blob: b2e7ac88a7e15f2f0ccbfec36d073f38e952d1c6 [file] [log] [blame]
From ef4fb4e5adca4c53de59d66b46e4f8f5be238073 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Mon, 9 Mar 2020 22:16:06 -0700
Subject: [PATCH] net: memcg: late association of sock to memcg
commit d752a4986532cb6305dfd5290a614cde8072769d upstream.
If a TCP socket is allocated in IRQ context or cloned from unassociated
(i.e. not associated to a memcg) in IRQ context then it will remain
unassociated for its whole life. Almost half of the TCPs created on the
system are created in IRQ context, so, memory used by such sockets will
not be accounted by the memcg.
This issue is more widespread in cgroup v1 where network memory
accounting is opt-in but it can happen in cgroup v2 if the source socket
for the cloning was created in root memcg.
To fix the issue, just do the association of the sockets at the accept()
time in the process context and then force charge the memory buffer
already used and reserved by the socket.
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e8502d2b7b1b..b95391b7663a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6452,20 +6452,6 @@ 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) {
- css_get(&sk->sk_memcg->css);
- return;
- }
-
/* Do not associate the sock with unrelated interrupted task's memcg. */
if (in_interrupt())
return;
diff --git a/net/core/sock.c b/net/core/sock.c
index da1af81e346c..365832769bc2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1826,7 +1826,10 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
atomic_set(&newsk->sk_zckey, 0);
sock_reset_flag(newsk, SOCK_DONE);
- mem_cgroup_sk_alloc(newsk);
+
+ /* sk->sk_memcg will be populated at accept() time */
+ newsk->sk_memcg = NULL;
+
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 2a16c83a866c..042b86433544 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -482,6 +482,26 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
}
spin_unlock_bh(&queue->fastopenq.lock);
}
+
+ if (mem_cgroup_sockets_enabled) {
+ int amt;
+
+ /* atomically get the memory usage, set and charge the
+ * sk->sk_memcg.
+ */
+ lock_sock(newsk);
+
+ /* The sk has not been accepted yet, no need to look at
+ * sk->sk_wmem_queued.
+ */
+ amt = sk_mem_pages(newsk->sk_forward_alloc +
+ atomic_read(&sk->sk_rmem_alloc));
+ mem_cgroup_sk_alloc(newsk);
+ if (newsk->sk_memcg && amt)
+ mem_cgroup_charge_skmem(newsk->sk_memcg, amt);
+
+ release_sock(newsk);
+ }
out:
release_sock(sk);
if (req)
--
2.7.4