linux-kernel - Re: [PATCH v3] perf/core: Set event shadow time for inactive events too

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: <YbHp2MXmP1V5WE4B@hirez.programming.kicks-ass.net>
Date:   Thu, 9 Dec 2021 12:34:48 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Namhyung Kim <namhyung@...nel.org>
Cc:     Ingo Molnar <mingo@...nel.org>,
        Arnaldo Carvalho de Melo <acme@...nel.org>,
        Jiri Olsa <jolsa@...hat.com>,
        Mark Rutland <mark.rutland@....com>,
        Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
        LKML <linux-kernel@...r.kernel.org>,
        Stephane Eranian <eranian@...gle.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Ian Rogers <irogers@...gle.com>,
        Song Liu <songliubraving@...com>
Subject: Re: [PATCH v3] perf/core: Set event shadow time for inactive events
 too

On Thu, Dec 09, 2021 at 12:26:32PM +0100, Peter Zijlstra wrote:
> On Sun, Dec 05, 2021 at 02:48:43PM -0800, Namhyung Kim wrote:
> 
> > Actually 18446744069443110306 is 0xffffffff01b345a2 so it seems to
> > have a negative enabled time.  In fact, bperf keeps values returned by
> > bpf_perf_event_read_value() which calls perf_event_read_local(), and
> > accumulates delta between two calls.  When event->shadow_ctx_time is
> > not set, it'd return invalid enabled time which is bigger than normal.
> 
> *that*, how does it happen that shadow_time isn't set? It should be last
> set when the event switches to INACTIVE, no? At which point the logic in
> perf_event_read_local() should make @enabled move forward while @running
> stays put.
> 
> Let me go rummage around a bit... either I'm missing something obvious
> or something's smelly.

How's this then?

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7b7525e9155f..82baa8bdfc86 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -686,9 +686,7 @@ struct perf_event {
 	/*
 	 * timestamp shadows the actual context timing but it can
 	 * be safely used in NMI interrupt context. It reflects the
-	 * context time as it was when the event was last scheduled in,
-	 * or when ctx_sched_in failed to schedule the event because we
-	 * run out of PMC.
+	 * context time as it was when the event was last scheduled in.
 	 *
 	 * ctx_time already accounts for ctx->timestamp. Therefore to
 	 * compute ctx_time for a sample, simply add perf_clock().
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 28aaeacdaea1..20637b7f420c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -640,6 +640,9 @@ __perf_update_times(struct perf_event *event, u64 now, u64 *enabled, u64 *runnin
 		*running += delta;
 }
 
+static void perf_set_shadow_time(struct perf_event *event,
+				 struct perf_event_context *ctx);
+
 static void perf_event_update_time(struct perf_event *event)
 {
 	u64 now = perf_event_time(event);
@@ -647,6 +650,7 @@ static void perf_event_update_time(struct perf_event *event)
 	__perf_update_times(event, now, &event->total_time_enabled,
 					&event->total_time_running);
 	event->tstamp = now;
+	perf_set_shadow_time(event, event->ctx);
 }
 
 static void perf_event_update_sibling_time(struct perf_event *leader)
@@ -2552,8 +2556,6 @@ event_sched_in(struct perf_event *event,
 
 	perf_pmu_disable(event->pmu);
 
-	perf_set_shadow_time(event, ctx);
-
 	perf_log_itrace_start(event);
 
 	if (event->pmu->add(event, PERF_EF_START)) {
@@ -3707,29 +3709,6 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx,
 	return 0;
 }
 
-static inline bool event_update_userpage(struct perf_event *event)
-{
-	if (likely(!atomic_read(&event->mmap_count)))
-		return false;
-
-	perf_event_update_time(event);
-	perf_set_shadow_time(event, event->ctx);
-	perf_event_update_userpage(event);
-
-	return true;
-}
-
-static inline void group_update_userpage(struct perf_event *group_event)
-{
-	struct perf_event *event;
-
-	if (!event_update_userpage(group_event))
-		return;
-
-	for_each_sibling_event(event, group_event)
-		event_update_userpage(event);
-}
-
 static int merge_sched_in(struct perf_event *event, void *data)
 {
 	struct perf_event_context *ctx = event->ctx;
@@ -3748,15 +3727,14 @@ static int merge_sched_in(struct perf_event *event, void *data)
 	}
 
 	if (event->state == PERF_EVENT_STATE_INACTIVE) {
-		*can_add_hw = 0;
 		if (event->attr.pinned) {
 			perf_cgroup_event_disable(event, ctx);
 			perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-		} else {
-			ctx->rotate_necessary = 1;
-			perf_mux_hrtimer_restart(cpuctx);
-			group_update_userpage(event);
 		}
+
+		*can_add_hw = 0;
+		ctx->rotate_necessary = 1;
+		perf_mux_hrtimer_restart(cpuctx);
 	}
 
 	return 0;
@@ -6349,7 +6327,6 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		ring_buffer_attach(event, rb);
 
 		perf_event_update_time(event);
-		perf_set_shadow_time(event, event->ctx);
 		perf_event_init_userpage(event);
 		perf_event_update_userpage(event);
 	} else {