Merge branch 'master' of /usr/src/ntfs-2.6/

15 files changed, 122 insertions, 93 deletions

diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 4684eb7d48c6..b3ad0bd0312f 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -501,11 +501,16 @@ int hostfs_commit_write(struct file *file, struct page *page, unsigned from,
 	long long start;
 	int err = 0;
 
-	start = (long long) (page->index << PAGE_CACHE_SHIFT) + from;
+	start = (((long long) page->index) << PAGE_CACHE_SHIFT) + from;
 	buffer = kmap(page);
 	err = write_file(FILE_HOSTFS_I(file)->fd, &start, buffer + from,
 			 to - from);
 	if(err > 0) err = 0;
+
+	/* Actually, if !err, write_file has added to-from to start, so, despite
+	 * the appearance, we are comparing i_size against the _last_ written
+	 * location, as we should. */
+
 	if(!err && (start > inode->i_size))
 		inode->i_size = start;
 
@@ -910,10 +915,8 @@ static struct inode_operations hostfs_dir_iops = {
 int hostfs_link_readpage(struct file *file, struct page *page)
 {
 	char *buffer, *name;
-	long long start;
 	int err;
 
-	start = page->index << PAGE_CACHE_SHIFT;
 	buffer = kmap(page);
 	name = inode_name(page->mapping->host, 0);
 	if(name == NULL) return(-ENOMEM);
diff --git a/fs/inotify.c b/fs/inotify.c
index bf7ce1d2412b..2fecb7af4a77 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -364,11 +364,12 @@ static int inotify_dev_get_wd(struct inotify_device *dev,
 /*
  * find_inode - resolve a user-given path to a specific inode and return a nd
  */
-static int find_inode(const char __user *dirname, struct nameidata *nd)
+static int find_inode(const char __user *dirname, struct nameidata *nd,
+		      unsigned flags)
 {
 	int error;
 
-	error = __user_walk(dirname, LOOKUP_FOLLOW, nd);
+	error = __user_walk(dirname, flags, nd);
 	if (error)
 		return error;
 	/* you can only watch an inode if you have read permissions on it */
@@ -933,6 +934,7 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
 	struct file *filp;
 	int ret, fput_needed;
 	int mask_add = 0;
+	unsigned flags = 0;
 
 	filp = fget_light(fd, &fput_needed);
 	if (unlikely(!filp))
@@ -944,7 +946,12 @@ asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
 		goto fput_and_out;
 	}
 
-	ret = find_inode(path, &nd);
+	if (!(mask & IN_DONT_FOLLOW))
+		flags |= LOOKUP_FOLLOW;
+	if (mask & IN_ONLYDIR)
+		flags |= LOOKUP_DIRECTORY;
+
+	ret = find_inode(path, &nd, flags);
 	if (unlikely(ret))
 		goto fput_and_out;
 
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 006bb9e14579..3eaf6e701087 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -157,6 +157,8 @@ void nlmclnt_mark_reclaim(struct nlm_host *host)
 		inode = fl->fl_file->f_dentry->d_inode;
 		if (inode->i_sb->s_magic != NFS_SUPER_MAGIC)
 			continue;
+		if (fl->fl_u.nfs_fl.owner == NULL)
+			continue;
 		if (fl->fl_u.nfs_fl.owner->host != host)
 			continue;
 		if (!(fl->fl_u.nfs_fl.flags & NFS_LCK_GRANTED))
@@ -226,6 +228,8 @@ restart:
 		inode = fl->fl_file->f_dentry->d_inode;
 		if (inode->i_sb->s_magic != NFS_SUPER_MAGIC)
 			continue;
+		if (fl->fl_u.nfs_fl.owner == NULL)
+			continue;
 		if (fl->fl_u.nfs_fl.owner->host != host)
 			continue;
 		if (!(fl->fl_u.nfs_fl.flags & NFS_LCK_RECLAIM))
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index b497c71384e8..079228817603 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -678,15 +678,9 @@ nfs_file_direct_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t
 	if (!count)
 		goto out;
 
-	if (mapping->nrpages) {
-		retval = filemap_fdatawrite(mapping);
-		if (retval == 0)
-			retval = nfs_wb_all(inode);
-		if (retval == 0)
-			retval = filemap_fdatawait(mapping);
-		if (retval)
-			goto out;
-	}
+	retval = nfs_sync_mapping(mapping);
+	if (retval)
+		goto out;
 
 	retval = nfs_direct_read(inode, ctx, &iov, pos, 1);
 	if (retval > 0)
@@ -764,15 +758,9 @@ nfs_file_direct_write(struct kiocb *iocb, const char __user *buf, size_t count,
 	if (!count)
 		goto out;
 
