mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Mi, Dapeng" <dapeng1.mi@linux.intel.com>
To: Zide Chen <zide.chen@intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Eranian Stephane <eranian@google.com>
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: Re: [PATCH V2 7/8] perf/x86/intel/uncore: Fix uncore_box ref/unref ordering on CPU hotplug
Date: Wed, 3 Jun 2026 10:32:33 +0800	[thread overview]
Message-ID: <74ab79eb-57c8-4a63-b401-b56b0483a5a5@linux.intel.com> (raw)
In-Reply-To: <20260601170114.173359-8-zide.chen@intel.com>


On 6/2/2026 1:01 AM, Zide Chen wrote:
> In uncore_event_cpu_online(), uncore_box_ref() was called before
> uncore_change_context().  uncore_box_ref() gates on box->cpu >= 0,
> but box->cpu is still -1 at that point because uncore_change_context()
> has not run yet.  As a result, the box is never initialized on the
> first CPU to come online in a die, leaving it permanently
> uninitialized in the single-CPU-per-die case.
>
> Thus, box->refcnt is one count below the true value, and in the CPU
> offline path, the box will be torn down on the second-to-last CPU.
>
> In uncore_event_cpu_offline(), uncore_box_unref() was called after
> uncore_change_context(), so box->cpu is already -1 when the collector
> CPU goes offline, which prevents it from tearing down the box.
>
> Fix by swapping the call order in both paths so that
> uncore_box_{ref,unref}() runs at the point where box->cpu reflects
> the correct context.
>
> Fixes: c74443d92f68 ("perf/x86/uncore: Support per PMU cpumask")
> Reviewed-by: Ian Rogers <irogers@google.com>
> Signed-off-by: Zide Chen <zide.chen@intel.com>
> ---
>  arch/x86/events/intel/uncore.c | 50 ++++++++++++++++------------------
>  1 file changed, 23 insertions(+), 27 deletions(-)
>
> diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
> index f2cb3fde2dda..6d710aef52ac 100644
> --- a/arch/x86/events/intel/uncore.c
> +++ b/arch/x86/events/intel/uncore.c
> @@ -1577,9 +1577,15 @@ static int uncore_event_cpu_offline(unsigned int cpu)
>  {
>  	int die, target;
>  
> +	/* Clear the references */
> +	die = topology_logical_die_id(cpu);
> +	uncore_box_unref(uncore_msr_uncores, die);
> +	uncore_box_unref(uncore_mmio_uncores, die);
> +
>  	/* Check if exiting cpu is used for collecting uncore events */
>  	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
> -		goto unref;
> +		return 0;
> +
>  	/* Find a new cpu to collect uncore events */
>  	target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
>  
> @@ -1592,16 +1598,10 @@ static int uncore_event_cpu_offline(unsigned int cpu)
>  	uncore_change_context(uncore_msr_uncores, cpu, target);
>  	uncore_change_context(uncore_mmio_uncores, cpu, target);
>  	uncore_change_context(uncore_pci_uncores, cpu, target);
> -
> -unref:
> -	/* Clear the references */
> -	die = topology_logical_die_id(cpu);
> -	uncore_box_unref(uncore_msr_uncores, die);
> -	uncore_box_unref(uncore_mmio_uncores, die);
>  	return 0;
>  }
>  
> -static int allocate_boxes(struct intel_uncore_type **types,
> +static void allocate_boxes(struct intel_uncore_type **types,
>  			 unsigned int die, unsigned int cpu)
>  {
>  	struct intel_uncore_box *box, *tmp;
> @@ -1618,8 +1618,10 @@ static int allocate_boxes(struct intel_uncore_type **types,
>  			if (pmu->boxes[die] || uncore_pmu_broken(pmu))
>  				continue;
>  			box = uncore_alloc_box(type, cpu_to_node(cpu));
> -			if (!box)
> +			if (!box) {
> +				uncore_pmu_set_broken(pmu);
>  				goto cleanup;
> +			}
>  			box->pmu = pmu;
>  			box->dieid = die;
>  			list_add(&box->active_list, &allocated);
> @@ -1630,14 +1632,13 @@ static int allocate_boxes(struct intel_uncore_type **types,
>  		list_del_init(&box->active_list);
>  		box->pmu->boxes[die] = box;
>  	}
> -	return 0;
> +	return;
>  
>  cleanup:
>  	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
>  		list_del_init(&box->active_list);
>  		kfree(box);
>  	}
> -	return -ENOMEM;
>  }
>  
>  static int uncore_box_ref(struct intel_uncore_type **types,
> @@ -1646,11 +1647,7 @@ static int uncore_box_ref(struct intel_uncore_type **types,
>  	struct intel_uncore_type *type;
>  	struct intel_uncore_pmu *pmu;
>  	struct intel_uncore_box *box;
> -	int i, ret;
> -
> -	ret = allocate_boxes(types, die, cpu);
> -	if (ret)
> -		return ret;
> +	int i;
>  
>  	for (; *types; types++) {
>  		type = *types;
> @@ -1666,27 +1663,26 @@ static int uncore_box_ref(struct intel_uncore_type **types,
>  
>  static int uncore_event_cpu_online(unsigned int cpu)
>  {
> -	int die, target, msr_ret, mmio_ret;
> +	int die, target;
>  
>  	die = topology_logical_die_id(cpu);
> -	msr_ret = uncore_box_ref(uncore_msr_uncores, die, cpu);
> -	mmio_ret = uncore_box_ref(uncore_mmio_uncores, die, cpu);
> +	allocate_boxes(uncore_msr_uncores, die, cpu);
> +	allocate_boxes(uncore_mmio_uncores, die, cpu);

