x86 2.6.24 patches review I

Index: linux/arch/i386/kernel/alternative.c
===================================================================
@@ -62,11 +62,11 @@ __setup("noreplace-paravirt", setup_nore
 /* Use inline assembly to define this because the nops are defined
    as inline assembly strings in the include files and we cannot
    get them easily into strings. */
-asm("\t.data\nintelnops: "
+asm("\t.section .rodata, \"a\"\nintelnops: "
 	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
 	GENERIC_NOP7 GENERIC_NOP8);
-extern unsigned char intelnops[];
-static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char intelnops[];
+static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	intelnops,
 	intelnops + 1,

@@ -80,11 +80,11 @@ static unsigned char *intel_nops[ASM_NOP
 #endif
 
 #ifdef K8_NOP1
-asm("\t.data\nk8nops: "
+asm("\t.section .rodata, \"a\"\nk8nops: "
 	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
 	K8_NOP7 K8_NOP8);
-extern unsigned char k8nops[];
-static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char k8nops[];
+static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	k8nops,
 	k8nops + 1,

@@ -98,11 +98,11 @@ static unsigned char *k8_nops[ASM_NOP_MA
 #endif
 
 #ifdef K7_NOP1
-asm("\t.data\nk7nops: "
+asm("\t.section .rodata, \"a\"\nk7nops: "
 	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
 	K7_NOP7 K7_NOP8);
-extern unsigned char k7nops[];
-static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
+extern const unsigned char k7nops[];
+static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 	NULL,
 	k7nops,
 	k7nops + 1,

@@ -118,25 +118,25 @@ static unsigned char *k7_nops[ASM_NOP_MA
 #ifdef CONFIG_X86_64
 
 extern char __vsyscall_0;
-static inline unsigned char** find_nop_table(void)
+static inline const unsigned char*const * find_nop_table(void)
 {
 	return k8_nops;
 }
 
 #else /* CONFIG_X86_64 */
 
-static struct nop {
+static const struct nop {
 	int cpuid;
-	unsigned char **noptable;
+	const unsigned char *const *noptable;
 } noptypes[] = {
 	{ X86_FEATURE_K8, k8_nops },
 	{ X86_FEATURE_K7, k7_nops },
 	{ -1, NULL }
 };
 
-static unsigned char** find_nop_table(void)
+static const unsigned char*const * find_nop_table(void)
 {
-	unsigned char **noptable = intel_nops;
+	const unsigned char *const *noptable = intel_nops;
 	int i;
 
 	for (i = 0; noptypes[i].cpuid >= 0; i++) {

@@ -153,7 +153,7 @@ static unsigned char** find_nop_table(vo
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void add_nops(void *insns, unsigned int len)
 {
-	unsigned char **noptable = find_nop_table();
+	const unsigned char *const *noptable = find_nop_table();
 
 	while (len > 0) {
 		unsigned int noplen = len;

Index: linux/arch/i386/kernel/smpboot.c
===================================================================
@@ -102,8 +102,8 @@ u8 apicid_2_node[MAX_APICID];
  * Trampoline 80x86 program as an array.
  */
 
-extern unsigned char trampoline_data [];
-extern unsigned char trampoline_end  [];
+extern const unsigned char trampoline_data [];
+extern const unsigned char trampoline_end  [];
 static unsigned char *trampoline_base;
 static int trampoline_exec;
 

Index: linux/arch/i386/mach-voyager/voyager_smp.c
===================================================================
@@ -442,8 +442,8 @@ static __u32 __init
 setup_trampoline(void)
 {
 	/* these two are global symbols in trampoline.S */
-	extern __u8 trampoline_end[];
-	extern __u8 trampoline_data[];
+	extern const __u8 trampoline_end[];
+	extern const __u8 trampoline_data[];
 
 	memcpy((__u8 *)trampoline_base, trampoline_data,
 	       trampoline_end - trampoline_data);

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -936,7 +936,7 @@ static int show_cpuinfo(struct seq_file 
 	 * applications want to get the raw CPUID data, they should access
 	 * /dev/cpu/<cpu_nr>/cpuid instead.
 	 */
-	static char *x86_cap_flags[] = {
+	static const char *const x86_cap_flags[] = {
 		/* Intel-defined */
 	        "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce",
 	        "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov",

@@ -990,7 +990,7 @@ static int show_cpuinfo(struct seq_file 
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 	};
-	static char *x86_power_flags[] = { 
+	static const char *const x86_power_flags[] = {
 		"ts",	/* temperature sensor */
 		"fid",  /* frequency id control */
 		"vid",  /* voltage id control */

Index: linux/arch/x86_64/kernel/smpboot.c
===================================================================
@@ -102,8 +102,8 @@ EXPORT_SYMBOL(cpu_core_map);
  * Trampoline 80x86 program as an array.
  */
 
-extern unsigned char trampoline_data[];
-extern unsigned char trampoline_end[];
+extern const unsigned char trampoline_data[];
+extern const unsigned char trampoline_end[];
 
 /* State of each CPU */
 DEFINE_PER_CPU(int, cpu_state) = { 0 };

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -114,7 +114,7 @@ struct stack_frame {
 
 static inline unsigned long print_context_stack(struct thread_info *tinfo,
 				unsigned long *stack, unsigned long ebp,
-				struct stacktrace_ops *ops, void *data)
+				const struct stacktrace_ops *ops, void *data)
 {
 #ifdef	CONFIG_FRAME_POINTER
 	struct stack_frame *frame = (struct stack_frame *)ebp;

@@ -151,7 +151,7 @@ static inline unsigned long print_contex
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	        unsigned long *stack,
-		struct stacktrace_ops *ops, void *data)
+		const struct stacktrace_ops *ops, void *data)
 {
 	unsigned long ebp = 0;
 

@@ -223,7 +223,7 @@ static void print_trace_address(void *da
 	touch_nmi_watchdog();
 }
 
-static struct stacktrace_ops print_trace_ops = {
+static const struct stacktrace_ops print_trace_ops = {
 	.warning = print_trace_warning,
 	.warning_symbol = print_trace_warning_symbol,
 	.stack = print_trace_stack,

Index: linux/arch/x86_64/kernel/stacktrace.c
===================================================================
@@ -35,7 +35,7 @@ static void save_stack_address(void *dat
 		trace->entries[trace->nr_entries++] = addr;
 }
 
-static struct stacktrace_ops save_stack_ops = {
+static const struct stacktrace_ops save_stack_ops = {
 	.warning = save_stack_warning,
 	.warning_symbol = save_stack_warning_symbol,
 	.stack = save_stack_stack,

Index: linux/arch/x86_64/kernel/traps.c
===================================================================
@@ -217,7 +217,7 @@ static inline int valid_stack_ptr(struct
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
 		unsigned long *stack,
-		struct stacktrace_ops *ops, void *data)
+		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
 	unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr;

@@ -338,7 +338,7 @@ static void print_trace_address(void *da
 	printk_address(addr);
 }
 
-static struct stacktrace_ops print_trace_ops = {
+static const struct stacktrace_ops print_trace_ops = {
 	.warning = print_trace_warning,
 	.warning_symbol = print_trace_warning_symbol,
 	.stack = print_trace_stack,

Index: linux/include/asm-x86_64/stacktrace.h
===================================================================
@@ -15,6 +15,6 @@ struct stacktrace_ops {
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack,
-		struct stacktrace_ops *ops, void *data);
+		const struct stacktrace_ops *ops, void *data);
 
 #endif

Index: linux/arch/i386/kernel/tsc.c
===================================================================
@@ -332,7 +332,7 @@ static struct dmi_system_id __initdata b
  */
 __cpuinit int unsynchronized_tsc(void)
 {
-	if (!cpu_has_tsc || tsc_unstable)
+	if (!cpu_has_tsc)
 		return 1;
 	/*
 	 * Intel systems are normally all synchronized.

