#include "internal.h"
-#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
-
/* [Feb-1997 T. Schoebel-Theuer]
* Fundamental changes in the pathname lookup mechanisms (namei)
* were necessary because of omirr. The reason is that omirr needs
/*
* Searching includes executable on directories, else just read.
*/
+ mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
if (capable(CAP_DAC_READ_SEARCH))
return 0;
}
/*
+ * force_reval_path - force revalidation of a dentry
+ *
+ * In some situations the path walking code will trust dentries without
+ * revalidating them. This causes problems for filesystems that depend on
+ * d_revalidate to handle file opens (e.g. NFSv4). When FS_REVAL_DOT is set
+ * (which indicates that it's possible for the dentry to go stale), force
+ * a d_revalidate call before proceeding.
+ *
+ * Returns 0 if the revalidation was successful. If the revalidation fails,
+ * either return the error returned by d_revalidate or -ESTALE if the
+ * revalidation it just returned 0. If d_revalidate returns 0, we attempt to
+ * invalidate the dentry. It's up to the caller to handle putting references
+ * to the path if necessary.
+ */
+static int
+force_reval_path(struct path *path, struct nameidata *nd)
+{
+ int status;
+ struct dentry *dentry = path->dentry;
+
+ /*
+ * only check on filesystems where it's possible for the dentry to
+ * become stale. It's assumed that if this flag is set then the
+ * d_revalidate op will also be defined.
+ */
+ if (!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT))
+ return 0;
+
+ status = dentry->d_op->d_revalidate(dentry, nd);
+ if (status > 0)
+ return 0;
+
+ if (!status) {
+ d_invalidate(dentry);
+ status = -ESTALE;
+ }
+ return status;
+}
+
+/*
* Short-cut version of permission(), for calling on directories
* during pathname resolution. Combines parts of permission()
* and generic_permission(), and tests ONLY for MAY_EXEC permission.
dget(dentry);
}
mntget(path->mnt);
+ nd->last_type = LAST_BIND;
cookie = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(cookie);
if (!IS_ERR(cookie)) {
error = 0;
if (s)
error = __vfs_follow_link(nd, s);
+ else if (nd->last_type == LAST_BIND) {
+ error = force_reval_path(&nd->path, nd);
+ if (error)
+ path_put(&nd->path);
+ }
if (dentry->d_inode->i_op->put_link)
dentry->d_inode->i_op->put_link(dentry, nd, cookie);
}
set_root(nd);
while(1) {
- struct vfsmount *parent;
struct dentry *old = nd->path.dentry;
if (nd->path.dentry == nd->root.dentry &&
nd->path.mnt == nd->root.mnt) {
break;
}
- spin_lock(&dcache_lock);
if (nd->path.dentry != nd->path.mnt->mnt_root) {
- nd->path.dentry = dget(nd->path.dentry->d_parent);
- spin_unlock(&dcache_lock);
+ /* rare case of legitimate dget_parent()... */
+ nd->path.dentry = dget_parent(nd->path.dentry);
dput(old);
break;
}
- spin_unlock(&dcache_lock);
- spin_lock(&vfsmount_lock);
- parent = nd->path.mnt->mnt_parent;
- if (parent == nd->path.mnt) {
- spin_unlock(&vfsmount_lock);
+ if (!follow_up(&nd->path))
break;
- }
- mntget(parent);
- nd->path.dentry = dget(nd->path.mnt->mnt_mountpoint);
- spin_unlock(&vfsmount_lock);
- dput(old);
- mntput(nd->path.mnt);
- nd->path.mnt = parent;
}
follow_mount(&nd->path);
}
}
/*
+ * This is a temporary kludge to deal with "automount" symlinks; proper
+ * solution is to trigger them on follow_mount(), so that do_lookup()
+ * would DTRT. To be killed before 2.6.34-final.
+ */
+static inline int follow_on_final(struct inode *inode, unsigned lookup_flags)
+{
+ return inode && unlikely(inode->i_op->follow_link) &&
+ ((lookup_flags & LOOKUP_FOLLOW) || S_ISDIR(inode->i_mode));
+}
+
+/*
* Name resolution.
