Revision 472e5b056f000a778abb41f1e443de58eb259783 authored by Linus Torvalds on 02 October 2020, 02:14:36 UTC, committed by Linus Torvalds on 02 October 2020, 02:14:36 UTC
The pipe splice code still used the old model of waiting for pipe IO by
using a non-specific "pipe_wait()" that waited for any pipe event to
happen, which depended on all pipe IO being entirely serialized by the
pipe lock.  So by checking the state you were waiting for, and then
adding yourself to the wait queue before dropping the lock, you were
guaranteed to see all the wakeups.

Strictly speaking, the actual wakeups were not done under the lock, but
the pipe_wait() model still worked, because since the waiter held the
lock when checking whether it should sleep, it would always see the
current state, and the wakeup was always done after updating the state.

However, commit 0ddad21d3e99 ("pipe: use exclusive waits when reading or
writing") split the single wait-queue into two, and in the process also
made the "wait for event" code wait for _two_ wait queues, and that then
showed a race with the wakers that were not serialized by the pipe lock.

It's only splice that used that "pipe_wait()" model, so the problem
wasn't obvious, but Josef Bacik reports:

 "I hit a hang with fstest btrfs/187, which does a btrfs send into
  /dev/null. This works by creating a pipe, the write side is given to
  the kernel to write into, and the read side is handed to a thread that
  splices into a file, in this case /dev/null.

  The box that was hung had the write side stuck here [pipe_write] and
  the read side stuck here [splice_from_pipe_next -> pipe_wait].

  [ more details about pipe_wait() scenario ]

  The problem is we're doing the prepare_to_wait, which sets our state
  each time, however we can be woken up either with reads or writes. In
  the case above we race with the WRITER waking us up, and re-set our
  state to INTERRUPTIBLE, and thus never break out of schedule"

Josef had a patch that avoided the issue in pipe_wait() by just making
it set the state only once, but the deeper problem is that pipe_wait()
depends on a level of synchonization by the pipe mutex that it really
shouldn't.  And the whole "wait for any pipe state change" model really
isn't very good to begin with.

So rather than trying to work around things in pipe_wait(), remove that
legacy model of "wait for arbitrary pipe event" entirely, and actually
create functions that wait for the pipe actually being readable or
writable, and can do so without depending on the pipe lock serializing
everything.

Fixes: 0ddad21d3e99 ("pipe: use exclusive waits when reading or writing")
Link: https://lore.kernel.org/linux-fsdevel/bfa88b5ad6f069b2b679316b9e495a970130416c.1601567868.git.josef@toxicpanda.com/
Reported-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-and-tested-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 44b6e23
Raw File
xattr.c
// 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/slab.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/evm.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>

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 **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);
}

/*
 * Check permissions for extended attribute access.  This is a bit complicated
 * because different namespaces have very different rules.
 */
static int
xattr_permission(struct inode *inode, const char *name, int mask)
{
	/*
	 * We can never set or remove an extended attribute on a read-only
	 * filesystem  or on an immutable / append-only inode.
	 */
	if (mask & MAY_WRITE) {
		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
			return -EPERM;
		/*
		 * Updating an xattr will likely cause i_uid and i_gid
		 * to be writen back improperly if their true value is
		 * unknown to the vfs.
		 */
		if (HAS_UNMAPPED_ID(inode))
			return -EPERM;
	}

	/*
	 * 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(inode))
			return -EPERM;
	}

	return inode_permission(inode, mask);
}

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

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

	preflen = strlen(prefix);

	for_each_xattr_handler(handlers, handler) {
		if (!strncmp(xattr_prefix(handler), prefix, preflen))
			return 0;
	}

	return -EOPNOTSUPP;
}
EXPORT_SYMBOL(xattr_supported_namespace);

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

	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, dentry, inode, name, value, size, flags);
}
EXPORT_SYMBOL(__vfs_setxattr);

/**
 *  __vfs_setxattr_noperm - perform setxattr operation without performing
 *  permission checks.
 *
 *  @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 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(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
 *
 *  @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 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(inode, name, MAY_WRITE);
	if (error)
		return error;

