Resguardo inicial

linux-7.2.3/fs/overlayfs/Kconfig

@@ -0,0 +1,136 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config OVERLAY_FS
+	tristate "Overlay filesystem support"
+	select FS_STACK
+	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.rst
+
+config OVERLAY_FS_REDIRECT_DIR
+	bool "Overlayfs: turn on redirect directory 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.
+
+	  If unsure, say N.
+
+config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW
+	bool "Overlayfs: follow redirects even if redirects are turned off"
+	default y
+	depends on OVERLAY_FS
+	help
+	  Disable this to get a possibly more secure configuration, but that
+	  might not be backward compatible with previous kernels.
+
+	  If backward compatibility is not an issue, then it is safe and
+	  recommended to say N here.
+
+	  For more information, see Documentation/filesystems/overlayfs.rst
+
+	  If unsure, say Y.
+
+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 index directory 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 not backward compatible.
+	  That is, mounting an overlay which has an inodes index on a kernel
+	  that doesn't support this feature will have unexpected results.
+
+	  If unsure, say N.
+
+config OVERLAY_FS_NFS_EXPORT
+	bool "Overlayfs: turn on NFS export feature by default"
+	depends on OVERLAY_FS
+	depends on OVERLAY_FS_INDEX
+	depends on !OVERLAY_FS_METACOPY
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  the index directory to decode overlay NFS file handles by default.
+	  In this case, it is still possible to turn off NFS export support
+	  globally with the "nfs_export=off" module option or on a filesystem
+	  instance basis with the "nfs_export=off" mount option.
+
+	  The NFS export feature creates an index on copy up of every file and
+	  directory.  This full index is used to detect overlay filesystems
+	  inconsistencies on lookup, like redirect from multiple upper dirs to
+	  the same lower dir.  The full index may incur some overhead on mount
+	  time, especially when verifying that directory file handles are not
+	  stale.
+
+	  Note, that the NFS export feature is not backward compatible.
+	  That is, mounting an overlay which has a full index on a kernel
+	  that doesn't support this feature will have unexpected results.
+
+	  Most users should say N here and enable this feature on a case-by-
+	  case basis with the "nfs_export=on" mount option.
+
+	  Say N unless you fully understand the consequences.
+
+config OVERLAY_FS_XINO_AUTO
+	bool "Overlayfs: auto enable inode number mapping"
+	default n
+	depends on OVERLAY_FS
+	depends on 64BIT
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  unused high bits in underlying filesystem inode numbers to map all
+	  inodes to a unified address space.  The mapped 64bit inode numbers
+	  might not be compatible with applications that expect 32bit inodes.
+
+	  If compatibility with applications that expect 32bit inodes is not an
+	  issue, then it is safe and recommended to say Y here.
+
+	  For more information, see Documentation/filesystems/overlayfs.rst
+
+	  If unsure, say N.
+
+config OVERLAY_FS_METACOPY
+	bool "Overlayfs: turn on metadata only copy up feature by default"
+	depends on OVERLAY_FS
+	select OVERLAY_FS_REDIRECT_DIR
+	help
+	  If this config option is enabled then overlay filesystems will
+	  copy up only metadata where appropriate and data copy up will
+	  happen when a file is opened for WRITE operation. It is still
+	  possible to turn off this feature globally with the "metacopy=off"
+	  module option or on a filesystem instance basis with the
+	  "metacopy=off" mount option.
+
+	  Note, that this feature is not backward compatible.  That is,
+	  mounting an overlay which has metacopy only inodes on a kernel
+	  that doesn't support this feature will have unexpected results.
+
+	  If unsure, say N.
+
+config OVERLAY_FS_DEBUG
+	bool "Overlayfs: turn on extra debugging checks"
+	default n
+	depends on OVERLAY_FS
+	help
+	  Say Y here to enable extra debugging checks in overlayfs.
+
+	  If unsure, say N.

linux-7.2.3/fs/overlayfs/Makefile

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the overlay filesystem.
+#
+
+obj-$(CONFIG_OVERLAY_FS) += overlay.o
+
+overlay-objs := super.o namei.o util.o inode.o file.o dir.o readdir.o \
+		copy_up.o export.o params.o xattrs.o

