x86_64: Update defconfig

Index: linux/arch/i386/mach-generic/probe.c
===================================================================
@@ -119,7 +119,9 @@ int __init acpi_madt_oem_check(char *oem
 	return 0;	
 }
 
+#ifdef CONFIG_SMP
 int hard_smp_processor_id(void)
 {
 	return genapic->get_apic_id(*(unsigned long *)(APIC_BASE+APIC_ID));
 }
+#endif

Index: linux/arch/i386/mach-generic/bigsmp.c
===================================================================
@@ -5,6 +5,7 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
+#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>

Index: linux/arch/i386/mach-generic/es7000.c
===================================================================
@@ -4,6 +4,7 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
+#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>

Index: linux/arch/i386/mach-generic/summit.c
===================================================================
@@ -4,6 +4,7 @@
 #define APIC_DEFINITION 1
 #include <linux/threads.h>
 #include <linux/cpumask.h>
+#include <asm/smp.h>
 #include <asm/mpspec.h>
 #include <asm/genapic.h>
 #include <asm/fixmap.h>

94 lines not on this page · raw message

Index: linux/include/asm-i386/mach-summit/mach_apic.h
===================================================================
@@ -46,10 +46,12 @@ extern u8 cpu_2_logical_apicid[];
 static inline void init_apic_ldr(void)
 {
 	unsigned long val, id;
-	int i, count;
-	u8 lid;
+	int count = 0;
 	u8 my_id = (u8)hard_smp_processor_id();
 	u8 my_cluster = (u8)apicid_cluster(my_id);
+#ifdef CONFIG_SMP
+	u8 lid;
+	int i;
 
 	/* Create logical APIC IDs by counting CPUs already in cluster. */
 	for (count = 0, i = NR_CPUS; --i >= 0; ) {

@@ -57,6 +59,7 @@ static inline void init_apic_ldr(void)
 		if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
 			++count;
 	}
+#endif
 	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
 	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
 	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);

@@ -91,9 +94,13 @@ static inline int apicid_to_node(int log
 /* Mapping from cpu number to logical apicid */
 static inline int cpu_to_logical_apicid(int cpu)
 {
+#ifdef CONFIG_SMP
        if (cpu >= NR_CPUS)
 	       return BAD_APICID;
 	return (int)cpu_2_logical_apicid[cpu];
+#else
+	return logical_smp_processor_id();
+#endif
 }
 
 static inline int cpu_present_to_apicid(int mps_cpu)

Index: linux/include/asm-i386/mach-es7000/mach_apic.h
===================================================================
@@ -123,9 +123,13 @@ extern u8 cpu_2_logical_apicid[];
 /* Mapping from cpu number to logical apicid */
 static inline int cpu_to_logical_apicid(int cpu)
 {
+#ifdef CONFIG_SMP
        if (cpu >= NR_CPUS)
 	       return BAD_APICID;
        return (int)cpu_2_logical_apicid[cpu];
+#else
+	return logical_smp_processor_id();
+#endif
 }
 
 static inline int mpc_apic_id(struct mpc_config_processor *m, struct mpc_config_translation *unused)

Index: linux/arch/i386/kernel/io_apic.c
===================================================================
@@ -40,6 +40,7 @@
 #include <asm/nmi.h>
 
 #include <mach_apic.h>
+#include <mach_apicdef.h>
 
 #include "io_ports.h"
 

Index: linux/arch/i386/kernel/mpparse.c
===================================================================
@@ -30,6 +30,7 @@
 #include <asm/io_apic.h>
 
 #include <mach_apic.h>
+#include <mach_apicdef.h>
 #include <mach_mpparse.h>
 #include <bios_ebda.h>
 

Index: linux/include/asm-i386/smp.h
===================================================================
@@ -80,17 +80,11 @@ static inline int hard_smp_processor_id(
 	return GET_APIC_ID(*(unsigned long *)(APIC_BASE+APIC_ID));
 }
 #endif
-
-static __inline int logical_smp_processor_id(void)
-{
-	/* we don't want to mark this access volatile - bad code generation */
-	return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
-}
-
 #endif
 
 extern int __cpu_disable(void);
 extern void __cpu_die(unsigned int cpu);
+
 #endif /* !__ASSEMBLY__ */
 
 #else /* CONFIG_SMP */

@@ -100,4 +94,15 @@ extern void __cpu_die(unsigned int cpu);
 #define NO_PROC_ID		0xFF		/* No processor magic marker */
 
 #endif
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_LOCAL_APIC
+static __inline int logical_smp_processor_id(void)
+{
+	/* we don't want to mark this access volatile - bad code generation */
+	return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
+}
+#endif
+#endif
+
 #endif

Index: linux/arch/i386/kernel/nmi.c
===================================================================
@@ -24,7 +24,6 @@
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
-#include <asm/intel_arch_perfmon.h>
 
 #include "mach_traps.h"
 

@@ -96,9 +95,6 @@ int nmi_active;
 	(P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT|	\
 	 P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE)
 
-#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
-#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
-
 #ifdef CONFIG_SMP
 /* The performance counters used by NMI_LOCAL_APIC don't trigger when
  * the CPU is idle. To make sure the NMI watchdog really ticks on all

@@ -211,8 +207,6 @@ static int __init setup_nmi_watchdog(cha
 
 __setup("nmi_watchdog=", setup_nmi_watchdog);
 
-static void disable_intel_arch_watchdog(void);
-
 static void disable_lapic_nmi_watchdog(void)
 {
 	if (nmi_active <= 0)

@@ -222,10 +216,6 @@ static void disable_lapic_nmi_watchdog(v
 		wrmsr(MSR_K7_EVNTSEL0, 0, 0);
 		break;
 	case X86_VENDOR_INTEL:
-		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-			disable_intel_arch_watchdog();
-			break;
-		}
 		switch (boot_cpu_data.x86) {
 		case 6:
 			if (boot_cpu_data.x86_model > 0xd)

@@ -454,53 +444,6 @@ static int setup_p4_watchdog(void)
 	return 1;
 }
 
-static void disable_intel_arch_watchdog(void)
-{
-	unsigned ebx;
-
-	/*
-	 * Check whether the Architectural PerfMon supports
-	 * Unhalted Core Cycles Event or not.
-	 * NOTE: Corresponding bit = 0 in ebp indicates event present.
-	 */
-	ebx = cpuid_ebx(10);
-	if (!(ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
-		wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, 0, 0);
-}
-
-static int setup_intel_arch_watchdog(void)
-{
-	unsigned int evntsel;
-	unsigned ebx;
-
-	/*
-	 * Check whether the Architectural PerfMon supports
-	 * Unhalted Core Cycles Event or not.
-	 * NOTE: Corresponding bit = 0 in ebp indicates event present.
-	 */
-	ebx = cpuid_ebx(10);
-	if ((ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
-		return 0;
-
-	nmi_perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
-
-	clear_msr_range(MSR_ARCH_PERFMON_EVENTSEL0, 2);
-	clear_msr_range(MSR_ARCH_PERFMON_PERFCTR0, 2);
-
-	evntsel = ARCH_PERFMON_EVENTSEL_INT
-		| ARCH_PERFMON_EVENTSEL_OS
-		| ARCH_PERFMON_EVENTSEL_USR
-		| ARCH_PERFMON_NMI_EVENT_SEL
-		| ARCH_PERFMON_NMI_EVENT_UMASK;
-
-	wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0);
-	write_watchdog_counter("INTEL_ARCH_PERFCTR0");
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
-	wrmsr(MSR_ARCH_PERFMON_EVENTSEL0, evntsel, 0);
-	return 1;
-}
-
 void setup_apic_nmi_watchdog (void)
 {
 	switch (boot_cpu_data.x86_vendor) {

@@ -510,11 +453,6 @@ void setup_apic_nmi_watchdog (void)
 		setup_k7_watchdog();
 		break;
 	case X86_VENDOR_INTEL:
-		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-			if (!setup_intel_arch_watchdog())
-				return;
-			break;
-		}
 		switch (boot_cpu_data.x86) {
 		case 6:
 			if (boot_cpu_data.x86_model > 0xd)

