Discussion:
[PATCH v3 5/5] exec: Add a exec_update_mutex to replace cred_guard_mutex
(too old to reply)
Kirill Tkhai
2020-03-17 08:56:53 UTC
Permalink
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.
Ref: 45c1a159b85b ("Add PTRACE_O_TRACEVFORKDONE and PTRACE_O_TRACEEXIT facilities.")
Ref: 456f17cd1a28 ("[PATCH] user-vm-unlock-2.5.31-A2")
---
fs/exec.c | 17 ++++++++++++++---
include/linux/binfmts.h | 8 +++++++-
include/linux/sched/signal.h | 9 ++++++++-
init/init_task.c | 1 +
kernel/fork.c | 1 +
5 files changed, 31 insertions(+), 5 deletions(-)
v3: this update fixes lock-order and adds an explicit data member in linux_binprm
diff --git a/fs/exec.c b/fs/exec.c
index d820a72..11974a1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1014,12 +1014,17 @@ 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 +1036,11 @@ 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 +1295,12 @@ 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;
The two below is non-breaking pair:

exec_mmap(bprm->mm);
bprm->called_exec_mmap = 1;

Why not move this into exec_mmap(), so nobody definitely inserts something
between them?
bprm->mm = NULL;
#ifdef CONFIG_POSIX_TIMERS
@@ -1438,6 +1446,8 @@ 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 +1497,7 @@ 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 +1689,7 @@ 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;
}
Kirill Tkhai
2020-03-17 08:58:04 UTC
Permalink
Despite this should fix the problem, this looks like a broken puzzle.
We can't use bprm->cred as an identifier whether the mutex was locked or not.
We can check for bprm->cred in regard to cred_guard_mutex, because of there is
strong rule: "cred_guard_mutex is becomes locked together with bprm->cred assignment
(see prepare_bprm_creds()), and it becomes unlocked together with bprm->cred zeroing".
Take attention on modularity of all this: there is no dependencies between anything else.
In regard to newly introduced exec_update_mutex, your fix and source patch way look like
an obfuscation. The mutex becomes deadly glued to unrelated bprm->cred and bprm->mm,
and this introduces the problems in the future modifications and support of all involved
entities. If someone wants to move some functions in relation to each other, there will
be a pain, and this person will have to go again the same dependencies and bug way,
Eric stepped on in the original patch.
Okay, yes, valid points you make, thanks.
I just wanted to understand what was exactly wrong with this patch,
since the failure mode looked a lot like it was failing because of
something clobbering the data unexpectedly.
[PATCH v3 5/5] exec: Add a exec_update_mutex to replace cred_guard_mutex
[PATCH] pidfd: Use new infrastructure to fix deadlocks in execve
[PATCH v2 5/5] exec: Add a exec_update_mutex to replace cred_guard_mutex
[PATCH] pidfd: Stop taking cred_guard_mutex
[PATCH 0/2] exec: Fix dead-lock in de_thread with ptrace_attach
[PATCH 1/2] exec: Fix dead-lock in de_thread with ptrace_attach
[PATCH 2/2] doc: Update documentation of ->exec_*_mutex
[PATCH v2 1/5] exec: Only compute current once in flush_old_exec
[PATCH v2 2/5] exec: Factor unshare_sighand out of de_thread and call it separately
[PATCH v2 3/5] exec: Move cleanup of posix timers on exec out of de_thread
[PATCH v2 4/5] exec: Move exec_mmap right after de_thread in flush_old_exec
1-4/5 look OK for me. You may add my
[PATCH 1/4] exec: Fix a deadlock in ptrace
[PATCH 2/4] selftests/ptrace: add test cases for dead-locks
[PATCH 3/4] mm: docs: Fix a comment in process_vm_rw_core
[PATCH 4/4] kernel: doc: remove outdated comment cred.c
[PATCH 1/4] kernel/kcmp.c: Use new infrastructure to fix deadlocks in execve
[PATCH 2/4] proc: Use new infrastructure to fix deadlocks in execve
[PATCH 3/4] proc: io_accounting: Use new infrastructure to fix deadlocks in execve
[PATCH 4/4] perf: Use new infrastructure to fix deadlocks in execve
I think most of the existing patches are already approved, but if
there are still change requests, please let me know.
Thanks
Bernd.
Hope it is correct now.
I haven't seen the new patches on the kernel archives yet,
so I cannot add URLs for them.
Bernd.
Bernd Edlinger
2020-03-17 21:53:53 UTC
Permalink
Post by Kirill Tkhai
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.
Ref: 45c1a159b85b ("Add PTRACE_O_TRACEVFORKDONE and PTRACE_O_TRACEEXIT facilities.")
Ref: 456f17cd1a28 ("[PATCH] user-vm-unlock-2.5.31-A2")
---
fs/exec.c | 17 ++++++++++++++---
include/linux/binfmts.h | 8 +++++++-
include/linux/sched/signal.h | 9 ++++++++-
init/init_task.c | 1 +
kernel/fork.c | 1 +
5 files changed, 31 insertions(+), 5 deletions(-)
v3: this update fixes lock-order and adds an explicit data member in linux_binprm
diff --git a/fs/exec.c b/fs/exec.c
index d820a72..11974a1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1014,12 +1014,17 @@ 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 +1036,11 @@ 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 +1295,12 @@ 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;
exec_mmap(bprm->mm);
bprm->called_exec_mmap = 1;
Why not move this into exec_mmap(), so nobody definitely inserts something
between them?
Hmm, could be done, but then I would probably need a different name than
"called_exec_mmap".

How about adding a nice function comment to exec_mmap that calls out the
changed behaviour that the exec_update_mutex is taken unless the function
fails?


Bernd.
Post by Kirill Tkhai
bprm->mm = NULL;
#ifdef CONFIG_POSIX_TIMERS
@@ -1438,6 +1446,8 @@ 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 +1497,7 @@ 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 +1689,7 @@ 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;
}
Loading...