Merge commit 'v2.6.30-rc1' into sched/urgent

Merge reason: update to latest upstream to queue up fix

Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 82 insertions, 491 deletions

diff --git a/net/netlink/Makefile b/net/netlink/Makefile
index e3589c2de49..bdd6ddf4e95 100644
--- a/net/netlink/Makefile
+++ b/net/netlink/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the netlink driver.
 #
 
-obj-y  				:= af_netlink.o attr.o genetlink.o
+obj-y  				:= af_netlink.o genetlink.o
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9eb895c7a2a..8b6bbb3032b 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -85,6 +85,8 @@ struct netlink_sock {
 
 #define NETLINK_KERNEL_SOCKET	0x1
 #define NETLINK_RECV_PKTINFO	0x2
+#define NETLINK_BROADCAST_SEND_ERROR	0x4
+#define NETLINK_RECV_NO_ENOBUFS	0x8
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
 {
@@ -716,10 +718,15 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
 
 static void netlink_overrun(struct sock *sk)
 {
-	if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
-		sk->sk_err = ENOBUFS;
-		sk->sk_error_report(sk);
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
+		if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
+			sk->sk_err = ENOBUFS;
+			sk->sk_error_report(sk);
+		}
 	}
+	atomic_inc(&sk->sk_drops);
 }
 
 static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
@@ -950,6 +957,7 @@ struct netlink_broadcast_data {
 	u32 pid;
 	u32 group;
 	int failure;
+	int delivery_failure;
 	int congested;
 	int delivered;
 	gfp_t allocation;
@@ -994,11 +1002,15 @@ static inline int do_one_broadcast(struct sock *sk,
 		netlink_overrun(sk);
 		/* Clone failed. Notify ALL listeners. */
 		p->failure = 1;
+		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+			p->delivery_failure = 1;
 	} else if (sk_filter(sk, p->skb2)) {
 		kfree_skb(p->skb2);
 		p->skb2 = NULL;
 	} else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
 		netlink_overrun(sk);
+		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+			p->delivery_failure = 1;
 	} else {
 		p->congested |= val;
 		p->delivered = 1;
@@ -1025,6 +1037,7 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 	info.pid = pid;
 	info.group = group;
 	info.failure = 0;
+	info.delivery_failure = 0;
 	info.congested = 0;
 	info.delivered = 0;
 	info.allocation = allocation;
@@ -1042,16 +1055,16 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 
 	netlink_unlock_table();
 
-	if (info.skb2)
-		kfree_skb(info.skb2);
+	kfree_skb(info.skb2);
+
+	if (info.delivery_failure)
+		return -ENOBUFS;
 
 	if (info.delivered) {
 		if (info.congested && (allocation & __GFP_WAIT))
 			yield();
 		return 0;
 	}
-	if (info.failure)
-		return -ENOBUFS;
 	return -ESRCH;
 }
 EXPORT_SYMBOL(netlink_broadcast);
@@ -1084,6 +1097,13 @@ out:
 	return 0;
 }
 
+/**
+ * netlink_set_err - report error to broadcast listeners
+ * @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
+ * @pid: the PID of a process that we want to skip (if any)
+ * @groups: the broadcast group that will notice the error
+ * @code: error code, must be negative (as usual in kernelspace)
+ */
 void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 {
 	struct netlink_set_err_data info;
@@ -1093,7 +1113,8 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 	info.exclude_sk = ssk;
 	info.pid = pid;
 	info.group = group;
-	info.code = code;
+	/* sk->sk_err wants a positive error value */
+	info.code = -code;
 
 	read_lock(&nl_table_lock);
 
@@ -1102,6 +1123,7 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 
 	read_unlock(&nl_table_lock);
 }
+EXPORT_SYMBOL(netlink_set_err);
 