@@ -619,8 +557,7 @@ void nmi_watchdog_tick (struct pt_regs *
 			wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0);
 			apic_write(APIC_LVTPC, APIC_DM_NMI);
 		}
-		else if (nmi_perfctr_msr == MSR_P6_PERFCTR0 ||
-		         nmi_perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
+		else if (nmi_perfctr_msr == MSR_P6_PERFCTR0) {
 			/* Only P6 based Pentium M need to re-unmask
 			 * the apic vector but it doesn't hurt
 			 * other P6 variant */

130 lines not on this page · raw message

Index: linux/include/asm-i386/intel_arch_perfmon.h
===================================================================
@@ -1,19 +0,0 @@
-#ifndef X86_INTEL_ARCH_PERFMON_H
-#define X86_INTEL_ARCH_PERFMON_H 1
-
-#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE      (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT          (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS           (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR          (1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT (1 << 0)
-
-#endif	/* X86_INTEL_ARCH_PERFMON_H */

Index: linux/include/asm-x86_64/intel_arch_perfmon.h
===================================================================
@@ -1,19 +0,0 @@
-#ifndef X86_64_INTEL_ARCH_PERFMON_H
-#define X86_64_INTEL_ARCH_PERFMON_H 1
-
-#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE      (1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT          (1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS           (1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR          (1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT (1 << 0)
-
-#endif	/* X86_64_INTEL_ARCH_PERFMON_H */

Index: linux/arch/x86_64/kernel/nmi.c
===================================================================
@@ -27,6 +27,20 @@
 #include <asm/kdebug.h>
 #include <asm/mce.h>
 
+/* perfctr_nmi_owner tracks the ownership of the perfctr registers:
+ * evtsel_nmi_owner tracks the ownership of the event selection
+ * - different performance counters/ event selection may be reserved for
+ *   different subsystems this reservation system just tries to coordinate
+ *   things a little
+ */
+static DEFINE_PER_CPU(unsigned, perfctr_nmi_owner);
+static DEFINE_PER_CPU(unsigned, evntsel_nmi_owner[2]);
+
+/* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
+ * offset from MSR_P4_BSU_ESCR0.  It will be the max for all platforms (for now)
+ */
+#define NMI_MAX_COUNTER_BITS 66
+
 /*
  * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
  * - it may be reserved by some other driver, or not

@@ -90,6 +104,95 @@ static unsigned int nmi_p4_cccr_val;
 	(P4_CCCR_OVF_PMI0|P4_CCCR_THRESHOLD(15)|P4_CCCR_COMPLEMENT|	\
 	 P4_CCCR_COMPARE|P4_CCCR_REQUIRED|P4_CCCR_ESCR_SELECT(4)|P4_CCCR_ENABLE)
 
+/* converts an msr to an appropriate reservation bit */
+static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
+{
+	/* returns the bit offset of the performance counter register */
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		return (msr - MSR_K7_PERFCTR0);
+	case X86_VENDOR_INTEL:
+		return (msr - MSR_P4_BPU_PERFCTR0);
+	}
+	return 0;
+}
+
+/* converts an msr to an appropriate reservation bit */
+static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
+{
+	/* returns the bit offset of the event selection register */
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+		return (msr - MSR_K7_EVNTSEL0);
+	case X86_VENDOR_INTEL:
+		return (msr - MSR_P4_BSU_ESCR0);
+	}
+	return 0;
+}
+
+/* checks for a bit availability (hack for oprofile) */
+int avail_to_resrv_perfctr_nmi_bit(unsigned int counter)
+{
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
+}
+
+/* checks the an msr for availability */
+int avail_to_resrv_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	return (!test_bit(counter, &__get_cpu_var(perfctr_nmi_owner)));
+}
+
+int reserve_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	if (!test_and_set_bit(counter, &__get_cpu_var(perfctr_nmi_owner)))
+		return 1;
+	return 0;
+}
+
+void release_perfctr_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_perfctr_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	clear_bit(counter, &__get_cpu_var(perfctr_nmi_owner));
+}
+
+int reserve_evntsel_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_evntsel_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	if (!test_and_set_bit(counter, &__get_cpu_var(evntsel_nmi_owner)))
+		return 1;
+	return 0;
+}
+
+void release_evntsel_nmi(unsigned int msr)
+{
+	unsigned int counter;
+
+	counter = nmi_evntsel_msr_to_bit(msr);
+	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+
+	clear_bit(counter, &__get_cpu_var(evntsel_nmi_owner));
+}
+
 static __cpuinit inline int nmi_known_cpu(void)
 {
 	switch (boot_cpu_data.x86_vendor) {

@@ -325,34 +428,22 @@ late_initcall(init_lapic_nmi_sysfs);
 
 #endif	/* CONFIG_PM */
 
-/*
- * Activate the NMI watchdog via the local APIC.
- * Original code written by Keith Owens.
- */
-
-static void clear_msr_range(unsigned int base, unsigned int n)
+static int setup_k7_watchdog(void)
 {
-	unsigned int i;
-
-	for(i = 0; i < n; ++i)
-		wrmsr(base+i, 0, 0);
-}
-
-static void setup_k7_watchdog(void)
-{
-	int i;
 	unsigned int evntsel;
 
 	nmi_perfctr_msr = MSR_K7_PERFCTR0;
 
-	for(i = 0; i < 4; ++i) {
-		/* Simulator may not support it */
-		if (checking_wrmsrl(MSR_K7_EVNTSEL0+i, 0UL)) {
-			nmi_perfctr_msr = 0;
-			return;
-		}
-		wrmsrl(MSR_K7_PERFCTR0+i, 0UL);
-	}
+	if (!reserve_perfctr_nmi(nmi_perfctr_msr))
+		goto fail;
+
+	if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0))
+		goto fail1;
+
+	/* Simulator may not support it */
+	if (checking_wrmsrl(MSR_K7_EVNTSEL0, 0UL))
+		goto fail2;
+	wrmsrl(MSR_K7_PERFCTR0, 0UL);
 
 	evntsel = K7_EVNTSEL_INT
 		| K7_EVNTSEL_OS

@@ -364,6 +455,13 @@ static void setup_k7_watchdog(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	evntsel |= K7_EVNTSEL_ENABLE;
 	wrmsr(MSR_K7_EVNTSEL0, evntsel, 0);
+	return 1;
+fail2:
+	release_evntsel_nmi(MSR_K7_EVNTSEL0);
+fail1:
+	release_perfctr_nmi(nmi_perfctr_msr);
+fail:
+	return 0;
 }
 
 

@@ -382,22 +480,11 @@ static int setup_p4_watchdog(void)
 		nmi_p4_cccr_val |= P4_CCCR_OVF_PMI1;
 #endif
 
-	if (!(misc_enable & MSR_P4_MISC_ENABLE_PEBS_UNAVAIL))
-		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. */
-	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);
-	clear_msr_range(MSR_P4_CCCR0, 18);
-	clear_msr_range(MSR_P4_PERFCTR0, 18);
+	if (!reserve_perfctr_nmi(nmi_perfctr_msr))
+		goto fail;
+
+	if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0))
+		goto fail1;
 
 	wrmsr(MSR_P4_CRU_ESCR0, P4_NMI_CRU_ESCR0, 0);
 	wrmsr(MSR_P4_IQ_CCCR0, P4_NMI_IQ_CCCR0 & ~P4_CCCR_ENABLE, 0);

@@ -406,6 +493,10 @@ static int setup_p4_watchdog(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	wrmsr(MSR_P4_IQ_CCCR0, nmi_p4_cccr_val, 0);
 	return 1;
+fail1:
+	release_perfctr_nmi(nmi_perfctr_msr);
+fail:
+	return 0;
 }
 
 void setup_apic_nmi_watchdog(void)

