Merge branch 'for-2.6.34' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.34' of git://linux-nfs.org/~bfields/linux: (22 commits)
  nfsd4: fix minor memory leak
  svcrpc: treat uid's as unsigned
  nfsd: ensure sockets are closed on error
  Revert "sunrpc: move the close processing after do recvfrom method"
  Revert "sunrpc: fix peername failed on closed listener"
  sunrpc: remove unnecessary svc_xprt_put
  NFSD: NFSv4 callback client should use RPC_TASK_SOFTCONN
  xfs_export_operations.commit_metadata
  commit_metadata export operation replacing nfsd_sync_dir
  lockd: don't clear sm_monitored on nsm_reboot_lookup
  lockd: release reference to nsm_handle in nlm_host_rebooted
  nfsd: Use vfs_fsync_range() in nfsd_commit
  NFSD: Create PF_INET6 listener in write_ports
  SUNRPC: NFS kernel APIs shouldn't return ENOENT for "transport not found"
  SUNRPC: Bury "#ifdef IPV6" in svc_create_xprt()
  NFSD: Support AF_INET6 in svc_addsock() function
  SUNRPC: Use rpc_pton() in ip_map_parse()
  nfsd: 4.1 has an rfc number
  nfsd41: Create the recovery entry for the NFSv4.1 client
  nfsd: use vfs_fsync for non-directories
  ...

6 files changed, 100 insertions, 92 deletions

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index c6eed2a3b09..4bc22c763de 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -525,6 +525,8 @@ static struct rpc_cred *callback_cred;
 
 int set_callback_cred(void)
 {
+	if (callback_cred)
+		return 0;
 	callback_cred = rpc_lookup_machine_cred();
 	if (!callback_cred)
 		return -ENOMEM;
@@ -542,7 +544,8 @@ void do_probe_callback(struct nfs4_client *clp)
 	};
 	int status;
 
-	status = rpc_call_async(cb->cb_client, &msg, RPC_TASK_SOFT,
+	status = rpc_call_async(cb->cb_client, &msg,
+				RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
 				&nfsd4_cb_probe_ops, (void *)clp);
 	if (status) {
 		warn_no_callback_path(clp, status);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 5a754f7b71e..98fb98e330b 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -119,9 +119,7 @@ out_no_tfm:
 static void
 nfsd4_sync_rec_dir(void)
 {
-	mutex_lock(&rec_dir.dentry->d_inode->i_mutex);
-	nfsd_sync_dir(rec_dir.dentry);
-	mutex_unlock(&rec_dir.dentry->d_inode->i_mutex);
+	vfs_fsync(NULL, rec_dir.dentry, 0);
 }
 
 int
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fcafe6087f6..c97fddbd17d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2482,8 +2482,10 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	}
 	memcpy(&open->op_stateid, &stp->st_stateid, sizeof(stateid_t));
 
-	if (nfsd4_has_session(&resp->cstate))
+	if (nfsd4_has_session(&resp->cstate)) {
 		open->op_stateowner->so_confirmed = 1;
+		nfsd4_create_clid_dir(open->op_stateowner->so_client);
+	}
 
 	/*
 	* Attempt to hand out a delegation. No error return, because the
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index bbf72d8f9fc..78c7e24e512 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1434,7 +1434,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 		}
 		op->opnum = ntohl(*argp->p++);
 
-		if (op->opnum >= OP_ACCESS && op->opnum < ops->nops)
+		if (op->opnum >= FIRST_NFS4_OP && op->opnum <= LAST_NFS4_OP)
 			op->status = ops->decoders[op->opnum](argp, &op->u);
 		else {
 			op->opnum = OP_ILLEGAL;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 2604c3e70ea..0f0e77f2012 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -988,6 +988,7 @@ static ssize_t __write_ports_delfd(char *buf)
 static ssize_t __write_ports_addxprt(char *buf)
 {
 	char transport[16];
+	struct svc_xprt *xprt;
 	int port, err;
 
 	if (sscanf(buf, "%15s %4u", transport, &port) != 2)
@@ -1002,13 +1003,24 @@ static ssize_t __write_ports_addxprt(char *buf)
 
 	err = svc_create_xprt(nfsd_serv, transport,
 				PF_INET, port, SVC_SOCK_ANONYMOUS);
-	if (err < 0) {
-		/* Give a reasonable perror msg for bad transport string */
-		if (err == -ENOENT)
-			err = -EPROTONOSUPPORT;
-		return err;
-	}
+	if (err < 0)
+		goto out_err;
+
+	err = svc_create_xprt(nfsd_serv, transport,
+				PF_INET6, port, SVC_SOCK_ANONYMOUS);
+	if (err < 0 && err != -EAFNOSUPPORT)
+		goto out_close;
 	return 0;
+out_close:
+	xprt = svc_find_xprt(nfsd_serv, transport, PF_INET, port);
+	if (xprt != NULL) {
+		svc_close_xprt(xprt);
+		svc_xprt_put(xprt);
+	}
+out_err:
+	/* Decrease the count, but don't shut down the service */
+	nfsd_serv->sv_nrthreads--;
+	return err;
 }
 
