Merge tag 'nfs-for-3.6-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:

 - Final (hopefully) fix for the range checking code in NFSv4 getacl.
   This should fix the Oopses being seen when the acl size is close to
   PAGE_SIZE.
 - Fix a regression with the legacy binary mount code
 - Fix a regression in the readdir cookieverf initialisation
 - Fix an RPC over UDP regression
 - Ensure that we report all errors in the NFSv4 open code
 - Ensure that fsync() reports all relevant synchronisation errors.

* tag 'nfs-for-3.6-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFS: fsync() must exit with an error if page writeback failed
  SUNRPC: Fix a UDP transport regression
  NFS: return error from decode_getfh in decode open
  NFSv4: Fix buffer overflow checking in __nfs4_get_acl_uncached
  NFSv4: Fix range checking in __nfs4_get_acl_uncached and __nfs4_proc_set_acl
  NFS: Fix a problem with the legacy binary mount code
  NFS: Fix the initialisation of the readdir 'cookieverf' array

13 files changed, 70 insertions, 64 deletions

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 75d6d0a3d32..6a7fcab7ecb 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -287,10 +287,12 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct inode *inode = file->f_path.dentry->d_inode;
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (ret != 0)
+		goto out;
 	mutex_lock(&inode->i_mutex);
 	ret = nfs_file_fsync_commit(file, start, end, datasync);
 	mutex_unlock(&inode->i_mutex);
-
+out:
 	return ret;
 }
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c6e895f0fbf..9b47610338f 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -154,7 +154,7 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 	nfsi->attrtimeo_timestamp = jiffies;
 
-	memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
+	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
 	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
 	else
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index d6b3b5f2d77..69322096c32 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -643,7 +643,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 		  u64 cookie, struct page **pages, unsigned int count, int plus)
 {
 	struct inode		*dir = dentry->d_inode;
-	__be32			*verf = NFS_COOKIEVERF(dir);
+	__be32			*verf = NFS_I(dir)->cookieverf;
 	struct nfs3_readdirargs	arg = {
 		.fh		= NFS_FH(dir),
 		.cookie		= cookie,
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index acb65e7887f..eb5eb8eef4d 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -96,13 +96,15 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	struct inode *inode = file->f_path.dentry->d_inode;
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (ret != 0)
+		goto out;
 	mutex_lock(&inode->i_mutex);
 	ret = nfs_file_fsync_commit(file, start, end, datasync);
 	if (!ret && !datasync)
 		/* application has asked for meta-data sync */
 		ret = pnfs_layoutcommit_inode(inode, true);
 	mutex_unlock(&inode->i_mutex);
-
+out:
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 635274140b1..1e50326d00d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3215,11 +3215,11 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 			dentry->d_parent->d_name.name,
 			dentry->d_name.name,
 			(unsigned long long)cookie);
-	nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args);
+	nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args);
 	res.pgbase = args.pgbase;
 	status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0);
 	if (status >= 0) {
-		memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE);
+		memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE);
 		status += args.pgbase;
 	}
 
@@ -3653,11 +3653,11 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
 		&& (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL);
 }
 
-/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_CACHE_SIZE, and that
- * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_CACHE_SIZE) bytes on
+/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
+ * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_SIZE) bytes on
  * the stack.
  */
-#define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
+#define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE)
 
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
@@ -3668,7 +3668,7 @@ static int buf_to_pages_noslab(const void *buf, size_t buflen,
 	spages = pages;
 
 	do {
-		len = min_t(size_t, PAGE_CACHE_SIZE, buflen);
+		len = min_t(size_t, PAGE_SIZE, buflen);
 		newpage = alloc_page(GFP_KERNEL);
 
 		if (newpage == NULL)
@@ -3739,7 +3739,7 @@ static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size
 	struct nfs4_cached_acl *acl;
 	size_t buflen = sizeof(*acl) + acl_len;
 
-	if (pages && buflen <= PAGE_SIZE) {
+	if (buflen <= PAGE_SIZE) {
 		acl = kmalloc(buflen, GFP_KERNEL);
 		if (acl == NULL)
 			goto out;
@@ -3782,17 +3782,15 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	int ret = -ENOMEM, npages, i;
-	size_t acl_len = 0;
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
+	int ret = -ENOMEM, i;
 
-	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	/* As long as we're doing a round trip to the server anyway,
 	 * let's be prepared for a page of acl data. */
 	if (npages == 0)
 		npages = 1;
-
-	/* Add an extra page to handle the bitmap returned */
-	npages++;
+	if (npages > ARRAY_SIZE(pages))
+		return -ERANGE;
 
 	for (i = 0; i < npages; i++) {
 		pages[i] = alloc_page(GFP_KERNEL);
@@ -3808,11 +3806,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 	args.acl_len = npages * PAGE_SIZE;
 	args.acl_pgbase = 0;
 
