linux-kernel - Re: [PATCH v8 2/2] sched/fair: Scan cluster before scanning LLC in wake-up path

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20230530115527.GC156198@hirez.programming.kicks-ass.net>
Date:   Tue, 30 May 2023 13:55:27 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Yicong Yang <yangyicong@...wei.com>
Cc:     mingo@...hat.com, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, dietmar.eggemann@....com,
        tim.c.chen@...ux.intel.com, yu.c.chen@...el.com,
        gautham.shenoy@....com, mgorman@...e.de, vschneid@...hat.com,
        linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
        rostedt@...dmis.org, bsegall@...gle.com, bristot@...hat.com,
        prime.zeng@...wei.com, yangyicong@...ilicon.com,
        jonathan.cameron@...wei.com, ego@...ux.vnet.ibm.com,
        srikar@...ux.vnet.ibm.com, linuxarm@...wei.com, 21cnbao@...il.com,
        kprateek.nayak@....com, wuyun.abel@...edance.com,
        Barry Song <song.bao.hua@...ilicon.com>
Subject: Re: [PATCH v8 2/2] sched/fair: Scan cluster before scanning LLC in
 wake-up path

On Tue, May 30, 2023 at 03:02:53PM +0800, Yicong Yang wrote:

> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 373ff5f55884..b8c129ed8b47 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6994,6 +6994,30 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
>  		}
>  	}
>  
> +	if (static_branch_unlikely(&sched_cluster_active)) {
> +		struct sched_domain *sdc = rcu_dereference(per_cpu(sd_cluster, target));
> +
> +		if (sdc) {
> +			for_each_cpu_wrap(cpu, sched_domain_span(sdc), target + 1) {
> +				if (!cpumask_test_cpu(cpu, cpus))
> +					continue;
> +
> +				if (has_idle_core) {
> +					i = select_idle_core(p, cpu, cpus, &idle_cpu);
> +					if ((unsigned int)i < nr_cpumask_bits)
> +						return i;
> +				} else {
> +					if (--nr <= 0)
> +						return -1;
> +					idle_cpu = __select_idle_cpu(cpu, p);
> +					if ((unsigned int)idle_cpu < nr_cpumask_bits)
> +						return idle_cpu;
> +				}
> +			}
> +			cpumask_andnot(cpus, cpus, sched_domain_span(sdc));
> +		}
> +	}

Would not this:

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6994,6 +6994,29 @@ static int select_idle_cpu(struct task_s
 		}
 	}
 
+	if (static_branch_unlikely(&sched_cluster_active)) {
+		struct sched_group *sg = sd->groups;
+		if (sg->flags & SD_CLUSTER) {
+			for_each_cpu_wrap(cpu, sched_group_span(sg), target+1) {
+				if (!cpumask_test_cpu(cpu, cpus))
+					continue;
+
+				if (has_idle_core) {
+					i = select_idle_core(p, cpu, cpus, &idle_cpu);
+					if ((unsigned)i < nr_cpumask_bits)
+						return 1;
+				} else {
+					if (--nr <= 0)
+						return -1;
+					idle_cpu = __select_idle_cpu(cpu, p);
+					if ((unsigned)idle_cpu < nr_cpumask_bits)
+						return idle_cpu;
+				}
+			}
+			cpumask_andnot(cpus, cpus, sched_group_span(sg));
+		}
+	}
+
 	for_each_cpu_wrap(cpu, cpus, target + 1) {
 		if (has_idle_core) {
 			i = select_idle_core(p, cpu, cpus, &idle_cpu);

also work? Then we can avoid the extra sd_cluster per-cpu variable.