From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from CO1PR03CU002.outbound.protection.outlook.com (mail-westus2azon11010000.outbound.protection.outlook.com [52.101.46.0]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 4E5DE331A65; Sun, 11 Oct 2026 18:22:29 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=fail smtp.client-ip=52.101.46.0 ARC-Seal:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791742950; cv=fail; b=pg5rnSwDq59EFgfcoYB8E4oTR3WKLl03X3vwD/buvm/V5UKf6uMI5X4bgFB8+hRQtL2qDz9m9O6Cjg+gMu4R2twsqN3UKze5/E4E3oV2p8wBbbFGU+MJDsPMKfAD+BWiYSNdhrwdj48VBN1CrA4DHl3xtVIIVrC/SfBgYH2YpjU= ARC-Message-Signature:i=2; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791742950; c=relaxed/simple; bh=BH4VtehASHj8VF6Ta4K1YRJZYT06uaZktC1dPzN0o3c=; h=Date:From:To:Cc:Subject:Message-ID:References:Content-Type: Content-Disposition:In-Reply-To:MIME-Version; b=uKzrANu1A7IYybUBHDr8UI9jfYGjWD00fpGjWJmcXRNblVcEcM2shk1eoDzXmz3Ef+CXCr9O5bGy3mFGN1XNy8p7JQH0OfyIXjkYuPqIsZAKk8+YMRA1d+/MmO9NmXmXvBG3U9Ht8Q6p8eU1aNwbIvjMkEePX0H7c250uKT15wQ= ARC-Authentication-Results:i=2; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com; spf=fail smtp.mailfrom=nvidia.com; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b=is/pYKB4; arc=fail smtp.client-ip=52.101.46.0 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=nvidia.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=Nvidia.com header.i=@Nvidia.com header.b="is/pYKB4" ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=zK0u4Ny6dfaclTgQS+3S3eRWjWZY1V8Xlsz9yc8+brnC4g0ZmsDKrYEyKZxA99CtPuDemkVF+l3ELaPQl0jxwpIacbO3ayNgRI/B9KepmfRS6G2rV2k+wm7JT/TUXESyEFxAm2yelA4LwqqyskTuvEDMUkmu4II+7F5xqdVrVVgPN4FeoHqPBQxB5QNf8Ikw9pU+hnU4G7KlwIBTj1Hw+hBBuL8/PK7TfWAxogakH8sA84ZWmx25sqJSijGt/qoXk8wbM0oTzf49IEpwxzMuphMSIqd2LezxXocPvCzw4U/SRsh0+7NlcoDlIv0w36Tz/1UN0pEUZbaZyLM5S6KDtg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=2tR5t+hAmK0Rr5dJK5AM2K+nlVdr2ZjSaMWtfWEzmPU=; b=NqsXzGPMH7ulvkpMBVbGXO6ljE22iHYt52J1ZFda/wMjWA+ydtHQx4FXYvKEBbcSdYtoFD3yPokQ8zPVA20AQBCurvqdV0Vj9WMXROos5zg3EJTGyI2jALJGPKuj9Omkm8zs+BwEe+x9m7PFGvM10AYqGcuLeEBbM3RBSUzM2vZT3eJd25O8qx1fq4TzIN2etpx90DnouDbZXWw8pLqO3G9n0xCFInSMz0asjwaIixUAkV8THGDowGxNWvrCMOFdQNvf2fjqugByLbxldVDe2RUq0lNS9SzaOOAzDe9/T//bcdKR3E/1czU+d7t7BCx2mirypMUJZKKsMh5gaSWTWg== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=nvidia.com; dmarc=pass action=none header.from=nvidia.com; dkim=pass header.d=nvidia.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=2tR5t+hAmK0Rr5dJK5AM2K+nlVdr2ZjSaMWtfWEzmPU=; b=is/pYKB4XLVipNgs6u370pFoGFFGJVJA5rpVVJ4R37DgpthczlbQMev0alo/c0d4E4PaOjjEB3bNbmPg+Bbkzw0zzL62NSa6Nxg6eLHaogyyN0saSz5GvA0eLqjqcfgazScgQxZ8UtQPSGnpGrx3/cdJLfqV6k8nbD9YyyzLxob8lJLXDpfbNV8z0ccGvmm/CV+UrBy6cbU6lK8zJdNhrQBctf3TKEQAwIgPS8YeDXALQD7UcVTWr20nD0wEi0g7Zbu56XKKSwr+RYrWnaW6jPGjn3iBUh3/XHm8tTC8Uhy4uQOUpz1qQxBGcWF5+wkS5+w/UZ4uSi5D5cAxg1s7Qg== Authentication-Results: mx.microsoft.com 1; dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=nvidia.com; Received: from