rpms/kernel/F-11 linux-2.6-clone-fix-race-between-copy-process-and-de-thread.patch, NONE, 1.1 kernel.spec, 1.1715, 1.1716

[Chuck Ebbert]

Author: cebbert

Update of /cvs/pkgs/rpms/kernel/F-11
In directory cvs1.fedora.phx.redhat.com:/tmp/cvs-serv7471

Modified Files:
	kernel.spec 
Added Files:
	linux-2.6-clone-fix-race-between-copy-process-and-de-thread.patch 
Log Message:
Fix race in clone() syscall.

linux-2.6-clone-fix-race-between-copy-process-and-de-thread.patch:
 fork.c |   20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)

--- NEW FILE linux-2.6-clone-fix-race-between-copy-process-and-de-thread.patch ---
From: Oleg Nesterov <oleg at redhat.com>
Date: Wed, 26 Aug 2009 21:29:24 +0000 (-0700)
Subject: clone(): fix race between copy_process() and de_thread()
X-Git-Url: http://git.kernel.org/?p=linux%2Fkernel%2Fgit%2Ftorvalds%2Flinux-2.6.git;a=commitdiff_plain;h=4ab6c08336535f8c8e42cf45d7adeda882eff06e

clone(): fix race between copy_process() and de_thread()

Spotted by Hiroshi Shimamoto who also provided the test-case below.

copy_process() uses signal->count as a reference counter, but it is not.
This test case

	#include <sys/types.h>
	#include <sys/wait.h>
	#include <unistd.h>
	#include <stdio.h>
	#include <errno.h>
	#include <pthread.h>

	void *null_thread(void *p)
	{
		for (;;)
			sleep(1);

		return NULL;
	}

	void *exec_thread(void *p)
	{
		execl("/bin/true", "/bin/true", NULL);

		return null_thread(p);
	}

	int main(int argc, char **argv)
	{
		for (;;) {
			pid_t pid;
			int ret, status;

			pid = fork();
			if (pid < 0)
				break;

			if (!pid) {
				pthread_t tid;

				pthread_create(&tid, NULL, exec_thread, NULL);
				for (;;)
					pthread_create(&tid, NULL, null_thread, NULL);
			}

			do {
				ret = waitpid(pid, &status, 0);
			} while (ret == -1 && errno == EINTR);
		}

		return 0;
	}

quickly creates an unkillable task.

If copy_process(CLONE_THREAD) races with de_thread()
copy_signal()->atomic(signal->count) breaks the signal->notify_count
logic, and the execing thread can hang forever in kernel space.

Change copy_process() to increment count/live only when we know for sure
we can't fail.  In this case the forked thread will take care of its
reference to signal correctly.

If copy_process() fails, check CLONE_THREAD flag.  If it it set - do
nothing, the counters were not changed and current belongs to the same
thread group.  If it is not set, ->signal must be released in any case
(and ->count must be == 1), the forked child is the only thread in the
thread group.

We need more cleanups here, in particular signal->count should not be used
by de_thread/__exit_signal at all.  This patch only fixes the bug.

Reported-by: Hiroshi Shimamoto <h-shimamoto at ct.jp.nec.com>
Tested-by: Hiroshi Shimamoto <h-shimamoto at ct.jp.nec.com>
Signed-off-by: Oleg Nesterov <oleg at redhat.com>
Acked-by: Roland McGrath <roland at redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu at jp.fujitsu.com>
Cc: <stable at kernel.org>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
---

diff --git a/kernel/fork.c b/kernel/fork.c
index 144326b..e6c04d4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -815,11 +815,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
 
-	if (clone_flags & CLONE_THREAD) {
-		atomic_inc(&current->signal->count);
-		atomic_inc(&current->signal->live);
+	if (clone_flags & CLONE_THREAD)
 		return 0;
-	}
 
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
@@ -877,16 +874,6 @@ void __cleanup_signal(struct signal_struct *sig)
 	kmem_cache_free(signal_cachep, sig);
 }
 
-static void cleanup_signal(struct task_struct *tsk)
-{
-	struct signal_struct *sig = tsk->signal;
-
-	atomic_dec(&sig->live);
-
-	if (atomic_dec_and_test(&sig->count))
-		__cleanup_signal(sig);
-}
-
 static void copy_flags(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long new_flags = p->flags;
@@ -1239,6 +1226,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	}
 
 	if (clone_flags & CLONE_THREAD) {
+		atomic_inc(&current->signal->count);
+		atomic_inc(&current->signal->live);
 		p->group_leader = current->group_leader;
 		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
 	}
@@ -1282,7 +1271,8 @@ bad_fork_cleanup_mm:
 	if (p->mm)
 		mmput(p->mm);
 bad_fork_cleanup_signal:
-	cleanup_signal(p);
+	if (!(clone_flags & CLONE_THREAD))
+		__cleanup_signal(p->signal);
 bad_fork_cleanup_sighand:
 	__cleanup_sighand(p->sighand);
 bad_fork_cleanup_fs:


Index: kernel.spec
===================================================================
RCS file: /cvs/pkgs/rpms/kernel/F-11/kernel.spec,v
retrieving revision 1.1715
retrieving revision 1.1716
diff -u -p -r1.1715 -r1.1716
--- kernel.spec	27 Aug 2009 18:04:32 -0000	1.1715
+++ kernel.spec	27 Aug 2009 18:23:32 -0000	1.1716
@@ -724,6 +724,9 @@ Patch14010: linux-2.6-x86-dont-send-ipi-
 Patch14020: linux-2.6-bitmap-make-ops-return-result.patch
 Patch14030: linux-2.6-x86-dont-call-send-ipi-mask-with-empty-mask.patch
 
+# fix race in clone()
+Patch14040: linux-2.6-clone-fix-race-between-copy-process-and-de-thread.patch
+
 %endif
 
 BuildRoot: %{_tmppath}/kernel-%{KVERREL}-root
@@ -1336,6 +1339,9 @@ ApplyPatch linux-2.6-x86-dont-send-ipi-t
 ApplyPatch linux-2.6-bitmap-make-ops-return-result.patch
 ApplyPatch linux-2.6-x86-dont-call-send-ipi-mask-with-empty-mask.patch
 
+# fix race in clone()
+ApplyPatch linux-2.6-clone-fix-race-between-copy-process-and-de-thread.patch
+
 # END OF PATCH APPLICATIONS
 
 %endif
@@ -1921,6 +1927,9 @@ fi
 # and build.
 
 %changelog
+* Thu Aug 27 2009 Chuck Ebbert <cebbert at redhat.com> 2.6.30.5-37
+- Fix race in clone() syscall.
+
 * Thu Aug 27 2009 Chuck Ebbert <cebbert at redhat.com> 2.6.30.5-36
 - Fix hangs on older x86 systems with 440*X chipsets.