linux-7.2.3/fs/overlayfs/export.c

@@ -0,0 +1,868 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Overlayfs NFS export support.
+ *
+ * Amir Goldstein <amir73il@gmail.com>
+ *
+ * Copyright (C) 2017-2018 CTERA Networks. All Rights Reserved.
+ */
+
+#include <linux/fs.h>
+#include <linux/cred.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/xattr.h>
+#include <linux/exportfs.h>
+#include <linux/ratelimit.h>
+#include "overlayfs.h"
+
+static int ovl_encode_maybe_copy_up(struct dentry *dentry)
+{
+	int err;
+
+	if (ovl_dentry_upper(dentry))
+		return 0;
+
+	err = ovl_copy_up(dentry);
+	if (err) {
+		pr_warn_ratelimited("failed to copy up on encode (%pd2, err=%i)\n",
+				    dentry, err);
+	}
+
+	return err;
+}
+
+/*
+ * Before encoding a non-upper directory file handle from real layer N, we need
+ * to check if it will be possible to reconnect an overlay dentry from the real
+ * lower decoded dentry. This is done by following the overlay ancestry up to a
+ * "layer N connected" ancestor and verifying that all parents along the way are
+ * "layer N connectable". If an ancestor that is NOT "layer N connectable" is
+ * found, we need to copy up an ancestor, which is "layer N connectable", thus
+ * making that ancestor "layer N connected". For example:
+ *
+ * layer 1: /a
+ * layer 2: /a/b/c
+ *
+ * The overlay dentry /a is NOT "layer 2 connectable", because if dir /a is
+ * copied up and renamed, upper dir /a will be indexed by lower dir /a from
+ * layer 1. The dir /a from layer 2 will never be indexed, so the algorithm (*)
+ * in ovl_lookup_real_ancestor() will not be able to lookup a connected overlay
+ * dentry from the connected lower dentry /a/b/c.
+ *
+ * To avoid this problem on decode time, we need to copy up an ancestor of
+ * /a/b/c, which is "layer 2 connectable", on encode time. That ancestor is
+ * /a/b. After copy up (and index) of /a/b, it will become "layer 2 connected"
+ * and when the time comes to decode the file handle from lower dentry /a/b/c,
+ * ovl_lookup_real_ancestor() will find the indexed ancestor /a/b and decoding
+ * a connected overlay dentry will be accomplished.
+ *
+ * (*) the algorithm in ovl_lookup_real_ancestor() can be improved to lookup an
+ * entry /a in the lower layers above layer N and find the indexed dir /a from
+ * layer 1. If that improvement is made, then the check for "layer N connected"
+ * will need to verify there are no redirects in lower layers above N. In the
+ * example above, /a will be "layer 2 connectable". However, if layer 2 dir /a
+ * is a target of a layer 1 redirect, then /a will NOT be "layer 2 connectable":
+ *
+ * layer 1: /A (redirect = /a)
+ * layer 2: /a/b/c
+ */
+
+/* Return the lowest layer for encoding a connectable file handle */
+static int ovl_connectable_layer(struct dentry *dentry)
+{
+	struct ovl_entry *oe = OVL_E(dentry);
+
+	/* We can get overlay root from root of any layer */
+	if (dentry == dentry->d_sb->s_root)
+		return ovl_numlower(oe);
+
+	/*
+	 * If it's an unindexed merge dir, then it's not connectable with any
+	 * lower layer
+	 */
+	if (ovl_dentry_upper(dentry) &&
+	    !ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+		return 0;
+
+	/* We can get upper/overlay path from indexed/lower dentry */
+	return ovl_lowerstack(oe)->layer->idx;
+}
+
+/*
+ * @dentry is "connected" if all ancestors up to root or a "connected" ancestor
+ * have the same uppermost lower layer as the origin's layer. We may need to
+ * copy up a "connectable" ancestor to make it "connected". A "connected" dentry
+ * cannot become non "connected", so cache positive result in dentry flags.
+ *
+ * Return the connected origin layer or < 0 on error.
+ */
+static int ovl_connect_layer(struct dentry *dentry)
+{
+	struct dentry *next, *parent = NULL;
+	struct ovl_entry *oe = OVL_E(dentry);
+	int origin_layer;
+	int err = 0;
+
+	if (WARN_ON(dentry == dentry->d_sb->s_root) ||
+	    WARN_ON(!ovl_dentry_lower(dentry)))
+		return -EIO;
+
+	origin_layer = ovl_lowerstack(oe)->layer->idx;
+	if (ovl_dentry_test_flag(OVL_E_CONNECTED, dentry))
+		return origin_layer;
+
+	/* Find the topmost origin layer connectable ancestor of @dentry */
+	next = dget(dentry);
+	for (;;) {
+		parent = dget_parent(next);
+		if (WARN_ON(parent == next)) {
+			err = -EIO;
+			break;
+		}
+
+		/*
+		 * If @parent is not origin layer connectable, then copy up
+		 * @next which is origin layer connectable and we are done.
+		 */
+		if (ovl_connectable_layer(parent) < origin_layer) {
+			err = ovl_encode_maybe_copy_up(next);
+			break;
+		}
+
+		/* If @parent is connected or indexed we are done */
+		if (ovl_dentry_test_flag(OVL_E_CONNECTED, parent) ||
+		    ovl_test_flag(OVL_INDEX, d_inode(parent)))
+			break;
+
+		dput(next);
+		next = parent;
+	}
+
+	dput(parent);
+	dput(next);
+
+	if (!err)
+		ovl_dentry_set_flag(OVL_E_CONNECTED, dentry);
+
+	return err ?: origin_layer;
+}
+
+/*
+ * We only need to encode origin if there is a chance that the same object was
+ * encoded pre copy up and then we need to stay consistent with the same
+ * encoding also after copy up. If non-pure upper is not indexed, then it was
+ * copied up before NFS export was enabled. In that case we don't need to worry
+ * about staying consistent with pre copy up encoding and we encode an upper
+ * file handle. Overlay root dentry is a private case of non-indexed upper.
+ *
+ * The following table summarizes the different file handle encodings used for
+ * different overlay object types:
+ *
+ *  Object type		| Encoding
+ * --------------------------------
+ *  Pure upper		| U
+ *  Non-indexed upper	| U
+ *  Indexed upper	| L (*)
+ *  Non-upper		| L (*)
+ *
+ * U = upper file handle
+ * L = lower file handle
+ *
+ * (*) Decoding a connected overlay dir from real lower dentry is not always
+ * possible when there are redirects in lower layers and non-indexed merge dirs.
+ * To mitigate those case, we may copy up the lower dir ancestor before encode
+ * of a decodable file handle for non-upper dir.
+ *
+ * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error.
+ */
+static int ovl_check_encode_origin(struct inode *inode)
+{
+	struct ovl_fs *ofs = OVL_FS(inode->i_sb);
+	bool decodable = ofs->config.nfs_export;
+	struct dentry *dentry;
+	int err;
+
+	/* No upper layer? */
+	if (!ovl_upper_mnt(ofs))
+		return 1;
+
+	/* Lower file handle for non-upper non-decodable */
+	if (!ovl_inode_upper(inode) && !decodable)
+		return 1;
+
+	/* Upper file handle for pure upper */
+	if (!ovl_inode_lower(inode))
+		return 0;
+
+	/*
+	 * Root is never indexed, so if there's an upper layer, encode upper for
+	 * root.
+	 */
+	if (inode == d_inode(inode->i_sb->s_root))
+		return 0;
+
+	/*
+	 * Upper decodable file handle for non-indexed upper.
+	 */
+	if (ovl_inode_upper(inode) && decodable &&
+	    !ovl_test_flag(OVL_INDEX, inode))
+		return 0;
+
+	/*
+	 * Decoding a merge dir, whose origin's ancestor is under a redirected
+	 * lower dir or under a non-indexed upper is not always possible.
+	 * ovl_connect_layer() will try to make origin's layer "connected" by
+	 * copying up a "connectable" ancestor.
+	 */
+	if (!decodable || !S_ISDIR(inode->i_mode))
+		return 1;
+
+	dentry = d_find_any_alias(inode);
+	if (!dentry)
+		return -ENOENT;
+
+	err = ovl_connect_layer(dentry);
+	dput(dentry);
+	if (err < 0)
+		return err;
+
+	/* Lower file handle for indexed and non-upper dir/non-dir */
+	return 1;
+}
+
+static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode,
+			     u32 *fid, int buflen)
+{
+	struct ovl_fh *fh = NULL;
+	int err, enc_lower;
+	int len;
+
+	/*
+	 * Check if we should encode a lower or upper file handle and maybe
+	 * copy up an ancestor to make lower file handle connectable.
+	 */
+	err = enc_lower = ovl_check_encode_origin(inode);
+	if (enc_lower < 0)
+		goto fail;
+
+	/* Encode an upper or lower file handle */
+	fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) :
+				ovl_inode_upper(inode), !enc_lower);
+	if (IS_ERR(fh))
+		return PTR_ERR(fh);
+
+	len = OVL_FH_LEN(fh);
+	if (len <= buflen)
+		memcpy(fid, fh, len);
+	err = len;
+
+out:
+	kfree(fh);
+	return err;
+
+fail:
+	pr_warn_ratelimited("failed to encode file handle (ino=%llu, err=%i)\n",
+			    inode->i_ino, err);
+	goto out;
+}
+
+static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len,
+			 struct inode *parent)
+{
+	struct ovl_fs *ofs = OVL_FS(inode->i_sb);
+	int bytes, buflen = *max_len << 2;
+
+	/* TODO: encode connectable file handles */
+	if (parent)
+		return FILEID_INVALID;
+
+	bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen);
+	if (bytes <= 0)
+		return FILEID_INVALID;
+
+	*max_len = bytes >> 2;
+	if (bytes > buflen)
+		return FILEID_INVALID;
+
+	return OVL_FILEID_V1;
+}
+
+/*
+ * Find or instantiate an overlay dentry from real dentries and index.
+ */
+static struct dentry *ovl_obtain_alias(struct super_block *sb,
+				       struct dentry *upper_alias,
+				       struct ovl_path *lowerpath,
+				       struct dentry *index)
+{
+	struct dentry *lower = lowerpath ? lowerpath->dentry : NULL;
+	struct dentry *upper = upper_alias ?: index;
+	struct inode *inode = NULL;
+	struct ovl_entry *oe;
+	struct ovl_inode_params oip = {
+		.index = index,
+	};
+
+	/* We get overlay directory dentries with ovl_lookup_real() */
+	if (d_is_dir(upper ?: lower))
+		return ERR_PTR(-EIO);
+
+	oe = ovl_alloc_entry(!!lower);
+	if (!oe)
+		return ERR_PTR(-ENOMEM);
+
+	oip.upperdentry = dget(upper);
+	if (lower) {
+		ovl_lowerstack(oe)->dentry = dget(lower);
+		ovl_lowerstack(oe)->layer = lowerpath->layer;
+	}
+	oip.oe = oe;
+	inode = ovl_get_inode(sb, &oip);
+	if (IS_ERR(inode)) {
+		ovl_free_entry(oe);
+		dput(upper);
+		return ERR_CAST(inode);
+	}
+
+	if (upper)
+		ovl_set_flag(OVL_UPPERDATA, inode);
+
+	return d_obtain_alias(inode);
+}
+
+/* Get the upper or lower dentry in stack whose on layer @idx */
+static struct dentry *ovl_dentry_real_at(struct dentry *dentry, int idx)
+{
+	struct ovl_entry *oe = OVL_E(dentry);
+	struct ovl_path *lowerstack = ovl_lowerstack(oe);
+	int i;
+
+	if (!idx)
+		return ovl_dentry_upper(dentry);
+
+	for (i = 0; i < ovl_numlower(oe); i++) {
+		if (lowerstack[i].layer->idx == idx)
+			return lowerstack[i].dentry;
+	}
+
+	return NULL;
+}
+
+/**
+ * ovl_lookup_real_one -  Lookup a child overlay dentry to get an overlay dentry whose real dentry is given
+ * @connected: parent overlay dentry
+ * @real: given child real dentry
+ * @layer: layer in which @real exists
+ *
+ *
+ * Lookup a child overlay dentry in @connected with the same name as the @real
+ * dentry.  Then check that the parent of the result is the real dentry for
+ * @connected, and @real is the real dentry for the result.
+ *
+ * Returns:
+ *   %-ECHILD if the parent of @real is no longer the real dentry for @connected.
+ *   %-ESTALE if @real is not the real dentry of the found dentry.
+ *   Otherwise the found dentry is returned.
+ */
+static struct dentry *ovl_lookup_real_one(struct dentry *connected,
+					  struct dentry *real,
+					  const struct ovl_layer *layer)
+{
+	struct dentry *this;
+	struct name_snapshot name;
+	int err;
+
+	/*
+	 * We need to take a snapshot of real dentry name to protect us
+	 * from racing with underlying layer rename. In this case, we don't
+	 * care about returning ESTALE, only from dereferencing a free name
+	 * pointer because we hold no lock on the real dentry.
+	 */
+	take_dentry_name_snapshot(&name, real);
+	this = lookup_noperm_unlocked(&name.name, connected);
+	release_dentry_name_snapshot(&name);
+
+	err = -ECHILD;
+	if (ovl_dentry_real_at(connected, layer->idx) != real->d_parent)
+		goto fail;
+
+	err = PTR_ERR(this);
+	if (IS_ERR(this))
+		goto fail;
+
+	err = -ENOENT;
+	if (!this || !this->d_inode)
+		goto fail;
+
+	err = -ESTALE;
+	if (ovl_dentry_real_at(this, layer->idx) != real)
+		goto fail;
+
+	return this;
+
+fail:
