--- zzzz-none-000/linux-3.10.107/fs/btrfs/extent_io.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/fs/btrfs/extent_io.h 2021-02-04 17:41:59.000000000 +0000 @@ -2,25 +2,26 @@ #define __EXTENTIO__ #include +#include "ulist.h" /* bits for the extent state */ -#define EXTENT_DIRTY 1 -#define EXTENT_WRITEBACK (1 << 1) -#define EXTENT_UPTODATE (1 << 2) -#define EXTENT_LOCKED (1 << 3) -#define EXTENT_NEW (1 << 4) -#define EXTENT_DELALLOC (1 << 5) -#define EXTENT_DEFRAG (1 << 6) -#define EXTENT_DEFRAG_DONE (1 << 7) -#define EXTENT_BUFFER_FILLED (1 << 8) -#define EXTENT_BOUNDARY (1 << 9) -#define EXTENT_NODATASUM (1 << 10) -#define EXTENT_DO_ACCOUNTING (1 << 11) -#define EXTENT_FIRST_DELALLOC (1 << 12) -#define EXTENT_NEED_WAIT (1 << 13) -#define EXTENT_DAMAGED (1 << 14) -#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) -#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) +#define EXTENT_DIRTY (1U << 0) +#define EXTENT_WRITEBACK (1U << 1) +#define EXTENT_UPTODATE (1U << 2) +#define EXTENT_LOCKED (1U << 3) +#define EXTENT_NEW (1U << 4) +#define EXTENT_DELALLOC (1U << 5) +#define EXTENT_DEFRAG (1U << 6) +#define EXTENT_BOUNDARY (1U << 9) +#define EXTENT_NODATASUM (1U << 10) +#define EXTENT_DO_ACCOUNTING (1U << 11) +#define EXTENT_FIRST_DELALLOC (1U << 12) +#define EXTENT_NEED_WAIT (1U << 13) +#define EXTENT_DAMAGED (1U << 14) +#define EXTENT_NORESERVE (1U << 15) +#define EXTENT_QGROUP_RESERVED (1U << 16) +#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) +#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) /* * flags for bio submission. The high bits indicate the compression @@ -28,39 +29,39 @@ */ #define EXTENT_BIO_COMPRESSED 1 #define EXTENT_BIO_TREE_LOG 2 +#define EXTENT_BIO_PARENT_LOCKED 4 #define EXTENT_BIO_FLAG_SHIFT 16 /* these are bit numbers for test/set bit */ #define EXTENT_BUFFER_UPTODATE 0 -#define EXTENT_BUFFER_BLOCKING 1 #define EXTENT_BUFFER_DIRTY 2 #define EXTENT_BUFFER_CORRUPT 3 #define EXTENT_BUFFER_READAHEAD 4 /* this got triggered by readahead */ #define EXTENT_BUFFER_TREE_REF 5 #define EXTENT_BUFFER_STALE 6 #define EXTENT_BUFFER_WRITEBACK 7 -#define EXTENT_BUFFER_IOERR 8 +#define EXTENT_BUFFER_READ_ERR 8 /* read IO error */ #define EXTENT_BUFFER_DUMMY 9 +#define EXTENT_BUFFER_IN_TREE 10 +#define EXTENT_BUFFER_WRITE_ERR 11 /* write IO error */ /* these are flags for extent_clear_unlock_delalloc */ -#define EXTENT_CLEAR_UNLOCK_PAGE 0x1 -#define EXTENT_CLEAR_UNLOCK 0x2 -#define EXTENT_CLEAR_DELALLOC 0x4 -#define EXTENT_CLEAR_DIRTY 0x8 -#define EXTENT_SET_WRITEBACK 0x10 -#define EXTENT_END_WRITEBACK 0x20 -#define EXTENT_SET_PRIVATE2 0x40 -#define EXTENT_CLEAR_ACCOUNTING 0x80 +#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) /* * page->private values. Every page that is controlled by the extent * map has page->private set to one. */ #define EXTENT_PAGE_PRIVATE 1 -#define EXTENT_PAGE_PRIVATE_FIRST_PAGE 3 struct extent_state; struct btrfs_root; +struct btrfs_io_bio; typedef int (extent_submit_bio_hook_t)(struct inode *inode, int rw, struct bio *bio, int mirror_num, @@ -76,14 +77,15 @@ size_t size, struct bio *bio, unsigned long bio_flags); int (*readpage_io_failed_hook)(struct page *page, int failed_mirror); - int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end, - struct extent_state *state, int mirror); + int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset, + struct page *page, u64 start, u64 end, + int mirror); int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); void (*set_bit_hook)(struct inode *inode, struct extent_state *state, - unsigned long *bits); + unsigned *bits); void (*clear_bit_hook)(struct inode *inode, struct extent_state *state, - unsigned long *bits); + unsigned *bits); void (*merge_extent_hook)(struct inode *inode, struct extent_state *new, struct extent_state *other); @@ -93,13 +95,11 @@ struct extent_io_tree { struct rb_root state; - struct radix_tree_root buffer; struct address_space *mapping; u64 dirty_bytes; int track_uptodate; spinlock_t