1 files changed, 154 insertions, 97 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index b52f084aa643..dcc9fcdf14e4 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -6,14 +6,19 @@
 #include <linux/mm.h>
 #include <linux/radix-tree.h>
 
-/* Flag for synchronous flush */
-#define DAXDEV_F_SYNC (1UL << 0)
-
 typedef unsigned long dax_entry_t;
 
+struct dax_device;
+struct gendisk;
 struct iomap_ops;
+struct iomap_iter;
 struct iomap;
-struct dax_device;
+
+enum dax_access_mode {
+	DAX_ACCESS,
+	DAX_RECOVERY_WRITE,
+};
+
 struct dax_operations {
 	/*
 	 * direct_access: translate a device-relative
@@ -21,45 +26,42 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			void **, pfn_t *);
-	/*
-	 * Validate whether this device is usable as an fsdax backing
-	 * device.
-	 */
-	bool (*dax_supported)(struct dax_device *, struct block_device *, int,
-			sector_t, sector_t);
-	/* copy_from_iter: required operation for fs-dax direct-i/o */
-	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
-			struct iov_iter *);
-	/* copy_to_iter: required operation for fs-dax direct-i/o */
-	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
-			struct iov_iter *);
+			enum dax_access_mode, void **, pfn_t *);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
+	/*
+	 * recovery_write: recover a poisoned range by DAX device driver
+	 * capable of clearing poison.
+	 */
+	size_t (*recovery_write)(struct dax_device *dax_dev, pgoff_t pgoff,
+			void *addr, size_t bytes, struct iov_iter *iter);
 };
 
-extern struct attribute_group dax_attribute_group;
+struct dax_holder_operations {
+	/*
+	 * notify_failure - notify memory failure into inner holder device
+	 * @dax_dev: the dax device which contains the holder
+	 * @offset: offset on this dax device where memory failure occurs
+	 * @len: length of this memory failure event
+	 * @flags: action flags for memory failure handler
+	 */
+	int (*notify_failure)(struct dax_device *dax_dev, u64 offset,
+			u64 len, int mf_flags);
+};
 
 #if IS_ENABLED(CONFIG_DAX)
-struct dax_device *dax_get_by_host(const char *host);
-struct dax_device *alloc_dax(void *private, const char *host,
-		const struct dax_operations *ops, unsigned long flags);
+struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
+void *dax_holder(struct dax_device *dax_dev);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
-bool __dax_synchronous(struct dax_device *dax_dev);
-static inline bool dax_synchronous(struct dax_device *dax_dev)
-{
-	return  __dax_synchronous(dax_dev);
-}
-void __set_dax_synchronous(struct dax_device *dax_dev);
-static inline void set_dax_synchronous(struct dax_device *dax_dev)
-{
-	__set_dax_synchronous(dax_dev);
-}
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len);
+bool dax_synchronous(struct dax_device *dax_dev);
+void set_dax_nocache(struct dax_device *dax_dev);
+void set_dax_nomc(struct dax_device *dax_dev);
+void set_dax_synchronous(struct dax_device *dax_dev);
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *i);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -73,18 +75,14 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	return dax_synchronous(dax_dev);
 }
 #else
-static inline struct dax_device *dax_get_by_host(const char *host)
+static inline void *dax_holder(struct dax_device *dax_dev)
 {
 	return NULL;
 }
-static inline struct dax_device *alloc_dax(void *private, const char *host,
-		const struct dax_operations *ops, unsigned long flags)
+static inline struct dax_device *alloc_dax(void *private,
+		const struct dax_operations *ops)
 {
-	/*
-	 * Callers should check IS_ENABLED(CONFIG_DAX) to know if this
-	 * NULL is an error or expected.
-	 */
-	return NULL;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 static inline void put_dax(struct dax_device *dax_dev)
 {
@@ -103,78 +101,66 @@ static inline bool dax_synchronous(struct dax_device *dax_dev)
 {
 	return true;
 }
-static inline void set_dax_synchronous(struct dax_device *dax_dev)
+static inline void set_dax_nocache(struct dax_device *dax_dev)
 {
 }
-static inline bool dax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t len)
+static inline void set_dax_nomc(struct dax_device *dax_dev)
+{
+}
+static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
-	return false;
 }
 static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 				struct dax_device *dax_dev)
 {
 	return !(vma->vm_flags & VM_SYNC);
 }
+static inline size_t dax_recovery_write(struct dax_device *dax_dev,
+		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
+{
+	return 0;
+}
 #endif
 
