Automatic merge of rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

8 files changed, 29 insertions, 199 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 053a883247b..eae84cc39d3 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -478,7 +478,7 @@ static int __init esp4_init(void)
 {
 	struct xfrm_decap_state decap;
 
-	if (sizeof(struct esp_decap_data)  <
+	if (sizeof(struct esp_decap_data)  >
 	    sizeof(decap.decap_data)) {
 		extern void decap_data_too_small(void);
 
diff --git a/net/ipv4/ipvs/Makefile b/net/ipv4/ipvs/Makefile
index a788461a40c..30e85de9fff 100644
--- a/net/ipv4/ipvs/Makefile
+++ b/net/ipv4/ipvs/Makefile
@@ -11,7 +11,7 @@ ip_vs_proto-objs-$(CONFIG_IP_VS_PROTO_AH) += ip_vs_proto_ah.o
 
 ip_vs-objs :=	ip_vs_conn.o ip_vs_core.o ip_vs_ctl.o ip_vs_sched.o	   \
 		ip_vs_xmit.o ip_vs_app.o ip_vs_sync.o	   		   \
-		ip_vs_est.o ip_vs_proto.o ip_vs_proto_icmp.o		   \
+		ip_vs_est.o ip_vs_proto.o 				   \
 		$(ip_vs_proto-objs-y)
 