+	pr_warn_ratelimited("failed to lookup one by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
+			    real, layer->idx, connected, err);
+	if (!IS_ERR(this))
+		dput(this);
+	return ERR_PTR(err);
+}
+
+static struct dentry *ovl_lookup_real(struct super_block *sb,
+				      struct dentry *real,
+				      const struct ovl_layer *layer);
+
+/*
+ * Lookup an indexed or hashed overlay dentry by real inode.
+ */
+static struct dentry *ovl_lookup_real_inode(struct super_block *sb,
+					    struct dentry *real,
+					    const struct ovl_layer *layer)
+{
+	struct ovl_fs *ofs = OVL_FS(sb);
+	struct dentry *index = NULL;
+	struct dentry *this = NULL;
+	struct inode *inode;
+
+	/*
+	 * Decoding upper dir from index is expensive, so first try to lookup
+	 * overlay dentry in inode/dcache.
+	 */
+	inode = ovl_lookup_inode(sb, real, !layer->idx);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	if (inode) {
+		this = d_find_any_alias(inode);
+		iput(inode);
+	}
+
+	/*
+	 * For decoded lower dir file handle, lookup index by origin to check
+	 * if lower dir was copied up and and/or removed.
+	 */
+	if (!this && layer->idx && ovl_indexdir(sb) && !WARN_ON(!d_is_dir(real))) {
+		index = ovl_lookup_index(ofs, NULL, real, false);
+		if (IS_ERR(index))
+			return index;
+	}
+
+	/* Get connected upper overlay dir from index */
+	if (index) {
+		struct dentry *upper = ovl_index_upper(ofs, index, true);
+
+		dput(index);
+		if (IS_ERR_OR_NULL(upper))
+			return upper;
+
+		/*
+		 * ovl_lookup_real() in lower layer may call recursively once to
+		 * ovl_lookup_real() in upper layer. The first level call walks
+		 * back lower parents to the topmost indexed parent. The second
+		 * recursive call walks back from indexed upper to the topmost
+		 * connected/hashed upper parent (or up to root).
+		 */
+		this = ovl_lookup_real(sb, upper, &ofs->layers[0]);
+		dput(upper);
+	}
+
+	if (IS_ERR_OR_NULL(this))
+		return this;
+
+	if (ovl_dentry_real_at(this, layer->idx) != real) {
+		dput(this);
+		this = ERR_PTR(-EIO);
+	}
+
+	return this;
+}
+
+/*
+ * Lookup an indexed or hashed overlay dentry, whose real dentry is an
+ * ancestor of @real.
+ */
+static struct dentry *ovl_lookup_real_ancestor(struct super_block *sb,
+					       struct dentry *real,
+					       const struct ovl_layer *layer)
+{
+	struct dentry *next, *parent = NULL;
+	struct dentry *ancestor = ERR_PTR(-EIO);
+
+	if (real == layer->mnt->mnt_root)
+		return dget(sb->s_root);
+
+	/* Find the topmost indexed or hashed ancestor */
+	next = dget(real);
+	for (;;) {
+		parent = dget_parent(next);
+
+		/*
+		 * Lookup a matching overlay dentry in inode/dentry
+		 * cache or in index by real inode.
+		 */
+		ancestor = ovl_lookup_real_inode(sb, next, layer);
+		if (ancestor)
+			break;
+
+		if (parent == layer->mnt->mnt_root) {
+			ancestor = dget(sb->s_root);
+			break;
+		}
+
+		/*
+		 * If @real has been moved out of the layer root directory,
+		 * we will eventully hit the real fs root. This cannot happen
+		 * by legit overlay rename, so we return error in that case.
+		 */
+		if (parent == next) {
+			ancestor = ERR_PTR(-EXDEV);
+			break;
+		}
+
+		dput(next);
+		next = parent;
+	}
+
+	dput(parent);
+	dput(next);
+
+	return ancestor;
+}
+
+/*
+ * Lookup a connected overlay dentry whose real dentry is @real.
+ * If @real is on upper layer, we lookup a child overlay dentry with the same
+ * path the real dentry. Otherwise, we need to consult index for lookup.
+ */
+static struct dentry *ovl_lookup_real(struct super_block *sb,
+				      struct dentry *real,
+				      const struct ovl_layer *layer)
+{
+	struct dentry *connected;
+	int err = 0;
+
+	connected = ovl_lookup_real_ancestor(sb, real, layer);
+	if (IS_ERR(connected))
+		return connected;
+
+	while (!err) {
+		struct dentry *next, *this;
+		struct dentry *parent = NULL;
+		struct dentry *real_connected = ovl_dentry_real_at(connected,
+								   layer->idx);
+
+		if (real_connected == real)
+			break;
+
+		/* Find the topmost dentry not yet connected */
+		next = dget(real);
+		for (;;) {
+			parent = dget_parent(next);
+
+			if (parent == real_connected)
+				break;
+
+			/*
+			 * If real has been moved out of 'real_connected',
+			 * we will not find 'real_connected' and hit the layer
+			 * root. In that case, we need to restart connecting.
+			 * This game can go on forever in the worst case. We
+			 * may want to consider taking s_vfs_rename_mutex if
+			 * this happens more than once.
+			 */
+			if (parent == layer->mnt->mnt_root) {
+				dput(connected);
+				connected = dget(sb->s_root);
+				break;
+			}
+
+			/*
+			 * If real file has been moved out of the layer root
+			 * directory, we will eventully hit the real fs root.
+			 * This cannot happen by legit overlay rename, so we
+			 * return error in that case.
+			 */
+			if (parent == next) {
+				err = -EXDEV;
+				break;
+			}
+
+			dput(next);
+			next = parent;
+		}
+
+		if (!err) {
+			this = ovl_lookup_real_one(connected, next, layer);
+			if (IS_ERR(this))
+				err = PTR_ERR(this);
+
+			/*
+			 * Lookup of child in overlay can fail when racing with
+			 * overlay rename of child away from 'connected' parent.
+			 * In this case, we need to restart the lookup from the
+			 * top, because we cannot trust that 'real_connected' is
+			 * still an ancestor of 'real'. There is a good chance
+			 * that the renamed overlay ancestor is now in cache, so
+			 * ovl_lookup_real_ancestor() will find it and we can
+			 * continue to connect exactly from where lookup failed.
+			 */
+			if (err == -ECHILD) {
+				this = ovl_lookup_real_ancestor(sb, real,
+								layer);
+				err = PTR_ERR_OR_ZERO(this);
+			}
+			if (!err) {
+				dput(connected);
+				connected = this;
+			}
+		}
+
+		dput(parent);
+		dput(next);
+	}
+
+	if (err)
+		goto fail;
+
+	return connected;
+
+fail:
+	pr_warn_ratelimited("failed to lookup by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
+			    real, layer->idx, connected, err);
+	dput(connected);
+	return ERR_PTR(err);
+}
+
+/*
+ * Get an overlay dentry from upper/lower real dentries and index.
+ */
+static struct dentry *ovl_get_dentry(struct super_block *sb,
+				     struct dentry *upper,
+				     struct ovl_path *lowerpath,
+				     struct dentry *index)
+{
+	struct ovl_fs *ofs = OVL_FS(sb);
+	const struct ovl_layer *layer = upper ? &ofs->layers[0] : lowerpath->layer;
+	struct dentry *real = upper ?: (index ?: lowerpath->dentry);
+
+	/*
+	 * Obtain a disconnected overlay dentry from a non-dir real dentry
+	 * and index.
+	 */
+	if (!d_is_dir(real))
+		return ovl_obtain_alias(sb, upper, lowerpath, index);
+
+	/* Removed empty directory? */
+	if ((real->d_flags & DCACHE_DISCONNECTED) || d_unhashed(real))
+		return ERR_PTR(-ENOENT);
+
+	/*
+	 * If real dentry is connected and hashed, get a connected overlay
+	 * dentry whose real dentry is @real.
+	 */
+	return ovl_lookup_real(sb, real, layer);
+}
+
+static struct dentry *ovl_upper_fh_to_d(struct super_block *sb,
+					struct ovl_fh *fh)
+{
+	struct ovl_fs *ofs = OVL_FS(sb);
+	struct dentry *dentry;
+	struct dentry *upper;
+
+	if (!ovl_upper_mnt(ofs))
+		return ERR_PTR(-EACCES);
+
+	upper = ovl_decode_real_fh(ofs, fh, ovl_upper_mnt(ofs), true);
+	if (IS_ERR_OR_NULL(upper))
+		return upper;
+
+	dentry = ovl_get_dentry(sb, upper, NULL, NULL);
+	dput(upper);
+
+	return dentry;
+}
+
+static struct dentry *ovl_lower_fh_to_d(struct super_block *sb,
+					struct ovl_fh *fh)
+{
+	struct ovl_fs *ofs = OVL_FS(sb);
+	struct ovl_path origin = { };
+	struct ovl_path *stack = &origin;
+	struct dentry *dentry = NULL;
+	struct dentry *index = NULL;
+	struct inode *inode;
+	int err;
+
+	/* First lookup overlay inode in inode cache by origin fh */
+	err = ovl_check_origin_fh(ofs, fh, false, NULL, &stack);
+	if (err)
+		return ERR_PTR(err);
+
+	if (!d_is_dir(origin.dentry) ||
+	    !(origin.dentry->d_flags & DCACHE_DISCONNECTED)) {
+		inode = ovl_lookup_inode(sb, origin.dentry, false);
+		err = PTR_ERR(inode);
+		if (IS_ERR(inode))
+			goto out_err;
+		if (inode) {
+			dentry = d_find_any_alias(inode);
+			iput(inode);
+			if (dentry)
+				goto out;
+		}
+	}
+
+	/* Then lookup indexed upper/whiteout by origin fh */
+	if (ovl_indexdir(sb)) {
+		index = ovl_get_index_fh(ofs, fh);
+		err = PTR_ERR(index);
+		if (IS_ERR(index)) {
+			index = NULL;
+			goto out_err;
+		}
+	}
+
+	/* Then try to get a connected upper dir by index */
+	if (index && d_is_dir(index)) {
+		struct dentry *upper = ovl_index_upper(ofs, index, true);
+
+		err = PTR_ERR(upper);
+		if (IS_ERR_OR_NULL(upper))
+			goto out_err;
+
+		dentry = ovl_get_dentry(sb, upper, NULL, NULL);
+		dput(upper);
+		goto out;
+	}
+
+	/* Find origin.dentry again with ovl_acceptable() layer check */
+	if (d_is_dir(origin.dentry)) {
+		dput(origin.dentry);
+		origin.dentry = NULL;
+		err = ovl_check_origin_fh(ofs, fh, true, NULL, &stack);
+		if (err)
+			goto out_err;
+	}
+	if (index) {
+		err = ovl_verify_origin(ofs, index, origin.dentry, false);
+		if (err)
+			goto out_err;
+	}
+
+	/* Get a connected non-upper dir or disconnected non-dir */
+	dentry = ovl_get_dentry(sb, NULL, &origin, index);
+
+out:
+	dput(origin.dentry);
+	dput(index);
+	return dentry;
+
+out_err:
+	dentry = ERR_PTR(err);
+	goto out;
+}
+
+static struct ovl_fh *ovl_fid_to_fh(struct fid *fid, int buflen, int fh_type)
+{
+	struct ovl_fh *fh;
+
+	/* If on-wire inner fid is aligned - nothing to do */
+	if (fh_type == OVL_FILEID_V1)
+		return (struct ovl_fh *)fid;
+
+	if (fh_type != OVL_FILEID_V0)
+		return ERR_PTR(-EINVAL);
+
+	if (buflen <= OVL_FH_WIRE_OFFSET)
+		return ERR_PTR(-EINVAL);
+
+	fh = kzalloc(buflen, GFP_KERNEL);
+	if (!fh)
+		return ERR_PTR(-ENOMEM);
+
+	/* Copy unaligned inner fh into aligned buffer */
+	memcpy(fh->buf, fid, buflen - OVL_FH_WIRE_OFFSET);
+	return fh;
+}
+
+static struct dentry *ovl_fh_to_dentry(struct super_block *sb, struct fid *fid,
+				       int fh_len, int fh_type)
+{
+	struct dentry *dentry = NULL;
+	struct ovl_fh *fh = NULL;
+	int len = fh_len << 2;
+	unsigned int flags = 0;
+	int err;
+
+	fh = ovl_fid_to_fh(fid, len, fh_type);
+	err = PTR_ERR(fh);
+	if (IS_ERR(fh))
+		goto out_err;
+
+	err = ovl_check_fh_len(fh, len);
+	if (err)
+		goto out_err;
+
+	flags = fh->fb.flags;
+	dentry = (flags & OVL_FH_FLAG_PATH_UPPER) ?
+		 ovl_upper_fh_to_d(sb, fh) :
+		 ovl_lower_fh_to_d(sb, fh);
+	err = PTR_ERR(dentry);
+	if (IS_ERR(dentry) && err != -ESTALE)
+		goto out_err;
+
+out:
+	/* We may have needed to re-align OVL_FILEID_V0 */
+	if (!IS_ERR_OR_NULL(fh) && fh != (void *)fid)
+		kfree(fh);
+
+	return dentry;
+
+out_err:
+	pr_warn_ratelimited("failed to decode file handle (len=%d, type=%d, flags=%x, err=%i)\n",
+			    fh_len, fh_type, flags, err);
+	dentry = ERR_PTR(err);
+	goto out;
+}
+
+static struct dentry *ovl_fh_to_parent(struct super_block *sb, struct fid *fid,
+				       int fh_len, int fh_type)
+{
+	pr_warn_ratelimited("connectable file handles not supported; use 'no_subtree_check' exportfs option.\n");
+	return ERR_PTR(-EACCES);
+}
+
+static int ovl_get_name(struct dentry *parent, char *name,
+			struct dentry *child)
+{
+	/*
+	 * ovl_fh_to_dentry() returns connected dir overlay dentries and
+	 * ovl_fh_to_parent() is not implemented, so we should not get here.
+	 */
+	WARN_ON_ONCE(1);
+	return -EIO;
+}
+
+static struct dentry *ovl_get_parent(struct dentry *dentry)
+{
+	/*
+	 * ovl_fh_to_dentry() returns connected dir overlay dentries, so we
+	 * should not get here.
+	 */
+	WARN_ON_ONCE(1);
+	return ERR_PTR(-EIO);
+}
+
+const struct export_operations ovl_export_operations = {
+	.encode_fh	= ovl_encode_fh,
+	.fh_to_dentry	= ovl_fh_to_dentry,
+	.fh_to_parent	= ovl_fh_to_parent,
+	.get_name	= ovl_get_name,
+	.get_parent	= ovl_get_parent,
+};
+
+/* encode_fh() encodes non-decodable file handles with nfs_export=off */
+const struct export_operations ovl_export_fid_operations = {
+	.encode_fh	= ovl_encode_fh,
+};

