Contributors: 58
Author Tokens Token Proportion Commits Commit Proportion
Christian Göttsche 828 12.98% 2 1.26%
Andreas Gruenbacher 711 11.15% 15 9.43%
Christian Brauner 684 10.72% 18 11.32%
Al Viro 597 9.36% 16 10.06%
Linus Torvalds 537 8.42% 7 4.40%
Aristeu Sergio Rozanski Filho 459 7.20% 1 0.63%
Christoph Hellwig 319 5.00% 3 1.89%
James Morris 282 4.42% 1 0.63%
Andrew Morton 262 4.11% 9 5.66%
van der Linden, Frank 198 3.10% 2 1.26%
Heiko Carstens 198 3.10% 2 1.26%
Stefan Roesch 155 2.43% 2 1.26%
David P. Quigley 139 2.18% 3 1.89%
Jeff Layton 107 1.68% 10 6.29%
Mimi Zohar 102 1.60% 1 0.63%
Eric Biggers 92 1.44% 1 0.63%
Hugh Dickins 83 1.30% 4 2.52%
Tycho Andersen 68 1.07% 1 0.63%
Stephen D. Smalley 68 1.07% 2 1.26%
Miklos Szeredi 65 1.02% 2 1.26%
David Howells 61 0.96% 3 1.89%
Dave Hansen 52 0.82% 1 0.63%
Nathan Scott 36 0.56% 3 1.89%
Linus Torvalds (pre-git) 32 0.50% 9 5.66%
Dave Kleikamp 31 0.49% 3 1.89%
Bill Nottingham 30 0.47% 1 0.63%
Eric Paris 22 0.34% 1 0.63%
Eric W. Biedermann 19 0.30% 2 1.26%
Andi Kleen 16 0.25% 1 0.63%
Jan Blunck 16 0.25% 2 1.26%
Dustin Kirkland 11 0.17% 1 0.63%
Roberto Sassu 10 0.16% 1 0.63%
Dmitry Kasatkin 9 0.14% 1 0.63%
Greg Kroah-Hartman 8 0.13% 3 1.89%
Robert Love 8 0.13% 1 0.63%
Sasha Levin 7 0.11% 1 0.63%
Mateusz Guzik 7 0.11% 1 0.63%
Jens Axboe 6 0.09% 1 0.63%
Andries E. Brouwer 6 0.09% 1 0.63%
Ondrej Mosnáček 4 0.06% 1 0.63%
Daniel Xu 4 0.06% 2 1.26%
Stephen Hemminger 4 0.06% 1 0.63%
Colin Ian King 3 0.05% 1 0.63%
Wedson Almeida Filho 3 0.05% 1 0.63%
David Rientjes 2 0.03% 1 0.63%
Theodore Y. Ts'o 2 0.03% 1 0.63%
Paul Moore 2 0.03% 1 0.63%
Richard Weinberger 2 0.03% 1 0.63%
Michal Hocko 2 0.03% 1 0.63%
Serge E. Hallyn 1 0.02% 1 0.63%
Amy Griffis 1 0.02% 1 0.63%
Paul Gortmaker 1 0.02% 1 0.63%
Sergei Trofimovich 1 0.02% 1 0.63%
Casey Schaufler 1 0.02% 1 0.63%
Daniel Drake 1 0.02% 1 0.63%
Tejun Heo 1 0.02% 1 0.63%
Satyam Sharma 1 0.02% 1 0.63%
Thomas Gleixner 1 0.02% 1 0.63%
Total 6378 159 
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553
// SPDX-License-Identifier: GPL-2.0-only
/*
  File: fs/xattr.c

  Extended attribute handling.

  Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org>
  Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com>
  Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
 */
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fsnotify.h>
#include <linux/audit.h>
#include <linux/vmalloc.h>
#include <linux/posix_acl_xattr.h>

#include <linux/uaccess.h>

#include "internal.h"

static const char *
strcmp_prefix(const char *a, const char *a_prefix)
{
	while (*a_prefix && *a == *a_prefix) {
		a++;
		a_prefix++;
	}
	return *a_prefix ? NULL : a;
}

/*
 * In order to implement different sets of xattr operations for each xattr
 * prefix, a filesystem should create a null-terminated array of struct
 * xattr_handler (one for each prefix) and hang a pointer to it off of the
 * s_xattr field of the superblock.
 */
#define for_each_xattr_handler(handlers, handler)		\
	if (handlers)						\
		for ((handler) = *(handlers)++;			\
			(handler) != NULL;			\
			(handler) = *(handlers)++)

/*
 * Find the xattr_handler with the matching prefix.
 */
static const struct xattr_handler *
xattr_resolve_name(struct inode *inode, const char **name)
{
	const struct xattr_handler * const *handlers = inode->i_sb->s_xattr;
	const struct xattr_handler *handler;

	if (!(inode->i_opflags & IOP_XATTR)) {
		if (unlikely(is_bad_inode(inode)))
			return ERR_PTR(-EIO);
		return ERR_PTR(-EOPNOTSUPP);
	}
	for_each_xattr_handler(handlers, handler) {
		const char *n;

		n = strcmp_prefix(*name, xattr_prefix(handler));
		if (n) {
			if (!handler->prefix ^ !*n) {
				if (*n)
					continue;
				return ERR_PTR(-EINVAL);
			}
			*name = n;
			return handler;
		}
	}
	return ERR_PTR(-EOPNOTSUPP);
}

/**
 * may_write_xattr - check whether inode allows writing xattr
 * @idmap: idmap of the mount the inode was found from
 * @inode: the inode on which to set an xattr
 *
 * Check whether the inode allows writing xattrs. Specifically, we can never
 * set or remove an extended attribute on a read-only filesystem  or on an
 * immutable / append-only inode.
 *
 * We also need to ensure that the inode has a mapping in the mount to
 * not risk writing back invalid i_{g,u}id values.
 *
 * Return: On success zero is returned. On error a negative errno is returned.
 */
int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode)
{
	if (IS_IMMUTABLE(inode))
		return -EPERM;
	if (IS_APPEND(inode))
		return -EPERM;
	if (HAS_UNMAPPED_ID(idmap, inode))
		return -EPERM;
	return 0;
}

