From: Dexuan Cui <decui@microsoft.com>
Date: Mon, 21 Dec 2020 22:55:41 -0800
Patch-mainline: v5.11-rc4
Subject: x86/hyperv: Fix kexec panic/hang issues
Git-commit: dfe94d4086e40e92b1926bddcefa629b791e9b28
References: bsc#1176831

Currently the kexec kernel can panic or hang due to 2 causes:

1) hv_cpu_die() is not called upon kexec, so the hypervisor corrupts the
old VP Assist Pages when the kexec kernel runs. The same issue is fixed
for hibernation in commit 421f090c819d ("x86/hyperv: Suspend/resume the
VP assist page for hibernation"). Now fix it for kexec.

2) hyperv_cleanup() is called too early. In the kexec path, the other CPUs
are stopped in hv_machine_shutdown() -> native_machine_shutdown(), so
between hv_kexec_handler() and native_machine_shutdown(), the other CPUs
can still try to access the hypercall page and cause panic. The workaround
"hv_hypercall_pg = NULL;" in hyperv_cleanup() is unreliabe. Move
hyperv_cleanup() to a better place.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20201222065541.24312-1-decui@microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Acked-by: Olaf Hering <ohering@suse.de>
---
 arch/x86/hyperv/hv_init.c       |  4 ++++
 arch/x86/include/asm/mshyperv.h |  2 ++
 arch/x86/kernel/cpu/mshyperv.c  | 18 ++++++++++++++++++
 drivers/hv/vmbus_drv.c          |  2 --
 4 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -16,6 +16,9 @@
 #include <asm/hypervisor.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
+#ifndef __GENKSYMS__ /* kABI workaround for SLE kernel */
+#include <linux/kexec.h>
+#endif
 #include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
@@ -33,6 +33,8 @@
 #include <linux/cpuhotplug.h>
 #include <clocksource/hyperv_timer.h>
 
+int hyperv_init_cpuhp;
+
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -314,6 +316,8 @@ void __init hyperv_init(void)
 
 	/* Register Hyper-V specific clocksource */
 	hv_init_clocksource();
+
+	hyperv_init_cpuhp = cpuhp;
 	return;
 
 remove_cpuhp_state:
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -72,6 +72,8 @@ static inline void hv_disable_stimer0_pe
 
 
 #if IS_ENABLED(CONFIG_HYPERV)
+extern int hyperv_init_cpuhp;
+
 extern void *hv_hypercall_pg;
 extern void  __percpu  **hyperv_pcpu_input_arg;
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -21,6 +21,7 @@
 #include <linux/irq.h>
 #include <linux/kexec.h>
 #include <linux/i8253.h>
+#include <linux/cpuhotplug.h>
 #include <linux/random.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
@@ -135,14 +135,32 @@ static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
 		hv_kexec_handler();
+
+	/*
+	 * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+	 * corrupts the old VP Assist Pages and can crash the kexec kernel.
+	 */
+	if (kexec_in_progress && hyperv_init_cpuhp > 0)
+		cpuhp_remove_state(hyperv_init_cpuhp);
+
+	/* The function calls stop_other_cpus(). */
 	native_machine_shutdown();
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	if (kexec_in_progress)
+		hyperv_cleanup();
 }
 
 static void hv_machine_crash_shutdown(struct pt_regs *regs)
 {
 	if (hv_crash_handler)
 		hv_crash_handler(regs);
+
+	/* The function calls crash_smp_send_stop(). */
 	native_machine_crash_shutdown(regs);
+
+	/* Disable the hypercall page when there is only 1 active CPU. */
+	hyperv_cleanup();
 }
 #endif /* CONFIG_KEXEC_CORE */
 #endif /* CONFIG_HYPERV */
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2550,7 +2550,6 @@ static void hv_kexec_handler(void)
 	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
 	mb();
 	cpuhp_remove_state(hyperv_cpuhp_online);
-	hyperv_cleanup();
 };
 
 static void hv_crash_handler(struct pt_regs *regs)
@@ -2144,7 +2144,6 @@ static void hv_crash_handler(struct pt_r
 	cpu = smp_processor_id();
 	hv_stimer_cleanup(cpu);
 	hv_synic_cleanup(cpu);
-	hyperv_cleanup();
 };
 
 static int __init hv_acpi_init(void)