Re: [RFC v2] perf: Rewrite core context handling

From: Peter Zijlstra <peterz@infradead.org>
To: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: acme@kernel.org, alexander.shishkin@linux.intel.com,
	jolsa@redhat.com, namhyung@kernel.org, songliubraving@fb.com,
	eranian@google.com, alexey.budankov@linux.intel.com,
	ak@linux.intel.com, mark.rutland@arm.com, megha.dey@intel.com,
	frederic@kernel.org, maddy@linux.ibm.com, irogers@google.com,
	kim.phillips@amd.com, linux-kernel@vger.kernel.org,
	santosh.shukla@amd.com
Subject: Re: [RFC v2] perf: Rewrite core context handling
Date: Wed, 24 Aug 2022 12:13:55 +0200	[thread overview]
Message-ID: <YwX546d8YxRCbQWl@worktop.programming.kicks-ass.net> (raw)
In-Reply-To: <YqyDc0i3C9OpNiPx@worktop.programming.kicks-ass.net>

On Fri, Jun 17, 2022 at 03:36:51PM +0200, Peter Zijlstra wrote:
> On Mon, Jun 13, 2022 at 04:35:11PM +0200, Peter Zijlstra wrote:
> > +/* XXX: No need of list now. Convert it to per-cpu variable */
> >  static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
> 
> Something like so I suppose...
> 

I need this on top to avoid a spat on perf_cgroup_attach()

---

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0cd81a3ef374..c6b64a48dea6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -13536,9 +13536,12 @@ static int perf_cgroup_css_online(struct cgroup_subsys_state *css)
 static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
-	rcu_read_lock();
-	perf_cgroup_switch(task);
-	rcu_read_unlock();
+
+	preempt_disable();
+	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
+		perf_cgroup_switch(task);
+	preempt_enable();
+
 	return 0;
 }
 
