Commit dc83d4d8 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp_skb_cb' 



Eric Dumazet says:

====================
tcp: better TCP_SKB_CB layout

TCP had the assumption that IPCB and IP6CB are first members of skb->cb[]

This is fine, except that IPCB/IP6CB are used in TCP for a very short time
in input path.

What really matters for TCP stack is to get skb->next,
TCP_SKB_CB(skb)->seq, and TCP_SKB_CB(skb)->end_seq in the same cache line.

skb that are immediately consumed do not care because whole skb->cb[] is
hot in cpu cache, while skb that sit in wocket write queue or receive queues
do not need TCP_SKB_CB(skb)->header at all.

This patch set implements the prereq for IPv4, IPv6, and TCP to make this
possible. This makes TCP more efficient.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents ff04a771 971f10ec

include/net/ip.h

+12 −3
Original line number Diff line number Diff line
@@ -180,8 +180,10 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg) 
	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;

}



void ip_send_unicast_reply(struct net *net, struct sk_buff *skb, __be32 daddr,

			   __be32 saddr, const struct ip_reply_arg *arg,

void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,

			   const struct ip_options *sopt,

			   __be32 daddr, __be32 saddr,

			   const struct ip_reply_arg *arg,

			   unsigned int len);



#define IP_INC_STATS(net, field)	SNMP_INC_STATS64((net)->mib.ip_statistics, field)
@@ -511,7 +513,14 @@ int ip_forward(struct sk_buff *skb); 
 

void ip_options_build(struct sk_buff *skb, struct ip_options *opt,

		      __be32 daddr, struct rtable *rt, int is_frag);

int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb);



int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,

		      const struct ip_options *sopt);

static inline int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)

{

	return __ip_options_echo(dopt, skb, &IPCB(skb)->opt);

}



void ip_options_fragment(struct sk_buff *skb);

int ip_options_compile(struct net *net, struct ip_options *opt,

		       struct sk_buff *skb);

include/net/ipv6.h

+2 −1
Original line number Diff line number Diff line
@@ -288,7 +288,8 @@ struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, 
struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,

					  struct ipv6_txoptions *opt);



bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb);

bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb,

		       const struct inet6_skb_parm *opt);



static inline bool ipv6_accept_ra(struct inet6_dev *idev)

{

include/net/tcp.h

+6 −6
Original line number Diff line number Diff line
@@ -696,12 +696,6 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) 
 * If this grows please adjust skbuff.h:skbuff->cb[xxx] size appropriately.

 */

struct tcp_skb_cb {

	union {

		struct inet_skb_parm	h4;

#if IS_ENABLED(CONFIG_IPV6)

		struct inet6_skb_parm	h6;

#endif

	} header;	/* For incoming frames		*/

	__u32		seq;		/* Starting sequence number	*/

	__u32		end_seq;	/* SEQ + FIN + SYN + datalen	*/

	__u32		tcp_tw_isn;	/* isn chosen by tcp_timewait_state_process() */
@@ -720,6 +714,12 @@ struct tcp_skb_cb { 
	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/

	/* 1 byte hole */

	__u32		ack_seq;	/* Sequence number ACK'd	*/

	union {

		struct inet_skb_parm	h4;

#if IS_ENABLED(CONFIG_IPV6)

		struct inet6_skb_parm	h6;

#endif

	} header;	/* For incoming frames		*/

};



#define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))

net/dccp/ipv6.c

+1 −1
Original line number Diff line number Diff line
@@ -404,7 +404,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) 
	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;

	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;



	if (ipv6_opt_accepted(sk, skb) ||

	if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||

	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||

	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {

		atomic_inc(&skb->users);

net/ipv4/ip_options.c

+2 −4
Original line number Diff line number Diff line
@@ -87,17 +87,15 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt, 
 * NOTE: dopt cannot point to skb.

 */



int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb)

int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb,

		      const struct ip_options *sopt)

{

	const struct ip_options *sopt;

	unsigned char *sptr, *dptr;

	int soffset, doffset;

	int	optlen;



	memset(dopt, 0, sizeof(struct ip_options));



	sopt = &(IPCB(skb)->opt);



	if (sopt->optlen == 0)

		return 0;

CRA Git | Maintained and supported by SUSTech CRA and CCSE