1 files changed, 95 insertions, 127 deletions

diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 5d205bbaafdc..7929f054dda3 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -5,15 +5,11 @@
 
 #include <linux/rbtree.h>
 #include <linux/refcount.h>
+#include <linux/fiemap.h>
+#include <linux/btrfs_tree.h>
+#include "compression.h"
 #include "ulist.h"
 
-/*
- * flags for bio submission. The high bits indicate the compression
- * type for this bio
- */
-#define EXTENT_BIO_COMPRESSED 1
-#define EXTENT_BIO_FLAG_SHIFT 16
-
 enum {
 	EXTENT_BUFFER_UPTODATE,
 	EXTENT_BUFFER_DIRTY,
@@ -29,16 +25,17 @@ enum {
 	EXTENT_BUFFER_IN_TREE,
 	/* write IO error */
 	EXTENT_BUFFER_WRITE_ERR,
+	EXTENT_BUFFER_NO_CHECK,
 };
 
 /* these are flags for __process_pages_contig */
 #define PAGE_UNLOCK		(1 << 0)
-#define PAGE_CLEAR_DIRTY	(1 << 1)
-#define PAGE_SET_WRITEBACK	(1 << 2)
-#define PAGE_END_WRITEBACK	(1 << 3)
-#define PAGE_SET_PRIVATE2	(1 << 4)
-#define PAGE_SET_ERROR		(1 << 5)
-#define PAGE_LOCK		(1 << 6)
+/* Page starts writeback, clear dirty bit and set writeback bit */
+#define PAGE_START_WRITEBACK	(1 << 1)
+#define PAGE_END_WRITEBACK	(1 << 2)
+#define PAGE_SET_ORDERED	(1 << 3)
+#define PAGE_SET_ERROR		(1 << 4)
+#define PAGE_LOCK		(1 << 5)
 
 /*
  * page->private values.  Every page that is controlled by the extent
@@ -60,30 +57,24 @@ enum {
 #define BITMAP_LAST_BYTE_MASK(nbits) \
 	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
 
+struct btrfs_bio;
 struct btrfs_root;
 struct btrfs_inode;
-struct btrfs_io_bio;
+struct btrfs_fs_info;
 struct io_failure_record;
 struct extent_io_tree;
 
-typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
-		struct bio *bio, u64 bio_offset);
+int __init extent_buffer_init_cachep(void);
+void __cold extent_buffer_free_cachep(void);
 
-struct extent_io_ops {
-	/*
-	 * The following callbacks must be always defined, the function
-	 * pointer will be called unconditionally.
-	 */
-	blk_status_t (*submit_bio_hook)(struct inode *inode, struct bio *bio,
-					int mirror_num, unsigned long bio_flags);
-	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
-				    struct page *page, u64 start, u64 end,
-				    int mirror);
-};
+typedef void (submit_bio_hook_t)(struct inode *inode, struct bio *bio,
+					 int mirror_num,
+					 enum btrfs_compression_type compress_type);
 
+typedef blk_status_t (extent_submit_bio_start_t)(struct inode *inode,
+		struct bio *bio, u64 dio_file_offset);
 
-#define INLINE_EXTENT_BUFFER_PAGES 16
-#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
+#define INLINE_EXTENT_BUFFER_PAGES     (BTRFS_MAX_METADATA_BLOCKSIZE / PAGE_SIZE)
 struct extent_buffer {
 	u64 start;
 	unsigned long len;
@@ -95,31 +86,14 @@ struct extent_buffer {
 	int read_mirror;
 	struct rcu_head rcu_head;
 	pid_t lock_owner;
-
-	int blocking_writers;
-	atomic_t blocking_readers;
-	bool lock_nested;
 	/* >= 0 if eb belongs to a log tree, -1 otherwise */
-	short log_index;
-
-	/* protects write locks */
-	rwlock_t lock;
+	s8 log_index;
 
-	/* readers use lock_wq while they wait for the write
-	 * lock holders to unlock
-	 */
-	wait_queue_head_t write_lock_wq;
+	struct rw_semaphore lock;
 
-	/* writers use read_lock_wq while they wait for readers
-	 * to unlock
-	 */
-	wait_queue_head_t read_lock_wq;
 	struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
+	struct list_head release_list;
 #ifdef CONFIG_BTRFS_DEBUG
-	int spinning_writers;
-	atomic_t spinning_readers;
-	atomic_t read_locks;
-	int write_locks;
 	struct list_head leak_list;
 #endif
 };
@@ -129,7 +103,7 @@ struct extent_buffer {
  */
 struct extent_changeset {
 	/* How many bytes are set/cleared in this operation */
-	unsigned int bytes_changed;
+	u64 bytes_changed;
 
