6636b6dcc3
Fix race issue in fid contention.
Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall
bug in 9p. But there is race issue in fid parallel accesses.
As Greg's patch stores all of fids from opened files into according inode,
so all the lookup fid ops can retrieve fid from inode preferentially. But
there is no mechanism to handle the fid contention issue. For example,
there are two threads get the same fid in the same time and one of them
clunk the fid before the other thread ready to discard the fid. In this
scenario, it will lead to some fatal problems, even kernel core dump.
I introduce a mechanism to fix this race issue. A counter field introduced
into p9_fid struct to store the reference counter to the fid. When a fid
is allocated from the inode or dentry, the counter will increase, and
will decrease at the end of its occupation. It is guaranteed that the
fid won't be clunked before the reference counter go down to 0, then
we can avoid the clunked fid to be used.
tests:
race issue test from the old test case:
for file in {01..50}; do touch f.${file}; done
seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null
open-unlink-f*syscall test:
I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat.
Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com
Fixes: 478ba09edc
("fs/9p: search open fids first")
Signed-off-by: Jianyong Wu <jianyong.wu@arm.com>
Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
201 lines
5.2 KiB
C
201 lines
5.2 KiB
C
/*
|
|
* Copyright IBM Corporation, 2010
|
|
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of version 2.1 of the GNU Lesser General Public License
|
|
* as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it would be useful, but
|
|
* WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
|
|
*
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/uio.h>
|
|
#include <net/9p/9p.h>
|
|
#include <net/9p/client.h>
|
|
|
|
#include "fid.h"
|
|
#include "xattr.h"
|
|
|
|
ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name,
|
|
void *buffer, size_t buffer_size)
|
|
{
|
|
ssize_t retval;
|
|
u64 attr_size;
|
|
struct p9_fid *attr_fid;
|
|
struct kvec kvec = {.iov_base = buffer, .iov_len = buffer_size};
|
|
struct iov_iter to;
|
|
int err;
|
|
|
|
iov_iter_kvec(&to, READ, &kvec, 1, buffer_size);
|
|
|
|
attr_fid = p9_client_xattrwalk(fid, name, &attr_size);
|
|
if (IS_ERR(attr_fid)) {
|
|
retval = PTR_ERR(attr_fid);
|
|
p9_debug(P9_DEBUG_VFS, "p9_client_attrwalk failed %zd\n",
|
|
retval);
|
|
return retval;
|
|
}
|
|
if (attr_size > buffer_size) {
|
|
if (!buffer_size) /* request to get the attr_size */
|
|
retval = attr_size;
|
|
else
|
|
retval = -ERANGE;
|
|
} else {
|
|
iov_iter_truncate(&to, attr_size);
|
|
retval = p9_client_read(attr_fid, 0, &to, &err);
|
|
if (err)
|
|
retval = err;
|
|
}
|
|
p9_client_clunk(attr_fid);
|
|
return retval;
|
|
}
|
|
|
|
|
|
/*
|
|
* v9fs_xattr_get()
|
|
*
|
|
* Copy an extended attribute into the buffer
|
|
* provided, or compute the buffer size required.
|
|
* Buffer is NULL to compute the size of the buffer required.
|
|
*
|
|
* Returns a negative error number on failure, or the number of bytes
|
|
* used / required on success.
|
|
*/
|
|
ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name,
|
|
void *buffer, size_t buffer_size)
|
|
{
|
|
struct p9_fid *fid;
|
|
int ret;
|
|
|
|
p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n",
|
|
name, buffer_size);
|
|
fid = v9fs_fid_lookup(dentry);
|
|
if (IS_ERR(fid))
|
|
return PTR_ERR(fid);
|
|
ret = v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
|
|
p9_client_clunk(fid);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* v9fs_xattr_set()
|
|
*
|
|
* Create, replace or remove an extended attribute for this inode. Buffer
|
|
* is NULL to remove an existing extended attribute, and non-NULL to
|
|
* either replace an existing extended attribute, or create a new extended
|
|
* attribute. The flags XATTR_REPLACE and XATTR_CREATE
|
|
* specify that an extended attribute must exist and must not exist
|
|
* previous to the call, respectively.
