[PATCH v3 net-next v3 0/6] Add TCP fraglist GRO support

[PATCH v3 net-next v3 0/6] Add TCP fraglist GRO support

[Felix Fietkau]

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 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

Felix Fietkau (6):
  net: move skb_gro_receive_list from udp to core
  net: add support for segmenting TCP fraglist GSO packets
  net: add code for TCP fraglist GRO
  net: create tcp_gro_lookup helper function
  net: create tcp_gro_header_pull helper function
  net: add heuristic for enabling TCP fraglist GRO

 include/net/gro.h        |   1 +
 include/net/tcp.h        |   5 +-
 net/core/gro.c           |  27 +++++
 net/ipv4/tcp_offload.c   | 211 ++++++++++++++++++++++++++++++++-------
 net/ipv4/udp_offload.c   |  27 -----
 net/ipv6/tcpv6_offload.c |  63 +++++++++++-
 6 files changed, 265 insertions(+), 69 deletions(-)

-- 
2.44.0

[PATCH v3 net-next v3 1/6] net: move skb_gro_receive_list from udp to core

[Felix Fietkau]

This helper function will be used for TCP fraglist GRO support

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 include/net/gro.h      |  1 +
 net/core/gro.c         | 27 +++++++++++++++++++++++++++
 net/ipv4/udp_offload.c | 27 ---------------------------
 3 files changed, 28 insertions(+), 27 deletions(-)

diff --git a/include/net/gro.h b/include/net/gro.h
index 50f1e403dbbb..ca8e4b3de044 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -429,6 +429,7 @@ 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)
diff --git a/net/core/gro.c b/net/core/gro.c
index 2459ab697f7f..268c6c826d09 100644
--- a/net/core/gro.c
+++ b/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)
 {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 3498dd1d0694..a3cd546a1aea 100644
--- a/net/ipv4/udp_offload.c
+++ b/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,
-- 
2.44.0

Re: [PATCH v3 net-next v3 1/6] net: move skb_gro_receive_list from udp to core

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>
> This helper function will be used for TCP fraglist GRO support
>
> Signed-off-by: Felix Fietkau <nbd@nbd.name>

Reviewed-by: Eric Dumazet <edumazet@google.com>

[PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Felix Fietkau]

Preparation for adding TCP fraglist GRO support. It expects packets to be
combined in a similar way as UDP fraglist GSO packets.
For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
 net/ipv6/tcpv6_offload.c |  3 ++
 2 files changed, 68 insertions(+)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index fab0973f995b..c493e95e09a5 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -28,6 +28,68 @@ 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)
+{
+	struct sk_buff *seg;
+	struct tcphdr *th, *th2;
+	struct iphdr *iph, *iph2;
+
+	seg = segs;
+	th = tcp_hdr(seg);
+	iph = ip_hdr(seg);
+	th2 = tcp_hdr(seg->next);
+	iph2 = ip_hdr(seg->next);
+
+	if (!(*(u32 *)&th->source ^ *(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 +99,9 @@ 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);
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 4b07d1e6c952..b3b8e1f6b92a 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -51,6 +51,9 @@ 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 skb_segment_list(skb, features, skb_mac_header_len(skb));
+
 	if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
 		const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 		struct tcphdr *th = tcp_hdr(skb);
-- 
2.44.0

Re: [PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>
> Preparation for adding TCP fraglist GRO support. It expects packets to be
> combined in a similar way as UDP fraglist GSO packets.
> For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.
>
> Signed-off-by: Felix Fietkau <nbd@nbd.name>
> ---
>  net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
>  net/ipv6/tcpv6_offload.c |  3 ++
>  2 files changed, 68 insertions(+)
>
> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> index fab0973f995b..c493e95e09a5 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -28,6 +28,68 @@ 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)


Do we really need pointers for newip and 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)
> +{
> +       struct sk_buff *seg;
> +       struct tcphdr *th, *th2;
> +       struct iphdr *iph, *iph2;

I would probably add a const qualifier to th and iph

> +
> +       seg = segs;
> +       th = tcp_hdr(seg);
> +       iph = ip_hdr(seg);
> +       th2 = tcp_hdr(seg->next);
> +       iph2 = ip_hdr(seg->next);
> +
> +       if (!(*(u32 *)&th->source ^ *(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;
> +}
>

Re: [PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Felix Fietkau]

On 26.04.24 09:44, Eric Dumazet wrote:
> On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>>
>> Preparation for adding TCP fraglist GRO support. It expects packets to be
>> combined in a similar way as UDP fraglist GSO packets.
>> For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.
>>
>> Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>  net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
>>  net/ipv6/tcpv6_offload.c |  3 ++
>>  2 files changed, 68 insertions(+)
>>
>> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> index fab0973f995b..c493e95e09a5 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -28,6 +28,68 @@ 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)
> 
> 
> Do we really need pointers for newip and 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)
>> +{
>> +       struct sk_buff *seg;
>> +       struct tcphdr *th, *th2;
>> +       struct iphdr *iph, *iph2;
> 
> I would probably add a const qualifier to th and iph

Will do, thanks.

