diff options
author | Ritesh Harjani <riteshh@linux.ibm.com> | 2022-02-16 12:32:44 +0530 |
---|---|---|
committer | Theodore Ts'o <tytso@mit.edu> | 2022-02-25 21:34:56 -0500 |
commit | bfdc502a4a4c058bf4cbb1df0c297761d528f54d (patch) | |
tree | a89a0ca75dc97385756d34f0f7ff4cf93329b513 /fs/ext4/mballoc.c | |
parent | a5c0e2fdf7cea535ba03259894dc184e5a4c2800 (diff) | |
download | linux-stable-bfdc502a4a4c058bf4cbb1df0c297761d528f54d.tar.gz linux-stable-bfdc502a4a4c058bf4cbb1df0c297761d528f54d.tar.bz2 linux-stable-bfdc502a4a4c058bf4cbb1df0c297761d528f54d.zip |
ext4: fix ext4_mb_mark_bb() with flex_bg with fast_commit
In case of flex_bg feature (which is by default enabled), extents for
any given inode might span across blocks from two different block group.
ext4_mb_mark_bb() only reads the buffer_head of block bitmap once for the
starting block group, but it fails to read it again when the extent length
boundary overflows to another block group. Then in this below loop it
accesses memory beyond the block group bitmap buffer_head and results
into a data abort.
for (i = 0; i < clen; i++)
if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
already++;
This patch adds this functionality for checking block group boundary in
ext4_mb_mark_bb() and update the buffer_head(bitmap_bh) for every different
block group.
w/o this patch, I was easily able to hit a data access abort using Power platform.
<...>
[ 74.327662] EXT4-fs error (device loop3): ext4_mb_generate_buddy:1141: group 11, block bitmap and bg descriptor inconsistent: 21248 vs 23294 free clusters
[ 74.533214] EXT4-fs (loop3): shut down requested (2)
[ 74.536705] Aborting journal on device loop3-8.
[ 74.702705] BUG: Unable to handle kernel data access on read at 0xc00000005e980000
[ 74.703727] Faulting instruction address: 0xc0000000007bffb8
cpu 0xd: Vector: 300 (Data Access) at [c000000015db7060]
pc: c0000000007bffb8: ext4_mb_mark_bb+0x198/0x5a0
lr: c0000000007bfeec: ext4_mb_mark_bb+0xcc/0x5a0
sp: c000000015db7300
msr: 800000000280b033
dar: c00000005e980000
dsisr: 40000000
current = 0xc000000027af6880
paca = 0xc00000003ffd5200 irqmask: 0x03 irq_happened: 0x01
pid = 5167, comm = mount
<...>
enter ? for help
[c000000015db7380] c000000000782708 ext4_ext_clear_bb+0x378/0x410
[c000000015db7400] c000000000813f14 ext4_fc_replay+0x1794/0x2000
[c000000015db7580] c000000000833f7c do_one_pass+0xe9c/0x12a0
[c000000015db7710] c000000000834504 jbd2_journal_recover+0x184/0x2d0
[c000000015db77c0] c000000000841398 jbd2_journal_load+0x188/0x4a0
[c000000015db7880] c000000000804de8 ext4_fill_super+0x2638/0x3e10
[c000000015db7a40] c0000000005f8404 get_tree_bdev+0x2b4/0x350
[c000000015db7ae0] c0000000007ef058 ext4_get_tree+0x28/0x40
[c000000015db7b00] c0000000005f6344 vfs_get_tree+0x44/0x100
[c000000015db7b70] c00000000063c408 path_mount+0xdd8/0xe70
[c000000015db7c40] c00000000063c8f0 sys_mount+0x450/0x550
[c000000015db7d50] c000000000035770 system_call_exception+0x4a0/0x4e0
[c000000015db7e10] c00000000000c74c system_call_common+0xec/0x250
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/2609bc8f66fc15870616ee416a18a3d392a209c4.1644992609.git.riteshh@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/mballoc.c')
-rw-r--r-- | fs/ext4/mballoc.c | 131 |
1 files changed, 76 insertions, 55 deletions
