sctp: Add GSO support

SCTP has this pecualiarity that its packets cannot be just segmented to
(P)MTU. Its chunks must be contained in IP segments, padding respected.
So we can't just generate a big skb, set gso_size to the fragmentation
point and deliver it to IP layer.

This patch takes a different approach. SCTP will now build a skb as it
would be if it was received using GRO. That is, there will be a cover
skb with protocol headers and children ones containing the actual
segments, already segmented to a way that respects SCTP RFCs.

With that, we can tell skb_segment() to just split based on frag_list,
trusting its sizes are already in accordance.

This way SCTP can benefit from GSO and instead of passing several
packets through the stack, it can pass a single large packet.

v2:
- Added support for receiving GSO frames, as requested by Dave Miller.
- Clear skb->cb if packet is GSO (otherwise it's not used by SCTP)
- Added heuristics similar to what we have in TCP for not generating
  single GSO packets that fills cwnd.
v3:
- consider sctphdr size in skb_gso_transport_seglen()
- rebased due to 5c7cdf339af5 ("gso: Remove arbitrary checks for
  unsupported GSO")

Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Tested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 98 insertions, 0 deletions

diff --git a/net/sctp/offload.c b/net/sctp/offload.c
new file mode 100644
index 000000000000..a37887b373a7
--- /dev/null
+++ b/net/sctp/offload.c
@@ -0,0 +1,98 @@
+/*
+ * 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);
+}