x86 candidate patches for review III: various stuff

Index: linux/include/linux/cpufreq.h
===================================================================
@@ -32,7 +32,15 @@
  *                     CPUFREQ NOTIFIER INTERFACE                    *
  *********************************************************************/
 
+#ifdef CONFIG_CPU_FREQ
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
+#else
+static inline int cpufreq_register_notifier(struct notifier_block *nb,
+						unsigned int list)
+{
+	return 0;
+}
+#endif
 int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list);
 
 #define CPUFREQ_TRANSITION_NOTIFIER	(0)

@@ -261,17 +269,22 @@ int cpufreq_set_policy(struct cpufreq_po
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
 int cpufreq_update_policy(unsigned int cpu);
 
-/* query the current CPU frequency (in kHz). If zero, cpufreq couldn't detect it */
-unsigned int cpufreq_get(unsigned int cpu);
 
-/* query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it */
+/*
+ * query the last known CPU freq (in kHz). If zero, cpufreq couldn't detect it
+ */
 #ifdef CONFIG_CPU_FREQ
 unsigned int cpufreq_quick_get(unsigned int cpu);
+unsigned int cpufreq_get(unsigned int cpu);
 #else
 static inline unsigned int cpufreq_quick_get(unsigned int cpu)
 {
 	return 0;
 }
+static inline unsigned int cpufreq_get(unsigned int cpu)
+{
+	return 0;
+}
 #endif
 
 

Index: linux/arch/i386/kernel/sched-clock.c
===================================================================
@@ -0,0 +1,213 @@
+/* A fast clock for the scheduler. */
+#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;		/* TSC or jiffies at syncpoint*/
+	unsigned long long ns_base;		/* nanoseconds at sync point */
+	unsigned long long last_val;		/* Last returned value */
+};
+
+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;
+}
+
+/*
+ * 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 sched_clock(void)
+{
+	unsigned long long r;
+	struct sc_data *sc = &get_cpu_var(sc_data);
+
+	if (sc->unstable) {
+		unsigned long flags;
+		r = (jiffies_64 - sc->sync_base) * (1000000000 / HZ);
+		r += sc->ns_base;
+		local_irq_save(flags);
+		/* last_val is used to avoid non monotonity on a
+		   stable->unstable transition. Make sure the time
+		   never goes to before the last value returned by
+		   the TSC clock */
+		if (r <= sc->last_val)
+			r = sc->last_val + 1;
+		sc->last_val = r;
+		local_irq_restore(flags);
+	} else {
+		get_scheduled_cycles(r);
+		r = cycles_2_ns(sc, r);
+		sc->last_val = r;
+	}
+
+	put_cpu_var(sc_data);
+
+	return r;
+}
+
+/* Resync with new CPU frequency */
+static void resync_sc_freq(struct sc_data *sc, unsigned int newfreq)
+{
+	sc->sync_base = jiffies;
+	if (!cpu_has_tsc) {
+		sc->unstable = 1;
+		return;
+	}
+	/* Handle nesting, but when we're zero multiple calls in a row
+	   are ok too and not a bug */
+	if (sc->unstable > 0)
+		sc->unstable--;
+	/* RED-PEN protect with seqlock? I hope that's not needed
+	   because sched_clock callers should be able to tolerate small
+	   errors. */
+	sc->ns_base = ktime_to_ns(ktime_get());
+	get_scheduled_cycles(sc->sync_base);
+	sc->cyc2ns_scale = (1000000 << CYC2NS_SCALE_FACTOR) / newfreq;
+}
+
+static void call_r_s_f(void *arg)
+{
+	struct cpufreq_freqs *freq = arg;
+	unsigned f = freq->new;
+	if (!f)
+		f = cpufreq_get(freq->cpu);
+	if (!f)
+		f = tsc_khz;
+	resync_sc_freq(&per_cpu(sc_data, freq->cpu), f);
+}
+
+static void call_r_s_f_here(void *arg)
+{
+	struct cpufreq_freqs f = { .cpu = get_cpu(), .new = 0 };
+	call_r_s_f(&f);
+	put_cpu();
+}
+
+static int sc_freq_event(struct notifier_block *nb, unsigned long event,
+			 void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	int cpu = get_cpu();
+	struct sc_data *sc = &per_cpu(sc_data, cpu);
+
+	if (cpu_has(&cpu_data[cpu], X86_FEATURE_CONSTANT_TSC))
+		goto out;
+	if (freq->old == freq->new)
+		goto out;
+
+	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 */
+		sc->unstable++;
+		break;
+	case CPUFREQ_RESUMECHANGE:
+	case CPUFREQ_POSTCHANGE:
+		/* Frequency change or resume is done -- update everything and
+		   mark TSC as stable again. */
+		if (cpu == freq->cpu)
+			resync_sc_freq(sc, freq->new);
+		else
+			smp_call_function_single(freq->cpu, call_r_s_f,
+						 freq, 0, 1);
+		break;
+	}
+out:
+	put_cpu();
+	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, call_r_s_f, &f, 0, 1);
+	}
+	return NOTIFY_DONE;
+}
+
+static __init int init_sched_clock(void)
+{
+	/* On a race between the various events the initialization might be
+	   done multiple times, but that is handled */
+	cpufreq_register_notifier(&sc_freq_notifier,
+				CPUFREQ_TRANSITION_NOTIFIER);
+	hotcpu_notifier(sc_cpu_event, 0);
+	on_each_cpu(call_r_s_f_here, NULL, 0, 0);
+	return 0;
+}
+core_initcall(init_sched_clock);
+

80 lines not on this page · raw message

Index: linux/arch/x86_64/kernel/tsc.c
===================================================================
@@ -16,32 +16,6 @@ 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;
 
 static inline int check_tsc_unstable(void)

@@ -114,8 +88,6 @@ static int time_cpufreq_notifier(struct 
 			mark_tsc_unstable();
 	}
 
-	set_cyc2ns_scale(tsc_khz_ref);
-
 	return 0;
 }
 

Index: linux/include/asm-x86_64/timer.h
===================================================================
@@ -0,0 +1 @@
+#define get_scheduled_cycles(x) rdtscll(x)

Index: linux/arch/x86_64/kernel/time.c
===================================================================
@@ -404,7 +404,6 @@ 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
===================================================================
@@ -28,5 +28,4 @@ extern int read_current_timer(unsigned l
 #define US_SCALE        32 /* 2^32, arbitralrily chosen */
 
 extern void mark_tsc_unstable(void);
-extern void set_cyc2ns_scale(unsigned long khz);
 #endif

Index: linux/arch/x86_64/kernel/traps.c
===================================================================
@@ -426,8 +426,7 @@ void show_registers(struct pt_regs *regs
 	const int cpu = smp_processor_id();
 	struct task_struct *cur = cpu_pda(cpu)->pcurrent;
 
-		rsp = regs->rsp;
-
+	rsp = regs->rsp;
 	printk("CPU %d ", cpu);
 	__show_regs(regs);
 	printk("Process %s (pid: %d, threadinfo %p, task %p)\n",

@@ -438,7 +437,6 @@ void show_registers(struct pt_regs *regs
 	 * time of the fault..
 	 */
 	if (in_kernel) {
-
 		printk("Stack: ");
 		_show_stack(NULL, regs, (unsigned long*)rsp);
 

Index: linux/include/linux/bootmem.h
===================================================================
@@ -122,9 +122,9 @@ extern void *alloc_large_system_hash(con
 #define HASH_EARLY	0x00000001	/* Allocating during early boot? */
 
 /* Only NUMA needs hash distribution.
- * IA64 is known to have sufficient vmalloc space.
+ * IA64 and x86_64 have sufficient vmalloc space.
  */
-#if defined(CONFIG_NUMA) && defined(CONFIG_IA64)
+#if defined(CONFIG_NUMA) && (defined(CONFIG_IA64) || defined(CONFIG_X86_64))
 #define HASHDIST_DEFAULT 1
 #else
 #define HASHDIST_DEFAULT 0

Index: linux/arch/i386/mach-generic/es7000.c
===================================================================
@@ -25,4 +25,45 @@ static int probe_es7000(void)
 	return 0;
 }
 
