#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
+#include <linux/fdtable.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
+#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/vfs.h>
if (!S_ISREG(inode->i_mode))
goto dput_and_out;
- error = vfs_permission(&nd, MAY_WRITE);
+ error = mnt_want_write(nd.path.mnt);
if (error)
goto dput_and_out;
- error = -EROFS;
- if (IS_RDONLY(inode))
- goto dput_and_out;
+ error = vfs_permission(&nd, MAY_WRITE);
+ if (error)
+ goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- goto dput_and_out;
+ goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
- goto dput_and_out;
+ goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
put_write_and_out:
put_write_access(inode);
+mnt_drop_write_and_out:
+ mnt_drop_write(nd.path.mnt);
dput_and_out:
path_put(&nd.path);
out:
{
struct nameidata nd;
int old_fsuid, old_fsgid;
- kernel_cap_t old_cap;
+ kernel_cap_t uninitialized_var(old_cap); /* !SECURE_NO_SETUID_FIXUP */
int res;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
old_fsuid = current->fsuid;
old_fsgid = current->fsgid;
- old_cap = current->cap_effective;
current->fsuid = current->uid;
current->fsgid = current->gid;
- /*
- * Clear the capabilities if we switch to a non-root user
- *
- * FIXME: There is a race here against sys_capset. The
- * capabilities can change yet we will restore the old
- * value below. We should hold task_capabilities_lock,
- * but we cannot because user_path_walk can sleep.
- */
- if (current->uid)
- cap_clear(current->cap_effective);
- else
- current->cap_effective = current->cap_permitted;
+ if (!issecure(SECURE_NO_SETUID_FIXUP)) {
+ /*
+ * Clear the capabilities if we switch to a non-root user
+ */
+#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
+ /*
+ * FIXME: There is a race here against sys_capset. The
+ * capabilities can change yet we will restore the old
+ * value below. We should hold task_capabilities_lock,
+ * but we cannot because user_path_walk can sleep.
+ */
+#endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */
+ if (current->uid)
+ old_cap = cap_set_effective(__cap_empty_set);
+ else
+ old_cap = cap_set_effective(current->cap_permitted);
+ }
res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
if (res)
if(res || !(mode & S_IWOTH) ||
special_file(nd.path.dentry->d_inode->i_mode))
goto out_path_release;
-
- if(IS_RDONLY(nd.path.dentry->d_inode))
+ /*
+ * This is a rare case where using __mnt_is_readonly()
+ * is OK without a mnt_want/drop_write() pair. Since
+ * no actual write to the fs is performed here, we do
+ * not need to telegraph to that to anyone.
+ *
+ * By doing this, we accept that this access is
+ * inherently racy and know that the fs may change
+ * state before we even see this result.
+ */
+ if (__mnt_is_readonly(nd.path.mnt))
res = -EROFS;
out_path_release:
out:
current->fsuid = old_fsuid;
current->fsgid = old_fsgid;
- current->cap_effective = old_cap;
+
+ if (!issecure(SECURE_NO_SETUID_FIXUP))
+ cap_set_effective(old_cap);
return res;
}
error = __get_file_write_access(inode, mnt);
if (error)
goto cleanup_file;
+ if (!special_file(inode->i_mode))
+ file_take_write(f);
}
f->f_mapping = inode->i_mapping;
if (f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops ||
((!f->f_mapping->a_ops->direct_IO) &&
- (!f->f_mapping->a_ops->get_xip_page))) {
+ (!f->f_mapping->a_ops->get_xip_mem))) {
fput(f);
f = ERR_PTR(-EINVAL);
}
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITE) {
put_write_access(inode);
- if (!special_file(inode->i_mode))
+ if (!special_file(inode->i_mode)) {
+ /*
+ * We don't consider this a real
+ * mnt_want/drop_write() pair
+ * because it all happenend right
+ * here, so just reset the state.
+ */
+ file_reset_write(f);
mnt_drop_write(mnt);
+ }
}
file_kill(f);
f->f_path.dentry = NULL;