linux-kernel - [PATCH 16/24] workqueue: Modularize wq_pod

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: <20230519001709.2563-17-tj@kernel.org>
Date:   Thu, 18 May 2023 14:17:01 -1000
From:   Tejun Heo <tj@...nel.org>
To:     jiangshanlai@...il.com
Cc:     torvalds@...ux-foundation.org, peterz@...radead.org,
        linux-kernel@...r.kernel.org, kernel-team@...a.com,
        joshdon@...gle.com, brho@...gle.com, briannorris@...omium.org,
        nhuck@...gle.com, agk@...hat.com, snitzer@...nel.org,
        void@...ifault.com, Tejun Heo <tj@...nel.org>
Subject: [PATCH 16/24] workqueue: Modularize wq_pod_type initialization

While wq_pod_type[] can now group CPUs in any aribitrary way, WQ_AFFN_NUM
init is hard coded into workqueue_init_topology(). This patch modularizes
the init path by introducing init_pod_type() which takes a callback to
determine whether two CPUs should share a pod as an argument.

init_pod_type() first scans the CPU combinations testing for sharing to
assign consecutive pod IDs and initialize pod_type->cpu_pod[]. Once
->cpu_pod[] is determined, ->pod_cpus[] and ->pod_node[] are initialized
accordingly. WQ_AFFN_NUMA is now initialized by calling init_pod_type() with
cpus_share_numa() which tests whether the CPU belongs to the same NUMA node.

This patch may change the pod ID assigned to each NUMA node but that
shouldn't cause any behavior changes as the NUMA node to use for allocations
are tracked separately in pod_type->pod_node[]. This makes adding new
affinty types pretty easy.

Signed-off-by: Tejun Heo <tj@...nel.org>
---
 kernel/workqueue.c | 84 +++++++++++++++++++++++++++-------------------
 1 file changed, 50 insertions(+), 34 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index dae1787833cb..1734b8a11a4c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6395,6 +6395,54 @@ void __init workqueue_init(void)
 	wq_watchdog_init();
 }
 
+/*
+ * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to
+ * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique
+ * and consecutive pod ID. The rest of @pt is initialized accordingly.
+ */
+static void __init init_pod_type(struct wq_pod_type *pt,
+				 bool (*cpus_share_pod)(int, int))
+{
+	int cur, pre, cpu, pod;
+
+	pt->nr_pods = 0;
+
+	/* init @pt->cpu_pod[] according to @cpus_share_pod() */
+	pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL);
+	BUG_ON(!pt->cpu_pod);
+
+	for_each_possible_cpu(cur) {
+		for_each_possible_cpu(pre) {
+			if (pre >= cur) {
+				pt->cpu_pod[cur] = pt->nr_pods++;
+				break;
+			}
+			if (cpus_share_pod(cur, pre)) {
+				pt->cpu_pod[cur] = pt->cpu_pod[pre];
+				break;
+			}
+		}
+	}
+
+	/* init the rest to match @pt->cpu_pod[] */
+	pt->pod_cpus = kcalloc(pt->nr_pods, sizeof(pt->pod_cpus[0]), GFP_KERNEL);
+	pt->pod_node = kcalloc(pt->nr_pods, sizeof(pt->pod_node[0]), GFP_KERNEL);
+	BUG_ON(!pt->pod_cpus || !pt->pod_node);
+
+	for (pod = 0; pod < pt->nr_pods; pod++)
+		BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL));
+
+	for_each_possible_cpu(cpu) {
+		cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]);
+		pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu);
+	}
+}
+
+static bool __init cpus_share_numa(int cpu0, int cpu1)
+{
+	return cpu_to_node(cpu0) == cpu_to_node(cpu1);
+}
+
 /**
  * workqueue_init_topology - initialize CPU pods for unbound workqueues
  *
@@ -6404,45 +6452,13 @@ void __init workqueue_init(void)
  */
 void __init workqueue_init_topology(void)
 {
-	struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA];
 	struct workqueue_struct *wq;
-	int node, cpu;
-
-	if (num_possible_nodes() <= 1)
-		return;
+	int cpu;
 
-	for_each_possible_cpu(cpu) {
-		if (WARN_ON(cpu_to_node(cpu) == NUMA_NO_NODE)) {
-			pr_warn("workqueue: NUMA node mapping not available for cpu%d, disabling NUMA support\n", cpu);
-			return;
-		}
-	}
+	init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa);
 
 	mutex_lock(&wq_pool_mutex);
 
-	/*
-	 * We want masks of possible CPUs of each node which isn't readily
-	 * available.  Build one from cpu_to_node() which should have been
-	 * fully initialized by now.
-	 */
-	pt->pod_cpus = kcalloc(nr_node_ids, sizeof(pt->pod_cpus[0]), GFP_KERNEL);
-	pt->pod_node = kcalloc(nr_node_ids, sizeof(pt->pod_node[0]), GFP_KERNEL);
-	pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL);
-	BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod);
-
-	for_each_node(node)
-		BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[node], GFP_KERNEL,
-				node_online(node) ? node : NUMA_NO_NODE));
-
-	for_each_possible_cpu(cpu) {
-		node = cpu_to_node(cpu);
-		cpumask_set_cpu(cpu, pt->pod_cpus[node]);
-		pt->pod_node[node] = node;
-		pt->cpu_pod[cpu] = node;
-	}
-
-	pt->nr_pods = nr_node_ids;
-
 	/*
 	 * Workqueues allocated earlier would have all CPUs sharing the default
 	 * worker pool. Explicitly call wq_update_pod() on all workqueue and CPU
-- 
2.40.1