[PATCH v4] sched/isolation: Defer freeing of cpumask memblock memory to initcall

[PATCH v4] sched/isolation: Defer freeing of cpumask memblock memory to initcall

[Waiman Long]

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.

  Cannot free reserved memory because of deferred initialization of the memory map
  WARNING: mm/memblock.c:904 at __free_reserved_area+0xde/0xf0, CPU#0: swapper/0/0
    :
  Call Trace:
   <TASK>
   memblock_phys_free+0xcb/0x100
   housekeeping_init+0x14c/0x170
   start_kernel+0x207/0x450
   x86_64_start_reservations+0x24/0x30
   x86_64_start_kernel+0xda/0xe0
   common_startup_64+0x13e/0x141
   </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 saving the housekeeping cpumask memblock memory to be
freed into a llist free list in housekeeping_init() and add a new
housekeeping_late_init() helper to defer the actual freeing of memblock
memory to when initcall's are being processed. The cpumask memblock
memory is treated as a llist_node with the size of a "long" type which
is also smallest cpumask size that can be allocated.

The non-atomic version of the llist APIs are used as there is no
contention.

This commit depends on the presence of commit 7c2eee9c1367 ("memblock:
don't touch memblock arrays when memblock_free() is called late")
to prevent a KASAN UAF bug report [1].

 [1] https://lore.kernel.org/lkml/20260505051821.1107133-1-longman@redhat.com/

Fixes: 27c3a5967f05 ("sched/isolation: Convert housekeeping cpumasks to rcu pointers")
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/sched/isolation.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

 [v4] Collect tags and update commit log

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index ef152d401fe2..156025ef81b7 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -8,6 +8,7 @@
  *
  */
 #include <linux/sched/isolation.h>
+#include <linux/llist.h>
 #include <linux/pci.h>
 #include "sched.h"
 
@@ -27,6 +28,7 @@ struct housekeeping {
 };
 
 static struct housekeeping housekeeping;
+static __initdata LLIST_HEAD(memblock_freelist);
 
 bool housekeeping_enabled(enum hk_type type)
 {
@@ -189,10 +191,22 @@ void __init housekeeping_init(void)
 		WARN_ON_ONCE(cpumask_empty(omask));
 		cpumask_copy(nmask, omask);
 		RCU_INIT_POINTER(housekeeping.cpumasks[type], nmask);
-		memblock_free(omask, cpumask_size());
+		__llist_add((struct llist_node *)omask, &memblock_freelist);
 	}
 }
 
+static int __init housekeeping_late_init(void)
+{
+	struct llist_node *llnode, *pos, *t;
+
+	/* Free allocated memblock memory, if any */
+	llnode = __llist_del_all(&memblock_freelist);
+	llist_for_each_safe(pos, t, llnode)
+		memblock_free(pos, cpumask_size());
+	return 0;
+}
+pure_initcall(housekeeping_late_init);
+
 static void __init housekeeping_setup_type(enum hk_type type,
 					   cpumask_var_t housekeeping_staging)
 {
-- 
2.54.0

Re: [PATCH v4] sched/isolation: Defer freeing of cpumask memblock memory to initcall

[Waiman Long]

On 7/1/26 3:58 PM, Waiman Long wrote:
> 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.
>
>    Cannot free reserved memory because of deferred initialization of the memory map
>    WARNING: mm/memblock.c:904 at __free_reserved_area+0xde/0xf0, CPU#0: swapper/0/0
>      :
>    Call Trace:
>     <TASK>
>     memblock_phys_free+0xcb/0x100
>     housekeeping_init+0x14c/0x170
>     start_kernel+0x207/0x450
>     x86_64_start_reservations+0x24/0x30
>     x86_64_start_kernel+0xda/0xe0
>     common_startup_64+0x13e/0x141
>     </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 saving the housekeeping cpumask memblock memory to be
> freed into a llist free list in housekeeping_init() and add a new
> housekeeping_late_init() helper to defer the actual freeing of memblock
> memory to when initcall's are being processed. The cpumask memblock
> memory is treated as a llist_node with the size of a "long" type which
> is also smallest cpumask size that can be allocated.
>
> The non-atomic version of the llist APIs are used as there is no
> contention.
>
> This commit depends on the presence of commit 7c2eee9c1367 ("memblock:
> don't touch memblock arrays when memblock_free() is called late")
> to prevent a KASAN UAF bug report [1].
>
>   [1] https://lore.kernel.org/lkml/20260505051821.1107133-1-longman@redhat.com/
>
> Fixes: 27c3a5967f05 ("sched/isolation: Convert housekeeping cpumasks to rcu pointers")
> Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
> Reviewed-by: Phil Auld <pauld@redhat.com>
> Signed-off-by: Waiman Long <longman@redhat.com>

Peter,

Are you OK with this patch as I would like to get it merged into v7.3 if 
possible?

Cheers,
Longman

> ---
>   kernel/sched/isolation.c | 16 +++++++++++++++-
>   1 file changed, 15 insertions(+), 1 deletion(-)
>
>   [v4] Collect tags and update commit log
>
> diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
> index ef152d401fe2..156025ef81b7 100644
> --- a/kernel/sched/isolation.c
> +++ b/kernel/sched/isolation.c
> @@ -8,6 +8,7 @@
>    *
>    */
>   #include <linux/sched/isolation.h>
> +#include <linux/llist.h>
>   #include <linux/pci.h>
>   #include "sched.h"
>   
> @@ -27,6 +28,7 @@ struct housekeeping {
>   };
>   
>   static struct housekeeping housekeeping;
> +static __initdata LLIST_HEAD(memblock_freelist);
>   
>   bool housekeeping_enabled(enum hk_type type)
>   {
> @@ -189,10 +191,22 @@ void __init housekeeping_init(void)
>   		WARN_ON_ONCE(cpumask_empty(omask));
>   		cpumask_copy(nmask, omask);
>   		RCU_INIT_POINTER(housekeeping.cpumasks[type], nmask);
> -		memblock_free(omask, cpumask_size());
> +		__llist_add((struct llist_node *)omask, &memblock_freelist);
>   	}
>   }
>   
> +static int __init housekeeping_late_init(void)
> +{
> +	struct llist_node *llnode, *pos, *t;
> +
> +	/* Free allocated memblock memory, if any */
> +	llnode = __llist_del_all(&memblock_freelist);
> +	llist_for_each_safe(pos, t, llnode)
> +		memblock_free(pos, cpumask_size());
> +	return 0;
> +}
> +pure_initcall(housekeeping_late_init);
> +
>   static void __init housekeeping_setup_type(enum hk_type type,
>   					   cpumask_var_t housekeeping_staging)
>   {