 
diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c
index 253c46252bd..867d4e9c659 100644
--- a/net/ipv4/ipvs/ip_vs_proto.c
+++ b/net/ipv4/ipvs/ip_vs_proto.c
@@ -216,9 +216,6 @@ int ip_vs_protocol_init(void)
 #ifdef CONFIG_IP_VS_PROTO_UDP
 	REGISTER_PROTOCOL(&ip_vs_protocol_udp);
 #endif
-#ifdef CONFIG_IP_VS_PROTO_ICMP
-	REGISTER_PROTOCOL(&ip_vs_protocol_icmp);
-#endif
 #ifdef CONFIG_IP_VS_PROTO_AH
 	REGISTER_PROTOCOL(&ip_vs_protocol_ah);
 #endif
diff --git a/net/ipv4/ipvs/ip_vs_proto_icmp.c b/net/ipv4/ipvs/ip_vs_proto_icmp.c
deleted file mode 100644
index 191e94aa1c1..00000000000
--- a/net/ipv4/ipvs/ip_vs_proto_icmp.c
+++ /dev/null
@@ -1,182 +0,0 @@
-/*
- * ip_vs_proto_icmp.c:	ICMP load balancing support for IP Virtual Server
- *
- * Authors:	Julian Anastasov <ja@ssi.bg>, March 2002
- *
- *		This program is free software; you can redistribute it and/or
- *		modify it under the terms of the GNU General Public License
- *		version 2 as published by the Free Software Foundation;
- *
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/icmp.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-
-#include <net/ip_vs.h>
-
-
-static int icmp_timeouts[1] =		{ 1*60*HZ };
-
-static char * icmp_state_name_table[1] = { "ICMP" };
-
-static struct ip_vs_conn *
-icmp_conn_in_get(const struct sk_buff *skb,
-		 struct ip_vs_protocol *pp,
-		 const struct iphdr *iph,
-		 unsigned int proto_off,
-		 int inverse)
-{
-#if 0
-	struct ip_vs_conn *cp;
-
-	if (likely(!inverse)) {
-		cp = ip_vs_conn_in_get(iph->protocol,
-			iph->saddr, 0,
-			iph->daddr, 0);
-	} else {
-		cp = ip_vs_conn_in_get(iph->protocol,
-			iph->daddr, 0,
-			iph->saddr, 0);
-	}
-
-	return cp;
-
-#else
-	return NULL;
-#endif
-}
-
-static struct ip_vs_conn *
-icmp_conn_out_get(const struct sk_buff *skb,
-		  struct ip_vs_protocol *pp,
-		  const struct iphdr *iph,
-		  unsigned int proto_off,
-		  int inverse)
-{
-#if 0
-	struct ip_vs_conn *cp;
-
-	if (likely(!inverse)) {
-		cp = ip_vs_conn_out_get(iph->protocol,
-			iph->saddr, 0,
-			iph->daddr, 0);
-	} else {
-		cp = ip_vs_conn_out_get(IPPROTO_UDP,
-			iph->daddr, 0,
-			iph->saddr, 0);
-	}
-
-	return cp;
-#else
-	return NULL;
-#endif
-}
-
-static int
-icmp_conn_schedule(struct sk_buff *skb, struct ip_vs_protocol *pp,
-		   int *verdict, struct ip_vs_conn **cpp)
-{
-	*verdict = NF_ACCEPT;
-	return 0;
-}
-
-static int
-icmp_csum_check(struct sk_buff *skb, struct ip_vs_protocol *pp)
-{
-	if (!(skb->nh.iph->frag_off & __constant_htons(IP_OFFSET))) {
-		if (skb->ip_summed != CHECKSUM_UNNECESSARY) {
-			if (ip_vs_checksum_complete(skb, skb->nh.iph->ihl * 4)) {
-				IP_VS_DBG_RL_PKT(0, pp, skb, 0, "Failed checksum for");
-				return 0;
-			}
-		}
-	}
-	return 1;
-}
-
-static void
-icmp_debug_packet(struct ip_vs_protocol *pp,
-		  const struct sk_buff *skb,
-		  int offset,
-		  const char *msg)
-{
-	char buf[256];
-	struct iphdr _iph, *ih;
-
-	ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph);
-	if (ih == NULL)
-		sprintf(buf, "%s TRUNCATED", pp->name);
-	else if (ih->frag_off & __constant_htons(IP_OFFSET))
-		sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u frag",
-			pp->name, NIPQUAD(ih->saddr),
-			NIPQUAD(ih->daddr));
-	else {
-		struct icmphdr _icmph, *ic;
-
-		ic = skb_header_pointer(skb, offset + ih->ihl*4,
-					sizeof(_icmph), &_icmph);
-		if (ic == NULL)
-			sprintf(buf, "%s TRUNCATED to %u bytes\n",
-				pp->name, skb->len - offset);
-		else
-			sprintf(buf, "%s %u.%u.%u.%u->%u.%u.%u.%u T:%d C:%d",
-				pp->name, NIPQUAD(ih->saddr),
-				NIPQUAD(ih->daddr),
-				ic->type, ic->code);
-	}
-	printk(KERN_DEBUG "IPVS: %s: %s\n", msg, buf);
-}
-
-static int
-icmp_state_transition(struct ip_vs_conn *cp, int direction,
-		      const struct sk_buff *skb,
-		      struct ip_vs_protocol *pp)
-{
-	cp->timeout = pp->timeout_table[IP_VS_ICMP_S_NORMAL];
-	return 1;
-}
-
-static int
-icmp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to)
-{
-	int num;
-	char **names;
-
-	num = IP_VS_ICMP_S_LAST;
-	names = icmp_state_name_table;
-	return ip_vs_set_state_timeout(pp->timeout_table, num, names, sname, to);
-}
-
-
-static void icmp_init(struct ip_vs_protocol *pp)
-{
-	pp->timeout_table = icmp_timeouts;
-}
-
-static void icmp_exit(struct ip_vs_protocol *pp)
-{
-}
-
-struct ip_vs_protocol ip_vs_protocol_icmp = {
-	.name =			"ICMP",
-	.protocol =		IPPROTO_ICMP,
-	.dont_defrag =		0,
-	.init =			icmp_init,
-	.exit =			icmp_exit,
-	.conn_schedule =	icmp_conn_schedule,
-	.conn_in_get =		icmp_conn_in_get,
-	.conn_out_get =		icmp_conn_out_get,
-	.snat_handler =		NULL,
-	.dnat_handler =		NULL,
-	.csum_check =		icmp_csum_check,
-	.state_transition =	icmp_state_transition,
-	.register_app =		NULL,
-	.unregister_app =	NULL,
-	.app_conn_bind =	NULL,
-	.debug_packet =		icmp_debug_packet,
-	.timeout_change =	NULL,
-	.set_state_timeout =	icmp_set_state_timeout,
-};
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index e5746b67441..eda1fba431a 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -3,6 +3,7 @@
  * communicating with userspace via netlink.
  *
  * (C) 2000-2002 James Morris <jmorris@intercode.com.au>
+ * (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -17,6 +18,7 @@
  * 2005-01-10: Added /proc counter for dropped packets; fixed so
  *             packets aren't delivered to user space if they're going 
  *             to be dropped. 
+ * 2005-05-26: local_bh_{disable,enable} around nf_reinject (Harald Welte)
  *
  */
 #include <linux/module.h>
@@ -71,7 +73,15 @@ static DECLARE_MUTEX(ipqnl_sem);
 static void
 ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
 {
+	/* TCP input path (and probably other bits) assume to be called
+	 * from softirq context, not from syscall, like ipq_issue_verdict is
+	 * called.  TCP input path deadlocks with locks taken from timer
+	 * softirq, e.g.  We therefore emulate this by local_bh_disable() */
+
+	local_bh_disable();
 	nf_reinject(entry->skb, entry->info, verdict);
+	local_bh_enable();
+
 	kfree(entry);
 }
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 4a6952e3fee..7c24e64b443 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -738,7 +738,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 			unsigned long amount;
 