lock; - spinlock_t buffer_lock; - struct extent_io_ops *ops; + const struct extent_io_ops *ops; }; struct extent_state { @@ -108,10 +108,9 @@ struct rb_node rb_node; /* ADD NEW ELEMENTS AFTER THIS */ - struct extent_io_tree *tree; wait_queue_head_t wq; atomic_t refs; - unsigned long state; + unsigned state; /* for use by the FS */ u64 private; @@ -126,10 +125,8 @@ struct extent_buffer { u64 start; unsigned long len; - unsigned long map_start; - unsigned long map_len; unsigned long bflags; - struct extent_io_tree *tree; + struct btrfs_fs_info *fs_info; spinlock_t refs_lock; atomic_t refs; atomic_t io_pages; @@ -144,7 +141,9 @@ atomic_t blocking_readers; atomic_t spinning_readers; atomic_t spinning_writers; - int lock_nested; + short lock_nested; + /* >= 0 if eb belongs to a log tree, -1 otherwise */ + short log_index; /* protects write locks */ rwlock_t lock; @@ -158,13 +157,23 @@ * to unlock */ wait_queue_head_t read_lock_wq; - wait_queue_head_t lock_wq; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; #endif }; +/* + * Structure to record how many bytes and which ranges are set/cleared + */ +struct extent_changeset { + /* How many bytes are set/cleared in this operation */ + u64 bytes_changed; + + /* Changed ranges */ + struct ulist *range_changed; +}; + static inline void extent_set_compress_type(unsigned long *bio_flags, int compress_type) { @@ -192,33 +201,41 @@ int try_release_extent_buffer(struct page *page); int lock_extent(struct extent_io_tree *tree, u64 start, u64 end); int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, struct extent_state **cached); + unsigned bits, struct extent_state **cached); int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end); int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached, gfp_t mask); int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end); int extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, int mirror_num); +int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, + get_extent_t *get_extent, int mirror_num); int __init extent_io_init(void); void extent_io_exit(void); u64 count_range_bits(struct extent_io_tree *tree, u64 *start, u64 search_end, - u64 max_bytes, unsigned long bits, int contig); + u64 max_bytes, unsigned bits, int contig); void free_extent_state(struct extent_state *state); int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, int filled, + unsigned bits, int filled, struct extent_state *cached_state); int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, gfp_t mask); + unsigned bits, gfp_t mask); +int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, gfp_t mask, + struct extent_changeset *changeset); int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, int wake, int delete, + unsigned bits, int wake, int delete, struct extent_state **cached, gfp_t mask); int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, gfp_t mask); + unsigned bits, gfp_t mask); +int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, + unsigned bits, gfp_t mask, + struct extent_changeset *changeset); int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, u64 *failed_start, + unsigned bits, u64 *failed_start, struct extent_state **cached_state, gfp_t mask); int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); @@ -231,14 +248,14 @@ int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, - unsigned long bits, unsigned long clear_bits, + unsigned bits, unsigned clear_bits, struct extent_state **cached_state, gfp_t mask); int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); int set_extent_defrag(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); int find_first_extent_bit(struct extent_io_tree *tree, u64 start, - u64 *start_ret, u64 *end_ret, unsigned long bits, + u64 *start_ret, u64 *end_ret, unsigned bits, struct extent_state **cached_state); int extent_invalidatepage(struct extent_io_tree *tree, struct page *page, unsigned long offset); @@ -260,20 +277,16 @@ get_extent_t get_extent); int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len, get_extent_t *get_extent); -int set_state_private(struct extent_io_tree *tree, u64 start, u64 private); -void extent_cache_csums_dio(struct extent_io_tree *tree, u64 start, u32 csums[], - int count); -void extent_cache_csums(struct extent_io_tree *tree, struct bio *bio, - int bvec_index, u32 csums[], int count); int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private); void set_page_extent_mapped(struct page *page); -struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, - u64 start, unsigned long len); -struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len); +struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, + u64 start); +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 *find_extent_buffer(struct extent_io_tree *tree, - u64 start, unsigned long len); +struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, + u64 start); void free_extent_buffer(struct extent_buffer *eb); void free_extent_buffer_stale(struct extent_buffer *eb); #define WAIT_NONE 0 @@ -290,12 +303,6 @@ (start >> PAGE_CACHE_SHIFT); } -static inline struct page *extent_buffer_page(struct extent_buffer *eb, - unsigned long i) -{ - return eb->pages[i]; -} - static inline void extent_buffer_get(struct extent_buffer *eb) { atomic_inc(&eb->refs); @@ -307,6 +314,9 @@ void read_extent_buffer(struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); +int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst, + unsigned long start, + unsigned long len); void write_extent_buffer(struct extent_buffer *eb, const void *src, unsigned long start, unsigned long len); void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src, @@ -323,16 +333,17 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb); int clear_extent_buffer_uptodate(struct extent_buffer *eb); int extent_buffer_uptodate(struct extent_buffer *eb); +int extent_buffer_under_io(struct extent_buffer *eb); int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset, unsigned long min_len, char **map, unsigned long *map_start, unsigned long *map_len); int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end); int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); -int extent_clear_unlock_delalloc(struct inode *inode, - struct extent_io_tree *tree, - u64 start, u64 end, struct page *locked_page, - unsigned long op); +int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, + struct page *locked_page, + unsigned bits_to_clear, + unsigned long page_ops); struct bio * btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, gfp_t gfp_flags); @@ -341,10 +352,50 @@ struct btrfs_fs_info; -int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start, - u64 length, u64 logical, struct page *page, - int mirror_num); +int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical, + struct page *page, unsigned int pg_offset, + int mirror_num); +int clean_io_failure(struct inode *inode, u64 start, struct page *page, + unsigned int pg_offset); int end_extent_writepage(struct page *page, int err, u64 start, u64 end); int repair_eb_io_failure(struct btrfs_root *root, 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 + * 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 { + struct page *page; + u64 start; + u64 len; + u64 logical; + unsigned long bio_flags; + int this_mirror; + int failed_mirror; + int in_validation; +}; + +void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end); +int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, + struct io_failure_record **failrec_ret); +int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, + 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); +int free_io_failure(struct inode *inode, struct io_failure_record *rec); +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS +noinline u64 find_lock_delalloc_range(struct inode *inode, + struct extent_io_tree *tree, + struct page *locked_page, u64 *start, + u64 *end, u64 max_bytes); +#endif +struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, + u64 start); #endif