AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity
d84f4f992c
kernel_optimize_test/fs/nfsd/nfs4recover.c
David Howells d84f4f992c CRED: Inaugurate COW credentials 
Inaugurate copy-on-write credentials management.  This uses RCU to manage the
credentials pointer in the task_struct with respect to accesses by other tasks.
A process may only modify its own credentials, and so does not need locking to
access or modify its own credentials.

A mutex (cred_replace_mutex) is added to the task_struct to control the effect
of PTRACE_ATTACHED on credential calculations, particularly with respect to
execve().

With this patch, the contents of an active credentials struct may not be
changed directly; rather a new set of credentials must be prepared, modified
and committed using something like the following sequence of events:

	struct cred *new = prepare_creds();
	int ret = blah(new);
	if (ret < 0) {
		abort_creds(new);
		return ret;
	}
	return commit_creds(new);

There are some exceptions to this rule: the keyrings pointed to by the active
credentials may be instantiated - keyrings violate the COW rule as managing
COW keyrings is tricky, given that it is possible for a task to directly alter
the keys in a keyring in use by another task.

To help enforce this, various pointers to sets of credentials, such as those in
the task_struct, are declared const.  The purpose of this is compile-time
discouragement of altering credentials through those pointers.  Once a set of
credentials has been made public through one of these pointers, it may not be
modified, except under special circumstances:

  (1) Its reference count may incremented and decremented.

  (2) The keyrings to which it points may be modified, but not replaced.

The only safe way to modify anything else is to create a replacement and commit
using the functions described in Documentation/credentials.txt (which will be
added by a later patch).

This patch and the preceding patches have been tested with the LTP SELinux
testsuite.

This patch makes several logical sets of alteration:

 (1) execve().

     This now prepares and commits credentials in various places in the
     security code rather than altering the current creds directly.

 (2) Temporary credential overrides.

     do_coredump() and sys_faccessat() now prepare their own credentials and
     temporarily override the ones currently on the acting thread, whilst
     preventing interference from other threads by holding cred_replace_mutex
     on the thread being dumped.

     This will be replaced in a future patch by something that hands down the
     credentials directly to the functions being called, rather than altering
     the task's objective credentials.

 (3) LSM interface.

     A number of functions have been changed, added or removed:

     (*) security_capset_check(), ->capset_check()
     (*) security_capset_set(), ->capset_set()

     	 Removed in favour of security_capset().

     (*) security_capset(), ->capset()

     	 New.  This is passed a pointer to the new creds, a pointer to the old
     	 creds and the proposed capability sets.  It should fill in the new
     	 creds or return an error.  All pointers, barring the pointer to the
     	 new creds, are now const.

     (*) security_bprm_apply_creds(), ->bprm_apply_creds()

     	 Changed; now returns a value, which will cause the process to be
     	 killed if it's an error.

     (*) security_task_alloc(), ->task_alloc_security()

     	 Removed in favour of security_prepare_creds().

     (*) security_cred_free(), ->cred_free()

     	 New.  Free security data attached to cred->security.

     (*) security_prepare_creds(), ->cred_prepare()

     	 New. Duplicate any security data attached to cred->security.

     (*) security_commit_creds(), ->cred_commit()

     	 New. Apply any security effects for the upcoming installation of new
     	 security by commit_creds().

     (*) security_task_post_setuid(), ->task_post_setuid()

     	 Removed in favour of security_task_fix_setuid().

     (*) security_task_fix_setuid(), ->task_fix_setuid()

     	 Fix up the proposed new credentials for setuid().  This is used by
     	 cap_set_fix_setuid() to implicitly adjust capabilities in line with
     	 setuid() changes.  Changes are made to the new credentials, rather
     	 than the task itself as in security_task_post_setuid().

     (*) security_task_reparent_to_init(), ->task_reparent_to_init()

     	 Removed.  Instead the task being reparented to init is referred
     	 directly to init's credentials.

	 NOTE!  This results in the loss of some state: SELinux's osid no
	 longer records the sid of the thread that forked it.

     (*) security_key_alloc(), ->key_alloc()
     (*) security_key_permission(), ->key_permission()

     	 Changed.  These now take cred pointers rather than task pointers to
     	 refer to the security context.

 (4) sys_capset().

     This has been simplified and uses less locking.  The LSM functions it
     calls have been merged.

 (5) reparent_to_kthreadd().

     This gives the current thread the same credentials as init by simply using
     commit_thread() to point that way.

