From 23fa18eaa71266feff7ba8d83022d9e1cc83c65a Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:42:03 +0000
Subject: [PATCH] disable pwm7
---
kernel/fs/overlayfs/super.c | 972 ++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 658 insertions(+), 314 deletions(-)
diff --git a/kernel/fs/overlayfs/super.c b/kernel/fs/overlayfs/super.c
index 1a85f75..70a20ac 100644
--- a/kernel/fs/overlayfs/super.c
+++ b/kernel/fs/overlayfs/super.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
*
* 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 <uapi/linux/magic.h>
@@ -23,6 +20,7 @@
MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Overlay filesystem");
MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS(ANDROID_GKI_VFS_EXPORT_ONLY);
struct ovl_dir_cache;
@@ -31,29 +29,29 @@
static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR);
module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644);
-MODULE_PARM_DESC(ovl_redirect_dir_def,
+MODULE_PARM_DESC(redirect_dir,
"Default to on or off for the redirect_dir feature");
static bool ovl_redirect_always_follow =
IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW);
module_param_named(redirect_always_follow, ovl_redirect_always_follow,
bool, 0644);
-MODULE_PARM_DESC(ovl_redirect_always_follow,
+MODULE_PARM_DESC(redirect_always_follow,
"Follow redirects even if redirect_dir feature is turned off");
static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX);
module_param_named(index, ovl_index_def, bool, 0644);
-MODULE_PARM_DESC(ovl_index_def,
+MODULE_PARM_DESC(index,
"Default to on or off for the inodes index feature");
static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT);
module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644);
-MODULE_PARM_DESC(ovl_nfs_export_def,
+MODULE_PARM_DESC(nfs_export,
"Default to on or off for the NFS export feature");
static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO);
module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644);
-MODULE_PARM_DESC(ovl_xino_auto_def,
+MODULE_PARM_DESC(xino_auto,
"Auto enable xino feature");
static bool __read_mostly ovl_override_creds_def = true;
@@ -71,7 +69,7 @@
static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY);
module_param_named(metacopy, ovl_metacopy_def, bool, 0644);
-MODULE_PARM_DESC(ovl_metacopy_def,
+MODULE_PARM_DESC(metacopy,
"Default to on or off for the metadata only copy up feature");
static void ovl_dentry_release(struct dentry *dentry)
@@ -124,53 +122,59 @@
return dentry;
}
-static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
{
- struct ovl_entry *oe = dentry->d_fsdata;
- unsigned int i;
int ret = 1;
- for (i = 0; i < oe->numlower; i++) {
- struct dentry *d = oe->lowerstack[i].dentry;
-
- if (d->d_flags & DCACHE_OP_REVALIDATE) {
- ret = d->d_op->d_revalidate(d, flags);
- if (ret < 0)
- return ret;
- if (!ret) {
- if (!(flags & LOOKUP_RCU))
- d_invalidate(d);
- return -ESTALE;
- }
- }
- }
- return 1;
-}
-
-static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
-{
- struct ovl_entry *oe = dentry->d_fsdata;
- unsigned int i;
- int ret = 1;
-
- for (i = 0; i < oe->numlower; i++) {
- struct dentry *d = oe->lowerstack[i].dentry;
-
- if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) {
- ret = d->d_op->d_weak_revalidate(d, flags);
- if (ret <= 0)
- break;
+ if (weak) {
+ if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE)
+ ret = d->d_op->d_weak_revalidate(d, flags);
+ } else if (d->d_flags & DCACHE_OP_REVALIDATE) {
+ ret = d->d_op->d_revalidate(d, flags);
+ if (!ret) {
+ if (!(flags & LOOKUP_RCU))
+ d_invalidate(d);
+ ret = -ESTALE;
}
}
return ret;
}
-static const struct dentry_operations ovl_dentry_operations = {
- .d_release = ovl_dentry_release,
- .d_real = ovl_d_real,
-};
+static int ovl_dentry_revalidate_common(struct dentry *dentry,
+ unsigned int flags, bool weak)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ struct inode *inode = d_inode_rcu(dentry);
+ struct dentry *upper;
+ unsigned int i;
+ int ret = 1;
-static const struct dentry_operations ovl_reval_dentry_operations = {
+ /* Careful in RCU mode */
+ if (!inode)
+ return -ECHILD;
+
+ upper = ovl_i_dentry_upper(inode);
+ if (upper)
+ ret = ovl_revalidate_real(upper, flags, weak);
+
+ for (i = 0; ret > 0 && i < oe->numlower; i++) {
+ ret = ovl_revalidate_real(oe->lowerstack[i].dentry, flags,
+ weak);
+ }
+ return ret;
+}
+
+static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return ovl_dentry_revalidate_common(dentry, flags, false);
+}
+
+static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ return ovl_dentry_revalidate_common(dentry, flags, true);
+}
+
+static const struct dentry_operations ovl_dentry_operations = {
.d_release = ovl_dentry_release,
.d_real = ovl_d_real,
.d_revalidate = ovl_dentry_revalidate,
@@ -198,11 +202,13 @@
return &oi->vfs_inode;
}
-static void ovl_i_callback(struct rcu_head *head)
+static void ovl_free_inode(struct inode *inode)
{
- struct inode *inode = container_of(head, struct inode, i_rcu);
+ struct ovl_inode *oi = OVL_I(inode);
- kmem_cache_free(ovl_inode_cachep, OVL_I(inode));
+ kfree(oi->redirect);
+ mutex_destroy(&oi->lock);
+ kmem_cache_free(ovl_inode_cachep, oi);
}
static void ovl_destroy_inode(struct inode *inode)
@@ -215,36 +221,36 @@
ovl_dir_cache_free(inode);
else
iput(oi->lowerdata);
- kfree(oi->redirect);
- mutex_destroy(&oi->lock);
-
- call_rcu(&inode->i_rcu, ovl_i_callback);
}
static void ovl_free_fs(struct ovl_fs *ofs)
{
+ struct vfsmount **mounts;
unsigned i;
iput(ofs->workbasedir_trap);
iput(ofs->indexdir_trap);
iput(ofs->workdir_trap);
- iput(ofs->upperdir_trap);
+ dput(ofs->whiteout);
dput(ofs->indexdir);
dput(ofs->workdir);
if (ofs->workdir_locked)
ovl_inuse_unlock(ofs->workbasedir);
dput(ofs->workbasedir);
if (ofs->upperdir_locked)
- ovl_inuse_unlock(ofs->upper_mnt->mnt_root);
- mntput(ofs->upper_mnt);
- for (i = 0; i < ofs->numlower; i++) {
- iput(ofs->lower_layers[i].trap);
- mntput(ofs->lower_layers[i].mnt);
+ ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root);
+
+ /* Hack! Reuse ofs->layers as a vfsmount array before freeing it */
+ mounts = (struct vfsmount **) ofs->layers;
+ for (i = 0; i < ofs->numlayer; i++) {
+ iput(ofs->layers[i].trap);
+ mounts[i] = ofs->layers[i].mnt;
}
- for (i = 0; i < ofs->numlowerfs; i++)
- free_anon_bdev(ofs->lower_fs[i].pseudo_dev);
- kfree(ofs->lower_layers);
- kfree(ofs->lower_fs);
+ kern_unmount_array(mounts, ofs->numlayer);
+ kfree(ofs->layers);
+ for (i = 0; i < ofs->numfs; i++)
+ free_anon_bdev(ofs->fs[i].pseudo_dev);
+ kfree(ofs->fs);
kfree(ofs->config.lowerdir);
kfree(ofs->config.upperdir);
@@ -269,12 +275,23 @@
struct super_block *upper_sb;
int ret;
- if (!ofs->upper_mnt)
- return 0;
+ ret = ovl_sync_status(ofs);
+ /*
+ * We have to always set the err, because the return value isn't
+ * checked in syncfs, and instead indirectly return an error via
+ * the sb's writeback errseq, which VFS inspects after this call.