+extern void es7000_sw_apic(void);
+static void __init enable_apic_mode(void)
+{
+	es7000_sw_apic();
+	return;
+}
+
+static __init int mps_oem_check(struct mp_config_table *mpc, char *oem,
+		char *productid)
+{
+	if (mpc->mpc_oemptr) {
+		struct mp_config_oemtable *oem_table =
+			(struct mp_config_oemtable *)mpc->mpc_oemptr;
+		if (!strncmp(oem, "UNISYS", 6))
+			return parse_unisys_oem((char *)oem_table);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_ACPI
+/* Hook from generic ACPI tables.c */
+static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	unsigned long oem_addr;
+	if (!find_unisys_acpi_oem_table(&oem_addr)) {
+		if (es7000_check_dsdt())
+			return parse_unisys_oem((char *)oem_addr);
+		else {
+			setup_unisys();
+			return 1;
+		}
+	}
+	return 0;
+}
+#else
+static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return 0;
+}
+#endif
+
 struct genapic apic_es7000 = APIC_INIT("es7000", probe_es7000);

Index: linux/include/asm-i386/mach-es7000/mach_apic.h
===================================================================
@@ -73,13 +73,6 @@ static inline void init_apic_ldr(void)
 	apic_write_around(APIC_LDR, val);
 }
 
-extern void es7000_sw_apic(void);
-static inline void enable_apic_mode(void)
-{
-	es7000_sw_apic();
-	return;
-}
-
 extern int apic_version [MAX_APICS];
 static inline void setup_apic_routing(void)
 {

Index: linux/include/asm-i386/mach-es7000/mach_mpparse.h
===================================================================
@@ -18,18 +18,6 @@ extern int parse_unisys_oem (char *oempt
 extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
 extern void setup_unisys(void);
 
-static inline int mps_oem_check(struct mp_config_table *mpc, char *oem,
-		char *productid)
-{
-	if (mpc->mpc_oemptr) {
-		struct mp_config_oemtable *oem_table =
-			(struct mp_config_oemtable *)mpc->mpc_oemptr;
-		if (!strncmp(oem, "UNISYS", 6))
-			return parse_unisys_oem((char *)oem_table);
-	}
-	return 0;
-}
-
 #ifdef CONFIG_ACPI
 
 static inline int es7000_check_dsdt(void)

@@ -41,26 +29,6 @@ static inline int es7000_check_dsdt(void
 		return 1;
 	return 0;
 }
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	unsigned long oem_addr;
-	if (!find_unisys_acpi_oem_table(&oem_addr)) {
-		if (es7000_check_dsdt())
-			return parse_unisys_oem((char *)oem_addr);
-		else {
-			setup_unisys();
-			return 1;
-		}
-	}
-	return 0;
-}
-#else
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	return 0;
-}
 #endif
 
 #endif /* __ASM_MACH_MPPARSE_H */

Index: linux/scripts/mod/modpost.c
===================================================================
@@ -606,6 +606,7 @@ static int secref_whitelist(const char *
 		"_probe",
 		"_probe_one",
 		"_console",
+		"apic_es7000",
 		NULL
 	};
 

Index: linux/arch/i386/kernel/vmi.c
===================================================================
@@ -56,7 +56,7 @@ static int disable_noidle;
 static int disable_vmi_timer;
 
 /* Cached VMI operations */
-struct {
+static struct {
 	void (*cpuid)(void /* non-c */);
 	void (*_set_ldt)(u32 selector);
 	void (*set_tr)(u32 selector);

Index: linux/arch/i386/lib/bitops.c
===================================================================
@@ -43,7 +43,7 @@ EXPORT_SYMBOL(find_next_bit);
  */
 int find_next_zero_bit(const unsigned long *addr, int size, int offset)
 {
-	unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
+	const unsigned long *p = addr + (offset >> 5);
 	int set = 0, bit = offset & 31, res;
 
 	if (bit) {

@@ -64,7 +64,7 @@ int find_next_zero_bit(const unsigned lo
 	/*
 	 * No zero yet, search remaining full bytes for a zero
 	 */
-	res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
+	res = find_first_zero_bit(p, size - 32 * (p - addr));
 	return (offset + set + res);
 }
 EXPORT_SYMBOL(find_next_zero_bit);

Index: linux/arch/i386/kernel/asm-offsets.c
===================================================================
@@ -25,6 +25,9 @@
 #define OFFSET(sym, str, mem) \
 	DEFINE(sym, offsetof(struct str, mem));
 
+/* workaround for a warning with -Wmissing-prototypes */
+void foo(void);
+
 void foo(void)
 {
 	OFFSET(SIGCONTEXT_eax, sigcontext, eax);

Index: linux/arch/i386/kernel/cpu/cyrix.c
===================================================================
@@ -279,7 +279,7 @@ static void __cpuinit init_cyrix(struct 
 		 */  
 		if (vendor == PCI_VENDOR_ID_CYRIX &&
 	 (device == PCI_DEVICE_ID_CYRIX_5510 || device == PCI_DEVICE_ID_CYRIX_5520))
-			mark_tsc_unstable();
+			mark_tsc_unstable("cyrix 5510/5520 detected");
 	}
 #endif
 		c->x86_cache_size=16;	/* Yep 16K integrated cache thats it */

Index: linux/arch/i386/kernel/tsc.c
===================================================================
@@ -172,7 +172,7 @@ time_cpufreq_notifier(struct notifier_bl
 						ref_freq, freq->new);
 			if (!(freq->flags & CPUFREQ_CONST_LOOPS)) {
 				tsc_khz = cpu_khz;
-				mark_tsc_unstable();
+				mark_tsc_unstable("cpufreq changes");
 			}
 		}
 	}

@@ -220,11 +220,12 @@ static struct clocksource clocksource_ts
 				  CLOCK_SOURCE_MUST_VERIFY,
 };
 
-void mark_tsc_unstable(void)
+void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
 		tsc_enabled = 0;
+		printk("Marking TSC unstable due to: %s.\n", reason);
 		/* Can be called before registration */
 		if (clocksource_tsc.mult)
 			clocksource_change_rating(&clocksource_tsc, 0);

Index: linux/arch/x86_64/kernel/time.c
===================================================================
@@ -397,7 +397,7 @@ void __init time_init(void)
 		cpu_khz = tsc_calibrate_cpu_khz();
 
 	if (unsynchronized_tsc())
-		mark_tsc_unstable();
+		mark_tsc_unstable("TSCs unsynchronized");
 
 	if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
 		vgetcpu_mode = VGETCPU_RDTSCP;

Index: linux/arch/x86_64/kernel/tsc.c
===================================================================
@@ -85,7 +85,7 @@ static int time_cpufreq_notifier(struct 
 
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
-			mark_tsc_unstable();
+			mark_tsc_unstable("cpufreq changes");
 	}
 
 	return 0;

@@ -171,10 +171,11 @@ static struct clocksource clocksource_ts
 	.vread			= vread_tsc,
 };
 
-void mark_tsc_unstable(void)
+void mark_tsc_unstable(char *reason)
 {
 	if (!tsc_unstable) {
 		tsc_unstable = 1;
+		printk("Marking TSC unstable due to %s\n", reason);
 		/* Change only the rating, when not registered */
 		if (clocksource_tsc.mult)
 			clocksource_change_rating(&clocksource_tsc, 0);

Index: linux/arch/x86_64/kernel/tsc_sync.c
===================================================================
@@ -138,7 +138,7 @@ void __cpuinit check_tsc_sync_source(int
 		printk("\n");
 		printk(KERN_WARNING "Measured %Ld cycles TSC warp between CPUs,"
 				    " turning off TSC clock.\n", max_warp);
-		mark_tsc_unstable();
+		mark_tsc_unstable("check_tsc_sync_source failed");
 		nr_warps = 0;
 		max_warp = 0;
 		last_tsc = 0;

Index: linux/drivers/acpi/processor_idle.c
===================================================================
@@ -483,7 +483,7 @@ static void acpi_processor_idle(void)
 
 #ifdef CONFIG_GENERIC_TIME
 		/* TSC halts in C2, so notify users */
-		mark_tsc_unstable();
+		mark_tsc_unstable("possible TSC halt in C2");
 #endif
 		/* Re-enable interrupts */
 		local_irq_enable();

@@ -525,7 +525,7 @@ static void acpi_processor_idle(void)
 
 #ifdef CONFIG_GENERIC_TIME
 		/* TSC halts in C3, so notify users */
-		mark_tsc_unstable();
+		mark_tsc_unstable("TSC halts in C3");
 #endif
 		/* Re-enable interrupts */
 		local_irq_enable();

Index: linux/include/asm-i386/mach-summit/mach_mpparse.h
===================================================================
@@ -30,7 +30,7 @@ static inline int mps_oem_check(struct m
 			(!strncmp(productid, "VIGIL SMP", 9) 
 			 || !strncmp(productid, "EXA", 3)
 			 || !strncmp(productid, "RUTHLESS SMP", 12))){
-		mark_tsc_unstable();
+		mark_tsc_unstable("Summit based system");
 		use_cyclone = 1; /*enable cyclone-timer*/
 		setup_summit();
 		return 1;