 /* must be called with netlink table grabbed */
 static void netlink_update_socket_mc(struct netlink_sock *nlk,
@@ -1159,6 +1181,22 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		err = 0;
 		break;
 	}
+	case NETLINK_BROADCAST_ERROR:
+		if (val)
+			nlk->flags |= NETLINK_BROADCAST_SEND_ERROR;
+		else
+			nlk->flags &= ~NETLINK_BROADCAST_SEND_ERROR;
+		err = 0;
+		break;
+	case NETLINK_NO_ENOBUFS:
+		if (val) {
+			nlk->flags |= NETLINK_RECV_NO_ENOBUFS;
+			clear_bit(0, &nlk->state);
+			wake_up_interruptible(&nlk->wait);
+		} else
+			nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1191,6 +1229,26 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 			return -EFAULT;
 		err = 0;
 		break;
+	case NETLINK_BROADCAST_ERROR:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_BROADCAST_SEND_ERROR ? 1 : 0;
+		if (put_user(len, optlen) ||
+		    put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
+	case NETLINK_NO_ENOBUFS:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_RECV_NO_ENOBUFS ? 1 : 0;
+		if (put_user(len, optlen) ||
+		    put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1517,8 +1575,7 @@ EXPORT_SYMBOL(netlink_set_nonroot);
 
 static void netlink_destroy_callback(struct netlink_callback *cb)
 {
-	if (cb->skb)
-		kfree_skb(cb->skb);
+	kfree_skb(cb->skb);
 	kfree(cb);
 }
 
@@ -1735,12 +1792,18 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid,
 			exclude_pid = pid;
 		}
 
-		/* errors reported via destination sk->sk_err */
-		nlmsg_multicast(sk, skb, exclude_pid, group, flags);
+		/* errors reported via destination sk->sk_err, but propagate
+		 * delivery errors if NETLINK_BROADCAST_ERROR flag is set */
+		err = nlmsg_multicast(sk, skb, exclude_pid, group, flags);
 	}
 
-	if (report)
-		err = nlmsg_unicast(sk, skb, pid);
+	if (report) {
+		int err2;
+
+		err2 = nlmsg_unicast(sk, skb, pid);
+		if (!err || err == -ESRCH)
+			err = err2;
+	}
 
 	return err;
 }
@@ -1841,12 +1904,12 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 	if (v == SEQ_START_TOKEN)
 		seq_puts(seq,
 			 "sk       Eth Pid    Groups   "
-			 "Rmem     Wmem     Dump     Locks\n");
+			 "Rmem     Wmem     Dump     Locks     Drops\n");
 	else {
 		struct sock *s = v;
 		struct netlink_sock *nlk = nlk_sk(s);
 
-		seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %d\n",
+		seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d\n",
 			   s,
 			   s->sk_protocol,
 			   nlk->pid,
@@ -1854,7 +1917,8 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 			   atomic_read(&s->sk_rmem_alloc),
 			   atomic_read(&s->sk_wmem_alloc),
 			   nlk->cb,
-			   atomic_read(&s->sk_refcnt)
+			   atomic_read(&s->sk_refcnt),
+			   atomic_read(&s->sk_drops)
 			);
 
