From 4dc6d9cc38cea1004a7f827cf76409ae42231fee Mon Sep 17 00:00:00 2001
From: Peter Chubb <peterc@gelato.unsw.edu.au>
Date: Thu, 23 Mar 2006 21:39:47 -0800
Subject: [BRIDGE]: Unaligned accesses in the ethernet bridge

I see lots of
	kernel unaligned access to 0xa0000001009dbb6f, ip=0xa000000100811591
	kernel unaligned access to 0xa0000001009dbb6b, ip=0xa0000001008115c1
	kernel unaligned access to 0xa0000001009dbb6d, ip=0xa0000001008115f1
messages in my logs on IA64 when using the ethernet bridge with 2.6.16.

Appended is a patch to fix them.

Signed-off-by: Peter Chubb <peterc@gelato.unsw.edu.au>
Signed-off-by: Stephen Hemminger <shemminger@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_stp_bpdu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 8934a54792be..a7ba0cce0b46 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -19,6 +19,7 @@
 #include <linux/llc.h>
 #include <net/llc.h>
 #include <net/llc_pdu.h>
+#include <asm/unaligned.h>
 
 #include "br_private.h"
 #include "br_private_stp.h"
@@ -59,12 +60,12 @@ static inline void br_set_ticks(unsigned char *dest, int j)
 {
 	unsigned long ticks = (STP_HZ * j)/ HZ;
 
-	*((__be16 *) dest) = htons(ticks);
+	put_unaligned(htons(ticks), (__be16 *)dest);
 }
 
 static inline int br_get_ticks(const unsigned char *src)
 {
-	unsigned long ticks = ntohs(*(__be16 *)src);
+	unsigned long ticks = ntohs(get_unaligned((__be16 *)src));
 
 	return (ticks * HZ + STP_HZ - 1) / STP_HZ;
 }
-- 
cgit v1.2.2


From a1a8feed1743ec8d2af1dafa7c5321679f0a3e4f Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Thu, 23 Mar 2006 22:07:34 -0800
Subject: [MODULES]: Don't allow statically declared exports

Add an extern declaration for exported symbols to make the compiler warn
on symbols declared statically.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/module.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/module.h b/include/linux/module.h
index 70bd843c71cb..d9569151c182 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -183,6 +183,7 @@ void *__symbol_get_gpl(const char *symbol);
 
 /* For every exported symbol, place a struct in the __ksymtab section */
 #define __EXPORT_SYMBOL(sym, sec)				\
+	extern typeof(sym) sym;					\
 	__CRC_SYMBOL(sym, sec)					\
 	static const char __kstrtab_##sym[]			\
 	__attribute__((section("__ksymtab_strings")))		\
-- 
cgit v1.2.2


From f67ed26f2b3e92c0450deae3ffc3fff21c878a75 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Thu, 23 Mar 2006 22:47:40 -0800
Subject: [NET]: Ensure device name passed to SO_BINDTODEVICE is NULL
 terminated.

Found by Solar Designer.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 1a7e6eac90b0..e110b9004147 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -404,8 +404,9 @@ set_rcvbuf:
 			if (!valbool) {
 				sk->sk_bound_dev_if = 0;
 			} else {
-				if (optlen > IFNAMSIZ) 
-					optlen = IFNAMSIZ; 
+				if (optlen > IFNAMSIZ - 1)
+					optlen = IFNAMSIZ - 1;
+				memset(devname, 0, sizeof(devname));
 				if (copy_from_user(devname, optval, optlen)) {
 					ret = -EFAULT;
 					break;
-- 
cgit v1.2.2


From 9932cf954691f20d548cd6010d89d1d48597e104 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@sunset.davemloft.net>
Date: Fri, 24 Mar 2006 15:12:37 -0800
Subject: [NET]: Fill in a 32-bit hole in struct sock on 64-bit platforms.

