diff options
author | Qu Wenruo <wqu@suse.com> | 2023-12-12 15:54:10 +1030 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2023-12-15 23:03:58 +0100 |
commit | 96c36eaa7730081e5c946819e4dfad0f432c70f7 (patch) | |
tree | 9e4096bfea121af932d0109534729cf55e3b808f /fs/btrfs/bio.c | |
parent | f4521b01c5246b921debc6db6f112f89f94cc61b (diff) |
btrfs: migrate btrfs_repair_io_failure() to folio interfaces
[BUG]
Test case btrfs/124 failed if larger metadata folio is enabled, the
dying message looks like this:
BTRFS error (device dm-2): bad tree block start, mirror 2 want 31686656 have 0
BTRFS info (device dm-2): read error corrected: ino 0 off 31686656 (dev /dev/mapper/test-scratch2 sector 20928)
BUG: kernel NULL pointer dereference, address: 0000000000000020
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
CPU: 6 PID: 350881 Comm: btrfs Tainted: G OE 6.7.0-rc3-custom+ #128
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS unknown 2/2/2022
RIP: 0010:btrfs_read_extent_buffer+0x106/0x180 [btrfs]
PKRU: 55555554
Call Trace:
<TASK>
read_tree_block+0x33/0xb0 [btrfs]
read_block_for_search+0x23e/0x340 [btrfs]
btrfs_search_slot+0x2f9/0xe60 [btrfs]
btrfs_lookup_csum+0x75/0x160 [btrfs]
btrfs_lookup_bio_sums+0x21a/0x560 [btrfs]
btrfs_submit_chunk+0x152/0x680 [btrfs]
btrfs_submit_bio+0x1c/0x50 [btrfs]
submit_one_bio+0x40/0x80 [btrfs]
submit_extent_page+0x158/0x390 [btrfs]
btrfs_do_readpage+0x330/0x740 [btrfs]
extent_readahead+0x38d/0x6c0 [btrfs]
read_pages+0x94/0x2c0
page_cache_ra_unbounded+0x12d/0x190
relocate_file_extent_cluster+0x7c1/0x9d0 [btrfs]
relocate_block_group+0x2d3/0x560 [btrfs]
btrfs_relocate_block_group+0x2c7/0x4b0 [btrfs]
btrfs_relocate_chunk+0x4c/0x1a0 [btrfs]
btrfs_balance+0x925/0x13c0 [btrfs]
btrfs_ioctl+0x19f1/0x25d0 [btrfs]
__x64_sys_ioctl+0x90/0xd0
do_syscall_64+0x3f/0xf0
entry_SYSCALL_64_after_hwframe+0x6e/0x76
[CAUSE]
The dying line is at btrfs_repair_io_failure() call inside
btrfs_repair_eb_io_failure().
The function is still relying on the extent buffer using page sized
folios.
When the extent buffer is using larger folio, we go into the 2nd slot of
folios[], and triggered the NULL pointer dereference.
[FIX]
Migrate btrfs_repair_io_failure() to folio interfaces.
So that when we hit a larger folio, we just submit the whole folio in
one go.
This also affects data repair path through btrfs_end_repair_bio(),
thankfully data is still fully page based, we can just add an
ASSERT(), and use page_folio() to convert the page to folio.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/bio.c')
-rw-r--r-- | fs/btrfs/bio.c | 15 |
1 files changed, 11 insertions, 4 deletions
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index 67a885d3f9a8..928f512cdb4a 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -194,6 +194,12 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio, struct bio_vec *bv = bio_first_bvec_all(&repair_bbio->bio); int mirror = repair_bbio->mirror_num; + /* + * We can only trigger this for data bio, which doesn't support larger + * folios yet. + */ + ASSERT(folio_order(page_folio(bv->bv_page)) == 0); + if (repair_bbio->bio.bi_status || !btrfs_data_csum_ok(repair_bbio, dev, 0, bv)) { bio_reset(&repair_bbio->bio, NULL, REQ_OP_READ); @@ -215,7 +221,7 @@ static void btrfs_end_repair_bio(struct btrfs_bio *repair_bbio, btrfs_repair_io_failure(fs_info, btrfs_ino(inode), repair_bbio->file_offset, fs_info->sectorsize, repair_bbio->saved_iter.bi_sector << SECTOR_SHIFT, - bv->bv_page, bv->bv_offset, mirror); + page_folio(bv->bv_page), bv->bv_offset, mirror); } while (mirror != fbio->bbio->mirror_num); done: @@ -767,8 +773,8 @@ void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num) * freeing the bio. */ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, - u64 length, u64 logical, struct page *page, - unsigned int pg_offset, int mirror_num) + u64 length, u64 logical, struct folio *folio, + unsigned int folio_offset, int mirror_num) { struct btrfs_io_stripe smap = { 0 }; struct bio_vec bvec; @@ -799,7 +805,8 @@ int btrfs_repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, bio_init(&bio, smap.dev->bdev, &bvec, 1, REQ_OP_WRITE | REQ_SYNC); bio.bi_iter.bi_sector = smap.physical >> SECTOR_SHIFT; - __bio_add_page(&bio, page, length, pg_offset); + ret = bio_add_folio(&bio, folio, length, folio_offset); + ASSERT(ret); ret = submit_bio_wait(&bio); if (ret) { /* try to remap that extent elsewhere? */ |