NET: Add ECN support for TSO
Subsystems (4)
PATCH 1/1 NET: Add ECN support for TSO
In the current TSO implementation, NETIF_F_TSO and ECN cannot be turned on together in a TCP connection. The problem is that most hardware that supports TSO does not handle CWR correctly if it is set in the TSO packet. Correct handling requires CWR to be set in the first packet only if it is set in the TSO header.
This patch adds the ability to turn on NETIF_F_TSO and ECN using GSO if necessary to handle TSO packets with CWR set. Hardware that handles CWR correctly can turn on NETIF_F_TSO_ECN in the dev-> features flag.
All TSO packets with CWR set will have the SKB_GSO_TCPV4_ECN set. If the output device does not have the NETIF_F_TSO_ECN feature set, GSO will split the packet up correctly with CWR only set in the first segment.
It is further assumed that all hardware will handle ECE properly by replicating the ECE flag in all segments. If that is not the case, a simple extension of the logic will be required.
include/linux/netdevice.h +6 -0
@@ -316,6 +316,7 @@ struct net_device#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)#define NETIF_F_UFO (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)#define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT) +#define NETIF_F_TSO_ECN (SKB_GSO_TCPV4_ECN << NETIF_F_GSO_SHIFT)#define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)#define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
@@ -1002,6 +1003,11 @@ static inline int netif_needs_gso(structreturn !skb_gso_ok (skb, dev->features); } +static inline int tso_ecn_capable (unsigned long features) +{ +return ((features &NETIF_F_GSO ) || (features &NETIF_F_TSO_ECN )); +} +#endif /* __KERNEL__ */ #endif /* _LINUX_DEV_H */
include/linux/skbuff.h +3 -0
@@ -175,6 +175,9 @@ enum {/* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY =1 <<2 , + +/* This indicates the tcp segment has CWR set. */ + SKB_GSO_TCPV4_ECN = 1 << 3, };/**
include/net/sock.h +2 -1
@@ -1033,7 +1033,8 @@ static inline void sk_setup_caps(structif (sk->sk_route_caps &NETIF_F_GSO ) sk->sk_route_caps |=NETIF_F_TSO ;if (sk->sk_route_caps &NETIF_F_TSO ) { -if (sock_flag (sk,SOCK_NO_LARGESEND ) || dst->header_len) +if ((sock_flag (sk,SOCK_NO_LARGESEND ) && + !tso_ecn_capable (sk->sk_route_caps)) || dst->header_len) sk->sk_route_caps &= ~NETIF_F_TSO ;else sk->sk_route_caps |=NETIF_F_SG |NETIF_F_HW_CSUM ;
include/net/tcp_ecn.h +5 -1
@@ -31,7 +31,8 @@ static inline void TCP_ECN_send_syn(stru struct sk_buff *skb) { tp->ecn_flags =0 ; -if (sysctl_tcp_ecn && !(sk->sk_route_caps &NETIF_F_TSO )) { +if (sysctl_tcp_ecn && (!(sk->sk_route_caps &NETIF_F_TSO ) || +tso_ecn_capable (sk->sk_route_caps))) {TCP_SKB_CB (skb)->flags |=TCPCB_FLAG_ECE |TCPCB_FLAG_CWR ; tp->ecn_flags =TCP_ECN_OK ;sock_set_flag (sk,SOCK_NO_LARGESEND );
@@ -56,6 +57,9 @@ static inline void TCP_ECN_send(struct sif (tp->ecn_flags&TCP_ECN_QUEUE_CWR ) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR ; skb->h.th->cwr =1 ; +if (skb_shinfo (skb)->gso_type &SKB_GSO_TCPV4 ) +skb_shinfo (skb)->gso_type |= +SKB_GSO_TCPV4_ECN ; } }else {/* ACK or retransmitted segment: clear ECT|CE */
net/ipv4/tcp_output.c +2 -1
@@ -2044,7 +2044,8 @@ struct sk_buff * tcp_make_synack(structmemset (th,0 ,sizeof (struct tcphdr )); th->syn =1 ; th->ack =1 ; -if (dst->dev->features&NETIF_F_TSO ) +if ((dst->dev->features &NETIF_F_TSO ) && + !tso_ecn_capable (dst->dev->features)) ireq->ecn_ok =0 ;TCP_ECN_make_synack (req, th); th->source =inet_sk (sk)->sport;
include/net/sock.h static inline void sk_setup_caps(struct · line 1038
Quoted 13 lines · Michael Chan
include/net/sock.h +2
-1@@ -1033,7 +1033,8 @@ static inline void sk_setup_caps(structif (sk->sk_route_caps &NETIF_F_GSO ) sk->sk_route_caps |=NETIF_F_TSO ;if (sk->sk_route_caps &NETIF_F_TSO ) { -if (sock_flag (sk,SOCK_NO_LARGESEND ) || dst->header_len) +if ((sock_flag (sk,SOCK_NO_LARGESEND ) && + !tso_ecn_capable (sk->sk_route_caps)) || dst->header_len) sk->sk_route_caps &= ~NETIF_F_TSO ;
Why turn it off? With GSO in place the stack will handle it just fine (even your description says so :) We should instead remove all code that turns off TSO/ECN when the other is present.
