diff options
Diffstat (limited to 'kernel/context_tracking.c')
| -rw-r--r-- | kernel/context_tracking.c | 126 |
1 files changed, 84 insertions, 42 deletions
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 937ecdfdf258..0a495ab35bc7 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -30,24 +30,35 @@ EXPORT_SYMBOL_GPL(context_tracking_enabled); DEFINE_PER_CPU(struct context_tracking, context_tracking); EXPORT_SYMBOL_GPL(context_tracking); -void context_tracking_cpu_set(int cpu) +static bool context_tracking_recursion_enter(void) { - if (!per_cpu(context_tracking.active, cpu)) { - per_cpu(context_tracking.active, cpu) = true; - static_key_slow_inc(&context_tracking_enabled); - } + int recursion; + + recursion = __this_cpu_inc_return(context_tracking.recursion); + if (recursion == 1) + return true; + + WARN_ONCE((recursion < 1), "Invalid context tracking recursion value %d\n", recursion); + __this_cpu_dec(context_tracking.recursion); + + return false; +} + +static void context_tracking_recursion_exit(void) +{ + __this_cpu_dec(context_tracking.recursion); } /** - * context_tracking_user_enter - Inform the context tracking that the CPU is going to - * enter userspace mode. + * context_tracking_enter - Inform the context tracking that the CPU is going + * enter user or guest space mode. * * This function must be called right before we switch from the kernel - * to userspace, when it's guaranteed the remaining kernel instructions - * to execute won't use any RCU read side critical section because this - * function sets RCU in extended quiescent state. + * to user or guest space, when it's guaranteed the remaining kernel + * instructions to execute won't use any RCU read side critical section + * because this function sets RCU in extended quiescent state. */ -void context_tracking_user_enter(void) +void context_tracking_enter(enum ctx_state state) { unsigned long flags; @@ -75,9 +86,11 @@ void context_tracking_user_enter(void) WARN_ON_ONCE(!current->mm); local_irq_save(flags); - if ( __this_cpu_read(context_tracking.state) != IN_USER) { + if (!context_tracking_recursion_enter()) + goto out_irq_restore; + + if ( __this_cpu_read(context_tracking.state) != state) { if (__this_cpu_read(context_tracking.active)) { - trace_user_enter(0); /* * At this stage, only low level arch entry code remains and * then we'll run in userspace. We can assume there won't be @@ -85,7 +98,10 @@ void context_tracking_user_enter(void) * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency * on the tick. */ - vtime_user_enter(current); + if (state == CONTEXT_USER) { + trace_user_enter(0); + vtime_user_enter(current); + } rcu_user_enter(); } /* @@ -101,24 +117,34 @@ void context_tracking_user_enter(void) * OTOH we can spare the calls to vtime and RCU when context_tracking.active * is false because we know that CPU is not tickless. */ - __this_cpu_write(context_tracking.state, IN_USER); + __this_cpu_write(context_tracking.state, state); } + context_tracking_recursion_exit(); +out_irq_restore: local_irq_restore(flags); } +NOKPROBE_SYMBOL(context_tracking_enter); +EXPORT_SYMBOL_GPL(context_tracking_enter); + +void context_tracking_user_enter(void) +{ + context_tracking_enter(CONTEXT_USER); +} NOKPROBE_SYMBOL(context_tracking_user_enter); /** - * context_tracking_user_exit - Inform the context tracking that the CPU is - * exiting userspace mode and entering the kernel. + * context_tracking_exit - Inform the context tracking that the CPU is + * exiting user or guest mode and entering the kernel. * - * This function must be called after we entered the kernel from userspace - * before any use of RCU read side critical section. This potentially include - * any high level kernel code like syscalls, exceptions, signal handling, etc... + * This function must be called after we entered the kernel from user or + * guest space before any use of RCU read side critical section. This + * potentially include any high level kernel code like syscalls, exceptions, + * signal handling, etc... * * This call supports re-entrancy. This way it can be called from any exception * handler without needing to know if we came from userspace or not. */ -void context_tracking_user_exit(void) +void context_tracking_exit(enum ctx_state state) { unsigned long flags; @@ -129,40 +155,56 @@ void context_tracking_user_exit(void) return; local_irq_save(flags); - if (__this_cpu_read(context_tracking.state) == IN_USER) { + if (!context_tracking_recursion_enter()) + goto out_irq_restore; + + if (__this_cpu_read(context_tracking.state) == state) { if (__this_cpu_read(context_tracking.active)) { /* * We are going to run code that may use RCU. Inform * RCU core about that (ie: we may need the tick again). */ rcu_user_exit(); - vtime_user_exit(current); - trace_user_exit(0); + if (state == CONTEXT_USER) { + vtime_user_exit(current); + trace_user_exit(0); + } } - __this_cpu_write(context_tracking.state, IN_KERNEL); + __this_cpu_write(context_tracking.state, CONTEXT_KERNEL); } + context_tracking_recursion_exit(); +out_irq_restore: local_irq_restore(flags); } +NOKPROBE_SYMBOL(context_tracking_exit); +EXPORT_SYMBOL_GPL(context_tracking_exit); + +void context_tracking_user_exit(void) +{ + context_tracking_exit(CONTEXT_USER); +} NOKPROBE_SYMBOL(context_tracking_user_exit); -/** - * __context_tracking_task_switch - context switch the syscall callbacks - * @prev: the task that is being switched out - * @next: the task that is being switched in - * - * The context tracking uses the syscall slow path to implement its user-kernel - * boundaries probes on syscalls. This way it doesn't impact the syscall fast - * path on CPUs that don't do context tracking. - * - * But we need to clear the flag on the previous task because it may later - * migrate to some CPU that doesn't do the context tracking. As such the TIF - * flag may not be desired there. - */ -void __context_tracking_task_switch(struct task_struct *prev, - struct task_struct *next) +void __init context_tracking_cpu_set(int cpu) { - clear_tsk_thread_flag(prev, TIF_NOHZ); - set_tsk_thread_flag(next, TIF_NOHZ); + static __initdata bool initialized = false; + + if (!per_cpu(context_tracking.active, cpu)) { + per_cpu(context_tracking.active, cpu) = true; + static_key_slow_inc(&context_tracking_enabled); + } + + if (initialized) + return; + + /* + * Set TIF_NOHZ to init/0 and let it propagate to all tasks through fork + * This assumes that init is the only task at this early boot stage. + */ + set_tsk_thread_flag(&init_task, TIF_NOHZ); + WARN_ON_ONCE(!tasklist_empty()); + + initialized = true; } #ifdef CONFIG_CONTEXT_TRACKING_FORCE |