From 96c36eaa7730081e5c946819e4dfad0f432c70f7 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 12 Dec 2023 15:54:10 +1030 Subject: 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: 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 Signed-off-by: David Sterba --- fs/btrfs/bio.c | 15 +++++++++++---- fs/btrfs/bio.h | 4 ++-- fs/btrfs/disk-io.c | 13 +++++++------ 3 files changed, 20 insertions(+), 12 deletions(-) (limited to 'fs') 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? */ diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h index ca79decee060..bbaed317161a 100644 --- a/fs/btrfs/bio.h +++ b/fs/btrfs/bio.h @@ -105,7 +105,7 @@ void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status); void btrfs_submit_bio(struct btrfs_bio *bbio, int mirror_num); void btrfs_submit_repair_write(struct btrfs_bio *bbio, int mirror_num, bool dev_replace); 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); #endif diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 2c83da36a9c7..c6907d533fe8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -183,21 +183,22 @@ static int btrfs_repair_eb_io_failure(const struct extent_buffer *eb, int mirror_num) { struct btrfs_fs_info *fs_info = eb->fs_info; - int i, num_pages = num_extent_pages(eb); + int num_folios = num_extent_folios(eb); int ret = 0; if (sb_rdonly(fs_info->sb)) return -EROFS; - for (i = 0; i < num_pages; i++) { - u64 start = max_t(u64, eb->start, folio_pos(eb->folios[i])); + for (int i = 0; i < num_folios; i++) { + struct folio *folio = eb->folios[i]; + u64 start = max_t(u64, eb->start, folio_pos(folio)); u64 end = min_t(u64, eb->start + eb->len, - folio_pos(eb->folios[i]) + PAGE_SIZE); + folio_pos(folio) + folio_size(folio)); u32 len = end - start; ret = btrfs_repair_io_failure(fs_info, 0, start, len, - start, folio_page(eb->folios[i], 0), - offset_in_page(start), mirror_num); + start, folio, offset_in_folio(folio, start), + mirror_num); if (ret) break; } -- cgit v1.2.3