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b8ffbc0ebe14..816322eddd2b 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3901,72 +3901,93 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, ext4_grpblk_t blkoff; int i, err; int already; - unsigned int clen, clen_changed; + unsigned int clen, clen_changed, thisgrp_len; - clen = EXT4_NUM_B2C(sbi, len); - - ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - bitmap_bh = ext4_read_block_bitmap(sb, group); - if (IS_ERR(bitmap_bh)) { - err = PTR_ERR(bitmap_bh); - bitmap_bh = NULL; - goto out_err; - } - - err = -EIO; - gdp = ext4_get_group_desc(sb, group, &gdp_bh); - if (!gdp) - goto out_err; + while (len > 0) { + ext4_get_group_no_and_offset(sb, block, &group, &blkoff); - ext4_lock_group(sb, group); - already = 0; - for (i = 0; i < clen; i++) - if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state) - already++; - - clen_changed = clen - already; - if (state) - ext4_set_bits(bitmap_bh->b_data, blkoff, clen); - else - mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen); - if (ext4_has_group_desc_csum(sb) && - (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { - gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); - ext4_free_group_clusters_set(sb, gdp, - ext4_free_clusters_after_init(sb, - group, gdp)); - } - if (state) - clen = ext4_free_group_clusters(sb, gdp) - clen_changed; - else - clen = ext4_free_group_clusters(sb, gdp) + clen_changed; + /* + * Check to see if we are freeing blocks across a group + * boundary. + * In case of flex_bg, this can happen that (block, len) may + * span across more than one group. In that case we need to + * get the corresponding group metadata to work with. + * For this we have goto again loop. + */ + thisgrp_len = min_t(unsigned int, (unsigned int)len, + EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff)); + clen = EXT4_NUM_B2C(sbi, thisgrp_len); - ext4_free_group_clusters_set(sb, gdp, clen); - ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); - ext4_group_desc_csum_set(sb, group, gdp); + bitmap_bh = ext4_read_block_bitmap(sb, group); + if (IS_ERR(bitmap_bh)) { + err = PTR_ERR(bitmap_bh); + bitmap_bh = NULL; + break; + } - ext4_unlock_group(sb, group); + err = -EIO; + gdp = ext4_get_group_desc(sb, group, &gdp_bh); + if (!gdp) + break; - if (sbi->s_log_groups_per_flex) { - ext4_group_t flex_group = ext4_flex_group(sbi, group); - struct flex_groups *fg = sbi_array_rcu_deref(sbi, - s_flex_groups, flex_group); + ext4_lock_group(sb, group); + already = 0; + for (i = 0; i < clen; i++) + if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == + !state) + already++; + clen_changed = clen - already; if (state) - atomic64_sub(clen_changed, &fg->free_clusters); + ext4_set_bits(bitmap_bh->b_data, blkoff, clen); else - atomic64_add(clen_changed, &fg->free_clusters); + mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen); + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) { + gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); + ext4_free_group_clusters_set(sb, gdp, + ext4_free_clusters_after_init(sb, group, gdp)); + } + if (state) + clen = ext4_free_group_clusters(sb, gdp) - clen_changed; + else + clen = ext4_free_group_clusters(sb, gdp) + clen_changed; + + ext4_free_group_clusters_set(sb, gdp, clen); + ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh); + ext4_group_desc_csum_set(sb, group, gdp); + + ext4_unlock_group(sb, group); + + if (sbi->s_log_groups_per_flex) { + ext4_group_t flex_group = ext4_flex_group(sbi, group); + struct flex_groups *fg = sbi_array_rcu_deref(sbi, + s_flex_groups, flex_group); + + if (state) + atomic64_sub(clen_changed, &fg->free_clusters); + else + atomic64_add(clen_changed, &fg->free_clusters); + + } + + err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); + if (err) + break; + sync_dirty_buffer(bitmap_bh); + err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); + sync_dirty_buffer(gdp_bh); + if (err) + break; + + block += thisgrp_len; + len -= thisgrp_len; + brelse(bitmap_bh); + BUG_ON(len < 0); } - err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh); if (err) - goto out_err; - sync_dirty_buffer(bitmap_bh); - err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh); - sync_dirty_buffer(gdp_bh); - -out_err: - brelse(bitmap_bh); + brelse(bitmap_bh); } /* |