Merge 42a7b4ed45 ("Merge tag 'for-5.17/io_uring-2022-01-11' of git://git.kernel.dk/linux-block") into android-mainline

Steps on the way to 5.17-rc1

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I1b575553c576938e1c3e6012c698ffc2383ae3f1

fs/io-wq.h

@@ -52,6 +52,28 @@ static inline void wq_list_add_after(struct io_wq_work_node *node,
 		list->last = node;
 }
 
+/**
+ * wq_list_merge - merge the second list to the first one.
+ * @list0: the first list
+ * @list1: the second list
+ * Return the first node after mergence.
+ */
+static inline struct io_wq_work_node *wq_list_merge(struct io_wq_work_list *list0,
+						    struct io_wq_work_list *list1)
+{
+	struct io_wq_work_node *ret;
+
+	if (!list0->first) {
+		ret = list1->first;
+	} else {
+		ret = list0->first;
+		list0->last->next = list1->first;
+	}
+	INIT_WQ_LIST(list0);
+	INIT_WQ_LIST(list1);
+	return ret;
+}
+
 static inline void wq_list_add_tail(struct io_wq_work_node *node,
 				    struct io_wq_work_list *list)
 {

include/linux/scatterlist.h

@@ -69,10 +69,27 @@ struct sg_append_table {
  * a valid sg entry, or whether it points to the start of a new scatterlist.
  * Those low bits are there for everyone! (thanks mason :-)
  */
-#define sg_is_chain(sg)		((sg)->page_link & SG_CHAIN)
-#define sg_is_last(sg)		((sg)->page_link & SG_END)
-#define sg_chain_ptr(sg)	\
-	((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END)))
+#define SG_PAGE_LINK_MASK (SG_CHAIN | SG_END)
+
+static inline unsigned int __sg_flags(struct scatterlist *sg)
+{
+	return sg->page_link & SG_PAGE_LINK_MASK;
+}
+
+static inline struct scatterlist *sg_chain_ptr(struct scatterlist *sg)
+{
+	return (struct scatterlist *)(sg->page_link & ~SG_PAGE_LINK_MASK);
+}
+
+static inline bool sg_is_chain(struct scatterlist *sg)
+{
+	return __sg_flags(sg) & SG_CHAIN;
+}
+
+static inline bool sg_is_last(struct scatterlist *sg)
+{
+	return __sg_flags(sg) & SG_END;
+}
 
 /**
  * sg_assign_page - Assign a given page to an SG entry
@@ -92,7 +109,7 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page)
 	 * In order for the low bit stealing approach to work, pages
 	 * must be aligned at a 32-bit boundary as a minimum.
 	 */
-	BUG_ON((unsigned long) page & (SG_CHAIN | SG_END));
+	BUG_ON((unsigned long)page & SG_PAGE_LINK_MASK);
 #ifdef CONFIG_DEBUG_SG
 	BUG_ON(sg_is_chain(sg));
 #endif
@@ -126,7 +143,7 @@ static inline struct page *sg_page(struct scatterlist *sg)
 #ifdef CONFIG_DEBUG_SG
 	BUG_ON(sg_is_chain(sg));
 #endif
-	return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END));
+	return (struct page *)((sg)->page_link & ~SG_PAGE_LINK_MASK);
 }
 
 /**

include/uapi/linux/io_uring.h

@@ -70,6 +70,7 @@ enum {
 	IOSQE_IO_HARDLINK_BIT,
 	IOSQE_ASYNC_BIT,
 	IOSQE_BUFFER_SELECT_BIT,
+	IOSQE_CQE_SKIP_SUCCESS_BIT,
 };
 
 /*
@@ -87,6 +88,8 @@ enum {
 #define IOSQE_ASYNC		(1U << IOSQE_ASYNC_BIT)
 /* select buffer from sqe->buf_group */
 #define IOSQE_BUFFER_SELECT	(1U << IOSQE_BUFFER_SELECT_BIT)
+/* don't post CQE if request succeeded */
+#define IOSQE_CQE_SKIP_SUCCESS	(1U << IOSQE_CQE_SKIP_SUCCESS_BIT)
 
 /*
  * io_uring_setup() flags
@@ -289,6 +292,7 @@ struct io_uring_params {
 #define IORING_FEAT_EXT_ARG		(1U << 8)
 #define IORING_FEAT_NATIVE_WORKERS	(1U << 9)
 #define IORING_FEAT_RSRC_TAGS		(1U << 10)
+#define IORING_FEAT_CQE_SKIP		(1U << 11)
 
 /*
  * io_uring_register(2) opcodes and arguments

kernel/dma/direct.c

@@ -75,15 +75,45 @@ static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 		min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
 }
 
