[Feature]add MT2731_MP2_MR2_SVN388 baseline version
Change-Id: Ief04314834b31e27effab435d3ca8ba33b499059
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/Kconfig b/src/kernel/linux/v4.14/fs/overlayfs/Kconfig
new file mode 100644
index 0000000..cbfc196
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/Kconfig
@@ -0,0 +1,45 @@
+config OVERLAY_FS
+ tristate "Overlay filesystem support"
+ select EXPORTFS
+ help
+ An overlay filesystem combines two filesystems - an 'upper' filesystem
+ and a 'lower' filesystem. When a name exists in both filesystems, the
+ object in the 'upper' filesystem is visible while the object in the
+ 'lower' filesystem is either hidden or, in the case of directories,
+ merged with the 'upper' object.
+
+ For more information see Documentation/filesystems/overlayfs.txt
+
+config OVERLAY_FS_REDIRECT_DIR
+ bool "Overlayfs: turn on redirect dir feature by default"
+ depends on OVERLAY_FS
+ help
+ If this config option is enabled then overlay filesystems will use
+ redirects when renaming directories by default. In this case it is
+ still possible to turn off redirects globally with the
+ "redirect_dir=off" module option or on a filesystem instance basis
+ with the "redirect_dir=off" mount option.
+
+ Note, that redirects are not backward compatible. That is, mounting
+ an overlay which has redirects on a kernel that doesn't support this
+ feature will have unexpected results.
+
+config OVERLAY_FS_INDEX
+ bool "Overlayfs: turn on inodes index feature by default"
+ depends on OVERLAY_FS
+ help
+ If this config option is enabled then overlay filesystems will use
+ the inodes index dir to map lower inodes to upper inodes by default.
+ In this case it is still possible to turn off index globally with the
+ "index=off" module option or on a filesystem instance basis with the
+ "index=off" mount option.
+
+ The inodes index feature prevents breaking of lower hardlinks on copy
+ up.
+
+ Note, that the inodes index feature is read-only backward compatible.
+ That is, mounting an overlay which has an index dir on a kernel that
+ doesn't support this feature read-only, will not have any negative
+ outcomes. However, mounting the same overlay with an old kernel
+ read-write and then mounting it again with a new kernel, will have
+ unexpected results.
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/Makefile b/src/kernel/linux/v4.14/fs/overlayfs/Makefile
new file mode 100644
index 0000000..99373bb
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the overlay filesystem.
+#
+
+obj-$(CONFIG_OVERLAY_FS) += overlay.o
+
+overlay-objs := super.o namei.o util.o inode.o dir.o readdir.o copy_up.o
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/copy_up.c b/src/kernel/linux/v4.14/fs/overlayfs/copy_up.c
new file mode 100644
index 0000000..b97fc1d
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/copy_up.c
@@ -0,0 +1,698 @@
+/*
+ *
+ * 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/module.h>
+#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/signal.h>
+#include <linux/cred.h>
+#include <linux/namei.h>
+#include <linux/fdtable.h>
+#include <linux/ratelimit.h>
+#include <linux/exportfs.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+#define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
+
+static bool __read_mostly ovl_check_copy_up;
+module_param_named(check_copy_up, ovl_check_copy_up, bool,
+ S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(ovl_check_copy_up,
+ "Warn on copy-up when causing process also has a R/O fd open");
+
+static int ovl_check_fd(const void *data, struct file *f, unsigned int fd)
+{
+ const struct dentry *dentry = data;
+
+ if (file_inode(f) == d_inode(dentry))
+ pr_warn_ratelimited("overlayfs: Warning: Copying up %pD, but open R/O on fd %u which will cease to be coherent [pid=%d %s]\n",
+ f, fd, current->pid, current->comm);
+ return 0;
+}
+
+/*
+ * Check the fds open by this process and warn if something like the following
+ * scenario is about to occur:
+ *
+ * fd1 = open("foo", O_RDONLY);
+ * fd2 = open("foo", O_RDWR);
+ */
+static void ovl_do_check_copy_up(struct dentry *dentry)
+{
+ if (ovl_check_copy_up)
+ iterate_fd(current->files, 0, ovl_check_fd, dentry);
+}
+
+int ovl_copy_xattr(struct dentry *old, struct dentry *new)
+{
+ ssize_t list_size, size, value_size = 0;
+ char *buf, *name, *value = NULL;
+ int error = 0;
+ size_t slen;
+
+ if (!(old->d_inode->i_opflags & IOP_XATTR) ||
+ !(new->d_inode->i_opflags & IOP_XATTR))
+ 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;
+
+ list_size = vfs_listxattr(old, buf, list_size);
+ if (list_size <= 0) {
+ error = list_size;
+ goto out;
+ }
+
+ for (name = buf; list_size; name += slen) {
+ slen = strnlen(name, list_size) + 1;
+
+ /* underlying fs providing us with an broken xattr list? */
+ if (WARN_ON(slen > list_size)) {
+ error = -EIO;
+ break;
+ }
+ list_size -= slen;
+
+ if (ovl_is_private_xattr(name))
+ continue;
+retry:
+ size = vfs_getxattr(old, name, value, value_size);
+ if (size == -ERANGE)
+ size = vfs_getxattr(old, name, NULL, 0);
+
+ if (size < 0) {
+ error = size;
+ break;
+ }
+
+ if (size > value_size) {
+ void *new;
+
+ new = krealloc(value, size, GFP_KERNEL);
+ if (!new) {
+ error = -ENOMEM;
+ break;
+ }
+ value = new;
+ value_size = size;
+ goto retry;
+ }
+
+ error = security_inode_copy_up_xattr(name);
+ if (error < 0 && error != -EOPNOTSUPP)
+ break;
+ if (error == 1) {
+ error = 0;
+ continue; /* Discard */
+ }
+ error = vfs_setxattr(new, name, value, size, 0);
+ if (error)
+ break;
+ }
+ 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_LARGEFILE | O_RDONLY);
+ if (IS_ERR(old_file))
+ return PTR_ERR(old_file);
+
+ new_file = ovl_path_open(new, O_LARGEFILE | O_WRONLY);
+ if (IS_ERR(new_file)) {
+ error = PTR_ERR(new_file);
+ goto out_fput;
+ }
+
+ /* Try to use clone_file_range to clone up within the same fs */
+ error = do_clone_file_range(old_file, 0, new_file, 0, len);
+ if (!error)
+ goto out;
+ /* Couldn't clone, so now we try to copy the data */
+ error = 0;
+
+ /* 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;
+ }
+out:
+ if (!error)
+ error = vfs_fsync(new_file, 0);
+ fput(new_file);
+out_fput:
+ fput(old_file);
+ return error;
+}
+
+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;
+}
+
+struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper)
+{
+ struct ovl_fh *fh;
+ int fh_type, fh_len, dwords;
+ void *buf;
+ int buflen = MAX_HANDLE_SZ;
+ uuid_t *uuid = &lower->d_sb->s_uuid;
+
+ buf = kmalloc(buflen, GFP_KERNEL);
+ if (!buf)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * We encode a non-connectable file handle for non-dir, because we
+ * only need to find the lower inode number and we don't want to pay
+ * the price or reconnecting the dentry.
+ */
+ dwords = buflen >> 2;
+ fh_type = exportfs_encode_fh(lower, buf, &dwords, 0);
+ buflen = (dwords << 2);
+
+ fh = ERR_PTR(-EIO);
+ if (WARN_ON(fh_type < 0) ||
+ WARN_ON(buflen > MAX_HANDLE_SZ) ||
+ WARN_ON(fh_type == FILEID_INVALID))
+ goto out;
+
+ BUILD_BUG_ON(MAX_HANDLE_SZ + offsetof(struct ovl_fh, fid) > 255);
+ fh_len = offsetof(struct ovl_fh, fid) + buflen;
+ fh = kmalloc(fh_len, GFP_KERNEL);
+ if (!fh) {
+ fh = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ fh->version = OVL_FH_VERSION;
+ fh->magic = OVL_FH_MAGIC;
+ fh->type = fh_type;
+ fh->flags = OVL_FH_FLAG_CPU_ENDIAN;
+ /*
+ * When we will want to decode an overlay dentry from this handle
+ * and all layers are on the same fs, if we get a disconncted real
+ * dentry when we decode fid, the only way to tell if we should assign
+ * it to upperdentry or to lowerstack is by checking this flag.
+ */
+ if (is_upper)
+ fh->flags |= OVL_FH_FLAG_PATH_UPPER;
+ fh->len = fh_len;
+ fh->uuid = *uuid;
+ memcpy(fh->fid, buf, buflen);
+
+out:
+ kfree(buf);
+ return fh;
+}
+
+static int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
+ struct dentry *upper)
+{
+ const struct ovl_fh *fh = NULL;
+ int err;
+
+ /*
+ * When lower layer doesn't support export operations store a 'null' fh,
+ * so we can use the overlay.origin xattr to distignuish between a copy
+ * up and a pure upper inode.
+ */
+ if (ovl_can_decode_fh(lower->d_sb)) {
+ fh = ovl_encode_fh(lower, false);
+ if (IS_ERR(fh))
+ return PTR_ERR(fh);
+ }
+
+ /*
+ * Do not fail when upper doesn't support xattrs.
+ */
+ err = ovl_check_setxattr(dentry, upper, OVL_XATTR_ORIGIN, fh,
+ fh ? fh->len : 0, 0);
+ kfree(fh);
+
+ return err;
+}
+
+struct ovl_copy_up_ctx {
+ struct dentry *parent;
+ struct dentry *dentry;
+ struct path lowerpath;
+ struct kstat stat;
+ struct kstat pstat;
+ const char *link;
+ struct dentry *destdir;
+ struct qstr destname;
+ struct dentry *workdir;
+ bool tmpfile;
+ bool origin;
+};
+
+static int ovl_link_up(struct ovl_copy_up_ctx *c)
+{
+ int err;
+ struct dentry *upper;
+ struct dentry *upperdir = ovl_dentry_upper(c->parent);
+ struct inode *udir = d_inode(upperdir);
+
+ /* Mark parent "impure" because it may now contain non-pure upper */
+ err = ovl_set_impure(c->parent, upperdir);
+ if (err)
+ return err;
+
+ err = ovl_set_nlink_lower(c->dentry);
+ if (err)
+ return err;
+
+ inode_lock_nested(udir, I_MUTEX_PARENT);
+ upper = lookup_one_len(c->dentry->d_name.name, upperdir,
+ c->dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (!IS_ERR(upper)) {
+ err = ovl_do_link(ovl_dentry_upper(c->dentry), udir, upper,
+ true);
+ dput(upper);
+
+ if (!err) {
+ /* Restore timestamps on parent (best effort) */
+ ovl_set_timestamps(upperdir, &c->pstat);
+ ovl_dentry_set_upper_alias(c->dentry);
+ }
+ }
+ inode_unlock(udir);
+ ovl_set_nlink_upper(c->dentry);
+
+ return err;
+}
+
+static int ovl_install_temp(struct ovl_copy_up_ctx *c, struct dentry *temp,
+ struct dentry **newdentry)
+{
+ int err;
+ struct dentry *upper;
+ struct inode *udir = d_inode(c->destdir);
+
+ upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
+ if (IS_ERR(upper))
+ return PTR_ERR(upper);
+
+ if (c->tmpfile)
+ err = ovl_do_link(temp, udir, upper, true);
+ else
+ err = ovl_do_rename(d_inode(c->workdir), temp, udir, upper, 0);
+
+ if (!err)
+ *newdentry = dget(c->tmpfile ? upper : temp);
+ dput(upper);
+
+ return err;
+}
+
+static int ovl_get_tmpfile(struct ovl_copy_up_ctx *c, struct dentry **tempp)
+{
+ int err;
+ struct dentry *temp;
+ const struct cred *old_creds = NULL;
+ struct cred *new_creds = NULL;
+ struct cattr cattr = {
+ /* Can't properly set mode on creation because of the umask */
+ .mode = c->stat.mode & S_IFMT,
+ .rdev = c->stat.rdev,
+ .link = c->link
+ };
+
+ err = security_inode_copy_up(c->dentry, &new_creds);
+ if (err < 0)
+ goto out;
+
+ if (new_creds)
+ old_creds = override_creds(new_creds);
+
+ if (c->tmpfile) {
+ temp = ovl_do_tmpfile(c->workdir, c->stat.mode);
+ if (IS_ERR(temp))
+ goto temp_err;
+ } else {
+ temp = ovl_lookup_temp(c->workdir);
+ if (IS_ERR(temp))
+ goto temp_err;
+
+ err = ovl_create_real(d_inode(c->workdir), temp, &cattr,
+ NULL, true);
+ if (err) {
+ dput(temp);
+ goto out;
+ }
+ }
+ err = 0;
+ *tempp = temp;
+out:
+ if (new_creds) {
+ revert_creds(old_creds);
+ put_cred(new_creds);
+ }
+
+ return err;
+
+temp_err:
+ err = PTR_ERR(temp);
+ goto out;
+}
+
+static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
+{
+ int err;
+
+ if (S_ISREG(c->stat.mode)) {
+ struct path upperpath;
+
+ ovl_path_upper(c->dentry, &upperpath);
+ BUG_ON(upperpath.dentry != NULL);
+ upperpath.dentry = temp;
+
+ err = ovl_copy_up_data(&c->lowerpath, &upperpath, c->stat.size);
+ if (err)
+ return err;
+ }
+
+ err = ovl_copy_xattr(c->lowerpath.dentry, temp);
+ if (err)
+ return err;
+
+ inode_lock(temp->d_inode);
+ err = ovl_set_attr(temp, &c->stat);
+ inode_unlock(temp->d_inode);
+ if (err)
+ return err;
+
+ /*
+ * Store identifier of lower inode in upper inode xattr to
+ * allow lookup of the copy up origin inode.
+ *
+ * Don't set origin when we are breaking the association with a lower
+ * hard link.
+ */
+ if (c->origin) {
+ err = ovl_set_origin(c->dentry, c->lowerpath.dentry, temp);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
+{
+ struct inode *udir = c->destdir->d_inode;
+ struct dentry *newdentry = NULL;
+ struct dentry *temp = NULL;
+ int err;
+
+ err = ovl_get_tmpfile(c, &temp);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up_inode(c, temp);
+ if (err)
+ goto out_cleanup;
+
+ if (c->tmpfile) {
+ inode_lock_nested(udir, I_MUTEX_PARENT);
+ err = ovl_install_temp(c, temp, &newdentry);
+ inode_unlock(udir);
+ } else {
+ err = ovl_install_temp(c, temp, &newdentry);
+ }
+ if (err)
+ goto out_cleanup;
+
+ ovl_inode_update(d_inode(c->dentry), newdentry);
+out:
+ dput(temp);
+ return err;
+
+out_cleanup:
+ if (!c->tmpfile)
+ ovl_cleanup(d_inode(c->workdir), temp);
+ goto out;
+}
+
+/*
+ * Copy up a single dentry
+ *
+ * All 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.
+ */
+static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
+{
+ int err;
+ struct ovl_fs *ofs = c->dentry->d_sb->s_fs_info;
+ bool indexed = false;
+
+ if (ovl_indexdir(c->dentry->d_sb) && !S_ISDIR(c->stat.mode) &&
+ c->stat.nlink > 1)
+ indexed = true;
+
+ if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || indexed)
+ c->origin = true;
+
+ if (indexed) {
+ c->destdir = ovl_indexdir(c->dentry->d_sb);
+ err = ovl_get_index_name(c->lowerpath.dentry, &c->destname);
+ if (err)
+ return err;
+ } else {
+ /*
+ * Mark parent "impure" because it may now contain non-pure
+ * upper
+ */
+ err = ovl_set_impure(c->parent, c->destdir);
+ if (err)
+ return err;
+ }
+
+ /* Should we copyup with O_TMPFILE or with workdir? */
+ if (S_ISREG(c->stat.mode) && ofs->tmpfile) {
+ c->tmpfile = true;
+ err = ovl_copy_up_locked(c);
+ } else {
+ err = ovl_lock_rename_workdir(c->workdir, c->destdir);
+ if (!err) {
+ err = ovl_copy_up_locked(c);
+ unlock_rename(c->workdir, c->destdir);
+ }
+ }
+
+ if (indexed) {
+ if (!err)
+ ovl_set_flag(OVL_INDEX, d_inode(c->dentry));
+ kfree(c->destname.name);
+ } else if (!err) {
+ struct inode *udir = d_inode(c->destdir);
+
+ /* Restore timestamps on parent (best effort) */
+ inode_lock(udir);
+ ovl_set_timestamps(c->destdir, &c->pstat);
+ inode_unlock(udir);
+
+ ovl_dentry_set_upper_alias(c->dentry);
+ }
+
+ return err;
+}
+
+static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
+ int flags)
+{
+ int err;
+ DEFINE_DELAYED_CALL(done);
+ struct path parentpath;
+ struct ovl_copy_up_ctx ctx = {
+ .parent = parent,
+ .dentry = dentry,
+ .workdir = ovl_workdir(dentry),
+ };
+
+ if (WARN_ON(!ctx.workdir))
+ return -EROFS;
+
+ ovl_path_lower(dentry, &ctx.lowerpath);
+ err = vfs_getattr(&ctx.lowerpath, &ctx.stat,
+ STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+ if (err)
+ return err;
+
+ ovl_path_upper(parent, &parentpath);
+ ctx.destdir = parentpath.dentry;
+ ctx.destname = dentry->d_name;
+
+ err = vfs_getattr(&parentpath, &ctx.pstat,
+ STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT);
+ if (err)
+ return err;
+
+ /* maybe truncate regular file. this has no effect on dirs */
+ if (flags & O_TRUNC)
+ ctx.stat.size = 0;
+
+ if (S_ISLNK(ctx.stat.mode)) {
+ ctx.link = vfs_get_link(ctx.lowerpath.dentry, &done);
+ if (IS_ERR(ctx.link))
+ return PTR_ERR(ctx.link);
+ }
+ ovl_do_check_copy_up(ctx.lowerpath.dentry);
+
+ err = ovl_copy_up_start(dentry);
+ /* err < 0: interrupted, err > 0: raced with another copy-up */
+ if (unlikely(err)) {
+ if (err > 0)
+ err = 0;
+ } else {
+ if (!ovl_dentry_upper(dentry))
+ err = ovl_do_copy_up(&ctx);
+ if (!err && !ovl_dentry_has_upper_alias(dentry))
+ err = ovl_link_up(&ctx);
+ ovl_copy_up_end(dentry);
+ }
+ do_delayed_call(&done);
+
+ return err;
+}
+
+int ovl_copy_up_flags(struct dentry *dentry, int flags)
+{
+ int err = 0;
+ const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
+
+ while (!err) {
+ struct dentry *next;
+ struct dentry *parent;
+
+ /*
+ * Check if copy-up has happened as well as for upper alias (in
+ * case of hard links) is there.
+ *
+ * Both checks are lockless:
+ * - false negatives: will recheck under oi->lock
+ * - false positives:
+ * + ovl_dentry_upper() uses memory barriers to ensure the
+ * upper dentry is up-to-date
+ * + ovl_dentry_has_upper_alias() relies on locking of
+ * upper parent i_rwsem to prevent reordering copy-up
+ * with rename.
+ */
+ if (ovl_dentry_upper(dentry) &&
+ ovl_dentry_has_upper_alias(dentry))
+ break;
+
+ next = dget(dentry);
+ /* find the topmost dentry not yet copied up */
+ for (;;) {
+ parent = dget_parent(next);
+
+ if (ovl_dentry_upper(parent))
+ break;
+
+ dput(next);
+ next = parent;
+ }
+
+ err = ovl_copy_up_one(parent, next, flags);
+
+ dput(parent);
+ dput(next);
+ }
+ revert_creds(old_cred);
+
+ return err;
+}
+
+int ovl_copy_up(struct dentry *dentry)
+{
+ return ovl_copy_up_flags(dentry, 0);
+}
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/dir.c b/src/kernel/linux/v4.14/fs/overlayfs/dir.c
new file mode 100644
index 0000000..8c56170
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/dir.c
@@ -0,0 +1,1117 @@
+/*
+ *
+ * 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/namei.h>
+#include <linux/xattr.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include <linux/module.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include <linux/atomic.h>
+#include <linux/ratelimit.h>
+#include "overlayfs.h"
+
+static unsigned short ovl_redirect_max = 256;
+module_param_named(redirect_max, ovl_redirect_max, ushort, 0644);
+MODULE_PARM_DESC(ovl_redirect_max,
+ "Maximum length of absolute redirect xattr value");
+
+int ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
+{
+ int err;
+
+ dget(wdentry);
+ if (d_is_dir(wdentry))
+ err = ovl_do_rmdir(wdir, wdentry);
+ else
+ err = ovl_do_unlink(wdir, wdentry);
+ dput(wdentry);
+
+ if (err) {
+ pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n",
+ wdentry, err);
+ }
+
+ return err;
+}
+
+struct dentry *ovl_lookup_temp(struct dentry *workdir)
+{
+ struct dentry *temp;
+ char name[20];
+ static atomic_t temp_id = ATOMIC_INIT(0);
+
+ /* counter is allowed to wrap, since temp dentries are ephemeral */
+ snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
+
+ temp = lookup_one_len(name, workdir, strlen(name));
+ if (!IS_ERR(temp) && temp->d_inode) {
+ pr_err("overlayfs: workdir/%s already exists\n", name);
+ dput(temp);
+ temp = ERR_PTR(-EIO);
+ }
+
+ return temp;
+}
+
+/* caller holds i_mutex on workdir */
+static struct dentry *ovl_whiteout(struct dentry *workdir,
+ struct dentry *dentry)
+{
+ int err;
+ struct dentry *whiteout;
+ struct inode *wdir = workdir->d_inode;
+
+ whiteout = ovl_lookup_temp(workdir);
+ if (IS_ERR(whiteout))
+ return whiteout;
+
+ err = ovl_do_whiteout(wdir, whiteout);
+ if (err) {
+ dput(whiteout);
+ whiteout = ERR_PTR(err);
+ }
+
+ return whiteout;
+}
+
+int ovl_create_real(struct inode *dir, struct dentry *newdentry,
+ struct cattr *attr, struct dentry *hardlink, bool debug)
+{
+ int err;
+
+ if (newdentry->d_inode)
+ return -ESTALE;
+
+ if (hardlink) {
+ err = ovl_do_link(hardlink, dir, newdentry, debug);
+ } else {
+ switch (attr->mode & S_IFMT) {
+ case S_IFREG:
+ err = ovl_do_create(dir, newdentry, attr->mode, debug);
+ break;
+
+ case S_IFDIR:
+ err = ovl_do_mkdir(dir, newdentry, attr->mode, debug);
+ break;
+
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFIFO:
+ case S_IFSOCK:
+ err = ovl_do_mknod(dir, newdentry,
+ attr->mode, attr->rdev, debug);
+ break;
+
+ case S_IFLNK:
+ err = ovl_do_symlink(dir, newdentry, attr->link, debug);
+ break;
+
+ default:
+ err = -EPERM;
+ }
+ }
+ if (!err && WARN_ON(!newdentry->d_inode)) {
+ /*
+ * Not quite sure if non-instantiated dentry is legal or not.