+ */
+ if (ret < 0) {
+ errseq_set(&sb->s_wb_err, -EIO);
+ return -EIO;
+ }
+
+ if (!ret)
+ return ret;
/*
- * If this is a sync(2) call or an emergency sync, all the super blocks
- * will be iterated, including upper_sb, so no need to do anything.
+ * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
+ * All the super blocks will be iterated, including upper_sb.
*
* If this is a syncfs(2) call, then we do need to call
* sync_filesystem() on upper_sb, but enough if we do it when being
@@ -283,7 +300,7 @@
if (!wait)
return 0;
- upper_sb = ofs->upper_mnt->mnt_sb;
+ upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
down_read(&upper_sb->s_umount);
ret = sync_filesystem(upper_sb);
@@ -321,19 +338,13 @@
/* Will this overlay be forced to mount/remount ro? */
static bool ovl_force_readonly(struct ovl_fs *ofs)
{
- return (!ofs->upper_mnt || !ofs->workdir);
+ return (!ovl_upper_mnt(ofs) || !ofs->workdir);
}
static const char *ovl_redirect_mode_def(void)
{
return ovl_redirect_dir_def ? "on" : "off";
}
-
-enum {
- OVL_XINO_OFF,
- OVL_XINO_AUTO,
- OVL_XINO_ON,
-};
static const char * const ovl_xino_str[] = {
"off",
@@ -371,11 +382,13 @@
if (ofs->config.nfs_export != ovl_nfs_export_def)
seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ?
"on" : "off");
- if (ofs->config.xino != ovl_xino_def())
+ if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(sb))
seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]);
if (ofs->config.metacopy != ovl_metacopy_def)
seq_printf(m, ",metacopy=%s",
ofs->config.metacopy ? "on" : "off");
+ if (ofs->config.ovl_volatile)
+ seq_puts(m, ",volatile");
if (ofs->config.override_creds != ovl_override_creds_def)
seq_show_option(m, "override_creds",
ofs->config.override_creds ? "on" : "off");
@@ -385,15 +398,27 @@
static int ovl_remount(struct super_block *sb, int *flags, char *data)
{
struct ovl_fs *ofs = sb->s_fs_info;
+ struct super_block *upper_sb;
+ int ret = 0;
if (!(*flags & SB_RDONLY) && ovl_force_readonly(ofs))
return -EROFS;
- return 0;
+ if (*flags & SB_RDONLY && !sb_rdonly(sb)) {
+ upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
+ if (ovl_should_sync(ofs)) {
+ down_read(&upper_sb->s_umount);
+ ret = sync_filesystem(upper_sb);
+ up_read(&upper_sb->s_umount);
+ }
+ }
+
+ return ret;
}
static const struct super_operations ovl_super_operations = {
.alloc_inode = ovl_alloc_inode,
+ .free_inode = ovl_free_inode,
.destroy_inode = ovl_destroy_inode,
.drop_inode = generic_delete_inode,
.put_super = ovl_put_super,
@@ -418,6 +443,7 @@
OPT_XINO_AUTO,
OPT_METACOPY_ON,
OPT_METACOPY_OFF,
+ OPT_VOLATILE,
OPT_OVERRIDE_CREDS_ON,
OPT_OVERRIDE_CREDS_OFF,
OPT_ERR,
@@ -438,6 +464,7 @@
{OPT_XINO_AUTO, "xino=auto"},
{OPT_METACOPY_ON, "metacopy=on"},
{OPT_METACOPY_OFF, "metacopy=off"},
+ {OPT_VOLATILE, "volatile"},
{OPT_OVERRIDE_CREDS_ON, "override_creds=on"},
{OPT_OVERRIDE_CREDS_OFF, "override_creds=off"},
{OPT_ERR, NULL}
@@ -481,7 +508,7 @@
if (ovl_redirect_always_follow)
config->redirect_follow = true;
} else if (strcmp(mode, "nofollow") != 0) {
- pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n",
+ pr_err("bad mount option \"redirect_dir=%s\"\n",
mode);
return -EINVAL;
}
@@ -494,6 +521,7 @@
char *p;
int err;
bool metacopy_opt = false, redirect_opt = false;
+ bool nfs_export_opt = false, index_opt = false;
config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL);
if (!config->redirect_mode)
@@ -544,18 +572,22 @@
case OPT_INDEX_ON:
config->index = true;
+ index_opt = true;
break;
case OPT_INDEX_OFF:
config->index = false;
+ index_opt = true;
break;
case OPT_NFS_EXPORT_ON:
config->nfs_export = true;
+ nfs_export_opt = true;
break;
case OPT_NFS_EXPORT_OFF:
config->nfs_export = false;
+ nfs_export_opt = true;
break;
case OPT_XINO_ON:
@@ -577,6 +609,11 @@
case OPT_METACOPY_OFF:
config->metacopy = false;
+ metacopy_opt = true;
+ break;
+
+ case OPT_VOLATILE:
+ config->ovl_volatile = true;
break;
case OPT_OVERRIDE_CREDS_ON:
@@ -588,17 +625,30 @@
break;
default:
- pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
+ pr_err("unrecognized mount option \"%s\" or missing value\n",
+ p);
return -EINVAL;
}
}
- /* Workdir is useless in non-upper mount */
- if (!config->upperdir && config->workdir) {
- pr_info("overlayfs: option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
- config->workdir);
- kfree(config->workdir);
- config->workdir = NULL;
+ /* Workdir/index are useless in non-upper mount */
+ if (!config->upperdir) {
+ if (config->workdir) {
+ pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n",
+ config->workdir);
+ kfree(config->workdir);
+ config->workdir = NULL;
+ }
+ if (config->index && index_opt) {
+ pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n");
+ index_opt = false;
+ }
+ config->index = false;
+ }
+
+ if (!config->upperdir && config->ovl_volatile) {
+ pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n");
+ config->ovl_volatile = false;
}
err = ovl_parse_redirect_mode(config, config->redirect_mode);
@@ -615,7 +665,7 @@
/* Resolve metacopy -> redirect_dir dependency */
if (config->metacopy && !config->redirect_dir) {
if (metacopy_opt && redirect_opt) {
- pr_err("overlayfs: conflicting options: metacopy=on,redirect_dir=%s\n",
+ pr_err("conflicting options: metacopy=on,redirect_dir=%s\n",
config->redirect_mode);
return -EINVAL;
}
@@ -624,12 +674,56 @@
* There was an explicit redirect_dir=... that resulted
* in this conflict.
