x86/hyperv: Fix kexec panic/hang issues

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>

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e04d90af4c27cd4966351d277e945ff4df47461b..4638a52d8eaeae7419a2881e0452237a7251f9e6 100644 (file)
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -16,6 +16,7 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/idtentry.h>
+#include <linux/kexec.h>
 #include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
@@ -26,6 +27,8 @@
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 
+int hyperv_init_cpuhp;
+
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -401,6 +404,7 @@ void __init hyperv_init(void)
 
        register_syscore_ops(&hv_syscore_ops);
 
+       hyperv_init_cpuhp = cpuhp;
        return;
 
 remove_cpuhp_state:

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index ffc289992d1b0f5bd81eeeed98feae67d71dfb22..30f76b96685799c7e95cfff039d265a1dc42dea0 100644 (file)
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {}
 
 
 #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
index f628e3dc150f38088dafb158857335f2f83866bf..43b54bef5448fa360c9ff21444b62fc678e80fd7 100644 (file)
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -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
index 502f8cd95f6d46cb6db5923ba877612f886d4a7a..d491fdcee61f025e37c0a3551c29b555ce5a2b87 100644 (file)
--- 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)
@@ -2566,7 +2565,6 @@ static void hv_crash_handler(struct pt_regs *regs)
        cpu = smp_processor_id();
        hv_stimer_cleanup(cpu);
        hv_synic_disable_regs(cpu);
-       hyperv_cleanup();
 };
 
 static int hv_synic_suspend(void)