OpenCloudOS-Kernel/fs/9p/xattr.c

194 lines
4.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: LGPL-2.1
/*
* Copyright IBM Corporation, 2010
* Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
*/
#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_fid_put(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;
9p: add refcount to p9_fid struct 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.${file}; done seq 1 1000 | xargs -n 1 -P 50 -I{} cat f.* > /dev/null open-unlink-f*syscall test: I have tested for f*syscall include: ftruncate fstat fchown fchmod faccessat. Link: http://lkml.kernel.org/r/20200923141146.90046-5-jianyong.wu@arm.com Fixes: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 22:11:46 +08:00
int ret;
p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n",
name, buffer_size);
fid = v9fs_fid_lookup(dentry);
if (IS_ERR(fid))
return PTR_ERR(fid);
9p: add refcount to p9_fid struct Fix race issue in fid contention. Eric's and Greg's patch offer a mechanism to fix open-unlink-f*syscall bug in 9p. But there is race issue in fid parallel accesses. As Greg's patch stores all of fids from opened files into according inode, so all the lookup fid ops can retrieve fid from inode preferentially. But there is no mechanism to handle the fid contention issue. For example, there are two threads get the same fid in the same time and one of them clunk the fid before the other thread ready to discard the fid. In this scenario, it will lead to some fatal problems, even kernel core dump. I introduce a mechanism to fix this race issue. A counter field introduced into p9_fid struct to store the reference counter to the fid. When a fid is allocated from the inode or dentry, the counter will increase, and will decrease at the end of its occupation. It is guaranteed that the fid won't be clunked before the reference counter go down to 0, then we can avoid the clunked fid to be used. tests: race issue test from the old test case: for file in {01..50}; do touch f.${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: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 22:11:46 +08:00
ret = v9fs_fid_xattr_get(fid, name, buffer, buffer_size);
p9_fid_put(fid);
9p: add refcount to p9_fid struct 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: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 22:11:46 +08:00
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)
{
9p: add refcount to p9_fid struct 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: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 22:11:46 +08:00
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_fid_put(fid);
9p: add refcount to p9_fid struct 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: 478ba09edc1f ("fs/9p: search open fids first") Signed-off-by: Jianyong Wu <jianyong.wu@arm.com> Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
2020-09-23 22:11:46 +08:00
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_fid_put(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,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 21:19:27 +08:00
struct user_namespace *mnt_userns,
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
};