drholy/linux-bredos
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
f18a35aaedf5331c224e49901acaa997d41a7165
linux-bredos/drivers/md
History
Mingzhe Zou b163173dbf bcache: fixup lock c->root error 
commit e34820f984 upstream.

We had a problem with io hung because it was waiting for c->root to
release the lock.

crash> cache_set.root -l cache_set.list ffffa03fde4c0050
  root = 0xffff802ef454c800
crash> btree -o 0xffff802ef454c800 | grep rw_semaphore
  [ffff802ef454c858] struct rw_semaphore lock;
crash> struct rw_semaphore ffff802ef454c858
struct rw_semaphore {
  count = {
    counter = -4294967297
  },
  wait_list = {
    next = 0xffff00006786fc28,
    prev = 0xffff00005d0efac8
  },
  wait_lock = {
    raw_lock = {
      {
        val = {
          counter = 0
        },
        {
          locked = 0 '\000',
          pending = 0 '\000'
        },
        {
          locked_pending = 0,
          tail = 0
        }
      }
    }
  },
  osq = {
    tail = {
      counter = 0
    }
  },
  owner = 0xffffa03fdc586603
}

The "counter = -4294967297" means that lock count is -1 and a write lock
is being attempted. Then, we found that there is a btree with a counter
of 1 in btree_cache_freeable.

crash> cache_set -l cache_set.list ffffa03fde4c0050 -o|grep btree_cache
  [ffffa03fde4c1140] struct list_head btree_cache;
  [ffffa03fde4c1150] struct list_head btree_cache_freeable;
  [ffffa03fde4c1160] struct list_head btree_cache_freed;
  [ffffa03fde4c1170] unsigned int btree_cache_used;
  [ffffa03fde4c1178] wait_queue_head_t btree_cache_wait;
  [ffffa03fde4c1190] struct task_struct *btree_cache_alloc_lock;
crash> list -H ffffa03fde4c1140|wc -l
973
crash> list -H ffffa03fde4c1150|wc -l
1123
crash> cache_set.btree_cache_used -l cache_set.list ffffa03fde4c0050
  btree_cache_used = 2097
crash> list -s btree -l btree.list -H ffffa03fde4c1140|grep -E -A2 "^  lock = {" > btree_cache.txt
crash> list -s btree -l btree.list -H ffffa03fde4c1150|grep -E -A2 "^  lock = {" > btree_cache_freeable.txt
[root@node-3 127.0.0.1-2023-08-04-16:40:28]# pwd
/var/crash/127.0.0.1-2023-08-04-16:40:28
[root@node-3 127.0.0.1-2023-08-04-16:40:28]# cat btree_cache.txt|grep counter|grep -v "counter = 0"
[root@node-3 127.0.0.1-2023-08-04-16:40:28]# cat btree_cache_freeable.txt|grep counter|grep -v "counter = 0"
      counter = 1

We found that this is a bug in bch_sectors_dirty_init() when locking c->root:
    (1). Thread X has locked c->root(A) write.
    (2). Thread Y failed to lock c->root(A), waiting for the lock(c->root A).
    (3). Thread X bch_btree_set_root() changes c->root from A to B.
    (4). Thread X releases the lock(c->root A).
    (5). Thread Y successfully locks c->root(A).
    (6). Thread Y releases the lock(c->root B).

        down_write locked ---(1)----------------------┐
                |                                     |
                |   down_read waiting ---(2)----┐     |
                |           |               ┌-------------┐ ┌-------------┐
        bch_btree_set_root ===(3)========>> | c->root   A | | c->root   B |
                |           |               └-------------┘ └-------------┘
            up_write ---(4)---------------------┘     |            |
                            |                         |            |
                    down_read locked ---(5)-----------┘            |
                            |                                      |
                        up_read ---(6)-----------------------------┘

Since c->root may change, the correct steps to lock c->root should be
the same as bch_root_usage(), compare after locking.