@@ -44,7 +44,7 @@ static inline int acpi_madt_oem_check(ch
 	if (!strncmp(oem_id, "IBM", 3) &&
 	    (!strncmp(oem_table_id, "SERVIGIL", 8)
 	     || !strncmp(oem_table_id, "EXA", 3))){
-		mark_tsc_unstable();
+		mark_tsc_unstable("Summit based system");
 		use_cyclone = 1; /*enable cyclone-timer*/
 		setup_summit();
 		return 1;

Index: linux/include/asm-i386/tsc.h
===================================================================
@@ -53,7 +53,7 @@ static __always_inline cycles_t get_cycl
 }
 
 extern void tsc_init(void);
-extern void mark_tsc_unstable(void);
+extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern void init_tsc_clocksource(void);
 

Index: linux/include/asm-x86_64/timex.h
===================================================================
@@ -27,5 +27,5 @@ extern int read_current_timer(unsigned l
 #define NS_SCALE        10 /* 2^10, carefully chosen */
 #define US_SCALE        32 /* 2^32, arbitralrily chosen */
 
-extern void mark_tsc_unstable(void);
+extern void mark_tsc_unstable(char *);
 #endif

Index: linux/arch/x86_64/ia32/ia32_binfmt.c
===================================================================
@@ -5,6 +5,11 @@
  * This tricks binfmt_elf.c into loading 32bit binaries using lots 
  * of ugly preprocessor tricks. Talk about very very poor man's inheritance.
  */ 
+#define __ASM_X86_64_ELF_H 1
+
+#undef ELF_CLASS
+#define ELF_CLASS ELFCLASS32
+
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/rwsem.h>

@@ -50,9 +55,6 @@ struct elf_phdr; 
 #undef ELF_ARCH
 #define ELF_ARCH EM_386
 
-#undef ELF_CLASS
-#define ELF_CLASS ELFCLASS32
-
 #define ELF_DATA	ELFDATA2LSB
 
 #define USE_ELF_CORE_DUMP 1

@@ -136,7 +138,7 @@ struct elf_prpsinfo
 
 #define user user32
 
-#define __ASM_X86_64_ELF_H 1
+#undef elf_read_implies_exec
 #define elf_read_implies_exec(ex, executable_stack)     (executable_stack != EXSTACK_DISABLE_X)
 //#include <asm/ia32.h>
 #include <linux/elf.h>

Index: linux/arch/x86_64/kernel/io_apic.c
===================================================================
@@ -1407,8 +1407,7 @@ static void irq_complete_move(unsigned i
 
 	vector = ~get_irq_regs()->orig_rax;
 	me = smp_processor_id();
-	if ((vector == cfg->vector) &&
-	    cpu_isset(smp_processor_id(), cfg->domain)) {
+	if ((vector == cfg->vector) && cpu_isset(me, cfg->domain)) {
 		cpumask_t cleanup_mask;
 
 		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);

Index: linux/arch/x86_64/kernel/early_printk.c
===================================================================
@@ -175,7 +175,7 @@ static noinline long simnow(long cmd, lo
 	return ret;
 }
 
-void __init simnow_init(char *str)
+static void __init simnow_init(char *str)
 {
 	char *fn = "klog";
 	if (*str == '=')

Index: linux/arch/i386/kernel/vmi.c
===================================================================
@@ -516,7 +516,7 @@ static void vmi_pte_clear(struct mm_stru
 	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
 }
 
-void vmi_pmd_clear(pmd_t *pmd)
+static void vmi_pmd_clear(pmd_t *pmd)
 {
 	const pte_t pte = { 0 };
 	vmi_check_page_type(__pa(pmd) >> PAGE_SHIFT, VMI_PAGE_PMD);

302 lines not on this page · raw message

Index: linux/include/asm-x86_64/mmzone.h
===================================================================
@@ -49,7 +49,7 @@ extern int pfn_valid(unsigned long pfn);
 
 #ifdef CONFIG_NUMA_EMU
 #define FAKE_NODE_MIN_SIZE	(64*1024*1024)
-#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1ul))
+#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1uL))
 #endif
 
 #endif

Index: linux/arch/x86_64/mm/numa.c
===================================================================
@@ -418,11 +418,25 @@ static int __init numa_emulation(unsigne
 done:
 	if (!num_nodes)
 		return -1;
-	/* Fill remainder of system RAM with a final node, if appropriate. */
+	/* Fill remainder of system RAM, if appropriate. */
 	if (addr < max_addr) {
-		setup_node_range(num_nodes, nodes, &addr, max_addr - addr,
-				 max_addr);
-		num_nodes++;
+		switch (*(cmdline - 1)) {
+		case '*':
+			/* Split remaining nodes into coeff chunks */
+			if (coeff <= 0)
+				break;
+			num_nodes += split_nodes_equally(nodes, &addr, max_addr,
+							 num_nodes, coeff);
+			break;
+		case ',':
+			/* Do not allocate remaining system RAM */
+			break;
+		default:
+			/* Give one final node */
+			setup_node_range(num_nodes, nodes, &addr,
+					 max_addr - addr, max_addr);
+			num_nodes++;
+		}
 	}
 out:
 	memnode_shift = compute_hash_shift(nodes, num_nodes);

87 lines not on this page · raw message

Index: linux/arch/i386/kernel/cpu/proc.c
===================================================================
@@ -72,8 +72,7 @@ static int show_cpuinfo(struct seq_file 
 		"stc",
 		"100mhzsteps",
 		"hwpstate",
-		NULL,
-		NULL,	/* constant_tsc - moved to flags */
+		"",	/* constant_tsc - moved to flags */
 		/* nothing */
 	};
 	struct cpuinfo_x86 *c = v;

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -979,9 +979,8 @@ static int show_cpuinfo(struct seq_file 
 		"stc",
 		"100mhzsteps",
 		"hwpstate",
-		NULL,	/* tsc invariant mapped to constant_tsc */
-		NULL,
-		/* nothing */	/* constant_tsc - moved to flags */
+		"",	/* tsc invariant mapped to constant_tsc */
+		/* nothing */
 	};
 
 

Index: linux/arch/i386/kernel/asm-offsets.c
===================================================================
@@ -97,7 +97,7 @@ void foo(void)
 		 sizeof(struct tss_struct));
 
 	DEFINE(PAGE_SIZE_asm, PAGE_SIZE);
-	DEFINE(VDSO_PRELINK, VDSO_PRELINK);
+	DEFINE(VDSO_PRELINK_asm, VDSO_PRELINK);
 
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
 

Index: linux/include/asm-i386/processor.h
===================================================================
@@ -421,6 +421,7 @@ struct thread_struct {
 };
 
 #define INIT_THREAD  {							\
+	.esp0 = sizeof(init_stack) + (long)&init_stack,			\
 	.vm86_info = NULL,						\
 	.sysenter_cs = __KERNEL_CS,					\
 	.io_bitmap_ptr = NULL,						\

Index: linux/include/asm-x86_64/desc.h
===================================================================
@@ -135,16 +135,13 @@ static inline void set_ldt_desc(unsigned
 	(info)->useable		== 0	&& \
 	(info)->lm		== 0)
 
-#if TLS_SIZE != 24
-# error update this code.
-#endif
-
 static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
 {
+	unsigned int i;
 	u64 *gdt = (u64 *)(cpu_gdt(cpu) + GDT_ENTRY_TLS_MIN);
-	gdt[0] = t->tls_array[0];
-	gdt[1] = t->tls_array[1];
-	gdt[2] = t->tls_array[2];
+
+	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+		gdt[i] = t->tls_array[i];
 } 
 
 /*

Index: linux/fs/proc/vmcore.c
===================================================================
@@ -514,7 +514,7 @@ static int __init parse_crash_elf64_head
 	/* Do some basic Verification. */
 	if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0 ||
 		(ehdr.e_type != ET_CORE) ||
-		!elf_check_arch(&ehdr) ||
+		!vmcore_elf_check_arch(&ehdr) ||
 		ehdr.e_ident[EI_CLASS] != ELFCLASS64 ||
 		ehdr.e_ident[EI_VERSION] != EV_CURRENT ||
 		ehdr.e_version != EV_CURRENT ||

Index: linux/include/asm-i386/kexec.h
===================================================================
@@ -42,6 +42,9 @@
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_386
 