Otherwise the patch looks good.
Thanks,
Signature · 4 lines
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txtQuoted 19 lines · Herbert Xu
include/net/sock.h static inline void sk_setup_caps(struct · line 1038
Quoted 13 lines · Michael Chan
include/net/sock.h +2
-1@@ -1033,7 +1033,8 @@ static inline void sk_setup_caps(structif (sk->sk_route_caps &NETIF_F_GSO ) sk->sk_route_caps |=NETIF_F_TSO ;if (sk->sk_route_caps &NETIF_F_TSO ) { -if (sock_flag (sk,SOCK_NO_LARGESEND ) || dst->header_len) +if ((sock_flag (sk,SOCK_NO_LARGESEND ) && + !tso_ecn_capable (sk->sk_route_caps)) || dst->header_len) sk->sk_route_caps &= ~NETIF_F_TSO ;Why turn it off? With GSO in place the stack will handle it just fine (even your description says so :) We should instead remove all code that turns off TSO/ECN when the other is present.
We need to turn off NETIF_F_TSO for a connection that has negotiated to turn on ECN if the output device cannot handle TSO and ECN. In other words, if the output device does not have either GSO or TSO_ECN feature set.
Quoted 5 lines · Michael Chan
We need to turn off
NETIF_F_TSOfor a connection that has negotiated to turn on ECN if the output device cannot handle TSO and ECN. In other words, if the output device does not have either GSO orTSO_ECNfeature set.
I think you're mixing up GSO the mechanism with GSO the flag. The GSO flag simply tells the TCP stack whether TSO should be used or not, even if the hardware does not support TSO at all. The GSO mechanism on the other hand is ALWAYS present. So regardless of the presence of the GSO flag, you can always rely on the GSO mechanism to pick up the pieces (or rather generate the pieces as the case may be :)
Cheers,
Signature · 4 lines
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txtQuoted 7 lines · Herbert Xu
I think you're mixing up GSO the mechanism with GSO the flag. The GSO flag simply tells the TCP stack whether TSO should be used or not, even if the hardware does not support TSO at all. The GSO mechanism on the other hand is ALWAYS present. So regardless of the presence of the GSO flag, you can always rely on the GSO mechanism to pick up the pieces (or rather generate the pieces as the case may be :)
Thanks, that was my confusion. Here's the revised patch:
[NET]: Add ECN support for TSO
In the current TSO implementation, NETIF_F_TSO and ECN cannot be turned on together in a TCP connection. The problem is that most hardware that supports TSO does not handle CWR correctly if it is set in the TSO packet. Correct handling requires CWR to be set in the first packet only if it is set in the TSO header.
This patch adds the ability to turn on NETIF_F_TSO and ECN using GSO if necessary to handle TSO packets with CWR set. Hardware that handles CWR correctly can turn on NETIF_F_TSO_ECN in the dev-> features flag.
All TSO packets with CWR set will have the SKB_GSO_TCPV4_ECN set. If the output device does not have the NETIF_F_TSO_ECN feature set, GSO will split the packet up correctly with CWR only set in the first segment.
With help from Herbert Xu <[email protected]>.