- Felix

Re: [PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Paolo Abeni]

On Fri, 2024-04-26 at 08:51 +0200, Felix Fietkau wrote:
> Preparation for adding TCP fraglist GRO support. It expects packets to be
> combined in a similar way as UDP fraglist GSO packets.
> For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.
> 
> Signed-off-by: Felix Fietkau <nbd@nbd.name>
> ---
>  net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
>  net/ipv6/tcpv6_offload.c |  3 ++
>  2 files changed, 68 insertions(+)
> 
> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> index fab0973f995b..c493e95e09a5 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -28,6 +28,68 @@ 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)
> +{
> +	struct sk_buff *seg;
> +	struct tcphdr *th, *th2;
> +	struct iphdr *iph, *iph2;
> +
> +	seg = segs;
> +	th = tcp_hdr(seg);
> +	iph = ip_hdr(seg);
> +	th2 = tcp_hdr(seg->next);
> +	iph2 = ip_hdr(seg->next);
> +
> +	if (!(*(u32 *)&th->source ^ *(u32 *)&th2->source) &&
> +	    iph->daddr == iph2->daddr && iph->saddr == iph2->saddr)
> +		return segs;

As mentioned in previous revisions, I think a problem with this
approach is that the stack could make other changes to the TCP header
after the GRO stage, that are unnoticed here and could cause csum
corruption, if the egress device does not recompute the packet csum.

Cheers,

Paolo

Re: [PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Felix Fietkau]

On 26.04.24 10:28, Paolo Abeni wrote:
> On Fri, 2024-04-26 at 08:51 +0200, Felix Fietkau wrote:
>> Preparation for adding TCP fraglist GRO support. It expects packets to be
>> combined in a similar way as UDP fraglist GSO packets.
>> For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.
>> 
>> Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>  net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
>>  net/ipv6/tcpv6_offload.c |  3 ++
>>  2 files changed, 68 insertions(+)
>> 
>> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> index fab0973f995b..c493e95e09a5 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -28,6 +28,68 @@ 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)
>> +{
>> +	struct sk_buff *seg;
>> +	struct tcphdr *th, *th2;
>> +	struct iphdr *iph, *iph2;
>> +
>> +	seg = segs;
>> +	th = tcp_hdr(seg);
>> +	iph = ip_hdr(seg);
>> +	th2 = tcp_hdr(seg->next);
>> +	iph2 = ip_hdr(seg->next);
>> +
>> +	if (!(*(u32 *)&th->source ^ *(u32 *)&th2->source) &&
>> +	    iph->daddr == iph2->daddr && iph->saddr == iph2->saddr)
>> +		return segs;
> 
> As mentioned in previous revisions, I think a problem with this
> approach is that the stack could make other changes to the TCP header
> after the GRO stage, that are unnoticed here and could cause csum
> corruption, if the egress device does not recompute the packet csum.

On segmentation, each packet keeps its original TCP header and csum. If 
the stack makes changes, they apply to the first packet only. I don't 
see how we could get csum corruption.

- Felix

Re: [PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Paolo Abeni]