+/* We can also handle crash dumps from 64 bit kernel. */
+#define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64)
+
 #define MAX_NOTE_BYTES 1024
 
 /* CPU does not save ss and esp on stack if execution is already

Index: linux/include/linux/crash_dump.h
===================================================================
@@ -14,5 +14,13 @@ extern ssize_t copy_oldmem_page(unsigned
 extern const struct file_operations proc_vmcore_operations;
 extern struct proc_dir_entry *proc_vmcore;
 
+/* Architecture code defines this if there are other possible ELF
+ * machine types, e.g. on bi-arch capable hardware. */
+#ifndef vmcore_elf_check_arch_cross
+#define vmcore_elf_check_arch_cross(x) 0
+#endif
+
+#define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x))
+
 #endif /* CONFIG_CRASH_DUMP */
 #endif /* LINUX_CRASHDUMP_H */

Index: linux/arch/i386/kernel/acpi/earlyquirk.c
===================================================================
@@ -21,11 +21,14 @@ static int __init nvidia_hpet_check(stru
 
 static int __init check_bridge(int vendor, int device)
 {
+	static int warned;
 #ifdef CONFIG_ACPI
 	/* According to Nvidia all timer overrides are bogus unless HPET
 	   is enabled. */
 	if (!acpi_use_timer_override && vendor == PCI_VENDOR_ID_NVIDIA) {
-		if (acpi_table_parse(ACPI_SIG_HPET, nvidia_hpet_check)) {
+		if (!warned && acpi_table_parse(ACPI_SIG_HPET,
+						nvidia_hpet_check)) {
+			warned = 1;
 			acpi_skip_timer_override = 1;
 			  printk(KERN_INFO "Nvidia board "
                        "detected. Ignoring ACPI "

Index: linux/arch/i386/kernel/cpu/common.c
===================================================================
@@ -25,8 +25,10 @@
 DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
 EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
 
-struct i386_pda *_cpu_pda[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
+DEFINE_PER_CPU(struct desc_struct, cpu_gdt[GDT_ENTRIES]);
+
+DEFINE_PER_CPU(struct i386_pda, _cpu_pda);
+EXPORT_PER_CPU_SYMBOL(_cpu_pda);
 
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_fxsr __cpuinitdata;

@@ -609,52 +611,6 @@ struct pt_regs * __devinit idle_regs(str
 	return regs;
 }
 
-static __cpuinit int alloc_gdt(int cpu)
-{
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-	struct desc_struct *gdt;
-	struct i386_pda *pda;
-
-	gdt = (struct desc_struct *)cpu_gdt_descr->address;
-	pda = cpu_pda(cpu);
-
-	/*
-	 * This is a horrible hack to allocate the GDT.  The problem
-	 * is that cpu_init() is called really early for the boot CPU
-	 * (and hence needs bootmem) but much later for the secondary
-	 * CPUs, when bootmem will have gone away
-	 */
-	if (NODE_DATA(0)->bdata->node_bootmem_map) {
-		BUG_ON(gdt != NULL || pda != NULL);
-
-		gdt = alloc_bootmem_pages(PAGE_SIZE);
-		pda = alloc_bootmem(sizeof(*pda));
-		/* alloc_bootmem(_pages) panics on failure, so no check */
-
-		memset(gdt, 0, PAGE_SIZE);
-		memset(pda, 0, sizeof(*pda));
-	} else {
-		/* GDT and PDA might already have been allocated if
-		   this is a CPU hotplug re-insertion. */
-		if (gdt == NULL)
-			gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL);
-
-		if (pda == NULL)
-			pda = kmalloc_node(sizeof(*pda), GFP_KERNEL, cpu_to_node(cpu));
-
-		if (unlikely(!gdt || !pda)) {
-			free_pages((unsigned long)gdt, 0);
-			kfree(pda);
-			return 0;
-		}
-	}
-
- 	cpu_gdt_descr->address = (unsigned long)gdt;
-	cpu_pda(cpu) = pda;
-
-	return 1;
-}
-
 /* Initial PDA used by boot CPU */
 struct i386_pda boot_pda = {
 	._pda = &boot_pda,

@@ -670,31 +626,17 @@ static inline void set_kernel_fs(void)
 	asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_PDA) : "memory");
 }
 
-/* Initialize the CPU's GDT and PDA.  The boot CPU does this for
-   itself, but secondaries find this done for them. */
-__cpuinit int init_gdt(int cpu, struct task_struct *idle)
+/* Initialize the CPU's GDT and PDA.  This is either the boot CPU doing itself
+   (still using cpu_gdt_table), or a CPU doing it for a secondary which
+   will soon come up. */
+__cpuinit void init_gdt(int cpu, struct task_struct *idle)
 {
 	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-	struct desc_struct *gdt;
-	struct i386_pda *pda;
-
-	/* For non-boot CPUs, the GDT and PDA should already have been
-	   allocated. */
-	if (!alloc_gdt(cpu)) {
-		printk(KERN_CRIT "CPU%d failed to allocate GDT or PDA\n", cpu);
-		return 0;
-	}
-
-	gdt = (struct desc_struct *)cpu_gdt_descr->address;
-	pda = cpu_pda(cpu);
-
-	BUG_ON(gdt == NULL || pda == NULL);
+	struct desc_struct *gdt = per_cpu(cpu_gdt, cpu);
+	struct i386_pda *pda = &per_cpu(_cpu_pda, cpu);
 
-	/*
-	 * Initialize the per-CPU GDT with the boot GDT,
-	 * and set up the GDT descriptor:
-	 */
  	memcpy(gdt, cpu_gdt_table, GDT_SIZE);
+ 	cpu_gdt_descr->address = (unsigned long)gdt;
 	cpu_gdt_descr->size = GDT_SIZE - 1;
 
 	pack_descriptor((u32 *)&gdt[GDT_ENTRY_PDA].a,

@@ -706,17 +648,12 @@ __cpuinit int init_gdt(int cpu, struct t
 	pda->_pda = pda;
 	pda->cpu_number = cpu;
 	pda->pcurrent = idle;
-
-	return 1;
 }
 
 void __cpuinit cpu_set_gdt(int cpu)
 {
 	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
 
-	/* Reinit these anyway, even if they've already been done (on
-	   the boot CPU, this will transition from the boot gdt+pda to
-	   the real ones). */
 	load_gdt(cpu_gdt_descr);
 	set_kernel_fs();
 }

@@ -804,13 +741,8 @@ void __cpuinit cpu_init(void)
 	struct task_struct *curr = current;
 
 	/* Set up the real GDT and PDA, so we can transition from the
-	   boot versions. */
-	if (!init_gdt(cpu, curr)) {
-		/* failed to allocate something; not much we can do... */
-		for (;;)
-			local_irq_enable();
-	}
-
+	   boot_gdt_table & boot_pda. */
+	init_gdt(cpu, curr);
 	cpu_set_gdt(cpu);
 	_cpu_init(cpu, curr);
 }

Index: linux/arch/i386/kernel/smpboot.c
===================================================================
@@ -808,13 +808,7 @@ static int __cpuinit do_boot_cpu(int api
 	if (IS_ERR(idle))
 		panic("failed fork for CPU %d", cpu);
 
-	/* Pre-allocate and initialize the CPU's GDT and PDA so it
-	   doesn't have to do any memory allocation during the
-	   delicate CPU-bringup phase. */
-	if (!init_gdt(cpu, idle)) {
-		printk(KERN_INFO "Couldn't allocate GDT/PDA for CPU %d\n", cpu);
-		return -1;	/* ? */
-	}
+	init_gdt(cpu, idle);
 
 	idle->thread.eip = (unsigned long) start_secondary;
 	/* start_eip had better be page-aligned! */

@@ -940,7 +934,6 @@ static int __cpuinit __smp_prepare_cpu(i
 	DECLARE_COMPLETION_ONSTACK(done);
 	struct warm_boot_cpu_info info;
 	int	apicid, ret;
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
 
 	apicid = x86_cpu_to_apicid[cpu];
 	if (apicid == BAD_APICID) {

@@ -948,18 +941,6 @@ static int __cpuinit __smp_prepare_cpu(i
 		goto exit;
 	}
 
-	/*
-	 * the CPU isn't initialized at boot time, allocate gdt table here.
-	 * cpu_init will initialize it
-	 */
-	if (!cpu_gdt_descr->address) {
-		cpu_gdt_descr->address = get_zeroed_page(GFP_KERNEL);
-		if (!cpu_gdt_descr->address)
-			printk(KERN_CRIT "CPU%d failed to allocate GDT\n", cpu);
-			ret = -ENOMEM;
-			goto exit;
-	}
-
 	info.complete = &done;
 	info.apicid = apicid;
 	info.cpu = cpu;

