tipc-discussion

[tipc-discussion] [PATCH net-next 0/8] tipc: add PLPMTUD probe and GSO offload

[Xin L. <luc...@gm...>]

This patchset is to implement PLPMTUD and GSO for TIPC,
Patch 1-5 are for PLPMTUD while 6-8 are for GSO.

It gets some ideas from SCTP as their similarities like
both are reliable datagram packets and possible to run
over IP(v6)/UDP. But also it does some adjustments for
TIPC.

Xin Long (8):
  tipc: set the mtu for bearer properly for udp media
  tipc: add the constants and variables for plpmtud
  tipc: build probe and its reply in tipc_link_build_proto_msg
  tipc: add probe send and state transition
  tipc: add probe recv and state transition
  tipc: add offload base
  tipc: add software gso
  tipc: add hardware gso

 include/uapi/linux/tipc_config.h |   6 --
 net/tipc/Makefile                |   2 +-
 net/tipc/bearer.c                |  23 ++++-
 net/tipc/core.c                  |   3 +
 net/tipc/link.c                  | 147 +++++++++++++++++++++++++++----
 net/tipc/link.h                  |  29 ++++++
 net/tipc/msg.c                   |   1 +
 net/tipc/msg.h                   |   3 +
 net/tipc/node.c                  |  15 +++-
 net/tipc/offload.c               |  70 +++++++++++++++
 net/tipc/udp_media.c             |  18 ++--
 11 files changed, 287 insertions(+), 30 deletions(-)
 create mode 100644 net/tipc/offload.c

-- 
2.27.0

[tipc-discussion] [PATCH net-next 1/8] tipc: set the mtu for bearer properly for udp media

[Xin L. <luc...@gm...>]

Instead of using 14000 for ipv4/udp mtu, and 1280 for ipv6/udp
mtu, this patch to set mtu according to the lower device's mtu
at the beginning. The pmtu will be determined by the PLPMTUD
probe in the following patches.

Signed-off-by: Xin Long <luc...@gm...>
---
 include/uapi/linux/tipc_config.h | 6 ------
 net/tipc/udp_media.c             | 8 ++++----
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h
index 4dfc05651c98..7e23b7f438b4 100644
--- a/include/uapi/linux/tipc_config.h
+++ b/include/uapi/linux/tipc_config.h
@@ -185,12 +185,6 @@
 #define TIPC_DEF_LINK_WIN 50
 #define TIPC_MAX_LINK_WIN 8191
 
-/*
- * Default MTU for UDP media
- */
-
-#define TIPC_DEF_LINK_UDP_MTU 14000
-
 struct tipc_node_info {
 	__be32 addr;			/* network address of node */
 	__be32 up;			/* 0=down, 1= up */
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index c2bb818704c8..dc4bae965549 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -661,7 +661,7 @@ int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr)
 static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 			   struct nlattr *attrs[])
 {
-	int err = -EINVAL;
+	int err = -EINVAL, hlen;
 	struct udp_bearer *ub;
 	struct udp_media_addr remote = {0};
 	struct udp_media_addr local = {0};
@@ -743,7 +743,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 			err = -EINVAL;
 			goto err;
 		}
-		b->mtu = b->media->mtu;
+		hlen = sizeof(struct iphdr);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (local.proto == htons(ETH_P_IPV6)) {
 		dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL;
@@ -760,12 +760,13 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 		else
 			udp_conf.local_ip6 = local.ipv6;
 		ub->ifindex = dev->ifindex;
-		b->mtu = 1280;
+		hlen = sizeof(struct ipv6hdr);
 #endif
 	} else {
 		err = -EAFNOSUPPORT;
 		goto err;
 	}
+	b->mtu = b->media->mtu ?: dev->mtu - hlen - sizeof(struct udphdr);
 	udp_conf.local_udp_port = local.port;
 	err = udp_sock_create(net, &udp_conf, &ub->ubsock);
 	if (err)
@@ -851,7 +852,6 @@ struct tipc_media udp_media_info = {
 	.tolerance	= TIPC_DEF_LINK_TOL,
 	.min_win	= TIPC_DEF_LINK_WIN,
 	.max_win	= TIPC_DEF_LINK_WIN,
-	.mtu		= TIPC_DEF_LINK_UDP_MTU,
 	.type_id	= TIPC_MEDIA_TYPE_UDP,
 	.hwaddr_len	= 0,
 	.name		= "udp"
-- 
2.27.0

[tipc-discussion] [PATCH net-next 2/8] tipc: add the constants and variables for plpmtud

[Xin L. <luc...@gm...>]

These are 4 constants described in rfc8899#section-5.1.2:

  MAX_PROBES, MIN_PLPMTU, MAX_PLPMTU, BASE_PLPMTU;

And 2 variables described in rfc8899#section-5.1.3:

  PROBED_SIZE, PROBE_COUNT;

And 5 states described in rfc8899#section-5.2:

  DISABLED, BASE, SEARCH, SEARCH_COMPLETE, ERROR;

'count' and 'raise' are used for two timers' counting:
PROBE_TIMER and PMTU_RAISE_TIMER. 'probe_high' is used
for finding the optimal value for pmtu.

Signed-off-by: Xin Long <luc...@gm...>
---
 net/tipc/link.c | 13 +++++++++++++
 net/tipc/link.h | 20 ++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index cf586840caeb..1aa775cef3bb 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -182,6 +182,14 @@ struct tipc_link {
 	/* Max packet negotiation */
 	u16 mtu;
 	u16 advertised_mtu;
+	struct {
+		u16 probe_size;
+		u16 probe_high;
+		u16 pmtu;
+		u8 count;
+		u8 state:3;
+		u8 raise:5;
+	} pl;
 
 	/* Sending */
 	struct sk_buff_head transmq;
@@ -984,6 +992,11 @@ void tipc_link_reset(struct tipc_link *l)
 	l->peer_session--;
 	l->session++;
 	l->mtu = l->advertised_mtu;
+	l->pl.state = TIPC_PL_BASE;
+	l->pl.pmtu = TIPC_BASE_PLPMTU;
+	l->pl.probe_size = TIPC_BASE_PLPMTU;
+	l->pl.count = 0;
+	l->pl.probe_high = 0;
 
 	spin_lock_bh(&l->wakeupq.lock);
 	skb_queue_splice_init(&l->wakeupq, &list);
diff --git a/net/tipc/link.h b/net/tipc/link.h
index a16f401fdabd..30bee2562987 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -66,6 +66,26 @@ enum {
 	TIPC_LINK_SND_STATE    = (1 << 2)
 };
 
+/* PLPMTUD state
+ */
+enum {
+	TIPC_PL_DISABLED,
+	TIPC_PL_BASE,
+	TIPC_PL_SEARCH,
+	TIPC_PL_COMPLETE,
+	TIPC_PL_ERROR,
+};
+
+#define	TIPC_BASE_PLPMTU	1200
+#define	TIPC_MAX_PLPMTU		9000
+#define	TIPC_MIN_PLPMTU		512
+
+#define	TIPC_MAX_PROBES		3
+#define	TIPC_PROBE_INTERVAL	10
+
+#define	TIPC_PL_BIG_STEP	32
+#define	TIPC_PL_MIN_STEP	4
+
 /* Starting value for maximum packet size negotiation on unicast links
  * (unless bearer MTU is less)
  */
-- 
2.27.0

[tipc-discussion] [PATCH net-next 4/8] tipc: add probe send and state transition

[Xin L. <luc...@gm...>]

pl.count will make a timer that 'timeout' every after '10 * node timer
interval', where it does state transition in tipc_link_pl_send() and
sends probe in tipc_link_build_proto_msg().

For the details, see:

  https://lwn.net/Articles/860385/

Signed-off-by: Xin Long <luc...@gm...>
---
 net/tipc/link.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 414f9cf543ff..3af6c04f82c2 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -292,6 +292,7 @@ static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r,
 				     bool *retransmitted, int *rc);
 static void tipc_link_update_cwin(struct tipc_link *l, int released,
 				  bool retransmitted);
+static void tipc_link_pl_send(struct tipc_link *l);
 /*
  *  Simple non-static link routines (i.e. referenced outside this file)
  */
@@ -902,6 +903,14 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 	if (state || probe || setup)
 		tipc_link_build_proto_msg(l, mtyp, PROBE_MSTATE, 0, 0, 0, 0, xmitq);
 
+	if (probe && tipc_link_is_up(l)) {
+		l->pl.count++;
+		if (!(l->pl.count % TIPC_PROBE_INTERVAL)) {
+			tipc_link_pl_send(l);
+			tipc_link_build_proto_msg(l, mtyp, PROBE_PLPMTU, 0, 0, 0, 0, xmitq);
+		}
+	}
+
 	return rc;
 }
 
@@ -3013,3 +3022,42 @@ int tipc_link_dump(struct tipc_link *l, u16 dqueues, char *buf)
 
 	return i;
 }
+
+static void tipc_link_pl_send(struct tipc_link *l)
+{
+	pr_debug("%s: PLPMTUD: link: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+		 __func__, l, l->pl.state, l->pl.pmtu, l->pl.probe_size, l->pl.probe_high);
+
+	if (l->pl.count <= TIPC_MAX_PROBES * TIPC_PROBE_INTERVAL)
+		return;
+
+	if (l->pl.state == TIPC_PL_BASE) {
+		if (l->pl.probe_size == TIPC_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
+			l->pl.state = TIPC_PL_ERROR; /* Base -> Error */
+
+			l->pl.pmtu = TIPC_MIN_PLPMTU;
+			l->mtu = l->pl.pmtu;
+		}
+	} else if (l->pl.state == TIPC_PL_SEARCH) {
+		if (l->pl.pmtu == l->pl.probe_size) { /* Black Hole Detected */
+			l->pl.state = TIPC_PL_BASE;  /* Search -> Base */
+			l->pl.probe_size = TIPC_BASE_PLPMTU;
+			l->pl.probe_high = 0;
+
+			l->pl.pmtu = TIPC_BASE_PLPMTU;
+			l->mtu = l->pl.pmtu;
+		} else { /* Normal probe failure. */
+			l->pl.probe_high = l->pl.probe_size;
+			l->pl.probe_size = l->pl.pmtu;
+		}
+	} else if (l->pl.state == TIPC_PL_COMPLETE) {
+		if (l->pl.pmtu == l->pl.probe_size) { /* Black Hole Detected */
+			l->pl.state = TIPC_PL_BASE;  /* Search Complete -> Base */
+			l->pl.probe_size = TIPC_BASE_PLPMTU;
+
+			l->pl.pmtu = TIPC_BASE_PLPMTU;
+			l->mtu = l->pl.pmtu;
+		}
+	}
+	l->pl.count = TIPC_PROBE_INTERVAL;
+}
-- 
2.27.0

[tipc-discussion] [PATCH net-next 3/8] tipc: build probe and its reply in tipc_link_build_proto_msg

[Xin L. <luc...@gm...>]

This patch is to adjust the code in tipc_link_build_proto_msg()
to make it able to build probe packet with a specific size for
sender, and probe reply packet with mtu set.

Note that to send the probe packet, the df flag has to be set.

