Merge branch 'bugfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* 'bugfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
  NFS: Fix the fix to Bugzilla #11061, when IPv6 isn't defined...
  SUNRPC: xprt_connect() don't abort the task if the transport isn't bound
  SUNRPC: Fix an Oops due to socket not set up yet...
  Bug 11061, NFS mounts dropped
  NFS: Handle -ESTALE error in access()
  NLM: Fix GRANT callback address comparison when IPv6 is enabled
  NLM: Shrink the IPv4-only version of nlm_cmp_addr()
  NFSv3: Fix posix ACL code
  NFS: Fix misparsing of nfsv4 fs_locations attribute (take 2)
  SUNRPC: Tighten up the task locking rules in __rpc_execute()

fs/lockd/clntlock.c

@@ -139,6 +139,55 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
 	return 0;
 }
 
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static const struct in6_addr *nlmclnt_map_v4addr(const struct sockaddr *sap,
+						 struct in6_addr *addr_mapped)
+{
+	const struct sockaddr_in *sin = (const struct sockaddr_in *)sap;
+
+	switch (sap->sa_family) {
+	case AF_INET6:
+		return &((const struct sockaddr_in6 *)sap)->sin6_addr;
+	case AF_INET:
+		ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, addr_mapped);
+		return addr_mapped;
+	}
+
+	return NULL;
+}
+
+/*
+ * If lockd is using a PF_INET6 listener, all incoming requests appear
+ * to come from AF_INET6 remotes.  The address of AF_INET remotes are
+ * mapped to AF_INET6 automatically by the network layer.  In case the
+ * user passed an AF_INET server address at mount time, ensure both
+ * addresses are AF_INET6 before comparing them.
+ */
+static int nlmclnt_cmp_addr(const struct nlm_host *host,
+			    const struct sockaddr *sap)
+{
+	const struct in6_addr *addr1;
+	const struct in6_addr *addr2;
+	struct in6_addr addr1_mapped;
+	struct in6_addr addr2_mapped;
+
+	addr1 = nlmclnt_map_v4addr(nlm_addr(host), &addr1_mapped);
+	if (likely(addr1 != NULL)) {
+		addr2 = nlmclnt_map_v4addr(sap, &addr2_mapped);
+		if (likely(addr2 != NULL))
+			return ipv6_addr_equal(addr1, addr2);
+	}
+
+	return 0;
+}
+#else	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+static int nlmclnt_cmp_addr(const struct nlm_host *host,
+			    const struct sockaddr *sap)
+{
+	return nlm_cmp_addr(nlm_addr(host), sap);
+}
+#endif	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+
 /*
  * The server lockd has called us back to tell us the lock was granted
  */
@@ -166,7 +215,7 @@ __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock)
 		 */
 		if (fl_blocked->fl_u.nfs_fl.owner->pid != lock->svid)
 			continue;
-		if (!nlm_cmp_addr(nlm_addr(block->b_host), addr))
+		if (!nlmclnt_cmp_addr(block->b_host, addr))
 			continue;
 		if (nfs_compare_fh(NFS_FH(fl_blocked->fl_file->f_path.dentry->d_inode) ,fh) != 0)
 			continue;

fs/nfs/client.c

@@ -255,6 +255,32 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
 	}
 	return 0;
 }
+
+/*
+ * Test if two ip6 socket addresses refer to the same socket by
+ * comparing relevant fields. The padding bytes specifically, are not
+ * compared. sin6_flowinfo is not compared because it only affects QoS
+ * and sin6_scope_id is only compared if the address is "link local"
+ * because "link local" addresses need only be unique to a specific
+ * link. Conversely, ordinary unicast addresses might have different
+ * sin6_scope_id.
+ *
+ * The caller should ensure both socket addresses are AF_INET6.
+ */
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1,
+				const struct sockaddr *sa2)
+{
+	const struct sockaddr_in6 *saddr1 = (const struct sockaddr_in6 *)sa1;
+	const struct sockaddr_in6 *saddr2 = (const struct sockaddr_in6 *)sa2;
+
+	if (!ipv6_addr_equal(&saddr1->sin6_addr,
+			     &saddr1->sin6_addr))
+		return 0;
+	if (ipv6_addr_scope(&saddr1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL &&
+	    saddr1->sin6_scope_id != saddr2->sin6_scope_id)
+		return 0;
+	return saddr1->sin6_port == saddr2->sin6_port;
+}
 #else
 static int nfs_sockaddr_match_ipaddr4(const struct sockaddr_in *sa1,
 				 const struct sockaddr_in *sa2)
@@ -270,8 +296,51 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
 	return nfs_sockaddr_match_ipaddr4((const struct sockaddr_in *)sa1,
 			(const struct sockaddr_in *)sa2);
 }
+
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1,
+				const struct sockaddr * sa2)
+{
+	return 0;
+}
 #endif
 
