Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  [patch 2/3] vfs: dcache cleanups
  [patch 1/3] vfs: dcache sparse fixes
  [patch 3/3] vfs: make d_path() consistent across mount operations
  [patch 4/4] flock: remove unused fields from file_lock_operations
  [patch 3/4] vfs: fix ERR_PTR abuse in generic_readlink
  [patch 2/4] fs: make struct file arg to d_path const
  [patch 1/4] vfs: path_{get,put}() cleanups
  [patch for 2.6.26 4/4] vfs: utimensat(): fix write access check for futimens()
  [patch for 2.6.26 3/4] vfs: utimensat(): fix error checking for {UTIME_NOW,UTIME_OMIT} case
  [patch for 2.6.26 1/4] vfs: utimensat(): ignore tv_sec if tv_nsec == UTIME_OMIT or UTIME_NOW
  [patch for 2.6.26 2/4] vfs: utimensat(): be consistent with utime() for immutable and append-only files
  [PATCH] fix cgroup-inflicted breakage in block_dev.c

6 files changed, 88 insertions, 91 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 470c10c..10d8a0a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -931,8 +931,16 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	struct gendisk *disk;
 	int ret;
 	int part;
+	int perm = 0;
 
-	ret = devcgroup_inode_permission(bdev->bd_inode, file->f_mode);
+	if (file->f_mode & FMODE_READ)
+		perm |= MAY_READ;
+	if (file->f_mode & FMODE_WRITE)
+		perm |= MAY_WRITE;
+	/*
+	 * hooks: /n/, see "layering violations".
+	 */
+	ret = devcgroup_inode_permission(bdev->bd_inode, perm);
 	if (ret != 0)
 		return ret;
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 3ee588d5..6068c25 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -17,6 +17,7 @@
 #include <linux/syscalls.h>
 #include <linux/string.h>
 #include <linux/mm.h>
+#include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/slab.h>
@@ -106,9 +107,10 @@ static void dentry_lru_remove(struct dentry *dentry)
 /*
  * Release the dentry's inode, using the filesystem
  * d_iput() operation if defined.
- * Called with dcache_lock and per dentry lock held, drops both.
  */
 static void dentry_iput(struct dentry * dentry)
+	__releases(dentry->d_lock)
+	__releases(dcache_lock)
 {
 	struct inode *inode = dentry->d_inode;
 	if (inode) {
@@ -132,12 +134,13 @@ static void dentry_iput(struct dentry * dentry)
  * d_kill - kill dentry and return parent
  * @dentry: dentry to kill
  *
- * Called with dcache_lock and d_lock, releases both.  The dentry must
- * already be unhashed and removed from the LRU.
+ * The dentry must already be unhashed and removed from the LRU.
  *
  * If this is the root of the dentry tree, return NULL.
  */
 static struct dentry *d_kill(struct dentry *dentry)
+	__releases(dentry->d_lock)
+	__releases(dcache_lock)
 {
 	struct dentry *parent;
 
@@ -383,11 +386,11 @@ restart:
  * Try to prune ancestors as well.  This is necessary to prevent
  * quadratic behavior of shrink_dcache_parent(), but is also expected
  * to be beneficial in reducing dentry cache fragmentation.
- *
- * Called with dcache_lock, drops it and then regains.
- * Called with dentry->d_lock held, drops it.
  */
 static void prune_one_dentry(struct dentry * dentry)
+	__releases(dentry->d_lock)
+	__releases(dcache_lock)
+	__acquires(dcache_lock)
 {
 	__d_drop(dentry);
 	dentry = d_kill(dentry);
@@ -1604,10 +1607,9 @@ static int d_isparent(struct dentry *p1, struct dentry *p2)
  *
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
- *
- * On return, dcache_lock will have been unlocked.
  */
 static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
+	__releases(dcache_lock)
 {
 	struct mutex *m1 = NULL, *m2 = NULL;
 	struct dentry *ret;
@@ -1743,11 +1745,9 @@ out_nolock:
 shouldnt_be_hashed:
 	spin_unlock(&dcache_lock);
 	BUG();
-	goto shouldnt_be_hashed;
 }
 
-static int prepend(char **buffer, int *buflen, const char *str,
-			  int namelen)
+static int prepend(char **buffer, int *buflen, const char *str, int namelen)
 {
 	*buflen -= namelen;
 	if (*buflen < 0)
@@ -1757,8 +1757,13 @@ static int prepend(char **buffer, int *buflen, const char *str,
 	return 0;
 }
 
+static int prepend_name(char **buffer, int *buflen, struct qstr *name)
+{
+	return prepend(buffer, buflen, name->name, name->len);
+}
+
 /**
- * d_path - return the path of a dentry
+ * __d_path - return the path of a dentry
  * @path: the dentry/vfsmount to report
  * @root: root vfsmnt/dentry (may be modified by this function)
  * @buffer: buffer to return value in
@@ -1779,9 +1784,10 @@ char *__d_path(const struct path *path, struct path *root,
 {
 	struct dentry *dentry = path->dentry;
 	struct vfsmount *vfsmnt = path->mnt;
-	char * end = buffer+buflen;
-	char * retval;
+	char *end = buffer + buflen;
+	char *retval;
 
+	spin_lock(&vfsmount_lock);
 	prepend(&end, &buflen, "\0", 1);
 	if (!IS_ROOT(dentry) && d_unhashed(dentry) &&
 		(prepend(&end, &buflen, " (deleted)", 10) != 0))
@@ -1800,38 +1806,37 @@ char *__d_path(const struct path *path, struct path *root,
 			break;
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
 			/* Global root? */
-			spin_lock(&vfsmount_lock);
 			if (vfsmnt->mnt_parent == vfsmnt) {
-				spin_unlock(&vfsmount_lock);
 				goto global_root;
 			}
 			dentry = vfsmnt->mnt_mountpoint;
 			vfsmnt = vfsmnt->mnt_parent;
-			spin_unlock(&vfsmount_lock);
 			continue;
 		}
 		parent = dentry->d_parent;
 		prefetch(parent);
-		if ((prepend(&end, &buflen, dentry->d_name.name,
-				dentry->d_name.len) != 0) ||
+		if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
 		    (prepend(&end, &buflen, "/", 1) != 0))
 			goto Elong;
 		retval = end;
 		dentry = parent;
 	}
 
+out:
+	spin_unlock(&vfsmount_lock);
 	return retval;
 
 global_root:
 	retval += 1;	/* hit the slash */
-	if (prepend(&retval, &buflen, dentry->d_name.name,
-		    dentry->d_name.len) != 0)
+	if (prepend_name(&retval, &buflen, &dentry->d_name) != 0)
 		goto Elong;
 	root->mnt = vfsmnt;
 	root->dentry = dentry;
-	return retval;
+	goto out;
+
 Elong:
-	return ERR_PTR(-ENAMETOOLONG);
+	retval = ERR_PTR(-ENAMETOOLONG);
+	goto out;
 }
 
 /**
@@ -1845,9 +1850,9 @@ Elong:
  *
  * Returns the buffer or an error code if the path was too long.
  *
- * "buflen" should be positive. Caller holds the dcache_lock.
+ * "buflen" should be positive.
  */
-char *d_path(struct path *path, char *buf, int buflen)
+char *d_path(const struct path *path, char *buf, int buflen)
 {
 	char *res;
 	struct path root;
@@ -1915,16 +1920,11 @@ char *dentry_path(struct dentry *dentry, char *buf, int buflen)
 	retval = end-1;
 	*retval = '/';
 
-	for (;;) {
-		struct dentry *parent;
-		if (IS_ROOT(dentry))
-			break;
+	while (!IS_ROOT(dentry)) {
+		struct dentry *parent = dentry->d_parent;
 
-		parent = dentry->d_parent;
 		prefetch(parent);
-
-		if ((prepend(&end, &buflen, dentry->d_name.name,
-				dentry->d_name.len) != 0) ||
+		if ((prepend_name(&end, &buflen, &dentry->d_name) != 0) ||
 		    (prepend(&end, &buflen, "/", 1) != 0))
 			goto Elong;
 
