Merge branch 'sctp-gso'

Marcelo Ricardo Leitner says:

====================
sctp: Add GSO support

This patchset adds sctp GSO support.

Performance tests indicates that increases throughput by 10% if using
bigger chunk sizes, specially if bigger than MTU. For small chunks, it
doesn't help much if not using heavy firewall rules.

For small chunks it will probably be of more use once we get something
like MSG_MORE as David Laight had suggested.

overall changes:
v1->v2:
Added support for receiving GSO frames on SCTP stack, as requested by
Dave Miller.

v2->v3:
Consider sctphdr size in skb_gso_transport_seglen()
rebased due to 5c7cdf33 ("gso: Remove arbitrary checks for
unsupported GSO")
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/loopback.c

@@ -169,10 +169,9 @@ static void loopback_setup(struct net_device *dev)
 	dev->flags		= IFF_LOOPBACK;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	netif_keep_dst(dev);
-	dev->hw_features	= NETIF_F_ALL_TSO | NETIF_F_UFO;
+	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
 	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
-		| NETIF_F_ALL_TSO
-		| NETIF_F_UFO
+		| NETIF_F_GSO_SOFTWARE
 		| NETIF_F_HW_CSUM
 		| NETIF_F_RXCSUM
 		| NETIF_F_SCTP_CRC

include/linux/netdev_features.h

@@ -53,8 +53,9 @@ enum {
 					 *     headers in software.
 					 */
 	NETIF_F_GSO_TUNNEL_REMCSUM_BIT, /* ... TUNNEL with TSO & REMCSUM */
+	NETIF_F_GSO_SCTP_BIT,		/* ... SCTP fragmentation */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_TUNNEL_REMCSUM_BIT,
+		NETIF_F_GSO_SCTP_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
@@ -128,6 +129,7 @@ enum {
 #define NETIF_F_TSO_MANGLEID	__NETIF_F(TSO_MANGLEID)
 #define NETIF_F_GSO_PARTIAL	 __NETIF_F(GSO_PARTIAL)
 #define NETIF_F_GSO_TUNNEL_REMCSUM __NETIF_F(GSO_TUNNEL_REMCSUM)
+#define NETIF_F_GSO_SCTP	__NETIF_F(GSO_SCTP)
 #define NETIF_F_HW_VLAN_STAG_FILTER __NETIF_F(HW_VLAN_STAG_FILTER)
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
@@ -166,7 +168,8 @@ enum {
 				 NETIF_F_FSO)
 
 /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_UFO)
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_UFO | \
+				 NETIF_F_GSO_SCTP)
 
 /*
  * If one device supports one of these features, then enable them

include/linux/netdevice.h

@@ -4012,6 +4012,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_SCTP    != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }

include/linux/skbuff.h

@@ -301,6 +301,11 @@ struct sk_buff;
 #endif
 extern int sysctl_max_skb_frags;
 
+/* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to
+ * segment using its current segmentation instead.
+ */
+#define GSO_BY_FRAGS	0xFFFF
+
 typedef struct skb_frag_struct skb_frag_t;
 
 struct skb_frag_struct {
@@ -482,6 +487,8 @@ enum {
 	SKB_GSO_PARTIAL = 1 << 13,
 
 	SKB_GSO_TUNNEL_REMCSUM = 1 << 14,
+
+	SKB_GSO_SCTP = 1 << 15,
 };
 
 #if BITS_PER_LONG > 32
@@ -2987,6 +2994,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len);
 int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen);
 void skb_scrub_packet(struct sk_buff *skb, bool xnet);
 unsigned int skb_gso_transport_seglen(const struct sk_buff *skb);
+bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu);
 struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features);
 struct sk_buff *skb_vlan_untag(struct sk_buff *skb);
 int skb_ensure_writable(struct sk_buff *skb, int write_len);

include/net/sctp/sctp.h

@@ -186,6 +186,10 @@ void sctp_assocs_proc_exit(struct net *net);
 int sctp_remaddr_proc_init(struct net *net);
 void sctp_remaddr_proc_exit(struct net *net);
 
+/*
+ * sctp/offload.c
+ */
+int sctp_offload_init(void);
 
 /*
  * Module global variables

include/net/sctp/structs.h

@@ -566,6 +566,9 @@ struct sctp_chunk {
 	/* This points to the sk_buff containing the actual data.  */
 	struct sk_buff *skb;
 
+	/* In case of GSO packets, this will store the head one */
+	struct sk_buff *head_skb;
+
 	/* These are the SCTP headers by reverse order in a packet.
 	 * Note that some of these may happen more than once.  In that
 	 * case, we point at the "current" one, whatever that means
@@ -696,6 +699,8 @@ struct sctp_packet {
 	size_t overhead;
 	/* This is the total size of all chunks INCLUDING padding.  */
 	size_t size;
+	/* This is the maximum size this packet may have */
+	size_t max_size;
 
