[PATCH v2 2/3] Drivers: hv: vmbus: add special kexec handler

[Vitaly Kuznetsov]

When general-purpose kexec (not kdump) is being performed in Hyper-V guest
the newly booted kernel fails with an MCE error coming from the host. It
is the same error which was fixed in the "Drivers: hv: vmbus: Implement
the protocol for tearing down vmbus state" commit - monitor pages remain
special and when they're being written to (as the new kernel doesn't know
these pages are special) bad things happen. We need to perform some
minimalistic cleanup before booting a new kernel on kexec. To do so we
need to register a special machine_ops.shutdown handler to be executed
before the native_machine_shutdown(). Registering a shutdown notification
handler via the register_reboot_notifier() call is not sufficient as it
happens to early for our purposes. machine_ops is not being exported to
modules (and I don't think we want to export it) so let's do this in
mshyperv.c

The minimalistic cleanup consists of cleaning up clockevents, synic MSRs,
guest os id MSR, and hypercall MSR.

Kdump doesn't require all this stuff as it lives in a separate memory
space.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 arch/x86/include/asm/mshyperv.h |  2 ++
 arch/x86/kernel/cpu/mshyperv.c  | 30 ++++++++++++++++++++++++++++++
 drivers/hv/vmbus_drv.c          | 14 ++++++++++++++
 3 files changed, 46 insertions(+)

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index c163215..d3db910 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -20,4 +20,6 @@ void hyperv_vector_handler(struct pt_regs *regs);
 void hv_setup_vmbus_irq(void (*handler)(void));
 void hv_remove_vmbus_irq(void);
 
+void hv_setup_kexec_handler(void (*handler)(void));
+void hv_remove_kexec_handler(void);
 #endif
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 939155f..efc20a0 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -18,6 +18,9 @@
 #include <linux/efi.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#ifdef CONFIG_KEXEC
+#include <linux/kexec.h>
+#endif
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>
@@ -28,12 +31,14 @@
 #include <asm/i8259.h>
 #include <asm/apic.h>
 #include <asm/timer.h>
+#include <asm/reboot.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
+static void (*hv_kexec_handler)(void);
 
 void hyperv_vector_handler(struct pt_regs *regs)
 {
@@ -69,6 +74,28 @@ void hv_remove_vmbus_irq(void)
 }
 EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
 EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
+
+void hv_setup_kexec_handler(void (*handler)(void))
+{
+	hv_kexec_handler = handler;
+}
+EXPORT_SYMBOL_GPL(hv_setup_kexec_handler);
+
+void hv_remove_kexec_handler(void)
+{
+	/* We have no way to deallocate the interrupt gate */
+	hv_kexec_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_remove_kexec_handler);
+
+static void hv_machine_shutdown(void)
+{
+#ifdef CONFIG_KEXEC
+	if (kexec_in_progress && hv_kexec_handler)
+		hv_kexec_handler();
+#endif
+	native_machine_shutdown();
+}
 #endif
 
 static uint32_t  __init ms_hyperv_platform(void)
@@ -143,6 +170,9 @@ static void __init ms_hyperv_init_platform(void)
 	no_timer_check = 1;
 #endif
 
+#if IS_ENABLED(CONFIG_HYPERV)
+	machine_ops.shutdown = hv_machine_shutdown;
+#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 00d5158..31748a2 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1060,6 +1060,17 @@ static struct acpi_driver vmbus_acpi_driver = {
 	},
 };
 
+static void hv_kexec_handler(void)
+{
+	int cpu;
+
+	hv_synic_clockevents_cleanup();
+	vmbus_initiate_unload();
+	for_each_online_cpu(cpu)
+		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
+	hv_cleanup();
+};
+
 static int __init hv_acpi_init(void)
 {
 	int ret, t;
@@ -1092,6 +1103,8 @@ static int __init hv_acpi_init(void)
 	if (ret)
 		goto cleanup;
 
+	hv_setup_kexec_handler(hv_kexec_handler);
+
 	return 0;
 
 cleanup:
@@ -1104,6 +1117,7 @@ static void __exit vmbus_exit(void)
 {
 	int cpu;
 
+	hv_remove_kexec_handler();
 	vmbus_connection.conn_state = DISCONNECTED;
 	hv_synic_clockevents_cleanup();
 	vmbus_disconnect();
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/