On Fri, Aug 07, 2020 at 11:06:47AM +0200, Vitaly Kuznetsov wrote:

Michael Kelley [off-list ref] writes:

quoted

Hyper-V currently may be notified of a panic for any die event. But
this results in false panic notifications for various user space traps
that are die events. Fix this by ignoring die events that aren't oops.

Fixes: 510f7aef65bb ("Drivers: hv: vmbus: prefer 'die' notification chain to 'panic'")
Signed-off-by: Michael Kelley <redacted>
---
 drivers/hv/vmbus_drv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index b50081c..910b6e9 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c

@@ -86,6 +86,10 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
 	struct die_args *die = (struct die_args *)args;
 	struct pt_regs *regs = die->regs;
 
+	/* Don't notify Hyper-V if the die event is other than oops */
+	if (val != DIE_OOPS)
+		return NOTIFY_DONE;
+

Looking at die_val enum, DIE_PANIC also sounds like something we would
want to report but it doesn't get emitted anywhere and honestly I don't
quite understand how is was supposed to be different from DIE_OOPS.

Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>

Applied to hyperv-fixes.

Wei.

quoted

 	/*
 	 * Hyper-V should be notified only once about a panic.  If we will be
 	 * doing hyperv_report_panic_msg() later with kmsg data, don't do

-- 
Vitaly