From nobody Sat Feb 7 15:10:22 2026 Received: from mail-dy1-f177.google.com (mail-dy1-f177.google.com [74.125.82.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 59FDD1F0E34 for ; Thu, 29 Jan 2026 02:26:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.82.177 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769653601; cv=none; b=nuk8RAeNxkne+GZZzy7OuLtUZqcKLywqZlc2ibGJFleUY052SmgHuLi8Qy1K1XQKr9bqOcK6+3FaGFf96xkKrHnGEX+DDf8D826zShvQ1b02R1o01ll3Ry+fm9o6OHCID7/5KvWOoz/f3ahScSfzba7f1hEUMe9L+DJF0dpgmZE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1769653601; c=relaxed/simple; bh=CAf2Etf/SR10lea8VN5fkUmacasr/02Ph7H3nfRTwjY=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=aLVm9RWyXZMmF+g1l2ynMvi3/1vSgWq6RBNPI0X3/kDU0osOQQMNLqQXcMjEXuuP2b/jyCuASKTCZ0tYMaVPm3GlKqhjKNU3fR51I8c7c72w/2NOkzqni6tb/TJaa8sU9HVZ2JhM23DIbJsw0C4Mf2MMCcQ03hX9No39hlf8qsw= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=kJoahQGH; arc=none smtp.client-ip=74.125.82.177 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="kJoahQGH" Received: by mail-dy1-f177.google.com with SMTP id 5a478bee46e88-2b785801c93so1272636eec.0 for ; Wed, 28 Jan 2026 18:26:40 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1769653599; x=1770258399; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to; bh=Vcq7aD3lYlVWIhmj7yegBQ/oAWD8jMRiUwoR40ggFyM=; b=kJoahQGH6TA33DiLoGqDe6QeC3jKjEhCv6RkyHN0j8fb8cm1fGtymAf+v0ZyedhZkc gsXytRmd+T3Z/Oakd8U4hEjPm8F1iyBaAdZjYQ8gd4Bvyg3w3XX51tfqasYikBUgA1wS 1QeC6da8F9hsLw9ZrcZqj6NULR+dEEi9a+BLnrmuUITYwH6j1jAJu1Mt5F0QS386H0HC voEcciL/NCwEX12yRbVpkyZjOK04i7yuc0+D99cvgUGuauElTF8Q3QqLj2ULxrvSC14Q PC57yHympGJLdeH4SPfHjLtWOEHU1RSuBG/Bekw7r/xj4JFlFHp9ZA53RYJ9nNmS7rBf iAGA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1769653599; x=1770258399; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-gg:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to; bh=Vcq7aD3lYlVWIhmj7yegBQ/oAWD8jMRiUwoR40ggFyM=; b=Pgzjh5bWB0GiMcAiuZbHZre+Tbv5NRCSi97Q2VMKWGXXmzmPNOIFO1nKIJ1CFhRw3J EjwIaxZqWMoMCTsBeM6lStwLjGa6TZhBzdTweOc8vh/0E33U3Wl16BhHCbVFRv1fFa4Z 4cBqGQI0IDscaW+A3V5zSAvybuhdY+QFqPGdhlB8JqELFAQQ6G0/lv+Rhb7i8cPH6/UL NXYub6lP0EWKZLfRskdSfmvWioxfk6boMZ1aJCFf4pbuzcz17hcUObW43ISrF8pGuIGq +ekos0IWoNIPHtcsvVKcLn7rMopzPOUuTJoXUJQtUHAU473OsBkmaKrMYcMJVSYb9eUf AC6w== X-Forwarded-Encrypted: i=1; AJvYcCVcQ3lgETAtrjB8qqQNx4P+i69XyDrKy92SxEavCGoa3AaWsoEKxxYUEfP3NTPabmirEc912vJ7nLNf8Ys=@vger.kernel.org X-Gm-Message-State: AOJu0YyJZyufKL1/OJXfJfU+/h0bsiombHDMjJPnDeDlFzlGcAOkFhBN IZJUyNBTXRbMof+4M0z0yPZoSikZkXqQbnjgedYUwglVnsSt60RWHT7k X-Gm-Gg: AZuq6aLUFXZsvRqU4cQ66EXoFckeImTqTRidiQb5hoPNEMdI4k7fuogRYUBWjYfRzr4 IqdPHtCme9gR/1U5fzGxSznPCyFqLRzV/09PSrBcrisfUQNa/vWL4MQnoVS22Cx8YGXnIprdSyH eLMvfzP/4AbMViitwCdXdocWJx1Jyjt9BEjyLI5B2pOQNusgWidHYBDa9rSH29p7QvCySPNYnuL bTH0qfTqUsfZkvL5R+wdprMGONmeY9fidlyZ7J1gOxn48SpAHWh0rdlDJCny1QnPp0XR9emwIlp 8jEFVH4KdNX06twRNLnQESN85G5ovz6CqWptHNBQb6nsqwXG+mdprcQDVgEqZVtpJLEHhatueDL ck+JWqejDFHZoQKkkLJgHiOSy+YCH863sN16jCe8V8UtVnLw+gHW/V69jthn8N8MqZqWD6fG1K8 dH+94= X-Received: by 2002:a05:7301:9f03:b0:2b7:3955:f50a with SMTP id 5a478bee46e88-2b78da4a0b4mr4654448eec.41.1769653597804; Wed, 28 Jan 2026 18:26:37 -0800 (PST) Received: from debian ([74.48.213.230]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-2b7a1adef97sm5088827eec.29.2026.01.28.18.26.34 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 28 Jan 2026 18:26:37 -0800 (PST) From: Qiliang Yuan To: Ingo Molnar , Li Huafei , Qiliang Yuan , Andrew Morton , Jinchao Wang , Yicong Yang , Thorsten Blum Cc: linux-watchdog@vger.kernel.org, mm-commits@vger.kernel.org, Shouxin Sun , Junnan Zhang , Qiliang Yuan , Douglas Anderson , Song Liu , linux-kernel@vger.kernel.org Subject: [PATCH v9] watchdog/hardlockup: simplify perf event probe and remove per-cpu dependency Date: Wed, 28 Jan 2026 21:26:14 -0500 Message-ID: <20260129022629.2201331-1-realwujing@gmail.com> X-Mailer: git-send-email 2.51.0 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Simplify the hardlockup detector's probe path and remove its implicit dependency on pinned per-cpu execution. Refactor hardlockup_detector_event_create() to be stateless. Return the created perf_event pointer to the caller instead of directly modifying the per-cpu 'watchdog_ev' variable. This allows the probe