This makes struct sock 8 bytes smaller on 64-bit.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index ec226f31dc2a..2aa73c0ec6c2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -210,6 +210,7 @@ struct sock {
 	gfp_t			sk_allocation;
 	int			sk_sndbuf;
 	int			sk_route_caps;
+	int			sk_rcvlowat;
 	unsigned long 		sk_flags;
 	unsigned long	        sk_lingertime;
 	/*
@@ -230,7 +231,6 @@ struct sock {
 	unsigned short		sk_max_ack_backlog;
 	__u32			sk_priority;
 	struct ucred		sk_peercred;
-	int			sk_rcvlowat;
 	long			sk_rcvtimeo;
 	long			sk_sndtimeo;
 	struct sk_filter      	*sk_filter;
-- 
cgit v1.2.2


From 868d2c1efe9cdd259b67a80d60a7fb2fcecd3d68 Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Fri, 24 Mar 2006 15:47:25 -0800
Subject: [WIRELESS]: Fix config dependencies.

I accidentally ended up with a config that set NET_RADIO off,
and NET_WIRELESS_RTNETLINK on, which blew up thus..

net/built-in.o: In function `do_setlink':net/core/rtnetlink.c:479: undefined reference to `wireless_rtnetlink_set'
net/built-in.o: In function `do_getlink':net/core/rtnetlink.c:521: undefined reference to `wireless_rtnetlink_get'

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wireless/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/Kconfig b/drivers/net/wireless/Kconfig
index 6a1033ec06cf..fd17aa8491b6 100644
--- a/drivers/net/wireless/Kconfig
+++ b/drivers/net/wireless/Kconfig
@@ -27,6 +27,7 @@ config NET_RADIO
 
 config NET_WIRELESS_RTNETLINK
 	bool "Wireless Extension API over RtNetlink"
+	depends on NET_RADIO
 	---help---
 	  Support the Wireless Extension API over the RtNetlink socket
 	  in addition to the traditional ioctl interface (selected above).
-- 
cgit v1.2.2


From 9f514950bb907e98f280492a091aa1889b97304e Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 25 Mar 2006 01:24:25 -0800
Subject: [NET]: Take RTNL when unregistering notifier

The netdev notifier call chain is currently unregistered without taking
any locks outside the notifier system.  Because the notifier system itself
does not synchronise unregistration with respect to the calling of the
chain, we as its user need to do our own locking.

We are supposed to take the RTNL for all calls to netdev notifiers, so
taking the RTNL should be sufficient to protect it.

The registration path in dev.c already takes the RTNL so it's OK.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 08dec6eb922b..e0489ca731c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -977,7 +977,12 @@ int register_netdevice_notifier(struct notifier_block *nb)
 
 int unregister_netdevice_notifier(struct notifier_block *nb)
 {
-	return notifier_chain_unregister(&netdev_chain, nb);
+	int err;
+
+	rtnl_lock();
+	err = notifier_chain_unregister(&netdev_chain, nb);
+	rtnl_unlock();
+	return err;
 }
 
 /**
-- 
cgit v1.2.2


From 2babf9daae4a3561f3264638a22ac7d0b14a6f52 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 25 Mar 2006 01:25:29 -0800
Subject: [SCTP]: Fix up sctp_rcv return value

I was working on the ipip/xfrm problem and as usual I get side-tracked by
other problems.

As part of an attempt to change the IPv4 protocol handler calling
convention I found that SCTP violated the existing convention.

It's returning non-zero values after freeing the skb.  This is doubly bad
as 1) the skb gets resubmitted; 2) the return value is interpreted as a
protocol number.

This patch changes those return values to zero.

