Merge branch 'add-tcp-fraglist-gro-support'

Felix Fietkau says:

====================
Add TCP fraglist GRO support

When forwarding TCP after GRO, software segmentation is very expensive,
especially when the checksum needs to be recalculated.
One case where that's currently unavoidable is when routing packets over
PPPoE. Performance improves significantly when using fraglist GRO
implemented in the same way as for UDP.

When NETIF_F_GRO_FRAGLIST is enabled, perform a lookup for an established
socket in the same netns as the receiving device. While this may not
cover all relevant use cases in multi-netns configurations, it should be
good enough for most configurations that need this.

Here's a measurement of running 2 TCP streams through a MediaTek MT7622
device (2-core Cortex-A53), which runs NAT with flow offload enabled from
one ethernet port to PPPoE on another ethernet port + cake qdisc set to
1Gbps.

rx-gro-list off: 630 Mbit/s, CPU 35% idle
rx-gro-list on:  770 Mbit/s, CPU 40% idle

Changes since v4:
 - add likely() to prefer the non-fraglist path in check

Changes since v3:
 - optimize __tcpv4_gso_segment_csum
 - add unlikely()
 - reorder dev_net/skb_gro_network_header calls after NETIF_F_GRO_FRAGLIST
   check
 - add support for ipv6 nat
 - drop redundant pskb_may_pull check

Changes since v2:
 - create tcp_gro_header_pull helper function to pull tcp header only once
 - optimize __tcpv4_gso_segment_list_csum, drop obsolete flags check

Changes since v1:
 - revert bogus tcp flags overwrite on segmentation
 - fix kbuild issue with !CONFIG_IPV6
 - only perform socket lookup for the first skb in the GRO train

Changes since RFC:
 - split up patches
 - handle TCP flags mutations
====================

Link: https://lore.kernel.org/r/20240502084450.44009-1-nbd@nbd.nameSigned-off-by: Paolo Abeni <pabeni@redhat.com>

include/net/gro.h

@@ -438,6 +438,7 @@ static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb,
 }
 
 int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
 
 /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
 static inline void gro_normal_list(struct napi_struct *napi)

include/net/tcp.h

@@ -2191,7 +2191,10 @@ void tcp_v4_destroy_sock(struct sock *sk);
 
 struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features);
-struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
+struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb);
+struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th);
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				struct tcphdr *th);
 INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));
 INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));
 INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff));

net/core/gro.c

@@ -231,6 +231,33 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	return 0;
 }
 
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
+{
+	if (unlikely(p->len + skb->len >= 65536))
+		return -E2BIG;
+
+	if (NAPI_GRO_CB(p)->last == p)
+		skb_shinfo(p)->frag_list = skb;
+	else
+		NAPI_GRO_CB(p)->last->next = skb;
+
+	skb_pull(skb, skb_gro_offset(skb));
+
+	NAPI_GRO_CB(p)->last = skb;
+	NAPI_GRO_CB(p)->count++;
+	p->data_len += skb->len;
+
+	/* sk ownership - if any - completely transferred to the aggregated packet */
+	skb->destructor = NULL;
+	skb->sk = NULL;
+	p->truesize += skb->truesize;
+	p->len += skb->len;
+
+	NAPI_GRO_CB(skb)->same_flow = 1;
+
+	return 0;
+}
+
 