+static int dma_set_decrypted(struct device *dev, void *vaddr, size_t size)
+{
+	if (!force_dma_unencrypted(dev))
+		return 0;
+	return set_memory_decrypted((unsigned long)vaddr, 1 << get_order(size));
+}
+
+static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size)
+{
+	int ret;
+
+	if (!force_dma_unencrypted(dev))
+		return 0;
+	ret = set_memory_encrypted((unsigned long)vaddr, 1 << get_order(size));
+	if (ret)
+		pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n");
+	return ret;
+}
+
 static void __dma_direct_free_pages(struct device *dev, struct page *page,
 				    size_t size)
 {
-	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
-	    swiotlb_free(dev, page, size))
+	if (swiotlb_free(dev, page, size))
 		return;
 	dma_free_contiguous(dev, page, size);
 }
 
+static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size)
+{
+	struct page *page = swiotlb_alloc(dev, size);
+
+	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+		swiotlb_free(dev, page, size);
+		return NULL;
+	}
+
+	return page;
+}
+
 static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		gfp_t gfp)
 {
@@ -93,18 +123,11 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
 
+	if (is_swiotlb_for_alloc(dev))
+		return dma_direct_alloc_swiotlb(dev, size);
+
 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 					   &phys_limit);
-	if (IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL) &&
-	    is_swiotlb_for_alloc(dev)) {
-		page = swiotlb_alloc(dev, size);
-		if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-			__dma_direct_free_pages(dev, page, size);
-			return NULL;
-		}
-		return page;
-	}
-
 	page = dma_alloc_contiguous(dev, size, gfp);
 	if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
 		dma_free_contiguous(dev, page, size);
@@ -133,6 +156,15 @@ again:
 	return page;
 }
 
+/*
+ * Check if a potentially blocking operations needs to dip into the atomic
+ * pools for the given device/gfp.
+ */
+static bool dma_direct_use_pool(struct device *dev, gfp_t gfp)
+{
+	return !gfpflags_allow_blocking(gfp) && !is_swiotlb_for_alloc(dev);
+}
+
 static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
@@ -140,6 +172,9 @@ static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
 	u64 phys_mask;
 	void *ret;
 
+	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_DMA_COHERENT_POOL)))
+		return NULL;
+
 	gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask,
 					   &phys_mask);
 	page = dma_alloc_from_pool(dev, size, &ret, gfp, dma_coherent_ok);
@@ -149,64 +184,103 @@ static void *dma_direct_alloc_from_pool(struct device *dev, size_t size,
 	return ret;
 }
 
+static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp)
+{
+	struct page *page;
+
+	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
+	if (!page)
+		return NULL;
+
+	/* remove any dirty cache lines on the kernel alias */
+	if (!PageHighMem(page))
+		arch_dma_prep_coherent(page, size);
+
+	/* return the page pointer as the opaque cookie */
+	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
+	return page;
+}
+
 void *dma_direct_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
+	bool remap = false, set_uncached = false;
 	struct page *page;
 	void *ret;
-	int err;
 
 	size = PAGE_ALIGN(size);
 	if (attrs & DMA_ATTR_NO_WARN)
 		gfp |= __GFP_NOWARN;
 
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) &&
-	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev)) {
-		page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
-		if (!page)
-			return NULL;
-		/* remove any dirty cache lines on the kernel alias */
-		if (!PageHighMem(page))
-			arch_dma_prep_coherent(page, size);
-		*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
-		/* return the page pointer as the opaque cookie */
-		return page;
+	    !force_dma_unencrypted(dev) && !is_swiotlb_for_alloc(dev))
+		return dma_direct_alloc_no_mapping(dev, size, dma_handle, gfp);
+
+	if (!dev_is_dma_coherent(dev)) {
+		/*
+		 * Fallback to the arch handler if it exists.  This should
+		 * eventually go away.
+		 */
+		if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
+		    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+		    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+		    !is_swiotlb_for_alloc(dev))
+			return arch_dma_alloc(dev, size, dma_handle, gfp,
+					      attrs);
+
+		/*
+		 * If there is a global pool, always allocate from it for
+		 * non-coherent devices.
+		 */
+		if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL))
+			return dma_alloc_from_global_coherent(dev, size,
+					dma_handle);
+
+		/*
+		 * Otherwise remap if the architecture is asking for it.  But
+		 * given that remapping memory is a blocking operation we'll
+		 * instead have to dip into the atomic pools.
+		 */
+		remap = IS_ENABLED(CONFIG_DMA_DIRECT_REMAP);
+		if (remap) {
+			if (dma_direct_use_pool(dev, gfp))
+				return dma_direct_alloc_from_pool(dev, size,
+						dma_handle, gfp);
+		} else {
+			if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED))
+				return NULL;
+			set_uncached = true;
+		}
 	}
 