@@ -416,7 +507,8 @@ void setup_apic_nmi_watchdog(void)
 			return;
 		if (strstr(boot_cpu_data.x86_model_id, "Screwdriver"))
 			return;
-		setup_k7_watchdog();
+		if (!setup_k7_watchdog())
+			return;
 		break;
 	case X86_VENDOR_INTEL:
 		if (boot_cpu_data.x86 != 15)

@@ -588,6 +680,12 @@ int proc_unknown_nmi_panic(struct ctl_ta
 
 EXPORT_SYMBOL(nmi_active);
 EXPORT_SYMBOL(nmi_watchdog);
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi);
+EXPORT_SYMBOL(avail_to_resrv_perfctr_nmi_bit);
+EXPORT_SYMBOL(reserve_perfctr_nmi);
+EXPORT_SYMBOL(release_perfctr_nmi);
+EXPORT_SYMBOL(reserve_evntsel_nmi);
+EXPORT_SYMBOL(release_evntsel_nmi);
 EXPORT_SYMBOL(reserve_lapic_nmi);
 EXPORT_SYMBOL(release_lapic_nmi);
 EXPORT_SYMBOL(disable_timer_nmi_watchdog);

Index: linux/include/asm-x86_64/nmi.h
===================================================================
@@ -56,7 +56,13 @@ extern int panic_on_timeout;
 extern int unknown_nmi_panic;
 
 extern int check_nmi_watchdog(void);
- 
+extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
+extern int avail_to_resrv_perfctr_nmi(unsigned int);
+extern int reserve_perfctr_nmi(unsigned int);
+extern void release_perfctr_nmi(unsigned int);
+extern int reserve_evntsel_nmi(unsigned int);
+extern void release_evntsel_nmi(unsigned int);
+
 extern void setup_apic_nmi_watchdog (void);
 extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);

266 lines not on this page · raw message

Index: linux/include/asm-i386/nmi.h
===================================================================
@@ -25,6 +25,13 @@ void set_nmi_callback(nmi_callback_t cal
  */
 void unset_nmi_callback(void);
 
+extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
+extern int avail_to_resrv_perfctr_nmi(unsigned int);
+extern int reserve_perfctr_nmi(unsigned int);
+extern void release_perfctr_nmi(unsigned int);
+extern int reserve_evntsel_nmi(unsigned int);
+extern void release_evntsel_nmi(unsigned int);
+
 extern void setup_apic_nmi_watchdog (void);
 extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);

Index: linux/arch/i386/oprofile/nmi_int.c
===================================================================
@@ -98,15 +98,19 @@ static void nmi_cpu_save_registers(struc
 	unsigned int i;
 
 	for (i = 0; i < nr_ctrs; ++i) {
-		rdmsr(counters[i].addr,
-			counters[i].saved.low,
-			counters[i].saved.high);
+		if (counters[i].addr){
+			rdmsr(counters[i].addr,
+				counters[i].saved.low,
+				counters[i].saved.high);
+		}
 	}
  
 	for (i = 0; i < nr_ctrls; ++i) {
-		rdmsr(controls[i].addr,
-			controls[i].saved.low,
-			controls[i].saved.high);
+		if (controls[i].addr){
+			rdmsr(controls[i].addr,
+				controls[i].saved.low,
+				controls[i].saved.high);
+		}
 	}
 }
 

@@ -205,15 +209,19 @@ static void nmi_restore_registers(struct
 	unsigned int i;
 
 	for (i = 0; i < nr_ctrls; ++i) {
-		wrmsr(controls[i].addr,
-			controls[i].saved.low,
-			controls[i].saved.high);
+		if (controls[i].addr){
+			wrmsr(controls[i].addr,
+				controls[i].saved.low,
+				controls[i].saved.high);
+		}
 	}
  
 	for (i = 0; i < nr_ctrs; ++i) {
-		wrmsr(counters[i].addr,
-			counters[i].saved.low,
-			counters[i].saved.high);
+		if (counters[i].addr){
+			wrmsr(counters[i].addr,
+				counters[i].saved.low,
+				counters[i].saved.high);
+		}
 	}
 }
  

@@ -234,6 +242,7 @@ static void nmi_cpu_shutdown(void * dumm
 	apic_write(APIC_LVTPC, saved_lvtpc[cpu]);
 	apic_write(APIC_LVTERR, v);
 	nmi_restore_registers(msrs);
+	model->shutdown(msrs);
 }
 
  

@@ -284,6 +293,14 @@ static int nmi_create_files(struct super
 		struct dentry * dir;
 		char buf[4];
  
+ 		/* quick little hack to _not_ expose a counter if it is not
+		 * available for use.  This should protect userspace app.
+		 * NOTE:  assumes 1:1 mapping here (that counters are organized
+		 *        sequentially in their struct assignment).
+		 */
+		if (unlikely(!avail_to_resrv_perfctr_nmi_bit(i)))
+			continue;
+
 		snprintf(buf,  sizeof(buf), "%d", i);
 		dir = oprofilefs_mkdir(sb, root, buf);
 		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled); 

109 lines not on this page · raw message

276 lines not on this page · raw message

127 lines not on this page · raw message

Index: linux/arch/i386/oprofile/op_x86_model.h
===================================================================
@@ -40,6 +40,7 @@ struct op_x86_model_spec {
 		struct op_msrs const * const msrs);
 	void (*start)(struct op_msrs const * const msrs);
 	void (*stop)(struct op_msrs const * const msrs);
+	void (*shutdown)(struct op_msrs const * const msrs);
 };
 
 extern struct op_x86_model_spec const op_ppro_spec;

Index: linux/arch/x86_64/kernel/apic.c
===================================================================
@@ -479,8 +479,7 @@ void __cpuinit setup_local_APIC (void)
 	}
 
 	nmi_watchdog_default();
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		setup_apic_nmi_watchdog();
+	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
 }
 

596 lines not on this page · raw message

Index: linux/include/asm-x86_64/nmi.h
===================================================================
@@ -63,7 +63,7 @@ extern void release_perfctr_nmi(unsigned
 extern int reserve_evntsel_nmi(unsigned int);
 extern void release_evntsel_nmi(unsigned int);
 
-extern void setup_apic_nmi_watchdog (void);
+extern void setup_apic_nmi_watchdog (void *);
 extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);

@@ -73,6 +73,7 @@ extern void nmi_watchdog_tick (struct pt
 extern void nmi_watchdog_default(void);
 extern int setup_nmi_watchdog(char *);
 
+extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
 #define NMI_DEFAULT	-1
 #define NMI_NONE	0

Index: linux/arch/i386/kernel/apic.c
===================================================================
@@ -586,8 +586,7 @@ void __devinit setup_local_APIC(void)
 			printk("No ESR for 82489DX.\n");
 	}
 
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		setup_apic_nmi_watchdog();
+	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
 }
 

745 lines not on this page · raw message

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -721,7 +721,7 @@ static void default_do_nmi(struct pt_reg
 		 * so it must be the NMI watchdog.
 		 */
 		if (nmi_watchdog) {
-			nmi_watchdog_tick(regs);
+			nmi_watchdog_tick(regs, reason);
 			return;
 		}
 #endif

Index: linux/include/asm-i386/nmi.h
===================================================================
@@ -32,13 +32,14 @@ extern void release_perfctr_nmi(unsigned
 extern int reserve_evntsel_nmi(unsigned int);
 extern void release_evntsel_nmi(unsigned int);
 
-extern void setup_apic_nmi_watchdog (void);
+extern void setup_apic_nmi_watchdog (void *);
 extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
-extern void nmi_watchdog_tick (struct pt_regs * regs);
+extern void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
 
+extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
 #define NMI_DEFAULT     -1
 #define NMI_NONE	0

Index: linux/arch/i386/oprofile/nmi_timer_int.c
===================================================================
@@ -42,9 +42,7 @@ static void timer_stop(void)
 
 int __init op_nmi_timer_init(struct oprofile_operations * ops)
 {
-	extern int nmi_active;
-
-	if (nmi_active <= 0)
+	if (atomic_read(&nmi_active) <= 0)
 		return -ENODEV;
 
 	ops->start = timer_start;