 			amount = 0;
-			spin_lock_irq(&sk->sk_receive_queue.lock);
+			spin_lock_bh(&sk->sk_receive_queue.lock);
 			skb = skb_peek(&sk->sk_receive_queue);
 			if (skb != NULL) {
 				/*
@@ -748,7 +748,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 				 */
 				amount = skb->len - sizeof(struct udphdr);
 			}
-			spin_unlock_irq(&sk->sk_receive_queue.lock);
+			spin_unlock_bh(&sk->sk_receive_queue.lock);
 			return put_user(amount, (int __user *)arg);
 		}
 
@@ -848,12 +848,12 @@ csum_copy_err:
 	/* Clear queue. */
 	if (flags&MSG_PEEK) {
 		int clear = 0;
-		spin_lock_irq(&sk->sk_receive_queue.lock);
+		spin_lock_bh(&sk->sk_receive_queue.lock);
 		if (skb == skb_peek(&sk->sk_receive_queue)) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			clear = 1;
 		}
-		spin_unlock_irq(&sk->sk_receive_queue.lock);
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
 		if (clear)
 			kfree_skb(skb);
 	}
@@ -1334,7 +1334,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		struct sk_buff_head *rcvq = &sk->sk_receive_queue;
 		struct sk_buff *skb;
 
-		spin_lock_irq(&rcvq->lock);
+		spin_lock_bh(&rcvq->lock);
 		while ((skb = skb_peek(rcvq)) != NULL) {
 			if (udp_checksum_complete(skb)) {
 				UDP_INC_STATS_BH(UDP_MIB_INERRORS);
@@ -1345,7 +1345,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 				break;
 			}
 		}
-		spin_unlock_irq(&rcvq->lock);
+		spin_unlock_bh(&rcvq->lock);
 
 		/* nothing to see, move along */
 		if (skb == NULL)
diff --git a/net/ipv6/ipv6_syms.c b/net/ipv6/ipv6_syms.c
index 2f4c91ddc9a..5ade5a5d199 100644
--- a/net/ipv6/ipv6_syms.c
+++ b/net/ipv6/ipv6_syms.c
@@ -37,5 +37,4 @@ EXPORT_SYMBOL(in6_dev_finish_destroy);
 EXPORT_SYMBOL(xfrm6_rcv);
 #endif
 EXPORT_SYMBOL(rt6_lookup);
-EXPORT_SYMBOL(fl6_sock_lookup);
 EXPORT_SYMBOL(ipv6_push_nfrag_opts);
diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c
index 8a3db9d95ba..d8bd2a569c7 100644
--- a/net/sched/sch_dsmark.c
+++ b/net/sched/sch_dsmark.c
@@ -18,7 +18,7 @@
 #include <asm/byteorder.h>
 
 
-#if 1 /* control */
+#if 0 /* control */
 #define DPRINTK(format,args...) printk(KERN_DEBUG format,##args)
 #else
 #define DPRINTK(format,args...)
@@ -73,8 +73,13 @@ static int dsmark_graft(struct Qdisc *sch,unsigned long arg,
 
 	DPRINTK("dsmark_graft(sch %p,[qdisc %p],new %p,old %p)\n",sch,p,new,
 	    old);
-	if (!new)
-		new = &noop_qdisc;
+
+	if (new == NULL) {
+		new = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops);
+		if (new == NULL)
+			new = &noop_qdisc;
+	}
+
 	sch_tree_lock(sch);
 	*old = xchg(&p->q,new);
 	if (*old)
@@ -163,14 +168,15 @@ static void dsmark_walk(struct Qdisc *sch,struct qdisc_walker *walker)
 		return;
 	for (i = 0; i < p->indices; i++) {
 		if (p->mask[i] == 0xff && !p->value[i])
-			continue;
+			goto ignore;
 		if (walker->count >= walker->skip) {
 			if (walker->fn(sch, i+1, walker) < 0) {
 				walker->stop = 1;
 				break;
 			}
 		}
-                walker->count++;
+ignore:		
+		walker->count++;
         }
 }