 struct writeback_control;
-int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
-#if IS_ENABLED(CONFIG_FS_DAX)
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize);
-static inline bool bdev_dax_supported(struct block_device *bdev, int blocksize)
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
+int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
+void dax_remove_host(struct gendisk *disk);
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
+		void *holder, const struct dax_holder_operations *ops);
+void fs_put_dax(struct dax_device *dax_dev, void *holder);
+#else
+static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 {
-	return __bdev_dax_supported(bdev, blocksize);
+	return 0;
 }
-
-bool __generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors);
-static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
+static inline void dax_remove_host(struct gendisk *disk)
 {
-	return __generic_fsdax_supported(dax_dev, bdev, blocksize, start,
-			sectors);
 }
-
-static inline void fs_put_dax(struct dax_device *dax_dev)
+static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
+		u64 *start_off, void *holder,
+		const struct dax_holder_operations *ops)
+{
+	return NULL;
+}
+static inline void fs_put_dax(struct dax_device *dax_dev, void *holder)
 {
-	put_dax(dax_dev);
 }
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
+#if IS_ENABLED(CONFIG_FS_DAX)
 int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
 struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
-dax_entry_t dax_lock_page(struct page *page);
-void dax_unlock_page(struct page *page, dax_entry_t cookie);
+dax_entry_t dax_lock_folio(struct folio *folio);
+void dax_unlock_folio(struct folio *folio, dax_entry_t cookie);
+dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
+		unsigned long index, struct page **page);
+void dax_unlock_mapping_entry(struct address_space *mapping,
+		unsigned long index, dax_entry_t cookie);
 #else
-static inline bool bdev_dax_supported(struct block_device *bdev,
-		int blocksize)
-{
-	return false;
-}
-
-static inline bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
-{
-	return false;
-}
-
-static inline void fs_put_dax(struct dax_device *dax_dev)
-{
-}
-
-static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
-{
-	return NULL;
-}
-
 static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 {
 	return NULL;
@@ -191,18 +177,41 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping,
 	return -EOPNOTSUPP;
 }
 
-static inline dax_entry_t dax_lock_page(struct page *page)
+static inline dax_entry_t dax_lock_folio(struct folio *folio)
 {
-	if (IS_DAX(page->mapping->host))
+	if (IS_DAX(folio->mapping->host))
 		return ~0UL;
 	return 0;
 }
 
-static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
+static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie)
+{
+}
+
+static inline dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
+		unsigned long index, struct page **page)
+{
+	return 0;
+}
+
+static inline void dax_unlock_mapping_entry(struct address_space *mapping,
+		unsigned long index, dax_entry_t cookie)
 {
 }
 #endif
 
+int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
+		const struct iomap_ops *ops);
+int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		const struct iomap_ops *ops);
+int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		const struct iomap_ops *ops);
+
+static inline bool dax_page_is_idle(struct page *page)
+{
+	return page && page_ref_count(page) == 0;
+}
+
 #if IS_ENABLED(CONFIG_DAX)
 int dax_read_lock(void);
 void dax_read_unlock(int id);
@@ -216,39 +225,87 @@ static inline void dax_read_unlock(int id)
 {
 }
 #endif /* CONFIG_DAX */
+
+#if !IS_ENABLED(CONFIG_FS_DAX)
+static inline int __must_check dax_break_layout(struct inode *inode,
+			    loff_t start, loff_t end, void (cb)(struct inode *))
+{
+	return 0;
+}
+
+static inline void dax_break_layout_final(struct inode *inode)
+{
+}
+#endif
+
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		void **kaddr, pfn_t *pfn);
+		enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 			size_t nr_pages);
+int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off, u64 len,
+		int mf_flags);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
-vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
 		    pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
 vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
-		enum page_entry_size pe_size, pfn_t pfn);
+		unsigned int order, pfn_t pfn);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+void dax_delete_mapping_range(struct address_space *mapping,
+				loff_t start, loff_t end);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
+int __must_check dax_break_layout(struct inode *inode, loff_t start,
+				loff_t end, void (cb)(struct inode *));
+static inline int __must_check dax_break_layout_inode(struct inode *inode,
+						void (cb)(struct inode *))
+{
+	return dax_break_layout(inode, 0, LLONG_MAX, cb);
+}
+void dax_break_layout_final(struct inode *inode);
+int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+				  struct inode *dest, loff_t destoff,
+				  loff_t len, bool *is_same,
+				  const struct iomap_ops *ops);
+int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
+			      struct file *file_out, loff_t pos_out,
+			      loff_t *len, unsigned int remap_flags,
+			      const struct iomap_ops *ops);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);
 }
 
+/*
+ * Due to dax's memory and block duo personalities, hwpoison reporting
+ * takes into consideration which personality is presently visible.
+ * When dax acts like a block device, such as in block IO, an encounter of
+ * dax hwpoison is reported as -EIO.
+ * When dax acts like memory, such as in page fault, a detection of hwpoison
+ * is reported as -EHWPOISON which leads to VM_FAULT_HWPOISON.
+ */
+static inline int dax_mem2blk_err(int err)
+{
+	return (err == -EHWPOISON) ? -EIO : err;
+}
+
 #ifdef CONFIG_DEV_DAX_HMEM_DEVICES
-void hmem_register_device(int target_nid, struct resource *r);
+void hmem_register_resource(int target_nid, struct resource *r);
 #else
-static inline void hmem_register_device(int target_nid, struct resource *r)
+static inline void hmem_register_resource(int target_nid, struct resource *r)
 {
 }
 #endif
 
+typedef int (*walk_hmem_fn)(struct device *dev, int target_nid,
+			    const struct resource *res);
+int walk_hmem_resources(struct device *dev, walk_hmem_fn fn);
 #endif