All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ravi Bangoria <ravi.bangoria@amd.com>
To: Peter Zijlstra <peterz@infradead.org>
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, ravi.bangoria@amd.com
Subject: Re: [RFC v2] perf: Rewrite core context handling
Date: Thu, 25 Aug 2022 16:33:51 +0530	[thread overview]
Message-ID: <05ba363d-12e4-83ca-fb20-203c93a27f3d@amd.com> (raw)
In-Reply-To: <YwY8u7gx6bO+RBcg@worktop.programming.kicks-ass.net>

On 24-Aug-22 8:29 PM, Peter Zijlstra wrote:
> On Wed, Aug 24, 2022 at 02:15:13PM +0200, Peter Zijlstra wrote:
>> On Mon, Jun 13, 2022 at 04:35:11PM +0200, Peter Zijlstra wrote:
>>>  void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu)
>>>  {
>>> -	struct perf_cpu_context *cpuctx;
>>> +	/* XXX: Don't need this quirk anymore */
>>> +	/*struct perf_cpu_context *cpuctx;
>>>  
>>>  	if (!pmu->pmu_cpu_context)
>>>  		return;
>>>  
>>>  	cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
>>> -	cpuctx->ctx.pmu = pmu;
>>> +	cpuctx->ctx.pmu = pmu;*/
>>>  }
>>
>> Confirmed; my ADL seems to work fine without all that.
> 
> Additionally; this doesn't insta crash.

While collating this I came across armv8pmu_start() which does:

	struct perf_event_context *task_ctx =
		this_cpu_ptr(cpu_pmu->pmu.pmu_cpu_context)->task_ctx;

	if (sysctl_perf_user_access && task_ctx && task_ctx->nr_user)

Not sure why it does not lock task_ctx. Should it be changed to
something like below? Untested:

---
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 016072a89f8f..747415a5f2b2 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -806,10 +806,19 @@ static void armv8pmu_disable_event(struct perf_event *event)
 
 static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 {
-	struct perf_event_context *task_ctx =
-		this_cpu_ptr(cpu_pmu->pmu.pmu_cpu_context)->task_ctx;
+	struct perf_event_context *ctx;
+	int nr_user = 0;
+
+	rcu_read_lock();
+	ctx = rcu_dereference(current->perf_event_ctxp);
+	if (ctx) {
+		raw_spin_lock(&ctx->lock);
+		nr_user = ctx->nr_user;
+		raw_spin_unlock(&ctx->lock);
+	}
+	rcu_read_unlock();
 
-	if (sysctl_perf_user_access && task_ctx && task_ctx->nr_user)
+	if (sysctl_perf_user_access && nr_user)
 		armv8pmu_enable_user_access(cpu_pmu);
 	else
 		armv8pmu_disable_user_access();
---

Thanks,
Ravi

  parent reply	other threads:[~2022-08-25 11:04 UTC|newest]

Thread overview: 50+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-01-13 13:47 [RFC v2] perf: Rewrite core context handling Ravi Bangoria
2022-01-13 19:06 ` [RFC PATCH] perf: find_get_pmu_context can be static kernel test robot
2022-01-13 19:15 ` [RFC v2] perf: Rewrite core context handling kernel test robot
2022-01-17  7:18 ` [perf] f7cf7134e4: WARNING:at_kernel/events/core.c:#__pmu_ctx_sched_out kernel test robot
2022-01-17  7:18   ` kernel test robot
2022-01-31  4:43 ` [RFC v2] perf: Rewrite core context handling Ravi Bangoria
2022-06-13 14:35 ` Peter Zijlstra
2022-06-13 14:36   ` Peter Zijlstra
2022-06-13 14:38   ` Peter Zijlstra
2022-08-02  6:11     ` Ravi Bangoria
2022-08-22 15:29       ` Peter Zijlstra
2022-08-22 15:43         ` Peter Zijlstra
2022-08-22 16:37           ` Ravi Bangoria
2022-08-23  4:20             ` Ravi Bangoria
2022-08-29  3:54               ` Ravi Bangoria
2022-08-23  6:30             ` Peter Zijlstra
2022-08-29  4:00             ` Ravi Bangoria
2022-08-29 11:58               ` Peter Zijlstra
2022-08-22 16:52       ` Peter Zijlstra
2022-08-23  4:57         ` Ravi Bangoria
2022-06-13 14:41   ` Peter Zijlstra
2022-08-22 14:38     ` Ravi Bangoria
2022-06-13 14:43   ` Peter Zijlstra
2022-08-02  6:16     ` Ravi Bangoria
2022-08-23  8:57       ` Peter Zijlstra
2022-08-24  5:07         ` Ravi Bangoria
2022-08-24  7:27           ` Peter Zijlstra
2022-08-24  7:53             ` Ravi Bangoria
2022-06-13 14:55   ` Peter Zijlstra
2022-08-02  6:10     ` Ravi Bangoria
2022-08-22 16:44       ` Peter Zijlstra
2022-08-23  4:46         ` Ravi Bangoria
2022-06-17 13:36   ` Peter Zijlstra
2022-08-24 10:13     ` Peter Zijlstra
2022-06-27  4:18   ` Ravi Bangoria
2022-08-02  6:06     ` Ravi Bangoria
2022-08-24 12:15   ` Peter Zijlstra
2022-08-24 14:59     ` Peter Zijlstra
2022-08-25  5:39       ` Ravi Bangoria
2022-08-25  9:17         ` Peter Zijlstra
2022-08-25 11:03       ` Ravi Bangoria [this message]
2022-08-02  6:13 ` Ravi Bangoria
2022-08-23  7:10   ` Peter Zijlstra
2022-08-02  6:17 ` Ravi Bangoria
2022-08-23  7:26   ` Peter Zijlstra
2022-08-23 15:14     ` Ravi Bangoria
2022-08-22 14:40 ` Ravi Bangoria
2022-01-14 21:48 kernel test robot
2022-01-18  6:01 ` kernel test robot
2022-01-18  6:01   ` kernel test robot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=05ba363d-12e4-83ca-fb20-203c93a27f3d@amd.com \
    --to=ravi.bangoria@amd.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=alexey.budankov@linux.intel.com \
    --cc=eranian@google.com \
    --cc=frederic@kernel.org \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=kim.phillips@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maddy@linux.ibm.com \
    --cc=mark.rutland@arm.com \
    --cc=megha.dey@intel.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=santosh.shukla@amd.com \
    --cc=songliubraving@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.