Index: linux/arch/i386/kernel/nmi.c
===================================================================
@@ -781,7 +781,7 @@ EXPORT_SYMBOL(touch_nmi_watchdog);
 
 extern void die_nmi(struct pt_regs *, const char *msg);
 
-void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
+int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
 {
 
 	/*

@@ -794,10 +794,12 @@ void nmi_watchdog_tick (struct pt_regs *
 	int cpu = smp_processor_id();
 	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 	u64 dummy;
+	int rc=0;
 
 	/* check for other users first */
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
 			== NOTIFY_STOP) {
+		rc = 1;
 		touched = 1;
 	}
 

@@ -850,10 +852,18 @@ void nmi_watchdog_tick (struct pt_regs *
 			}
 			/* start the cycle over again */
 			write_watchdog_counter(wd->perfctr_msr, NULL);
-		}
+			rc = 1;
+		} else if (nmi_watchdog == NMI_IO_APIC) {
+			/* don't know how to accurately check for this.
+			 * just assume it was a watchdog timer interrupt
+			 * This matches the old behaviour.
+			 */
+			rc = 1;
+		} else
+			printk(KERN_WARNING "Unknown enabled NMI hardware?!\n");
 	}
 done:
-	return;
+	return rc;
 }
 
 #ifdef CONFIG_SYSCTL

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -703,6 +703,13 @@ void die_nmi (struct pt_regs *regs, cons
 	do_exit(SIGSEGV);
 }
 
+static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
+{
+	return 0;
+}
+
+static nmi_callback_t nmi_callback = dummy_nmi_callback;
+
 static void default_do_nmi(struct pt_regs * regs)
 {
 	unsigned char reason = 0;

@@ -720,12 +727,11 @@ static void default_do_nmi(struct pt_reg
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
 		 */
-		if (nmi_watchdog) {
-			nmi_watchdog_tick(regs, reason);
+		if (nmi_watchdog_tick(regs, reason))
 			return;
-		}
 #endif
-		unknown_nmi_error(reason, regs);
+		if (!rcu_dereference(nmi_callback)(regs, smp_processor_id()))
+			unknown_nmi_error(reason, regs);
 		return;
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)

@@ -741,13 +747,6 @@ static void default_do_nmi(struct pt_reg
 	reassert_nmi();
 }
 
-static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
-{
-	return 0;
-}
- 
-static nmi_callback_t nmi_callback = dummy_nmi_callback;
- 
 fastcall void do_nmi(struct pt_regs * regs, long error_code)
 {
 	int cpu;

@@ -758,8 +757,7 @@ fastcall void do_nmi(struct pt_regs * re
 
 	++nmi_count(cpu);
 
-	if (!rcu_dereference(nmi_callback)(regs, cpu))
-		default_do_nmi(regs);
+	default_do_nmi(regs);
 
 	nmi_exit();
 }

Index: linux/arch/x86_64/kernel/nmi.c
===================================================================
@@ -682,16 +682,18 @@ void touch_nmi_watchdog (void)
  	touch_softlockup_watchdog();
 }
 
-void __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
+int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 {
 	int sum;
 	int touched = 0;
 	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 	u64 dummy;
+	int rc=0;
 
 	/* check for other users first */
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
 			== NOTIFY_STOP) {
+		rc = 1;
 		touched = 1;
 	}
 

@@ -746,10 +748,18 @@ void __kprobes nmi_watchdog_tick(struct 
 	 		}
 			/* start the cycle over again */
 			wrmsrl(wd->perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
-		}
+			rc = 1;
+		} else 	if (nmi_watchdog == NMI_IO_APIC) {
+			/* don't know how to accurately check for this.
+			 * just assume it was a watchdog timer interrupt
+			 * This matches the old behaviour.
+			 */
+			rc = 1;
+		} else
+			printk(KERN_WARNING "Unknown enabled NMI hardware?!\n");
 	}
 done:
-	return;
+	return rc;
 }
 
 static __kprobes int dummy_nmi_callback(struct pt_regs * regs, int cpu)

@@ -761,15 +771,17 @@ static nmi_callback_t nmi_callback = dum
  
 asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code)
 {
-	int cpu = safe_smp_processor_id();
-
 	nmi_enter();
 	add_pda(__nmi_count,1);
-	if (!rcu_dereference(nmi_callback)(regs, cpu))
-		default_do_nmi(regs);
+	default_do_nmi(regs);
 	nmi_exit();
 }
 
+int do_nmi_callback(struct pt_regs * regs, int cpu)
+{
+	return rcu_dereference(nmi_callback)(regs, cpu);
+}
+
 void set_nmi_callback(nmi_callback_t callback)
 {
 	vmalloc_sync_all();

Index: linux/arch/x86_64/kernel/traps.c
===================================================================
@@ -777,12 +777,12 @@ asmlinkage __kprobes void default_do_nmi
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
 		 */
-		if (nmi_watchdog > 0) {
-			nmi_watchdog_tick(regs,reason);
+		if (nmi_watchdog_tick(regs,reason))
 			return;
-		}
+		if (!do_nmi_callback(regs,cpu))
 #endif
-		unknown_nmi_error(reason, regs);
+			unknown_nmi_error(reason, regs);
+
 		return;
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)

Index: linux/include/asm-i386/nmi.h
===================================================================
@@ -37,7 +37,7 @@ extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
-extern void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
+extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
 
 extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;

Index: linux/include/asm-x86_64/nmi.h
===================================================================
@@ -26,6 +26,14 @@ void set_nmi_callback(nmi_callback_t cal
  */
 void unset_nmi_callback(void);
 
+/**
+ * do_nmi_callback
+ *
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
+ */
+int do_nmi_callback(struct pt_regs *regs, int cpu);
+
 #ifdef CONFIG_PM
  
 /** Replace the PM callback routine for NMI. */

@@ -68,7 +76,7 @@ extern int reserve_lapic_nmi(void);
 extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
-extern void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
+extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
 
 extern void nmi_watchdog_default(void);
 extern int setup_nmi_watchdog(char *);

Index: linux/arch/x86_64/ia32/ia32_signal.c
===================================================================
@@ -113,25 +113,19 @@ int copy_siginfo_from_user32(siginfo_t *
 }
 
 asmlinkage long
-sys32_sigsuspend(int history0, int history1, old_sigset_t mask,
-		 struct pt_regs *regs)
+sys32_sigsuspend(int history0, int history1, old_sigset_t mask)
 {
-	sigset_t saveset;
-
 	mask &= _BLOCKABLE;
 	spin_lock_irq(&current->sighand->siglock);
-	saveset = current->blocked;
+	current->saved_sigmask = current->blocked;
 	siginitset(&current->blocked, mask);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	regs->rax = -EINTR;
-	while (1) {
-		current->state = TASK_INTERRUPTIBLE;
-		schedule();
-		if (do_signal(regs, &saveset))
-			return -EINTR;
-	}
+	current->state = TASK_INTERRUPTIBLE;
+	schedule();
+	set_thread_flag(TIF_RESTORE_SIGMASK);
+	return -ERESTARTNOHAND;
 }
 
 asmlinkage long

@@ -508,11 +502,11 @@ int ia32_setup_frame(int sig, struct k_s
 		current->comm, current->pid, frame, regs->rip, frame->pretcode);
 #endif
 
-	return 1;
+	return 0;
 
 give_sigsegv:
 	force_sigsegv(sig, current);
-	return 0;
+	return -EFAULT;
 }
 
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,

@@ -595,7 +589,7 @@ int ia32_setup_rt_frame(int sig, struct 
 	regs->ss = __USER32_DS; 
 
 	set_fs(USER_DS);
-    regs->eflags &= ~TF_MASK;
+	regs->eflags &= ~TF_MASK;
     if (test_thread_flag(TIF_SINGLESTEP))
         ptrace_notify(SIGTRAP);
 

@@ -604,9 +598,9 @@ int ia32_setup_rt_frame(int sig, struct 
 		current->comm, current->pid, frame, regs->rip, frame->pretcode);
 #endif
 
-	return 1;
+	return 0;
 
 give_sigsegv:
 	force_sigsegv(sig, current);
-	return 0;
+	return -EFAULT;
 }

148 lines not on this page · raw message

Index: linux/include/asm-x86_64/signal.h
===================================================================
@@ -24,10 +24,6 @@ typedef struct {
 } sigset_t;
 
 
-struct pt_regs; 
-asmlinkage int do_signal(struct pt_regs *regs, sigset_t *oldset);
-
-
 #else
 /* Here we must cater to libcs that poke about in kernel headers.  */
 

Index: linux/include/asm-x86_64/thread_info.h
===================================================================
@@ -114,6 +114,7 @@ static inline struct thread_info *stack_
 #define TIF_IRET		5	/* force IRET */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
+#define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal */
 /* 16 free */
 #define TIF_IA32		17	/* 32bit process */ 
 #define TIF_FORK		18	/* ret_from_fork */

@@ -128,6 +129,7 @@ static inline struct thread_info *stack_
 #define _TIF_IRET		(1<<TIF_IRET)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
+#define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_IA32		(1<<TIF_IA32)
 #define _TIF_FORK		(1<<TIF_FORK)
 #define _TIF_ABI_PENDING	(1<<TIF_ABI_PENDING)

Index: linux/include/asm-x86_64/unistd.h
===================================================================
@@ -658,6 +658,7 @@ do { \
 #define __ARCH_WANT_SYS_SIGPENDING
 #define __ARCH_WANT_SYS_SIGPROCMASK
 #define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_SYS_TIME
 #define __ARCH_WANT_COMPAT_SYS_TIME
 

Index: linux/include/asm-x86_64/unistd.h
===================================================================
@@ -600,9 +600,9 @@ __SYSCALL(__NR_fchmodat, sys_fchmodat)
 #define __NR_faccessat		269
 __SYSCALL(__NR_faccessat, sys_faccessat)
 #define __NR_pselect6		270
-__SYSCALL(__NR_pselect6, sys_ni_syscall)	/* for now */
+__SYSCALL(__NR_pselect6, sys_pselect6)
 #define __NR_ppoll		271
-__SYSCALL(__NR_ppoll,	sys_ni_syscall)		/* for now */
+__SYSCALL(__NR_ppoll,	sys_ppoll)
 #define __NR_unshare		272
 __SYSCALL(__NR_unshare,	sys_unshare)
 #define __NR_set_robust_list	273

Index: linux/arch/x86_64/kernel/nmi.c
===================================================================
@@ -41,20 +41,6 @@ static DEFINE_PER_CPU(unsigned, evntsel_
  */
 #define NMI_MAX_COUNTER_BITS 66
 
-/*
- * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
- * - it may be reserved by some other driver, or not
- * - when not reserved by some other driver, it may be used for
- *   the NMI watchdog, or not
- *
- * This is maintained separately from nmi_active because the NMI
- * watchdog may also be driven from the I/O APIC timer.
- */
-static DEFINE_SPINLOCK(lapic_nmi_owner_lock);
-static unsigned int lapic_nmi_owner;
-#define LAPIC_NMI_WATCHDOG	(1<<0)
-#define LAPIC_NMI_RESERVED	(1<<1)
-
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
  * <0: the lapic NMI watchdog has not been set up, and cannot

@@ -321,33 +307,6 @@ static void enable_lapic_nmi_watchdog(vo
 	touch_nmi_watchdog();
 }
 
-int reserve_lapic_nmi(void)
-{
-	unsigned int old_owner;
-
-	spin_lock(&lapic_nmi_owner_lock);
-	old_owner = lapic_nmi_owner;
-	lapic_nmi_owner |= LAPIC_NMI_RESERVED;
-	spin_unlock(&lapic_nmi_owner_lock);
-	if (old_owner & LAPIC_NMI_RESERVED)
-		return -EBUSY;
-	if (old_owner & LAPIC_NMI_WATCHDOG)
-		disable_lapic_nmi_watchdog();
-	return 0;
-}
-
-void release_lapic_nmi(void)
-{
-	unsigned int new_owner;
-
-	spin_lock(&lapic_nmi_owner_lock);
-	new_owner = lapic_nmi_owner & ~LAPIC_NMI_RESERVED;
-	lapic_nmi_owner = new_owner;
-	spin_unlock(&lapic_nmi_owner_lock);
-	if (new_owner & LAPIC_NMI_WATCHDOG)
-		enable_lapic_nmi_watchdog();
-}
-
 void disable_timer_nmi_watchdog(void)
 {
 	BUG_ON(nmi_watchdog != NMI_IO_APIC);

@@ -762,13 +721,6 @@ done:
 	return rc;
 }
 
-static __kprobes int dummy_nmi_callback(struct pt_regs * regs, int cpu)
-{
-	return 0;
-}
- 
-static nmi_callback_t nmi_callback = dummy_nmi_callback;
- 
 asmlinkage __kprobes void do_nmi(struct pt_regs * regs, long error_code)
 {
 	nmi_enter();

@@ -779,21 +731,12 @@ asmlinkage __kprobes void do_nmi(struct 
 
 int do_nmi_callback(struct pt_regs * regs, int cpu)
 {
-	return rcu_dereference(nmi_callback)(regs, cpu);
-}
-
-void set_nmi_callback(nmi_callback_t callback)
-{
-	vmalloc_sync_all();
-	rcu_assign_pointer(nmi_callback, callback);
-}
-EXPORT_SYMBOL_GPL(set_nmi_callback);
-
-void unset_nmi_callback(void)
-{
-	nmi_callback = dummy_nmi_callback;
+#ifdef CONFIG_SYSCTL
+	if (unknown_nmi_panic)
+		return unknown_nmi_panic_callback(regs, cpu);
+#endif
+	return 0;
 }
-EXPORT_SYMBOL_GPL(unset_nmi_callback);
 
 #ifdef CONFIG_SYSCTL
 

@@ -802,37 +745,8 @@ static int unknown_nmi_panic_callback(st
 	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();
-	}
+	sprintf(buf, "NMI received for unknown reason %02x\n", reason);
+	die_nmi(buf,regs);
 	return 0;
 }
 

@@ -846,8 +760,6 @@ EXPORT_SYMBOL(reserve_perfctr_nmi);
 EXPORT_SYMBOL(release_perfctr_nmi);
 EXPORT_SYMBOL(reserve_evntsel_nmi);
 EXPORT_SYMBOL(release_evntsel_nmi);
-EXPORT_SYMBOL(reserve_lapic_nmi);
-EXPORT_SYMBOL(release_lapic_nmi);
 EXPORT_SYMBOL(disable_timer_nmi_watchdog);
 EXPORT_SYMBOL(enable_timer_nmi_watchdog);
 EXPORT_SYMBOL(touch_nmi_watchdog);

Index: linux/include/asm-x86_64/nmi.h
===================================================================
@@ -7,25 +7,6 @@
 #include <linux/pm.h>
 #include <asm/io.h>
  
-struct pt_regs;
-
-typedef int (*nmi_callback_t)(struct pt_regs * regs, int cpu);
-
-/**
- * set_nmi_callback
- *
- * Set a handler for an NMI. Only one handler may be
- * set. Return 1 if the NMI was handled.
- */
-void set_nmi_callback(nmi_callback_t callback);
-
-/**
- * unset_nmi_callback
- *
- * Remove the handler previously set.
- */
-void unset_nmi_callback(void);
-
 /**
  * do_nmi_callback
  *

@@ -72,8 +53,6 @@ extern int reserve_evntsel_nmi(unsigned 
 extern void release_evntsel_nmi(unsigned int);
 
 extern void setup_apic_nmi_watchdog (void *);
-extern int reserve_lapic_nmi(void);
-extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
 extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);

92 lines not on this page · raw message

Index: linux/arch/i386/oprofile/nmi_timer_int.c
===================================================================
@@ -17,32 +17,49 @@
 #include <asm/nmi.h>
 #include <asm/apic.h>
 #include <asm/ptrace.h>
+#include <asm/kdebug.h>
  