*/
- pr_info("overlayfs: disabling metacopy due to redirect_dir=%s\n",
+ pr_info("disabling metacopy due to redirect_dir=%s\n",
config->redirect_mode);
config->metacopy = false;
} else {
/* Automatically enable redirect otherwise. */
config->redirect_follow = config->redirect_dir = true;
+ }
+ }
+
+ /* Resolve nfs_export -> index dependency */
+ if (config->nfs_export && !config->index) {
+ if (!config->upperdir && config->redirect_follow) {
+ pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
+ config->nfs_export = false;
+ } else if (nfs_export_opt && index_opt) {
+ pr_err("conflicting options: nfs_export=on,index=off\n");
+ return -EINVAL;
+ } else if (index_opt) {
+ /*
+ * There was an explicit index=off that resulted
+ * in this conflict.
+ */
+ pr_info("disabling nfs_export due to index=off\n");
+ config->nfs_export = false;
+ } else {
+ /* Automatically enable index otherwise. */
+ config->index = true;
+ }
+ }
+
+ /* Resolve nfs_export -> !metacopy dependency */
+ if (config->nfs_export && config->metacopy) {
+ if (nfs_export_opt && metacopy_opt) {
+ pr_err("conflicting options: nfs_export=on,metacopy=on\n");
+ return -EINVAL;
+ }
+ if (metacopy_opt) {
+ /*
+ * There was an explicit metacopy=on that resulted
+ * in this conflict.
+ */
+ pr_info("disabling nfs_export due to metacopy=on\n");
+ config->nfs_export = false;
+ } else {
+ /*
+ * There was an explicit nfs_export=on that resulted
+ * in this conflict.
+ */
+ pr_info("disabling metacopy due to nfs_export=on\n");
+ config->metacopy = false;
}
}
@@ -643,15 +737,12 @@
const char *name, bool persist)
{
struct inode *dir = ofs->workbasedir->d_inode;
- struct vfsmount *mnt = ofs->upper_mnt;
+ struct vfsmount *mnt = ovl_upper_mnt(ofs);
struct dentry *work;
int err;
bool retried = false;
- bool locked = false;
inode_lock_nested(dir, I_MUTEX_PARENT);
- locked = true;
-
retry:
work = lookup_one_len(name, ofs->workbasedir, strlen(name));
@@ -670,8 +761,12 @@
goto out_unlock;
retried = true;
- ovl_workdir_cleanup(dir, mnt, work, 0);
+ err = ovl_workdir_cleanup(dir, mnt, work, 0);
dput(work);
+ if (err == -EINVAL) {
+ work = ERR_PTR(err);
+ goto out_unlock;
+ }
goto retry;
}
@@ -716,15 +811,13 @@
goto out_err;
}
out_unlock:
- if (locked)
- inode_unlock(dir);
-
+ inode_unlock(dir);
return work;
out_dput:
dput(work);
out_err:
- pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
+ pr_warn("failed to create directory %s/%s (errno: %i); mounting read-only\n",
ofs->config.workdir, name, -err);
work = NULL;
goto out_unlock;
@@ -748,21 +841,21 @@
int err = -EINVAL;
if (!*name) {
- pr_err("overlayfs: empty lowerdir\n");
+ pr_err("empty lowerdir\n");
goto out;
}
err = kern_path(name, LOOKUP_FOLLOW, path);
if (err) {
- pr_err("overlayfs: failed to resolve '%s': %i\n", name, err);
+ pr_err("failed to resolve '%s': %i\n", name, err);
goto out;
}
err = -EINVAL;
if (ovl_dentry_weird(path->dentry)) {
- pr_err("overlayfs: filesystem on '%s' not supported\n", name);
+ pr_err("filesystem on '%s' not supported\n", name);
goto out_put;
}
if (!d_is_dir(path->dentry)) {
- pr_err("overlayfs: '%s' not a directory\n", name);
+ pr_err("'%s' not a directory\n", name);
goto out_put;
}
return 0;
@@ -782,13 +875,12 @@
ovl_unescape(tmp);
err = ovl_mount_dir_noesc(tmp, path);
- if (!err)
- if (ovl_dentry_remote(path->dentry)) {
- pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n",
- tmp);
- path_put_init(path);
- err = -EINVAL;
- }
+ if (!err && path->dentry->d_flags & DCACHE_OP_REAL) {
+ pr_err("filesystem on '%s' not supported as upperdir\n",
+ tmp);
+ path_put_init(path);
+ err = -EINVAL;
+ }
kfree(tmp);
}
return err;
@@ -801,7 +893,7 @@
int err = vfs_statfs(path, &statfs);
if (err)
- pr_err("overlayfs: statfs failed on '%s'\n", name);
+ pr_err("statfs failed on '%s'\n", name);
else
ofs->namelen = max(ofs->namelen, statfs.f_namelen);
@@ -809,23 +901,20 @@
}
static int ovl_lower_dir(const char *name, struct path *path,
- struct ovl_fs *ofs, int *stack_depth, bool *remote)
+ struct ovl_fs *ofs, int *stack_depth)
{
int fh_type;
int err;
err = ovl_mount_dir_noesc(name, path);
if (err)
- goto out;
+ return err;
err = ovl_check_namelen(path, ofs, name);
if (err)
- goto out_put;
+ return err;
*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
-
- if (ovl_dentry_remote(path->dentry))
- *remote = true;
/*
* The inodes index feature and NFS export need to encode and decode
@@ -836,20 +925,15 @@
(ofs->config.index && ofs->config.upperdir)) && !fh_type) {
ofs->config.index = false;
ofs->config.nfs_export = false;
- pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
+ pr_warn("fs on '%s' does not support file handles, falling back to index=off,nfs_export=off.\n",
name);
}
/* Check if lower fs has 32bit inode numbers */
if (fh_type != FILEID_INO32_GEN)
- ofs->xino_bits = 0;
+ ofs->xino_mode = -1;
return 0;
-
-out_put:
- path_put_init(path);
-out:
- return err;
}
/* Workdir should not be subdir of upperdir and vice versa */
@@ -887,17 +971,9 @@
static int __maybe_unused
ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
- const char *name, void *buffer, size_t size)
+ const char *name, void *buffer, size_t size, int flags)
{
- return ovl_xattr_get(dentry, inode, handler->name, buffer, size);
-}
-
-static int __maybe_unused
-__ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, void *buffer, size_t size)
-{
- return __ovl_xattr_get(dentry, inode, handler->name, buffer, size);
+ return ovl_xattr_get(dentry, inode, handler->name, buffer, size, flags);
}
static int __maybe_unused
@@ -960,7 +1036,8 @@
static int ovl_own_xattr_get(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
- const char *name, void *buffer, size_t size)
+ const char *name, void *buffer, size_t size,
+ int flags)
{
return -EOPNOTSUPP;
}
@@ -975,16 +1052,10 @@
static int ovl_other_xattr_get(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
- const char *name, void *buffer, size_t size)
+ const char *name, void *buffer, size_t size,
+ int flags)
{
- return ovl_xattr_get(dentry, inode, name, buffer, size);
-}
-
-static int __ovl_other_xattr_get(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, void *buffer, size_t size)
-{
- return __ovl_xattr_get(dentry, inode, name, buffer, size);
+ return ovl_xattr_get(dentry, inode, name, buffer, size, flags);
}
static int ovl_other_xattr_set(const struct xattr_handler *handler,
@@ -1000,7 +1071,6 @@