+ * VFS doesn't seem to care so check and warn here.
+ */
+ err = -ENOENT;
+ }
+ return err;
+}
+
+static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
+ int xerr)
+{
+ int err;
+
+ err = ovl_check_setxattr(dentry, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
+ if (!err)
+ ovl_dentry_set_opaque(dentry);
+
+ return err;
+}
+
+static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
+{
+ /*
+ * Fail with -EIO when trying to create opaque dir and upper doesn't
+ * support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to
+ * return a specific error for noxattr case.
+ */
+ return ovl_set_opaque_xerr(dentry, upperdentry, -EIO);
+}
+
+/* Common operations required to be done after creation of file on upper */
+static void ovl_instantiate(struct dentry *dentry, struct inode *inode,
+ struct dentry *newdentry, bool hardlink)
+{
+ ovl_dentry_version_inc(dentry->d_parent, false);
+ ovl_dentry_set_upper_alias(dentry);
+ if (!hardlink) {
+ ovl_inode_update(inode, newdentry);
+ ovl_copyattr(newdentry->d_inode, inode);
+ } else {
+ WARN_ON(ovl_inode_real(inode) != d_inode(newdentry));
+ dput(newdentry);
+ inc_nlink(inode);
+ }
+ d_instantiate(dentry, inode);
+ /* Force lookup of new upper hardlink to find its lower */
+ if (hardlink)
+ d_drop(dentry);
+}
+
+static bool ovl_type_merge(struct dentry *dentry)
+{
+ return OVL_TYPE_MERGE(ovl_path_type(dentry));
+}
+
+static bool ovl_type_origin(struct dentry *dentry)
+{
+ return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
+}
+
+static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
+ struct cattr *attr, struct dentry *hardlink)
+{
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *newdentry;
+ int err;
+
+ if (!hardlink && !IS_POSIXACL(udir))
+ attr->mode &= ~current_umask();
+
+ inode_lock_nested(udir, I_MUTEX_PARENT);
+ newdentry = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_unlock;
+ err = ovl_create_real(udir, newdentry, attr, hardlink, false);
+ if (err)
+ goto out_dput;
+
+ if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry)) {
+ /* Setting opaque here is just an optimization, allow to fail */
+ ovl_set_opaque(dentry, newdentry);
+ }
+
+ ovl_instantiate(dentry, inode, newdentry, !!hardlink);
+ newdentry = NULL;
+out_dput:
+ dput(newdentry);
+out_unlock:
+ inode_unlock(udir);
+ return err;
+}
+
+static struct dentry *ovl_clear_empty(struct dentry *dentry,
+ struct list_head *list)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *wdir = workdir->d_inode;
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct path upperpath;
+ struct dentry *upper;
+ struct dentry *opaquedir;
+ struct kstat stat;
+ int err;
+
+ if (WARN_ON(!workdir))
+ return ERR_PTR(-EROFS);
+
+ err = ovl_lock_rename_workdir(workdir, upperdir);
+ if (err)
+ goto out;
+
+ ovl_path_upper(dentry, &upperpath);
+ err = vfs_getattr(&upperpath, &stat,
+ STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+ if (err)
+ goto out_unlock;
+
+ err = -ESTALE;
+ if (!S_ISDIR(stat.mode))
+ goto out_unlock;
+ upper = upperpath.dentry;
+ if (upper->d_parent->d_inode != udir)
+ goto out_unlock;
+
+ opaquedir = ovl_lookup_temp(workdir);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out_unlock;
+
+ err = ovl_create_real(wdir, opaquedir,
+ &(struct cattr){.mode = stat.mode}, NULL, true);
+ if (err)
+ goto out_dput;
+
+ err = ovl_copy_xattr(upper, opaquedir);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_set_opaque(dentry, opaquedir);
+ if (err)
+ goto out_cleanup;
+
+ inode_lock(opaquedir->d_inode);
+ err = ovl_set_attr(opaquedir, &stat);
+ inode_unlock(opaquedir->d_inode);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
+ if (err)
+ goto out_cleanup;
+
+ ovl_cleanup_whiteouts(upper, list);
+ ovl_cleanup(wdir, upper);
+ unlock_rename(workdir, upperdir);
+
+ /* dentry's upper doesn't match now, get rid of it */
+ d_drop(dentry);
+
+ return opaquedir;
+
+out_cleanup:
+ ovl_cleanup(wdir, opaquedir);
+out_dput:
+ dput(opaquedir);
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out:
+ return ERR_PTR(err);
+}
+
+static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
+{
+ int err;
+ struct dentry *ret = NULL;
+ enum ovl_path_type type = ovl_path_type(dentry);
+ LIST_HEAD(list);
+
+ err = ovl_check_empty_dir(dentry, &list);
+ if (err) {
+ ret = ERR_PTR(err);
+ goto out_free;
+ }
+
+ /*
+ * When removing an empty opaque directory, then it makes no sense to
+ * replace it with an exact replica of itself.
+ *
+ * If no upperdentry then skip clearing whiteouts.
+ *
+ * Can race with copy-up, since we don't hold the upperdir mutex.
+ * Doesn't matter, since copy-up can't create a non-empty directory
+ * from an empty one.
+ */
+ if (OVL_TYPE_UPPER(type) && OVL_TYPE_MERGE(type))
+ ret = ovl_clear_empty(dentry, &list);
+
+out_free:
+ ovl_cache_free(&list);
+
+ return ret;
+}
+
+static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
+ const struct posix_acl *acl)
+{
+ void *buffer;
+ size_t size;
+ int err;
+
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl)
+ return 0;
+
+ size = posix_acl_to_xattr(NULL, acl, NULL, 0);
+ buffer = kmalloc(size, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ size = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+ err = size;
+ if (err < 0)
+ goto out_free;
+
+ err = vfs_setxattr(upperdentry, name, buffer, size, XATTR_CREATE);
+out_free:
+ kfree(buffer);
+ return err;
+}
+
+static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
+ struct cattr *cattr,
+ struct dentry *hardlink)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *wdir = workdir->d_inode;
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *upper;
+ struct dentry *newdentry;
+ int err;
+ struct posix_acl *acl, *default_acl;
+
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ if (!hardlink) {
+ err = posix_acl_create(dentry->d_parent->d_inode,
+ &cattr->mode, &default_acl, &acl);
+ if (err)
+ return err;
+ }
+
+ err = ovl_lock_rename_workdir(workdir, upperdir);
+ if (err)
+ goto out;
+
+ newdentry = ovl_lookup_temp(workdir);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_unlock;
+
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out_dput;
+
+ err = -ESTALE;
+ if (d_is_negative(upper) || !IS_WHITEOUT(d_inode(upper)))
+ goto out_dput2;
+
+ err = ovl_create_real(wdir, newdentry, cattr, hardlink, true);
+ if (err)
+ goto out_dput2;
+
+ /*
+ * mode could have been mutilated due to umask (e.g. sgid directory)
+ */
+ if (!hardlink &&
+ !S_ISLNK(cattr->mode) &&
+ newdentry->d_inode->i_mode != cattr->mode) {
+ struct iattr attr = {
+ .ia_valid = ATTR_MODE,
+ .ia_mode = cattr->mode,
+ };
+ inode_lock(newdentry->d_inode);
+ err = notify_change(newdentry, &attr, NULL);
+ inode_unlock(newdentry->d_inode);
+ if (err)
+ goto out_cleanup;
+ }
+ if (!hardlink) {
+ err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_ACCESS,
+ acl);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_DEFAULT,
+ default_acl);
+ if (err)
+ goto out_cleanup;
+ }
+
+ if (!hardlink && S_ISDIR(cattr->mode)) {
+ err = ovl_set_opaque(dentry, newdentry);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_do_rename(wdir, newdentry, udir, upper,
+ RENAME_EXCHANGE);
+ if (err)
+ goto out_cleanup;
+
+ ovl_cleanup(wdir, upper);
+ } else {
+ err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+ if (err)
+ goto out_cleanup;
+ }
+ ovl_instantiate(dentry, inode, newdentry, !!hardlink);
+ newdentry = NULL;
+out_dput2:
+ dput(upper);
+out_dput:
+ dput(newdentry);
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out:
+ if (!hardlink) {
+ posix_acl_release(acl);
+ posix_acl_release(default_acl);
+ }
+ return err;
+
+out_cleanup:
+ ovl_cleanup(wdir, newdentry);
+ goto out_dput2;
+}
+
+static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
+ struct cattr *attr, struct dentry *hardlink,
+ bool origin)
+{
+ int err;
+ const struct cred *old_cred;
+ struct cred *override_cred;
+ struct dentry *parent = dentry->d_parent;
+
+ err = ovl_copy_up(parent);
+ if (err)
+ return err;
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+
+ /*
+ * When linking a file with copy up origin into a new parent, mark the
+ * new parent dir "impure".
+ */
+ if (origin) {
+ err = ovl_set_impure(parent, ovl_dentry_upper(parent));
+ if (err)
+ goto out_revert_creds;
+ }
+
+ err = -ENOMEM;
+ override_cred = prepare_creds();
+ if (override_cred) {
+ override_cred->fsuid = inode->i_uid;
+ override_cred->fsgid = inode->i_gid;
+ if (!hardlink) {
+ err = security_dentry_create_files_as(dentry,
+ attr->mode, &dentry->d_name, old_cred,
+ override_cred);
+ if (err) {
+ put_cred(override_cred);
+ goto out_revert_creds;
+ }
+ }
+ put_cred(override_creds(override_cred));
+ put_cred(override_cred);
+
+ if (!ovl_dentry_is_whiteout(dentry))
+ err = ovl_create_upper(dentry, inode, attr,
+ hardlink);
+ else
+ err = ovl_create_over_whiteout(dentry, inode, attr,
+ hardlink);
+ }
+out_revert_creds:
+ revert_creds(old_cred);
+ if (!err) {
+ struct inode *realinode = d_inode(ovl_dentry_upper(dentry));
+
+ WARN_ON(inode->i_mode != realinode->i_mode);
+ WARN_ON(!uid_eq(inode->i_uid, realinode->i_uid));
+ WARN_ON(!gid_eq(inode->i_gid, realinode->i_gid));
+ }
+ return err;
+}
+
+static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
+ const char *link)
+{
+ int err;
+ struct inode *inode;
+ struct cattr attr = {
+ .rdev = rdev,
+ .link = link,
+ };
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = -ENOMEM;
+ inode = ovl_new_inode(dentry->d_sb, mode, rdev);
+ if (!inode)
+ goto out_drop_write;
+
+ inode_init_owner(inode, dentry->d_parent->d_inode, mode);
+ attr.mode = inode->i_mode;
+
+ err = ovl_create_or_link(dentry, inode, &attr, NULL, false);
+ if (err)
+ iput(inode);
+
+out_drop_write:
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static int ovl_create(struct inode *dir, struct dentry *dentry, umode_t mode,
+ bool excl)
+{
+ return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
+}
+
+static int ovl_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+{
+ return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL);
+}
+
+static int ovl_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
+ dev_t rdev)
+{
+ /* Don't allow creation of "whiteout" on overlay */
+ if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
+ return -EPERM;
+
+ return ovl_create_object(dentry, mode, rdev, NULL);
+}
+
+static int ovl_symlink(struct inode *dir, struct dentry *dentry,
+ const char *link)
+{
+ return ovl_create_object(dentry, S_IFLNK, 0, link);
+}
+
+static int ovl_link(struct dentry *old, struct inode *newdir,
+ struct dentry *new)
+{
+ int err;
+ bool locked = false;
+ struct inode *inode;
+
+ err = ovl_want_write(old);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(old);
+ if (err)
+ goto out_drop_write;
+
+ err = ovl_copy_up(new->d_parent);
+ if (err)
+ goto out_drop_write;
+
+
+ err = ovl_nlink_start(old, &locked);
+ if (err)
+ goto out_drop_write;
+
+ inode = d_inode(old);
+ ihold(inode);
+
+ err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old),
+ ovl_type_origin(old));
+ if (err)
+ iput(inode);
+
+ ovl_nlink_end(old, locked);
+out_drop_write:
+ ovl_drop_write(old);
+out:
+ return err;
+}
+
+static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper)
+{
+ return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper);
+}
+
+static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *wdir = workdir->d_inode;
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *udir = upperdir->d_inode;
+ struct dentry *whiteout;
+ struct dentry *upper;
+ struct dentry *opaquedir = NULL;
+ int err;
+ int flags = 0;
+
+ if (WARN_ON(!workdir))
+ return -EROFS;
+
+ if (is_dir) {
+ opaquedir = ovl_check_empty_and_clear(dentry);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out;
+ }
+
+ err = ovl_lock_rename_workdir(workdir, upperdir);
+ if (err)
+ goto out_dput;
+
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out_unlock;
+
+ err = -ESTALE;
+ if ((opaquedir && upper != opaquedir) ||
+ (!opaquedir && ovl_dentry_upper(dentry) &&
+ !ovl_matches_upper(dentry, upper))) {
+ goto out_dput_upper;
+ }
+
+ whiteout = ovl_whiteout(workdir, dentry);
+ err = PTR_ERR(whiteout);
+ if (IS_ERR(whiteout))
+ goto out_dput_upper;
+
+ if (d_is_dir(upper))
+ flags = RENAME_EXCHANGE;
+
+ err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
+ if (err)
+ goto kill_whiteout;
+ if (flags)
+ ovl_cleanup(wdir, upper);
+
+ ovl_dentry_version_inc(dentry->d_parent, true);
+out_d_drop:
+ d_drop(dentry);
+ dput(whiteout);
+out_dput_upper:
+ dput(upper);
+out_unlock:
+ unlock_rename(workdir, upperdir);
+out_dput:
+ dput(opaquedir);
+out:
+ return err;
+
+kill_whiteout:
+ ovl_cleanup(wdir, whiteout);
+ goto out_d_drop;
+}
+
+static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
+{
+ struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
+ struct inode *dir = upperdir->d_inode;
+ struct dentry *upper;
+ struct dentry *opaquedir = NULL;
+ int err;
+
+ /* Redirect dir can be !ovl_lower_positive && OVL_TYPE_MERGE */
+ if (is_dir && ovl_dentry_get_redirect(dentry)) {
+ opaquedir = ovl_check_empty_and_clear(dentry);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir))
+ goto out;
+ }
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ upper = lookup_one_len(dentry->d_name.name, upperdir,
+ dentry->d_name.len);
+ err = PTR_ERR(upper);
+ if (IS_ERR(upper))
+ goto out_unlock;
+
+ err = -ESTALE;
+ if ((opaquedir && upper != opaquedir) ||
+ (!opaquedir && !ovl_matches_upper(dentry, upper)))
+ goto out_dput_upper;
+
+ if (is_dir)
+ err = vfs_rmdir(dir, upper);
+ else
+ err = vfs_unlink(dir, upper, NULL);
+ ovl_dentry_version_inc(dentry->d_parent, ovl_type_origin(dentry));
+
+ /*
+ * Keeping this dentry hashed would mean having to release
+ * upperpath/lowerpath, which could only be done if we are the
+ * sole user of this dentry. Too tricky... Just unhash for
+ * now.
+ */
+ if (!err)
+ d_drop(dentry);
+out_dput_upper:
+ dput(upper);
+out_unlock:
+ inode_unlock(dir);
+ dput(opaquedir);
+out:
+ return err;
+}
+
+static int ovl_do_remove(struct dentry *dentry, bool is_dir)
+{
+ int err;
+ bool locked = false;
+ const struct cred *old_cred;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(dentry->d_parent);
+ if (err)
+ goto out_drop_write;
+
+ err = ovl_nlink_start(dentry, &locked);
+ if (err)
+ goto out_drop_write;
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ if (!ovl_lower_positive(dentry))
+ err = ovl_remove_upper(dentry, is_dir);
+ else
+ err = ovl_remove_and_whiteout(dentry, is_dir);
+ revert_creds(old_cred);
+ if (!err) {
+ if (is_dir)
+ clear_nlink(dentry->d_inode);
+ else
+ drop_nlink(dentry->d_inode);
+ }
+ ovl_nlink_end(dentry, locked);
+out_drop_write:
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+static int ovl_unlink(struct inode *dir, struct dentry *dentry)
+{
+ return ovl_do_remove(dentry, false);
+}
+
+static int ovl_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ return ovl_do_remove(dentry, true);
+}
+
+static bool ovl_type_merge_or_lower(struct dentry *dentry)
+{
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ return OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type);
+}
+
+static bool ovl_can_move(struct dentry *dentry)
+{
+ return ovl_redirect_dir(dentry->d_sb) ||
+ !d_is_dir(dentry) || !ovl_type_merge_or_lower(dentry);
+}
+
+static char *ovl_get_redirect(struct dentry *dentry, bool samedir)
+{
+ char *buf, *ret;
+ struct dentry *d, *tmp;
+ int buflen = ovl_redirect_max + 1;
+
+ if (samedir) {
+ ret = kstrndup(dentry->d_name.name, dentry->d_name.len,
+ GFP_KERNEL);
+ goto out;
+ }
+
+ buf = ret = kmalloc(buflen, GFP_KERNEL);
+ if (!buf)
+ goto out;
+
+ buflen--;
+ buf[buflen] = '\0';
+ for (d = dget(dentry); !IS_ROOT(d);) {
+ const char *name;
+ int thislen;
+
+ spin_lock(&d->d_lock);
+ name = ovl_dentry_get_redirect(d);
+ if (name) {
+ thislen = strlen(name);
+ } else {
+ name = d->d_name.name;
+ thislen = d->d_name.len;
+ }
+
+ /* If path is too long, fall back to userspace move */
+ if (thislen + (name[0] != '/') > buflen) {
+ ret = ERR_PTR(-EXDEV);
+ spin_unlock(&d->d_lock);
+ goto out_put;
+ }
+
+ buflen -= thislen;
+ memcpy(&buf[buflen], name, thislen);
+ tmp = dget_dlock(d->d_parent);
+ spin_unlock(&d->d_lock);
+
+ dput(d);
+ d = tmp;
+
+ /* Absolute redirect: finished */
+ if (buf[buflen] == '/')
+ break;
+ buflen--;
+ buf[buflen] = '/';
+ }
+ ret = kstrdup(&buf[buflen], GFP_KERNEL);
+out_put:
+ dput(d);
+ kfree(buf);
+out:
+ return ret ? ret : ERR_PTR(-ENOMEM);
+}
+
+static int ovl_set_redirect(struct dentry *dentry, bool samedir)
+{
+ int err;
+ const char *redirect = ovl_dentry_get_redirect(dentry);
+
+ if (redirect && (samedir || redirect[0] == '/'))
+ return 0;
+
+ redirect = ovl_get_redirect(dentry, samedir);
+ if (IS_ERR(redirect))
+ return PTR_ERR(redirect);
+
+ err = ovl_check_setxattr(dentry, ovl_dentry_upper(dentry),
+ OVL_XATTR_REDIRECT,
+ redirect, strlen(redirect), -EXDEV);
+ if (!err) {
+ spin_lock(&dentry->d_lock);
+ ovl_dentry_set_redirect(dentry, redirect);
+ spin_unlock(&dentry->d_lock);
+ } else {
+ kfree(redirect);
+ pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err);
+ /* Fall back to userspace copy-up */
+ err = -EXDEV;
+ }
+ return err;
+}
+
+static int ovl_rename(struct inode *olddir, struct dentry *old,
+ struct inode *newdir, struct dentry *new,
+ unsigned int flags)
+{
+ int err;
+ bool locked = false;
+ struct dentry *old_upperdir;
+ struct dentry *new_upperdir;
+ struct dentry *olddentry;
+ struct dentry *newdentry;
+ struct dentry *trap;
+ bool old_opaque;
+ bool new_opaque;
+ bool cleanup_whiteout = false;
+ bool overwrite = !(flags & RENAME_EXCHANGE);
+ bool is_dir = d_is_dir(old);
+ bool new_is_dir = d_is_dir(new);
+ bool samedir = olddir == newdir;
+ struct dentry *opaquedir = NULL;
+ const struct cred *old_cred = NULL;
+
+ err = -EINVAL;
+ if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
+ goto out;
+
+ flags &= ~RENAME_NOREPLACE;
+
+ /* Don't copy up directory trees */
+ err = -EXDEV;
+ if (!ovl_can_move(old))
+ goto out;
+ if (!overwrite && !ovl_can_move(new))
+ goto out;
+
+ err = ovl_want_write(old);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(old);
+ if (err)
+ goto out_drop_write;
+
+ err = ovl_copy_up(new->d_parent);
+ if (err)
+ goto out_drop_write;
+ if (!overwrite) {
+ err = ovl_copy_up(new);
+ if (err)
+ goto out_drop_write;
+ } else {
+ err = ovl_nlink_start(new, &locked);
+ if (err)
+ goto out_drop_write;
+ }
+
+ old_cred = ovl_override_creds(old->d_sb);
+
+ if (overwrite && new_is_dir && ovl_type_merge_or_lower(new)) {
+ opaquedir = ovl_check_empty_and_clear(new);
+ err = PTR_ERR(opaquedir);
+ if (IS_ERR(opaquedir)) {
+ opaquedir = NULL;
+ goto out_revert_creds;
+ }
+ }
+
+ if (overwrite) {
+ if (ovl_lower_positive(old)) {
+ if (!ovl_dentry_is_whiteout(new)) {
+ /* Whiteout source */
+ flags |= RENAME_WHITEOUT;
+ } else {
+ /* Switch whiteouts */
+ flags |= RENAME_EXCHANGE;
+ }
+ } else if (is_dir && ovl_dentry_is_whiteout(new)) {
+ flags |= RENAME_EXCHANGE;
+ cleanup_whiteout = true;
+ }
+ }
+
+ old_upperdir = ovl_dentry_upper(old->d_parent);
+ new_upperdir = ovl_dentry_upper(new->d_parent);
+
+ if (!samedir) {
+ /*
+ * When moving a merge dir or non-dir with copy up origin into
+ * a new parent, we are marking the new parent dir "impure".
+ * When ovl_iterate() iterates an "impure" upper dir, it will
+ * lookup the origin inodes of the entries to fill d_ino.
