[v4,3/5] exec: Add a exec_update_mutex to replace cred_guard_mutex

Commit Message

Bernd Edlinger March 19, 2020, 9:11 a.m. UTC

The cred_guard_mutex is problematic.  The cred_guard_mutex is held
over the userspace accesses as the arguments from userspace are read.
The cred_guard_mutex is held of PTRACE_EVENT_EXIT as the the other
threads are killed.  The cred_guard_mutex is held over
"put_user(0, tsk->clear_child_tid)" in exit_mm().

Any of those can result in deadlock, as the cred_guard_mutex is held
over a possible indefinite userspace waits for userspace.

Add exec_update_mutex that is only held over exec updating process
with the new contents of exec, so that code that needs not to be
confused by exec changing the mm and the cred in ways that can not
happen during ordinary execution of a process.

The plan is to switch the users of cred_guard_mutex to
exec_udpate_mutex one by one.  This lets us move forward while still
being careful and not introducing any regressions.

Link: https://lore.kernel.org/lkml/[e-mail]/
Link: https://lore.kernel.org/lkml/[e-mail]/
Link: https://lore.kernel.org/linux-fsdevel/[e-mail]/
Link: https://lore.kernel.org/lkml/[e-mail]/
Link: https://lore.kernel.org/lkml/[e-mail]/
Ref: 45c1a159b85b ("Add PTRACE_O_TRACEVFORKDONE and PTRACE_O_TRACEEXIT facilities.")
Ref: 456f17cd1a28 ("[PATCH] user-vm-unlock-2.5.31-A2")
Signed-off-by: "Eric W. Biederman" <[e-mail]>
Signed-off-by: Bernd Edlinger <[e-mail]>
---
 fs/exec.c                    | 22 +++++++++++++++++++---
 include/linux/binfmts.h      |  8 +++++++-
 include/linux/sched/signal.h |  9 ++++++++-
 init/init_task.c             |  1 +
 kernel/fork.c                |  1 +
 5 files changed, 36 insertions(+), 5 deletions(-)

v3: this update fixes lock-order and adds an explicit data member in linux_binprm
v4: add a function comment to exec_mmap

Comments

Bernd Edlinger March 19, 2020, 9:13 a.m. UTC | #1

Ah, sorry this is actuall v4 5/5.
Should I send a new version or can you handle it?