 /*
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 8eca17df4f6..a11b0e8678e 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -26,6 +26,8 @@
 #include <linux/jhash.h>
 #include <linux/ima.h>
 #include <asm/uaccess.h>
+#include <linux/exportfs.h>
+#include <linux/writeback.h>
 
 #ifdef CONFIG_NFSD_V3
 #include "xdr3.h"
@@ -270,6 +272,32 @@ out:
 	return err;
 }
 
+/*
+ * Commit metadata changes to stable storage.
+ */
+static int
+commit_metadata(struct svc_fh *fhp)
+{
+	struct inode *inode = fhp->fh_dentry->d_inode;
+	const struct export_operations *export_ops = inode->i_sb->s_export_op;
+	int error = 0;
+
+	if (!EX_ISSYNC(fhp->fh_export))
+		return 0;
+
+	if (export_ops->commit_metadata) {
+		error = export_ops->commit_metadata(inode);
+	} else {
+		struct writeback_control wbc = {
+			.sync_mode = WB_SYNC_ALL,
+			.nr_to_write = 0, /* metadata only */
+		};
+
+		error = sync_inode(inode, &wbc);
+	}
+
+	return error;
+}
 
 /*
  * Set various file attributes.
@@ -767,43 +795,6 @@ nfsd_close(struct file *filp)
 }
 
 /*
- * Sync a file
- * As this calls fsync (not fdatasync) there is no need for a write_inode
- * after it.
- */
-static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
-			      const struct file_operations *fop)
-{
-	struct inode *inode = dp->d_inode;
-	int (*fsync) (struct file *, struct dentry *, int);
-	int err;
-
-	err = filemap_write_and_wait(inode->i_mapping);
-	if (err == 0 && fop && (fsync = fop->fsync))
-		err = fsync(filp, dp, 0);
-	return err;
-}
-
-static int
-nfsd_sync(struct file *filp)
-{
-        int err;
-	struct inode *inode = filp->f_path.dentry->d_inode;
-	dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name);
-	mutex_lock(&inode->i_mutex);
-	err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
-	mutex_unlock(&inode->i_mutex);
-
-	return err;
-}
-
-int
-nfsd_sync_dir(struct dentry *dp)
-{
-	return nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
-}
-
-/*
  * Obtain the readahead parameters for the file
  * specified by (dev, ino).
  */
@@ -1006,7 +997,7 @@ static int wait_for_concurrent_writes(struct file *file)
 
 	if (inode->i_state & I_DIRTY) {
 		dprintk("nfsd: write sync %d\n", task_pid_nr(current));
-		err = nfsd_sync(file);
+		err = vfs_fsync(file, file->f_path.dentry, 0);
 	}
 	last_ino = inode->i_ino;
 	last_dev = inode->i_sb->s_dev;
@@ -1154,8 +1145,9 @@ out:
 #ifdef CONFIG_NFSD_V3
 /*
  * Commit all pending writes to stable storage.
- * Strictly speaking, we could sync just the indicated file region here,
- * but there's currently no way we can ask the VFS to do so.
+ *
+ * Note: we only guarantee that data that lies within the range specified
+ * by the 'offset' and 'count' parameters will be synced.
  *
  * Unfortunately we cannot lock the file to make sure we return full WCC
  * data to the client, as locking happens lower down in the filesystem.
@@ -1165,23 +1157,32 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
                loff_t offset, unsigned long count)
 {
 	struct file	*file;
-	__be32		err;
+	loff_t		end = LLONG_MAX;
+	__be32		err = nfserr_inval;
 
-	if ((u64)count > ~(u64)offset)
-		return nfserr_inval;
+	if (offset < 0)
+		goto out;
+	if (count != 0) {
+		end = offset + (loff_t)count - 1;
+		if (end < offset)
+			goto out;
+	}
 
