ext4: prevent used blocks from being allocated during fast commit replay

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

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 715ee206dfe123c1d445ee7ae02f1a3c70c06ff1..598ecf07652afccbd201e64a88f056c9abf94cc6 100644 (file)
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2934,6 +2934,9 @@ void ext4_fc_replay_cleanup(struct super_block *sb);
 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;

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 1077ce7e189fe776fbda6c2fdb882f98f6fed7d8..5dd13108d4b70b7a556d358bd5a598aa695bdfdc 100644 (file)
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -6093,11 +6093,15 @@ int ext4_ext_clear_bb(struct inode *inode)
 
                                        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;
        }

diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 5ae8026a0c56294de77d19a8ea88615d41cd8d62..1abe78b8d84f540edad4c87aaf16dc7247b9b064 100644 (file)
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1563,16 +1563,23 @@ 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;
@@ -1590,6 +1597,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino,
        region->pblk = pblk;
        region->len = len;
 
+       if (replay)
+               state->fc_regions_valid++;
+
        return 0;
 }
 
@@ -1937,7 +1947,7 @@ static int ext4_fc_replay_scan(journal_t *journal,
                        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;