+ */
+ if (ovl_type_origin(old)) {
+ err = ovl_set_impure(new->d_parent, new_upperdir);
+ if (err)
+ goto out_revert_creds;
+ }
+ if (!overwrite && ovl_type_origin(new)) {
+ err = ovl_set_impure(old->d_parent, old_upperdir);
+ if (err)
+ goto out_revert_creds;
+ }
+ }
+
+ trap = lock_rename(new_upperdir, old_upperdir);
+
+ olddentry = lookup_one_len(old->d_name.name, old_upperdir,
+ old->d_name.len);
+ err = PTR_ERR(olddentry);
+ if (IS_ERR(olddentry))
+ goto out_unlock;
+
+ err = -ESTALE;
+ if (!ovl_matches_upper(old, olddentry))
+ goto out_dput_old;
+
+ newdentry = lookup_one_len(new->d_name.name, new_upperdir,
+ new->d_name.len);
+ err = PTR_ERR(newdentry);
+ if (IS_ERR(newdentry))
+ goto out_dput_old;
+
+ old_opaque = ovl_dentry_is_opaque(old);
+ new_opaque = ovl_dentry_is_opaque(new);
+
+ err = -ESTALE;
+ if (d_inode(new) && ovl_dentry_upper(new)) {
+ if (opaquedir) {
+ if (newdentry != opaquedir)
+ goto out_dput;
+ } else {
+ if (!ovl_matches_upper(new, newdentry))
+ goto out_dput;
+ }
+ } else {
+ if (!d_is_negative(newdentry) &&
+ (!new_opaque || !ovl_is_whiteout(newdentry)))
+ goto out_dput;
+ }
+
+ if (olddentry == trap)
+ goto out_dput;
+ if (newdentry == trap)
+ goto out_dput;
+
+ if (olddentry->d_inode == newdentry->d_inode)
+ goto out_dput;
+
+ err = 0;
+ if (is_dir) {
+ if (ovl_type_merge_or_lower(old))
+ err = ovl_set_redirect(old, samedir);
+ else if (!old_opaque && ovl_type_merge(new->d_parent))
+ err = ovl_set_opaque_xerr(old, olddentry, -EXDEV);
+ if (err)
+ goto out_dput;
+ }
+ if (!overwrite && new_is_dir) {
+ if (ovl_type_merge_or_lower(new))
+ err = ovl_set_redirect(new, samedir);
+ else if (!new_opaque && ovl_type_merge(old->d_parent))
+ err = ovl_set_opaque_xerr(new, newdentry, -EXDEV);
+ if (err)
+ goto out_dput;
+ }
+
+ err = ovl_do_rename(old_upperdir->d_inode, olddentry,
+ new_upperdir->d_inode, newdentry, flags);
+ if (err)
+ goto out_dput;
+
+ if (cleanup_whiteout)
+ ovl_cleanup(old_upperdir->d_inode, newdentry);
+
+ if (overwrite && d_inode(new)) {
+ if (new_is_dir)
+ clear_nlink(d_inode(new));
+ else
+ drop_nlink(d_inode(new));
+ }
+
+ ovl_dentry_version_inc(old->d_parent,
+ !overwrite && ovl_type_origin(new));
+ ovl_dentry_version_inc(new->d_parent, ovl_type_origin(old));
+
+out_dput:
+ dput(newdentry);
+out_dput_old:
+ dput(olddentry);
+out_unlock:
+ unlock_rename(new_upperdir, old_upperdir);
+out_revert_creds:
+ revert_creds(old_cred);
+ ovl_nlink_end(new, locked);
+out_drop_write:
+ ovl_drop_write(old);
+out:
+ dput(opaquedir);
+ return err;
+}
+
+const struct inode_operations ovl_dir_inode_operations = {
+ .lookup = ovl_lookup,
+ .mkdir = ovl_mkdir,
+ .symlink = ovl_symlink,
+ .unlink = ovl_unlink,
+ .rmdir = ovl_rmdir,
+ .rename = ovl_rename,
+ .link = ovl_link,
+ .setattr = ovl_setattr,
+ .create = ovl_create,
+ .mknod = ovl_mknod,
+ .permission = ovl_permission,
+ .getattr = ovl_getattr,
+ .listxattr = ovl_listxattr,
+ .get_acl = ovl_get_acl,
+ .update_time = ovl_update_time,
+};
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/inode.c b/src/kernel/linux/v4.14/fs/overlayfs/inode.c
new file mode 100644
index 0000000..30a1c7f
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/inode.c
@@ -0,0 +1,712 @@
+/*
+ *
+ * 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/cred.h>
+#include <linux/xattr.h>
+#include <linux/posix_acl.h>
+#include <linux/ratelimit.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+int ovl_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ int err;
+ struct dentry *upperdentry;
+ const struct cred *old_cred;
+
+ /*
+ * Check for permissions before trying to copy-up. This is redundant
+ * since it will be rechecked later by ->setattr() on upper dentry. But
+ * without this, copy-up can be triggered by just about anybody.
+ *
+ * We don't initialize inode->size, which just means that
+ * inode_newsize_ok() will always check against MAX_LFS_FILESIZE and not
+ * check for a swapfile (which this won't be anyway).
+ */
+ err = setattr_prepare(dentry, attr);
+ if (err)
+ return err;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ err = ovl_copy_up(dentry);
+ if (!err) {
+ upperdentry = ovl_dentry_upper(dentry);
+
+ if (attr->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID))
+ attr->ia_valid &= ~ATTR_MODE;
+
+ inode_lock(upperdentry->d_inode);
+ old_cred = ovl_override_creds(dentry->d_sb);
+ err = notify_change(upperdentry, attr, NULL);
+ revert_creds(old_cred);
+ if (!err)
+ ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
+ inode_unlock(upperdentry->d_inode);
+ }
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+int ovl_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags)
+{
+ struct dentry *dentry = path->dentry;
+ enum ovl_path_type type;
+ struct path realpath;
+ const struct cred *old_cred;
+ bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
+ int err;
+
+ type = ovl_path_real(dentry, &realpath);
+ old_cred = ovl_override_creds(dentry->d_sb);
+ err = vfs_getattr(&realpath, stat, request_mask, flags);
+ if (err)
+ goto out;
+
+ /*
+ * When all layers are on the same fs, all real inode number are
+ * unique, so we use the overlay st_dev, which is friendly to du -x.
+ *
+ * We also use st_ino of the copy up origin, if we know it.
+ * This guaranties constant st_dev/st_ino across copy up.
+ *
+ * If filesystem supports NFS export ops, this also guaranties
+ * persistent st_ino across mount cycle.
+ */
+ if (ovl_same_sb(dentry->d_sb)) {
+ if (OVL_TYPE_ORIGIN(type)) {
+ struct kstat lowerstat;
+ u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);
+
+ ovl_path_lower(dentry, &realpath);
+ err = vfs_getattr(&realpath, &lowerstat,
+ lowermask, flags);
+ if (err)
+ goto out;
+
+ WARN_ON_ONCE(stat->dev != lowerstat.dev);
+ /*
+ * Lower hardlinks may be broken on copy up to different
+ * upper files, so we cannot use the lower origin st_ino
+ * for those different files, even for the same fs case.
+ * With inodes index enabled, it is safe to use st_ino
+ * of an indexed hardlinked origin. The index validates
+ * that the upper hardlink is not broken.
+ */
+ if (is_dir || lowerstat.nlink == 1 ||
+ ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+ stat->ino = lowerstat.ino;
+ }
+ stat->dev = dentry->d_sb->s_dev;
+ } else if (is_dir) {
+ /*
+ * If not all layers are on the same fs the pair {real st_ino;
+ * overlay st_dev} is not unique, so use the non persistent
+ * overlay st_ino.
+ *
+ * Always use the overlay st_dev for directories, so 'find
+ * -xdev' will scan the entire overlay mount and won't cross the
+ * overlay mount boundaries.
+ */
+ stat->dev = dentry->d_sb->s_dev;
+ stat->ino = dentry->d_inode->i_ino;
+ }
+
+ /*
+ * It's probably not worth it to count subdirs to get the
+ * correct link count. nlink=1 seems to pacify 'find' and
+ * other utilities.
+ */
+ if (is_dir && OVL_TYPE_MERGE(type))
+ stat->nlink = 1;
+
+ /*
+ * Return the overlay inode nlinks for indexed upper inodes.
+ * Overlay inode nlink counts the union of the upper hardlinks
+ * and non-covered lower hardlinks. It does not include the upper
+ * index hardlink.
+ */
+ if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+ stat->nlink = dentry->d_inode->i_nlink;
+
+out:
+ revert_creds(old_cred);
+
+ return err;
+}
+
+int ovl_permission(struct inode *inode, int mask)
+{
+ struct inode *upperinode = ovl_inode_upper(inode);
+ struct inode *realinode = upperinode ?: ovl_inode_lower(inode);
+ const struct cred *old_cred;
+ int err;
+
+ /* Careful in RCU walk mode */
+ if (!realinode) {
+ WARN_ON(!(mask & MAY_NOT_BLOCK));
+ return -ECHILD;
+ }
+
+ /*
+ * Check overlay inode with the creds of task and underlying inode
+ * with creds of mounter
+ */
+ err = generic_permission(inode, mask);
+ if (err)
+ return err;
+
+ old_cred = ovl_override_creds(inode->i_sb);
+ if (!upperinode &&
+ !special_file(realinode->i_mode) && mask & MAY_WRITE) {
+ mask &= ~(MAY_WRITE | MAY_APPEND);
+ /* Make sure mounter can read file for copy up later */
+ mask |= MAY_READ;
+ }
+ err = inode_permission(realinode, mask);
+ revert_creds(old_cred);
+
+ return err;
+}
+
+static const char *ovl_get_link(struct dentry *dentry,
+ struct inode *inode,
+ struct delayed_call *done)
+{
+ const struct cred *old_cred;
+ const char *p;
+
+ if (!dentry)
+ return ERR_PTR(-ECHILD);
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ p = vfs_get_link(ovl_dentry_real(dentry), done);
+ revert_creds(old_cred);
+ return p;
+}
+
+bool ovl_is_private_xattr(const char *name)
+{
+ return strncmp(name, OVL_XATTR_PREFIX,
+ sizeof(OVL_XATTR_PREFIX) - 1) == 0;
+}
+
+int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+ const void *value, size_t size, int flags)
+{
+ int err;
+ struct dentry *upperdentry = ovl_i_dentry_upper(inode);
+ struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry);
+ const struct cred *old_cred;
+
+ err = ovl_want_write(dentry);
+ if (err)
+ goto out;
+
+ if (!value && !upperdentry) {
+ err = vfs_getxattr(realdentry, name, NULL, 0);
+ if (err < 0)
+ goto out_drop_write;
+ }
+
+ if (!upperdentry) {
+ err = ovl_copy_up(dentry);
+ if (err)
+ goto out_drop_write;
+
+ realdentry = ovl_dentry_upper(dentry);
+ }
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ if (value)
+ err = vfs_setxattr(realdentry, name, value, size, flags);
+ else {
+ WARN_ON(flags != XATTR_REPLACE);
+ err = vfs_removexattr(realdentry, name);
+ }
+ revert_creds(old_cred);
+
+out_drop_write:
+ ovl_drop_write(dentry);
+out:
+ return err;
+}
+
+int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
+ void *value, size_t size)
+{
+ ssize_t res;
+ const struct cred *old_cred;
+ struct dentry *realdentry =
+ ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry);
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ res = vfs_getxattr(realdentry, name, value, size);
+ revert_creds(old_cred);
+ return res;
+}
+
+static bool ovl_can_list(const char *s)
+{
+ /* List all non-trusted xatts */
+ if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
+ return true;
+
+ /* Never list trusted.overlay, list other trusted for superuser only */
+ return !ovl_is_private_xattr(s) &&
+ ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN);
+}
+
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
+{
+ struct dentry *realdentry = ovl_dentry_real(dentry);
+ ssize_t res;
+ size_t len;
+ char *s;
+ const struct cred *old_cred;
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ res = vfs_listxattr(realdentry, list, size);
+ revert_creds(old_cred);
+ if (res <= 0 || size == 0)
+ return res;
+
+ /* filter out private xattrs */
+ for (s = list, len = res; len;) {
+ size_t slen = strnlen(s, len) + 1;
+
+ /* underlying fs providing us with an broken xattr list? */
+ if (WARN_ON(slen > len))
+ return -EIO;
+
+ len -= slen;
+ if (!ovl_can_list(s)) {
+ res -= slen;
+ memmove(s, s + slen, len);
+ } else {
+ s += slen;
+ }
+ }
+
+ return res;
+}
+
+struct posix_acl *ovl_get_acl(struct inode *inode, int type)
+{
+ struct inode *realinode = ovl_inode_real(inode);
+ const struct cred *old_cred;
+ struct posix_acl *acl;
+
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
+ return NULL;
+
+ old_cred = ovl_override_creds(inode->i_sb);
+ acl = get_acl(realinode, type);
+ revert_creds(old_cred);
+
+ return acl;
+}
+
+static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
+{
+ if (ovl_dentry_upper(dentry) &&
+ ovl_dentry_has_upper_alias(dentry))
+ return false;
+
+ if (special_file(d_inode(dentry)->i_mode))
+ return false;
+
+ if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC))
+ return false;
+
+ return true;
+}
+
+int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
+{
+ int err = 0;
+
+ if (ovl_open_need_copy_up(dentry, file_flags)) {
+ err = ovl_want_write(dentry);
+ if (!err) {
+ err = ovl_copy_up_flags(dentry, file_flags);
+ ovl_drop_write(dentry);
+ }
+ }
+
+ return err;
+}
+
+int ovl_update_time(struct inode *inode, struct timespec *ts, int flags)
+{
+ struct dentry *alias;
+ struct path upperpath;
+
+ if (!(flags & S_ATIME))
+ return 0;
+
+ alias = d_find_any_alias(inode);
+ if (!alias)
+ return 0;
+
+ ovl_path_upper(alias, &upperpath);
+ if (upperpath.dentry) {
+ touch_atime(&upperpath);
+ inode->i_atime = d_inode(upperpath.dentry)->i_atime;
+ }
+
+ dput(alias);
+
+ return 0;
+}
+
+static const struct inode_operations ovl_file_inode_operations = {
+ .setattr = ovl_setattr,
+ .permission = ovl_permission,
+ .getattr = ovl_getattr,
+ .listxattr = ovl_listxattr,
+ .get_acl = ovl_get_acl,
+ .update_time = ovl_update_time,
+};
+
+static const struct inode_operations ovl_symlink_inode_operations = {
+ .setattr = ovl_setattr,
+ .get_link = ovl_get_link,
+ .getattr = ovl_getattr,
+ .listxattr = ovl_listxattr,
+ .update_time = ovl_update_time,
+};
+
+/*
+ * It is possible to stack overlayfs instance on top of another
+ * overlayfs instance as lower layer. We need to annonate the
+ * stackable i_mutex locks according to stack level of the super
+ * block instance. An overlayfs instance can never be in stack
+ * depth 0 (there is always a real fs below it). An overlayfs
+ * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
+ *
+ * For example, here is a snip from /proc/lockdep_chains after
+ * dir_iterate of nested overlayfs:
+ *
+ * [...] &ovl_i_mutex_dir_key[depth] (stack_depth=2)
+ * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
+ * [...] &type->i_mutex_dir_key (stack_depth=0)
+ */
+#define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH
+
+static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
+{
+#ifdef CONFIG_LOCKDEP
+ static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
+ static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];
+
+ int depth = inode->i_sb->s_stack_depth - 1;
+
+ if (WARN_ON_ONCE(depth < 0 || depth >= OVL_MAX_NESTING))
+ depth = 0;
+
+ if (S_ISDIR(inode->i_mode))
+ lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
+ else
+ lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);
+#endif
+}
+
+static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
+{
+ inode->i_ino = get_next_ino();
+ inode->i_mode = mode;
+ inode->i_flags |= S_NOCMTIME;
+#ifdef CONFIG_FS_POSIX_ACL
+ inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
+#endif
+
+ ovl_lockdep_annotate_inode_mutex_key(inode);
+
+ switch (mode & S_IFMT) {
+ case S_IFREG:
+ inode->i_op = &ovl_file_inode_operations;
+ break;
+
+ case S_IFDIR:
+ inode->i_op = &ovl_dir_inode_operations;
+ inode->i_fop = &ovl_dir_operations;
+ break;
+
+ case S_IFLNK:
+ inode->i_op = &ovl_symlink_inode_operations;
+ break;
+
+ default:
+ inode->i_op = &ovl_file_inode_operations;
+ init_special_inode(inode, mode, rdev);
+ break;
+ }
+}
+
+/*
+ * With inodes index enabled, an overlay inode nlink counts the union of upper
+ * hardlinks and non-covered lower hardlinks. During the lifetime of a non-pure
+ * upper inode, the following nlink modifying operations can happen:
+ *
+ * 1. Lower hardlink copy up
+ * 2. Upper hardlink created, unlinked or renamed over
+ * 3. Lower hardlink whiteout or renamed over
+ *
+ * For the first, copy up case, the union nlink does not change, whether the
+ * operation succeeds or fails, but the upper inode nlink may change.
+ * Therefore, before copy up, we store the union nlink value relative to the
+ * lower inode nlink in the index inode xattr trusted.overlay.nlink.
+ *
+ * For the second, upper hardlink case, the union nlink should be incremented
+ * or decremented IFF the operation succeeds, aligned with nlink change of the
+ * upper inode. Therefore, before link/unlink/rename, we store the union nlink
+ * value relative to the upper inode nlink in the index inode.
+ *
+ * For the last, lower cover up case, we simplify things by preceding the
+ * whiteout or cover up with copy up. This makes sure that there is an index
+ * upper inode where the nlink xattr can be stored before the copied up upper
+ * entry is unlink.
+ */
+#define OVL_NLINK_ADD_UPPER (1 << 0)
+
+/*
+ * On-disk format for indexed nlink:
+ *
+ * nlink relative to the upper inode - "U[+-]NUM"
+ * nlink relative to the lower inode - "L[+-]NUM"
+ */
+
+static int ovl_set_nlink_common(struct dentry *dentry,
+ struct dentry *realdentry, const char *format)
+{
+ struct inode *inode = d_inode(dentry);
+ struct inode *realinode = d_inode(realdentry);
+ char buf[13];
+ int len;
+
+ len = snprintf(buf, sizeof(buf), format,
+ (int) (inode->i_nlink - realinode->i_nlink));
+
+ if (WARN_ON(len >= sizeof(buf)))
+ return -EIO;
+
+ return ovl_do_setxattr(ovl_dentry_upper(dentry),
+ OVL_XATTR_NLINK, buf, len, 0);
+}
+
+int ovl_set_nlink_upper(struct dentry *dentry)
+{
+ return ovl_set_nlink_common(dentry, ovl_dentry_upper(dentry), "U%+i");
+}
+
+int ovl_set_nlink_lower(struct dentry *dentry)
+{
+ return ovl_set_nlink_common(dentry, ovl_dentry_lower(dentry), "L%+i");
+}
+
+unsigned int ovl_get_nlink(struct dentry *lowerdentry,
+ struct dentry *upperdentry,
+ unsigned int fallback)
+{
+ int nlink_diff;
+ int nlink;
+ char buf[13];
+ int err;
+
+ if (!lowerdentry || !upperdentry || d_inode(lowerdentry)->i_nlink == 1)
+ return fallback;
+
+ err = vfs_getxattr(upperdentry, OVL_XATTR_NLINK, &buf, sizeof(buf) - 1);
+ if (err < 0)
+ goto fail;
+
+ buf[err] = '\0';
+ if ((buf[0] != 'L' && buf[0] != 'U') ||
+ (buf[1] != '+' && buf[1] != '-'))
+ goto fail;
+
+ err = kstrtoint(buf + 1, 10, &nlink_diff);
+ if (err < 0)
+ goto fail;
+
+ nlink = d_inode(buf[0] == 'L' ? lowerdentry : upperdentry)->i_nlink;
+ nlink += nlink_diff;
+
+ if (nlink <= 0)
+ goto fail;
+
+ return nlink;
+
+fail:
+ pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n",
+ upperdentry, err);
+ return fallback;
+}
+
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
+{
+ struct inode *inode;
+
+ inode = new_inode(sb);
+ if (inode)
+ ovl_fill_inode(inode, mode, rdev);
+
+ return inode;
+}
+
+static int ovl_inode_test(struct inode *inode, void *data)
+{
+ return inode->i_private == data;
+}
+
+static int ovl_inode_set(struct inode *inode, void *data)
+{
+ inode->i_private = data;
+ return 0;
+}
+
+static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry,
+ struct dentry *upperdentry)
+{
+ if (S_ISDIR(inode->i_mode)) {
+ /* Real lower dir moved to upper layer under us? */
+ if (!lowerdentry && ovl_inode_lower(inode))
+ return false;
+
+ /* Lookup of an uncovered redirect origin? */
+ if (!upperdentry && ovl_inode_upper(inode))
+ return false;
+ }
+
+ /*
+ * Allow non-NULL lower inode in ovl_inode even if lowerdentry is NULL.
+ * This happens when finding a copied up overlay inode for a renamed
+ * or hardlinked overlay dentry and lower dentry cannot be followed
+ * by origin because lower fs does not support file handles.
+ */
+ if (lowerdentry && ovl_inode_lower(inode) != d_inode(lowerdentry))
+ return false;
+
+ /*
+ * Allow non-NULL __upperdentry in inode even if upperdentry is NULL.
+ * This happens when finding a lower alias for a copied up hard link.
+ */
+ if (upperdentry && ovl_inode_upper(inode) != d_inode(upperdentry))
+ return false;
+
+ return true;
+}
+
+/*
+ * Does overlay inode need to be hashed by lower inode?
+ */
+static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper,
+ struct dentry *lower, struct dentry *index)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ /* No, if pure upper */
+ if (!lower)
+ return false;
+
+ /* Yes, if already indexed */
+ if (index)
+ return true;
+
+ /* Yes, if won't be copied up */
+ if (!ofs->upper_mnt)
+ return true;
+
+ /* No, if lower hardlink is or will be broken on copy up */
+ if ((upper || !ovl_indexdir(sb)) &&
+ !d_is_dir(lower) && d_inode(lower)->i_nlink > 1)
+ return false;
+
+ /* No, if non-indexed upper with NFS export */
+ if (sb->s_export_op && upper)
+ return false;
+
+ /* Otherwise, hash by lower inode for fsnotify */
+ return true;
+}
+
+struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
+ struct dentry *index)
+{
+ struct super_block *sb = dentry->d_sb;
+ struct dentry *lowerdentry = ovl_dentry_lower(dentry);
+ struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
+ struct inode *inode;
+ bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index);
+ bool is_dir;
+
+ if (!realinode)
+ realinode = d_inode(lowerdentry);
+
+ /*
+ * Copy up origin (lower) may exist for non-indexed upper, but we must
+ * not use lower as hash key if this is a broken hardlink.
+ */
+ is_dir = S_ISDIR(realinode->i_mode);
+ if (upperdentry || bylower) {
+ struct inode *key = d_inode(bylower ? lowerdentry :
+ upperdentry);
+ unsigned int nlink = is_dir ? 1 : realinode->i_nlink;
+
+ inode = iget5_locked(sb, (unsigned long) key,
+ ovl_inode_test, ovl_inode_set, key);
+ if (!inode)
+ goto out_nomem;
+ if (!(inode->i_state & I_NEW)) {
+ /*
+ * Verify that the underlying files stored in the inode
+ * match those in the dentry.