linux-7.2.3/fs/overlayfs/file.c

@@ -0,0 +1,666 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2017 Red Hat, Inc.
+ */
+
+#include <linux/cred.h>
+#include <linux/file.h>
+#include <linux/filelock.h>
+#include <linux/mount.h>
+#include <linux/xattr.h>
+#include <linux/uio.h>
+#include <linux/uaccess.h>
+#include <linux/security.h>
+#include <linux/fs.h>
+#include <linux/backing-file.h>
+#include "overlayfs.h"
+
+static char ovl_whatisit(struct inode *inode, struct inode *realinode)
+{
+	if (realinode != ovl_inode_upper(inode))
+		return 'l';
+	if (ovl_has_upperdata(inode))
+		return 'u';
+	else
+		return 'm';
+}
+
+static struct file *ovl_open_realfile(const struct file *file,
+				      const struct path *realpath)
+{
+	struct inode *realinode = d_inode(realpath->dentry);
+	struct inode *inode = file_inode(file);
+	struct mnt_idmap *real_idmap;
+	struct file *realfile;
+	int flags = file->f_flags | OVL_OPEN_FLAGS;
+	int acc_mode = ACC_MODE(flags);
+	int err;
+
+	if (flags & O_APPEND)
+		acc_mode |= MAY_APPEND;
+
+	with_ovl_creds(inode->i_sb) {
+		real_idmap = mnt_idmap(realpath->mnt);
+		err = inode_permission(real_idmap, realinode, MAY_OPEN | acc_mode);
+		if (err) {
+			realfile = ERR_PTR(err);
+		} else {
+			if (!inode_owner_or_capable(real_idmap, realinode))
+				flags &= ~O_NOATIME;
+
+			realfile = backing_file_open(file,
+						     flags, realpath, current_cred());
+		}
+	}
+
+	pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n",
+		 file, file, ovl_whatisit(inode, realinode), file->f_flags,
+		 realfile, IS_ERR(realfile) ? 0 : realfile->f_flags);
+
+	return realfile;
+}
+
+#define OVL_SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT)
+
+static int ovl_change_flags(struct file *file, unsigned int flags)
+{
+	struct inode *inode = file_inode(file);
+	int err;
+
+	flags &= OVL_SETFL_MASK;
+
+	if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode))
+		return -EPERM;
+
+	if ((flags & O_DIRECT) && !(file->f_mode & FMODE_CAN_ODIRECT))
+		return -EINVAL;
+
+	if (file->f_op->check_flags) {
+		err = file->f_op->check_flags(flags);
+		if (err)
+			return err;
+	}
+
+	spin_lock(&file->f_lock);
+	file->f_flags = (file->f_flags & ~OVL_SETFL_MASK) | flags;
+	file->f_iocb_flags = iocb_flags(file);
+	spin_unlock(&file->f_lock);
+
+	return 0;
+}
+
+struct ovl_file {
+	struct file *realfile;
+	struct file *upperfile;
+};
+
+struct ovl_file *ovl_file_alloc(struct file *realfile)
+{
+	struct ovl_file *of = kzalloc_obj(struct ovl_file);
+
+	if (unlikely(!of))
+		return NULL;
+
+	of->realfile = realfile;
+	return of;
+}
+
+void ovl_file_free(struct ovl_file *of)
+{
+	fput(of->realfile);
+	if (of->upperfile)
+		fput(of->upperfile);
+	kfree(of);
+}
+
+static bool ovl_is_real_file(const struct file *realfile,
+			     const struct path *realpath)
+{
+	return file_inode(realfile) == d_inode(realpath->dentry);
+}
+
+static struct file *ovl_real_file_path(const struct file *file,
+				       const struct path *realpath)
+{
+	struct ovl_file *of = file->private_data;
+	struct file *realfile = of->realfile;
+
+	if (WARN_ON_ONCE(!realpath->dentry))
+		return ERR_PTR(-EIO);
+
+	/*
+	 * If the realfile that we want is not where the data used to be at
+	 * open time, either we'd been copied up, or it's an fsync of a
+	 * metacopied file.  We need the upperfile either way, so see if it
+	 * is already opened and if it is not then open and store it.
+	 */
+	if (unlikely(!ovl_is_real_file(realfile, realpath))) {
+		struct file *upperfile = READ_ONCE(of->upperfile);
+		struct file *old;
+
+		if (!upperfile) { /* Nobody opened upperfile yet */
+			upperfile = ovl_open_realfile(file, realpath);
+			if (IS_ERR(upperfile))
+				return upperfile;
+
+			/* Store the upperfile for later */
+			old = cmpxchg_release(&of->upperfile, NULL, upperfile);
+			if (old) { /* Someone opened upperfile before us */
+				fput(upperfile);
+				upperfile = old;
+			}
+		}
+		/*
+		 * Stored file must be from the right inode, unless someone's
+		 * been corrupting the upper layer.
+		 */
+		if (WARN_ON_ONCE(!ovl_is_real_file(upperfile, realpath)))
+			return ERR_PTR(-EIO);
+
+		realfile = upperfile;
+	}
+
+	/* Did the flags change since open? */
+	if (unlikely((file->f_flags ^ realfile->f_flags) & ~OVL_OPEN_FLAGS)) {
+		int err = ovl_change_flags(realfile, file->f_flags);
+
+		if (err)
+			return ERR_PTR(err);
+	}
+
+	return realfile;
+}
+
+static struct file *ovl_real_file(const struct file *file)
+{
+	struct dentry *dentry = file_dentry(file);
+	struct path realpath;
+	int err;
+
+	if (d_is_dir(dentry)) {
+		struct file *f = ovl_dir_real_file(file, false);
+
+		if (WARN_ON_ONCE(!f))
+			return ERR_PTR(-EIO);
+		return f;
+	}
+
+	/* lazy lookup and verify of lowerdata */
+	err = ovl_verify_lowerdata(dentry);
+	if (err)
+		return ERR_PTR(err);
+
+	ovl_path_realdata(dentry, &realpath);
+
+	return ovl_real_file_path(file, &realpath);
+}
+
+static int ovl_open(struct inode *inode, struct file *file)
+{
+	struct dentry *dentry = file_dentry(file);
+	struct file *realfile;
+	struct path realpath;
+	struct ovl_file *of;
+	int err;
+
+	/* lazy lookup and verify lowerdata */
+	err = ovl_verify_lowerdata(dentry);
+	if (err)
+		return err;
+
+	err = ovl_maybe_copy_up(dentry, file->f_flags);
+	if (err)
+		return err;
+
+	/* No longer need these flags, so don't pass them on to underlying fs */
+	file->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
+
+	ovl_path_realdata(dentry, &realpath);
+	if (!realpath.dentry)
+		return -EIO;
+
+	realfile = ovl_open_realfile(file, &realpath);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	of = ovl_file_alloc(realfile);
+	if (!of) {
+		fput(realfile);
+		return -ENOMEM;
+	}
+
+	file->private_data = of;
+
+	return 0;
+}
+
+static int ovl_release(struct inode *inode, struct file *file)
+{
+	ovl_file_free(file->private_data);
+	return 0;
+}
+
+static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *inode = file_inode(file);
+	struct file *realfile;
+	loff_t ret;
+
+	/*
+	 * The two special cases below do not need to involve real fs,
+	 * so we can optimizing concurrent callers.
+	 */
+	if (offset == 0) {
+		if (whence == SEEK_CUR)
+			return file->f_pos;
+
+		if (whence == SEEK_SET)
+			return vfs_setpos(file, 0, 0);
+	}
+
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	/*
+	 * Overlay file f_pos is the master copy that is preserved
+	 * through copy up and modified on read/write, but only real
+	 * fs knows how to SEEK_HOLE/SEEK_DATA and real fs may impose
+	 * limitations that are more strict than ->s_maxbytes for specific
+	 * files, so we use the real file to perform seeks.
+	 */
+	ovl_inode_lock(inode);
+	realfile->f_pos = file->f_pos;
+
+	with_ovl_creds(inode->i_sb)
+		ret = vfs_llseek(realfile, offset, whence);
+
+	file->f_pos = realfile->f_pos;
+	ovl_inode_unlock(inode);
+
+	return ret;
+}
+
+static void ovl_file_modified(struct file *file)
+{
+	/* Update size/mtime */
+	ovl_copyattr(file_inode(file));
+}
+
+static void ovl_file_end_write(struct kiocb *iocb, ssize_t ret)
+{
+	ovl_file_modified(iocb->ki_filp);
+}
+
+static void ovl_file_accessed(struct file *file)
+{
+	struct inode *inode, *upperinode;
+	struct timespec64 ctime, uctime;
+	struct timespec64 mtime, umtime;
+
+	if (file->f_flags & O_NOATIME)
+		return;
+
+	inode = file_inode(file);
+	upperinode = ovl_inode_upper(inode);
+
+	if (!upperinode)
+		return;
+
+	ctime = inode_get_ctime(inode);
+	uctime = inode_get_ctime(upperinode);
+	mtime = inode_get_mtime(inode);
+	umtime = inode_get_mtime(upperinode);
+	if ((!timespec64_equal(&mtime, &umtime)) ||
+	     !timespec64_equal(&ctime, &uctime)) {
+		inode_set_mtime_to_ts(inode, inode_get_mtime(upperinode));
+		inode_set_ctime_to_ts(inode, uctime);
+	}
+
+	touch_atime(&file->f_path);
+}
+
+static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct file *realfile;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(file)->i_sb),
+		.accessed = ovl_file_accessed,
+	};
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	return backing_file_read_iter(realfile, iter, iocb, iocb->ki_flags,
+				      &ctx);
+}
+
+static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct file *realfile;
+	ssize_t ret;
+	int ifl = iocb->ki_flags;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(inode->i_sb),
+		.end_write = ovl_file_end_write,
+	};
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	inode_lock(inode);
+	/* Update mode */
+	ovl_copyattr(inode);
+
+	realfile = ovl_real_file(file);
+	ret = PTR_ERR(realfile);
+	if (IS_ERR(realfile))
+		goto out_unlock;
+
+	if (!ovl_should_sync(OVL_FS(inode->i_sb)))
+		ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
+
+	ret = backing_file_write_iter(realfile, iter, iocb, ifl, &ctx);
+
+out_unlock:
+	inode_unlock(inode);
+
+	return ret;
+}
+
+static ssize_t ovl_splice_read(struct file *in, loff_t *ppos,
+			       struct pipe_inode_info *pipe, size_t len,
+			       unsigned int flags)
+{
+	struct file *realfile;
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(in)->i_sb),
+		.accessed = ovl_file_accessed,
+	};
+	struct kiocb iocb;
+
+	realfile = ovl_real_file(in);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	init_sync_kiocb(&iocb, in);
+	iocb.ki_pos = *ppos;
+	ret = backing_file_splice_read(realfile, &iocb, pipe, len, flags, &ctx);
+	*ppos = iocb.ki_pos;
+
+	return ret;
+}
+
+/*
+ * Calling iter_file_splice_write() directly from overlay's f_op may deadlock
+ * due to lock order inversion between pipe->mutex in iter_file_splice_write()
+ * and file_start_write(realfile) in ovl_write_iter().
+ *
+ * So do everything ovl_write_iter() does and call iter_file_splice_write() on
+ * the real file.
+ */
+static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
+				loff_t *ppos, size_t len, unsigned int flags)
+{
+	struct file *realfile;
+	struct inode *inode = file_inode(out);
+	ssize_t ret;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(inode->i_sb),
+		.end_write = ovl_file_end_write,
+	};
+	struct kiocb iocb;
+
+	inode_lock(inode);
+	/* Update mode */
+	ovl_copyattr(inode);
+
+	realfile = ovl_real_file(out);
+	ret = PTR_ERR(realfile);
+	if (IS_ERR(realfile))
+		goto out_unlock;
+
+	init_sync_kiocb(&iocb, out);
+	iocb.ki_pos = *ppos;
+	ret = backing_file_splice_write(pipe, realfile, &iocb, len, flags, &ctx);
+	*ppos = iocb.ki_pos;
+
+out_unlock:
+	inode_unlock(inode);
+
+	return ret;
+}
+
+static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+	struct dentry *dentry = file_dentry(file);
+	enum ovl_path_type type;
+	struct path upperpath;
+	struct file *upperfile;
+	int ret;
+
+	ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb));
+	if (ret <= 0)
+		return ret;
+
+	/* Don't sync lower file for fear of receiving EROFS error */
+	type = ovl_path_type(dentry);
+	if (!OVL_TYPE_UPPER(type) || (datasync && OVL_TYPE_MERGE(type)))
+		return 0;
+
+	ovl_path_upper(dentry, &upperpath);
+	upperfile = ovl_real_file_path(file, &upperpath);
+	if (IS_ERR(upperfile))
+		return PTR_ERR(upperfile);
+
+	with_ovl_creds(file_inode(file)->i_sb)
+		return vfs_fsync_range(upperfile, start, end, datasync);
+}
+
+static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct ovl_file *of = file->private_data;
+	struct backing_file_ctx ctx = {
+		.cred = ovl_creds(file_inode(file)->i_sb),
+		.accessed = ovl_file_accessed,
+	};
+
+	return backing_file_mmap(of->realfile, vma, &ctx);
+}
+
+static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
+{
+	struct inode *inode = file_inode(file);
+	struct file *realfile;
+	int ret;
+
+	inode_lock(inode);
+	/* Update mode */
+	ovl_copyattr(inode);
+	ret = file_remove_privs(file);
+	if (ret)
+		goto out_unlock;
+
+	realfile = ovl_real_file(file);
+	ret = PTR_ERR(realfile);
+	if (IS_ERR(realfile))
+		goto out_unlock;
+
+	with_ovl_creds(inode->i_sb)
+		ret = vfs_fallocate(realfile, mode, offset, len);
+
+	/* Update size */
+	ovl_file_modified(file);
+
+out_unlock:
+	inode_unlock(inode);
+
+	return ret;
+}
+
+static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
+{
+	struct file *realfile;
+
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	with_ovl_creds(file_inode(file)->i_sb)
+		return vfs_fadvise(realfile, offset, len, advice);
+}
+
+enum ovl_copyop {
+	OVL_COPY,
+	OVL_CLONE,
+	OVL_DEDUPE,
+};
+
+static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
+			    struct file *file_out, loff_t pos_out,
+			    loff_t len, unsigned int flags, enum ovl_copyop op)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	struct file *realfile_in, *realfile_out;
+	loff_t ret;
+
+	inode_lock(inode_out);
+	if (op != OVL_DEDUPE) {
+		/* Update mode */
+		ovl_copyattr(inode_out);
+		ret = file_remove_privs(file_out);
+		if (ret)
+			goto out_unlock;
+	}
+
+	realfile_out = ovl_real_file(file_out);
+	ret = PTR_ERR(realfile_out);
+	if (IS_ERR(realfile_out))
+		goto out_unlock;
+
+	realfile_in = ovl_real_file(file_in);
+	ret = PTR_ERR(realfile_in);
+	if (IS_ERR(realfile_in))
+		goto out_unlock;
+
+	/*
+	 * For cross-sb copy, vfs_copy_file_range() will verify read access with
+	 * the mounter creds of the dest fs mounter, so we need to explicitly
+	 * verify read access with the source mounter creds.
+	 */
+	if (unlikely(inode_in->i_sb != inode_out->i_sb)) {
+		with_ovl_creds(inode_in->i_sb) {
+			ret = rw_verify_area(READ, realfile_in, &pos_in, len);
+			if (unlikely(ret))
+				goto out_unlock;
+		}
+	}
+
+	with_ovl_creds(inode_out->i_sb) {
+		switch (op) {
+		case OVL_COPY:
+			ret = vfs_copy_file_range(realfile_in, pos_in,
+						  realfile_out, pos_out, len, flags);
+			break;
+
+		case OVL_CLONE:
+			ret = vfs_clone_file_range(realfile_in, pos_in,
+						   realfile_out, pos_out, len, flags);
+			break;
+
+		case OVL_DEDUPE:
+			ret = vfs_dedupe_file_range_one(realfile_in, pos_in,
+							realfile_out, pos_out, len,
+							flags);
+			break;
+		}
+	}
+
+	/* Update size */
+	ovl_file_modified(file_out);
+
+out_unlock:
+	inode_unlock(inode_out);
+
+	return ret;
+}
+
+static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in,
+				   struct file *file_out, loff_t pos_out,
+				   size_t len, unsigned int flags)
+{
+	return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, flags,
+			    OVL_COPY);
+}
+
+static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in,
+				   struct file *file_out, loff_t pos_out,
+				   loff_t len, unsigned int remap_flags)
+{
+	enum ovl_copyop op;
+
+	if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
+		return -EINVAL;
+
+	if (remap_flags & REMAP_FILE_DEDUP)
+		op = OVL_DEDUPE;
+	else
+		op = OVL_CLONE;
+
+	/*
+	 * Don't copy up because of a dedupe request, this wouldn't make sense
+	 * most of the time (data would be duplicated instead of deduplicated).
+	 */
+	if (op == OVL_DEDUPE &&
+	    (!ovl_inode_upper(file_inode(file_in)) ||
+	     !ovl_inode_upper(file_inode(file_out))))
+		return -EPERM;
+
+	return ovl_copyfile(file_in, pos_in, file_out, pos_out, len,
+			    remap_flags, op);
+}
+
+static int ovl_flush(struct file *file, fl_owner_t id)
+{
+	struct file *realfile;
+	int err = 0;
+
+	realfile = ovl_real_file(file);
+	if (IS_ERR(realfile))
+		return PTR_ERR(realfile);
+
+	if (realfile->f_op->flush) {
+		with_ovl_creds(file_inode(file)->i_sb)
+			err = realfile->f_op->flush(realfile, id);
+	}
+
+	return err;
+}
+
+const struct file_operations ovl_file_operations = {
+	.open		= ovl_open,
+	.release	= ovl_release,
+	.llseek		= ovl_llseek,
+	.read_iter	= ovl_read_iter,
+	.write_iter	= ovl_write_iter,
+	.fsync		= ovl_fsync,
+	.mmap		= ovl_mmap,
+	.fallocate	= ovl_fallocate,
+	.fadvise	= ovl_fadvise,
+	.flush		= ovl_flush,
+	.splice_read    = ovl_splice_read,
+	.splice_write   = ovl_splice_write,
+
+	.copy_file_range	= ovl_copy_file_range,
+	.remap_file_range	= ovl_remap_file_range,
+	.setlease		= generic_setlease,
+};

