Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

* master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6:
  [TCP]: Fix minisock tcp_create_openreq_child() typo.
  [TCP]: Document several sysctls.
  [NET]: Fix kfree(skb)
  [NET]: Handle disabled preemption in gfp_any()
  [BRIDGE]: Fix locking of set path cost.
  [IPV6]: /proc/net/anycast6 unbalanced inet6_dev refcnt
  [IPX]: Remove ancient changelog
  [IPX]: Remove outdated information from Kconfig
  [NET]: Revert socket.h/stat.h ifdef hacks.
  [IPV6]: anycast refcnt fix
  [XFRM] xfrm_user: Fix return values of xfrm_add_sa_expire.

15 files changed, 43 insertions, 121 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a0f6842368c..d3aae1f9b4c 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -147,6 +147,11 @@ tcp_available_congestion_control - STRING
 	More congestion control algorithms may be available as modules,
 	but not loaded.
 
+tcp_base_mss - INTEGER
+	The initial value of search_low to be used by Packetization Layer
+	Path MTU Discovery (MTU probing).  If MTU probing is enabled,
+	this is the inital MSS used by the connection.
+
 tcp_congestion_control - STRING
 	Set the congestion control algorithm to be used for new
 	connections. The algorithm "reno" is always available, but
@@ -243,6 +248,27 @@ tcp_mem - vector of 3 INTEGERs: min, pressure, max
 	Defaults are calculated at boot time from amount of available
 	memory.
 
+tcp_moderate_rcvbuf - BOOLEAN
+	If set, TCP performs receive buffer autotuning, attempting to
+	automatically size the buffer (no greater than tcp_rmem[2]) to
+	match the size required by the path for full throughput.  Enabled by
+	default.
+
+tcp_mtu_probing - INTEGER
+	Controls TCP Packetization-Layer Path MTU Discovery.  Takes three
+	values:
+	  0 - Disabled
+	  1 - Disabled by default, enabled when an ICMP black hole detected
+	  2 - Always enabled, use initial MSS of tcp_base_mss.
+
+tcp_no_metrics_save - BOOLEAN
+	By default, TCP saves various connection metrics in the route cache
+	when the connection closes, so that connections established in the
+	near future can use these to set initial conditions.  Usually, this
+	increases overall performance, but may sometimes cause performance
+	degredation.  If set, TCP will not cache metrics on closing
+	connections.
+
 tcp_orphan_retries - INTEGER
 	How may times to retry before killing TCP connection, closed
 	by our side. Default value 7 corresponds to ~50sec-16min
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 28157a36e6c..fcd35a210e7 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -16,7 +16,7 @@ struct __kernel_sockaddr_storage {
 				/* _SS_MAXSIZE value minus size of ss_family */
 } __attribute__ ((aligned(_K_SS_ALIGNSIZE)));	/* force desired alignment */
 
-#ifdef __KERNEL__
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
 
 #include <asm/socket.h>			/* arch-dependent defines	*/
 #include <linux/sockios.h>		/* the SIOCxxx I/O controls	*/
diff --git a/include/linux/stat.h b/include/linux/stat.h
index 4f8539ccff6..679ef0d70b6 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -7,7 +7,7 @@
 
 #endif
 
-#ifdef __KERNEL__
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
 
 #define S_IFMT  00170000
 #define S_IFSOCK 0140000
diff --git a/include/net/sock.h b/include/net/sock.h
index 03684e702d1..2c7d60ca354 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1278,7 +1278,7 @@ static inline int sock_writeable(const struct sock *sk)
 
 static inline gfp_t gfp_any(void)
 {
-	return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
+	return in_atomic() ? GFP_ATOMIC : GFP_KERNEL;
 }
 
 static inline long sock_rcvtimeo(const struct sock *sk, int noblock)
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 3ab153d3c50..147015fe5c7 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -291,12 +291,11 @@ static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		if (!capable(CAP_NET_ADMIN))
 			return -EPERM;
 
