[PATCH v2] mm/mm_init: Don't call cond_resched() in deferred_init_memmap_chunk() if rcu_preempt_depth() set

Waiman Long posted 1 patch 2 weeks, 2 days ago
mm/mm_init.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
[PATCH v2] mm/mm_init: Don't call cond_resched() in deferred_init_memmap_chunk() if rcu_preempt_depth() set
Posted by Waiman Long 2 weeks, 2 days ago
Commit 3acb913c9d5b ("mm/mm_init: use deferred_init_memmap_chunk()
in deferred_grow_zone()") made deferred_grow_zone() call
deferred_init_memmap_chunk() within a pgdat_resize_lock() critical
section with irqs disabled. It did check for irqs_disabled() in
deferred_init_memmap_chunk() to avoid calling cond_resched(). For a
PREEMPT_RT kernel build, however, spin_lock_irqsave() does not disable
interrupt but rcu_read_lock() is called. This leads to the following
bug report.

  BUG: sleeping function called from invalid context at mm/mm_init.c:2091
  in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid: 1, name: swapper/0
  preempt_count: 0, expected: 0
  RCU nest depth: 1, expected: 0
  3 locks held by swapper/0/1:
   #0: ffff80008471b7a0 (sched_domains_mutex){+.+.}-{4:4}, at: sched_domains_mutex_lock+0x28/0x40
   #1: ffff003bdfffef48 (&pgdat->node_size_lock){+.+.}-{3:3}, at: deferred_grow_zone+0x140/0x278
   #2: ffff800084acf600 (rcu_read_lock){....}-{1:3}, at: rt_spin_lock+0x1b4/0x408
  CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Tainted: G        W           6.19.0-rc6-test #1 PREEMPT_{RT,(full)
}
  Tainted: [W]=WARN
  Call trace:
   show_stack+0x20/0x38 (C)
   dump_stack_lvl+0xdc/0xf8
   dump_stack+0x1c/0x28
   __might_resched+0x384/0x530
   deferred_init_memmap_chunk+0x560/0x688
   deferred_grow_zone+0x190/0x278
   _deferred_grow_zone+0x18/0x30
   get_page_from_freelist+0x780/0xf78
   __alloc_frozen_pages_noprof+0x1dc/0x348
   alloc_slab_page+0x30/0x110
   allocate_slab+0x98/0x2a0
   new_slab+0x4c/0x80
   ___slab_alloc+0x5a4/0x770
   __slab_alloc.constprop.0+0x88/0x1e0
   __kmalloc_node_noprof+0x2c0/0x598
   __sdt_alloc+0x3b8/0x728
   build_sched_domains+0xe0/0x1260
   sched_init_domains+0x14c/0x1c8
   sched_init_smp+0x9c/0x1d0
   kernel_init_freeable+0x218/0x358
   kernel_init+0x28/0x208
   ret_from_fork+0x10/0x20

Fix it by checking rcu_preempt_depth() too before calling
cond_resched(). Note that rcu_preempt_depth() is a helper defined
in the public rcupdate.h header file and is defined whether or not
CONFIG_PREEMPT_RCU is defined. By default, CONFIG_PREEMPT_RCU is enabled
in the PREEMPT_RT kernel.

Fixes: 3acb913c9d5b ("mm/mm_init: use deferred_init_memmap_chunk() in deferred_grow_zone()")
Signed-off-by: Waiman Long <longman@redhat.com>

 [v2]: Add "linux/rcupdate.h" include.

---
 mm/mm_init.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index fc2a6f1e518f..ba0b476c2d45 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -32,6 +32,7 @@
 #include <linux/vmstat.h>
 #include <linux/kexec_handover.h>
 #include <linux/hugetlb.h>
+#include <linux/rcupdate.h>
 #include "internal.h"
 #include "slab.h"
 #include "shuffle.h"
@@ -2085,7 +2086,12 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
 
 			spfn = chunk_end;
 
-			if (irqs_disabled())
+			/*
+			 * pgdat_resize_lock() only disables irqs in non-RT
+			 * kernels but implies rcu_read_lock() in a PREEMPT_RT
+			 * kernel.
+			 */
+			if (irqs_disabled() || rcu_preempt_depth())
 				touch_nmi_watchdog();
 			else
 				cond_resched();
-- 
2.52.0
Re: [PATCH v2] mm/mm_init: Don't call cond_resched() in deferred_init_memmap_chunk() if rcu_preempt_depth() set
Posted by Sebastian Andrzej Siewior 2 weeks, 2 days ago
On 2026-01-21 22:40:17 [-0500], Waiman Long wrote:
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -2085,7 +2086,12 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
>  
>  			spfn = chunk_end;
>  
> -			if (irqs_disabled())
> +			/*
> +			 * pgdat_resize_lock() only disables irqs in non-RT
> +			 * kernels but implies rcu_read_lock() in a PREEMPT_RT
> +			 * kernel.
> +			 */
> +			if (irqs_disabled() || rcu_preempt_depth())
>  				touch_nmi_watchdog();
>  			else
>  				cond_resched();

What about (as suggested in the previous mail)

diff --git a/mm/mm_init.c b/mm/mm_init.c
index fc2a6f1e518f1..0b283fd48b282 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -2059,7 +2059,7 @@ static unsigned long __init deferred_init_pages(struct zone *zone,
  */
 static unsigned long __init
 deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
-			   struct zone *zone)
+			   struct zone *zone, bool may_schedule)
 {
 	int nid = zone_to_nid(zone);
 	unsigned long nr_pages = 0;
@@ -2085,10 +2085,10 @@ deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
 
 			spfn = chunk_end;
 
-			if (irqs_disabled())
-				touch_nmi_watchdog();
-			else
+			if (may_schedule)
 				cond_resched();
+			else
+				touch_nmi_watchdog();
 		}
 	}
 
@@ -2101,7 +2101,7 @@ deferred_init_memmap_job(unsigned long start_pfn, unsigned long end_pfn,
 {
 	struct zone *zone = arg;
 
-	deferred_init_memmap_chunk(start_pfn, end_pfn, zone);
+	deferred_init_memmap_chunk(start_pfn, end_pfn, zone, true);
 }
 
 static unsigned int __init
@@ -2216,7 +2216,7 @@ bool __init deferred_grow_zone(struct zone *zone, unsigned int order)
 	for (spfn = first_deferred_pfn, epfn = SECTION_ALIGN_UP(spfn + 1);
 	     nr_pages < nr_pages_needed && spfn < zone_end_pfn(zone);
 	     spfn = epfn, epfn += PAGES_PER_SECTION) {
-		nr_pages += deferred_init_memmap_chunk(spfn, epfn, zone);
+		nr_pages += deferred_init_memmap_chunk(spfn, epfn, zone, false);
 	}
 
 	/*


Sebastian