inetpeer: Optimize inet_getid()
While investigating for network latencies, I found inet_getid() was a
contention point for some workloads, as inet_peer_idlock is shared
by all inet_getid() users regardless of peers.
One way to fix this is to make ip_id_count an atomic_t instead
of __u16, and use atomic_add_return().
In order to keep sizeof(struct inet_peer) = 64 on 64bit arches
tcp_ts_stamp is also converted to __u32 instead of "unsigned long".
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b1fbe18..6bcfe52 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -67,9 +67,6 @@
* ip_id_count: idlock
*/
-/* Exported for inet_getid inline function. */
-DEFINE_SPINLOCK(inet_peer_idlock);
-
static struct kmem_cache *peer_cachep __read_mostly;
#define node_height(x) x->avl_height
@@ -390,7 +387,7 @@
n->v4daddr = daddr;
atomic_set(&n->refcnt, 1);
atomic_set(&n->rid, 0);
- n->ip_id_count = secure_ip_id(daddr);
+ atomic_set(&n->ip_id_count, secure_ip_id(daddr));
n->tcp_ts_stamp = 0;
write_lock_bh(&peer_pool_lock);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff258b5..4284cee 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2852,7 +2852,7 @@
error = rt->u.dst.error;
expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
if (rt->peer) {
- id = rt->peer->ip_id_count;
+ id = atomic_read(&rt->peer->ip_id_count) & 0xffff;
if (rt->peer->tcp_ts_stamp) {
ts = rt->peer->tcp_ts;
tsage = get_seconds() - rt->peer->tcp_ts_stamp;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cf7f208..df18ce0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -204,7 +204,7 @@
* when trying new connection.
*/
if (peer != NULL &&
- peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) {
+ (u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
@@ -1308,7 +1308,7 @@
tcp_death_row.sysctl_tw_recycle &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
- if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL &&
+ if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
(s32)(peer->tcp_ts - req->ts_recent) >
TCP_PAWS_WINDOW) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
@@ -1727,9 +1727,9 @@
if (peer) {
if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 ||
- (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() &&
- peer->tcp_ts_stamp <= tp->rx_opt.ts_recent_stamp)) {
- peer->tcp_ts_stamp = tp->rx_opt.ts_recent_stamp;
+ ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
+ peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) {
+ peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp;
peer->tcp_ts = tp->rx_opt.ts_recent;
}
if (release_it)
@@ -1748,9 +1748,9 @@
const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 ||
- (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() &&
- peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) {
- peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp;
+ ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL &&
+ peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) {
+ peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp;
peer->tcp_ts = tcptw->tw_ts_recent;
}
inet_putpeer(peer);
