Merge master.kernel.org:/home/acme/BK/net-2.5

into nuts.ninka.net:/home/davem/src/BK/net-2.5

include/linux/mroute.h

@@ -126,6 +126,8 @@ struct igmpmsg
  */
 
 #ifdef __KERNEL__
+#include <net/sock.h>
+
 extern int ip_mroute_setsockopt(struct sock *, int, char *, int);
 extern int ip_mroute_getsockopt(struct sock *, int, char *, int *);
 extern int ipmr_ioctl(struct sock *sk, int cmd, unsigned long arg);

net/core/dev.c

@@ -94,6 +94,7 @@
 #include <net/sock.h>
 #include <linux/rtnetlink.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/stat.h>
 #include <linux/if_bridge.h>
 #include <linux/divert.h>
@@ -114,6 +115,7 @@
 extern int plip_init(void);
 #endif
 
+#include <asm/current.h>
 
 /* This define, if set, will randomly drop a packet when congestion
  * is more than moderate.  It helps fairness in the multi-interface
@@ -1719,128 +1721,196 @@ static int dev_ifconf(char *arg)
 	return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
 }
 
+#ifdef CONFIG_PROC_FS
 /*
  *	This is invoked by the /proc filesystem handler to display a device
  *	in detail.
  */
+static __inline__ struct net_device *dev_get_idx(struct seq_file *seq,
+						 loff_t pos)
+{
+	struct net_device *dev;
+	loff_t i;
 
-#ifdef CONFIG_PROC_FS
+	for (i = 0, dev = dev_base; dev && i < pos; dev = dev->next);
+
+	return i == pos ? dev : NULL;
+}
+
+void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	read_lock(&dev_base_lock);
+	return *pos ? dev_get_idx(seq, *pos) : (void *)1;
+}
 
-static int sprintf_stats(char *buffer, struct net_device *dev)
+void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	return v == (void *)1 ? dev_base : ((struct net_device *)v)->next;
+}
+
+void dev_seq_stop(struct seq_file *seq, void *v)
+{
+	read_unlock(&dev_base_lock);
+}
+
+static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
 {
 	struct net_device_stats *stats = dev->get_stats ? dev->get_stats(dev) :
 							  NULL;
-	int size;
-
 	if (stats)
-		size = sprintf(buffer, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu "
-				       "%10lu %9lu %8lu %7lu %4lu %4lu %4lu "
-				       "%5lu %7lu %10lu\n",
- 		   dev->name,
-		   stats->rx_bytes,
-		   stats->rx_packets, stats->rx_errors,
-		   stats->rx_dropped + stats->rx_missed_errors,
-		   stats->rx_fifo_errors,
-		   stats->rx_length_errors + stats->rx_over_errors +
-		   	stats->rx_crc_errors + stats->rx_frame_errors,
-		   stats->rx_compressed, stats->multicast,
-		   stats->tx_bytes,
-		   stats->tx_packets, stats->tx_errors, stats->tx_dropped,
-		   stats->tx_fifo_errors, stats->collisions,
-		   stats->tx_carrier_errors + stats->tx_aborted_errors +
-		   	stats->tx_window_errors + stats->tx_heartbeat_errors,
-		   stats->tx_compressed);
+		seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
+				"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+			   dev->name, stats->rx_bytes, stats->rx_packets,
+			   stats->rx_errors,
+			   stats->rx_dropped + stats->rx_missed_errors,
+			   stats->rx_fifo_errors,
+			   stats->rx_length_errors + stats->rx_over_errors +
+			     stats->rx_crc_errors + stats->rx_frame_errors,
+			   stats->rx_compressed, stats->multicast,
+			   stats->tx_bytes, stats->tx_packets,
+			   stats->tx_errors, stats->tx_dropped,
+			   stats->tx_fifo_errors, stats->collisions,
+			   stats->tx_carrier_errors +
+			     stats->tx_aborted_errors +
+			     stats->tx_window_errors +
+			     stats->tx_heartbeat_errors,
+			   stats->tx_compressed);
 	else
-		size = sprintf(buffer, "%6s: No statistics available.\n",
-			       dev->name);
-
-	return size;
+		seq_printf(seq, "%6s: No statistics available.\n", dev->name);
 }
 