* This is the basic name resolution function, turning a pathname into
* the final dentry. We expect 'base' to be positive and a directory.
if (err)
break;
inode = next.dentry->d_inode;
- if ((lookup_flags & LOOKUP_FOLLOW)
- && inode && inode->i_op->follow_link) {
+ if (follow_on_final(inode, lookup_flags)) {
err = do_follow_link(&next, nd);
if (err)
goto return_err;
return -ENOENT;
BUG_ON(victim->d_parent->d_inode != dir);
- audit_inode_child(victim->d_name.name, victim, dir);
+ audit_inode_child(victim, dir);
error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
* An append-only file must be opened in append mode for writing.
*/
if (IS_APPEND(inode)) {
- if ((flag & FMODE_WRITE) && !(flag & O_APPEND))
+ if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
return -EPERM;
if (flag & O_TRUNC)
return -EPERM;
/*
* Ensure there are no outstanding leases on the file.
*/
- error = break_lease(inode, flag);
- if (error)
- return error;
-
- return ima_path_check(path, acc_mode ?
- acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC) :
- ACC_MODE(flag) & (MAY_READ | MAY_WRITE),
- IMA_COUNT_UPDATE);
+ return break_lease(inode, flag);
}
static int handle_truncate(struct path *path)
* what get passed to sys_open().
*/
static int __open_namei_create(struct nameidata *nd, struct path *path,
- int flag, int mode)
+ int open_flag, int mode)
{
int error;
struct dentry *dir = nd->path.dentry;
if (error)
return error;
/* Don't check for write permission, don't truncate */
- return may_open(&nd->path, 0, flag & ~O_TRUNC);
+ return may_open(&nd->path, 0, open_flag & ~O_TRUNC);
}
/*
return (flag & O_TRUNC);
}
+static struct file *finish_open(struct nameidata *nd,
+ int open_flag, int flag, int acc_mode)
+{
+ struct file *filp;
+ int will_truncate;
+ int error;
+
+ will_truncate = open_will_truncate(flag, nd->path.dentry->d_inode);
+ if (will_truncate) {
+ error = mnt_want_write(nd->path.mnt);
+ if (error)
+ goto exit;
+ }
+ error = may_open(&nd->path, acc_mode, open_flag);
+ if (error) {
+ if (will_truncate)
+ mnt_drop_write(nd->path.mnt);
+ goto exit;
+ }
+ filp = nameidata_to_filp(nd);
+ if (!IS_ERR(filp)) {
+ error = ima_file_check(filp, acc_mode);
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ if (!IS_ERR(filp)) {
+ if (acc_mode & MAY_WRITE)
+ vfs_dq_init(nd->path.dentry->d_inode);
+
+ if (will_truncate) {
+ error = handle_truncate(&nd->path);
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ }
+ /*
+ * It is now safe to drop the mnt write
+ * because the filp has had a write taken
+ * on its behalf.
+ */
+ if (will_truncate)
+ mnt_drop_write(nd->path.mnt);
+ return filp;
+
+exit:
+ if (!IS_ERR(nd->intent.open.file))
+ release_open_intent(nd);
+ path_put(&nd->path);
+ return ERR_PTR(error);
+}
+
+static struct file *do_last(struct nameidata *nd, struct path *path,
+ int open_flag, int flag, int acc_mode,
+ int mode, const char *pathname,
+ struct dentry *dir, int *is_link)
+{
+ struct file *filp;
+ int error;
+
+ *is_link = 0;
+
+ error = PTR_ERR(path->dentry);
+ if (IS_ERR(path->dentry)) {
+ mutex_unlock(&dir->d_inode->i_mutex);
+ goto exit;
+ }
+
+ if (IS_ERR(nd->intent.open.file)) {
+ error = PTR_ERR(nd->intent.open.file);
+ goto exit_mutex_unlock;
+ }
+
+ /* Negative dentry, just create the file */
+ if (!path->dentry->d_inode) {
+ /*
+ * This write is needed to ensure that a
+ * ro->rw transition does not occur between
+ * the time when the file is created and when
+ * a permanent write count is taken through
+ * the 'struct file' in nameidata_to_filp().
+ */
+ error = mnt_want_write(nd->path.mnt);
+ if (error)
+ goto exit_mutex_unlock;
+ error = __open_namei_create(nd, path, open_flag, mode);
+ if (error) {
+ mnt_drop_write(nd->path.mnt);
+ goto exit;
+ }
+ filp = nameidata_to_filp(nd);
+ mnt_drop_write(nd->path.mnt);
+ if (nd->root.mnt)
+ path_put(&nd->root);
+ if (!IS_ERR(filp)) {
+ error = ima_file_check(filp, acc_mode);
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ return filp;
+ }
+
+ /*
+ * It already exists.
