Commit 77968b78 authored by David S. Miller's avatar David S. Miller
Browse files

ipv4: Pass flow keys down into datagram packet building engine. 



This way ip_output.c no longer needs rt->rt_{src,dst}.

We already have these keys sitting, ready and waiting, on the stack or
in a socket structure.

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent e474995f

include/net/ip.h

+5 −3
Original line number Diff line number Diff line
@@ -117,12 +117,14 @@ extern int ip_generic_getfrag(void *from, char *to, int offset, int len, int od 
extern ssize_t		ip_append_page(struct sock *sk, struct page *page,

				int offset, size_t size, int flags);

extern struct sk_buff  *__ip_make_skb(struct sock *sk,

				      struct flowi4 *fl4,

				      struct sk_buff_head *queue,

				      struct inet_cork *cork);

extern int		ip_send_skb(struct sk_buff *skb);

extern int		ip_push_pending_frames(struct sock *sk);

extern int		ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4);

extern void		ip_flush_pending_frames(struct sock *sk);

extern struct sk_buff  *ip_make_skb(struct sock *sk,

				    struct flowi4 *fl4,

				    int getfrag(void *from, char *to, int offset, int len,

						int odd, struct sk_buff *skb),

				    void *from, int length, int transhdrlen,
@@ -130,9 +132,9 @@ extern struct sk_buff *ip_make_skb(struct sock *sk, 
				    struct rtable **rtp,

				    unsigned int flags);



static inline struct sk_buff *ip_finish_skb(struct sock *sk)

static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)

{

	return __ip_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork.base);

	return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);

}



/* datagram.c */

net/ipv4/icmp.c

+36 −38
Original line number Diff line number Diff line
@@ -290,6 +290,7 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, 
}



static void icmp_push_reply(struct icmp_bxm *icmp_param,

			    struct flowi4 *fl4,

			    struct ipcm_cookie *ipc, struct rtable **rt)

{

	struct sock *sk;
@@ -315,7 +316,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param, 
						 icmp_param->head_len, csum);

		icmph->checksum = csum_fold(csum);

		skb->ip_summed = CHECKSUM_NONE;

		ip_push_pending_frames(sk);

		ip_push_pending_frames(sk, fl4);

	}

}
@@ -328,6 +329,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) 
	struct ipcm_cookie ipc;

	struct rtable *rt = skb_rtable(skb);

	struct net *net = dev_net(rt->dst.dev);

	struct flowi4 fl4;

	struct sock *sk;

	struct inet_sock *inet;

	__be32 daddr;
@@ -351,57 +353,52 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) 
		if (ipc.opt->opt.srr)

			daddr = icmp_param->replyopts.opt.opt.faddr;

	}

	{

		struct flowi4 fl4 = {

			.daddr = daddr,

			.saddr = rt->rt_spec_dst,

			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),

			.flowi4_proto = IPPROTO_ICMP,

		};

	memset(&fl4, 0, sizeof(fl4));

	fl4.daddr = daddr;

	fl4.saddr = rt->rt_spec_dst;

	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);

	fl4.flowi4_proto = IPPROTO_ICMP;

	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));

	rt = ip_route_output_key(net, &fl4);

	if (IS_ERR(rt))

		goto out_unlock;

	}

	if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type,

			       icmp_param->data.icmph.code))

		icmp_push_reply(icmp_param, &ipc, &rt);

		icmp_push_reply(icmp_param, &fl4, &ipc, &rt);

	ip_rt_put(rt);

out_unlock:

	icmp_xmit_unlock(sk);

}



static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in,

static struct rtable *icmp_route_lookup(struct net *net,

					struct flowi4 *fl4,

					struct sk_buff *skb_in,

					const struct iphdr *iph,

					__be32 saddr, u8 tos,

					int type, int code,

					struct icmp_bxm *param)

{

	struct flowi4 fl4 = {

		.daddr = (param->replyopts.opt.opt.srr ?

			  param->replyopts.opt.opt.faddr : iph->saddr),

		.saddr = saddr,

		.flowi4_tos = RT_TOS(tos),

		.flowi4_proto = IPPROTO_ICMP,

		.fl4_icmp_type = type,

		.fl4_icmp_code = code,

	};

	struct rtable *rt, *rt2;

	int err;



	security_skb_classify_flow(skb_in, flowi4_to_flowi(&fl4));

	rt = __ip_route_output_key(net, &fl4);

	memset(fl4, 0, sizeof(*fl4));

	fl4->daddr = (param->replyopts.opt.opt.srr ?