 /*
  *	Called from the PROCfs module. This now uses the new arbitrary sized
  *	/proc/net interface to create /proc/net/dev
  */
-static int dev_get_info(char *buffer, char **start, off_t offset, int length)
+static int dev_seq_show(struct seq_file *seq, void *v)
 {
-	int len = 0;
-	off_t begin = 0;
-	off_t pos = 0;
-	int size;
-	struct net_device *dev;
+	if (v == (void *)1)
+		seq_printf(seq, "Inter-|   Receive                            "
+				"                    |  Transmit\n"
+				" face |bytes    packets errs drop fifo frame "
+				"compressed multicast|bytes    packets errs "
+				"drop fifo colls carrier compressed\n");
+	else
+		dev_seq_printf_stats(seq, v);
+	return 0;
+}
 
-	size = sprintf(buffer,
-		"Inter-|   Receive                                                |  Transmit\n"
-		" face |bytes    packets errs drop fifo frame compressed multicast|bytes    packets errs drop fifo colls carrier compressed\n");
+static struct netif_rx_stats *softnet_get_online(loff_t *pos)
+{
+	struct netif_rx_stats *rc = NULL;
 
-	pos += size;
-	len += size;
+	while (*pos < NR_CPUS)
+	       	if (cpu_online(*pos)) {
+			rc = &netdev_rx_stat[*pos];
+			break;
+		} else
+			++*pos;
+	return rc;
+}
 
-	read_lock(&dev_base_lock);
-	for (dev = dev_base; dev; dev = dev->next) {
-		size = sprintf_stats(buffer+len, dev);
-		len += size;
-		pos = begin + len;
+static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return softnet_get_online(pos);
+}
 
-		if (pos < offset) {
-			len = 0;
-			begin = pos;
-		}
-		if (pos > offset + length)
-			break;
-	}
-	read_unlock(&dev_base_lock);
+static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return softnet_get_online(pos);
+}
 
-	*start = buffer + (offset - begin);	/* Start of wanted data */
-	len -= offset - begin;			/* Start slop */
-	if (len > length)
-		len = length;			/* Ending slop */
-	if (len < 0)
-		len = 0;
-	return len;
+static void softnet_seq_stop(struct seq_file *seq, void *v)
+{
 }
 
-static int dev_proc_stats(char *buffer, char **start, off_t offset,
-			  int length, int *eof, void *data)
+static int softnet_seq_show(struct seq_file *seq, void *v)
 {
-	int i;
-	int len = 0;
+	struct netif_rx_stats *s = v;
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_online(i))
-			continue;
-
-		len += sprintf(buffer + len, "%08x %08x %08x %08x %08x %08x "
-					     "%08x %08x %08x\n",
-			       netdev_rx_stat[i].total,
-			       netdev_rx_stat[i].dropped,
-			       netdev_rx_stat[i].time_squeeze,
-			       netdev_rx_stat[i].throttled,
-			       netdev_rx_stat[i].fastroute_hit,
-			       netdev_rx_stat[i].fastroute_success,
-			       netdev_rx_stat[i].fastroute_defer,
-			       netdev_rx_stat[i].fastroute_deferred_out,
+	seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+		   s->total, s->dropped, s->time_squeeze, s->throttled,
+		   s->fastroute_hit, s->fastroute_success, s->fastroute_defer,
+		   s->fastroute_deferred_out,
 #if 0
-			       netdev_rx_stat[i].fastroute_latency_reduction
+		   s->fastroute_latency_reduction
 #else
-			       netdev_rx_stat[i].cpu_collision
+		   s->cpu_collision
 #endif
-			       );
-	}
+		  );
+	return 0;
+}
 
-	len -= offset;
+static struct seq_operations dev_seq_ops = {
+	.start = dev_seq_start,
+	.next  = dev_seq_next,
+	.stop  = dev_seq_stop,
+	.show  = dev_seq_show,
+};
 
-	if (len > length)
-		len = length;
-	if (len < 0)
-		len = 0;
+static int dev_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &dev_seq_ops);
+}
+
+static struct file_operations dev_seq_fops = {
+	.open    = dev_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
 
-	*start = buffer + offset;
-	*eof = 1;
+static struct seq_operations softnet_seq_ops = {
+	.start = softnet_seq_start,
+	.next  = softnet_seq_next,
+	.stop  = softnet_seq_stop,
+	.show  = softnet_seq_show,
+};
 
-	return len;
+static int softnet_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &softnet_seq_ops);
 }
 