IPv6 doesn't suffer from this problem because it uses a positive return
value as an indication for resubmission.  So the only effect of this patch
there is to increment the IPSTATS_MIB_INDELIVERS counter which IMHO is
the right thing to do.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/input.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/sctp/input.c b/net/sctp/input.c
index cb78b50868ee..d117ebc75cf8 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -127,7 +127,6 @@ int sctp_rcv(struct sk_buff *skb)
 	union sctp_addr dest;
 	int family;
 	struct sctp_af *af;
-	int ret = 0;
 
 	if (skb->pkt_type!=PACKET_HOST)
 		goto discard_it;
@@ -227,16 +226,13 @@ int sctp_rcv(struct sk_buff *skb)
 		goto discard_release;
 	nf_reset(skb);
 
-	ret = sk_filter(sk, skb, 1);
-	if (ret)
+	if (sk_filter(sk, skb, 1))
                 goto discard_release;
 
 	/* Create an SCTP packet structure. */
 	chunk = sctp_chunkify(skb, asoc, sk);
-	if (!chunk) {
-		ret = -ENOMEM;
+	if (!chunk)
 		goto discard_release;
-	}
 	SCTP_INPUT_CB(skb)->chunk = chunk;
 
 	/* Remember what endpoint is to handle this packet. */
@@ -277,11 +273,11 @@ int sctp_rcv(struct sk_buff *skb)
 	sctp_bh_unlock_sock(sk);
 	sock_put(sk);
 
-	return ret;
+	return 0;
 
 discard_it:
 	kfree_skb(skb);
-	return ret;
+	return 0;
 
 discard_release:
 	/* Release any structures we may be holding. */
-- 
cgit v1.2.2


From 7b4f4b5ebceab67ce440a61081a69f0265e17c2a Mon Sep 17 00:00:00 2001
From: John Heffner <jheffner@psc.edu>
Date: Sat, 25 Mar 2006 01:34:07 -0800
Subject: [TCP]: Set default max buffers from memory pool size

This patch sets the maximum TCP buffer sizes (available to automatic
buffer tuning, not to setsockopt) based on the TCP memory pool size.
The maximum sndbuf and rcvbuf each will be up to 4 MB, but no more
than 1/128 of the memory pressure threshold.

Signed-off-by: John Heffner <jheffner@psc.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4b0272c92d66..591e96dffc28 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -276,8 +276,8 @@ atomic_t tcp_orphan_count = ATOMIC_INIT(0);
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
 int sysctl_tcp_mem[3];
-int sysctl_tcp_wmem[3] = { 4 * 1024, 16 * 1024, 128 * 1024 };
-int sysctl_tcp_rmem[3] = { 4 * 1024, 87380, 87380 * 2 };
+int sysctl_tcp_wmem[3];
+int sysctl_tcp_rmem[3];
 
 EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
@@ -2081,7 +2081,8 @@ __setup("thash_entries=", set_thash_entries);
 void __init tcp_init(void)
 {
 	struct sk_buff *skb = NULL;
-	int order, i;
+	unsigned long limit;
+	int order, i, max_share;
 
 	if (sizeof(struct tcp_skb_cb) > sizeof(skb->cb))
 		__skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb),
@@ -2155,12 +2156,16 @@ void __init tcp_init(void)
 	sysctl_tcp_mem[1] = 1024 << order;
 	sysctl_tcp_mem[2] = 1536 << order;
 
-	if (order < 3) {
-		sysctl_tcp_wmem[2] = 64 * 1024;
-		sysctl_tcp_rmem[0] = PAGE_SIZE;
-		sysctl_tcp_rmem[1] = 43689;
-		sysctl_tcp_rmem[2] = 2 * 43689;
-	}
+	limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
+	max_share = min(4UL*1024*1024, limit);
+
+	sysctl_tcp_wmem[0] = SK_STREAM_MEM_QUANTUM;
+	sysctl_tcp_wmem[1] = 16*1024;
+	sysctl_tcp_wmem[2] = max(64*1024, max_share);
+
+	sysctl_tcp_rmem[0] = SK_STREAM_MEM_QUANTUM;
+	sysctl_tcp_rmem[1] = 87380;
+	sysctl_tcp_rmem[2] = max(87380, max_share);
 
 	printk(KERN_INFO "TCP: Hash tables configured "
 	       "(established %d bind %d)\n",
-- 
cgit v1.2.2


From b8059eadf9f4dc24bd72da71daa832a9a9899fb4 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@sunset.davemloft.net>
Date: Sat, 25 Mar 2006 01:36:56 -0800
Subject: [TCP]: Mark tcp_*mem[] __read_mostly.

