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>

1 files changed, 11 insertions, 7 deletions

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 843ceca9a21e..e50b31d18462 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -19,6 +19,7 @@
 
 #include <linux/atomic.h>
 #include <linux/compiler.h>
+#include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/jhash.h>
 #include <linux/list_nulls.h>
@@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
 int rhashtable_init(struct rhashtable *ht,
 		    const struct rhashtable_params *params);
 
-int rhashtable_insert_slow(struct rhashtable *ht, const void *key,
-			   struct rhash_head *obj,
-			   struct bucket_table *old_tbl);
-int rhashtable_insert_rehash(struct rhashtable *ht);
+struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht,
+					    const void *key,
+					    struct rhash_head *obj,
+					    struct bucket_table *old_tbl);
+int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl);
 
 int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter);
 void rhashtable_walk_exit(struct rhashtable_iter *iter);
@@ -598,9 +600,11 @@ restart:
 
 	new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	if (unlikely(new_tbl)) {
-		err = rhashtable_insert_slow(ht, key, obj, new_tbl);
-		if (err == -EAGAIN)
+		tbl = rhashtable_insert_slow(ht, key, obj, new_tbl);
+		if (!IS_ERR_OR_NULL(tbl))
 			goto slow_path;
+
+		err = PTR_ERR(tbl);
 		goto out;
 	}
 
@@ -611,7 +615,7 @@ restart:
 	if (unlikely(rht_grow_above_100(ht, tbl))) {
 slow_path:
 		spin_unlock_bh(lock);
-		err = rhashtable_insert_rehash(ht);
+		err = rhashtable_insert_rehash(ht, tbl);
 		rcu_read_unlock();
 		if (err)
 			return err;