 	/* The packet is destined for this transport address.
 	 * The function we finally use to pass down to the next lower

net/core/ethtool.c

@@ -89,6 +89,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_GSO_UDP_TUNNEL_BIT] =	 "tx-udp_tnl-segmentation",
 	[NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation",
 	[NETIF_F_GSO_PARTIAL_BIT] =	 "tx-gso-partial",
+	[NETIF_F_GSO_SCTP_BIT] =	 "tx-sctp-segmentation",
 
 	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
 	[NETIF_F_SCTP_CRC_BIT] =        "tx-checksum-sctp",

net/core/skbuff.c

@@ -49,6 +49,7 @@
 #include <linux/slab.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
+#include <linux/sctp.h>
 #include <linux/netdevice.h>
 #ifdef CONFIG_NET_CLS_ACT
 #include <net/pkt_sched.h>
@@ -3116,9 +3117,13 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
 		int hsize;
 		int size;
 
-		len = head_skb->len - offset;
-		if (len > mss)
-			len = mss;
+		if (unlikely(mss == GSO_BY_FRAGS)) {
+			len = list_skb->len;
+		} else {
+			len = head_skb->len - offset;
+			if (len > mss)
+				len = mss;
+		}
 
 		hsize = skb_headlen(head_skb) - offset;
 		if (hsize < 0)
@@ -3438,6 +3443,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	NAPI_GRO_CB(skb)->same_flow = 1;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(skb_gro_receive);
 
 void __init skb_init(void)
 {
@@ -4378,6 +4384,8 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
 			thlen += inner_tcp_hdrlen(skb);
 	} else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) {
 		thlen = tcp_hdrlen(skb);
+	} else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) {
+		thlen = sizeof(struct sctphdr);
 	}
 	/* UFO sets gso_size to the size of the fragmentation
 	 * payload, i.e. the size of the L4 (UDP) header is already
@@ -4387,6 +4395,37 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(skb_gso_transport_seglen);
 
+/**
+ * skb_gso_validate_mtu - Return in case such skb fits a given MTU
+ *
+ * @skb: GSO skb
+ *
+ * skb_gso_validate_mtu validates if a given skb will fit a wanted MTU
+ * once split.
+ */
+bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	const struct sk_buff *iter;
+	unsigned int hlen;
+
+	hlen = skb_gso_network_seglen(skb);
+
+	if (shinfo->gso_size != GSO_BY_FRAGS)
+		return hlen <= mtu;
+
+	/* Undo this so we can re-use header sizes */
+	hlen -= GSO_BY_FRAGS;
+
+	skb_walk_frags(skb, iter) {
+		if (hlen + skb_headlen(iter) > mtu)
+			return false;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(skb_gso_validate_mtu);
+
 static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 {
 	if (skb_cow(skb, skb_headroom(skb)) < 0) {

net/ipv4/ip_forward.c

@@ -54,7 +54,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->ignore_df)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
 		return false;
 
 	return true;

net/ipv4/ip_output.c

@@ -225,7 +225,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
 
 	/* common case: locally created skb or seglen is <= mtu */
 	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
-	      skb_gso_network_seglen(skb) <= mtu)
+	      skb_gso_validate_mtu(skb, mtu))
 		return ip_finish_output2(net, sk, skb);
 
 	/* Slowpath -  GSO segment length is exceeding the dst MTU.

net/ipv6/ip6_output.c

@@ -368,7 +368,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->ignore_df)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
 		return false;
 
 	return true;

net/mpls/af_mpls.c

@@ -91,7 +91,7 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 	if (skb->len <= mtu)
 		return false;
 
-	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
+	if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
 		return false;
 
 	return true;

net/sctp/Makefile

@@ -11,7 +11,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
 	  transport.o chunk.o sm_make_chunk.o ulpevent.o \
 	  inqueue.o outqueue.o ulpqueue.o \
 	  tsnmap.o bind_addr.o socket.o primitive.o \
-	  output.o input.o debug.o ssnmap.o auth.o
+	  output.o input.o debug.o ssnmap.o auth.o \
+	  offload.o
 
 sctp_probe-y := probe.o
 

net/sctp/input.c

@@ -112,7 +112,6 @@ int sctp_rcv(struct sk_buff *skb)
 	struct sctp_ep_common *rcvr;
 	struct sctp_transport *transport = NULL;
 	struct sctp_chunk *chunk;
-	struct sctphdr *sh;
 	union sctp_addr src;
 	union sctp_addr dest;
 	int family;
@@ -124,28 +123,29 @@ int sctp_rcv(struct sk_buff *skb)
 
 	__SCTP_INC_STATS(net, SCTP_MIB_INSCTPPACKS);
 
-	if (skb_linearize(skb))
+	/* If packet is too small to contain a single chunk, let's not
+	 * waste time on it anymore.
+	 */
+	if (skb->len < sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr) +
+		       skb_transport_offset(skb))
 		goto discard_it;
 
