Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   Sandipan Das <sandipan.das@amd.com>
To:     <linux-kernel@vger.kernel.org>, <linux-perf-users@vger.kernel.org>
CC:     <x86@kernel.org>, <peterz@infradead.org>, <mingo@redhat.com>,
        <acme@kernel.org>, <mark.rutland@arm.com>,
        <alexander.shishkin@linux.intel.com>, <jolsa@kernel.org>,
        <namhyung@kernel.org>, <irogers@google.com>,
        <adrian.hunter@intel.com>, <tglx@linutronix.de>, <bp@alien8.de>,
        <dave.hansen@linux.intel.com>, <hpa@zytor.com>,
        <stable@vger.kernel.org>, <eranian@google.com>,
        <ananth.narayan@amd.com>, <ravi.bangoria@amd.com>,
        <santosh.shukla@amd.com>, <sandipan.das@amd.com>
Subject: [PATCH] perf/x86/amd/core: Fix overflow reset on hotplug
Date:   Tue, 13 Jun 2023 16:28:09 +0530
Message-ID: <20230613105809.524535-1-sandipan.das@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 13 Jun 2023 10:58:23.7303
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 4ee303c8-10bd-43a0-d1d9-08db6bfd1bae
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: CY4PEPF0000EE37.namprd05.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DS7PR12MB5718
X-Spam-Status: No, score=-1.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,
        RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE,
        T_SCC_BODY_TEXT_LINE,URIBL_BLOCKED autolearn=no autolearn_force=no
        version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Kernels older than v5.19 do not support PerfMonV2 and the PMI handler
does not clear the overflow bits of the PerfCntrGlobalStatus register.
Because of this, loading a recent kernel using kexec from an older
kernel can result in inconsistent register states on Zen 4 systems.

The PMI handler of the new kernel gets confused and shows a warning when
an overflow occurs because some of the overflow bits are set even if the
corresponding counters are inactive. These are remnants from overflows
that were handled by the older kernel.

During CPU hotplug, the PerfCntrGlobalCtl and PerfCntrGlobalStatus
registers should always be cleared for PerfMonV2-capable processors.
However, a condition used for NB event constaints applicable only to
older processors currently prevents this from happening. Move the reset
sequence to an appropriate place and also clear the LBR Freeze bit.

Fixes: 21d59e3e2c40 ("perf/x86/amd/core: Detect PerfMonV2 support")
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
---
 arch/x86/events/amd/core.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index abadd5f23425..ed626bfa1eed 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu)
 	/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
 	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
 
-	/* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask);
+	/*
+	 * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
+	 * and PerfCntrGLobalStatus.PerfCntrOvfl
+	 */
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+	       GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
 }
 
 static int amd_pmu_cpu_prepare(int cpu)
@@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu)
 	int i, nb_id;
 
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
+	amd_pmu_cpu_reset(cpu);
 
 	if (!x86_pmu.amd_nb_constraints)
 		return;
@@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu)
 
 	cpuc->amd_nb->nb_id = nb_id;
 	cpuc->amd_nb->refcnt++;
-
-	amd_pmu_cpu_reset(cpu);
 }
 
 static void amd_pmu_cpu_dead(int cpu)
@@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu)
 
 	kfree(cpuhw->lbr_sel);
 	cpuhw->lbr_sel = NULL;
+	amd_pmu_cpu_reset(cpu);
 
 	if (!x86_pmu.amd_nb_constraints)
 		return;
@@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
 		cpuhw->amd_nb = NULL;
 	}
-
-	amd_pmu_cpu_reset(cpu);
 }
 
 static inline void amd_pmu_set_global_ctl(u64 ctl)
-- 
2.34.1