#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
+#include <linux/device_cgroup.h>
#include <asm/namei.h>
#include <asm/uaccess.h>
if (retval)
return retval;
+ retval = devcgroup_inode_permission(inode, mask);
+ if (retval)
+ return retval;
+
return security_inode_permission(inode, mask, 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);
}
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 &&
return -EACCES;
flag &= ~O_TRUNC;
- } else if (IS_RDONLY(inode) && (acc_mode & MAY_WRITE))
- return -EROFS;
+ }
error = vfs_permission(nd, acc_mode);
if (error)
return flag;
}
+static int open_will_write_to_fs(int flag, struct inode *inode)
+{
+ /*
+ * We'll never write to the fs underlying
+ * a device file.
+ */
+ if (special_file(inode->i_mode))
+ return 0;
+ return (flag & O_TRUNC);
+}
+
/*
- * Note that the low bits of "flag" aren't the same as in the open
- * system call. See open_to_namei_flags().
+ * Note that the low bits of the passed in "open_flag"
+ * are not the same as in the local variable "flag". See
+ * open_to_namei_flags() for more details.
*/
struct file *do_filp_open(int dfd, const char *pathname,
int open_flag, int mode)
{
+ struct file *filp;
struct nameidata nd;
int acc_mode, error;
struct path path;
struct dentry *dir;
int count = 0;
+ int will_write;
int flag = open_to_namei_flags(open_flag);
acc_mode = ACC_MODE(flag);
}
if (IS_ERR(nd.intent.open.file)) {
- mutex_unlock(&dir->d_inode->i_mutex);
error = PTR_ERR(nd.intent.open.file);
- goto exit_dput;
+ goto exit_mutex_unlock;
}
/* Negative dentry, just create the file */
if (!path.dentry->d_inode) {
- error = __open_namei_create(&nd, &path, flag, mode);
+ /*
+ * 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;
- return nameidata_to_filp(&nd, open_flag);
+ }
+ filp = nameidata_to_filp(&nd, open_flag);
+ mnt_drop_write(nd.path.mnt);
+ return filp;
}
/*
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_write = open_will_write_to_fs(flag, nd.path.dentry->d_inode);
+ if (will_write) {
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto exit;
+ }
error = may_open(&nd, acc_mode, flag);
- if (error)
+ if (error) {
+ if (will_write)
+ mnt_drop_write(nd.path.mnt);
goto exit;
- return nameidata_to_filp(&nd, open_flag);
+ }
+ filp = nameidata_to_filp(&nd, open_flag);
+ /*
+ * It is now safe to drop the mnt write
+ * because the filp has had a write taken
+ * on its behalf.
+ */
+ if (will_write)
+ mnt_drop_write(nd.path.mnt);
+ return filp;
+exit_mutex_unlock:
+ mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
path_put_conditional(&path, &nd);
exit:
if (IS_ERR(dentry))
goto fail;
+ if (dentry->d_inode)
+ goto eexist;
/*
* Special case - lookup gave negative, but... we had foo/bar/
* From the vfs_mknod() POV we just have a negative dentry -
* all is fine. Let's be bastards - you had / on the end, you've
* been asking for (non-existent) directory. -ENOENT for you.
*/
- if (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode)
- goto enoent;
+ if (unlikely(!is_dir && nd->last.name[nd->last.len])) {
+ dput(dentry);
+ dentry = ERR_PTR(-ENOENT);
+ }
return dentry;
-enoent:
+eexist:
dput(dentry);
- dentry = ERR_PTR(-ENOENT);
+ dentry = ERR_PTR(-EEXIST);
fail:
return dentry;
}
if (!dir->i_op || !dir->i_op->mknod)
return -EPERM;
+ error = devcgroup_inode_mknod(mode, dev);
+ if (error)
+ return error;
+
error = security_inode_mknod(dir, dentry, mode, dev);
if (error)
return error;
{
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)