Index: linux/arch/i386/mach-voyager/voyager_smp.c
===================================================================
@@ -580,15 +580,7 @@ do_boot_cpu(__u8 cpu)
 	/* init_tasks (in sched.c) is indexed logically */
 	stack_start.esp = (void *) idle->thread.esp;
 
-	/* Pre-allocate and initialize the CPU's GDT and PDA so it
-	   doesn't have to do any memory allocation during the
-	   delicate CPU-bringup phase. */
-	if (!init_gdt(cpu, idle)) {
-		printk(KERN_INFO "Couldn't allocate GDT/PDA for CPU %d\n", cpu);
-		cpucount--;
-		return;
-	}
-
+	init_gdt(cpu, idle);
 	irq_ctx_init(cpu);
 
 	/* Note: Don't modify initial ss override */

Index: linux/include/asm-generic/percpu.h
===================================================================
@@ -1,6 +1,7 @@
 #ifndef _ASM_GENERIC_PERCPU_H_
 #define _ASM_GENERIC_PERCPU_H_
 #include <linux/compiler.h>
+#include <linux/threads.h>
 
 #define __GENERIC_PER_CPU
 #ifdef CONFIG_SMP

Index: linux/include/asm-i386/desc.h
===================================================================
@@ -22,6 +22,7 @@ struct Xgt_desc_struct {
 
 extern struct Xgt_desc_struct idt_descr;
 DECLARE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
+DECLARE_PER_CPU(struct desc_struct, cpu_gdt[GDT_ENTRIES]);
 extern struct Xgt_desc_struct early_gdt_descr;
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)

Index: linux/include/asm-i386/pda.h
===================================================================
@@ -8,6 +8,7 @@
 
 #include <linux/stddef.h>
 #include <linux/types.h>
+#include <asm/percpu.h>
 
 struct i386_pda
 {

@@ -18,10 +19,8 @@ struct i386_pda
 	struct pt_regs *irq_regs;
 };
 
-extern struct i386_pda *_cpu_pda[];
-
-#define cpu_pda(i)	(_cpu_pda[i])
-
+DECLARE_PER_CPU(struct i386_pda, _cpu_pda);
+#define cpu_pda(i)	(&per_cpu(_cpu_pda, (i)))
 #define pda_offset(field) offsetof(struct i386_pda, field)
 
 extern void __bad_pda_field(void);

Index: linux/include/asm-i386/processor.h
===================================================================
@@ -743,7 +743,7 @@ extern unsigned long boot_option_idle_ov
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
-extern int init_gdt(int cpu, struct task_struct *idle);
+extern void init_gdt(int cpu, struct task_struct *idle);
 extern void cpu_set_gdt(int);
 extern void secondary_cpu_init(void);
 

Index: linux/arch/i386/kernel/cpu/common.c
===================================================================
@@ -25,7 +25,33 @@
 DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
 EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
 
-DEFINE_PER_CPU(struct desc_struct, cpu_gdt[GDT_ENTRIES]);
+DEFINE_PER_CPU(struct desc_struct, cpu_gdt[GDT_ENTRIES]) = {
+	[GDT_ENTRY_KERNEL_CS] = { 0x0000ffff, 0x00cf9a00 },
+	[GDT_ENTRY_KERNEL_DS] = { 0x0000ffff, 0x00cf9200 },
+	[GDT_ENTRY_DEFAULT_USER_CS] = { 0x0000ffff, 0x00cffa00 },
+	[GDT_ENTRY_DEFAULT_USER_DS] = { 0x0000ffff, 0x00cff200 },
+	/*
+	 * Segments used for calling PnP BIOS have byte granularity.
+	 * They code segments and data segments have fixed 64k limits,
+	 * the transfer segment sizes are set at run time.
+	 */
+	[GDT_ENTRY_PNPBIOS_CS32] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */
+	[GDT_ENTRY_PNPBIOS_CS16] = { 0x0000ffff, 0x00009a00 },/* 16-bit code */
+	[GDT_ENTRY_PNPBIOS_DS] = { 0x0000ffff, 0x00009200 }, /* 16-bit data */
+	[GDT_ENTRY_PNPBIOS_TS1] = { 0x00000000, 0x00009200 },/* 16-bit data */
+	[GDT_ENTRY_PNPBIOS_TS2] = { 0x00000000, 0x00009200 },/* 16-bit data */
+	/*
+	 * The APM segments have byte granularity and their bases
+	 * are set at run time.  All have 64k limits.
+	 */
+	[GDT_ENTRY_APMBIOS_BASE] = { 0x0000ffff, 0x00409a00 },/* 32-bit code */
+	/* 16-bit code */
+	[GDT_ENTRY_APMBIOS_BASE+1] = { 0x0000ffff, 0x00009a00 },
+	[GDT_ENTRY_APMBIOS_BASE+2] = { 0x0000ffff, 0x00409200 }, /* data */
+
+	[GDT_ENTRY_ESPFIX_SS] = { 0x00000000, 0x00c09200 },
+	[GDT_ENTRY_PDA] = { 0x00000000, 0x00c09200 }, /* set in setup_pda */
+};
 
 DEFINE_PER_CPU(struct i386_pda, _cpu_pda);
 EXPORT_PER_CPU_SYMBOL(_cpu_pda);

@@ -618,46 +644,6 @@ struct i386_pda boot_pda = {
 	.pcurrent = &init_task,
 };
 
-static inline void set_kernel_fs(void)
-{
-	/* Set %fs for this CPU's PDA.  Memory clobber is to create a
-	   barrier with respect to any PDA operations, so the compiler
-	   doesn't move any before here. */
-	asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_PDA) : "memory");
-}
-
-/* Initialize the CPU's GDT and PDA.  This is either the boot CPU doing itself
-   (still using cpu_gdt_table), or a CPU doing it for a secondary which
-   will soon come up. */
-__cpuinit void init_gdt(int cpu, struct task_struct *idle)
-{
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-	struct desc_struct *gdt = per_cpu(cpu_gdt, cpu);
-	struct i386_pda *pda = &per_cpu(_cpu_pda, cpu);
-
- 	memcpy(gdt, cpu_gdt_table, GDT_SIZE);
- 	cpu_gdt_descr->address = (unsigned long)gdt;
-	cpu_gdt_descr->size = GDT_SIZE - 1;
-
-	pack_descriptor((u32 *)&gdt[GDT_ENTRY_PDA].a,
-			(u32 *)&gdt[GDT_ENTRY_PDA].b,
-			(unsigned long)pda, sizeof(*pda) - 1,
-			0x80 | DESCTYPE_S | 0x2, 0); /* present read-write data segment */
-
-	memset(pda, 0, sizeof(*pda));
-	pda->_pda = pda;
-	pda->cpu_number = cpu;
-	pda->pcurrent = idle;
-}
-
-void __cpuinit cpu_set_gdt(int cpu)
-{
-	struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
-
-	load_gdt(cpu_gdt_descr);
-	set_kernel_fs();
-}
-
 /* Common CPU init for both boot and secondary CPUs */
 static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
 {

@@ -740,10 +726,6 @@ void __cpuinit cpu_init(void)
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
 
-	/* Set up the real GDT and PDA, so we can transition from the
-	   boot_gdt_table & boot_pda. */
-	init_gdt(cpu, curr);
-	cpu_set_gdt(cpu);
 	_cpu_init(cpu, curr);
 }
 

84 lines not on this page · raw message

Index: linux/arch/i386/mach-voyager/voyager_smp.c
===================================================================
@@ -765,12 +765,6 @@ initialize_secondary(void)
 #endif
 
 	/*
-	 * switch to the per CPU GDT we already set up
-	 * in do_boot_cpu()
-	 */
-	cpu_set_gdt(current_thread_info()->cpu);
-
-	/*
 	 * We don't actually need to load the full TSS,
 	 * basically just the stack pointer and the eip.
 	 */

Index: linux/include/asm-i386/desc.h
===================================================================
@@ -12,8 +12,6 @@
 
 #include <asm/mmu.h>
 
-extern struct desc_struct cpu_gdt_table[GDT_ENTRIES];
-
 struct Xgt_desc_struct {
 	unsigned short size;
 	unsigned long address __attribute__((packed));

Index: linux/include/asm-i386/processor.h
===================================================================
@@ -743,7 +743,6 @@ extern unsigned long boot_option_idle_ov
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
-extern void init_gdt(int cpu, struct task_struct *idle);
 extern void cpu_set_gdt(int);
 extern void secondary_cpu_init(void);
 

