summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2018-02-02 18:26:57 +0300
committerDavid S. Miller <davem@davemloft.net>2018-02-03 03:49:31 +0300
commitedbe69ef2c90fc86998a74b08319a01c508bd497 (patch)
treeae886133adf7f3518a47f81db0644fe74732b80b
parent4db428a7c9ab07e08783e0fcdc4ca0f555da0567 (diff)
downloadlinux-edbe69ef2c90fc86998a74b08319a01c508bd497.tar.xz
Revert "defer call to mem_cgroup_sk_alloc()"
This patch effectively reverts commit 9f1c2674b328 ("net: memcontrol: defer call to mem_cgroup_sk_alloc()"). Moving mem_cgroup_sk_alloc() to the inet_csk_accept() completely breaks memcg socket memory accounting, as packets received before memcg pointer initialization are not accounted and are causing refcounting underflow on socket release. Actually the free-after-use problem was fixed by commit c0576e397508 ("net: call cgroup_sk_alloc() earlier in sk_clone_lock()") for the cgroup pointer. So, let's revert it and call mem_cgroup_sk_alloc() just before cgroup_sk_alloc(). This is safe, as we hold a reference to the socket we're cloning, and it holds a reference to the memcg. Also, let's drop BUG_ON(mem_cgroup_is_root()) check from mem_cgroup_sk_alloc(). I see no reasons why bumping the root memcg counter is a good reason to panic, and there are no realistic ways to hit it. Signed-off-by: Roman Gushchin <guro@fb.com> Cc: Eric Dumazet <edumazet@google.com> Cc: David S. Miller <davem@davemloft.net> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--mm/memcontrol.c14
-rw-r--r--net/core/sock.c5
-rw-r--r--net/ipv4/inet_connection_sock.c1
3 files changed, 15 insertions, 5 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0ae2dc3a1748..0937f2c52c7d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5747,6 +5747,20 @@ 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) {
+ 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 1033f8ab0547..e50e7b3f2223 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1683,16 +1683,13 @@ 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;
atomic_set(&newsk->sk_zckey, 0);
sock_reset_flag(newsk, SOCK_DONE);
+ mem_cgroup_sk_alloc(newsk);
cgroup_sk_alloc(&newsk->sk_cgrp_data);
rcu_read_lock();
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 12410ec6f7f7..881ac6d046f2 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -475,7 +475,6 @@ 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)