af_unix: Define locking order for unix_table_double_lock().

When created, AF_UNIX socket is put into net->unx.table.buckets[],
and the hash is stored in sk->sk_hash.

  * unbound socket  : 0 <= sk_hash <= UNIX_HASH_MOD

When bind() is called, the socket could be moved to another bucket.

  * pathname socket : 0 <= sk_hash <= UNIX_HASH_MOD
  * abstract socket : UNIX_HASH_MOD + 1 <= sk_hash <= UNIX_HASH_MOD * 2 + 1

Then, we call unix_table_double_lock() which locks a single bucket
or two.

Let's define the order as unix_table_lock_cmp_fn() instead of using
spin_lock_nested().

The locking is always done in ascending order of sk->sk_hash, which
is the index of buckets/locks array allocated by kvmalloc_array().

  sk_hash_A < sk_hash_B
  <=> &locks[sk_hash_A].dep_map < &locks[sk_hash_B].dep_map

So, the relation of two sk->sk_hash can be derived from the addresses
of dep_map in the array of locks.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e9c941e6a464cffebcc733f47575f9ce3b0e364e..7889d47239595fe2e4765741d0e61295a53f6c88 100644 (file)
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -126,6 +126,15 @@ static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
  *    hash table is protected with spinlock.
  *    each socket state is protected by separate spinlock.
  */
+#ifdef CONFIG_PROVE_LOCKING
+#define cmp_ptr(l, r)  (((l) > (r)) - ((l) < (r)))
+
+static int unix_table_lock_cmp_fn(const struct lockdep_map *a,
+                                 const struct lockdep_map *b)
+{
+       return cmp_ptr(a, b);
+}
+#endif
 
 static unsigned int unix_unbound_hash(struct sock *sk)
 {
@@ -168,7 +177,7 @@ static void unix_table_double_lock(struct net *net,
                swap(hash1, hash2);
 
        spin_lock(&net->unx.table.locks[hash1]);
-       spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING);
+       spin_lock(&net->unx.table.locks[hash2]);
 }
 
 static void unix_table_double_unlock(struct net *net,
@@ -3578,6 +3587,7 @@ static int __net_init unix_net_init(struct net *net)
 
        for (i = 0; i < UNIX_HASH_SIZE; i++) {
                spin_lock_init(&net->unx.table.locks[i]);
+               lock_set_cmp_fn(&net->unx.table.locks[i], unix_table_lock_cmp_fn, NULL);
                INIT_HLIST_HEAD(&net->unx.table.buckets[i]);
        }