public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: Jon Maloy <jmaloy@redhat.com>
To: passt-dev@passt.top, sbrivio@redhat.com, lvivier@redhat.com,
	dgibson@redhat.com, jmaloy@redhat.com
Subject: [PATCH v8] tcp: move seq_to_tap update to when frame is queued
Date: Tue,  4 Jun 2024 14:29:08 -0400	[thread overview]
Message-ID: <20240604182908.1833186-1-jmaloy@redhat.com> (raw)

commit a469fc393fa1 ("tcp, tap: Don't increase tap-side sequence counter for dropped frames")
delayed update of conn->seq_to_tap until the moment the corresponding
frame has been successfully pushed out. This has the advantage that we
immediately can make a new attempt to transmit a frame after a failed
trasnmit, rather than waiting for the peer to later discover a gap and
trigger the fast retransmit mechanism to solve the problem.

This approach has turned out to cause a problem with spurious sequence
number updates during peer-initiated retransmits, and we have realized
it may not be the best way to solve the above issue.

We now restore the previous method, by updating the said field at the
moment a frame is added to the outqueue. To retain the advantage of
having a quick re-attempt based on local failure detection, we now scan
through the part of the outqueue that had do be dropped, and restore the
sequence counter for each affected connection to the most appropriate
value.

Signed-off-by: Jon Maloy <jmaloy@redhat.com>

---
v2: - Re-spun loop in tcp_revert_seq() and some other changes based on
        feedback from Stefano Brivio.
    - Added paranoid test to avoid that seq_to_tap becomes lower than
      seq_ack_from_tap.

v3: - Identical to v2. Called v3 because it was embedded in a series
      with that version.

v4: - In tcp_revert_seq(), we read the sequence number from the TCP
      header instead of keeping a copy in struct tcp_buf_seq_update.
    - Since the only remaining field in struct tcp_buf_seq_update is
      a pointer to struct tcp_tap_conn, we eliminate the struct
      altogether, and make the tcp6/tcp3_buf_seq_update arrays into
      arrays of said pointer.
    - Removed 'paranoid' test in tcp_revert_seq. If it happens, it
      is not fatal, and will be caught by other code anyway.
    - Separated from the series again.

v5: - Changed way to index array within tcp_revert_seq()

v6-v7: No changes.

v8: Fixed missing indexing of tcp4/6_frame_conns array in
    tcp_payload_flush().
---
 tcp.c | 61 ++++++++++++++++++++++++++++++++++++++---------------------
 1 file changed, 39 insertions(+), 22 deletions(-)

diff --git a/tcp.c b/tcp.c
index 06acb41..89a5b19 100644
--- a/tcp.c
+++ b/tcp.c
@@ -408,16 +408,6 @@ static int tcp_sock_ns		[NUM_PORTS][IP_VERSIONS];
  */
 static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
 
-/**
- * tcp_buf_seq_update - Sequences to update with length of frames once sent
- * @seq:	Pointer to sequence number sent to tap-side, to be updated
- * @len:	TCP payload length
- */
-struct tcp_buf_seq_update {
-	uint32_t *seq;
-	uint16_t len;
-};
-
 /* Static buffers */
 /**
  * struct tcp_payload_t - TCP header and data to send segments with payload
@@ -459,7 +449,8 @@ static struct tcp_payload_t	tcp4_payload[TCP_FRAMES_MEM];
 
 static_assert(MSS4 <= sizeof(tcp4_payload[0].data), "MSS4 is greater than 65516");
 
-static struct tcp_buf_seq_update tcp4_seq_update[TCP_FRAMES_MEM];
+/* References tracking the owner connection of frames in the tap outqueue */
+static struct tcp_tap_conn *tcp4_frame_conns[TCP_FRAMES_MEM];
 static unsigned int tcp4_payload_used;
 
 static struct tap_hdr		tcp4_flags_tap_hdr[TCP_FRAMES_MEM];
@@ -481,7 +472,8 @@ static struct tcp_payload_t	tcp6_payload[TCP_FRAMES_MEM];
 
 static_assert(MSS6 <= sizeof(tcp6_payload[0].data), "MSS6 is greater than 65516");
 
-static struct tcp_buf_seq_update tcp6_seq_update[TCP_FRAMES_MEM];
+/* References tracking the owner connection of frames in the tap outqueue */
+static struct tcp_tap_conn *tcp6_frame_conns[TCP_FRAMES_MEM];
 static unsigned int tcp6_payload_used;
 
 static struct tap_hdr		tcp6_flags_tap_hdr[TCP_FRAMES_MEM];
@@ -1257,25 +1249,51 @@ static void tcp_flags_flush(const struct ctx *c)
 	tcp4_flags_used = 0;
 }
 