+static struct file_operations softnet_seq_fops = {
+	.open    = softnet_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+#ifdef WIRELESS_EXT
+extern int wireless_proc_init(void);
+#else
+#define wireless_proc_init() 0
+#endif
+
+static int __init dev_proc_init(void)
+{
+	struct proc_dir_entry *p;
+	int rc = -ENOMEM;
+
+	p = create_proc_entry("dev", S_IRUGO, proc_net);
+	if (!p)
+		goto out;
+	p->proc_fops = &dev_seq_fops;
+	p = create_proc_entry("softnet_stat", S_IRUGO, proc_net);
+	if (!p)
+		goto out_dev;
+	p->proc_fops = &softnet_seq_fops;
+	if (wireless_proc_init())
+		goto out_softnet;
+	rc = 0;
+out:
+	return rc;
+out_softnet:
+	remove_proc_entry("softnet_stat", proc_net);
+out_dev:
+	remove_proc_entry("dev", proc_net);
+	goto out;
+}
+#else
+#define dev_proc_init() 0
 #endif	/* CONFIG_PROC_FS */
 
 
@@ -2680,10 +2750,13 @@ extern void dv_init(void);
 static int __init net_dev_init(void)
 {
 	struct net_device *dev, **dp;
-	int i;
+	int i, rc = -ENOMEM;
 
 	BUG_ON(!dev_boot_phase);
 
+	if (dev_proc_init())
+		goto out;
+
 #ifdef CONFIG_NET_DIVERT
 	dv_init();
 #endif /* CONFIG_NET_DIVERT */
@@ -2787,15 +2860,6 @@ static int __init net_dev_init(void)
 		}
 	}
 
-#ifdef CONFIG_PROC_FS
-	proc_net_create("dev", 0, dev_get_info);
-	create_proc_read_entry("net/softnet_stat", 0, 0, dev_proc_stats, NULL);
-#ifdef WIRELESS_EXT
-	/* Available in net/core/wireless.c */
-	proc_net_create("wireless", 0, dev_get_wireless_info);
-#endif	/* WIRELESS_EXT */
-#endif	/* CONFIG_PROC_FS */
-
 	dev_boot_phase = 0;
 
 	open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
@@ -2812,8 +2876,9 @@ static int __init net_dev_init(void)
 	 */
 
 	net_device_init();
-
-	return 0;
+	rc = 0;
+out:
+	return rc;
 }
 
 subsys_initcall(net_dev_init);

net/core/wireless.c

@@ -47,15 +47,18 @@
 
 /***************************** INCLUDES *****************************/
 
-#include <asm/uaccess.h>		/* copy_to_user() */
 #include <linux/config.h>		/* Not needed ??? */
 #include <linux/types.h>		/* off_t */
 #include <linux/netdevice.h>		/* struct ifreq, dev_get_by_name() */
+#include <linux/proc_fs.h>
 #include <linux/rtnetlink.h>		/* rtnetlink stuff */
-
+#include <linux/seq_file.h>
 #include <linux/wireless.h>		/* Pretty obvious */
+
 #include <net/iw_handler.h>		/* New driver API */
 
+#include <asm/uaccess.h>		/* copy_to_user() */
+
 /**************************** CONSTANTS ****************************/
 
 /* Enough lenience, let's make sure things are proper... */
@@ -330,83 +333,78 @@ static inline int get_priv_size(__u16	args)
 /*
  * Print one entry (line) of /proc/net/wireless
  */
-static inline int sprintf_wireless_stats(char *buffer, struct net_device *dev)
+static __inline__ void wireless_seq_printf_stats(struct seq_file *seq,
+						 struct net_device *dev)
 {
 	/* Get stats from the driver */
-	struct iw_statistics *stats;
-	int size;
-
-	stats = get_wireless_stats(dev);
-	if (stats != (struct iw_statistics *) NULL) {
-		size = sprintf(buffer,
-			       "%6s: %04x  %3d%c  %3d%c  %3d%c  %6d %6d %6d %6d %6d   %6d\n",
-			       dev->name,
-			       stats->status,
-			       stats->qual.qual,
-			       stats->qual.updated & 1 ? '.' : ' ',
-			       ((__u8) stats->qual.level),
-			       stats->qual.updated & 2 ? '.' : ' ',
-			       ((__u8) stats->qual.noise),
-			       stats->qual.updated & 4 ? '.' : ' ',
-			       stats->discard.nwid,
-			       stats->discard.code,
-			       stats->discard.fragment,
-			       stats->discard.retries,
-			       stats->discard.misc,
-			       stats->miss.beacon);
+	struct iw_statistics *stats = get_wireless_stats(dev);
+
+	if (stats) {
+		seq_printf(seq, "%6s: %04x  %3d%c  %3d%c  %3d%c  %6d %6d %6d "
+				"%6d %6d   %6d\n",
+			   dev->name, stats->status, stats->qual.qual,
+			   stats->qual.updated & 1 ? '.' : ' ',
+			   ((__u8) stats->qual.level),
+			   stats->qual.updated & 2 ? '.' : ' ',
+			   ((__u8) stats->qual.noise),
+			   stats->qual.updated & 4 ? '.' : ' ',
+			   stats->discard.nwid, stats->discard.code,
+			   stats->discard.fragment, stats->discard.retries,
+			   stats->discard.misc, stats->miss.beacon);
 		stats->qual.updated = 0;
 	}
-	else
-		size = 0;
-
-	return size;
 }
 