BL1PR12MB5174.namprd12.prod.outlook.com (2603:10b6:208:31c::19) by PH8PR12MB6770.namprd12.prod.outlook.com (2603:10b6:510:1c5::11) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.21.496.20; Sun, 11 Oct 2026 18:22:25 +0000 Received: from BL1PR12MB5174.namprd12.prod.outlook.com ([fe80::58de:822b:868:96e9]) by BL1PR12MB5174.namprd12.prod.outlook.com ([fe80::58de:822b:868:96e9%6]) with mapi id 15.21.0496.020; Sun, 11 Oct 2026 18:22:25 +0000 Date: Sun, 11 Oct 2026 20:22:22 +0200 From: Andrea Righi To: Hui Su Cc: tj@kernel.org, void@manifault.com, changwoo@igalia.com, mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com, vincent.guittot@linaro.org, dietmar.eggemann@arm.com, rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de, vschneid@redhat.com, kprateek.nayak@amd.com, sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org, bpf@vger.kernel.org, stable@vger.kernel.org Subject: Re: [PATCH v3] sched_ext: idle: Respect task affinity in restricted CPU selection Message-ID: References: <20261011173100.2090211-1-sh_def@163.com> Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20261011173100.2090211-1-sh_def@163.com> X-ClientProxiedBy: MI1P293CA0015.ITAP293.PROD.OUTLOOK.COM (2603:10a6:290:2::14) To BL1PR12MB5174.namprd12.prod.outlook.com (2603:10b6:208:31c::19) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: BL1PR12MB5174:EE_|PH8PR12MB6770:EE_ X-MS-Office365-Filtering-Correlation-Id: a4135cdf-c5b4-47bc-649d-08df27c4998f X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|7416014|376014|366016|1800799024|23010399003|11063799006|56012099006|18002099003|22082099003|261009223027099003|10067099003; X-Microsoft-Antispam-Message-Info: 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 X-Forefront-Antispam-Report: CIP:255.255.255.255;CTRY:;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:BL1PR12MB5174.namprd12.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230040)(7416014)(376014)(366016)(1800799024)(23010399003)(11063799006)(56012099006)(18002099003)(22082099003)(261009223027099003)(10067099003);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?LNCRqRUS3EXm6GDoBcdQuRKBkhTOxsVxjvvMAHhGeepvukEh/kpuOYW+3riJ?= =?us-ascii?Q?KppZjNLC3UixYvsr6HwwMAkIcTclF4cvB3Q4EydYJzdVnQZ2JZYU3/WvwM6/?= =?us-ascii?Q?A3/6L5NWgUUvxyJDK3pEuj1TqVWoGXw5iAwXiGq0BTTGeQeB2vkUMDBp9GTj?= =?us-ascii?Q?fmOBeUCVV0Om2fFkag89tEXuq/cdCo4WBfbBtASqnh/AwqGruPe0q5xtFlaL?= =?us-ascii?Q?Rh4z0QkoY427M+rilz+jMToRUw6UT8OWbmzJ/DlvP89E7tofDrkip5ea81/f?= =?us-ascii?Q?fCX/bgyEIY54H5x2iMX4aMeVIrSkF0pYsJdLTEqd8Iv7bSV5WupIkIuhVQjr?= =?us-ascii?Q?wf/kBYQAP0x0REGGbEzWzoUAEe6sxr1pn2SaCQ6j9N9ugSwa1K/THrJAOGDy?= =?us-ascii?Q?Rc1gB0lYMSxcuwOEvbxugWvW9HSDJ4PHf7O5PKJ13pBYBr4pPiK1nfjgJekq?= =?us-ascii?Q?d/ot4uxMYDeIG7/HIuY9vZJBKQ7TKFPCYjJeIuh3i3hcVnntfs/WpdwVf3FG?= =?us-ascii?Q?sc5Zdf7r4B7LORR2b6gDn0/HKkgcNnpzcizuPVs366kcVu+DBFKNBHMG1tMP?= =?us-ascii?Q?SH/s0Op/9uCpwM12SsjKGYU/V4tWK5DWAhQdBjS8LUsrq/zUO7je9MMyyZAv?= =?us-ascii?Q?dYK1J5sdAMu2QtCCpOPWJtle2XLWDfGmP5y0rcMTMIxAZCiTpShpmm2rFMW9?