tcp: defer skb freeing after socket lock is released

tcp recvmsg() (or rx zerocopy) spends a fair amount of time
freeing skbs after their payload has been consumed.

A typical ~64KB GRO packet has to release ~45 page
references, eventually going to page allocator
for each of them.

Currently, this freeing is performed while socket lock
is held, meaning that there is a high chance that
BH handler has to queue incoming packets to tcp socket backlog.

This can cause additional latencies, because the user
thread has to process the backlog at release_sock() time,
and while doing so, additional frames can be added
by BH handler.

This patch adds logic to defer these frees after socket
lock is released, or directly from BH handler if possible.

Being able to free these skbs from BH handler helps a lot,
because this avoids the usual alloc/free assymetry,
when BH handler and user thread do not run on same cpu or
NUMA node.

One cpu can now be fully utilized for the kernel->user copy,
and another cpu is handling BH processing and skb/page
allocs/frees (assuming RFS is not forcing use of a single CPU)

Tested:
 100Gbit NIC
 Max throughput for one TCP_STREAM flow, over 10 runs

MTU : 1500
Before: 55 Gbit
After:  66 Gbit

MTU : 4096+(headers)
Before: 82 Gbit
After:  95 Gbit

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 686a666..b8b8065 100644 (file)
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -36,6 +36,7 @@
 #include <linux/splice.h>
 #include <linux/in6.h>
 #include <linux/if_packet.h>
+#include <linux/llist.h>
 #include <net/flow.h>
 #include <net/page_pool.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
@@ -743,6 +744,7 @@ struct sk_buff {
                };
                struct rb_node          rbnode; /* used in netem, ip4 defrag, and tcp stack */
                struct list_head        list;
+               struct llist_node       ll_node;
        };
 
        union {

diff --git a/include/net/sock.h b/include/net/sock.h
index 2d40fe4..2578d1f 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -63,6 +63,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <linux/atomic.h>
 #include <linux/refcount.h>
+#include <linux/llist.h>
 #include <net/dst.h>
 #include <net/checksum.h>
 #include <net/tcp_states.h>
@@ -408,6 +409,8 @@ struct sock {
                struct sk_buff  *head;
                struct sk_buff  *tail;
        } sk_backlog;
+       struct llist_head defer_list;
+
 #define sk_rmem_alloc sk_backlog.rmem_alloc
 
        int                     sk_forward_alloc;

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 05c8167..44e442b 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1368,6 +1368,16 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb)
 }
 
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb);
+
+void __sk_defer_free_flush(struct sock *sk);
+
+static inline void sk_defer_free_flush(struct sock *sk)
+{
+       if (llist_empty(&sk->defer_list))
+               return;
+       __sk_defer_free_flush(sk);
+}
+
 int tcp_filter(struct sock *sk, struct sk_buff *skb);
 void tcp_set_state(struct sock *sk, int state);
 void tcp_done(struct sock *sk);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4e70116..33cd9a1 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1580,14 +1580,34 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
                tcp_send_ack(sk);
 }
 
+void __sk_defer_free_flush(struct sock *sk)
+{
+       struct llist_node *head;
+       struct sk_buff *skb, *n;
+
+       head = llist_del_all(&sk->defer_list);
+       llist_for_each_entry_safe(skb, n, head, ll_node) {
+               prefetch(n);
+               skb_mark_not_on_list(skb);
+               __kfree_skb(skb);
+       }
+}
+EXPORT_SYMBOL(__sk_defer_free_flush);
+
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
+       __skb_unlink(skb, &sk->sk_receive_queue);
        if (likely(skb->destructor == sock_rfree)) {
                sock_rfree(skb);
                skb->destructor = NULL;
                skb->sk = NULL;
+               if (!skb_queue_empty(&sk->sk_receive_queue) ||
+                   !llist_empty(&sk->defer_list)) {
+                       llist_add(&skb->ll_node, &sk->defer_list);
+                       return;
+               }
        }
-       sk_eat_skb(sk, skb);
+       __kfree_skb(skb);
 }
 
 static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
@@ -2422,6 +2442,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
                        /* Do not sleep, just process backlog. */
                        __sk_flush_backlog(sk);
                } else {
+                       sk_defer_free_flush(sk);
                        sk_wait_data(sk, &timeo, last);
                }
 
@@ -2540,6 +2561,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
        ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss,
                                 &cmsg_flags);
        release_sock(sk);
+       sk_defer_free_flush(sk);
 
        if (cmsg_flags && ret >= 0) {
                if (cmsg_flags & TCP_CMSG_TS)
@@ -3065,7 +3087,7 @@ int tcp_disconnect(struct sock *sk, int flags)
                sk->sk_frag.page = NULL;
                sk->sk_frag.offset = 0;
        }
-
+       sk_defer_free_flush(sk);
        sk_error_report(sk);
        return 0;
 }
@@ -4194,6 +4216,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
                err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
                                                          &zc, &len, err);
                release_sock(sk);
+               sk_defer_free_flush(sk);
                if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
                        goto zerocopy_rcv_cmsg;
                switch (len) {

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5ad81bf..3dd19a2 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2102,6 +2102,7 @@ process:
 
        sk_incoming_cpu_update(sk);
 
+       sk_defer_free_flush(sk);
        bh_lock_sock_nested(sk);
        tcp_segs_in(tcp_sk(sk), skb);
        ret = 0;

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index f41f14b..3b7d6ed 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1758,6 +1758,7 @@ process:
 
        sk_incoming_cpu_update(sk);
 
+       sk_defer_free_flush(sk);
        bh_lock_sock_nested(sk);
        tcp_segs_in(tcp_sk(sk), skb);
        ret = 0;