ext4: initialize the percpu counters before replaying the journal

We now initialize the percpu counters before replaying the journal,
but after the journal, we recalculate the global counters, to deal
with the possibility of the per-blockgroup counts getting updated by
the journal replay.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4d7ef31eacb1e47d11dc51409cb5a02d275a7f70..04352e9729d0d3c9f32fd04434706ce4d22c95e4 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3347,6 +3347,24 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
        get_random_bytes(&sbi->s_next_generation, sizeof(u32));
        spin_lock_init(&sbi->s_next_gen_lock);
 
+       err = percpu_counter_init(&sbi->s_freeblocks_counter,
+                       ext4_count_free_blocks(sb));
+       if (!err) {
+               err = percpu_counter_init(&sbi->s_freeinodes_counter,
+                               ext4_count_free_inodes(sb));
+       }
+       if (!err) {
+               err = percpu_counter_init(&sbi->s_dirs_counter,
+                               ext4_count_dirs(sb));
+       }
+       if (!err) {
+               err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
+       }
+       if (err) {
+               ext4_msg(sb, KERN_ERR, "insufficient memory");
+               goto failed_mount3;
+       }
+
        sbi->s_stripe = ext4_get_stripe_size(sbi);
        sbi->s_max_writeback_mb_bump = 128;
 
@@ -3445,22 +3463,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
        }
        set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
 
-no_journal:
-       err = percpu_counter_init(&sbi->s_freeblocks_counter,
-                                 ext4_count_free_blocks(sb));
-       if (!err)
-               err = percpu_counter_init(&sbi->s_freeinodes_counter,
-                                         ext4_count_free_inodes(sb));
-       if (!err)
-               err = percpu_counter_init(&sbi->s_dirs_counter,
-                                         ext4_count_dirs(sb));
-       if (!err)
-               err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0);
-       if (err) {
-               ext4_msg(sb, KERN_ERR, "insufficient memory");
-               goto failed_mount_wq;
-       }
+       /*
+        * The journal may have updated the bg summary counts, so we
+        * need to update the global counters.
+        */
+       percpu_counter_set(&sbi->s_freeblocks_counter,
+                          ext4_count_free_blocks(sb));
+       percpu_counter_set(&sbi->s_freeinodes_counter,
+                          ext4_count_free_inodes(sb));
+       percpu_counter_set(&sbi->s_dirs_counter,
+                          ext4_count_dirs(sb));
+       percpu_counter_set(&sbi->s_dirtyblocks_counter, 0);
 
+no_journal:
        EXT4_SB(sb)->dio_unwritten_wq = create_workqueue("ext4-dio-unwritten");
        if (!EXT4_SB(sb)->dio_unwritten_wq) {
                printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n");
@@ -3610,10 +3625,6 @@ failed_mount_wq:
                jbd2_journal_destroy(sbi->s_journal);
                sbi->s_journal = NULL;
        }
-       percpu_counter_destroy(&sbi->s_freeblocks_counter);
-       percpu_counter_destroy(&sbi->s_freeinodes_counter);
-       percpu_counter_destroy(&sbi->s_dirs_counter);
-       percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount3:
        if (sbi->s_flex_groups) {
                if (is_vmalloc_addr(sbi->s_flex_groups))
@@ -3621,6 +3632,10 @@ failed_mount3:
                else
                        kfree(sbi->s_flex_groups);
        }
+       percpu_counter_destroy(&sbi->s_freeblocks_counter);
+       percpu_counter_destroy(&sbi->s_freeinodes_counter);
+       percpu_counter_destroy(&sbi->s_dirs_counter);
+       percpu_counter_destroy(&sbi->s_dirtyblocks_counter);
 failed_mount2:
        for (i = 0; i < db_count; i++)
                brelse(sbi->s_group_desc[i]);
@@ -3948,13 +3963,11 @@ static int ext4_commit_super(struct super_block *sb, int sync)
        else
                es->s_kbytes_written =
                        cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
-       if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeblocks_counter))
-               ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
-                                       &EXT4_SB(sb)->s_freeblocks_counter));
-       if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
-               es->s_free_inodes_count =
-                       cpu_to_le32(percpu_counter_sum_positive(
-                                       &EXT4_SB(sb)->s_freeinodes_counter));
+       ext4_free_blocks_count_set(es, percpu_counter_sum_positive(
+                                          &EXT4_SB(sb)->s_freeblocks_counter));
+       es->s_free_inodes_count =
+               cpu_to_le32(percpu_counter_sum_positive(
+                               &EXT4_SB(sb)->s_freeinodes_counter));
        sb->s_dirt = 0;
        BUFFER_TRACE(sbh, "marking dirty");
        mark_buffer_dirty(sbh);