/*
 * Check permissions for extended attribute access.  This is a bit complicated
 * because different namespaces have very different rules.
 */
static int
xattr_permission(struct mnt_idmap *idmap, struct inode *inode,
		 const char *name, int mask)
{
	if (mask & MAY_WRITE) {
		int ret;

		ret = may_write_xattr(idmap, inode);
		if (ret)
			return ret;
	}

	/*
	 * No restriction for security.* and system.* from the VFS.  Decision
	 * on these is left to the underlying filesystem / security module.
	 */
	if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) ||
	    !strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
		return 0;

	/*
	 * The trusted.* namespace can only be accessed by privileged users.
	 */
	if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
		if (!capable(CAP_SYS_ADMIN))
			return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
		return 0;
	}

	/*
	 * In the user.* namespace, only regular files and directories can have
	 * extended attributes. For sticky directories, only the owner and
	 * privileged users can write attributes.
	 */
	if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
		if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
			return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
		if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
		    (mask & MAY_WRITE) &&
		    !inode_owner_or_capable(idmap, inode))
			return -EPERM;
	}

	return inode_permission(idmap, inode, mask);
}

/*
 * Look for any handler that deals with the specified namespace.
 */
int
xattr_supports_user_prefix(struct inode *inode)
{
	const struct xattr_handler * const *handlers = inode->i_sb->s_xattr;
	const struct xattr_handler *handler;

	if (!(inode->i_opflags & IOP_XATTR)) {
		if (unlikely(is_bad_inode(inode)))
			return -EIO;
		return -EOPNOTSUPP;
	}

	for_each_xattr_handler(handlers, handler) {
		if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX,
			     XATTR_USER_PREFIX_LEN))
			return 0;
	}

	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(xattr_supports_user_prefix);

int
__vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
	       struct inode *inode, const char *name, const void *value,
	       size_t size, int flags)
{
	const struct xattr_handler *handler;

	if (is_posix_acl_xattr(name))
		return -EOPNOTSUPP;

	handler = xattr_resolve_name(inode, &name);
	if (IS_ERR(handler))
		return PTR_ERR(handler);
	if (!handler->set)
		return -EOPNOTSUPP;
	if (size == 0)
		value = "";  /* empty EA, do not remove */
	return handler->set(handler, idmap, dentry, inode, name, value,
			    size, flags);
}
EXPORT_SYMBOL(__vfs_setxattr);

/**
 *  __vfs_setxattr_noperm - perform setxattr operation without performing
 *  permission checks.
 *
 *  @idmap: idmap of the mount the inode was found from
 *  @dentry: object to perform setxattr on
 *  @name: xattr name to set
 *  @value: value to set @name to
 *  @size: size of @value
 *  @flags: flags to pass into filesystem operations
 *
 *  returns the result of the internal setxattr or setsecurity operations.
 *
 *  This function requires the caller to lock the inode's i_mutex before it
 *  is executed. It also assumes that the caller will make the appropriate
 *  permission checks.
 */
int __vfs_setxattr_noperm(struct mnt_idmap *idmap,
			  struct dentry *dentry, const char *name,
			  const void *value, size_t size, int flags)
{
	struct inode *inode = dentry->d_inode;
	int error = -EAGAIN;
	int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
				   XATTR_SECURITY_PREFIX_LEN);

	if (issec)
		inode->i_flags &= ~S_NOSEC;
	if (inode->i_opflags & IOP_XATTR) {
		error = __vfs_setxattr(idmap, dentry, inode, name, value,
				       size, flags);
		if (!error) {
			fsnotify_xattr(dentry);
			security_inode_post_setxattr(dentry, name, value,
						     size, flags);
		}
	} else {
		if (unlikely(is_bad_inode(inode)))
			return -EIO;
	}
	if (error == -EAGAIN) {
		error = -EOPNOTSUPP;

		if (issec) {
			const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;

			error = security_inode_setsecurity(inode, suffix, value,
							   size, flags);
			if (!error)
				fsnotify_xattr(dentry);
		}
	}

	return error;
}

/**
 * __vfs_setxattr_locked - set an extended attribute while holding the inode
 * lock
 *
 *  @idmap: idmap of the mount of the target inode
 *  @dentry: object to perform setxattr on
 *  @name: xattr name to set
 *  @value: value to set @name to
 *  @size: size of @value
 *  @flags: flags to pass into filesystem operations
 *  @delegated_inode: on return, will contain an inode pointer that
 *  a delegation was broken on, NULL if none.
 */
int
__vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry,
		      const char *name, const void *value, size_t size,
		      int flags, struct inode **delegated_inode)
{
	struct inode *inode = dentry->d_inode;
	int error;

	error = xattr_permission(idmap, inode, name, MAY_WRITE);
	if (error)
		return error;

	error = security_inode_setxattr(idmap, dentry, name, value, size,
					flags);
	if (error)
		goto out;

	error = try_break_deleg(inode, delegated_inode);
	if (error)
		goto out;

	error = __vfs_setxattr_noperm(idmap, dentry, name, value,
				      size, flags);

out:
	return error;
}
EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);

int
vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
	     const char *name, const void *value, size_t size, int flags)
{
	struct inode *inode = dentry->d_inode;
	struct inode *delegated_inode = NULL;
	const void  *orig_value = value;
	int error;

	if (size && strcmp(name, XATTR_NAME_CAPS) == 0) {
		error = cap_convert_nscap(idmap, dentry, &value, size);
		if (error < 0)
			return error;
		size = error;
	}