-	if (mapping->nrpages) {
-		retval = filemap_fdatawrite(mapping);
-		if (retval == 0)
-			retval = nfs_wb_all(inode);
-		if (retval == 0)
-			retval = filemap_fdatawait(mapping);
-		if (retval)
-			goto out;
-	}
+	retval = nfs_sync_mapping(mapping);
+	if (retval)
+		goto out;
 
 	retval = nfs_direct_write(inode, ctx, &iov, pos, 1);
 	if (mapping->nrpages)
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 57d3e77d97ee..7a79fbe9f539 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -433,11 +433,7 @@ static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
 	 * Flush all pending writes before doing anything
 	 * with locks..
 	 */
-	filemap_fdatawrite(filp->f_mapping);
-	down(&inode->i_sem);
-	nfs_wb_all(inode);
-	up(&inode->i_sem);
-	filemap_fdatawait(filp->f_mapping);
+	nfs_sync_mapping(filp->f_mapping);
 
 	/* NOTE: special case
 	 * 	If we're signalled while cleaning up locks on process exit, we
@@ -465,15 +461,8 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
 	 * Flush all pending writes before doing anything
 	 * with locks..
 	 */
-	status = filemap_fdatawrite(filp->f_mapping);
-	if (status == 0) {
-		down(&inode->i_sem);
-		status = nfs_wb_all(inode);
-		up(&inode->i_sem);
-		if (status == 0)
-			status = filemap_fdatawait(filp->f_mapping);
-	}
-	if (status < 0)
+	status = nfs_sync_mapping(filp->f_mapping);
+	if (status != 0)
 		goto out;
 
 	lock_kernel();
@@ -497,11 +486,7 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
 	 * Make sure we clear the cache whenever we try to get the lock.
 	 * This makes locking act as a cache coherency point.
 	 */
-	filemap_fdatawrite(filp->f_mapping);
-	down(&inode->i_sem);
-	nfs_wb_all(inode);	/* we may have slept */
-	up(&inode->i_sem);
-	filemap_fdatawait(filp->f_mapping);
+	nfs_sync_mapping(filp->f_mapping);
 	nfs_zap_caches(inode);
 out:
 	rpc_clnt_sigunmask(NFS_CLIENT(inode), &oldset);
@@ -524,7 +509,8 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 		return -EINVAL;
 
 	/* No mandatory locks over NFS */
-	if ((inode->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
+	if ((inode->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID &&
+	    fl->fl_type != F_UNLCK)
 		return -ENOLCK;
 
 	if (IS_GETLK(cmd))
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index afd75d0463fd..432f41cd75e6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -640,6 +640,27 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
 	return 0;
 }
 
+/**
+ * nfs_sync_mapping - helper to flush all mmapped dirty data to disk
+ */
+int nfs_sync_mapping(struct address_space *mapping)
+{
+	int ret;
+
+	if (mapping->nrpages == 0)
+		return 0;
+	unmap_mapping_range(mapping, 0, 0, 0);
+	ret = filemap_fdatawrite(mapping);
+	if (ret != 0)
+		goto out;
+	ret = filemap_fdatawait(mapping);
+	if (ret != 0)
+		goto out;
+	ret = nfs_wb_all(mapping->host);
+out:
+	return ret;
+}
+
 /*
  * Invalidate the local caches
  */
@@ -1179,11 +1200,8 @@ void nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
-		if (S_ISREG(inode->i_mode)) {
-			if (filemap_fdatawrite(mapping) == 0)
-				filemap_fdatawait(mapping);
-			nfs_wb_all(inode);
-		}
+		if (S_ISREG(inode->i_mode))
+			nfs_sync_mapping(mapping);
 		invalidate_inode_pages2(mapping);
 
 		spin_lock(&inode->i_lock);
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 7cbf0682b2f0..fc95c4df6693 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -107,7 +107,7 @@ static int nfsacld_proc_setacl(struct svc_rqst * rqstp,
 	dprintk("nfsd: SETACL(2acl)   %s\n", SVCFH_fmt(&argp->fh));
 
 	fh = fh_copy(&resp->fh, &argp->fh);
-	nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_SATTR);
 
 	if (!nfserr) {
 		nfserr = nfserrno( nfsd_set_posix_acl(
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 64ba40572fea..16e10c170aed 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -101,7 +101,7 @@ static int nfsd3_proc_setacl(struct svc_rqst * rqstp,
 	int nfserr = 0;
 
 	fh = fh_copy(&resp->fh, &argp->fh);
-	nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_NOP);
+	nfserr = fh_verify(rqstp, &resp->fh, 0, MAY_SATTR);
 