+ */
+ mutex_unlock(&dir->d_inode->i_mutex);
+ audit_inode(pathname, path->dentry);
+
+ error = -EEXIST;
+ if (flag & O_EXCL)
+ goto exit_dput;
+
+ if (__follow_mount(path)) {
+ error = -ELOOP;
+ if (flag & O_NOFOLLOW)
+ goto exit_dput;
+ }
+
+ error = -ENOENT;
+ if (!path->dentry->d_inode)
+ goto exit_dput;
+ if (path->dentry->d_inode->i_op->follow_link) {
+ *is_link = 1;
+ return NULL;
+ }
+
+ path_to_nameidata(path, nd);
+ error = -EISDIR;
+ if (S_ISDIR(path->dentry->d_inode->i_mode))
+ goto exit;
+ filp = finish_open(nd, open_flag, flag, acc_mode);
+ if (nd->root.mnt)
+ path_put(&nd->root);
+ return filp;
+
+exit_mutex_unlock:
+ mutex_unlock(&dir->d_inode->i_mutex);
+exit_dput:
+ path_put_conditional(path, nd);
+exit:
+ if (!IS_ERR(nd->intent.open.file))
+ release_open_intent(nd);
+ if (nd->root.mnt)
+ path_put(&nd->root);
+ path_put(&nd->path);
+ return ERR_PTR(error);
+}
+
/*
* Note that the low bits of the passed in "open_flag"
* are not the same as in the local variable "flag". See
struct file *filp;
struct nameidata nd;
int error;
- struct path path, save;
+ struct path path;
struct dentry *dir;
int count = 0;
- int will_truncate;
int flag = open_to_namei_flags(open_flag);
+ int force_reval = 0;
+ int is_link;
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
open_flag |= O_DSYNC;
if (!acc_mode)
- acc_mode = MAY_OPEN | ACC_MODE(flag);
+ acc_mode = MAY_OPEN | ACC_MODE(open_flag);
/* O_TRUNC implies we need access checks for write permissions */
if (flag & O_TRUNC)
if (filp == NULL)
return ERR_PTR(-ENFILE);
nd.intent.open.file = filp;
+ filp->f_flags = open_flag;
nd.intent.open.flags = flag;
nd.intent.open.create_mode = 0;
error = do_path_lookup(dfd, pathname,
/*
* Create - we need to know the parent.
*/
+reval:
error = path_init(dfd, pathname, LOOKUP_PARENT, &nd);
if (error)
return ERR_PTR(error);
+ if (force_reval)
+ nd.flags |= LOOKUP_REVAL;
error = path_walk(pathname, &nd);
if (error) {
if (nd.root.mnt)
if (filp == NULL)
goto exit_parent;
nd.intent.open.file = filp;
+ filp->f_flags = open_flag;
nd.intent.open.flags = flag;
nd.intent.open.create_mode = mode;
dir = nd.path.dentry;
path.mnt = nd.path.mnt;
do_last:
- error = PTR_ERR(path.dentry);
- if (IS_ERR(path.dentry)) {
- mutex_unlock(&dir->d_inode->i_mutex);
- goto exit;
- }
-
- if (IS_ERR(nd.intent.open.file)) {
- error = PTR_ERR(nd.intent.open.file);
- goto exit_mutex_unlock;
- }
-
- /* Negative dentry, just create the file */
- if (!path.dentry->d_inode) {
- /*
- * This write is needed to ensure that a
- * ro->rw transition does not occur between
- * the time when the file is created and when
- * a permanent write count is taken through
- * the 'struct file' in nameidata_to_filp().
- */
- error = mnt_want_write(nd.path.mnt);
- if (error)
- goto exit_mutex_unlock;
- error = __open_namei_create(&nd, &path, flag, mode);
- if (error) {
- mnt_drop_write(nd.path.mnt);
- goto exit;
- }
- filp = nameidata_to_filp(&nd, open_flag);
- if (IS_ERR(filp))
- ima_counts_put(&nd.path,
- acc_mode & (MAY_READ | MAY_WRITE |
- MAY_EXEC));
- mnt_drop_write(nd.path.mnt);
- if (nd.root.mnt)
- path_put(&nd.root);
- return filp;
- }
-
- /*
- * It already exists.