linux-7.2.3/fs/overlayfs/overlayfs.h

@@ -0,0 +1,954 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/uuid.h>
+#include <linux/fs.h>
+#include <linux/fsverity.h>
+#include <linux/namei.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
+#include "ovl_entry.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "overlayfs: " fmt
+
+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_NAMESPACE "overlay."
+#define OVL_XATTR_TRUSTED_PREFIX XATTR_TRUSTED_PREFIX OVL_XATTR_NAMESPACE
+#define OVL_XATTR_TRUSTED_PREFIX_LEN (sizeof(OVL_XATTR_TRUSTED_PREFIX) - 1)
+#define OVL_XATTR_USER_PREFIX XATTR_USER_PREFIX OVL_XATTR_NAMESPACE
+#define OVL_XATTR_USER_PREFIX_LEN (sizeof(OVL_XATTR_USER_PREFIX) - 1)
+
+#define OVL_XATTR_ESCAPE_PREFIX OVL_XATTR_NAMESPACE
+#define OVL_XATTR_ESCAPE_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_PREFIX) - 1)
+#define OVL_XATTR_ESCAPE_TRUSTED_PREFIX OVL_XATTR_TRUSTED_PREFIX OVL_XATTR_ESCAPE_PREFIX
+#define OVL_XATTR_ESCAPE_TRUSTED_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_TRUSTED_PREFIX) - 1)
+#define OVL_XATTR_ESCAPE_USER_PREFIX OVL_XATTR_USER_PREFIX OVL_XATTR_ESCAPE_PREFIX
+#define OVL_XATTR_ESCAPE_USER_PREFIX_LEN (sizeof(OVL_XATTR_ESCAPE_USER_PREFIX) - 1)
+
+enum ovl_xattr {
+	OVL_XATTR_OPAQUE,
+	OVL_XATTR_REDIRECT,
+	OVL_XATTR_ORIGIN,
+	OVL_XATTR_IMPURE,
+	OVL_XATTR_NLINK,
+	OVL_XATTR_UPPER,
+	OVL_XATTR_UUID,
+	OVL_XATTR_METACOPY,
+	OVL_XATTR_PROTATTR,
+	OVL_XATTR_XWHITEOUT,
+};
+
+enum ovl_inode_flag {
+	/* Pure upper dir that may contain non pure upper entries */
+	OVL_IMPURE,
+	/* Non-merge dir that may contain whiteout entries */
+	OVL_WHITEOUTS,
+	OVL_INDEX,
+	OVL_UPPERDATA,
+	/* Inode number will remain constant over copy up. */
+	OVL_CONST_INO,
+	OVL_HAS_DIGEST,
+	OVL_VERIFIED_DIGEST,
+};
+
+enum ovl_entry_flag {
+	OVL_E_UPPER_ALIAS,
+	OVL_E_OPAQUE,
+	OVL_E_CONNECTED,
+	/* Lower stack may contain xwhiteout entries */
+	OVL_E_XWHITEOUTS,
+};
+
+enum {
+	OVL_REDIRECT_OFF,	/* "off" mode is never used. In effect	*/
+	OVL_REDIRECT_FOLLOW,	/* ...it translates to either "follow"	*/
+	OVL_REDIRECT_NOFOLLOW,	/* ...or "nofollow".			*/
+	OVL_REDIRECT_ON,
+};
+
+enum {
+	OVL_UUID_OFF,
+	OVL_UUID_NULL,
+	OVL_UUID_AUTO,
+	OVL_UUID_ON,
+};
+
+enum {
+	OVL_XINO_OFF,
+	OVL_XINO_AUTO,
+	OVL_XINO_ON,
+};
+
+enum {
+	OVL_VERITY_OFF,
+	OVL_VERITY_ON,
+	OVL_VERITY_REQUIRE,
+};
+
+enum {
+	OVL_FSYNC_VOLATILE,
+	OVL_FSYNC_AUTO,
+	OVL_FSYNC_STRICT,
+};
+
+/*
+ * 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
+
+/* The type used to be returned by overlay exportfs for misaligned fid */
+#define OVL_FILEID_V0	0xfb
+/* The type returned by overlay exportfs for 32bit aligned fid */
+#define OVL_FILEID_V1	0xf8
+
+/* On-disk format for "origin" file handle */
+struct ovl_fb {
+	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 */
+	u32 fid[];	/* file identifier should be 32bit aligned in-memory */
+} __packed;
+
+/* In-memory and on-wire format for overlay file handle */
+struct ovl_fh {
+	u8 padding[3];	/* make sure fb.fid is 32bit aligned */
+	union {
+		struct ovl_fb fb;
+		DECLARE_FLEX_ARRAY(u8, buf);
+	};
+} __packed;
+
+#define OVL_FH_WIRE_OFFSET	offsetof(struct ovl_fh, fb)
+#define OVL_FH_LEN(fh)		(OVL_FH_WIRE_OFFSET + (fh)->fb.len)
+#define OVL_FH_FID_OFFSET	(OVL_FH_WIRE_OFFSET + \
+				 offsetof(struct ovl_fb, fid))
+
+/* On-disk format for "metacopy" xattr (if non-zero size) */
+struct ovl_metacopy {
+	u8 version;	/* 0 */
+	u8 len;         /* size of this header + used digest bytes */
+	u8 flags;
+	u8 digest_algo;	/* FS_VERITY_HASH_ALG_* constant, 0 for no digest */
+	u8 digest[FS_VERITY_MAX_DIGEST_SIZE];  /* Only the used part on disk */
+} __packed;
+
+#define OVL_METACOPY_MAX_SIZE (sizeof(struct ovl_metacopy))
+#define OVL_METACOPY_MIN_SIZE (OVL_METACOPY_MAX_SIZE - FS_VERITY_MAX_DIGEST_SIZE)
+#define OVL_METACOPY_INIT { 0, OVL_METACOPY_MIN_SIZE }
+
+static inline int ovl_metadata_digest_size(const struct ovl_metacopy *metacopy)
+{
+	if (metacopy->len < OVL_METACOPY_MIN_SIZE)
+		return 0;
+	return (int)metacopy->len - OVL_METACOPY_MIN_SIZE;
+}
+
+/* No atime modification on underlying */
+#define OVL_OPEN_FLAGS (O_NOATIME)
+
+extern const char *const ovl_xattr_table[][2];
+static inline const char *ovl_xattr(struct ovl_fs *ofs, enum ovl_xattr ox)
+{
+	return ovl_xattr_table[ox][ofs->config.userxattr];
+}
+
+/*
+ * When changing ownership of an upper object map the intended ownership
+ * according to the upper layer's idmapping. When an upper mount idmaps files
+ * that are stored on-disk as owned by id 1001 to id 1000 this means stat on
+ * this object will report it as being owned by id 1000 when calling stat via
+ * the upper mount.
+ * In order to change ownership of an object so stat reports id 1000 when
+ * called on an idmapped upper mount the value written to disk - i.e., the
+ * value stored in ia_*id - must 1001. The mount mapping helper will thus take
+ * care to map 1000 to 1001.
+ * The mnt idmapping helpers are nops if the upper layer isn't idmapped.
+ */
+static inline int ovl_do_notify_change(struct ovl_fs *ofs,
+				       struct dentry *upperdentry,
+				       struct iattr *attr)
+{
+	return notify_change(ovl_upper_mnt_idmap(ofs), upperdentry, attr, NULL);
+}
+
+static inline int ovl_do_rmdir(struct ovl_fs *ofs,
+			       struct inode *dir, struct dentry *dentry)
+{
+	int err = vfs_rmdir(ovl_upper_mnt_idmap(ofs), dir, dentry, NULL);
+
+	pr_debug("rmdir(%pd2) = %i\n", dentry, err);
+	return err;
+}
+
+static inline int ovl_do_unlink(struct ovl_fs *ofs, struct inode *dir,
+				struct dentry *dentry)
+{
+	int err = vfs_unlink(ovl_upper_mnt_idmap(ofs), dir, dentry, NULL);
+
+	pr_debug("unlink(%pd2) = %i\n", dentry, err);
+	return err;
+}
+
+static inline int ovl_do_link(struct ovl_fs *ofs, struct dentry *old_dentry,
+			      struct inode *dir, struct dentry *new_dentry)
+{
+	int err = vfs_link(old_dentry, ovl_upper_mnt_idmap(ofs), dir,
+			   new_dentry, NULL);
+
+	pr_debug("link(%pd2, %pd2) = %i\n", old_dentry, new_dentry, err);
+	return err;
+}
+
+static inline int ovl_do_create(struct ovl_fs *ofs,
+				struct inode *dir, struct dentry *dentry,
+				umode_t mode)
+{
+	int err = vfs_create(ovl_upper_mnt_idmap(ofs), dentry, mode, NULL);
+
+	pr_debug("create(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return err;
+}
+
+static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs,
+					  struct inode *dir,
+					  struct dentry *dentry,
+					  umode_t mode)
+{
+	struct dentry *ret;
+
+	ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, NULL);
+	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret));
+	return ret;
+}
+
+static inline int ovl_do_mknod(struct ovl_fs *ofs,
+			       struct inode *dir, struct dentry *dentry,
+			       umode_t mode, dev_t dev)
+{
+	int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev, NULL);
+
+	pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err);
+	return err;
+}
+
+static inline int ovl_do_symlink(struct ovl_fs *ofs,
+				 struct inode *dir, struct dentry *dentry,
+				 const char *oldname)
+{
+	int err = vfs_symlink(ovl_upper_mnt_idmap(ofs), dir, dentry, oldname, NULL);
+
+	pr_debug("symlink(\"%s\", %pd2) = %i\n", oldname, dentry, err);
+	return err;
+}
+
+static inline ssize_t ovl_do_getxattr(const struct path *path, const char *name,
+				      void *value, size_t size)
+{
+	int err, len;
+
+	WARN_ON(path->dentry->d_sb != path->mnt->mnt_sb);
+
+	err = vfs_getxattr(mnt_idmap(path->mnt), path->dentry,
+			       name, value, size);
+	len = (value && err > 0) ? err : 0;
+
+	pr_debug("getxattr(%pd2, \"%s\", \"%*pE\", %zu, 0) = %i\n",
+		 path->dentry, name, min(len, 48), value, size, err);
+	return err;
+}
+
+static inline ssize_t ovl_getxattr_upper(struct ovl_fs *ofs,
+					 struct dentry *upperdentry,
+					 enum ovl_xattr ox, void *value,
+					 size_t size)
+{
+	struct path upperpath = {
+		.dentry = upperdentry,
+		.mnt = ovl_upper_mnt(ofs),
+	};
+
+	return ovl_do_getxattr(&upperpath, ovl_xattr(ofs, ox), value, size);
+}
+
+static inline ssize_t ovl_path_getxattr(struct ovl_fs *ofs,
+					 const struct path *path,
+					 enum ovl_xattr ox, void *value,
+					 size_t size)
+{
+	return ovl_do_getxattr(path, ovl_xattr(ofs, ox), value, size);
+}
+
+static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
+				  const char *name, const void *value,
+				  size_t size, int flags)
+{
+	int err = vfs_setxattr(ovl_upper_mnt_idmap(ofs), dentry, name,
+			       value, size, flags);
+
+	pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, %d) = %i\n",
+		 dentry, name, min((int)size, 48), value, size, flags, err);
+	return err;
+}
+
+static inline int ovl_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
+			       enum ovl_xattr ox, const void *value,
+			       size_t size)
+{
+	return ovl_do_setxattr(ofs, dentry, ovl_xattr(ofs, ox), value, size, 0);
+}
+
+static inline int ovl_do_removexattr(struct ovl_fs *ofs, struct dentry *dentry,
+				     const char *name)
+{
+	int err = vfs_removexattr(ovl_upper_mnt_idmap(ofs), dentry, name);
+	pr_debug("removexattr(%pd2, \"%s\") = %i\n", dentry, name, err);
+	return err;
+}
+
+static inline int ovl_removexattr(struct ovl_fs *ofs, struct dentry *dentry,
+				  enum ovl_xattr ox)
+{
+	return ovl_do_removexattr(ofs, dentry, ovl_xattr(ofs, ox));
+}
+
+static inline int ovl_do_set_acl(struct ovl_fs *ofs, struct dentry *dentry,
+				 const char *acl_name, struct posix_acl *acl)
+{
+	return vfs_set_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name, acl);
+}
+
+static inline int ovl_do_remove_acl(struct ovl_fs *ofs, struct dentry *dentry,
+				    const char *acl_name)
+{
+	return vfs_remove_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name);
+}
+
+static inline int ovl_do_rename_rd(struct renamedata *rd)
+{
+	int err;
+
+	pr_debug("rename(%pd2, %pd2, 0x%x)\n", rd->old_dentry, rd->new_dentry,
+		 rd->flags);
+	err = vfs_rename(rd);
+	if (err) {
+		pr_debug("...rename(%pd2, %pd2, ...) = %i\n",
+			 rd->old_dentry, rd->new_dentry, err);
+	}
+	return err;
+}
+
+static inline int ovl_do_rename(struct ovl_fs *ofs, struct dentry *olddir,