-	/* Let decode_getfacl know not to fail if the ACL data is larger than
-	 * the page we send as a guess */
-	if (buf == NULL)
-		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
-
 	dprintk("%s  buf %p buflen %zu npages %d args.acl_len %zu\n",
 		__func__, buf, buflen, npages, args.acl_len);
 	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
@@ -3820,20 +3813,19 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 	if (ret)
 		goto out_free;
 
-	acl_len = res.acl_len;
-	if (acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, 0, acl_len);
-	else
-		nfs4_write_cached_acl(inode, pages, res.acl_data_offset,
-				      acl_len);
-	if (buf) {
+	/* Handle the case where the passed-in buffer is too short */
+	if (res.acl_flags & NFS4_ACL_TRUNC) {
+		/* Did the user only issue a request for the acl length? */
+		if (buf == NULL)
+			goto out_ok;
 		ret = -ERANGE;
-		if (acl_len > buflen)
-			goto out_free;
-		_copy_from_pages(buf, pages, res.acl_data_offset,
-				acl_len);
+		goto out_free;
 	}
-	ret = acl_len;
+	nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len);
+	if (buf)
+		_copy_from_pages(buf, pages, res.acl_data_offset, res.acl_len);
+out_ok:
+	ret = res.acl_len;
 out_free:
 	for (i = 0; i < npages; i++)
 		if (pages[i])
@@ -3891,10 +3883,13 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 		.rpc_argp	= &arg,
 		.rpc_resp	= &res,
 	};
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
 	int ret, i;
 
 	if (!nfs4_server_supports_acls(server))
 		return -EOPNOTSUPP;
+	if (npages > ARRAY_SIZE(pages))
+		return -ERANGE;
 	i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	if (i < 0)
 		return i;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1bfbd67c556..8dba6bd4855 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -5072,18 +5072,14 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req,
 		 * are stored with the acl data to handle the problem of
 		 * variable length bitmaps.*/
 		res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset;
-
-		/* We ignore &savep and don't do consistency checks on
-		 * the attr length.  Let userspace figure it out.... */
 		res->acl_len = attrlen;
-		if (attrlen > (xdr->nwords << 2)) {
-			if (res->acl_flags & NFS4_ACL_LEN_REQUEST) {
-				/* getxattr interface called with a NULL buf */
-				goto out;
-			}
+
+		/* Check for receive buffer overflow */
+		if (res->acl_len > (xdr->nwords << 2) ||
+		    res->acl_len + res->acl_data_offset > xdr->buf->page_len) {
+			res->acl_flags |= NFS4_ACL_TRUNC;
 			dprintk("NFS: acl reply: attrlen %u > page_len %u\n",
 					attrlen, xdr->nwords << 2);
-			return -EINVAL;
 		}
 	} else
 		status = -EOPNOTSUPP;
@@ -6229,7 +6225,8 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
-	if (decode_getfh(xdr, &res->fh) != 0)
+	status = decode_getfh(xdr, &res->fh);
+	if (status)
 		goto out;
 	decode_getfattr(xdr, res->f_attr, res->server);
 out:
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 239aff7338e..b8eda700584 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1867,6 +1867,7 @@ static int nfs23_validate_mount_data(void *options,
 
 		memcpy(sap, &data->addr, sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
+		args->nfs_server.port = ntohs(data->addr.sin_port);
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
@@ -2564,6 +2565,7 @@ static int nfs4_validate_mount_data(void *options,
 			return -EFAULT;
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
+		args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port);
 
 		if (data->auth_flavourlen) {
 			if (data->auth_flavourlen > 1)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 1f8fc7f9bcd..4b03f56e280 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -265,11 +265,6 @@ static inline const struct nfs_rpc_ops *NFS_PROTO(const struct inode *inode)
 	return NFS_SERVER(inode)->nfs_client->rpc_ops;
 }
 
-static inline __be32 *NFS_COOKIEVERF(const struct inode *inode)
-{
-	return NFS_I(inode)->cookieverf;
-}
-
 static inline unsigned NFS_MINATTRTIMEO(const struct inode *inode)
 {
 	struct nfs_server *nfss = NFS_SERVER(inode);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index ac7c8ae254f..be9cf3c7e79 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -652,7 +652,7 @@ struct nfs_getaclargs {
 };
 
 /* getxattr ACL interface flags */
-#define NFS4_ACL_LEN_REQUEST	0x0001	/* zero length getxattr buffer */
+#define NFS4_ACL_TRUNC		0x0001	/* ACL was truncated */
 struct nfs_getaclres {
 	size_t				acl_len;
 	size_t				acl_data_offset;
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index cff40aa7db6..bf8c49ff753 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -114,6 +114,7 @@ struct rpc_xprt_ops {
 	void		(*set_buffer_size)(struct rpc_xprt *xprt, size_t sndsize, size_t rcvsize);
 	int		(*reserve_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
 	void		(*release_xprt)(struct rpc_xprt *xprt, struct rpc_task *task);
+	void		(*alloc_slot)(struct rpc_xprt *xprt, struct rpc_task *task);
 	void		(*rpcbind)(struct rpc_task *task);
 	void		(*set_port)(struct rpc_xprt *xprt, unsigned short port);
 	void		(*connect)(struct rpc_task *task);
@@ -281,6 +282,8 @@ void			xprt_connect(struct rpc_task *task);
 void			xprt_reserve(struct rpc_task *task);
 int			xprt_reserve_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 int			xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
+void			xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
+void			xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task);
 int			xprt_prepare_transmit(struct rpc_task *task);
 void			xprt_transmit(struct rpc_task *task);
 void			xprt_end_transmit(struct rpc_task *task);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index a5a402a7d21..5d7f61d7559 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -969,11 +969,11 @@ static bool xprt_dynamic_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
 	return false;
 }
 
