Merge git://git.linux-nfs.org/pub/linux/nfs-2.6

* git://git.linux-nfs.org/pub/linux/nfs-2.6:
  NFS: Clean up new multi-segment direct I/O changes
  NFS: Ensure we return zero if applications attempt to write zero bytes
  NFS: Support multiple segment iovecs in the NFS direct I/O path
  NFS: Introduce iovec I/O helpers to fs/nfs/direct.c
  SUNRPC: Add missing "space" to net/sunrpc/auth_gss.c
  SUNRPC: make sunrpc/xprtsock.c:xs_setup_{udp,tcp}() static
  NFS: fs/nfs/dir.c should #include "internal.h"
  NFS: make nfs_wb_page_priority() static
  NFS: mount failure causes bad page state
  SUNRPC: remove NFS/RDMA client's binary sysctls
  kernel BUG at fs/nfs/namespace.c:108! - can be triggered by bad server
  sunrpc: rpc_pipe_poll may miss available data in some cases
  sunrpc: return error if unsupported enctype or cksumtype is encountered
  sunrpc: gss_pipe_downcall(), don't assume all errors are transient
  NFS: Fix the ustat() regression

5 files changed, 138 insertions, 100 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 3533453..f697b5c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -38,6 +38,7 @@
 #include "nfs4_fs.h"
 #include "delegation.h"
 #include "iostat.h"
+#include "internal.h"
 
 /* #define NFS_DEBUG_VERBOSE 1 */
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index afcab00..5e8d82f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -263,17 +263,19 @@ static const struct rpc_call_ops nfs_read_direct_ops = {
  * handled automatically by nfs_direct_read_result().  Otherwise, if
  * no requests have been sent, just return an error.
  */
-static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned long user_addr, size_t count, loff_t pos)
+static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
+						const struct iovec *iov,
+						loff_t pos)
 {
 	struct nfs_open_context *ctx = dreq->ctx;
 	struct inode *inode = ctx->path.dentry->d_inode;
+	unsigned long user_addr = (unsigned long)iov->iov_base;
+	size_t count = iov->iov_len;
 	size_t rsize = NFS_SERVER(inode)->rsize;
 	unsigned int pgbase;
 	int result;
 	ssize_t started = 0;
 
-	get_dreq(dreq);
-
 	do {
 		struct nfs_read_data *data;
 		size_t bytes;
@@ -347,15 +349,46 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo
 		count -= bytes;
 	} while (count != 0);
 
+	if (started)
+		return started;
+	return result < 0 ? (ssize_t) result : -EFAULT;
+}
+
+static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
+					      const struct iovec *iov,
+					      unsigned long nr_segs,
+					      loff_t pos)
+{
+	ssize_t result = -EINVAL;
+	size_t requested_bytes = 0;
+	unsigned long seg;
+
+	get_dreq(dreq);
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		const struct iovec *vec = &iov[seg];
+		result = nfs_direct_read_schedule_segment(dreq, vec, pos);
+		if (result < 0)
+			break;
+		requested_bytes += result;
+		if ((size_t)result < vec->iov_len)
+			break;
+		pos += vec->iov_len;
+	}
+
 	if (put_dreq(dreq))
 		nfs_direct_complete(dreq);
 
-	if (started)
+	if (requested_bytes != 0)
 		return 0;
-	return result < 0 ? (ssize_t) result : -EFAULT;
+
+	if (result < 0)
+		return result;
+	return -EIO;
 }
 
-static ssize_t nfs_direct_read(struct kiocb *iocb, unsigned long user_addr, size_t count, loff_t pos)
+static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
+			       unsigned long nr_segs, loff_t pos)
 {
 	ssize_t result = 0;
 	sigset_t oldset;
@@ -372,9 +405,8 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, unsigned long user_addr, size
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	nfs_add_stats(inode, NFSIOS_DIRECTREADBYTES, count);
 	rpc_clnt_sigmask(clnt, &oldset);
-	result = nfs_direct_read_schedule(dreq, user_addr, count, pos);
+	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 	rpc_clnt_sigunmask(clnt, &oldset);
@@ -601,17 +633,19 @@ static const struct rpc_call_ops nfs_write_direct_ops = {
  * handled automatically by nfs_direct_write_result().  Otherwise, if
  * no requests have been sent, just return an error.
  */
-static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned long user_addr, size_t count, loff_t pos, int sync)
+static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
+						 const struct iovec *iov,
+						 loff_t pos, int sync)
 {
 	struct nfs_open_context *ctx = dreq->ctx;
 	struct inode *inode = ctx->path.dentry->d_inode;
+	unsigned long user_addr = (unsigned long)iov->iov_base;
+	size_t count = iov->iov_len;
 	size_t wsize = NFS_SERVER(inode)->wsize;
 	unsigned int pgbase;
 	int result;
 	ssize_t started = 0;
 
-	get_dreq(dreq);
-
 	do {
 		struct nfs_write_data *data;
 		size_t bytes;
@@ -689,15 +723,48 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l
 		count -= bytes;
 	} while (count != 0);
 