+ */
+ if (!ovl_verify_inode(inode, lowerdentry, upperdentry)) {
+ iput(inode);
+ inode = ERR_PTR(-ESTALE);
+ goto out;
+ }
+
+ dput(upperdentry);
+ goto out;
+ }
+
+ /* Recalculate nlink for non-dir due to indexing */
+ if (!is_dir)
+ nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink);
+ set_nlink(inode, nlink);
+ } else {
+ /* Lower hardlink that will be broken on copy up */
+ inode = new_inode(sb);
+ if (!inode)
+ goto out_nomem;
+ }
+ ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
+ ovl_inode_init(inode, upperdentry, lowerdentry);
+
+ if (upperdentry && ovl_is_impuredir(upperdentry))
+ ovl_set_flag(OVL_IMPURE, inode);
+
+ if (inode->i_state & I_NEW)
+ unlock_new_inode(inode);
+out:
+ return inode;
+
+out_nomem:
+ inode = ERR_PTR(-ENOMEM);
+ goto out;
+}
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/namei.c b/src/kernel/linux/v4.14/fs/overlayfs/namei.c
new file mode 100644
index 0000000..8442f98
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/namei.c
@@ -0,0 +1,809 @@
+/*
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, 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/cred.h>
+#include <linux/namei.h>
+#include <linux/xattr.h>
+#include <linux/ratelimit.h>
+#include <linux/mount.h>
+#include <linux/exportfs.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+struct ovl_lookup_data {
+ struct qstr name;
+ bool is_dir;
+ bool opaque;
+ bool stop;
+ bool last;
+ char *redirect;
+};
+
+static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d,
+ size_t prelen, const char *post)
+{
+ int res;
+ char *s, *next, *buf = NULL;
+
+ res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0);
+ if (res < 0) {
+ if (res == -ENODATA || res == -EOPNOTSUPP)
+ return 0;
+ goto fail;
+ }
+ buf = kzalloc(prelen + res + strlen(post) + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ if (res == 0)
+ goto invalid;
+
+ res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res);
+ if (res < 0)
+ goto fail;
+ if (res == 0)
+ goto invalid;
+ if (buf[0] == '/') {
+ for (s = buf; *s++ == '/'; s = next) {
+ next = strchrnul(s, '/');
+ if (s == next)
+ goto invalid;
+ }
+ /*
+ * One of the ancestor path elements in an absolute path
+ * lookup in ovl_lookup_layer() could have been opaque and
+ * that will stop further lookup in lower layers (d->stop=true)
+ * But we have found an absolute redirect in decendant path
+ * element and that should force continue lookup in lower
+ * layers (reset d->stop).
+ */
+ d->stop = false;
+ } else {
+ if (strchr(buf, '/') != NULL)
+ goto invalid;
+
+ memmove(buf + prelen, buf, res);
+ memcpy(buf, d->name.name, prelen);
+ }
+
+ strcat(buf, post);
+ kfree(d->redirect);
+ d->redirect = buf;
+ d->name.name = d->redirect;
+ d->name.len = strlen(d->redirect);
+
+ return 0;
+
+err_free:
+ kfree(buf);
+ return 0;
+fail:
+ pr_warn_ratelimited("overlayfs: failed to get redirect (%i)\n", res);
+ goto err_free;
+invalid:
+ pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf);
+ goto err_free;
+}
+
+static int ovl_acceptable(void *ctx, struct dentry *dentry)
+{
+ return 1;
+}
+
+static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
+{
+ int res;
+ struct ovl_fh *fh = NULL;
+
+ res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);
+ if (res < 0) {
+ if (res == -ENODATA || res == -EOPNOTSUPP)
+ return NULL;
+ goto fail;
+ }
+ /* Zero size value means "copied up but origin unknown" */
+ if (res == 0)
+ return NULL;
+
+ fh = kzalloc(res, GFP_KERNEL);
+ if (!fh)
+ return ERR_PTR(-ENOMEM);
+
+ res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res);
+ if (res < 0)
+ goto fail;
+
+ if (res < sizeof(struct ovl_fh) || res < fh->len)
+ goto invalid;
+
+ if (fh->magic != OVL_FH_MAGIC)
+ goto invalid;
+
+ /* Treat larger version and unknown flags as "origin unknown" */
+ if (fh->version > OVL_FH_VERSION || fh->flags & ~OVL_FH_FLAG_ALL)
+ goto out;
+
+ /* Treat endianness mismatch as "origin unknown" */
+ if (!(fh->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
+ (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
+ goto out;
+
+ return fh;
+
+out:
+ kfree(fh);
+ return NULL;
+
+fail:
+ pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res);
+ goto out;
+invalid:
+ pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh);
+ goto out;
+}
+
+static struct dentry *ovl_get_origin(struct dentry *dentry,
+ struct vfsmount *mnt)
+{
+ struct dentry *origin = NULL;
+ struct ovl_fh *fh = ovl_get_origin_fh(dentry);
+ int bytes;
+
+ if (IS_ERR_OR_NULL(fh))
+ return (struct dentry *)fh;
+
+ /*
+ * Make sure that the stored uuid matches the uuid of the lower
+ * layer where file handle will be decoded.
+ */
+ if (!uuid_equal(&fh->uuid, &mnt->mnt_sb->s_uuid))
+ goto out;
+
+ bytes = (fh->len - offsetof(struct ovl_fh, fid));
+ origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid,
+ bytes >> 2, (int)fh->type,
+ ovl_acceptable, NULL);
+ if (IS_ERR(origin)) {
+ /* Treat stale file handle as "origin unknown" */
+ if (origin == ERR_PTR(-ESTALE))
+ origin = NULL;
+ goto out;
+ }
+
+ if (ovl_dentry_weird(origin) ||
+ ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT))
+ goto invalid;
+
+out:
+ kfree(fh);
+ return origin;
+
+invalid:
+ pr_warn_ratelimited("overlayfs: invalid origin (%pd2)\n", origin);
+ dput(origin);
+ origin = NULL;
+ goto out;
+}
+
+static bool ovl_is_opaquedir(struct dentry *dentry)
+{
+ return ovl_check_dir_xattr(dentry, OVL_XATTR_OPAQUE);
+}
+
+static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
+ const char *name, unsigned int namelen,
+ size_t prelen, const char *post,
+ struct dentry **ret)
+{
+ struct dentry *this;
+ int err;
+
+ this = lookup_one_len_unlocked(name, base, namelen);
+ if (IS_ERR(this)) {
+ err = PTR_ERR(this);
+ this = NULL;
+ if (err == -ENOENT || err == -ENAMETOOLONG)
+ goto out;
+ goto out_err;
+ }
+ if (!this->d_inode)
+ goto put_and_out;
+
+ if (ovl_dentry_weird(this)) {
+ /* Don't support traversing automounts and other weirdness */
+ err = -EREMOTE;
+ goto out_err;
+ }
+ if (ovl_is_whiteout(this)) {
+ d->stop = d->opaque = true;
+ goto put_and_out;
+ }
+ if (!d_can_lookup(this)) {
+ d->stop = true;
+ if (d->is_dir)
+ goto put_and_out;
+ goto out;
+ }
+ d->is_dir = true;
+ if (!d->last && ovl_is_opaquedir(this)) {
+ d->stop = d->opaque = true;
+ goto out;
+ }
+ err = ovl_check_redirect(this, d, prelen, post);
+ if (err)
+ goto out_err;
+out:
+ *ret = this;
+ return 0;
+
+put_and_out:
+ dput(this);
+ this = NULL;
+ goto out;
+
+out_err:
+ dput(this);
+ return err;
+}
+
+static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
+ struct dentry **ret)
+{
+ /* Counting down from the end, since the prefix can change */
+ size_t rem = d->name.len - 1;
+ struct dentry *dentry = NULL;
+ int err;
+
+ if (d->name.name[0] != '/')
+ return ovl_lookup_single(base, d, d->name.name, d->name.len,
+ 0, "", ret);
+
+ while (!IS_ERR_OR_NULL(base) && d_can_lookup(base)) {
+ const char *s = d->name.name + d->name.len - rem;
+ const char *next = strchrnul(s, '/');
+ size_t thislen = next - s;
+ bool end = !next[0];
+
+ /* Verify we did not go off the rails */
+ if (WARN_ON(s[-1] != '/'))
+ return -EIO;
+
+ err = ovl_lookup_single(base, d, s, thislen,
+ d->name.len - rem, next, &base);
+ dput(dentry);
+ if (err)
+ return err;
+ dentry = base;
+ if (end)
+ break;
+
+ rem -= thislen + 1;
+
+ if (WARN_ON(rem >= d->name.len))
+ return -EIO;
+ }
+ *ret = dentry;
+ return 0;
+}
+
+
+static int ovl_check_origin(struct dentry *upperdentry,
+ struct path *lowerstack, unsigned int numlower,
+ struct path **stackp, unsigned int *ctrp)
+{
+ struct vfsmount *mnt;
+ struct dentry *origin = NULL;
+ int i;
+
+
+ for (i = 0; i < numlower; i++) {
+ mnt = lowerstack[i].mnt;
+ origin = ovl_get_origin(upperdentry, mnt);
+ if (IS_ERR(origin))
+ return PTR_ERR(origin);
+
+ if (origin)
+ break;
+ }
+
+ if (!origin)
+ return 0;
+
+ BUG_ON(*ctrp);
+ if (!*stackp)
+ *stackp = kmalloc(sizeof(struct path), GFP_KERNEL);
+ if (!*stackp) {
+ dput(origin);
+ return -ENOMEM;
+ }
+ **stackp = (struct path) { .dentry = origin, .mnt = mnt };
+ *ctrp = 1;
+
+ return 0;
+}
+
+/*
+ * Verify that @fh matches the origin file handle stored in OVL_XATTR_ORIGIN.
+ * Return 0 on match, -ESTALE on mismatch, < 0 on error.
+ */
+static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh)
+{
+ struct ovl_fh *ofh = ovl_get_origin_fh(dentry);
+ int err = 0;
+
+ if (!ofh)
+ return -ENODATA;
+
+ if (IS_ERR(ofh))
+ return PTR_ERR(ofh);
+
+ if (fh->len != ofh->len || memcmp(fh, ofh, fh->len))
+ err = -ESTALE;
+
+ kfree(ofh);
+ return err;
+}
+
+/*
+ * Verify that an inode matches the origin file handle stored in upper inode.
+ *
+ * If @set is true and there is no stored file handle, encode and store origin
+ * file handle in OVL_XATTR_ORIGIN.
+ *
+ * Return 0 on match, -ESTALE on mismatch, < 0 on error.
+ */
+int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
+ struct dentry *origin, bool is_upper, bool set)
+{
+ struct inode *inode;
+ struct ovl_fh *fh;
+ int err;
+
+ fh = ovl_encode_fh(origin, is_upper);
+ err = PTR_ERR(fh);
+ if (IS_ERR(fh)) {
+ fh = NULL;
+ goto fail;
+ }
+
+ err = ovl_verify_origin_fh(dentry, fh);
+ if (set && err == -ENODATA)
+ err = ovl_do_setxattr(dentry, OVL_XATTR_ORIGIN, fh, fh->len, 0);
+ if (err)
+ goto fail;
+
+out:
+ kfree(fh);
+ return err;
+
+fail:
+ inode = d_inode(origin);
+ pr_warn_ratelimited("overlayfs: failed to verify origin (%pd2, ino=%lu, err=%i)\n",
+ origin, inode ? inode->i_ino : 0, err);
+ goto out;
+}
+
+/*
+ * Verify that an index entry name matches the origin file handle stored in
+ * OVL_XATTR_ORIGIN and that origin file handle can be decoded to lower path.
+ * Return 0 on match, -ESTALE on mismatch or stale origin, < 0 on error.
+ */
+int ovl_verify_index(struct dentry *index, struct path *lowerstack,
+ unsigned int numlower)
+{
+ struct ovl_fh *fh = NULL;
+ size_t len;
+ struct path origin = { };
+ struct path *stack = &origin;
+ unsigned int ctr = 0;
+ int err;
+
+ if (!d_inode(index))
+ return 0;
+
+ /*
+ * Directory index entries are going to be used for looking up
+ * redirected upper dirs by lower dir fh when decoding an overlay
+ * file handle of a merge dir. Whiteout index entries are going to be
+ * used as an indication that an exported overlay file handle should
+ * be treated as stale (i.e. after unlink of the overlay inode).
+ * We don't know the verification rules for directory and whiteout
+ * index entries, because they have not been implemented yet, so return
+ * EINVAL if those entries are found to abort the mount to avoid
+ * corrupting an index that was created by a newer kernel.
+ */
+ err = -EINVAL;
+ if (d_is_dir(index) || ovl_is_whiteout(index))
+ goto fail;
+
+ if (index->d_name.len < sizeof(struct ovl_fh)*2)
+ goto fail;
+
+ err = -ENOMEM;
+ len = index->d_name.len / 2;
+ fh = kzalloc(len, GFP_KERNEL);
+ if (!fh)
+ goto fail;
+
+ err = -EINVAL;
+ if (hex2bin((u8 *)fh, index->d_name.name, len) || len != fh->len)
+ goto fail;
+
+ err = ovl_verify_origin_fh(index, fh);
+ if (err)
+ goto fail;
+
+ err = ovl_check_origin(index, lowerstack, numlower, &stack, &ctr);
+ if (!err && !ctr)
+ err = -ESTALE;
+ if (err)
+ goto fail;
+
+ /* Check if index is orphan and don't warn before cleaning it */
+ if (d_inode(index)->i_nlink == 1 &&
+ ovl_get_nlink(origin.dentry, index, 0) == 0)
+ err = -ENOENT;
+
+ dput(origin.dentry);
+out:
+ kfree(fh);
+ return err;
+
+fail:
+ pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n",
+ index, d_inode(index)->i_mode & S_IFMT, err);
+ goto out;
+}
+
+/*
+ * Lookup in indexdir for the index entry of a lower real inode or a copy up
+ * origin inode. The index entry name is the hex representation of the lower
+ * inode file handle.
+ *
+ * If the index dentry in negative, then either no lower aliases have been
+ * copied up yet, or aliases have been copied up in older kernels and are
+ * not indexed.
+ *
+ * If the index dentry for a copy up origin inode is positive, but points
+ * to an inode different than the upper inode, then either the upper inode
+ * has been copied up and not indexed or it was indexed, but since then
+ * index dir was cleared. Either way, that index cannot be used to indentify
+ * the overlay inode.
+ */
+int ovl_get_index_name(struct dentry *origin, struct qstr *name)
+{
+ int err;
+ struct ovl_fh *fh;
+ char *n, *s;
+
+ fh = ovl_encode_fh(origin, false);
+ if (IS_ERR(fh))
+ return PTR_ERR(fh);
+
+ err = -ENOMEM;
+ n = kzalloc(fh->len * 2, GFP_KERNEL);
+ if (n) {
+ s = bin2hex(n, fh, fh->len);
+ *name = (struct qstr) QSTR_INIT(n, s - n);
+ err = 0;
+ }
+ kfree(fh);
+
+ return err;
+
+}
+
+static struct dentry *ovl_lookup_index(struct dentry *dentry,
+ struct dentry *upper,
+ struct dentry *origin)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ struct dentry *index;
+ struct inode *inode;
+ struct qstr name;
+ int err;
+
+ err = ovl_get_index_name(origin, &name);
+ if (err)
+ return ERR_PTR(err);
+
+ index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
+ if (IS_ERR(index)) {
+ err = PTR_ERR(index);
+ if (err == -ENOENT) {
+ index = NULL;
+ goto out;
+ }
+ pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n"
+ "overlayfs: mount with '-o index=off' to disable inodes index.\n",
+ d_inode(origin)->i_ino, name.len, name.name,
+ err);
+ goto out;
+ }
+
+ inode = d_inode(index);
+ if (d_is_negative(index)) {
+ goto out_dput;
+ } else if (upper && d_inode(upper) != inode) {
+ goto out_dput;
+ } else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) ||
+ ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) {
+ /*
+ * Index should always be of the same file type as origin
+ * except for the case of a whiteout index. A whiteout
+ * index should only exist if all lower aliases have been
+ * unlinked, which means that finding a lower origin on lookup
+ * whose index is a whiteout should be treated as an error.
+ */
+ pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n",
+ index, d_inode(index)->i_mode & S_IFMT,
+ d_inode(origin)->i_mode & S_IFMT);
+ goto fail;
+ }
+
+out:
+ kfree(name.name);
+ return index;
+
+out_dput:
+ dput(index);
+ index = NULL;
+ goto out;
+
+fail:
+ dput(index);
+ index = ERR_PTR(-EIO);
+ goto out;
+}
+
+/*
+ * Returns next layer in stack starting from top.
+ * Returns -1 if this is the last layer.
+ */
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ BUG_ON(idx < 0);
+ if (idx == 0) {
+ ovl_path_upper(dentry, path);
+ if (path->dentry)
+ return oe->numlower ? 1 : -1;
+ idx++;
+ }
+ BUG_ON(idx > oe->numlower);
+ *path = oe->lowerstack[idx - 1];
+
+ return (idx < oe->numlower) ? idx + 1 : -1;
+}
+
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+{
+ struct ovl_entry *oe;
+ const struct cred *old_cred;
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+ struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
+ struct path *stack = NULL;
+ struct dentry *upperdir, *upperdentry = NULL;
+ struct dentry *index = NULL;
+ unsigned int ctr = 0;
+ struct inode *inode = NULL;
+ bool upperopaque = false;
+ char *upperredirect = NULL;
+ struct dentry *this;
+ unsigned int i;
+ int err;
+ struct ovl_lookup_data d = {
+ .name = dentry->d_name,
+ .is_dir = false,
+ .opaque = false,
+ .stop = false,
+ .last = !poe->numlower,
+ .redirect = NULL,
+ };
+
+ if (dentry->d_name.len > ofs->namelen)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ upperdir = ovl_dentry_upper(dentry->d_parent);
+ if (upperdir) {
+ err = ovl_lookup_layer(upperdir, &d, &upperdentry);
+ if (err)
+ goto out;
+
+ if (upperdentry && unlikely(ovl_dentry_remote(upperdentry))) {
+ dput(upperdentry);
+ err = -EREMOTE;
+ goto out;
+ }
+ if (upperdentry && !d.is_dir) {
+ BUG_ON(!d.stop || d.redirect);
+ /*
+ * Lookup copy up origin by decoding origin file handle.
+ * We may get a disconnected dentry, which is fine,
+ * because we only need to hold the origin inode in
+ * cache and use its inode number. We may even get a
+ * connected dentry, that is not under any of the lower
+ * layers root. That is also fine for using it's inode
+ * number - it's the same as if we held a reference
+ * to a dentry in lower layer that was moved under us.
+ */
+ err = ovl_check_origin(upperdentry, roe->lowerstack,
+ roe->numlower, &stack, &ctr);
+ if (err)
+ goto out_put_upper;
+ }
+
+ if (d.redirect) {
+ err = -ENOMEM;
+ upperredirect = kstrdup(d.redirect, GFP_KERNEL);
+ if (!upperredirect)
+ goto out_put_upper;
+ if (d.redirect[0] == '/')
+ poe = roe;
+ }
+ upperopaque = d.opaque;
+ }
+
+ if (!d.stop && poe->numlower) {
+ err = -ENOMEM;
+ stack = kcalloc(ofs->numlower, sizeof(struct path),
+ GFP_KERNEL);
+ if (!stack)
+ goto out_put_upper;
+ }
+
+ for (i = 0; !d.stop && i < poe->numlower; i++) {
+ struct path lowerpath = poe->lowerstack[i];
+
+ d.last = i == poe->numlower - 1;
+ err = ovl_lookup_layer(lowerpath.dentry, &d, &this);
+ if (err)
+ goto out_put;
+
+ if (!this)
+ continue;
+
+ stack[ctr].dentry = this;
+ stack[ctr].mnt = lowerpath.mnt;
+ ctr++;
+
+ if (d.stop)
+ break;
+
+ if (d.redirect && d.redirect[0] == '/' && poe != roe) {
+ poe = roe;
+
+ /* Find the current layer on the root dentry */
+ for (i = 0; i < poe->numlower; i++)
+ if (poe->lowerstack[i].mnt == lowerpath.mnt)
+ break;
+ if (WARN_ON(i == poe->numlower))
+ break;
+ }
+ }
+
+ /* Lookup index by lower inode and verify it matches upper inode */
+ if (ctr && !d.is_dir && ovl_indexdir(dentry->d_sb)) {
+ struct dentry *origin = stack[0].dentry;
+
+ index = ovl_lookup_index(dentry, upperdentry, origin);
+ if (IS_ERR(index)) {
+ err = PTR_ERR(index);
+ index = NULL;
+ goto out_put;
+ }
+ }
+
+ oe = ovl_alloc_entry(ctr);
+ err = -ENOMEM;
+ if (!oe)
+ goto out_put;
+
+ oe->opaque = upperopaque;
+ memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+ dentry->d_fsdata = oe;
+
+ if (upperdentry)
+ ovl_dentry_set_upper_alias(dentry);
+ else if (index)
+ upperdentry = dget(index);
+
+ if (upperdentry || ctr) {
+ inode = ovl_get_inode(dentry, upperdentry, index);
+ err = PTR_ERR(inode);
+ if (IS_ERR(inode))
+ goto out_free_oe;
+
+ OVL_I(inode)->redirect = upperredirect;
+ if (index)
+ ovl_set_flag(OVL_INDEX, inode);
+ }
+
+ revert_creds(old_cred);
+ dput(index);
+ kfree(stack);
+ kfree(d.redirect);
+ d_add(dentry, inode);
+
+ return NULL;
+
+out_free_oe:
+ dentry->d_fsdata = NULL;
+ kfree(oe);
+out_put:
+ dput(index);
+ for (i = 0; i < ctr; i++)
+ dput(stack[i].dentry);
+ kfree(stack);
+out_put_upper:
+ dput(upperdentry);
+ kfree(upperredirect);
+out:
+ kfree(d.redirect);
+ revert_creds(old_cred);
+ return ERR_PTR(err);
+}
+
+bool ovl_lower_positive(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+ const struct qstr *name = &dentry->d_name;
+ unsigned int i;
+ bool positive = false;
+ bool done = false;
+
+ /*
+ * If dentry is negative, then lower is positive iff this is a
+ * whiteout.
+ */
+ if (!dentry->d_inode)
+ return oe->opaque;
+
+ /* Negative upper -> positive lower */
+ if (!ovl_dentry_upper(dentry))
+ return true;
+
+ /* Positive upper -> have to look up lower to see whether it exists */
+ for (i = 0; !done && !positive && i < poe->numlower; i++) {
+ struct dentry *this;
+ struct dentry *lowerdir = poe->lowerstack[i].dentry;
+
+ this = lookup_one_len_unlocked(name->name, lowerdir,
+ name->len);
+ if (IS_ERR(this)) {
+ switch (PTR_ERR(this)) {
+ case -ENOENT:
+ case -ENAMETOOLONG:
+ break;
+
+ default:
+ /*
+ * Assume something is there, we just couldn't
+ * access it.
+ */
+ positive = true;
+ break;
+ }
+ } else {
+ if (this->d_inode) {
+ positive = !ovl_is_whiteout(this);
+ done = true;
+ }
+ dput(this);
+ }
+ }
+
+ return positive;
+}
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/overlayfs.h b/src/kernel/linux/v4.14/fs/overlayfs/overlayfs.h
new file mode 100644
index 0000000..e1e7430
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/overlayfs.h
@@ -0,0 +1,319 @@
+/*
+ *
+ * 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/kernel.h>
+#include <linux/uuid.h>
+
+enum ovl_path_type {
+ __OVL_PATH_UPPER = (1 << 0),
+ __OVL_PATH_MERGE = (1 << 1),
+ __OVL_PATH_ORIGIN = (1 << 2),
+};
+
+#define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER)
+#define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE)
+#define OVL_TYPE_ORIGIN(type) ((type) & __OVL_PATH_ORIGIN)
+
+#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay."