+/*
+ * Test if two ip4 socket addresses refer to the same socket, by
+ * comparing relevant fields. The padding bytes specifically, are
+ * not compared.
+ *
+ * The caller should ensure both socket addresses are AF_INET.
+ */
+static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
+				const struct sockaddr *sa2)
+{
+	const struct sockaddr_in *saddr1 = (const struct sockaddr_in *)sa1;
+	const struct sockaddr_in *saddr2 = (const struct sockaddr_in *)sa2;
+
+	if (saddr1->sin_addr.s_addr != saddr2->sin_addr.s_addr)
+		return 0;
+	return saddr1->sin_port == saddr2->sin_port;
+}
+
+/*
+ * Test if two socket addresses represent the same actual socket,
+ * by comparing (only) relevant fields.
+ */
+static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
+			    const struct sockaddr *sa2)
+{
+	if (sa1->sa_family != sa2->sa_family)
+		return 0;
+
+	switch (sa1->sa_family) {
+	case AF_INET:
+		return nfs_sockaddr_cmp_ip4(sa1, sa2);
+	case AF_INET6:
+		return nfs_sockaddr_cmp_ip6(sa1, sa2);
+	}
+	return 0;
+}
+
 /*
  * Find a client by IP address and protocol version
  * - returns NULL if no such client
@@ -344,8 +413,10 @@ struct nfs_client *nfs_find_client_next(struct nfs_client *clp)
 static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data)
 {
 	struct nfs_client *clp;
+	const struct sockaddr *sap = data->addr;
 
 	list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+	        const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
 		/* Don't match clients that failed to initialise properly */
 		if (clp->cl_cons_state < 0)
 			continue;
@@ -358,7 +429,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 			continue;
 
 		/* Match the full socket address */
-		if (memcmp(&clp->cl_addr, data->addr, sizeof(clp->cl_addr)) != 0)
+		if (!nfs_sockaddr_cmp(sap, clap))
 			continue;
 
 		atomic_inc(&clp->cl_count);

fs/nfs/dir.c

@@ -1892,8 +1892,14 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	cache.cred = cred;
 	cache.jiffies = jiffies;
 	status = NFS_PROTO(inode)->access(inode, &cache);
-	if (status != 0)
+	if (status != 0) {
+		if (status == -ESTALE) {
+			nfs_zap_caches(inode);
+			if (!S_ISDIR(inode->i_mode))
+				set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
+		}
 		return status;
+	}
 	nfs_access_add_cache(inode, &cache);
 out:
 	if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)

fs/nfs/nfs3acl.c

@@ -292,7 +292,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_fattr fattr;
-	struct page *pages[NFSACL_MAXPAGES] = { };
+	struct page *pages[NFSACL_MAXPAGES];
 	struct nfs3_setaclargs args = {
 		.inode = inode,
 		.mask = NFS_ACL,
@@ -303,7 +303,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		.rpc_argp	= &args,
 		.rpc_resp	= &fattr,
 	};
-	int status, count;
+	int status;
 