Index: linux/arch/i386/kernel/cpu/common.c
===================================================================
@@ -644,9 +644,16 @@ struct i386_pda boot_pda = {
 	.pcurrent = &init_task,
 };
 
-/* Common CPU init for both boot and secondary CPUs */
-static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ */
+void __cpuinit cpu_init(void)
 {
+	int cpu = smp_processor_id();
+	struct task_struct *curr = current;
 	struct tss_struct * t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 

@@ -706,29 +713,6 @@ static void __cpuinit _cpu_init(int cpu,
 	mxcsr_feature_mask_init();
 }
 
-/* Entrypoint to initialize secondary CPU */
-void __cpuinit secondary_cpu_init(void)
-{
-	int cpu = smp_processor_id();
-	struct task_struct *curr = current;
-
-	_cpu_init(cpu, curr);
-}
-
-/*
- * cpu_init() initializes state that is per-CPU. Some data is already
- * initialized (naturally) in the bootstrap process, such as the GDT
- * and IDT. We reload them nevertheless, this function acts as a
- * 'CPU state barrier', nothing should get across.
- */
-void __cpuinit cpu_init(void)
-{
-	int cpu = smp_processor_id();
-	struct task_struct *curr = current;
-
-	_cpu_init(cpu, curr);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 void __cpuinit cpu_uninit(void)
 {

Index: linux/arch/i386/kernel/smpboot.c
===================================================================
@@ -378,14 +378,14 @@ set_cpu_sibling_map(int cpu)
 static void __cpuinit start_secondary(void *unused)
 {
 	/*
-	 * Don't put *anything* before secondary_cpu_init(), SMP
-	 * booting is too fragile that we want to limit the
-	 * things done here to the most necessary things.
+	 * Don't put *anything* before cpu_init(), SMP booting is too
+	 * fragile that we want to limit the things done here to the
+	 * most necessary things.
 	 */
 #ifdef CONFIG_VMI
 	vmi_bringup();
 #endif
-	secondary_cpu_init();
+	cpu_init();
 	preempt_disable();
 	smp_callin();
 	while (!cpu_isset(smp_processor_id(), smp_commenced_mask))

Index: linux/include/asm-i386/processor.h
===================================================================
@@ -744,6 +744,6 @@ extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
 extern void cpu_set_gdt(int);
-extern void secondary_cpu_init(void);
+extern void cpu_init(void);
 
 #endif /* __ASM_I386_PROCESSOR_H */

Index: linux/arch/i386/kernel/paravirt.c
===================================================================
@@ -93,294 +93,11 @@ static unsigned native_patch(u8 type, u1
 	return insn_len;
 }
 
-static unsigned long native_get_debugreg(int regno)
-{
-	unsigned long val = 0; 	/* Damn you, gcc! */
-
-	switch (regno) {
-	case 0:
-		asm("movl %%db0, %0" :"=r" (val)); break;
-	case 1:
-		asm("movl %%db1, %0" :"=r" (val)); break;
-	case 2:
-		asm("movl %%db2, %0" :"=r" (val)); break;
-	case 3:
-		asm("movl %%db3, %0" :"=r" (val)); break;
-	case 6:
-		asm("movl %%db6, %0" :"=r" (val)); break;
-	case 7:
-		asm("movl %%db7, %0" :"=r" (val)); break;
-	default:
-		BUG();
-	}
-	return val;
-}
-
-static void native_set_debugreg(int regno, unsigned long value)
-{
-	switch (regno) {
-	case 0:
-		asm("movl %0,%%db0"	: /* no output */ :"r" (value));
-		break;
-	case 1:
-		asm("movl %0,%%db1"	: /* no output */ :"r" (value));
-		break;
-	case 2:
-		asm("movl %0,%%db2"	: /* no output */ :"r" (value));
-		break;
-	case 3:
-		asm("movl %0,%%db3"	: /* no output */ :"r" (value));
-		break;
-	case 6:
-		asm("movl %0,%%db6"	: /* no output */ :"r" (value));
-		break;
-	case 7:
-		asm("movl %0,%%db7"	: /* no output */ :"r" (value));
-		break;
-	default:
-		BUG();
-	}
-}
-
 void init_IRQ(void)
 {
 	paravirt_ops.init_IRQ();
 }
 
-static void native_clts(void)
-{
-	asm volatile ("clts");
-}
-
-static unsigned long native_read_cr0(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr0,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static void native_write_cr0(unsigned long val)
-{
-	asm volatile("movl %0,%%cr0": :"r" (val));
-}
-
-static unsigned long native_read_cr2(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr2,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static void native_write_cr2(unsigned long val)
-{
-	asm volatile("movl %0,%%cr2": :"r" (val));
-}
-
-static unsigned long native_read_cr3(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr3,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static void native_write_cr3(unsigned long val)
-{
-	asm volatile("movl %0,%%cr3": :"r" (val));
-}
-
-static unsigned long native_read_cr4(void)
-{
-	unsigned long val;
-	asm volatile("movl %%cr4,%0\n\t" :"=r" (val));
-	return val;
-}
-
-static unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist */
-	asm("1: movl %%cr4, %0		\n"
-		"2:				\n"
-		".section __ex_table,\"a\"	\n"
-		".long 1b,2b			\n"
-		".previous			\n"
-		: "=r" (val): "0" (0));
-	return val;
-}
-
-static void native_write_cr4(unsigned long val)
-{
-	asm volatile("movl %0,%%cr4": :"r" (val));
-}
-
-static unsigned long native_save_fl(void)
-{
-	unsigned long f;
-	asm volatile("pushfl ; popl %0":"=g" (f): /* no input */);
-	return f;
-}
-
-static void native_restore_fl(unsigned long f)
-{
-	asm volatile("pushl %0 ; popfl": /* no output */
-			     :"g" (f)
-			     :"memory", "cc");
-}
-
-static void native_irq_disable(void)
-{
-	asm volatile("cli": : :"memory");
-}
-
-static void native_irq_enable(void)
-{
-	asm volatile("sti": : :"memory");
-}
-
-static void native_safe_halt(void)
-{
-	asm volatile("sti; hlt": : :"memory");
-}
-
-static void native_halt(void)
-{
-	asm volatile("hlt": : :"memory");
-}
-
-static void native_wbinvd(void)
-{
-	asm volatile("wbinvd": : :"memory");
-}
-
-static unsigned long long native_read_msr(unsigned int msr, int *err)
-{
-	unsigned long long val;
-
-	asm volatile("2: rdmsr ; xorl %0,%0\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  movl %3,%0 ; jmp 1b\n\t"
-		     ".previous\n\t"
- 		     ".section __ex_table,\"a\"\n"
-		     "   .align 4\n\t"
-		     "   .long 	2b,3b\n\t"
-		     ".previous"
-		     : "=r" (*err), "=A" (val)
-		     : "c" (msr), "i" (-EFAULT));
-
-	return val;
-}
-
-static int native_write_msr(unsigned int msr, unsigned long long val)
-{
-	int err;
-	asm volatile("2: wrmsr ; xorl %0,%0\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  movl %4,%0 ; jmp 1b\n\t"
-		     ".previous\n\t"
- 		     ".section __ex_table,\"a\"\n"
-		     "   .align 4\n\t"
-		     "   .long 	2b,3b\n\t"
-		     ".previous"
-		     : "=a" (err)
-		     : "c" (msr), "0" ((u32)val), "d" ((u32)(val>>32)),
-		       "i" (-EFAULT));
-	return err;
-}
-
-static unsigned long long native_read_tsc(void)
-{
-	unsigned long long val;
-	asm volatile("rdtsc" : "=A" (val));
-	return val;
-}
-
-static unsigned long long native_read_pmc(void)
-{
-	unsigned long long val;
-	asm volatile("rdpmc" : "=A" (val));
-	return val;
-}
-
-static void native_load_tr_desc(void)
-{
-	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
-}
-
-static void native_load_gdt(const struct Xgt_desc_struct *dtr)
-{
-	asm volatile("lgdt %0"::"m" (*dtr));
-}
-
-static void native_load_idt(const struct Xgt_desc_struct *dtr)
-{
-	asm volatile("lidt %0"::"m" (*dtr));
-}
-
-static void native_store_gdt(struct Xgt_desc_struct *dtr)
-{
-	asm ("sgdt %0":"=m" (*dtr));
-}
-
-static void native_store_idt(struct Xgt_desc_struct *dtr)
-{
-	asm ("sidt %0":"=m" (*dtr));
-}
-
-static unsigned long native_store_tr(void)
-{
-	unsigned long tr;
-	asm ("str %0":"=r" (tr));
-	return tr;
-}
-
-static void native_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-#define C(i) get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]
-	C(0); C(1); C(2);
-#undef C
-}
-
-static inline void native_write_dt_entry(void *dt, int entry, u32 entry_low, u32 entry_high)
-{
-	u32 *lp = (u32 *)((char *)dt + entry*8);
-	lp[0] = entry_low;
-	lp[1] = entry_high;
-}
-
-static void native_write_ldt_entry(void *dt, int entrynum, u32 low, u32 high)
-{
-	native_write_dt_entry(dt, entrynum, low, high);
-}
-
-static void native_write_gdt_entry(void *dt, int entrynum, u32 low, u32 high)
-{
-	native_write_dt_entry(dt, entrynum, low, high);
-}
-
-static void native_write_idt_entry(void *dt, int entrynum, u32 low, u32 high)
-{
-	native_write_dt_entry(dt, entrynum, low, high);
-}
-
-static void native_load_esp0(struct tss_struct *tss,
-				      struct thread_struct *thread)
-{
-	tss->esp0 = thread->esp0;
-
-	/* This can only happen when SEP is enabled, no need to test "SEP"arately */
-	if (unlikely(tss->ss1 != thread->sysenter_cs)) {
-		tss->ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
-}
-
-static void native_io_delay(void)
-{
-	asm volatile("outb %al,$0x80");
-}
-
 static void native_flush_tlb(void)
 {
 	__native_flush_tlb();