Suggested by Stephen Hemminger.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 591e96dffc28..8f5042bd8252 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -257,6 +257,7 @@
 #include <linux/fs.h>
 #include <linux/random.h>
 #include <linux/bootmem.h>
+#include <linux/cache.h>
 
 #include <net/icmp.h>
 #include <net/tcp.h>
@@ -275,9 +276,9 @@ atomic_t tcp_orphan_count = ATOMIC_INIT(0);
 
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
-int sysctl_tcp_mem[3];
-int sysctl_tcp_wmem[3];
-int sysctl_tcp_rmem[3];
+int sysctl_tcp_mem[3] __read_mostly;
+int sysctl_tcp_wmem[3] __read_mostly;
+int sysctl_tcp_rmem[3] __read_mostly;
 
 EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
-- 
cgit v1.2.2


From cef2685e0053945ea0f3c02297386b040f486ea7 Mon Sep 17 00:00:00 2001
From: Ilia Sotnikov <hostcc@gmail.com>
Date: Sat, 25 Mar 2006 01:38:55 -0800
Subject: [IPV4]: Aggregate route entries with different TOS values

When we get an ICMP need-to-frag message, the original TOS value in the
ICMP payload cannot be used as a key to look up the routes to update.
This is because the TOS field may have been modified by routers on the
way.  Similarly, ip_rt_redirect should also ignore the TOS as the router
that gave us the message may have modified the TOS value.

The patch achieves this objective by aggregating entries with different
TOS values (but are otherwise identical) into the same bucket.  This
makes it easy to update them at the same time when an ICMP message is
received.

In future we should use a twin-hashing scheme where teh aggregation
occurs at the entry level.  That is, the TOS goes back into the hash
for normal lookups while ICMP lookups will end up with a node that
gives us a list that contains all other route entries that differ
only by TOS.

Signed-off-by: Ilia Sotnikov <hostcc@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/route.h |  2 +-
 net/ipv4/icmp.c     |  2 +-
 net/ipv4/route.c    | 45 ++++++++++++++++++---------------------------
 3 files changed, 20 insertions(+), 29 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index 9c04f15090d2..98c915abdec8 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -110,7 +110,7 @@ extern struct ip_rt_acct *ip_rt_acct;
 struct in_device;
 extern int		ip_rt_init(void);
 extern void		ip_rt_redirect(u32 old_gw, u32 dst, u32 new_gw,
-				       u32 src, u8 tos, struct net_device *dev);
+				       u32 src, struct net_device *dev);
 extern void		ip_rt_advice(struct rtable **rp, int advice);
 extern void		rt_cache_flush(int how);
 extern int		__ip_route_output_key(struct rtable **, const struct flowi *flp);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e7bbff4340bb..9831fd2c73a0 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -753,7 +753,7 @@ static void icmp_redirect(struct sk_buff *skb)
 	case ICMP_REDIR_HOST:
 	case ICMP_REDIR_HOSTTOS:
 		ip_rt_redirect(skb->nh.iph->saddr, ip, skb->h.icmph->un.gateway,
-			       iph->saddr, iph->tos, skb->dev);
+			       iph->saddr, skb->dev);
 		break;
   	}
 out:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fca5fe0cf94a..94fcbc5e5a1b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -55,6 +55,8 @@
  *	Robert Olsson		:	Added rt_cache statistics
  *	Arnaldo C. Melo		:	Convert proc stuff to seq_file
  *	Eric Dumazet		:	hashed spinlocks and rt_check_expire() fixes.
+ * 	Ilia Sotnikov		:	Ignore TOS on PMTUD and Redirect
+ * 	Ilia Sotnikov		:	Removed TOS from hash calculations
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
@@ -247,9 +249,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
 static int rt_intern_hash(unsigned hash, struct rtable *rth,
 				struct rtable **res);
 