@@ -341,9 +341,9 @@ __cpuinit int unsynchronized_tsc(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
 		/* assume multi socket systems are not synchronized: */
 		if (num_possible_cpus() > 1)
-			tsc_unstable = 1;
+			return 1;
 	}
-	return tsc_unstable;
+	return 0;
 }
 
 /*

@@ -387,13 +387,12 @@ void __init tsc_init(void)
 	/* Check and install the TSC clocksource */
 	dmi_check_system(bad_tsc_dmi_table);
 
-	unsynchronized_tsc();
 	check_geode_tsc_reliable();
 	current_tsc_khz = tsc_khz;
 	clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz,
 							clocksource_tsc.shift);
 	/* lower the rating if we already know its unstable: */
-	if (check_tsc_unstable()) {
+	if (check_tsc_unstable() || unsynchronized_tsc()) {
 		clocksource_tsc.rating = 0;
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
 	} else

Index: linux/arch/x86_64/kernel/tsc.c
===================================================================
@@ -124,9 +124,6 @@ core_initcall(cpufreq_tsc);
  */
 __cpuinit int unsynchronized_tsc(void)
 {
-	if (tsc_unstable)
-		return 1;
-
 #ifdef CONFIG_SMP
 	if (apic_is_clustered_box())
 		return 1;

@@ -199,7 +196,7 @@ void __init init_tsc_clocksource(void)
 	if (!notsc) {
 		clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
 							clocksource_tsc.shift);
-		if (check_tsc_unstable())
+		if (unsynchronized_tsc() || check_tsc_unstable())
 			clocksource_tsc.rating = 0;
 
 		clocksource_register(&clocksource_tsc);

Index: linux/arch/i386/kernel/sched-clock.c
===================================================================
@@ -0,0 +1,270 @@
+/* A fast clock for the scheduler.
+ * Copyright 2007 Andi Kleen SUSE Labs
+ * Subject to the GNU Public License, version 2 only.
+ */
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/smp.h>
+#include <linux/notifier.h>
+#include <linux/init.h>
+#include <asm/tsc.h>
+#include <asm/cpufeature.h>
+#include <asm/timer.h>
+
+/*
+ * convert from cycles(64bits) => nanoseconds (64bits)
+ *  basic equation:
+ *		ns = cycles / (freq / ns_per_sec)
+ *		ns = cycles * (ns_per_sec / freq)
+ *		ns = cycles * (10^9 / (cpu_khz * 10^3))
+ *		ns = cycles * (10^6 / cpu_khz)
+ *
+ *	Then we use scaling math (suggested by [email protected]) to get:
+ *		ns = cycles * (10^6 * SC / cpu_khz) / SC
+ *		ns = cycles * cyc2ns_scale / SC
+ *
+ *	And since SC is a constant power of two, we can convert the div
+ *  into a shift.
+ *
+ *  We can use khz divisor instead of mhz to keep a better percision, since
+ *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ *  ([email protected])
+ *
+ *			[email protected] "math is hard, lets go shopping!"
+ */
+
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+struct sc_data {
+	unsigned cyc2ns_scale;
+	unsigned unstable;
+	unsigned long long sync_base;
+	unsigned long long ns_base;		/* nanoseconds at sync point */
+	unsigned long long min_val;		/* Minimum value during instable periods */
+};
+
+static DEFINE_PER_CPU(struct sc_data, sc_data) =
+	{ .unstable = 1, .sync_base = INITIAL_JIFFIES };
+
+static inline u64 __cycles_2_ns(struct sc_data *sc, u64 cyc)
+{
+	u64 ns;
+
+	cyc -= sc->sync_base;
+	ns = (cyc * sc->cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
+	ns += sc->ns_base;
+
+	return ns;
+}
+
+u64 cycles_2_ns(u64 cyc)
+{
+	struct sc_data *sc = &get_cpu_var(sc_data);
+	u64 ns = __cycles_2_ns(sc, cyc);
+	put_cpu_var(sc_data);
+	return ns;
+}
+
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * All data is local to the CPU.
+ * The values are approximately[1] monotonic local to a CPU, but not
+ * between CPUs.   There might be also an occasionally random error,
+ * but not too bad. Between CPUs the values can be non monotonic.
+ *
+ * [1] no attempt to stop CPU instruction reordering, which can hit
+ * in a 100 instruction window or so.
+ *
+ * The clock can be in two states: stable and unstable.
+ * When it is stable we use the TSC per CPU.
+ * When it is unstable we use jiffies as fallback.
+ * stable->unstable->stable transitions can happen regularly
+ * during CPU frequency changes.
+ * There is special code to avoid having the clock jump backwards
+ * when we switch from TSC to jiffies, which needs to keep some state
+ * per CPU. This state is protected against parallel state changes
+ * with interrupts off.
+ */
+unsigned long long tsc_sched_clock(void)
+{
+	unsigned long long r;
+	struct sc_data *sc = &get_cpu_var(sc_data);
+
+	if (unlikely(sc->unstable)) {
+		r = (jiffies_64 - sc->sync_base) * (1000000000 / HZ);
+		r += sc->ns_base;
+		if (r < sc->min_val)
+			r = sc->min_val;
+	} else {
+		rdtscll(r);
+		r = __cycles_2_ns(sc, r);
+	}
+
+	put_cpu_var(sc_data);
+
+	return r;
+}
+
+/* We need to define a real function for sched_clock, to override the
+   weak default version */
+#ifdef CONFIG_PARAVIRT
+unsigned long long sched_clock(void)
+{
+	return paravirt_sched_clock();
+}
+#else
+unsigned long long sched_clock(void)
+	__attribute__((alias("tsc_sched_clock")));
+#endif
+
+static int no_sc_for_printk;
+
+/*
+ * printk clock: when it is known the sc results are very non monotonic
+ * fall back to jiffies for printk. Other sched_clock users are supposed
+ * to handle this.
+ */
+unsigned long long printk_clock(void)
+{
+	if (unlikely(no_sc_for_printk))
+		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
+	return tsc_sched_clock();
+}
+
+static void resolve_freq(struct cpufreq_freqs *freq)
+{
+	if (!freq->new) {
+		freq->new = cpufreq_get(freq->cpu);
+		if (!freq->new)
+			freq->new = tsc_khz;
+	}
+}
+
+/* Resync with new CPU frequency. Must run on to be synced CPU */
+static void resync_freq(void *arg)
+{
+	struct cpufreq_freqs *freq = arg;
+	struct sc_data *sc = &__get_cpu_var(sc_data);
+
+	sc->sync_base = jiffies_64;
+	if (!cpu_has_tsc) {
+		sc->unstable = 1;
+		return;
+	}
+	resolve_freq(freq);
+
+	/*
+	 * Handle nesting, but when we're zero multiple calls in a row
+	 * are ok too and not a bug. This can happen during startup
+	 * when the different callbacks race with each other.
+	 */
+	if (sc->unstable > 0)
+		sc->unstable--;
+	if (sc->unstable)
+		return;
+
+	/* Minor race window here, but should not add significant errors. */
+	sc->ns_base = ktime_to_ns(ktime_get());
+	rdtscll(sc->sync_base);
+	sc->cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR) / freq->new;
+}
+
+static void resync_freq_on_cpu(void *arg)
+{
+	struct cpufreq_freqs f = { .new = 0 };
+
+	f.cpu = get_cpu();
+	resync_freq(&f);
+	put_cpu();
+}
+
+/* Mark CPU as unstable before cpufreq changes the frequency. */
+static void cpu_unstable(void *arg)
+{
+	struct sc_data *sc = &__get_cpu_var(sc_data);
+	unsigned long flags;
+	unsigned long long ns, r;
+	ns = ktime_to_ns(ktime_get());
+	local_irq_save(flags);
+	r = tsc_sched_clock();
+	sync_core();
+	sc->ns_base = ns;
+	sc->min_val = r;
+	sc->sync_base = jiffies_64;
+	sc->unstable = 1;
+	local_irq_restore(flags);
+}
+
+static int sc_freq_event(struct notifier_block *nb, unsigned long event,
+			 void *data)
+{
+	struct cpufreq_freqs *freq = data;
+
+	if (cpu_has(&cpu_data[freq->cpu], X86_FEATURE_CONSTANT_TSC))
+		return NOTIFY_DONE;
+	if (freq->old == freq->new)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case CPUFREQ_SUSPENDCHANGE:
+		/* Mark TSC unstable during suspend/resume */
+	case CPUFREQ_PRECHANGE:
+		/*
+		 * Mark TSC as unstable until cpu frequency change is
+		 * done because we don't know when exactly it will
+		 * change.  unstable in used as a counter to guard
+		 * against races between the cpu frequency notifiers
+		 * and normal resyncs
+		 */
+		smp_call_function_single(freq->cpu, cpu_unstable, NULL, 0, 1);
+		break;
+	case CPUFREQ_RESUMECHANGE:
+	case CPUFREQ_POSTCHANGE:
+		/*
+		 * Frequency change or resume is done -- update everything and
+		 * mark TSC as stable again.
+		 */
+		smp_call_function_single(freq->cpu, resync_freq, freq, 0, 1);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block sc_freq_notifier = {
+	.notifier_call = sc_freq_event
+};
+
+static int __cpuinit
+sc_cpu_event(struct notifier_block *self, unsigned long event, void *hcpu)
+{
+	long cpu = (long)hcpu;
+	if (event == CPU_ONLINE) {
+		struct cpufreq_freqs f = { .cpu = cpu, .new = 0 };
+
+		smp_call_function_single(cpu, resync_freq, &f, 0, 1);
+	}
+	return NOTIFY_DONE;
+}
+
+static __init int init_sched_clock(void)
+{
+	if (unsynchronized_tsc())
+		no_sc_for_printk = 1;
+
+	/*
+	 * On a race between the various events the initialization
+	 * might be done multiple times, but code is tolerant to
+	 * this .
+	 */
+	cpufreq_register_notifier(&sc_freq_notifier,
+				CPUFREQ_TRANSITION_NOTIFIER);
+	hotcpu_notifier(sc_cpu_event, 0);
+	on_each_cpu(resync_freq_on_cpu, NULL, 0, 0);
+	return 0;
+}
+core_initcall(init_sched_clock);

92 lines not on this page · raw message

Index: linux/include/asm-i386/timer.h
===================================================================
@@ -5,7 +5,7 @@
 
 #define TICK_SIZE (tick_nsec / 1000)
 