+/**
+ * tcp_revert_seq() - Revert affected conn->seq_to_tap after failed transmission
+ * @conns:       Array of connection pointers corresponding to queued frames
+ * @frames:      Two-dimensional array containing queued frames with sub-iovs
+ * @num_frames:  Number of entries in the two arrays to be compared
+ */
+static void tcp_revert_seq(struct tcp_tap_conn **conns, struct iovec (*frames)[TCP_NUM_IOVS],
+			   int num_frames)
+{
+	int i;
+
+	for (i = 0; i < num_frames; i++) {
+		struct tcp_tap_conn *conn = conns[i];
+		struct tcphdr *th = frames[i][TCP_IOV_PAYLOAD].iov_base;
+		uint32_t seq = ntohl(th->seq);
+
+		if (SEQ_LE(conn->seq_to_tap, seq))
+			continue;
+
+		conn->seq_to_tap = seq;
+	}
+}
+
 /**
  * tcp_payload_flush() - Send out buffers for segments with data
  * @c:		Execution context
  */
 static void tcp_payload_flush(const struct ctx *c)
 {
-	unsigned i;
 	size_t m;
 
 	m = tap_send_frames(c, &tcp6_l2_iov[0][0], TCP_NUM_IOVS,
 			    tcp6_payload_used);
-	for (i = 0; i < m; i++)
-		*tcp6_seq_update[i].seq += tcp6_seq_update[i].len;
+	if (m != tcp6_payload_used) {
+		tcp_revert_seq(&tcp6_frame_conns[m], &tcp6_l2_iov[m],
+			       tcp6_payload_used - m);
+	}
 	tcp6_payload_used = 0;
 
 	m = tap_send_frames(c, &tcp4_l2_iov[0][0], TCP_NUM_IOVS,
 			    tcp4_payload_used);
-	for (i = 0; i < m; i++)
-		*tcp4_seq_update[i].seq += tcp4_seq_update[i].len;
+	if (m != tcp4_payload_used) {
+		tcp_revert_seq(&tcp4_frame_conns[m], &tcp4_l2_iov[m],
+			       tcp4_payload_used - m);
+	}
 	tcp4_payload_used = 0;
 }
 
@@ -2129,10 +2147,11 @@ static int tcp_sock_consume(const struct tcp_tap_conn *conn, uint32_t ack_seq)
 static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
 			    ssize_t dlen, int no_csum, uint32_t seq)
 {
-	uint32_t *seq_update = &conn->seq_to_tap;
 	struct iovec *iov;
 	size_t l4len;
 
+	conn->seq_to_tap = seq + dlen;
+
 	if (CONN_V4(conn)) {
 		struct iovec *iov_prev = tcp4_l2_iov[tcp4_payload_used - 1];
 		const uint16_t *check = NULL;
@@ -2142,8 +2161,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
 			check = &iph->check;
 		}
 
-		tcp4_seq_update[tcp4_payload_used].seq = seq_update;
-		tcp4_seq_update[tcp4_payload_used].len = dlen;
+		tcp4_frame_conns[tcp4_payload_used] = conn;
 
 		iov = tcp4_l2_iov[tcp4_payload_used++];
 		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq);
@@ -2151,8 +2169,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
 		if (tcp4_payload_used > TCP_FRAMES_MEM - 1)
 			tcp_payload_flush(c);
 	} else if (CONN_V6(conn)) {
-		tcp6_seq_update[tcp6_payload_used].seq = seq_update;
-		tcp6_seq_update[tcp6_payload_used].len = dlen;
+		tcp6_frame_conns[tcp6_payload_used] = conn;
 
 		iov = tcp6_l2_iov[tcp6_payload_used++];
 		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq);
-- 
@@ -408,16 +408,6 @@ static int tcp_sock_ns		[NUM_PORTS][IP_VERSIONS];
  */
 static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE];
 
-/**
- * tcp_buf_seq_update - Sequences to update with length of frames once sent
- * @seq:	Pointer to sequence number sent to tap-side, to be updated
- * @len:	TCP payload length
- */
-struct tcp_buf_seq_update {
-	uint32_t *seq;
-	uint16_t len;
-};
-
 /* Static buffers */
 /**
  * struct tcp_payload_t - TCP header and data to send segments with payload
@@ -459,7 +449,8 @@ static struct tcp_payload_t	tcp4_payload[TCP_FRAMES_MEM];
 
 static_assert(MSS4 <= sizeof(tcp4_payload[0].data), "MSS4 is greater than 65516");
 
-static struct tcp_buf_seq_update tcp4_seq_update[TCP_FRAMES_MEM];
+/* References tracking the owner connection of frames in the tap outqueue */
+static struct tcp_tap_conn *tcp4_frame_conns[TCP_FRAMES_MEM];
 static unsigned int tcp4_payload_used;
 
 static struct tap_hdr		tcp4_flags_tap_hdr[TCP_FRAMES_MEM];
@@ -481,7 +472,8 @@ static struct tcp_payload_t	tcp6_payload[TCP_FRAMES_MEM];
 
 static_assert(MSS6 <= sizeof(tcp6_payload[0].data), "MSS6 is greater than 65516");
 