-static unsigned int rt_hash_code(u32 daddr, u32 saddr, u8 tos)
+static unsigned int rt_hash_code(u32 daddr, u32 saddr)
 {
-	return (jhash_3words(daddr, saddr, (u32) tos, rt_hash_rnd)
+	return (jhash_2words(daddr, saddr, rt_hash_rnd)
 		& rt_hash_mask);
 }
 
@@ -1111,7 +1113,7 @@ static void rt_del(unsigned hash, struct rtable *rt)
 }
 
 void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
-		    u32 saddr, u8 tos, struct net_device *dev)
+		    u32 saddr, struct net_device *dev)
 {
 	int i, k;
 	struct in_device *in_dev = in_dev_get(dev);
@@ -1119,8 +1121,6 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
 	u32  skeys[2] = { saddr, 0 };
 	int  ikeys[2] = { dev->ifindex, 0 };
 
-	tos &= IPTOS_RT_MASK;
-
 	if (!in_dev)
 		return;
 
@@ -1141,8 +1141,7 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
 	for (i = 0; i < 2; i++) {
 		for (k = 0; k < 2; k++) {
 			unsigned hash = rt_hash_code(daddr,
-						     skeys[i] ^ (ikeys[k] << 5),
-						     tos);
+						     skeys[i] ^ (ikeys[k] << 5));
 
 			rthp=&rt_hash_table[hash].chain;
 
@@ -1152,7 +1151,6 @@ void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
 
 				if (rth->fl.fl4_dst != daddr ||
 				    rth->fl.fl4_src != skeys[i] ||
-				    rth->fl.fl4_tos != tos ||
 				    rth->fl.oif != ikeys[k] ||
 				    rth->fl.iif != 0) {
 					rthp = &rth->u.rt_next;
@@ -1232,10 +1230,9 @@ reject_redirect:
 	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
 		printk(KERN_INFO "Redirect from %u.%u.%u.%u on %s about "
 			"%u.%u.%u.%u ignored.\n"
-			"  Advised path = %u.%u.%u.%u -> %u.%u.%u.%u, "
-			"tos %02x\n",
+			"  Advised path = %u.%u.%u.%u -> %u.%u.%u.%u\n",
 		       NIPQUAD(old_gw), dev->name, NIPQUAD(new_gw),
-		       NIPQUAD(saddr), NIPQUAD(daddr), tos);
+		       NIPQUAD(saddr), NIPQUAD(daddr));
 #endif
 	in_dev_put(in_dev);
 }
@@ -1253,8 +1250,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
 			   rt->u.dst.expires) {
 			unsigned hash = rt_hash_code(rt->fl.fl4_dst,
 						     rt->fl.fl4_src ^
-							(rt->fl.oif << 5),
-						     rt->fl.fl4_tos);
+							(rt->fl.oif << 5));
 #if RT_CACHE_DEBUG >= 1
 			printk(KERN_DEBUG "ip_rt_advice: redirect to "
 					  "%u.%u.%u.%u/%02x dropped\n",
@@ -1391,14 +1387,13 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
 	struct rtable *rth;
 	u32  skeys[2] = { iph->saddr, 0, };
 	u32  daddr = iph->daddr;
-	u8   tos = iph->tos & IPTOS_RT_MASK;
 	unsigned short est_mtu = 0;
 
 	if (ipv4_config.no_pmtu_disc)
 		return 0;
 
 	for (i = 0; i < 2; i++) {
-		unsigned hash = rt_hash_code(daddr, skeys[i], tos);
+		unsigned hash = rt_hash_code(daddr, skeys[i]);
 
