net: memcontrol: defer call to mem_cgroup_sk_alloc()

Instead of calling mem_cgroup_sk_alloc() from BH context,
it is better to call it from inet_csk_accept() in process context.

Not only this removes code in mem_cgroup_sk_alloc(), but it also
fixes a bug since listener might have been dismantled and css_get()
might cause a use-after-free.

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5f3a62887cf958f6b657c0f542f0cf2c3e86e8d..661f046ad3181f65eccfd9bf3832e395e27aa226 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5828,21 +5828,6 @@ void mem_cgroup_sk_alloc(struct sock *sk)
        if (!mem_cgroup_sockets_enabled)
                return;
 
-       /*
-        * Socket cloning can throw us here with sk_memcg already
-        * filled. It won't however, necessarily happen from
-        * process context. So the test for root memcg given
-        * the current task's memcg won't help us in this case.
-        *
-        * Respecting the original socket's memcg is a better
-        * decision in this case.
-        */
-       if (sk->sk_memcg) {
-               BUG_ON(mem_cgroup_is_root(sk->sk_memcg));
-               css_get(&sk->sk_memcg->css);
-               return;
-       }
-
        rcu_read_lock();
        memcg = mem_cgroup_from_task(current);
        if (memcg == root_mem_cgroup)

diff --git a/net/core/sock.c b/net/core/sock.c
index 23953b741a41fbcf4a6ffb0dd5bf05bd5266b99d..70c6ccbdf49f2f8a5a0f7c41c7849ea01459be50 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1677,6 +1677,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                newsk->sk_dst_pending_confirm = 0;
                newsk->sk_wmem_queued   = 0;
                newsk->sk_forward_alloc = 0;
+
+               /* sk->sk_memcg will be populated at accept() time */
+               newsk->sk_memcg = NULL;
+
                atomic_set(&newsk->sk_drops, 0);
                newsk->sk_send_head     = NULL;
                newsk->sk_userlocks     = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
@@ -1714,7 +1718,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                newsk->sk_incoming_cpu = raw_smp_processor_id();
                atomic64_set(&newsk->sk_cookie, 0);
 
-               mem_cgroup_sk_alloc(newsk);
                cgroup_sk_alloc(&newsk->sk_cgrp_data);
 
                /*

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c039c937ba90c7aec39ba2687bceb8253ead70aa..67aec7a106860b26c929fea1624d652c87972f04 100644 (file)
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -475,6 +475,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
                }
                spin_unlock_bh(&queue->fastopenq.lock);
        }
+       mem_cgroup_sk_alloc(newsk);
 out:
        release_sock(sk);
        if (req)