+#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
+#define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect"
+#define OVL_XATTR_ORIGIN OVL_XATTR_PREFIX "origin"
+#define OVL_XATTR_IMPURE OVL_XATTR_PREFIX "impure"
+#define OVL_XATTR_NLINK OVL_XATTR_PREFIX "nlink"
+
+enum ovl_flag {
+ OVL_IMPURE,
+ OVL_INDEX,
+};
+
+/*
+ * The tuple (fh,uuid) is a universal unique identifier for a copy up origin,
+ * where:
+ * origin.fh - exported file handle of the lower file
+ * origin.uuid - uuid of the lower filesystem
+ */
+#define OVL_FH_VERSION 0
+#define OVL_FH_MAGIC 0xfb
+
+/* CPU byte order required for fid decoding: */
+#define OVL_FH_FLAG_BIG_ENDIAN (1 << 0)
+#define OVL_FH_FLAG_ANY_ENDIAN (1 << 1)
+/* Is the real inode encoded in fid an upper inode? */
+#define OVL_FH_FLAG_PATH_UPPER (1 << 2)
+
+#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN | \
+ OVL_FH_FLAG_PATH_UPPER)
+
+#if defined(__LITTLE_ENDIAN)
+#define OVL_FH_FLAG_CPU_ENDIAN 0
+#elif defined(__BIG_ENDIAN)
+#define OVL_FH_FLAG_CPU_ENDIAN OVL_FH_FLAG_BIG_ENDIAN
+#else
+#error Endianness not defined
+#endif
+
+/* On-disk and in-memeory format for redirect by file handle */
+struct ovl_fh {
+ u8 version; /* 0 */
+ u8 magic; /* 0xfb */
+ u8 len; /* size of this header + size of fid */
+ u8 flags; /* OVL_FH_FLAG_* */
+ u8 type; /* fid_type of fid */
+ uuid_t uuid; /* uuid of filesystem */
+ u8 fid[0]; /* file identifier */
+} __packed;
+
+static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry)
+{
+ int err = vfs_rmdir(dir, dentry);
+ pr_debug("rmdir(%pd2) = %i\n", dentry, err);
+ return err;
+}
+
+static inline int ovl_do_unlink(struct inode *dir, struct dentry *dentry)
+{
+ int err = vfs_unlink(dir, dentry, NULL);
+ pr_debug("unlink(%pd2) = %i\n", dentry, err);
+ return err;
+}
+
+static inline int ovl_do_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *new_dentry, bool debug)
+{
+ int err = vfs_link(old_dentry, dir, new_dentry, NULL);
+ if (debug) {
+ pr_debug("link(%pd2, %pd2) = %i\n",
+ old_dentry, new_dentry, err);
+ }
+ return err;
+}
+
+static inline int ovl_do_create(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool debug)
+{
+ int err = vfs_create(dir, dentry, mode, true);
+ if (debug)
+ pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err);
+ return err;
+}
+
+static inline int ovl_do_mkdir(struct inode *dir, struct dentry *dentry,
+ umode_t mode, bool debug)
+{
+ int err = vfs_mkdir(dir, dentry, mode);
+ if (debug)
+ pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err);
+ return err;
+}
+
+static inline int ovl_do_mknod(struct inode *dir, struct dentry *dentry,
+ umode_t mode, dev_t dev, bool debug)
+{
+ int err = vfs_mknod(dir, dentry, mode, dev);
+ if (debug) {
+ pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n",
+ dentry, mode, dev, err);
+ }
+ return err;
+}
+
+static inline int ovl_do_symlink(struct inode *dir, struct dentry *dentry,
+ const char *oldname, bool debug)
+{
+ int err = vfs_symlink(dir, dentry, oldname);
+ if (debug)
+ pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err);
+ return err;
+}
+
+static inline int ovl_do_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ int err = vfs_setxattr(dentry, name, value, size, flags);
+ pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, 0x%x) = %i\n",
+ dentry, name, min((int)size, 48), value, size, flags, err);
+ return err;
+}
+
+static inline int ovl_do_removexattr(struct dentry *dentry, const char *name)
+{
+ int err = vfs_removexattr(dentry, name);
+ pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err);
+ return err;
+}
+
+static inline int ovl_do_rename(struct inode *olddir, struct dentry *olddentry,
+ struct inode *newdir, struct dentry *newdentry,
+ unsigned int flags)
+{
+ int err;
+
+ pr_debug("rename(%pd2, %pd2, 0x%x)\n",
+ olddentry, newdentry, flags);
+
+ err = vfs_rename(olddir, olddentry, newdir, newdentry, NULL, flags);
+
+ if (err) {
+ pr_debug("...rename(%pd2, %pd2, ...) = %i\n",
+ olddentry, newdentry, err);
+ }
+ return err;
+}
+
+static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
+{
+ int err = vfs_whiteout(dir, dentry);
+ pr_debug("whiteout(%pd2) = %i\n", dentry, err);
+ return err;
+}
+
+static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode)
+{
+ struct dentry *ret = vfs_tmpfile(dentry, mode, 0);
+ int err = IS_ERR(ret) ? PTR_ERR(ret) : 0;
+
+ pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
+ return ret;
+}
+
+/* util.c */
+int ovl_want_write(struct dentry *dentry);
+void ovl_drop_write(struct dentry *dentry);
+struct dentry *ovl_workdir(struct dentry *dentry);
+const struct cred *ovl_override_creds(struct super_block *sb);
+struct super_block *ovl_same_sb(struct super_block *sb);
+bool ovl_can_decode_fh(struct super_block *sb);
+struct dentry *ovl_indexdir(struct super_block *sb);
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
+bool ovl_dentry_remote(struct dentry *dentry);
+bool ovl_dentry_weird(struct dentry *dentry);
+enum ovl_path_type ovl_path_type(struct dentry *dentry);
+void ovl_path_upper(struct dentry *dentry, struct path *path);
+void ovl_path_lower(struct dentry *dentry, struct path *path);
+enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
+struct dentry *ovl_dentry_upper(struct dentry *dentry);
+struct dentry *ovl_dentry_lower(struct dentry *dentry);
+struct dentry *ovl_dentry_real(struct dentry *dentry);
+struct dentry *ovl_i_dentry_upper(struct inode *inode);
+struct inode *ovl_inode_upper(struct inode *inode);
+struct inode *ovl_inode_lower(struct inode *inode);
+struct inode *ovl_inode_real(struct inode *inode);
+struct ovl_dir_cache *ovl_dir_cache(struct inode *inode);
+void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache);
+bool ovl_dentry_is_opaque(struct dentry *dentry);
+bool ovl_dentry_is_whiteout(struct dentry *dentry);
+void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_dentry_has_upper_alias(struct dentry *dentry);
+void ovl_dentry_set_upper_alias(struct dentry *dentry);
+bool ovl_redirect_dir(struct super_block *sb);
+const char *ovl_dentry_get_redirect(struct dentry *dentry);
+void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect);
+void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
+ struct dentry *lowerdentry);
+void ovl_inode_update(struct inode *inode, struct dentry *upperdentry);
+void ovl_dentry_version_inc(struct dentry *dentry, bool impurity);
+u64 ovl_dentry_version_get(struct dentry *dentry);
+bool ovl_is_whiteout(struct dentry *dentry);
+struct file *ovl_path_open(struct path *path, int flags);
+int ovl_copy_up_start(struct dentry *dentry);
+void ovl_copy_up_end(struct dentry *dentry);
+bool ovl_check_dir_xattr(struct dentry *dentry, const char *name);
+int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+ const char *name, const void *value, size_t size,
+ int xerr);
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
+void ovl_set_flag(unsigned long flag, struct inode *inode);
+void ovl_clear_flag(unsigned long flag, struct inode *inode);
+bool ovl_test_flag(unsigned long flag, struct inode *inode);
+bool ovl_inuse_trylock(struct dentry *dentry);
+void ovl_inuse_unlock(struct dentry *dentry);
+int ovl_nlink_start(struct dentry *dentry, bool *locked);
+void ovl_nlink_end(struct dentry *dentry, bool locked);
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir);
+
+static inline bool ovl_is_impuredir(struct dentry *dentry)
+{
+ return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE);
+}
+
+
+/* namei.c */
+int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
+ struct dentry *origin, bool is_upper, bool set);
+int ovl_verify_index(struct dentry *index, struct path *lowerstack,
+ unsigned int numlower);
+int ovl_get_index_name(struct dentry *origin, struct qstr *name);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags);
+bool ovl_lower_positive(struct dentry *dentry);
+
+/* readdir.c */
+extern const struct file_operations ovl_dir_operations;
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
+void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
+void ovl_cache_free(struct list_head *list);
+void ovl_dir_cache_free(struct inode *inode);
+int ovl_check_d_type_supported(struct path *realpath);
+void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
+ struct dentry *dentry, int level);
+int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
+ struct path *lowerstack, unsigned int numlower);
+
+/* inode.c */
+int ovl_set_nlink_upper(struct dentry *dentry);
+int ovl_set_nlink_lower(struct dentry *dentry);
+unsigned int ovl_get_nlink(struct dentry *lowerdentry,
+ struct dentry *upperdentry,
+ unsigned int fallback);
+int ovl_setattr(struct dentry *dentry, struct iattr *attr);
+int ovl_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags);
+int ovl_permission(struct inode *inode, int mask);
+int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+ const void *value, size_t size, int flags);
+int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
+ void *value, size_t size);
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
+struct posix_acl *ovl_get_acl(struct inode *inode, int type);
+int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
+int ovl_update_time(struct inode *inode, struct timespec *ts, int flags);
+bool ovl_is_private_xattr(const char *name);
+
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev);
+struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry,
+ struct dentry *index);
+static inline void ovl_copyattr(struct inode *from, struct inode *to)
+{
+ to->i_uid = from->i_uid;
+ to->i_gid = from->i_gid;
+ to->i_mode = from->i_mode;
+ to->i_atime = from->i_atime;
+ to->i_mtime = from->i_mtime;
+ to->i_ctime = from->i_ctime;
+}
+
+/* dir.c */
+extern const struct inode_operations ovl_dir_inode_operations;
+struct dentry *ovl_lookup_temp(struct dentry *workdir);
+struct cattr {
+ dev_t rdev;
+ umode_t mode;
+ const char *link;
+};
+int ovl_create_real(struct inode *dir, struct dentry *newdentry,
+ struct cattr *attr,
+ struct dentry *hardlink, bool debug);
+int ovl_cleanup(struct inode *dir, struct dentry *dentry);
+
+/* copy_up.c */
+int ovl_copy_up(struct dentry *dentry);
+int ovl_copy_up_flags(struct dentry *dentry, int flags);
+int ovl_copy_xattr(struct dentry *old, struct dentry *new);
+int ovl_set_attr(struct dentry *upper, struct kstat *stat);
+struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper);
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/ovl_entry.h b/src/kernel/linux/v4.14/fs/overlayfs/ovl_entry.h
new file mode 100644
index 0000000..36b49bd
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/ovl_entry.h
@@ -0,0 +1,81 @@
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, 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.
+ */
+
+struct ovl_config {
+ char *lowerdir;
+ char *upperdir;
+ char *workdir;
+ bool default_permissions;
+ bool redirect_dir;
+ bool index;
+};
+
+/* private information held for overlayfs's superblock */
+struct ovl_fs {
+ struct vfsmount *upper_mnt;
+ unsigned numlower;
+ struct vfsmount **lower_mnt;
+ /* workbasedir is the path at workdir= mount option */
+ struct dentry *workbasedir;
+ /* workdir is the 'work' directory under workbasedir */
+ struct dentry *workdir;
+ /* index directory listing overlay inodes by origin file handle */
+ struct dentry *indexdir;
+ long namelen;
+ /* pathnames of lower and upper dirs, for show_options */
+ struct ovl_config config;
+ /* creds of process who forced instantiation of super block */
+ const struct cred *creator_cred;
+ bool tmpfile;
+ bool noxattr;
+ /* sb common to all layers */
+ struct super_block *same_sb;
+ /* Did we take the inuse lock? */
+ bool upperdir_locked;
+ bool workdir_locked;
+};
+
+/* private information held for every overlayfs dentry */
+struct ovl_entry {
+ union {
+ struct {
+ unsigned long has_upper;
+ bool opaque;
+ };
+ struct rcu_head rcu;
+ };
+ unsigned numlower;
+ struct path lowerstack[];
+};
+
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
+
+struct ovl_inode {
+ struct ovl_dir_cache *cache;
+ const char *redirect;
+ u64 version;
+ unsigned long flags;
+ struct inode vfs_inode;
+ struct dentry *__upperdentry;
+ struct inode *lower;
+
+ /* synchronize copy up and more */
+ struct mutex lock;
+};
+
+static inline struct ovl_inode *OVL_I(struct inode *inode)
+{
+ return container_of(inode, struct ovl_inode, vfs_inode);
+}
+
+static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
+{
+ return READ_ONCE(oi->__upperdentry);
+}
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/readdir.c b/src/kernel/linux/v4.14/fs/overlayfs/readdir.c
new file mode 100644
index 0000000..1d4f999
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/readdir.c
@@ -0,0 +1,1069 @@
+/*
+ *
+ * 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/namei.h>
+#include <linux/file.h>
+#include <linux/xattr.h>
+#include <linux/rbtree.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include <linux/ratelimit.h>
+#include "overlayfs.h"
+
+struct ovl_cache_entry {
+ unsigned int len;
+ unsigned int type;
+ u64 real_ino;
+ u64 ino;
+ struct list_head l_node;
+ struct rb_node node;
+ struct ovl_cache_entry *next_maybe_whiteout;
+ bool is_whiteout;
+ char name[];
+};
+
+struct ovl_dir_cache {
+ long refcount;
+ u64 version;
+ struct list_head entries;
+ struct rb_root root;
+};
+
+struct ovl_readdir_data {
+ struct dir_context ctx;
+ struct dentry *dentry;
+ bool is_lowest;
+ struct rb_root *root;
+ struct list_head *list;
+ struct list_head middle;
+ struct ovl_cache_entry *first_maybe_whiteout;
+ int count;
+ int err;
+ bool is_upper;
+ bool d_type_supported;
+};
+
+struct ovl_dir_file {
+ bool is_real;
+ bool is_upper;
+ struct ovl_dir_cache *cache;
+ struct list_head *cursor;
+ struct file *realfile;
+ struct file *upperfile;
+};
+
+static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n)
+{
+ return rb_entry(n, struct ovl_cache_entry, node);
+}
+
+static bool ovl_cache_entry_find_link(const char *name, int len,
+ struct rb_node ***link,
+ struct rb_node **parent)
+{
+ bool found = false;
+ struct rb_node **newp = *link;
+
+ while (!found && *newp) {
+ int cmp;
+ struct ovl_cache_entry *tmp;
+
+ *parent = *newp;
+ tmp = ovl_cache_entry_from_node(*newp);
+ cmp = strncmp(name, tmp->name, len);
+ if (cmp > 0)
+ newp = &tmp->node.rb_right;
+ else if (cmp < 0 || len < tmp->len)
+ newp = &tmp->node.rb_left;
+ else
+ found = true;
+ }
+ *link = newp;
+
+ return found;
+}
+
+static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root,
+ const char *name, int len)
+{
+ struct rb_node *node = root->rb_node;
+ int cmp;
+
+ while (node) {
+ struct ovl_cache_entry *p = ovl_cache_entry_from_node(node);
+
+ cmp = strncmp(name, p->name, len);
+ if (cmp > 0)
+ node = p->node.rb_right;
+ else if (cmp < 0 || len < p->len)
+ node = p->node.rb_left;
+ else
+ return p;
+ }
+
+ return NULL;
+}
+
+static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd,
+ struct ovl_cache_entry *p)
+{
+ /* Don't care if not doing ovl_iter() */
+ if (!rdd->dentry)
+ return false;
+
+ /* Always recalc d_ino for parent */
+ if (strcmp(p->name, "..") == 0)
+ return true;
+
+ /* If this is lower, then native d_ino will do */
+ if (!rdd->is_upper)
+ return false;
+
+ /*
+ * Recalc d_ino for '.' and for all entries if dir is impure (contains
+ * copied up entries)
+ */
+ if ((p->name[0] == '.' && p->len == 1) ||
+ ovl_test_flag(OVL_IMPURE, d_inode(rdd->dentry)))
+ return true;
+
+ return false;
+}
+
+static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd,
+ const char *name, int len,
+ u64 ino, unsigned int d_type)
+{
+ struct ovl_cache_entry *p;
+ size_t size = offsetof(struct ovl_cache_entry, name[len + 1]);
+
+ p = kmalloc(size, GFP_KERNEL);
+ if (!p)
+ return NULL;
+
+ memcpy(p->name, name, len);
+ p->name[len] = '\0';
+ p->len = len;
+ p->type = d_type;
+ p->real_ino = ino;
+ p->ino = ino;
+ /* Defer setting d_ino for upper entry to ovl_iterate() */
+ if (ovl_calc_d_ino(rdd, p))
+ p->ino = 0;
+ p->is_whiteout = false;
+
+ if (d_type == DT_CHR) {
+ p->next_maybe_whiteout = rdd->first_maybe_whiteout;
+ rdd->first_maybe_whiteout = p;
+ }
+ return p;
+}
+
+static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd,
+ const char *name, int len, u64 ino,
+ unsigned int d_type)
+{
+ struct rb_node **newp = &rdd->root->rb_node;
+ struct rb_node *parent = NULL;
+ struct ovl_cache_entry *p;
+
+ if (ovl_cache_entry_find_link(name, len, &newp, &parent))
+ return 0;
+
+ p = ovl_cache_entry_new(rdd, name, len, ino, d_type);
+ if (p == NULL) {
+ rdd->err = -ENOMEM;
+ return -ENOMEM;
+ }
+
+ list_add_tail(&p->l_node, rdd->list);
+ rb_link_node(&p->node, parent, newp);
+ rb_insert_color(&p->node, rdd->root);
+
+ return 0;
+}
+
+static int ovl_fill_lowest(struct ovl_readdir_data *rdd,
+ const char *name, int namelen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct ovl_cache_entry *p;
+
+ p = ovl_cache_entry_find(rdd->root, name, namelen);
+ if (p) {
+ list_move_tail(&p->l_node, &rdd->middle);
+ } else {
+ p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type);
+ if (p == NULL)
+ rdd->err = -ENOMEM;
+ else
+ list_add_tail(&p->l_node, &rdd->middle);
+ }
+
+ return rdd->err;
+}
+
+void ovl_cache_free(struct list_head *list)
+{
+ struct ovl_cache_entry *p;
+ struct ovl_cache_entry *n;
+
+ list_for_each_entry_safe(p, n, list, l_node)
+ kfree(p);
+
+ INIT_LIST_HEAD(list);
+}
+
+void ovl_dir_cache_free(struct inode *inode)
+{
+ struct ovl_dir_cache *cache = ovl_dir_cache(inode);
+
+ if (cache) {
+ ovl_cache_free(&cache->entries);
+ kfree(cache);
+ }
+}
+
+static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry)
+{
+ struct ovl_dir_cache *cache = od->cache;
+
+ WARN_ON(cache->refcount <= 0);
+ cache->refcount--;
+ if (!cache->refcount) {
+ if (ovl_dir_cache(d_inode(dentry)) == cache)
+ ovl_set_dir_cache(d_inode(dentry), NULL);
+
+ ovl_cache_free(&cache->entries);
+ kfree(cache);
+ }
+}
+
+static int ovl_fill_merge(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino,
+ unsigned int d_type)
+{
+ struct ovl_readdir_data *rdd =
+ container_of(ctx, struct ovl_readdir_data, ctx);
+
+ rdd->count++;
+ if (!rdd->is_lowest)
+ return ovl_cache_entry_add_rb(rdd, name, namelen, ino, d_type);
+ else
+ return ovl_fill_lowest(rdd, name, namelen, offset, ino, d_type);
+}
+
+static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
+{
+ int err;
+ struct ovl_cache_entry *p;
+ struct dentry *dentry;
+ const struct cred *old_cred;
+
+ old_cred = ovl_override_creds(rdd->dentry->d_sb);
+
+ err = down_write_killable(&dir->d_inode->i_rwsem);
+ if (!err) {
+ while (rdd->first_maybe_whiteout) {
+ p = rdd->first_maybe_whiteout;
+ rdd->first_maybe_whiteout = p->next_maybe_whiteout;
+ dentry = lookup_one_len(p->name, dir, p->len);
+ if (!IS_ERR(dentry)) {
+ p->is_whiteout = ovl_is_whiteout(dentry);
+ dput(dentry);
+ }
+ }
+ inode_unlock(dir->d_inode);
+ }
+ revert_creds(old_cred);
+
+ return err;
+}
+
+static inline int ovl_dir_read(struct path *realpath,
+ struct ovl_readdir_data *rdd)
+{
+ struct file *realfile;
+ int err;
+
+ realfile = ovl_path_open(realpath, O_RDONLY | O_DIRECTORY);
+ if (IS_ERR(realfile))
+ return PTR_ERR(realfile);
+
+ rdd->first_maybe_whiteout = NULL;
+ rdd->ctx.pos = 0;
+ do {
+ rdd->count = 0;
+ rdd->err = 0;
+ err = iterate_dir(realfile, &rdd->ctx);
+ if (err >= 0)
+ err = rdd->err;
+ } while (!err && rdd->count);
+
+ if (!err && rdd->first_maybe_whiteout && rdd->dentry)
+ err = ovl_check_whiteouts(realpath->dentry, rdd);
+
+ fput(realfile);
+
+ return err;
+}
+
+static void ovl_dir_reset(struct file *file)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct ovl_dir_cache *cache = od->cache;
+ struct dentry *dentry = file->f_path.dentry;
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ if (cache && ovl_dentry_version_get(dentry) != cache->version) {
+ ovl_cache_put(od, dentry);
+ od->cache = NULL;
+ od->cursor = NULL;
+ }
+ WARN_ON(!od->is_real && !OVL_TYPE_MERGE(type));
+ if (od->is_real && OVL_TYPE_MERGE(type))
+ od->is_real = false;
+}
+
+static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list,
+ struct rb_root *root)
+{
+ int err;
+ struct path realpath;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_merge,
+ .dentry = dentry,
+ .list = list,
+ .root = root,
+ .is_lowest = false,
+ };
+ int idx, next;
+
+ for (idx = 0; idx != -1; idx = next) {
+ next = ovl_path_next(idx, dentry, &realpath);
+ rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry;
+
+ if (next != -1) {
+ err = ovl_dir_read(&realpath, &rdd);
+ if (err)
+ break;
+ } else {
+ /*
+ * Insert lowest layer entries before upper ones, this
+ * allows offsets to be reasonably constant
+ */
+ list_add(&rdd.middle, rdd.list);
+ rdd.is_lowest = true;
+ err = ovl_dir_read(&realpath, &rdd);
+ list_del(&rdd.middle);
+ }
+ }
+ return err;
+}
+
+static void ovl_seek_cursor(struct ovl_dir_file *od, loff_t pos)
+{
+ struct list_head *p;
+ loff_t off = 0;
+
+ list_for_each(p, &od->cache->entries) {
+ if (off >= pos)
+ break;
+ off++;
+ }
+ /* Cursor is safe since the cache is stable */
+ od->cursor = p;
+}
+
+static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry)
+{
+ int res;
+ struct ovl_dir_cache *cache;
+
+ cache = ovl_dir_cache(d_inode(dentry));
+ if (cache && ovl_dentry_version_get(dentry) == cache->version) {
+ WARN_ON(!cache->refcount);
+ cache->refcount++;
+ return cache;
+ }
+ ovl_set_dir_cache(d_inode(dentry), NULL);
+
+ cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL);
+ if (!cache)
+ return ERR_PTR(-ENOMEM);
+
+ cache->refcount = 1;
+ INIT_LIST_HEAD(&cache->entries);
+ cache->root = RB_ROOT;
+
+ res = ovl_dir_read_merged(dentry, &cache->entries, &cache->root);
+ if (res) {
+ ovl_cache_free(&cache->entries);
+ kfree(cache);
+ return ERR_PTR(res);
+ }
+
+ cache->version = ovl_dentry_version_get(dentry);
+ ovl_set_dir_cache(d_inode(dentry), cache);
+
+ return cache;
+}
+
+/*
+ * Set d_ino for upper entries. Non-upper entries should always report
+ * the uppermost real inode ino and should not call this function.
