x86: Fix panic vs. NMI issues

index d05bd2e..c14b23f 100644
@@ -230,8 +230,8 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 	}
 #endif
 
-	if (panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
+	if (panic_on_unrecovered_nmi && spin_trylock(&panic_lock))
+		__panic("NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 

@@ -255,8 +255,12 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 		 reason, smp_processor_id());
 	show_regs(regs);
 
-	if (panic_on_io_nmi)
-		panic("NMI IOCK error: Not continuing");
+	if (panic_on_io_nmi) {
+		if (spin_trylock(&panic_lock))
+			__panic("NMI IOCK error: Not continuing");
+		else
+			return; /* We don't want to wait and re-enable NMI */
+	}
 
 	/* Re-enable the IOCK line, wait for a few seconds */
 	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;

@@ -296,8 +300,10 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 		 reason, smp_processor_id());
 
 	pr_emerg("Do you have a strange power saving mode enabled?\n");
-	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
+	if (unknown_nmi_panic || panic_on_unrecovered_nmi) {
+		if (spin_trylock(&panic_lock))
+			__panic("NMI: Not continuing");
+	}
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 }

index 5582410..be430dc 100644
@@ -250,11 +250,15 @@ static inline u32 reciprocal_scale(u32 val, u32 ep_ro)
 static inline void might_fault(void) { }
 #endif
 
+typedef struct spinlock spinlock_t;
+extern spinlock_t panic_lock;
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(int state);
 __printf(1, 2)
 void panic(const char *fmt, ...)
 	__noreturn __cold;
+void __panic(char *msg)
+	__noreturn __cold;
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);

index 04e91ff..3c8338b 100644
@@ -60,6 +60,8 @@ void __weak panic_smp_self_stop(void)
 		cpu_relax();
 }
 
+DEFINE_SPINLOCK(panic_lock);
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print

@@ -70,11 +72,8 @@ void __weak panic_smp_self_stop(void)
  */
 void panic(const char *fmt, ...)
 {
-	static DEFINE_SPINLOCK(panic_lock);
 	static char buf[1024];
 	va_list args;
-	long i, i_next = 0;
-	int state = 0;
 
 	/*
 	 * Disable local interrupts. This will prevent panic_smp_self_stop

@@ -97,12 +96,30 @@ void panic(const char *fmt, ...)
 	if (!spin_trylock(&panic_lock))
 		panic_smp_self_stop();
 
-	console_verbose();
-	bust_spinlocks(1);
 	va_start(args, fmt);
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
-	pr_emerg("Kernel panic - not syncing: %s\n", buf);
+
+	__panic(buf);
+}
+
+/**
+ *	__panic - no lock version of panic
+ *	@msg: The text string to print
+ *
+ *	Normally, please use panic().  This function can be used
+ *	only if panic_lock has already been held.
+ *
+ *	This function never returns.
+ */
+void __panic(char *msg)
+{
+	long i, i_next = 0;
+	int state = 0;
+
+	console_verbose();
+	bust_spinlocks(1);
+	pr_emerg("Kernel panic - not syncing: %s\n", msg);
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 	/*
 	 * Avoid nested stack-dumping if a panic occurs during oops processing

@@ -131,7 +148,7 @@ void panic(const char *fmt, ...)
 	 * Run any panic handlers, including those that might need to
 	 * add information to the kmsg dump output.
 	 */
-	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
+	atomic_notifier_call_chain(&panic_notifier_list, 0, msg);
 
 	kmsg_dump(KMSG_DUMP_PANIC);
 

@@ -190,7 +207,7 @@ void panic(const char *fmt, ...)
 		disabled_wait(caller);
 	}
 #endif
-	pr_emerg("---[ end Kernel panic - not syncing: %s\n", buf);
+	pr_emerg("---[ end Kernel panic - not syncing: %s\n", msg);
 	local_irq_enable();
 	for (i = 0; ; i += PANIC_TIMER_STEP) {
 		touch_softlockup_watchdog();

index e804306..bd6e477 100644
@@ -238,6 +238,7 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image,
 extern void *kexec_purgatory_get_symbol_addr(struct kimage *image,
 					     const char *name);
 extern void crash_kexec(struct pt_regs *);
+extern void __crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
 void crash_save_vmcoreinfo(void);

@@ -322,6 +323,7 @@ int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
 struct pt_regs;
 struct task_struct;
 static inline void crash_kexec(struct pt_regs *regs) { }
+static inline void __crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
 #endif /* CONFIG_KEXEC */
 

index a785c10..fcdd825 100644
@@ -1470,7 +1470,7 @@ void __weak crash_unmap_reserved_pages(void)
 
 #endif /* CONFIG_KEXEC_FILE */
 
-void crash_kexec(struct pt_regs *regs)
+void __crash_kexec(struct pt_regs *regs)
 {
 	/* Take the kexec_mutex here to prevent sys_kexec_load
 	 * running on one cpu from replacing the crash kernel

@@ -1493,6 +1493,16 @@ void crash_kexec(struct pt_regs *regs)
 	}
 }
 
+void crash_kexec(struct pt_regs *regs)
+{
+	unsigned long flags;
+
+	if (spin_trylock_irqsave(&panic_lock, flags)) {
+		__crash_kexec(regs);
+		spin_unlock_irqrestore(&panic_lock, flags);
+	}
+}
+
 size_t crash_get_memory_size(void)
 {
 	size_t size = 0;

index 3c8338b..ce5c8ab 100644
@@ -135,7 +135,7 @@ void __panic(char *msg)
 	 * the "crash_kexec_post_notifiers" option to the kernel.
 	 */
 	if (!crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which

@@ -160,7 +160,7 @@ void __panic(char *msg)
 	 * more unstable, it can increase risks of the kdump failure too.
 	 */
 	if (crash_kexec_post_notifiers)
-		crash_kexec(NULL);
+		__crash_kexec(NULL);
 
 	bust_spinlocks(0);
 

index dcb5285..a140410 100644
@@ -82,6 +82,12 @@
 static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID;
 
 /*
+ * Don't enable external NMI via LINT1 on BSP.  This is useful for
+ * the dump capture kernel.
+ */
+static bool apic_noextnmi;
+
+/*
  * Map cpu index to physical APIC ID
  */
 DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);

@@ -1150,6 +1156,8 @@ void __init init_bsp_APIC(void)
 	value = APIC_DM_NMI;
 	if (!lapic_is_integrated())		/* 82489DX */
 		value |= APIC_LVT_LEVEL_TRIGGER;
+	if (apic_noextnmi)
+		value |= APIC_LVT_MASKED;
 	apic_write(APIC_LVT1, value);
 }
 

@@ -1369,7 +1377,7 @@ void setup_local_APIC(void)
 	/*
 	 * only the BP should see the LINT1 NMI signal, obviously.
 	 */
-	if (!cpu)
+	if (!cpu && !apic_noextnmi)
 		value = APIC_DM_NMI;
 	else
 		value = APIC_DM_NMI | APIC_LVT_MASKED;

@@ -2537,3 +2545,10 @@ static int __init apic_set_disabled_cpu_apicid(char *arg)
 	return 0;
 }
 early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid);
+
+static int __init apic_set_noextnmi(char *arg)
+{
+	apic_noextnmi = true;
+	return 0;
+}
+early_param("noextnmi", apic_set_noextnmi);

index a785c1015e25..d61b1478167d 100644
@@ -1470,7 +1470,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 
 #endif /* CONFIG_KEXEC_FILE */
 
-void crash_kexec(struct pt_regs *regs)
+static bool try_crash_kexec(struct pt_regs *regs)
 {
 	/* Take the kexec_mutex here to prevent sys_kexec_load
 	 * running on one cpu from replacing the crash kernel

@@ -1490,7 +1490,20 @@ void crash_kexec(struct pt_regs *regs)
 			machine_kexec(kexec_crash_image);
 		}
 		mutex_unlock(&kexec_mutex);
+		return true;
 	}
+	return false;
+}
+
+void crash_kexec(struct pt_regs *regs)
+{
+	/*
+	 * Never return from this function if a kexec is in progress
+	 * already because next steps might interfere with it.
+	 * try_crash_kexec will never succeed in such a case.
+	 */
+	while (!try_crash_kexec(regs))
+		cpu_relax();
 }
 
 size_t crash_get_memory_size(void)