- */
- mutex_unlock(&dir->d_inode->i_mutex);
- audit_inode(pathname, path.dentry);
-
- error = -EEXIST;
- if (flag & O_EXCL)
- goto exit_dput;
-
- if (__follow_mount(&path)) {
- error = -ELOOP;
- if (flag & O_NOFOLLOW)
- goto exit_dput;
- }
-
- error = -ENOENT;
- if (!path.dentry->d_inode)
- goto exit_dput;
- if (path.dentry->d_inode->i_op->follow_link)
+ filp = do_last(&nd, &path, open_flag, flag, acc_mode, mode,
+ pathname, dir, &is_link);
+ if (is_link)
goto do_link;
+ return filp;
- path_to_nameidata(&path, &nd);
- error = -EISDIR;
- if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode))
- goto exit;
ok:
- /*
- * Consider:
- * 1. may_open() truncates a file
- * 2. a rw->ro mount transition occurs
- * 3. nameidata_to_filp() fails due to
- * the ro mount.
- * That would be inconsistent, and should
- * be avoided. Taking this mnt write here
- * ensures that (2) can not occur.
- */
- will_truncate = open_will_truncate(flag, nd.path.dentry->d_inode);
- if (will_truncate) {
- error = mnt_want_write(nd.path.mnt);
- if (error)
- goto exit;
- }
- error = may_open(&nd.path, acc_mode, flag);
- if (error) {
- if (will_truncate)
- mnt_drop_write(nd.path.mnt);
- goto exit;
- }
- filp = nameidata_to_filp(&nd, open_flag);
- if (IS_ERR(filp)) {
- ima_counts_put(&nd.path,
- acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
- if (will_truncate)
- mnt_drop_write(nd.path.mnt);
- if (nd.root.mnt)
- path_put(&nd.root);
- return filp;
- }
-
- if (acc_mode & MAY_WRITE)
- vfs_dq_init(nd.path.dentry->d_inode);
-
- if (will_truncate) {
- error = handle_truncate(&nd.path);
- if (error) {
- mnt_drop_write(nd.path.mnt);
- fput(filp);
- if (nd.root.mnt)
- path_put(&nd.root);
- return ERR_PTR(error);
- }
- }
- /*
- * It is now safe to drop the mnt write
- * because the filp has had a write taken
- * on its behalf.
- */
- if (will_truncate)
- mnt_drop_write(nd.path.mnt);
+ filp = finish_open(&nd, open_flag, flag, acc_mode);
if (nd.root.mnt)
path_put(&nd.root);
return filp;
-exit_mutex_unlock:
- mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
path_put_conditional(&path, &nd);
exit:
error = security_inode_follow_link(path.dentry, &nd);
if (error)
goto exit_dput;
- save = nd.path;
- path_get(&save);
error = __do_follow_link(&path, &nd);
- if (error == -ESTALE) {
- /* nd.path had been dropped */
- nd.path = save;
- path_get(&nd.path);
- nd.flags |= LOOKUP_REVAL;
- error = __do_follow_link(&path, &nd);
- }
- path_put(&save);
path_put(&path);
if (error) {
/* Does someone understand code flow here? Or it is only
release_open_intent(&nd);
if (nd.root.mnt)
path_put(&nd.root);
+ if (error == -ESTALE && !force_reval) {
+ force_reval = 1;
+ goto reval;
+ }
return ERR_PTR(error);
}
nd.flags &= ~LOOKUP_PARENT;
error = -EBUSY;
else {
error = security_inode_unlink(dir, dentry);
- if (!error)
+ if (!error) {
error = dir->i_op->unlink(dir, dentry);
+ if (!error)
+ dentry->d_inode->i_flags |= S_DEAD;
+ }
}
mutex_unlock(&dentry->d_inode->i_mutex);
else
error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
if (!error) {
+ if (target)
+ target->i_flags |= S_DEAD;
if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
d_move(old_dentry, new_dentry);
}
error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
else
error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry);
- if (!error) {
- const char *new_name = old_dentry->d_name.name;
- fsnotify_move(old_dir, new_dir, old_name, new_name, is_dir,
+ if (!error)
+ fsnotify_move(old_dir, new_dir, old_name, is_dir,
new_dentry->d_inode, old_dentry);
- }
fsnotify_oldname_free(old_name);
return error;