On Fri, 2024-04-26 at 11:39 +0200, Felix Fietkau wrote:
> On 26.04.24 10:28, Paolo Abeni wrote:
> > On Fri, 2024-04-26 at 08:51 +0200, Felix Fietkau wrote:
> > > Preparation for adding TCP fraglist GRO support. It expects packets to be
> > > combined in a similar way as UDP fraglist GSO packets.
> > > For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.
> > > 
> > > Signed-off-by: Felix Fietkau <nbd@nbd.name>
> > > ---
> > >  net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
> > >  net/ipv6/tcpv6_offload.c |  3 ++
> > >  2 files changed, 68 insertions(+)
> > > 
> > > diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> > > index fab0973f995b..c493e95e09a5 100644
> > > --- a/net/ipv4/tcp_offload.c
> > > +++ b/net/ipv4/tcp_offload.c
> > > @@ -28,6 +28,68 @@ 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)
> > > +{
> > > +	struct sk_buff *seg;
> > > +	struct tcphdr *th, *th2;
> > > +	struct iphdr *iph, *iph2;
> > > +
> > > +	seg = segs;
> > > +	th = tcp_hdr(seg);
> > > +	iph = ip_hdr(seg);
> > > +	th2 = tcp_hdr(seg->next);
> > > +	iph2 = ip_hdr(seg->next);
> > > +
> > > +	if (!(*(u32 *)&th->source ^ *(u32 *)&th2->source) &&
> > > +	    iph->daddr == iph2->daddr && iph->saddr == iph2->saddr)
> > > +		return segs;
> > 
> > As mentioned in previous revisions, I think a problem with this
> > approach is that the stack could make other changes to the TCP header
> > after the GRO stage, that are unnoticed here and could cause csum
> > corruption, if the egress device does not recompute the packet csum.
> 
> On segmentation, each packet keeps its original TCP header and csum. If 
> the stack makes changes, they apply to the first packet only. I don't 
> see how we could get csum corruption.

You are right. I did not take in account that such changes (to the
first skb) are not reflected to the frag_list at segmentation time. The
end result could be different from what the user/admin is expecting,
but at least should not impact drops.

Side note: alike UDP, this is not supporting IPv6 NAT...

Thanks,

Paolo

Re: [PATCH v3 net-next v3 2/6] net: add support for segmenting TCP fraglist GSO packets

[Felix Fietkau]

On 26.04.24 12:40, Paolo Abeni wrote:
> On Fri, 2024-04-26 at 11:39 +0200, Felix Fietkau wrote:
>> On 26.04.24 10:28, Paolo Abeni wrote:
>> > On Fri, 2024-04-26 at 08:51 +0200, Felix Fietkau wrote:
>> > > Preparation for adding TCP fraglist GRO support. It expects packets to be
>> > > combined in a similar way as UDP fraglist GSO packets.
>> > > For IPv4 packets, NAT is handled in the same way as UDP fraglist GSO.
>> > > 
>> > > Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> > > ---
>> > >  net/ipv4/tcp_offload.c   | 65 ++++++++++++++++++++++++++++++++++++++++
>> > >  net/ipv6/tcpv6_offload.c |  3 ++
>> > >  2 files changed, 68 insertions(+)
>> > > 
>> > > diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> > > index fab0973f995b..c493e95e09a5 100644
>> > > --- a/net/ipv4/tcp_offload.c
>> > > +++ b/net/ipv4/tcp_offload.c
>> > > @@ -28,6 +28,68 @@ 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)
>> > > +{
>> > > +	struct sk_buff *seg;
>> > > +	struct tcphdr *th, *th2;
>> > > +	struct iphdr *iph, *iph2;
>> > > +
>> > > +	seg = segs;
>> > > +	th = tcp_hdr(seg);
>> > > +	iph = ip_hdr(seg);
>> > > +	th2 = tcp_hdr(seg->next);
>> > > +	iph2 = ip_hdr(seg->next);
>> > > +
>> > > +	if (!(*(u32 *)&th->source ^ *(u32 *)&th2->source) &&
>> > > +	    iph->daddr == iph2->daddr && iph->saddr == iph2->saddr)
>> > > +		return segs;
>> > 
>> > As mentioned in previous revisions, I think a problem with this
>> > approach is that the stack could make other changes to the TCP header
>> > after the GRO stage, that are unnoticed here and could cause csum
>> > corruption, if the egress device does not recompute the packet csum.
>> 
>> On segmentation, each packet keeps its original TCP header and csum. If 
>> the stack makes changes, they apply to the first packet only. I don't 
>> see how we could get csum corruption.
> 
> You are right. I did not take in account that such changes (to the
> first skb) are not reflected to the frag_list at segmentation time. The
> end result could be different from what the user/admin is expecting,
> but at least should not impact drops.
> 
> Side note: alike UDP, this is not supporting IPv6 NAT...

I will add that for both in the next version.