 	}
diff --git a/net/netlink/attr.c b/net/netlink/attr.c
deleted file mode 100644
index 56c3ce7fe29..00000000000
--- a/net/netlink/attr.c
+++ /dev/null
@@ -1,473 +0,0 @@
-/*
- * NETLINK      Netlink attributes
- *
- * 		Authors:	Thomas Graf <tgraf@suug.ch>
- * 				Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/jiffies.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <net/netlink.h>
-
-static u16 nla_attr_minlen[NLA_TYPE_MAX+1] __read_mostly = {
-	[NLA_U8]	= sizeof(u8),
-	[NLA_U16]	= sizeof(u16),
-	[NLA_U32]	= sizeof(u32),
-	[NLA_U64]	= sizeof(u64),
-	[NLA_NESTED]	= NLA_HDRLEN,
-};
-
-static int validate_nla(struct nlattr *nla, int maxtype,
-			const struct nla_policy *policy)
-{
-	const struct nla_policy *pt;
-	int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla);
-
-	if (type <= 0 || type > maxtype)
-		return 0;
-
-	pt = &policy[type];
-
-	BUG_ON(pt->type > NLA_TYPE_MAX);
-
-	switch (pt->type) {
-	case NLA_FLAG:
-		if (attrlen > 0)
-			return -ERANGE;
-		break;
-
-	case NLA_NUL_STRING:
-		if (pt->len)
-			minlen = min_t(int, attrlen, pt->len + 1);
-		else
-			minlen = attrlen;
-
-		if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL)
-			return -EINVAL;
-		/* fall through */
-
-	case NLA_STRING:
-		if (attrlen < 1)
-			return -ERANGE;
-
-		if (pt->len) {
-			char *buf = nla_data(nla);
-
-			if (buf[attrlen - 1] == '\0')
-				attrlen--;
-
-			if (attrlen > pt->len)
-				return -ERANGE;
-		}
-		break;
-
-	case NLA_BINARY:
-		if (pt->len && attrlen > pt->len)
-			return -ERANGE;
-		break;
-
-	case NLA_NESTED_COMPAT:
-		if (attrlen < pt->len)
-			return -ERANGE;
-		if (attrlen < NLA_ALIGN(pt->len))
-			break;
-		if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN)
-			return -ERANGE;
-		nla = nla_data(nla) + NLA_ALIGN(pt->len);
-		if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN + nla_len(nla))
-			return -ERANGE;
-		break;
-	case NLA_NESTED:
-		/* a nested attributes is allowed to be empty; if its not,
-		 * it must have a size of at least NLA_HDRLEN.
-		 */
-		if (attrlen == 0)
-			break;
-	default:
-		if (pt->len)
-			minlen = pt->len;
-		else if (pt->type != NLA_UNSPEC)
-			minlen = nla_attr_minlen[pt->type];
-
-		if (attrlen < minlen)
-			return -ERANGE;
-	}
-
-	return 0;
-}
-
-/**
- * nla_validate - Validate a stream of attributes
- * @head: head of attribute stream
- * @len: length of attribute stream
- * @maxtype: maximum attribute type to be expected
- * @policy: validation policy
- *
- * Validates all attributes in the specified attribute stream against the
- * specified policy. Attributes with a type exceeding maxtype will be
- * ignored. See documenation of struct nla_policy for more details.
- *
- * Returns 0 on success or a negative error code.
- */
-int nla_validate(struct nlattr *head, int len, int maxtype,
-		 const struct nla_policy *policy)
-{
-	struct nlattr *nla;
-	int rem, err;
-
-	nla_for_each_attr(nla, head, len, rem) {
-		err = validate_nla(nla, maxtype, policy);
-		if (err < 0)
-			goto errout;
-	}
-
-	err = 0;
-errout:
-	return err;
-}
-
-/**
- * nla_parse - Parse a stream of attributes into a tb buffer
- * @tb: destination array with maxtype+1 elements
- * @maxtype: maximum attribute type to be expected
- * @head: head of attribute stream
- * @len: length of attribute stream
- * @policy: validation policy
- *
- * Parses a stream of attributes and stores a pointer to each attribute in
- * the tb array accessable via the attribute type. Attributes with a type
- * exceeding maxtype will be silently ignored for backwards compatibility
- * reasons. policy may be set to NULL if no validation is required.
- *
- * Returns 0 on success or a negative error code.
- */
-int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-	      const struct nla_policy *policy)
-{
-	struct nlattr *nla;
-	int rem, err;
-
-	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
-
-	nla_for_each_attr(nla, head, len, rem) {
-		u16 type = nla_type(nla);
-
-		if (type > 0 && type <= maxtype) {
-			if (policy) {
-				err = validate_nla(nla, maxtype, policy);
