summaryrefslogtreecommitdiff
path: root/include/linux/skmsg.h
diff options
context:
space:
mode:
authorJohn Fastabend <john.fastabend@gmail.com>2021-04-01 15:00:19 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2021-04-07 01:29:06 +0200
commit1c84b33101c82683dee8b06761ca1f69e78c8ee7 (patch)
tree708e48c979c81f8c2e569806232852e2b4951d69 /include/linux/skmsg.h
parent2a2403ca3add03f542f6b34bef9f74649969b06d (diff)
bpf, sockmap: Fix sk->prot unhash op reset
In '4da6a196f93b1' we fixed a potential unhash loop caused when a TLS socket in a sockmap was removed from the sockmap. This happened because the unhash operation on the TLS ctx continued to point at the sockmap implementation of unhash even though the psock has already been removed. The sockmap unhash handler when a psock is removed does the following, void sock_map_unhash(struct sock *sk) { void (*saved_unhash)(struct sock *sk); struct sk_psock *psock; rcu_read_lock(); psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); if (sk->sk_prot->unhash) sk->sk_prot->unhash(sk); return; } [...] } The unlikely() case is there to handle the case where psock is detached but the proto ops have not been updated yet. But, in the above case with TLS and removed psock we never fixed sk_prot->unhash() and unhash() points back to sock_map_unhash resulting in a loop. To fix this we added this bit of code, static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; This will set the sk_prot->unhash back to its saved value. This is the correct callback for a TLS socket that has been removed from the sock_map. Unfortunately, this also overwrites the unhash pointer for all psocks. We effectively break sockmap unhash handling for any future socks. Omitting the unhash operation will leave stale entries in the map if a socket transition through unhash, but does not do close() op. To fix set unhash correctly before calling into tls_update. This way the TLS enabled socket will point to the saved unhash() handler. Fixes: 4da6a196f93b1 ("bpf: Sockmap/tls, during free we may call tcp_bpf_unhash() in loop") Reported-by: Cong Wang <xiyou.wangcong@gmail.com> Reported-by: Lorenz Bauer <lmb@cloudflare.com> Suggested-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/161731441904.68884.15593917809745631972.stgit@john-XPS-13-9370
Diffstat (limited to 'include/linux/skmsg.h')
-rw-r--r--include/linux/skmsg.h7
1 files changed, 6 insertions, 1 deletions
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 8edbbf5f2f93..822c048934e3 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -349,8 +349,13 @@ static inline void sk_psock_update_proto(struct sock *sk,
static inline void sk_psock_restore_proto(struct sock *sk,
struct sk_psock *psock)
{
- sk->sk_prot->unhash = psock->saved_unhash;
if (inet_csk_has_ulp(sk)) {
+ /* TLS does not have an unhash proto in SW cases, but we need
+ * to ensure we stop using the sock_map unhash routine because
+ * the associated psock is being removed. So use the original
+ * unhash handler.
+ */
+ WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
} else {
sk->sk_write_space = psock->saved_write_space;