[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230313201732.887488-3-edumazet@google.com>
Date: Mon, 13 Mar 2023 20:17:32 +0000
From: Eric Dumazet <edumazet@...gle.com>
To: "David S . Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>
Cc: David Ahern <dsahern@...nel.org>, netdev@...r.kernel.org,
eric.dumazet@...il.com, Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net-next 2/2] ipv6: remove one read_lock()/read_unlock() pair
in rt6_check_neigh()
rt6_check_neigh() uses read_lock() to protect n->nud_state reading.
This seems overkill and causes false sharing.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
---
net/ipv6/route.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 25c00c6f5131c55055f30348ef4605f50440ddbb..e829bd880384077027dc79fcae1a62eb0073f7c8 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -687,16 +687,16 @@ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh)
neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev,
&fib6_nh->fib_nh_gw6);
if (neigh) {
- read_lock(&neigh->lock);
- if (neigh->nud_state & NUD_VALID)
+ u8 nud_state = READ_ONCE(neigh->nud_state);
+
+ if (nud_state & NUD_VALID)
ret = RT6_NUD_SUCCEED;
#ifdef CONFIG_IPV6_ROUTER_PREF
- else if (!(neigh->nud_state & NUD_FAILED))
+ else if (!(nud_state & NUD_FAILED))
ret = RT6_NUD_SUCCEED;
else
ret = RT6_NUD_FAIL_PROBE;
#endif
- read_unlock(&neigh->lock);
} else {
ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ?
RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR;
--
2.40.0.rc1.284.g88254d51c5-goog
Powered by blists - more mailing lists