-static int nmi_timer_callback(struct pt_regs * regs, int cpu)
+int profile_timer_exceptions_notify(struct notifier_block *self,
+				unsigned long val, void *data)
 {
-	oprofile_add_sample(regs, 0);
-	return 1;
+	struct die_args *args = (struct die_args *)data;
+	int ret = NOTIFY_DONE;
+
+	switch(val) {
+	case DIE_NMI:
+		oprofile_add_sample(args->regs, 0);
+		ret = NOTIFY_STOP;
+		break;
+	default:
+		break;
+	}
+	return ret;
 }
 
+static struct notifier_block profile_timer_exceptions_nb = {
+	.notifier_call = profile_timer_exceptions_notify,
+	.next = NULL,
+	.priority = 0
+};
+
 static int timer_start(void)
 {
-	disable_timer_nmi_watchdog();
-	set_nmi_callback(nmi_timer_callback);
+	if (register_die_notifier(&profile_timer_exceptions_nb))
+		return 1;
 	return 0;
 }
 
 
 static void timer_stop(void)
 {
-	enable_timer_nmi_watchdog();
-	unset_nmi_callback();
+	unregister_die_notifier(&profile_timer_exceptions_nb);
 	synchronize_sched();  /* Allow already-started NMIs to complete. */
 }
 
 
 int __init op_nmi_timer_init(struct oprofile_operations * ops)
 {
-	if (atomic_read(&nmi_active) <= 0)
+	if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0))
 		return -ENODEV;
 
 	ops->start = timer_start;

114 lines not on this page · raw message

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -703,13 +703,6 @@ void die_nmi (struct pt_regs *regs, cons
 	do_exit(SIGSEGV);
 }
 
-static int dummy_nmi_callback(struct pt_regs * regs, int cpu)
-{
-	return 0;
-}
-
-static nmi_callback_t nmi_callback = dummy_nmi_callback;
-
 static void default_do_nmi(struct pt_regs * regs)
 {
 	unsigned char reason = 0;

@@ -729,9 +722,10 @@ static void default_do_nmi(struct pt_reg
 		 */
 		if (nmi_watchdog_tick(regs, reason))
 			return;
+		if (!do_nmi_callback(regs, smp_processor_id()))
 #endif
-		if (!rcu_dereference(nmi_callback)(regs, smp_processor_id()))
 			unknown_nmi_error(reason, regs);
+
 		return;
 	}
 	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP)

@@ -762,19 +756,6 @@ fastcall void do_nmi(struct pt_regs * re
 	nmi_exit();
 }
 
-void set_nmi_callback(nmi_callback_t callback)
-{
-	vmalloc_sync_all();
-	rcu_assign_pointer(nmi_callback, callback);
-}
-EXPORT_SYMBOL_GPL(set_nmi_callback);
-
-void unset_nmi_callback(void)
-{
-	nmi_callback = dummy_nmi_callback;
-}
-EXPORT_SYMBOL_GPL(unset_nmi_callback);
-
 #ifdef CONFIG_KPROBES
 fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {

Index: linux/include/asm-i386/nmi.h
===================================================================
@@ -6,24 +6,13 @@
 
 #include <linux/pm.h>
 
-struct pt_regs;
-
-typedef int (*nmi_callback_t)(struct pt_regs * regs, int cpu);
-
-/**
- * set_nmi_callback
- *
- * Set a handler for an NMI. Only one handler may be
- * set. Return 1 if the NMI was handled.
- */
-void set_nmi_callback(nmi_callback_t callback);
-
 /**
- * unset_nmi_callback
+ * do_nmi_callback
  *
- * Remove the handler previously set.
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
  */
-void unset_nmi_callback(void);
+int do_nmi_callback(struct pt_regs *regs, int cpu);
 
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int avail_to_resrv_perfctr_nmi(unsigned int);

@@ -33,8 +22,6 @@ extern int reserve_evntsel_nmi(unsigned 
 extern void release_evntsel_nmi(unsigned int);
 
 extern void setup_apic_nmi_watchdog (void *);
-extern int reserve_lapic_nmi(void);
-extern void release_lapic_nmi(void);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
 extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);

Index: linux/kernel/sysctl.c
===================================================================
@@ -76,8 +76,6 @@ extern int compat_log;
 
 #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 *);
 #endif
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */

@@ -628,7 +626,7 @@ static ctl_table kern_table[] = {
 		.data           = &unknown_nmi_panic,
 		.maxlen         = sizeof (int),
 		.mode           = 0644,
-		.proc_handler   = &proc_unknown_nmi_panic,
+		.proc_handler   = &proc_dointvec,
 	},
 #endif
 #if defined(CONFIG_X86)

Index: linux/arch/i386/kernel/crash.c
===================================================================
@@ -22,6 +22,8 @@
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
+#include <asm/kdebug.h>
+
 #include <mach_ipi.h>
 
 

@@ -93,9 +95,18 @@ static void crash_save_self(struct pt_re
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct pt_regs *regs, int cpu)
+static int crash_nmi_callback(struct notifier_block *self,
+			unsigned long val, void *data)
 {
+	struct pt_regs *regs;
 	struct pt_regs fixed_regs;
+	int cpu;
+
+	if (val != DIE_NMI)
+		return NOTIFY_OK;
+
+	regs = ((struct die_args *)data)->regs;
+	cpu = raw_smp_processor_id();
 
 	/* Don't do anything if this handler is invoked on crashing cpu.
 	 * Otherwise, system will completely hang. Crashing cpu can get

@@ -125,13 +136,18 @@ static void smp_send_nmi_allbutself(void
 	send_IPI_allbutself(NMI_VECTOR);
 }
 
+static struct notifier_block crash_nmi_nb = {
+	.notifier_call = crash_nmi_callback,
+};
+
 static void nmi_shootdown_cpus(void)
 {
 	unsigned long msecs;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
 	/* Would it be better to replace the trap vector here? */
-	set_nmi_callback(crash_nmi_callback);
+	if (register_die_notifier(&crash_nmi_nb))
+		return;		/* return what? */
 	/* Ensure the new callback function is set before sending
 	 * out the NMI
 	 */

Index: linux/arch/x86_64/kernel/crash.c
===================================================================
@@ -23,6 +23,7 @@
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
 #include <asm/mach_apic.h>
+#include <asm/kdebug.h>
 
 /* This keeps a track of which one is crashing cpu. */
 static int crashing_cpu;

@@ -95,8 +96,18 @@ static void crash_save_self(struct pt_re
 #ifdef CONFIG_SMP
 static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct pt_regs *regs, int cpu)
+static int crash_nmi_callback(struct notifier_block *self,
+				unsigned long val, void *data)
 {
+	struct pt_regs *regs;
+	int cpu;
+
+	if (val != DIE_NMI)
+		return NOTIFY_OK;
+
+	regs = ((struct die_args *)data)->regs;
+	cpu = raw_smp_processor_id();
+
 	/*
 	 * Don't do anything if this handler is invoked on crashing cpu.
 	 * Otherwise, system will completely hang. Crashing cpu can get

@@ -127,12 +138,17 @@ static void smp_send_nmi_allbutself(void
  * cpu hotplug shouldn't matter.
  */
 
+static struct notifier_block crash_nmi_nb = {
+	.notifier_call = crash_nmi_callback,
+};
+
 static void nmi_shootdown_cpus(void)
 {
 	unsigned long msecs;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	set_nmi_callback(crash_nmi_callback);
+	if (register_die_notifier(&crash_nmi_nb))
+		return;         /* return what? */
 
 	/*
 	 * Ensure the new callback function is set before sending

Index: linux/arch/i386/kernel/nmi.c
===================================================================
@@ -846,6 +846,58 @@ static int unknown_nmi_panic_callback(st
 	return 0;
 }
 
