From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-pj1-f45.google.com (mail-pj1-f45.google.com [209.85.216.45]) (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 0CF573A6B77 for ; Wed, 29 Apr 2026 07:44:07 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.216.45 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777448649; cv=none; b=Omw0cXho8xPtQQwcvR4xhjGtjOZ07ORahf20nspgCC2wC/Cn2uk8qerLshP6o6KQ8BCuVCF4SMJRgBwXAHfLuLTsu4j11MuFuUs79aFKh0arjXgX+moq+Litjun/EV27CYMyCgGD1e7rUdiU0cGqzJkKNr6X3cebdUrfPdkZQ/s= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1777448649; c=relaxed/simple; bh=KMTwrO6lyGA9HXWMDRxyqvFbl0UsijqV/ZH6/je9Ys4=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=f8zIKBXptV9vr4+bNU8P57d/gKBe/0cglgrRov28mnqiXSuiUPRigpqk72VAPHm+aKiWBn/VVIFONEjfOqb53/+HjTLfhhCR54CwBrOxz5Tj2ZtYIU7xy6F59KVYydd3M4JtnMRX8tmwNLC0B1Orqxr8XQWda/FJXZH1GYY8Uo8= 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=I+suWJyj; arc=none smtp.client-ip=209.85.216.45 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="I+suWJyj" Received: by mail-pj1-f45.google.com with SMTP id 98e67ed59e1d1-35d94f4ee36so7455195a91.3 for ; Wed, 29 Apr 2026 00:44:07 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1777448647; x=1778053447; 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=ug4IsgIcxYoU7FipCLH2YRUtUPisQjttB4gCz1feTAY=; b=I+suWJyjaLWujMMbcBt2o52W4O0TDyDRBShL0wZ8wo21ArU+TZ5Ad66MahWXJ/qsFK SsaRdulVuAo1DgvKPNT2gA5iJS6uGK33n3JbFWzzHlZMdUlWPF2ue+ewrIxKnEhJOf+f L1ZxsTmU5b6KLRNhDqq8p0mhbE09KrTqkvHvmkdKPWByvuZV3SRICiWtrzWTN77nDoJm zq882/cx5s/12QdTpxh9v7E+NOrBVajgekJ/gnQv6WDO4zhR7Eu64bVqf0wjKWT54Dot hPaPEzFtlwdWkJhP9U5wkkQgbivgkXvPH41/RyJ70vFR7+dVp+ER5sUM0eFMwtmkLmHy j4eg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1777448647; x=1778053447; 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=ug4IsgIcxYoU7FipCLH2YRUtUPisQjttB4gCz1feTAY=; b=cvdrCrpar+4/fw1cldAE3WYl/Zz6p86bvbhaZ99oDaK47zgdPK9dBrRuoat8r7N4u5 VHSOXwsB8DlKjoFP2mjG+7tw10Y7pAEvzXJPIv0pGt6asBHtns6QvI82fOrhJVj2b+b3 PqPXEzhiWm/PMmsWF3MGV+fZGNmZKm+WRTB0TnZyFWf6SAbX4B7RVOsVkH1k+kVyq94H yS96Jh59CFHFNvGy4ZUXr2JkjBKACETZC8OpGAXAk4qhYqr2tvScQmnKQJtJnFIIPQwG 3HipPO34WhWgTbmksUcHGZMBdAq85xilPtg//OyalarmocgY8rHO3jc2pRSZJz+KDvq1 w44A== X-Forwarded-Encrypted: i=1; AFNElJ8FIRTdiH7Cqp4z6EzuxKbB24oQYyR3wy5IOevDTmyRgQMszbL0ztDEmiS+e/FCPtLQFIWsuzR3CADuVAw=@vger.kernel.org X-Gm-Message-State: AOJu0Yyq0IvoqPJSYhocRKsS42437Q4agQBccI2hIxBI2+BizUbjDhQb mDnb+pTurY+hWehbQcbXJwI1tgRv6tPoL0bV74MPy09/Wftd1ToObe2P X-Gm-Gg: AeBDiev2zjsps39/lakrLrf3Gd36nmljfNB7IuofuMainuwvle31WGrr7aVB7B62v1A ELacOPajBs/yGKvqa1w90U1mDkptirWO7lZwgCta3sMz9h7stsb7zlxxrE4UHdxeGWRcbYhb2uZ jjjCKRMBqt9fm9T6Ifa+XKT0/NPRjoaj4eIU5k+SAiC7GYfDpHMHWsdYZMnWyhSje4oDtJqbM5Q M+kNxtu141wKGNnmOrJmf5te0orxDbw6ydsZ4XarMi2rcoN6+3R53V52COsnPy6a1CMpQmpsYTI Ndp5MxOh/T4FMJIkhpKy6GwyYWgwDkdzlvSTKuSQwUCmijmByzCMjpNPs+wnw83Tk6rCiI0zwiN 9MZiYDxrandP8h98MHLMNiz6G8Mh/wCFpZhR0Li0qXBrjpeHlGqnDrUlcEprficebDhDzTcYlpx jiuLxWzfVamsIU2qFIZfSqUYGulqmDzMZuug/QKLUTJo7p7nEdDExDQbJ/2w== X-Received: by 2002:a17:90b:2604:b0:35b:e4d8:e21d with SMTP id 98e67ed59e1d1-36491f6c9b5mr7194320a91.2.1777448647126; Wed, 29 Apr 2026 00:44:07 -0700 (PDT) Received: from localhost.localdomain ([165.132.143.163]) by smtp.gmail.com with ESMTPSA id 98e67ed59e1d1-364a2a4b65dsm569443a91.14.2026.04.29.00.44.04 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 29 Apr 2026 00:44:06 -0700 (PDT) From: Minwoo Ahn To: Peter Zijlstra , Ingo Molnar , Arnaldo Carvalho de Melo , Namhyung Kim Cc: Mark Rutland , Alexander Shishkin , Jiri Olsa , Ian Rogers , Adrian Hunter , James Clark , Jinkyu Jeong , Minwoo Ahn , linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH v3] perf/core: Fix sampling period inconsistency across CPU migration Date: Wed, 29 Apr 2026 07:43:28 +0000 Message-ID: <20260429074328.41991-1-mwahn402@gmail.com> X-Mailer: git-send-email 2.43.0 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit When per-task software events are sampled, period_left is not managed consistently when task migration happens. The perf_event may observe a different hw_perf_event::period_left on the new CPU, breaking the sampling periodicity. Even if a task was near its sampling point, it would use a stale period_left