+ *
+ * When not all layer are on same fs, report real ino also for upper.
+ *
+ * When all layers are on the same fs, and upper has a reference to
+ * copy up origin, call vfs_getattr() on the overlay entry to make
+ * sure that d_ino will be consistent with st_ino from stat(2).
+ */
+static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p)
+
+{
+ struct dentry *dir = path->dentry;
+ struct dentry *this = NULL;
+ enum ovl_path_type type;
+ u64 ino = p->real_ino;
+ int err = 0;
+
+ if (!ovl_same_sb(dir->d_sb))
+ goto out;
+
+ if (p->name[0] == '.') {
+ if (p->len == 1) {
+ this = dget(dir);
+ goto get;
+ }
+ if (p->len == 2 && p->name[1] == '.') {
+ /* we shall not be moved */
+ this = dget(dir->d_parent);
+ goto get;
+ }
+ }
+ this = lookup_one_len(p->name, dir, p->len);
+ if (IS_ERR_OR_NULL(this) || !this->d_inode) {
+ if (IS_ERR(this)) {
+ err = PTR_ERR(this);
+ this = NULL;
+ goto fail;
+ }
+ goto out;
+ }
+
+get:
+ type = ovl_path_type(this);
+ if (OVL_TYPE_ORIGIN(type)) {
+ struct kstat stat;
+ struct path statpath = *path;
+
+ statpath.dentry = this;
+ err = vfs_getattr(&statpath, &stat, STATX_INO, 0);
+ if (err)
+ goto fail;
+
+ WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev);
+ ino = stat.ino;
+ }
+
+out:
+ p->ino = ino;
+ dput(this);
+ return err;
+
+fail:
+ pr_warn_ratelimited("overlay: failed to look up (%s) for ino (%i)\n",
+ p->name, err);
+ goto out;
+}
+
+static int ovl_fill_plain(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino,
+ unsigned int d_type)
+{
+ struct ovl_cache_entry *p;
+ struct ovl_readdir_data *rdd =
+ container_of(ctx, struct ovl_readdir_data, ctx);
+
+ rdd->count++;
+ p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type);
+ if (p == NULL) {
+ rdd->err = -ENOMEM;
+ return -ENOMEM;
+ }
+ list_add_tail(&p->l_node, rdd->list);
+
+ return 0;
+}
+
+static int ovl_dir_read_impure(struct path *path, struct list_head *list,
+ struct rb_root *root)
+{
+ int err;
+ struct path realpath;
+ struct ovl_cache_entry *p, *n;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_plain,
+ .list = list,
+ .root = root,
+ };
+
+ INIT_LIST_HEAD(list);
+ *root = RB_ROOT;
+ ovl_path_upper(path->dentry, &realpath);
+
+ err = ovl_dir_read(&realpath, &rdd);
+ if (err)
+ return err;
+
+ list_for_each_entry_safe(p, n, list, l_node) {
+ if (strcmp(p->name, ".") != 0 &&
+ strcmp(p->name, "..") != 0) {
+ err = ovl_cache_update_ino(path, p);
+ if (err)
+ return err;
+ }
+ if (p->ino == p->real_ino) {
+ list_del(&p->l_node);
+ kfree(p);
+ } else {
+ struct rb_node **newp = &root->rb_node;
+ struct rb_node *parent = NULL;
+
+ if (WARN_ON(ovl_cache_entry_find_link(p->name, p->len,
+ &newp, &parent)))
+ return -EIO;
+
+ rb_link_node(&p->node, parent, newp);
+ rb_insert_color(&p->node, root);
+ }
+ }
+ return 0;
+}
+
+static struct ovl_dir_cache *ovl_cache_get_impure(struct path *path)
+{
+ int res;
+ struct dentry *dentry = path->dentry;
+ struct ovl_dir_cache *cache;
+
+ cache = ovl_dir_cache(d_inode(dentry));
+ if (cache && ovl_dentry_version_get(dentry) == cache->version)
+ return cache;
+
+ /* Impure cache is not refcounted, free it here */
+ ovl_dir_cache_free(d_inode(dentry));
+ ovl_set_dir_cache(d_inode(dentry), NULL);
+
+ cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL);
+ if (!cache)
+ return ERR_PTR(-ENOMEM);
+
+ res = ovl_dir_read_impure(path, &cache->entries, &cache->root);
+ if (res) {
+ ovl_cache_free(&cache->entries);
+ kfree(cache);
+ return ERR_PTR(res);
+ }
+ if (list_empty(&cache->entries)) {
+ /*
+ * A good opportunity to get rid of an unneeded "impure" flag.
+ * Removing the "impure" xattr is best effort.
+ */
+ if (!ovl_want_write(dentry)) {
+ ovl_do_removexattr(ovl_dentry_upper(dentry),
+ OVL_XATTR_IMPURE);
+ ovl_drop_write(dentry);
+ }
+ ovl_clear_flag(OVL_IMPURE, d_inode(dentry));
+ kfree(cache);
+ return NULL;
+ }
+
+ cache->version = ovl_dentry_version_get(dentry);
+ ovl_set_dir_cache(d_inode(dentry), cache);
+
+ return cache;
+}
+
+struct ovl_readdir_translate {
+ struct dir_context *orig_ctx;
+ struct ovl_dir_cache *cache;
+ struct dir_context ctx;
+ u64 parent_ino;
+};
+
+static int ovl_fill_real(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino,
+ unsigned int d_type)
+{
+ struct ovl_readdir_translate *rdt =
+ container_of(ctx, struct ovl_readdir_translate, ctx);
+ struct dir_context *orig_ctx = rdt->orig_ctx;
+
+ if (rdt->parent_ino && strcmp(name, "..") == 0)
+ ino = rdt->parent_ino;
+ else if (rdt->cache) {
+ struct ovl_cache_entry *p;
+
+ p = ovl_cache_entry_find(&rdt->cache->root, name, namelen);
+ if (p)
+ ino = p->ino;
+ }
+
+ return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type);
+}
+
+static bool ovl_is_impure_dir(struct file *file)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct inode *dir = d_inode(file->f_path.dentry);
+
+ /*
+ * Only upper dir can be impure, but if we are in the middle of
+ * iterating a lower real dir, dir could be copied up and marked
+ * impure. We only want the impure cache if we started iterating
+ * a real upper dir to begin with.
+ */
+ return od->is_upper && ovl_test_flag(OVL_IMPURE, dir);
+
+}
+
+static int ovl_iterate_real(struct file *file, struct dir_context *ctx)
+{
+ int err;
+ struct ovl_dir_file *od = file->private_data;
+ struct dentry *dir = file->f_path.dentry;
+ struct ovl_readdir_translate rdt = {
+ .ctx.actor = ovl_fill_real,
+ .orig_ctx = ctx,
+ };
+
+ if (OVL_TYPE_MERGE(ovl_path_type(dir->d_parent))) {
+ struct kstat stat;
+ struct path statpath = file->f_path;
+
+ statpath.dentry = dir->d_parent;
+ err = vfs_getattr(&statpath, &stat, STATX_INO, 0);
+ if (err)
+ return err;
+
+ WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev);
+ rdt.parent_ino = stat.ino;
+ }
+
+ if (ovl_is_impure_dir(file)) {
+ rdt.cache = ovl_cache_get_impure(&file->f_path);
+ if (IS_ERR(rdt.cache))
+ return PTR_ERR(rdt.cache);
+ }
+
+ err = iterate_dir(od->realfile, &rdt.ctx);
+ ctx->pos = rdt.ctx.pos;
+
+ return err;
+}
+
+
+static int ovl_iterate(struct file *file, struct dir_context *ctx)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct dentry *dentry = file->f_path.dentry;
+ struct ovl_cache_entry *p;
+ int err;
+
+ if (!ctx->pos)
+ ovl_dir_reset(file);
+
+ if (od->is_real) {
+ /*
+ * If parent is merge, then need to adjust d_ino for '..', if
+ * dir is impure then need to adjust d_ino for copied up
+ * entries.
+ */
+ if (ovl_same_sb(dentry->d_sb) &&
+ (ovl_is_impure_dir(file) ||
+ OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent)))) {
+ return ovl_iterate_real(file, ctx);
+ }
+ return iterate_dir(od->realfile, ctx);
+ }
+
+ if (!od->cache) {
+ struct ovl_dir_cache *cache;
+
+ cache = ovl_cache_get(dentry);
+ if (IS_ERR(cache))
+ return PTR_ERR(cache);
+
+ od->cache = cache;
+ ovl_seek_cursor(od, ctx->pos);
+ }
+
+ while (od->cursor != &od->cache->entries) {
+ p = list_entry(od->cursor, struct ovl_cache_entry, l_node);
+ if (!p->is_whiteout) {
+ if (!p->ino) {
+ err = ovl_cache_update_ino(&file->f_path, p);
+ if (err)
+ return err;
+ }
+ if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
+ break;
+ }
+ od->cursor = p->l_node.next;
+ ctx->pos++;
+ }
+ return 0;
+}
+
+static loff_t ovl_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ loff_t res;
+ struct ovl_dir_file *od = file->private_data;
+
+ inode_lock(file_inode(file));
+ if (!file->f_pos)
+ ovl_dir_reset(file);
+
+ if (od->is_real) {
+ res = vfs_llseek(od->realfile, offset, origin);
+ file->f_pos = od->realfile->f_pos;
+ } else {
+ res = -EINVAL;
+
+ switch (origin) {
+ case SEEK_CUR:
+ offset += file->f_pos;
+ break;
+ case SEEK_SET:
+ break;
+ default:
+ goto out_unlock;
+ }
+ if (offset < 0)
+ goto out_unlock;
+
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ if (od->cache)
+ ovl_seek_cursor(od, offset);
+ }
+ res = offset;
+ }
+out_unlock:
+ inode_unlock(file_inode(file));
+
+ return res;
+}
+
+static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
+ int datasync)
+{
+ struct ovl_dir_file *od = file->private_data;
+ struct dentry *dentry = file->f_path.dentry;
+ struct file *realfile = od->realfile;
+
+ /* Nothing to sync for lower */
+ if (!OVL_TYPE_UPPER(ovl_path_type(dentry)))
+ return 0;
+
+ /*
+ * Need to check if we started out being a lower dir, but got copied up
+ */
+ if (!od->is_upper) {
+ struct inode *inode = file_inode(file);
+
+ realfile = READ_ONCE(od->upperfile);
+ if (!realfile) {
+ struct path upperpath;
+
+ ovl_path_upper(dentry, &upperpath);
+ realfile = ovl_path_open(&upperpath, O_RDONLY);
+
+ inode_lock(inode);
+ if (!od->upperfile) {
+ if (IS_ERR(realfile)) {
+ inode_unlock(inode);
+ return PTR_ERR(realfile);
+ }
+ smp_store_release(&od->upperfile, realfile);
+ } else {
+ /* somebody has beaten us to it */
+ if (!IS_ERR(realfile))
+ fput(realfile);
+ realfile = od->upperfile;
+ }
+ inode_unlock(inode);
+ }
+ }
+
+ return vfs_fsync_range(realfile, start, end, datasync);
+}
+
+static int ovl_dir_release(struct inode *inode, struct file *file)
+{
+ struct ovl_dir_file *od = file->private_data;
+
+ if (od->cache) {
+ inode_lock(inode);
+ ovl_cache_put(od, file->f_path.dentry);
+ inode_unlock(inode);
+ }
+ fput(od->realfile);
+ if (od->upperfile)
+ fput(od->upperfile);
+ kfree(od);
+
+ return 0;
+}
+
+static int ovl_dir_open(struct inode *inode, struct file *file)
+{
+ struct path realpath;
+ struct file *realfile;
+ struct ovl_dir_file *od;
+ enum ovl_path_type type;
+
+ od = kzalloc(sizeof(struct ovl_dir_file), GFP_KERNEL);
+ if (!od)
+ return -ENOMEM;
+
+ type = ovl_path_real(file->f_path.dentry, &realpath);
+ realfile = ovl_path_open(&realpath, file->f_flags);
+ if (IS_ERR(realfile)) {
+ kfree(od);
+ return PTR_ERR(realfile);
+ }
+ od->realfile = realfile;
+ od->is_real = !OVL_TYPE_MERGE(type);
+ od->is_upper = OVL_TYPE_UPPER(type);
+ file->private_data = od;
+
+ return 0;
+}
+
+const struct file_operations ovl_dir_operations = {
+ .read = generic_read_dir,
+ .open = ovl_dir_open,
+ .iterate = ovl_iterate,
+ .llseek = ovl_dir_llseek,
+ .fsync = ovl_dir_fsync,
+ .release = ovl_dir_release,
+};
+
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
+{
+ int err;
+ struct ovl_cache_entry *p;
+ struct rb_root root = RB_ROOT;
+
+ err = ovl_dir_read_merged(dentry, list, &root);
+ if (err)
+ return err;
+
+ err = 0;
+
+ list_for_each_entry(p, list, l_node) {
+ if (p->is_whiteout)
+ continue;
+
+ if (p->name[0] == '.') {
+ if (p->len == 1)
+ continue;
+ if (p->len == 2 && p->name[1] == '.')
+ continue;
+ }
+ err = -ENOTEMPTY;
+ break;
+ }
+
+ return err;
+}
+
+void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list)
+{
+ struct ovl_cache_entry *p;
+
+ inode_lock_nested(upper->d_inode, I_MUTEX_CHILD);
+ list_for_each_entry(p, list, l_node) {
+ struct dentry *dentry;
+
+ if (!p->is_whiteout)
+ continue;
+
+ dentry = lookup_one_len(p->name, upper, p->len);
+ if (IS_ERR(dentry)) {
+ pr_err("overlayfs: lookup '%s/%.*s' failed (%i)\n",
+ upper->d_name.name, p->len, p->name,
+ (int) PTR_ERR(dentry));
+ continue;
+ }
+ if (dentry->d_inode)
+ ovl_cleanup(upper->d_inode, dentry);
+ dput(dentry);
+ }
+ inode_unlock(upper->d_inode);
+}
+
+static int ovl_check_d_type(struct dir_context *ctx, const char *name,
+ int namelen, loff_t offset, u64 ino,
+ unsigned int d_type)
+{
+ struct ovl_readdir_data *rdd =
+ container_of(ctx, struct ovl_readdir_data, ctx);
+
+ /* Even if d_type is not supported, DT_DIR is returned for . and .. */
+ if (!strncmp(name, ".", namelen) || !strncmp(name, "..", namelen))
+ return 0;
+
+ if (d_type != DT_UNKNOWN)
+ rdd->d_type_supported = true;
+
+ return 0;
+}
+
+/*
+ * Returns 1 if d_type is supported, 0 not supported/unknown. Negative values
+ * if error is encountered.
+ */
+int ovl_check_d_type_supported(struct path *realpath)
+{
+ int err;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_check_d_type,
+ .d_type_supported = false,
+ };
+
+ err = ovl_dir_read(realpath, &rdd);
+ if (err)
+ return err;
+
+ return rdd.d_type_supported;
+}
+
+static void ovl_workdir_cleanup_recurse(struct path *path, int level)
+{
+ int err;
+ struct inode *dir = path->dentry->d_inode;
+ LIST_HEAD(list);
+ struct rb_root root = RB_ROOT;
+ struct ovl_cache_entry *p;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_merge,
+ .dentry = NULL,
+ .list = &list,
+ .root = &root,
+ .is_lowest = false,
+ };
+
+ err = ovl_dir_read(path, &rdd);
+ if (err)
+ goto out;
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ list_for_each_entry(p, &list, l_node) {
+ struct dentry *dentry;
+
+ if (p->name[0] == '.') {
+ if (p->len == 1)
+ continue;
+ if (p->len == 2 && p->name[1] == '.')
+ continue;
+ }
+ dentry = lookup_one_len(p->name, path->dentry, p->len);
+ if (IS_ERR(dentry))
+ continue;
+ if (dentry->d_inode)
+ ovl_workdir_cleanup(dir, path->mnt, dentry, level);
+ dput(dentry);
+ }
+ inode_unlock(dir);
+out:
+ ovl_cache_free(&list);
+}
+
+void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
+ struct dentry *dentry, int level)
+{
+ int err;
+
+ if (!d_is_dir(dentry) || level > 1) {
+ ovl_cleanup(dir, dentry);
+ return;
+ }
+
+ err = ovl_do_rmdir(dir, dentry);
+ if (err) {
+ struct path path = { .mnt = mnt, .dentry = dentry };
+
+ inode_unlock(dir);
+ ovl_workdir_cleanup_recurse(&path, level + 1);
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ ovl_cleanup(dir, dentry);
+ }
+}
+
+int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
+ struct path *lowerstack, unsigned int numlower)
+{
+ int err;
+ struct dentry *index = NULL;
+ struct inode *dir = dentry->d_inode;
+ struct path path = { .mnt = mnt, .dentry = dentry };
+ LIST_HEAD(list);
+ struct rb_root root = RB_ROOT;
+ struct ovl_cache_entry *p;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_merge,
+ .dentry = NULL,
+ .list = &list,
+ .root = &root,
+ .is_lowest = false,
+ };
+
+ err = ovl_dir_read(&path, &rdd);
+ if (err)
+ goto out;
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ list_for_each_entry(p, &list, l_node) {
+ if (p->name[0] == '.') {
+ if (p->len == 1)
+ continue;
+ if (p->len == 2 && p->name[1] == '.')
+ continue;
+ }
+ index = lookup_one_len(p->name, dentry, p->len);
+ if (IS_ERR(index)) {
+ err = PTR_ERR(index);
+ index = NULL;
+ break;
+ }
+ err = ovl_verify_index(index, lowerstack, numlower);
+ /* Cleanup stale and orphan index entries */
+ if (err && (err == -ESTALE || err == -ENOENT))
+ err = ovl_cleanup(dir, index);
+ if (err)
+ break;
+
+ dput(index);
+ index = NULL;
+ }
+ dput(index);
+ inode_unlock(dir);
+out:
+ ovl_cache_free(&list);
+ if (err)
+ pr_err("overlayfs: failed index dir cleanup (%i)\n", err);
+ return err;
+}
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/super.c b/src/kernel/linux/v4.14/fs/overlayfs/super.c
new file mode 100644
index 0000000..ba20393
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/super.c
@@ -0,0 +1,1255 @@
+/*
+ *
+ * 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>
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/xattr.h>
+#include <linux/mount.h>
+#include <linux/parser.h>
+#include <linux/module.h>
+#include <linux/statfs.h>
+#include <linux/seq_file.h>
+#include <linux/posix_acl_xattr.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
+MODULE_DESCRIPTION("Overlay filesystem");
+MODULE_LICENSE("GPL");
+
+
+struct ovl_dir_cache;
+
+#define OVL_MAX_STACK 500
+
+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,
+ "Default to on or off for the redirect_dir feature");
+
+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,
+ "Default to on or off for the inodes index feature");
+
+static void ovl_dentry_release(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ if (oe) {
+ unsigned int i;
+
+ for (i = 0; i < oe->numlower; i++)
+ dput(oe->lowerstack[i].dentry);
+ kfree_rcu(oe, rcu);
+ }
+}
+
+static int ovl_check_append_only(struct inode *inode, int flag)
+{
+ /*
+ * This test was moot in vfs may_open() because overlay inode does
+ * not have the S_APPEND flag, so re-check on real upper inode
+ */
+ if (IS_APPEND(inode)) {
+ if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
+ return -EPERM;
+ if (flag & O_TRUNC)
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+static struct dentry *ovl_d_real(struct dentry *dentry,
+ const struct inode *inode,
+ unsigned int open_flags, unsigned int flags)
+{
+ struct dentry *real;
+ int err;
+
+ if (flags & D_REAL_UPPER)
+ return ovl_dentry_upper(dentry);
+
+ if (!d_is_reg(dentry)) {
+ if (!inode || inode == d_inode(dentry))
+ return dentry;
+ goto bug;
+ }
+
+ if (open_flags) {
+ err = ovl_open_maybe_copy_up(dentry, open_flags);
+ if (err)
+ return ERR_PTR(err);
+ }
+
+ real = ovl_dentry_upper(dentry);
+ if (real && (!inode || inode == d_inode(real))) {
+ if (!inode) {
+ err = ovl_check_append_only(d_inode(real), open_flags);
+ if (err)
+ return ERR_PTR(err);
+ }
+ return real;
+ }
+
+ real = ovl_dentry_lower(dentry);
+ if (!real)
+ goto bug;
+
+ /* Handle recursion */
+ real = d_real(real, inode, open_flags, 0);
+
+ if (!inode || inode == d_inode(real))
+ return real;
+bug:
+ WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry,
+ inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0);
+ return dentry;
+}
+
+static int ovl_dentry_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_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;
+ }
+ }
+ return ret;
+}
+
+static const struct dentry_operations ovl_dentry_operations = {
+ .d_release = ovl_dentry_release,
+ .d_real = ovl_d_real,
+};
+
+static const struct dentry_operations ovl_reval_dentry_operations = {
+ .d_release = ovl_dentry_release,
+ .d_real = ovl_d_real,
+ .d_revalidate = ovl_dentry_revalidate,
+ .d_weak_revalidate = ovl_dentry_weak_revalidate,
+};
+
+static struct kmem_cache *ovl_inode_cachep;
+
+static struct inode *ovl_alloc_inode(struct super_block *sb)
+{
+ struct ovl_inode *oi = kmem_cache_alloc(ovl_inode_cachep, GFP_KERNEL);
+
+ if (!oi)
+ return NULL;
+
+ oi->cache = NULL;
+ oi->redirect = NULL;
+ oi->version = 0;
+ oi->flags = 0;
+ oi->__upperdentry = NULL;
+ oi->lower = NULL;
+ mutex_init(&oi->lock);
+
+ return &oi->vfs_inode;
+}
+
+static void ovl_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+
+ kmem_cache_free(ovl_inode_cachep, OVL_I(inode));
+}
+
+static void ovl_destroy_inode(struct inode *inode)
+{
+ struct ovl_inode *oi = OVL_I(inode);
+
+ dput(oi->__upperdentry);
+ iput(oi->lower);
+ kfree(oi->redirect);
+ ovl_dir_cache_free(inode);
+ mutex_destroy(&oi->lock);
+
+ call_rcu(&inode->i_rcu, ovl_i_callback);
+}
+
+static void ovl_put_super(struct super_block *sb)
+{
+ struct ovl_fs *ufs = sb->s_fs_info;
+ unsigned i;
+
+ dput(ufs->indexdir);
+ dput(ufs->workdir);
+ if (ufs->workdir_locked)
+ ovl_inuse_unlock(ufs->workbasedir);
+ dput(ufs->workbasedir);
+ if (ufs->upper_mnt && ufs->upperdir_locked)
+ ovl_inuse_unlock(ufs->upper_mnt->mnt_root);
+ mntput(ufs->upper_mnt);
+ for (i = 0; i < ufs->numlower; i++)
+ mntput(ufs->lower_mnt[i]);
+ kfree(ufs->lower_mnt);
+
+ kfree(ufs->config.lowerdir);
+ kfree(ufs->config.upperdir);
+ kfree(ufs->config.workdir);
+ put_cred(ufs->creator_cred);
+ kfree(ufs);
+}
+
+/* Sync real dirty inodes in upper filesystem (if it exists) */
+static int ovl_sync_fs(struct super_block *sb, int wait)
+{
+ struct ovl_fs *ufs = sb->s_fs_info;
+ struct super_block *upper_sb;
+ int ret;
+
+ if (!ufs->upper_mnt)
+ return 0;
+
+ /*
+ * 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.