Since ECN can always be enabled with TSO, the SOCK_NO_LARGESEND sock flag is completely removed.
include/linux/netdevice.h +1 -0
@@ -316,6 +316,7 @@ struct net_device#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)#define NETIF_F_UFO (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT)#define NETIF_F_GSO_ROBUST (SKB_GSO_DODGY << NETIF_F_GSO_SHIFT) +#define NETIF_F_TSO_ECN (SKB_GSO_TCPV4_ECN << NETIF_F_GSO_SHIFT)#define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)#define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM)
include/linux/skbuff.h +3 -0
@@ -175,6 +175,9 @@ enum {/* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY =1 <<2 , + +/* This indicates the tcp segment has CWR set. */ + SKB_GSO_TCPV4_ECN = 1 << 3, };/**
include/net/sock.h +1 -2
@@ -383,7 +383,6 @@ enum sock_flags {SOCK_USE_WRITE_QUEUE ,/* whether to call sk->sk_write_space in sock_wfree */ SOCK_DBG ,/* %SO_DEBUG setting */ SOCK_RCVTSTAMP ,/* %SO_TIMESTAMP setting */ -SOCK_NO_LARGESEND ,/* whether to sent large segments or not */ SOCK_LOCALROUTE ,/* route locally only, %SO_DONTROUTE setting */ SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */ };
@@ -1033,7 +1032,7 @@ static inline void sk_setup_caps(structif (sk->sk_route_caps &NETIF_F_GSO ) sk->sk_route_caps |=NETIF_F_TSO ;if (sk->sk_route_caps &NETIF_F_TSO ) { -if (sock_flag (sk,SOCK_NO_LARGESEND ) || dst->header_len) +if (dst->header_len) sk->sk_route_caps &= ~NETIF_F_TSO ;else sk->sk_route_caps |=NETIF_F_SG |NETIF_F_HW_CSUM ;
include/net/tcp_ecn.h +4 -2
@@ -31,10 +31,9 @@ static inline void TCP_ECN_send_syn(stru struct sk_buff *skb) { tp->ecn_flags =0 ; -if (sysctl_tcp_ecn && !(sk->sk_route_caps &NETIF_F_TSO )) { +if (sysctl_tcp_ecn) {TCP_SKB_CB (skb)->flags |=TCPCB_FLAG_ECE |TCPCB_FLAG_CWR ; tp->ecn_flags =TCP_ECN_OK ; -sock_set_flag (sk,SOCK_NO_LARGESEND ); } }
@@ -56,6 +55,9 @@ static inline void TCP_ECN_send(struct sif (tp->ecn_flags&TCP_ECN_QUEUE_CWR ) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR ; skb->h.th->cwr =1 ; +if (skb_shinfo (skb)->gso_type &SKB_GSO_TCPV4 ) +skb_shinfo (skb)->gso_type |= +SKB_GSO_TCPV4_ECN ; } }else {/* ACK or retransmitted segment: clear ECT|CE */
net/ipv4/tcp_input.c +0 -4
@@ -4178,8 +4178,6 @@ static int tcp_rcv_synsent_state_process*/ TCP_ECN_rcv_synack (tp, th); -if (tp->ecn_flags&TCP_ECN_OK ) -sock_set_flag (sk,SOCK_NO_LARGESEND ); tp->snd_wl1 =TCP_SKB_CB (skb)->seq;tcp_ack (sk, skb,FLAG_SLOWPATH );
@@ -4322,8 +4320,6 @@ discard: tp->max_window = tp->snd_wnd;TCP_ECN_rcv_syn (tp, th); -if (tp->ecn_flags&TCP_ECN_OK ) -sock_set_flag (sk,SOCK_NO_LARGESEND );tcp_mtup_init (sk);tcp_sync_mss (sk, icsk->icsk_pmtu_cookie);
net/ipv4/tcp_minisocks.c +0 -2
@@ -440,8 +440,6 @@ struct sock *tcp_create_openreq_child(st newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss;TCP_ECN_openreq_child (newtp, req); -if (newtp->ecn_flags&TCP_ECN_OK ) -sock_set_flag (newsk,SOCK_NO_LARGESEND );TCP_INC_STATS_BH (TCP_MIB_PASSIVEOPENS ); }
net/ipv4/tcp_output.c +0 -2
@@ -2044,8 +2044,6 @@ struct sk_buff * tcp_make_synack(structmemset (th,0 ,sizeof (struct tcphdr )); th->syn =1 ; th->ack =1 ; -if (dst->dev->features&NETIF_F_TSO ) - ireq->ecn_ok =0 ;TCP_ECN_make_synack (req, th); th->source =inet_sk (sk)->sport; th->dest = ireq->rmt_port;
Quoted 2 lines · Michael Chan
Signed-off-by Michael Chan <[email protected]>
Looks good to me too!
