linux-kernel - [RFC 2/2] perf/core: Invoke pmu::sched

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: <20201102145221.309001-3-namhyung@kernel.org>
Date:   Mon,  2 Nov 2020 23:52:21 +0900
From:   Namhyung Kim <namhyung@...nel.org>
To:     Peter Zijlstra <a.p.zijlstra@...llo.nl>,
        Ingo Molnar <mingo@...nel.org>
Cc:     Arnaldo Carvalho de Melo <acme@...nel.org>,
        Jiri Olsa <jolsa@...hat.com>,
        LKML <linux-kernel@...r.kernel.org>,
        Stephane Eranian <eranian@...gle.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Ian Rogers <irogers@...gle.com>,
        Kan Liang <kan.liang@...ux.intel.com>,
        Gabriel Marin <gmx@...gle.com>
Subject: [RFC 2/2] perf/core: Invoke pmu::sched_task callback for per-cpu events

The commit 44fae179ce73 ("perf/core: Pull pmu::sched_task() into
perf_event_context_sched_out()") moved the pmu::sched_task callback to
be called for task event context.  But it missed to call it for
per-cpu events to flush PMU internal buffers (i.e. for PEBS, ...).

This commit basically reverts the commit but keeps the optimization
for task events and only add missing calls for cpu events.

Fixes: 44fae179ce73 ("perf/core: Pull pmu::sched_task() into perf_event_context_sched_out()")
Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
 include/linux/perf_event.h |  1 +
 kernel/events/core.c       | 38 ++++++++++++++++++++++++++++++++++++--
 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 0defb526cd0c..abb70a557cb5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -872,6 +872,7 @@ struct perf_cpu_context {
 	struct list_head		cgrp_cpuctx_entry;
 #endif
 
+	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
 
 	int				online;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index aaa0155c4142..c04d9a913537 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -383,6 +383,7 @@ static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
 static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
@@ -3480,11 +3481,16 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	}
 }
 
+static DEFINE_PER_CPU(struct list_head, sched_cb_list);
+
 void perf_sched_cb_dec(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	--cpuctx->sched_cb_usage;
+	this_cpu_dec(perf_sched_cb_usages);
+
+	if (!--cpuctx->sched_cb_usage)
+		list_del(&cpuctx->sched_cb_entry);
 }
 
 
@@ -3492,7 +3498,10 @@ void perf_sched_cb_inc(struct pmu *pmu)
 {
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 
-	cpuctx->sched_cb_usage++;
+	if (!cpuctx->sched_cb_usage++)
+		list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
+	this_cpu_inc(perf_sched_cb_usages);
 }
 
 /*
@@ -3521,6 +3530,24 @@ static void __perf_pmu_sched_task(struct perf_cpu_context *cpuctx, bool sched_in
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 }
 
+static void perf_pmu_sched_task(struct task_struct *prev,
+				struct task_struct *next,
+				bool sched_in)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (prev == next)
+		return;
+
+	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+		/* will be handled in perf_event_context_sched_in/out */
+		if (cpuctx->task_ctx)
+			continue;
+
+		__perf_pmu_sched_task(cpuctx, sched_in);
+	}
+}
+
 static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in);
 
@@ -3543,6 +3570,9 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(task, next, false);
+
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, next, false);
 
@@ -3850,6 +3880,9 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 
 	if (atomic_read(&nr_switch_events))
 		perf_event_switch(task, prev, true);
+
+	if (__this_cpu_read(perf_sched_cb_usages))
+		perf_pmu_sched_task(prev, task, true);
 }
 
 static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -12999,6 +13032,7 @@ static void __init perf_event_init_all_cpus(void)
 #ifdef CONFIG_CGROUP_PERF
 		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
 #endif
+		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }
 
-- 
2.29.1.341.ge80a0c044ae-goog