[PATCH v14 14/14] WIP: migrate, tcp: Shrink windows before migration

[David Gibson <david@gibson.dropbear.id.au>]

From: Stefano Brivio <sbrivio@redhat.com>

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 flow.c     | 36 ++++++++++++++++++++++++++++++++++++
 flow.h     |  2 ++
 migrate.c  |  9 +++++++++
 tcp.c      | 30 ++++++++++++++++++++++++++++++
 tcp_conn.h |  1 +
 5 files changed, 78 insertions(+)

diff --git a/flow.c b/flow.c
index dbe57082..4807653a 100644
--- a/flow.c
+++ b/flow.c
@@ -956,6 +956,42 @@ static int flow_migrate_repair_all(struct ctx *c, bool enable)
 	return 0;
 }
 
+/**
+ * flow_migrate_source_early() - Early tasks: shrink (RFC 7323 2.2) TCP windows
+ * @c:		Execution context
+ * @stage:	Migration stage information, unused
+ * @fd:		Migration file descriptor, unused
+ *
+ * Return: 0 on success, positive error code on failure
+ */
+int flow_migrate_source_early(struct ctx *c, const struct migrate_stage *stage,
+			      int fd)
+{
+	union flow *flow;
+	unsigned i;
+	int rc;
+
+	(void)stage;
+	(void)fd;
+
+	/* We need repair mode to dump and set (some) window parameters */
+	if ((rc = flow_migrate_repair_all(c, true)))
+		return -rc;
+
+	foreach_tcp_flow(i, flow, FLOW_MAX) {
+		if ((rc = tcp_flow_migrate_shrink_window(i, &flow->tcp))) {
+			err("Shrinking window, flow %u: %s", i, strerror_(-rc));
+			return flow_migrate_source_rollback(c, i, -rc);
+		}
+	}
+
+	/* Now send window updates. We'll flip repair mode back on in a bit */
+	if ((rc = flow_migrate_repair_all(c, false)))
+		return -rc;
+
+	return 0;
+}
+
 /**
  * flow_migrate_source_pre() - Prepare flows for migration: enable repair mode
  * @c:		Execution context
diff --git a/flow.h b/flow.h
index a485c359..675726eb 100644
--- a/flow.h
+++ b/flow.h
@@ -249,6 +249,8 @@ union flow;
 
 void flow_init(void);
 void flow_defer_handler(const struct ctx *c, const struct timespec *now);
+int flow_migrate_source_early(struct ctx *c, const struct migrate_stage *stage,
+			      int fd);
 int flow_migrate_source_pre(struct ctx *c, const struct migrate_stage *stage,
 			    int fd);
 int flow_migrate_source(struct ctx *c, const struct migrate_stage *stage,
diff --git a/migrate.c b/migrate.c
index d035deda..b4e53b45 100644
--- a/migrate.c
+++ b/migrate.c
@@ -98,6 +98,15 @@ static int seen_addrs_target_v1(struct ctx *c,
 
 /* Stages for version 1 */
 static const struct migrate_stage stages_v1[] = {
+	/* FIXME: With this step, close() in tcp_flow_migrate_source_ext()
+	 * *sometimes* closes the connection for real.
+	 */
+/*	{
+		.name = "shrink TCP windows",
+		.source = flow_migrate_source_early,
+		.target = NULL,
+	},
+*/
 	{
 		.name = "observed addresses",
 		.source = seen_addrs_source_v1,
diff --git a/tcp.c b/tcp.c
index c3db1696..94bb059a 100644
--- a/tcp.c
+++ b/tcp.c
@@ -3061,6 +3061,36 @@ static int tcp_flow_repair_wnd(int s, uint32_t *snd_wl1, uint32_t *snd_wnd,
 	return 0;
 }
 
+/**
+ * tcp_flow_migrate_shrink_window() - Dump window data, decrease socket window
+ * @fidx:	Flow index
+ * @conn:	Pointer to the TCP connection structure
+ *
+ * Return: 0 on success, negative error code on failure
+ */
+int tcp_flow_migrate_shrink_window(int fidx, const struct tcp_tap_conn *conn)
+{
+	struct tcp_tap_transfer_ext *t = &migrate_ext[fidx];
+	struct tcp_repair_window wnd;
+	socklen_t sl = sizeof(wnd);
+	int s = conn->sock;
+
+	if (setsockopt(s, SOL_SOCKET, SO_RCVBUF, &((int){ 0 }), sizeof(int)))
+		debug("TCP: failed to set SO_RCVBUF to minimum value");
+
+	/* Dump window data as it is for the target, before touching stuff */
+	tcp_flow_repair_wnd(s, &t->sock_snd_wl1, &t->sock_snd_wnd,
+			    &t->sock_max_window, &t->sock_rcv_wnd,
+			    &t->sock_rcv_wup, &wnd);
+
+	wnd.rcv_wnd = 0;
+
+	if (setsockopt(s, IPPROTO_TCP, TCP_REPAIR_WINDOW, &wnd, sl))
+		debug_perror("Setting window repair data, socket %i", s);
+
+	return 0;
+}
+
 /**
  * tcp_flow_migrate_source() - Send data (flow table part) for a single flow
  * @c:		Execution context
diff --git a/tcp_conn.h b/tcp_conn.h
index 1c920a6e..b64e857a 100644
--- a/tcp_conn.h
+++ b/tcp_conn.h
@@ -227,6 +227,7 @@ bool tcp_flow_defer(const struct tcp_tap_conn *conn);
 int tcp_flow_repair_on(struct ctx *c, const struct tcp_tap_conn *conn);
 int tcp_flow_repair_off(struct ctx *c, const struct tcp_tap_conn *conn);
 
+int tcp_flow_migrate_shrink_window(int fidx, const struct tcp_tap_conn *conn);
 int tcp_flow_migrate_source(int fd, const struct tcp_tap_conn *conn);
 int tcp_flow_migrate_source_ext(int fd, int fidx,
 				const struct tcp_tap_conn *conn);
-- 
@@ -227,6 +227,7 @@ bool tcp_flow_defer(const struct tcp_tap_conn *conn);
 int tcp_flow_repair_on(struct ctx *c, const struct tcp_tap_conn *conn);
 int tcp_flow_repair_off(struct ctx *c, const struct tcp_tap_conn *conn);
 
+int tcp_flow_migrate_shrink_window(int fidx, const struct tcp_tap_conn *conn);
 int tcp_flow_migrate_source(int fd, const struct tcp_tap_conn *conn);
 int tcp_flow_migrate_source_ext(int fd, int fidx,
 				const struct tcp_tap_conn *conn);
-- 
2.48.1