From 2500ad1c7fa42ad734677853961a3a8bec0772c5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 Apr 2022 08:43:34 -0500 Subject: 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 Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-10-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/sched/jobctl.h | 2 ++ include/linux/sched/signal.h | 5 +++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index fa067de9f1a9..d556c3425963 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -19,6 +19,7 @@ struct task_struct; #define JOBCTL_TRAPPING_BIT 21 /* switching to TRACED */ #define JOBCTL_LISTENING_BIT 22 /* ptracer is listening for events */ #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ +#define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) @@ -28,6 +29,7 @@ struct task_struct; #define JOBCTL_TRAPPING (1UL << JOBCTL_TRAPPING_BIT) #define JOBCTL_LISTENING (1UL << JOBCTL_LISTENING_BIT) #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) +#define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..e66948abbee4 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -435,9 +435,10 @@ extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); -static inline void signal_wake_up(struct task_struct *t, bool resume) +static inline void signal_wake_up(struct task_struct *t, bool fatal) { - signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); + fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); + signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { -- cgit v1.2.3 From 31cae1eaae4fd65095ad6a3659db467bc3c2599e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 3 May 2022 15:57:47 -0500 Subject: sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state Currently ptrace_stop() / do_signal_stop() rely on the special states TASK_TRACED and TASK_STOPPED resp. to keep unique state. That is, this state exists only in task->__state and nowhere else. There's two spots of bother with this: - PREEMPT_RT has task->saved_state which complicates matters, meaning task_is_{traced,stopped}() needs to check an additional variable. - An alternative freezer implementation that itself relies on a special TASK state would loose TASK_TRACED/TASK_STOPPED and will result in misbehaviour. As such, add additional state to task->jobctl to track this state outside of task->__state. NOTE: this doesn't actually fix anything yet, just adds extra state. --EWB * didn't add a unnecessary newline in signal.h * Update t->jobctl in signal_wake_up and ptrace_signal_wake_up instead of in signal_wake_up_state. This prevents the clearing of TASK_STOPPED and TASK_TRACED from getting lost. * Added warnings if JOBCTL_STOPPED or JOBCTL_TRACED are not cleared Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20220421150654.757693825@infradead.org Tested-by: Kees Cook Reviewed-by: Oleg Nesterov Link: https://lkml.kernel.org/r/20220505182645.497868-12-ebiederm@xmission.com Signed-off-by: Eric W. Biederman --- include/linux/sched/jobctl.h | 6 ++++++ include/linux/sched/signal.h | 19 +++++++++++++++---- 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux/sched') diff --git a/include/linux/sched/jobctl.h b/include/linux/sched/jobctl.h index d556c3425963..68876d0a7ef9 100644 --- a/include/linux/sched/jobctl.h +++ b/include/linux/sched/jobctl.h @@ -21,6 +21,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE_BIT 23 /* trap for cgroup freezer */ #define JOBCTL_PTRACE_FROZEN_BIT 24 /* frozen for ptrace */ +#define JOBCTL_STOPPED_BIT 26 /* do_signal_stop() */ +#define JOBCTL_TRACED_BIT 27 /* ptrace_stop() */ + #define JOBCTL_STOP_DEQUEUED (1UL << JOBCTL_STOP_DEQUEUED_BIT) #define JOBCTL_STOP_PENDING (1UL << JOBCTL_STOP_PENDING_BIT) #define JOBCTL_STOP_CONSUME (1UL << JOBCTL_STOP_CONSUME_BIT) @@ -31,6 +34,9 @@ struct task_struct; #define JOBCTL_TRAP_FREEZE (1UL << JOBCTL_TRAP_FREEZE_BIT) #define JOBCTL_PTRACE_FROZEN (1UL << JOBCTL_PTRACE_FROZEN_BIT) +#define JOBCTL_STOPPED (1UL << JOBCTL_STOPPED_BIT) +#define JOBCTL_TRACED (1UL << JOBCTL_TRACED_BIT) + #define JOBCTL_TRAP_MASK (JOBCTL_TRAP_STOP | JOBCTL_TRAP_NOTIFY) #define JOBCTL_PENDING_MASK (JOBCTL_STOP_PENDING | JOBCTL_TRAP_MASK) diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e66948abbee4..07ba3404fcde 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -294,8 +294,10 @@ static inline int kernel_dequeue_signal(void) static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); - if (current->jobctl & JOBCTL_STOP_DEQUEUED) + if (current->jobctl & JOBCTL_STOP_DEQUEUED) { + current->jobctl |= JOBCTL_STOPPED; set_special_state(TASK_STOPPED); + } spin_unlock_irq(¤t->sighand->siglock); schedule(); @@ -437,12 +439,21 @@ extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool fatal) { - fatal = fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN); - signal_wake_up_state(t, fatal ? TASK_WAKEKILL | __TASK_TRACED : 0); + unsigned int state = 0; + if (fatal && !(t->jobctl & JOBCTL_PTRACE_FROZEN)) { + t->jobctl &= ~(JOBCTL_STOPPED | JOBCTL_TRACED); + state = TASK_WAKEKILL | __TASK_TRACED; + } + signal_wake_up_state(t, state); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { - signal_wake_up_state(t, resume ? __TASK_TRACED : 0); + unsigned int state = 0; + if (resume) { + t->jobctl &= ~JOBCTL_TRACED; + state = __TASK_TRACED; + } + signal_wake_up_state(t, state); } void task_join_group_stop(struct task_struct *task); -- cgit v1.2.3