Thanks,

- Felix

[PATCH v3 net-next v3 3/6] net: add code for TCP fraglist GRO

[Felix Fietkau]

This implements fraglist GRO similar to how it's handled in UDP, however
no functional changes are added yet. The next change adds a heuristic for
using fraglist GRO instead of regular GRO.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 net/ipv4/tcp_offload.c   | 22 ++++++++++++++++++++++
 net/ipv6/tcpv6_offload.c |  9 +++++++++
 2 files changed, 31 insertions(+)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index c493e95e09a5..ffd6b7a4163a 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -332,6 +332,19 @@ 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 (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 |= !pskb_may_pull(skb, skb_gro_offset(skb));
+		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;
@@ -398,6 +411,15 @@ 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 (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);
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index b3b8e1f6b92a..c97d55cf036f 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -32,6 +32,15 @@ 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 (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;
-- 
2.44.0

Re: [PATCH v3 net-next v3 3/6] net: add code for TCP fraglist GRO

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>
> This implements fraglist GRO similar to how it's handled in UDP, however
> no functional changes are added yet. The next change adds a heuristic for
> using fraglist GRO instead of regular GRO.
>
> Signed-off-by: Felix Fietkau <nbd@nbd.name>
> ---
>  net/ipv4/tcp_offload.c   | 22 ++++++++++++++++++++++
>  net/ipv6/tcpv6_offload.c |  9 +++++++++
>  2 files changed, 31 insertions(+)
>
> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> index c493e95e09a5..ffd6b7a4163a 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -332,6 +332,19 @@ 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 (NAPI_GRO_CB(p)->is_flist) {


Please add unlikely() for all NAPI_GRO_CB(p)->is_flist checks added in
this patch.

> +               flush |= (__force int)(flags ^ tcp_flag_word(th2));
> +               flush |= skb->ip_summed != p->ip_summed;
> +               flush |= skb->csum_level != p->csum_level;
> +               flush |= !pskb_may_pull(skb, skb_gro_offset(skb));
> +               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;
> @@ -398,6 +411,15 @@ 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 (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);
>
> diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
> index b3b8e1f6b92a..c97d55cf036f 100644
> --- a/net/ipv6/tcpv6_offload.c
> +++ b/net/ipv6/tcpv6_offload.c
> @@ -32,6 +32,15 @@ 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 (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;
> --
> 2.44.0
>

Re: [PATCH v3 net-next v3 3/6] net: add code for TCP fraglist GRO

[Felix Fietkau]

On 26.04.24 09:47, Eric Dumazet wrote:
> On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>>
>> This implements fraglist GRO similar to how it's handled in UDP, however
>> no functional changes are added yet. The next change adds a heuristic for
>> using fraglist GRO instead of regular GRO.
>>
>> Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>  net/ipv4/tcp_offload.c   | 22 ++++++++++++++++++++++
>>  net/ipv6/tcpv6_offload.c |  9 +++++++++
>>  2 files changed, 31 insertions(+)
>>
>> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> index c493e95e09a5..ffd6b7a4163a 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -332,6 +332,19 @@ 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 (NAPI_GRO_CB(p)->is_flist) {
> 
> 
> Please add unlikely() for all NAPI_GRO_CB(p)->is_flist checks added in
> this patch.

Will do, thanks.

- Felix

Re: [PATCH v3 net-next v3 3/6] net: add code for TCP fraglist GRO

[Paolo Abeni]

On Fri, 2024-04-26 at 08:51 +0200, Felix Fietkau wrote:
> This implements fraglist GRO similar to how it's handled in UDP, however
> no functional changes are added yet. The next change adds a heuristic for
> using fraglist GRO instead of regular GRO.
> 
> Signed-off-by: Felix Fietkau <nbd@nbd.name>
> ---
>  net/ipv4/tcp_offload.c   | 22 ++++++++++++++++++++++
>  net/ipv6/tcpv6_offload.c |  9 +++++++++
>  2 files changed, 31 insertions(+)
> 
> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> index c493e95e09a5..ffd6b7a4163a 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -332,6 +332,19 @@ 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 (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 |= !pskb_may_pull(skb, skb_gro_offset(skb));

I'm sorry, I'm lagging behind. I think the TCP flags handling here is
correct - preserving the original ones should work.

The question a made WRT 2 above checks being non necessary/redundant:

		flush |= (__force int)(flags ^ tcp_flag_word(th2));
		flush |= !pskb_may_pull(skb, skb_gro_offset(skb));

still stands, I think.