retry_deleg:
	inode_lock(inode);
	error = __vfs_setxattr_locked(idmap, dentry, name, value, size,
				      flags, &delegated_inode);
	inode_unlock(inode);

	if (delegated_inode) {
		error = break_deleg_wait(&delegated_inode);
		if (!error)
			goto retry_deleg;
	}
	if (value != orig_value)
		kfree(value);

	return error;
}
EXPORT_SYMBOL_GPL(vfs_setxattr);

static ssize_t
xattr_getsecurity(struct mnt_idmap *idmap, struct inode *inode,
		  const char *name, void *value, size_t size)
{
	void *buffer = NULL;
	ssize_t len;

	if (!value || !size) {
		len = security_inode_getsecurity(idmap, inode, name,
						 &buffer, false);
		goto out_noalloc;
	}

	len = security_inode_getsecurity(idmap, inode, name, &buffer,
					 true);
	if (len < 0)
		return len;
	if (size < len) {
		len = -ERANGE;
		goto out;
	}
	memcpy(value, buffer, len);
out:
	kfree(buffer);
out_noalloc:
	return len;
}

/*
 * vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr
 *
 * Allocate memory, if not already allocated, or re-allocate correct size,
 * before retrieving the extended attribute.  The xattr value buffer should
 * always be freed by the caller, even on error.
 *
 * Returns the result of alloc, if failed, or the getxattr operation.
 */
int
vfs_getxattr_alloc(struct mnt_idmap *idmap, struct dentry *dentry,
		   const char *name, char **xattr_value, size_t xattr_size,
		   gfp_t flags)
{
	const struct xattr_handler *handler;
	struct inode *inode = dentry->d_inode;
	char *value = *xattr_value;
	int error;

	error = xattr_permission(idmap, inode, name, MAY_READ);
	if (error)
		return error;

	handler = xattr_resolve_name(inode, &name);
	if (IS_ERR(handler))
		return PTR_ERR(handler);
	if (!handler->get)
		return -EOPNOTSUPP;
	error = handler->get(handler, dentry, inode, name, NULL, 0);
	if (error < 0)
		return error;

	if (!value || (error > xattr_size)) {
		value = krealloc(*xattr_value, error + 1, flags);
		if (!value)
			return -ENOMEM;
		memset(value, 0, error + 1);
	}

	error = handler->get(handler, dentry, inode, name, value, error);
	*xattr_value = value;
	return error;
}

ssize_t
__vfs_getxattr(struct dentry *dentry, struct inode *inode, const char *name,
	       void *value, size_t size)
{
	const struct xattr_handler *handler;

	if (is_posix_acl_xattr(name))
		return -EOPNOTSUPP;

	handler = xattr_resolve_name(inode, &name);
	if (IS_ERR(handler))
		return PTR_ERR(handler);
	if (!handler->get)
		return -EOPNOTSUPP;
	return handler->get(handler, dentry, inode, name, value, size);
}
EXPORT_SYMBOL(__vfs_getxattr);

ssize_t
vfs_getxattr(struct mnt_idmap *idmap, struct dentry *dentry,
	     const char *name, void *value, size_t size)
{
	struct inode *inode = dentry->d_inode;
	int error;

	error = xattr_permission(idmap, inode, name, MAY_READ);
	if (error)
		return error;

	error = security_inode_getxattr(dentry, name);
	if (error)
		return error;

	if (!strncmp(name, XATTR_SECURITY_PREFIX,
				XATTR_SECURITY_PREFIX_LEN)) {
		const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
		int ret = xattr_getsecurity(idmap, inode, suffix, value,
					    size);
		/*
		 * Only overwrite the return value if a security module
		 * is actually active.
		 */
		if (ret == -EOPNOTSUPP)
			goto nolsm;
		return ret;
	}
nolsm:
	return __vfs_getxattr(dentry, inode, name, value, size);
}
EXPORT_SYMBOL_GPL(vfs_getxattr);

/**
 * vfs_listxattr - retrieve \0 separated list of xattr names
 * @dentry: the dentry from whose inode the xattr names are retrieved
 * @list: buffer to store xattr names into
 * @size: size of the buffer
 *
 * This function returns the names of all xattrs associated with the
 * inode of @dentry.
 *
 * Note, for legacy reasons the vfs_listxattr() function lists POSIX
 * ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the
 * vfs_listxattr() function doesn't check for this flag since a
 * filesystem could implement POSIX ACLs without implementing any other
 * xattrs.
 *
 * However, since all codepaths that remove IOP_XATTR also assign of
 * inode operations that either don't implement or implement a stub
 * ->listxattr() operation.
 *
 * Return: On success, the size of the buffer that was used. On error a
 *         negative error code.
 */
ssize_t
vfs_listxattr(struct dentry *dentry, char *list, size_t size)
{
	struct inode *inode = d_inode(dentry);
	ssize_t error;

	error = security_inode_listxattr(dentry);
	if (error)
		return error;

	if (inode->i_op->listxattr) {
		error = inode->i_op->listxattr(dentry, list, size);
	} else {
		error = security_inode_listsecurity(inode, list, size);
		if (size && error > size)
			error = -ERANGE;
	}
	return error;
}
EXPORT_SYMBOL_GPL(vfs_listxattr);

int
__vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry,
		  const char *name)
{
	struct inode *inode = d_inode(dentry);
	const struct xattr_handler *handler;

	if (is_posix_acl_xattr(name))
		return -EOPNOTSUPP;

	handler = xattr_resolve_name(inode, &name);
	if (IS_ERR(handler))
		return PTR_ERR(handler);
	if (!handler->set)
		return -EOPNOTSUPP;
	return handler->set(handler, idmap, dentry, inode, name, NULL, 0,
			    XATTR_REPLACE);
}
EXPORT_SYMBOL(__vfs_removexattr);