-unsigned long long native_sched_clock(void);
+unsigned long long tsc_sched_clock(void);
 unsigned long native_calculate_cpu_khz(void);
 
 extern int timer_ack;

@@ -16,35 +16,6 @@ extern int recalibrate_cpu_khz(void);
 #define calculate_cpu_khz() native_calculate_cpu_khz()
 #endif
 
-/* Accellerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- *  basic equation:
- *		ns = cycles / (freq / ns_per_sec)
- *		ns = cycles * (ns_per_sec / freq)
- *		ns = cycles * (10^9 / (cpu_khz * 10^3))
- *		ns = cycles * (10^6 / cpu_khz)
- *
- *	Then we use scaling math (suggested by [email protected]) to get:
- *		ns = cycles * (10^6 * SC / cpu_khz) / SC
- *		ns = cycles * cyc2ns_scale / SC
- *
- *	And since SC is a constant power of two, we can convert the div
- *  into a shift.
- *
- *  We can use khz divisor instead of mhz to keep a better percision, since
- *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- *  ([email protected])
- *
- *			[email protected] "math is hard, lets go shopping!"
- */
-extern unsigned long cyc2ns_scale __read_mostly;
-
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	return (cyc * cyc2ns_scale) >> CYC2NS_SCALE_FACTOR;
-}
-
+u64 cycles_2_ns(u64 cyc);
 
 #endif

Index: linux/include/asm-i386/tsc.h
===================================================================
@@ -64,6 +64,7 @@ extern void mark_tsc_unstable(char *reas
 extern int unsynchronized_tsc(void);
 extern void init_tsc_clocksource(void);
 int check_tsc_unstable(void);
+extern unsigned long long tsc_sched_clock(void);
 
 /*
  * Boot-time check whether the TSCs are synchronized across

Index: linux/arch/i386/kernel/paravirt.c
===================================================================
@@ -312,7 +312,7 @@ struct paravirt_ops paravirt_ops = {
 	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
-	.sched_clock = native_sched_clock,
+	.sched_clock = tsc_sched_clock,
 	.get_cpu_khz = native_calculate_cpu_khz,
 	.load_tr_desc = native_load_tr_desc,
 	.set_ldt = native_set_ldt,

Index: linux/arch/x86_64/kernel/tsc.c
===================================================================
@@ -8,6 +8,7 @@
 #include <linux/cpufreq.h>
 
 #include <asm/timex.h>
+#include <asm/tsc.h>
 
 static int notsc __initdata = 0;
 

@@ -16,32 +17,6 @@ EXPORT_SYMBOL(cpu_khz);
 unsigned int tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
-static unsigned int cyc2ns_scale __read_mostly;
-
-void set_cyc2ns_scale(unsigned long khz)
-{
-	cyc2ns_scale = (NSEC_PER_MSEC << NS_SCALE) / khz;
-}
-
-static unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	return (cyc * cyc2ns_scale) >> NS_SCALE;
-}
-
-unsigned long long sched_clock(void)
-{
-	unsigned long a = 0;
-
-	/* Could do CPU core sync here. Opteron can execute rdtsc speculatively,
-	 * which means it is not completely exact and may not be monotonous
-	 * between CPUs. But the errors should be too small to matter for
-	 * scheduling purposes.
-	 */
-
-	rdtscll(a);
-	return cycles_2_ns(a);
-}
-
 static int tsc_unstable;
 
 inline int check_tsc_unstable(void)

@@ -98,8 +73,6 @@ static int time_cpufreq_notifier(struct 
 			mark_tsc_unstable("cpufreq changes");
 	}
 
-	set_cyc2ns_scale(tsc_khz_ref);
-
 	return 0;
 }
 

Index: linux/arch/x86_64/kernel/time.c
===================================================================
@@ -398,7 +398,6 @@ void __init time_init(void)
 	else
 		vgetcpu_mode = VGETCPU_LSL;
 
-	set_cyc2ns_scale(tsc_khz);
 	printk(KERN_INFO "time.c: Detected %d.%03d MHz processor.\n",
 		cpu_khz / 1000, cpu_khz % 1000);
 	init_tsc_clocksource();

Index: linux/include/asm-x86_64/timex.h
===================================================================
@@ -27,5 +27,4 @@ extern int read_current_timer(unsigned l
 #define US_SCALE        32 /* 2^32, arbitralrily chosen */
 
 extern void mark_tsc_unstable(char *msg);
-extern void set_cyc2ns_scale(unsigned long khz);
 #endif

Index: linux/include/asm-x86_64/timer.h
===================================================================
@@ -0,0 +1,5 @@
+#ifndef _ASM_TIMER_H
+#define _ASM_TIMER_H 1
+
+#endif
+

Index: linux/arch/x86_64/kernel/early-quirks.c
===================================================================
@@ -13,9 +13,13 @@
 #include <linux/acpi.h>
 #include <linux/pci_ids.h>
 #include <asm/pci-direct.h>
-#include <asm/proto.h>
-#include <asm/iommu.h>
 #include <asm/dma.h>
+#include <asm/io_apic.h>
+#include <asm/apic.h>
+
+#ifdef CONFIG_IOMMU
+#include <asm/iommu.h>
+#endif
 
 static void __init via_bugs(void)
 {

@@ -40,6 +44,7 @@ static int __init nvidia_hpet_check(stru
 static void __init nvidia_bugs(void)
 {
 #ifdef CONFIG_ACPI
+#ifdef CONFIG_X86_IO_APIC
 	/*
 	 * All timer overrides on Nvidia are
 	 * wrong unless HPET is enabled.

@@ -59,17 +64,20 @@ static void __init nvidia_bugs(void)
 			"try acpi_use_timer_override\n");
 	}
 #endif
+#endif
 	/* RED-PEN skip them on mptables too? */
 
 }
 
 static void __init ati_bugs(void)
 {
+#ifdef CONFIG_X86_IO_APIC
 	if (timer_over_8254 == 1) {
 		timer_over_8254 = 0;
 		printk(KERN_INFO
 	 	"ATI board detected. Disabling timer routing over 8254.\n");
 	}
+#endif
 }
 
 struct chipset {

84 lines not on this page · raw message

Index: linux/arch/i386/kernel/setup.c
===================================================================
@@ -619,9 +619,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 #ifdef CONFIG_PCI
-#ifdef CONFIG_X86_IO_APIC
-	check_acpi_pci();	/* Checks more than just ACPI actually */
-#endif
+	early_quirks();
 #endif
 
 #ifdef CONFIG_ACPI

Index: linux/include/asm-i386/acpi.h
===================================================================
@@ -81,11 +81,7 @@ int __acpi_release_global_lock(unsigned 
         :"=r"(n_hi), "=r"(n_lo)     \
         :"0"(n_hi), "1"(n_lo))
 
-#ifdef CONFIG_X86_IO_APIC
-extern void check_acpi_pci(void);
-#else
-static inline void check_acpi_pci(void) { }
-#endif
+extern void early_quirks(void);
 
 #ifdef CONFIG_ACPI
 extern int acpi_lapic;

Index: linux/include/asm-x86_64/io_apic.h
===================================================================
@@ -133,4 +133,6 @@ void enable_NMI_through_LVT0 (void * dum
 
 extern spinlock_t i8259A_lock;
 
+extern int timer_over_8254;
+
 #endif

Index: linux/include/asm-x86_64/proto.h
===================================================================
@@ -86,8 +86,6 @@ extern unsigned tsc_khz;
 extern int reboot_force;
 extern int notsc_setup(char *);
 
-extern int timer_over_8254;
-
 extern int gsi_irq_sharing(int gsi);
 
 extern void smp_local_timer_interrupt(void);

Index: linux/arch/x86_64/kernel/early-quirks.c
===================================================================
@@ -33,36 +33,20 @@ static void __init via_bugs(void)
 #endif
 }
 
-#ifdef CONFIG_ACPI
-
-static int __init nvidia_hpet_check(struct acpi_table_header *header)
-{
-	return 0;
-}
-#endif
-
 static void __init nvidia_bugs(void)
 {
 #ifdef CONFIG_ACPI
 #ifdef CONFIG_X86_IO_APIC
 	/*
-	 * All timer overrides on Nvidia are
-	 * wrong unless HPET is enabled.
-	 * Unfortunately that's not true on many Asus boards.
-	 * We don't know yet how to detect this automatically, but
-	 * at least allow a command line override.
+	 * All timer overrides on Nvidia NF3/NF4 are
+	 * wrong.
 	 */
 	if (acpi_use_timer_override)
 		return;
 
-	if (acpi_table_parse(ACPI_SIG_HPET, nvidia_hpet_check)) {
-		acpi_skip_timer_override = 1;
-		printk(KERN_INFO "Nvidia board "
-		       "detected. Ignoring ACPI "
-		       "timer override.\n");
-		printk(KERN_INFO "If you got timer trouble "
-			"try acpi_use_timer_override\n");
-	}
+	acpi_skip_timer_override = 1;
+	printk(KERN_INFO "Nvidia board detected. Ignoring ACPI timer override.\n");
+	printk(KERN_INFO "If you got timer trouble try acpi_use_timer_override\n");
 #endif
 #endif
 	/* RED-PEN skip them on mptables too? */