 		rcu_read_lock();
 		for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
@@ -1407,7 +1402,6 @@ unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
 			    rth->fl.fl4_src == skeys[i] &&
 			    rth->rt_dst  == daddr &&
 			    rth->rt_src  == iph->saddr &&
-			    rth->fl.fl4_tos == tos &&
 			    rth->fl.iif == 0 &&
 			    !(dst_metric_locked(&rth->u.dst, RTAX_MTU))) {
 				unsigned short mtu = new_mtu;
@@ -1658,7 +1652,7 @@ static int ip_route_input_mc(struct sk_buff *skb, u32 daddr, u32 saddr,
 	RT_CACHE_STAT_INC(in_slow_mc);
 
 	in_dev_put(in_dev);
-	hash = rt_hash_code(daddr, saddr ^ (dev->ifindex << 5), tos);
+	hash = rt_hash_code(daddr, saddr ^ (dev->ifindex << 5));
 	return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst);
 
 e_nobufs:
@@ -1823,7 +1817,7 @@ static inline int ip_mkroute_input_def(struct sk_buff *skb,
 		return err;
 
 	/* put it into the cache */
-	hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5), tos);
+	hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5));
 	return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);	
 }
 
@@ -1864,7 +1858,7 @@ static inline int ip_mkroute_input(struct sk_buff *skb,
 			return err;
 
 		/* put it into the cache */
-		hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5), tos);
+		hash = rt_hash_code(daddr, saddr ^ (fl->iif << 5));
 		err = rt_intern_hash(hash, rth, &rtres);
 		if (err)
 			return err;
@@ -2041,7 +2035,7 @@ local_input:
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
 	rth->rt_type	= res.type;
-	hash = rt_hash_code(daddr, saddr ^ (fl.iif << 5), tos);
+	hash = rt_hash_code(daddr, saddr ^ (fl.iif << 5));
 	err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
 	goto done;
 
@@ -2088,7 +2082,7 @@ int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr,
 	int iif = dev->ifindex;
 
 	tos &= IPTOS_RT_MASK;
-	hash = rt_hash_code(daddr, saddr ^ (iif << 5), tos);
+	hash = rt_hash_code(daddr, saddr ^ (iif << 5));
 
 	rcu_read_lock();
 	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
@@ -2286,10 +2280,8 @@ static inline int ip_mkroute_output_def(struct rtable **rp,
 	int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
 	unsigned hash;
 	if (err == 0) {
-		u32 tos = RT_FL_TOS(oldflp);
-
 		hash = rt_hash_code(oldflp->fl4_dst, 
-				    oldflp->fl4_src ^ (oldflp->oif << 5), tos);
+				    oldflp->fl4_src ^ (oldflp->oif << 5));
 		err = rt_intern_hash(hash, rth, rp);
 	}
 	
@@ -2304,7 +2296,6 @@ static inline int ip_mkroute_output(struct rtable** rp,
 				    unsigned flags)
 {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
-	u32 tos = RT_FL_TOS(oldflp);
 	unsigned char hop;
 	unsigned hash;
 	int err = -EINVAL;
@@ -2334,7 +2325,7 @@ static inline int ip_mkroute_output(struct rtable** rp,
 
 			hash = rt_hash_code(oldflp->fl4_dst, 
 					    oldflp->fl4_src ^
-					    (oldflp->oif << 5), tos);
+					    (oldflp->oif << 5));
 			err = rt_intern_hash(hash, rth, rp);
 
 			/* forward hop information to multipath impl. */
@@ -2563,7 +2554,7 @@ int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
 	unsigned hash;
 	struct rtable *rth;
 
-	hash = rt_hash_code(flp->fl4_dst, flp->fl4_src ^ (flp->oif << 5), flp->fl4_tos);
+	hash = rt_hash_code(flp->fl4_dst, flp->fl4_src ^ (flp->oif << 5));
 
 	rcu_read_lock_bh();
 	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
-- 
cgit v1.2.2


From 9e19bb6d7a0959f5028d46e1ab99c50f0d36eda8 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sat, 25 Mar 2006 01:41:10 -0800
Subject: [NETFILTER] x_table.c: sem2mutex

Semaphore to mutex conversion.