/**
 * __vfs_removexattr_locked - set an extended attribute while holding the inode
 * lock
 *
 *  @idmap: idmap of the mount of the target inode
 *  @dentry: object to perform setxattr on
 *  @name: name of xattr to remove
 *  @delegated_inode: on return, will contain an inode pointer that
 *  a delegation was broken on, NULL if none.
 */
int
__vfs_removexattr_locked(struct mnt_idmap *idmap,
			 struct dentry *dentry, const char *name,
			 struct inode **delegated_inode)
{
	struct inode *inode = dentry->d_inode;
	int error;

	error = xattr_permission(idmap, inode, name, MAY_WRITE);
	if (error)
		return error;

	error = security_inode_removexattr(idmap, dentry, name);
	if (error)
		goto out;

	error = try_break_deleg(inode, delegated_inode);
	if (error)
		goto out;

	error = __vfs_removexattr(idmap, dentry, name);
	if (error)
		return error;

	fsnotify_xattr(dentry);
	security_inode_post_removexattr(dentry, name);

out:
	return error;
}
EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);

int
vfs_removexattr(struct mnt_idmap *idmap, struct dentry *dentry,
		const char *name)
{
	struct inode *inode = dentry->d_inode;
	struct inode *delegated_inode = NULL;
	int error;

retry_deleg:
	inode_lock(inode);
	error = __vfs_removexattr_locked(idmap, dentry,
					 name, &delegated_inode);
	inode_unlock(inode);

	if (delegated_inode) {
		error = break_deleg_wait(&delegated_inode);
		if (!error)
			goto retry_deleg;
	}

	return error;
}
EXPORT_SYMBOL_GPL(vfs_removexattr);

int import_xattr_name(struct xattr_name *kname, const char __user *name)
{
	int error = strncpy_from_user(kname->name, name,
					sizeof(kname->name));
	if (error == 0 || error == sizeof(kname->name))
		return -ERANGE;
	if (error < 0)
		return error;
	return 0;
}

/*
 * Extended attribute SET operations
 */

int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx)
{
	int error;

	if (ctx->flags & ~(XATTR_CREATE|XATTR_REPLACE))
		return -EINVAL;

	error = import_xattr_name(ctx->kname, name);
	if (error)
		return error;

	if (ctx->size) {
		if (ctx->size > XATTR_SIZE_MAX)
			return -E2BIG;

		ctx->kvalue = vmemdup_user(ctx->cvalue, ctx->size);
		if (IS_ERR(ctx->kvalue)) {
			error = PTR_ERR(ctx->kvalue);
			ctx->kvalue = NULL;
		}
	}

	return error;
}

static int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
		struct kernel_xattr_ctx *ctx)
{
	if (is_posix_acl_xattr(ctx->kname->name))
		return do_set_acl(idmap, dentry, ctx->kname->name,
				  ctx->kvalue, ctx->size);

	return vfs_setxattr(idmap, dentry, ctx->kname->name,
			ctx->kvalue, ctx->size, ctx->flags);
}

int file_setxattr(struct file *f, struct kernel_xattr_ctx *ctx)
{
	int error = mnt_want_write_file(f);

	if (!error) {
		audit_file(f);
		error = do_setxattr(file_mnt_idmap(f), f->f_path.dentry, ctx);
		mnt_drop_write_file(f);
	}
	return error;
}

/* unconditionally consumes filename */
int filename_setxattr(int dfd, struct filename *filename,
		      unsigned int lookup_flags, struct kernel_xattr_ctx *ctx)
{
	struct path path;
	int error;

retry:
	error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
	if (error)
		goto out;
	error = mnt_want_write(path.mnt);
	if (!error) {
		error = do_setxattr(mnt_idmap(path.mnt), path.dentry, ctx);
		mnt_drop_write(path.mnt);
	}
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}

out:
	putname(filename);
	return error;
}

static int path_setxattrat(int dfd, const char __user *pathname,
			   unsigned int at_flags, const char __user *name,
			   const void __user *value, size_t size, int flags)
{
	struct xattr_name kname;
	struct kernel_xattr_ctx ctx = {
		.cvalue	= value,
		.kvalue	= NULL,
		.size	= size,
		.kname	= &kname,
		.flags	= flags,
	};
	struct filename *filename;
	unsigned int lookup_flags = 0;
	int error;

	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;

	if (!(at_flags & AT_SYMLINK_NOFOLLOW))
		lookup_flags = LOOKUP_FOLLOW;

	error = setxattr_copy(name, &ctx);
	if (error)
		return error;

	filename = getname_maybe_null(pathname, at_flags);
	if (!filename) {
		CLASS(fd, f)(dfd);
		if (fd_empty(f))
			error = -EBADF;
		else
			error = file_setxattr(fd_file(f), &ctx);
	} else {
		error = filename_setxattr(dfd, filename, lookup_flags, &ctx);
	}
	kvfree(ctx.kvalue);
	return error;
}

SYSCALL_DEFINE6(setxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags,
		const char __user *, name, const struct xattr_args __user *, uargs,
		size_t, usize)
{
	struct xattr_args args = {};
	int error;

	BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0);
	BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST);

	if (unlikely(usize < XATTR_ARGS_SIZE_VER0))
		return -EINVAL;
	if (usize > PAGE_SIZE)
		return -E2BIG;

	error = copy_struct_from_user(&args, sizeof(args), uargs, usize);
	if (error)
		return error;

	return path_setxattrat(dfd, pathname, at_flags, name,
			       u64_to_user_ptr(args.value), args.size,
			       args.flags);
}

SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
		const char __user *, name, const void __user *, value,
		size_t, size, int, flags)
{
	return path_setxattrat(AT_FDCWD, pathname, 0, name, value, size, flags);
}

SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
		const char __user *, name, const void __user *, value,
		size_t, size, int, flags)
{
	return path_setxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name,
			       value, size, flags);
}

SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
		const void __user *,value, size_t, size, int, flags)
{
	return path_setxattrat(fd, NULL, AT_EMPTY_PATH, name,
			       value, size, flags);
}

/*
 * Extended attribute GET operations
 */
static ssize_t
do_getxattr(struct mnt_idmap *idmap, struct dentry *d,
	struct kernel_xattr_ctx *ctx)
{
	ssize_t error;
	char *kname = ctx->kname->name;
	void *kvalue = NULL;

	if (ctx->size) {
		if (ctx->size > XATTR_SIZE_MAX)
			ctx->size = XATTR_SIZE_MAX;
		kvalue = kvzalloc(ctx->size, GFP_KERNEL);
		if (!kvalue)
			return -ENOMEM;
	}

	if (is_posix_acl_xattr(kname))
		error = do_get_acl(idmap, d, kname, kvalue, ctx->size);
	else
		error = vfs_getxattr(idmap, d, kname, kvalue, ctx->size);
	if (error > 0) {
		if (ctx->size && copy_to_user(ctx->value, kvalue, error))
			error = -EFAULT;
	} else if (error == -ERANGE && ctx->size >= XATTR_SIZE_MAX) {
		/* The file system tried to returned a value bigger
		   than XATTR_SIZE_MAX bytes. Not possible. */
		error = -E2BIG;
	}

	kvfree(kvalue);
	return error;
}

ssize_t file_getxattr(struct file *f, struct kernel_xattr_ctx *ctx)
{
	audit_file(f);
	return do_getxattr(file_mnt_idmap(f), f->f_path.dentry, ctx);
}

/* unconditionally consumes filename */
ssize_t filename_getxattr(int dfd, struct filename *filename,
			  unsigned int lookup_flags, struct kernel_xattr_ctx *ctx)
{
	struct path path;
	ssize_t error;
retry:
	error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
	if (error)
		goto out;
	error = do_getxattr(mnt_idmap(path.mnt), path.dentry, ctx);
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
out:
	putname(filename);
	return error;
}

static ssize_t path_getxattrat(int dfd, const char __user *pathname,
			       unsigned int at_flags, const char __user *name,
			       void __user *value, size_t size)
{
	struct xattr_name kname;
	struct kernel_xattr_ctx ctx = {
		.value    = value,
		.size     = size,
		.kname    = &kname,
		.flags    = 0,
	};
	struct filename *filename;
	ssize_t error;

	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;

	error = import_xattr_name(&kname, name);
	if (error)
		return error;

	filename = getname_maybe_null(pathname, at_flags);
	if (!filename) {
		CLASS(fd, f)(dfd);
		if (fd_empty(f))
			return -EBADF;
		return file_getxattr(fd_file(f), &ctx);
	} else {
		int lookup_flags = 0;
		if (!(at_flags & AT_SYMLINK_NOFOLLOW))
			lookup_flags = LOOKUP_FOLLOW;
		return filename_getxattr(dfd, filename, lookup_flags, &ctx);
	}
}

SYSCALL_DEFINE6(getxattrat, int, dfd, const char __user *, pathname, unsigned int, at_flags,
		const char __user *, name, struct xattr_args __user *, uargs, size_t, usize)
{
	struct xattr_args args = {};
	int error;

	BUILD_BUG_ON(sizeof(struct xattr_args) < XATTR_ARGS_SIZE_VER0);
	BUILD_BUG_ON(sizeof(struct xattr_args) != XATTR_ARGS_SIZE_LATEST);

	if (unlikely(usize < XATTR_ARGS_SIZE_VER0))
		return -EINVAL;
	if (usize > PAGE_SIZE)
		return -E2BIG;

	error = copy_struct_from_user(&args, sizeof(args), uargs, usize);
	if (error)
		return error;

	if (args.flags != 0)
		return -EINVAL;

	return path_getxattrat(dfd, pathname, at_flags, name,
			       u64_to_user_ptr(args.value), args.size);
}

SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
		const char __user *, name, void __user *, value, size_t, size)
{
	return path_getxattrat(AT_FDCWD, pathname, 0, name, value, size);
}

SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
		const char __user *, name, void __user *, value, size_t, size)
{
	return path_getxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name,
			       value, size);
}

SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
		void __user *, value, size_t, size)
{
	return path_getxattrat(fd, NULL, AT_EMPTY_PATH, name, value, size);
}

/*
 * Extended attribute LIST operations
 */
static ssize_t
listxattr(struct dentry *d, char __user *list, size_t size)
{
	ssize_t error;
	char *klist = NULL;

	if (size) {
		if (size > XATTR_LIST_MAX)
			size = XATTR_LIST_MAX;
		klist = kvmalloc(size, GFP_KERNEL);
		if (!klist)
			return -ENOMEM;
	}

	error = vfs_listxattr(d, klist, size);
	if (error > 0) {
		if (size && copy_to_user(list, klist, error))
			error = -EFAULT;
	} else if (error == -ERANGE && size >= XATTR_LIST_MAX) {
		/* The file system tried to returned a list bigger
		   than XATTR_LIST_MAX bytes. Not possible. */
		error = -E2BIG;
	}

	kvfree(klist);

	return error;
}

static
ssize_t file_listxattr(struct file *f, char __user *list, size_t size)
{
	audit_file(f);
	return listxattr(f->f_path.dentry, list, size);
}

/* unconditionally consumes filename */
static
ssize_t filename_listxattr(int dfd, struct filename *filename,
			   unsigned int lookup_flags,
			   char __user *list, size_t size)
{
	struct path path;
	ssize_t error;
retry:
	error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
	if (error)
		goto out;
	error = listxattr(path.dentry, list, size);
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
out:
	putname(filename);
	return error;
}

static ssize_t path_listxattrat(int dfd, const char __user *pathname,
				unsigned int at_flags, char __user *list,
				size_t size)
{
	struct filename *filename;
	int lookup_flags;