 /* ---------------------------------------------------------------- */
 /*
  * Print info for /proc/net/wireless (print all entries)
  */
-int dev_get_wireless_info(char * buffer, char **start, off_t offset,
-			  int length)
+static int wireless_seq_show(struct seq_file *seq, void *v)
 {
-	int		len = 0;
-	off_t		begin = 0;
-	off_t		pos = 0;
-	int		size;
-	
-	struct net_device *	dev;
-
-	size = sprintf(buffer,
-		       "Inter-| sta-|   Quality        |   Discarded packets               | Missed\n"
-		       " face | tus | link level noise |  nwid  crypt   frag  retry   misc | beacon\n"
-			);
-	
-	pos += size;
-	len += size;
-
-	read_lock(&dev_base_lock);
-	for (dev = dev_base; dev != NULL; dev = dev->next) {
-		size = sprintf_wireless_stats(buffer + len, dev);
-		len += size;
-		pos = begin + len;
-
-		if (pos < offset) {
-			len = 0;
-			begin = pos;
-		}
-		if (pos > offset + length)
-			break;
-	}
-	read_unlock(&dev_base_lock);
+	if (v == (void *)1)
+		seq_printf(seq, "Inter-| sta-|   Quality        |   Discarded "
+				"packets               | Missed\n"
+				" face | tus | link level noise |  nwid  "
+				"crypt   frag  retry   misc | beacon\n");
+	else
+		wireless_seq_printf_stats(seq, v);
+	return 0;
+}
+
+extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
+extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
+extern void dev_seq_stop(struct seq_file *seq, void *v);
+
+static struct seq_operations wireless_seq_ops = {
+	.start = dev_seq_start,
+	.next  = dev_seq_next,
+	.stop  = dev_seq_stop,
+	.show  = wireless_seq_show,
+};
 
-	*start = buffer + (offset - begin);	/* Start of wanted data */
-	len -= (offset - begin);		/* Start slop */
-	if (len > length)
-		len = length;			/* Ending slop */
-	if (len < 0)
-		len = 0;
+static int wireless_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &wireless_seq_ops);
+}
+
+static struct file_operations wireless_seq_fops = {
+	.open    = wireless_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
 
-	return len;
+int __init wireless_proc_init(void)
+{
+	struct proc_dir_entry *p;
+	int rc = 0;
+
+	p = create_proc_entry("wireless", S_IRUGO, proc_net);
+	if (p)
+		p->proc_fops = &wireless_seq_fops;
+	else
+		rc = -ENOMEM;
+	return rc;
 }
 #endif	/* CONFIG_PROC_FS */
 

net/ipv4/af_inet.c

@@ -103,8 +103,6 @@
 #include <net/tcp.h>
 #include <net/udp.h>
 #include <linux/skbuff.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
 #include <net/sock.h>
 #include <net/raw.h>
 #include <net/icmp.h>
@@ -1165,7 +1163,8 @@ extern void fib_proc_exit(void);
 extern int  ip_misc_proc_init(void);
 extern int  raw_proc_init(void);
 extern void raw_proc_exit(void);
-extern int  tcp_get_info(char *buffer, char **start, off_t offset, int length);
+extern int  tcp_proc_init(void);
+extern void tcp_proc_exit(void);
 extern int  udp_proc_init(void);
 extern void udp_proc_exit(void);
 
