Merge branch 'big-tcp'

Eric Dumazet says:

====================
tcp: BIG TCP implementation

This series implements BIG TCP as presented in netdev 0x15:

https://netdevconf.info/0x15/session.html?BIG-TCP

Jonathan Corbet made a nice summary: https://lwn.net/Articles/884104/

Standard TSO/GRO packet limit is 64KB

With BIG TCP, we allow bigger TSO/GRO packet sizes for IPv6 traffic.

Note that this feature is by default not enabled, because it might
break some eBPF programs assuming TCP header immediately follows IPv6 header.

While tcpdump recognizes the HBH/Jumbo header, standard pcap filters
are unable to skip over IPv6 extension headers.

Reducing number of packets traversing networking stack usually improves
performance, as shown on this experiment using a 100Gbit NIC, and 4K MTU.

'Standard' performance with current (74KB) limits.
for i in {1..10}; do ./netperf -t TCP_RR -H iroa23  -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
77           138          183          8542.19
79           143          178          8215.28
70           117          164          9543.39
80           144          176          8183.71
78           126          155          9108.47
80           146          184          8115.19
71           113          165          9510.96
74           113          164          9518.74
79           137          178          8575.04
73           111          171          9561.73

Now enable BIG TCP on both hosts.

ip link set dev eth0 gro_max_size 185000 gso_max_size 185000
for i in {1..10}; do ./netperf -t TCP_RR -H iroa23  -- -r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done
57           83           117          13871.38
64           118          155          11432.94
65           116          148          11507.62
60           105          136          12645.15
60           103          135          12760.34
60           102          134          12832.64
62           109          132          10877.68
58           82           115          14052.93
57           83           124          14212.58
57           82           119          14196.01

We see an increase of transactions per second, and lower latencies as well.

v7: adopt unsafe_memcpy() in mlx5 to avoid FORTIFY warnings.

v6: fix a compilation error for CONFIG_IPV6=n in
    "net: allow gso_max_size to exceed 65536", reported by kernel bots.

v5: Replaced two patches (that were adding new attributes) with patches
    from Alexander Duyck. Idea is to reuse existing gso_max_size/gro_max_size

v4: Rebased on top of Jakub series (Merge branch 'tso-gso-limit-split')
    max_tso_size is now family independent.

v3: Fixed a typo in RFC number (Alexander)
    Added Reviewed-by: tags from Tariq on mlx4/mlx5 parts.

v2: Removed the MAX_SKB_FRAGS change, this belongs to a different series.
    Addressed feedback, for Alexander and nvidia folks.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

11 files changed, 114 insertions, 24 deletions

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 8d54fef9a568..9b5a1f630bb0 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -1001,7 +1001,7 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
 		cb->pkt_len = skb->len;
 	} else {
 		if (__skb->wire_len < skb->len ||
-		    __skb->wire_len > GSO_MAX_SIZE)
+		    __skb->wire_len > GSO_LEGACY_MAX_SIZE)
 			return -EINVAL;
 		cb->pkt_len = __skb->wire_len;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index a601da3b4a7c..d93456c75b55 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2998,11 +2998,12 @@ EXPORT_SYMBOL(netif_set_real_num_queues);
  * @size:	max skb->len of a TSO frame
  *
  * Set the limit on the size of TSO super-frames the device can handle.
- * Unless explicitly set the stack will assume the value of %GSO_MAX_SIZE.
+ * Unless explicitly set the stack will assume the value of
+ * %GSO_LEGACY_MAX_SIZE.
  */
 void netif_set_tso_max_size(struct net_device *dev, unsigned int size)
 {
-	dev->tso_max_size = size;
+	dev->tso_max_size = min(GSO_MAX_SIZE, size);
 	if (size < READ_ONCE(dev->gso_max_size))
 		netif_set_gso_max_size(dev, size);
 }
@@ -10595,9 +10596,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
-	dev->gso_max_size = GSO_MAX_SIZE;
+	dev->gso_max_size = GSO_LEGACY_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
-	dev->gro_max_size = GRO_MAX_SIZE;
+	dev->gro_max_size = GRO_LEGACY_MAX_SIZE;
 	dev->tso_max_size = TSO_LEGACY_MAX_SIZE;
 	dev->tso_max_segs = TSO_MAX_SEGS;
 	dev->upper_level = 1;
diff --git a/net/core/gro.c b/net/core/gro.c
index 78110edf5d4b..b4190eb08467 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -167,6 +167,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
+	if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
+		if (p->protocol != htons(ETH_P_IPV6) ||
+		    skb_headroom(p) < sizeof(struct hop_jumbo_hdr) ||
+		    ipv6_hdr(p)->nexthdr != IPPROTO_TCP ||
+		    p->encapsulation)
+			return -E2BIG;
+	}
+
 	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index bdc891326102..ac45328607f7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1064,6 +1064,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */
 	       + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */
 	       + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_TSO_MAX_SIZE */
+	       + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
@@ -1769,6 +1771,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) ||
 	    nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) ||
 	    nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) ||
+	    nla_put_u32(skb, IFLA_TSO_MAX_SIZE, dev->tso_max_size) ||
+	    nla_put_u32(skb, IFLA_TSO_MAX_SEGS, dev->tso_max_segs) ||
 #ifdef CONFIG_RPS
 	    nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) ||
 #endif
@@ -1922,6 +1926,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_NEW_IFINDEX]	= NLA_POLICY_MIN(NLA_S32, 1),
 	[IFLA_PARENT_DEV_NAME]	= { .type = NLA_NUL_STRING },
 	[IFLA_GRO_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_TSO_MAX_SIZE]	= { .type = NLA_REJECT },
+	[IFLA_TSO_MAX_SEGS]	= { .type = NLA_REJECT },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2354,14 +2360,6 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
-	if (tb[IFLA_GRO_MAX_SIZE]) {
-		u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]);
-
-		if (gro_max_size > GRO_MAX_SIZE) {
-			NL_SET_ERR_MSG(extack, "too big gro_max_size");
-			return -EINVAL;
-		}
-	}
 	return 0;
 }
 
