Merge tag 'hyperv-fixes-signed-20210111' of...

Merge tag 'hyperv-fixes-signed-20210111' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv fixes from Wei Liu:

  - fix kexec panic/hang (Dexuan Cui)

  - fix occasional crashes when flushing TLB (Wei Liu)

* tag 'hyperv-fixes-signed-20210111' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  x86/hyperv: check cpu mask after interrupt has been disabled
  x86/hyperv: Fix kexec panic/hang issues

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:

arch/x86/hyperv/mmu.c

@@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (!hv_hypercall_pg)
 		goto do_native;
 
-	if (cpumask_empty(cpus))
-		return;
-
 	local_irq_save(flags);
 
+	/*
+	 * Only check the mask _after_ interrupt has been disabled to avoid the
+	 * mask changing under our feet.
+	 */
+	if (cpumask_empty(cpus)) {
+		local_irq_restore(flags);
+		return;
+	}
+
 	flush_pcpu = (struct hv_tlb_flush **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 

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;
 

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 */

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)