 static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
 {

net/ipv4/tcp_offload.c

@@ -28,6 +28,70 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
 	}
 }
 
+static void __tcpv4_gso_segment_csum(struct sk_buff *seg,
+				     __be32 *oldip, __be32 newip,
+				     __be16 *oldport, __be16 newport)
+{
+	struct tcphdr *th;
+	struct iphdr *iph;
+
+	if (*oldip == newip && *oldport == newport)
+		return;
+
+	th = tcp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	inet_proto_csum_replace4(&th->check, seg, *oldip, newip, true);
+	inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
+	*oldport = newport;
+
+	csum_replace4(&iph->check, *oldip, newip);
+	*oldip = newip;
+}
+
+static struct sk_buff *__tcpv4_gso_segment_list_csum(struct sk_buff *segs)
+{
+	const struct tcphdr *th;
+	const struct iphdr *iph;
+	struct sk_buff *seg;
+	struct tcphdr *th2;
+	struct iphdr *iph2;
+
+	seg = segs;
+	th = tcp_hdr(seg);
+	iph = ip_hdr(seg);
+	th2 = tcp_hdr(seg->next);
+	iph2 = ip_hdr(seg->next);
+
+	if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) &&
+	    iph->daddr == iph2->daddr && iph->saddr == iph2->saddr)
+		return segs;
+
+	while ((seg = seg->next)) {
+		th2 = tcp_hdr(seg);
+		iph2 = ip_hdr(seg);
+
+		__tcpv4_gso_segment_csum(seg,
+					 &iph2->saddr, iph->saddr,
+					 &th2->source, th->source);
+		__tcpv4_gso_segment_csum(seg,
+					 &iph2->daddr, iph->daddr,
+					 &th2->dest, th->dest);
+	}
+
+	return segs;
+}
+
+static struct sk_buff *__tcp4_gso_segment_list(struct sk_buff *skb,
+					      netdev_features_t features)
+{
+	skb = skb_segment_list(skb, features, skb_mac_header_len(skb));
+	if (IS_ERR(skb))
+		return skb;
+
+	return __tcpv4_gso_segment_list_csum(skb);
+}
+
 static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
@@ -37,6 +101,9 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
 		return ERR_PTR(-EINVAL);
 
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)
+		return __tcp4_gso_segment_list(skb, features);
+
 	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
 		const struct iphdr *iph = ip_hdr(skb);
 		struct tcphdr *th = tcp_hdr(skb);
@@ -178,61 +245,76 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	return segs;
 }
 
-struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
+struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th)
 {
-	struct sk_buff *pp = NULL;
+	struct tcphdr *th2;
 	struct sk_buff *p;
+
+	list_for_each_entry(p, head, list) {
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		th2 = tcp_hdr(p);
+		if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+
+		return p;
+	}
+
+	return NULL;
+}
+
+struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb)
+{
+	unsigned int thlen, hlen, off;
 	struct tcphdr *th;
-	struct tcphdr *th2;
-	unsigned int len;
-	unsigned int thlen;
-	__be32 flags;
-	unsigned int mss = 1;
-	unsigned int hlen;
-	unsigned int off;
-	int flush = 1;
-	int i;
 
 	off = skb_gro_offset(skb);
 	hlen = off + sizeof(*th);
 	th = skb_gro_header(skb, hlen, off);
 	if (unlikely(!th))
-		goto out;
+		return NULL;
 
 	thlen = th->doff * 4;
 	if (thlen < sizeof(*th))
-		goto out;
+		return NULL;
 
 	hlen = off + thlen;
 	if (!skb_gro_may_pull(skb, hlen)) {
 		th = skb_gro_header_slow(skb, hlen, off);
 		if (unlikely(!th))
-			goto out;
+			return NULL;
 	}
 
 	skb_gro_pull(skb, thlen);
 
-	len = skb_gro_len(skb);
-	flags = tcp_flag_word(th);
-
-	list_for_each_entry(p, head, list) {
-		if (!NAPI_GRO_CB(p)->same_flow)
-			continue;
+	return th;
+}
 
-		th2 = tcp_hdr(p);
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				struct tcphdr *th)
+{
+	unsigned int thlen = th->doff * 4;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
+	struct tcphdr *th2;
+	unsigned int len;
+	__be32 flags;
+	unsigned int mss = 1;
+	int flush = 1;
+	int i;
 
-		if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
-			NAPI_GRO_CB(p)->same_flow = 0;
-			continue;
-		}
+	len = skb_gro_len(skb);
+	flags = tcp_flag_word(th);
 
-		goto found;
-	}
-	p = NULL;
-	goto out_check_final;
+	p = tcp_gro_lookup(head, th);
+	if (!p)
+		goto out_check_final;
 