@@ -83,10 +67,19 @@ static void __init ati_bugs(void)
 struct chipset {
 	u16 vendor;
 	void (*f)(void);
+	int id;
 };
 
 static struct chipset early_qrk[] __initdata = {
-	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs },
+	/* This list should cover at least one PCI ID from each NF3 or NF4
+	   mainboard to handle a bug in their reference BIOS. May be incomplete. */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x00dd },	/* nforce 3 */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x00e1 },	/* nforce 3 */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x00ed },	/* nforce 3 */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x003d },	/* mcp 04 ?? */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x005c },	/* ck 804 */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x026f },	/* mcp 51 / nf4 ? */
+	{ PCI_VENDOR_ID_NVIDIA, nvidia_bugs, 0x02f0 },	/* mcp 51 / nf4 ? */
 	{ PCI_VENDOR_ID_VIA, via_bugs },
 	{ PCI_VENDOR_ID_ATI, ati_bugs },
 	{}

@@ -99,12 +92,13 @@ void __init early_quirks(void)
 	if (!early_pci_allowed())
 		return;
 
-	/* Poor man's PCI discovery */
+	/* Poor man's PCI discovery.
+	   We just look for a chipset unique PCI bridge; not scan all devices */
 	for (num = 0; num < 32; num++) {
 		for (slot = 0; slot < 32; slot++) {
 			for (func = 0; func < 8; func++) {
 				u32 class;
-				u32 vendor;
+				u32 vendor, device;
 				u8 type;
 				int i;
 				class = read_pci_config(num,slot,func,

@@ -117,13 +111,17 @@ void __init early_quirks(void)
 
 				vendor = read_pci_config(num, slot, func,
 							 PCI_VENDOR_ID);
+				device = vendor >> 16;
+
 				vendor &= 0xffff;
 
-				for (i = 0; early_qrk[i].f; i++)
-					if (early_qrk[i].vendor == vendor) {
+				for (i = 0; early_qrk[i].f; i++) {
+					struct chipset *c = &early_qrk[i];
+					if (c->vendor == vendor && (!c->id || (c->id && c->id==device))) {
 						early_qrk[i].f();
 						return;
 					}
+				}
 
 				type = read_pci_config_byte(num, slot, func,
 							    PCI_HEADER_TYPE);

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -575,7 +575,7 @@ static void __cpuinit init_amd(struct cp
 	level = cpuid_eax(1);
 	if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58))
 		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
-	if (c->x86 == 0x10)
+	if (c->x86 == 0x10 || c->x86 == 0x11)
 		set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability);
 
 	/* Enable workaround for FXSAVE leak */

Index: linux/arch/i386/kernel/pci-dma.c
===================================================================
@@ -12,7 +12,6 @@
 #include <linux/string.h>
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/pci.h>
 #include <asm/io.h>
 
 struct dma_coherent_mem {

Index: linux/arch/x86_64/kernel/e820.c
===================================================================
@@ -639,6 +639,8 @@ static int __init parse_memmap_opt(char 
 	mem_size = memparse(p, &p);
 	if (p == oldp)
 		return -EINVAL;
+
+	userdef = 1;
 	if (*p == '@') {
 		start_at = memparse(p+1, &p);
 		add_memory_region(start_at, mem_size, E820_RAM);

@@ -658,6 +660,11 @@ early_param("memmap", parse_memmap_opt);
 void __init finish_e820_parsing(void)
 {
 	if (userdef) {
+		char nr = e820.nr_map;
+		if (sanitize_e820_map(e820.map, &nr) < 0)
+			early_panic("Invalid user supplied memory map");
+		e820.nr_map = nr;
+
 		printk(KERN_INFO "user-defined physical RAM map:\n");
 		e820_print_map("user");
 	}

Index: linux/arch/i386/kernel/nmi.c
===================================================================
@@ -49,8 +49,9 @@ static unsigned int nmi_hz = HZ;
 static DEFINE_PER_CPU(short, wd_enabled);
 
 /* local prototypes */
+#ifdef CONFIG_SYSCTL
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
-
+#endif
 static int endflag __initdata = 0;
 
 #ifdef CONFIG_SMP

index c7227e2..9a8ff0b 100644
@@ -48,9 +48,6 @@ static unsigned int nmi_hz = HZ;
 
 static DEFINE_PER_CPU(short, wd_enabled);
 
-/* local prototypes */
-static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
-
 static int endflag __initdata = 0;
 
 #ifdef CONFIG_SMP

@@ -389,15 +386,6 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 	return rc;
 }
 
-int do_nmi_callback(struct pt_regs * regs, int cpu)
-{
-#ifdef CONFIG_SYSCTL
-	if (unknown_nmi_panic)
-		return unknown_nmi_panic_callback(regs, cpu);
-#endif
-	return 0;
-}
-
 #ifdef CONFIG_SYSCTL
 
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)

@@ -451,6 +439,16 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
 
 #endif
 
+int do_nmi_callback(struct pt_regs * regs, int cpu)
+{
+#ifdef CONFIG_SYSCTL
+	if (unknown_nmi_panic)
+		return unknown_nmi_panic_callback(regs, cpu);
+#endif
+	return 0;
+}
+
+
 void __trigger_all_cpu_backtrace(void)
 {
 	int i;

Index: linux/arch/x86_64/vdso/voffset.h
===================================================================
@@ -1 +1 @@
-#define VDSO_TEXT_OFFSET 0x500
+#define VDSO_TEXT_OFFSET 0x600

Index: linux/arch/i386/mm/pageattr.c
===================================================================
@@ -70,10 +70,10 @@ static struct page *split_large_page(uns
 
 static void cache_flush_page(struct page *p)
 { 
-	unsigned long adr = (unsigned long)page_address(p);
+	void *adr = page_address(p);
 	int i;
 	for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
-		asm volatile("clflush (%0)" :: "r" (adr + i));
+		clflush(adr+i);
 }
 
 static void flush_kernel_map(void *arg)

Index: linux/arch/x86_64/kernel/tce.c
===================================================================
@@ -40,9 +40,9 @@ static inline void flush_tce(void* tcead
 {
 	/* a single tce can't cross a cache line */
 	if (cpu_has_clflush)
-		asm volatile("clflush (%0)" :: "r" (tceaddr));
+		clflush(tceaddr);
 	else
-		asm volatile("wbinvd":::"memory");
+		wbinvd();
 }
 
 void tce_build(struct iommu_table *tbl, unsigned long index,

Index: linux/arch/x86_64/mm/pageattr.c
===================================================================
@@ -65,7 +65,7 @@ static void cache_flush_page(void *adr)
 {
 	int i;
 	for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
-		asm volatile("clflush (%0)" :: "r" (adr + i));
+		clflush(adr+i);
 }
 
 static void flush_kernel_map(void *arg)

Index: linux/drivers/char/agp/efficeon-agp.c
===================================================================
@@ -221,7 +221,7 @@ static int efficeon_create_gatt_table(st
 		SetPageReserved(virt_to_page((char *)page));
 
 		for (offset = 0; offset < PAGE_SIZE; offset += clflush_chunk)
-			asm volatile("clflush %0" : : "m" (*(char *)(page+offset)));
+			clflush((char *)page+offset);
 
 		efficeon_private.l1_table[index] = page;
 

@@ -268,15 +268,16 @@ static int efficeon_insert_memory(struct
 		*page = insert;
 
 		/* clflush is slow, so don't clflush until we have to */
-		if ( last_page &&
-		     ((unsigned long)page^(unsigned long)last_page) & clflush_mask )
-		    asm volatile("clflush %0" : : "m" (*last_page));
+		if (last_page &&
+		    (((unsigned long)page^(unsigned long)last_page) &
+		     clflush_mask))
+			clflush(last_page);
 
 		last_page = page;
 	}
 
 	if ( last_page )
-		asm volatile("clflush %0" : : "m" (*last_page));
+		clflush(last_page);
 
 	agp_bridge->driver->tlb_flush(mem);
 	return 0;

Index: linux/include/asm-i386/system.h
===================================================================
@@ -160,6 +160,10 @@ static inline void native_wbinvd(void)
 	asm volatile("wbinvd": : :"memory");
 }
 
+static inline void clflush(volatile void *__p)
+{
+	asm volatile("clflush %0" : "+m" (*(char __force *)__p));
+}
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>

Index: linux/include/asm-x86_64/system.h
===================================================================
@@ -137,6 +137,11 @@ static inline void write_cr8(unsigned lo
 
 #endif	/* __KERNEL__ */
 
+static inline void clflush(volatile void *__p)
+{
+	asm volatile("clflush %0" : "+m" (*(char __force *)__p));
+}
+
 #define nop() __asm__ __volatile__ ("nop")
 
 #ifdef CONFIG_SMP

Index: linux/include/asm-i386/msr-index.h
===================================================================
@@ -73,8 +73,32 @@
 #define MSR_P6_EVNTSEL0			0x00000186
 #define MSR_P6_EVNTSEL1			0x00000187
 
