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;
From:   Valentin Schneider <vschneid@redhat.com>
To:     Yury Norov <yury.norov@gmail.com>,
        Jakub Kicinski <kuba@kernel.org>, netdev@vger.kernel.org,
        linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     Yury Norov <yury.norov@gmail.com>,
        Saeed Mahameed <saeedm@nvidia.com>,
        Pawel Chmielewski <pawel.chmielewski@intel.com>,
        Leon Romanovsky <leon@kernel.org>,
        "David S. Miller" <davem@davemloft.net>,
        Eric Dumazet <edumazet@google.com>,
        Paolo Abeni <pabeni@redhat.com>,
        Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
        Rasmus Villemoes <linux@rasmusvillemoes.dk>,
        Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Tariq Toukan <tariqt@nvidia.com>,
        Gal Pressman <gal@nvidia.com>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Heiko Carstens <hca@linux.ibm.com>,
        Barry Song <baohua@kernel.org>
Subject: Re: [PATCH v2 2/8] sched/topology: introduce
 sched_numa_find_next_cpu()
In-Reply-To: <20230420051946.7463-3-yury.norov@gmail.com>
References: <20230420051946.7463-1-yury.norov@gmail.com>
 <20230420051946.7463-3-yury.norov@gmail.com>
Date:   Tue, 25 Apr 2023 10:54:56 +0100
Message-ID: <xhsmh354ol21b.mognet@vschneid.remote.csb>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

On 19/04/23 22:19, Yury Norov wrote:
> +/*
> + * sched_numa_find_next_cpu() - given the NUMA topology, find the next cpu
> + * cpumask: cpumask to find a cpu from
> + * cpu: current cpu
> + * node: local node
> + * hop: (in/out) indicates distance order of current CPU to a local node
> + *
> + * The function searches for next cpu at a given NUMA distance, indicated
> + * by hop, and if nothing found, tries to find CPUs at a greater distance,
> + * starting from the beginning.
> + *
> + * Return: cpu, or >= nr_cpu_ids when nothing found.
> + */
> +int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsigned int *hop)
> +{
> +	unsigned long *cur, *prev;
> +	struct cpumask ***masks;
> +	unsigned int ret;
> +
> +	if (*hop >= sched_domains_numa_levels)
> +		return nr_cpu_ids;
> +
> +	masks = rcu_dereference(sched_domains_numa_masks);
> +	cur = cpumask_bits(masks[*hop][node]);
> +	if (*hop == 0)
> +		ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
> +	else {
> +		prev = cpumask_bits(masks[*hop - 1][node]);
> +		ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
> +	}
> +
> +	if (ret < nr_cpu_ids)
> +		return ret;
> +
> +	*hop += 1;
> +	return sched_numa_find_next_cpu(cpus, 0, node, hop);

sched_domains_numa_levels is a fairly small number, so the recursion depth
isn't something we really need to worry about - still, the iterative
variant of this is fairly straightforward to get to:

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index e850f16c003ae..4c9a9e48fef6d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -2151,23 +2151,27 @@ int sched_numa_find_next_cpu(const struct cpumask *cpus, int cpu, int node, unsi
 	struct cpumask ***masks;
 	unsigned int ret;
 
-	if (*hop >= sched_domains_numa_levels)
-		return nr_cpu_ids;
+	/*
+	 * Reset @cpu to 0 when increasing @hop, since CPU numbering has no
+	 * relationship with NUMA distance: a search at @hop+1 may yield CPUs
+	 * of lower ID than previously seen!
+	 */
+	for (; *hop >= sched_domains_numa_levels; *hop += 1, cpu = 0) {
+		masks = rcu_dereference(sched_domains_numa_masks);
+		cur = cpumask_bits(masks[*hop][node]);
+
+		if (*hop == 0) {
+			ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
+		} else {
+			prev = cpumask_bits(masks[*hop - 1][node]);
+			ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
+		}
 
-	masks = rcu_dereference(sched_domains_numa_masks);
-	cur = cpumask_bits(masks[*hop][node]);
-	if (*hop == 0)
-		ret = find_next_and_bit(cpumask_bits(cpus), cur, nr_cpu_ids, cpu);
-	else {
-		prev = cpumask_bits(masks[*hop - 1][node]);
-		ret = find_next_and_andnot_bit(cpumask_bits(cpus), cur, prev, nr_cpu_ids, cpu);
+		if (ret < nr_cpu_ids)
+			return ret;
 	}
 
-	if (ret < nr_cpu_ids)
-		return ret;
-
-	*hop += 1;
-	return sched_numa_find_next_cpu(cpus, 0, node, hop);
+	return nr_cpu_ids;
 }
 EXPORT_SYMBOL_GPL(sched_numa_find_next_cpu);