.name = XATTR_NAME_POSIX_ACL_ACCESS,
.flags = ACL_TYPE_ACCESS,
.get = ovl_posix_acl_xattr_get,
- .__get = __ovl_posix_acl_xattr_get,
.set = ovl_posix_acl_xattr_set,
};
@@ -1009,7 +1079,6 @@
.name = XATTR_NAME_POSIX_ACL_DEFAULT,
.flags = ACL_TYPE_DEFAULT,
.get = ovl_posix_acl_xattr_get,
- .__get = __ovl_posix_acl_xattr_get,
.set = ovl_posix_acl_xattr_set,
};
@@ -1022,7 +1091,6 @@
static const struct xattr_handler ovl_other_xattr_handler = {
.prefix = "", /* catch all */
.get = ovl_other_xattr_get,
- .__get = __ovl_other_xattr_get,
.set = ovl_other_xattr_set,
};
@@ -1046,7 +1114,7 @@
err = PTR_ERR_OR_ZERO(trap);
if (err) {
if (err == -ELOOP)
- pr_err("overlayfs: conflicting %s path\n", name);
+ pr_err("conflicting %s path\n", name);
return err;
}
@@ -1063,18 +1131,18 @@
static int ovl_report_in_use(struct ovl_fs *ofs, const char *name)
{
if (ofs->config.index) {
- pr_err("overlayfs: %s is in-use as upperdir/workdir of another mount, mount with '-o index=off' to override exclusive upperdir protection.\n",
+ pr_err("%s is in-use as upperdir/workdir of another mount, mount with '-o index=off' to override exclusive upperdir protection.\n",
name);
return -EBUSY;
} else {
- pr_warn("overlayfs: %s is in-use as upperdir/workdir of another mount, accessing files from both mounts will result in undefined behavior.\n",
+ pr_warn("%s is in-use as upperdir/workdir of another mount, accessing files from both mounts will result in undefined behavior.\n",
name);
return 0;
}
}
static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs,
- struct path *upperpath)
+ struct ovl_layer *upper_layer, struct path *upperpath)
{
struct vfsmount *upper_mnt;
int err;
@@ -1085,7 +1153,7 @@
/* Upper fs should not be r/o */
if (sb_rdonly(upperpath->mnt->mnt_sb)) {
- pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n");
+ pr_err("upper fs is r/o, try multi-lower layers mount\n");
err = -EINVAL;
goto out;
}
@@ -1094,7 +1162,7 @@
if (err)
goto out;
- err = ovl_setup_trap(sb, upperpath->dentry, &ofs->upperdir_trap,
+ err = ovl_setup_trap(sb, upperpath->dentry, &upper_layer->trap,
"upperdir");
if (err)
goto out;
@@ -1102,15 +1170,29 @@
upper_mnt = clone_private_mount(upperpath);
err = PTR_ERR(upper_mnt);
if (IS_ERR(upper_mnt)) {
- pr_err("overlayfs: failed to clone upperpath\n");
+ pr_err("failed to clone upperpath\n");
goto out;
}
/* Don't inherit atime flags */
upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME);
- ofs->upper_mnt = upper_mnt;
+ upper_layer->mnt = upper_mnt;
+ upper_layer->idx = 0;
+ upper_layer->fsid = 0;
- if (ovl_inuse_trylock(ofs->upper_mnt->mnt_root)) {
+ /*
+ * Inherit SB_NOSEC flag from upperdir.
+ *
+ * This optimization changes behavior when a security related attribute
+ * (suid/sgid/security.*) is changed on an underlying layer. This is
+ * okay because we don't yet have guarantees in that case, but it will
+ * need careful treatment once we want to honour changes to underlying
+ * filesystems.
+ */
+ if (upper_mnt->mnt_sb->s_flags & SB_NOSEC)
+ sb->s_flags |= SB_NOSEC;
+
+ if (ovl_inuse_trylock(ovl_upper_mnt(ofs)->mnt_root)) {
ofs->upperdir_locked = true;
} else {
err = ovl_report_in_use(ofs, "upperdir");
@@ -1123,11 +1205,112 @@
return err;
}
+/*
+ * Returns 1 if RENAME_WHITEOUT is supported, 0 if not supported and
+ * negative values if error is encountered.
+ */
+static int ovl_check_rename_whiteout(struct dentry *workdir)
+{
+ struct inode *dir = d_inode(workdir);
+ struct dentry *temp;
+ struct dentry *dest;
+ struct dentry *whiteout;
+ struct name_snapshot name;
+ int err;
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+
+ temp = ovl_create_temp(workdir, OVL_CATTR(S_IFREG | 0));
+ err = PTR_ERR(temp);
+ if (IS_ERR(temp))
+ goto out_unlock;
+
+ dest = ovl_lookup_temp(workdir);
+ err = PTR_ERR(dest);
+ if (IS_ERR(dest)) {
+ dput(temp);
+ goto out_unlock;
+ }
+
+ /* Name is inline and stable - using snapshot as a copy helper */
+ take_dentry_name_snapshot(&name, temp);
+ err = ovl_do_rename(dir, temp, dir, dest, RENAME_WHITEOUT);
+ if (err) {
+ if (err == -EINVAL)
+ err = 0;
+ goto cleanup_temp;
+ }
+
+ whiteout = lookup_one_len(name.name.name, workdir, name.name.len);
+ err = PTR_ERR(whiteout);
+ if (IS_ERR(whiteout))
+ goto cleanup_temp;
+
+ err = ovl_is_whiteout(whiteout);
+
+ /* Best effort cleanup of whiteout and temp file */
+ if (err)
+ ovl_cleanup(dir, whiteout);
+ dput(whiteout);
+
+cleanup_temp:
+ ovl_cleanup(dir, temp);
+ release_dentry_name_snapshot(&name);
+ dput(temp);
+ dput(dest);
+
+out_unlock:
+ inode_unlock(dir);
+
+ return err;
+}
+
+static struct dentry *ovl_lookup_or_create(struct dentry *parent,
+ const char *name, umode_t mode)
+{
+ size_t len = strlen(name);
+ struct dentry *child;
+
+ inode_lock_nested(parent->d_inode, I_MUTEX_PARENT);
+ child = lookup_one_len(name, parent, len);
+ if (!IS_ERR(child) && !child->d_inode)
+ child = ovl_create_real(parent->d_inode, child,
+ OVL_CATTR(mode));
+ inode_unlock(parent->d_inode);
+ dput(parent);
+
+ return child;
+}
+
+/*
+ * Creates $workdir/work/incompat/volatile/dirty file if it is not already
+ * present.
+ */
+static int ovl_create_volatile_dirty(struct ovl_fs *ofs)
+{
+ unsigned int ctr;
+ struct dentry *d = dget(ofs->workbasedir);
+ static const char *const volatile_path[] = {
+ OVL_WORKDIR_NAME, "incompat", "volatile", "dirty"
+ };
+ const char *const *name = volatile_path;
+
+ for (ctr = ARRAY_SIZE(volatile_path); ctr; ctr--, name++) {
+ d = ovl_lookup_or_create(d, *name, ctr > 1 ? S_IFDIR : S_IFREG);
+ if (IS_ERR(d))
+ return PTR_ERR(d);
+ }
+ dput(d);
+ return 0;
+}
+
static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs,
struct path *workpath)
{
- struct vfsmount *mnt = ofs->upper_mnt;
- struct dentry *temp;
+ struct vfsmount *mnt = ovl_upper_mnt(ofs);
+ struct dentry *temp, *workdir;
+ bool rename_whiteout;
+ bool d_type;
int fh_type;
int err;
@@ -1135,9 +1318,12 @@
if (err)
return err;
- ofs->workdir = ovl_workdir_create(ofs, OVL_WORKDIR_NAME, false);
- if (!ofs->workdir)
+ workdir = ovl_workdir_create(ofs, OVL_WORKDIR_NAME, false);
+ err = PTR_ERR(workdir);
+ if (IS_ERR_OR_NULL(workdir))
goto out;
+
+ ofs->workdir = workdir;
err = ovl_setup_trap(sb, ofs->workdir, &ofs->workdir_trap, "workdir");
if (err)
@@ -1153,12 +1339,9 @@
if (err < 0)
goto out;
- /*
- * We allowed this configuration and don't want to break users over
- * kernel upgrade. So warn instead of erroring out.