@@ -1175,7 +1174,7 @@ int __init ipv4_proc_init(void)
 
 	if (raw_proc_init())
 		goto out_raw;
-	if (!proc_net_create("tcp", 0, tcp_get_info))
+	if (tcp_proc_init())
 		goto out_tcp;
 	if (udp_proc_init())
 		goto out_udp;
@@ -1190,7 +1189,7 @@ int __init ipv4_proc_init(void)
 out_fib:
 	udp_proc_exit();
 out_udp:
-	proc_net_remove("tcp");
+	tcp_proc_exit();
 out_tcp:
 	raw_proc_exit();
 out_raw:

net/ipv4/raw.c

@@ -55,6 +55,7 @@
 #include <linux/sockios.h>
 #include <linux/socket.h>
 #include <linux/in.h>
+#include <linux/mroute.h>
 #include <linux/netdevice.h>
 #include <linux/in_route.h>
 #include <linux/route.h>

net/ipv4/tcp_ipv4.c

@@ -69,6 +69,8 @@
 #include <linux/inet.h>
 #include <linux/ipv6.h>
 #include <linux/stddef.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 
 extern int sysctl_ip_dynaddr;
 extern int sysctl_ip_default_ttl;
@@ -2131,7 +2133,295 @@ static int tcp_v4_destroy_sock(struct sock *sk)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */
+
+enum tcp_seq_states {
+	TCP_SEQ_STATE_LISTENING,
+	TCP_SEQ_STATE_OPENREQ,
+	TCP_SEQ_STATE_ESTABLISHED,
+	TCP_SEQ_STATE_TIME_WAIT,
+};
+
+struct tcp_iter_state {
+	enum tcp_seq_states state;
+	struct sock	   *syn_wait_sk;
+	int		    bucket, sbucket, num, uid;
+};
+
+static void *listening_get_first(struct seq_file *seq)
+{
+	struct tcp_iter_state* st = seq->private;
+	void *rc = NULL;
+
+	for (st->bucket = 0; st->bucket < TCP_LHTABLE_SIZE; ++st->bucket) {
+		struct open_request *req;
+		struct tcp_opt *tp;
+		struct sock *sk = tcp_listening_hash[st->bucket];
+
+		if (!sk)
+			continue;
+		++st->num;
+		if (TCP_INET_FAMILY(sk->family)) {
+			rc = sk;
+			goto out;
+		}
+	       	tp = tcp_sk(sk);
+		read_lock_bh(&tp->syn_wait_lock);
+		if (tp->listen_opt && tp->listen_opt->qlen) {
+			st->uid		= sock_i_uid(sk);
+			st->syn_wait_sk = sk;
+			st->state	= TCP_SEQ_STATE_OPENREQ;
+			for (st->sbucket = 0; st->sbucket < TCP_SYNQ_HSIZE;
+			     ++st->sbucket) {
+				for (req = tp->listen_opt->syn_table[st->sbucket];
+				     req; req = req->dl_next, ++st->num) {
+					if (!TCP_INET_FAMILY(req->class->family))
+						continue;
+					rc = req;
+					goto out;
+				}
+			}
+			st->state = TCP_SEQ_STATE_LISTENING;
+		}
+		read_unlock_bh(&tp->syn_wait_lock);
+	}
+out:
+	return rc;
+}
+
+static void *listening_get_next(struct seq_file *seq, void *cur)
+{
+	struct tcp_opt *tp;
+	struct sock *sk = cur;
+	struct tcp_iter_state* st = seq->private;
+
+	if (st->state == TCP_SEQ_STATE_OPENREQ) {
+		struct open_request *req = cur;
+
+	       	tp = tcp_sk(st->syn_wait_sk);
+		req = req->dl_next;
+		while (1) {
+			while (req) {
+				++st->num;
+				if (TCP_INET_FAMILY(req->class->family)) {
+					cur = req;
+					goto out;
+				}
+				req = req->dl_next;
+			}
+			if (++st->sbucket >= TCP_SYNQ_HSIZE)
+				break;
+get_req:
+			req = tp->listen_opt->syn_table[st->sbucket];
+		}
+		sk	  = st->syn_wait_sk->next;
+		st->state = TCP_SEQ_STATE_LISTENING;
+		read_unlock_bh(&tp->syn_wait_lock);
+	} else
+		sk = sk->next;
+get_sk:
+	while (sk) {
+		if (TCP_INET_FAMILY(sk->family)) {
+			cur = sk;
+			goto out;
+		}
+	       	tp = tcp_sk(sk);
+		read_lock_bh(&tp->syn_wait_lock);
+		if (tp->listen_opt && tp->listen_opt->qlen) {
+			st->uid		= sock_i_uid(sk);
+			st->syn_wait_sk = sk;
+			st->state	= TCP_SEQ_STATE_OPENREQ;
+			st->sbucket	= 0;
+			goto get_req;
+		}
+		read_unlock_bh(&tp->syn_wait_lock);
+	}
+	if (++st->bucket < TCP_LHTABLE_SIZE) {
+		sk = tcp_listening_hash[st->bucket];
+		goto get_sk;
+	}
+	cur = NULL;
+out:
+	return cur;
+}
+
+static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
+{
+	void *rc = listening_get_first(seq);
+
+	if (rc)
+		while (*pos && (rc = listening_get_next(seq, rc)))
+			--*pos;
+	return *pos ? NULL : rc;
+}
+
+static void *established_get_first(struct seq_file *seq)
+{
+	struct tcp_iter_state* st = seq->private;