= =?us-ascii?Q?CUTGOe0EdSJcr131ULufFzuMntREIXtDYky44rtGBwq4V9IaiC/qfesyawz5?= =?us-ascii?Q?BQyRmH7LranJIXLu1uYxisoXmUkOdq79uLZoKj76lmfl5AnkTxA812ey899K?= =?us-ascii?Q?mEf8E/rCTP23+/CYnyzTY2XV/13gzxPwg1uqe59Acoi0XpoHFFSZ+zDmti/J?= =?us-ascii?Q?U8NXX2k3J+saijjO6i9GxYkx2JG+MyuI8ks3cl6OTeP/PiRICon1U+wMIxw1?= =?us-ascii?Q?eMiLzWoPbZ4lCPcXXYeVjo4KwuIs6oSCNhXaUCAYENdHEsYuC3T8MAR/Hdb5?= =?us-ascii?Q?XB1p1m83wwM17mnVf2Nu1go3D5740oi2eJmk1faHKCOoT2yk/GZS83ZoLlaG?= =?us-ascii?Q?Pf9obXymigkkS+79cm+9lIjlut1P5AKQxp8XYej0ndffiSZkG5qxToYOM3YP?= =?us-ascii?Q?QFU/Krouc0qvIQVbPe2XvlBdXhfOUUy3SQ2O+9zIrQeEaP1p6mRGtFEa2Jmq?= =?us-ascii?Q?dQpgWzs6d2DnTNReN9DlbyZOm/IemrT+ZM6fC+4D1SnCEmcDZb80rfpdKMtC?= =?us-ascii?Q?Z1ikiPXGyOEObSAcE0R03255CE3Wx1Wfr3p7elUO/yWdHprCe+Lgk+WZrLoe?= =?us-ascii?Q?xllau5EtqT9t39kl81MVFsPL7pQ7znwY1uAVhgwEwJz8FO8C4Ep80AEuNlyI?= =?us-ascii?Q?8oXBHJbNWKFbsppIxmOVvUIbLmUidzqLmJk6hXG765luT1mVPBKwhMgp+hNV?= =?us-ascii?Q?Ka0JlvDabXM6Dth3Cl9e74PD9DuHISvCKgNqHgXYmZal1N2PO2PFYJahl3DW?= =?us-ascii?Q?ThiiVITK6JIIm7Jbsva371XiOeVWRr/hdcoAbl6QzN1XruYU3T86gfNznn6g?= =?us-ascii?Q?wmzjOrDmLsgGNnjp+4PGVf/IEun8s3vDKbnHNgrgDixCDRWAfGmZje+Mbzvg?= =?us-ascii?Q?zqlsvU4p4C+C/L1eHblJTHVQL07w69NojqHAtSpwV8d4hcI+/4Z578ByeLkO?= =?us-ascii?Q?VmCtTBOYNYWoI2MV7Is/ukggW4DMf9YIiQfTN13inK3JrVLh?= X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-Network-Message-Id: a4135cdf-c5b4-47bc-649d-08df27c4998f X-MS-Exchange-CrossTenant-AuthSource: BL1PR12MB5174.namprd12.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 11 Oct 2026 18:22:25.6181 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a X-MS-Exchange-CrossTenant-MailboxType: HOSTED X-MS-Exchange-CrossTenant-UserPrincipalName: G1zyQpPnYcTinroh9wh1V5LjreuKxQAdFwCIhqGm5cKQq6bCVs6coMV/wu4teXvsZPWuB1r5M7EjiU3Hm+l65A== X-MS-Exchange-Transport-CrossTenantHeadersStamped: PH8PR12MB6770 Hi Hui, On Mon, Oct 12, 2026 at 02:31:00AM +0900, Hui Su wrote: > The restricted select_cpu kfunc path handles single-CPU and > migration-disabled tasks without going through scx_select_cpu_dfl(). > > It currently uses prev_cpu as the candidate, even though prev_cpu is only a > hint and may no longer be usable after an affinity change. With a > caller-provided @allowed mask, this can also return an idle CPU outside > p->cpus_ptr. > > Derive the candidate from task state instead: use the sole CPU in > p->cpus_ptr for single-CPU tasks and task_cpu(p) for migration-disabled > tasks. Validate it against p->cpus_ptr and @allowed before claiming its > idle state. > > Since the derived candidate may be on a different NUMA node from > prev_cpu, also preserve SCX_PICK_IDLE_IN_NODE by rejecting cross-node > candidates. > > Perform all checks before scx_idle_test_and_clear_cpu(), as a successful > call consumes the CPU's idle bit. > Fixes: 683d2d0faba1 ("sched_ext: idle: Introduce scx_bpf_select_cpu_and()") > Cc: stable@vger.kernel.org > Signed-off-by: Hui Su Reviewed-by: Andrea Righi Thanks, -Andrea > --- > Tested on x86_64 KVM/QEMU: > - Private BPF harness passed