 	if (!nfserr) {
 		nfserr = nfserrno( nfsd_set_posix_acl(
diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig
index deb25b661f04..656bc43431b9 100644
--- a/fs/partitions/Kconfig
+++ b/fs/partitions/Kconfig
@@ -203,7 +203,7 @@ config ULTRIX_PARTITION
 
 config SUN_PARTITION
 	bool "Sun partition tables support" if PARTITION_ADVANCED
-	default y if (SPARC32 || SPARC64 || SUN3 || SUN3X)
+	default y if (SPARC || SUN3 || SUN3X)
 	---help---
 	  Like most systems, SunOS uses its own hard disk partition table
 	  format, incompatible with all others. Saying Y here allows you to
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index b638fb500743..72b431d0a0a4 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -54,6 +54,18 @@ proc_file_read(struct file *file, char __user *buf, size_t nbytes,
 	ssize_t	n, count;
 	char	*start;
 	struct proc_dir_entry * dp;
+	unsigned long long pos;
+
+	/*
+	 * Gaah, please just use "seq_file" instead. The legacy /proc
+	 * interfaces cut loff_t down to off_t for reads, and ignore
+	 * the offset entirely for writes..
+	 */
+	pos = *ppos;
+	if (pos > MAX_NON_LFS)
+		return 0;
+	if (nbytes > MAX_NON_LFS - pos)
+		nbytes = MAX_NON_LFS - pos;
 
 	dp = PDE(inode);
 	if (!(page = (char*) __get_free_page(GFP_KERNEL)))
@@ -202,30 +214,17 @@ proc_file_write(struct file *file, const char __user *buffer,
 static loff_t
 proc_file_lseek(struct file *file, loff_t offset, int orig)
 {
-    lock_kernel();
-
-    switch (orig) {
-    case 0:
-	if (offset < 0)
-	    goto out;
-	file->f_pos = offset;
-	unlock_kernel();
-	return(file->f_pos);
-    case 1:
-	if (offset + file->f_pos < 0)
-	    goto out;
-	file->f_pos += offset;
-	unlock_kernel();
-	return(file->f_pos);
-    case 2:
-	goto out;
-    default:
-	goto out;
-    }
-
-out:
-    unlock_kernel();
-    return -EINVAL;
+	loff_t retval = -EINVAL;
+	switch (orig) {
+	case 1:
+		offset += file->f_pos;
+	/* fallthrough */
+	case 0:
+		if (offset < 0 || offset > MAX_NON_LFS)
+			break;
+		file->f_pos = retval = offset;
+	}
+	return retval;
 }
 
 static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 0a044ad98885..a5e3a0ddbe53 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -32,6 +32,7 @@ void reiserfs_delete_inode(struct inode *inode)
 	    JOURNAL_PER_BALANCE_CNT * 2 +
 	    2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
 	struct reiserfs_transaction_handle th;
+	int err;
 
 	truncate_inode_pages(&inode->i_data, 0);
 
@@ -49,15 +50,13 @@ void reiserfs_delete_inode(struct inode *inode)
 		}
 		reiserfs_update_inode_transaction(inode);
 
-		if (reiserfs_delete_object(&th, inode)) {
-			up(&inode->i_sem);
-			goto out;
-		}
+		err = reiserfs_delete_object(&th, inode);
 
 		/* Do quota update inside a transaction for journaled quotas. We must do that
 		 * after delete_object so that quota updates go into the same transaction as
 		 * stat data deletion */
-		DQUOT_FREE_INODE(inode);
+		if (!err) 
+			DQUOT_FREE_INODE(inode);
 
 		if (journal_end(&th, inode->i_sb, jbegin_count)) {
 			up(&inode->i_sem);
@@ -66,6 +65,12 @@ void reiserfs_delete_inode(struct inode *inode)
 
 		up(&inode->i_sem);
 
+		/* check return value from reiserfs_delete_object after
+		 * ending the transaction
+		 */
+		if (err)
+		    goto out;
+
 		/* all items of file are deleted, so we can remove "save" link */
 		remove_save_link(inode, 0 /* not truncate */ );	/* we can't do anything
 								 * about an error here */
@@ -2099,6 +2104,7 @@ int reiserfs_truncate_file(struct inode *p_s_inode, int update_timestamps)
 	struct page *page = NULL;
 	int error;
 	struct buffer_head *bh = NULL;
+	int err2;
 
 	reiserfs_write_lock(p_s_inode->i_sb);
 