 	/* Changed ranges */
 	struct ulist range_changed;
@@ -169,48 +143,30 @@ static inline void extent_changeset_free(struct extent_changeset *changeset)
 	kfree(changeset);
 }
 
-static inline void extent_set_compress_type(unsigned long *bio_flags,
-					    int compress_type)
-{
-	*bio_flags |= compress_type << EXTENT_BIO_FLAG_SHIFT;
-}
-
-static inline int extent_compress_type(unsigned long bio_flags)
-{
-	return bio_flags >> EXTENT_BIO_FLAG_SHIFT;
-}
-
 struct extent_map_tree;
 
-typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
-					  struct page *page, size_t pg_offset,
-					  u64 start, u64 len);
-
 int try_release_extent_mapping(struct page *page, gfp_t mask);
 int try_release_extent_buffer(struct page *page);
 
-int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
-			  get_extent_t *get_extent, int mirror_num);
-int extent_write_full_page(struct page *page, struct writeback_control *wbc);
-int extent_write_locked_range(struct inode *inode, u64 start, u64 end,
-			      int mode);
+int btrfs_read_folio(struct file *file, struct folio *folio);
+int extent_write_locked_range(struct inode *inode, u64 start, u64 end);
 int extent_writepages(struct address_space *mapping,
 		      struct writeback_control *wbc);
 int btree_write_cache_pages(struct address_space *mapping,
 			    struct writeback_control *wbc);
-int extent_readpages(struct address_space *mapping, struct list_head *pages,
-		     unsigned nr_pages);
-int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
-		__u64 start, __u64 len);
-void set_page_extent_mapped(struct page *page);
+void extent_readahead(struct readahead_control *rac);
+int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
+		  u64 start, u64 len);
+int set_page_extent_mapped(struct page *page);
+void clear_page_extent_mapped(struct page *page);
 
 struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
-					  u64 start);
+					  u64 start, u64 owner_root, int level);
 struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len);
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						u64 start);
-struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
+struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src);
 struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
 					 u64 start);
 void free_extent_buffer(struct extent_buffer *eb);
@@ -221,14 +177,23 @@ void free_extent_buffer_stale(struct extent_buffer *eb);
 int read_extent_buffer_pages(struct extent_buffer *eb, int wait,
 			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
+void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
+				u64 bytenr, u64 owner_root, u64 gen, int level);
+void btrfs_readahead_node_child(struct extent_buffer *node, int slot);
 
 static inline int num_extent_pages(const struct extent_buffer *eb)
 {
-	return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
-	       (eb->start >> PAGE_SHIFT);
+	/*
+	 * For sectorsize == PAGE_SIZE case, since nodesize is always aligned to
+	 * sectorsize, it's just eb->len >> PAGE_SHIFT.
+	 *
+	 * For sectorsize < PAGE_SIZE case, we could have nodesize < PAGE_SIZE,
+	 * thus have to ensure we get at least one page.
+	 */
+	return (eb->len >> PAGE_SHIFT) ?: 1;
 }
 