+	if (started)
+		return started;
+	return result < 0 ? (ssize_t) result : -EFAULT;
+}
+
+static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
+					       const struct iovec *iov,
+					       unsigned long nr_segs,
+					       loff_t pos, int sync)
+{
+	ssize_t result = 0;
+	size_t requested_bytes = 0;
+	unsigned long seg;
+
+	get_dreq(dreq);
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		const struct iovec *vec = &iov[seg];
+		result = nfs_direct_write_schedule_segment(dreq, vec,
+							   pos, sync);
+		if (result < 0)
+			break;
+		requested_bytes += result;
+		if ((size_t)result < vec->iov_len)
+			break;
+		pos += vec->iov_len;
+	}
+
 	if (put_dreq(dreq))
-		nfs_direct_write_complete(dreq, inode);
+		nfs_direct_write_complete(dreq, dreq->inode);
 
-	if (started)
+	if (requested_bytes != 0)
 		return 0;
-	return result < 0 ? (ssize_t) result : -EFAULT;
+
+	if (result < 0)
+		return result;
+	return -EIO;
 }
 
-static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, size_t count, loff_t pos)
+static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
+				unsigned long nr_segs, loff_t pos,
+				size_t count)
 {
 	ssize_t result = 0;
 	sigset_t oldset;
@@ -720,10 +787,8 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, unsigned long user_addr, siz
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	nfs_add_stats(inode, NFSIOS_DIRECTWRITTENBYTES, count);
-
 	rpc_clnt_sigmask(clnt, &oldset);
-	result = nfs_direct_write_schedule(dreq, user_addr, count, pos, sync);
+	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 	rpc_clnt_sigunmask(clnt, &oldset);
@@ -759,21 +824,16 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
-	/* XXX: temporary */
-	const char __user *buf = iov[0].iov_base;
-	size_t count = iov[0].iov_len;
+	size_t count;
+
+	count = iov_length(iov, nr_segs);
+	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
 
-	dprintk("nfs: direct read(%s/%s, %lu@%Ld)\n",
+	dprintk("nfs: direct read(%s/%s, %zd@%Ld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name,
-		(unsigned long) count, (long long) pos);
-
-	if (nr_segs != 1)
-		goto out;
+		count, (long long) pos);
 
-	retval = -EFAULT;
-	if (!access_ok(VERIFY_WRITE, buf, count))
-		goto out;
 	retval = 0;
 	if (!count)
 		goto out;
@@ -782,7 +842,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	if (retval)
 		goto out;
 
-	retval = nfs_direct_read(iocb, (unsigned long) buf, count, pos);
+	retval = nfs_direct_read(iocb, iov, nr_segs, pos);
 	if (retval > 0)
 		iocb->ki_pos = pos + retval;
 
@@ -821,21 +881,21 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t retval = -EINVAL;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
-	/* XXX: temporary */
-	const char __user *buf = iov[0].iov_base;
-	size_t count = iov[0].iov_len;
+	size_t count;
+
+	count = iov_length(iov, nr_segs);
+	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
 
-	dprintk("nfs: direct write(%s/%s, %lu@%Ld)\n",
+	dfprintk(VFS, "nfs: direct write(%s/%s, %zd@%Ld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name,
-		(unsigned long) count, (long long) pos);
-
-	if (nr_segs != 1)
-		goto out;
+		count, (long long) pos);
 
 	retval = generic_write_checks(file, &pos, &count, 0);
 	if (retval)
 		goto out;
+	if (!count)
+		goto out;	/* return 0 */
 
 	retval = -EINVAL;
 	if ((ssize_t) count < 0)
@@ -844,15 +904,11 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!count)
 		goto out;
 
-	retval = -EFAULT;
-	if (!access_ok(VERIFY_READ, buf, count))
-		goto out;
-
 	retval = nfs_sync_mapping(mapping);
 	if (retval)
 		goto out;
 
-	retval = nfs_direct_write(iocb, (unsigned long) buf, count, pos);
+	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
 
 	if (retval > 0)
 		iocb->ki_pos = pos + retval;
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 522e5ad..0ee4384 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -43,6 +43,25 @@
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
 /*
+ * Set the superblock root dentry.
+ * Note that this function frees the inode in case of error.
+ */
+static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *inode)
+{
+	/* The mntroot acts as the dummy root dentry for this superblock */
+	if (sb->s_root == NULL) {
+		sb->s_root = d_alloc_root(inode);
+		if (sb->s_root == NULL) {
+			iput(inode);
+			return -ENOMEM;
+		}
+		/* Circumvent igrab(): we know the inode is not being freed */
+		atomic_inc(&inode->i_count);
+	}
+	return 0;
+}
+
+/*
  * get an NFS2/NFS3 root dentry from the root filehandle
  */
 struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
@@ -54,33 +73,6 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 	struct inode *inode;
 	int error;
 
