aboutsummaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorShakeel Butt <shakeelb@google.com>2020-03-09 22:16:06 -0700
committerDavid S. Miller <davem@davemloft.net>2020-03-10 15:33:05 -0700
commitd752a4986532cb6305dfd5290a614cde8072769d (patch)
treec6ef3751498db84ff219e13746c548b001037f70 /net
parentcgroup: memcg: net: do not associate sock with unrelated cgroup (diff)
downloadlinux-dev-d752a4986532cb6305dfd5290a614cde8072769d.tar.xz
linux-dev-d752a4986532cb6305dfd5290a614cde8072769d.zip
net: memcg: late association of sock to memcg
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>
Diffstat (limited to 'net')
-rw-r--r--net/core/sock.c5
-rw-r--r--net/ipv4/inet_connection_sock.c20
2 files changed, 24 insertions, 1 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index a4c8fac781ff..8f71684305c3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1830,7 +1830,10 @@ 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 a4db79b1b643..65a3b2565102 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)