+				struct dentry *olddentry, struct dentry *newdir,
+				struct dentry *newdentry, unsigned int flags)
+{
+	struct renamedata rd = {
+		.mnt_idmap	= ovl_upper_mnt_idmap(ofs),
+		.old_parent	= olddir,
+		.old_dentry	= olddentry,
+		.new_parent	= newdir,
+		.new_dentry	= newdentry,
+		.flags		= flags,
+	};
+
+	return ovl_do_rename_rd(&rd);
+}
+
+static inline int ovl_do_whiteout(struct ovl_fs *ofs,
+				  struct inode *dir, struct dentry *dentry)
+{
+	int err = vfs_whiteout(ovl_upper_mnt_idmap(ofs), dir, dentry);
+	pr_debug("whiteout(%pd2) = %i\n", dentry, err);
+	return err;
+}
+
+static inline struct file *ovl_do_tmpfile(struct ovl_fs *ofs,
+					  struct dentry *dentry, umode_t mode)
+{
+	struct path path = { .mnt = ovl_upper_mnt(ofs), .dentry = dentry };
+	struct file *file = kernel_tmpfile_open(ovl_upper_mnt_idmap(ofs), &path,
+						mode, O_LARGEFILE | O_WRONLY,
+						current_cred());
+	int err = PTR_ERR_OR_ZERO(file);
+
+	pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return file;
+}
+
+static inline struct dentry *ovl_lookup_upper_unlocked(struct ovl_fs *ofs,
+						       const char *name,
+						       struct dentry *base,
+						       int len)
+{
+	return lookup_one_unlocked(ovl_upper_mnt_idmap(ofs),
+				   &QSTR_LEN(name, len), base);
+}
+
+static inline struct dentry *ovl_start_creating_upper(struct ovl_fs *ofs,
+						      struct dentry *parent,
+						      struct qstr *name)
+{
+	return start_creating(ovl_upper_mnt_idmap(ofs),
+			      parent, name);
+}
+
+static inline struct dentry *ovl_start_removing_upper(struct ovl_fs *ofs,
+						      struct dentry *parent,
+						      struct qstr *name)
+{
+	return start_removing(ovl_upper_mnt_idmap(ofs),
+			      parent, name);
+}
+
+static inline bool ovl_open_flags_need_copy_up(int flags)
+{
+	if (!flags)
+		return false;
+
+	return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC));
+}
+
+/* util.c */
+int ovl_get_write_access(struct dentry *dentry);
+void ovl_put_write_access(struct dentry *dentry);
+void ovl_start_write(struct dentry *dentry);
+void ovl_end_write(struct dentry *dentry);
+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);
+
+EXTEND_CLASS(override_creds, _ovl, ovl_override_creds(sb), struct super_block *sb)
+
+#define with_ovl_creds(sb) \
+	scoped_class(override_creds_ovl, __UNIQUE_ID(label), sb)
+
+static inline const struct cred *ovl_creds(struct super_block *sb)
+{
+	return OVL_FS(sb)->creator_cred;
+}
+
+int ovl_can_decode_fh(struct super_block *sb);
+struct dentry *ovl_indexdir(struct super_block *sb);
+bool ovl_index_all(struct super_block *sb);
+bool ovl_verify_lower(struct super_block *sb);
+struct ovl_path *ovl_stack_alloc(unsigned int n);
+void ovl_stack_cpy(struct ovl_path *dst, struct ovl_path *src, unsigned int n);
+void ovl_stack_put(struct ovl_path *stack, unsigned int n);
+void ovl_stack_free(struct ovl_path *stack, unsigned int n);
+struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
+void ovl_free_entry(struct ovl_entry *oe);
+bool ovl_dentry_remote(struct dentry *dentry);
+void ovl_dentry_update_reval(struct dentry *dentry, struct dentry *realdentry);
+void ovl_dentry_init_reval(struct dentry *dentry, struct dentry *upperdentry,
+			   struct ovl_entry *oe);
+void ovl_dentry_init_flags(struct dentry *dentry, struct dentry *upperdentry,
+			   struct ovl_entry *oe, unsigned int mask);
+bool ovl_dentry_weird(struct dentry *dentry);
+
+static inline bool ovl_dentry_casefolded(struct dentry *dentry)
+{
+	return sb_has_encoding(dentry->d_sb) && IS_CASEFOLDED(d_inode(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);
+void ovl_path_lowerdata(struct dentry *dentry, struct path *path);
+struct inode *ovl_i_path_real(struct inode *inode, struct path *path);
+enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
+enum ovl_path_type ovl_path_realdata(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_lowerdata(struct dentry *dentry);
+int ovl_dentry_set_lowerdata(struct dentry *dentry, struct ovl_path *datapath);
+const struct ovl_layer *ovl_i_layer_lower(struct inode *inode);
+const struct ovl_layer *ovl_layer_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_lowerdata(struct inode *inode);
+struct inode *ovl_inode_real(struct inode *inode);
+struct inode *ovl_inode_realdata(struct inode *inode);
+const char *ovl_lowerdata_redirect(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);
+void ovl_dentry_set_flag(unsigned long flag, struct dentry *dentry);
+void ovl_dentry_clear_flag(unsigned long flag, struct dentry *dentry);
+bool ovl_dentry_test_flag(unsigned long flag, struct dentry *dentry);
+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_xwhiteouts(struct dentry *dentry);
+void ovl_dentry_set_xwhiteouts(struct dentry *dentry);
+void ovl_layer_set_xwhiteouts(struct ovl_fs *ofs,
+			      const struct ovl_layer *layer);
+bool ovl_dentry_has_upper_alias(struct dentry *dentry);
+void ovl_dentry_set_upper_alias(struct dentry *dentry);
+bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags);
+bool ovl_dentry_needs_data_copy_up_locked(struct dentry *dentry, int flags);
+bool ovl_has_upperdata(struct inode *inode);
+void ovl_set_upperdata(struct inode *inode);
+const char *ovl_dentry_get_redirect(struct dentry *dentry);
+void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect);
+void ovl_inode_update(struct inode *inode, struct dentry *upperdentry);
+void ovl_dir_modified(struct dentry *dentry, bool impurity);
+u64 ovl_inode_version_get(struct inode *inode);
+bool ovl_is_whiteout(struct dentry *dentry);
+bool ovl_path_is_whiteout(struct ovl_fs *ofs, const struct path *path);
+struct file *ovl_path_open(const struct path *path, int flags);
+int ovl_copy_up_start(struct dentry *dentry, int flags);
+void ovl_copy_up_end(struct dentry *dentry);
+bool ovl_already_copied_up(struct dentry *dentry, int flags);
+char ovl_get_dir_xattr_val(struct ovl_fs *ofs, const struct path *path,
+			   enum ovl_xattr ox);
+bool ovl_path_check_origin_xattr(struct ovl_fs *ofs, const struct path *path);
+bool ovl_path_check_xwhiteout_xattr(struct ovl_fs *ofs, const struct path *path);
+bool ovl_init_uuid_xattr(struct super_block *sb, struct ovl_fs *ofs,
+			 const struct path *upperpath);
+
+static inline bool ovl_upper_is_whiteout(struct ovl_fs *ofs,
+					 struct dentry *upperdentry)
+{
+	struct path upperpath = {
+		.dentry = upperdentry,
+		.mnt = ovl_upper_mnt(ofs),
+	};
+	return ovl_path_is_whiteout(ofs, &upperpath);
+}
+
+static inline bool ovl_check_origin_xattr(struct ovl_fs *ofs,
+					  struct dentry *upperdentry)
+{
+	struct path upperpath = {
+		.dentry = upperdentry,
+		.mnt = ovl_upper_mnt(ofs),
+	};
+	return ovl_path_check_origin_xattr(ofs, &upperpath);
+}
+
+int ovl_check_setxattr(struct ovl_fs *ofs, struct dentry *upperdentry,
+		       enum ovl_xattr ox, const void *value, size_t size,
+		       int xerr);
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
+bool ovl_inuse_trylock(struct dentry *dentry);
+void ovl_inuse_unlock(struct dentry *dentry);
+bool ovl_is_inuse(struct dentry *dentry);
+bool ovl_need_index(struct dentry *dentry);
+int ovl_nlink_start(struct dentry *dentry);
+void ovl_nlink_end(struct dentry *dentry);
+int ovl_check_metacopy_xattr(struct ovl_fs *ofs, const struct path *path,
+			     struct ovl_metacopy *data);
+int ovl_set_metacopy_xattr(struct ovl_fs *ofs, struct dentry *d,
+			   struct ovl_metacopy *metacopy);
+bool ovl_is_metacopy_dentry(struct dentry *dentry);
+char *ovl_get_redirect_xattr(struct ovl_fs *ofs, const struct path *path, int padding);
+int ovl_ensure_verity_loaded(const struct path *path);
+int ovl_validate_verity(struct ovl_fs *ofs,
+			const struct path *metapath,
+			const struct path *datapath);
+int ovl_get_verity_digest(struct ovl_fs *ofs, const struct path *src,
+			  struct ovl_metacopy *metacopy);
+int ovl_sync_status(struct ovl_fs *ofs);
+
+static inline void ovl_set_flag(unsigned long flag, struct inode *inode)
+{
+	set_bit(flag, &OVL_I(inode)->flags);
+}
+
+static inline void ovl_clear_flag(unsigned long flag, struct inode *inode)
+{
+	clear_bit(flag, &OVL_I(inode)->flags);
+}
+
+static inline bool ovl_test_flag(unsigned long flag, struct inode *inode)
+{
+	return test_bit(flag, &OVL_I(inode)->flags);
+}
+
+static inline bool ovl_is_impuredir(struct super_block *sb,
+				    struct dentry *upperdentry)
+{
+	struct ovl_fs *ofs = OVL_FS(sb);
+	struct path upperpath = {
+		.dentry = upperdentry,
+		.mnt = ovl_upper_mnt(ofs),
+	};
+
+	return ovl_get_dir_xattr_val(ofs, &upperpath, OVL_XATTR_IMPURE) == 'y';
+}
+
+static inline char ovl_get_opaquedir_val(struct ovl_fs *ofs,
+					 const struct path *path)
+{
+	return ovl_get_dir_xattr_val(ofs, path, OVL_XATTR_OPAQUE);
+}
+
+static inline bool ovl_redirect_follow(struct ovl_fs *ofs)
+{
+	return ofs->config.redirect_mode != OVL_REDIRECT_NOFOLLOW;
+}
+
+static inline bool ovl_redirect_dir(struct ovl_fs *ofs)
+{
+	return ofs->config.redirect_mode == OVL_REDIRECT_ON;
+}
+
+static inline bool ovl_origin_uuid(struct ovl_fs *ofs)
+{
+	return ofs->config.uuid != OVL_UUID_OFF;
+}
+
+static inline bool ovl_has_fsid(struct ovl_fs *ofs)
+{
+	return ofs->config.uuid == OVL_UUID_ON ||
+	       ofs->config.uuid == OVL_UUID_AUTO;
+}
+
+/*
+ * With xino=auto, we do best effort to keep all inodes on same st_dev and
+ * d_ino consistent with st_ino.
+ * With xino=on, we do the same effort but we warn if we failed.
+ */
+static inline bool ovl_xino_warn(struct ovl_fs *ofs)
+{
+	return ofs->config.xino == OVL_XINO_ON;
+}
+
+static inline bool ovl_should_sync(struct ovl_fs *ofs)
+{
+	return ofs->config.fsync_mode != OVL_FSYNC_VOLATILE;
+}
+
+static inline bool ovl_should_sync_metadata(struct ovl_fs *ofs)
+{
+	return ofs->config.fsync_mode == OVL_FSYNC_STRICT;
+}
+
+static inline bool ovl_is_volatile(struct ovl_config *config)
+{
+	return config->fsync_mode == OVL_FSYNC_VOLATILE;
+}
+
+/*
+ * To avoid regressions in existing setups with overlay lower offline changes,
+ * we allow lower changes only if none of the new features are used.
+ */