The conversion was generated via scripts, and the result was validated
automatically via a script as well.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/netfilter/x_tables.c | 56 +++++++++++++++++++++++++-----------------------
 1 file changed, 29 insertions(+), 27 deletions(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 0a29a24d9a72..a657ab5394c3 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -21,10 +21,12 @@
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
+#include <linux/mutex.h>
 
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_arp.h>
 
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
 MODULE_DESCRIPTION("[ip,ip6,arp]_tables backend module");
@@ -32,7 +34,7 @@ MODULE_DESCRIPTION("[ip,ip6,arp]_tables backend module");
 #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))
 
 struct xt_af {
-	struct semaphore mutex;
+	struct mutex mutex;
 	struct list_head match;
 	struct list_head target;
 	struct list_head tables;
@@ -64,11 +66,11 @@ xt_register_target(struct xt_target *target)
 {
 	int ret, af = target->family;
 
-	ret = down_interruptible(&xt[af].mutex);
+	ret = mutex_lock_interruptible(&xt[af].mutex);
 	if (ret != 0)
 		return ret;
 	list_add(&target->list, &xt[af].target);
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 	return ret;
 }
 EXPORT_SYMBOL(xt_register_target);
@@ -78,9 +80,9 @@ xt_unregister_target(struct xt_target *target)
 {
 	int af = target->family;
 
-	down(&xt[af].mutex);
+	mutex_lock(&xt[af].mutex);
 	LIST_DELETE(&xt[af].target, target);
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 }
 EXPORT_SYMBOL(xt_unregister_target);
 
@@ -89,12 +91,12 @@ xt_register_match(struct xt_match *match)
 {
 	int ret, af = match->family;
 
-	ret = down_interruptible(&xt[af].mutex);
+	ret = mutex_lock_interruptible(&xt[af].mutex);
 	if (ret != 0)
 		return ret;
 
 	list_add(&match->list, &xt[af].match);
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 
 	return ret;
 }
@@ -105,9 +107,9 @@ xt_unregister_match(struct xt_match *match)
 {
 	int af =  match->family;
 
-	down(&xt[af].mutex);
+	mutex_lock(&xt[af].mutex);
 	LIST_DELETE(&xt[af].match, match);
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 }
 EXPORT_SYMBOL(xt_unregister_match);
 
@@ -124,21 +126,21 @@ struct xt_match *xt_find_match(int af, const char *name, u8 revision)
 	struct xt_match *m;
 	int err = 0;
 
-	if (down_interruptible(&xt[af].mutex) != 0)
+	if (mutex_lock_interruptible(&xt[af].mutex) != 0)
 		return ERR_PTR(-EINTR);
 
 	list_for_each_entry(m, &xt[af].match, list) {
 		if (strcmp(m->name, name) == 0) {
 			if (m->revision == revision) {
 				if (try_module_get(m->me)) {
-					up(&xt[af].mutex);
+					mutex_unlock(&xt[af].mutex);
 					return m;
 				}
 			} else
 				err = -EPROTOTYPE; /* Found something. */
 		}
 	}
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(xt_find_match);
@@ -149,21 +151,21 @@ struct xt_target *xt_find_target(int af, const char *name, u8 revision)
 	struct xt_target *t;
 	int err = 0;
 
-	if (down_interruptible(&xt[af].mutex) != 0)
+	if (mutex_lock_interruptible(&xt[af].mutex) != 0)
 		return ERR_PTR(-EINTR);
 
 	list_for_each_entry(t, &xt[af].target, list) {
 		if (strcmp(t->name, name) == 0) {
 			if (t->revision == revision) {
 				if (try_module_get(t->me)) {
-					up(&xt[af].mutex);
+					mutex_unlock(&xt[af].mutex);
 					return t;
 				}
 			} else
 				err = -EPROTOTYPE; /* Found something. */
 		}
 	}
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(xt_find_target);
@@ -218,7 +220,7 @@ int xt_find_revision(int af, const char *name, u8 revision, int target,
 {
 	int have_rev, best = -1;
 