+	void *rc = NULL;
+
+	for (st->bucket = 0; st->bucket < tcp_ehash_size; ++st->bucket) {
+		struct sock *sk;
+		struct tcp_tw_bucket *tw;
+	       
+		read_lock(&tcp_ehash[st->bucket].lock);
+		for (sk = tcp_ehash[st->bucket].chain; sk;
+		     sk = sk->next, ++st->num) {
+			if (!TCP_INET_FAMILY(sk->family))
+				continue;
+			rc = sk;
+			goto out;
+		}
+		st->state = TCP_SEQ_STATE_TIME_WAIT;
+		for (tw = (struct tcp_tw_bucket *)
+				tcp_ehash[st->bucket + tcp_ehash_size].chain;
+		     tw; tw = (struct tcp_tw_bucket *)tw->next, ++st->num) {
+			if (!TCP_INET_FAMILY(tw->family))
+				continue;
+			rc = tw;
+			goto out;
+		}
+		read_unlock(&tcp_ehash[st->bucket].lock);
+		st->state = TCP_SEQ_STATE_ESTABLISHED;
+	}
+out:
+	return rc;
+}
+
+static void *established_get_next(struct seq_file *seq, void *cur)
+{
+	struct sock *sk = cur;
+	struct tcp_tw_bucket *tw;
+	struct tcp_iter_state* st = seq->private;
+
+	if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
+		tw = cur;
+		tw = (struct tcp_tw_bucket *)tw->next;
+get_tw:
+		while (tw && !TCP_INET_FAMILY(tw->family)) {
+			++st->num;
+			tw = (struct tcp_tw_bucket *)tw->next;
+		}
+		if (tw) {
+			cur = tw;
+			goto out;
+		}
+		read_unlock(&tcp_ehash[st->bucket].lock);
+		st->state = TCP_SEQ_STATE_ESTABLISHED;
+		if (++st->bucket < tcp_ehash_size) {
+			read_lock(&tcp_ehash[st->bucket].lock);
+			sk = tcp_ehash[st->bucket].chain;
+		} else {
+			cur = NULL;
+			goto out;
+		}
+	} else
+		sk = sk->next;
+
+	while (sk && !TCP_INET_FAMILY(sk->family)) {
+		++st->num;
+		sk = sk->next;
+	}
+	if (!sk) {
+		st->state = TCP_SEQ_STATE_TIME_WAIT;
+		tw = (struct tcp_tw_bucket *)
+				tcp_ehash[st->bucket + tcp_ehash_size].chain;
+		goto get_tw;
+	}
+	cur = sk;
+out:
+	return cur;
+}
+
+static void *established_get_idx(struct seq_file *seq, loff_t pos)
+{
+	void *rc = established_get_first(seq);
+
+	if (rc)
+		while (pos && (rc = established_get_next(seq, rc)))
+			--pos;
+	return pos ? NULL : rc;
+}
+
+static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
+{
+	void *rc;
+	struct tcp_iter_state* st = seq->private;
+
+	tcp_listen_lock();
+	st->state = TCP_SEQ_STATE_LISTENING;
+	rc	  = listening_get_idx(seq, &pos);
+
+	if (!rc) {
+		tcp_listen_unlock();
+		local_bh_disable();
+		st->state = TCP_SEQ_STATE_ESTABLISHED;
+		rc	  = established_get_idx(seq, pos);
+	}
+
+	return rc;
+}
+
+static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return *pos ? tcp_get_idx(seq, *pos - 1) : (void *)1;
+}
+
+static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	void *rc = NULL;
+	struct tcp_iter_state* st;
+
+	if (v == (void *)1) {
+		rc = tcp_get_idx(seq, 0);
+		goto out;
+	}
+	st = seq->private;
+
+	switch (st->state) {
+	case TCP_SEQ_STATE_OPENREQ:
+	case TCP_SEQ_STATE_LISTENING:
+		rc = listening_get_next(seq, v);
+		if (!rc) {
+			tcp_listen_unlock();
+			local_bh_disable();
+			st->state = TCP_SEQ_STATE_ESTABLISHED;
+			rc	  = established_get_first(seq);
+		}
+		break;
+	case TCP_SEQ_STATE_ESTABLISHED:
+	case TCP_SEQ_STATE_TIME_WAIT:
+		rc = established_get_next(seq, v);
+		break;
+	}
+out:
+	++*pos;
+	return rc;
+}
+
+static void tcp_seq_stop(struct seq_file *seq, void *v)
+{
+	struct tcp_iter_state* st = seq->private;
+
+	switch (st->state) {
+	case TCP_SEQ_STATE_OPENREQ:
+		if (v) {
+			struct tcp_opt *tp = tcp_sk(st->syn_wait_sk);
+			read_unlock_bh(&tp->syn_wait_lock);
+		}
+	case TCP_SEQ_STATE_LISTENING:
+		tcp_listen_unlock();
+		break;
+	case TCP_SEQ_STATE_TIME_WAIT:
+	case TCP_SEQ_STATE_ESTABLISHED:
+		if (v)
+			read_unlock(&tcp_ehash[st->bucket].lock);
+		local_bh_enable();
+		break;
+	}
+}
+
 static void get_openreq(struct sock *sk, struct open_request *req,
 			char *tmpbuf, int i, int uid)
 {
@@ -2219,137 +2509,89 @@ static void get_timewait_sock(struct tcp_tw_bucket *tw, char *tmpbuf, int i)
 