after migration. Introduce struct perf_task_context as a per-task container to preserve period_left across CPU migrations. A separate structure is used rather than adding fields to hw_perf_event, because hw_perf_event is a general-purpose structure shared by all event types (hardware, software, tracepoint, breakpoint, etc.) and embedding per-task sampling state there would bloat it for the majority of events that do not need it. perf_task_context is only allocated for per-task software sampling events. Multiple per-CPU perf_event instances originating from the same perf_event_open caller share a single perf_task_context via refcounting. The perf_event owner field is used to distinguish events from different perf_event_open callers, preventing unrelated sampling sessions from interfering with each other. For inherited events (where owner is NULL), the inherit flag relaxes the owner check so that child events properly share perf_task_context. The allocation condition for inherited events checks that the parent event actually has a perf_task_ctxp, ensuring only genuine software events propagate the context. The existing perf_task_context lookup uses perf_lock_task_context() to safely access the task's event context under proper RCU and IRQ protection. perf_task_context serves purely as a transport for period_left across CPU migrations. On event removal (swevent_del for non-clock events, cancel_hrtimer for clock events), hw_perf_event::period_left is backed up to perf_task_context::period_left. On event addition (swevent_add for non-clock events, start_hrtimer for clock events), perf_task_context::period_left is restored to hw_perf_event::period_left. During normal operation between migrations, hw_perf_event::period_left remains the sole working copy, keeping existing code paths unaffected. To reproduce, force CPU migration during task-clock sampling: $ sysbench cpu --threads=1 --time=60 run & $ sleep 0.1 $ TID=$(ls /proc/$!/task/ | grep -v "^$!$") $ perf record -e task-clock -c 1000000000 -t $TID & # Force migration across CPUs every 1.2 seconds $ while kill -0 $TID 2>/dev/null; do taskset -p -c 0 $TID; sleep 1.2 taskset -p -c 1 $TID; sleep 1.2 taskset -p -c 2 $TID; sleep 1.2 done # Check sample intervals (expected: ~1.000s each) $ perf script -F time | \ awk 'NR==1 {prev=$1; next} {print $1-prev; prev=$1}' Without this patch, sample intervals show significant deviation from the expected 1-second period after each migration. With this patch, intervals remain consistent. Co-developed-by: Jinkyu Jeong Signed-off-by: Jinkyu Jeong Signed-off-by: Minwoo Ahn --- Changes in v3: - Move struct perf_task_context and perf_event_equal_task_ctx macro inside #ifdef CONFIG_PERF_EVENTS guard to fix build error on configs where CONFIG_PERF_EVENTS is disabled (local64_t undefined) Changes in v2: - Use perf_lock_task_context() to safely access the task's event context, avoiding a potential use-after-free and IRQ inversion deadlock - Tighten allocation condition for inherited events by checking parent_event->perf_task_ctxp instead of just parent_event include/linux/perf_event.h | 18 +++++++++++ kernel/events/core.c | 77 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 48d851fbd8ea..f8c973325c76 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -829,6 +829,9 @@ struct perf_event { u16 read_size; struct hw_perf_event hw; + /* Per-task sampling state for sw events, survives CPU migration */ + struct perf_task_context *perf_task_ctxp; + struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event @@ -1207,6 +1210,21 @@ perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) #ifdef CONFIG_PERF_EVENTS +#define perf_event_equal_task_ctx(a1, a2) \ + ((a1)->config == (a2)->config && \ + (a1)->sample_period == (a2)->sample_period) + +/** + * struct perf_task_context - per-task software event context + * + * Shared across per-CPU perf_event instances of the same task to + * preserve period_left across CPU migrations. + */ +struct perf_task_context { + refcount_t refcount; + local64_t period_left; +}; + extern struct perf_event_context *perf_cpu_task_ctx(void); extern void *perf_aux_output_begin(struct perf_output_handle *handle, diff --git a/kernel/events/core.c b/kernel/events/core.c