-				if (err < 0)
-					goto errout;
-			}
-
-			tb[type] = nla;
-		}
-	}
-
-	if (unlikely(rem > 0))
-		printk(KERN_WARNING "netlink: %d bytes leftover after parsing "
-		       "attributes.\n", rem);
-
-	err = 0;
-errout:
-	return err;
-}
-
-/**
- * nla_find - Find a specific attribute in a stream of attributes
- * @head: head of attribute stream
- * @len: length of attribute stream
- * @attrtype: type of attribute to look for
- *
- * Returns the first attribute in the stream matching the specified type.
- */
-struct nlattr *nla_find(struct nlattr *head, int len, int attrtype)
-{
-	struct nlattr *nla;
-	int rem;
-
-	nla_for_each_attr(nla, head, len, rem)
-		if (nla_type(nla) == attrtype)
-			return nla;
-
-	return NULL;
-}
-
-/**
- * nla_strlcpy - Copy string attribute payload into a sized buffer
- * @dst: where to copy the string to
- * @nla: attribute to copy the string from
- * @dstsize: size of destination buffer
- *
- * Copies at most dstsize - 1 bytes into the destination buffer.
- * The result is always a valid NUL-terminated string. Unlike
- * strlcpy the destination buffer is always padded out.
- *
- * Returns the length of the source buffer.
- */
-size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize)
-{
-	size_t srclen = nla_len(nla);
-	char *src = nla_data(nla);
-
-	if (srclen > 0 && src[srclen - 1] == '\0')
-		srclen--;
-
-	if (dstsize > 0) {
-		size_t len = (srclen >= dstsize) ? dstsize - 1 : srclen;
-
-		memset(dst, 0, dstsize);
-		memcpy(dst, src, len);
-	}
-
-	return srclen;
-}
-
-/**
- * nla_memcpy - Copy a netlink attribute into another memory area
- * @dest: where to copy to memcpy
- * @src: netlink attribute to copy from
- * @count: size of the destination area
- *
- * Note: The number of bytes copied is limited by the length of
- *       attribute's payload. memcpy
- *
- * Returns the number of bytes copied.
- */
-int nla_memcpy(void *dest, const struct nlattr *src, int count)
-{
-	int minlen = min_t(int, count, nla_len(src));
-
-	memcpy(dest, nla_data(src), minlen);
-
-	return minlen;
-}
-
-/**
- * nla_memcmp - Compare an attribute with sized memory area
- * @nla: netlink attribute
- * @data: memory area
- * @size: size of memory area
- */
-int nla_memcmp(const struct nlattr *nla, const void *data,
-			     size_t size)
-{
-	int d = nla_len(nla) - size;
-
-	if (d == 0)
-		d = memcmp(nla_data(nla), data, size);
-
-	return d;
-}
-
-/**
- * nla_strcmp - Compare a string attribute against a string
- * @nla: netlink string attribute
- * @str: another string
- */
-int nla_strcmp(const struct nlattr *nla, const char *str)
-{
-	int len = strlen(str) + 1;
-	int d = nla_len(nla) - len;
-
-	if (d == 0)
-		d = memcmp(nla_data(nla), str, len);
-
-	return d;
-}
-
-/**
- * __nla_reserve - reserve room for attribute on the skb
- * @skb: socket buffer to reserve room on
- * @attrtype: attribute type
- * @attrlen: length of attribute payload
- *
- * Adds a netlink attribute header to a socket buffer and reserves
- * room for the payload but does not copy it.
- *
- * The caller is responsible to ensure that the skb provides enough
- * tailroom for the attribute header and payload.
- */
-struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen)
-{
-	struct nlattr *nla;
-
-	nla = (struct nlattr *) skb_put(skb, nla_total_size(attrlen));
-	nla->nla_type = attrtype;
-	nla->nla_len = nla_attr_size(attrlen);
-
-	memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen));
-
-	return nla;
-}
-
-/**
- * __nla_reserve_nohdr - reserve room for attribute without header
- * @skb: socket buffer to reserve room on
- * @attrlen: length of attribute payload
- *
- * Reserves room for attribute payload without a header.
- *
- * The caller is responsible to ensure that the skb provides enough
- * tailroom for the payload.
- */
-void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen)
-{
-	void *start;
-
-	start = skb_put(skb, NLA_ALIGN(attrlen));
-	memset(start, 0, NLA_ALIGN(attrlen));
-
-	return start;
-}
-
-/**
- * nla_reserve - reserve room for attribute on the skb
- * @skb: socket buffer to reserve room on