@@ -517,8 +234,8 @@ struct paravirt_ops paravirt_ops = {
 	.safe_halt = native_safe_halt,
 	.halt = native_halt,
 	.wbinvd = native_wbinvd,
-	.read_msr = native_read_msr,
-	.write_msr = native_write_msr,
+	.read_msr = native_read_msr_safe,
+	.write_msr = native_write_msr_safe,
 	.read_tsc = native_read_tsc,
 	.read_pmc = native_read_pmc,
 	.get_scheduled_cycles = native_read_tsc,

@@ -531,9 +248,9 @@ struct paravirt_ops paravirt_ops = {
 	.store_idt = native_store_idt,
 	.store_tr = native_store_tr,
 	.load_tls = native_load_tls,
-	.write_ldt_entry = native_write_ldt_entry,
-	.write_gdt_entry = native_write_gdt_entry,
-	.write_idt_entry = native_write_idt_entry,
+	.write_ldt_entry = write_dt_entry,
+	.write_gdt_entry = write_dt_entry,
+	.write_idt_entry = write_dt_entry,
 	.load_esp0 = native_load_esp0,
 
 	.set_iopl_mask = native_set_iopl_mask,

107 lines not on this page · raw message

Index: linux/include/asm-i386/io.h
===================================================================
@@ -250,19 +250,22 @@ static inline void flush_write_buffers(v
 
 #endif /* __KERNEL__ */
 
+static inline void native_io_delay(void)
+{
+	asm volatile("outb %%al,$0x80" : : : "memory");
+}
+
 #if defined(CONFIG_PARAVIRT)
 #include <asm/paravirt.h>
 #else
 
-#define __SLOW_DOWN_IO "outb %%al,$0x80;"
-
 static inline void slow_down_io(void) {
-	__asm__ __volatile__(
-		__SLOW_DOWN_IO
+	native_io_delay();
 #ifdef REALLY_SLOW_IO
-		__SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
+	native_io_delay();
+	native_io_delay();
+	native_io_delay();
 #endif
-		: : );
 }
 
 #endif

97 lines not on this page · raw message

189 lines not on this page · raw message

Index: linux/include/asm-i386/paravirt.h
===================================================================
@@ -29,6 +29,7 @@ struct thread_struct;
 struct Xgt_desc_struct;
 struct tss_struct;
 struct mm_struct;
+struct desc_struct;
 struct paravirt_ops
 {
 	unsigned int kernel_rpl;

@@ -105,14 +106,13 @@ struct paravirt_ops
 	void (*set_ldt)(const void *desc, unsigned entries);
 	unsigned long (*store_tr)(void);
 	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
-	void (*write_ldt_entry)(void *dt, int entrynum,
-					 u32 low, u32 high);
-	void (*write_gdt_entry)(void *dt, int entrynum,
-					 u32 low, u32 high);
-	void (*write_idt_entry)(void *dt, int entrynum,
-					 u32 low, u32 high);
-	void (*load_esp0)(struct tss_struct *tss,
-				   struct thread_struct *thread);
+	void (*write_ldt_entry)(struct desc_struct *,
+				int entrynum, u32 low, u32 high);
+	void (*write_gdt_entry)(struct desc_struct *,
+				int entrynum, u32 low, u32 high);
+	void (*write_idt_entry)(struct desc_struct *,
+				int entrynum, u32 low, u32 high);
+	void (*load_esp0)(struct tss_struct *tss, struct thread_struct *t);
 
 	void (*set_iopl_mask)(unsigned mask);
 

@@ -232,6 +232,7 @@ static inline void halt(void)
 
 #define get_kernel_rpl()  (paravirt_ops.kernel_rpl)
 
+/* These should all do BUG_ON(_err), but our headers are too tangled. */
 #define rdmsr(msr,val1,val2) do {				\
 	int _err;						\
 	u64 _l = paravirt_ops.read_msr(msr,&_err);		\

123 lines not on this page · raw message

149 lines not on this page · raw message

Index: linux/arch/i386/mm/init.c
===================================================================
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
 #include <linux/slab.h>

@@ -751,13 +752,25 @@ static int noinline do_test_wp_bit(void)
 
 void mark_rodata_ro(void)
 {
-	unsigned long addr = (unsigned long)__start_rodata;
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
 
-	for (; addr < (unsigned long)__end_rodata; addr += PAGE_SIZE)
-		change_page_attr(virt_to_page(addr), 1, PAGE_KERNEL_RO);
-
-	printk("Write protecting the kernel read-only data: %uk\n",
-			(__end_rodata - __start_rodata) >> 10);
+#ifdef CONFIG_HOTPLUG_CPU
+	/* It must still be possible to apply SMP alternatives. */
+	if (num_possible_cpus() <= 1)
+#endif
+	{
+		change_page_attr(virt_to_page(start),
+		                 size >> PAGE_SHIFT, PAGE_KERNEL_RX);
+		printk("Write protecting the kernel text: %luk\n", size >> 10);
+	}
+
+	start += size;
+	size = (unsigned long)__end_rodata - start;
+	change_page_attr(virt_to_page(start),
+	                 size >> PAGE_SHIFT, PAGE_KERNEL_RO);
+	printk("Write protecting the kernel read-only data: %luk\n",
+	       size >> 10);
 
 	/*
 	 * change_page_attr() requires a global_flush_tlb() call after it.

@@ -781,7 +794,7 @@ void free_init_pages(char *what, unsigne
 		__free_page(page);
 		totalram_pages++;
 	}
-	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 }
 
 void free_initmem(void)

Index: linux/arch/i386/mm/pageattr.c
===================================================================
@@ -140,9 +140,11 @@ __change_page_attr(struct page *page, pg
 	kpte = lookup_address(address);
 	if (!kpte)
 		return -EINVAL;
+	if (!pte_present(*kpte))
+		return 0;
 	kpte_page = virt_to_page(kpte);
 	if (pgprot_val(prot) != pgprot_val(PAGE_KERNEL)) { 
-		if ((pte_val(*kpte) & _PAGE_PSE) == 0) { 
+		if (!pte_huge(*kpte)) {
 			set_pte_atomic(kpte, mk_pte(page, prot)); 
 		} else {
 			pgprot_t ref_prot;

@@ -158,7 +160,7 @@ __change_page_attr(struct page *page, pg
 			kpte_page = split;
 		}
 		page_private(kpte_page)++;
-	} else if ((pte_val(*kpte) & _PAGE_PSE) == 0) { 
+	} else if (!pte_huge(*kpte)) {
 		set_pte_atomic(kpte, mk_pte(page, PAGE_KERNEL));
 		BUG_ON(page_private(kpte_page) == 0);
 		page_private(kpte_page)--;

Index: linux/arch/x86_64/mm/init.c
===================================================================
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/proc_fs.h>
 #include <linux/pci.h>
+#include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>

@@ -563,21 +564,23 @@ void free_init_pages(char *what, unsigne
 	if (begin >= end)
 		return;
 
