linux-kernel - Re: [PATCH 6/8] lazy tlb: shoot lazies, a non-refcounting lazy tlb option

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20201202141957.GJ3021@hirez.programming.kicks-ass.net>
Date:   Wed, 2 Dec 2020 15:19:57 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Nicholas Piggin <npiggin@...il.com>
Cc:     linux-kernel@...r.kernel.org, x86@...nel.org,
        Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
        Arnd Bergmann <arnd@...db.de>, linux-arch@...r.kernel.org,
        linuxppc-dev@...ts.ozlabs.org, linux-mm@...ck.org,
        Anton Blanchard <anton@...abs.org>
Subject: Re: [PATCH 6/8] lazy tlb: shoot lazies, a non-refcounting lazy tlb
 option

On Sun, Nov 29, 2020 at 02:01:39AM +1000, Nicholas Piggin wrote:
> +		 * - A delayed freeing and RCU-like quiescing sequence based on
> +		 *   mm switching to avoid IPIs completely.

That one's interesting too. so basically you want to count switch_mm()
invocations on each CPU. Then, periodically snapshot the counter on each
CPU, and when they've all changed, increment a global counter.

Then, you snapshot the global counter and wait for it to increment
(twice I think, the first increment might already be in progress).

The only question here is what should drive this machinery.. the tick
probably.

This shouldn't be too hard to do I think.

Something a little like so perhaps?


diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 41404afb7f4c..27b64a60a468 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4525,6 +4525,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		 * finish_task_switch()'s mmdrop().
 		 */
 		switch_mm_irqs_off(prev->active_mm, next->mm, next);
+		rq->nr_mm_switches++;
 
 		if (!prev->mm) {                        // from kernel
 			/* will mmdrop() in finish_task_switch(). */
@@ -4739,6 +4740,80 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	return ns;
 }
 
+static DEFINE_PER_CPU(unsigned long[2], mm_switches);
+
+static struct {
+	unsigned long __percpu *switches[2];
+	unsigned long generation;
+	atomic_t complete;
+	struct wait_queue_dead wait;
+} mm_foo = {
+	.switches = &mm_switches,
+	.generation = 0,
+	.complete = -1, // XXX bootstrap, hotplug
+	.wait = __WAIT_QUEUE_HEAD_INITIALIZER(mm_foo.wait),
+};
+
+static void mm_gen_tick(int cpu, struct rq *rq)
+{
+	unsigned long prev, curr, switches = rq->nr_mm_switches;
+	int idx = READ_ONCE(mm_foo.generation) & 1;
+
+	/* DATA-DEP on mm_foo.generation */
+
+	prev = __this_cpu_read(mm_foo.switches[idx^1]);
+	curr = __this_cpu_read(mm_foo.switches[idx]);
+
+	/* we haven't switched since the last generation */
+	if (prev == switches)
+		return false;
+
+	__this_cpu_write(mm_foo.switches[idx], switches);
+
+	/*
+	 * If @curr is less than @prev, this is the first update of
+	 * this generation, per the above, switches has also increased since,
+	 * so mark out CPU complete.
+	 */
+	if ((long)(curr - prev) < 0 && atomic_dec_and_test(&mm_foo.complete)) {
+		/*
+		 * All CPUs are complete, IOW they all switched at least once
+		 * since the last generation. Reset the completion counter and
+		 * increment the generation.
+		 */
+		atomic_set(&mm_foo.complete, nr_online_cpus());
+		/*
+		 * Matches the address dependency above:
+		 *
+		 *   idx = gen & 1	complete = nr_cpus
+		 *   <DATA-DEP>		<WMB>
+		 *   curr = sw[idx]	generation++;
+		 *   prev = sw[idx^1]
+		 *   if (curr < prev)
+		 *     complete--
+		 *
+		 * If we don't observe the new generation; we'll not decrement. If we
+		 * do see the new generation, we must also see the new completion count.
+		 */
+		smp_wmb();
+		mm_foo.generation++;
+		return true;
+	}
+
+	return false;
+}
+
+static void mm_gen_wake(void)
+{
+	wake_up_all(&mm_foo.wait);
+}
+
+static void mm_gen_wait(void)
+{
+	unsigned int gen = READ_ONCE(mm_foo.generation);
+	wait_event(&mm_foo.wait, READ_ONCE(mm_foo.generation) - gen > 1);
+}
+
 /*
  * This function gets called by the timer code, with HZ frequency.
  * We call it with interrupts disabled.
@@ -4750,6 +4825,7 @@ void scheduler_tick(void)
 	struct task_struct *curr = rq->curr;
 	struct rq_flags rf;
 	unsigned long thermal_pressure;
+	bool wake_mm_gen;
 
 	arch_scale_freq_tick();
 	sched_clock_tick();
@@ -4763,8 +4839,13 @@ void scheduler_tick(void)
 	calc_global_load_tick(rq);
 	psi_task_tick(rq);
 
+	wake_mm_gen = mm_gen_tick(cpu, rq);
+
 	rq_unlock(rq, &rf);
 
+	if (wake_mm_gen)
+		mm_gen_wake();
+
 	perf_event_task_tick();
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index bf9d8da7d35e..62fb685db8d0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -927,6 +927,7 @@ struct rq {
 	unsigned int		ttwu_pending;
 #endif
 	u64			nr_switches;
+	u64			nr_mm_switches;
 
 #ifdef CONFIG_UCLAMP_TASK
 	/* Utilization clamp values based on CPU's RUNNABLE tasks */