[RFC] simple_lmk: Introduce Simple Low Memory Killer for Android

[Sultan Alsawaf]

On Tue, Mar 12, 2019 at 10:17:43AM -0700, Tim Murray wrote:
> Knowing whether a SIGKILL'd process has finished reclaiming is as far
> as I know not possible without something like procfds. That's where
> the 100ms timeout in lmkd comes in. lowmemorykiller and lmkd both
> attempt to wait up to 100ms for reclaim to finish by checking for the
> continued existence of the thread that received the SIGKILL, but this
> really means that they wait up to 100ms for the _thread_ to finish,
> which doesn't tell you anything about the memory used by that process.
> If those threads terminate early and lowmemorykiller/lmkd get a signal
> to kill again, then there may be two processes competing for CPU time
> to reclaim memory. That doesn't reclaim any faster and may be an
> unnecessary kill.
> ...
> - offer a way to wait for process termination so lmkd can tell when
> reclaim has finished and know when killing another process is
> appropriate

Should be pretty easy with something like this:
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1549584a1..6ac478af2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1199,6 +1199,7 @@ struct task_struct {
 	unsigned long			lowest_stack;
 	unsigned long			prev_lowest_stack;
 #endif
+	ktime_t sigkill_time;
 
 	/*
 	 * New fields for task_struct should be added above here, so that
diff --git a/kernel/fork.c b/kernel/fork.c
index 9dcd18aa2..0ae182777 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -435,6 +435,8 @@ void put_task_stack(struct task_struct *tsk)
 
 void free_task(struct task_struct *tsk)
 {
+	ktime_t sigkill_time = tsk->sigkill_time;
+	pid_t pid = tsk->pid;
 #ifndef CONFIG_THREAD_INFO_IN_TASK
 	/*
 	 * The task is finally done with both the stack and thread_info,
@@ -455,6 +457,9 @@ void free_task(struct task_struct *tsk)
 	if (tsk->flags & PF_KTHREAD)
 		free_kthread_struct(tsk);
 	free_task_struct(tsk);
+	if (sigkill_time)
+		printk("%d killed after %lld us\n", pid,
+		       ktime_us_delta(ktime_get(), sigkill_time));
 }
 EXPORT_SYMBOL(free_task);
 
@@ -1881,6 +1886,7 @@ static __latent_entropy struct task_struct *copy_process(
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;
 #endif
+	p->sigkill_time = 0;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	retval = sched_fork(clone_flags, p);
diff --git a/kernel/signal.c b/kernel/signal.c
index 5d53183e2..1142c8811 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1168,6 +1168,8 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc
 	}
 
 out_set:
+	if (sig == SIGKILL)
+		t->sigkill_time = ktime_get();
 	signalfd_notify(t, sig);
 	sigaddset(&pending->signal, sig);