static unsigned int bch_root_usage(struct cache_set *c)
{
        unsigned int bytes = 0;
        struct bkey *k;
        struct btree *b;
        struct btree_iter iter;

        goto lock_root;

        do {
                rw_unlock(false, b);
lock_root:
                b = c->root;
                rw_lock(false, b, b->level);
        } while (b != c->root);

        for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
                bytes += bkey_bytes(k);

        rw_unlock(false, b);

        return (bytes * 100) / btree_bytes(c);
}

Fixes: b144e45fc5 ("bcache: make bch_sectors_dirty_init() to be multithreaded")
Signed-off-by: Mingzhe Zou <mingzhe.zou@easystack.cn>
Cc:  <stable@vger.kernel.org>
Signed-off-by: Coly Li <colyli@suse.de>
Link: https://lore.kernel.org/r/20231120052503.6122-7-colyli@suse.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-12-03 07:33:09 +01:00
..
bcache
bcache: fixup lock c->root error
2023-12-03 07:33:09 +01:00
persistent-data
dm thin metadata: Fix ABBA deadlock by resetting dm_bufio_client
2023-06-16 18:24:13 -04:00
dm-audit.c
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-audit.h
dm: introduce audit event module for device mapper
2021-10-27 16:53:47 -04:00
dm-bio-prison-v1.c
dm: improve hash_locks sizing and hash function
2023-03-30 15:57:51 -04:00
dm-bio-prison-v1.h
dm bio prison v1: add dm_cell_key_has_valid_range
2023-03-30 15:57:51 -04:00
dm-bio-prison-v2.c
dm: address space issues relative to switch/while/for/...
2023-02-14 14:23:06 -05:00
dm-bio-prison-v2.h
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-bio-record.h
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-bufio.c
dm-bufio: fix no-sleep mode
2023-11-28 17:20:12 +00:00
dm-builtin.c
dm: adjust EXPORT_SYMBOL() to follow functions immediately
2023-02-14 14:23:07 -05:00
dm-cache-background-tracker.c
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-cache-background-tracker.h
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-cache-block-types.h
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-cache-metadata.c
Revert "mm: shrinkers: convert shrinker_rwsem to mutex"
2023-06-19 13:19:33 -07:00
dm-cache-metadata.h
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-cache-policy-internal.h
dm: add missing empty lines
2023-02-14 14:23:06 -05:00
dm-cache-policy-smq.c
dm cache policy smq: ensure IO doesn't prevent cleaner policy progress
2023-07-25 11:55:50 -04:00
dm-cache-policy.c
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-cache-policy.h
dm: address indent/space issues
2023-02-14 14:23:06 -05:00
dm-cache-target.c
block: replace fmode_t with a block-specific type for block open flags
2023-06-12 08:04:05 -06:00
dm-clone-metadata.c
dm clone metadata: remove unused function
2021-04-19 13:20:31 -04:00
dm-clone-metadata.h
dm clone metadata: Fix return type of dm_clone_nr_of_hydrated_regions()
2020-03-27 14:42:51 -04:00
dm-clone-target.c
block: replace fmode_t with a block-specific type for block open flags
2023-06-12 08:04:05 -06:00
dm-core.h
dm: fix a race condition in retrieve_deps
2023-09-14 11:18:29 -04:00
dm-crypt.c
dm crypt: account large pages in cc->n_allocated_pages
2023-11-28 17:19:58 +00:00
dm-delay.c
dm-delay: fix a race between delay_presuspend and delay_bio
2023-12-03 07:33:09 +01:00
dm-dust.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-ebs-target.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-era-target.c
block: replace fmode_t with a block-specific type for block open flags
2023-06-12 08:04:05 -06:00
dm-exception-store.c
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-exception-store.h
dm: avoid spaces before function arguments or in favour of tabs
2023-02-14 14:23:06 -05:00
dm-flakey.c
dm flakey: introduce random_read_corrupt and random_write_corrupt options
2023-06-16 18:24:13 -04:00
dm-ima.c
dm: avoid inline filenames
2023-02-14 14:23:07 -05:00
dm-ima.h
dm: avoid inline filenames
2023-02-14 14:23:07 -05:00
dm-init.c
dm: open code dm_get_dev_t in dm_init_init
2023-06-05 10:57:40 -06:00
dm-integrity.c
dm integrity: fix double free on memory allocation failure
2023-07-25 11:55:50 -04:00
dm-io-rewind.c
dm: avoid void function return statements
2023-02-14 14:23:07 -05:00
dm-io-tracker.h
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-io.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-ioctl.c
dm: fix a race condition in retrieve_deps
2023-09-14 11:18:29 -04:00
dm-kcopyd.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-linear.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-log-userspace-base.c
dm: avoid void function return statements
2023-02-14 14:23:07 -05:00
dm-log-userspace-transfer.c
dm: avoid split of quoted strings where possible
2023-02-14 14:23:07 -05:00
dm-log-userspace-transfer.h
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-log-writes.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-log.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-mpath.c
dm: push error reporting down to dm_register_target()
2023-04-11 12:01:01 -04:00
dm-mpath.h
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-path-selector.c
dm: adjust EXPORT_SYMBOL() to follow functions immediately
2023-02-14 14:23:07 -05:00
dm-path-selector.h
dm: avoid spaces before function arguments or in favour of tabs
2023-02-14 14:23:06 -05:00
dm-ps-historical-service-time.c
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-ps-io-affinity.c
dm: address space issues relative to switch/while/for/...
2023-02-14 14:23:06 -05:00
dm-ps-queue-length.c
dm: avoid spaces before function arguments or in favour of tabs
2023-02-14 14:23:06 -05:00
dm-ps-round-robin.c
dm: correct block comments format.
2023-02-14 14:23:06 -05:00
dm-ps-service-time.c
dm: avoid spaces before function arguments or in favour of tabs
2023-02-14 14:23:06 -05:00
dm-raid1.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-raid.c
Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux
2023-08-29 20:21:42 -07:00
dm-region-hash.c
dm: correct block comments format.
2023-02-14 14:23:06 -05:00
dm-rq.c
dm: avoid using symbolic permissions
2023-02-14 14:23:07 -05:00
dm-rq.h
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-snap-persistent.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-snap-transient.c
dm: avoid split of quoted strings where possible
2023-02-14 14:23:07 -05:00
dm-snap.c
block: replace fmode_t with a block-specific type for block open flags
2023-06-12 08:04:05 -06:00
dm-stats.c
dm stats: check for and propagate alloc_percpu failure
2023-03-16 13:37:06 -04:00
dm-stats.h
dm stats: check for and propagate alloc_percpu failure
2023-03-16 13:37:06 -04:00
dm-stripe.c
dm: remove unnecessary (void*) conversions
2023-04-11 12:01:01 -04:00
dm-switch.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-sysfs.c
dm sysfs: make kobj_type structure constant
2023-02-14 14:23:08 -05:00
dm-table.c
dm: fix a race condition in retrieve_deps
2023-09-14 11:18:29 -04:00
dm-target.c
dm: push error reporting down to dm_register_target()
2023-04-11 12:01:01 -04:00
dm-thin-metadata.c
Merge tag 'for-6.5/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
2023-06-30 12:16:00 -07:00
dm-thin-metadata.h
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-thin.c
Merge tag 'for-6.5/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm
2023-06-30 12:16:00 -07:00
dm-uevent.c
dm: avoid spaces before function arguments or in favour of tabs
2023-02-14 14:23:06 -05:00
dm-uevent.h
dm: fix undue/missing spaces
2023-02-14 14:23:06 -05:00