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

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

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

out:
	return error;
}
EXPORT_SYMBOL_GPL(__vfs_setxattr_locked);

int
vfs_setxattr(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;
	int error;

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

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

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

	len = security_inode_getsecurity(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.
 *
 * Returns the result of alloc, if failed, or the getxattr operation.
 */
ssize_t
vfs_getxattr_alloc(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(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;

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

	error = xattr_permission(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(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);

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 && (inode->i_opflags & IOP_XATTR)) {
		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 dentry *dentry, const char *name)
{
	struct inode *inode = d_inode(dentry);
	const struct xattr_handler *handler;

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

/**
 * __vfs_removexattr_locked: set an extended attribute while holding the inode
 * lock
 *
 *  @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 dentry *dentry, const char *name,
		struct inode **delegated_inode)
{
	struct inode *inode = dentry->d_inode;
	int error;

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

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

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

	error = __vfs_removexattr(dentry, name);

	if (!error) {
		fsnotify_xattr(dentry);
		evm_inode_post_removexattr(dentry, name);
	}

out:
	return error;
}
EXPORT_SYMBOL_GPL(__vfs_removexattr_locked);

int
vfs_removexattr(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(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);

/*
 * Extended attribute SET operations
 */
static long
setxattr(struct dentry *d, const char __user *name, const void __user *value,
	 size_t size, int flags)
{
	int error;
	void *kvalue = NULL;
	char kname[XATTR_NAME_MAX + 1];

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

	error = strncpy_from_user(kname, name, sizeof(kname));
	if (error == 0 || error == sizeof(kname))
		error = -ERANGE;
	if (error < 0)
		return error;

	if (size) {
		if (size > XATTR_SIZE_MAX)
			return -E2BIG;
		kvalue = kvmalloc(size, GFP_KERNEL);
		if (!kvalue)
			return -ENOMEM;
		if (copy_from_user(kvalue, value, size)) {
			error = -EFAULT;
			goto out;
		}
		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
			posix_acl_fix_xattr_from_user(kvalue, size);
		else if (strcmp(kname, XATTR_NAME_CAPS) == 0) {
			error = cap_convert_nscap(d, &kvalue, size);
			if (error < 0)
				goto out;
			size = error;
		}
	}

	error = vfs_setxattr(d, kname, kvalue, size, flags);
out:
	kvfree(kvalue);

	return error;
}

static int path_setxattr(const char __user *pathname,
			 const char __user *name, const void __user *value,
			 size_t size, int flags, unsigned int lookup_flags)
{
	struct path path;
	int error;
retry:
	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
	if (error)
		return error;
	error = mnt_want_write(path.mnt);
	if (!error) {
		error = setxattr(path.dentry, name, value, size, flags);
		mnt_drop_write(path.mnt);
	}
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
	return error;
}

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

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

SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
		const void __user *,value, size_t, size, int, flags)
{
	struct fd f = fdget(fd);
	int error = -EBADF;

	if (!f.file)
		return error;
	audit_file(f.file);
	error = mnt_want_write_file(f.file);
	if (!error) {
		error = setxattr(f.file->f_path.dentry, name, value, size, flags);
		mnt_drop_write_file(f.file);
	}
	fdput(f);
	return error;
}

/*
 * Extended attribute GET operations
 */
static ssize_t
getxattr(struct dentry *d, const char __user *name, void __user *value,
	 size_t size)
{
	ssize_t error;
	void *kvalue = NULL;
	char kname[XATTR_NAME_MAX + 1];

	error = strncpy_from_user(kname, name, sizeof(kname));
	if (error == 0 || error == sizeof(kname))
		error = -ERANGE;
	if (error < 0)
		return error;