+/*
+ * proc handler for /proc/sys/kernel/nmi_watchdog
+ */
+int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
+			void __user *buffer, size_t *length, loff_t *ppos)
+{
+	int old_state;
+
+	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
+	old_state = nmi_watchdog_enabled;
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	if (!!old_state == !!nmi_watchdog_enabled)
+		return 0;
+
+	if (atomic_read(&nmi_active) < 0) {
+		printk(KERN_WARNING "NMI watchdog is permanently disabled\n");
+		return -EINVAL;
+	}
+
+	if (nmi_watchdog == NMI_DEFAULT) {
+		if (nmi_known_cpu() > 0)
+			nmi_watchdog = NMI_LOCAL_APIC;
+		else
+			nmi_watchdog = NMI_IO_APIC;
+	}
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+	{
+		if (nmi_watchdog_enabled)
+			enable_lapic_nmi_watchdog();
+		else
+			disable_lapic_nmi_watchdog();
+	} else if (nmi_watchdog == NMI_IO_APIC) {
+		/* FIXME
+		 * for some reason these functions don't work
+		 */
+		printk("Can not enable/disable NMI on IO APIC\n");
+		return -EINVAL;
+#if 0
+		if (nmi_watchdog_enabled)
+			enable_timer_nmi_watchdog();
+		else
+			disable_timer_nmi_watchdog();
+#endif
+	} else {
+		printk( KERN_WARNING
+			"NMI watchdog doesn't know what hardware to touch\n");
+		return -EIO;
+	}
+	return 0;
+}
+
 #endif
 
 EXPORT_SYMBOL(nmi_active);

54 lines not on this page · raw message

Index: linux/include/asm-i386/nmi.h
===================================================================
@@ -14,6 +14,7 @@
  */
 int do_nmi_callback(struct pt_regs *regs, int cpu);
 
+extern int nmi_watchdog_enabled;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);

Index: linux/include/asm-x86_64/nmi.h
===================================================================
@@ -43,6 +43,7 @@ extern void die_nmi(char *str, struct pt
 
 extern int panic_on_timeout;
 extern int unknown_nmi_panic;
+extern int nmi_watchdog_enabled;
 
 extern int check_nmi_watchdog(void);
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);

Index: linux/include/linux/sysctl.h
===================================================================
@@ -150,6 +150,7 @@ enum
 	KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */
 	KERN_COMPAT_LOG=73,	/* int: print compat layer  messages */
 	KERN_MAX_LOCK_DEPTH=74,
+	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
 };
 
 

Index: linux/kernel/sysctl.c
===================================================================
@@ -76,6 +76,9 @@ extern int compat_log;
 
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
+int nmi_watchdog_enabled;
+extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+			void __user *, size_t *, loff_t *);
 #endif
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */

@@ -628,6 +631,14 @@ static ctl_table kern_table[] = {
 		.mode           = 0644,
 		.proc_handler   = &proc_dointvec,
 	},
+	{
+		.ctl_name       = KERN_NMI_WATCHDOG,
+		.procname       = "nmi_watchdog",
+		.data           = &nmi_watchdog_enabled,
+		.maxlen         = sizeof (int),
+		.mode           = 0644,
+		.proc_handler   = &proc_nmi_enabled,
+	},
 #endif
 #if defined(CONFIG_X86)
 	{

diff -purN /tmp/ia32.c /tmp/amd64.c
@@ -10,16 +10,12 @@
 +		return 0;
 +
 +	if (atomic_read(&nmi_active) < 0) {
-+		printk(KERN_WARNING "NMI watchdog is permanently disabled\n");
++		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
 +		return -EINVAL;
 

Index: linux/arch/i386/kernel/nmi.c
===================================================================
@@ -847,7 +847,7 @@ static int unknown_nmi_panic_callback(st
 }
 
 /*
- * proc handler for /proc/sys/kernel/nmi_watchdog
+ * proc handler for /proc/sys/kernel/nmi
  */
 int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
 			void __user *buffer, size_t *length, loff_t *ppos)

@@ -861,8 +861,8 @@ int proc_nmi_enabled(struct ctl_table *t
 		return 0;
 
 	if (atomic_read(&nmi_active) < 0) {
-		printk(KERN_WARNING "NMI watchdog is permanently disabled\n");
-		return -EINVAL;
+		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
+		return -EIO;
 	}
 
 	if (nmi_watchdog == NMI_DEFAULT) {

@@ -872,24 +872,11 @@ int proc_nmi_enabled(struct ctl_table *t
 			nmi_watchdog = NMI_IO_APIC;
 	}
 
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-	{
+	if (nmi_watchdog == NMI_LOCAL_APIC) {
 		if (nmi_watchdog_enabled)
 			enable_lapic_nmi_watchdog();
 		else
 			disable_lapic_nmi_watchdog();
-	} else if (nmi_watchdog == NMI_IO_APIC) {
-		/* FIXME
-		 * for some reason these functions don't work
-		 */
-		printk("Can not enable/disable NMI on IO APIC\n");
-		return -EINVAL;
-#if 0
-		if (nmi_watchdog_enabled)
-			enable_timer_nmi_watchdog();
-		else
-			disable_timer_nmi_watchdog();
-#endif
 	} else {
 		printk( KERN_WARNING
 			"NMI watchdog doesn't know what hardware to touch\n");

Index: linux/arch/x86_64/kernel/nmi.c
===================================================================
@@ -167,7 +167,7 @@ static __cpuinit inline int nmi_known_cp
 }
 
 /* Run after command line and cpu_init init, but before all other checks */
-void __cpuinit nmi_watchdog_default(void)
+void nmi_watchdog_default(void)
 {
 	if (nmi_watchdog != NMI_DEFAULT)
 		return;

@@ -766,32 +766,19 @@ int proc_nmi_enabled(struct ctl_table *t
 
 	if (atomic_read(&nmi_active) < 0) {
 		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
-		return -EINVAL;
+		return -EIO;
 	}
 
 	/* if nmi_watchdog is not set yet, then set it */
 	nmi_watchdog_default();
 
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-	{
+	if (nmi_watchdog == NMI_LOCAL_APIC) {
 		if (nmi_watchdog_enabled)
 			enable_lapic_nmi_watchdog();
 		else
 			disable_lapic_nmi_watchdog();
-	} else if (nmi_watchdog == NMI_IO_APIC) {
-		/* FIXME
-		 * for some reason these functions don't work
-		 */
-		printk("Can not enable/disable NMI on IO APIC\n");
-		return -EIO;
-#if 0
-		if (nmi_watchdog_enabled)
-			enable_timer_nmi_watchdog();
-		else
-			disable_timer_nmi_watchdog();
-#endif
 	} else {
-		printk(KERN_WARNING
+		printk( KERN_WARNING
 			"NMI watchdog doesn't know what hardware to touch\n");
 		return -EIO;
 	}

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -632,6 +632,8 @@ static void mem_parity_error(unsigned ch
 			"to continue\n");
 	printk(KERN_EMERG "You probably have a hardware problem with your RAM "
 			"chips\n");
+	if (panic_on_unrecovered_nmi)
+                panic("NMI: Not continuing");
 
 	/* Clear and disable the memory parity error line. */
 	clear_mem_error(reason);

@@ -667,6 +669,10 @@ static void unknown_nmi_error(unsigned c
 		reason, smp_processor_id());
 	printk("Dazed and confused, but trying to continue\n");
 	printk("Do you have a strange power saving mode enabled?\n");
+
+	if (panic_on_unrecovered_nmi)
+                panic("NMI: Not continuing");
+
 }
 
 static DEFINE_SPINLOCK(nmi_print_lock);

Index: linux/arch/x86_64/kernel/traps.c
===================================================================
@@ -728,6 +728,8 @@ mem_parity_error(unsigned char reason, s
 {
 	printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n");
 	printk("You probably have a hardware problem with your RAM chips\n");
+	if (panic_on_unrecovered_nmi)
+               panic("NMI: Not continuing");
 
 	/* Clear and disable the memory parity error line. */
 	reason = (reason & 0xf) | 4;

@@ -753,6 +755,10 @@ unknown_nmi_error(unsigned char reason, 
 {	printk("Uhhuh. NMI received for unknown reason %02x.\n", reason);
 	printk("Dazed and confused, but trying to continue\n");
 	printk("Do you have a strange power saving mode enabled?\n");
+
+	if (panic_on_unrecovered_nmi)
+                panic("NMI: Not continuing");
+
 }
 
 /* Runs on IST stack. This code must keep interrupts off all the time.