+ *
+ * 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
+ * called with wait == 1.
+ */
+ if (!wait)
+ return 0;
+
+ upper_sb = ufs->upper_mnt->mnt_sb;
+
+ down_read(&upper_sb->s_umount);
+ ret = sync_filesystem(upper_sb);
+ up_read(&upper_sb->s_umount);
+
+ return ret;
+}
+
+/**
+ * ovl_statfs
+ * @sb: The overlayfs super block
+ * @buf: The struct kstatfs to fill in with stats
+ *
+ * Get the filesystem statistics. As writes always target the upper layer
+ * filesystem pass the statfs to the upper filesystem (if it exists)
+ */
+static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ struct dentry *root_dentry = dentry->d_sb->s_root;
+ struct path path;
+ int err;
+
+ ovl_path_real(root_dentry, &path);
+
+ err = vfs_statfs(&path, buf);
+ if (!err) {
+ buf->f_namelen = ofs->namelen;
+ buf->f_type = OVERLAYFS_SUPER_MAGIC;
+ }
+
+ return err;
+}
+
+/* Will this overlay be forced to mount/remount ro? */
+static bool ovl_force_readonly(struct ovl_fs *ufs)
+{
+ return (!ufs->upper_mnt || !ufs->workdir);
+}
+
+/**
+ * ovl_show_options
+ *
+ * Prints the mount options for a given superblock.
+ * Returns zero; does not fail.
+ */
+static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
+{
+ struct super_block *sb = dentry->d_sb;
+ struct ovl_fs *ufs = sb->s_fs_info;
+
+ seq_show_option(m, "lowerdir", ufs->config.lowerdir);
+ if (ufs->config.upperdir) {
+ seq_show_option(m, "upperdir", ufs->config.upperdir);
+ seq_show_option(m, "workdir", ufs->config.workdir);
+ }
+ if (ufs->config.default_permissions)
+ seq_puts(m, ",default_permissions");
+ if (ufs->config.redirect_dir != ovl_redirect_dir_def)
+ seq_printf(m, ",redirect_dir=%s",
+ ufs->config.redirect_dir ? "on" : "off");
+ if (ufs->config.index != ovl_index_def)
+ seq_printf(m, ",index=%s",
+ ufs->config.index ? "on" : "off");
+ return 0;
+}
+
+static int ovl_remount(struct super_block *sb, int *flags, char *data)
+{
+ struct ovl_fs *ufs = sb->s_fs_info;
+
+ if (!(*flags & MS_RDONLY) && ovl_force_readonly(ufs))
+ return -EROFS;
+
+ return 0;
+}
+
+static const struct super_operations ovl_super_operations = {
+ .alloc_inode = ovl_alloc_inode,
+ .destroy_inode = ovl_destroy_inode,
+ .drop_inode = generic_delete_inode,
+ .put_super = ovl_put_super,
+ .sync_fs = ovl_sync_fs,
+ .statfs = ovl_statfs,
+ .show_options = ovl_show_options,
+ .remount_fs = ovl_remount,
+};
+
+enum {
+ OPT_LOWERDIR,
+ OPT_UPPERDIR,
+ OPT_WORKDIR,
+ OPT_DEFAULT_PERMISSIONS,
+ OPT_REDIRECT_DIR_ON,
+ OPT_REDIRECT_DIR_OFF,
+ OPT_INDEX_ON,
+ OPT_INDEX_OFF,
+ OPT_ERR,
+};
+
+static const match_table_t ovl_tokens = {
+ {OPT_LOWERDIR, "lowerdir=%s"},
+ {OPT_UPPERDIR, "upperdir=%s"},
+ {OPT_WORKDIR, "workdir=%s"},
+ {OPT_DEFAULT_PERMISSIONS, "default_permissions"},
+ {OPT_REDIRECT_DIR_ON, "redirect_dir=on"},
+ {OPT_REDIRECT_DIR_OFF, "redirect_dir=off"},
+ {OPT_INDEX_ON, "index=on"},
+ {OPT_INDEX_OFF, "index=off"},
+ {OPT_ERR, NULL}
+};
+
+static char *ovl_next_opt(char **s)
+{
+ char *sbegin = *s;
+ char *p;
+
+ if (sbegin == NULL)
+ return NULL;
+
+ for (p = sbegin; *p; p++) {
+ if (*p == '\\') {
+ p++;
+ if (!*p)
+ break;
+ } else if (*p == ',') {
+ *p = '\0';
+ *s = p + 1;
+ return sbegin;
+ }
+ }
+ *s = NULL;
+ return sbegin;
+}
+
+static int ovl_parse_opt(char *opt, struct ovl_config *config)
+{
+ char *p;
+
+ while ((p = ovl_next_opt(&opt)) != NULL) {
+ int token;
+ substring_t args[MAX_OPT_ARGS];
+
+ if (!*p)
+ continue;
+
+ token = match_token(p, ovl_tokens, args);
+ switch (token) {
+ case OPT_UPPERDIR:
+ kfree(config->upperdir);
+ config->upperdir = match_strdup(&args[0]);
+ if (!config->upperdir)
+ return -ENOMEM;
+ break;
+
+ case OPT_LOWERDIR:
+ kfree(config->lowerdir);
+ config->lowerdir = match_strdup(&args[0]);
+ if (!config->lowerdir)
+ return -ENOMEM;
+ break;
+
+ case OPT_WORKDIR:
+ kfree(config->workdir);
+ config->workdir = match_strdup(&args[0]);
+ if (!config->workdir)
+ return -ENOMEM;
+ break;
+
+ case OPT_DEFAULT_PERMISSIONS:
+ config->default_permissions = true;
+ break;
+
+ case OPT_REDIRECT_DIR_ON:
+ config->redirect_dir = true;
+ break;
+
+ case OPT_REDIRECT_DIR_OFF:
+ config->redirect_dir = false;
+ break;
+
+ case OPT_INDEX_ON:
+ config->index = true;
+ break;
+
+ case OPT_INDEX_OFF:
+ config->index = false;
+ break;
+
+ default:
+ pr_err("overlayfs: 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;
+ }
+
+ return 0;
+}
+
+#define OVL_WORKDIR_NAME "work"
+#define OVL_INDEXDIR_NAME "index"
+
+static struct dentry *ovl_workdir_create(struct super_block *sb,
+ struct ovl_fs *ufs,
+ struct dentry *dentry,
+ const char *name, bool persist)
+{
+ struct inode *dir = dentry->d_inode;
+ struct vfsmount *mnt = ufs->upper_mnt;
+ struct dentry *work;
+ int err;
+ bool retried = false;
+ bool locked = false;
+
+ err = mnt_want_write(mnt);
+ if (err)
+ goto out_err;
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ locked = true;
+
+retry:
+ work = lookup_one_len(name, dentry, strlen(name));
+
+ if (!IS_ERR(work)) {
+ struct iattr attr = {
+ .ia_valid = ATTR_MODE,
+ .ia_mode = S_IFDIR | 0,
+ };
+
+ if (work->d_inode) {
+ err = -EEXIST;
+ if (retried)
+ goto out_dput;
+
+ if (persist)
+ goto out_unlock;
+
+ retried = true;
+ ovl_workdir_cleanup(dir, mnt, work, 0);
+ dput(work);
+ goto retry;
+ }
+
+ err = ovl_create_real(dir, work,
+ &(struct cattr){.mode = S_IFDIR | 0},
+ NULL, true);
+ if (err)
+ goto out_dput;
+
+ /*
+ * Try to remove POSIX ACL xattrs from workdir. We are good if:
+ *
+ * a) success (there was a POSIX ACL xattr and was removed)
+ * b) -ENODATA (there was no POSIX ACL xattr)
+ * c) -EOPNOTSUPP (POSIX ACL xattrs are not supported)
+ *
+ * There are various other error values that could effectively
+ * mean that the xattr doesn't exist (e.g. -ERANGE is returned
+ * if the xattr name is too long), but the set of filesystems
+ * allowed as upper are limited to "normal" ones, where checking
+ * for the above two errors is sufficient.
+ */
+ err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+ if (err && err != -ENODATA && err != -EOPNOTSUPP)
+ goto out_dput;
+
+ err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+ if (err && err != -ENODATA && err != -EOPNOTSUPP)
+ goto out_dput;
+
+ /* Clear any inherited mode bits */
+ inode_lock(work->d_inode);
+ err = notify_change(work, &attr, NULL);
+ inode_unlock(work->d_inode);
+ if (err)
+ goto out_dput;
+ } else {
+ err = PTR_ERR(work);
+ goto out_err;
+ }
+out_unlock:
+ mnt_drop_write(mnt);
+ if (locked)
+ 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",
+ ufs->config.workdir, name, -err);
+ sb->s_flags |= MS_RDONLY;
+ work = NULL;
+ goto out_unlock;
+}
+
+static void ovl_unescape(char *s)
+{
+ char *d = s;
+
+ for (;; s++, d++) {
+ if (*s == '\\')
+ s++;
+ *d = *s;
+ if (!*s)
+ break;
+ }
+}
+
+static int ovl_mount_dir_noesc(const char *name, struct path *path)
+{
+ int err = -EINVAL;
+
+ if (!*name) {
+ pr_err("overlayfs: 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);
+ goto out;
+ }
+ err = -EINVAL;
+ if (ovl_dentry_weird(path->dentry)) {
+ pr_err("overlayfs: 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);
+ goto out_put;
+ }
+ return 0;
+
+out_put:
+ path_put(path);
+out:
+ return err;
+}
+
+static int ovl_mount_dir(const char *name, struct path *path)
+{
+ int err = -ENOMEM;
+ char *tmp = kstrdup(name, GFP_KERNEL);
+
+ if (tmp) {
+ 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(path);
+ err = -EINVAL;
+ }
+ kfree(tmp);
+ }
+ return err;
+}
+
+static int ovl_check_namelen(struct path *path, struct ovl_fs *ofs,
+ const char *name)
+{
+ struct kstatfs statfs;
+ int err = vfs_statfs(path, &statfs);
+
+ if (err)
+ pr_err("overlayfs: statfs failed on '%s'\n", name);
+ else
+ ofs->namelen = max(ofs->namelen, statfs.f_namelen);
+
+ return err;
+}
+
+static int ovl_lower_dir(const char *name, struct path *path,
+ struct ovl_fs *ofs, int *stack_depth, bool *remote)
+{
+ int err;
+
+ err = ovl_mount_dir_noesc(name, path);
+ if (err)
+ goto out;
+
+ err = ovl_check_namelen(path, ofs, name);
+ if (err)
+ goto out_put;
+
+ *stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
+
+ if (ovl_dentry_remote(path->dentry))
+ *remote = true;
+
+ /*
+ * The inodes index feature needs to encode and decode file
+ * handles, so it requires that all layers support them.
+ */
+ if (ofs->config.index && !ovl_can_decode_fh(path->dentry->d_sb)) {
+ ofs->config.index = false;
+ pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off.\n", name);
+ }
+
+ return 0;
+
+out_put:
+ path_put(path);
+out:
+ return err;
+}
+
+/* Workdir should not be subdir of upperdir and vice versa */
+static bool ovl_workdir_ok(struct dentry *workdir, struct dentry *upperdir)
+{
+ bool ok = false;
+
+ if (workdir != upperdir) {
+ ok = (lock_rename(workdir, upperdir) == NULL);
+ unlock_rename(workdir, upperdir);
+ }
+ return ok;
+}
+
+static unsigned int ovl_split_lowerdirs(char *str)
+{
+ unsigned int ctr = 1;
+ char *s, *d;
+
+ for (s = d = str;; s++, d++) {
+ if (*s == '\\') {
+ s++;
+ } else if (*s == ':') {
+ *d = '\0';
+ ctr++;
+ continue;
+ }
+ *d = *s;
+ if (!*s)
+ break;
+ }
+ return ctr;
+}
+
+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);
+}
+
+static int __maybe_unused
+ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ struct dentry *workdir = ovl_workdir(dentry);
+ struct inode *realinode = ovl_inode_real(inode);
+ struct posix_acl *acl = NULL;
+ int err;
+
+ /* Check that everything is OK before copy-up */
+ if (value) {
+ acl = posix_acl_from_xattr(&init_user_ns, value, size);
+ if (IS_ERR(acl))
+ return PTR_ERR(acl);
+ }
+ err = -EOPNOTSUPP;
+ if (!IS_POSIXACL(d_inode(workdir)))
+ goto out_acl_release;
+ if (!realinode->i_op->set_acl)
+ goto out_acl_release;
+ if (handler->flags == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode)) {
+ err = acl ? -EACCES : 0;
+ goto out_acl_release;
+ }
+ err = -EPERM;
+ if (!inode_owner_or_capable(inode))
+ goto out_acl_release;
+
+ posix_acl_release(acl);
+
+ /*
+ * Check if sgid bit needs to be cleared (actual setacl operation will
+ * be done with mounter's capabilities and so that won't do it for us).
+ */
+ if (unlikely(inode->i_mode & S_ISGID) &&
+ handler->flags == ACL_TYPE_ACCESS &&
+ !in_group_p(inode->i_gid) &&
+ !capable_wrt_inode_uidgid(inode, CAP_FSETID)) {
+ struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
+
+ err = ovl_setattr(dentry, &iattr);
+ if (err)
+ return err;
+ }
+
+ err = ovl_xattr_set(dentry, inode, handler->name, value, size, flags);
+ if (!err)
+ ovl_copyattr(ovl_inode_real(inode), inode);
+
+ return err;
+
+out_acl_release:
+ posix_acl_release(acl);
+ return err;
+}
+
+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)
+{
+ return -EOPNOTSUPP;
+}
+
+static int ovl_own_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ return -EOPNOTSUPP;
+}
+
+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);
+}
+
+static int ovl_other_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ return ovl_xattr_set(dentry, inode, name, value, size, flags);
+}
+
+static const struct xattr_handler __maybe_unused
+ovl_posix_acl_access_xattr_handler = {
+ .name = XATTR_NAME_POSIX_ACL_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
+ .get = ovl_posix_acl_xattr_get,
+ .set = ovl_posix_acl_xattr_set,
+};
+
+static const struct xattr_handler __maybe_unused
+ovl_posix_acl_default_xattr_handler = {
+ .name = XATTR_NAME_POSIX_ACL_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
+ .get = ovl_posix_acl_xattr_get,
+ .set = ovl_posix_acl_xattr_set,
+};
+
+static const struct xattr_handler ovl_own_xattr_handler = {
+ .prefix = OVL_XATTR_PREFIX,
+ .get = ovl_own_xattr_get,
+ .set = ovl_own_xattr_set,
+};
+
+static const struct xattr_handler ovl_other_xattr_handler = {
+ .prefix = "", /* catch all */
+ .get = ovl_other_xattr_get,
+ .set = ovl_other_xattr_set,
+};
+
+static const struct xattr_handler *ovl_xattr_handlers[] = {
+#ifdef CONFIG_FS_POSIX_ACL
+ &ovl_posix_acl_access_xattr_handler,
+ &ovl_posix_acl_default_xattr_handler,
+#endif
+ &ovl_own_xattr_handler,
+ &ovl_other_xattr_handler,
+ NULL
+};
+
+static int ovl_fill_super(struct super_block *sb, void *data, int silent)
+{
+ struct path upperpath = { };
+ struct path workpath = { };
+ struct dentry *root_dentry;
+ struct ovl_entry *oe;
+ struct ovl_fs *ufs;
+ struct path *stack = NULL;
+ char *lowertmp;
+ char *lower;
+ unsigned int numlower;
+ unsigned int stacklen = 0;
+ unsigned int i;
+ bool remote = false;
+ struct cred *cred;
+ int err;
+
+ err = -ENOMEM;
+ ufs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL);
+ if (!ufs)
+ goto out;
+
+ ufs->config.redirect_dir = ovl_redirect_dir_def;
+ ufs->config.index = ovl_index_def;
+ err = ovl_parse_opt((char *) data, &ufs->config);
+ if (err)
+ goto out_free_config;
+
+ err = -EINVAL;
+ if (!ufs->config.lowerdir) {
+ if (!silent)
+ pr_err("overlayfs: missing 'lowerdir'\n");
+ goto out_free_config;
+ }
+
+ sb->s_stack_depth = 0;
+ sb->s_maxbytes = MAX_LFS_FILESIZE;
+ if (ufs->config.upperdir) {
+ if (!ufs->config.workdir) {
+ pr_err("overlayfs: missing 'workdir'\n");
+ goto out_free_config;
+ }
+
+ err = ovl_mount_dir(ufs->config.upperdir, &upperpath);
+ if (err)
+ goto out_free_config;
+
+ /* 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");
+ err = -EINVAL;
+ goto out_put_upperpath;
+ }
+
+ err = ovl_check_namelen(&upperpath, ufs, ufs->config.upperdir);
+ if (err)
+ goto out_put_upperpath;
+
+ err = -EBUSY;
+ if (ovl_inuse_trylock(upperpath.dentry)) {
+ ufs->upperdir_locked = true;
+ } else if (ufs->config.index) {
+ pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n");
+ goto out_put_upperpath;
+ } else {
+ pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
+ }
+
+ err = ovl_mount_dir(ufs->config.workdir, &workpath);
+ if (err)
+ goto out_unlock_upperdentry;
+
+ err = -EINVAL;
+ if (upperpath.mnt != workpath.mnt) {
+ pr_err("overlayfs: workdir and upperdir must reside under the same mount\n");
+ goto out_put_workpath;
+ }
+ if (!ovl_workdir_ok(workpath.dentry, upperpath.dentry)) {
+ pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
+ goto out_put_workpath;
+ }
+
+ err = -EBUSY;
+ if (ovl_inuse_trylock(workpath.dentry)) {
+ ufs->workdir_locked = true;
+ } else if (ufs->config.index) {
+ pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n");
+ goto out_put_workpath;
+ } else {
+ pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
+ }
+
+ ufs->workbasedir = workpath.dentry;
+ sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth;
+ }
+ err = -ENOMEM;
+ lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL);
+ if (!lowertmp)
+ goto out_unlock_workdentry;
+
+ 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_free_lowertmp;
+ } else if (!ufs->config.upperdir && stacklen == 1) {
+ pr_err("overlayfs: at least 2 lowerdir are needed while upperdir nonexistent\n");
+ goto out_free_lowertmp;
+ }
+
+ err = -ENOMEM;
+ stack = kcalloc(stacklen, sizeof(struct path), GFP_KERNEL);
+ if (!stack)
+ goto out_free_lowertmp;
+
+ err = -EINVAL;
+ lower = lowertmp;
+ for (numlower = 0; numlower < stacklen; numlower++) {
+ err = ovl_lower_dir(lower, &stack[numlower], ufs,
+ &sb->s_stack_depth, &remote);
+ if (err)
+ goto out_put_lowerpath;
+
+ lower = strchr(lower, '\0') + 1;
+ }
+
+ err = -EINVAL;
+ sb->s_stack_depth++;
+ if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) {
+ pr_err("overlayfs: maximum fs stacking depth exceeded\n");
+ goto out_put_lowerpath;
+ }
+
+ if (ufs->config.upperdir) {
+ ufs->upper_mnt = clone_private_mount(&upperpath);
+ err = PTR_ERR(ufs->upper_mnt);
+ if (IS_ERR(ufs->upper_mnt)) {
+ pr_err("overlayfs: failed to clone upperpath\n");
+ goto out_put_lowerpath;
+ }
+
+ /* Don't inherit atime flags */
+ ufs->upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME);
+
+ sb->s_time_gran = ufs->upper_mnt->mnt_sb->s_time_gran;
+
+ ufs->workdir = ovl_workdir_create(sb, ufs, workpath.dentry,
+ OVL_WORKDIR_NAME, false);
+ /*
+ * Upper should support d_type, else whiteouts are visible.
+ * Given workdir and upper are on same fs, we can do
+ * iterate_dir() on workdir. This check requires successful
+ * creation of workdir in previous step.
+ */
+ if (ufs->workdir) {
+ struct dentry *temp;
+
+ err = ovl_check_d_type_supported(&workpath);
+ if (err < 0)
+ goto out_put_workdir;
+
+ /*
+ * 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");
+
+ /* Check if upper/work fs supports O_TMPFILE */
+ temp = ovl_do_tmpfile(ufs->workdir, S_IFREG | 0);
+ ufs->tmpfile = !IS_ERR(temp);
+ if (ufs->tmpfile)
+ dput(temp);
+ else
+ pr_warn("overlayfs: upper fs does not support tmpfile.\n");
+
+ /*
+ * Check if upper/work fs supports trusted.overlay.*
+ * xattr
+ */
+ err = ovl_do_setxattr(ufs->workdir, OVL_XATTR_OPAQUE,
+ "0", 1, 0);
+ if (err) {
+ ufs->noxattr = true;
+ pr_warn("overlayfs: upper fs does not support xattr.\n");
+ } else {
+ vfs_removexattr(ufs->workdir, OVL_XATTR_OPAQUE);
+ }
+
+ /* Check if upper/work fs supports file handles */
+ if (ufs->config.index &&
+ !ovl_can_decode_fh(ufs->workdir->d_sb)) {
+ ufs->config.index = false;
+ pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
+ }
+ }
+ }
+
+ err = -ENOMEM;
+ ufs->lower_mnt = kcalloc(numlower, sizeof(struct vfsmount *), GFP_KERNEL);
+ if (ufs->lower_mnt == NULL)
+ goto out_put_workdir;
+ for (i = 0; i < numlower; i++) {
+ struct vfsmount *mnt = clone_private_mount(&stack[i]);
+
+ err = PTR_ERR(mnt);
+ if (IS_ERR(mnt)) {
+ pr_err("overlayfs: failed to clone lowerpath\n");
+ goto out_put_lower_mnt;
+ }
+ /*
+ * Make lower_mnt R/O. That way fchmod/fchown on lower file
+ * will fail instead of modifying lower fs.