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

	error = vfs_getxattr(d, kname, kvalue, size);
	if (error > 0) {
		if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
		    (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
			posix_acl_fix_xattr_to_user(kvalue, error);
		if (size && copy_to_user(value, kvalue, error))
			error = -EFAULT;
	} else if (error == -ERANGE && 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;
}

static ssize_t path_getxattr(const char __user *pathname,
			     const char __user *name, void __user *value,
			     size_t size, unsigned int lookup_flags)
{
	struct path path;
	ssize_t error;
retry:
	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
	if (error)
		return error;
	error = getxattr(path.dentry, name, value, size);
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
	return error;
}

SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
		const char __user *, name, void __user *, value, size_t, size)
{
	return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW);
}

SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
		const char __user *, name, void __user *, value, size_t, size)
{
	return path_getxattr(pathname, name, value, size, 0);
}

SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
		void __user *, value, size_t, size)
{
	struct fd f = fdget(fd);
	ssize_t error = -EBADF;

	if (!f.file)
		return error;
	audit_file(f.file);
	error = getxattr(f.file->f_path.dentry, name, value, size);
	fdput(f);
	return error;
}

/*
 * 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 path_listxattr(const char __user *pathname, char __user *list,
			      size_t size, unsigned int lookup_flags)
{
	struct path path;
	ssize_t error;
retry:
	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
	if (error)
		return error;
	error = listxattr(path.dentry, list, size);
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
	return error;
}

SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
		size_t, size)
{
	return path_listxattr(pathname, list, size, LOOKUP_FOLLOW);
}

SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
		size_t, size)
{
	return path_listxattr(pathname, list, size, 0);
}

SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
{
	struct fd f = fdget(fd);
	ssize_t error = -EBADF;

	if (!f.file)
		return error;
	audit_file(f.file);
	error = listxattr(f.file->f_path.dentry, list, size);
	fdput(f);
	return error;
}

/*
 * Extended attribute REMOVE operations
 */
static long
removexattr(struct dentry *d, const char __user *name)
{
	int error;
	char kname[XATTR_NAME_MAX + 1];

	error = strncpy_from_user(kname, name, sizeof(kname));
	if (error == 0 || error == sizeof(kname))
		error = -ERANGE;
	if (error < 0)
		return error;

	return vfs_removexattr(d, kname);
}

static int path_removexattr(const char __user *pathname,
			    const char __user *name, unsigned int lookup_flags)
{
	struct path path;
	int error;
retry:
	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
	if (error)
		return error;
	error = mnt_want_write(path.mnt);
	if (!error) {
		error = removexattr(path.dentry, name);
		mnt_drop_write(path.mnt);
	}
	path_put(&path);
	if (retry_estale(error, lookup_flags)) {
		lookup_flags |= LOOKUP_REVAL;
		goto retry;
	}
	return error;
}

SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
		const char __user *, name)
{
	return path_removexattr(pathname, name, LOOKUP_FOLLOW);
}

SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
		const char __user *, name)
{
	return path_removexattr(pathname, name, 0);
}

SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
{
	struct fd f = fdget(fd);
	int error = -EBADF;

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

/*
 * Combine the results of the list() operation from every xattr_handler in the
 * list.
 */
ssize_t
generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
	const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr;
	unsigned int size = 0;

	if (!buffer) {
		for_each_xattr_handler(handlers, handler) {
			if (!handler->name ||
			    (handler->list && !handler->list(dentry)))
				continue;
			size += strlen(handler->name) + 1;
		}
	} else {
		char *buf = buffer;
		size_t len;

		for_each_xattr_handler(handlers, handler) {
			if (!handler->name ||
			    (handler->list && !handler->list(dentry)))
				continue;
			len = strlen(handler->name);
			if (len + 1 > buffer_size)
				return -ERANGE;
			memcpy(buf, handler->name, len + 1);
			buf += len + 1;
			buffer_size -= len + 1;
		}
		size = buf - buffer;
	}
	return 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);

/*
 * Allocate new xattr and copy in the value; but leave the name to callers.
 */
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);
	if (!new_xattr)
		return NULL;