Signed-off-by: Xin Long <luc...@gm...>
---
 net/tipc/link.c      | 38 +++++++++++++++++++++++---------------
 net/tipc/link.h      |  9 +++++++++
 net/tipc/msg.c       |  1 +
 net/tipc/udp_media.c |  3 ++-
 4 files changed, 35 insertions(+), 16 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 1aa775cef3bb..414f9cf543ff 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -273,8 +273,8 @@ static int link_is_up(struct tipc_link *l)
 
 static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			       struct sk_buff_head *xmitq);
-static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
-				      bool probe_reply, u16 rcvgap,
+static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp,
+				      u8 ptype, u32 mtu, u16 rcvgap,
 				      int tolerance, int priority,
 				      struct sk_buff_head *xmitq);
 static void link_print(struct tipc_link *l, const char *str);
@@ -900,7 +900,7 @@ int tipc_link_timeout(struct tipc_link *l, struct sk_buff_head *xmitq)
 	}
 
 	if (state || probe || setup)
-		tipc_link_build_proto_msg(l, mtyp, probe, 0, 0, 0, 0, xmitq);
+		tipc_link_build_proto_msg(l, mtyp, PROBE_MSTATE, 0, 0, 0, 0, xmitq);
 
 	return rc;
 }
@@ -1862,8 +1862,8 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
 	return rc;
 }
 
-static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
-				      bool probe_reply, u16 rcvgap,
+static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp,
+				      u8 ptype, u32 mtu, u16 rcvgap,
 				      int tolerance, int priority,
 				      struct sk_buff_head *xmitq)
 {
@@ -1874,7 +1874,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 	struct sk_buff *skb;
 	bool node_up = link_is_up(bcl);
 	u16 glen = 0, bc_rcvgap = 0;
-	int dlen = 0;
+	int dlen = 0, msg_sz;
 	void *data;
 
 	/* Don't send protocol message during reset or link failover */
@@ -1884,11 +1884,13 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 	if (!tipc_link_is_up(l) && (mtyp == STATE_MSG))
 		return;
 
-	if ((probe || probe_reply) && !skb_queue_empty(dfq))
+	if (ptype && !skb_queue_empty(dfq))
 		rcvgap = buf_seqno(skb_peek(dfq)) - l->rcv_nxt;
 
-	skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE,
-			      tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ,
+	msg_sz = tipc_max_domain_size + MAX_GAP_ACK_BLKS_SZ;
+	if (ptype == PROBE_PLPMTU)
+		msg_sz = l->pl.probe_size - INT_H_SIZE;
+	skb = tipc_msg_create(LINK_PROTOCOL, mtyp, INT_H_SIZE, msg_sz,
 			      l->addr, tipc_own_addr(l->net), 0, 0, 0);
 	if (!skb)
 		return;
@@ -1915,13 +1917,19 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 		msg_set_seq_gap(hdr, rcvgap);
 		bc_rcvgap = link_bc_rcv_gap(bcl);
 		msg_set_bc_gap(hdr, bc_rcvgap);
-		msg_set_probe(hdr, probe);
-		msg_set_is_keepalive(hdr, probe || probe_reply);
+		msg_set_probe(hdr, ptype == PROBE_MSTATE || ptype == PROBE_PLPMTU);
+		msg_set_is_keepalive(hdr, !!ptype);
+		if (ptype == PROBE_REPLY)
+			msg_set_max_pkt(hdr, mtu);
 		if (l->peer_caps & TIPC_GAP_ACK_BLOCK)
 			glen = tipc_build_gap_ack_blks(l, hdr);
 		tipc_mon_prep(l->net, data + glen, &dlen, mstate, l->bearer_id);
-		msg_set_size(hdr, INT_H_SIZE + glen + dlen);
-		skb_trim(skb, INT_H_SIZE + glen + dlen);
+		if (ptype != PROBE_PLPMTU) {
+			msg_set_size(hdr, INT_H_SIZE + glen + dlen);
+			skb_trim(skb, INT_H_SIZE + glen + dlen);
+		} else {
+			skb->ignore_df = 0;
+		}
 		l->stats.sent_states++;
 		l->rcv_unacked = 0;
 	} else {
@@ -1935,7 +1943,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 		msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME);
 		skb_trim(skb, INT_H_SIZE + TIPC_MAX_IF_NAME);
 	}
-	if (probe)
+	if (ptype == PROBE_MSTATE || ptype == PROBE_PLPMTU)
 		l->stats.sent_probes++;
 	if (rcvgap)
 		l->stats.sent_nacks++;
@@ -2329,7 +2337,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		    skb_queue_empty(&l->deferdq))
 			rcvgap = peers_snd_nxt - l->rcv_nxt;
 		if (rcvgap || reply)
-			tipc_link_build_proto_msg(l, STATE_MSG, 0, reply,
+			tipc_link_build_proto_msg(l, STATE_MSG, PROBE_REPLY, msg_size(hdr),
 						  rcvgap, 0, 0, xmitq);
 
 		released = tipc_link_advance_transmq(l, l, ack, gap, ga, xmitq,
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 30bee2562987..87b3ebe5b91d 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -66,6 +66,15 @@ enum {
 	TIPC_LINK_SND_STATE    = (1 << 2)
 };
 
+/* Probe Type
+ */
+enum {
+	PROBE_NONE,
+	PROBE_MSTATE,
+	PROBE_REPLY,
+	PROBE_PLPMTU,
+};
+
 /* PLPMTUD state
  */
 enum {
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 5c9fd4791c4b..6d8bcc180f8b 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -75,6 +75,7 @@ struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
 		skb_put(skb, size);
 		skb->next = NULL;
 	}
+	skb->ignore_df = 1;
 	return skb;
 }
 
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index dc4bae965549..5078c5b19e81 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -174,6 +174,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 	local_bh_disable();
 	ndst = dst_cache_get(cache);
 	if (dst->proto == htons(ETH_P_IP)) {
+		u8 df = skb->ignore_df ? 0 : htons(IP_DF);
 		struct rtable *rt = (struct rtable *)ndst;
 
 		if (!rt) {
@@ -193,7 +194,7 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb,
 
 		ttl = ip4_dst_hoplimit(&rt->dst);
 		udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr,
-				    dst->ipv4.s_addr, 0, ttl, 0, src->port,
+				    dst->ipv4.s_addr, 0, ttl, df, src->port,
 				    dst->port, false, true);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else {
-- 
2.27.0

[tipc-discussion] [PATCH net-next 5/8] tipc: add probe recv and state transition

[Xin L. <luc...@gm...>]

This patch is to receive and process the probe ack by checking
msg_max_pkt() == l->pl.probe_size then does state transition
in tipc_link_pl_recv().

