diff mbox series

[v2,net-next,v2,3/5] net: add code for TCP fraglist GRO

Message ID 20240425150432.44142-4-nbd@nbd.name (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series Add TCP fraglist GRO support | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 932 this patch: 932
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 5 of 5 maintainers
netdev/build_clang success Errors and warnings before: 938 this patch: 938
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
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: 943 this patch: 943
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 49 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-04-26--00-00 (tests: 991)

Commit Message

Felix Fietkau April 25, 2024, 3:04 p.m. UTC 
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(+)

Comments

Willem de Bruijn April 25, 2024, 3:18 p.m. UTC | #1 
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 e455f884190c..68157130c264 100644
> --- a/net/ipv4/tcp_offload.c
> +++ b/net/ipv4/tcp_offload.c
> @@ -336,6 +336,19 @@ 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));

What is the purpose of this check, given the existing check above

        flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
                  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));

> +		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;
> @@ -402,6 +415,15 @@ 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
>
Felix Fietkau April 25, 2024, 3:26 p.m. UTC | #2 
On 25.04.24 17:18, Willem de Bruijn wrote:
> 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 e455f884190c..68157130c264 100644
>> --- a/net/ipv4/tcp_offload.c
>> +++ b/net/ipv4/tcp_offload.c
>> @@ -336,6 +336,19 @@ 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));
> 
> What is the purpose of this check, given the existing check above
> 
>          flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
>                    ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));

The fraglist codepath is not updating the TCP flags of the first packet, 
so the extra check ensures it doesn't have to.

- Felix
diff mbox series

Patch

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index e455f884190c..68157130c264 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -336,6 +336,19 @@  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;
@@ -402,6 +415,15 @@  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;