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

/*
 * xattr GET operation for in-memory/pseudo filesystems
 */
int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
		     void *buffer, size_t size)
{
	struct simple_xattr *xattr;
	int ret = -ENODATA;

	spin_lock(&xattrs->lock);
	list_for_each_entry(xattr, &xattrs->head, list) {
		if (strcmp(name, xattr->name))
			continue;

		ret = xattr->size;
		if (buffer) {
			if (size < xattr->size)
				ret = -ERANGE;
			else
				memcpy(buffer, xattr->value, xattr->size);
		}
		break;
	}
	spin_unlock(&xattrs->lock);
	return ret;
}

/**
 * simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
 * @xattrs: target simple_xattr list
 * @name: name of the extended attribute
 * @value: value of the xattr. If %NULL, will remove the attribute.
 * @size: size of the new xattr
 * @flags: %XATTR_{CREATE|REPLACE}
 * @removed_size: returns size of the removed xattr, -1 if none removed
 *
 * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
 * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
 * otherwise, fails with -ENODATA.
 *
 * Returns 0 on success, -errno on failure.
 */
int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
		     const void *value, size_t size, int flags,
		     ssize_t *removed_size)
{
	struct simple_xattr *xattr;
	struct simple_xattr *new_xattr = NULL;
	int err = 0;

	if (removed_size)
		*removed_size = -1;

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

		new_xattr->name = kstrdup(name, GFP_KERNEL);
		if (!new_xattr->name) {
			kvfree(new_xattr);
			return -ENOMEM;
		}
	}

	spin_lock(&xattrs->lock);
	list_for_each_entry(xattr, &xattrs->head, list) {
		if (!strcmp(name, xattr->name)) {
			if (flags & XATTR_CREATE) {
				xattr = new_xattr;
				err = -EEXIST;
			} else if (new_xattr) {
				list_replace(&xattr->list, &new_xattr->list);
				if (removed_size)
					*removed_size = xattr->size;
			} else {
				list_del(&xattr->list);
				if (removed_size)
					*removed_size = xattr->size;
			}
			goto out;
		}
	}
	if (flags & XATTR_REPLACE) {
		xattr = new_xattr;
		err = -ENODATA;
	} else {
		list_add(&new_xattr->list, &xattrs->head);
		xattr = NULL;
	}
out:
	spin_unlock(&xattrs->lock);
	if (xattr) {
		kfree(xattr->name);
		kvfree(xattr);
	}
	return err;

}

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

static int xattr_list_one(char **buffer, ssize_t *remaining_size,
			  const char *name)
{
	size_t len = strlen(name) + 1;
	if (*buffer) {
		if (*remaining_size < len)
			return -ERANGE;
		memcpy(*buffer, name, len);
		*buffer += len;
	}
	*remaining_size -= len;
	return 0;
}

/*
 * xattr LIST operation for in-memory/pseudo filesystems
 */
ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
			  char *buffer, size_t size)
{
	bool trusted = capable(CAP_SYS_ADMIN);
	struct simple_xattr *xattr;
	ssize_t remaining_size = size;
	int err = 0;

#ifdef CONFIG_FS_POSIX_ACL
	if (IS_POSIXACL(inode)) {
		if (inode->i_acl) {
			err = xattr_list_one(&buffer, &remaining_size,
					     XATTR_NAME_POSIX_ACL_ACCESS);
			if (err)
				return err;
		}
		if (inode->i_default_acl) {
			err = xattr_list_one(&buffer, &remaining_size,
					     XATTR_NAME_POSIX_ACL_DEFAULT);
			if (err)
				return err;
		}
	}
#endif

	spin_lock(&xattrs->lock);
	list_for_each_entry(xattr, &xattrs->head, list) {
		/* 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;
	}
	spin_unlock(&xattrs->lock);

	return err ? err : size - remaining_size;
}

/*
 * Adds an extended attribute to the list
 */
void simple_xattr_list_add(struct simple_xattrs *xattrs,
			   struct simple_xattr *new_xattr)
{
	spin_lock(&xattrs->lock);
	list_add(&new_xattr->list, &xattrs->head);
	spin_unlock(&xattrs->lock);
}
back to top