This patch introduces a new callback in tcp_tx_timestamp() to correlate
tcp_sendmsg timestamp with timestamps from other tx timestamping
callbacks (e.g., SND/SW/ACK).
Without this patch, BPF program wouldn't know which timestamps belong
to which flow because of no socket lock protection. This new callback
is inserted in tcp_tx_timestamp() to address this issue because
tcp_tx_timestamp() still owns the same socket lock with
tcp_sendmsg_locked() in the meanwhile tcp_tx_timestamp() initializes
the timestamping related fields for the skb, especially tskey. The
tskey is the bridge to do the correlation.
For TCP, BPF program hooks the beginning of tcp_sendmsg_locked() and
then stores the sendmsg timestamp at the bpf_sk_storage, correlating
this timestamp with its tskey that are later used in other sending
timestamping callbacks.
Reviewed-by: Willem de Bruijn <willemb@xxxxxxxxxx>
Signed-off-by: Jason Xing <kerneljasonxing@xxxxxxxxx>
---
include/uapi/linux/bpf.h | 5 +++++
net/ipv4/tcp.c | 4 ++++
tools/include/uapi/linux/bpf.h | 5 +++++
3 files changed, 14 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6f728342fabc..a46f6c35b232 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7053,6 +7053,11 @@ enum {
* when SK_BPF_CB_TX_TIMESTAMPING
* feature is on.
*/
+ BPF_SOCK_OPS_TSTAMP_SENDMSG_CB, /* Called when every sendmsg syscall
+ * is triggered. It's used to correlate
+ * sendmsg timestamp with corresponding
+ * tskey.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 12b9c4f9c151..2b4791a6791c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -492,6 +492,10 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
}
+
+ if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) &&
+ SK_BPF_CB_FLAG_TEST(sk, SK_BPF_CB_TX_TIMESTAMPING) && skb)
+ bpf_skops_tx_timestamping(sk, skb, BPF_SOCK_OPS_TSTAMP_SENDMSG_CB);
}
static bool tcp_stream_is_readable(struct sock *sk, int target)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 11d9fc3e3434..8429c01573cd 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7050,6 +7050,11 @@ enum {
* when SK_BPF_CB_TX_TIMESTAMPING
* feature is on.
*/
+ BPF_SOCK_OPS_TSTAMP_SENDMSG_CB, /* Called when every sendmsg syscall
+ * is triggered. It's used to correlate
+ * sendmsg timestamp with corresponding
+ * tskey.
+ */
};
/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
--
2.43.5