-found:
 	/* Include the IP ID check below from the inner most IP hdr */
+	th2 = tcp_hdr(p);
 	flush = NAPI_GRO_CB(p)->flush;
 	flush |= (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
@@ -267,6 +349,18 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
 	flush |= skb_cmp_decrypted(p, skb);
 
+	if (unlikely(NAPI_GRO_CB(p)->is_flist)) {
+		flush |= (__force int)(flags ^ tcp_flag_word(th2));
+		flush |= skb->ip_summed != p->ip_summed;
+		flush |= skb->csum_level != p->csum_level;
+		flush |= NAPI_GRO_CB(p)->count >= 64;
+
+		if (flush || skb_gro_receive_list(p, skb))
+			mss = 1;
+
+		goto out_check_final;
+	}
+
 	if (flush || skb_gro_receive(p, skb)) {
 		mss = 1;
 		goto out_check_final;
@@ -288,7 +382,6 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 	if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
 		pp = p;
 
-out:
 	NAPI_GRO_CB(skb)->flush |= (flush != 0);
 
 	return pp;
@@ -314,18 +407,58 @@ void tcp_gro_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 
+static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
+				    struct tcphdr *th)
+{
+	const struct iphdr *iph;
+	struct sk_buff *p;
+	struct sock *sk;
+	struct net *net;
+	int iif, sdif;
+
+	if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST)))
+		return;
+
+	p = tcp_gro_lookup(head, th);
+	if (p) {
+		NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist;
+		return;
+	}
+
+	inet_get_iif_sdif(skb, &iif, &sdif);
+	iph = skb_gro_network_header(skb);
+	net = dev_net(skb->dev);
+	sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
+				       iph->saddr, th->source,
+				       iph->daddr, ntohs(th->dest),
+				       iif, sdif);
+	NAPI_GRO_CB(skb)->is_flist = !sk;
+	if (sk)
+		sock_put(sk);
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
+	struct tcphdr *th;
+
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
 	    skb_gro_checksum_validate(skb, IPPROTO_TCP,
-				      inet_gro_compute_pseudo)) {
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-	}
+				      inet_gro_compute_pseudo))
+		goto flush;
+
+	th = tcp_gro_pull_header(skb);
+	if (!th)
+		goto flush;
 
-	return tcp_gro_receive(head, skb);
+	tcp4_check_fraglist_gro(head, skb, th);
+
+	return tcp_gro_receive(head, skb, th);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
@@ -333,6 +466,15 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
+	if (unlikely(NAPI_GRO_CB(skb)->is_flist)) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV4;
+		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+		__skb_incr_checksum_unnecessary(skb);
+
+		return 0;
+	}
+
 	th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr,
 				  iph->daddr, 0);
 

net/ipv4/udp_offload.c

@@ -433,33 +433,6 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	return segs;
 }
 
-static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
-{
-	if (unlikely(p->len + skb->len >= 65536))
-		return -E2BIG;
-
-	if (NAPI_GRO_CB(p)->last == p)
-		skb_shinfo(p)->frag_list = skb;
-	else
-		NAPI_GRO_CB(p)->last->next = skb;
-
-	skb_pull(skb, skb_gro_offset(skb));
-
-	NAPI_GRO_CB(p)->last = skb;
-	NAPI_GRO_CB(p)->count++;
-	p->data_len += skb->len;
-
-	/* sk ownership - if any - completely transferred to the aggregated packet */
-	skb->destructor = NULL;
-	skb->sk = NULL;
-	p->truesize += skb->truesize;
-	p->len += skb->len;
-
-	NAPI_GRO_CB(skb)->same_flow = 1;
-
-	return 0;
-}
-
 