 #define TMPSZ 150
 
-int tcp_get_info(char *buffer, char **start, off_t offset, int length)
+static int tcp_seq_show(struct seq_file *seq, void *v)
 {
-	int len = 0, num = 0, i;
-	off_t begin, pos = 0;
+	struct tcp_iter_state* st;
 	char tmpbuf[TMPSZ + 1];
 
-	if (offset < TMPSZ)
-		len += sprintf(buffer, "%-*s\n", TMPSZ - 1,
-			       "  sl  local_address rem_address   st tx_queue "
-			       "rx_queue tr tm->when retrnsmt   uid  timeout "
-			       "inode");
-
-	pos = TMPSZ;
-
-	/* First, walk listening socket table. */
-	tcp_listen_lock();
-	for (i = 0; i < TCP_LHTABLE_SIZE; i++) {
-		struct sock *sk;
-		struct tcp_listen_opt *lopt;
-		int k;
-
-		for (sk = tcp_listening_hash[i]; sk; sk = sk->next, num++) {
-			struct open_request *req;
-			int uid;
-			struct tcp_opt *tp = tcp_sk(sk);
-
-			if (!TCP_INET_FAMILY(sk->family))
-				goto skip_listen;
-
-			pos += TMPSZ;
-			if (pos >= offset) {
-				get_tcp_sock(sk, tmpbuf, num);
-				len += sprintf(buffer + len, "%-*s\n",
-					       TMPSZ - 1, tmpbuf);
-				if (pos >= offset + length) {
-					tcp_listen_unlock();
-					goto out_no_bh;
-				}
-			}
-
-skip_listen:
-			uid = sock_i_uid(sk);
-			read_lock_bh(&tp->syn_wait_lock);
-			lopt = tp->listen_opt;
-			if (lopt && lopt->qlen) {
-				for (k = 0; k < TCP_SYNQ_HSIZE; k++) {
-					for (req = lopt->syn_table[k];
-					     req; req = req->dl_next, num++) {
-						if (!TCP_INET_FAMILY(req->class->family))
-							continue;
-
-						pos += TMPSZ;
-						if (pos <= offset)
-							continue;
-						get_openreq(sk, req, tmpbuf,
-							    num, uid);
-						len += sprintf(buffer + len,
-							       "%-*s\n",
-							       TMPSZ - 1,
-							       tmpbuf);
-						if (pos >= offset + length) {
-							read_unlock_bh(&tp->syn_wait_lock);
-							tcp_listen_unlock();
-							goto out_no_bh;
-						}
-					}
-				}
-			}
-			read_unlock_bh(&tp->syn_wait_lock);
-
-			/* Completed requests are in normal socket hash table */
-		}
+	if (v == (void *)1) {
+		seq_printf(seq, "%-*s\n", TMPSZ - 1,
+			   "  sl  local_address rem_address   st tx_queue "
+			   "rx_queue tr tm->when retrnsmt   uid  timeout "
+			   "inode");
+		goto out;
 	}
-	tcp_listen_unlock();
+	st = seq->private;
 
