From 346404682434ad0e31b71f9f37fb6c45a46fe208 Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Mon, 29 Apr 2013 15:08:50 -0700 Subject: [PATCH] numa, cpu hotplug: change links of CPU and node when changing node number by onlining CPU When booting x86 system contains memoryless node, node numbers of CPUs on memoryless node were changed to nearest online node number by init_cpu_to_node() because the node is not online. In my system, node numbers of cpu#30-44 and 75-89 were changed from 2 to 0 as follows: $ numactl --hardware available: 2 nodes (0-1) node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 node 0 size: 32394 MB node 0 free: 27898 MB node 1 cpus: 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 node 1 size: 32768 MB node 1 free: 30335 MB If we hot add memory to memoryless node and offine/online all CPUs on the node, node numbers of these CPUs are changed to correct node numbers by srat_detect_node() because the node become online. In this case, node numbers of cpu#30-44 and 75-89 were changed from 0 to 2 in my system as follows: $ numactl --hardware available: 3 nodes (0-2) node 0 cpus: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 node 0 size: 32394 MB node 0 free: 27218 MB node 1 cpus: 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 node 1 size: 32768 MB node 1 free: 30014 MB node 2 cpus: 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 node 2 size: 16384 MB node 2 free: 16384 MB But "cpu to node" and "node to cpu" links were not changed as follows: $ ls /sys/devices/system/cpu/cpu30/|grep node node0 $ ls /sys/devices/system/node/node0/|grep cpu30 cpu30 "numactl --hardware" shows that cpu30 belongs to node 2. But sysfs links does not change. This patch changes "cpu to node" and "node to cpu" links when node number changed by onlining CPU. Signed-off-by: Yasuaki Ishimatsu Cc: KOSAKI Motohiro Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: "Srivatsa S. Bhat" Cc: Greg KH Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/cpu.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index d8c7f3ee6e19..3d48fc887ef4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -25,6 +25,15 @@ EXPORT_SYMBOL_GPL(cpu_subsys); static DEFINE_PER_CPU(struct device *, cpu_sys_devices); #ifdef CONFIG_HOTPLUG_CPU +static void change_cpu_under_node(struct cpu *cpu, + unsigned int from_nid, unsigned int to_nid) +{ + int cpuid = cpu->dev.id; + unregister_cpu_under_node(cpuid, from_nid); + register_cpu_under_node(cpuid, to_nid); + cpu->node_id = to_nid; +} + static ssize_t show_online(struct device *dev, struct device_attribute *attr, char *buf) @@ -39,17 +48,29 @@ static ssize_t __ref store_online(struct device *dev, const char *buf, size_t count) { struct cpu *cpu = container_of(dev, struct cpu, dev); + int cpuid = cpu->dev.id; + int from_nid, to_nid; ssize_t ret; cpu_hotplug_driver_lock(); switch (buf[0]) { case '0': - ret = cpu_down(cpu->dev.id); + ret = cpu_down(cpuid); if (!ret) kobject_uevent(&dev->kobj, KOBJ_OFFLINE); break; case '1': - ret = cpu_up(cpu->dev.id); + from_nid = cpu_to_node(cpuid); + ret = cpu_up(cpuid); + + /* + * When hot adding memory to memoryless node and enabling a cpu + * on the node, node number of the cpu may internally change. + */ + to_nid = cpu_to_node(cpuid); + if (from_nid != to_nid) + change_cpu_under_node(cpu, from_nid, to_nid); + if (!ret) kobject_uevent(&dev->kobj, KOBJ_ONLINE); break;