		      param->replyopts.opt.opt.faddr : iph->saddr);

	fl4->saddr = saddr;

	fl4->flowi4_tos = RT_TOS(tos);

	fl4->flowi4_proto = IPPROTO_ICMP;

	fl4->fl4_icmp_type = type;

	fl4->fl4_icmp_code = code;

	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));

	rt = __ip_route_output_key(net, fl4);

	if (IS_ERR(rt))

		return rt;



	/* No need to clone since we're just using its address. */

	rt2 = rt;



	if (!fl4.saddr)

		fl4.saddr = rt->rt_src;



	rt = (struct rtable *) xfrm_lookup(net, &rt->dst,

					   flowi4_to_flowi(&fl4), NULL, 0);

					   flowi4_to_flowi(fl4), NULL, 0);

	if (!IS_ERR(rt)) {

		if (rt != rt2)

			return rt;
@@ -410,19 +407,19 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, 
	} else

		return rt;



	err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4), AF_INET);

	err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(fl4), AF_INET);

	if (err)

		goto relookup_failed;



	if (inet_addr_type(net, fl4.saddr) == RTN_LOCAL) {

		rt2 = __ip_route_output_key(net, &fl4);

	if (inet_addr_type(net, fl4->saddr) == RTN_LOCAL) {

		rt2 = __ip_route_output_key(net, fl4);

		if (IS_ERR(rt2))

			err = PTR_ERR(rt2);

	} else {

		struct flowi4 fl4_2 = {};

		unsigned long orefdst;



		fl4_2.daddr = fl4.saddr;

		fl4_2.daddr = fl4->saddr;

		rt2 = ip_route_output_key(net, &fl4_2);

		if (IS_ERR(rt2)) {

			err = PTR_ERR(rt2);
@@ -430,7 +427,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, 
		}

		/* Ugh! */

		orefdst = skb_in->_skb_refdst; /* save old refdst */

		err = ip_route_input(skb_in, fl4.daddr, fl4.saddr,

		err = ip_route_input(skb_in, fl4->daddr, fl4->saddr,

				     RT_TOS(tos), rt2->dst.dev);



		dst_release(&rt2->dst);
@@ -442,7 +439,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct sk_buff *skb_in, 
		goto relookup_failed;



	rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst,

					    flowi4_to_flowi(&fl4), NULL,

					    flowi4_to_flowi(fl4), NULL,

					    XFRM_LOOKUP_ICMP);

	if (!IS_ERR(rt2)) {

		dst_release(&rt->dst);
@@ -481,6 +478,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) 
	struct icmp_bxm icmp_param;

	struct rtable *rt = skb_rtable(skb_in);

	struct ipcm_cookie ipc;

	struct flowi4 fl4;

	__be32 saddr;

	u8  tos;

	struct net *net;
@@ -599,7 +597,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) 
	ipc.opt = &icmp_param.replyopts.opt;

	ipc.tx_flags = 0;



	rt = icmp_route_lookup(net, skb_in, iph, saddr, tos,

	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,

			       type, code, &icmp_param);

	if (IS_ERR(rt))

		goto out_unlock;
@@ -620,7 +618,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) 
		icmp_param.data_len = room;

	icmp_param.head_len = sizeof(struct icmphdr);



	icmp_push_reply(&icmp_param, &ipc, &rt);

	icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);

ende:

	ip_rt_put(rt);

out_unlock:

net/ipv4/ip_output.c

+19 −20
Original line number Diff line number Diff line
@@ -1267,6 +1267,7 @@ static void ip_cork_release(struct inet_cork *cork) 
 *	and push them out.

 */

struct sk_buff *__ip_make_skb(struct sock *sk,

			      struct flowi4 *fl4,

			      struct sk_buff_head *queue,

			      struct inet_cork *cork)

{
@@ -1333,8 +1334,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, 
	ip_select_ident(iph, &rt->dst, sk);

	iph->ttl = ttl;

	iph->protocol = sk->sk_protocol;

	iph->saddr = rt->rt_src;

	iph->daddr = rt->rt_dst;

	iph->saddr = fl4->saddr;

	iph->daddr = fl4->daddr;



	skb->priority = sk->sk_priority;

	skb->mark = sk->sk_mark;
@@ -1370,11 +1371,11 @@ int ip_send_skb(struct sk_buff *skb) 
	return err;

}



int ip_push_pending_frames(struct sock *sk)

int ip_push_pending_frames(struct sock *sk, struct flowi4 *fl4)

