diff options
| -rw-r--r-- | fs/ext4/ext4.h | 1 | ||||
| -rw-r--r-- | fs/ext4/extents.c | 12 | ||||
| -rw-r--r-- | fs/ext4/fast_commit.c | 3 | ||||
| -rw-r--r-- | fs/ext4/inode.c | 28 |
4 files changed, 32 insertions, 12 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 84cbe8024f1e..3e724def1b06 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -741,6 +741,7 @@ enum { #define EXT4_EX_NOCACHE 0x40000000 #define EXT4_EX_FORCE_CACHE 0x20000000 #define EXT4_EX_NOFAIL 0x10000000 +#define EXT4_EX_FILTER 0x70000000 /* * Flags used by ext4_free_blocks diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d8eac736cc9a..8a5724b2dc51 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4202,7 +4202,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ - path = ext4_find_extent(inode, map->m_lblk, NULL, 0); + path = ext4_find_extent(inode, map->m_lblk, NULL, flags); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; @@ -4315,7 +4315,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, goto out; ar.lright = map->m_lblk; err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, - &ex2, 0); + &ex2, flags); if (err < 0) goto out; @@ -4820,8 +4820,14 @@ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, break; } } + /* + * Do not cache any unrelated extents, as it does not hold the + * i_rwsem or invalidate_lock, which could corrupt the extent + * status tree. + */ ret = ext4_map_blocks(handle, inode, &map, - EXT4_GET_BLOCKS_IO_CONVERT_EXT); + EXT4_GET_BLOCKS_IO_CONVERT_EXT | + EXT4_EX_NOCACHE); if (ret <= 0) ext4_warning(inode->i_sb, "inode #%lu: block %u: len %u: " diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index bfe5b3c40078..1392241de5e6 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -918,7 +918,8 @@ static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc) map.m_lblk = cur_lblk_off; map.m_len = new_blk_size - cur_lblk_off + 1; ret = ext4_map_blocks(NULL, inode, &map, - EXT4_GET_BLOCKS_IO_SUBMIT); + EXT4_GET_BLOCKS_IO_SUBMIT | + EXT4_EX_NOCACHE); if (ret < 0) return -ECANCELED; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 3005053e92a7..8c0d6fa58f26 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -463,15 +463,16 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, #endif /* ES_AGGRESSIVE_TEST */ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode, - struct ext4_map_blocks *map) + struct ext4_map_blocks *map, int flags) { unsigned int status; int retval; + flags &= EXT4_EX_FILTER; if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - retval = ext4_ext_map_blocks(handle, inode, map, 0); + retval = ext4_ext_map_blocks(handle, inode, map, flags); else - retval = ext4_ind_map_blocks(handle, inode, map, 0); + retval = ext4_ind_map_blocks(handle, inode, map, flags); if (retval <= 0) return retval; @@ -622,6 +623,13 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) return -EFSCORRUPTED; + /* + * Do not allow caching of unrelated ranges of extents during I/O + * submission. + */ + if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) + WARN_ON_ONCE(!(flags & EXT4_EX_NOCACHE)); + /* Lookup extent status tree firstly */ if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) && ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { @@ -667,7 +675,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * file system block. */ down_read(&EXT4_I(inode)->i_data_sem); - retval = ext4_map_query_blocks(handle, inode, map); + retval = ext4_map_query_blocks(handle, inode, map, flags); up_read((&EXT4_I(inode)->i_data_sem)); found: @@ -1807,7 +1815,7 @@ found: if (ext4_has_inline_data(inode)) retval = 0; else - retval = ext4_map_query_blocks(NULL, inode, map); + retval = ext4_map_query_blocks(NULL, inode, map, 0); up_read(&EXT4_I(inode)->i_data_sem); if (retval) return retval < 0 ? retval : 0; @@ -1830,7 +1838,7 @@ add_delayed: goto found; } } else if (!ext4_has_inline_data(inode)) { - retval = ext4_map_query_blocks(NULL, inode, map); + retval = ext4_map_query_blocks(NULL, inode, map, 0); if (retval) { up_write(&EXT4_I(inode)->i_data_sem); return retval < 0 ? retval : 0; @@ -2214,11 +2222,15 @@ static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) * previously reserved. However we must not fail because we're in * writeback and there is nothing we can do about it so it might result * in data loss. So use reserved blocks to allocate metadata if - * possible. + * possible. In addition, do not cache any unrelated extents, as it + * only holds the folio lock but does not hold the i_rwsem or + * invalidate_lock, which could corrupt the extent status tree. */ get_blocks_flags = EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL | - EXT4_GET_BLOCKS_IO_SUBMIT; + EXT4_GET_BLOCKS_IO_SUBMIT | + EXT4_EX_NOCACHE; + dioread_nolock = ext4_should_dioread_nolock(inode); if (dioread_nolock) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; |