-	local_bh_disable();
+	switch (st->state) {
+	case TCP_SEQ_STATE_LISTENING:
+	case TCP_SEQ_STATE_ESTABLISHED:
+		get_tcp_sock(v, tmpbuf, st->num);
+		break;
+	case TCP_SEQ_STATE_OPENREQ:
+		get_openreq(st->syn_wait_sk, v, tmpbuf, st->num, st->uid);
+		break;
+	case TCP_SEQ_STATE_TIME_WAIT:
+		get_timewait_sock(v, tmpbuf, st->num);
+		break;
+	}
+	seq_printf(seq, "%-*s\n", TMPSZ - 1, tmpbuf);
+out:
+	return 0;
+}
 
-	/* Next, walk established hash chain. */
-	for (i = 0; i < tcp_ehash_size; i++) {
-		struct tcp_ehash_bucket *head = &tcp_ehash[i];
-		struct sock *sk;
-		struct tcp_tw_bucket *tw;
+static struct seq_operations tcp_seq_ops = {
+	.start  = tcp_seq_start,
+	.next   = tcp_seq_next,
+	.stop   = tcp_seq_stop,
+	.show   = tcp_seq_show,
+};
 
-		read_lock(&head->lock);
-		for (sk = head->chain; sk; sk = sk->next, num++) {
-			if (!TCP_INET_FAMILY(sk->family))
-				continue;
-			pos += TMPSZ;
-			if (pos <= offset)
-				continue;
-			get_tcp_sock(sk, tmpbuf, num);
-			len += sprintf(buffer + len, "%-*s\n",
-				       TMPSZ - 1, tmpbuf);
-			if (pos >= offset + length) {
-				read_unlock(&head->lock);
-				goto out;
-			}
-		}
-		for (tw = (struct tcp_tw_bucket *)tcp_ehash[i +
-							  tcp_ehash_size].chain;
-		     tw;
-		     tw = (struct tcp_tw_bucket *)tw->next, num++) {
-			if (!TCP_INET_FAMILY(tw->family))
-				continue;
-			pos += TMPSZ;
-			if (pos <= offset)
-				continue;
-			get_timewait_sock(tw, tmpbuf, num);
-			len += sprintf(buffer + len, "%-*s\n",
-				       TMPSZ - 1, tmpbuf);
-			if (pos >= offset + length) {
-				read_unlock(&head->lock);
-				goto out;
-			}
-		}
-		read_unlock(&head->lock);
-	}
+static int tcp_seq_open(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq;
+	int rc = -ENOMEM;
+	struct tcp_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
 
+	if (!s)
+		goto out;
+	rc = seq_open(file, &tcp_seq_ops);
+	if (rc)
+		goto out_kfree;
+	seq	     = file->private_data;
+	seq->private = s;
+	memset(s, 0, sizeof(*s));
 out:
-	local_bh_enable();
-out_no_bh:
+	return rc;
+out_kfree:
+	kfree(s);
+	goto out;
+}
+
+static struct file_operations tcp_seq_fops = {
+	.open           = tcp_seq_open,
+	.read           = seq_read,
+	.llseek         = seq_lseek,
+	.release	= ip_seq_release,
+};
 
-	begin = len - (pos - offset);
-	*start = buffer + begin;
-	len -= begin;
-	if (len > length)
-		len = length;
-	if (len < 0)
-		len = 0;
-	return len;
+int __init tcp_proc_init(void)
+{
+	int rc = 0;
+	struct proc_dir_entry *p = create_proc_entry("tcp", S_IRUGO, proc_net);
+
+	if (p)
+		p->proc_fops = &tcp_seq_fops;
+	else
+		rc = -ENOMEM;
+	return rc;
+}
+
+void __init tcp_proc_exit(void)
+{
+	remove_proc_entry("tcp", proc_net);
 }
+#endif /* CONFIG_PROC_FS */
 
 struct proto tcp_prot = {
 	.name =		"TCP",