Skip to contentSkip to conversation

Generalise tcp_listen_opt

PATCH In review Arnaldo Carvalho de Melo 1 participant 1 message May 24, 2005

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

PATCH 1/2 Generalise tcp_listen_opt

Hi David,

Please consider pulling into your net-2.6.13 pending tree from:

rsync://rsync.kernel.org/pub/scm/linux/kernel/git/acme/net-2.6.13.git

The bksend like output below was done using this script, people
starting to use git may find it useful :-)

http://dccp.ghostprotocols.net:81/acme-git-send-changeset

Best Regards,

- Arnaldo

tree f416accfe16809dce40f34fb711d42a67aea892d
parent 0642cf1e6afa649d8d9a9d3dc7275ceebb038ae0
author Arnaldo Carvalho de Melo <[email protected]> 1113623934 -0300 committer Arnaldo Carvalho de Melo <[email protected]> 1116886806 -0300

[NET] Generalise tcp_listen_opt

This chunks out the accept_queue and tcp_listen_opt code and moves them to net/core/request_sock.c and include/net/request_sock.h, to make it useful for other transport protocols, DCCP being the first one to use it.

Next patches will rename tcp_listen_opt to accept_sock and remove the inline tcp functions that just call a reqsk_queue_ function.

------------------------------------------------------------------------------

 include/linux/tcp.h        |   17 ----
 include/net/request_sock.h |  178 +++++++++++++++++++++++++++++++++++++++++++++
 include/net/tcp.h          |   46 ++---------
 net/core/Makefile          |    3 
 net/core/request_sock.c    |   48 ++++++++++++
 net/ipv4/tcp.c             |   67 +++++-----------
 net/ipv4/tcp_diag.c        |    6 -
 net/ipv4/tcp_ipv4.c        |   32 +++-----
 net/ipv4/tcp_minisocks.c   |    6 -
 net/ipv4/tcp_timer.c       |   10 --
 net/ipv6/tcp_ipv6.c        |   14 ---
 11 files changed, 281 insertions(+), 146 deletions(-)

------------------------------------------------------------------------------

include/linux/tcp.h +1 -16
@@ -379,22 +379,7 @@ struct tcp_sock {
 
 	__u32	total_retrans;	/* Total retransmits for entire connection */
 
-	/* The syn_wait_lock is necessary only to avoid proc interface having
-	 * to grab the main lock sock while browsing the listening hash
-	 * (otherwise it's deadlock prone).
-	 * This lock is acquired in read mode only from listening_get_next()
-	 * and it's acquired in write mode _only_ from code that is actively
-	 * changing the syn_wait_queue. All readers that are holding
-	 * the master sock lock don't need to grab this lock in read mode
-	 * too as the syn_wait_queue writes are always protected from
-	 * the main sock lock.
-	 */
-	rwlock_t		syn_wait_lock;
-	struct tcp_listen_opt	*listen_opt;
-
-	/* FIFO of established children */
-	struct request_sock	*accept_queue;
-	struct request_sock	*accept_queue_tail;
+	struct request_sock_queue accept_queue; /* FIFO of established children */
 
 	unsigned int		keepalive_time;	  /* time before keep alive takes place */
 	unsigned int		keepalive_intvl;  /* time interval between keep alive probes */
include/net/request_sock.h +178 -0

189 lines not on this page · raw message

include/net/tcp.h +8 -38

79 lines not on this page · raw message

net/core/Makefile +2 -1
@@ -2,7 +2,8 @@
 # Makefile for the Linux networking core.
 #
 
-obj-y := sock.o skbuff.o iovec.o datagram.o stream.o scm.o gen_stats.o gen_estimator.o
+obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
+	 gen_stats.o gen_estimator.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
net/core/request_sock.c new file +48 -0

48 lines not on this page · raw message

net/ipv4/tcp.c +21 -46

139 lines not on this page · raw message

net/ipv4/tcp_diag.c +3 -3
@@ -529,9 +529,9 @@ static int tcpdiag_dump_reqs(struct sk_b
 
 	entry.family = sk->sk_family;
 
-	read_lock_bh(&tp->syn_wait_lock);
+	read_lock_bh(&tp->accept_queue.syn_wait_lock);
 
-	lopt = tp->listen_opt;
+	lopt = tp->accept_queue.listen_opt;
 	if (!lopt || !lopt->qlen)
 		goto out;
 
@@ -588,7 +588,7 @@ static int tcpdiag_dump_reqs(struct sk_b
 	}
 
 out:
-	read_unlock_bh(&tp->syn_wait_lock);
+	read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 
 	return err;
 }
net/ipv4/tcp_ipv4.c +12 -20
@@ -874,7 +874,7 @@ static struct request_sock *tcp_v4_searc
 					      __u16 rport,
 					      __u32 raddr, __u32 laddr)
 {
-	struct tcp_listen_opt *lopt = tp->listen_opt;
+	struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt;
 	struct request_sock *req, **prev;
 
 	for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)];
@@ -898,18 +898,10 @@ static struct request_sock *tcp_v4_searc
 static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
+	struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt;
 	u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd);
 