{

	struct sk_buff *skb;



	skb = ip_finish_skb(sk);

	skb = ip_finish_skb(sk, fl4);

	if (!skb)

		return 0;
@@ -1403,6 +1404,7 @@ void ip_flush_pending_frames(struct sock *sk) 
}



struct sk_buff *ip_make_skb(struct sock *sk,

			    struct flowi4 *fl4,

			    int getfrag(void *from, char *to, int offset,

					int len, int odd, struct sk_buff *skb),

			    void *from, int length, int transhdrlen,
@@ -1432,7 +1434,7 @@ struct sk_buff *ip_make_skb(struct sock *sk, 
		return ERR_PTR(err);

	}



	return __ip_make_skb(sk, &queue, &cork);

	return __ip_make_skb(sk, fl4, &queue, &cork);

}



/*
@@ -1461,6 +1463,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar 
	struct inet_sock *inet = inet_sk(sk);

	struct ip_options_data replyopts;

	struct ipcm_cookie ipc;

	struct flowi4 fl4;

	__be32 daddr;

	struct rtable *rt = skb_rtable(skb);
@@ -1478,9 +1481,6 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar 
			daddr = replyopts.opt.opt.faddr;

	}



	{

		struct flowi4 fl4;



	flowi4_init_output(&fl4, arg->bound_dev_if, 0,

			   RT_TOS(ip_hdr(skb)->tos),

			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
@@ -1491,7 +1491,6 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar 
	rt = ip_route_output_key(sock_net(sk), &fl4);

	if (IS_ERR(rt))

		return;

	}



	/* And let IP do all the hard work.
@@ -1512,7 +1511,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar 
			  arg->csumoffset) = csum_fold(csum_add(skb->csum,

								arg->csum));

		skb->ip_summed = CHECKSUM_NONE;

		ip_push_pending_frames(sk);

		ip_push_pending_frames(sk, &fl4);

	}



	bh_unlock_sock(sk);

net/ipv4/raw.c

+29 −30
Original line number Diff line number Diff line
@@ -314,7 +314,8 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) 
	return 0;

}



static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,

static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,

			   void *from, size_t length,

			   struct rtable **rtp,

			   unsigned int flags)

{
@@ -327,7 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, 
	struct rtable *rt = *rtp;



	if (length > rt->dst.dev->mtu) {

		ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport,

		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,

			       rt->dst.dev->mtu);

		return -EMSGSIZE;

	}
@@ -372,7 +373,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, 


	if (iphlen >= sizeof(*iph)) {

		if (!iph->saddr)

			iph->saddr = rt->rt_src;

			iph->saddr = fl4->saddr;

		iph->check   = 0;

		iph->tot_len = htons(length);

		if (!iph->id)
@@ -455,6 +456,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, 
	struct inet_sock *inet = inet_sk(sk);

	struct ipcm_cookie ipc;

	struct rtable *rt = NULL;

	struct flowi4 fl4;

	int free = 0;

	__be32 daddr;

	__be32 saddr;
@@ -558,9 +560,6 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, 
			saddr = inet->mc_addr;

	}



	{

		struct flowi4 fl4;



	flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,

			   RT_SCOPE_UNIVERSE,

			   inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
@@ -579,7 +578,6 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, 
		rt = NULL;

		goto done;

	}

	}



	err = -EACCES;

	if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
@@ -590,19 +588,20 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, 
back_from_confirm:



	if (inet->hdrincl)

		err = raw_send_hdrinc(sk, msg->msg_iov, len,

		err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,

				      &rt, msg->msg_flags);



	 else {

		if (!ipc.addr)

			ipc.addr = rt->rt_dst;

			ipc.addr = fl4.daddr;

		lock_sock(sk);

		err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,

		err = ip_append_data(sk, ip_generic_getfrag,

				     msg->msg_iov, len, 0,

				     &ipc, &rt, msg->msg_flags);

		if (err)

			ip_flush_pending_frames(sk);

		else if (!(msg->msg_flags & MSG_MORE)) {

			err = ip_push_pending_frames(sk);

			err = ip_push_pending_frames(sk, &fl4);

			if (err == -ENOBUFS && !inet->recverr)

				err = 0;

		}

net/ipv4/udp.c

+2 −2
Original line number Diff line number Diff line
@@ -774,7 +774,7 @@ static int udp_push_pending_frames(struct sock *sk) 
	struct sk_buff *skb;

	int err = 0;



	skb = ip_finish_skb(sk);

	skb = ip_finish_skb(sk, fl4);

	if (!skb)

		goto out;
@@ -958,7 +958,7 @@ back_from_confirm: 


	/* Lockless fast path for the non-corking case. */

	if (!corkreq) {

		skb = ip_make_skb(sk, getfrag, msg->msg_iov, ulen,

		skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen,

				  sizeof(struct udphdr), &ipc, &rt,

				  msg->msg_flags);

		err = PTR_ERR(skb);