From a6a0251c6fce496744121b4e08c899f45270dbcc Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Mon, 18 Oct 2021 15:15:35 -0700 Subject: [PATCH] mm/migrate: fix CPUHP state to update node demotion order The node demotion order needs to be updated during CPU hotplug. Because whether a NUMA node has CPU may influence the demotion order. The update function should be called during CPU online/offline after the node_states[N_CPU] has been updated. That is done in CPUHP_AP_ONLINE_DYN during CPU online and in CPUHP_MM_VMSTAT_DEAD during CPU offline. But in commit 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events"), the function to update node demotion order is called in CPUHP_AP_ONLINE_DYN during CPU online/offline. This doesn't satisfy the order requirement. For example, there are 4 CPUs (P0, P1, P2, P3) in 2 sockets (P0, P1 in S0 and P2, P3 in S1), the demotion order is - S0 -> NUMA_NO_NODE - S1 -> NUMA_NO_NODE After P2 and P3 is offlined, because S1 has no CPU now, the demotion order should have been changed to - S0 -> S1 - S1 -> NO_NODE but it isn't changed, because the order updating callback for CPU hotplug doesn't see the new nodemask. After that, if P1 is offlined, the demotion order is changed to the expected order as above. So in this patch, we added CPUHP_AP_MM_DEMOTION_ONLINE and CPUHP_MM_DEMOTION_DEAD to be called after CPUHP_AP_ONLINE_DYN and CPUHP_MM_VMSTAT_DEAD during CPU online and offline, and register the update function on them. Link: https://lkml.kernel.org/r/20210929060351.7293-1-ying.huang@intel.com Fixes: 884a6e5d1f93 ("mm/migrate: update node demotion order on hotplug events") Signed-off-by: "Huang, Ying" Cc: Thomas Gleixner Cc: Dave Hansen Cc: Yang Shi Cc: Zi Yan Cc: Michal Hocko Cc: Wei Xu Cc: Oscar Salvador Cc: David Rientjes Cc: Dan Williams Cc: David Hildenbrand Cc: Greg Thelen Cc: Keith Busch Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuhotplug.h | 4 ++++ mm/migrate.c | 8 +++++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 832d8a74fa59..991911048857 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -72,6 +72,8 @@ enum cpuhp_state { CPUHP_SLUB_DEAD, CPUHP_DEBUG_OBJ_DEAD, CPUHP_MM_WRITEBACK_DEAD, + /* Must be after CPUHP_MM_VMSTAT_DEAD */ + CPUHP_MM_DEMOTION_DEAD, CPUHP_MM_VMSTAT_DEAD, CPUHP_SOFTIRQ_DEAD, CPUHP_NET_MVNETA_DEAD, @@ -240,6 +242,8 @@ enum cpuhp_state { CPUHP_AP_BASE_CACHEINFO_ONLINE, CPUHP_AP_ONLINE_DYN, CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, + /* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */ + CPUHP_AP_MM_DEMOTION_ONLINE, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, CPUHP_AP_DTPM_CPU_ONLINE, diff --git a/mm/migrate.c b/mm/migrate.c index 700112c0123d..1852d787e6ab 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -3288,9 +3288,8 @@ static int __init migrate_on_reclaim_init(void) { int ret; - ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "migrate on reclaim", - migration_online_cpu, - migration_offline_cpu); + ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline", + NULL, migration_offline_cpu); /* * In the unlikely case that this fails, the automatic * migration targets may become suboptimal for nodes @@ -3298,6 +3297,9 @@ static int __init migrate_on_reclaim_init(void) * rare case, do not bother trying to do anything special. */ WARN_ON(ret < 0); + ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online", + migration_online_cpu, NULL); + WARN_ON(ret < 0); hotplug_memory_notifier(migrate_on_reclaim_callback, 100); return 0;