For the details, see:

  https://lwn.net/Articles/860385/

Signed-off-by: Xin Long <luc...@gm...>
---
 net/tipc/link.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 3af6c04f82c2..241c9378e258 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -293,6 +293,7 @@ static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r,
 static void tipc_link_update_cwin(struct tipc_link *l, int released,
 				  bool retransmitted);
 static void tipc_link_pl_send(struct tipc_link *l);
+static void tipc_link_pl_recv(struct tipc_link *l);
 /*
  *  Simple non-static link routines (i.e. referenced outside this file)
  */
@@ -2333,6 +2334,13 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			break;
 		}
 
+		if (!reply && msg_max_pkt(hdr) == l->pl.probe_size) {
+			tipc_link_pl_recv(l);
+			if (l->pl.state == TIPC_PL_COMPLETE)
+				break;
+			tipc_link_build_proto_msg(l, STATE_MSG, PROBE_PLPMTU, 0, 0, 0, 0, xmitq);
+		}
+
 		/* Receive Gap ACK blocks from peer if any */
 		glen = tipc_get_gap_ack_blks(&ga, l, hdr, true);
 
@@ -3061,3 +3069,43 @@ static void tipc_link_pl_send(struct tipc_link *l)
 	}
 	l->pl.count = TIPC_PROBE_INTERVAL;
 }
+
+static void tipc_link_pl_recv(struct tipc_link *l)
+{
+	pr_debug("%s: PLPMTUD: link: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+		 __func__, l, l->pl.state, l->pl.pmtu, l->pl.probe_size, l->pl.probe_high);
+
+	l->pl.pmtu = l->pl.probe_size;
+	l->pl.count = 0;
+	if (l->pl.state == TIPC_PL_BASE) {
+		l->pl.state = TIPC_PL_SEARCH; /* Base -> Search */
+		l->pl.probe_size += TIPC_PL_BIG_STEP;
+	} else if (l->pl.state == TIPC_PL_ERROR) {
+		l->pl.state = TIPC_PL_SEARCH; /* Error -> Search */
+
+		l->pl.pmtu = l->pl.probe_size;
+		l->mtu = l->pl.pmtu;
+		l->pl.probe_size += TIPC_PL_BIG_STEP;
+	} else if (l->pl.state == TIPC_PL_SEARCH) {
+		if (!l->pl.probe_high) {
+			l->pl.probe_size = min(l->pl.probe_size + TIPC_PL_BIG_STEP,
+					       TIPC_MAX_PLPMTU);
+			return;
+		}
+		l->pl.probe_size += TIPC_PL_MIN_STEP;
+		if (l->pl.probe_size >= l->pl.probe_high) {
+			l->pl.probe_high = 0;
+			l->pl.raise = 0;
+			l->pl.state = TIPC_PL_COMPLETE; /* Search -> Search Complete */
+
+			l->pl.probe_size = l->pl.pmtu;
+			l->mtu = l->pl.pmtu;
+		}
+	} else if (l->pl.state == TIPC_PL_COMPLETE) {
+		l->pl.raise++;
+		if (l->pl.raise == 30) {
+			l->pl.state = TIPC_PL_SEARCH; /* Search Complete -> Search */
+			l->pl.probe_size += TIPC_PL_MIN_STEP;
+		}
+	}
+}
-- 
2.27.0

Re: [tipc-discussion] [PATCH net-next 5/8] tipc: add probe recv and state transition

[Jon M. <jm...@re...>]

On 06/07/2021 14:22, Xin Long wrote:
> This patch is to receive and process the probe ack by checking
> msg_max_pkt() == l->pl.probe_size then does state transition
> in tipc_link_pl_recv().
> 
> For the details, see:
> 
>    https://lwn.net/Articles/860385/
> 
> Signed-off-by: Xin Long <luc...@gm...>
> ---
>   net/tipc/link.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
>   1 file changed, 48 insertions(+)
> 
> diff --git a/net/tipc/link.c b/net/tipc/link.c
> index 3af6c04f82c2..241c9378e258 100644
> --- a/net/tipc/link.c
> +++ b/net/tipc/link.c
> @@ -293,6 +293,7 @@ static int tipc_link_advance_transmq(struct tipc_link *l, struct tipc_link *r,
>   static void tipc_link_update_cwin(struct tipc_link *l, int released,
>   				  bool retransmitted);
>   static void tipc_link_pl_send(struct tipc_link *l);
> +static void tipc_link_pl_recv(struct tipc_link *l);
>   /*
>    *  Simple non-static link routines (i.e. referenced outside this file)
>    */
> @@ -2333,6 +2334,13 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
>   			break;
>   		}
>   
> +		if (!reply && msg_max_pkt(hdr) == l->pl.probe_size) {
> +			tipc_link_pl_recv(l);
> +			if (l->pl.state == TIPC_PL_COMPLETE)
> +				break;
> +			tipc_link_build_proto_msg(l, STATE_MSG, PROBE_PLPMTU, 0, 0, 0, 0, xmitq);
> +		}
> +
>   		/* Receive Gap ACK blocks from peer if any */
>   		glen = tipc_get_gap_ack_blks(&ga, l, hdr, true);
>   
> @@ -3061,3 +3069,43 @@ static void tipc_link_pl_send(struct tipc_link *l)
>   	}
>   	l->pl.count = TIPC_PROBE_INTERVAL;
>   }
> +
> +static void tipc_link_pl_recv(struct tipc_link *l)
> +{
> +	pr_debug("%s: PLPMTUD: link: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
> +		 __func__, l, l->pl.state, l->pl.pmtu, l->pl.probe_size, l->pl.probe_high);