-	sh = sctp_hdr(skb);
+	if (!pskb_may_pull(skb, sizeof(struct sctphdr)))
+		goto discard_it;
 
-	/* Pull up the IP and SCTP headers. */
+	/* Pull up the IP header. */
 	__skb_pull(skb, skb_transport_offset(skb));
-	if (skb->len < sizeof(struct sctphdr))
-		goto discard_it;
 
 	skb->csum_valid = 0; /* Previous value not applicable */
 	if (skb_csum_unnecessary(skb))
 		__skb_decr_checksum_unnecessary(skb);
-	else if (!sctp_checksum_disable && sctp_rcv_checksum(net, skb) < 0)
+	else if (!sctp_checksum_disable &&
+		 !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) &&
+		 sctp_rcv_checksum(net, skb) < 0)
 		goto discard_it;
 	skb->csum_valid = 1;
 
-	skb_pull(skb, sizeof(struct sctphdr));
-
-	/* Make sure we at least have chunk headers worth of data left. */
-	if (skb->len < sizeof(struct sctp_chunkhdr))
-		goto discard_it;
+	__skb_pull(skb, sizeof(struct sctphdr));
 
 	family = ipver2af(ip_hdr(skb)->version);
 	af = sctp_get_af_specific(family);
@@ -230,7 +230,7 @@ int sctp_rcv(struct sk_buff *skb)
 	chunk->rcvr = rcvr;
 
 	/* Remember the SCTP header. */
-	chunk->sctp_hdr = sh;
+	chunk->sctp_hdr = sctp_hdr(skb);
 
 	/* Set the source and destination addresses of the incoming chunk.  */
 	sctp_init_addrs(chunk, &src, &dest);
@@ -660,19 +660,23 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
  */
 static int sctp_rcv_ootb(struct sk_buff *skb)
 {
-	sctp_chunkhdr_t *ch;
-	__u8 *ch_end;
-
-	ch = (sctp_chunkhdr_t *) skb->data;
+	sctp_chunkhdr_t *ch, _ch;
+	int ch_end, offset = 0;
 
 	/* Scan through all the chunks in the packet.  */
 	do {
+		/* Make sure we have at least the header there */
+		if (offset + sizeof(sctp_chunkhdr_t) > skb->len)
+			break;
+
+		ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch);
+
 		/* Break out if chunk length is less then minimal. */
 		if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t))
 			break;
 
-		ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
-		if (ch_end > skb_tail_pointer(skb))
+		ch_end = offset + WORD_ROUND(ntohs(ch->length));
+		if (ch_end > skb->len)
 			break;
 
 		/* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the
@@ -697,8 +701,8 @@ static int sctp_rcv_ootb(struct sk_buff *skb)
 		if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data)
 			goto discard;
 
-		ch = (sctp_chunkhdr_t *) ch_end;
-	} while (ch_end < skb_tail_pointer(skb));
+		offset = ch_end;
+	} while (ch_end < skb->len);
 
 	return 0;
 
@@ -1173,6 +1177,17 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net,
 {
 	sctp_chunkhdr_t *ch;
 
+	/* We do not allow GSO frames here as we need to linearize and
+	 * then cannot guarantee frame boundaries. This shouldn't be an
+	 * issue as packets hitting this are mostly INIT or INIT-ACK and
+	 * those cannot be on GSO-style anyway.
+	 */
+	if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP)
+		return NULL;
+
+	if (skb_linearize(skb))
+		return NULL;
+
 	ch = (sctp_chunkhdr_t *) skb->data;
 
 	/* The code below will attempt to walk the chunk and extract

net/sctp/inqueue.c

@@ -130,13 +130,25 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 	 * at this time.
 	 */
 
-	if ((chunk = queue->in_progress)) {
+	chunk = queue->in_progress;
+	if (chunk) {
 		/* There is a packet that we have been working on.
 		 * Any post processing work to do before we move on?
 		 */
 		if (chunk->singleton ||
 		    chunk->end_of_packet ||
 		    chunk->pdiscard) {
+			if (chunk->head_skb == chunk->skb) {
+				chunk->skb = skb_shinfo(chunk->skb)->frag_list;
+				goto new_skb;
+			}
+			if (chunk->skb->next) {
+				chunk->skb = chunk->skb->next;
+				goto new_skb;
+			}
+
+			if (chunk->head_skb)
+				chunk->skb = chunk->head_skb;
 			sctp_chunk_free(chunk);
 			chunk = queue->in_progress = NULL;
 		} else {
@@ -152,34 +164,64 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 	if (!chunk) {
 		struct list_head *entry;
 
+next_chunk:
 		/* Is the queue empty?  */
-		if (list_empty(&queue->in_chunk_list))
+		entry = sctp_list_dequeue(&queue->in_chunk_list);
+		if (!entry)
 			return NULL;
 
-		entry = queue->in_chunk_list.next;
-		chunk = queue->in_progress =
-			list_entry(entry, struct sctp_chunk, list);
-		list_del_init(entry);
+		chunk = list_entry(entry, struct sctp_chunk, list);
 