include/net/tcp_ecn.h static inline void TCP_ECN_send(struct s · line 60
Quoted 7 lines
include/net/tcp_ecn.h +3
-0@@ -56,6 +55,9 @@ static inline void TCP_ECN_send(struct sif (tp->ecn_flags&TCP_ECN_QUEUE_CWR ) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR ; skb->h.th->cwr =1 ; +if (skb_shinfo (skb)->gso_type &SKB_GSO_TCPV4 ) +skb_shinfo (skb)->gso_type |= +SKB_GSO_TCPV4_ECN ;
As a byte-pincher I must suggest that you turn this check into something like
if (skb_shinfo(skb)->gso_type)
or even
if (skb_shinfo(skb)->gso_size)
:)
Cheers,
Signature · 4 lines
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txtQuoted 13 lines · Herbert Xu
include/net/tcp_ecn.h static inline void TCP_ECN_send(struct s · line 60
Quoted 7 lines · Michael Chan
include/net/tcp_ecn.h +3
-0@@ -56,6 +55,9 @@ static inline void TCP_ECN_send(struct sif (tp->ecn_flags&TCP_ECN_QUEUE_CWR ) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR ; skb->h.th->cwr =1 ; +if (skb_shinfo (skb)->gso_type &SKB_GSO_TCPV4 ) +skb_shinfo (skb)->gso_type |= +SKB_GSO_TCPV4_ECN ;As a byte-pincher I must suggest that you turn this check into something like
Quoted 6 lines
if (skb_shinfo(skb)->gso_type)or even
if (skb_shinfo(skb)->gso_size)
Assuming that we'll later have GSO_TCPV6, isn't it better to check for TCPV4 explicitly now? Or just change it later when necessary.
Quoted 3 lines · Michael Chan
Assuming that we'll later have
GSO_TCPV6, isn't it better to check for TCPV4 explicitly now? Or just change it later when necessary.
Good point, I suppose you never know whether a V6 TSO-capable card is going to handle ECN correctly in both cases.
Cheers,
Signature · 4 lines
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txtFrom: "Michael Chan" <[email protected]>
Date: Tue, 27 Jun 2006 21:37:01 -0700
Quoted 1 line
[NET]: Add ECN support for TSO
Applied, thanks a lot.
Michael,
Are network cards expected to be aware-of and implement RFC3540(ECN with nonces) ?
Thanks,
Ravi
-----Original Message-----
From: [email protected] [mailto:[email protected]]On Behalf Of Michael Chan
Sent: Tuesday, June 27, 2006 8:07 PM
To: [email protected]; [email protected]
Cc: [email protected]
Subject: [PATCH]NET: Add ECN support for TSO
In the current TSO implementation, NETIF_F_TSO and ECN cannot be turned on together in a TCP connection. The problem is that most hardware that supports TSO does not handle CWR correctly if it is set in the TSO packet. Correct handling requires CWR to be set in the first packet only if it is set in the TSO header.
This patch adds the ability to turn on NETIF_F_TSO and ECN using GSO if necessary to handle TSO packets with CWR set. Hardware that handles CWR correctly can turn on NETIF_F_TSO_ECN in the dev-> features flag.
All TSO packets with CWR set will have the SKB_GSO_TCPV4_ECN set. If the output device does not have the NETIF_F_TSO_ECN feature set, GSO will split the packet up correctly with CWR only set in the first segment.
It is further assumed that all hardware will handle ECE properly by replicating the ECE flag in all segments. If that is not the case, a simple extension of the logic will be required.