 	status = -EOPNOTSUPP;
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
@@ -319,6 +319,20 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 	if (S_ISDIR(inode->i_mode)) {
 		args.mask |= NFS_DFACL;
 		args.acl_default = dfacl;
+		args.len = nfsacl_size(acl, dfacl);
+	} else
+		args.len = nfsacl_size(acl, NULL);
+
+	if (args.len > NFS_ACL_INLINE_BUFSIZE) {
+		unsigned int npages = 1 + ((args.len - 1) >> PAGE_SHIFT);
+
+		status = -ENOMEM;
+		do {
+			args.pages[args.npages] = alloc_page(GFP_KERNEL);
+			if (args.pages[args.npages] == NULL)
+				goto out_freepages;
+			args.npages++;
+		} while (args.npages < npages);
 	}
 
 	dprintk("NFS call setacl\n");
@@ -329,10 +343,6 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 	nfs_zap_acl_cache(inode);
 	dprintk("NFS reply setacl: %d\n", status);
 
-	/* pages may have been allocated at the xdr layer. */
-	for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++)
-		__free_page(args.pages[count]);
-
 	switch (status) {
 		case 0:
 			status = nfs_refresh_inode(inode, &fattr);
@@ -346,6 +356,11 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		case -ENOTSUPP:
 			status = -EOPNOTSUPP;
 	}
+out_freepages:
+	while (args.npages != 0) {
+		args.npages--;
+		__free_page(args.pages[args.npages]);
+	}
 out:
 	return status;
 }

fs/nfs/nfs3xdr.c

@@ -82,8 +82,10 @@
 #define NFS3_commitres_sz	(1+NFS3_wcc_data_sz+2)
 
 #define ACL3_getaclargs_sz	(NFS3_fh_sz+1)
-#define ACL3_setaclargs_sz	(NFS3_fh_sz+1+2*(2+5*3))
-#define ACL3_getaclres_sz	(1+NFS3_post_op_attr_sz+1+2*(2+5*3))
+#define ACL3_setaclargs_sz	(NFS3_fh_sz+1+ \
+				XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
+#define ACL3_getaclres_sz	(1+NFS3_post_op_attr_sz+1+ \
+				XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
 #define ACL3_setaclres_sz	(1+NFS3_post_op_attr_sz)
 
 /*
@@ -703,28 +705,18 @@ nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p,
                    struct nfs3_setaclargs *args)
 {
 	struct xdr_buf *buf = &req->rq_snd_buf;
-	unsigned int base, len_in_head, len = nfsacl_size(
-		(args->mask & NFS_ACL)   ? args->acl_access  : NULL,
-		(args->mask & NFS_DFACL) ? args->acl_default : NULL);
-	int count, err;
+	unsigned int base;
+	int err;
 
 	p = xdr_encode_fhandle(p, NFS_FH(args->inode));
 	*p++ = htonl(args->mask);
-	base = (char *)p - (char *)buf->head->iov_base;
-	/* put as much of the acls into head as possible. */
-	len_in_head = min_t(unsigned int, buf->head->iov_len - base, len);
-	len -= len_in_head;
-	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p + (len_in_head >> 2));
-
-	for (count = 0; (count << PAGE_SHIFT) < len; count++) {
-		args->pages[count] = alloc_page(GFP_KERNEL);
-		if (!args->pages[count]) {
-			while (count)
-				__free_page(args->pages[--count]);
-			return -ENOMEM;
-		}
-	}
-	xdr_encode_pages(buf, args->pages, 0, len);
+	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+	base = req->rq_slen;
+
+	if (args->npages != 0)
+		xdr_encode_pages(buf, args->pages, 0, args->len);
+	else
+		req->rq_slen += args->len;
 
 	err = nfsacl_encode(buf, base, args->inode,
 			    (args->mask & NFS_ACL) ?

fs/nfs/nfs4namespace.c

@@ -21,7 +21,9 @@
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
 /*
- * Check if fs_root is valid
+ * Convert the NFSv4 pathname components into a standard posix path.
+ *
+ * Note that the resulting string will be placed at the end of the buffer
  */
 static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname,
 					 char *buffer, ssize_t buflen)
@@ -99,21 +101,20 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 {
 	struct vfsmount *mnt = ERR_PTR(-ENOENT);
 	char *mnt_path;
-	int page2len;
+	unsigned int maxbuflen;
 	unsigned int s;
 
 	mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
 	if (IS_ERR(mnt_path))
 		return mnt;
 	mountdata->mnt_path = mnt_path;
-	page2 += strlen(mnt_path) + 1;
-	page2len = PAGE_SIZE - strlen(mnt_path) - 1;
+	maxbuflen = mnt_path - 1 - page2;
 
 	for (s = 0; s < location->nservers; s++) {
 		const struct nfs4_string *buf = &location->servers[s];
 		struct sockaddr_storage addr;
 