@@ -2136,14 +2142,18 @@ int reiserfs_truncate_file(struct inode *p_s_inode, int update_timestamps)
 		   transaction of truncating gets committed - on reboot the file
 		   either appears truncated properly or not truncated at all */
 		add_save_link(&th, p_s_inode, 1);
-	error = reiserfs_do_truncate(&th, p_s_inode, page, update_timestamps);
-	if (error)
-		goto out;
+	err2 = reiserfs_do_truncate(&th, p_s_inode, page, update_timestamps);
 	error =
 	    journal_end(&th, p_s_inode->i_sb, JOURNAL_PER_BALANCE_CNT * 2 + 1);
 	if (error)
 		goto out;
 
+	/* check reiserfs_do_truncate after ending the transaction */
+	if (err2) {
+		error = err2;
+  		goto out;
+	}
+	
 	if (update_timestamps) {
 		error = remove_save_link(p_s_inode, 1 /* truncate */ );
 		if (error)
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 68b7b78638ff..3f17ef844fb6 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1039,6 +1039,10 @@ static int flush_commit_list(struct super_block *s,
 	}
 	atomic_dec(&journal->j_async_throttle);
 
+	/* We're skipping the commit if there's an error */
+	if (retval || reiserfs_is_journal_aborted(journal))
+		barrier = 0;
+
 	/* wait on everything written so far before writing the commit
 	 * if we are in barrier mode, send the commit down now
 	 */
@@ -1077,10 +1081,16 @@ static int flush_commit_list(struct super_block *s,
 	BUG_ON(atomic_read(&(jl->j_commit_left)) != 1);
 
 	if (!barrier) {
-		if (buffer_dirty(jl->j_commit_bh))
-			BUG();
-		mark_buffer_dirty(jl->j_commit_bh);
-		sync_dirty_buffer(jl->j_commit_bh);
+		/* If there was a write error in the journal - we can't commit
+		 * this transaction - it will be invalid and, if successful,
+		 * will just end up propogating the write error out to
+		 * the file system. */
+		if (likely(!retval && !reiserfs_is_journal_aborted (journal))) {
+			if (buffer_dirty(jl->j_commit_bh))
+				BUG();
+			mark_buffer_dirty(jl->j_commit_bh) ;
+			sync_dirty_buffer(jl->j_commit_bh) ;
+		}
 	} else
 		wait_on_buffer(jl->j_commit_bh);
 
diff --git a/fs/relayfs/relay.c b/fs/relayfs/relay.c
index 16446a15c96d..2a6f7f12b7f9 100644
--- a/fs/relayfs/relay.c
+++ b/fs/relayfs/relay.c
@@ -333,8 +333,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 	return length;
 
 toobig:
-	printk(KERN_WARNING "relayfs: event too large (%Zd)\n", length);
-	WARN_ON(1);
+	buf->chan->last_toobig = length;
 	return 0;
 }
 
@@ -399,6 +398,11 @@ void relay_close(struct rchan *chan)
 		relay_close_buf(chan->buf[i]);
 	}
 
+	if (chan->last_toobig)
+		printk(KERN_WARNING "relayfs: one or more items not logged "
+		       "[item size (%Zd) > sub-buffer size (%Zd)]\n",
+		       chan->last_toobig, chan->subbuf_size);
+
 	kref_put(&chan->kref, relay_destroy_channel);
 }
 
diff --git a/fs/xattr.c b/fs/xattr.c
index a9db22557998..bcc2156d4d28 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -245,7 +245,7 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 		error = d->d_inode->i_op->listxattr(d, klist, size);
 	} else {
 		error = security_inode_listsecurity(d->d_inode, klist, size);
-		if (size && error >= size)
+		if (size && error > size)
 			error = -ERANGE;
 	}
 	if (error > 0) {
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 1aea42d71a64..5328a2937127 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -78,7 +78,7 @@ STATIC int	xfs_qm_dqhashlock_nowait(xfs_dquot_t *);
 
 STATIC int	xfs_qm_init_quotainos(xfs_mount_t *);
 STATIC int	xfs_qm_init_quotainfo(xfs_mount_t *);
-STATIC int	xfs_qm_shake(int, unsigned int);
+STATIC int	xfs_qm_shake(int, gfp_t);
 
 #ifdef DEBUG
 extern mutex_t	qcheck_lock;
@@ -2197,7 +2197,7 @@ xfs_qm_shake_freelist(
  */
 /* ARGSUSED */
 STATIC int
-xfs_qm_shake(int nr_to_scan, unsigned int gfp_mask)
+xfs_qm_shake(int nr_to_scan, gfp_t gfp_mask)
 {
 	int	ndqused, nfree, n;