 #define UDP_GRO_CNT_MAX 64
 static struct sk_buff *udp_gro_receive_segment(struct list_head *head,

net/ipv6/tcpv6_offload.c

@@ -7,24 +7,67 @@
  */
 #include <linux/indirect_call_wrapper.h>
 #include <linux/skbuff.h>
+#include <net/inet6_hashtables.h>
 #include <net/gro.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
+static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
+				    struct tcphdr *th)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	const struct ipv6hdr *hdr;
+	struct sk_buff *p;
+	struct sock *sk;
+	struct net *net;
+	int iif, sdif;
+
+	if (likely(!(skb->dev->features & NETIF_F_GRO_FRAGLIST)))
+		return;
+
+	p = tcp_gro_lookup(head, th);
+	if (p) {
+		NAPI_GRO_CB(skb)->is_flist = NAPI_GRO_CB(p)->is_flist;
+		return;
+	}
+
+	inet6_get_iif_sdif(skb, &iif, &sdif);
+	hdr = skb_gro_network_header(skb);
+	net = dev_net(skb->dev);
+	sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
+					&hdr->saddr, th->source,
+					&hdr->daddr, ntohs(th->dest),
+					iif, sdif);
+	NAPI_GRO_CB(skb)->is_flist = !sk;
+	if (sk)
+		sock_put(sk);
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
+	struct tcphdr *th;
+
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
 	    skb_gro_checksum_validate(skb, IPPROTO_TCP,
-				      ip6_gro_compute_pseudo)) {
-		NAPI_GRO_CB(skb)->flush = 1;
-		return NULL;
-	}
+				      ip6_gro_compute_pseudo))
+		goto flush;
 
-	return tcp_gro_receive(head, skb);
+	th = tcp_gro_pull_header(skb);
+	if (!th)
+		goto flush;
+
+	tcp6_check_fraglist_gro(head, skb, th);
+
+	return tcp_gro_receive(head, skb, th);
+
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
@@ -32,6 +75,15 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
+	if (unlikely(NAPI_GRO_CB(skb)->is_flist)) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV6;
+		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+		__skb_incr_checksum_unnecessary(skb);
+
+		return 0;
+	}
+
 	th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr,
 				  &iph->daddr, 0);
 	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
@@ -40,6 +92,61 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 	return 0;
 }
 
+static void __tcpv6_gso_segment_csum(struct sk_buff *seg,
+				     __be16 *oldport, __be16 newport)
+{
+	struct tcphdr *th;
+
+	if (*oldport == newport)
+		return;
+
+	th = tcp_hdr(seg);
+	inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
+	*oldport = newport;
+}
+
+static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs)
+{
+	const struct tcphdr *th;
+	const struct ipv6hdr *iph;
+	struct sk_buff *seg;
+	struct tcphdr *th2;
+	struct ipv6hdr *iph2;
+
+	seg = segs;
+	th = tcp_hdr(seg);
+	iph = ipv6_hdr(seg);
+	th2 = tcp_hdr(seg->next);
+	iph2 = ipv6_hdr(seg->next);
+
+	if (!(*(const u32 *)&th->source ^ *(const u32 *)&th2->source) &&
+	    ipv6_addr_equal(&iph->saddr, &iph2->saddr) &&
+	    ipv6_addr_equal(&iph->daddr, &iph2->daddr))
+		return segs;
+
+	while ((seg = seg->next)) {
+		th2 = tcp_hdr(seg);
+		iph2 = ipv6_hdr(seg);
+
+		iph2->saddr = iph->saddr;
+		iph2->daddr = iph->daddr;
+		__tcpv6_gso_segment_csum(seg, &th2->source, th->source);
+		__tcpv6_gso_segment_csum(seg, &th2->dest, th->dest);
+	}
+
+	return segs;
+}
+
+static struct sk_buff *__tcp6_gso_segment_list(struct sk_buff *skb,
+					      netdev_features_t features)
+{
+	skb = skb_segment_list(skb, features, skb_mac_header_len(skb));
+	if (IS_ERR(skb))
+		return skb;
+
+	return __tcpv6_gso_segment_list_csum(skb);
+}
+
 static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 					netdev_features_t features)
 {
@@ -51,6 +158,9 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(*th)))
 		return ERR_PTR(-EINVAL);
 
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)
+		return __tcp6_gso_segment_list(skb, features);
+
 	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
 		const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 		struct tcphdr *th = tcp_hdr(skb);