On 3/19/20 10:11 AM, Bernd Edlinger wrote:
> The cred_guard_mutex is problematic.  The cred_guard_mutex is held
> over the userspace accesses as the arguments from userspace are read.
> The cred_guard_mutex is held of PTRACE_EVENT_EXIT as the the other
> threads are killed.  The cred_guard_mutex is held over
> "put_user(0, tsk->clear_child_tid)" in exit_mm().
> 
> Any of those can result in deadlock, as the cred_guard_mutex is held
> over a possible indefinite userspace waits for userspace.
> 
> Add exec_update_mutex that is only held over exec updating process
> with the new contents of exec, so that code that needs not to be
> confused by exec changing the mm and the cred in ways that can not
> happen during ordinary execution of a process.
> 
> The plan is to switch the users of cred_guard_mutex to
> exec_udpate_mutex one by one.  This lets us move forward while still
> being careful and not introducing any regressions.
> 
> Link: https://lore.kernel.org/lkml/[e-mail]/
> Link: https://lore.kernel.org/lkml/[e-mail]/
> Link: https://lore.kernel.org/linux-fsdevel/[e-mail]/
> Link: https://lore.kernel.org/lkml/[e-mail]/
> Link: https://lore.kernel.org/lkml/[e-mail]/
> Ref: 45c1a159b85b ("Add PTRACE_O_TRACEVFORKDONE and PTRACE_O_TRACEEXIT facilities.")
> Ref: 456f17cd1a28 ("[PATCH] user-vm-unlock-2.5.31-A2")
> Signed-off-by: "Eric W. Biederman" <[e-mail]>
> Signed-off-by: Bernd Edlinger <[e-mail]>
> ---
>  fs/exec.c                    | 22 +++++++++++++++++++---
>  include/linux/binfmts.h      |  8 +++++++-
>  include/linux/sched/signal.h |  9 ++++++++-
>  init/init_task.c             |  1 +
>  kernel/fork.c                |  1 +
>  5 files changed, 36 insertions(+), 5 deletions(-)
> 
> v3: this update fixes lock-order and adds an explicit data member in linux_binprm
> v4: add a function comment to exec_mmap
> 
> diff --git a/fs/exec.c b/fs/exec.c
> index d820a72..0e46ec5 100644
> --- a/fs/exec.c
> +++ b/fs/exec.c
> @@ -1010,16 +1010,26 @@ ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
>  }
>  EXPORT_SYMBOL(read_code);
>  
> +/*
> + * Maps the mm_struct mm into the current task struct.
> + * On success, this function returns with the mutex
> + * exec_update_mutex locked.
> + */
>  static int exec_mmap(struct mm_struct *mm)
>  {
>  	struct task_struct *tsk;
>  	struct mm_struct *old_mm, *active_mm;
> +	int ret;
>  
>  	/* Notify parent that we're no longer interested in the old VM */
>  	tsk = current;
>  	old_mm = current->mm;
>  	exec_mm_release(tsk, old_mm);
>  
> +	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
> +	if (ret)
> +		return ret;
> +
>  	if (old_mm) {
>  		sync_mm_rss(old_mm);
>  		/*
> @@ -1031,9 +1041,11 @@ static int exec_mmap(struct mm_struct *mm)
>  		down_read(&old_mm->mmap_sem);
>  		if (unlikely(old_mm->core_state)) {
>  			up_read(&old_mm->mmap_sem);
> +			mutex_unlock(&tsk->signal->exec_update_mutex);
>  			return -EINTR;
>  		}
>  	}
> +
>  	task_lock(tsk);
>  	active_mm = tsk->active_mm;
>  	membarrier_exec_mmap(mm);
> @@ -1288,11 +1300,12 @@ int flush_old_exec(struct linux_binprm * bprm)
>  		goto out;
>  
>  	/*
> -	 * After clearing bprm->mm (to mark that current is using the
> -	 * prepared mm now), we have nothing left of the original
> +	 * After setting bprm->called_exec_mmap (to mark that current is
> +	 * using the prepared mm now), we have nothing left of the original
>  	 * process. If anything from here on returns an error, the check
>  	 * in search_binary_handler() will SEGV current.
>  	 */
> +	bprm->called_exec_mmap = 1;
>  	bprm->mm = NULL;
>  
>  #ifdef CONFIG_POSIX_TIMERS
> @@ -1438,6 +1451,8 @@ static void free_bprm(struct linux_binprm *bprm)
>  {
>  	free_arg_pages(bprm);
>  	if (bprm->cred) {
> +		if (bprm->called_exec_mmap)
> +			mutex_unlock(&current->signal->exec_update_mutex);
>  		mutex_unlock(&current->signal->cred_guard_mutex);
>  		abort_creds(bprm->cred);
>  	}
> @@ -1487,6 +1502,7 @@ void install_exec_creds(struct linux_binprm *bprm)
>  	 * credentials; any time after this it may be unlocked.
>  	 */
>  	security_bprm_committed_creds(bprm);
> +	mutex_unlock(&current->signal->exec_update_mutex);
>  	mutex_unlock(&current->signal->cred_guard_mutex);
>  }
>  EXPORT_SYMBOL(install_exec_creds);
> @@ -1678,7 +1694,7 @@ int search_binary_handler(struct linux_binprm *bprm)
>  
>  		read_lock(&binfmt_lock);
>  		put_binfmt(fmt);
> -		if (retval < 0 && !bprm->mm) {
> +		if (retval < 0 && bprm->called_exec_mmap) {
>  			/* we got to flush_old_exec() and failed after it */
>  			read_unlock(&binfmt_lock);
>  			force_sigsegv(SIGSEGV);
> diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
> index b40fc63..a345d9f 100644
> --- a/include/linux/binfmts.h
> +++ b/include/linux/binfmts.h
> @@ -44,7 +44,13 @@ struct linux_binprm {
>  		 * exec has happened. Used to sanitize execution environment
>  		 * and to set AT_SECURE auxv for glibc.
>  		 */
> -		secureexec:1;
> +		secureexec:1,
> +		/*
> +		 * Set by flush_old_exec, when exec_mmap has been called.
> +		 * This is past the point of no return, when the
> +		 * exec_update_mutex has been taken.
> +		 */
> +		called_exec_mmap:1;
>  #ifdef __alpha__
>  	unsigned int taso:1;
>  #endif
> diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
> index 8805025..a29df79 100644
> --- a/include/linux/sched/signal.h
> +++ b/include/linux/sched/signal.h
> @@ -224,7 +224,14 @@ struct signal_struct {
>  
>  	struct mutex cred_guard_mutex;	/* guard against foreign influences on
>  					 * credential calculations
> -					 * (notably. ptrace) */
> +					 * (notably. ptrace)
> +					 * Deprecated do not use in new code.
> +					 * Use exec_update_mutex instead.
> +					 */
> +	struct mutex exec_update_mutex;	/* Held while task_struct is being
> +					 * updated during exec, and may have
> +					 * inconsistent permissions.
> +					 */
>  } __randomize_layout;
>  
>  /*
> diff --git a/init/init_task.c b/init/init_task.c
> index 9e5cbe5..bd403ed 100644
> --- a/init/init_task.c
> +++ b/init/init_task.c
> @@ -26,6 +26,7 @@
>  	.multiprocess	= HLIST_HEAD_INIT,
>  	.rlim		= INIT_RLIMITS,
>  	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
> +	.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
>  #ifdef CONFIG_POSIX_TIMERS
>  	.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
>  	.cputimer	= {
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 8642530..036b692 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1594,6 +1594,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
>  	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
>  
>  	mutex_init(&sig->cred_guard_mutex);
> +	mutex_init(&sig->exec_update_mutex);
>  
>  	return 0;
>  }
>

