[PATCH] sched/isolation: Postpone re-allocation of housekeeping cpumask until initcall

[Waiman Long <longman@redhat.com>]

When testing a linux-next kernel with commit 59bd1d914bb5 ("memblock:
warn when freeing reserved memory before memory map is initialized"),
the following warning was hit when there was a "nohz_full" kernel boot
parameter.

[    0.080911] Cannot free reserved memory because of deferred initialization of the memory map
[    0.080911] WARNING: mm/memblock.c:904 at __free_reserved_area+0xde/0xf0, CPU#0: swapper/0/0
  :
[    0.080945] Call Trace:
[    0.080947]  <TASK>
[    0.080949]  memblock_phys_free+0xcb/0x100
[    0.080953]  housekeeping_init+0x14c/0x170
[    0.080957]  start_kernel+0x207/0x450
[    0.080961]  x86_64_start_reservations+0x24/0x30
[    0.080965]  x86_64_start_kernel+0xda/0xe0
[    0.080967]  common_startup_64+0x13e/0x141
[    0.080972]  </TASK>

IOW, we shouldn't free memblock allocated memory so early in
the boot process when memory map isn't fully initialized in
deferred_init_memmap(). Fix it by adding a new housekeeping_late_init()
helper to defer the re-allocation of the housekeeping cpumasks to when
initcall's are being processed.

Fixes: 27c3a5967f05 ("sched/isolation: Convert housekeeping cpumasks to rcu pointers")
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/sched/isolation.c | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index ef152d401fe2..3f582ed6b985 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -164,8 +164,6 @@ int housekeeping_update(struct cpumask *isol_mask)
 
 void __init housekeeping_init(void)
 {
-	enum hk_type type;
-
 	if (!housekeeping.flags)
 		return;
 
@@ -173,15 +171,25 @@ void __init housekeeping_init(void)
 
 	if (housekeeping.flags & HK_FLAG_KERNEL_NOISE)
 		sched_tick_offload_init();
+}
+
+static int __init housekeeping_late_init(void)
+{
+	enum hk_type type;
+
+	if (!housekeeping.flags)
+		return 0;
+
 	/*
 	 * Realloc with a proper allocator so that any cpumask update
-	 * can indifferently free the old version with kfree().
+	 * can indifferently free the old version with kfree(). This
+	 * should be done after the completion of deferred_init_memmap().
 	 */
 	for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
 		struct cpumask *omask, *nmask = kmalloc(cpumask_size(), GFP_KERNEL);
 
 		if (WARN_ON_ONCE(!nmask))
-			return;
+			return 0;
 
 		omask = rcu_dereference(housekeeping.cpumasks[type]);
 
@@ -191,7 +199,9 @@ void __init housekeeping_init(void)
 		RCU_INIT_POINTER(housekeeping.cpumasks[type], nmask);
 		memblock_free(omask, cpumask_size());
 	}
+	return 0;
 }
+pure_initcall(housekeeping_late_init);
 
 static void __init housekeeping_setup_type(enum hk_type type,
 					   cpumask_var_t housekeeping_staging)
-- 
2.53.0