|
|
*
|
|
* Returns 0, or a negative error number on failure.
|
|
*/
|
|
int v9fs_xattr_set(struct dentry *dentry, const char *name,
|
|
const void *value, size_t value_len, int flags)
|
|
{
|
|
int ret;
|
|
struct p9_fid *fid;
|
|
|
|
fid = v9fs_fid_lookup(dentry);
|
|
if (IS_ERR(fid))
|
|
return PTR_ERR(fid);
|
|
ret = v9fs_fid_xattr_set(fid, name, value, value_len, flags);
|
|
p9_client_clunk(fid);
|
|
return ret;
|
|
}
|
|
|
|
int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name,
|
|
const void *value, size_t value_len, int flags)
|
|
{
|
|
struct kvec kvec = {.iov_base = (void *)value, .iov_len = value_len};
|
|
struct iov_iter from;
|
|
int retval, err;
|
|
|
|
iov_iter_kvec(&from, WRITE, &kvec, 1, value_len);
|
|
|
|
p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n",
|
|
name, value_len, flags);
|
|
|
|
/* Clone it */
|
|
fid = clone_fid(fid);
|
|
if (IS_ERR(fid))
|
|
return PTR_ERR(fid);
|
|
|
|
/*
|
|
* On success fid points to xattr
|
|
*/
|
|
retval = p9_client_xattrcreate(fid, name, value_len, flags);
|
|
if (retval < 0)
|
|
p9_debug(P9_DEBUG_VFS, "p9_client_xattrcreate failed %d\n",
|
|
retval);
|
|
else
|
|
p9_client_write(fid, 0, &from, &retval);
|
|
err = p9_client_clunk(fid);
|
|
if (!retval && err)
|
|
retval = err;
|
|
return retval;
|
|
}
|
|
|
|
ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
|
|
{
|
|
return v9fs_xattr_get(dentry, NULL, buffer, buffer_size);
|
|
}
|
|
|
|
static int v9fs_xattr_handler_get(const struct xattr_handler *handler,
|
|
struct dentry *dentry, struct inode *inode,
|
|
const char *name, void *buffer, size_t size)
|
|
{
|
|
const char *full_name = xattr_full_name(handler, name);
|
|
|
|
return v9fs_xattr_get(dentry, full_name, buffer, size);
|
|
}
|
|
|
|
static int v9fs_xattr_handler_set(const struct xattr_handler *handler,
|
|
struct dentry *dentry, struct inode *inode,
|
|
const char *name, const void *value,
|
|
size_t size, int flags)
|
|
{
|
|
const char *full_name = xattr_full_name(handler, name);
|
|
|
|
return v9fs_xattr_set(dentry, full_name, value, size, flags);
|
|
}
|
|
|
|
static struct xattr_handler v9fs_xattr_user_handler = {
|
|
.prefix = XATTR_USER_PREFIX,
|
|
.get = v9fs_xattr_handler_get,
|
|
.set = v9fs_xattr_handler_set,
|
|
};
|
|
|
|
static struct xattr_handler v9fs_xattr_trusted_handler = {
|
|
.prefix = XATTR_TRUSTED_PREFIX,
|
|
.get = v9fs_xattr_handler_get,
|
|
.set = v9fs_xattr_handler_set,
|
|
};
|
|
|
|
#ifdef CONFIG_9P_FS_SECURITY
|
|
static struct xattr_handler v9fs_xattr_security_handler = {
|
|
.prefix = XATTR_SECURITY_PREFIX,
|
|
.get = v9fs_xattr_handler_get,
|
|
.set = v9fs_xattr_handler_set,
|
|
};
|
|
#endif
|
|
|
|
const struct xattr_handler *v9fs_xattr_handlers[] = {
|
|
&v9fs_xattr_user_handler,
|
|
&v9fs_xattr_trusted_handler,
|
|
#ifdef CONFIG_9P_FS_POSIX_ACL
|
|
&v9fs_xattr_acl_access_handler,
|
|
&v9fs_xattr_acl_default_handler,
|
|
#endif
|
|
#ifdef CONFIG_9P_FS_SECURITY
|
|
&v9fs_xattr_security_handler,
|
|
#endif
|
|
NULL
|
|
};
|