summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
authorQu Wenruo <wqu@suse.com>2024-01-17 03:32:25 +0300
committerDavid Sterba <dsterba@suse.com>2024-01-19 01:42:06 +0300
commitf546c4282673497a06ecb6190b50ae7f6c85b02f (patch)
tree9adb938e9f1733022a660e807d8c017b4eccaed5 /fs/btrfs
parent1e61b8c672ab2f59b282c8d48a29c14b52c0f5b4 (diff)
downloadlinux-f546c4282673497a06ecb6190b50ae7f6c85b02f.tar.xz
btrfs: scrub: avoid use-after-free when chunk length is not 64K aligned
[BUG] There is a bug report that, on a ext4-converted btrfs, scrub leads to various problems, including: - "unable to find chunk map" errors BTRFS info (device vdb): scrub: started on devid 1 BTRFS critical (device vdb): unable to find chunk map for logical 2214744064 length 4096 BTRFS critical (device vdb): unable to find chunk map for logical 2214744064 length 45056 This would lead to unrepariable errors. - Use-after-free KASAN reports: ================================================================== BUG: KASAN: slab-use-after-free in __blk_rq_map_sg+0x18f/0x7c0 Read of size 8 at addr ffff8881013c9040 by task btrfs/909 CPU: 0 PID: 909 Comm: btrfs Not tainted 6.7.0-x64v3-dbg #11 c50636e9419a8354555555245df535e380563b2b Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 2023.11-2 12/24/2023 Call Trace: <TASK> dump_stack_lvl+0x43/0x60 print_report+0xcf/0x640 kasan_report+0xa6/0xd0 __blk_rq_map_sg+0x18f/0x7c0 virtblk_prep_rq.isra.0+0x215/0x6a0 [virtio_blk 19a65eeee9ae6fcf02edfad39bb9ddee07dcdaff] virtio_queue_rqs+0xc4/0x310 [virtio_blk 19a65eeee9ae6fcf02edfad39bb9ddee07dcdaff] blk_mq_flush_plug_list.part.0+0x780/0x860 __blk_flush_plug+0x1ba/0x220 blk_finish_plug+0x3b/0x60 submit_initial_group_read+0x10a/0x290 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] flush_scrub_stripes+0x38e/0x430 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] scrub_stripe+0x82a/0xae0 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] scrub_chunk+0x178/0x200 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] scrub_enumerate_chunks+0x4bc/0xa30 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] btrfs_scrub_dev+0x398/0x810 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] btrfs_ioctl+0x4b9/0x3020 [btrfs e57987a360bed82fe8756dcd3e0de5406ccfe965] __x64_sys_ioctl+0xbd/0x100 do_syscall_64+0x5d/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0x6b RIP: 0033:0x7f47e5e0952b - Crash, mostly due to above use-after-free [CAUSE] The converted fs has the following data chunk layout: item 2 key (FIRST_CHUNK_TREE CHUNK_ITEM 2214658048) itemoff 16025 itemsize 80 length 86016 owner 2 stripe_len 65536 type DATA|single For above logical bytenr 2214744064, it's at the chunk end (2214658048 + 86016 = 2214744064). This means btrfs_submit_bio() would split the bio, and trigger endio function for both of the two halves. However scrub_submit_initial_read() would only expect the endio function to be called once, not any more. This means the first endio function would already free the bbio::bio, leaving the bvec freed, thus the 2nd endio call would lead to use-after-free. [FIX] - Make sure scrub_read_endio() only updates bits in its range Since we may read less than 64K at the end of the chunk, we should not touch the bits beyond chunk boundary. - Make sure scrub_submit_initial_read() only to read the chunk range This is done by calculating the real number of sectors we need to read, and add sector-by-sector to the bio. Thankfully the scrub read repair path won't need extra fixes: - scrub_stripe_submit_repair_read() With above fixes, we won't update error bit for range beyond chunk, thus scrub_stripe_submit_repair_read() should never submit any read beyond the chunk. Reported-by: Rongrong <i@rong.moe> Fixes: e02ee89baa66 ("btrfs: scrub: switch scrub_simple_mirror() to scrub_stripe infrastructure") Tested-by: Rongrong <i@rong.moe> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by: Qu Wenruo <wqu@suse.com> Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/scrub.c29
1 files changed, 22 insertions, 7 deletions
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index a01807cbd4d4..2d81b1a18a04 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1098,12 +1098,22 @@ out:
static void scrub_read_endio(struct btrfs_bio *bbio)
{
struct scrub_stripe *stripe = bbio->private;
+ struct bio_vec *bvec;
+ int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio));
+ int num_sectors;
+ u32 bio_size = 0;
+ int i;
+
+ ASSERT(sector_nr < stripe->nr_sectors);
+ bio_for_each_bvec_all(bvec, &bbio->bio, i)
+ bio_size += bvec->bv_len;
+ num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits;
if (bbio->bio.bi_status) {
- bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
- bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors);
+ bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors);
+ bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors);
} else {
- bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
+ bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors);
}
bio_put(&bbio->bio);
if (atomic_dec_and_test(&stripe->pending_io)) {
@@ -1701,6 +1711,9 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct btrfs_bio *bbio;
+ unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+ stripe->bg->length - stripe->logical) >>
+ fs_info->sectorsize_bits;
int mirror = stripe->mirror_num;
ASSERT(stripe->bg);
@@ -1715,14 +1728,16 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info,
scrub_read_endio, stripe);
- /* Read the whole stripe. */
bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT;
- for (int i = 0; i < BTRFS_STRIPE_LEN >> PAGE_SHIFT; i++) {
+ /* Read the whole range inside the chunk boundary. */
+ for (unsigned int cur = 0; cur < nr_sectors; cur++) {
+ struct page *page = scrub_stripe_get_page(stripe, cur);
+ unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur);
int ret;
- ret = bio_add_page(&bbio->bio, stripe->pages[i], PAGE_SIZE, 0);
+ ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
/* We should have allocated enough bio vectors. */
- ASSERT(ret == PAGE_SIZE);
+ ASSERT(ret == fs_info->sectorsize);
}
atomic_inc(&stripe->pending_io);