summaryrefslogtreecommitdiff
path: root/fs/overlayfs/copy_up.c
diff options
context:
space:
mode:
authorOlof Johansson <olof@lixom.net>2014-11-02 13:36:05 -0800
committerOlof Johansson <olof@lixom.net>2014-11-02 13:37:07 -0800
commit4257412db57900e43716d0b7ddd4f4a51e6ed2f4 (patch)
tree759963245a484422e9ad2639cb223b53f844ff15 /fs/overlayfs/copy_up.c
parentcc040ba269ae6972face1dc7376ab3eaab9f64c8 (diff)
parent4b91f7f3c8b20e073b7bfc098625b37f99789508 (diff)
Merge tag 'fixes-against-v3.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap into fixes
Merge "omap fixes against v3.18-rc2" from Tony Lindgren: Few fixes for omaps to enable NAND BCH so devices won't produce errors when booted with omap2plus_defconfig, and reduce bloat by making IPV6 a loadable module. Also let's add a warning about legacy boot being deprecated for omap3. We now have things working with device tree, and only omap3 is still booting in legacy mode. So hopefully this warning will help move the remaining legacy mode users to boot with device tree. As the total reduction of code and static data is somewhere around 20000 lines of code once we remove omap3 legacy mode booting, we really do want to make omap3 to boot also in device tree mode only over the next few merge cycles. * tag 'fixes-against-v3.18-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap: (407 commits) ARM: OMAP2+: Warn about deprecated legacy booting mode ARM: omap2plus_defconfig: Fix errors with NAND BCH ARM: omap2plus_defconfig: Fix bloat caused by having ipv6 built-in + Linux 3.18-rc2 Signed-off-by: Olof Johansson <olof@lixom.net>
Diffstat (limited to 'fs/overlayfs/copy_up.c')
-rw-r--r--fs/overlayfs/copy_up.c414
1 files changed, 414 insertions, 0 deletions
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
new file mode 100644
index 000000000000..ea10a8719107
--- /dev/null
+++ b/fs/overlayfs/copy_up.c
@@ -0,0 +1,414 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/fs.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/splice.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include "overlayfs.h"
+
+#define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
+
+int ovl_copy_xattr(struct dentry *old, struct dentry *new)
+{
+ ssize_t list_size, size;
+ char *buf, *name, *value;
+ int error;
+
+ if (!old->d_inode->i_op->getxattr ||
+ !new->d_inode->i_op->getxattr)
+ return 0;
+
+ list_size = vfs_listxattr(old, NULL, 0);
+ if (list_size <= 0) {
+ if (list_size == -EOPNOTSUPP)
+ return 0;
+ return list_size;
+ }
+
+ buf = kzalloc(list_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ error = -ENOMEM;
+ value = kmalloc(XATTR_SIZE_MAX, GFP_KERNEL);
+ if (!value)
+ goto out;
+
+ list_size = vfs_listxattr(old, buf, list_size);
+ if (list_size <= 0) {
+ error = list_size;
+ goto out_free_value;
+ }
+
+ for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+ size = vfs_getxattr(old, name, value, XATTR_SIZE_MAX);
+ if (size <= 0) {
+ error = size;
+ goto out_free_value;
+ }
+ error = vfs_setxattr(new, name, value, size, 0);
+ if (error)
+ goto out_free_value;
+ }
+
+out_free_value:
+ kfree(value);
+out:
+ kfree(buf);
+ return error;
+}
+
+static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
+{
+ struct file *old_file;
+ struct file *new_file;
+ loff_t old_pos = 0;
+ loff_t new_pos = 0;
+ int error = 0;
+
+ if (len == 0)
+ return 0;
+
+ old_file = ovl_path_open(old, O_RDONLY);
+ if (IS_ERR(old_file))
+ return PTR_ERR(old_file);
+
+ new_file = ovl_path_open(new, O_WRONLY);
+ if (IS_ERR(new_file)) {
+ error = PTR_ERR(new_file);
+ goto out_fput;
+ }
+
+ /* FIXME: copy up sparse files efficiently */
+ while (len) {
+ size_t this_len = OVL_COPY_UP_CHUNK_SIZE;
+ long bytes;
+
+ if (len < this_len)
+ this_len = len;
+
+ if (signal_pending_state(TASK_KILLABLE, current)) {