allocate_boxes() are moved to uncore_event_cpu_online() from
uncore_box_ref(). It's a significant and good change since PCI uncore PMUs
doesn't call allocate_boxes(), but the commit message doesn't mention this.
We'd better extract this change to a separate patch which would make the
changes clearer. Thanks.

Others look good to me.


>  
>  	/*
>  	 * Check if there is an online cpu in the package
>  	 * which collects uncore events already.
>  	 */
>  	target = cpumask_any_and(&uncore_cpu_mask, topology_die_cpumask(cpu));
> -	if (target < nr_cpu_ids)
> -		return 0;
> -
> -	cpumask_set_cpu(cpu, &uncore_cpu_mask);
> -
> -	if (!msr_ret)
> +	if (target >= nr_cpu_ids) {
> +		cpumask_set_cpu(cpu, &uncore_cpu_mask);
>  		uncore_change_context(uncore_msr_uncores, -1, cpu);
> -	if (!mmio_ret)
>  		uncore_change_context(uncore_mmio_uncores, -1, cpu);
> -	uncore_change_context(uncore_pci_uncores, -1, cpu);
> +		uncore_change_context(uncore_pci_uncores, -1, cpu);
> +	}
> +
> +	uncore_box_ref(uncore_msr_uncores, die, cpu);
> +	uncore_box_ref(uncore_mmio_uncores, die, cpu);
>  	return 0;
>  }
>  

  reply	other threads:[~2026-06-03  2:32 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-01 17:01 [PATCH v2 0/8] perf/x86/intel/uncore: PMU setup robustness fixes Zide Chen
2026-06-01 17:01 ` [PATCH V2 1/8] perf/x86/intel/uncore: Fix PCI PMU cleanup on setup failure Zide Chen
2026-06-02  7:24   ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 2/8] perf/x86/intel/uncore: Fix refcnt and other cleanups Zide Chen
2026-06-02  9:52   ` Mi, Dapeng
2026-06-02 14:16     ` Chen, Zide
2026-06-03  1:13       ` Mi, Dapeng
2026-06-03 15:09         ` Chen, Zide
2026-06-04  1:00           ` Mi, Dapeng
2026-06-04 15:41             ` Chen, Zide
2026-06-05  0:30               ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 3/8] perf/x86/intel/uncore: Let init_box() callback report failures Zide Chen
2026-06-02  9:57   ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 4/8] perf/x86/intel/uncore: Keep PCI PMUs working when MMIO/MSR setup fails Zide Chen
2026-06-03  1:24   ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 5/8] perf/x86/intel/uncore: Factor out box setup code Zide Chen
2026-06-03  1:30   ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 6/8] perf/x86/intel/uncore: Introduce PMU flags and broken state Zide Chen
2026-06-03  2:13   ` Mi, Dapeng
2026-06-03 15:46     ` Chen, Zide
2026-06-04  1:15       ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 7/8] perf/x86/intel/uncore: Fix uncore_box ref/unref ordering on CPU hotplug Zide Chen
2026-06-03  2:32   ` Mi, Dapeng [this message]
2026-06-03 16:40     ` Chen, Zide
2026-06-04  1:16       ` Mi, Dapeng
2026-06-01 17:01 ` [PATCH V2 8/8] perf/x86/intel/uncore: Implement lazy setup for MSR/MMIO PMU Zide Chen
2026-06-03  2:43   ` Mi, Dapeng

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=74ab79eb-57c8-4a63-b401-b56b0483a5a5@linux.intel.com \
    --to=dapeng1.mi@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=zide.chen@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

Powered by JetHome