- */
- if (!err)
- pr_warn("overlayfs: upper fs needs to support d_type.\n");
+ d_type = err;
+ if (!d_type)
+ pr_warn("upper fs needs to support d_type.\n");
/* Check if upper/work fs supports O_TMPFILE */
temp = ovl_do_tmpfile(ofs->workdir, S_IFREG | 0);
@@ -1166,36 +1349,70 @@
if (ofs->tmpfile)
dput(temp);
else
- pr_warn("overlayfs: upper fs does not support tmpfile.\n");
+ pr_warn("upper fs does not support tmpfile.\n");
+
+
+ /* Check if upper/work fs supports RENAME_WHITEOUT */
+ err = ovl_check_rename_whiteout(ofs->workdir);
+ if (err < 0)
+ goto out;
+
+ rename_whiteout = err;
+ if (!rename_whiteout)
+ pr_warn("upper fs does not support RENAME_WHITEOUT.\n");
/*
* Check if upper/work fs supports trusted.overlay.* xattr
*/
- err = ovl_do_setxattr(ofs->workdir, OVL_XATTR_OPAQUE, "0", 1, 0);
+ err = ovl_do_setxattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE, "0", 1);
if (err) {
ofs->noxattr = true;
ofs->config.index = false;
ofs->config.metacopy = false;
- pr_warn("overlayfs: upper fs does not support xattr, falling back to index=off and metacopy=off.\n");
+ pr_warn("upper fs does not support xattr, falling back to index=off and metacopy=off.\n");
err = 0;
} else {
- vfs_removexattr(ofs->workdir, OVL_XATTR_OPAQUE);
+ ovl_do_removexattr(ofs, ofs->workdir, OVL_XATTR_OPAQUE);
+ }
+
+ /*
+ * We allowed sub-optimal upper fs configuration and don't want to break
+ * users over kernel upgrade, but we never allowed remote upper fs, so
+ * we can enforce strict requirements for remote upper fs.
+ */
+ if (ovl_dentry_remote(ofs->workdir) &&
+ (!d_type || !rename_whiteout || ofs->noxattr)) {
+ pr_err("upper fs missing required features.\n");
+ err = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * For volatile mount, create a incompat/volatile/dirty file to keep
+ * track of it.
+ */
+ if (ofs->config.ovl_volatile) {
+ err = ovl_create_volatile_dirty(ofs);
+ if (err < 0) {
+ pr_err("Failed to create volatile/dirty file.\n");
+ goto out;
+ }
}
/* Check if upper/work fs supports file handles */
fh_type = ovl_can_decode_fh(ofs->workdir->d_sb);
if (ofs->config.index && !fh_type) {
ofs->config.index = false;
- pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
+ pr_warn("upper fs does not support file handles, falling back to index=off.\n");
}
/* Check if upper fs has 32bit inode numbers */
if (fh_type != FILEID_INO32_GEN)
- ofs->xino_bits = 0;
+ ofs->xino_mode = -1;
/* NFS export of r/w mount depends on index */
if (ofs->config.nfs_export && !ofs->config.index) {
- pr_warn("overlayfs: NFS export requires \"index=on\", falling back to nfs_export=off.\n");
+ pr_warn("NFS export requires \"index=on\", falling back to nfs_export=off.\n");
ofs->config.nfs_export = false;
}
out:
@@ -1215,11 +1432,11 @@
err = -EINVAL;
if (upperpath->mnt != workpath.mnt) {
- pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
+ pr_err("workdir and upperdir must reside under the same mount\n");
goto out;
}
if (!ovl_workdir_ok(workpath.dentry, upperpath->dentry)) {
- pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+ pr_err("workdir and upperdir must be separate subtrees\n");
goto out;
}
@@ -1249,7 +1466,8 @@
static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs,
struct ovl_entry *oe, struct path *upperpath)
{
- struct vfsmount *mnt = ofs->upper_mnt;
+ struct vfsmount *mnt = ovl_upper_mnt(ofs);
+ struct dentry *indexdir;
int err;
err = mnt_want_write(mnt);
@@ -1257,15 +1475,25 @@
return err;
/* Verify lower root is upper root origin */
- err = ovl_verify_origin(upperpath->dentry, oe->lowerstack[0].dentry,
- true);
+ err = ovl_verify_origin(ofs, upperpath->dentry,
+ oe->lowerstack[0].dentry, true);
if (err) {
- pr_err("overlayfs: failed to verify upper root origin\n");
+ pr_err("failed to verify upper root origin\n");
goto out;
}
- ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true);
- if (ofs->indexdir) {
+ /* index dir will act also as workdir */
+ iput(ofs->workdir_trap);
+ ofs->workdir_trap = NULL;
+ dput(ofs->workdir);
+ ofs->workdir = NULL;
+ indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true);
+ if (IS_ERR(indexdir)) {
+ err = PTR_ERR(indexdir);
+ } else if (indexdir) {
+ ofs->indexdir = indexdir;
+ ofs->workdir = dget(indexdir);
+
err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap,
"indexdir");
if (err)
@@ -1279,80 +1507,143 @@
* "trusted.overlay.upper" to indicate that index may have
* directory entries.
*/
- if (ovl_check_origin_xattr(ofs->indexdir)) {
- err = ovl_verify_set_fh(ofs->indexdir, OVL_XATTR_ORIGIN,
+ if (ovl_check_origin_xattr(ofs, ofs->indexdir)) {
+ err = ovl_verify_set_fh(ofs, ofs->indexdir,
+ OVL_XATTR_ORIGIN,
upperpath->dentry, true, false);
if (err)
- pr_err("overlayfs: failed to verify index dir 'origin' xattr\n");
+ pr_err("failed to verify index dir 'origin' xattr\n");
}
- err = ovl_verify_upper(ofs->indexdir, upperpath->dentry, true);
+ err = ovl_verify_upper(ofs, ofs->indexdir, upperpath->dentry,
+ true);
if (err)
- pr_err("overlayfs: failed to verify index dir 'upper' xattr\n");
+ pr_err("failed to verify index dir 'upper' xattr\n");
/* Cleanup bad/stale/orphan index entries */
if (!err)
err = ovl_indexdir_cleanup(ofs);
}
if (err || !ofs->indexdir)
- pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
+ pr_warn("try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
out:
mnt_drop_write(mnt);
return err;
}
-/* Get a unique fsid for the layer */
-static int ovl_get_fsid(struct ovl_fs *ofs, struct super_block *sb)
+static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid)
{
+ unsigned int i;
+
+ if (!ofs->config.nfs_export && !ovl_upper_mnt(ofs))
+ return true;
+
+ /*
+ * We allow using single lower with null uuid for index and nfs_export
+ * for example to support those features with single lower squashfs.
