summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
authorMike Maloney <maloney@google.com>2017-08-22 17:08:48 -0400
committerDavid S. Miller <davem@davemloft.net>2017-08-23 20:30:47 -0700
commit98aaa913b4ed250324429f0a9e6d5f77a3b5276c (patch)
tree651cb3f820b76e3b199d25c4997dd0e494cdcc06 /net/ipv4/tcp.c
parentb28547728d4fd42a004df2b662724e16ff778db6 (diff)
downloadop-kernel-dev-98aaa913b4ed250324429f0a9e6d5f77a3b5276c.zip
op-kernel-dev-98aaa913b4ed250324429f0a9e6d5f77a3b5276c.tar.gz
tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg
When SOF_TIMESTAMPING_RX_SOFTWARE is enabled for tcp sockets, return the timestamp corresponding to the highest sequence number data returned. Previously the skb->tstamp is overwritten when a TCP packet is placed in the out of order queue. While the packet is in the ooo queue, save the timestamp in the TCB_SKB_CB. This space is shared with the gso_* options which are only used on the tx path, and a previously unused 4 byte hole. When skbs are coalesced either in the sk_receive_queue or the out_of_order_queue always choose the timestamp of the appended skb to maintain the invariant of returning the timestamp of the last byte in the recvmsg buffer. Signed-off-by: Mike Maloney <maloney@google.com> Acked-by: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c65
1 files changed, 65 insertions, 0 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d25e3bc..0cce447 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -269,6 +269,7 @@
#include <linux/err.h>
#include <linux/time.h>
#include <linux/slab.h>
+#include <linux/errqueue.h>
#include <net/icmp.h>
#include <net/inet_common.h>
@@ -1695,6 +1696,61 @@ int tcp_peek_len(struct socket *sock)
}
EXPORT_SYMBOL(tcp_peek_len);
+static void tcp_update_recv_tstamps(struct sk_buff *skb,
+ struct scm_timestamping *tss)
+{
+ if (skb->tstamp)
+ tss->ts[0] = ktime_to_timespec(skb->tstamp);
+ else
+ tss->ts[0] = (struct timespec) {0};
+
+ if (skb_hwtstamps(skb)->hwtstamp)
+ tss->ts[2] = ktime_to_timespec(skb_hwtstamps(skb)->hwtstamp);
+ else
+ tss->ts[2] = (struct timespec) {0};
+}
+
+/* Similar to __sock_recv_timestamp, but does not require an skb */
+void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+ struct scm_timestamping *tss)
+{
+ struct timeval tv;
+ bool has_timestamping = false;
+
+ if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) {
+ if (sock_flag(sk, SOCK_RCVTSTAMP)) {
+ if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
+ put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS,
+ sizeof(tss->ts[0]), &tss->ts[0]);
+ } else {
+ tv.tv_sec = tss->ts[0].tv_sec;
+ tv.tv_usec = tss->ts[0].tv_nsec / 1000;
+
+ put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP,
+ sizeof(tv), &tv);
+ }
+ }
+
+ if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE)
+ has_timestamping = true;
+ else
+ tss->ts[0] = (struct timespec) {0};
+ }
+
+ if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
+ if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)
+ has_timestamping = true;
+ else
+ tss->ts[2] = (struct timespec) {0};
+ }
+
+ if (has_timestamping) {
+ tss->ts[1] = (struct timespec) {0};
+ put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING,
+ sizeof(*tss), tss);
+ }
+}
+
/*
* This routine copies from a sock struct into the user buffer.
*
@@ -1716,6 +1772,8 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
long timeo;
struct sk_buff *skb, *last;
u32 urg_hole = 0;
+ struct scm_timestamping tss;
+ bool has_tss = false;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
@@ -1911,6 +1969,10 @@ skip_copy:
if (used + offset < skb->len)
continue;
+ if (TCP_SKB_CB(skb)->has_rxtstamp) {
+ tcp_update_recv_tstamps(skb, &tss);
+ has_tss = true;
+ }
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
goto found_fin_ok;
if (!(flags & MSG_PEEK))
@@ -1929,6 +1991,9 @@ skip_copy:
* on connected socket. I was just happy when found this 8) --ANK
*/
+ if (has_tss)
+ tcp_recv_timestamp(msg, sk, &tss);
+
/* Clean up data we have read: This will do ACK frames. */
tcp_cleanup_rbuf(sk, copied);
OpenPOWER on IntegriCloud