diff options
author | Eric W. Biederman <ebiederm@xmission.com> | 2022-04-29 08:43:34 -0500 |
---|---|---|
committer | Eric W. Biederman <ebiederm@xmission.com> | 2022-05-11 14:35:32 -0500 |
commit | 2500ad1c7fa42ad734677853961a3a8bec0772c5 (patch) | |
tree | e94af9b15cf725771c652439f12c2c9607663c38 /kernel | |
parent | 57b6de08b5f6586851c2261ef0cc16cd275615e7 (diff) | |
download | linux-stable-2500ad1c7fa42ad734677853961a3a8bec0772c5.tar.gz linux-stable-2500ad1c7fa42ad734677853961a3a8bec0772c5.tar.bz2 linux-stable-2500ad1c7fa42ad734677853961a3a8bec0772c5.zip |
ptrace: Don't change __state
Stop playing with tsk->__state to remove TASK_WAKEKILL while a ptrace
command is executing.
Instead remove TASK_WAKEKILL from the definition of TASK_TRACED, and
implement a new jobctl flag TASK_PTRACE_FROZEN. This new flag is set
in jobctl_freeze_task and cleared when ptrace_stop is awoken or in
jobctl_unfreeze_task (when ptrace_stop remains asleep).
In signal_wake_up add __TASK_TRACED to state along with TASK_WAKEKILL
when the wake up is for a fatal signal. Skip adding __TASK_TRACED
when TASK_PTRACE_FROZEN is not set. This has the same effect as
changing TASK_TRACED to __TASK_TRACED as all of the wake_ups that use
TASK_KILLABLE go through signal_wake_up.
Handle a ptrace_stop being called with a pending fatal signal.
Previously it would have been handled by schedule simply failing to
sleep. As TASK_WAKEKILL is no longer part of TASK_TRACED schedule
will sleep with a fatal_signal_pending. The code in signal_wake_up
guarantees that the code will be awaked by any fatal signal that
codes after TASK_TRACED is set.
Previously the __state value of __TASK_TRACED was changed to
TASK_RUNNING when woken up or back to TASK_TRACED when the code was
left in ptrace_stop. Now when woken up ptrace_stop now clears
JOBCTL_PTRACE_FROZEN and when left sleeping ptrace_unfreezed_traced
clears JOBCTL_PTRACE_FROZEN.
Tested-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/ptrace.c | 21 | ||||
-rw-r--r-- | kernel/sched/core.c | 5 | ||||
-rw-r--r-- | kernel/signal.c | 14 |
3 files changed, 15 insertions, 25 deletions
diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 05953ac9f7bd..83ed28262708 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -197,7 +197,7 @@ static bool ptrace_freeze_traced(struct task_struct *task) spin_lock_irq(&task->sighand->siglock); if (task_is_traced(task) && !looks_like_a_spurious_pid(task) && !__fatal_signal_pending(task)) { - WRITE_ONCE(task->__state, __TASK_TRACED); + task->jobctl |= JOBCTL_PTRACE_FROZEN; ret = true; } spin_unlock_irq(&task->sighand->siglock); @@ -207,23 +207,19 @@ static bool ptrace_freeze_traced(struct task_struct *task) static void ptrace_unfreeze_traced(struct task_struct *task) { - if (READ_ONCE(task->__state) != __TASK_TRACED) - return; - - WARN_ON(!task->ptrace || task->parent != current); + unsigned long flags; /* - * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely. - * Recheck state under the lock to close this race. + * The child may be awake and may have cleared + * JOBCTL_PTRACE_FROZEN (see ptrace_resume). The child will + * not set JOBCTL_PTRACE_FROZEN or enter __TASK_TRACED anew. */ - spin_lock_irq(&task->sighand->siglock); - if (READ_ONCE(task->__state) == __TASK_TRACED) { + if (lock_task_sighand(task, &flags)) { + task->jobctl &= ~JOBCTL_PTRACE_FROZEN; if (__fatal_signal_pending(task)) wake_up_state(task, __TASK_TRACED); - else - WRITE_ONCE(task->__state, TASK_TRACED); + unlock_task_sighand(task, &flags); } - spin_unlock_irq(&task->sighand->siglock); } /** @@ -256,7 +252,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) */ read_lock(&tasklist_lock); if (child->ptrace && child->parent == current) { - WARN_ON(READ_ONCE(child->__state) == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..3c351707e830 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6304,10 +6304,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) /* * We must load prev->state once (task_struct::state is volatile), such - * that: - * - * - we form a control dependency vs deactivate_task() below. - * - ptrace_{,un}freeze_traced() can change ->state underneath us. + * that we form a control dependency vs deactivate_task() below. */ prev_state = READ_ONCE(prev->__state); if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) { diff --git a/kernel/signal.c b/kernel/signal.c index d2d0c753156c..a58b68a2d3c6 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2209,14 +2209,12 @@ static int ptrace_stop(int exit_code, int why, unsigned long message, } /* - * schedule() will not sleep if there is a pending signal that - * can awaken the task. - * - * After this point ptrace_signal_wake_up will clear TASK_TRACED - * if ptrace_unlink happens. Handle previous ptrace_unlinks - * here to prevent ptrace_stop sleeping in schedule. + * After this point ptrace_signal_wake_up or signal_wake_up + * will clear TASK_TRACED if ptrace_unlink happens or a fatal + * signal comes in. Handle previous ptrace_unlinks and fatal + * signals here to prevent ptrace_stop sleeping in schedule. */ - if (!current->ptrace) + if (!current->ptrace || __fatal_signal_pending(current)) return exit_code; set_special_state(TASK_TRACED); @@ -2305,7 +2303,7 @@ static int ptrace_stop(int exit_code, int why, unsigned long message, current->exit_code = 0; /* LISTENING can be set only during STOP traps, clear it */ - current->jobctl &= ~JOBCTL_LISTENING; + current->jobctl &= ~(JOBCTL_LISTENING | JOBCTL_PTRACE_FROZEN); /* * Queued signals ignored us while we were stopped for tracing. |