Greg KH March 19, 2020, 9:19 a.m. UTC | #2

On Thu, Mar 19, 2020 at 10:13:20AM +0100, Bernd Edlinger wrote:
> Ah, sorry this is actuall v4 5/5.
> Should I send a new version or can you handle it?

This thread is a total crazy mess of different versions.

I know I can't unwind any of this, so I _STRONGLY_ suggest resending the
whole series, properly versioned, as a new thread.

Would you want to try to pick out the proper patches from this pile?

thanks,

greg k-h

Bernd Edlinger March 19, 2020, 9:20 a.m. UTC | #3

On 3/19/20 10:19 AM, Greg Kroah-Hartman wrote:
> On Thu, Mar 19, 2020 at 10:13:20AM +0100, Bernd Edlinger wrote:
>> Ah, sorry this is actuall v4 5/5.
>> Should I send a new version or can you handle it?
> 
> This thread is a total crazy mess of different versions.
> 
> I know I can't unwind any of this, so I _STRONGLY_ suggest resending the
> whole series, properly versioned, as a new thread.
> 
> Would you want to try to pick out the proper patches from this pile?
> 
> thanks,
> 
> greg k-h
> 

Yes, thanks, good suggestion.

I will do that in the evening.

Bernd Edlinger March 21, 2020, 10:53 p.m. UTC | #4

On 3/19/20 10:19 AM, Greg Kroah-Hartman wrote:
> On Thu, Mar 19, 2020 at 10:13:20AM +0100, Bernd Edlinger wrote:
>> Ah, sorry this is actuall v4 5/5.
>> Should I send a new version or can you handle it?
> 
> This thread is a total crazy mess of different versions.
> 
> I know I can't unwind any of this, so I _STRONGLY_ suggest resending the
> whole series, properly versioned, as a new thread.
> 
> Would you want to try to pick out the proper patches from this pile?
> 
> thanks,
> 
> greg k-h
> 

Okay, meanwhile I collected everything I could find from this thread
and sent it again:

[PATCH v6 00/16] Infrastructure to allow fixing exec deadlocks
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 01/16] exec: Only compute current once in flush_old_exec
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 02/16] exec: Factor unshare_sighand out of de_thread and call it separately
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 03/16] exec: Move cleanup of posix timers on exec out of de_thread
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 04/16] exec: Move exec_mmap right after de_thread in flush_old_exec
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 05/16] exec: Add exec_update_mutex to replace cred_guard_mutex
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 06/16] exec: Fix a deadlock in strace
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 07/16] selftests/ptrace: add test cases for dead-locks
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 08/16] mm: docs: Fix a comment in process_vm_rw_core
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 09/16] kernel: doc: remove outdated comment cred.c
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 10/16] kernel/kcmp.c: Use new infrastructure to fix deadlocks in execve
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 11/16] proc: Use new infrastructure to fix deadlocks in execve
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 12/16] proc: io_accounting: Use new infrastructure to fix deadlocks in execve
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 13/16] perf: Use new infrastructure to fix deadlocks in execve
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 14/16] pidfd: Use new infrastructure to fix deadlocks in execve
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 15/16] exec: Fix dead-lock in de_thread with ptrace_attach
https://lore.kernel.org/lkml/[e-mail]/

[PATCH v6 16/16] doc: Update documentation of ->exec_*_mutex
https://lore.kernel.org/lkml/[e-mail]/


Each of the patches in this series build on the previous one and are independent from the following
patches.  So if one or more of these turn out to be controversial, the previous patches are still an
improvement, especially [PATCH v6 06/16] which fixes the deadlock in strace, this one fixes the most
important tracing deadlocks.


Thanks
Bernd.