Thanks,

Paolo

Re: [PATCH v3 net-next v3 3/6] net: add code for TCP fraglist GRO

[Felix Fietkau]

On 26.04.24 10:21, Paolo Abeni wrote:
> On Fri, 2024-04-26 at 08:51 +0200, Felix Fietkau wrote:
>> This implements fraglist GRO similar to how it's handled in UDP, however
>> no functional changes are added yet. The next change adds a heuristic for
>> using fraglist GRO instead of regular GRO.
>> 
>> Signed-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>  net/ipv4/tcp_offload.c   | 22 ++++++++++++++++++++++
>>  net/ipv6/tcpv6_offload.c |  9 +++++++++
>>  2 files changed, 31 insertions(+)
>> 
>> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> index c493e95e09a5..ffd6b7a4163a 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -332,6 +332,19 @@ 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 (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 |= !pskb_may_pull(skb, skb_gro_offset(skb));
> 
> I'm sorry, I'm lagging behind. I think the TCP flags handling here is
> correct - preserving the original ones should work.
> 
> The question a made WRT 2 above checks being non necessary/redundant:
> 
> 		flush |= (__force int)(flags ^ tcp_flag_word(th2));

This one is not redundant, because the earlier flags check includes this 
part: & ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH))

> 		flush |= !pskb_may_pull(skb, skb_gro_offset(skb));

This one looks like a redundant leftover, I will remove it in the next 
version.

Thanks,

- Felix

[PATCH v3 net-next v3 4/6] net: create tcp_gro_lookup helper function

[Felix Fietkau]

This pulls the flow port matching out of tcp_gro_receive, so that it can be
reused for the next change, which adds the TCP fraglist GRO heuristic.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 include/net/tcp.h      |  1 +
 net/ipv4/tcp_offload.c | 41 +++++++++++++++++++++++++----------------
 2 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index ffc9371fe9de..a3f09aa44487 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2198,6 +2198,7 @@ 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_lookup(struct list_head *head, struct tcphdr *th);
 struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
 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));
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index ffd6b7a4163a..3ee5a1b21976 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -243,6 +243,27 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	return segs;
 }
 
+struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th)
+{
+	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 sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct sk_buff *pp = NULL;
@@ -280,24 +301,12 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 	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;
-
-		th2 = tcp_hdr(p);
-
-		if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
-			NAPI_GRO_CB(p)->same_flow = 0;
-			continue;
-		}
-
-		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)) &
-- 
2.44.0

Re: [PATCH v3 net-next v3 4/6] net: create tcp_gro_lookup helper function

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>
> This pulls the flow port matching out of tcp_gro_receive, so that it can be
> reused for the next change, which adds the TCP fraglist GRO heuristic.
>
> Signed-off-by: Felix Fietkau <nbd@nbd.name>

Reviewed-by: Eric Dumazet <edumazet@google.com>

[PATCH v3 net-next v3 5/6] net: create tcp_gro_header_pull helper function

[Felix Fietkau]

Pull the code out of tcp_gro_receive in order to access the tcp header
from tcp4/6_gro_receive.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 include/net/tcp.h        |  4 ++-
 net/ipv4/tcp_offload.c   | 55 +++++++++++++++++++++++++---------------
 net/ipv6/tcpv6_offload.c | 18 +++++++++----
 3 files changed, 50 insertions(+), 27 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a3f09aa44487..52371be181a2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2198,8 +2198,10 @@ void tcp_v4_destroy_sock(struct sock *sk);
 
 struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features);
+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 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));
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 3ee5a1b21976..ee5403760775 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -264,40 +264,46 @@ struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th)
 	return NULL;
 }
 
-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 *pp = NULL;
-	struct sk_buff *p;
+	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);
 
+	return th;
+}
+
+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;
+
 	len = skb_gro_len(skb);
 	flags = tcp_flag_word(th);
 
@@ -375,7 +381,6 @@ 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;
@@ -404,15 +409,23 @@ EXPORT_SYMBOL(tcp_gro_complete);
 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);
+	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)
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index c97d55cf036f..c01ace2e9ff0 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -16,15 +16,23 @@
 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;
+
+	th = tcp_gro_pull_header(skb);
+	if (!th)
+		goto flush;
+
+	return tcp_gro_receive(head, skb, th);
 
-	return tcp_gro_receive(head, skb);
+flush:
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
 }
 
 INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
-- 
2.44.0

Re: [PATCH v3 net-next v3 5/6] net: create tcp_gro_header_pull helper function

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>
> Pull the code out of tcp_gro_receive in order to access the tcp header
> from tcp4/6_gro_receive.
>
> Signed-off-by: Felix Fietkau <nbd@nbd.name>

Reviewed-by: Eric Dumazet <edumazet@google.com>

[PATCH v3 net-next v3 6/6] net: add heuristic for enabling TCP fraglist GRO

[Felix Fietkau]

