diff options
author | Herbert Xu <herbert@gondor.apana.org.au> | 2015-12-03 12:41:29 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2015-12-04 19:38:26 (GMT) |
commit | 3cf92222a39cc7842c373dd90a0c204fa7d7cced (patch) | |
tree | da9e396b430096bc864ee7522667f228bb672630 /lib | |
parent | 071f5d105a0ae93aeb02197c4ee3557e8cc57a21 (diff) | |
download | linux-3cf92222a39cc7842c373dd90a0c204fa7d7cced.tar.xz |
rhashtable: Prevent spurious EBUSY errors on insertion
Thomas and Phil observed that under stress rhashtable insertion
sometimes failed with EBUSY, even though this error should only
ever been seen when we're under attack and our hash chain length
has grown to an unacceptable level, even after a rehash.
It turns out that the logic for detecting whether there is an
existing rehash is faulty. In particular, when two threads both
try to grow the same table at the same time, one of them may see
the newly grown table and thus erroneously conclude that it had
been rehashed. This is what leads to the EBUSY error.
This patch fixes this by remembering the current last table we
used during insertion so that rhashtable_insert_rehash can detect
when another thread has also done a resize/rehash. When this is
detected we will give up our resize/rehash and simply retry the
insertion with the new table.
Reported-by: Thomas Graf <tgraf@suug.ch>
Reported-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'lib')
-rw-r--r-- | lib/rhashtable.c | 45 |
1 files changed, 30 insertions, 15 deletions
diff --git a/lib/rhashtable.c b/lib/rhashtable.c index a54ff89..2ff7ed9 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -389,33 +389,31 @@ static bool rhashtable_check_elasticity(struct rhashtable *ht, return false; } -int rhashtable_insert_rehash(struct rhashtable *ht) +int rhashtable_insert_rehash(struct rhashtable *ht, + struct bucket_table *tbl) { struct bucket_table *old_tbl; struct bucket_table *new_tbl; - struct bucket_table *tbl; unsigned int size; int err; old_tbl = rht_dereference_rcu(ht->tbl, ht); - tbl = rhashtable_last_table(ht, old_tbl); size = tbl->size; + err = -EBUSY; + if (rht_grow_above_75(ht, tbl)) size *= 2; /* Do not schedule more than one rehash */ else if (old_tbl != tbl) - return -EBUSY; + goto fail; + + err = -ENOMEM; new_tbl = bucket_table_alloc(ht, size, GFP_ATOMIC); - if (new_tbl == NULL) { - /* Schedule async resize/rehash to try allocation - * non-atomic context. - */ - schedule_work(&ht->run_work); - return -ENOMEM; - } + if (new_tbl == NULL) + goto fail; err = rhashtable_rehash_attach(ht, tbl, new_tbl); if (err) { @@ -426,12 +424,24 @@ int rhashtable_insert_rehash(struct rhashtable *ht) schedule_work(&ht->run_work); return err; + +fail: + /* Do not fail the insert if someone else did a rehash. */ + if (likely(rcu_dereference_raw(tbl->future_tbl))) + return 0; + + /* Schedule async rehash to retry allocation in process context. */ + if (err == -ENOMEM) + schedule_work(&ht->run_work); + + return err; } EXPORT_SYMBOL_GPL(rhashtable_insert_rehash); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *tbl) +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *tbl) { struct rhash_head *head; unsigned int hash; @@ -467,7 +477,12 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key, exit: spin_unlock(rht_bucket_lock(tbl, hash)); - return err; + if (err == 0) + return NULL; + else if (err == -EAGAIN) + return tbl; + else + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(rhashtable_insert_slow); |