dm-unstripe.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-verity-fec.c
dm-verity: don't use blocking calls from tasklets
2023-11-28 17:20:12 +00:00
dm-verity-fec.h
dm: change "unsigned" to "unsigned int"
2023-02-14 14:23:06 -05:00
dm-verity-loadpin.c
dm: verity-loadpin: Add NULL pointer check for 'bdev' parameter
2023-06-28 10:43:04 -07:00
dm-verity-target.c
dm-verity: don't use blocking calls from tasklets
2023-11-28 17:20:12 +00:00
dm-verity-verify-sig.c
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-verity-verify-sig.h
dm: add missing SPDX-License-Indentifiers
2023-02-14 14:23:06 -05:00
dm-verity.h
dm-verity: don't use blocking calls from tasklets
2023-11-28 17:20:12 +00:00
dm-writecache.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-zero.c
dm: add helper macro for simple DM target module init and exit
2023-04-11 12:09:08 -04:00
dm-zone.c
dm zone: Use the bitmap API to allocate bitmaps
2023-06-16 18:24:13 -04:00
dm-zoned-metadata.c
dm: dm-zoned: use __bio_add_page for adding single metadata page
2023-05-31 09:50:02 -06:00
dm-zoned-reclaim.c
dm kcopyd: avoid useless atomic operations
2021-06-04 12:07:24 -04:00
dm-zoned-target.c
dm zoned: free dmz->ddev array in dmz_put_zoned_devices
2023-09-20 13:48:06 -04:00
dm-zoned.h
dm/dm-zoned: Use the enum req_op type
2022-07-14 12:14:31 -06:00
dm.c
dm: don't attempt to queue IO under RCU protection
2023-09-15 15:39:59 -04:00
dm.h
dm: remove stale/redundant dm_internal_{suspend,resume} prototypes in dm.h
2023-06-16 18:24:14 -04:00
Kconfig
fs: add CONFIG_BUFFER_HEAD
2023-08-02 09:13:09 -06:00
Makefile
Merge tag 'hardening-v5.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
2022-08-02 14:38:59 -07:00
md-autodetect.c
init: improve the name_to_dev_t interface
2023-06-05 10:56:46 -06:00
md-bitmap.c
md/md-bitmap: hold 'reconfig_mutex' in backlog_store()
2023-07-27 00:13:30 -07:00
md-bitmap.h
md-bitmap: don't use ->index for pages backing the bitmap file
2023-07-27 00:13:29 -07:00
md-cluster.c
md: Hold mddev->reconfig_mutex when trying to get mddev->sync_thread
2023-08-15 09:40:26 -07:00
md-cluster.h
…
md-faulty.c
md/md-faulty: enable io accounting
2023-07-27 00:13:30 -07:00
md-linear.c
md/md-linear: enable io accounting
2023-07-27 00:13:30 -07:00
md-linear.h
md/raid1: Replace zero-length array with flexible-array
2020-05-13 12:02:23 -07:00
md-multipath.c
md/md-multipath: enable io accounting
2023-07-27 00:13:29 -07:00
md-multipath.h
…
md.c
md: fix bi_status reporting in md_end_clone_io
2023-12-03 07:33:07 +01:00
md.h
md: fix warning for holder mismatch from export_rdev()
2023-09-08 13:16:40 -07:00
raid0.c
md: raid0: account for split bio in iostat accounting
2023-08-17 21:11:31 -07:00
raid0.h
md/raid0: add discard support for the 'original' layout
2023-06-30 15:43:50 -07:00
raid1-10.c
md/raid1-10: fix casting from randomized structure in raid1_submit_write()
2023-06-23 09:33:16 -07:00
raid1.c
md/raid1: fix error: ISO C90 forbids mixed declarations
2023-09-11 14:41:58 -07:00
raid1.h
md/raid1: switch to use md_account_bio() for io accounting
2023-07-27 00:13:29 -07:00
raid5-cache.c
md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
2023-08-15 09:40:27 -07:00
raid5-log.h
md/raid5-ppl: Drop unused argument from ppl_handle_flush_request()
2022-08-02 17:14:31 -06:00
raid5-ppl.c
md: raid5: use __bio_add_page to add single page to new bio
2023-05-31 09:50:02 -06:00
raid5.c
md/raid5: release batch_last before waiting for another stripe_head
2023-10-03 08:53:09 -07:00
raid5.h
Merge tag 'hardening-v6.5-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
2023-06-27 21:24:18 -07:00
raid10.c
md: Hold mddev->reconfig_mutex when trying to get mddev->sync_thread
2023-08-15 09:40:26 -07:00
raid10.h
md/raid10: switch to use md_account_bio() for io accounting
2023-07-27 00:13:29 -07:00