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

Signe-off-by: Felix Fietkau <nbd@nbd.name>
---
 net/ipv4/tcp_offload.c   | 30 ++++++++++++++++++++++++++++++
 net/ipv6/tcpv6_offload.c | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index ee5403760775..2ae83f4394dc 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -406,6 +406,34 @@ 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 = skb_gro_network_header(skb);
+	struct net *net = dev_net(skb->dev);
+	struct sk_buff *p;
+	struct sock *sk;
+	int iif, sdif;
+
+	if (!(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);
+	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)
 {
@@ -421,6 +449,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 	if (!th)
 		goto flush;
 
+	tcp4_check_fraglist_gro(head, skb, th);
+
 	return tcp_gro_receive(head, skb, th);
 
 flush:
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index c01ace2e9ff0..1ab45cca3936 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -7,12 +7,43 @@
  */
 #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 = skb_gro_network_header(skb);
+	struct net *net = dev_net(skb->dev);
+	struct sk_buff *p;
+	struct sock *sk;
+	int iif, sdif;
+
+	if (!(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);
+	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)
 {
@@ -28,6 +59,8 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 	if (!th)
 		goto flush;
 
+	tcp6_check_fraglist_gro(head, skb, th);
+
 	return tcp_gro_receive(head, skb, th);
 
 flush:
-- 
2.44.0

Re: [PATCH v3 net-next v3 6/6] net: add heuristic for enabling TCP fraglist GRO

[Eric Dumazet]

On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>
> 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
>
> Signe-off-by: Felix Fietkau <nbd@nbd.name>
> ---
>  net/ipv4/tcp_offload.c   | 30 ++++++++++++++++++++++++++++++
>  net/ipv6/tcpv6_offload.c | 33 +++++++++++++++++++++++++++++++++
>  2 files changed, 63 insertions(+)
>
> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
> index ee5403760775..2ae83f4394dc 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -406,6 +406,34 @@ 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 = skb_gro_network_header(skb);
> +       struct net *net = dev_net(skb->dev);

Could you defer the initializations of iph and net after the
NETIF_F_GRO_FRAGLIST check ?

dev_net() has an implicit READ_ONCE() ...

> +       struct sk_buff *p;
> +       struct sock *sk;
> +       int iif, sdif;
> +
> +       if (!(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);
> +       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)
>  {
> @@ -421,6 +449,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
>         if (!th)
>                 goto flush;
>
> +       tcp4_check_fraglist_gro(head, skb, th);
> +
>         return tcp_gro_receive(head, skb, th);
>
>  flush:
> diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
> index c01ace2e9ff0..1ab45cca3936 100644
> --- a/net/ipv6/tcpv6_offload.c
> +++ b/net/ipv6/tcpv6_offload.c
> @@ -7,12 +7,43 @@
>   */
>  #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 = skb_gro_network_header(skb);
> +       struct net *net = dev_net(skb->dev);

Same remark here.

> +       struct sk_buff *p;
> +       struct sock *sk;
> +       int iif, sdif;
> +
> +       if (!(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);
> +       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)
>  {
> @@ -28,6 +59,8 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
>         if (!th)
>                 goto flush;
>
> +       tcp6_check_fraglist_gro(head, skb, th);
> +
>         return tcp_gro_receive(head, skb, th);
>
>  flush:
> --
> 2.44.0
>

Re: [PATCH v3 net-next v3 6/6] net: add heuristic for enabling TCP fraglist GRO

[Felix Fietkau]

On 26.04.24 09:32, Eric Dumazet wrote:
> On Fri, Apr 26, 2024 at 8:51 AM Felix Fietkau <nbd@nbd.name> wrote:
>>
>> 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
>>
>> Signe-off-by: Felix Fietkau <nbd@nbd.name>
>> ---
>>  net/ipv4/tcp_offload.c   | 30 ++++++++++++++++++++++++++++++
>>  net/ipv6/tcpv6_offload.c | 33 +++++++++++++++++++++++++++++++++
>>  2 files changed, 63 insertions(+)
>>
>> diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
>> index ee5403760775..2ae83f4394dc 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -406,6 +406,34 @@ 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 = skb_gro_network_header(skb);
>> +       struct net *net = dev_net(skb->dev);
> 
> Could you defer the initializations of iph and net after the
> NETIF_F_GRO_FRAGLIST check ?
> 
> dev_net() has an implicit READ_ONCE() ...

Will do, thanks.

- Felix