertything goes well! 66 is lucky.
 		 */
 		if (map->dir != DMA_FROM_DEVICE)
-			memset(buf, 0x66, PAGE_SIZE);
+			memset(buf, 0x66, size);
 
 		map_stime = ktime_get();
-		dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir);
+		dma_addr = dma_map_single(map->dev, buf, size, map->dir);
 		if (unlikely(dma_mapping_error(map->dev, dma_addr))) {
 			pr_err("dma_map_single failed on %s\n",
 				dev_name(map->dev));
@@ -93,7 +96,7 @@ static int map_benchmark_thread(void *data)
 		ndelay(map->bparam.dma_trans_ns);
 
 		unmap_stime = ktime_get();
-		dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);
+		dma_unmap_single(map->dev, dma_addr, size, map->dir);
 		unmap_etime = ktime_get();
 		unmap_delta = ktime_sub(unmap_etime, unmap_stime);
 
@@ -112,7 +115,7 @@ static int map_benchmark_thread(void *data)
 	}
 
 out:
-	free_page((unsigned long)buf);
+	free_pages_exact(buf, size);
 	return ret;
 }
 
@@ -203,7 +206,6 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 	struct map_benchmark_data *map = file->private_data;
 	void __user *argp = (void __user *)arg;
 	u64 old_dma_mask;
-
 	int ret;
 
 	if (copy_from_user(&map->bparam, argp, sizeof(map->bparam)))
@@ -234,6 +236,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		}
 
+		if (map->bparam.granule < 1 || map->bparam.granule > 1024) {
+			pr_err("invalid granule size\n");
+			return -EINVAL;
+		}
+
 		switch (map->bparam.dma_dir) {
 		case DMA_MAP_BIDIRECTIONAL:
 			map->dir = DMA_BIDIRECTIONAL;
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index b6a633679933..2b06a809d0b9 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -477,11 +477,10 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 }
 EXPORT_SYMBOL(dma_free_attrs);
 
-struct page *dma_alloc_pages(struct device *dev, size_t size,
+static struct page *__dma_alloc_pages(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);
-	struct page *page;
 
 	if (WARN_ON_ONCE(!dev->coherent_dma_mask))
 		return NULL;
@@ -490,33 +489,162 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 
 	size = PAGE_ALIGN(size);
 	if (dma_alloc_direct(dev, ops))
-		page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
-	else if (ops->alloc_pages)
-		page = ops->alloc_pages(dev, size, dma_handle, dir, gfp);
-	else
+		return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
+	if (!ops->alloc_pages)
 		return NULL;
+	return ops->alloc_pages(dev, size, dma_handle, dir, gfp);
+}
 
-	debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+struct page *dma_alloc_pages(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);
 
+	if (page)
+		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
 	return page;
 }
 EXPORT_SYMBOL_GPL(dma_alloc_pages);
 
-void dma_free_pages(struct device *dev, size_t size, struct page *page,
+static void __dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	size = PAGE_ALIGN(size);
-	debug_dma_unmap_page(dev, dma_handle, size, dir);
-
 	if (dma_alloc_direct(dev, ops))
 		dma_direct_free_pages(dev, size, page, dma_handle, dir);
 	else if (ops->free_pages)
 		ops->free_pages(dev, size, page, dma_handle, dir);
 }
+
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	__dma_free_pages(dev, size, page, dma_handle, dir);
+}
 EXPORT_SYMBOL_GPL(dma_free_pages);
 
+int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct page *page)
+{
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (vma->vm_pgoff >= count || vma_pages(vma) > count - vma->vm_pgoff)
+		return -ENXIO;
+	return remap_pfn_range(vma, vma->vm_start,
+			       page_to_pfn(page) + vma->vm_pgoff,
+			       vma_pages(vma) << PAGE_SHIFT, vma->vm_page_prot);
+}
+EXPORT_SYMBOL_GPL(dma_mmap_pages);
+
+static struct sg_table *alloc_single_sgt(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp)
+{
+	struct sg_table *sgt;
+	struct page *page;
+
+	sgt = kmalloc(sizeof(*sgt), gfp);
+	if (!sgt)
+		return NULL;
+	if (sg_alloc_table(sgt, 1, gfp))
+		goto out_free_sgt;
+	page = __dma_alloc_pages(dev, size, &sgt->sgl->dma_address, dir, gfp);
+	if (!page)
+		goto out_free_table;
+	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	sg_dma_len(sgt->sgl) = sgt->sgl->length;
+	return sgt;
+out_free_table:
+	sg_free_table(sgt);
+out_free_sgt:
+	kfree(sgt);
+	return NULL;
+}
+
+struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct sg_table *sgt;
+
+	if (WARN_ON_ONCE(attrs & ~DMA_ATTR_ALLOC_SINGLE_PAGES))
+		return NULL;
+
+	if (ops && ops->alloc_noncontiguous)
+		sgt = ops->alloc_noncontiguous(dev, size, dir, gfp, attrs);
+	else
+		sgt = alloc_single_sgt(dev, size, dir, gfp);
+
+	if (sgt) {
+		sgt->nents = 1;
+		debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir);
+	}
+	return sgt;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_noncontiguous);
+
+static void free_single_sgt(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	__dma_free_pages(dev, size, sg_page(sgt->sgl), sgt->sgl->dma_address,
+			 dir);
+	sg_free_table(sgt);
+	kfree(sgt);
+}
+
+void dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
+	if (ops && ops->free_noncontiguous)
+		ops->free_noncontiguous(dev, size, sgt, dir);
+	else
+		free_single_sgt(dev, size, sgt, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_noncontiguous);
+
+void *dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (ops && ops->alloc_noncontiguous)
+		return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL);
+	return page_address(sg_page(sgt->sgl));
+}
+EXPORT_SYMBOL_GPL(dma_vmap_noncontiguous);
+
+void dma_vunmap_noncontiguous(struct device *dev, void *vaddr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops && ops->alloc_noncontiguous)
+		vunmap(vaddr);
+}
+EXPORT_SYMBOL_GPL(dma_vunmap_noncontiguous);
+
+int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct sg_table *sgt)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops && ops->alloc_noncontiguous) {
+		unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+		if (vma->vm_pgoff >= count ||
+		    vma_pages(vma) > count - vma->vm_pgoff)
+			return -ENXIO;
+		return vm_map_pages(vma, sgt_handle(sgt)->pages, count);
+	}
+	return dma_mmap_pages(dev, vma, size, sg_page(sgt->sgl));
+}
+EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous);
+
 int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);