-static inline int extent_buffer_uptodate(struct extent_buffer *eb)
+static inline int extent_buffer_uptodate(const struct extent_buffer *eb)
 {
 	return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 }
@@ -238,86 +203,82 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv,
 void read_extent_buffer(const struct extent_buffer *eb, void *dst,
 			unsigned long start,
 			unsigned long len);
-int read_extent_buffer_to_user(const struct extent_buffer *eb,
-			       void __user *dst, unsigned long start,
-			       unsigned long len);
-void write_extent_buffer_fsid(struct extent_buffer *eb, const void *src);
-void write_extent_buffer_chunk_tree_uuid(struct extent_buffer *eb,
+int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb,
+				       void __user *dst, unsigned long start,
+				       unsigned long len);
+void write_extent_buffer_fsid(const struct extent_buffer *eb, const void *src);
+void write_extent_buffer_chunk_tree_uuid(const struct extent_buffer *eb,
 		const void *src);
-void write_extent_buffer(struct extent_buffer *eb, const void *src,
+void write_extent_buffer(const struct extent_buffer *eb, const void *src,
 			 unsigned long start, unsigned long len);
-void copy_extent_buffer_full(struct extent_buffer *dst,
-			     struct extent_buffer *src);
-void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
+void copy_extent_buffer_full(const struct extent_buffer *dst,
+			     const struct extent_buffer *src);
+void copy_extent_buffer(const struct extent_buffer *dst,
+			const struct extent_buffer *src,
 			unsigned long dst_offset, unsigned long src_offset,
 			unsigned long len);
-void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
-			   unsigned long src_offset, unsigned long len);
-void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
-			   unsigned long src_offset, unsigned long len);
-void memzero_extent_buffer(struct extent_buffer *eb, unsigned long start,
+void memcpy_extent_buffer(const struct extent_buffer *dst,
+			  unsigned long dst_offset, unsigned long src_offset,
+			  unsigned long len);
+void memmove_extent_buffer(const struct extent_buffer *dst,
+			   unsigned long dst_offset, unsigned long src_offset,
+			   unsigned long len);
+void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start,
 			   unsigned long len);
-int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
+int extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start,
 			   unsigned long pos);
-void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
+void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start,
 			      unsigned long pos, unsigned long len);
-void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
-				unsigned long pos, unsigned long len);
-void clear_extent_buffer_dirty(struct extent_buffer *eb);
+void extent_buffer_bitmap_clear(const struct extent_buffer *eb,
+				unsigned long start, unsigned long pos,
+				unsigned long len);
+void clear_extent_buffer_dirty(const struct extent_buffer *eb);
 bool set_extent_buffer_dirty(struct extent_buffer *eb);
 void set_extent_buffer_uptodate(struct extent_buffer *eb);
 void clear_extent_buffer_uptodate(struct extent_buffer *eb);
-int extent_buffer_under_io(struct extent_buffer *eb);
-int map_private_extent_buffer(const struct extent_buffer *eb,
-			      unsigned long offset, unsigned long min_len,
-			      char **map, unsigned long *map_start,
-			      unsigned long *map_len);
+int extent_buffer_under_io(const struct extent_buffer *eb);
 void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
 void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
-void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 				  struct page *locked_page,
-				  unsigned bits_to_clear,
-				  unsigned long page_ops);
-struct bio *btrfs_bio_alloc(u64 first_byte);
-struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs);
-struct bio *btrfs_bio_clone(struct bio *bio);
-struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size);
+				  u32 bits_to_clear, unsigned long page_ops);
+int extent_invalidate_folio(struct extent_io_tree *tree,
+			    struct folio *folio, size_t offset);
 
-struct btrfs_fs_info;
-struct btrfs_inode;
+int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array);
 
-int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
-		      u64 length, u64 logical, struct page *page,
-		      unsigned int pg_offset, int mirror_num);
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
-int btrfs_repair_eb_io_failure(struct extent_buffer *eb, int mirror_num);
+int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num);
 
 /*
  * When IO fails, either with EIO or csum verification fails, we
  * try other mirrors that might have a good copy of the data.  This
  * io_failure_record is used to record state as we go through all the
- * mirrors.  If another mirror has good data, the page is set up to date
+ * mirrors.  If another mirror has good data, the sector is set up to date
  * and things continue.  If a good mirror can't be found, the original
  * bio end_io callback is called to indicate things have failed.
  */
 struct io_failure_record {
+	/* Use rb_simple_node for search/insert */
+	struct {
+		struct rb_node rb_node;
+		u64 bytenr;
+	};
 	struct page *page;
-	u64 start;
 	u64 len;
 	u64 logical;
-	unsigned long bio_flags;
 	int this_mirror;
 	int failed_mirror;
-	int in_validation;
+	int num_copies;
 };
 
+int btrfs_repair_one_sector(struct inode *inode, struct btrfs_bio *failed_bbio,
+			    u32 bio_offset, struct page *page, unsigned int pgoff,
+			    submit_bio_hook_t *submit_bio_hook);
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end);
+int btrfs_clean_io_failure(struct btrfs_inode *inode, u64 start,
+			   struct page *page, unsigned int pg_offset);
 
-bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
-			    struct io_failure_record *failrec, int fail_mirror);
-struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
-				    struct io_failure_record *failrec,
-				    struct page *page, int pg_offset, int icsum,
-				    bio_end_io_t *endio_func, void *data);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 bool find_lock_delalloc_range(struct inode *inode,
 			     struct page *locked_page, u64 *start,
@@ -325,4 +286,11 @@ bool find_lock_delalloc_range(struct inode *inode,
 #endif
 struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
 					       u64 start);
+
+#ifdef CONFIG_BTRFS_DEBUG
+void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info);
+#else
+#define btrfs_extent_buffer_leak_debug_check(fs_info)	do {} while (0)
+#endif
+
 #endif