@@ -2811,7 +2809,7 @@ static int do_setlink(const struct sk_buff *skb,
 	if (tb[IFLA_GSO_MAX_SIZE]) {
 		u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]);
 
-		if (max_size > GSO_MAX_SIZE || max_size > dev->tso_max_size) {
+		if (max_size > dev->tso_max_size) {
 			err = -EINVAL;
 			goto errout;
 		}
diff --git a/net/core/sock.c b/net/core/sock.c
index 6b287eb5427b..24a46a1e4f28 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2293,6 +2293,19 @@ void sk_free_unlock_clone(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
 
+static void sk_trim_gso_size(struct sock *sk)
+{
+	if (sk->sk_gso_max_size <= GSO_LEGACY_MAX_SIZE)
+		return;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6 &&
+	    sk_is_tcp(sk) &&
+	    !ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+		return;
+#endif
+	sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
+}
+
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
 	u32 max_segs = 1;
@@ -2312,6 +2325,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 			sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
 			/* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */
 			sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size);
+			sk_trim_gso_size(sk);
 			sk->sk_gso_max_size -= (MAX_TCP_HEADER + 1);
 			/* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */
 			max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index c7d30a3bbd81..075e744bfb48 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -310,7 +310,7 @@ static u32 bbr_tso_segs_goal(struct sock *sk)
 	 */
 	bytes = min_t(unsigned long,
 		      sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
-		      GSO_MAX_SIZE - 1 - MAX_TCP_HEADER);
+		      GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER);
 	segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
 
 	return min(segs, 0x7FU);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index b0918839bee7..68178e7280ce 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -372,7 +372,7 @@ static void cubictcp_state(struct sock *sk, u8 new_state)
  * We apply another 100% factor because @rate is doubled at this point.
  * We cap the cushion to 1ms.
  */
-static u32 hystart_ack_delay(struct sock *sk)
+static u32 hystart_ack_delay(const struct sock *sk)
 {
 	unsigned long rate;
 
@@ -380,7 +380,7 @@ static u32 hystart_ack_delay(struct sock *sk)
 	if (!rate)
 		return 0;
 	return min_t(u64, USEC_PER_MSEC,
-		     div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate));
+		     div64_ul((u64)sk->sk_gso_max_size * 4 * USEC_PER_SEC, rate));
 }
 
 static void hystart_update(struct sock *sk, u32 delay)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b092228e4342..b4b2284ed4a2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1553,7 +1553,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	 * SO_SNDBUF values.
 	 * Also allow first and last skb in retransmit queue to be split.
 	 */
-	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_LEGACY_MAX_SIZE);
 	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
 		     tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
 		     skb != tcp_rtx_queue_head(sk) &&
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index c4fc03c1ac99..d12dba2dd535 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -77,7 +77,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct ipv6hdr *ipv6h;
 	const struct net_offload *ops;
-	int proto;
+	int proto, nexthdr;
 	struct frag_hdr *fptr;
 	unsigned int payload_len;
 	u8 *prevhdr;
@@ -87,6 +87,28 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 	bool gso_partial;
 