-	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
+	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
 		ClearPageReserved(page);
 		init_page_count(page);
 		memset(page_address(page), POISON_FREE_INITMEM, PAGE_SIZE);
+		if (addr >= __START_KERNEL_map)
+			change_page_attr_addr(addr, 1, __pgprot(0));
 		__free_page(page);
 		totalram_pages++;
 	}
+	if (addr > __START_KERNEL_map)
+		global_flush_tlb();
 }
 
 void free_initmem(void)
 {
-	memset(__initdata_begin, POISON_FREE_INITDATA,
-		__initdata_end - __initdata_begin);
 	free_init_pages("unused kernel memory",
 			__pa_symbol(&__init_begin),
 			__pa_symbol(&__init_end));

@@ -587,14 +590,18 @@ void free_initmem(void)
 
 void mark_rodata_ro(void)
 {
-	unsigned long addr = (unsigned long)__va(__pa_symbol(&__start_rodata));
-	unsigned long end  = (unsigned long)__va(__pa_symbol(&__end_rodata));
+	unsigned long start = PFN_ALIGN(__va(__pa_symbol(&_stext))), size;
 
-	for (; addr < end; addr += PAGE_SIZE)
-		change_page_attr_addr(addr, 1, PAGE_KERNEL_RO);
+#ifdef CONFIG_HOTPLUG_CPU
+	/* It must still be possible to apply SMP alternatives. */
+	if (num_possible_cpus() > 1)
+		start = PFN_ALIGN(__va(__pa_symbol(&_etext)));
+#endif
+	size = (unsigned long)__va(__pa_symbol(&__end_rodata)) - start;
+	change_page_attr_addr(start, size >> PAGE_SHIFT, PAGE_KERNEL_RO);
 
-	printk ("Write protecting the kernel read-only data: %luk\n",
-			(__end_rodata - __start_rodata) >> 10);
+	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
+	       size >> 10);
 
 	/*
 	 * change_page_attr_addr() requires a global_flush_tlb() call after it.

Index: linux/arch/x86_64/mm/pageattr.c
===================================================================
@@ -126,7 +126,7 @@ __change_page_attr(unsigned long address
 	struct page *kpte_page;
 	pgprot_t ref_prot2;
 	kpte = lookup_address(address);
-	if (!kpte) return 0;
+	if (!kpte || !pte_present(*kpte)) return 0;
 	kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK);
 	if (pgprot_val(prot) != pgprot_val(ref_prot)) { 
 		if (!pte_huge(*kpte)) {

@@ -179,16 +179,24 @@ __change_page_attr(unsigned long address
 int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
 {
 	unsigned long phys_base_pfn = __pa_symbol(__START_KERNEL_map) >> PAGE_SHIFT;
-	int err = 0; 
+	int err = 0, kernel_map = 0;
 	int i; 
 
+	if (address >= __START_KERNEL_map
+	    && address < __START_KERNEL_map + KERNEL_TEXT_SIZE) {
+		address = (unsigned long)__va(__pa(address));
+		kernel_map = 1;
+	}
+
 	down_write(&init_mm.mmap_sem);
 	for (i = 0; i < numpages; i++, address += PAGE_SIZE) {
 		unsigned long pfn = __pa(address) >> PAGE_SHIFT;
 
-		err = __change_page_attr(address, pfn, prot, PAGE_KERNEL);
-		if (err) 
-			break; 
+		if (!kernel_map || pte_present(pfn_pte(0, prot))) {
+			err = __change_page_attr(address, pfn, prot, PAGE_KERNEL);
+			if (err)
+				break;
+		}
 		/* Handle kernel mapping too which aliases part of the
 		 * lowmem */
 		if ((pfn >= phys_base_pfn) &&

Index: linux/include/asm-i386/pgtable.h
===================================================================
@@ -159,6 +159,7 @@ void paging_init(void);
 
 extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
 #define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
 #define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)

@@ -166,6 +167,7 @@ extern unsigned long long __PAGE_KERNEL,
 #define PAGE_KERNEL		__pgprot(__PAGE_KERNEL)
 #define PAGE_KERNEL_RO		__pgprot(__PAGE_KERNEL_RO)
 #define PAGE_KERNEL_EXEC	__pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX		__pgprot(__PAGE_KERNEL_RX)
 #define PAGE_KERNEL_NOCACHE	__pgprot(__PAGE_KERNEL_NOCACHE)
 #define PAGE_KERNEL_LARGE	__pgprot(__PAGE_KERNEL_LARGE)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot(__PAGE_KERNEL_LARGE_EXEC)

Index: linux/include/linux/poison.h
===================================================================
@@ -26,9 +26,6 @@
 /********** arch/$ARCH/mm/init.c **********/
 #define POISON_FREE_INITMEM	0xcc
 
-/********** arch/x86_64/mm/init.c **********/
-#define	POISON_FREE_INITDATA	0xba
-
 /********** arch/ia64/hp/common/sba_iommu.c **********/
 /*
  * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a

Index: linux/arch/i386/kernel/apm.c
===================================================================
@@ -384,13 +384,6 @@ static int			ignore_sys_suspend;
 static int			ignore_normal_resume;
 static int			bounce_interval __read_mostly = DEFAULT_BOUNCE_INTERVAL;
 
-#ifdef CONFIG_APM_RTC_IS_GMT
-#	define	clock_cmos_diff	0
-#	define	got_clock_diff	1
-#else
-static long			clock_cmos_diff;
-static int			got_clock_diff;
-#endif
 static int			debug __read_mostly;
 static int			smp __read_mostly;
 static int			apm_disabled = -1;

Index: linux/include/asm-i386/processor-flags.h
===================================================================
@@ -0,0 +1,26 @@
+#ifndef __ASM_I386_PROCESSOR_FLAGS_H
+#define __ASM_I386_PROCESSOR_FLAGS_H
+/* Various flags defined: can be included from assembler. */
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF	0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF	0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF	0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF	0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF	0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF	0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF	0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF	0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF	0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL	0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT	0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF	0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM	0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC	0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF	0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP	0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID	0x00200000 /* CPUID detection flag */
+
+#endif	/* __ASM_I386_PROCESSOR_FLAGS_H */

Index: linux/include/asm-i386/irqflags.h
===================================================================
@@ -9,6 +9,7 @@
  */
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
+#include <asm/processor-flags.h>
 
 #ifndef __ASSEMBLY__
 static inline unsigned long native_save_fl(void)

@@ -119,7 +120,7 @@ static inline unsigned long __raw_local_
 
 static inline int raw_irqs_disabled_flags(unsigned long flags)
 {
-	return !(flags & (1 << 9));
+	return !(flags & X86_EFLAGS_IF);
 }
 
 static inline int raw_irqs_disabled(void)

Index: linux/include/asm-i386/processor.h
===================================================================
@@ -21,6 +21,7 @@
 #include <asm/percpu.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
+#include <asm/processor-flags.h>
 
 /* flag for disabling the tsc */
 extern int tsc_disable;

@@ -126,27 +127,6 @@ extern void detect_ht(struct cpuinfo_x86
 static inline void detect_ht(struct cpuinfo_x86 *c) {}
 #endif
 
-/*
- * EFLAGS bits
- */
-#define X86_EFLAGS_CF	0x00000001 /* Carry Flag */
-#define X86_EFLAGS_PF	0x00000004 /* Parity Flag */
-#define X86_EFLAGS_AF	0x00000010 /* Auxillary carry Flag */
-#define X86_EFLAGS_ZF	0x00000040 /* Zero Flag */
-#define X86_EFLAGS_SF	0x00000080 /* Sign Flag */
-#define X86_EFLAGS_TF	0x00000100 /* Trap Flag */
-#define X86_EFLAGS_IF	0x00000200 /* Interrupt Flag */
-#define X86_EFLAGS_DF	0x00000400 /* Direction Flag */
-#define X86_EFLAGS_OF	0x00000800 /* Overflow Flag */
-#define X86_EFLAGS_IOPL	0x00003000 /* IOPL mask */
-#define X86_EFLAGS_NT	0x00004000 /* Nested Task */
-#define X86_EFLAGS_RF	0x00010000 /* Resume Flag */
-#define X86_EFLAGS_VM	0x00020000 /* Virtual Mode */
-#define X86_EFLAGS_AC	0x00040000 /* Alignment Check */
-#define X86_EFLAGS_VIF	0x00080000 /* Virtual Interrupt Flag */
-#define X86_EFLAGS_VIP	0x00100000 /* Virtual Interrupt Pending */
-#define X86_EFLAGS_ID	0x00200000 /* CPUID detection flag */
-
 static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 					 unsigned int *ecx, unsigned int *edx)
 {