On L1VH, debugfs stats pages are overlay pages: the kernel allocates
them and registers the GPAs with the hypervisor via
HVCALL_MAP_STATS_PAGE2. These overlay mappings persist in the
hypervisor across kexec. If the kexec'd kernel reuses those physical
pages, the hypervisor's overlay semantics cause a machine check
exception.

Fix this by calling mshv_debugfs_exit() from the reboot notifier,
which issues HVCALL_UNMAP_STATS_PAGE for each mapped stats page before
kexec. This releases the overlay bindings so the physical pages can be
safely reused. Guard mshv_debugfs_exit() against being called when
init failed.

Signed-off-by: Jork Loeser <jloeser@linux.microsoft.com>
---
 drivers/hv/mshv_debugfs.c   | 7 ++++++-
 drivers/hv/mshv_root_main.c | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/hv/mshv_debugfs.c b/drivers/hv/mshv_debugfs.c
index ebf2549eb44d..f9a4499cf8f3 100644
--- a/drivers/hv/mshv_debugfs.c
+++ b/drivers/hv/mshv_debugfs.c
@@ -676,8 +676,10 @@ int __init mshv_debugfs_init(void)
 
 	mshv_debugfs = debugfs_create_dir("mshv", NULL);
 	if (IS_ERR(mshv_debugfs)) {
+		err = PTR_ERR(mshv_debugfs);
+		mshv_debugfs = NULL;
 		pr_err("%s: failed to create debugfs directory\n", __func__);
-		return PTR_ERR(mshv_debugfs);
+		return err;
 	}
 
 	if (hv_root_partition()) {
@@ -712,6 +714,9 @@ int __init mshv_debugfs_init(void)
 
 void mshv_debugfs_exit(void)
 {
+	if (!mshv_debugfs)
+		return;
+
 	mshv_debugfs_parent_partition_remove();
 
 	if (hv_root_partition()) {
diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
index 281f530b68a9..7038fd830646 100644
--- a/drivers/hv/mshv_root_main.c
+++ b/drivers/hv/mshv_root_main.c
@@ -2252,6 +2252,7 @@ root_scheduler_deinit(void)
 static int mshv_reboot_notify(struct notifier_block *nb,
 			      unsigned long code, void *unused)
 {
+	mshv_debugfs_exit();
 	cpuhp_remove_state(mshv_cpuhp_online);
 	return 0;
 }
-- 
2.43.0

On Fri, Mar 27, 2026 at 01:19:17PM -0700, Jork Loeser wrote:
> On L1VH, debugfs stats pages are overlay pages: the kernel allocates
> them and registers the GPAs with the hypervisor via
> HVCALL_MAP_STATS_PAGE2. These overlay mappings persist in the
> hypervisor across kexec. If the kexec'd kernel reuses those physical
> pages, the hypervisor's overlay semantics cause a machine check
> exception.
> 
> Fix this by calling mshv_debugfs_exit() from the reboot notifier,
> which issues HVCALL_UNMAP_STATS_PAGE for each mapped stats page before
> kexec. This releases the overlay bindings so the physical pages can be
> safely reused. Guard mshv_debugfs_exit() against being called when
> init failed.
> 
> Signed-off-by: Jork Loeser <jloeser@linux.microsoft.com>
> ---
>  drivers/hv/mshv_debugfs.c   | 7 ++++++-
>  drivers/hv/mshv_root_main.c | 1 +
>  2 files changed, 7 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/hv/mshv_debugfs.c b/drivers/hv/mshv_debugfs.c
> index ebf2549eb44d..f9a4499cf8f3 100644
> --- a/drivers/hv/mshv_debugfs.c
> +++ b/drivers/hv/mshv_debugfs.c
> @@ -676,8 +676,10 @@ int __init mshv_debugfs_init(void)
>  
>  	mshv_debugfs = debugfs_create_dir("mshv", NULL);
>  	if (IS_ERR(mshv_debugfs)) {
> +		err = PTR_ERR(mshv_debugfs);
> +		mshv_debugfs = NULL;
>  		pr_err("%s: failed to create debugfs directory\n", __func__);
> -		return PTR_ERR(mshv_debugfs);
> +		return err;
>  	}
>  
>  	if (hv_root_partition()) {
> @@ -712,6 +714,9 @@ int __init mshv_debugfs_init(void)
>  
>  void mshv_debugfs_exit(void)
>  {
> +	if (!mshv_debugfs)

nit: this should allow to avoid setting mshv_debugfs to NULL in the
error path of mshv_debugfs_init():

if (!IS_ERR_OR_NULL(mshv_debugfs))

Reviewed-by: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>

> +		return;
> +
>  	mshv_debugfs_parent_partition_remove();
>  
>  	if (hv_root_partition()) {
> diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
> index 281f530b68a9..7038fd830646 100644
> --- a/drivers/hv/mshv_root_main.c
> +++ b/drivers/hv/mshv_root_main.c
> @@ -2252,6 +2252,7 @@ root_scheduler_deinit(void)
>  static int mshv_reboot_notify(struct notifier_block *nb,
>  			      unsigned long code, void *unused)
>  {
> +	mshv_debugfs_exit();
>  	cpuhp_remove_state(mshv_cpuhp_online);
>  	return 0;
>  }
> -- 
> 2.43.0
>

On Mon, 30 Mar 2026, Stanislav Kinsburskii wrote:

>> diff --git a/drivers/hv/mshv_debugfs.c b/drivers/hv/mshv_debugfs.c
[...]
>> +++ b/drivers/hv/mshv_debugfs.c
>> @@ -676,8 +676,10 @@ int __init mshv_debugfs_init(void)
> nit: this should allow to avoid setting mshv_debugfs to NULL in the
> error path of mshv_debugfs_init():
>
> if (!IS_ERR_OR_NULL(mshv_debugfs))

Yes, of course one could. Though a permanent ERR_PTR in a global variable 
to indicate init-problems feels off to me. NULL for "not there" seems more 
canonical, no?

Best,
Jork