 	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
 	if (err)
-		return err;
+		goto out;
 	if (EX_ISSYNC(fhp->fh_export)) {
-		if (file->f_op && file->f_op->fsync) {
-			err = nfserrno(nfsd_sync(file));
-		} else {
+		int err2 = vfs_fsync_range(file, file->f_path.dentry,
+				offset, end, 0);
+
+		if (err2 != -EINVAL)
+			err = nfserrno(err2);
+		else
 			err = nfserr_notsupp;
-		}
 	}
 
 	nfsd_close(file);
+out:
 	return err;
 }
 #endif /* CONFIG_NFSD_V3 */
@@ -1334,12 +1335,14 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto out_nfserr;
 	}
 
-	if (EX_ISSYNC(fhp->fh_export)) {
-		err = nfserrno(nfsd_sync_dir(dentry));
-		write_inode_now(dchild->d_inode, 1);
-	}
+	err = nfsd_create_setattr(rqstp, resfhp, iap);
 
-	err2 = nfsd_create_setattr(rqstp, resfhp, iap);
+	/*
+	 * nfsd_setattr already committed the child.  Transactional filesystems
+	 * had a chance to commit changes for both parent and child
+	 * simultaneously making the following commit_metadata a noop.
+	 */
+	err2 = nfserrno(commit_metadata(fhp));
 	if (err2)
 		err = err2;
 	mnt_drop_write(fhp->fh_export->ex_path.mnt);
@@ -1371,7 +1374,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	struct dentry	*dentry, *dchild = NULL;
 	struct inode	*dirp;
 	__be32		err;
-	__be32		err2;
 	int		host_err;
 	__u32		v_mtime=0, v_atime=0;
 
@@ -1466,11 +1468,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (created)
 		*created = 1;
 
-	if (EX_ISSYNC(fhp->fh_export)) {
-		err = nfserrno(nfsd_sync_dir(dentry));
-		/* setattr will sync the child (or not) */
-	}
-
 	nfsd_check_ignore_resizing(iap);
 
 	if (createmode == NFS3_CREATE_EXCLUSIVE) {
@@ -1485,9 +1482,13 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	}
 
  set_attr:
-	err2 = nfsd_create_setattr(rqstp, resfhp, iap);
-	if (err2)
-		err = err2;
+	err = nfsd_create_setattr(rqstp, resfhp, iap);
+
+	/*
+	 * nfsd_setattr already committed the child (and possibly also the parent).
+	 */
+	if (!err)
+		err = nfserrno(commit_metadata(fhp));
 
 	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 	/*
@@ -1602,12 +1603,9 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		}
 	} else
 		host_err = vfs_symlink(dentry->d_inode, dnew, path);
-
-	if (!host_err) {
-		if (EX_ISSYNC(fhp->fh_export))
-			host_err = nfsd_sync_dir(dentry);
-	}
 	err = nfserrno(host_err);
+	if (!err)
+		err = nfserrno(commit_metadata(fhp));
 	fh_unlock(fhp);
 
 	mnt_drop_write(fhp->fh_export->ex_path.mnt);
@@ -1669,11 +1667,9 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	}
 	host_err = vfs_link(dold, dirp, dnew);
 	if (!host_err) {
-		if (EX_ISSYNC(ffhp->fh_export)) {
-			err = nfserrno(nfsd_sync_dir(ddir));
-			write_inode_now(dest, 1);
-		}
-		err = 0;
+		err = nfserrno(commit_metadata(ffhp));
+		if (!err)
+			err = nfserrno(commit_metadata(tfhp));
 	} else {
 		if (host_err == -EXDEV && rqstp->rq_vers == 2)
 			err = nfserr_acces;
@@ -1769,10 +1765,10 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		goto out_dput_new;
 
 	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
-	if (!host_err && EX_ISSYNC(tfhp->fh_export)) {
-		host_err = nfsd_sync_dir(tdentry);
+	if (!host_err) {
+		host_err = commit_metadata(tfhp);
 		if (!host_err)
-			host_err = nfsd_sync_dir(fdentry);
+			host_err = commit_metadata(ffhp);
 	}
 
 	mnt_drop_write(ffhp->fh_export->ex_path.mnt);
@@ -1853,12 +1849,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 
 	dput(rdentry);
 
-	if (host_err)
-		goto out_drop;
-	if (EX_ISSYNC(fhp->fh_export))
-		host_err = nfsd_sync_dir(dentry);
+	if (!host_err)
+		host_err = commit_metadata(fhp);
 
-out_drop:
 	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 out_nfserr:
 	err = nfserrno(host_err);