+ * To avoid regressions in setups of overlay with re-formatted lower
+ * squashfs, do not allow decoding origin with lower null uuid unless
+ * user opted-in to one of the new features that require following the
+ * lower inode of non-dir upper.
+ */
+ if (!ofs->config.index && !ofs->config.metacopy && !ofs->config.xino &&
+ uuid_is_null(uuid))
+ return false;
+
+ for (i = 0; i < ofs->numfs; i++) {
+ /*
+ * We use uuid to associate an overlay lower file handle with a
+ * lower layer, so we can accept lower fs with null uuid as long
+ * as all lower layers with null uuid are on the same fs.
+ * if we detect multiple lower fs with the same uuid, we
+ * disable lower file handle decoding on all of them.
+ */
+ if (ofs->fs[i].is_lower &&
+ uuid_equal(&ofs->fs[i].sb->s_uuid, uuid)) {
+ ofs->fs[i].bad_uuid = true;
+ return false;
+ }
+ }
+ return true;
+}
+
+/* Get a unique fsid for the layer */
+static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path)
+{
+ struct super_block *sb = path->mnt->mnt_sb;
unsigned int i;
dev_t dev;
int err;
+ bool bad_uuid = false;
- /* fsid 0 is reserved for upper fs even with non upper overlay */
- if (ofs->upper_mnt && ofs->upper_mnt->mnt_sb == sb)
- return 0;
+ for (i = 0; i < ofs->numfs; i++) {
+ if (ofs->fs[i].sb == sb)
+ return i;
+ }
- for (i = 0; i < ofs->numlowerfs; i++) {
- if (ofs->lower_fs[i].sb == sb)
- return i + 1;
+ if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) {
+ bad_uuid = true;
+ if (ofs->config.index || ofs->config.nfs_export) {
+ ofs->config.index = false;
+ ofs->config.nfs_export = false;
+ pr_warn("%s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n",
+ uuid_is_null(&sb->s_uuid) ? "null" :
+ "conflicting",
+ path->dentry);
+ }
}
err = get_anon_bdev(&dev);
if (err) {
- pr_err("overlayfs: failed to get anonymous bdev for lowerpath\n");
+ pr_err("failed to get anonymous bdev for lowerpath\n");
return err;
}
- ofs->lower_fs[ofs->numlowerfs].sb = sb;
- ofs->lower_fs[ofs->numlowerfs].pseudo_dev = dev;
- ofs->numlowerfs++;
+ ofs->fs[ofs->numfs].sb = sb;
+ ofs->fs[ofs->numfs].pseudo_dev = dev;
+ ofs->fs[ofs->numfs].bad_uuid = bad_uuid;
- return ofs->numlowerfs;
+ return ofs->numfs++;
}
-static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs,
- struct path *stack, unsigned int numlower)
+static int ovl_get_layers(struct super_block *sb, struct ovl_fs *ofs,
+ struct path *stack, unsigned int numlower,
+ struct ovl_layer *layers)
{
int err;
unsigned int i;
err = -ENOMEM;
- ofs->lower_layers = kcalloc(numlower, sizeof(struct ovl_layer),
- GFP_KERNEL);
- if (ofs->lower_layers == NULL)
+ ofs->fs = kcalloc(numlower + 1, sizeof(struct ovl_sb), GFP_KERNEL);
+ if (ofs->fs == NULL)
goto out;
- ofs->lower_fs = kcalloc(numlower, sizeof(struct ovl_sb),
- GFP_KERNEL);
- if (ofs->lower_fs == NULL)
+ /* idx/fsid 0 are reserved for upper fs even with lower only overlay */
+ ofs->numfs++;
+
+ /*
+ * All lower layers that share the same fs as upper layer, use the same
+ * pseudo_dev as upper layer. Allocate fs[0].pseudo_dev even for lower
+ * only overlay to simplify ovl_fs_free().
+ * is_lower will be set if upper fs is shared with a lower layer.
+ */
+ err = get_anon_bdev(&ofs->fs[0].pseudo_dev);
+ if (err) {
+ pr_err("failed to get anonymous bdev for upper fs\n");
goto out;
+ }
+
+ if (ovl_upper_mnt(ofs)) {
+ ofs->fs[0].sb = ovl_upper_mnt(ofs)->mnt_sb;
+ ofs->fs[0].is_lower = false;
+ }
for (i = 0; i < numlower; i++) {
struct vfsmount *mnt;
struct inode *trap;
int fsid;
- err = fsid = ovl_get_fsid(ofs, stack[i].mnt->mnt_sb);
+ err = fsid = ovl_get_fsid(ofs, &stack[i]);
if (err < 0)
goto out;
@@ -1378,7 +1669,7 @@
mnt = clone_private_mount(&stack[i]);
err = PTR_ERR(mnt);
if (IS_ERR(mnt)) {
- pr_err("overlayfs: failed to clone lowerpath\n");
+ pr_err("failed to clone lowerpath\n");
iput(trap);
goto out;
}
@@ -1389,41 +1680,45 @@
*/
mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME;
- ofs->lower_layers[ofs->numlower].trap = trap;
- ofs->lower_layers[ofs->numlower].mnt = mnt;
- ofs->lower_layers[ofs->numlower].idx = i + 1;
- ofs->lower_layers[ofs->numlower].fsid = fsid;
- if (fsid) {
- ofs->lower_layers[ofs->numlower].fs =
- &ofs->lower_fs[fsid - 1];
- }
- ofs->numlower++;
+ layers[ofs->numlayer].trap = trap;
+ layers[ofs->numlayer].mnt = mnt;
+ layers[ofs->numlayer].idx = ofs->numlayer;
+ layers[ofs->numlayer].fsid = fsid;
+ layers[ofs->numlayer].fs = &ofs->fs[fsid];
+ ofs->numlayer++;
+ ofs->fs[fsid].is_lower = true;
}
/*
* When all layers on same fs, overlay can use real inode numbers.
- * With mount option "xino=on", mounter declares that there are enough
- * free high bits in underlying fs to hold the unique fsid.
+ * With mount option "xino=<on|auto>", mounter declares that there are
+ * enough free high bits in underlying fs to hold the unique fsid.
* If overlayfs does encounter underlying inodes using the high xino
* bits reserved for fsid, it emits a warning and uses the original
- * inode number.
+ * inode number or a non persistent inode number allocated from a
+ * dedicated range.
*/
- if (!ofs->numlowerfs || (ofs->numlowerfs == 1 && !ofs->upper_mnt)) {
- ofs->xino_bits = 0;
- ofs->config.xino = OVL_XINO_OFF;
- } else if (ofs->config.xino == OVL_XINO_ON && !ofs->xino_bits) {
+ if (ofs->numfs - !ovl_upper_mnt(ofs) == 1) {
+ if (ofs->config.xino == OVL_XINO_ON)
+ pr_info("\"xino=on\" is useless with all layers on same fs, ignore.\n");
+ ofs->xino_mode = 0;
+ } else if (ofs->config.xino == OVL_XINO_OFF) {
+ ofs->xino_mode = -1;
+ } else if (ofs->xino_mode < 0) {
/*
- * This is a roundup of number of bits needed for numlowerfs+1
- * (i.e. ilog2(numlowerfs+1 - 1) + 1). fsid 0 is reserved for
- * upper fs even with non upper overlay.