+static inline bool ovl_allow_offline_changes(struct ovl_fs *ofs)
+{
+	return (!ofs->config.index && !ofs->config.metacopy &&
+		!ovl_redirect_dir(ofs) && !ovl_xino_warn(ofs));
+}
+
+/* All layers on same fs? */
+static inline bool ovl_same_fs(struct ovl_fs *ofs)
+{
+	return ofs->xino_mode == 0;
+}
+
+/* All overlay inodes have same st_dev? */
+static inline bool ovl_same_dev(struct ovl_fs *ofs)
+{
+	return ofs->xino_mode >= 0;
+}
+
+static inline unsigned int ovl_xino_bits(struct ovl_fs *ofs)
+{
+	return ovl_same_dev(ofs) ? ofs->xino_mode : 0;
+}
+
+static inline void ovl_inode_lock(struct inode *inode)
+{
+	mutex_lock(&OVL_I(inode)->lock);
+}
+
+static inline int ovl_inode_lock_interruptible(struct inode *inode)
+{
+	return mutex_lock_interruptible(&OVL_I(inode)->lock);
+}
+
+static inline void ovl_inode_unlock(struct inode *inode)
+{
+	mutex_unlock(&OVL_I(inode)->lock);
+}
+
+
+/* namei.c */
+int ovl_check_fb_len(struct ovl_fb *fb, int fb_len);
+
+static inline int ovl_check_fh_len(struct ovl_fh *fh, int fh_len)
+{
+	if (fh_len < sizeof(struct ovl_fh))
+		return -EINVAL;
+
+	return ovl_check_fb_len(&fh->fb, fh_len - OVL_FH_WIRE_OFFSET);
+}
+
+bool ovl_uuid_match(struct ovl_fs *ofs, const struct super_block *sb,
+		    const uuid_t *uuid);
+struct dentry *ovl_decode_real_fh(struct ovl_fs *ofs, struct ovl_fh *fh,
+				  struct vfsmount *mnt, bool connected);
+int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected,
+			struct dentry *upperdentry, struct ovl_path **stackp);
+int ovl_verify_set_fh(struct ovl_fs *ofs, struct dentry *dentry,
+		      enum ovl_xattr ox, const struct ovl_fh *fh,
+		      bool is_upper, bool set);
+int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry,
+			    enum ovl_xattr ox, struct dentry *real,
+			    bool is_upper, bool set);
+struct dentry *ovl_index_upper(struct ovl_fs *ofs, struct dentry *index,
+			       bool connected);
+int ovl_verify_index(struct ovl_fs *ofs, struct dentry *index);
+int ovl_get_index_name_fh(const struct ovl_fh *fh, struct qstr *name);
+int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin,
+		       struct qstr *name);
+struct dentry *ovl_get_index_fh(struct ovl_fs *ofs, struct ovl_fh *fh);
+struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
+				struct dentry *origin, bool verify);
+int ovl_path_next(int idx, struct dentry *dentry, struct path *path,
+		  const struct ovl_layer **layer);
+int ovl_verify_lowerdata(struct dentry *dentry);
+struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
+			  unsigned int flags);
+bool ovl_lower_positive(struct dentry *dentry);
+
+static inline int ovl_verify_origin_fh(struct ovl_fs *ofs, struct dentry *upper,
+				       const struct ovl_fh *fh, bool set)
+{
+	return ovl_verify_set_fh(ofs, upper, OVL_XATTR_ORIGIN, fh, false, set);
+}
+
+static inline int ovl_verify_origin(struct ovl_fs *ofs, struct dentry *upper,
+				    struct dentry *origin, bool set)
+{
+	return ovl_verify_origin_xattr(ofs, upper, OVL_XATTR_ORIGIN, origin,
+				       false, set);
+}
+
+static inline int ovl_verify_upper(struct ovl_fs *ofs, struct dentry *index,
+				   struct dentry *upper, bool set)
+{
+	return ovl_verify_origin_xattr(ofs, index, OVL_XATTR_UPPER, upper,
+				       true, set);
+}
+
+/* readdir.c */
+extern const struct file_operations ovl_dir_operations;
+struct file *ovl_dir_real_file(const struct file *file, bool want_upper);
+int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list);
+void ovl_cleanup_whiteouts(struct ovl_fs *ofs, 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(const struct path *realpath);
+int ovl_workdir_cleanup(struct ovl_fs *ofs, struct dentry *parent,
+			struct vfsmount *mnt, struct dentry *dentry, int level);
+int ovl_indexdir_cleanup(struct ovl_fs *ofs);
+
+/*
+ * Can we iterate real dir directly?
+ *
+ * Non-merge dir may contain whiteouts from a time it was a merge upper, before
+ * lower dir was removed under it and possibly before it was rotated from upper
+ * to lower layer.
+ */
+static inline bool ovl_dir_is_real(struct inode *dir)
+{
+	return !ovl_test_flag(OVL_WHITEOUTS, dir);
+}
+
+/* inode.c */
+int ovl_set_nlink_upper(struct dentry *dentry);
+int ovl_set_nlink_lower(struct dentry *dentry);
+unsigned int ovl_get_nlink(struct ovl_fs *ofs, struct dentry *lowerdentry,
+			   struct dentry *upperdentry,
+			   unsigned int fallback);
+int ovl_permission(struct mnt_idmap *idmap, struct inode *inode,
+		   int mask);
+
+#ifdef CONFIG_FS_POSIX_ACL
+struct posix_acl *do_ovl_get_acl(struct mnt_idmap *idmap,
+				 struct inode *inode, int type,
+				 bool rcu, bool noperm);
+static inline struct posix_acl *ovl_get_inode_acl(struct inode *inode, int type,
+						  bool rcu)
+{
+	return do_ovl_get_acl(&nop_mnt_idmap, inode, type, rcu, true);
+}
+static inline struct posix_acl *ovl_get_acl(struct mnt_idmap *idmap,
+					    struct dentry *dentry, int type)
+{
+	return do_ovl_get_acl(idmap, d_inode(dentry), type, false, false);
+}
+int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
+		struct posix_acl *acl, int type);
+struct posix_acl *ovl_get_acl_path(const struct path *path,
+				   const char *acl_name, bool noperm);
+#else
+#define ovl_get_inode_acl	NULL
+#define ovl_get_acl		NULL
+#define ovl_set_acl		NULL
+static inline struct posix_acl *ovl_get_acl_path(const struct path *path,
+						 const char *acl_name,
+						 bool noperm)
+{
+	return NULL;
+}
+#endif
+
+int ovl_update_time(struct inode *inode, enum fs_update_time type,
+		unsigned int flags);
+bool ovl_is_private_xattr(struct super_block *sb, const char *name);
+
+struct ovl_inode_params {
+	struct inode *newinode;
+	struct dentry *upperdentry;
+	struct ovl_entry *oe;
+	bool index;
+	char *redirect;
+	char *lowerdata_redirect;
+};
+void ovl_inode_init(struct inode *inode, struct ovl_inode_params *oip,
+		    unsigned long ino, int fsid);
+struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev);
+struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real,
+			       bool is_upper);
+bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir);
+struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir);
+struct inode *ovl_get_inode(struct super_block *sb,
+			    struct ovl_inode_params *oip);
+void ovl_copyattr(struct inode *to);
+
+/* vfs fileattr flags read from overlay.protattr xattr to ovl inode */
+#define OVL_PROT_I_FLAGS_MASK  (S_APPEND | S_IMMUTABLE)
+/* vfs fileattr flags copied from real to ovl inode */
+#define OVL_FATTR_I_FLAGS_MASK (OVL_PROT_I_FLAGS_MASK | S_SYNC | S_NOATIME)
+/* vfs inode flags copied from real to ovl inode */
+#define OVL_COPY_I_FLAGS_MASK  (OVL_FATTR_I_FLAGS_MASK | S_CASEFOLD)
+
+/*
+ * fileattr flags copied from lower to upper inode on copy up.
+ * We cannot copy up immutable/append-only flags, because that would prevent
+ * linking temp inode to upper dir, so we store them in xattr instead.
+ */
+#define OVL_COPY_FS_FLAGS_MASK	(FS_SYNC_FL | FS_NOATIME_FL)
+#define OVL_COPY_FSX_FLAGS_MASK	(FS_XFLAG_SYNC | FS_XFLAG_NOATIME)
+#define OVL_PROT_FS_FLAGS_MASK  (FS_APPEND_FL | FS_IMMUTABLE_FL)
+#define OVL_PROT_FSX_FLAGS_MASK (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE)
+
+void ovl_check_protattr(struct inode *inode, struct dentry *upper);
+int ovl_set_protattr(struct inode *inode, struct dentry *upper,
+		      struct file_kattr *fa);
+
+static inline void ovl_copyflags(struct inode *from, struct inode *to)
+{
+	unsigned int mask = OVL_COPY_I_FLAGS_MASK;
+
+	inode_set_flags(to, from->i_flags & mask, mask);
+}
+
+/* dir.c */
+extern const struct inode_operations ovl_dir_inode_operations;
+int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
+			     struct dentry *dentry);
+struct ovl_cattr {
+	dev_t rdev;
+	umode_t mode;
+	const char *link;
+	struct dentry *hardlink;
+};
+
+#define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) })
+
+struct dentry *ovl_create_real(struct ovl_fs *ofs,
+			       struct dentry *parent, struct dentry *newdentry,
+			       struct qstr *qname,
+			       struct ovl_cattr *attr);
+int ovl_cleanup(struct ovl_fs *ofs, struct dentry *workdir, struct dentry *dentry);
+#define OVL_TEMPNAME_SIZE 20
+void ovl_tempname(char name[OVL_TEMPNAME_SIZE]);
+struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
+			       struct ovl_cattr *attr);
+
+/* file.c */
+extern const struct file_operations ovl_file_operations;
+int ovl_real_fileattr_get(const struct path *realpath, struct file_kattr *fa);
+int ovl_real_fileattr_set(const struct path *realpath, struct file_kattr *fa);
+int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
+int ovl_fileattr_set(struct mnt_idmap *idmap,
+		     struct dentry *dentry, struct file_kattr *fa);
+struct ovl_file;
+struct ovl_file *ovl_file_alloc(struct file *realfile);
+void ovl_file_free(struct ovl_file *of);
+
+/* copy_up.c */
+int ovl_copy_up(struct dentry *dentry);
+int ovl_copy_up_with_data(struct dentry *dentry);
+int ovl_maybe_copy_up(struct dentry *dentry, int flags);
+int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new);
+int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat);
+struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode,
+				  bool is_upper);
+struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin);
+int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh,
+		      struct dentry *upper);
+
+/* export.c */
+extern const struct export_operations ovl_export_operations;
+extern const struct export_operations ovl_export_fid_operations;
+
+/* super.c */
+int ovl_fill_super(struct super_block *sb, struct fs_context *fc);
+
+/* Will this overlay be forced to mount/remount ro? */
+static inline bool ovl_force_readonly(struct ovl_fs *ofs)
+{
+	return (!ovl_upper_mnt(ofs) || !ofs->workdir);
+}
+
+/* xattr.c */
+
+const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs);
+int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+		struct iattr *attr);
+int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
+		struct kstat *stat, u32 request_mask, unsigned int flags);
+ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);