-static struct tcp_buf_seq_update tcp6_seq_update[TCP_FRAMES_MEM];
+/* References tracking the owner connection of frames in the tap outqueue */
+static struct tcp_tap_conn *tcp6_frame_conns[TCP_FRAMES_MEM];
 static unsigned int tcp6_payload_used;
 
 static struct tap_hdr		tcp6_flags_tap_hdr[TCP_FRAMES_MEM];
@@ -1257,25 +1249,51 @@ static void tcp_flags_flush(const struct ctx *c)
 	tcp4_flags_used = 0;
 }
 
+/**
+ * tcp_revert_seq() - Revert affected conn->seq_to_tap after failed transmission
+ * @conns:       Array of connection pointers corresponding to queued frames
+ * @frames:      Two-dimensional array containing queued frames with sub-iovs
+ * @num_frames:  Number of entries in the two arrays to be compared
+ */
+static void tcp_revert_seq(struct tcp_tap_conn **conns, struct iovec (*frames)[TCP_NUM_IOVS],
+			   int num_frames)
+{
+	int i;
+
+	for (i = 0; i < num_frames; i++) {
+		struct tcp_tap_conn *conn = conns[i];
+		struct tcphdr *th = frames[i][TCP_IOV_PAYLOAD].iov_base;
+		uint32_t seq = ntohl(th->seq);
+
+		if (SEQ_LE(conn->seq_to_tap, seq))
+			continue;
+
+		conn->seq_to_tap = seq;
+	}
+}
+
 /**
  * tcp_payload_flush() - Send out buffers for segments with data
  * @c:		Execution context
  */
 static void tcp_payload_flush(const struct ctx *c)
 {
-	unsigned i;
 	size_t m;
 
 	m = tap_send_frames(c, &tcp6_l2_iov[0][0], TCP_NUM_IOVS,
 			    tcp6_payload_used);
-	for (i = 0; i < m; i++)
-		*tcp6_seq_update[i].seq += tcp6_seq_update[i].len;
+	if (m != tcp6_payload_used) {
+		tcp_revert_seq(&tcp6_frame_conns[m], &tcp6_l2_iov[m],
+			       tcp6_payload_used - m);
+	}
 	tcp6_payload_used = 0;
 
 	m = tap_send_frames(c, &tcp4_l2_iov[0][0], TCP_NUM_IOVS,
 			    tcp4_payload_used);
-	for (i = 0; i < m; i++)
-		*tcp4_seq_update[i].seq += tcp4_seq_update[i].len;
+	if (m != tcp4_payload_used) {
+		tcp_revert_seq(&tcp4_frame_conns[m], &tcp4_l2_iov[m],
+			       tcp4_payload_used - m);
+	}
 	tcp4_payload_used = 0;
 }
 
@@ -2129,10 +2147,11 @@ static int tcp_sock_consume(const struct tcp_tap_conn *conn, uint32_t ack_seq)
 static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
 			    ssize_t dlen, int no_csum, uint32_t seq)
 {
-	uint32_t *seq_update = &conn->seq_to_tap;
 	struct iovec *iov;
 	size_t l4len;
 
+	conn->seq_to_tap = seq + dlen;
+
 	if (CONN_V4(conn)) {
 		struct iovec *iov_prev = tcp4_l2_iov[tcp4_payload_used - 1];
 		const uint16_t *check = NULL;
@@ -2142,8 +2161,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
 			check = &iph->check;
 		}
 
-		tcp4_seq_update[tcp4_payload_used].seq = seq_update;
-		tcp4_seq_update[tcp4_payload_used].len = dlen;
+		tcp4_frame_conns[tcp4_payload_used] = conn;
 
 		iov = tcp4_l2_iov[tcp4_payload_used++];
 		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq);
@@ -2151,8 +2169,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
 		if (tcp4_payload_used > TCP_FRAMES_MEM - 1)
 			tcp_payload_flush(c);
 	} else if (CONN_V6(conn)) {
-		tcp6_seq_update[tcp6_payload_used].seq = seq_update;
-		tcp6_seq_update[tcp6_payload_used].len = dlen;
+		tcp6_frame_conns[tcp6_payload_used] = conn;
 
 		iov = tcp6_l2_iov[tcp6_payload_used++];
 		l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq);
-- 
2.42.0


             reply	other threads:[~2024-06-04 18:29 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-04 18:29 Jon Maloy [this message]
2024-06-04 21:30 ` [PATCH v8] tcp: move seq_to_tap update to when frame is queued Stefano Brivio
2024-06-04 23:59   ` David Gibson
2024-06-05  9:53     ` Stefano Brivio
2024-06-05 16:21   ` Jon Maloy
2024-06-04 23:59 ` David Gibson
2024-06-05 19:58 ` Stefano Brivio

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240604182908.1833186-1-jmaloy@redhat.com \
    --to=jmaloy@redhat.com \
    --cc=dgibson@redhat.com \
    --cc=lvivier@redhat.com \
    --cc=passt-dev@passt.top \
    --cc=sbrivio@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).