Many of these lines will not pass checkpatch.
///jon

> +
> +	l->pl.pmtu = l->pl.probe_size;
> +	l->pl.count = 0;
> +	if (l->pl.state == TIPC_PL_BASE) {
> +		l->pl.state = TIPC_PL_SEARCH; /* Base -> Search */
> +		l->pl.probe_size += TIPC_PL_BIG_STEP;
> +	} else if (l->pl.state == TIPC_PL_ERROR) {
> +		l->pl.state = TIPC_PL_SEARCH; /* Error -> Search */
> +
> +		l->pl.pmtu = l->pl.probe_size;
> +		l->mtu = l->pl.pmtu;
> +		l->pl.probe_size += TIPC_PL_BIG_STEP;
> +	} else if (l->pl.state == TIPC_PL_SEARCH) {
> +		if (!l->pl.probe_high) {
> +			l->pl.probe_size = min(l->pl.probe_size + TIPC_PL_BIG_STEP,
> +					       TIPC_MAX_PLPMTU);
> +			return;
> +		}
> +		l->pl.probe_size += TIPC_PL_MIN_STEP;
> +		if (l->pl.probe_size >= l->pl.probe_high) {
> +			l->pl.probe_high = 0;
> +			l->pl.raise = 0;
> +			l->pl.state = TIPC_PL_COMPLETE; /* Search -> Search Complete */
> +
> +			l->pl.probe_size = l->pl.pmtu;
> +			l->mtu = l->pl.pmtu;
> +		}
> +	} else if (l->pl.state == TIPC_PL_COMPLETE) {
> +		l->pl.raise++;
> +		if (l->pl.raise == 30) {
> +			l->pl.state = TIPC_PL_SEARCH; /* Search Complete -> Search */
> +			l->pl.probe_size += TIPC_PL_MIN_STEP;
> +		}
> +	}
> +}
> 

[tipc-discussion] [PATCH net-next 8/8] tipc: add hardware gso

[Xin L. <luc...@gm...>]

Since there's no enough bit in netdev_features_t for
NETIF_F_GSO_TIPC_BIT, and tipc is using the simliar
code as sctp, this patch will reuse SKB_GSO_SCTP and
NETIF_F_GSO_SCTP_BIT for tipc.

Signed-off-by: Xin Long <luc...@gm...>
---
 include/linux/skbuff.h |  2 --
 net/tipc/node.c        | 15 ++++++++++++++-
 net/tipc/offload.c     |  4 ++--
 3 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 148bf0ed7336..b2db9cd9a73f 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -599,8 +599,6 @@ enum {
 	SKB_GSO_UDP_L4 = 1 << 17,
 
 	SKB_GSO_FRAGLIST = 1 << 18,
-
-	SKB_GSO_TIPC = 1 << 19,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 9947b7dfe1d2..17e59c8dac31 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -2068,7 +2068,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
  * Invoked with no locks held. Bearer pointer must point to a valid bearer
  * structure (i.e. cannot be NULL), but bearer can be inactive.
  */
-void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
+static void __tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 {
 	struct sk_buff_head xmitq;
 	struct tipc_link_entry *le;
@@ -2189,6 +2189,19 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
 	kfree_skb(skb);
 }
 
+void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
+{
+	struct sk_buff *seg, *next;
+
+	if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
+		return __tipc_rcv(net, skb, b);
+
+	skb_list_walk_safe(skb_shinfo(skb)->frag_list, seg, next)
+		__tipc_rcv(net, seg, b);
+	skb_shinfo(skb)->frag_list = NULL;
+	consume_skb(skb);
+}
+
 void tipc_node_apply_property(struct net *net, struct tipc_bearer *b,
 			      int prop)
 {
diff --git a/net/tipc/offload.c b/net/tipc/offload.c
index d137679f4db0..26e372178635 100644
--- a/net/tipc/offload.c
+++ b/net/tipc/offload.c
@@ -5,7 +5,7 @@
 static struct sk_buff *tipc_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
-	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TIPC))
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP))
 		return ERR_PTR(-EINVAL);
 
 	return skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG);
@@ -39,7 +39,7 @@ bool tipc_msg_gso_append(struct sk_buff **p, struct sk_buff *skb, u16 segs)
 
 		skb_shinfo(nskb)->frag_list = head;
 		skb_shinfo(nskb)->gso_segs = 1;
-		skb_shinfo(nskb)->gso_type = SKB_GSO_TIPC;
+		skb_shinfo(nskb)->gso_type = SKB_GSO_SCTP;
 		skb_shinfo(nskb)->gso_size = GSO_BY_FRAGS;
 		skb_reset_network_header(head);
 
-- 
2.27.0

[tipc-discussion] [PATCH net-next 6/8] tipc: add offload base

[Xin L. <luc...@gm...>]

This is the base code for tipc gso, and tipc_gso_segment() will
only be called after gso packets are built in the next patch.

Signed-off-by: Xin Long <luc...@gm...>
---
 include/linux/skbuff.h |  2 ++
 net/tipc/Makefile      |  2 +-
 net/tipc/core.c        |  3 +++
 net/tipc/msg.h         |  2 ++
 net/tipc/offload.c     | 29 +++++++++++++++++++++++++++++
 5 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 net/tipc/offload.c

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b2db9cd9a73f..148bf0ed7336 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -599,6 +599,8 @@ enum {
 	SKB_GSO_UDP_L4 = 1 << 17,
 
 	SKB_GSO_FRAGLIST = 1 << 18,
+
+	SKB_GSO_TIPC = 1 << 19,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/tipc/Makefile b/net/tipc/Makefile
index ee49a9f1dd4f..ff276bf78d03 100644
--- a/net/tipc/Makefile
+++ b/net/tipc/Makefile
@@ -9,7 +9,7 @@ tipc-y	+= addr.o bcast.o bearer.o \
 	   core.o link.o discover.o msg.o  \
 	   name_distr.o  subscr.o monitor.o name_table.o net.o  \
 	   netlink.o netlink_compat.o node.o socket.o eth_media.o \
-	   topsrv.o group.o trace.o
+	   topsrv.o group.o trace.o offload.o
 