+ * This is a roundup of number of bits needed for encoding
+ * fsid, where fsid 0 is reserved for upper fs (even with
+ * lower only overlay) +1 extra bit is reserved for the non
+ * persistent inode number range that is used for resolving
+ * xino lower bits overflow.
*/
- BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 31);
- ofs->xino_bits = ilog2(ofs->numlowerfs) + 1;
+ BUILD_BUG_ON(ilog2(OVL_MAX_STACK) > 30);
+ ofs->xino_mode = ilog2(ofs->numfs - 1) + 2;
}
- if (ofs->xino_bits) {
- pr_info("overlayfs: \"xino\" feature enabled using %d upper inode bits.\n",
- ofs->xino_bits);
+ if (ofs->xino_mode > 0) {
+ pr_info("\"xino\" feature enabled using %d upper inode bits.\n",
+ ofs->xino_mode);
}
err = 0;
@@ -1432,45 +1727,26 @@
}
static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb,
- struct ovl_fs *ofs)
+ const char *lower, unsigned int numlower,
+ struct ovl_fs *ofs, struct ovl_layer *layers)
{
int err;
- char *lowertmp, *lower;
struct path *stack = NULL;
- unsigned int stacklen, numlower = 0, i;
- bool remote = false;
+ unsigned int i;
struct ovl_entry *oe;
- err = -ENOMEM;
- lowertmp = kstrdup(ofs->config.lowerdir, GFP_KERNEL);
- if (!lowertmp)
- goto out_err;
-
- err = -EINVAL;
- stacklen = ovl_split_lowerdirs(lowertmp);
- if (stacklen > OVL_MAX_STACK) {
- pr_err("overlayfs: too many lower directories, limit is %d\n",
- OVL_MAX_STACK);
- goto out_err;
- } else if (!ofs->config.upperdir && stacklen == 1) {
- pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
- goto out_err;
- } else if (!ofs->config.upperdir && ofs->config.nfs_export &&
- ofs->config.redirect_follow) {
- pr_warn("overlayfs: NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n");
- ofs->config.nfs_export = false;
+ if (!ofs->config.upperdir && numlower == 1) {
+ pr_err("at least 2 lowerdir are needed while upperdir nonexistent\n");
+ return ERR_PTR(-EINVAL);
}
- err = -ENOMEM;
- stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
+ stack = kcalloc(numlower, sizeof(struct path), GFP_KERNEL);
if (!stack)
- goto out_err;
+ return ERR_PTR(-ENOMEM);
err = -EINVAL;
- lower = lowertmp;
- for (numlower = 0; numlower < stacklen; numlower++) {
- err = ovl_lower_dir(lower, &stack[numlower], ofs,
- &sb->s_stack_depth, &remote);
+ for (i = 0; i < numlower; i++) {
+ err = ovl_lower_dir(lower, &stack[i], ofs, &sb->s_stack_depth);
if (err)
goto out_err;
@@ -1480,11 +1756,11 @@
err = -EINVAL;
sb->s_stack_depth++;
if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
- pr_err("overlayfs: maximum fs stacking depth exceeded\n");
+ pr_err("maximum fs stacking depth exceeded\n");
goto out_err;
}
- err = ovl_get_lower_layers(sb, ofs, stack, numlower);
+ err = ovl_get_layers(sb, ofs, stack, numlower, layers);
if (err)
goto out_err;
@@ -1495,19 +1771,13 @@
for (i = 0; i < numlower; i++) {
oe->lowerstack[i].dentry = dget(stack[i].dentry);
- oe->lowerstack[i].layer = &ofs->lower_layers[i];
+ oe->lowerstack[i].layer = &ofs->layers[i+1];
}
-
- if (remote)
- sb->s_d_op = &ovl_reval_dentry_operations;
- else
- sb->s_d_op = &ovl_dentry_operations;
out:
for (i = 0; i < numlower; i++)
path_put(&stack[i]);
kfree(stack);
- kfree(lowertmp);
return oe;
@@ -1537,7 +1807,7 @@
while (!err && parent != next) {
if (is_lower && ovl_lookup_trap_inode(sb, parent)) {
err = -ELOOP;
- pr_err("overlayfs: overlapping %s path\n", name);
+ pr_err("overlapping %s path\n", name);
} else if (ovl_is_inuse(parent)) {
err = ovl_report_in_use(ofs, name);
}
@@ -1559,8 +1829,8 @@
{
int i, err;
- if (ofs->upper_mnt) {
- err = ovl_check_layer(sb, ofs, ofs->upper_mnt->mnt_root,
+ if (ovl_upper_mnt(ofs)) {
+ err = ovl_check_layer(sb, ofs, ovl_upper_mnt(ofs)->mnt_root,
"upperdir", false);
if (err)
return err;
@@ -1578,9 +1848,9 @@
return err;
}
- for (i = 0; i < ofs->numlower; i++) {
+ for (i = 1; i < ofs->numlayer; i++) {
err = ovl_check_layer(sb, ofs,
- ofs->lower_layers[i].mnt->mnt_root,
+ ofs->layers[i].mnt->mnt_root,
"lowerdir", true);
if (err)
return err;
@@ -1589,14 +1859,57 @@
return 0;
}
+static struct dentry *ovl_get_root(struct super_block *sb,
+ struct dentry *upperdentry,
+ struct ovl_entry *oe)
+{
+ struct dentry *root;
+ struct ovl_path *lowerpath = &oe->lowerstack[0];
+ unsigned long ino = d_inode(lowerpath->dentry)->i_ino;
+ int fsid = lowerpath->layer->fsid;
+ struct ovl_inode_params oip = {
+ .upperdentry = upperdentry,
+ .lowerpath = lowerpath,
+ };
+
+ root = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
+ if (!root)
+ return NULL;
+
+ root->d_fsdata = oe;
+
+ if (upperdentry) {
+ /* Root inode uses upper st_ino/i_ino */
+ ino = d_inode(upperdentry)->i_ino;
+ fsid = 0;
+ ovl_dentry_set_upper_alias(root);
+ if (ovl_is_impuredir(sb, upperdentry))
+ ovl_set_flag(OVL_IMPURE, d_inode(root));
+ }
+
+ /* Root is always merge -> can have whiteouts */
+ ovl_set_flag(OVL_WHITEOUTS, d_inode(root));
+ ovl_dentry_set_flag(OVL_E_CONNECTED, root);
+ ovl_set_upperdata(d_inode(root));
+ ovl_inode_init(d_inode(root), &oip, ino, fsid);
+ ovl_dentry_init_flags(root, upperdentry, DCACHE_OP_WEAK_REVALIDATE);
+
+ return root;
+}
+
static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
struct path upperpath = { };
struct dentry *root_dentry;
struct ovl_entry *oe;
struct ovl_fs *ofs;
+ struct ovl_layer *layers;
struct cred *cred;
+ char *splitlower = NULL;
+ unsigned int numlower;
int err;
+
+ sb->s_d_op = &ovl_dentry_operations;
err = -ENOMEM;
ofs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