-		/* This is the first chunk in the packet.  */
-		chunk->singleton = 1;
-		ch = (sctp_chunkhdr_t *) chunk->skb->data;
-		chunk->data_accepted = 0;
+		/* Linearize if it's not GSO */
+		if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP &&
+		    skb_is_nonlinear(chunk->skb)) {
+			if (skb_linearize(chunk->skb)) {
+				__SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS);
+				sctp_chunk_free(chunk);
+				goto next_chunk;
+			}
+
+			/* Update sctp_hdr as it probably changed */
+			chunk->sctp_hdr = sctp_hdr(chunk->skb);
+		}
+
+		if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) {
+			/* GSO-marked skbs but without frags, handle
+			 * them normally
+			 */
+			if (skb_shinfo(chunk->skb)->frag_list)
+				chunk->head_skb = chunk->skb;
+
+			/* skbs with "cover letter" */
+			if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len)
+				chunk->skb = skb_shinfo(chunk->skb)->frag_list;
+
+			if (WARN_ON(!chunk->skb)) {
+				__SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS);
+				sctp_chunk_free(chunk);
+				goto next_chunk;
+			}
+		}
 
 		if (chunk->asoc)
 			sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb);
+
+		queue->in_progress = chunk;
+
+new_skb:
+		/* This is the first chunk in the packet.  */
+		ch = (sctp_chunkhdr_t *) chunk->skb->data;
+		chunk->singleton = 1;
+		chunk->data_accepted = 0;
+		chunk->pdiscard = 0;
+		chunk->auth = 0;
+		chunk->has_asconf = 0;
+		chunk->end_of_packet = 0;
+		chunk->ecn_ce_done = 0;
 	}
 
 	chunk->chunk_hdr = ch;
 	chunk->chunk_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length));
-	/* In the unlikely case of an IP reassembly, the skb could be
-	 * non-linear. If so, update chunk_end so that it doesn't go past
-	 * the skb->tail.
-	 */
-	if (unlikely(skb_is_nonlinear(chunk->skb))) {
-		if (chunk->chunk_end > skb_tail_pointer(chunk->skb))
-			chunk->chunk_end = skb_tail_pointer(chunk->skb);
-	}
 	skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t));
 	chunk->subh.v = NULL; /* Subheader is no longer valid.  */
 

net/sctp/offload.c

+/*
+ * sctp_offload - GRO/GSO Offloading for SCTP
+ *
+ * Copyright (C) 2015, Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/socket.h>
+#include <linux/sctp.h>
+#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/kfifo.h>
+#include <linux/time.h>
+#include <net/net_namespace.h>
+
+#include <linux/skbuff.h>
+#include <net/sctp/sctp.h>
+#include <net/sctp/checksum.h>
+#include <net/protocol.h>
+
+static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
+{
+	skb->ip_summed = CHECKSUM_NONE;
+	return sctp_compute_cksum(skb, skb_transport_offset(skb));
+}
+
+static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
+					netdev_features_t features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct sctphdr *sh;
+
+	sh = sctp_hdr(skb);
+	if (!pskb_may_pull(skb, sizeof(*sh)))
+		goto out;
+
+	__skb_pull(skb, sizeof(*sh));
+
+	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+		/* Packet is from an untrusted source, reset gso_segs. */
+		struct skb_shared_info *pinfo = skb_shinfo(skb);
+		struct sk_buff *frag_iter;
+
+		pinfo->gso_segs = 0;
+		if (skb->len != skb->data_len) {
+			/* Means we have chunks in here too */
+			pinfo->gso_segs++;
+		}
+
+		skb_walk_frags(skb, frag_iter)
+			pinfo->gso_segs++;
+
+		segs = NULL;
+		goto out;
+	}
+
+	segs = skb_segment(skb, features | NETIF_F_HW_CSUM);
+	if (IS_ERR(segs))
+		goto out;
+
+	/* All that is left is update SCTP CRC if necessary */
+	if (!(features & NETIF_F_SCTP_CRC)) {
+		for (skb = segs; skb; skb = skb->next) {
+			if (skb->ip_summed == CHECKSUM_PARTIAL) {
+				sh = sctp_hdr(skb);
+				sh->checksum = sctp_gso_make_checksum(skb);
+			}
+		}
+	}
+
+out:
+	return segs;
+}
+
+static const struct net_offload sctp_offload = {
+	.callbacks = {
+		.gso_segment = sctp_gso_segment,
+	},
+};
+
+int __init sctp_offload_init(void)
+{
+	return inet_add_offload(&sctp_offload, IPPROTO_SCTP);
+}

net/sctp/output.c

@@ -84,18 +84,42 @@ static void sctp_packet_reset(struct sctp_packet *packet)
 struct sctp_packet *sctp_packet_config(struct sctp_packet *packet,
 				       __u32 vtag, int ecn_capable)
 {
-	struct sctp_chunk *chunk = NULL;
+	struct sctp_transport *tp = packet->transport;
+	struct sctp_association *asoc = tp->asoc;
 
 	pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
 
 	packet->vtag = vtag;
 