-static void xprt_alloc_slot(struct rpc_task *task)
+void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
 {
-	struct rpc_xprt	*xprt = task->tk_xprt;
 	struct rpc_rqst *req;
 
+	spin_lock(&xprt->reserve_lock);
 	if (!list_empty(&xprt->free)) {
 		req = list_entry(xprt->free.next, struct rpc_rqst, rq_list);
 		list_del(&req->rq_list);
@@ -994,12 +994,29 @@ static void xprt_alloc_slot(struct rpc_task *task)
 	default:
 		task->tk_status = -EAGAIN;
 	}
+	spin_unlock(&xprt->reserve_lock);
 	return;
 out_init_req:
 	task->tk_status = 0;
 	task->tk_rqstp = req;
 	xprt_request_init(task, xprt);
+	spin_unlock(&xprt->reserve_lock);
+}
+EXPORT_SYMBOL_GPL(xprt_alloc_slot);
+
+void xprt_lock_and_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task)
+{
+	/* Note: grabbing the xprt_lock_write() ensures that we throttle
+	 * new slot allocation if the transport is congested (i.e. when
+	 * reconnecting a stream transport or when out of socket write
+	 * buffer space).
+	 */
+	if (xprt_lock_write(xprt, task)) {
+		xprt_alloc_slot(xprt, task);
+		xprt_release_write(xprt, task);
+	}
 }
+EXPORT_SYMBOL_GPL(xprt_lock_and_alloc_slot);
 
 static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
 {
@@ -1083,20 +1100,9 @@ void xprt_reserve(struct rpc_task *task)
 	if (task->tk_rqstp != NULL)
 		return;
 
-	/* Note: grabbing the xprt_lock_write() here is not strictly needed,
-	 * but ensures that we throttle new slot allocation if the transport
-	 * is congested (e.g. if reconnecting or if we're out of socket
-	 * write buffer space).
-	 */
 	task->tk_timeout = 0;
 	task->tk_status = -EAGAIN;
-	if (!xprt_lock_write(xprt, task))
-		return;
-
-	spin_lock(&xprt->reserve_lock);
-	xprt_alloc_slot(task);
-	spin_unlock(&xprt->reserve_lock);
-	xprt_release_write(xprt, task);
+	xprt->ops->alloc_slot(xprt, task);
 }
 
 static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 06cdbff79e4..5d9202dc7cb 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -713,6 +713,7 @@ static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 static struct rpc_xprt_ops xprt_rdma_procs = {
 	.reserve_xprt		= xprt_rdma_reserve_xprt,
 	.release_xprt		= xprt_release_xprt_cong, /* sunrpc/xprt.c */
+	.alloc_slot		= xprt_alloc_slot,
 	.release_request	= xprt_release_rqst_cong,       /* ditto */
 	.set_retrans_timeout	= xprt_set_retrans_timeout_def, /* ditto */
 	.rpcbind		= rpcb_getport_async,	/* sunrpc/rpcb_clnt.c */
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 400567243f8..a35b8e52e55 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2473,6 +2473,7 @@ static void bc_destroy(struct rpc_xprt *xprt)
 static struct rpc_xprt_ops xs_local_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xs_tcp_release_xprt,
+	.alloc_slot		= xprt_alloc_slot,
 	.rpcbind		= xs_local_rpcbind,
 	.set_port		= xs_local_set_port,
 	.connect		= xs_connect,
@@ -2489,6 +2490,7 @@ static struct rpc_xprt_ops xs_udp_ops = {
 	.set_buffer_size	= xs_udp_set_buffer_size,
 	.reserve_xprt		= xprt_reserve_xprt_cong,
 	.release_xprt		= xprt_release_xprt_cong,
+	.alloc_slot		= xprt_alloc_slot,
 	.rpcbind		= rpcb_getport_async,
 	.set_port		= xs_set_port,
 	.connect		= xs_connect,
@@ -2506,6 +2508,7 @@ static struct rpc_xprt_ops xs_udp_ops = {
 static struct rpc_xprt_ops xs_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xs_tcp_release_xprt,
+	.alloc_slot		= xprt_lock_and_alloc_slot,
 	.rpcbind		= rpcb_getport_async,
 	.set_port		= xs_set_port,
 	.connect		= xs_connect,