X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fi386%2Fkernel%2Fnmi.c;h=c9dcd1f42788f1967e3a89f898c05a44184bce5e;hb=c7b5ebbddf7bcd3651947760f423e3783bbe6573;hp=16d91e3e138f884654d4a04c62e674919367dac9;hpb=a2c21200f1c81b08cb55e417b68150bba439b646;p=linux-2.6.git

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 16d91e3e1..c9dcd1f42 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -25,13 +25,17 @@
 #include <linux/module.h>
 #include <linux/nmi.h>
 #include <linux/sysdev.h>
+#include <linux/sysctl.h>
 
 #include <asm/smp.h>
 #include <asm/mtrr.h>
 #include <asm/mpspec.h>
 #include <asm/nmi.h>
 
+#include "mach_traps.h"
+
 unsigned int nmi_watchdog = NMI_NONE;
+extern int unknown_nmi_panic;
 static unsigned int nmi_hz = HZ;
 static unsigned int nmi_perfctr_msr;	/* the MSR to reset in NMI handler */
 static unsigned int nmi_p4_cccr_val;
@@ -376,7 +380,13 @@ static int setup_p4_watchdog(void)
 		clear_msr_range(0x3F1, 2);
 	/* MSR 0x3F0 seems to have a default value of 0xFC00, but current
 	   docs doesn't fully define it, so leave it alone for now. */
-	clear_msr_range(0x3A0, 31);
+	if (boot_cpu_data.x86_model >= 0x3) {
+		/* MSR_P4_IQ_ESCR0/1 (0x3ba/0x3bb) removed */
+		clear_msr_range(0x3A0, 26);
+		clear_msr_range(0x3BC, 3);
+	} else {
+		clear_msr_range(0x3A0, 31);
+	}
 	clear_msr_range(0x3C0, 6);
 	clear_msr_range(0x3C8, 6);
 	clear_msr_range(0x3E0, 2);
@@ -426,8 +436,6 @@ 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
@@ -459,6 +467,8 @@ void touch_nmi_watchdog (void)
 		alert_counter[i] = 0;
 }
 
+extern void die_nmi(struct pt_regs *, const char *msg);
+
 void nmi_watchdog_tick (struct pt_regs * regs)
 {
 
@@ -477,21 +487,8 @@ void nmi_watchdog_tick (struct pt_regs * regs)
 		 * wait a few IRQs (5 seconds) before doing the oops ...
 		 */
 		alert_counter[cpu]++;
-		if (alert_counter[cpu] == 5*nmi_hz) {
-			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, eip %08lx, registers:\n", cpu, regs->eip);
-			show_registers(regs);
-			printk("console shuts up ...\n");
-			console_silent();
-			spin_unlock(&nmi_print_lock);
-			bust_spinlocks(0);
-			do_exit(SIGSEGV);
-		}
+		if (alert_counter[cpu] == 5*nmi_hz)
+			die_nmi(regs, "NMI Watchdog detected LOCKUP");
 	} else {
 		last_irq_sums[cpu] = sum;
 		alert_counter[cpu] = 0;
@@ -518,6 +515,49 @@ void nmi_watchdog_tick (struct pt_regs * regs)
 	}
 }
 
+#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(regs, buf);
+	}
+	return 0;
+}
+
+/*
+ * proc handler for /proc/sys/kernel/unknown_nmi_panic
+ */
+int proc_unknown_nmi_panic(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);