+	if (asoc && tp->dst) {
+		struct sock *sk = asoc->base.sk;
+
+		rcu_read_lock();
+		if (__sk_dst_get(sk) != tp->dst) {
+			dst_hold(tp->dst);
+			sk_setup_caps(sk, tp->dst);
+		}
+
+		if (sk_can_gso(sk)) {
+			struct net_device *dev = tp->dst->dev;
+
+			packet->max_size = dev->gso_max_size;
+		} else {
+			packet->max_size = asoc->pathmtu;
+		}
+		rcu_read_unlock();
+
+	} else {
+		packet->max_size = tp->pathmtu;
+	}
+
 	if (ecn_capable && sctp_packet_empty(packet)) {
-		chunk = sctp_get_ecne_prepend(packet->transport->asoc);
+		struct sctp_chunk *chunk;
 
 		/* If there a is a prepend chunk stick it on the list before
 		 * any other chunks get appended.
 		 */
+		chunk = sctp_get_ecne_prepend(asoc);
 		if (chunk)
 			sctp_packet_append_chunk(packet, chunk);
 	}
@@ -158,7 +182,8 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet,
 	sctp_xmit_t retval;
 	int error = 0;
 
-	pr_debug("%s: packet:%p chunk:%p\n", __func__, packet, chunk);
+	pr_debug("%s: packet:%p size:%lu chunk:%p size:%d\n", __func__,
+		 packet, packet->size, chunk, chunk->skb ? chunk->skb->len : -1);
 
 	switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) {
 	case SCTP_XMIT_PMTU_FULL:
@@ -381,12 +406,15 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	struct sctp_transport *tp = packet->transport;
 	struct sctp_association *asoc = tp->asoc;
 	struct sctphdr *sh;
-	struct sk_buff *nskb;
+	struct sk_buff *nskb = NULL, *head = NULL;
 	struct sctp_chunk *chunk, *tmp;
 	struct sock *sk;
 	int err = 0;
 	int padding;		/* How much padding do we need?  */
+	int pkt_size;
 	__u8 has_data = 0;
+	int gso = 0;
+	int pktcount = 0;
 	struct dst_entry *dst;
 	unsigned char *auth = NULL;	/* pointer to auth in skb data */
 
@@ -400,18 +428,37 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
 	sk = chunk->skb->sk;
 
-	/* Allocate the new skb.  */
-	nskb = alloc_skb(packet->size + MAX_HEADER, gfp);
-	if (!nskb)
+	/* Allocate the head skb, or main one if not in GSO */
+	if (packet->size > tp->pathmtu && !packet->ipfragok) {
+		if (sk_can_gso(sk)) {
+			gso = 1;
+			pkt_size = packet->overhead;
+		} else {
+			/* If this happens, we trash this packet and try
+			 * to build a new one, hopefully correct this
+			 * time. Application may notice this error.
+			 */
+			pr_err_once("Trying to GSO but underlying device doesn't support it.");
+			goto nomem;
+		}
+	} else {
+		pkt_size = packet->size;
+	}
+	head = alloc_skb(pkt_size + MAX_HEADER, gfp);
+	if (!head)
 		goto nomem;
+	if (gso) {
+		NAPI_GRO_CB(head)->last = head;
+		skb_shinfo(head)->gso_type = sk->sk_gso_type;
+	}
 
 	/* Make sure the outbound skb has enough header room reserved. */
-	skb_reserve(nskb, packet->overhead + MAX_HEADER);
+	skb_reserve(head, packet->overhead + MAX_HEADER);
 
 	/* Set the owning socket so that we know where to get the
 	 * destination IP address.
 	 */
-	sctp_packet_set_owner_w(nskb, sk);
+	sctp_packet_set_owner_w(head, sk);
 
 	if (!sctp_transport_dst_check(tp)) {
 		sctp_transport_route(tp, NULL, sctp_sk(sk));
@@ -422,11 +469,11 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	dst = dst_clone(tp->dst);
 	if (!dst)
 		goto no_route;
-	skb_dst_set(nskb, dst);
+	skb_dst_set(head, dst);
 
 	/* Build the SCTP header.  */
-	sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr));
-	skb_reset_transport_header(nskb);
+	sh = (struct sctphdr *)skb_push(head, sizeof(struct sctphdr));
+	skb_reset_transport_header(head);
 	sh->source = htons(packet->source_port);
 	sh->dest   = htons(packet->destination_port);
 
@@ -441,90 +488,133 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	sh->vtag     = htonl(packet->vtag);
 	sh->checksum = 0;
 