	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;

	filename = getname_maybe_null(pathname, at_flags);
	if (!filename) {
		CLASS(fd, f)(dfd);
		if (fd_empty(f))
			return -EBADF;
		return file_listxattr(fd_file(f), list, size);
	}

	lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
	return filename_listxattr(dfd, filename, lookup_flags, list, size);
}

SYSCALL_DEFINE5(listxattrat, int, dfd, const char __user *, pathname,
		unsigned int, at_flags,
		char __user *, list, size_t, size)
{
	return path_listxattrat(dfd, pathname, at_flags, list, size);
}

SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
		size_t, size)
{
	return path_listxattrat(AT_FDCWD, pathname, 0, list, size);
}

SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
		size_t, size)
{
	return path_listxattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, list, size);
}

SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
{
	return path_listxattrat(fd, NULL, AT_EMPTY_PATH, list, size);
}

/*
 * Extended attribute REMOVE operations
 */
static long
removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
{
	if (is_posix_acl_xattr(name))
		return vfs_remove_acl(idmap, d, name);
	return vfs_removexattr(idmap, d, name);
}

static int file_removexattr(struct file *f, struct xattr_name *kname)
{
	int error = mnt_want_write_file(f);

	if (!error) {
		audit_file(f);
		error = removexattr(file_mnt_idmap(f),
				    f->f_path.dentry, kname->name);
		mnt_drop_write_file(f);
	}
	return error;
}

/* unconditionally consumes filename */
static int filename_removexattr(int dfd, struct filename *filename,
				unsigned int lookup_flags, struct xattr_name *kname)
{
	struct path path;
	int error;

retry:
	error = filename_lookup(dfd, filename, lookup_flags, &path, NULL);
	if (error)
		goto out;
	error = mnt_want_write(path.mnt);
	if (!error) {
		error = removexattr(mnt_idmap(path.mnt), path.dentry, kname->name);
		mnt_drop_write(path.mnt);
	}
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
out:
	putname(filename);
	return error;
}

static int path_removexattrat(int dfd, const char __user *pathname,
			      unsigned int at_flags, const char __user *name)
{
	struct xattr_name kname;
	struct filename *filename;
	unsigned int lookup_flags;
	int error;

	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;

	error = import_xattr_name(&kname, name);
	if (error)
		return error;

	filename = getname_maybe_null(pathname, at_flags);
	if (!filename) {
		CLASS(fd, f)(dfd);
		if (fd_empty(f))
			return -EBADF;
		return file_removexattr(fd_file(f), &kname);
	}
	lookup_flags = (at_flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
	return filename_removexattr(dfd, filename, lookup_flags, &kname);
}

SYSCALL_DEFINE4(removexattrat, int, dfd, const char __user *, pathname,
		unsigned int, at_flags, const char __user *, name)
{
	return path_removexattrat(dfd, pathname, at_flags, name);
}

SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
		const char __user *, name)
{
	return path_removexattrat(AT_FDCWD, pathname, 0, name);
}

SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
		const char __user *, name)
{
	return path_removexattrat(AT_FDCWD, pathname, AT_SYMLINK_NOFOLLOW, name);
}

SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
{
	return path_removexattrat(fd, NULL, AT_EMPTY_PATH, name);
}

int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name)
{
	size_t len;

	len = strlen(name) + 1;
	if (*buffer) {
		if (*remaining_size < len)
			return -ERANGE;
		memcpy(*buffer, name, len);
		*buffer += len;
	}
	*remaining_size -= len;
	return 0;
}

/**
 * generic_listxattr - run through a dentry's xattr list() operations
 * @dentry: dentry to list the xattrs
 * @buffer: result buffer
 * @buffer_size: size of @buffer
 *
 * Combine the results of the list() operation from every xattr_handler in the
 * xattr_handler stack.
 *
 * Note that this will not include the entries for POSIX ACLs.
 */
ssize_t
generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
	const struct xattr_handler *handler, * const *handlers = dentry->d_sb->s_xattr;
	ssize_t remaining_size = buffer_size;

	for_each_xattr_handler(handlers, handler) {
		int err;

		if (!handler->name || (handler->list && !handler->list(dentry)))
			continue;
		err = xattr_list_one(&buffer, &remaining_size, handler->name);
		if (err)
			return err;
	}

	return buffer_size - remaining_size;
}
EXPORT_SYMBOL(generic_listxattr);

/**
 * xattr_full_name  -  Compute full attribute name from suffix
 *
 * @handler:	handler of the xattr_handler operation
 * @name:	name passed to the xattr_handler operation
 *
 * The get and set xattr handler operations are called with the remainder of
 * the attribute name after skipping the handler's prefix: for example, "foo"
 * is passed to the get operation of a handler with prefix "user." to get
 * attribute "user.foo".  The full name is still "there" in the name though.
 *
 * Note: the list xattr handler operation when called from the vfs is passed a
 * NULL name; some file systems use this operation internally, with varying
 * semantics.
 */
const char *xattr_full_name(const struct xattr_handler *handler,
			    const char *name)
{
	size_t prefix_len = strlen(xattr_prefix(handler));

	return name - prefix_len;
}
EXPORT_SYMBOL(xattr_full_name);

/**
 * simple_xattr_space - estimate the memory used by a simple xattr
 * @name: the full name of the xattr
 * @size: the size of its value
 *
 * This takes no account of how much larger the two slab objects actually are:
 * that would depend on the slab implementation, when what is required is a
 * deterministic number, which grows with name length and size and quantity.
 *
 * Return: The approximate number of bytes of memory used by such an xattr.
 */
size_t simple_xattr_space(const char *name, size_t size)
{
	/*
	 * Use "40" instead of sizeof(struct simple_xattr), to return the
	 * same result on 32-bit and 64-bit, and even if simple_xattr grows.
	 */
	return 40 + size + strlen(name);
}