 CFLAGS_trace.o += -I$(src)
 
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 3f4542e0f065..1f59371aa036 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -186,6 +186,8 @@ static int __init tipc_init(void)
 	if (err)
 		goto out_netlink_compat;
 
+	tipc_offload_init();
+
 	pr_info("Started in single node mode\n");
 	return 0;
 
@@ -210,6 +212,7 @@ static int __init tipc_init(void)
 
 static void __exit tipc_exit(void)
 {
+	tipc_offload_exit();
 	tipc_netlink_compat_stop();
 	tipc_netlink_stop();
 	tipc_bearer_cleanup();
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 64ae4c4c44f8..d6c6231b8208 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1203,6 +1203,8 @@ bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg,
 bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
 			     struct sk_buff *skb);
 bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy);
+void tipc_offload_init(void);
+void tipc_offload_exit(void);
 
 static inline u16 buf_seqno(struct sk_buff *skb)
 {
diff --git a/net/tipc/offload.c b/net/tipc/offload.c
new file mode 100644
index 000000000000..f8a81c8886f0
--- /dev/null
+++ b/net/tipc/offload.c
@@ -0,0 +1,29 @@
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include "msg.h"
+
+static struct sk_buff *tipc_gso_segment(struct sk_buff *skb,
+					netdev_features_t features)
+{
+	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TIPC))
+		return ERR_PTR(-EINVAL);
+
+	return skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG);
+}
+
+static struct packet_offload tipc_packet_offload __read_mostly = {
+	.type = cpu_to_be16(ETH_P_TIPC),
+	.callbacks = {
+		.gso_segment = tipc_gso_segment,
+	},
+};
+
+void tipc_offload_init(void)
+{
+	dev_add_offload(&tipc_packet_offload);
+}
+
+void tipc_offload_exit(void)
+{
+	dev_remove_offload(&tipc_packet_offload);
+}
-- 
2.27.0

[tipc-discussion] [PATCH net-next 7/8] tipc: add software gso

[Xin L. <luc...@gm...>]

TIPC GSO is implemented in the skb frag_list way as SCTP does.

We don't need to change much in the tx path, but only create
a head skb and append the skbs when there are more than one
skb ready to send. In the lower-layer gso_segment(), it does
fragmentation by copy eth header or ip/udp header to each
skb in the head_skb's frag_list and send them one by one.

This supports with both eth media and udp media.

Signed-off-by: Xin Long <luc...@gm...>
---
 net/tipc/bearer.c    | 23 +++++++++++++++++++++--
 net/tipc/msg.h       |  1 +
 net/tipc/offload.c   | 41 +++++++++++++++++++++++++++++++++++++++++
 net/tipc/udp_media.c |  7 +++++++
 4 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 443f8e5b9477..b0321b21bfdc 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -570,8 +570,9 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id,
 		      struct tipc_media_addr *dst,
 		      struct tipc_node *__dnode)
 {
+	struct sk_buff *head = NULL, *skb, *tmp;
 	struct tipc_bearer *b;
-	struct sk_buff *skb, *tmp;
+	u16 segs = 0;
 
 	if (skb_queue_empty(xmitq))
 		return;
@@ -585,13 +586,31 @@ void tipc_bearer_xmit(struct net *net, u32 bearer_id,
 		if (likely(test_bit(0, &b->up) || msg_is_reset(buf_msg(skb)))) {
 #ifdef CONFIG_TIPC_CRYPTO
 			tipc_crypto_xmit(net, &skb, b, dst, __dnode);
-			if (skb)
+			if (!skb)
+				continue;
 #endif
+			if (!skb->ignore_df) { /* PLPMTUD probe packet*/
 				b->media->send_msg(net, skb, b, dst);
+				continue;
+			}
+			if (!head) {
+				segs = 1;
+				head = skb;
+				continue;
+			}
+			if (tipc_msg_gso_append(&head, skb, segs)) {
+				segs++;
+				continue;
+			}
+			b->media->send_msg(net, head, b, dst);
+			segs = 1;
+			head = skb;
 		} else {
 			kfree_skb(skb);
 		}
 	}
+	if (head)
+		b->media->send_msg(net, head, b, dst);
 	rcu_read_unlock();
 }
 
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index d6c6231b8208..4d1ff666790c 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -1205,6 +1205,7 @@ bool __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
 bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy);
 void tipc_offload_init(void);
 void tipc_offload_exit(void);
+bool tipc_msg_gso_append(struct sk_buff **p, struct sk_buff *skb, u16 segs);
 
 static inline u16 buf_seqno(struct sk_buff *skb)
 {
diff --git a/net/tipc/offload.c b/net/tipc/offload.c
index f8a81c8886f0..d137679f4db0 100644
--- a/net/tipc/offload.c
+++ b/net/tipc/offload.c
@@ -18,6 +18,47 @@ static struct packet_offload tipc_packet_offload __read_mostly = {
 	},
 };
 
