From: Xin Yin yinxin.x@bytedance.com
commit 599ea31d13617c5484c40cdf50d88301dc351cfc upstream.
During fast commit replay procedure, we clear inode blocks bitmap in ext4_ext_clear_bb(), this may cause ext4_mb_new_blocks_simple() allocate blocks still in use.
Make ext4_fc_record_regions() also record physical disk regions used by inodes during replay procedure. Then ext4_mb_new_blocks_simple() can excludes these blocks in use.
Signed-off-by: Xin Yin yinxin.x@bytedance.com Link: https://lore.kernel.org/r/20220110035141.1980-2-yinxin.x@bytedance.com Signed-off-by: Theodore Ts'o tytso@mit.edu Cc: stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/ext4.h | 3 +++ fs/ext4/extents.c | 4 ++++ fs/ext4/fast_commit.c | 20 +++++++++++++++----- 3 files changed, 22 insertions(+), 5 deletions(-)
--- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2936,6 +2936,9 @@ void ext4_fc_replay_cleanup(struct super int ext4_fc_commit(journal_t *journal, tid_t commit_tid); int __init ext4_fc_init_dentry_cache(void); void ext4_fc_destroy_dentry_cache(void); +int ext4_fc_record_regions(struct super_block *sb, int ino, + ext4_lblk_t lblk, ext4_fsblk_t pblk, + int len, int replay);
/* mballoc.c */ extern const struct seq_operations ext4_mb_seq_groups_ops; --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -6101,11 +6101,15 @@ int ext4_ext_clear_bb(struct inode *inod
ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 0); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + 0, path[j].p_block, 1, 1); } ext4_ext_drop_refs(path); kfree(path); } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + map.m_lblk, map.m_pblk, map.m_len, 1); } cur = cur + map.m_len; } --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1606,16 +1606,23 @@ out: }
/* - * Record physical disk regions which are in use as per fast commit area. Our - * simple replay phase allocator excludes these regions from allocation. + * Record physical disk regions which are in use as per fast commit area, + * and used by inodes during replay phase. Our simple replay phase + * allocator excludes these regions from allocation. */ -static int ext4_fc_record_regions(struct super_block *sb, int ino, - ext4_lblk_t lblk, ext4_fsblk_t pblk, int len) +int ext4_fc_record_regions(struct super_block *sb, int ino, + ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay) { struct ext4_fc_replay_state *state; struct ext4_fc_alloc_region *region;
state = &EXT4_SB(sb)->s_fc_replay_state; + /* + * during replay phase, the fc_regions_valid may not same as + * fc_regions_used, update it when do new additions. + */ + if (replay && state->fc_regions_used != state->fc_regions_valid) + state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; @@ -1633,6 +1640,9 @@ static int ext4_fc_record_regions(struct region->pblk = pblk; region->len = len;
+ if (replay) + state->fc_regions_valid++; + return 0; }
@@ -1980,7 +1990,7 @@ static int ext4_fc_replay_scan(journal_t ret = ext4_fc_record_regions(sb, le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), - ext4_ext_get_actual_len(ex)); + ext4_ext_get_actual_len(ex), 0); if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE;