Drivers: hv: vmbus: prefer 'die' notification chain to 'panic'

current_pt_regs() sometimes returns regs of the userspace process and in
case of a kernel crash this is not what we need to report. E.g. when we
trigger crash with sysrq we see the following:
...
 RIP: 0010:[<ffffffff815b8696>]  [<ffffffff815b8696>] sysrq_handle_crash+0x16/0x20
 RSP: 0018:ffff8800db0a7d88  EFLAGS: 00010246
 RAX: 000000000000000f RBX: ffffffff820a0660 RCX: 0000000000000000
...
at the same time current_pt_regs() give us:
ip=7f899ea7e9e0, ax=ffffffffffffffda, bx=26c81a0, cx=7f899ea7e9e0, ...
These registers come from the userspace process triggered the crash. As we
don't even know which process it was this information is rather useless.

When kernel crash happens through 'die' proper regs are being passed to
all receivers on the die_chain (and panic_notifier_list is being notified
with the string passed to panic() only). If panic() is called manually
(e.g. on BUG()) we won't get 'die' notification so keep the 'panic'
notification reporter as well but guard against double reporting.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 36 insertions, 4 deletions

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 1ed9b32853a1..b6114cc89aeb 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -39,6 +39,7 @@
 #include <asm/mshyperv.h>
 #include <linux/notifier.h>
 #include <linux/ptrace.h>
+#include <linux/kdebug.h>
 #include "hyperv_vmbus.h"
 
 static struct acpi_device  *hv_acpi_dev;
@@ -48,12 +49,18 @@ static struct completion probe_event;
 static int irq;
 
 
-static int hyperv_panic_event(struct notifier_block *nb,
-			unsigned long event, void *ptr)
+static void hyperv_report_panic(struct pt_regs *regs)
 {
-	struct pt_regs *regs;
+	static bool panic_reported;
 
-	regs = current_pt_regs();
+	/*
+	 * We prefer to report panic on 'die' chain as we have proper
+	 * registers to report, but if we miss it (e.g. on BUG()) we need
+	 * to report it on 'panic'.
+	 */
+	if (panic_reported)
+		return;
+	panic_reported = true;
 
 	wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip);
 	wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax);
@@ -65,9 +72,32 @@ static int hyperv_panic_event(struct notifier_block *nb,
 	 * Let Hyper-V know there is crash data available
 	 */
 	wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
+}
+
+static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
+			      void *args)
+{
+	struct pt_regs *regs;
+
+	regs = current_pt_regs();
+
+	hyperv_report_panic(regs);
 	return NOTIFY_DONE;
 }
 
+static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
+			    void *args)
+{
+	struct die_args *die = (struct die_args *)args;
+	struct pt_regs *regs = die->regs;
+
+	hyperv_report_panic(regs);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block hyperv_die_block = {
+	.notifier_call = hyperv_die_event,
+};
 static struct notifier_block hyperv_panic_block = {
 	.notifier_call = hyperv_panic_event,
 };
@@ -842,6 +872,7 @@ static int vmbus_bus_init(int irq)
 	 * Only register if the crash MSRs are available
 	 */
 	if (ms_hyperv.features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+		register_die_notifier(&hyperv_die_block);
 		atomic_notifier_chain_register(&panic_notifier_list,
 					       &hyperv_panic_block);
 	}
@@ -1139,6 +1170,7 @@ static void __exit vmbus_exit(void)
 	tasklet_kill(&msg_dpc);
 	vmbus_free_channels();
 	if (ms_hyperv.features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+		unregister_die_notifier(&hyperv_die_block);
 		atomic_notifier_chain_unregister(&panic_notifier_list,
 						 &hyperv_panic_block);
 	}