[PATCH] x86_64: add nmi button support

Ported from i386

Support a sysctl to raise an oops with an NMI
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/x86_64/kernel/nmi.c

@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/sysdev.h>
 #include <linux/nmi.h>
+#include <linux/sysctl.h>
 
 #include <asm/smp.h>
 #include <asm/mtrr.h>
@@ -54,7 +55,7 @@ static unsigned int lapic_nmi_owner;
  * -1: the lapic NMI watchdog is disabled, but can be enabled
  */
 int nmi_active;		/* oprofile uses this */
-static int panic_on_timeout;
+int panic_on_timeout;
 
 unsigned int nmi_watchdog = NMI_DEFAULT;
 static unsigned int nmi_hz = HZ;
@@ -344,8 +345,6 @@ void setup_apic_nmi_watchdog(void)
 	nmi_active = 1;
 }
 
-static spinlock_t nmi_print_lock = SPIN_LOCK_UNLOCKED;
-
 /*
  * the best way to detect whether a CPU has a 'hard lockup' problem
  * is to check it's local APIC timer IRQ counts. If they are not
@@ -395,21 +394,7 @@ void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
 				alert_counter[cpu] = 0; 
 				return;
 			} 
-			spin_lock(&nmi_print_lock);
-			/*
-			 * We are in trouble anyway, lets at least try
-			 * to get a message out.
-			 */
-			bust_spinlocks(1);
-			printk("NMI Watchdog detected LOCKUP on CPU%d, registers:\n", cpu);
-			show_registers(regs);
-			if (panic_on_timeout || panic_on_oops)
-				panic("nmi watchdog");
-			printk("console shuts up ...\n");
-			console_silent();
-			spin_unlock(&nmi_print_lock);
-			bust_spinlocks(0);
-			do_exit(SIGSEGV);
+			die_nmi("NMI Watchdog detected LOCKUP on CPU%d", regs);
 		}
 	} else {
 		last_irq_sums[cpu] = sum;
@@ -447,6 +432,49 @@ void unset_nmi_callback(void)
 	nmi_callback = dummy_nmi_callback;
 }
 
+#ifdef CONFIG_SYSCTL
+
+static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
+{
+	unsigned char reason = get_nmi_reason();
+	char buf[64];
+
+	if (!(reason & 0xc0)) {
+		sprintf(buf, "NMI received for unknown reason %02x\n", reason);
+		die_nmi(buf,regs);
+	}
+	return 0;
+}
+
+/*
+ * proc handler for /proc/sys/kernel/unknown_nmi_panic
+ */
+int proc_unknown_nmi_panic(struct ctl_table *table, int write, struct file *file,
+			void __user *buffer, size_t *length, loff_t *ppos)
+{
+	int old_state;
+
+	old_state = unknown_nmi_panic;
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	if (!!old_state == !!unknown_nmi_panic)
+		return 0;
+
+	if (unknown_nmi_panic) {
+		if (reserve_lapic_nmi() < 0) {
+			unknown_nmi_panic = 0;
+			return -EBUSY;
+		} else {
+			set_nmi_callback(unknown_nmi_panic_callback);
+		}
+	} else {
+		release_lapic_nmi();
+		unset_nmi_callback();
+	}
+	return 0;
+}
+
+#endif
+
 EXPORT_SYMBOL(nmi_active);
 EXPORT_SYMBOL(nmi_watchdog);
 EXPORT_SYMBOL(reserve_lapic_nmi);

arch/x86_64/kernel/traps.c

@@ -43,6 +43,7 @@
 #include <asm/pgalloc.h>
 #include <asm/pda.h>
 #include <asm/proto.h>
+#include <asm/nmi.h>
 
 #include <linux/irq.h>
 
@@ -376,6 +377,22 @@ static inline void die_if_kernel(const char * str, struct pt_regs * regs, long e
 		die(str, regs, err);
 }
 
+void die_nmi(char *str, struct pt_regs *regs)
+{
+	oops_begin();
+	/*
+	 * We are in trouble anyway, lets at least try
+	 * to get a message out.
+	 */
+	printk(str, safe_smp_processor_id());
+	show_registers(regs);
+	if (panic_on_timeout || panic_on_oops)
+		panic("nmi watchdog");
+	printk("console shuts up ...\n");
+	oops_end();
+	do_exit(SIGSEGV);
+}
+
 static inline unsigned long get_cr2(void)
 {
 	unsigned long address;
@@ -565,7 +582,7 @@ static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
 
 asmlinkage void default_do_nmi(struct pt_regs * regs)
 {
-	unsigned char reason = inb(0x61);
+	unsigned char reason = get_nmi_reason();
 
 	if (!(reason & 0xc0)) {
 		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT)
@@ -586,6 +603,9 @@ asmlinkage void default_do_nmi(struct pt_regs * regs)
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP)
 		return; 
+
+	/* AK: following checks seem to be broken on modern chipsets. FIXME */
+
 	if (reason & 0x80)
 		mem_parity_error(reason, regs);
 	if (reason & 0x40)

include/asm-x86_64/nmi.h

@@ -47,5 +47,11 @@ static inline void unset_nmi_pm_callback(struct pm_dev * dev)
 #endif /* CONFIG_PM */
  
 extern void default_do_nmi(struct pt_regs *);
+extern void die_nmi(char *str, struct pt_regs *regs);
+
+#define get_nmi_reason() inb(0x61)
+
+extern int panic_on_timeout;
+extern int unknown_nmi_panic;
  
 #endif /* ASM_NMI_H */

kernel/sysctl.c

@@ -68,7 +68,7 @@ extern int printk_ratelimit_jiffies;
 extern int printk_ratelimit_burst;
 extern int pid_max_min, pid_max_max;
 
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(__i386__)
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
 extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *,
 				  void __user *, size_t *, loff_t *);
@@ -614,7 +614,7 @@ static ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= &proc_dointvec,
 	},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(__i386__)
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 	{
 		.ctl_name       = KERN_UNKNOWN_NMI_PANIC,
 		.procname       = "unknown_nmi_panic",