/**
 * simple_xattr_free - free an xattr object
 * @xattr: the xattr object
 *
 * Free the xattr object. Can handle @xattr being NULL.
 */
void simple_xattr_free(struct simple_xattr *xattr)
{
	if (xattr)
		kfree(xattr->name);
	kvfree(xattr);
}

/**
 * simple_xattr_alloc - allocate new xattr object
 * @value: value of the xattr object
 * @size: size of @value
 *
 * Allocate a new xattr object and initialize respective members. The caller is
 * responsible for handling the name of the xattr.
 *
 * Return: On success a new xattr object is returned. On failure NULL is
 * returned.
 */
struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
{
	struct simple_xattr *new_xattr;
	size_t len;

	/* wrap around? */
	len = sizeof(*new_xattr) + size;
	if (len < sizeof(*new_xattr))
		return NULL;

	new_xattr = kvmalloc(len, GFP_KERNEL_ACCOUNT);
	if (!new_xattr)
		return NULL;

	new_xattr->size = size;
	memcpy(new_xattr->value, value, size);
	return new_xattr;
}

/**
 * rbtree_simple_xattr_cmp - compare xattr name with current rbtree xattr entry
 * @key: xattr name
 * @node: current node
 *
 * Compare the xattr name with the xattr name attached to @node in the rbtree.
 *
 * Return: Negative value if continuing left, positive if continuing right, 0
 * if the xattr attached to @node matches @key.
 */
static int rbtree_simple_xattr_cmp(const void *key, const struct rb_node *node)
{
	const char *xattr_name = key;
	const struct simple_xattr *xattr;

	xattr = rb_entry(node, struct simple_xattr, rb_node);
	return strcmp(xattr->name, xattr_name);
}

/**
 * rbtree_simple_xattr_node_cmp - compare two xattr rbtree nodes
 * @new_node: new node
 * @node: current node
 *
 * Compare the xattr attached to @new_node with the xattr attached to @node.
 *
 * Return: Negative value if continuing left, positive if continuing right, 0
 * if the xattr attached to @new_node matches the xattr attached to @node.
 */
static int rbtree_simple_xattr_node_cmp(struct rb_node *new_node,
					const struct rb_node *node)
{
	struct simple_xattr *xattr;
	xattr = rb_entry(new_node, struct simple_xattr, rb_node);
	return rbtree_simple_xattr_cmp(xattr->name, node);
}

/**
 * simple_xattr_get - get an xattr object
 * @xattrs: the header of the xattr object
 * @name: the name of the xattr to retrieve
 * @buffer: the buffer to store the value into
 * @size: the size of @buffer
 *
 * Try to find and retrieve the xattr object associated with @name.
 * If @buffer is provided store the value of @xattr in @buffer
 * otherwise just return the length. The size of @buffer is limited
 * to XATTR_SIZE_MAX which currently is 65536.
 *
 * Return: On success the length of the xattr value is returned. On error a
 * negative error code is returned.
 */
int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
		     void *buffer, size_t size)
{
	struct simple_xattr *xattr = NULL;
	struct rb_node *rbp;
	int ret = -ENODATA;

	read_lock(&xattrs->lock);
	rbp = rb_find(name, &xattrs->rb_root, rbtree_simple_xattr_cmp);
	if (rbp) {
		xattr = rb_entry(rbp, struct simple_xattr, rb_node);
		ret = xattr->size;
		if (buffer) {
			if (size < xattr->size)
				ret = -ERANGE;
			else
				memcpy(buffer, xattr->value, xattr->size);
		}
	}
	read_unlock(&xattrs->lock);
	return ret;
}

/**
 * simple_xattr_set - set an xattr object
 * @xattrs: the header of the xattr object
 * @name: the name of the xattr to retrieve
 * @value: the value to store along the xattr
 * @size: the size of @value
 * @flags: the flags determining how to set the xattr
 *
 * Set a new xattr object.
 * If @value is passed a new xattr object will be allocated. If XATTR_REPLACE
 * is specified in @flags a matching xattr object for @name must already exist.
 * If it does it will be replaced with the new xattr object. If it doesn't we
 * fail. If XATTR_CREATE is specified and a matching xattr does already exist
 * we fail. If it doesn't we create a new xattr. If @flags is zero we simply
 * insert the new xattr replacing any existing one.
 *
 * If @value is empty and a matching xattr object is found we delete it if
 * XATTR_REPLACE is specified in @flags or @flags is zero.
 *
 * If @value is empty and no matching xattr object for @name is found we do
 * nothing if XATTR_CREATE is specified in @flags or @flags is zero. For
 * XATTR_REPLACE we fail as mentioned above.
 *
 * Return: On success, the removed or replaced xattr is returned, to be freed
 * by the caller; or NULL if none. On failure a negative error code is returned.
 */
struct simple_xattr *simple_xattr_set(struct simple_xattrs *xattrs,
				      const char *name, const void *value,
				      size_t size, int flags)
{
	struct simple_xattr *old_xattr = NULL, *new_xattr = NULL;
	struct rb_node *parent = NULL, **rbp;
	int err = 0, ret;