Patch

diff --git a/fs/exec.c b/fs/exec.c
index d820a72..0e46ec5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1010,16 +1010,26 @@  ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len)
 }
 EXPORT_SYMBOL(read_code);
 
+/*
+ * Maps the mm_struct mm into the current task struct.
+ * On success, this function returns with the mutex
+ * exec_update_mutex locked.
+ */
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
 	struct mm_struct *old_mm, *active_mm;
+	int ret;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
 	old_mm = current->mm;
 	exec_mm_release(tsk, old_mm);
 
+	ret = mutex_lock_killable(&tsk->signal->exec_update_mutex);
+	if (ret)
+		return ret;
+
 	if (old_mm) {
 		sync_mm_rss(old_mm);
 		/*
@@ -1031,9 +1041,11 @@  static int exec_mmap(struct mm_struct *mm)
 		down_read(&old_mm->mmap_sem);
 		if (unlikely(old_mm->core_state)) {
 			up_read(&old_mm->mmap_sem);
+			mutex_unlock(&tsk->signal->exec_update_mutex);
 			return -EINTR;
 		}
 	}
+
 	task_lock(tsk);
 	active_mm = tsk->active_mm;
 	membarrier_exec_mmap(mm);
@@ -1288,11 +1300,12 @@  int flush_old_exec(struct linux_binprm * bprm)
 		goto out;
 
 	/*
-	 * After clearing bprm->mm (to mark that current is using the
-	 * prepared mm now), we have nothing left of the original
+	 * After setting bprm->called_exec_mmap (to mark that current is
+	 * using the prepared mm now), we have nothing left of the original
 	 * process. If anything from here on returns an error, the check
 	 * in search_binary_handler() will SEGV current.
 	 */
+	bprm->called_exec_mmap = 1;
 	bprm->mm = NULL;
 
 #ifdef CONFIG_POSIX_TIMERS
@@ -1438,6 +1451,8 @@  static void free_bprm(struct linux_binprm *bprm)
 {
 	free_arg_pages(bprm);
 	if (bprm->cred) {
+		if (bprm->called_exec_mmap)
+			mutex_unlock(&current->signal->exec_update_mutex);
 		mutex_unlock(&current->signal->cred_guard_mutex);
 		abort_creds(bprm->cred);
 	}
@@ -1487,6 +1502,7 @@  void install_exec_creds(struct linux_binprm *bprm)
 	 * credentials; any time after this it may be unlocked.
 	 */
 	security_bprm_committed_creds(bprm);
+	mutex_unlock(&current->signal->exec_update_mutex);
 	mutex_unlock(&current->signal->cred_guard_mutex);
 }
 EXPORT_SYMBOL(install_exec_creds);
@@ -1678,7 +1694,7 @@  int search_binary_handler(struct linux_binprm *bprm)
 
 		read_lock(&binfmt_lock);
 		put_binfmt(fmt);
-		if (retval < 0 && !bprm->mm) {
+		if (retval < 0 && bprm->called_exec_mmap) {
 			/* we got to flush_old_exec() and failed after it */
 			read_unlock(&binfmt_lock);
 			force_sigsegv(SIGSEGV);
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index b40fc63..a345d9f 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -44,7 +44,13 @@  struct linux_binprm {
 		 * exec has happened. Used to sanitize execution environment
 		 * and to set AT_SECURE auxv for glibc.
 		 */
-		secureexec:1;
+		secureexec:1,
+		/*
+		 * Set by flush_old_exec, when exec_mmap has been called.
+		 * This is past the point of no return, when the
+		 * exec_update_mutex has been taken.
+		 */
+		called_exec_mmap:1;
 #ifdef __alpha__
 	unsigned int taso:1;
 #endif
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 8805025..a29df79 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -224,7 +224,14 @@  struct signal_struct {
 
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
-					 * (notably. ptrace) */
+					 * (notably. ptrace)
+					 * Deprecated do not use in new code.
+					 * Use exec_update_mutex instead.
+					 */
+	struct mutex exec_update_mutex;	/* Held while task_struct is being
+					 * updated during exec, and may have
+					 * inconsistent permissions.
+					 */
 } __randomize_layout;
 
 /*
diff --git a/init/init_task.c b/init/init_task.c
index 9e5cbe5..bd403ed 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -26,6 +26,7 @@ 
 	.multiprocess	= HLIST_HEAD_INIT,
 	.rlim		= INIT_RLIMITS,
 	.cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex),
+	.exec_update_mutex = __MUTEX_INITIALIZER(init_signals.exec_update_mutex),
 #ifdef CONFIG_POSIX_TIMERS
 	.posix_timers = LIST_HEAD_INIT(init_signals.posix_timers),
 	.cputimer	= {
diff --git a/kernel/fork.c b/kernel/fork.c
index 8642530..036b692 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1594,6 +1594,7 @@  static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
 	mutex_init(&sig->cred_guard_mutex);
+	mutex_init(&sig->exec_update_mutex);
 
 	return 0;
 }