+bool tipc_msg_gso_append(struct sk_buff **p, struct sk_buff *skb, u16 segs)
+{
+	struct sk_buff *head = *p;
+	struct sk_buff *nskb;
+
+	if (head->len + skb->len >= 65535)
+		return false;
+
+	if (segs == 1) {
+		nskb = tipc_buf_acquire(0, GFP_ATOMIC);
+		if (!nskb)
+			return false;
+
+		nskb->ip_summed = CHECKSUM_UNNECESSARY;
+		nskb->truesize += head->truesize;
+		nskb->data_len += head->len;
+		nskb->len += head->len;
+		TIPC_SKB_CB(nskb)->tail = head;
+
+		skb_shinfo(nskb)->frag_list = head;
+		skb_shinfo(nskb)->gso_segs = 1;
+		skb_shinfo(nskb)->gso_type = SKB_GSO_TIPC;
+		skb_shinfo(nskb)->gso_size = GSO_BY_FRAGS;
+		skb_reset_network_header(head);
+
+		head = nskb;
+		*p = head;
+	}
+
+	head->truesize += skb->truesize;
+	head->data_len += skb->len;
+	head->len += skb->len;
+	TIPC_SKB_CB(head)->tail->next = skb;
+	TIPC_SKB_CB(head)->tail = skb;
+
+	skb_shinfo(head)->gso_segs++;
+	skb_reset_network_header(skb);
+
+	return true;
+}
+
 void tipc_offload_init(void)
 {
 	dev_add_offload(&tipc_packet_offload);
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 5078c5b19e81..7da02db6a50e 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -245,6 +245,13 @@ static int tipc_udp_send_msg(struct net *net, struct sk_buff *skb,
 			goto out;
 	}
 
+	if (skb_is_gso(skb))
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+
+	skb->encapsulation = 1;
+	skb_reset_inner_mac_header(skb);
+	skb_reset_inner_network_header(skb);
+	skb_reset_inner_transport_header(skb);
 	skb_set_inner_protocol(skb, htons(ETH_P_TIPC));
 	ub = rcu_dereference(b->media_ptr);
 	if (!ub) {
-- 
2.27.0

Re: [tipc-discussion] [PATCH net-next 0/8] tipc: add PLPMTUD probe and GSO offload

[Jon M. <jm...@re...>]

On 06/07/2021 14:22, Xin Long wrote:
> This patchset is to implement PLPMTUD and GSO for TIPC,
> Patch 1-5 are for PLPMTUD while 6-8 are for GSO.

I think this should be posted as two separate series, as they really 
implement two different features.

The problem I see with this is that you reduce MTU in patch #1, so
performance will suffer until the second series is adapted.

Unless there is a way around this the two series mut at least be
applied within the same release.

Also, if I understand this correctly, PLTMUD will work also for
the Ethernet bearer, so that jumbo frame capability can be detected?
I am uncertain about the value of this, since jumbo frame capability is 
already detected by the endpoint bearers, and I doubt that such frames
ever do more than one intra-subnet hop. But maybe I am wrong here? 
Anyway, this feature cannot do any harm even on Ethernet.

///jon

> 
> It gets some ideas from SCTP as their similarities like
> both are reliable datagram packets and possible to run
> over IP(v6)/UDP. But also it does some adjustments for
> TIPC.
> 
> Xin Long (8):
>    tipc: set the mtu for bearer properly for udp media
>    tipc: add the constants and variables for plpmtud
>    tipc: build probe and its reply in tipc_link_build_proto_msg
>    tipc: add probe send and state transition
>    tipc: add probe recv and state transition
>    tipc: add offload base
>    tipc: add software gso
>    tipc: add hardware gso
> 
>   include/uapi/linux/tipc_config.h |   6 --
>   net/tipc/Makefile                |   2 +-
>   net/tipc/bearer.c                |  23 ++++-
>   net/tipc/core.c                  |   3 +
>   net/tipc/link.c                  | 147 +++++++++++++++++++++++++++----
>   net/tipc/link.h                  |  29 ++++++
>   net/tipc/msg.c                   |   1 +
>   net/tipc/msg.h                   |   3 +
>   net/tipc/node.c                  |  15 +++-
>   net/tipc/offload.c               |  70 +++++++++++++++
>   net/tipc/udp_media.c             |  18 ++--
>   11 files changed, 287 insertions(+), 30 deletions(-)
>   create mode 100644 net/tipc/offload.c
> 

Re: [tipc-discussion] [PATCH net-next 8/8] tipc: add hardware gso

[Jon M. <jm...@re...>]

On 06/07/2021 14:22, Xin Long wrote:
> Since there's no enough bit in netdev_features_t for
> NETIF_F_GSO_TIPC_BIT, and tipc is using the simliar
> code as sctp, this patch will reuse SKB_GSO_SCTP and
> NETIF_F_GSO_SCTP_BIT for tipc.
> 
> Signed-off-by: Xin Long <luc...@gm...>
> ---
>   include/linux/skbuff.h |  2 --
>   net/tipc/node.c        | 15 ++++++++++++++-
>   net/tipc/offload.c     |  4 ++--
>   3 files changed, 16 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index 148bf0ed7336..b2db9cd9a73f 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -599,8 +599,6 @@ enum {
>   	SKB_GSO_UDP_L4 = 1 << 17,
>   
>   	SKB_GSO_FRAGLIST = 1 << 18,
> -
> -	SKB_GSO_TIPC = 1 << 19,
>   };
>   
>   #if BITS_PER_LONG > 32
> diff --git a/net/tipc/node.c b/net/tipc/node.c
> index 9947b7dfe1d2..17e59c8dac31 100644
> --- a/net/tipc/node.c
> +++ b/net/tipc/node.c
> @@ -2068,7 +2068,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
>    * Invoked with no locks held. Bearer pointer must point to a valid bearer
>    * structure (i.e. cannot be NULL), but bearer can be inactive.
>    */
> -void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
> +static void __tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
>   {
>   	struct sk_buff_head xmitq;
>   	struct tipc_link_entry *le;
> @@ -2189,6 +2189,19 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
>   	kfree_skb(skb);
>   }
>   
> +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
> +{
> +	struct sk_buff *seg, *next;
> +
> +	if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
> +		return __tipc_rcv(net, skb, b);
> +
> +	skb_list_walk_safe(skb_shinfo(skb)->frag_list, seg, next)
> +		__tipc_rcv(net, seg, b);
> +	skb_shinfo(skb)->frag_list = NULL;
> +	consume_skb(skb);
> +}
> +
>   void tipc_node_apply_property(struct net *net, struct tipc_bearer *b,
>   			      int prop)
>   {
> diff --git a/net/tipc/offload.c b/net/tipc/offload.c
> index d137679f4db0..26e372178635 100644
> --- a/net/tipc/offload.c
> +++ b/net/tipc/offload.c
> @@ -5,7 +5,7 @@
>   static struct sk_buff *tipc_gso_segment(struct sk_buff *skb,
>   					netdev_features_t features)
>   {
> -	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TIPC))
> +	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP))
>   		return ERR_PTR(-EINVAL);
>   
>   	return skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG);
> @@ -39,7 +39,7 @@ bool tipc_msg_gso_append(struct sk_buff **p, struct sk_buff *skb, u16 segs)
>   
>   		skb_shinfo(nskb)->frag_list = head;
>   		skb_shinfo(nskb)->gso_segs = 1;
> -		skb_shinfo(nskb)->gso_type = SKB_GSO_TIPC;
> +		skb_shinfo(nskb)->gso_type = SKB_GSO_SCTP;
>   		skb_shinfo(nskb)->gso_size = GSO_BY_FRAGS;
>   		skb_reset_network_header(head);
>   
> 