	/* value == NULL means remove */
	if (value) {
		new_xattr = simple_xattr_alloc(value, size);
		if (!new_xattr)
			return ERR_PTR(-ENOMEM);

		new_xattr->name = kstrdup(name, GFP_KERNEL_ACCOUNT);
		if (!new_xattr->name) {
			simple_xattr_free(new_xattr);
			return ERR_PTR(-ENOMEM);
		}
	}

	write_lock(&xattrs->lock);
	rbp = &xattrs->rb_root.rb_node;
	while (*rbp) {
		parent = *rbp;
		ret = rbtree_simple_xattr_cmp(name, *rbp);
		if (ret < 0)
			rbp = &(*rbp)->rb_left;
		else if (ret > 0)
			rbp = &(*rbp)->rb_right;
		else
			old_xattr = rb_entry(*rbp, struct simple_xattr, rb_node);
		if (old_xattr)
			break;
	}

	if (old_xattr) {
		/* Fail if XATTR_CREATE is requested and the xattr exists. */
		if (flags & XATTR_CREATE) {
			err = -EEXIST;
			goto out_unlock;
		}

		if (new_xattr)
			rb_replace_node(&old_xattr->rb_node,
					&new_xattr->rb_node, &xattrs->rb_root);
		else
			rb_erase(&old_xattr->rb_node, &xattrs->rb_root);
	} else {
		/* Fail if XATTR_REPLACE is requested but no xattr is found. */
		if (flags & XATTR_REPLACE) {
			err = -ENODATA;
			goto out_unlock;
		}

		/*
		 * If XATTR_CREATE or no flags are specified together with a
		 * new value simply insert it.
		 */
		if (new_xattr) {
			rb_link_node(&new_xattr->rb_node, parent, rbp);
			rb_insert_color(&new_xattr->rb_node, &xattrs->rb_root);
		}

		/*
		 * If XATTR_CREATE or no flags are specified and neither an
		 * old or new xattr exist then we don't need to do anything.
		 */
	}

out_unlock:
	write_unlock(&xattrs->lock);
	if (!err)
		return old_xattr;
	simple_xattr_free(new_xattr);
	return ERR_PTR(err);
}

static bool xattr_is_trusted(const char *name)
{
	return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}

/**
 * simple_xattr_list - list all xattr objects
 * @inode: inode from which to get the xattrs
 * @xattrs: the header of the xattr object
 * @buffer: the buffer to store all xattrs into
 * @size: the size of @buffer
 *
 * List all xattrs associated with @inode. If @buffer is NULL we returned
 * the required size of the buffer. If @buffer is provided we store the
 * xattrs value into it provided it is big enough.
 *
 * Note, the number of xattr names that can be listed with listxattr(2) is
 * limited to XATTR_LIST_MAX aka 65536 bytes. If a larger buffer is passed
 * then vfs_listxattr() caps it to XATTR_LIST_MAX and if more xattr names
 * are found it will return -E2BIG.
 *
 * Return: On success the required size or the size of the copied xattrs is
 * returned. On error a negative error code is returned.
 */
ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
			  char *buffer, size_t size)
{
	bool trusted = ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN);
	struct simple_xattr *xattr;
	struct rb_node *rbp;
	ssize_t remaining_size = size;
	int err = 0;

	err = posix_acl_listxattr(inode, &buffer, &remaining_size);
	if (err)
		return err;

	read_lock(&xattrs->lock);
	for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
		xattr = rb_entry(rbp, struct simple_xattr, rb_node);

		/* skip "trusted." attributes for unprivileged callers */
		if (!trusted && xattr_is_trusted(xattr->name))
			continue;

		err = xattr_list_one(&buffer, &remaining_size, xattr->name);
		if (err)
			break;
	}
	read_unlock(&xattrs->lock);

	return err ? err : size - remaining_size;
}

/**
 * rbtree_simple_xattr_less - compare two xattr rbtree nodes
 * @new_node: new node
 * @node: current node
 *
 * Compare the xattr attached to @new_node with the xattr attached to @node.
 * Note that this function technically tolerates duplicate entries.
 *
 * Return: True if insertion point in the rbtree is found.
 */
static bool rbtree_simple_xattr_less(struct rb_node *new_node,
				     const struct rb_node *node)
{
	return rbtree_simple_xattr_node_cmp(new_node, node) < 0;
}

/**
 * simple_xattr_add - add xattr objects
 * @xattrs: the header of the xattr object
 * @new_xattr: the xattr object to add
 *
 * Add an xattr object to @xattrs. This assumes no replacement or removal
 * of matching xattrs is wanted. Should only be called during inode
 * initialization when a few distinct initial xattrs are supposed to be set.
 */
void simple_xattr_add(struct simple_xattrs *xattrs,
		      struct simple_xattr *new_xattr)
{
	write_lock(&xattrs->lock);
	rb_add(&new_xattr->rb_node, &xattrs->rb_root, rbtree_simple_xattr_less);
	write_unlock(&xattrs->lock);
}

/**
 * simple_xattrs_init - initialize new xattr header
 * @xattrs: header to initialize
 *
 * Initialize relevant fields of a an xattr header.
 */
void simple_xattrs_init(struct simple_xattrs *xattrs)
{
	xattrs->rb_root = RB_ROOT;
	rwlock_init(&xattrs->lock);
}

/**
 * simple_xattrs_free - free xattrs
 * @xattrs: xattr header whose xattrs to destroy
 * @freed_space: approximate number of bytes of memory freed from @xattrs
 *
 * Destroy all xattrs in @xattr. When this is called no one can hold a
 * reference to any of the xattrs anymore.
 */
void simple_xattrs_free(struct simple_xattrs *xattrs, size_t *freed_space)
{
	struct rb_node *rbp;

	if (freed_space)
		*freed_space = 0;
	rbp = rb_first(&xattrs->rb_root);
	while (rbp) {
		struct simple_xattr *xattr;
		struct rb_node *rbp_next;

		rbp_next = rb_next(rbp);
		xattr = rb_entry(rbp, struct simple_xattr, rb_node);
		rb_erase(&xattr->rb_node, &xattrs->rb_root);
		if (freed_space)
			*freed_space += simple_xattr_space(xattr->name,
							   xattr->size);
		simple_xattr_free(xattr);
		rbp = rbp_next;
	}
}