-/* K7/K8 MSRs. Not complete. See the architecture manual for a more
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
+
+#define MSR_AMD64_IBSFETCHCTL		0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
+#define MSR_AMD64_IBSOPCTL		0xc0011033
+#define MSR_AMD64_IBSOPRIP		0xc0011034
+#define MSR_AMD64_IBSOPDATA		0xc0011035
+#define MSR_AMD64_IBSOPDATA2		0xc0011036
+#define MSR_AMD64_IBSOPDATA3		0xc0011037
+#define MSR_AMD64_IBSDCLINAD		0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
+#define MSR_AMD64_IBSCTL		0xc001103a
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1			0xc001001a
+#define MSR_K8_TOP_MEM2			0xc001001d
+#define MSR_K8_SYSCFG			0xc0010010
+#define MSR_K8_HWCR			0xc0010015
+#define MSR_K8_ENABLE_C1E		0xc0010055
+#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
+
+/* K7 MSRs */
 #define MSR_K7_EVNTSEL0			0xc0010000
 #define MSR_K7_PERFCTR0			0xc0010004
 #define MSR_K7_EVNTSEL1			0xc0010001

@@ -83,20 +107,10 @@
 #define MSR_K7_PERFCTR2			0xc0010006
 #define MSR_K7_EVNTSEL3			0xc0010003
 #define MSR_K7_PERFCTR3			0xc0010007
-#define MSR_K8_TOP_MEM1			0xc001001a
 #define MSR_K7_CLK_CTL			0xc001001b
-#define MSR_K8_TOP_MEM2			0xc001001d
-#define MSR_K8_SYSCFG			0xc0010010
-
-#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
-#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
-#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
-
 #define MSR_K7_HWCR			0xc0010015
-#define MSR_K8_HWCR			0xc0010015
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
-#define MSR_K8_ENABLE_C1E		0xc0010055
 
 /* K6 MSRs */
 #define MSR_K6_EFER			0xc0000080

Index: linux/arch/i386/kernel/cpu/perfctr-watchdog.c
===================================================================
@@ -120,7 +120,9 @@ int reserve_perfctr_nmi(unsigned int msr
 	unsigned int counter;
 
 	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+	/* register not managed by the allocator? */
+	if (counter > NMI_MAX_COUNTER_BITS)
+		return 1;
 
 	if (!test_and_set_bit(counter, perfctr_nmi_owner))
 		return 1;

@@ -132,7 +134,9 @@ void release_perfctr_nmi(unsigned int ms
 	unsigned int counter;
 
 	counter = nmi_perfctr_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+	/* register not managed by the allocator? */
+	if (counter > NMI_MAX_COUNTER_BITS)
+		return;
 
 	clear_bit(counter, perfctr_nmi_owner);
 }

@@ -142,7 +146,9 @@ int reserve_evntsel_nmi(unsigned int msr
 	unsigned int counter;
 
 	counter = nmi_evntsel_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+	/* register not managed by the allocator? */
+	if (counter > NMI_MAX_COUNTER_BITS)
+		return 1;
 
 	if (!test_and_set_bit(counter, evntsel_nmi_owner))
 		return 1;

@@ -154,7 +160,9 @@ void release_evntsel_nmi(unsigned int ms
 	unsigned int counter;
 
 	counter = nmi_evntsel_msr_to_bit(msr);
-	BUG_ON(counter > NMI_MAX_COUNTER_BITS);
+	/* register not managed by the allocator? */
+	if (counter > NMI_MAX_COUNTER_BITS)
+		return;
 
 	clear_bit(counter, evntsel_nmi_owner);
 }

Index: linux/arch/i386/oprofile/nmi_int.c
===================================================================
@@ -269,7 +269,6 @@ 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);
 }
 
  

@@ -278,6 +277,7 @@ static void nmi_shutdown(void)
 	nmi_enabled = 0;
 	on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
 	unregister_die_notifier(&profile_exceptions_nb);
+	model->shutdown(cpu_msrs);
 	free_msrs();
 }
 

Index: linux/arch/x86_64/mm/numa.c
===================================================================
@@ -166,7 +166,7 @@ early_node_mem(int nodeid, unsigned long
 		return __va(mem);
 	ptr = __alloc_bootmem_nopanic(size,
 				SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
-	if (ptr == 0) {
+	if (ptr == NULL) {
 		printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
 			size, nodeid);
 		return NULL;

Index: linux/arch/x86_64/kernel/pci-gart.c
===================================================================
@@ -8,6 +8,7 @@
  * See Documentation/DMA-mapping.txt for the interface specification.
  * 
  * Copyright 2002 Andi Kleen, SuSE Labs.
+ * Subject to the GNU General Public License v2 only.
  */
 
 #include <linux/types.h>

@@ -374,7 +375,8 @@ static inline int dma_map_cont(struct sc
  * DMA map all entries in a scatterlist.
  * Merge chunks that have page aligned sizes into a continuous mapping. 
  */
-int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
+static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+			int dir)
 {
 	int i;
 	int out;

Index: linux/arch/x86_64/kernel/pci-dma.c
===================================================================
@@ -11,7 +11,7 @@
 #include <asm/iommu.h>
 #include <asm/calgary.h>
 
-int iommu_merge __read_mostly = 0;
+int iommu_merge __read_mostly = 1;
 EXPORT_SYMBOL(iommu_merge);
 
 dma_addr_t bad_dma_address __read_mostly;

Index: linux/arch/i386/oprofile/backtrace.c
===================================================================
@@ -13,25 +13,45 @@
 #include <linux/mm.h>
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
+#include <asm/stacktrace.h>
 
-struct frame_head {
-	struct frame_head * ebp;
-	unsigned long ret;
-} __attribute__((packed));
+static void backtrace_warning_symbol(void *data, char *msg,
+				     unsigned long symbol)
+{
+	/* Ignore warnings */
+}
 
-static struct frame_head *
-dump_kernel_backtrace(struct frame_head * head)
+static void backtrace_warning(void *data, char *msg)
 {
-	oprofile_add_trace(head->ret);
+	/* Ignore warnings */
+}
 
-	/* frame pointers should strictly progress back up the stack
-	 * (towards higher addresses) */
-	if (head >= head->ebp)
-		return NULL;
+static int backtrace_stack(void *data, char *name)
+{
+	/* Yes, we want all stacks */
+	return 0;
+}
 
-	return head->ebp;
+static void backtrace_address(void *data, unsigned long addr)
+{
+	unsigned int *depth = data;
+
+	if ((*depth)--)
+		oprofile_add_trace(addr);
 }
 
+static struct stacktrace_ops backtrace_ops = {
+	.warning = backtrace_warning,
+	.warning_symbol = backtrace_warning_symbol,
+	.stack = backtrace_stack,
+	.address = backtrace_address,
+};
+
+struct frame_head {
+	struct frame_head * ebp;
+	unsigned long ret;
+} __attribute__((packed));
+
 static struct frame_head *
 dump_user_backtrace(struct frame_head * head)
 {

@@ -53,72 +73,24 @@ dump_user_backtrace(struct frame_head * 
 	return bufhead[0].ebp;
 }
 
-/*
- * |             | /\ Higher addresses
- * |             |
- * --------------- stack base (address of current_thread_info)
- * | thread info |
- * .             .
- * |    stack    |
- * --------------- saved regs->ebp value if valid (frame_head address)
- * .             .
- * --------------- saved regs->rsp value if x86_64
- * |             |
- * --------------- struct pt_regs * stored on stack if 32-bit
- * |             |
- * .             .
- * |             |
- * --------------- %esp
- * |             |
- * |             | \/ Lower addresses
- *
- * Thus, regs (or regs->rsp for x86_64) <-> stack base restricts the
- * valid(ish) ebp values. Note: (1) for x86_64, NMI and several other
- * exceptions use special stacks, maintained by the interrupt stack table
- * (IST). These stacks are set up in trap_init() in
- * arch/x86_64/kernel/traps.c. Thus, for x86_64, regs now does not point
- * to the kernel stack; instead, it points to some location on the NMI
- * stack. On the other hand, regs->rsp is the stack pointer saved when the
- * NMI occurred. (2) For 32-bit, regs->esp is not valid because the
- * processor does not save %esp on the kernel stack when interrupts occur
- * in the kernel mode.
- */
-#ifdef CONFIG_FRAME_POINTER
-static int valid_kernel_stack(struct frame_head * head, struct pt_regs * regs)
-{
-	unsigned long headaddr = (unsigned long)head;
-#ifdef CONFIG_X86_64
-	unsigned long stack = (unsigned long)regs->rsp;
-#else
-	unsigned long stack = (unsigned long)regs;
-#endif
-	unsigned long stack_base = (stack & ~(THREAD_SIZE - 1)) + THREAD_SIZE;
-
-	return headaddr > stack && headaddr < stack_base;
-}
-#else
-/* without fp, it's just junk */
-static int valid_kernel_stack(struct frame_head * head, struct pt_regs * regs)
-{
-	return 0;
-}
-#endif
-
-
 void
 x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
 	struct frame_head *head;
+	unsigned long stack;
 