-	/**
-	 * 6.10 Bundling
-	 *
-	 *    An endpoint bundles chunks by simply including multiple
-	 *    chunks in one outbound SCTP packet.  ...
-	 */
-
-	/**
-	 * 3.2  Chunk Field Descriptions
-	 *
-	 * The total length of a chunk (including Type, Length and
-	 * Value fields) MUST be a multiple of 4 bytes.  If the length
-	 * of the chunk is not a multiple of 4 bytes, the sender MUST
-	 * pad the chunk with all zero bytes and this padding is not
-	 * included in the chunk length field.  The sender should
-	 * never pad with more than 3 bytes.
-	 *
-	 * [This whole comment explains WORD_ROUND() below.]
-	 */
-
 	pr_debug("***sctp_transmit_packet***\n");
 
-	list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
-		list_del_init(&chunk->list);
-		if (sctp_chunk_is_data(chunk)) {
-			/* 6.3.1 C4) When data is in flight and when allowed
-			 * by rule C5, a new RTT measurement MUST be made each
-			 * round trip.  Furthermore, new RTT measurements
-			 * SHOULD be made no more than once per round-trip
-			 * for a given destination transport address.
-			 */
+	do {
+		/* Set up convenience variables... */
+		chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list);
+		pktcount++;
 
-			if (!chunk->resent && !tp->rto_pending) {
-				chunk->rtt_in_progress = 1;
-				tp->rto_pending = 1;
+		/* Calculate packet size, so it fits in PMTU. Leave
+		 * other chunks for the next packets.
+		 */
+		if (gso) {
+			pkt_size = packet->overhead;
+			list_for_each_entry(chunk, &packet->chunk_list, list) {
+				int padded = WORD_ROUND(chunk->skb->len);
+
+				if (pkt_size + padded > tp->pathmtu)
+					break;
+				pkt_size += padded;
 			}
 
-			has_data = 1;
-		}
+			/* Allocate a new skb. */
+			nskb = alloc_skb(pkt_size + MAX_HEADER, gfp);
+			if (!nskb)
+				goto nomem;
 
-		padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len;
-		if (padding)
-			memset(skb_put(chunk->skb, padding), 0, padding);
+			/* Make sure the outbound skb has enough header
+			 * room reserved.
+			 */
+			skb_reserve(nskb, packet->overhead + MAX_HEADER);
+		} else {
+			nskb = head;
+		}
 
-		/* if this is the auth chunk that we are adding,
-		 * store pointer where it will be added and put
-		 * the auth into the packet.
+		/**
+		 * 3.2  Chunk Field Descriptions
+		 *
+		 * The total length of a chunk (including Type, Length and
+		 * Value fields) MUST be a multiple of 4 bytes.  If the length
+		 * of the chunk is not a multiple of 4 bytes, the sender MUST
+		 * pad the chunk with all zero bytes and this padding is not
+		 * included in the chunk length field.  The sender should
+		 * never pad with more than 3 bytes.
+		 *
+		 * [This whole comment explains WORD_ROUND() below.]
 		 */
-		if (chunk == packet->auth)
-			auth = skb_tail_pointer(nskb);
 
-		memcpy(skb_put(nskb, chunk->skb->len),
+		pkt_size -= packet->overhead;
+		list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
+			list_del_init(&chunk->list);
+			if (sctp_chunk_is_data(chunk)) {
+				/* 6.3.1 C4) When data is in flight and when allowed
+				 * by rule C5, a new RTT measurement MUST be made each
+				 * round trip.  Furthermore, new RTT measurements
+				 * SHOULD be made no more than once per round-trip
+				 * for a given destination transport address.
+				 */
+
+				if (!chunk->resent && !tp->rto_pending) {
+					chunk->rtt_in_progress = 1;
+					tp->rto_pending = 1;
+				}
+
+				has_data = 1;
+			}
+
+			padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len;
+			if (padding)
+				memset(skb_put(chunk->skb, padding), 0, padding);
+
+			/* if this is the auth chunk that we are adding,
+			 * store pointer where it will be added and put
+			 * the auth into the packet.
+			 */
+			if (chunk == packet->auth)
+				auth = skb_tail_pointer(nskb);
+
+			memcpy(skb_put(nskb, chunk->skb->len),
 			       chunk->skb->data, chunk->skb->len);
 
-		pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, "
-			 "rtt_in_progress:%d\n", chunk,
-			 sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)),
-			 chunk->has_tsn ? "TSN" : "No TSN",
-			 chunk->has_tsn ? ntohl(chunk->subh.data_hdr->tsn) : 0,
-			 ntohs(chunk->chunk_hdr->length), chunk->skb->len,
-			 chunk->rtt_in_progress);
-
-		/*
-		 * If this is a control chunk, this is our last
-		 * reference. Free data chunks after they've been
-		 * acknowledged or have failed.
-		 */
-		if (!sctp_chunk_is_data(chunk))
-			sctp_chunk_free(chunk);
-	}
+			pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, rtt_in_progress:%d\n",
+				 chunk,
+				 sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)),
+				 chunk->has_tsn ? "TSN" : "No TSN",
+				 chunk->has_tsn ? ntohl(chunk->subh.data_hdr->tsn) : 0,
+				 ntohs(chunk->chunk_hdr->length), chunk->skb->len,
+				 chunk->rtt_in_progress);
+
+			/* If this is a control chunk, this is our last
+			 * reference. Free data chunks after they've been
+			 * acknowledged or have failed.
+			 * Re-queue auth chunks if needed.
+			 */
+			pkt_size -= WORD_ROUND(chunk->skb->len);
 
