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@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Eric Dumazet 2023-03-13 20:17:32 +00:00 коммит произвёл Jakub Kicinski
Родитель b071af5235
Коммит c486640aa7
1 изменённых файлов: 4 добавлений и 4 удалений

Просмотреть файл

@ -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;