-	req->expires = jiffies + TCP_TIMEOUT_INIT;
-	req->retrans = 0;
-	req->sk = NULL;
-	req->dl_next = lopt->syn_table[h];
-
-	write_lock(&tp->syn_wait_lock);
-	lopt->syn_table[h] = req;
-	write_unlock(&tp->syn_wait_lock);
-
+	reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT);
 	tcp_synq_added(sk);
 }
 
@@ -2167,17 +2159,17 @@ static void *listening_get_next(struct s
 			if (++st->sbucket >= TCP_SYNQ_HSIZE)
 				break;
 get_req:
-			req = tp->listen_opt->syn_table[st->sbucket];
+			req = tp->accept_queue.listen_opt->syn_table[st->sbucket];
 		}
 		sk	  = sk_next(st->syn_wait_sk);
 		st->state = TCP_SEQ_STATE_LISTENING;
-		read_unlock_bh(&tp->syn_wait_lock);
+		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 	} else {
 	       	tp = tcp_sk(sk);
-		read_lock_bh(&tp->syn_wait_lock);
-		if (tp->listen_opt && tp->listen_opt->qlen)
+		read_lock_bh(&tp->accept_queue.syn_wait_lock);
+		if (reqsk_queue_len(&tp->accept_queue))
 			goto start_req;
-		read_unlock_bh(&tp->syn_wait_lock);
+		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 		sk = sk_next(sk);
 	}
 get_sk:
@@ -2187,8 +2179,8 @@ get_sk:
 			goto out;
 		}
 	       	tp = tcp_sk(sk);
-		read_lock_bh(&tp->syn_wait_lock);
-		if (tp->listen_opt && tp->listen_opt->qlen) {
+		read_lock_bh(&tp->accept_queue.syn_wait_lock);
+		if (reqsk_queue_len(&tp->accept_queue)) {
 start_req:
 			st->uid		= sock_i_uid(sk);
 			st->syn_wait_sk = sk;
@@ -2196,7 +2188,7 @@ start_req:
 			st->sbucket	= 0;
 			goto get_req;
 		}
-		read_unlock_bh(&tp->syn_wait_lock);
+		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 	}
 	if (++st->bucket < TCP_LHTABLE_SIZE) {
 		sk = sk_head(&tcp_listening_hash[st->bucket]);
@@ -2383,7 +2375,7 @@ static void tcp_seq_stop(struct seq_file
 	case TCP_SEQ_STATE_OPENREQ:
 		if (v) {
 			struct tcp_sock *tp = tcp_sk(st->syn_wait_sk);
-			read_unlock_bh(&tp->syn_wait_lock);
+			read_unlock_bh(&tp->accept_queue.syn_wait_lock);
 		}
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
net/ipv4/tcp_minisocks.c +2 -4
@@ -790,10 +790,8 @@ struct sock *tcp_create_openreq_child(st
 		newtp->probes_out = 0;
 		newtp->rx_opt.num_sacks = 0;
 		newtp->urg_data = 0;
-		newtp->listen_opt = NULL;
-		newtp->accept_queue = newtp->accept_queue_tail = NULL;
-		/* Deinitialize syn_wait_lock to trap illegal accesses. */
-		memset(&newtp->syn_wait_lock, 0, sizeof(newtp->syn_wait_lock));
+		/* Deinitialize accept_queue to trap illegal accesses. */
+		memset(&newtp->accept_queue, 0, sizeof(newtp->accept_queue));
 
 		/* Back to base struct sock members. */
 		newsk->sk_err = 0;
net/ipv4/tcp_timer.c +3 -7
@@ -464,7 +464,7 @@ out_unlock:
 static void tcp_synack_timer(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
+	struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt;
 	int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries;
 	int thresh = max_retries;
 	unsigned long now = jiffies;
@@ -527,12 +527,8 @@ static void tcp_synack_timer(struct sock
 				}
 
 				/* Drop this request */
-				write_lock(&tp->syn_wait_lock);
-				*reqp = req->dl_next;
-				write_unlock(&tp->syn_wait_lock);
-				lopt->qlen--;
-				if (req->retrans == 0)
-					lopt->qlen_young--;
+				tcp_synq_unlink(tp, req, reqp);
+				reqsk_queue_removed(&tp->accept_queue, req);
 				reqsk_free(req);
 				continue;
 			}
net/ipv6/tcp_ipv6.c +3 -11
@@ -401,7 +401,7 @@ static struct request_sock *tcp_v6_searc
 					      struct in6_addr *laddr,
 					      int iif)
 {
-	struct tcp_listen_opt *lopt = tp->listen_opt;
+	struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt;
 	struct request_sock *req, **prev;  
 
 	for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)];
@@ -1267,18 +1267,10 @@ static struct sock *tcp_v6_hnd_req(struc
 static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	struct tcp_listen_opt *lopt = tp->listen_opt;
+	struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt;
 	u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd);
 
-	req->sk = NULL;
-	req->expires = jiffies + TCP_TIMEOUT_INIT;
-	req->retrans = 0;
-	req->dl_next = lopt->syn_table[h];
-
-	write_lock(&tp->syn_wait_lock);
-	lopt->syn_table[h] = req;
-	write_unlock(&tp->syn_wait_lock);
-
+	reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT);
 	tcp_synq_added(sk);
 }