 (6) __sigqueue_alloc() and switch_uid()

     __sigqueue_alloc() can't stop the target task from changing its creds
     beneath it, so this function gets a reference to the currently applicable
     user_struct which it then passes into the sigqueue struct it returns if
     successful.

     switch_uid() is now called from commit_creds(), and possibly should be
     folded into that.  commit_creds() should take care of protecting
     __sigqueue_alloc().

 (7) [sg]et[ug]id() and co and [sg]et_current_groups.

     The set functions now all use prepare_creds(), commit_creds() and
     abort_creds() to build and check a new set of credentials before applying
     it.

     security_task_set[ug]id() is called inside the prepared section.  This
     guarantees that nothing else will affect the creds until we've finished.

     The calling of set_dumpable() has been moved into commit_creds().

     Much of the functionality of set_user() has been moved into
     commit_creds().

     The get functions all simply access the data directly.

 (8) security_task_prctl() and cap_task_prctl().

     security_task_prctl() has been modified to return -ENOSYS if it doesn't
     want to handle a function, or otherwise return the return value directly
     rather than through an argument.

     Additionally, cap_task_prctl() now prepares a new set of credentials, even
     if it doesn't end up using it.

 (9) Keyrings.

     A number of changes have been made to the keyrings code:

     (a) switch_uid_keyring(), copy_keys(), exit_keys() and suid_keys() have
     	 all been dropped and built in to the credentials functions directly.
     	 They may want separating out again later.

     (b) key_alloc() and search_process_keyrings() now take a cred pointer
     	 rather than a task pointer to specify the security context.

     (c) copy_creds() gives a new thread within the same thread group a new
     	 thread keyring if its parent had one, otherwise it discards the thread
     	 keyring.

     (d) The authorisation key now points directly to the credentials to extend
     	 the search into rather pointing to the task that carries them.

     (e) Installing thread, process or session keyrings causes a new set of
     	 credentials to be created, even though it's not strictly necessary for
     	 process or session keyrings (they're shared).

(10) Usermode helper.

     The usermode helper code now carries a cred struct pointer in its
     subprocess_info struct instead of a new session keyring pointer.  This set
     of credentials is derived from init_cred and installed on the new process
     after it has been cloned.

     call_usermodehelper_setup() allocates the new credentials and
     call_usermodehelper_freeinfo() discards them if they haven't been used.  A
     special cred function (prepare_usermodeinfo_creds()) is provided
     specifically for call_usermodehelper_setup() to call.

     call_usermodehelper_setkeys() adjusts the credentials to sport the
     supplied keyring as the new session keyring.

(11) SELinux.

     SELinux has a number of changes, in addition to those to support the LSM
     interface changes mentioned above:

     (a) selinux_setprocattr() no longer does its check for whether the
     	 current ptracer can access processes with the new SID inside the lock
     	 that covers getting the ptracer's SID.  Whilst this lock ensures that
     	 the check is done with the ptracer pinned, the result is only valid
     	 until the lock is released, so there's no point doing it inside the
     	 lock.

(12) is_single_threaded().

     This function has been extracted from selinux_setprocattr() and put into
     a file of its own in the lib/ directory as join_session_keyring() now
     wants to use it too.

     The code in SELinux just checked to see whether a task shared mm_structs
     with other tasks (CLONE_VM), but that isn't good enough.  We really want
     to know if they're part of the same thread group (CLONE_THREAD).

(13) nfsd.

     The NFS server daemon now has to use the COW credentials to set the
     credentials it is going to use.  It really needs to pass the credentials
     down to the functions it calls, but it can't do that until other patches
     in this series have been applied.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 10:39:23 +11:00