path to safely manage a temporary event without the risk of leaving stale pointers should task migration occur. Signed-off-by: Shouxin Sun Signed-off-by: Junnan Zhang Signed-off-by: Qiliang Yuan Signed-off-by: Qiliang Yuan Cc: Douglas Anderson Cc: Song Liu Cc: Jinchao Wang Reviewed-by: Douglas Anderson --- v9: - remove unused `#include ` v8: - Add Signed-off-by with work email. v7: - Update Signed-off-by to match author email. - Remove redundant cpu_hotplug_disable() in probe path. v6: - Change title to "simplify/cleanup" and remove "Fixes" tag since the issue is not reproducible on mainline. - Rewrite commit message in imperative mood. - Clarify that mainline is safe while this improves robustness. v5: - Refine description: clarify that the retry path uses worker threads without PF_PERCPU_THREAD (though mainline is safe due to system_percpu_wq= ). v4: - Add cpu_hotplug_disable() in watchdog_hardlockup_probe() to stabilize the probe CPU. - Update description to explain the relevance of 4.19 logs. v3: - Refactor hardlockup_detector_event_create() to be stateless by returning the event pointer instead of directly assigning to per-cpu variables. - Restore PMU cycle fallback and unify the enable/probe paths. v2: - Add Cc: stable@vger.kernel.org. v1: - Avoid 'watchdog_ev' in probe path by manually creating and releasing a local perf event. kernel/watchdog_perf.c | 50 +++++++++++++++++++++++------------------- 1 file changed, 28 insertions(+), 22 deletions(-) diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c index d3ca70e3c256..cf05775a96d3 100644 --- a/kernel/watchdog_perf.c +++ b/kernel/watchdog_perf.c @@ -118,18 +118,11 @@ static void watchdog_overflow_callback(struct perf_ev= ent *event, watchdog_hardlockup_check(smp_processor_id(), regs); } =20 -static int hardlockup_detector_event_create(void) +static struct perf_event *hardlockup_detector_event_create(unsigned int cp= u) { - unsigned int cpu; struct perf_event_attr *wd_attr; struct perf_event *evt; =20 - /* - * Preemption is not disabled because memory will be allocated. - * Ensure CPU-locality by calling this in per-CPU kthread. - */ - WARN_ON(!is_percpu_thread()); - cpu =3D raw_smp_processor_id(); wd_attr =3D &wd_hw_attr; wd_attr->sample_period =3D hw_nmi_get_sample_period(watchdog_thresh); =20 @@ -143,14 +136,7 @@ static int hardlockup_detector_event_create(void) watchdog_overflow_callback, NULL); } =20 - if (IS_ERR(evt)) { - pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, - PTR_ERR(evt)); - return PTR_ERR(evt); - } - WARN_ONCE(this_cpu_read(watchdog_ev), "unexpected watchdog_ev leak"); - this_cpu_write(watchdog_ev, evt); - return 0; + return evt; } =20 /** @@ -159,17 +145,26 @@ static int hardlockup_detector_event_create(void) */ void watchdog_hardlockup_enable(unsigned int cpu) { + struct perf_event *evt; + WARN_ON_ONCE(cpu !=3D smp_processor_id()); =20 - if (hardlockup_detector_event_create()) + evt =3D hardlockup_detector_event_create(cpu); + if (IS_ERR(evt)) { + pr_debug("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); return; + } =20 /* use original value for check */ if (!atomic_fetch_inc(&watchdog_cpus)) pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); =20 + WARN_ONCE(this_cpu_read(watchdog_ev), "unexpected watchdog_ev leak"); + this_cpu_write(watchdog_ev, evt); + watchdog_init_timestamp(); - perf_event_enable(this_cpu_read(watchdog_ev)); + perf_event_enable(evt); } =20 /** @@ -263,19 +258,30 @@ bool __weak __init arch_perf_nmi_is_available(void) */ int __init watchdog_hardlockup_probe(void) { + struct perf_event *evt; + unsigned int cpu; int ret; =20 if (!arch_perf_nmi_is_available()) return -ENODEV; =20 - ret =3D hardlockup_detector_event_create(); + if (!hw_nmi_get_sample_period(watchdog_thresh)) + return -EINVAL; =20 - if (ret) { + /* + * Test hardware PMU availability by creating a temporary perf event. + * The event is released immediately. + */ + cpu =3D raw_smp_processor_id(); + evt =3D hardlockup_detector_event_create(cpu); + if (IS_ERR(evt)) { pr_info("Perf NMI watchdog permanently disabled\n"); + ret =3D PTR_ERR(evt); } else { - perf_event_release_kernel(this_cpu_read(watchdog_ev)); - this_cpu_write(watchdog_ev, NULL); + perf_event_release_kernel(evt); + ret =3D 0; } + return ret; } =20 --=20 2.51.0