-		spin_lock_bh(&br->lock);
 		if ((p = br_get_port(br, args[1])) == NULL)
 			ret = -EINVAL;
 		else
 			br_stp_set_path_cost(p, args[2]);
-		spin_unlock_bh(&br->lock);
+
 		return ret;
 	}
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f89ff151cfa..820761f9eee 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2037,7 +2037,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 err:
 	while ((skb = segs)) {
 		segs = skb->next;
-		kfree(skb);
+		kfree_skb(skb);
 	}
 	return ERR_PTR(err);
 }
diff --git a/net/dccp/output.c b/net/dccp/output.c
index f5c6aca1dfa..3282f2f2291 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -269,7 +269,7 @@ void dccp_write_xmit(struct sock *sk, int block)
 					 err);
 		} else {
 			dccp_pr_debug("packet discarded\n");
-			kfree(skb);
+			kfree_skb(skb);
 		}
 	}
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 30b1e520ad9..6b5c64f3c92 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -381,7 +381,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 	if (newsk != NULL) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
 		struct tcp_request_sock *treq = tcp_rsk(req);
-		struct inet_connection_sock *newicsk = inet_csk(sk);
+		struct inet_connection_sock *newicsk = inet_csk(newsk);
 		struct tcp_sock *newtp;
 
 		/* Now setup tcp_sock */
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f6ac65d3655..e16f1bba5df 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -400,6 +400,8 @@ static void dev_forward_change(struct inet6_dev *idev)
 			ipv6_dev_mc_dec(dev, &addr);
 	}
 	for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) {
+		if (ifa->flags&IFA_F_TENTATIVE)
+			continue;
 		if (idev->cnf.forwarding)
 			addrconf_join_anycast(ifa);
 		else
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index e5ef5979ade..09117d63256 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -461,6 +461,7 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
 			break;
 		}
 		read_unlock_bh(&idev->lock);
+		in6_dev_put(idev);
 	}
 	return im;
 }
diff --git a/net/ipx/ChangeLog b/net/ipx/ChangeLog
deleted file mode 100644
index 3b29763751a..00000000000
--- a/net/ipx/ChangeLog
+++ /dev/null
@@ -1,101 +0,0 @@
- Revision 0.21:	Uses the new generic socket option code.
-
- Revision 0.22:	Gcc clean ups and drop out device registration. Use the
- 		new multi-protocol edition of hard_header
-
- Revision 0.23: IPX /proc by Mark Evans. Adding a route will
- 		will overwrite any existing route to the same network.
-
- Revision 0.24:	Supports new /proc with no 4K limit
-
- Revision 0.25:	Add ephemeral sockets, passive local network
- 		identification, support for local net 0 and
- 		multiple datalinks <Greg Page>
-
- Revision 0.26: Device drop kills IPX routes via it. (needed for module)
-
- Revision 0.27: Autobind <Mark Evans>
-
- Revision 0.28: Small fix for multiple local networks <Thomas Winder>
-
- Revision 0.29: Assorted major errors removed <Mark Evans>
- 		Small correction to promisc mode error fix <Alan Cox>
- 		Asynchronous I/O support. Changed to use notifiers
- 		and the newer packet_type stuff. Assorted major
- 		fixes <Alejandro Liu>
-
- Revision 0.30:	Moved to net/ipx/...	<Alan Cox>
- 		Don't set address length on recvfrom that errors.
- 		Incorrect verify_area.
-
- Revision 0.31:	New sk_buffs. This still needs a lot of 
- 		testing. <Alan Cox>
-
- Revision 0.32: Using sock_alloc_send_skb, firewall hooks. <Alan Cox>
- 		Supports sendmsg/recvmsg
-
- Revision 0.33:	Internal network support, routing changes, uses a
- 		protocol private area for ipx data.
-
- Revision 0.34:	Module support. <Jim Freeman>
-
- Revision 0.35: Checksum support. <Neil Turton>, hooked in by <Alan Cox>
- 		Handles WIN95 discovery packets <Volker Lendecke>
-
- Revision 0.36:	Internal bump up for 2.1
-
- Revision 0.37:	Began adding POSIXisms.
-
- Revision 0.38: Asynchronous socket stuff made current.
-
- Revision 0.39: SPX interfaces
-
- Revision 0.40: Tiny SIOCGSTAMP fix (chris@cybernet.co.nz)
-
- Revision 0.41: 802.2TR removed (p.norton@computer.org)
- 		Fixed connecting to primary net,
- 		Automatic binding on send & receive,
- 		Martijn van Oosterhout <kleptogimp@geocities.com>
-
- Revision 042:  Multithreading - use spinlocks and refcounting to
- 		protect some structures: ipx_interface sock list, list
- 		of ipx interfaces, etc. 
- 		Bugfixes - do refcounting on net_devices, check function
- 		results, etc. Thanks to davem and freitag for
- 		suggestions and guidance.
- 		Arnaldo Carvalho de Melo <acme@conectiva.com.br>,
- 		November, 2000
-
- Revision 043:	Shared SKBs, don't mangle packets, some cleanups
- 		Arnaldo Carvalho de Melo <acme@conectiva.com.br>,
- 		December, 2000
-
- Revision 044:	Call ipxitf_hold on NETDEV_UP - acme
-
- Revision 045:	fix PPROP routing bug - acme
-
- Revision 046:	Further fixes to PPROP, ipxitf_create_internal was
- 		doing an unneeded MOD_INC_USE_COUNT, implement
- 		sysctl for ipx_pprop_broacasting, fix the ipx sysctl
- 		handling, making it dynamic, some cleanups, thanks to
- 		Petr Vandrovec for review and good suggestions. (acme)
-
- Revision 047:	Cleanups, CodingStyle changes, move the ncp connection
- 		hack out of line - acme
-
- Revision 048:	Use sk->protinfo to store the pointer to IPX private
- 		area, remove af_ipx from sk->protinfo and move ipx_opt
- 		to include/net/ipx.h, use IPX_SK like DecNET, etc - acme
-
- Revision 049:	SPX support dropped, see comment in ipx_create - acme
-
- Revision 050:	Use seq_file for proc stuff, moving it to ipx_proc.c - acme
-
-Other fixes:
- 
- Protect the module by a MOD_INC_USE_COUNT/MOD_DEC_USE_COUNT pair. Also, now
- usage count is managed this way:
- -Count one if the auto_interface mode is on
- -Count one per configured interface
- 
- Jacques Gelinas (jacques@solucorp.qc.ca)
diff --git a/net/ipx/Kconfig b/net/ipx/Kconfig
index 980a826f5d0..e9ad0062fbb 100644
--- a/net/ipx/Kconfig
+++ b/net/ipx/Kconfig
@@ -16,8 +16,7 @@ config IPX
 	  support", below.
 