451 lines
10 KiB
C
Raw Blame History

/*
* linux/fs/nfsd/nfs4recover.c
*
* Copyright (c) 2004 The Regents of the University of Michigan.
* All rights reserved.
*
* Andy Adamson <andros@citi.umich.edu>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
*/
#include <linux/err.h>
#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfs4.h>
#include <linux/nfsd/state.h>
#include <linux/nfsd/xdr4.h>
#include <linux/param.h>
#include <linux/file.h>
#include <linux/namei.h>
#include <asm/uaccess.h>
#include <linux/scatterlist.h>
#include <linux/crypto.h>
#include <linux/sched.h>
#include <linux/mount.h>
#define NFSDDBG_FACILITY NFSDDBG_PROC
/* Globals */
static struct path rec_dir;
static int rec_dir_init = 0;
static int
nfs4_save_creds(const struct cred **original_creds)
{
struct cred *new;
new = prepare_creds();
if (!new)
return -ENOMEM;
new->fsuid = 0;
new->fsgid = 0;
*original_creds = override_creds(new);
put_cred(new);
return 0;
}
static void
nfs4_reset_creds(const struct cred *original)
{
revert_creds(original);
}
static void
md5_to_hex(char *out, char *md5)
{
int i;
for (i=0; i<16; i++) {
unsigned char c = md5[i];
*out++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1);
*out++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1);
}
*out = '\0';
}
__be32
nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
{
struct xdr_netobj cksum;
struct hash_desc desc;
struct scatterlist sg;
__be32 status = nfserr_resource;
dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
clname->len, clname->data);
desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(desc.tfm))
goto out_no_tfm;
cksum.len = crypto_hash_digestsize(desc.tfm);
cksum.data = kmalloc(cksum.len, GFP_KERNEL);
if (cksum.data == NULL)
goto out;
sg_init_one(&sg, clname->data, clname->len);
if (crypto_hash_digest(&desc, &sg, sg.length, cksum.data))
goto out;
md5_to_hex(dname, cksum.data);
kfree(cksum.data);
status = nfs_ok;
out:
crypto_free_hash(desc.tfm);
out_no_tfm:
return status;
}
static void
nfsd4_sync_rec_dir(void)
{
mutex_lock(&rec_dir.dentry->d_inode->i_mutex);
nfsd_sync_dir(rec_dir.dentry);
mutex_unlock(&rec_dir.dentry->d_inode->i_mutex);
}
int
nfsd4_create_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
char *dname = clp->cl_recdir;
struct dentry *dentry;
int status;
dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
if (!rec_dir_init || clp->cl_firststate)
return 0;
status = nfs4_save_creds(&original_cred);
if (status < 0)
return status;
/* lock the parent */
mutex_lock(&rec_dir.dentry->d_inode->i_mutex);
dentry = lookup_one_len(dname, rec_dir.dentry, HEXDIR_LEN-1);
if (IS_ERR(dentry)) {
status = PTR_ERR(dentry);
goto out_unlock;
}
status = -EEXIST;
if (dentry->d_inode) {
dprintk("NFSD: nfsd4_create_clid_dir: DIRECTORY EXISTS\n");
goto out_put;
}
status = mnt_want_write(rec_dir.mnt);
if (status)
goto out_put;
status = vfs_mkdir(rec_dir.dentry->d_inode, dentry, S_IRWXU);
mnt_drop_write(rec_dir.mnt);
out_put:
dput(dentry);
out_unlock:
mutex_unlock(&rec_dir.dentry->d_inode->i_mutex);
if (status == 0) {
clp->cl_firststate = 1;
nfsd4_sync_rec_dir();
}
nfs4_reset_creds(original_cred);
dprintk("NFSD: nfsd4_create_clid_dir returns %d\n", status);
return status;
}
typedef int (recdir_func)(struct dentry *, struct dentry *);
struct dentry_list {
struct dentry *dentry;
struct list_head list;
};
struct dentry_list_arg {
struct list_head dentries;
struct dentry *parent;
};
static int
nfsd4_build_dentrylist(void *arg, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct dentry_list_arg *dla = arg;
struct list_head *dentries = &dla->dentries;
struct dentry *parent = dla->parent;
struct dentry *dentry;
struct dentry_list *child;
if (name && isdotent(name, namlen))
return 0;
dentry = lookup_one_len(name, parent, namlen);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
child = kmalloc(sizeof(*child), GFP_KERNEL);
if (child == NULL)
return -ENOMEM;
child->dentry = dentry;
list_add(&child->list, dentries);
return 0;
}
static int
nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f)
{
const struct cred *original_cred;
struct file *filp;
struct dentry_list_arg dla = {
.parent = dir,
};
struct list_head *dentries = &dla.dentries;
struct dentry_list *child;
int status;
if (!rec_dir_init)
return 0;
status = nfs4_save_creds(&original_cred);
if (status < 0)
return status;
filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY,
current_cred());
status = PTR_ERR(filp);
if (IS_ERR(filp))
goto out;
