diff mbox series

[net-next,08/10] net: add support for ipv4 big tcp

Message ID c28bb5c3d730677be7f90a44a9e29fec56393443.1673666803.git.lucien.xin@gmail.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series net: support ipv4 big tcp | expand

Checks

Context Check Description
netdev/tree_selection success Clearly marked for net-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 7 this patch: 7
netdev/cc_maintainers warning 4 maintainers not CCed: dsahern@kernel.org richardbgobert@gmail.com martin.lau@kernel.org steffen.klassert@secunet.com
netdev/build_clang success Errors and warnings before: 1 this patch: 1
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 7 this patch: 7
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 72 lines checked
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Xin Long Jan. 14, 2023, 3:31 a.m. UTC
Similar to Eric's IPv6 BIG TCP, this patch is to enable IPv4 BIG TCP.

Firstly, allow sk->sk_gso_max_size to be set to a value greater than
GSO_LEGACY_MAX_SIZE by not trimming gso_max_size in sk_trim_gso_size()
for IPv4 TCP sockets.

Then on TX path, set IP header tot_len to 0 when skb->len > IP_MAX_MTU
in __ip_local_out() to allow to send BIG TCP packets, and this implies
that skb->len is the length of a IPv4 packet; On RX path, use skb->len
as the length of the IPv4 packet when the IP header tot_len is 0 and
skb->len > IP_MAX_MTU in ip_rcv_core(). As the API iph_set_totlen() and
skb_ip_totlen() are used in __ip_local_out() and ip_rcv_core(), we only
need to update these APIs.

Also in GRO receive, add the check for ETH_P_IP/IPPROTO_TCP, and allows
the merged packet size >= GRO_LEGACY_MAX_SIZE in skb_gro_receive(). In
GRO complete, set IP header tot_len to 0 when the merged packet size
greater than IP_MAX_MTU in iph_set_totlen() so that it can be processed
on RX path.

Note that by checking skb_is_gso_tcp() in API iph_totlen(), it makes
this implementation safe to use iph->len == 0 indicates IPv4 BIG TCP
packets.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
 net/core/gro.c       |  6 +++---
 net/core/sock.c      | 11 ++---------
 net/ipv4/af_inet.c   |  7 ++++---
 net/ipv4/ip_input.c  |  2 +-
 net/ipv4/ip_output.c |  2 +-
 5 files changed, 11 insertions(+), 17 deletions(-)
diff mbox series

Patch

diff --git a/net/core/gro.c b/net/core/gro.c
index 506f83d715f8..82656dc787f2 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -169,9 +169,9 @@  int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 		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 ||
+		if (NAPI_GRO_CB(skb)->proto != IPPROTO_TCP ||
+		    (p->protocol == htons(ETH_P_IPV6) &&
+		     skb_headroom(p) < sizeof(struct hop_jumbo_hdr)) ||
 		    p->encapsulation)
 			return -E2BIG;
 	}
diff --git a/net/core/sock.c b/net/core/sock.c
index f954d5893e79..554aa09fe504 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2375,15 +2375,8 @@  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;
+	if (sk->sk_gso_max_size > GSO_LEGACY_MAX_SIZE && !sk_is_tcp(sk))
+		sk->sk_gso_max_size = GSO_LEGACY_MAX_SIZE;
 }
 
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6c0ec2789943..2f992a323b95 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1485,6 +1485,7 @@  struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	if (unlikely(ip_fast_csum((u8 *)iph, 5)))
 		goto out;
 
+	NAPI_GRO_CB(skb)->proto = proto;
 	id = ntohl(*(__be32 *)&iph->id);
 	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
 	id >>= 16;
@@ -1618,9 +1619,9 @@  int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len)
 
 int inet_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	__be16 newlen = htons(skb->len - nhoff);
 	struct iphdr *iph = (struct iphdr *)(skb->data + nhoff);
 	const struct net_offload *ops;
+	__be16 totlen = iph->tot_len;
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
@@ -1629,8 +1630,8 @@  int inet_gro_complete(struct sk_buff *skb, int nhoff)
 		skb_set_inner_network_header(skb, nhoff);
 	}
 
-	csum_replace2(&iph->check, iph->tot_len, newlen);
-	iph->tot_len = newlen;
+	iph_set_totlen(iph, skb->len - nhoff);
+	csum_replace2(&iph->check, totlen, iph->tot_len);
 
 	ops = rcu_dereference(inet_offloads[proto]);
 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index e880ce77322a..0aa8c49b4e1b 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -511,7 +511,7 @@  static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 	if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
 		goto csum_error;
 
-	len = ntohs(iph->tot_len);
+	len = skb_ip_totlen(skb);
 	if (skb->len < len) {
 		drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 		__IP_INC_STATS(net, IPSTATS_MIB_INTRUNCATEDPKTS);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 922c87ef1ab5..4e4e308c3230 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -100,7 +100,7 @@  int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
-	iph->tot_len = htons(skb->len);
+	iph_set_totlen(iph, skb->len);
 	ip_send_check(iph);
 
 	/* if egress device is enslaved to an L3 master device pass the