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
-	    !dev_is_dma_coherent(dev) &&
-	    !is_swiotlb_for_alloc(dev))
-		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
-
-	if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
-	    !dev_is_dma_coherent(dev))
-		return dma_alloc_from_global_coherent(dev, size, dma_handle);
-
 	/*
-	 * Remapping or decrypting memory may block. If either is required and
-	 * we can't block, allocate the memory from the atomic pools.
-	 * If restricted DMA (i.e., is_swiotlb_for_alloc) is required, one must
-	 * set up another device coherent pool by shared-dma-pool and use
-	 * dma_alloc_from_dev_coherent instead.
+	 * Decrypting memory may block, so allocate the memory from the atomic
+	 * pools if we can't block.
 	 */
-	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
-	    !gfpflags_allow_blocking(gfp) &&
-	    (force_dma_unencrypted(dev) ||
-	     (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	      !dev_is_dma_coherent(dev))) &&
-	    !is_swiotlb_for_alloc(dev))
+	if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	/* we always manually zero the memory once we are done */
 	page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO);
 	if (!page)
 		return NULL;
+	if (PageHighMem(page)) {
+		/*
+		 * Depending on the cma= arguments and per-arch setup,
+		 * dma_alloc_contiguous could return highmem pages.
+		 * Without remapping there is no way to return them here, so
+		 * log an error and fail.
+		 */
+		if (!IS_ENABLED(CONFIG_DMA_REMAP)) {
+			dev_info(dev, "Rejecting highmem page from CMA.\n");
+			goto out_free_pages;
+		}
+		remap = true;
+		set_uncached = false;
+	}
 
-	if ((IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
-	     !dev_is_dma_coherent(dev)) ||
-	    (IS_ENABLED(CONFIG_DMA_REMAP) && PageHighMem(page))) {
+	if (remap) {
 		/* remove any dirty cache lines on the kernel alias */
 		arch_dma_prep_coherent(page, size);
 
@@ -216,56 +290,27 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 				__builtin_return_address(0));
 		if (!ret)
 			goto out_free_pages;
-		if (force_dma_unencrypted(dev)) {
-			err = set_memory_decrypted((unsigned long)ret,
-						   1 << get_order(size));
-			if (err)
-				goto out_free_pages;
-		}
-		memset(ret, 0, size);
-		goto done;
-	}
-
-	if (PageHighMem(page)) {
-		/*
-		 * Depending on the cma= arguments and per-arch setup
-		 * dma_alloc_contiguous could return highmem pages.
-		 * Without remapping there is no way to return them here,
-		 * so log an error and fail.
-		 */
-		dev_info(dev, "Rejecting highmem page from CMA.\n");
-		goto out_free_pages;
-	}
-
-	ret = page_address(page);
-	if (force_dma_unencrypted(dev)) {
-		err = set_memory_decrypted((unsigned long)ret,
-					   1 << get_order(size));
-		if (err)
+	} else {
+		ret = page_address(page);
+		if (dma_set_decrypted(dev, ret, size))
 			goto out_free_pages;
 	}
 
 	memset(ret, 0, size);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
-	    !dev_is_dma_coherent(dev)) {
+	if (set_uncached) {
 		arch_dma_prep_coherent(page, size);
 		ret = arch_dma_set_uncached(ret, size);
 		if (IS_ERR(ret))
 			goto out_encrypt_pages;
 	}
-done:
+
 	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 	return ret;
 
 out_encrypt_pages:
-	if (force_dma_unencrypted(dev)) {
-		err = set_memory_encrypted((unsigned long)page_address(page),
-					   1 << get_order(size));
-		/* If memory cannot be re-encrypted, it must be leaked */
-		if (err)
-			return NULL;
-	}
+	if (dma_set_encrypted(dev, page_address(page), size))
+		return NULL;
 out_free_pages:
 	__dma_direct_free_pages(dev, page, size);
 	return NULL;
@@ -304,13 +349,14 @@ void dma_direct_free(struct device *dev, size_t size,
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
 		return;
 
-	if (force_dma_unencrypted(dev))
-		set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
-
-	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr))
+	if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) {
 		vunmap(cpu_addr);
-	else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
-		arch_dma_clear_uncached(cpu_addr, size);
+	} else {
+		if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED))
+			arch_dma_clear_uncached(cpu_addr, size);
+		if (dma_set_encrypted(dev, cpu_addr, 1 << page_order))
+			return;
+	}
 
 	__dma_direct_free_pages(dev, dma_direct_to_page(dev, dma_addr), size);
 }
@@ -321,9 +367,7 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 	struct page *page;
 	void *ret;
 
-	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
-	    force_dma_unencrypted(dev) && !gfpflags_allow_blocking(gfp) &&
-	    !is_swiotlb_for_alloc(dev))
+	if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp))
 		return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp);
 
 	page = __dma_direct_alloc_pages(dev, size, gfp);
@@ -341,11 +385,8 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size,
 	}
 
 	ret = page_address(page);
-	if (force_dma_unencrypted(dev)) {
-		if (set_memory_decrypted((unsigned long)ret,
-				1 << get_order(size)))
-			goto out_free_pages;
-	}
+	if (dma_set_decrypted(dev, ret, size))
+		goto out_free_pages;
 	memset(ret, 0, size);
 	*dma_handle = phys_to_dma_direct(dev, page_to_phys(page));
 	return page;
@@ -366,9 +407,8 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 	    dma_free_from_pool(dev, vaddr, size))
 		return;
 
-	if (force_dma_unencrypted(dev))
-		set_memory_encrypted((unsigned long)vaddr, 1 << page_order);
-
+	if (dma_set_encrypted(dev, vaddr, 1 << page_order))
+		return;
 	__dma_direct_free_pages(dev, page, size);
 }