INIT_LIST_HEAD(dentries);
status = vfs_readdir(filp, nfsd4_build_dentrylist, &dla);
fput(filp);
while (!list_empty(dentries)) {
child = list_entry(dentries->next, struct dentry_list, list);
status = f(dir, child->dentry);
if (status)
goto out;
list_del(&child->list);
dput(child->dentry);
kfree(child);
}
out:
while (!list_empty(dentries)) {
child = list_entry(dentries->next, struct dentry_list, list);
list_del(&child->list);
dput(child->dentry);
kfree(child);
}
nfs4_reset_creds(original_cred);
return status;
}
static int
nfsd4_remove_clid_file(struct dentry *dir, struct dentry *dentry)
{
int status;
if (!S_ISREG(dir->d_inode->i_mode)) {
printk("nfsd4: non-file found in client recovery directory\n");
return -EINVAL;
}
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
status = vfs_unlink(dir->d_inode, dentry);
mutex_unlock(&dir->d_inode->i_mutex);
return status;
}
static int
nfsd4_clear_clid_dir(struct dentry *dir, struct dentry *dentry)
{
int status;
/* For now this directory should already be empty, but we empty it of
* any regular files anyway, just in case the directory was created by
* a kernel from the future.... */
nfsd4_list_rec_dir(dentry, nfsd4_remove_clid_file);
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
status = vfs_rmdir(dir->d_inode, dentry);
mutex_unlock(&dir->d_inode->i_mutex);
return status;
}
static int
nfsd4_unlink_clid_dir(char *name, int namlen)
{
struct dentry *dentry;
int status;
dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
mutex_lock(&rec_dir.dentry->d_inode->i_mutex);
dentry = lookup_one_len(name, rec_dir.dentry, namlen);
mutex_unlock(&rec_dir.dentry->d_inode->i_mutex);
if (IS_ERR(dentry)) {
status = PTR_ERR(dentry);
return status;
}
status = -ENOENT;
if (!dentry->d_inode)
goto out;
status = nfsd4_clear_clid_dir(rec_dir.dentry, dentry);
out:
dput(dentry);
return status;
}
void
nfsd4_remove_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
int status;
if (!rec_dir_init || !clp->cl_firststate)
return;
status = mnt_want_write(rec_dir.mnt);
if (status)
goto out;
clp->cl_firststate = 0;
status = nfs4_save_creds(&original_cred);
if (status < 0)
goto out;
status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1);
nfs4_reset_creds(original_cred);
if (status == 0)
nfsd4_sync_rec_dir();
mnt_drop_write(rec_dir.mnt);
out:
if (status)
printk("NFSD: Failed to remove expired client state directory"
" %.*s\n", HEXDIR_LEN, clp->cl_recdir);
return;
}
static int
purge_old(struct dentry *parent, struct dentry *child)
{
int status;
if (nfs4_has_reclaimed_state(child->d_name.name))
return 0;
status = nfsd4_clear_clid_dir(parent, child);
if (status)
printk("failed to remove client recovery directory %s\n",
child->d_name.name);
/* Keep trying, success or failure: */
return 0;
}
void
nfsd4_recdir_purge_old(void) {
int status;
if (!rec_dir_init)
return;
status = mnt_want_write(rec_dir.mnt);
if (status)
goto out;
status = nfsd4_list_rec_dir(rec_dir.dentry, purge_old);
if (status == 0)
nfsd4_sync_rec_dir();
mnt_drop_write(rec_dir.mnt);
out:
if (status)
printk("nfsd4: failed to purge old clients from recovery"
" directory %s\n", rec_dir.dentry->d_name.name);
}
static int
load_recdir(struct dentry *parent, struct dentry *child)
{
if (child->d_name.len != HEXDIR_LEN - 1) {
printk("nfsd4: illegal name %s in recovery directory\n",
child->d_name.name);
/* Keep trying; maybe the others are OK: */
return 0;
}
nfs4_client_to_reclaim(child->d_name.name);
return 0;
}
int
nfsd4_recdir_load(void) {
int status;
status = nfsd4_list_rec_dir(rec_dir.dentry, load_recdir);
if (status)
printk("nfsd4: failed loading clients from recovery"
" directory %s\n", rec_dir.dentry->d_name.name);
return status;
}
/*
* Hold reference to the recovery directory.
*/
void
nfsd4_init_recdir(char *rec_dirname)
{
const struct cred *original_cred;
int status;
printk("NFSD: Using %s as the NFSv4 state recovery directory\n",
rec_dirname);
BUG_ON(rec_dir_init);
status = nfs4_save_creds(&original_cred);
if (status < 0) {
printk("NFSD: Unable to change credentials to find recovery"
" directory: error %d\n",
status);
return;
}
status = kern_path(rec_dirname, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
&rec_dir);
if (status)
printk("NFSD: unable to find recovery directory %s\n",
rec_dirname);
if (!status)
rec_dir_init = 1;
nfs4_reset_creds(original_cred);
}
void
nfsd4_shutdown_recdir(void)
{
if (!rec_dir_init)
return;
rec_dir_init = 0;
path_put(&rec_dir);
}
View Git Blame Copy Permalink