-	/* create a dummy root dentry with dummy inode for this superblock */
-	if (!sb->s_root) {
-		struct nfs_fh dummyfh;
-		struct dentry *root;
-		struct inode *iroot;
-
-		memset(&dummyfh, 0, sizeof(dummyfh));
-		memset(&fattr, 0, sizeof(fattr));
-		nfs_fattr_init(&fattr);
-		fattr.valid = NFS_ATTR_FATTR;
-		fattr.type = NFDIR;
-		fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR;
-		fattr.nlink = 2;
-
-		iroot = nfs_fhget(sb, &dummyfh, &fattr);
-		if (IS_ERR(iroot))
-			return ERR_PTR(PTR_ERR(iroot));
-
-		root = d_alloc_root(iroot);
-		if (!root) {
-			iput(iroot);
-			return ERR_PTR(-ENOMEM);
-		}
-
-		sb->s_root = root;
-	}
-
 	/* get the actual root for this mount */
 	fsinfo.fattr = &fattr;
 
@@ -96,6 +88,10 @@ struct dentry *nfs_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 		return ERR_PTR(PTR_ERR(inode));
 	}
 
+	error = nfs_superblock_set_dummy_root(sb, inode);
+	if (error != 0)
+		return ERR_PTR(error);
+
 	/* root dentries normally start off anonymous and get spliced in later
 	 * if the dentry tree reaches them; however if the dentry already
 	 * exists, we'll pick it up at this point and use it as the root
@@ -241,33 +237,6 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 
 	dprintk("--> nfs4_get_root()\n");
 
-	/* create a dummy root dentry with dummy inode for this superblock */
-	if (!sb->s_root) {
-		struct nfs_fh dummyfh;
-		struct dentry *root;
-		struct inode *iroot;
-
-		memset(&dummyfh, 0, sizeof(dummyfh));
-		memset(&fattr, 0, sizeof(fattr));
-		nfs_fattr_init(&fattr);
-		fattr.valid = NFS_ATTR_FATTR;
-		fattr.type = NFDIR;
-		fattr.mode = S_IFDIR | S_IRUSR | S_IWUSR;
-		fattr.nlink = 2;
-
-		iroot = nfs_fhget(sb, &dummyfh, &fattr);
-		if (IS_ERR(iroot))
-			return ERR_PTR(PTR_ERR(iroot));
-
-		root = d_alloc_root(iroot);
-		if (!root) {
-			iput(iroot);
-			return ERR_PTR(-ENOMEM);
-		}
-
-		sb->s_root = root;
-	}
-
 	/* get the info about the server and filesystem */
 	error = nfs4_server_capabilities(server, mntfh);
 	if (error < 0) {
@@ -289,6 +258,10 @@ struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh)
 		return ERR_PTR(PTR_ERR(inode));
 	}
 
+	error = nfs_superblock_set_dummy_root(sb, inode);
+	if (error != 0)
+		return ERR_PTR(error);
+
 	/* root dentries normally start off anonymous and get spliced in later
 	 * if the dentry tree reaches them; however if the dentry already
 	 * exists, we'll pick it up at this point and use it as the root
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index fa517ae..2426e71 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1054,10 +1054,11 @@ static int nfs_validate_mount_data(void *options,
 {
 	struct nfs_mount_data *data = (struct nfs_mount_data *)options;
 
+	memset(args, 0, sizeof(*args));
+
 	if (data == NULL)
 		goto out_no_data;
 
-	memset(args, 0, sizeof(*args));
 	args->flags		= (NFS_MOUNT_VER3 | NFS_MOUNT_TCP);
 	args->rsize		= NFS_MAX_FILE_IO_SIZE;
 	args->wsize		= NFS_MAX_FILE_IO_SIZE;
@@ -1474,6 +1475,11 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags,
 		error = PTR_ERR(mntroot);
 		goto error_splat_super;
 	}
+	if (mntroot->d_inode->i_op != &nfs_dir_inode_operations) {
+		dput(mntroot);
+		error = -ESTALE;
+		goto error_splat_super;
+	}
 
 	s->s_flags |= MS_ACTIVE;
 	mnt->mnt_sb = s;
@@ -1531,10 +1537,11 @@ static int nfs4_validate_mount_data(void *options,
 	struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
 	char *c;
 
+	memset(args, 0, sizeof(*args));
+
 	if (data == NULL)
 		goto out_no_data;
 
-	memset(args, 0, sizeof(*args));
 	args->rsize		= NFS_MAX_FILE_IO_SIZE;
 	args->wsize		= NFS_MAX_FILE_IO_SIZE;
 	args->timeo		= 600;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 89527a4..51cc1bd 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1436,7 +1436,8 @@ out:
 	return ret;
 }
 
-int nfs_wb_page_priority(struct inode *inode, struct page *page, int how)
+static int nfs_wb_page_priority(struct inode *inode, struct page *page,
+				int how)
 {
 	loff_t range_start = page_offset(page);
 	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);