 #ifdef CONFIG_X86_64
 	head = (struct frame_head *)regs->rbp;
+	stack = regs->rsp;
 #else
 	head = (struct frame_head *)regs->ebp;
+	stack = regs->esp;
 #endif
 
 	if (!user_mode_vm(regs)) {
-		while (depth-- && valid_kernel_stack(head, regs))
-			head = dump_kernel_backtrace(head);
+		if (depth)
+			dump_trace(NULL, regs, (unsigned long *)stack,
+				   &backtrace_ops, &depth);
 		return;
 	}
 

Index: linux/arch/i386/oprofile/backtrace.c
===================================================================
@@ -76,16 +76,8 @@ dump_user_backtrace(struct frame_head * 
 void
 x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
-	struct frame_head *head;
-	unsigned long stack;
-
-#ifdef CONFIG_X86_64
-	head = (struct frame_head *)regs->rbp;
-	stack = regs->rsp;
-#else
-	head = (struct frame_head *)regs->ebp;
-	stack = regs->esp;
-#endif
+	struct frame_head *head = (struct frame_head *)frame_pointer(regs);
+	unsigned long stack = stack_pointer(regs);
 
 	if (!user_mode_vm(regs)) {
 		if (depth)

Index: linux/include/asm-i386/ptrace.h
===================================================================
@@ -55,6 +55,8 @@ static inline int v8086_mode(struct pt_r
 }
 
 #define instruction_pointer(regs) ((regs)->eip)
+#define frame_pointer(regs) ((regs)->ebp)
+#define stack_pointer(regs) ((regs)->esp)
 #define regs_return_value(regs) ((regs)->eax)
 
 extern unsigned long profile_pc(struct pt_regs *regs);

Index: linux/include/asm-x86_64/ptrace.h
===================================================================
@@ -40,6 +40,8 @@ struct pt_regs {
 #define user_mode(regs) (!!((regs)->cs & 3))
 #define user_mode_vm(regs) user_mode(regs)
 #define instruction_pointer(regs) ((regs)->rip)
+#define frame_pointer(regs) ((regs)->rbp)
+#define stack_pointer(regs) ((regs)->rsp)
 #define regs_return_value(regs) ((regs)->rax)
 
 extern unsigned long profile_pc(struct pt_regs *regs);

Index: linux/arch/x86_64/kernel/apic.c
===================================================================
@@ -283,23 +283,6 @@ int __init verify_local_APIC(void)
 	return 1;
 }
 
-void __init sync_Arb_IDs(void)
-{
-	/* Unsupported on P4 - see Intel Dev. Manual Vol. 3, Ch. 8.6.1 */
-	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-	if (ver >= 0x14)	/* P4 or higher */
-		return;
-
-	/*
-	 * Wait for idle.
-	 */
-	apic_wait_icr_idle();
-
-	apic_printk(APIC_DEBUG, "Synchronizing Arb IDs.\n");
-	apic_write(APIC_ICR, APIC_DEST_ALLINC | APIC_INT_LEVELTRIG
-				| APIC_DM_INIT);
-}
-
 /*
  * An initial setup of the virtual wire mode.
  */

Index: linux/arch/x86_64/kernel/io_apic.c
===================================================================
@@ -1784,7 +1784,6 @@ void __init setup_IO_APIC(void)
 
 	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
 
-	sync_Arb_IDs();
 	setup_IO_APIC_irqs();
 	init_IO_APIC_traps();
 	check_timer();

Index: linux/arch/x86_64/kernel/apic.c
===================================================================
@@ -419,6 +419,14 @@ void __cpuinit setup_local_APIC (void)
 		value = APIC_DM_NMI | APIC_LVT_MASKED;
 	apic_write(APIC_LVT1, value);
 
+	/*
+	 * Now enable IO-APICs, actually call clear_IO_APIC
+	 * We need clear_IO_APIC before enabling vector on BP
+	 */
+	if (!smp_processor_id())
+	if (!skip_ioapic_setup && nr_ioapics)
+		enable_IO_APIC();
+
 	{
 		unsigned oldvalue;
 		maxlvt = get_maxlvt();

Index: linux/arch/x86_64/kernel/io_apic.c
===================================================================
@@ -1166,7 +1166,7 @@ void __apicdebuginit print_PIC(void)
 
 #endif  /*  0  */
 
-static void __init enable_IO_APIC(void)
+void __init enable_IO_APIC(void)
 {
 	union IO_APIC_reg_01 reg_01;
 	int i8259_apic, i8259_pin;

@@ -1775,7 +1775,10 @@ __setup("no_timer_check", notimercheck);
 
 void __init setup_IO_APIC(void)
 {
-	enable_IO_APIC();
+
+	/*
+	 * calling enable_IO_APIC() is moved to setup_local_APIC for BP
+	 */
 
 	if (acpi_ioapic)
 		io_apic_irqs = ~0;	/* all IRQs go through IOAPIC */

Index: linux/include/asm-x86_64/hw_irq.h
===================================================================
@@ -135,6 +135,7 @@ extern void init_8259A(int aeoi);
 extern void send_IPI_self(int vector);
 extern void init_VISWS_APIC_irqs(void);
 extern void setup_IO_APIC(void);
+extern void enable_IO_APIC(void);
 extern void disable_IO_APIC(void);
 extern void print_IO_APIC(void);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);

Index: linux/arch/x86_64/kernel/ldt.c
===================================================================
@@ -98,13 +98,13 @@ int init_new_context(struct task_struct 
 	struct mm_struct * old_mm;
 	int retval = 0;
 
-	init_MUTEX(&mm->context.sem);
+	mutex_init(&mm->context.lock);
 	mm->context.size = 0;
 	old_mm = current->mm;
 	if (old_mm && old_mm->context.size > 0) {
-		down(&old_mm->context.sem);
+		mutex_lock(&old_mm->context.lock);
 		retval = copy_ldt(&mm->context, &old_mm->context);
-		up(&old_mm->context.sem);
+		mutex_unlock(&old_mm->context.lock);
 	}
 	return retval;
 }

@@ -135,7 +135,7 @@ static int read_ldt(void __user * ptr, u
 	if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES;
 
-	down(&mm->context.sem);
+	mutex_lock(&mm->context.lock);
 	size = mm->context.size*LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;

@@ -143,7 +143,7 @@ static int read_ldt(void __user * ptr, u
 	err = 0;
 	if (copy_to_user(ptr, mm->context.ldt, size))
 		err = -EFAULT;
-	up(&mm->context.sem);
+	mutex_unlock(&mm->context.lock);
 	if (err < 0)
 		goto error_return;
 	if (size != bytecount) {

@@ -195,7 +195,7 @@ static int write_ldt(void __user * ptr, 
 			goto out;
 	}
 
-	down(&mm->context.sem);
+	mutex_lock(&mm->context.lock);
 	if (ldt_info.entry_number >= (unsigned)mm->context.size) {
 		error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1);
 		if (error < 0)

@@ -225,7 +225,7 @@ install:
 	error = 0;
 
 out_unlock:
-	up(&mm->context.sem);
+	mutex_unlock(&mm->context.lock);
 out:
 	return error;
 }

Index: linux/arch/x86_64/kernel/ptrace.c
===================================================================
@@ -104,7 +104,7 @@ unsigned long convert_rip_to_linear(stru
 
 		seg &= ~7UL;
 
-		down(&child->mm->context.sem);
+		mutex_lock(&child->mm->context.lock);
 		if (unlikely((seg >> 3) >= child->mm->context.size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {

@@ -118,7 +118,7 @@ unsigned long convert_rip_to_linear(stru
 				addr &= 0xffff;
 			addr += base;
 		}
-		up(&child->mm->context.sem);
+		mutex_unlock(&child->mm->context.lock);
 	}
 
 	return addr;

Index: linux/include/asm-x86_64/mmu.h
===================================================================
@@ -2,7 +2,7 @@
 #define __x86_64_MMU_H
 
 #include <linux/spinlock.h>
-#include <asm/semaphore.h>
+#include <linux/mutex.h>
 
 /*
  * The x86_64 doesn't have a mmu context, but

@@ -14,7 +14,7 @@ typedef struct { 
 	void *ldt;
 	rwlock_t ldtlock; 
 	int size;
-	struct semaphore sem; 
+	struct mutex lock;
 	void *vdso;
 } mm_context_t;
 

Index: linux/include/asm-x86_64/numa.h
===================================================================
@@ -2,6 +2,7 @@
 #define _ASM_X8664_NUMA_H 1
 
 #include <linux/nodemask.h>
+#include <asm/apicdef.h>
 
 struct bootnode {
 	u64 start,end; 

@@ -19,7 +20,7 @@ extern void numa_set_node(int cpu, int n
 extern void srat_reserve_add_area(int nodeid);
 extern int hotadd_percent;
 
-extern unsigned char apicid_to_node[256];
+extern unsigned char apicid_to_node[MAX_LOCAL_APIC];
 #ifdef CONFIG_NUMA
 extern void __init init_cpu_to_node(void);
 

Index: linux/arch/i386/kernel/process.c
===================================================================
@@ -297,34 +297,52 @@ static int __init idle_setup(char *str)
 }
 early_param("idle", idle_setup);
 
