[ Upstream commit ce3e4cfb59cb382f8e5ce359238aa580d4ae7778 ]
Currently run_cache_set() has no return value, if there is failure in bch_journal_replay(), the caller of run_cache_set() has no idea about such failure and just continue to execute following code after run_cache_set(). The internal failure is triggered inside bch_journal_replay() and being handled in async way. This behavior is inefficient, while failure handling inside bch_journal_replay(), cache register code is still running to start the cache set. Registering and unregistering code running as same time may introduce some rare race condition, and make the code to be more hard to be understood.
This patch adds return value to run_cache_set(), and returns -EIO if bch_journal_rreplay() fails. Then caller of run_cache_set() may detect such failure and stop registering code flow immedidately inside register_cache_set().
If journal replay fails, run_cache_set() can report error immediately to register_cache_set(). This patch makes the failure handling for bch_journal_replay() be in synchronized way, easier to understand and debug, and avoid poetential race condition for register-and-unregister in same time.
Signed-off-by: Coly Li colyli@suse.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/bcache/super.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index d8190804aee9b..2409507d7bff8 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1770,7 +1770,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) return NULL; }
-static void run_cache_set(struct cache_set *c) +static int run_cache_set(struct cache_set *c) { const char *err = "cannot allocate memory"; struct cached_dev *dc, *t; @@ -1866,7 +1866,9 @@ static void run_cache_set(struct cache_set *c) if (j->version < BCACHE_JSET_VERSION_UUID) __uuid_write(c);
- bch_journal_replay(c, &journal); + err = "bcache: replay journal failed"; + if (bch_journal_replay(c, &journal)) + goto err; } else { pr_notice("invalidating existing data");
@@ -1934,7 +1936,7 @@ static void run_cache_set(struct cache_set *c) flash_devs_run(c);
set_bit(CACHE_SET_RUNNING, &c->flags); - return; + return 0; err: while (!list_empty(&journal)) { l = list_first_entry(&journal, struct journal_replay, list); @@ -1945,6 +1947,8 @@ static void run_cache_set(struct cache_set *c) closure_sync(&cl); /* XXX: test this, it's broken */ bch_cache_set_error(c, "%s", err); + + return -EIO; }
static bool can_attach_cache(struct cache *ca, struct cache_set *c) @@ -2008,8 +2012,11 @@ static const char *register_cache_set(struct cache *ca) ca->set->cache[ca->sb.nr_this_dev] = ca; c->cache_by_alloc[c->caches_loaded++] = ca;
- if (c->caches_loaded == c->sb.nr_in_set) - run_cache_set(c); + if (c->caches_loaded == c->sb.nr_in_set) { + err = "failed to run cache set"; + if (run_cache_set(c) < 0) + goto err; + }
return NULL; err: