linux/crypto/algboss.c

295 lines
5.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Create default crypto algorithm instances.
*
* Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
*/
#include <crypto/internal/aead.h>
#include <linux/completion.h>
#include <linux/ctype.h>
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/notifier.h>
#include <linux/rtnetlink.h>
#include <linux/sched/signal.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/string.h>
#include "internal.h"
struct cryptomgr_param {
struct rtattr *tb[CRYPTO_MAX_ATTRS + 2];
struct {
struct rtattr attr;
struct crypto_attr_type data;
} type;
union {
struct rtattr attr;
struct {
struct rtattr attr;
struct crypto_attr_alg data;
} alg;
struct {
struct rtattr attr;
struct crypto_attr_u32 data;
} nu32;
} attrs[CRYPTO_MAX_ATTRS];
char template[CRYPTO_MAX_ALG_NAME];
crypto: algboss - Hold ref count on larval On Thu, Jun 20, 2013 at 10:00:21AM +0200, Daniel Borkmann wrote: > After having fixed a NULL pointer dereference in SCTP 1abd165e ("net: > sctp: fix NULL pointer dereference in socket destruction"), I ran into > the following NULL pointer dereference in the crypto subsystem with > the same reproducer, easily hit each time: > > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: [<ffffffff81070321>] __wake_up_common+0x31/0x90 > PGD 0 > Oops: 0000 [#1] SMP > Modules linked in: padlock_sha(F-) sha256_generic(F) sctp(F) libcrc32c(F) [..] > CPU: 6 PID: 3326 Comm: cryptomgr_probe Tainted: GF 3.10.0-rc5+ #1 > Hardware name: Dell Inc. PowerEdge T410/0H19HD, BIOS 1.6.3 02/01/2011 > task: ffff88007b6cf4e0 ti: ffff88007b7cc000 task.ti: ffff88007b7cc000 > RIP: 0010:[<ffffffff81070321>] [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP: 0018:ffff88007b7cde08 EFLAGS: 00010082 > RAX: ffffffffffffffe8 RBX: ffff88003756c130 RCX: 0000000000000000 > RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffff88003756c130 > RBP: ffff88007b7cde48 R08: 0000000000000000 R09: ffff88012b173200 > R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000282 > R13: ffff88003756c138 R14: 0000000000000000 R15: 0000000000000000 > FS: 0000000000000000(0000) GS:ffff88012fc60000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 0000000001a0b000 CR4: 00000000000007e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Stack: > ffff88007b7cde28 0000000300000000 ffff88007b7cde28 ffff88003756c130 > 0000000000000282 ffff88003756c128 ffffffff81227670 0000000000000000 > ffff88007b7cde78 ffffffff810722b7 ffff88007cdcf000 ffffffff81a90540 > Call Trace: > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff810722b7>] complete_all+0x47/0x60 > [<ffffffff81227708>] cryptomgr_probe+0x98/0xc0 > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff8106760e>] kthread+0xce/0xe0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > [<ffffffff815450dc>] ret_from_fork+0x7c/0xb0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > Code: 41 56 41 55 41 54 53 48 83 ec 18 66 66 66 66 90 89 75 cc 89 55 c8 > 4c 8d 6f 08 48 8b 57 08 41 89 cf 4d 89 c6 48 8d 42 e > RIP [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP <ffff88007b7cde08> > CR2: 0000000000000000 > ---[ end trace b495b19270a4d37e ]--- > > My assumption is that the following is happening: the minimal SCTP > tool runs under ``echo 1 > /proc/sys/net/sctp/auth_enable'', hence > it's making use of crypto_alloc_hash() via sctp_auth_init_hmacs(). > It forks itself, heavily allocates, binds, listens and waits in > accept on sctp sockets, and then randomly kills some of them (no > need for an actual client in this case to hit this). Then, again, > allocating, binding, etc, and then killing child processes. > > The problem that might be happening here is that cryptomgr requests > the module to probe/load through cryptomgr_schedule_probe(), but > before the thread handler cryptomgr_probe() returns, we return from > the wait_for_completion_interruptible() function and probably already > have cleared up larval, thus we run into a NULL pointer dereference > when in cryptomgr_probe() complete_all() is being called. > > If we wait with wait_for_completion() instead, this panic will not > occur anymore. This is valid, because in case a signal is pending, > cryptomgr_probe() returns from probing anyway with properly calling > complete_all(). The use of wait_for_completion_interruptible is intentional so that we don't lock up the thread if a bug causes us to never wake up. This bug is caused by the helper thread using the larval without holding a reference count on it. If the helper thread completes after the original thread requesting for help has gone away and destroyed the larval, then we get the crash above. So the fix is to hold a reference count on the larval. Cc: <stable@vger.kernel.org> # 3.6+ Reported-by: Daniel Borkmann <dborkman@redhat.com> Tested-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2013-06-25 11:15:17 +00:00
struct crypto_larval *larval;
u32 otype;
u32 omask;
};
struct crypto_test_param {
char driver[CRYPTO_MAX_ALG_NAME];
char alg[CRYPTO_MAX_ALG_NAME];
u32 type;
};
static int cryptomgr_probe(void *data)
{
struct cryptomgr_param *param = data;
struct crypto_template *tmpl;
int err;
tmpl = crypto_lookup_template(param->template);
if (!tmpl)
goto out;
do {
err = tmpl->create(tmpl, param->tb);
} while (err == -EAGAIN && !signal_pending(current));
crypto_tmpl_put(tmpl);
out:
crypto: algboss - Hold ref count on larval On Thu, Jun 20, 2013 at 10:00:21AM +0200, Daniel Borkmann wrote: > After having fixed a NULL pointer dereference in SCTP 1abd165e ("net: > sctp: fix NULL pointer dereference in socket destruction"), I ran into > the following NULL pointer dereference in the crypto subsystem with > the same reproducer, easily hit each time: > > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: [<ffffffff81070321>] __wake_up_common+0x31/0x90 > PGD 0 > Oops: 0000 [#1] SMP > Modules linked in: padlock_sha(F-) sha256_generic(F) sctp(F) libcrc32c(F) [..] > CPU: 6 PID: 3326 Comm: cryptomgr_probe Tainted: GF 3.10.0-rc5+ #1 > Hardware name: Dell Inc. PowerEdge T410/0H19HD, BIOS 1.6.3 02/01/2011 > task: ffff88007b6cf4e0 ti: ffff88007b7cc000 task.ti: ffff88007b7cc000 > RIP: 0010:[<ffffffff81070321>] [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP: 0018:ffff88007b7cde08 EFLAGS: 00010082 > RAX: ffffffffffffffe8 RBX: ffff88003756c130 RCX: 0000000000000000 > RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffff88003756c130 > RBP: ffff88007b7cde48 R08: 0000000000000000 R09: ffff88012b173200 > R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000282 > R13: ffff88003756c138 R14: 0000000000000000 R15: 0000000000000000 > FS: 0000000000000000(0000) GS:ffff88012fc60000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 0000000001a0b000 CR4: 00000000000007e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Stack: > ffff88007b7cde28 0000000300000000 ffff88007b7cde28 ffff88003756c130 > 0000000000000282 ffff88003756c128 ffffffff81227670 0000000000000000 > ffff88007b7cde78 ffffffff810722b7 ffff88007cdcf000 ffffffff81a90540 > Call Trace: > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff810722b7>] complete_all+0x47/0x60 > [<ffffffff81227708>] cryptomgr_probe+0x98/0xc0 > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff8106760e>] kthread+0xce/0xe0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > [<ffffffff815450dc>] ret_from_fork+0x7c/0xb0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > Code: 41 56 41 55 41 54 53 48 83 ec 18 66 66 66 66 90 89 75 cc 89 55 c8 > 4c 8d 6f 08 48 8b 57 08 41 89 cf 4d 89 c6 48 8d 42 e > RIP [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP <ffff88007b7cde08> > CR2: 0000000000000000 > ---[ end trace b495b19270a4d37e ]--- > > My assumption is that the following is happening: the minimal SCTP > tool runs under ``echo 1 > /proc/sys/net/sctp/auth_enable'', hence > it's making use of crypto_alloc_hash() via sctp_auth_init_hmacs(). > It forks itself, heavily allocates, binds, listens and waits in > accept on sctp sockets, and then randomly kills some of them (no > need for an actual client in this case to hit this). Then, again, > allocating, binding, etc, and then killing child processes. > > The problem that might be happening here is that cryptomgr requests > the module to probe/load through cryptomgr_schedule_probe(), but > before the thread handler cryptomgr_probe() returns, we return from > the wait_for_completion_interruptible() function and probably already > have cleared up larval, thus we run into a NULL pointer dereference > when in cryptomgr_probe() complete_all() is being called. > > If we wait with wait_for_completion() instead, this panic will not > occur anymore. This is valid, because in case a signal is pending, > cryptomgr_probe() returns from probing anyway with properly calling > complete_all(). The use of wait_for_completion_interruptible is intentional so that we don't lock up the thread if a bug causes us to never wake up. This bug is caused by the helper thread using the larval without holding a reference count on it. If the helper thread completes after the original thread requesting for help has gone away and destroyed the larval, then we get the crash above. So the fix is to hold a reference count on the larval. Cc: <stable@vger.kernel.org> # 3.6+ Reported-by: Daniel Borkmann <dborkman@redhat.com> Tested-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2013-06-25 11:15:17 +00:00
complete_all(&param->larval->completion);
crypto_alg_put(&param->larval->alg);
kfree(param);
module_put_and_exit(0);
}
static int cryptomgr_schedule_probe(struct crypto_larval *larval)
{
struct task_struct *thread;
struct cryptomgr_param *param;
const char *name = larval->alg.cra_name;
const char *p;
unsigned int len;
int i;
if (!try_module_get(THIS_MODULE))
goto err;
param = kzalloc(sizeof(*param), GFP_KERNEL);
if (!param)
goto err_put_module;
for (p = name; isalnum(*p) || *p == '-' || *p == '_'; p++)
;
len = p - name;
if (!len || *p != '(')
goto err_free_param;
memcpy(param->template, name, len);
i = 0;
for (;;) {
int notnum = 0;
name = ++p;
for (; isalnum(*p) || *p == '-' || *p == '_'; p++)
notnum |= !isdigit(*p);
if (*p == '(') {
int recursion = 0;
for (;;) {
if (!*++p)
goto err_free_param;
if (*p == '(')
recursion++;
else if (*p == ')' && !recursion--)
break;
}
notnum = 1;
p++;
}
len = p - name;
if (!len)
goto err_free_param;
if (notnum) {
param->attrs[i].alg.attr.rta_len =
sizeof(param->attrs[i].alg);
param->attrs[i].alg.attr.rta_type = CRYPTOA_ALG;
memcpy(param->attrs[i].alg.data.name, name, len);
} else {
param->attrs[i].nu32.attr.rta_len =
sizeof(param->attrs[i].nu32);
param->attrs[i].nu32.attr.rta_type = CRYPTOA_U32;
param->attrs[i].nu32.data.num =
simple_strtol(name, NULL, 0);
}
param->tb[i + 1] = &param->attrs[i].attr;
i++;
if (i >= CRYPTO_MAX_ATTRS)
goto err_free_param;
if (*p == ')')
break;
if (*p != ',')
goto err_free_param;
}
if (!i)
goto err_free_param;
param->tb[i + 1] = NULL;
param->type.attr.rta_len = sizeof(param->type);
param->type.attr.rta_type = CRYPTOA_TYPE;
param->type.data.type = larval->alg.cra_flags & ~CRYPTO_ALG_TESTED;
param->type.data.mask = larval->mask & ~CRYPTO_ALG_TESTED;
param->tb[0] = &param->type.attr;
param->otype = larval->alg.cra_flags;
param->omask = larval->mask;
crypto: algboss - Hold ref count on larval On Thu, Jun 20, 2013 at 10:00:21AM +0200, Daniel Borkmann wrote: > After having fixed a NULL pointer dereference in SCTP 1abd165e ("net: > sctp: fix NULL pointer dereference in socket destruction"), I ran into > the following NULL pointer dereference in the crypto subsystem with > the same reproducer, easily hit each time: > > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: [<ffffffff81070321>] __wake_up_common+0x31/0x90 > PGD 0 > Oops: 0000 [#1] SMP > Modules linked in: padlock_sha(F-) sha256_generic(F) sctp(F) libcrc32c(F) [..] > CPU: 6 PID: 3326 Comm: cryptomgr_probe Tainted: GF 3.10.0-rc5+ #1 > Hardware name: Dell Inc. PowerEdge T410/0H19HD, BIOS 1.6.3 02/01/2011 > task: ffff88007b6cf4e0 ti: ffff88007b7cc000 task.ti: ffff88007b7cc000 > RIP: 0010:[<ffffffff81070321>] [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP: 0018:ffff88007b7cde08 EFLAGS: 00010082 > RAX: ffffffffffffffe8 RBX: ffff88003756c130 RCX: 0000000000000000 > RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffff88003756c130 > RBP: ffff88007b7cde48 R08: 0000000000000000 R09: ffff88012b173200 > R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000282 > R13: ffff88003756c138 R14: 0000000000000000 R15: 0000000000000000 > FS: 0000000000000000(0000) GS:ffff88012fc60000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 0000000001a0b000 CR4: 00000000000007e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Stack: > ffff88007b7cde28 0000000300000000 ffff88007b7cde28 ffff88003756c130 > 0000000000000282 ffff88003756c128 ffffffff81227670 0000000000000000 > ffff88007b7cde78 ffffffff810722b7 ffff88007cdcf000 ffffffff81a90540 > Call Trace: > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff810722b7>] complete_all+0x47/0x60 > [<ffffffff81227708>] cryptomgr_probe+0x98/0xc0 > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff8106760e>] kthread+0xce/0xe0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > [<ffffffff815450dc>] ret_from_fork+0x7c/0xb0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > Code: 41 56 41 55 41 54 53 48 83 ec 18 66 66 66 66 90 89 75 cc 89 55 c8 > 4c 8d 6f 08 48 8b 57 08 41 89 cf 4d 89 c6 48 8d 42 e > RIP [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP <ffff88007b7cde08> > CR2: 0000000000000000 > ---[ end trace b495b19270a4d37e ]--- > > My assumption is that the following is happening: the minimal SCTP > tool runs under ``echo 1 > /proc/sys/net/sctp/auth_enable'', hence > it's making use of crypto_alloc_hash() via sctp_auth_init_hmacs(). > It forks itself, heavily allocates, binds, listens and waits in > accept on sctp sockets, and then randomly kills some of them (no > need for an actual client in this case to hit this). Then, again, > allocating, binding, etc, and then killing child processes. > > The problem that might be happening here is that cryptomgr requests > the module to probe/load through cryptomgr_schedule_probe(), but > before the thread handler cryptomgr_probe() returns, we return from > the wait_for_completion_interruptible() function and probably already > have cleared up larval, thus we run into a NULL pointer dereference > when in cryptomgr_probe() complete_all() is being called. > > If we wait with wait_for_completion() instead, this panic will not > occur anymore. This is valid, because in case a signal is pending, > cryptomgr_probe() returns from probing anyway with properly calling > complete_all(). The use of wait_for_completion_interruptible is intentional so that we don't lock up the thread if a bug causes us to never wake up. This bug is caused by the helper thread using the larval without holding a reference count on it. If the helper thread completes after the original thread requesting for help has gone away and destroyed the larval, then we get the crash above. So the fix is to hold a reference count on the larval. Cc: <stable@vger.kernel.org> # 3.6+ Reported-by: Daniel Borkmann <dborkman@redhat.com> Tested-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2013-06-25 11:15:17 +00:00
crypto_alg_get(&larval->alg);
param->larval = larval;
thread = kthread_run(cryptomgr_probe, param, "cryptomgr_probe");
if (IS_ERR(thread))
crypto: algboss - Hold ref count on larval On Thu, Jun 20, 2013 at 10:00:21AM +0200, Daniel Borkmann wrote: > After having fixed a NULL pointer dereference in SCTP 1abd165e ("net: > sctp: fix NULL pointer dereference in socket destruction"), I ran into > the following NULL pointer dereference in the crypto subsystem with > the same reproducer, easily hit each time: > > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: [<ffffffff81070321>] __wake_up_common+0x31/0x90 > PGD 0 > Oops: 0000 [#1] SMP > Modules linked in: padlock_sha(F-) sha256_generic(F) sctp(F) libcrc32c(F) [..] > CPU: 6 PID: 3326 Comm: cryptomgr_probe Tainted: GF 3.10.0-rc5+ #1 > Hardware name: Dell Inc. PowerEdge T410/0H19HD, BIOS 1.6.3 02/01/2011 > task: ffff88007b6cf4e0 ti: ffff88007b7cc000 task.ti: ffff88007b7cc000 > RIP: 0010:[<ffffffff81070321>] [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP: 0018:ffff88007b7cde08 EFLAGS: 00010082 > RAX: ffffffffffffffe8 RBX: ffff88003756c130 RCX: 0000000000000000 > RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffff88003756c130 > RBP: ffff88007b7cde48 R08: 0000000000000000 R09: ffff88012b173200 > R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000282 > R13: ffff88003756c138 R14: 0000000000000000 R15: 0000000000000000 > FS: 0000000000000000(0000) GS:ffff88012fc60000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 0000000001a0b000 CR4: 00000000000007e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Stack: > ffff88007b7cde28 0000000300000000 ffff88007b7cde28 ffff88003756c130 > 0000000000000282 ffff88003756c128 ffffffff81227670 0000000000000000 > ffff88007b7cde78 ffffffff810722b7 ffff88007cdcf000 ffffffff81a90540 > Call Trace: > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff810722b7>] complete_all+0x47/0x60 > [<ffffffff81227708>] cryptomgr_probe+0x98/0xc0 > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff8106760e>] kthread+0xce/0xe0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > [<ffffffff815450dc>] ret_from_fork+0x7c/0xb0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > Code: 41 56 41 55 41 54 53 48 83 ec 18 66 66 66 66 90 89 75 cc 89 55 c8 > 4c 8d 6f 08 48 8b 57 08 41 89 cf 4d 89 c6 48 8d 42 e > RIP [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP <ffff88007b7cde08> > CR2: 0000000000000000 > ---[ end trace b495b19270a4d37e ]--- > > My assumption is that the following is happening: the minimal SCTP > tool runs under ``echo 1 > /proc/sys/net/sctp/auth_enable'', hence > it's making use of crypto_alloc_hash() via sctp_auth_init_hmacs(). > It forks itself, heavily allocates, binds, listens and waits in > accept on sctp sockets, and then randomly kills some of them (no > need for an actual client in this case to hit this). Then, again, > allocating, binding, etc, and then killing child processes. > > The problem that might be happening here is that cryptomgr requests > the module to probe/load through cryptomgr_schedule_probe(), but > before the thread handler cryptomgr_probe() returns, we return from > the wait_for_completion_interruptible() function and probably already > have cleared up larval, thus we run into a NULL pointer dereference > when in cryptomgr_probe() complete_all() is being called. > > If we wait with wait_for_completion() instead, this panic will not > occur anymore. This is valid, because in case a signal is pending, > cryptomgr_probe() returns from probing anyway with properly calling > complete_all(). The use of wait_for_completion_interruptible is intentional so that we don't lock up the thread if a bug causes us to never wake up. This bug is caused by the helper thread using the larval without holding a reference count on it. If the helper thread completes after the original thread requesting for help has gone away and destroyed the larval, then we get the crash above. So the fix is to hold a reference count on the larval. Cc: <stable@vger.kernel.org> # 3.6+ Reported-by: Daniel Borkmann <dborkman@redhat.com> Tested-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2013-06-25 11:15:17 +00:00
goto err_put_larval;
wait_for_completion_interruptible(&larval->completion);
return NOTIFY_STOP;
crypto: algboss - Hold ref count on larval On Thu, Jun 20, 2013 at 10:00:21AM +0200, Daniel Borkmann wrote: > After having fixed a NULL pointer dereference in SCTP 1abd165e ("net: > sctp: fix NULL pointer dereference in socket destruction"), I ran into > the following NULL pointer dereference in the crypto subsystem with > the same reproducer, easily hit each time: > > BUG: unable to handle kernel NULL pointer dereference at (null) > IP: [<ffffffff81070321>] __wake_up_common+0x31/0x90 > PGD 0 > Oops: 0000 [#1] SMP > Modules linked in: padlock_sha(F-) sha256_generic(F) sctp(F) libcrc32c(F) [..] > CPU: 6 PID: 3326 Comm: cryptomgr_probe Tainted: GF 3.10.0-rc5+ #1 > Hardware name: Dell Inc. PowerEdge T410/0H19HD, BIOS 1.6.3 02/01/2011 > task: ffff88007b6cf4e0 ti: ffff88007b7cc000 task.ti: ffff88007b7cc000 > RIP: 0010:[<ffffffff81070321>] [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP: 0018:ffff88007b7cde08 EFLAGS: 00010082 > RAX: ffffffffffffffe8 RBX: ffff88003756c130 RCX: 0000000000000000 > RDX: 0000000000000000 RSI: 0000000000000003 RDI: ffff88003756c130 > RBP: ffff88007b7cde48 R08: 0000000000000000 R09: ffff88012b173200 > R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000282 > R13: ffff88003756c138 R14: 0000000000000000 R15: 0000000000000000 > FS: 0000000000000000(0000) GS:ffff88012fc60000(0000) knlGS:0000000000000000 > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b > CR2: 0000000000000000 CR3: 0000000001a0b000 CR4: 00000000000007e0 > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 > Stack: > ffff88007b7cde28 0000000300000000 ffff88007b7cde28 ffff88003756c130 > 0000000000000282 ffff88003756c128 ffffffff81227670 0000000000000000 > ffff88007b7cde78 ffffffff810722b7 ffff88007cdcf000 ffffffff81a90540 > Call Trace: > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff810722b7>] complete_all+0x47/0x60 > [<ffffffff81227708>] cryptomgr_probe+0x98/0xc0 > [<ffffffff81227670>] ? crypto_alloc_pcomp+0x20/0x20 > [<ffffffff8106760e>] kthread+0xce/0xe0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > [<ffffffff815450dc>] ret_from_fork+0x7c/0xb0 > [<ffffffff81067540>] ? kthread_freezable_should_stop+0x70/0x70 > Code: 41 56 41 55 41 54 53 48 83 ec 18 66 66 66 66 90 89 75 cc 89 55 c8 > 4c 8d 6f 08 48 8b 57 08 41 89 cf 4d 89 c6 48 8d 42 e > RIP [<ffffffff81070321>] __wake_up_common+0x31/0x90 > RSP <ffff88007b7cde08> > CR2: 0000000000000000 > ---[ end trace b495b19270a4d37e ]--- > > My assumption is that the following is happening: the minimal SCTP > tool runs under ``echo 1 > /proc/sys/net/sctp/auth_enable'', hence > it's making use of crypto_alloc_hash() via sctp_auth_init_hmacs(). > It forks itself, heavily allocates, binds, listens and waits in > accept on sctp sockets, and then randomly kills some of them (no > need for an actual client in this case to hit this). Then, again, > allocating, binding, etc, and then killing child processes. > > The problem that might be happening here is that cryptomgr requests > the module to probe/load through cryptomgr_schedule_probe(), but > before the thread handler cryptomgr_probe() returns, we return from > the wait_for_completion_interruptible() function and probably already > have cleared up larval, thus we run into a NULL pointer dereference > when in cryptomgr_probe() complete_all() is being called. > > If we wait with wait_for_completion() instead, this panic will not > occur anymore. This is valid, because in case a signal is pending, > cryptomgr_probe() returns from probing anyway with properly calling > complete_all(). The use of wait_for_completion_interruptible is intentional so that we don't lock up the thread if a bug causes us to never wake up. This bug is caused by the helper thread using the larval without holding a reference count on it. If the helper thread completes after the original thread requesting for help has gone away and destroyed the larval, then we get the crash above. So the fix is to hold a reference count on the larval. Cc: <stable@vger.kernel.org> # 3.6+ Reported-by: Daniel Borkmann <dborkman@redhat.com> Tested-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2013-06-25 11:15:17 +00:00
err_put_larval:
crypto_alg_put(&larval->alg);
err_free_param:
kfree(param);
err_put_module:
module_put(THIS_MODULE);
err:
return NOTIFY_OK;
}
static int cryptomgr_test(void *data)
{
struct crypto_test_param *param = data;
u32 type = param->type;
int err = 0;
#ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
goto skiptest;
#endif
if (type & CRYPTO_ALG_TESTED)
goto skiptest;
err = alg_test(param->driver, param->alg, type, CRYPTO_ALG_TESTED);
skiptest:
crypto_alg_tested(param->driver, err);
kfree(param);
module_put_and_exit(0);
}
static int cryptomgr_schedule_test(struct crypto_alg *alg)
{
struct task_struct *thread;
struct crypto_test_param *param;
u32 type;
if (!try_module_get(THIS_MODULE))
goto err;
param = kzalloc(sizeof(*param), GFP_KERNEL);
if (!param)
goto err_put_module;
memcpy(param->driver, alg->cra_driver_name, sizeof(param->driver));
memcpy(param->alg, alg->cra_name, sizeof(param->alg));
type = alg->cra_flags;
/* Do not test internal algorithms. */
if (type & CRYPTO_ALG_INTERNAL)
type |= CRYPTO_ALG_TESTED;
param->type = type;
thread = kthread_run(cryptomgr_test, param, "cryptomgr_test");
if (IS_ERR(thread))
goto err_free_param;
return NOTIFY_STOP;
err_free_param:
kfree(param);
err_put_module:
module_put(THIS_MODULE);
err:
return NOTIFY_OK;
}
static int cryptomgr_notify(struct notifier_block *this, unsigned long msg,
void *data)
{
switch (msg) {
case CRYPTO_MSG_ALG_REQUEST:
return cryptomgr_schedule_probe(data);
case CRYPTO_MSG_ALG_REGISTER:
return cryptomgr_schedule_test(data);
case CRYPTO_MSG_ALG_LOADED:
break;
}
return NOTIFY_DONE;
}
static struct notifier_block cryptomgr_notifier = {
.notifier_call = cryptomgr_notify,
};
static int __init cryptomgr_init(void)
{
return crypto_register_notifier(&cryptomgr_notifier);
}
static void __exit cryptomgr_exit(void)
{
int err = crypto_unregister_notifier(&cryptomgr_notifier);
BUG_ON(err);
}
/*
* This is arch_initcall() so that the crypto self-tests are run on algorithms
* registered early by subsys_initcall(). subsys_initcall() is needed for
* generic implementations so that they're available for comparison tests when
* other implementations are registered later by module_init().
*/
arch_initcall(cryptomgr_init);
module_exit(cryptomgr_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Crypto Algorithm Manager");