-void show_regs(struct pt_regs * regs)
+void __show_registers(struct pt_regs *regs, int all)
 {
 	unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L;
 	unsigned long d0, d1, d2, d3, d6, d7;
+	unsigned long esp;
+	unsigned short ss, gs;
+
+	if (user_mode_vm(regs)) {
+		esp = regs->esp;
+		ss = regs->xss & 0xffff;
+		savesegment(gs, gs);
+	} else {
+		esp = (unsigned long) (&regs->esp);
+		savesegment(ss, ss);
+		savesegment(gs, gs);
+	}
 
 	printk("\n");
-	printk("Pid: %d, comm: %20s\n", current->pid, current->comm);
-	printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id());
+	printk("Pid: %d, comm: %.*s %s (%s %.*s)\n",
+			current->pid, TASK_COMM_LEN, current->comm,
+			print_tainted(), init_utsname()->release,
+			(int)strcspn(init_utsname()->version, " "),
+			init_utsname()->version);
+
+	printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n",
+			0xffff & regs->xcs, regs->eip, regs->eflags,
+			smp_processor_id());
 	print_symbol("EIP is at %s\n", regs->eip);
 
-	if (user_mode_vm(regs))
-		printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
-	printk(" EFLAGS: %08lx    %s  (%s %.*s)\n",
-	       regs->eflags, print_tainted(), init_utsname()->release,
-	       (int)strcspn(init_utsname()->version, " "),
-	       init_utsname()->version);
 	printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
-		regs->eax,regs->ebx,regs->ecx,regs->edx);
-	printk("ESI: %08lx EDI: %08lx EBP: %08lx",
-		regs->esi, regs->edi, regs->ebp);
-	printk(" DS: %04x ES: %04x FS: %04x\n",
-	       0xffff & regs->xds,0xffff & regs->xes, 0xffff & regs->xfs);
+		regs->eax, regs->ebx, regs->ecx, regs->edx);
+	printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n",
+		regs->esi, regs->edi, regs->ebp, esp);
+	printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n",
+	       regs->xds & 0xffff, regs->xes & 0xffff,
+	       regs->xfs & 0xffff, gs, ss);
+
+	if (!all)
+		return;
 
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = read_cr3();
 	cr4 = read_cr4_safe();
-	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
+	printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n",
+			cr0, cr2, cr3, cr4);
 
 	get_debugreg(d0, 0);
 	get_debugreg(d1, 1);

@@ -332,10 +350,16 @@ void show_regs(struct pt_regs * regs)
 	get_debugreg(d3, 3);
 	printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
 			d0, d1, d2, d3);
+
 	get_debugreg(d6, 6);
 	get_debugreg(d7, 7);
-	printk("DR6: %08lx DR7: %08lx\n", d6, d7);
+	printk("DR6: %08lx DR7: %08lx\n",
+			d6, d7);
+}
 
+void show_regs(struct pt_regs * regs)
+{
+	__show_registers(regs, 1);
 	show_trace(NULL, regs, &regs->esp);
 }
 

Index: linux/arch/i386/kernel/traps.c
===================================================================
@@ -358,33 +358,9 @@ EXPORT_SYMBOL(dump_stack);
 void show_registers(struct pt_regs *regs)
 {
 	int i;
-	int in_kernel = 1;
-	unsigned long esp;
-	unsigned short ss, gs;
-
-	esp = (unsigned long) (&regs->esp);
-	savesegment(ss, ss);
-	savesegment(gs, gs);
-	if (user_mode_vm(regs)) {
-		in_kernel = 0;
-		esp = regs->esp;
-		ss = regs->xss & 0xffff;
-	}
+
 	print_modules();
-	printk(KERN_EMERG "CPU:    %d\n"
-		KERN_EMERG "EIP:    %04x:[<%08lx>]    %s VLI\n"
-		KERN_EMERG "EFLAGS: %08lx   (%s %.*s)\n",
-		smp_processor_id(), 0xffff & regs->xcs, regs->eip,
-		print_tainted(), regs->eflags, init_utsname()->release,
-		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version);
-	print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip);
-	printk(KERN_EMERG "eax: %08lx   ebx: %08lx   ecx: %08lx   edx: %08lx\n",
-		regs->eax, regs->ebx, regs->ecx, regs->edx);
-	printk(KERN_EMERG "esi: %08lx   edi: %08lx   ebp: %08lx   esp: %08lx\n",
-		regs->esi, regs->edi, regs->ebp, esp);
-	printk(KERN_EMERG "ds: %04x   es: %04x   fs: %04x  gs: %04x  ss: %04x\n",
-	       regs->xds & 0xffff, regs->xes & 0xffff, regs->xfs & 0xffff, gs, ss);
+	__show_registers(regs, 0);
 	printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)",
 		TASK_COMM_LEN, current->comm, current->pid,
 		current_thread_info(), current, task_thread_info(current));

@@ -392,14 +368,14 @@ void show_registers(struct pt_regs *regs
 	 * When in-kernel, we also print out the stack and code at the
 	 * time of the fault..
 	 */
-	if (in_kernel) {
+	if (!user_mode_vm(regs)) {
 		u8 *eip;
 		unsigned int code_prologue = code_bytes * 43 / 64;
 		unsigned int code_len = code_bytes;
 		unsigned char c;
 
 		printk("\n" KERN_EMERG "Stack: ");
-		show_stack_log_lvl(NULL, regs, (unsigned long *)esp, KERN_EMERG);
+		show_stack_log_lvl(NULL, regs, &regs->esp, KERN_EMERG);
 
 		printk(KERN_EMERG "Code: ");
 

Index: linux/include/asm-i386/system.h
===================================================================
@@ -318,5 +318,6 @@ extern unsigned long arch_align_stack(un
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
 void default_idle(void);
+void __show_registers(struct pt_regs *, int all);
 
 #endif

Index: linux/arch/i386/kernel/cpu/mtrr/main.c
===================================================================
@@ -738,13 +738,7 @@ void mtrr_ap_init(void)
  */
 void mtrr_save_state(void)
 {
-	int cpu = get_cpu();
-
-	if (cpu == 0)
-		mtrr_save_fixed_ranges(NULL);
-	else
-		smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
-	put_cpu();
+	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
 }
 
 static int __init mtrr_init_finialize(void)

Index: linux/arch/i386/mach-generic/probe.c
===================================================================
@@ -22,7 +22,7 @@ extern struct genapic apic_default;
 
 struct genapic *genapic = &apic_default;
 
-struct genapic *apic_probe[] __initdata = { 
+static struct genapic *apic_probe[] __initdata = {
 	&apic_summit,
 	&apic_bigsmp, 
 	&apic_es7000,

Index: linux/include/asm-x86_64/unistd.h
===================================================================
@@ -676,6 +676,7 @@ asmlinkage long sys_rt_sigaction(int sig
 #endif	/* __KERNEL__ */
 #endif	/* __NO_STUBS */
 
+#ifdef __KERNEL__
 /*
  * "Conditional" syscalls
  *

@@ -683,5 +684,6 @@ asmlinkage long sys_rt_sigaction(int sig
  * but it doesn't work on all toolchains, so we just do it by hand
  */
 #define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+#endif	/* __KERNEL__ */
 
 #endif /* _ASM_X86_64_UNISTD_H_ */

Index: linux/arch/i386/mach-es7000/es7000plat.c
===================================================================
@@ -46,11 +46,11 @@
  * ES7000 Globals
  */
 
-volatile unsigned long	*psai = NULL;
-struct mip_reg		*mip_reg;
-struct mip_reg		*host_reg;
-int 			mip_port;
-unsigned long		mip_addr, host_addr;
+static volatile unsigned long	*psai = NULL;
+static struct mip_reg		*mip_reg;
+static struct mip_reg		*host_reg;
+static int 			mip_port;
+static unsigned long		mip_addr, host_addr;
 
 /*
  * GSI override for ES7000 platforms.

@@ -288,28 +288,8 @@ es7000_start_cpu(int cpu, unsigned long 
 
 }
 
-int
-es7000_stop_cpu(int cpu)
-{
-	int startup;
-
-	if (psai == NULL)
-		return -1;
-
-	startup= (0x1000000 | cpu);
-
-	while ((*psai & 0xff00ffff) != startup)
-		;
-
-	startup = (*psai & 0xff0000) >> 16;
-	*psai &= 0xffffff;
-
-	return 0;
-
-}
-
 void __init
-es7000_sw_apic()
+es7000_sw_apic(void)
 {
 	if (es7000_plat) {
 		int mip_status;

Index: linux/arch/i386/kernel/topology.c
===================================================================
@@ -51,8 +51,6 @@ int arch_register_cpu(int num)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int enable_cpu_hotplug = 1;
-
 void arch_unregister_cpu(int num) {
 	return unregister_cpu(&cpu_devices[num].cpu);
 }

Index: linux/include/asm-i386/cpu.h
===================================================================
@@ -13,7 +13,7 @@ struct i386_cpu {
 extern int arch_register_cpu(int num);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void arch_unregister_cpu(int);
-extern int enable_cpu_hotplug;
+#define enable_cpu_hotplug	1
 #else
 #define enable_cpu_hotplug	0
 #endif

Index: linux/arch/i386/mm/discontig.c
===================================================================
@@ -103,14 +103,14 @@ extern unsigned long highend_pfn, highst
 
 #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE)
 