- * @attrtype: attribute type
- * @attrlen: length of attribute payload
- *
- * Adds a netlink attribute header to a socket buffer and reserves
- * room for the payload but does not copy it.
- *
- * Returns NULL if the tailroom of the skb is insufficient to store
- * the attribute header and payload.
- */
-struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen)
-{
-	if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen)))
-		return NULL;
-
-	return __nla_reserve(skb, attrtype, attrlen);
-}
-
-/**
- * nla_reserve_nohdr - reserve room for attribute without header
- * @skb: socket buffer to reserve room on
- * @attrlen: length of attribute payload
- *
- * Reserves room for attribute payload without a header.
- *
- * Returns NULL if the tailroom of the skb is insufficient to store
- * the attribute payload.
- */
-void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen)
-{
-	if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
-		return NULL;
-
-	return __nla_reserve_nohdr(skb, attrlen);
-}
-
-/**
- * __nla_put - Add a netlink attribute to a socket buffer
- * @skb: socket buffer to add attribute to
- * @attrtype: attribute type
- * @attrlen: length of attribute payload
- * @data: head of attribute payload
- *
- * The caller is responsible to ensure that the skb provides enough
- * tailroom for the attribute header and payload.
- */
-void __nla_put(struct sk_buff *skb, int attrtype, int attrlen,
-			     const void *data)
-{
-	struct nlattr *nla;
-
-	nla = __nla_reserve(skb, attrtype, attrlen);
-	memcpy(nla_data(nla), data, attrlen);
-}
-
-/**
- * __nla_put_nohdr - Add a netlink attribute without header
- * @skb: socket buffer to add attribute to
- * @attrlen: length of attribute payload
- * @data: head of attribute payload
- *
- * The caller is responsible to ensure that the skb provides enough
- * tailroom for the attribute payload.
- */
-void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
-{
-	void *start;
-
-	start = __nla_reserve_nohdr(skb, attrlen);
-	memcpy(start, data, attrlen);
-}
-
-/**
- * nla_put - Add a netlink attribute to a socket buffer
- * @skb: socket buffer to add attribute to
- * @attrtype: attribute type
- * @attrlen: length of attribute payload
- * @data: head of attribute payload
- *
- * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
- * the attribute header and payload.
- */
-int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data)
-{
-	if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen)))
-		return -EMSGSIZE;
-
-	__nla_put(skb, attrtype, attrlen, data);
-	return 0;
-}
-
-/**
- * nla_put_nohdr - Add a netlink attribute without header
- * @skb: socket buffer to add attribute to
- * @attrlen: length of attribute payload
- * @data: head of attribute payload
- *
- * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
- * the attribute payload.
- */
-int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data)
-{
-	if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
-		return -EMSGSIZE;
-
-	__nla_put_nohdr(skb, attrlen, data);
-	return 0;
-}
-
-/**
- * nla_append - Add a netlink attribute without header or padding
- * @skb: socket buffer to add attribute to
- * @attrlen: length of attribute payload
- * @data: head of attribute payload
- *
- * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store
- * the attribute payload.
- */
-int nla_append(struct sk_buff *skb, int attrlen, const void *data)
-{
-	if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen)))
-		return -EMSGSIZE;
-
-	memcpy(skb_put(skb, attrlen), data, attrlen);
-	return 0;
-}
-
-EXPORT_SYMBOL(nla_validate);
-EXPORT_SYMBOL(nla_parse);
-EXPORT_SYMBOL(nla_find);
-EXPORT_SYMBOL(nla_strlcpy);
-EXPORT_SYMBOL(__nla_reserve);
-EXPORT_SYMBOL(__nla_reserve_nohdr);
-EXPORT_SYMBOL(nla_reserve);
-EXPORT_SYMBOL(nla_reserve_nohdr);
-EXPORT_SYMBOL(__nla_put);
-EXPORT_SYMBOL(__nla_put_nohdr);
-EXPORT_SYMBOL(nla_put);
-EXPORT_SYMBOL(nla_put_nohdr);
-EXPORT_SYMBOL(nla_memcpy);
-EXPORT_SYMBOL(nla_memcmp);
-EXPORT_SYMBOL(nla_strcmp);
-EXPORT_SYMBOL(nla_append);