-	if (down_interruptible(&xt[af].mutex) != 0) {
+	if (mutex_lock_interruptible(&xt[af].mutex) != 0) {
 		*err = -EINTR;
 		return 1;
 	}
@@ -226,7 +228,7 @@ int xt_find_revision(int af, const char *name, u8 revision, int target,
 		have_rev = target_revfn(af, name, revision, &best);
 	else
 		have_rev = match_revfn(af, name, revision, &best);
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 
 	/* Nothing at all?  Return 0 to try loading module. */
 	if (best == -1) {
@@ -352,20 +354,20 @@ struct xt_table *xt_find_table_lock(int af, const char *name)
 {
 	struct xt_table *t;
 
-	if (down_interruptible(&xt[af].mutex) != 0)
+	if (mutex_lock_interruptible(&xt[af].mutex) != 0)
 		return ERR_PTR(-EINTR);
 
 	list_for_each_entry(t, &xt[af].tables, list)
 		if (strcmp(t->name, name) == 0 && try_module_get(t->me))
 			return t;
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(xt_find_table_lock);
 
 void xt_table_unlock(struct xt_table *table)
 {
-	up(&xt[table->af].mutex);
+	mutex_unlock(&xt[table->af].mutex);
 }
 EXPORT_SYMBOL_GPL(xt_table_unlock);
 
@@ -405,7 +407,7 @@ int xt_register_table(struct xt_table *table,
 	int ret;
 	struct xt_table_info *private;
 
-	ret = down_interruptible(&xt[table->af].mutex);
+	ret = mutex_lock_interruptible(&xt[table->af].mutex);
 	if (ret != 0)
 		return ret;
 
@@ -431,7 +433,7 @@ int xt_register_table(struct xt_table *table,
 
 	ret = 0;
  unlock:
-	up(&xt[table->af].mutex);
+	mutex_unlock(&xt[table->af].mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(xt_register_table);
@@ -440,10 +442,10 @@ void *xt_unregister_table(struct xt_table *table)
 {
 	struct xt_table_info *private;
 
-	down(&xt[table->af].mutex);
+	mutex_lock(&xt[table->af].mutex);
 	private = table->private;
 	LIST_DELETE(&xt[table->af].tables, table);
-	up(&xt[table->af].mutex);
+	mutex_unlock(&xt[table->af].mutex);
 
 	return private;
 }
@@ -507,7 +509,7 @@ static void *xt_tgt_seq_start(struct seq_file *seq, loff_t *pos)
 	if (!list)
 		return NULL;
 
-	if (down_interruptible(&xt[af].mutex) != 0)
+	if (mutex_lock_interruptible(&xt[af].mutex) != 0)
 		return NULL;
 	
 	return xt_get_idx(list, seq, *pos);
@@ -536,7 +538,7 @@ static void xt_tgt_seq_stop(struct seq_file *seq, void *v)
 	struct proc_dir_entry *pde = seq->private;
 	u_int16_t af = (unsigned long)pde->data & 0xffff;
 
-	up(&xt[af].mutex);
+	mutex_unlock(&xt[af].mutex);
 }
 
 static int xt_name_seq_show(struct seq_file *seq, void *v)
@@ -668,7 +670,7 @@ static int __init xt_init(void)
 		return -ENOMEM;
 
 	for (i = 0; i < NPROTO; i++) {
-		init_MUTEX(&xt[i].mutex);
+		mutex_init(&xt[i].mutex);
 		INIT_LIST_HEAD(&xt[i].target);
 		INIT_LIST_HEAD(&xt[i].match);
 		INIT_LIST_HEAD(&xt[i].tables);
-- 
cgit v1.2.2