-		if (buf->len <= 0 || buf->len >= PAGE_SIZE)
+		if (buf->len <= 0 || buf->len >= maxbuflen)
 			continue;
 
 		mountdata->addr = (struct sockaddr *)&addr;
@@ -126,8 +127,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 			continue;
 		nfs_set_port(mountdata->addr, NFS_PORT);
 
-		strncpy(page2, buf->data, page2len);
-		page2[page2len] = '\0';
+		memcpy(page2, buf->data, buf->len);
+		page2[buf->len] = '\0';
 		mountdata->hostname = page2;
 
 		snprintf(page, PAGE_SIZE, "%s:%s",

include/linux/lockd/lockd.h

@@ -346,6 +346,7 @@ static inline int __nlm_cmp_addr4(const struct sockaddr *sap1,
 	return sin1->sin_addr.s_addr == sin2->sin_addr.s_addr;
 }
 
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
 				  const struct sockaddr *sap2)
 {
@@ -353,6 +354,13 @@ static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
 	const struct sockaddr_in6 *sin2 = (const struct sockaddr_in6 *)sap2;
 	return ipv6_addr_equal(&sin1->sin6_addr, &sin2->sin6_addr);
 }
+#else	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+static inline int __nlm_cmp_addr6(const struct sockaddr *sap1,
+				  const struct sockaddr *sap2)
+{
+	return 0;
+}
+#endif	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
 
 /*
  * Compare two host addresses

include/linux/nfs_xdr.h

@@ -406,6 +406,8 @@ struct nfs3_setaclargs {
 	int			mask;
 	struct posix_acl *	acl_access;
 	struct posix_acl *	acl_default;
+	size_t			len;
+	unsigned int		npages;
 	struct page **		pages;
 };
 

include/linux/nfsacl.h

@@ -37,6 +37,9 @@
 #define NFSACL_MAXPAGES		((2*(8+12*NFS_ACL_MAX_ENTRIES) + PAGE_SIZE-1) \
 				 >> PAGE_SHIFT)
 
+#define NFS_ACL_MAX_ENTRIES_INLINE	(5)
+#define NFS_ACL_INLINE_BUFSIZE	((2*(2+3*NFS_ACL_MAX_ENTRIES_INLINE)) << 2)
+
 static inline unsigned int
 nfsacl_size(struct posix_acl *acl_access, struct posix_acl *acl_default)
 {

net/sunrpc/sched.c

@@ -293,11 +293,6 @@ static void rpc_make_runnable(struct rpc_task *task)
 	rpc_clear_queued(task);
 	if (rpc_test_and_set_running(task))
 		return;
-	/* We might have raced */
-	if (RPC_IS_QUEUED(task)) {
-		rpc_clear_running(task);
-		return;
-	}
 	if (RPC_IS_ASYNC(task)) {
 		int status;
 
@@ -607,7 +602,9 @@ void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
  */
 static void __rpc_execute(struct rpc_task *task)
 {
-	int		status = 0;
+	struct rpc_wait_queue *queue;
+	int task_is_async = RPC_IS_ASYNC(task);
+	int status = 0;
 