@@ -1975,7 +1975,7 @@ asmlinkage long sys_getcwd(char __user *buf, unsigned long size)
 	error = -ENOENT;
 	/* Has the current directory has been unlinked? */
 	spin_lock(&dcache_lock);
-	if (pwd.dentry->d_parent == pwd.dentry || !d_unhashed(pwd.dentry)) {
+	if (IS_ROOT(pwd.dentry) || !d_unhashed(pwd.dentry)) {
 		unsigned long len;
 		struct path tmp = root;
 		char * cwd;
diff --git a/fs/locks.c b/fs/locks.c
index 11dbf08..dce8c747 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -561,9 +561,6 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
 	/* insert into file's list */
 	fl->fl_next = *pos;
 	*pos = fl;
-
-	if (fl->fl_ops && fl->fl_ops->fl_insert)
-		fl->fl_ops->fl_insert(fl);
 }
 
 /*
@@ -586,9 +583,6 @@ static void locks_delete_lock(struct file_lock **thisfl_p)
 		fl->fl_fasync = NULL;
 	}
 
-	if (fl->fl_ops && fl->fl_ops->fl_remove)
-		fl->fl_ops->fl_remove(fl);
-
 	if (fl->fl_nspid) {
 		put_pid(fl->fl_nspid);
 		fl->fl_nspid = NULL;
diff --git a/fs/namei.c b/fs/namei.c
index c7e4353..01e67dd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -581,15 +581,13 @@ static __always_inline int link_path_walk(const char *name, struct nameidata *nd
 	int result;
 
 	/* make sure the stuff we saved doesn't go away */
-	dget(save.dentry);
-	mntget(save.mnt);
+	path_get(&save);
 
 	result = __link_path_walk(name, nd);
 	if (result == -ESTALE) {
 		/* nd->path had been dropped */
 		nd->path = save;
-		dget(nd->path.dentry);
-		mntget(nd->path.mnt);
+		path_get(&nd->path);
 		nd->flags |= LOOKUP_REVAL;
 		result = __link_path_walk(name, nd);
 	}
@@ -1216,8 +1214,9 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 	nd->flags = flags;
 	nd->depth = 0;
 
-	nd->path.mnt = mntget(mnt);
-	nd->path.dentry = dget(dentry);
+	nd->path.dentry = dentry;
+	nd->path.mnt = mnt;
+	path_get(&nd->path);
 
 	retval = path_walk(name, nd);
 	if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
@@ -2857,16 +2856,17 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct nameidata nd;
 	void *cookie;
+	int res;
 
 	nd.depth = 0;
 	cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
-	if (!IS_ERR(cookie)) {
-		int res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
-		if (dentry->d_inode->i_op->put_link)
-			dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
-		cookie = ERR_PTR(res);
-	}
-	return PTR_ERR(cookie);
+	if (IS_ERR(cookie))
+		return PTR_ERR(cookie);
+
+	res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+	if (dentry->d_inode->i_op->put_link)
+		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
+	return res;
 }
 
 int vfs_follow_link(struct nameidata *nd, const char *link)
diff --git a/fs/pipe.c b/fs/pipe.c
index ec228bc..700f4e0 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1003,8 +1003,7 @@ struct file *create_write_pipe(void)
 void free_write_pipe(struct file *f)
 {
 	free_pipe_info(f->f_dentry->d_inode);
-	dput(f->f_path.dentry);
-	mntput(f->f_path.mnt);
+	path_put(&f->f_path);
 	put_filp(f);
 }
 
@@ -1015,8 +1014,8 @@ struct file *create_read_pipe(struct file *wrf)
 		return ERR_PTR(-ENFILE);
 
 	/* Grab pipe from the writer */
-	f->f_path.mnt = mntget(wrf->f_path.mnt);
-	f->f_path.dentry = dget(wrf->f_path.dentry);
+	f->f_path = wrf->f_path;
+	path_get(&wrf->f_path);
 	f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
 
 	f->f_pos = 0;
@@ -1068,8 +1067,7 @@ int do_pipe(int *fd)
  err_fdr:
 	put_unused_fd(fdr);
  err_read_pipe:
-	dput(fr->f_dentry);
-	mntput(fr->f_vfsmnt);
+	path_put(&fr->f_path);
 	put_filp(fr);
  err_write_pipe:
 	free_write_pipe(fw);
diff --git a/fs/utimes.c b/fs/utimes.c
index af059d5..b6b664e 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -40,14 +40,9 @@ asmlinkage long sys_utime(char __user *filename, struct utimbuf __user *times)
 