+ error = -EINTR;
+ break;
+ }
+
+ bytes = do_splice_direct(old_file, &old_pos,
+ new_file, &new_pos,
+ this_len, SPLICE_F_MOVE);
+ if (bytes <= 0) {
+ error = bytes;
+ break;
+ }
+ WARN_ON(old_pos != new_pos);
+
+ len -= bytes;
+ }
+
+ fput(new_file);
+out_fput:
+ fput(old_file);
+ return error;
+}
+
+static char *ovl_read_symlink(struct dentry *realdentry)
+{
+ int res;
+ char *buf;
+ struct inode *inode = realdentry->d_inode;
+ mm_segment_t old_fs;
+
+ res = -EINVAL;
+ if (!inode->i_op->readlink)
+ goto err;
+
+ res = -ENOMEM;
+ buf = (char *) __get_free_page(GFP_KERNEL);
+ if (!buf)
+ goto err;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ /* The cast to a user pointer is valid due to the set_fs() */
+ res = inode->i_op->readlink(realdentry,
+ (char __user *)buf, PAGE_SIZE - 1);
+ set_fs(old_fs);
+ if (res < 0) {
+ free_page((unsigned long) buf);
+ goto err;
+ }
+ buf[res] = '\0';
+
+ return buf;
+
+err:
+ return ERR_PTR(res);
+}
+
+static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
+{
+ struct iattr attr = {
+ .ia_valid =
+ ATTR_ATIME | ATTR_MTIME | ATTR_ATIME_SET | ATTR_MTIME_SET,
+ .ia_atime = stat->atime,
+ .ia_mtime = stat->mtime,
+ };
+
+ return notify_change(upperdentry, &attr, NULL);
+}
+
+int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
+{
+ int err = 0;
+
+ if (!S_ISLNK(stat->mode)) {
+ struct iattr attr = {
+ .ia_valid = ATTR_MODE,
+ .ia_mode = stat->mode,
+ };
+ err = notify_change(upperdentry, &attr, NULL);
+ }
+ if (!err) {
+ struct iattr attr = {
+ .ia_valid = ATTR_UID | ATTR_GID,
+ .ia_uid = stat->uid,
+ .ia_gid = stat->gid,
+ };
+ err = notify_change(upperdentry, &attr, NULL);
+ }
+ if (!err)
+ ovl_set_timestamps(upperdentry, stat);
+
+ return err;
+
+}
+
+static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
+ struct dentry *dentry, struct path *lowerpath,
+ struct kstat *stat, struct iattr *attr,
+ const char *link)
+{
+ struct inode *wdir = workdir->d_inode;
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *newdentry = NULL;
+ struct dentry *upper = NULL;
+ umode_t mode = stat->mode;
+ int err;
+
+ newdentry = ovl_lookup_temp(workdir, dentry);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out;
+
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out1;
+
+ /* Can't properly set mode on creation because of the umask */
+ stat->mode &= S_IFMT;
+ err = ovl_create_real(wdir, newdentry, stat, link, NULL, true);
+ stat->mode = mode;
+ if (err)
+ goto out2;
+
+ if (S_ISREG(stat->mode)) {
+ struct path upperpath;
+ ovl_path_upper(dentry, &upperpath);
+ BUG_ON(upperpath.dentry != NULL);
+ upperpath.dentry = newdentry;
+
+ err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
+ if (err)
+ goto out_cleanup;
+ }
+
+ err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+ if (err)
+ goto out_cleanup;
+
+ mutex_lock(&newdentry->d_inode->i_mutex);
+ err = ovl_set_attr(newdentry, stat);
+ if (!err && attr)
+ err = notify_change(newdentry, attr, NULL);
+ mutex_unlock(&newdentry->d_inode->i_mutex);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+ if (err)
+ goto out_cleanup;
+
+ ovl_dentry_update(dentry, newdentry);
+ newdentry = NULL;
+
+ /*
+ * Non-directores become opaque when copied up.
+ */
+ if (!S_ISDIR(stat->mode))
+ ovl_dentry_set_opaque(dentry, true);
+out2:
+ dput(upper);
+out1:
+ dput(newdentry);
+out:
+ return err;
+
+out_cleanup:
+ ovl_cleanup(wdir, newdentry);
+ goto out;
+}
+
+/*
+ * Copy up a single dentry
+ *
+ * Directory renames only allowed on "pure upper" (already created on
+ * upper filesystem, never copied up). Directories which are on lower or
+ * are merged may not be renamed. For these -EXDEV is returned and
+ * userspace has to deal with it. This means, when copying up a
+ * directory we can rely on it and ancestors being stable.