linux-7.2.3/fs/overlayfs/ovl_entry.h

@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright (C) 2011 Novell Inc.
+ * Copyright (C) 2016 Red Hat, Inc.
+ */
+
+struct ovl_config {
+	char *upperdir;
+	char *workdir;
+	char **lowerdirs;
+	bool default_permissions;
+	int redirect_mode;
+	int verity_mode;
+	bool index;
+	int uuid;
+	bool nfs_export;
+	int xino;
+	bool metacopy;
+	bool userxattr;
+	int fsync_mode;
+};
+
+struct ovl_sb {
+	struct super_block *sb;
+	dev_t pseudo_dev;
+	/* Unusable (conflicting) uuid */
+	bool bad_uuid;
+	/* Used as a lower layer (but maybe also as upper) */
+	bool is_lower;
+};
+
+struct ovl_layer {
+	/* ovl_free_fs() relies on @mnt being the first member! */
+	struct vfsmount *mnt;
+	/* Trap in ovl inode cache */
+	struct inode *trap;
+	struct ovl_sb *fs;
+	/* Index of this layer in fs root (upper idx == 0) */
+	int idx;
+	/* One fsid per unique underlying sb (upper fsid == 0) */
+	int fsid;
+	/* xwhiteouts were found on this layer */
+	bool has_xwhiteouts;
+};
+
+struct ovl_path {
+	const struct ovl_layer *layer;
+	struct dentry *dentry;
+};
+
+struct ovl_entry {
+	unsigned int __numlower;
+	struct ovl_path __lowerstack[] __counted_by(__numlower);
+};
+
+/* private information held for overlayfs's superblock */
+struct ovl_fs {
+	unsigned int numlayer;
+	/* Number of unique fs among layers including upper fs */
+	unsigned int numfs;
+	/* Number of data-only lower layers */
+	unsigned int numdatalayer;
+	struct ovl_layer *layers;
+	struct ovl_sb *fs;
+	/* workbasedir is the path at workdir= mount option */
+	struct dentry *workbasedir;
+	/* workdir is the 'work' or 'index' directory under workbasedir */
+	struct dentry *workdir;
+	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;
+	bool nofh;
+	/* Did we take the inuse lock? */
+	bool upperdir_locked;
+	bool workdir_locked;
+	/* Traps in ovl inode cache */
+	struct inode *workbasedir_trap;
+	struct inode *workdir_trap;
+	/* -1: disabled, 0: same fs, 1..32: number of unused ino bits */
+	int xino_mode;
+	/* For allocation of non-persistent inode numbers */
+	atomic_long_t last_ino;
+	/* Shared whiteout cache */
+	struct dentry *whiteout;
+	bool no_shared_whiteout;
+	struct mutex whiteout_lock;
+	/* r/o snapshot of upperdir sb's only taken on volatile mounts */
+	errseq_t errseq;
+	bool casefold;
+};
+
+/* Number of lower layers, not including data-only layers */
+static inline unsigned int ovl_numlowerlayer(struct ovl_fs *ofs)
+{
+	return ofs->numlayer - ofs->numdatalayer - 1;
+}
+
+static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs)
+{
+	return ofs->layers[0].mnt;
+}
+
+static inline struct mnt_idmap *ovl_upper_mnt_idmap(struct ovl_fs *ofs)
+{
+	return mnt_idmap(ovl_upper_mnt(ofs));
+}
+
+extern struct file_system_type ovl_fs_type;
+
+static inline struct ovl_fs *OVL_FS(struct super_block *sb)
+{
+	if (IS_ENABLED(CONFIG_OVERLAY_FS_DEBUG))
+		WARN_ON_ONCE(sb->s_type != &ovl_fs_type);
+
+	return (struct ovl_fs *)sb->s_fs_info;
+}
+
+static inline unsigned int ovl_numlower(struct ovl_entry *oe)
+{
+	return oe ? oe->__numlower : 0;
+}
+
+static inline struct ovl_path *ovl_lowerstack(struct ovl_entry *oe)
+{
+	return ovl_numlower(oe) ? oe->__lowerstack : NULL;
+}
+
+static inline struct ovl_path *ovl_lowerpath(struct ovl_entry *oe)
+{
+	return ovl_lowerstack(oe);
+}
+
+static inline struct ovl_path *ovl_lowerdata(struct ovl_entry *oe)
+{
+	struct ovl_path *lowerstack = ovl_lowerstack(oe);
+
+	return lowerstack ? &lowerstack[oe->__numlower - 1] : NULL;
+}
+
+/* May return NULL if lazy lookup of lowerdata is needed */
+static inline struct dentry *ovl_lowerdata_dentry(struct ovl_entry *oe)
+{
+	struct ovl_path *lowerdata = ovl_lowerdata(oe);
+
+	return lowerdata ? READ_ONCE(lowerdata->dentry) : NULL;
+}
+
+/* private information held for every overlayfs dentry */
+static inline unsigned long *OVL_E_FLAGS(struct dentry *dentry)
+{
+	return (unsigned long *) &dentry->d_fsdata;
+}
+
+struct ovl_inode {
+	union {
+		struct ovl_dir_cache *cache;	/* directory */
+		const char *lowerdata_redirect;	/* regular file */
+	};
+	const char *redirect;
+	u64 version;
+	unsigned long flags;
+	struct inode vfs_inode;
+	struct dentry *__upperdentry;
+	struct ovl_entry *oe;
+
+	/* 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 ovl_entry *OVL_I_E(struct inode *inode)
+{
+	return inode ? OVL_I(inode)->oe : NULL;
+}
+
+static inline struct ovl_entry *OVL_E(struct dentry *dentry)
+{
+	return OVL_I_E(d_inode(dentry));
+}
+
+static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
+{
+	return READ_ONCE(oi->__upperdentry);
+}

linux-7.2.3/fs/overlayfs/params.h

@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
+
+struct ovl_fs;
+struct ovl_config;
+
+extern const struct fs_parameter_spec ovl_parameter_spec[];
+extern const struct constant_table ovl_parameter_redirect_dir[];
+
+/* The set of options that user requested explicitly via mount options */
+struct ovl_opt_set {
+	bool metacopy;
+	bool redirect;
+	bool nfs_export;
+	bool index;
+};
+
+#define OVL_MAX_STACK 500
+
+struct ovl_fs_context_layer {
+	char *name;
+	struct path path;
+};
+
+struct ovl_fs_context {
+	struct path upper;
+	struct path work;
+	size_t capacity;
+	size_t nr; /* includes nr_data */
+	size_t nr_data;
+	struct ovl_opt_set set;
+	struct ovl_fs_context_layer *lower;
+	char *lowerdir_all; /* user provided lowerdir string */
+	bool casefold_set;
+};
+
+int ovl_init_fs_context(struct fs_context *fc);
+void ovl_free_fs(struct ovl_fs *ofs);
+int ovl_fs_params_verify(const struct ovl_fs_context *ctx,
+			 struct ovl_config *config);
+int ovl_show_options(struct seq_file *m, struct dentry *dentry);
+const char *ovl_xino_mode(struct ovl_config *config);

linux-7.2.3/fs/overlayfs/xattrs.c

@@ -0,0 +1,261 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/fs.h>
+#include <linux/xattr.h>
+#include "overlayfs.h"
+
+static bool ovl_is_escaped_xattr(struct super_block *sb, const char *name)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	if (ofs->config.userxattr)
+		return strncmp(name, OVL_XATTR_ESCAPE_USER_PREFIX,
+			       OVL_XATTR_ESCAPE_USER_PREFIX_LEN) == 0;
+	else
+		return strncmp(name, OVL_XATTR_ESCAPE_TRUSTED_PREFIX,
+			       OVL_XATTR_ESCAPE_TRUSTED_PREFIX_LEN) == 0;
+}
+
+static bool ovl_is_own_xattr(struct super_block *sb, const char *name)
+{
+	struct ovl_fs *ofs = OVL_FS(sb);
+
+	if (ofs->config.userxattr)
+		return strncmp(name, OVL_XATTR_USER_PREFIX,
+			       OVL_XATTR_USER_PREFIX_LEN) == 0;
+	else
+		return strncmp(name, OVL_XATTR_TRUSTED_PREFIX,
+			       OVL_XATTR_TRUSTED_PREFIX_LEN) == 0;
+}
+
+bool ovl_is_private_xattr(struct super_block *sb, const char *name)
+{
+	return ovl_is_own_xattr(sb, name) && !ovl_is_escaped_xattr(sb, name);
+}
+
+static int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+			 const void *value, size_t size, int flags)
+{
+	int err;
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
+	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
+	struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry);
+	struct path realpath;
+
+	if (!value && !upperdentry) {
+		ovl_path_lower(dentry, &realpath);
+		with_ovl_creds(dentry->d_sb)
+			err = vfs_getxattr(mnt_idmap(realpath.mnt), realdentry, name, NULL, 0);
+		if (err < 0)
+			goto out;
+	}
+
+	if (!upperdentry) {
+		err = ovl_copy_up(dentry);
+		if (err)
+			goto out;
+
+		realdentry = ovl_dentry_upper(dentry);
+	}
+
+	err = ovl_want_write(dentry);
+	if (err)
+		goto out;
+
+	with_ovl_creds(dentry->d_sb) {
+		if (value) {
+			err = ovl_do_setxattr(ofs, realdentry, name, value, size, flags);
+		} else {
+			WARN_ON(flags != XATTR_REPLACE);
+			err = ovl_do_removexattr(ofs, realdentry, name);
+		}
+	}
+	ovl_drop_write(dentry);
+
+	/* copy c/mtime */
+	ovl_copyattr(inode);
+out:
+	return err;
+}
+
+static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
+			 void *value, size_t size)
+{
+	struct path realpath;
+
+	ovl_i_path_real(inode, &realpath);
+	with_ovl_creds(dentry->d_sb)
+		return vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size);
+}
+
+static bool ovl_can_list(struct super_block *sb, const char *s)
+{
+	/* Never list private (.overlay) */
+	if (ovl_is_private_xattr(sb, s))
+		return false;
+
+	/* List all non-trusted xattrs */
+	if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
+		return true;
+
+	/* list other trusted for superuser only */
+	return 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);
+	struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
+	ssize_t res;
+	size_t len;
+	char *s;
+	size_t prefix_len, name_len;
+
+	with_ovl_creds(dentry->d_sb)
+		res = vfs_listxattr(realdentry, list, size);
+	if (res <= 0 || size == 0)
+		return res;
+
+	prefix_len = ofs->config.userxattr ?
+		OVL_XATTR_USER_PREFIX_LEN : OVL_XATTR_TRUSTED_PREFIX_LEN;
+
+	/* 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(dentry->d_sb, s)) {
+			res -= slen;
+			memmove(s, s + slen, len);
+		} else if (ovl_is_escaped_xattr(dentry->d_sb, s)) {
+			res -= OVL_XATTR_ESCAPE_PREFIX_LEN;
+			name_len = slen - prefix_len - OVL_XATTR_ESCAPE_PREFIX_LEN;
+			s += prefix_len;
+			memmove(s, s + OVL_XATTR_ESCAPE_PREFIX_LEN, name_len + len);
+			s += name_len;
+		} else {
+			s += slen;
+		}
+	}
+
+	return res;
+}
+
+static char *ovl_xattr_escape_name(const char *prefix, const char *name)
+{
+	size_t prefix_len = strlen(prefix);
+	size_t name_len = strlen(name);
+	size_t escaped_len;
+	char *escaped, *s;
+
+	escaped_len = prefix_len + OVL_XATTR_ESCAPE_PREFIX_LEN + name_len;
+	if (escaped_len > XATTR_NAME_MAX)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	escaped = kmalloc(escaped_len + 1, GFP_KERNEL);
+	if (escaped == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	s = escaped;
+	memcpy(s, prefix, prefix_len);
+	s += prefix_len;
+	memcpy(s, OVL_XATTR_ESCAPE_PREFIX, OVL_XATTR_ESCAPE_PREFIX_LEN);
+	s += OVL_XATTR_ESCAPE_PREFIX_LEN;
+	memcpy(s, name, name_len + 1);
+
+	return escaped;
+}
+
+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)
+{
+	char *escaped;
+	int r;
+
+	escaped = ovl_xattr_escape_name(handler->prefix, name);
+	if (IS_ERR(escaped))
+		return PTR_ERR(escaped);
+
+	r = ovl_xattr_get(dentry, inode, escaped, buffer, size);
+
+	kfree(escaped);
+
+	return r;
+}
+
+static int ovl_own_xattr_set(const struct xattr_handler *handler,
+			     struct mnt_idmap *idmap,
+			     struct dentry *dentry, struct inode *inode,
+			     const char *name, const void *value,
+			     size_t size, int flags)
+{
+	char *escaped;
+	int r;
+
+	escaped = ovl_xattr_escape_name(handler->prefix, name);
+	if (IS_ERR(escaped))
+		return PTR_ERR(escaped);
+
+	r = ovl_xattr_set(dentry, inode, escaped, value, size, flags);
+
+	kfree(escaped);
+
+	return r;
+}
+
+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 mnt_idmap *idmap,
+			       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 ovl_own_trusted_xattr_handler = {
+	.prefix	= OVL_XATTR_TRUSTED_PREFIX,
+	.get = ovl_own_xattr_get,
+	.set = ovl_own_xattr_set,
+};
+
+static const struct xattr_handler ovl_own_user_xattr_handler = {
+	.prefix	= OVL_XATTR_USER_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 * const ovl_trusted_xattr_handlers[] = {
+	&ovl_own_trusted_xattr_handler,
+	&ovl_other_xattr_handler,
+	NULL
+};
+
+static const struct xattr_handler * const ovl_user_xattr_handlers[] = {
+	&ovl_own_user_xattr_handler,
+	&ovl_other_xattr_handler,
+	NULL
+};
+
+const struct xattr_handler * const *ovl_xattr_handlers(struct ovl_fs *ofs)
+{
+	return ofs->config.userxattr ? ovl_user_xattr_handlers :
+		ovl_trusted_xattr_handlers;
+}