 #endif
 
-static bool nsec_special(long nsec)
-{
-	return nsec == UTIME_OMIT || nsec == UTIME_NOW;
-}
-
 static bool nsec_valid(long nsec)
 {
-	if (nsec_special(nsec))
+	if (nsec == UTIME_OMIT || nsec == UTIME_NOW)
 		return true;
 
 	return nsec >= 0 && nsec <= 999999999;
@@ -102,7 +97,11 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
 	if (error)
 		goto dput_and_out;
 
-	/* Don't worry, the checks are done in inode_change_ok() */
+	if (times && times[0].tv_nsec == UTIME_NOW &&
+		     times[1].tv_nsec == UTIME_NOW)
+		times = NULL;
+
+	/* In most cases, the checks are done in inode_change_ok() */
 	newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME;
 	if (times) {
 		error = -EPERM;
@@ -124,28 +123,34 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
 			newattrs.ia_mtime.tv_nsec = times[1].tv_nsec;
 			newattrs.ia_valid |= ATTR_MTIME_SET;
 		}
-	}
 
-	/*
-	 * If times is NULL or both times are either UTIME_OMIT or
-	 * UTIME_NOW, then need to check permissions, because
-	 * inode_change_ok() won't do it.
-	 */
-	if (!times || (nsec_special(times[0].tv_nsec) &&
-		       nsec_special(times[1].tv_nsec))) {
+		/*
+		 * For the UTIME_OMIT/UTIME_NOW and UTIME_NOW/UTIME_OMIT
+		 * cases, we need to make an extra check that is not done by
+		 * inode_change_ok().
+		 */
+		if (((times[0].tv_nsec == UTIME_NOW &&
+			    times[1].tv_nsec == UTIME_OMIT)
+		     ||
+		     (times[0].tv_nsec == UTIME_OMIT &&
+			    times[1].tv_nsec == UTIME_NOW))
+		    && !is_owner_or_cap(inode))
+			goto mnt_drop_write_and_out;
+	} else {
+
+		/*
+		 * If times is NULL (or both times are UTIME_NOW),
+		 * then we need to check permissions, because
+		 * inode_change_ok() won't do it.
+		 */
 		error = -EACCES;
                 if (IS_IMMUTABLE(inode))
 			goto mnt_drop_write_and_out;
 
 		if (!is_owner_or_cap(inode)) {
-			if (f) {
-				if (!(f->f_mode & FMODE_WRITE))
-					goto mnt_drop_write_and_out;
-			} else {
-				error = vfs_permission(&nd, MAY_WRITE);
-				if (error)
-					goto mnt_drop_write_and_out;
-			}
+			error = permission(inode, MAY_WRITE, NULL);
+			if (error)
+				goto mnt_drop_write_and_out;
 		}
 	}
 	mutex_lock(&inode->i_mutex);
@@ -169,14 +174,6 @@ asmlinkage long sys_utimensat(int dfd, char __user *filename, struct timespec __
 	if (utimes) {
 		if (copy_from_user(&tstimes, utimes, sizeof(tstimes)))
 			return -EFAULT;
-		if ((tstimes[0].tv_nsec == UTIME_OMIT ||
-		     tstimes[0].tv_nsec == UTIME_NOW) &&
-		    tstimes[0].tv_sec != 0)
-			return -EINVAL;
-		if ((tstimes[1].tv_nsec == UTIME_OMIT ||
-		     tstimes[1].tv_nsec == UTIME_NOW) &&
-		    tstimes[1].tv_sec != 0)
-			return -EINVAL;
 
 		/* Nothing to do, we must not even check the path.  */
 		if (tstimes[0].tv_nsec == UTIME_OMIT &&