Index: linux/include/linux/kernel.h
===================================================================
@@ -186,6 +186,7 @@ extern void bust_spinlocks(int yes);
 extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern int panic_on_oops;
+extern int panic_on_unrecovered_nmi;
 extern int tainted;
 extern const char *print_tainted(void);
 extern void add_taint(unsigned);

Index: linux/kernel/sysctl.c
===================================================================
@@ -642,6 +642,14 @@ static ctl_table kern_table[] = {
 #endif
 #if defined(CONFIG_X86)
 	{
+		.ctl_name	= KERN_PANIC_ON_NMI,
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+	{
 		.ctl_name	= KERN_BOOTLOADER_TYPE,
 		.procname	= "bootloader_type",
 		.data		= &bootloader_type,

Index: linux/include/linux/sysctl.h
===================================================================
@@ -151,6 +151,7 @@ enum
 	KERN_COMPAT_LOG=73,	/* int: print compat layer  messages */
 	KERN_MAX_LOCK_DEPTH=74,
 	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
+	KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
 };
 
 

Index: linux/kernel/panic.c
===================================================================
@@ -20,6 +20,7 @@
 #include <linux/kexec.h>
 
 int panic_on_oops;
+int panic_on_unrecovered_nmi;
 int tainted;
 static int pause_on_oops;
 static int pause_on_oops_flag;

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -628,13 +628,15 @@ gp_in_kernel:
 
 static void mem_parity_error(unsigned char reason, struct pt_regs * regs)
 {
-	printk(KERN_EMERG "Uhhuh. NMI received. Dazed and confused, but trying "
-			"to continue\n");
+	printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on "
+		"CPU %d.\n", reason, smp_processor_id());
 	printk(KERN_EMERG "You probably have a hardware problem with your RAM "
 			"chips\n");
 	if (panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
+	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
+
 	/* Clear and disable the memory parity error line. */
 	clear_mem_error(reason);
 }

@@ -665,14 +667,13 @@ static void unknown_nmi_error(unsigned c
 		return;
 	}
 #endif
-	printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-		reason, smp_processor_id());
-	printk("Dazed and confused, but trying to continue\n");
-	printk("Do you have a strange power saving mode enabled?\n");
-
+	printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x on "
+		"CPU %d.\n", reason, smp_processor_id());
+	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
 	if (panic_on_unrecovered_nmi)
                 panic("NMI: Not continuing");
 
+	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
 }
 
 static DEFINE_SPINLOCK(nmi_print_lock);

Index: linux/arch/x86_64/kernel/traps.c
===================================================================
@@ -726,10 +726,15 @@ asmlinkage void __kprobes do_general_pro
 static __kprobes void
 mem_parity_error(unsigned char reason, struct pt_regs * regs)
 {
-	printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n");
-	printk("You probably have a hardware problem with your RAM chips\n");
+	printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n",
+		reason);
+	printk(KERN_EMERG "You probably have a hardware problem with your "
+		"RAM chips\n");
+
 	if (panic_on_unrecovered_nmi)
-               panic("NMI: Not continuing");
+		panic("NMI: Not continuing");
+
+	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
 
 	/* Clear and disable the memory parity error line. */
 	reason = (reason & 0xf) | 4;

@@ -752,13 +757,15 @@ io_check_error(unsigned char reason, str
 
 static __kprobes void
 unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
-{	printk("Uhhuh. NMI received for unknown reason %02x.\n", reason);
-	printk("Dazed and confused, but trying to continue\n");
-	printk("Do you have a strange power saving mode enabled?\n");
+{
+	printk(KERN_EMERG "Uhhuh. NMI received for unknown reason %02x.\n",
+		reason);
+	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
 
 	if (panic_on_unrecovered_nmi)
-                panic("NMI: Not continuing");
+		panic("NMI: Not continuing");
 
+	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
 }
 
 /* Runs on IST stack. This code must keep interrupts off all the time.

Index: linux/arch/i386/kernel/nmi.c
===================================================================
@@ -63,7 +63,6 @@ struct nmi_watchdog_ctlblk {
 static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
 
 /* local prototypes */
-static void stop_apic_nmi_watchdog(void *unused);
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
 
 extern void show_registers(struct pt_regs *regs);

@@ -341,15 +340,20 @@ static int nmi_pm_active; /* nmi_active 
 
 static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
 {
+	/* only CPU0 goes here, other CPUs should be offline */
 	nmi_pm_active = atomic_read(&nmi_active);
-	disable_lapic_nmi_watchdog();
+	stop_apic_nmi_watchdog(NULL);
+	BUG_ON(atomic_read(&nmi_active) != 0);
 	return 0;
 }
 
 static int lapic_nmi_resume(struct sys_device *dev)
 {
-	if (nmi_pm_active > 0)
-		enable_lapic_nmi_watchdog();
+	/* only CPU0 goes here, other CPUs should be offline */
+	if (nmi_pm_active > 0) {
+		setup_apic_nmi_watchdog(NULL);
+		touch_nmi_watchdog();
+	}
 	return 0;
 }
 

@@ -667,7 +671,7 @@ void setup_apic_nmi_watchdog (void *unus
 	atomic_inc(&nmi_active);
 }
 
-static void stop_apic_nmi_watchdog(void *unused)
+void stop_apic_nmi_watchdog(void *unused)
 {
 	/* only support LOCAL and IO APICs for now */
 	if ((nmi_watchdog != NMI_LOCAL_APIC) &&

Index: linux/arch/i386/kernel/smpboot.c
===================================================================
@@ -1372,7 +1372,8 @@ int __cpu_disable(void)
 	 */
 	if (cpu == 0)
 		return -EBUSY;
-
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		stop_apic_nmi_watchdog(NULL);
 	clear_local_APIC();
 	/* Allow any queued timer interrupts to get serviced */
 	local_irq_enable();

Index: linux/arch/x86_64/kernel/nmi.c
===================================================================
@@ -63,7 +63,6 @@ struct nmi_watchdog_ctlblk {
 static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
 
 /* local prototypes */
-static void stop_apic_nmi_watchdog(void *unused);
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
 
 /* converts an msr to an appropriate reservation bit */

@@ -337,15 +336,20 @@ static int nmi_pm_active; /* nmi_active 
 
 static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
 {
+	/* only CPU0 goes here, other CPUs should be offline */
 	nmi_pm_active = atomic_read(&nmi_active);
-	disable_lapic_nmi_watchdog();
+	stop_apic_nmi_watchdog(NULL);
+	BUG_ON(atomic_read(&nmi_active) != 0);
 	return 0;
 }
 
 static int lapic_nmi_resume(struct sys_device *dev)
 {
-	if (nmi_pm_active > 0)
-		enable_lapic_nmi_watchdog();
+	/* only CPU0 goes here, other CPUs should be offline */
+	if (nmi_pm_active > 0) {
+		setup_apic_nmi_watchdog(NULL);
+		touch_nmi_watchdog();
+	}
 	return 0;
 }
 

@@ -586,7 +590,7 @@ void setup_apic_nmi_watchdog(void *unuse
 	atomic_inc(&nmi_active);
 }
 
-static void stop_apic_nmi_watchdog(void *unused)
+void stop_apic_nmi_watchdog(void *unused)
 {
 	/* only support LOCAL and IO APICs for now */
 	if ((nmi_watchdog != NMI_LOCAL_APIC) &&

Index: linux/arch/x86_64/kernel/smpboot.c
===================================================================
@@ -1233,6 +1233,8 @@ int __cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+		stop_apic_nmi_watchdog(NULL);
 	clear_local_APIC();
 
 	/*