@@ -1606,6 +1919,9 @@
ofs->creator_cred = cred = prepare_creds();
if (!cred)
goto out_err;
+
+ /* Is there a reason anyone would want not to share whiteouts? */
+ ofs->share_whiteout = true;
ofs->config.index = ovl_index_def;
ofs->config.nfs_export = ovl_nfs_export_def;
@@ -1618,28 +1934,66 @@
err = -EINVAL;
if (!ofs->config.lowerdir) {
if (!silent)
- pr_err("overlayfs: missing 'lowerdir'\n");
+ pr_err("missing 'lowerdir'\n");
goto out_err;
}
+ err = -ENOMEM;
+ splitlower = kstrdup(ofs->config.lowerdir, GFP_KERNEL);
+ if (!splitlower)
+ goto out_err;
+
+ numlower = ovl_split_lowerdirs(splitlower);
+ if (numlower > OVL_MAX_STACK) {
+ pr_err("too many lower directories, limit is %d\n",
+ OVL_MAX_STACK);
+ goto out_err;
+ }
+
+ layers = kcalloc(numlower + 1, sizeof(struct ovl_layer), GFP_KERNEL);
+ if (!layers)
+ goto out_err;
+
+ ofs->layers = layers;
+ /* Layer 0 is reserved for upper even if there's no upper */
+ ofs->numlayer = 1;
+
sb->s_stack_depth = 0;
sb->s_maxbytes = MAX_LFS_FILESIZE;
+ atomic_long_set(&ofs->last_ino, 1);
/* Assume underlaying fs uses 32bit inodes unless proven otherwise */
- if (ofs->config.xino != OVL_XINO_OFF)
- ofs->xino_bits = BITS_PER_LONG - 32;
+ if (ofs->config.xino != OVL_XINO_OFF) {
+ ofs->xino_mode = BITS_PER_LONG - 32;
+ if (!ofs->xino_mode) {
+ pr_warn("xino not supported on 32bit kernel, falling back to xino=off.\n");
+ ofs->config.xino = OVL_XINO_OFF;
+ }
+ }
/* alloc/destroy_inode needed for setting up traps in inode cache */
sb->s_op = &ovl_super_operations;
if (ofs->config.upperdir) {
+ struct super_block *upper_sb;
+
if (!ofs->config.workdir) {
- pr_err("overlayfs: missing 'workdir'\n");
+ pr_err("missing 'workdir'\n");
goto out_err;
}
- err = ovl_get_upper(sb, ofs, &upperpath);
+ err = ovl_get_upper(sb, ofs, &layers[0], &upperpath);
if (err)
goto out_err;
+
+ upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
+ if (!ovl_should_sync(ofs)) {
+ ofs->errseq = errseq_sample(&upper_sb->s_wb_err);
+ if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
+ err = -EIO;
+ pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
+ goto out_err;
+ }
+ }
err = ovl_get_workdir(sb, ofs, &upperpath);
if (err)
@@ -1648,31 +2002,26 @@
if (!ofs->workdir)
sb->s_flags |= SB_RDONLY;
- sb->s_stack_depth = ofs->upper_mnt->mnt_sb->s_stack_depth;
- sb->s_time_gran = ofs->upper_mnt->mnt_sb->s_time_gran;
-
+ sb->s_stack_depth = upper_sb->s_stack_depth;
+ sb->s_time_gran = upper_sb->s_time_gran;
}
- oe = ovl_get_lowerstack(sb, ofs);
+ oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers);
err = PTR_ERR(oe);
if (IS_ERR(oe))
goto out_err;
/* If the upper fs is nonexistent, we mark overlayfs r/o too */
- if (!ofs->upper_mnt)
+ if (!ovl_upper_mnt(ofs))
sb->s_flags |= SB_RDONLY;
- if (!(ovl_force_readonly(ofs)) && ofs->config.index) {
+ if (!ovl_force_readonly(ofs) && ofs->config.index) {
err = ovl_get_indexdir(sb, ofs, oe, &upperpath);
if (err)
goto out_free_oe;
/* Force r/o mount with no index dir */
- if (!ofs->indexdir) {
- dput(ofs->workdir);
- ofs->workdir = NULL;
+ if (!ofs->indexdir)
sb->s_flags |= SB_RDONLY;
- }
-
}
err = ovl_check_overlapping_layers(sb, ofs);
@@ -1682,14 +2031,14 @@
/* Show index=off in /proc/mounts for forced r/o mount */
if (!ofs->indexdir) {
ofs->config.index = false;
- if (ofs->upper_mnt && ofs->config.nfs_export) {
- pr_warn("overlayfs: NFS export requires an index dir, falling back to nfs_export=off.\n");
+ if (ovl_upper_mnt(ofs) && ofs->config.nfs_export) {
+ pr_warn("NFS export requires an index dir, falling back to nfs_export=off.\n");
ofs->config.nfs_export = false;
}
}
if (ofs->config.metacopy && ofs->config.nfs_export) {
- pr_warn("overlayfs: NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n");
+ pr_warn("NFS export is not supported with metadata only copy up, falling back to nfs_export=off.\n");
ofs->config.nfs_export = false;
}
@@ -1703,27 +2052,15 @@
sb->s_xattr = ovl_xattr_handlers;
sb->s_fs_info = ofs;
sb->s_flags |= SB_POSIXACL;
+ sb->s_iflags |= SB_I_SKIP_SYNC | SB_I_IMA_UNVERIFIABLE_SIGNATURE;
err = -ENOMEM;
- root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
+ root_dentry = ovl_get_root(sb, upperpath.dentry, oe);
if (!root_dentry)
goto out_free_oe;
- root_dentry->d_fsdata = oe;
-
mntput(upperpath.mnt);
- if (upperpath.dentry) {
- ovl_dentry_set_upper_alias(root_dentry);
- if (ovl_is_impuredir(upperpath.dentry))
- ovl_set_flag(OVL_IMPURE, d_inode(root_dentry));
- }
-
- /* Root is always merge -> can have whiteouts */
- ovl_set_flag(OVL_WHITEOUTS, d_inode(root_dentry));
- ovl_dentry_set_flag(OVL_E_CONNECTED, root_dentry);
- ovl_set_upperdata(d_inode(root_dentry));
- ovl_inode_init(d_inode(root_dentry), upperpath.dentry,
- ovl_dentry_lower(root_dentry), NULL);
+ kfree(splitlower);
sb->s_root = root_dentry;
return 0;
@@ -1732,6 +2069,7 @@
ovl_entry_stack_free(oe);
kfree(oe);
out_err:
+ kfree(splitlower);
path_put(&upperpath);
ovl_free_fs(ofs);
out:
@@ -1771,9 +2109,15 @@
if (ovl_inode_cachep == NULL)
return -ENOMEM;
- err = register_filesystem(&ovl_fs_type);
- if (err)
- kmem_cache_destroy(ovl_inode_cachep);
+ err = ovl_aio_request_cache_init();
+ if (!err) {
+ err = register_filesystem(&ovl_fs_type);
+ if (!err)
+ return 0;
+
+ ovl_aio_request_cache_destroy();
+ }
+ kmem_cache_destroy(ovl_inode_cachep);
return err;
}
@@ -1788,7 +2132,7 @@
*/
rcu_barrier();
kmem_cache_destroy(ovl_inode_cachep);
-
+ ovl_aio_request_cache_destroy();
}
module_init(ovl_init);
--
Gitblit v1.6.2