-	/* SCTP-AUTH, Section 6.2
-	 *    The sender MUST calculate the MAC as described in RFC2104 [2]
-	 *    using the hash function H as described by the MAC Identifier and
-	 *    the shared association key K based on the endpoint pair shared key
-	 *    described by the shared key identifier.  The 'data' used for the
-	 *    computation of the AUTH-chunk is given by the AUTH chunk with its
-	 *    HMAC field set to zero (as shown in Figure 6) followed by all
-	 *    chunks that are placed after the AUTH chunk in the SCTP packet.
-	 */
-	if (auth)
-		sctp_auth_calculate_hmac(asoc, nskb,
-					 (struct sctp_auth_chunk *)auth,
-					 gfp);
+			if (chunk == packet->auth && !list_empty(&packet->chunk_list))
+				list_add(&chunk->list, &packet->chunk_list);
+			else if (!sctp_chunk_is_data(chunk))
+				sctp_chunk_free(chunk);
+
+			if (!pkt_size)
+				break;
+		}
+
+		/* SCTP-AUTH, Section 6.2
+		 *    The sender MUST calculate the MAC as described in RFC2104 [2]
+		 *    using the hash function H as described by the MAC Identifier and
+		 *    the shared association key K based on the endpoint pair shared key
+		 *    described by the shared key identifier.  The 'data' used for the
+		 *    computation of the AUTH-chunk is given by the AUTH chunk with its
+		 *    HMAC field set to zero (as shown in Figure 6) followed by all
+		 *    chunks that are placed after the AUTH chunk in the SCTP packet.
+		 */
+		if (auth)
+			sctp_auth_calculate_hmac(asoc, nskb,
+						 (struct sctp_auth_chunk *)auth,
+						 gfp);
+
+		if (!gso)
+			break;
+
+		if (skb_gro_receive(&head, nskb))
+			goto nomem;
+		nskb = NULL;
+		if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >=
+				 sk->sk_gso_max_segs))
+			goto nomem;
+	} while (!list_empty(&packet->chunk_list));
 
 	/* 2) Calculate the Adler-32 checksum of the whole packet,
 	 *    including the SCTP common header and all the
@@ -532,16 +622,18 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	 *
 	 * Note: Adler-32 is no longer applicable, as has been replaced
 	 * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
+	 *
+	 * If it's a GSO packet, it's postponed to sctp_skb_segment.
 	 */
-	if (!sctp_checksum_disable) {
-		if (!(dst->dev->features & NETIF_F_SCTP_CRC) ||
-		    (dst_xfrm(dst) != NULL) || packet->ipfragok) {
-			sh->checksum = sctp_compute_cksum(nskb, 0);
+	if (!sctp_checksum_disable || gso) {
+		if (!gso && (!(dst->dev->features & NETIF_F_SCTP_CRC) ||
+			     dst_xfrm(dst) || packet->ipfragok)) {
+			sh->checksum = sctp_compute_cksum(head, 0);
 		} else {
 			/* no need to seed pseudo checksum for SCTP */
-			nskb->ip_summed = CHECKSUM_PARTIAL;
-			nskb->csum_start = skb_transport_header(nskb) - nskb->head;
-			nskb->csum_offset = offsetof(struct sctphdr, checksum);
+			head->ip_summed = CHECKSUM_PARTIAL;
+			head->csum_start = skb_transport_header(head) - head->head;
+			head->csum_offset = offsetof(struct sctphdr, checksum);
 		}
 	}
 
@@ -557,7 +649,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	 * Note: The works for IPv6 layer checks this bit too later
 	 * in transmission.  See IP6_ECN_flow_xmit().
 	 */
-	tp->af_specific->ecn_capable(nskb->sk);
+	tp->af_specific->ecn_capable(sk);
 
 	/* Set up the IP options.  */
 	/* BUG: not implemented
@@ -566,7 +658,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 
 	/* Dump that on IP!  */
 	if (asoc) {
-		asoc->stats.opackets++;
+		asoc->stats.opackets += pktcount;
 		if (asoc->peer.last_sent_to != tp)
 			/* Considering the multiple CPU scenario, this is a
 			 * "correcter" place for last_sent_to.  --xguo
@@ -589,16 +681,36 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 		}
 	}
 