 	dprintk("RPC: %5u __rpc_execute flags=0x%x\n",
 			task->tk_pid, task->tk_flags);
@@ -647,15 +644,25 @@ static void __rpc_execute(struct rpc_task *task)
 		 */
 		if (!RPC_IS_QUEUED(task))
 			continue;
-		rpc_clear_running(task);
-		if (RPC_IS_ASYNC(task)) {
-			/* Careful! we may have raced... */
-			if (RPC_IS_QUEUED(task))
-				return;
-			if (rpc_test_and_set_running(task))
-				return;
+		/*
+		 * The queue->lock protects against races with
+		 * rpc_make_runnable().
+		 *
+		 * Note that once we clear RPC_TASK_RUNNING on an asynchronous
+		 * rpc_task, rpc_make_runnable() can assign it to a
+		 * different workqueue. We therefore cannot assume that the
+		 * rpc_task pointer may still be dereferenced.
+		 */
+		queue = task->tk_waitqueue;
+		spin_lock_bh(&queue->lock);
+		if (!RPC_IS_QUEUED(task)) {
+			spin_unlock_bh(&queue->lock);
 			continue;
 		}
+		rpc_clear_running(task);
+		spin_unlock_bh(&queue->lock);
+		if (task_is_async)
+			return;
 
 		/* sync task: sleep here */
 		dprintk("RPC: %5u sync task going to sleep\n", task->tk_pid);

net/sunrpc/xprt.c

@@ -663,7 +663,7 @@ void xprt_connect(struct rpc_task *task)
 			xprt, (xprt_connected(xprt) ? "is" : "is not"));
 
 	if (!xprt_bound(xprt)) {
-		task->tk_status = -EIO;
+		task->tk_status = -EAGAIN;
 		return;
 	}
 	if (!xprt_lock_write(xprt, task))

net/sunrpc/xprtsock.c

@@ -467,7 +467,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,
 	int err, sent = 0;
 
 	if (unlikely(!sock))
-		return -ENOTCONN;
+		return -ENOTSOCK;
 
 	clear_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
 	if (base != 0) {
@@ -577,6 +577,8 @@ static int xs_udp_send_request(struct rpc_task *task)
 				req->rq_svec->iov_base,
 				req->rq_svec->iov_len);
 
+	if (!xprt_bound(xprt))
+		return -ENOTCONN;
 	status = xs_sendpages(transport->sock,
 			      xs_addr(xprt),
 			      xprt->addrlen, xdr,
@@ -594,6 +596,10 @@ static int xs_udp_send_request(struct rpc_task *task)
 	}
 
 	switch (status) {
+	case -ENOTSOCK:
+		status = -ENOTCONN;
+		/* Should we call xs_close() here? */
+		break;
 	case -EAGAIN:
 		xs_nospace(task);
 		break;
@@ -693,6 +699,10 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	}
 
 	switch (status) {
+	case -ENOTSOCK:
+		status = -ENOTCONN;
+		/* Should we call xs_close() here? */
+		break;
 	case -EAGAIN:
 		xs_nospace(task);
 		break;
@@ -1523,7 +1533,7 @@ static void xs_udp_connect_worker4(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int err, status = -EIO;
 
-	if (xprt->shutdown || !xprt_bound(xprt))
+	if (xprt->shutdown)
 		goto out;
 
 	/* Start by resetting any existing state */
@@ -1564,7 +1574,7 @@ static void xs_udp_connect_worker6(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int err, status = -EIO;
 
-	if (xprt->shutdown || !xprt_bound(xprt))
+	if (xprt->shutdown)
 		goto out;
 
 	/* Start by resetting any existing state */
@@ -1648,6 +1658,9 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 		write_unlock_bh(&sk->sk_callback_lock);
 	}
 
+	if (!xprt_bound(xprt))
+		return -ENOTCONN;
+
 	/* Tell the socket layer to start connecting... */
 	xprt->stat.connect_count++;
 	xprt->stat.connect_start = jiffies;
@@ -1668,7 +1681,7 @@ static void xs_tcp_connect_worker4(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int err, status = -EIO;
 
-	if (xprt->shutdown || !xprt_bound(xprt))
+	if (xprt->shutdown)
 		goto out;
 
 	if (!sock) {
@@ -1728,7 +1741,7 @@ static void xs_tcp_connect_worker6(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int err, status = -EIO;
 
-	if (xprt->shutdown || !xprt_bound(xprt))
+	if (xprt->shutdown)
 		goto out;
 
 	if (!sock) {