+ *
+ * Non-directory renames start with copy up of source if necessary. The
+ * actual rename will only proceed once the copy up was successful. Copy
+ * up uses upper parent i_mutex for exclusion. Since rename can change
+ * d_parent it is possible that the copy up will lock the old parent. At
+ * that point the file will have already been copied up anyway.
+ */
+int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
+ struct path *lowerpath, struct kstat *stat,
+ struct iattr *attr)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ int err;
+ struct kstat pstat;
+ struct path parentpath;
+ struct dentry *upperdir;
+ struct dentry *upperdentry;
+ const struct cred *old_cred;
+ struct cred *override_cred;
+ char *link = NULL;
+
+ ovl_path_upper(parent, &parentpath);
+ upperdir = parentpath.dentry;
+
+ err = vfs_getattr(&parentpath, &pstat);
+ if (err)
+ return err;
+
+ if (S_ISLNK(stat->mode)) {
+ link = ovl_read_symlink(lowerpath->dentry);
+ if (IS_ERR(link))
+ return PTR_ERR(link);
+ }
+
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (!override_cred)
+ goto out_free_link;
+
+ override_cred->fsuid = stat->uid;
+ override_cred->fsgid = stat->gid;
+ /*
+ * CAP_SYS_ADMIN for copying up extended attributes
+ * CAP_DAC_OVERRIDE for create
+ * CAP_FOWNER for chmod, timestamp update
+ * CAP_FSETID for chmod
+ * CAP_CHOWN for chown
+ * CAP_MKNOD for mknod
+ */
+ cap_raise(override_cred->cap_effective, CAP_SYS_ADMIN);
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ cap_raise(override_cred->cap_effective, CAP_FOWNER);
+ cap_raise(override_cred->cap_effective, CAP_FSETID);
+ cap_raise(override_cred->cap_effective, CAP_CHOWN);
+ cap_raise(override_cred->cap_effective, CAP_MKNOD);
+ old_cred = override_creds(override_cred);
+
+ err = -EIO;
+ if (lock_rename(workdir, upperdir) != NULL) {
+ pr_err("overlayfs: failed to lock workdir+upperdir\n");
+ goto out_unlock;
+ }
+ upperdentry = ovl_dentry_upper(dentry);
+ if (upperdentry) {
+ unlock_rename(workdir, upperdir);
+ err = 0;
+ /* Raced with another copy-up? Do the setattr here */
+ if (attr) {
+ mutex_lock(&upperdentry->d_inode->i_mutex);
+ err = notify_change(upperdentry, attr, NULL);
+ mutex_unlock(&upperdentry->d_inode->i_mutex);
+ }
+ goto out_put_cred;
+ }
+
+ err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
+ stat, attr, link);
+ if (!err) {
+ /* Restore timestamps on parent (best effort) */
+ ovl_set_timestamps(upperdir, &pstat);
+ }
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out_put_cred:
+ revert_creds(old_cred);
+ put_cred(override_cred);
+
+out_free_link:
+ if (link)
+ free_page((unsigned long) link);
+
+ return err;
+}
+
+int ovl_copy_up(struct dentry *dentry)
+{
+ int err;
+
+ err = 0;
+ while (!err) {
+ struct dentry *next;
+ struct dentry *parent;
+ struct path lowerpath;
+ struct kstat stat;
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ if (type != OVL_PATH_LOWER)
+ break;
+
+ next = dget(dentry);
+ /* find the topmost dentry not yet copied up */
+ for (;;) {
+ parent = dget_parent(next);
+
+ type = ovl_path_type(parent);
+ if (type != OVL_PATH_LOWER)
+ break;
+
+ dput(next);
+ next = parent;
+ }
+
+ ovl_path_lower(next, &lowerpath);
+ err = vfs_getattr(&lowerpath, &stat);
+ if (!err)
+ err = ovl_copy_up_one(parent, next, &lowerpath, &stat, NULL);
+
+ dput(parent);
+ dput(next);
+ }
+
+ return err;
+}