affinity, stale-prev_cpu, caller-mask, and > cross-NUMA SCX_PICK_IDLE_IN_NODE cases; v2 returned CPU2 across nodes, > while v3 returned -EBUSY. > - Build coverage passed with CONFIG_PREEMPT_RCU=y/n and CONFIG_SMP=n. > > Changes in v3: > - Factor restricted selection into select_cpu_restricted(). > - Preserve SCX_PICK_IDLE_IN_NODE and add cross-NUMA validation. > > v2: https://lore.kernel.org/lkml/20261011131700.1351541-1-sh_def@163.com/ > > kernel/sched/ext/idle.c | 50 ++++++++++++++++++++++++++++++++--------- > 1 file changed, 39 insertions(+), 11 deletions(-) > > diff --git a/kernel/sched/ext/idle.c b/kernel/sched/ext/idle.c > index aa9fb6de0ad6..28ed9e327085 100644 > --- a/kernel/sched/ext/idle.c > +++ b/kernel/sched/ext/idle.c > @@ -952,12 +952,43 @@ static bool is_bpf_migration_disabled(const struct task_struct *p) > return p->migration_disabled; > } > > +static s32 select_cpu_restricted(struct task_struct *p, s32 prev_cpu, > + const struct cpumask *allowed, u64 flags, > + bool migration_disabled) > +{ > + s32 cpu; > + > + if (migration_disabled) > + cpu = task_cpu(p); > + else > + cpu = cpumask_first(p->cpus_ptr); > + > + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) > + return -EBUSY; > + > + if (allowed && !cpumask_test_cpu(cpu, allowed)) > + return -EBUSY; > + > + if (flags & SCX_PICK_IDLE_IN_NODE) { > + int node = scx_cpu_node_if_enabled(prev_cpu); > + > + if (scx_cpu_node_if_enabled(cpu) != node) > + return -EBUSY; > + } > + > + if (!scx_idle_test_and_clear_cpu(cpu)) > + return -EBUSY; > + > + return cpu; > +} > + > static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p, > s32 prev_cpu, u64 wake_flags, > const struct cpumask *allowed, u64 flags) > { > unsigned long irq_flags; > bool we_locked = false; > + bool migration_disabled; > s32 cpu; > > if (!scx_cpu_valid(sch, prev_cpu, NULL)) > @@ -994,20 +1025,17 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p, > > /* > * This may also be called from ops.enqueue(), so we need to handle > - * per-CPU tasks as well. For these tasks, we can skip all idle CPU > - * selection optimizations and simply check whether the previously > - * used CPU is idle and within the allowed cpumask. > + * per-CPU tasks as well. For these tasks, skip general idle CPU > + * selection and validate the task's only usable CPU directly. > */ > - if (p->nr_cpus_allowed == 1 || is_bpf_migration_disabled(p)) { > - if (cpumask_test_cpu(prev_cpu, allowed ?: p->cpus_ptr) && > - scx_idle_test_and_clear_cpu(prev_cpu)) > - cpu = prev_cpu; > - else > - cpu = -EBUSY; > - } else { > + migration_disabled = is_bpf_migration_disabled(p); > + > + if (p->nr_cpus_allowed == 1 || migration_disabled) > + cpu = select_cpu_restricted(p, prev_cpu, allowed, flags, > + migration_disabled); > + else > cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, > allowed ?: p->cpus_ptr, flags); > - } > > if (we_locked) > raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags); > > base-commit: 7b63ef2d55f24519e7e9e5f4d15dbea03f126e40 > >