I don´t have much more to add, -it looks good to me, and way simpler 
than what I was trying a couple of years ago.

If you fix the checkpatch issues and, maybe if possible, split it into 
two series, you have my ack.

PS. Did you test this with crypto?

///jon

Re: [tipc-discussion] [PATCH net-next 8/8] tipc: add hardware gso

[Xin L. <luc...@gm...>]

On Fri, Sep 10, 2021 at 8:08 AM Jon Maloy <jm...@re...> wrote:
>
>
>
> On 06/07/2021 14:22, Xin Long wrote:
> > Since there's no enough bit in netdev_features_t for
> > NETIF_F_GSO_TIPC_BIT, and tipc is using the simliar
> > code as sctp, this patch will reuse SKB_GSO_SCTP and
> > NETIF_F_GSO_SCTP_BIT for tipc.
> >
> > Signed-off-by: Xin Long <luc...@gm...>
> > ---
> >   include/linux/skbuff.h |  2 --
> >   net/tipc/node.c        | 15 ++++++++++++++-
> >   net/tipc/offload.c     |  4 ++--
> >   3 files changed, 16 insertions(+), 5 deletions(-)
> >
> > diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> > index 148bf0ed7336..b2db9cd9a73f 100644
> > --- a/include/linux/skbuff.h
> > +++ b/include/linux/skbuff.h
> > @@ -599,8 +599,6 @@ enum {
> >       SKB_GSO_UDP_L4 = 1 << 17,
> >
> >       SKB_GSO_FRAGLIST = 1 << 18,
> > -
> > -     SKB_GSO_TIPC = 1 << 19,
> >   };
> >
> >   #if BITS_PER_LONG > 32
> > diff --git a/net/tipc/node.c b/net/tipc/node.c
> > index 9947b7dfe1d2..17e59c8dac31 100644
> > --- a/net/tipc/node.c
> > +++ b/net/tipc/node.c
> > @@ -2068,7 +2068,7 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
> >    * Invoked with no locks held. Bearer pointer must point to a valid bearer
> >    * structure (i.e. cannot be NULL), but bearer can be inactive.
> >    */
> > -void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
> > +static void __tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
> >   {
> >       struct sk_buff_head xmitq;
> >       struct tipc_link_entry *le;
> > @@ -2189,6 +2189,19 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
> >       kfree_skb(skb);
> >   }
> >
> > +void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b)
> > +{
> > +     struct sk_buff *seg, *next;
> > +
> > +     if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
> > +             return __tipc_rcv(net, skb, b);
> > +
> > +     skb_list_walk_safe(skb_shinfo(skb)->frag_list, seg, next)
> > +             __tipc_rcv(net, seg, b);
> > +     skb_shinfo(skb)->frag_list = NULL;
> > +     consume_skb(skb);
> > +}
> > +
> >   void tipc_node_apply_property(struct net *net, struct tipc_bearer *b,
> >                             int prop)
> >   {
> > diff --git a/net/tipc/offload.c b/net/tipc/offload.c
> > index d137679f4db0..26e372178635 100644
> > --- a/net/tipc/offload.c
> > +++ b/net/tipc/offload.c
> > @@ -5,7 +5,7 @@
> >   static struct sk_buff *tipc_gso_segment(struct sk_buff *skb,
> >                                       netdev_features_t features)
> >   {
> > -     if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TIPC))
> > +     if (!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP))
> >               return ERR_PTR(-EINVAL);
> >
> >       return skb_segment(skb, (features | NETIF_F_HW_CSUM) & ~NETIF_F_SG);
> > @@ -39,7 +39,7 @@ bool tipc_msg_gso_append(struct sk_buff **p, struct sk_buff *skb, u16 segs)
> >
> >               skb_shinfo(nskb)->frag_list = head;
> >               skb_shinfo(nskb)->gso_segs = 1;
> > -             skb_shinfo(nskb)->gso_type = SKB_GSO_TIPC;
> > +             skb_shinfo(nskb)->gso_type = SKB_GSO_SCTP;
> >               skb_shinfo(nskb)->gso_size = GSO_BY_FRAGS;
> >               skb_reset_network_header(head);
> >
> >
>
> I don´t have much more to add, -it looks good to me, and way simpler
> than what I was trying a couple of years ago.
>
> If you fix the checkpatch issues and, maybe if possible, split it into
> two series, you have my ack.
>
> PS. Did you test this with crypto?
Hi Jon,

Sorry for late.

Got an urgent problem from a customer recently, and spent quite a few
weeks getting things almost done.
I need to do more testing for its performance in different scenarios
before continuing.
I think I did, but I will confirm it will work well over crypto.

Thanks a lot for checking!

>
> ///jon
>