+ */
+ mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME;
+
+ ufs->lower_mnt[ufs->numlower] = mnt;
+ ufs->numlower++;
+
+ /* Check if all lower layers are on same sb */
+ if (i == 0)
+ ufs->same_sb = mnt->mnt_sb;
+ else if (ufs->same_sb != mnt->mnt_sb)
+ ufs->same_sb = NULL;
+ }
+
+ /* If the upper fs is nonexistent, we mark overlayfs r/o too */
+ if (!ufs->upper_mnt)
+ sb->s_flags |= MS_RDONLY;
+ else if (ufs->upper_mnt->mnt_sb != ufs->same_sb)
+ ufs->same_sb = NULL;
+
+ if (!(ovl_force_readonly(ufs)) && ufs->config.index) {
+ /* Verify lower root is upper root origin */
+ err = ovl_verify_origin(upperpath.dentry, ufs->lower_mnt[0],
+ stack[0].dentry, false, true);
+ if (err) {
+ pr_err("overlayfs: failed to verify upper root origin\n");
+ goto out_put_lower_mnt;
+ }
+
+ ufs->indexdir = ovl_workdir_create(sb, ufs, workpath.dentry,
+ OVL_INDEXDIR_NAME, true);
+ if (ufs->indexdir) {
+ /* Verify upper root is index dir origin */
+ err = ovl_verify_origin(ufs->indexdir, ufs->upper_mnt,
+ upperpath.dentry, true, true);
+ if (err)
+ pr_err("overlayfs: failed to verify index dir origin\n");
+
+ /* Cleanup bad/stale/orphan index entries */
+ if (!err)
+ err = ovl_indexdir_cleanup(ufs->indexdir,
+ ufs->upper_mnt,
+ stack, numlower);
+ }
+ if (err || !ufs->indexdir)
+ pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
+ if (err)
+ goto out_put_indexdir;
+ }
+
+ /* Show index=off/on in /proc/mounts for any of the reasons above */
+ if (!ufs->indexdir)
+ ufs->config.index = false;
+
+ if (remote)
+ sb->s_d_op = &ovl_reval_dentry_operations;
+ else
+ sb->s_d_op = &ovl_dentry_operations;
+
+ err = -ENOMEM;
+ ufs->creator_cred = cred = prepare_creds();
+ if (!cred)
+ goto out_put_indexdir;
+
+ /* Never override disk quota limits or use reserved space */
+ cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
+
+ err = -ENOMEM;
+ oe = ovl_alloc_entry(numlower);
+ if (!oe)
+ goto out_put_cred;
+
+ sb->s_magic = OVERLAYFS_SUPER_MAGIC;
+ sb->s_op = &ovl_super_operations;
+ sb->s_xattr = ovl_xattr_handlers;
+ sb->s_fs_info = ufs;
+ sb->s_flags |= MS_POSIXACL | MS_NOREMOTELOCK;
+
+ root_dentry = d_make_root(ovl_new_inode(sb, S_IFDIR, 0));
+ if (!root_dentry)
+ goto out_free_oe;
+
+ mntput(upperpath.mnt);
+ for (i = 0; i < numlower; i++)
+ mntput(stack[i].mnt);
+ mntput(workpath.mnt);
+ kfree(lowertmp);
+
+ if (upperpath.dentry) {
+ oe->has_upper = true;
+ if (ovl_is_impuredir(upperpath.dentry))
+ ovl_set_flag(OVL_IMPURE, d_inode(root_dentry));
+ }
+ for (i = 0; i < numlower; i++) {
+ oe->lowerstack[i].dentry = stack[i].dentry;
+ oe->lowerstack[i].mnt = ufs->lower_mnt[i];
+ }
+ kfree(stack);
+
+ root_dentry->d_fsdata = oe;
+
+ ovl_inode_init(d_inode(root_dentry), upperpath.dentry,
+ ovl_dentry_lower(root_dentry));
+
+ sb->s_root = root_dentry;
+
+ return 0;
+
+out_free_oe:
+ kfree(oe);
+out_put_cred:
+ put_cred(ufs->creator_cred);
+out_put_indexdir:
+ dput(ufs->indexdir);
+out_put_lower_mnt:
+ for (i = 0; i < ufs->numlower; i++)
+ mntput(ufs->lower_mnt[i]);
+ kfree(ufs->lower_mnt);
+out_put_workdir:
+ dput(ufs->workdir);
+ mntput(ufs->upper_mnt);
+out_put_lowerpath:
+ for (i = 0; i < numlower; i++)
+ path_put(&stack[i]);
+ kfree(stack);
+out_free_lowertmp:
+ kfree(lowertmp);
+out_unlock_workdentry:
+ if (ufs->workdir_locked)
+ ovl_inuse_unlock(workpath.dentry);
+out_put_workpath:
+ path_put(&workpath);
+out_unlock_upperdentry:
+ if (ufs->upperdir_locked)
+ ovl_inuse_unlock(upperpath.dentry);
+out_put_upperpath:
+ path_put(&upperpath);
+out_free_config:
+ kfree(ufs->config.lowerdir);
+ kfree(ufs->config.upperdir);
+ kfree(ufs->config.workdir);
+ kfree(ufs);
+out:
+ return err;
+}
+
+static struct dentry *ovl_mount(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *raw_data)
+{
+ return mount_nodev(fs_type, flags, raw_data, ovl_fill_super);
+}
+
+static struct file_system_type ovl_fs_type = {
+ .owner = THIS_MODULE,
+ .name = "overlay",
+ .mount = ovl_mount,
+ .kill_sb = kill_anon_super,
+};
+MODULE_ALIAS_FS("overlay");
+
+static void ovl_inode_init_once(void *foo)
+{
+ struct ovl_inode *oi = foo;
+
+ inode_init_once(&oi->vfs_inode);
+}
+
+static int __init ovl_init(void)
+{
+ int err;
+
+ ovl_inode_cachep = kmem_cache_create("ovl_inode",
+ sizeof(struct ovl_inode), 0,
+ (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+ ovl_inode_init_once);
+ if (ovl_inode_cachep == NULL)
+ return -ENOMEM;
+
+ err = register_filesystem(&ovl_fs_type);
+ if (err)
+ kmem_cache_destroy(ovl_inode_cachep);
+
+ return err;
+}
+
+static void __exit ovl_exit(void)
+{
+ unregister_filesystem(&ovl_fs_type);
+
+ /*
+ * Make sure all delayed rcu free inodes are flushed before we
+ * destroy cache.
+ */
+ rcu_barrier();
+ kmem_cache_destroy(ovl_inode_cachep);
+
+}
+
+module_init(ovl_init);
+module_exit(ovl_exit);
diff --git a/src/kernel/linux/v4.14/fs/overlayfs/util.c b/src/kernel/linux/v4.14/fs/overlayfs/util.c
new file mode 100644
index 0000000..afdc253
--- /dev/null
+++ b/src/kernel/linux/v4.14/fs/overlayfs/util.c
@@ -0,0 +1,582 @@
+/*
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, 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/mount.h>
+#include <linux/slab.h>
+#include <linux/cred.h>
+#include <linux/xattr.h>
+#include <linux/exportfs.h>
+#include <linux/uuid.h>
+#include <linux/namei.h>
+#include <linux/ratelimit.h>
+#include "overlayfs.h"
+#include "ovl_entry.h"
+
+int ovl_want_write(struct dentry *dentry)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ return mnt_want_write(ofs->upper_mnt);
+}
+
+void ovl_drop_write(struct dentry *dentry)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ mnt_drop_write(ofs->upper_mnt);
+}
+
+struct dentry *ovl_workdir(struct dentry *dentry)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+ return ofs->workdir;
+}
+
+const struct cred *ovl_override_creds(struct super_block *sb)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ return override_creds(ofs->creator_cred);
+}
+
+struct super_block *ovl_same_sb(struct super_block *sb)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ return ofs->same_sb;
+}
+
+bool ovl_can_decode_fh(struct super_block *sb)
+{
+ return (sb->s_export_op && sb->s_export_op->fh_to_dentry &&
+ !uuid_is_null(&sb->s_uuid));
+}
+
+struct dentry *ovl_indexdir(struct super_block *sb)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ return ofs->indexdir;
+}
+
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
+{
+ size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
+ struct ovl_entry *oe = kzalloc(size, GFP_KERNEL);
+
+ if (oe)
+ oe->numlower = numlower;
+
+ return oe;
+}
+
+bool ovl_dentry_remote(struct dentry *dentry)
+{
+ return dentry->d_flags &
+ (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE |
+ DCACHE_OP_REAL);
+}
+
+bool ovl_dentry_weird(struct dentry *dentry)
+{
+ return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
+ DCACHE_MANAGE_TRANSIT |
+ DCACHE_OP_HASH |
+ DCACHE_OP_COMPARE);
+}
+
+enum ovl_path_type ovl_path_type(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ enum ovl_path_type type = 0;
+
+ if (ovl_dentry_upper(dentry)) {
+ type = __OVL_PATH_UPPER;
+
+ /*
+ * Non-dir dentry can hold lower dentry of its copy up origin.
+ */
+ if (oe->numlower) {
+ type |= __OVL_PATH_ORIGIN;
+ if (d_is_dir(dentry))
+ type |= __OVL_PATH_MERGE;
+ }
+ } else {
+ if (oe->numlower > 1)
+ type |= __OVL_PATH_MERGE;
+ }
+ return type;
+}
+
+void ovl_path_upper(struct dentry *dentry, struct path *path)
+{
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+
+ path->mnt = ofs->upper_mnt;
+ path->dentry = ovl_dentry_upper(dentry);
+}
+
+void ovl_path_lower(struct dentry *dentry, struct path *path)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ *path = oe->numlower ? oe->lowerstack[0] : (struct path) { };
+}
+
+enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
+{
+ enum ovl_path_type type = ovl_path_type(dentry);
+
+ if (!OVL_TYPE_UPPER(type))
+ ovl_path_lower(dentry, path);
+ else
+ ovl_path_upper(dentry, path);
+
+ return type;
+}
+
+struct dentry *ovl_dentry_upper(struct dentry *dentry)
+{
+ return ovl_upperdentry_dereference(OVL_I(d_inode(dentry)));
+}
+
+struct dentry *ovl_dentry_lower(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ return oe->numlower ? oe->lowerstack[0].dentry : NULL;
+}
+
+struct dentry *ovl_dentry_real(struct dentry *dentry)
+{
+ return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);
+}
+
+struct dentry *ovl_i_dentry_upper(struct inode *inode)
+{
+ return ovl_upperdentry_dereference(OVL_I(inode));
+}
+
+struct inode *ovl_inode_upper(struct inode *inode)
+{
+ struct dentry *upperdentry = ovl_i_dentry_upper(inode);
+
+ return upperdentry ? d_inode(upperdentry) : NULL;
+}
+
+struct inode *ovl_inode_lower(struct inode *inode)
+{
+ return OVL_I(inode)->lower;
+}
+
+struct inode *ovl_inode_real(struct inode *inode)
+{
+ return ovl_inode_upper(inode) ?: ovl_inode_lower(inode);
+}
+
+
+struct ovl_dir_cache *ovl_dir_cache(struct inode *inode)
+{
+ return OVL_I(inode)->cache;
+}
+
+void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache)
+{
+ OVL_I(inode)->cache = cache;
+}
+
+bool ovl_dentry_is_opaque(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ return oe->opaque;
+}
+
+bool ovl_dentry_is_whiteout(struct dentry *dentry)
+{
+ return !dentry->d_inode && ovl_dentry_is_opaque(dentry);
+}
+
+void ovl_dentry_set_opaque(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ oe->opaque = true;
+}
+
+/*
+ * For hard links it's possible for ovl_dentry_upper() to return positive, while
+ * there's no actual upper alias for the inode. Copy up code needs to know
+ * about the existence of the upper alias, so it can't use ovl_dentry_upper().
+ */
+bool ovl_dentry_has_upper_alias(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ return oe->has_upper;
+}
+
+void ovl_dentry_set_upper_alias(struct dentry *dentry)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+
+ oe->has_upper = true;
+}
+
+bool ovl_redirect_dir(struct super_block *sb)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ return ofs->config.redirect_dir && !ofs->noxattr;
+}
+
+const char *ovl_dentry_get_redirect(struct dentry *dentry)
+{
+ return OVL_I(d_inode(dentry))->redirect;
+}
+
+void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect)
+{
+ struct ovl_inode *oi = OVL_I(d_inode(dentry));
+
+ kfree(oi->redirect);
+ oi->redirect = redirect;
+}
+
+void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
+ struct dentry *lowerdentry)
+{
+ if (upperdentry)
+ OVL_I(inode)->__upperdentry = upperdentry;
+ if (lowerdentry)
+ OVL_I(inode)->lower = igrab(d_inode(lowerdentry));
+
+ ovl_copyattr(d_inode(upperdentry ?: lowerdentry), inode);
+}
+
+void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
+{
+ struct inode *upperinode = d_inode(upperdentry);
+
+ WARN_ON(OVL_I(inode)->__upperdentry);
+
+ /*
+ * Make sure upperdentry is consistent before making it visible
+ */
+ smp_wmb();
+ OVL_I(inode)->__upperdentry = upperdentry;
+ if (inode_unhashed(inode)) {
+ inode->i_private = upperinode;
+ __insert_inode_hash(inode, (unsigned long) upperinode);
+ }
+}
+
+void ovl_dentry_version_inc(struct dentry *dentry, bool impurity)
+{
+ struct inode *inode = d_inode(dentry);
+
+ WARN_ON(!inode_is_locked(inode));
+ /*
+ * Version is used by readdir code to keep cache consistent. For merge
+ * dirs all changes need to be noted. For non-merge dirs, cache only
+ * contains impure (ones which have been copied up and have origins)
+ * entries, so only need to note changes to impure entries.
+ */
+ if (OVL_TYPE_MERGE(ovl_path_type(dentry)) || impurity)
+ OVL_I(inode)->version++;
+}
+
+u64 ovl_dentry_version_get(struct dentry *dentry)
+{
+ struct inode *inode = d_inode(dentry);
+
+ WARN_ON(!inode_is_locked(inode));
+ return OVL_I(inode)->version;
+}
+
+bool ovl_is_whiteout(struct dentry *dentry)
+{
+ struct inode *inode = dentry->d_inode;
+
+ return inode && IS_WHITEOUT(inode);
+}
+
+struct file *ovl_path_open(struct path *path, int flags)
+{
+ return dentry_open(path, flags | O_NOATIME, current_cred());
+}
+
+int ovl_copy_up_start(struct dentry *dentry)
+{
+ struct ovl_inode *oi = OVL_I(d_inode(dentry));
+ int err;
+
+ err = mutex_lock_interruptible(&oi->lock);
+ if (!err && ovl_dentry_has_upper_alias(dentry)) {
+ err = 1; /* Already copied up */
+ mutex_unlock(&oi->lock);
+ }
+
+ return err;
+}
+
+void ovl_copy_up_end(struct dentry *dentry)
+{
+ mutex_unlock(&OVL_I(d_inode(dentry))->lock);
+}
+
+bool ovl_check_dir_xattr(struct dentry *dentry, const char *name)
+{
+ int res;
+ char val;
+
+ if (!d_is_dir(dentry))
+ return false;
+
+ res = vfs_getxattr(dentry, name, &val, 1);
+ if (res == 1 && val == 'y')
+ return true;
+
+ return false;
+}
+
+int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+ const char *name, const void *value, size_t size,
+ int xerr)
+{
+ int err;
+ struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+
+ if (ofs->noxattr)
+ return xerr;
+
+ err = ovl_do_setxattr(upperdentry, name, value, size, 0);
+
+ if (err == -EOPNOTSUPP) {
+ pr_warn("overlayfs: cannot set %s xattr on upper\n", name);
+ ofs->noxattr = true;
+ return xerr;
+ }
+
+ return err;
+}
+
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
+{
+ int err;
+
+ if (ovl_test_flag(OVL_IMPURE, d_inode(dentry)))
+ return 0;
+
+ /*
+ * Do not fail when upper doesn't support xattrs.
+ * Upper inodes won't have origin nor redirect xattr anyway.
+ */
+ err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE,
+ "y", 1, 0);
+ if (!err)
+ ovl_set_flag(OVL_IMPURE, d_inode(dentry));
+
+ return err;
+}
+
+void ovl_set_flag(unsigned long flag, struct inode *inode)
+{
+ set_bit(flag, &OVL_I(inode)->flags);
+}
+
+void ovl_clear_flag(unsigned long flag, struct inode *inode)
+{
+ clear_bit(flag, &OVL_I(inode)->flags);
+}
+
+bool ovl_test_flag(unsigned long flag, struct inode *inode)
+{
+ return test_bit(flag, &OVL_I(inode)->flags);
+}
+
+/**
+ * Caller must hold a reference to inode to prevent it from being freed while
+ * it is marked inuse.
+ */
+bool ovl_inuse_trylock(struct dentry *dentry)
+{
+ struct inode *inode = d_inode(dentry);
+ bool locked = false;
+
+ spin_lock(&inode->i_lock);
+ if (!(inode->i_state & I_OVL_INUSE)) {
+ inode->i_state |= I_OVL_INUSE;
+ locked = true;
+ }
+ spin_unlock(&inode->i_lock);
+
+ return locked;
+}
+
+void ovl_inuse_unlock(struct dentry *dentry)
+{
+ if (dentry) {
+ struct inode *inode = d_inode(dentry);
+
+ spin_lock(&inode->i_lock);
+ WARN_ON(!(inode->i_state & I_OVL_INUSE));
+ inode->i_state &= ~I_OVL_INUSE;
+ spin_unlock(&inode->i_lock);
+ }
+}
+
+/* Caller must hold OVL_I(inode)->lock */
+static void ovl_cleanup_index(struct dentry *dentry)
+{
+ struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode;
+ struct dentry *lowerdentry = ovl_dentry_lower(dentry);
+ struct dentry *upperdentry = ovl_dentry_upper(dentry);
+ struct dentry *index = NULL;
+ struct inode *inode;
+ struct qstr name = { };
+ int err;
+
+ err = ovl_get_index_name(lowerdentry, &name);
+ if (err)
+ goto fail;
+
+ inode = d_inode(upperdentry);
+ if (inode->i_nlink != 1) {
+ pr_warn_ratelimited("overlayfs: cleanup linked index (%pd2, ino=%lu, nlink=%u)\n",
+ upperdentry, inode->i_ino, inode->i_nlink);
+ /*
+ * We either have a bug with persistent union nlink or a lower
+ * hardlink was added while overlay is mounted. Adding a lower
+ * hardlink and then unlinking all overlay hardlinks would drop
+ * overlay nlink to zero before all upper inodes are unlinked.
+ * As a safety measure, when that situation is detected, set
+ * the overlay nlink to the index inode nlink minus one for the
+ * index entry itself.
+ */
+ set_nlink(d_inode(dentry), inode->i_nlink - 1);
+ ovl_set_nlink_upper(dentry);
+ goto out;
+ }
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ /* TODO: whiteout instead of cleanup to block future open by handle */
+ index = lookup_one_len(name.name, ovl_indexdir(dentry->d_sb), name.len);
+ err = PTR_ERR(index);
+ if (!IS_ERR(index))
+ err = ovl_cleanup(dir, index);
+ else
+ index = NULL;
+
+ inode_unlock(dir);
+ if (err)
+ goto fail;
+
+out:
+ kfree(name.name);
+ dput(index);
+ return;
+
+fail:
+ pr_err("overlayfs: cleanup index of '%pd2' failed (%i)\n", dentry, err);
+ goto out;
+}
+
+/*
+ * Operations that change overlay inode and upper inode nlink need to be
+ * synchronized with copy up for persistent nlink accounting.
+ */
+int ovl_nlink_start(struct dentry *dentry, bool *locked)
+{
+ struct ovl_inode *oi = OVL_I(d_inode(dentry));
+ const struct cred *old_cred;
+ int err;
+
+ if (!d_inode(dentry) || d_is_dir(dentry))
+ return 0;
+
+ /*
+ * With inodes index is enabled, we store the union overlay nlink
+ * in an xattr on the index inode. When whiting out lower hardlinks
+ * we need to decrement the overlay persistent nlink, but before the
+ * first copy up, we have no upper index inode to store the xattr.
+ *
+ * As a workaround, before whiteout/rename over of a lower hardlink,
+ * copy up to create the upper index. Creating the upper index will
+ * initialize the overlay nlink, so it could be dropped if unlink
+ * or rename succeeds.
+ *
+ * TODO: implement metadata only index copy up when called with
+ * ovl_copy_up_flags(dentry, O_PATH).
+ */
+ if (ovl_indexdir(dentry->d_sb) && !ovl_dentry_has_upper_alias(dentry) &&
+ d_inode(ovl_dentry_lower(dentry))->i_nlink > 1) {
+ err = ovl_copy_up(dentry);
+ if (err)
+ return err;
+ }
+
+ err = mutex_lock_interruptible(&oi->lock);
+ if (err)
+ return err;
+
+ if (!ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+ goto out;
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ /*
+ * The overlay inode nlink should be incremented/decremented IFF the
+ * upper operation succeeds, along with nlink change of upper inode.
+ * Therefore, before link/unlink/rename, we store the union nlink
+ * value relative to the upper inode nlink in an upper inode xattr.
+ */
+ err = ovl_set_nlink_upper(dentry);
+ revert_creds(old_cred);
+
+out:
+ if (err)
+ mutex_unlock(&oi->lock);
+ else
+ *locked = true;
+
+ return err;
+}
+
+void ovl_nlink_end(struct dentry *dentry, bool locked)
+{
+ if (locked) {
+ if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) &&
+ d_inode(dentry)->i_nlink == 0) {
+ const struct cred *old_cred;
+
+ old_cred = ovl_override_creds(dentry->d_sb);
+ ovl_cleanup_index(dentry);
+ revert_creds(old_cred);
+ }
+
+ mutex_unlock(&OVL_I(d_inode(dentry))->lock);
+ }
+}
+
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
+{
+ /* Workdir should not be the same as upperdir */
+ if (workdir == upperdir)
+ goto err;
+
+ /* Workdir should not be subdir of upperdir and vice versa */
+ if (lock_rename(workdir, upperdir) != NULL)
+ goto err_unlock;
+
+ return 0;
+
+err_unlock:
+ unlock_rename(workdir, upperdir);
+err:
+ pr_err("overlayfs: failed to lock workdir+upperdir\n");
+ return -EIO;
+}