-unsigned long node_remap_start_pfn[MAX_NUMNODES];
+static unsigned long node_remap_start_pfn[MAX_NUMNODES];
 unsigned long node_remap_size[MAX_NUMNODES];
-unsigned long node_remap_offset[MAX_NUMNODES];
-void *node_remap_start_vaddr[MAX_NUMNODES];
+static unsigned long node_remap_offset[MAX_NUMNODES];
+static void *node_remap_start_vaddr[MAX_NUMNODES];
 void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
-void *node_remap_end_vaddr[MAX_NUMNODES];
-void *node_remap_alloc_vaddr[MAX_NUMNODES];
+static void *node_remap_end_vaddr[MAX_NUMNODES];
+static void *node_remap_alloc_vaddr[MAX_NUMNODES];
 static unsigned long kva_start_pfn;
 static unsigned long kva_pages;
 /*

Index: linux/arch/x86_64/kernel/io_apic.c
===================================================================
@@ -1847,7 +1847,7 @@ static struct sysdev_class ioapic_sysdev
 static int __init ioapic_init_sysfs(void)
 {
 	struct sys_device * dev;
-	int i, size, error = 0;
+	int i, size, error;
 
 	error = sysdev_class_register(&ioapic_sysdev_class);
 	if (error)

@@ -1856,12 +1856,11 @@ static int __init ioapic_init_sysfs(void
 	for (i = 0; i < nr_ioapics; i++ ) {
 		size = sizeof(struct sys_device) + nr_ioapic_registers[i]
 			* sizeof(struct IO_APIC_route_entry);
-		mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
+		mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL);
 		if (!mp_ioapic_data[i]) {
 			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
 			continue;
 		}
-		memset(mp_ioapic_data[i], 0, size);
 		dev = &mp_ioapic_data[i]->dev;
 		dev->id = i;
 		dev->cls = &ioapic_sysdev_class;

Index: linux/arch/i386/kernel/smpboot.c
===================================================================
@@ -118,7 +118,7 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 };
  * has made sure it's suitably aligned.
  */
 
-static unsigned long __devinit setup_trampoline(void)
+static unsigned long __cpuinit setup_trampoline(void)
 {
 	memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data);
 	return virt_to_phys(trampoline_base);

Index: linux/arch/x86_64/kernel/time.c
===================================================================
@@ -360,7 +360,7 @@ void stop_timer_interrupt(void)
 
 static struct irqaction irq0 = {
 	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_IRQPOLL,
+	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
 	.mask		= CPU_MASK_NONE,
 	.name		= "timer"
 };

Index: linux/arch/i386/kernel/vmi.c
===================================================================
@@ -242,7 +242,7 @@ static void vmi_nop(void)
 {
 }
 
-#ifdef CONFIG_DEBUG_PAGE_TYPE
+#if 0 /* debug page type */
 
 #ifdef CONFIG_X86_PAE
 #define MAX_BOOT_PTS (2048+4+1)

@@ -343,7 +343,7 @@ static void vmi_check_page_type(u32 pfn,
 #else
 #define vmi_set_page_type(p,t) do { } while (0)
 #define vmi_check_page_type(p,t) do { } while (0)
-#endif
+#endif /* debug page type */
 
 #ifdef CONFIG_HIGHPTE
 static void *vmi_kmap_atomic_pte(struct page *page, enum km_type type)

Index: linux/arch/i386/kernel/signal.c
===================================================================
@@ -387,7 +387,6 @@ static int setup_frame(int sig, struct k
 	regs->edx = (unsigned long) 0;
 	regs->ecx = (unsigned long) 0;
 
-	set_fs(USER_DS);
 	regs->xds = __USER_DS;
 	regs->xes = __USER_DS;
 	regs->xss = __USER_DS;

@@ -481,7 +480,6 @@ static int setup_rt_frame(int sig, struc
 	regs->edx = (unsigned long) &frame->info;
 	regs->ecx = (unsigned long) &frame->uc;
 
-	set_fs(USER_DS);
 	regs->xds = __USER_DS;
 	regs->xes = __USER_DS;
 	regs->xss = __USER_DS;

Index: linux/arch/x86_64/kernel/head64.c
===================================================================
@@ -70,7 +70,7 @@ void __init x86_64_start_kernel(char * r
 
 	for (i = 0; i < IDT_ENTRIES; i++)
 		set_intr_gate(i, early_idt_handler);
-	asm volatile("lidt %0" :: "m" (idt_descr));
+	load_idt((const struct desc_ptr *)&idt_descr);
 
 	early_printk("Kernel alive\n");
 

Index: linux/arch/x86_64/kernel/reboot.c
===================================================================
@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <asm/io.h>
 #include <asm/delay.h>
+#include <asm/desc.h>
 #include <asm/hw_irq.h>
 #include <asm/system.h>
 #include <asm/pgtable.h>

@@ -136,7 +137,7 @@ void machine_emergency_restart(void)
 		}
 
 		case BOOT_TRIPLE: 
-			__asm__ __volatile__("lidt (%0)": :"r" (&no_idt));
+			load_idt((const struct desc_ptr *)&no_idt);
 			__asm__ __volatile__("int3");
 
 			reboot_type = BOOT_KBD;

Index: linux/arch/x86_64/kernel/setup64.c
===================================================================
@@ -224,8 +224,8 @@ void __cpuinit cpu_init (void)
  		memcpy(cpu_gdt(cpu), cpu_gdt_table, GDT_SIZE);
 
 	cpu_gdt_descr[cpu].size = GDT_SIZE;
-	asm volatile("lgdt %0" :: "m" (cpu_gdt_descr[cpu]));
-	asm volatile("lidt %0" :: "m" (idt_descr));
+	load_gdt((const struct desc_ptr *)&cpu_gdt_descr[cpu]);
+	load_idt((const struct desc_ptr *)&idt_descr);
 
 	memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
 	syscall_init();

Index: linux/arch/x86_64/kernel/suspend.c
===================================================================
@@ -32,9 +32,9 @@ void __save_processor_state(struct saved
 	/*
 	 * descriptor tables
 	 */
-	asm volatile ("sgdt %0" : "=m" (ctxt->gdt_limit));
-	asm volatile ("sidt %0" : "=m" (ctxt->idt_limit));
-	asm volatile ("str %0"  : "=m" (ctxt->tr));
+	store_gdt((struct desc_ptr *)&ctxt->gdt_limit);
+	store_idt((struct desc_ptr *)&ctxt->idt_limit);
+	store_tr(ctxt->tr);
 
 	/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
 	/*

@@ -91,8 +91,9 @@ void __restore_processor_state(struct sa
 	 * now restore the descriptor tables to their proper values
 	 * ltr is done i fix_processor_context().
 	 */
-	asm volatile ("lgdt %0" :: "m" (ctxt->gdt_limit));
-	asm volatile ("lidt %0" :: "m" (ctxt->idt_limit));
+	load_gdt((const struct desc_ptr *)&ctxt->gdt_limit);
+	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
+
 
 	/*
 	 * segment registers

Index: linux/include/asm-x86_64/desc.h
===================================================================
@@ -20,6 +20,15 @@ extern struct desc_struct cpu_gdt_table[
 #define load_LDT_desc() asm volatile("lldt %w0"::"r" (GDT_ENTRY_LDT*8))
 #define clear_LDT()  asm volatile("lldt %w0"::"r" (0))
 
+static inline unsigned long __store_tr(void)
+{
+       unsigned long tr;
+       asm volatile ("str %w0":"=r" (tr));
+       return tr;
+}
+
+#define store_tr(tr) (tr) = __store_tr()
+
 /*
  * This is the ldt that every process will get unless we need
  * something other than this.

@@ -31,6 +40,16 @@ extern struct desc_ptr cpu_gdt_descr[];
 /* the cpu gdt accessor */
 #define cpu_gdt(_cpu) ((struct desc_struct *)cpu_gdt_descr[_cpu].address)
 
+static inline void load_gdt(const struct desc_ptr *ptr)
+{
+	asm volatile("lgdt %w0"::"m" (*ptr));
+}
+
+static inline void store_gdt(struct desc_ptr *ptr)
+{
+       asm ("sgdt %w0":"=m" (*ptr));
+}
+
 static inline void _set_gate(void *adr, unsigned type, unsigned long func, unsigned dpl, unsigned ist)  
 {
 	struct gate_struct s; 	

@@ -71,6 +90,16 @@ static inline void set_system_gate_ist(i
 	_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, ist);
 }
 
+static inline void load_idt(const struct desc_ptr *ptr)
+{
+	asm volatile("lidt %w0"::"m" (*ptr));
+}
+
+static inline void store_idt(struct desc_ptr *dtr)
+{
+       asm ("sidt %w0":"=m" (*dtr));
+}
+
 static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned type, 
 					 unsigned size) 
 { 

Index: linux/arch/i386/xen/enlighten.c
===================================================================
@@ -25,7 +25,6 @@
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
-#include <linux/smp.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/physdev.h>

Index: linux/arch/i386/xen/mmu.c
===================================================================
@@ -41,7 +41,6 @@
 #include <linux/sched.h>
 #include <linux/highmem.h>
 #include <linux/bug.h>
-#include <linux/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>