index 6d1f8bad7e1c..f5cb1a273fbf 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5740,6 +5740,13 @@ static bool exclusive_event_installable(struct perf_event *event, static void perf_free_addr_filters(struct perf_event *event); +static void perf_put_task_ctxp(struct perf_event *event) +{ + if (event->perf_task_ctxp && + refcount_dec_and_test(&event->perf_task_ctxp->refcount)) + kfree(event->perf_task_ctxp); +} + /* vs perf_event_alloc() error */ static void __free_event(struct perf_event *event) { @@ -5761,6 +5768,9 @@ static void __free_event(struct perf_event *event) if (event->attach_state & PERF_ATTACH_TASK_DATA) detach_perf_ctx_data(event); + if (event->perf_task_ctxp) + perf_put_task_ctxp(event); + if (event->destroy) event->destroy(event); @@ -11054,9 +11064,14 @@ static void perf_swevent_read(struct perf_event *event) static int perf_swevent_add(struct perf_event *event, int flags) { struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); + struct perf_task_context *ctxp = event->perf_task_ctxp; struct hw_perf_event *hwc = &event->hw; struct hlist_head *head; + if (ctxp) + local64_set(&hwc->period_left, + local64_read(&ctxp->period_left)); + if (is_sampling_event(event)) { hwc->last_period = hwc->sample_period; perf_swevent_set_period(event); @@ -11076,7 +11091,13 @@ static int perf_swevent_add(struct perf_event *event, int flags) static void perf_swevent_del(struct perf_event *event, int flags) { + struct perf_task_context *ctxp = event->perf_task_ctxp; + hlist_del_rcu(&event->hlist_entry); + + if (ctxp) + local64_set(&ctxp->period_left, + local64_read(&event->hw.period_left)); } static void perf_swevent_start(struct perf_event *event, int flags) @@ -12203,12 +12224,17 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) static void perf_swevent_start_hrtimer(struct perf_event *event) { + struct perf_task_context *ctxp = event->perf_task_ctxp; struct hw_perf_event *hwc = &event->hw; s64 period; if (!is_sampling_event(event)) return; + if (ctxp) + local64_set(&hwc->period_left, + local64_read(&ctxp->period_left)); + period = local64_read(&hwc->period_left); if (period) { if (period < 0) @@ -12224,6 +12250,7 @@ static void perf_swevent_start_hrtimer(struct perf_event *event) static void perf_swevent_cancel_hrtimer(struct perf_event *event) { + struct perf_task_context *ctxp = event->perf_task_ctxp; struct hw_perf_event *hwc = &event->hw; /* @@ -12238,8 +12265,13 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event) */ if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) { ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer); + local64_set(&hwc->period_left, ktime_to_ns(remaining)); + if (ctxp) + local64_set(&ctxp->period_left, + ktime_to_ns(remaining)); + hrtimer_try_to_cancel(&hwc->hrtimer); } } @@ -13259,6 +13291,41 @@ static void account_event(struct perf_event *event) account_pmu_sb_event(event); } +static struct perf_task_context * +perf_get_task_ctxp(struct perf_event *event, struct task_struct *task, + bool inherit) +{ + struct perf_task_context *ctxp = NULL; + struct perf_event_context *ctx; + struct perf_event *iter; + unsigned long flags; + + ctx = perf_lock_task_context(task, &flags); + if (ctx) { + list_for_each_entry(iter, &ctx->event_list, event_entry) { + if (iter->perf_task_ctxp && + (iter->owner == current || + (inherit && !iter->owner)) && + perf_event_equal_task_ctx(&iter->attr, + &event->attr)) { + ctxp = iter->perf_task_ctxp; + refcount_inc(&ctxp->refcount); + break; + } + } + raw_spin_unlock_irqrestore(&ctx->lock, flags); + } + + if (!ctxp) { + ctxp = kzalloc_obj(struct perf_task_context); + if (!ctxp) + return NULL; + refcount_set(&ctxp->refcount, 1); + } + + return ctxp; +} + /* * Allocate and initialize an event structure */ @@ -13344,6 +13411,16 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, * pmu before we get a ctx. */ event->hw.target = get_task_struct(task); + + if (attr->sample_period && + attr->config < PERF_COUNT_SW_MAX && + (attr->type == PERF_TYPE_SOFTWARE || + (parent_event && parent_event->perf_task_ctxp))) { + event->perf_task_ctxp = perf_get_task_ctxp(event, task, + !!parent_event); + if (!event->perf_task_ctxp) + return ERR_PTR(-ENOMEM); + } } event->clock = &local_clock; -- 2.49.0