-	pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len);
+	pr_debug("***sctp_transmit_packet*** skb->len:%d\n", head->len);
+
+	if (gso) {
+		/* Cleanup our debris for IP stacks */
+		memset(head->cb, 0, max(sizeof(struct inet_skb_parm),
+					sizeof(struct inet6_skb_parm)));
 
-	nskb->ignore_df = packet->ipfragok;
-	tp->af_specific->sctp_xmit(nskb, tp);
+		skb_shinfo(head)->gso_segs = pktcount;
+		skb_shinfo(head)->gso_size = GSO_BY_FRAGS;
+
+		/* We have to refresh this in case we are xmiting to
+		 * more than one transport at a time
+		 */
+		rcu_read_lock();
+		if (__sk_dst_get(sk) != tp->dst) {
+			dst_hold(tp->dst);
+			sk_setup_caps(sk, tp->dst);
+		}
+		rcu_read_unlock();
+	}
+	head->ignore_df = packet->ipfragok;
+	tp->af_specific->sctp_xmit(head, tp);
 
 out:
 	sctp_packet_reset(packet);
 	return err;
 no_route:
-	kfree_skb(nskb);
+	kfree_skb(head);
+	if (nskb != head)
+		kfree_skb(nskb);
 
 	if (asoc)
 		IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES);
@@ -751,39 +863,63 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet,
 					struct sctp_chunk *chunk,
 					u16 chunk_len)
 {
-	size_t psize;
-	size_t pmtu;
-	int too_big;
+	size_t psize, pmtu;
 	sctp_xmit_t retval = SCTP_XMIT_OK;
 
 	psize = packet->size;
-	pmtu  = ((packet->transport->asoc) ?
-		(packet->transport->asoc->pathmtu) :
-		(packet->transport->pathmtu));
-
-	too_big = (psize + chunk_len > pmtu);
+	if (packet->transport->asoc)
+		pmtu = packet->transport->asoc->pathmtu;
+	else
+		pmtu = packet->transport->pathmtu;
 
 	/* Decide if we need to fragment or resubmit later. */
-	if (too_big) {
-		/* It's OK to fragmet at IP level if any one of the following
+	if (psize + chunk_len > pmtu) {
+		/* It's OK to fragment at IP level if any one of the following
 		 * is true:
-		 * 	1. The packet is empty (meaning this chunk is greater
-		 * 	   the MTU)
-		 * 	2. The chunk we are adding is a control chunk
-		 * 	3. The packet doesn't have any data in it yet and data
-		 * 	requires authentication.
+		 *	1. The packet is empty (meaning this chunk is greater
+		 *	   the MTU)
+		 *	2. The packet doesn't have any data in it yet and data
+		 *	   requires authentication.
 		 */
-		if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) ||
+		if (sctp_packet_empty(packet) ||
 		    (!packet->has_data && chunk->auth)) {
 			/* We no longer do re-fragmentation.
 			 * Just fragment at the IP layer, if we
 			 * actually hit this condition
 			 */
 			packet->ipfragok = 1;
-		} else {
-			retval = SCTP_XMIT_PMTU_FULL;
+			goto out;
 		}
+
+		/* It is also okay to fragment if the chunk we are
+		 * adding is a control chunk, but only if current packet
+		 * is not a GSO one otherwise it causes fragmentation of
+		 * a large frame. So in this case we allow the
+		 * fragmentation by forcing it to be in a new packet.
+		 */
+		if (!sctp_chunk_is_data(chunk) && packet->has_data)
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		if (psize + chunk_len > packet->max_size)
+			/* Hit GSO/PMTU limit, gotta flush */
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		if (!packet->transport->burst_limited &&
+		    psize + chunk_len > (packet->transport->cwnd >> 1))
+			/* Do not allow a single GSO packet to use more
+			 * than half of cwnd.
+			 */
+			retval = SCTP_XMIT_PMTU_FULL;
+
+		if (packet->transport->burst_limited &&
+		    psize + chunk_len > (packet->transport->burst_limited >> 1))
+			/* Do not allow a single GSO packet to use more
+			 * than half of original cwnd.
+			 */
+			retval = SCTP_XMIT_PMTU_FULL;
+		/* Otherwise it will fit in the GSO packet */
 	}
 
+out:
 	return retval;
 }

net/sctp/protocol.c

@@ -1516,6 +1516,9 @@ static __init int sctp_init(void)
 	if (status)
 		goto err_v6_add_protocol;
 
+	if (sctp_offload_init() < 0)
+		pr_crit("%s: Cannot add SCTP protocol offload\n", __func__);
+
 out:
 	return status;
 err_v6_add_protocol:

net/sctp/socket.c

@@ -4003,6 +4003,8 @@ static int sctp_init_sock(struct sock *sk)
 		return -ESOCKTNOSUPPORT;
 	}
 
+	sk->sk_gso_type = SKB_GSO_SCTP;
+
 	/* Initialize default send parameters. These parameters can be
 	 * modified with the SCTP_DEFAULT_SEND_PARAM socket option.
 	 */