 	skb_reset_network_header(skb);
+	nexthdr = ipv6_has_hopopt_jumbo(skb);
+	if (nexthdr) {
+		const int hophdr_len = sizeof(struct hop_jumbo_hdr);
+		int err;
+
+		err = skb_cow_head(skb, 0);
+		if (err < 0)
+			return ERR_PTR(err);
+
+		/* remove the HBH header.
+		 * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
+		 */
+		memmove(skb_mac_header(skb) + hophdr_len,
+			skb_mac_header(skb),
+			ETH_HLEN + sizeof(struct ipv6hdr));
+		skb->data += hophdr_len;
+		skb->len -= hophdr_len;
+		skb->network_header += hophdr_len;
+		skb->mac_header += hophdr_len;
+		ipv6h = (struct ipv6hdr *)skb->data;
+		ipv6h->nexthdr = nexthdr;
+	}
 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
 		goto out;
@@ -320,15 +342,43 @@ static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
 INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 {
 	const struct net_offload *ops;
-	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
+	struct ipv6hdr *iph;
 	int err = -ENOSYS;
+	u32 payload_len;
 
 	if (skb->encapsulation) {
 		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
 	}
 
-	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
+	payload_len = skb->len - nhoff - sizeof(*iph);
+	if (unlikely(payload_len > IPV6_MAXPLEN)) {
+		struct hop_jumbo_hdr *hop_jumbo;
+		int hoplen = sizeof(*hop_jumbo);
+
+		/* Move network header left */
+		memmove(skb_mac_header(skb) - hoplen, skb_mac_header(skb),
+			skb->transport_header - skb->mac_header);
+		skb->data -= hoplen;
+		skb->len += hoplen;
+		skb->mac_header -= hoplen;
+		skb->network_header -= hoplen;
+		iph = (struct ipv6hdr *)(skb->data + nhoff);
+		hop_jumbo = (struct hop_jumbo_hdr *)(iph + 1);
+
+		/* Build hop-by-hop options */
+		hop_jumbo->nexthdr = iph->nexthdr;
+		hop_jumbo->hdrlen = 0;
+		hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+		hop_jumbo->tlv_len = 4;
+		hop_jumbo->jumbo_payload_len = htonl(payload_len + hoplen);
+
+		iph->nexthdr = NEXTHDR_HOP;
+		iph->payload_len = 0;
+	} else {
+		iph = (struct ipv6hdr *)(skb->data + nhoff);
+		iph->payload_len = htons(payload_len);
+	}
 
 	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index afa5bd4ad167..4081b12a01ff 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -182,7 +182,9 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 #endif
 
 	mtu = ip6_skb_dst_mtu(skb);
-	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+	if (skb_is_gso(skb) &&
+	    !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) &&
+	    !skb_gso_validate_network_len(skb, mtu))
 		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
 
 	if ((skb->len > mtu && !skb_is_gso(skb)) ||
@@ -252,6 +254,8 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
 	struct inet6_dev *idev = ip6_dst_idev(dst);
+	struct hop_jumbo_hdr *hop_jumbo;
+	int hoplen = sizeof(*hop_jumbo);
 	unsigned int head_room;
 	struct ipv6hdr *hdr;
 	u8  proto = fl6->flowi6_proto;
@@ -259,7 +263,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	int hlimit = -1;
 	u32 mtu;
 
-	head_room = sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dev);
+	head_room = sizeof(struct ipv6hdr) + hoplen + LL_RESERVED_SPACE(dev);
 	if (opt)
 		head_room += opt->opt_nflen + opt->opt_flen;
 
@@ -282,6 +286,20 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 					     &fl6->saddr);
 	}
 
+	if (unlikely(seg_len > IPV6_MAXPLEN)) {
+		hop_jumbo = skb_push(skb, hoplen);
+
+		hop_jumbo->nexthdr = proto;
+		hop_jumbo->hdrlen = 0;
+		hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
+		hop_jumbo->tlv_len = 4;
+		hop_jumbo->jumbo_payload_len = htonl(seg_len + hoplen);
+
+		proto = IPPROTO_HOPOPTS;
+		seg_len = 0;
+		IP6CB(skb)->flags |= IP6SKB_FAKEJUMBO;
+	}
+
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	hdr = ipv6_hdr(skb);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 72fe6669c50d..a63df055ac57 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -134,7 +134,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 		dst_hold(tp->dst);
 		sk_setup_caps(sk, tp->dst);
 	}
-	packet->max_size = sk_can_gso(sk) ? READ_ONCE(tp->dst->dev->gso_max_size)
+	packet->max_size = sk_can_gso(sk) ? min(READ_ONCE(tp->dst->dev->gso_max_size),
+						GSO_LEGACY_MAX_SIZE)
 					  : asoc->pathmtu;
 	rcu_read_unlock();
 }