linux-kernel - [RFC] lib: optimize cpumask_local

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-next>] [day] [month] [year] [list]

Message-ID: <1571307788-43169-1-git-send-email-zhangshaokun@hisilicon.com>
Date:   Thu, 17 Oct 2019 18:23:08 +0800
From:   Shaokun Zhang <zhangshaokun@...ilicon.com>
To:     <linux-kernel@...r.kernel.org>
CC:     yuqi jin <jinyuqi@...wei.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Mike Rapoport <rppt@...ux.ibm.com>,
        Paul Burton <paul.burton@...s.com>,
        Michal Hocko <mhocko@...e.com>,
        Michael Ellerman <mpe@...erman.id.au>,
        Anshuman Khandual <anshuman.khandual@....com>,
        Shaokun Zhang <zhangshaokun@...ilicon.com>
Subject: [RFC] lib: optimize cpumask_local_spread()

From: yuqi jin <jinyuqi@...wei.com>

In the multi-processor and NUMA system, A device may have many numa
nodes belonging to multiple cpus. When we get a local numa, it is better
to find the node closest to the local numa node to return instead of
going to the online cpu immediately.

For example, In Huawei Kunpeng 920 system, there are 4 NUMA node(0 -3)
in the 2-socket system(0 - 1). If the I/O device is in socket1
and the local NUMA node is 2, we shall choose the non-local node3 in
the same socket when cpu core in NUMA node2 is less that I/O requirements.
If we directly pick one cpu core from all online ones, it may be in
the another socket and it is not friendly for performance.

Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Mike Rapoport <rppt@...ux.ibm.com>
Cc: Paul Burton <paul.burton@...s.com>
Cc: Michal Hocko <mhocko@...e.com>
Cc: Michael Ellerman <mpe@...erman.id.au>
Cc: Anshuman Khandual <anshuman.khandual@....com>
Signed-off-by: yuqi jin <jinyuqi@...wei.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@...ilicon.com>
---
 lib/cpumask.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 67 insertions(+), 11 deletions(-)

diff --git a/lib/cpumask.c b/lib/cpumask.c
index 0cb672eb107c..8f89c7cebfb0 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -192,6 +192,33 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 }
 #endif
 
+static void calc_node_distance(int *node_dist, int node)
+{
+	int i;
+
+	for (i = 0; i < nr_node_ids; i++)
+		node_dist[i] = node_distance(node, i);
+}
+
+static int find_nearest_node(int *node_dist, bool *used_flag)
+{
+	int i, min_dist = node_dist[0], node_id = -1;
+
+	for (i = 0; i < nr_node_ids; i++)
+		if (used_flag[i] == 0) {
+			min_dist = node_dist[i];
+			node_id = i;
+			break;
+		}
+	for (i = 0; i < nr_node_ids; i++)
+		if (node_dist[i] < min_dist && used_flag[i] == 0) {
+			min_dist = node_dist[i];
+			node_id = i;
+		}
+
+	return node_id;
+}
+
 /**
  * cpumask_local_spread - select the i'th cpu with local numa cpu's first
  * @i: index number
@@ -205,7 +232,8 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
  */
 unsigned int cpumask_local_spread(unsigned int i, int node)
 {
-	int cpu;
+	int cpu, j, id, *node_dist;
+	bool *used_flag;
 
 	/* Wrap: we always want a cpu. */
 	i %= num_online_cpus();
@@ -215,19 +243,47 @@ unsigned int cpumask_local_spread(unsigned int i, int node)
 			if (i-- == 0)
 				return cpu;
 	} else {
-		/* NUMA first. */
-		for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
-			if (i-- == 0)
-				return cpu;
+		node_dist = kmalloc_array(nr_node_ids,
+			sizeof(int), GFP_KERNEL);
+		if (!node_dist)
+			for_each_cpu(cpu, cpu_online_mask)
+				if (i-- == 0)
+					return cpu;
 
-		for_each_cpu(cpu, cpu_online_mask) {
-			/* Skip NUMA nodes, done above. */
-			if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
-				continue;
+		used_flag = kmalloc_array(nr_node_ids,
+			sizeof(bool), GFP_KERNEL);
+		if (!used_flag)
+			for_each_cpu(cpu, cpu_online_mask)
+				if (i-- == 0) {
+					kfree(node_dist);
+					return cpu;
+				}
+		memset(used_flag, 0, nr_node_ids * sizeof(bool));
 
-			if (i-- == 0)
-				return cpu;
+		calc_node_distance(node_dist, node);
+		for (j = 0; j < nr_node_ids; j++) {
+			id = find_nearest_node(node_dist, used_flag);
+			if (id < 0)
+				break;
+			for_each_cpu_and(cpu,
+				cpumask_of_node(id), cpu_online_mask)
+				if (i-- == 0) {
+					kfree(node_dist);
+					kfree(used_flag);
+					return cpu;
+				}
+			used_flag[id] = 1;
 		}
+
+		for_each_cpu(cpu, cpu_online_mask)
+			if (i-- == 0) {
+				kfree(node_dist);
+				kfree(used_flag);
+				return cpu;
+			}
+
+		kfree(node_dist);
+		kfree(used_flag);
 	}
 	BUG();
 }
-- 
2.7.4