 	  IPX is similar in scope to IP, while SPX, which runs on top of IPX,
-	  is similar to TCP. There is also experimental support for SPX in
-	  Linux (see "SPX networking", below).
+	  is similar to TCP.
 
 	  To turn your Linux box into a fully featured NetWare file server and
 	  IPX router, say Y here and fetch either lwared from
@@ -26,9 +25,6 @@ config IPX
 	  information, read the IPX-HOWTO available from
 	  <http://www.tldp.org/docs.html#howto>.
 
-	  General information about how to connect Linux, Windows machines and
-	  Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>.
-
 	  The IPX driver would enlarge your kernel by about 16 KB. To compile
 	  this driver as a module, choose M here: the module will be called ipx.
 	  Unless you want to integrate your Linux box with a local Novell
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 11d504d0ac7..bf23e489e4c 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -197,13 +197,12 @@ EXPORT_SYMBOL_GPL(nfnetlink_has_listeners);
 
 int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo)
 {
-	gfp_t allocation = in_interrupt() ? GFP_ATOMIC : GFP_KERNEL;
 	int err = 0;
 
 	NETLINK_CB(skb).dst_group = group;
 	if (echo)
 		atomic_inc(&skb->users);
-	netlink_broadcast(nfnl, skb, pid, group, allocation);
+	netlink_broadcast(nfnl, skb, pid, group, gfp_any());
 	if (echo)
 		err = netlink_unicast(nfnl, skb, pid, MSG_DONTWAIT);
 
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 5bc37181662..b931edee4b8 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -173,7 +173,7 @@ static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 
 list_failure:
-	kfree(ans_skb);
+	kfree_skb(ans_skb);
 	return ret_val;
 }
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 25674532161..956cfe0ff7f 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1401,7 +1401,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	x = xfrm_state_lookup(&id->daddr, id->spi, id->proto, id->family);
 	if (x == NULL) {
-		kfree(r_skb);
+		kfree_skb(r_skb);
 		return -ESRCH;
 	}
 
@@ -1557,14 +1557,13 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct xfrm_usersa_info *p = &ue->state;
 
 	x = xfrm_state_lookup(&p->id.daddr, p->id.spi, p->id.proto, p->family);
-		err = -ENOENT;
 
+	err = -ENOENT;
 	if (x == NULL)
 		return err;
 
-	err = -EINVAL;
-
 	spin_lock_bh(&x->lock);
+	err = -EINVAL;
 	if (x->km.state != XFRM_STATE_VALID)
 		goto out;
 	km_state_expired(x, ue->hard, current->pid);
@@ -1574,6 +1573,7 @@ static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 		xfrm_audit_log(NETLINK_CB(skb).loginuid, NETLINK_CB(skb).sid,
 			       AUDIT_MAC_IPSEC_DELSA, 1, NULL, x);
 	}
+	err = 0;
 out:
 	spin_unlock_bh(&x->lock);
 	xfrm_state_put(x);