Merge branch 'linus' into x86/x2apic

54 files changed, 611 insertions, 384 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 81280e9..673f1d1 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -6,6 +6,12 @@ extra-y                := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinu
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
+ifdef CONFIG_FTRACE
+# Do not profile debug utilities
+CFLAGS_REMOVE_tsc.o = -pg
+CFLAGS_REMOVE_rtc.o = -pg
+endif
+
 #
 # vsyscalls (which work on the user stack) should have
 # no stack-protector checks:
@@ -57,6 +63,7 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic_$(BITS).o nmi.o
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic_$(BITS).o
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b314bcd..b41b27a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1411,7 +1411,6 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
 {
 	pr_notice("%s detected: Ignoring BIOS IRQ0 pin2 override\n", d->ident);
 	acpi_skip_timer_override = 1;
-	force_mask_ioapic_irq_2();
 	return 0;
 }
 
diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c
index de2d2e4..7c074ee 100644
--- a/arch/x86/kernel/acpi/processor.c
+++ b/arch/x86/kernel/acpi/processor.c
@@ -56,6 +56,12 @@ static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_ACPI))
 		buf[2] |= ACPI_PDC_T_FFH;
 
+	/*
+	 * If mwait/monitor is unsupported, C2/C3_FFH will be disabled
+	 */
+	if (!cpu_has(c, X86_FEATURE_MWAIT))
+		buf[2] &= ~(ACPI_PDC_C_C2C3_FFH);
+
 	obj->type = ACPI_TYPE_BUFFER;
 	obj->buffer.length = 12;
 	obj->buffer.pointer = (u8 *) buf;
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index e6a4b56..868de3d 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -23,6 +23,15 @@ static unsigned long acpi_realmode;
 static char temp_stack[10240];
 #endif
 
+/* XXX: this macro should move to asm-x86/segment.h and be shared with the
+   boot code... */
+#define GDT_ENTRY(flags, base, limit)		\
+	(((u64)(base & 0xff000000) << 32) |	\
+	 ((u64)flags << 40) |			\
+	 ((u64)(limit & 0x00ff0000) << 32) |	\
+	 ((u64)(base & 0x00ffffff) << 16) |	\
+	 ((u64)(limit & 0x0000ffff)))
+
 /**
  * acpi_save_state_mem - save kernel state
  *
@@ -51,18 +60,27 @@ int acpi_save_state_mem(void)
 	header->video_mode = saved_video_mode;
 
 	header->wakeup_jmp_seg = acpi_wakeup_address >> 4;
+
+	/*
+	 * Set up the wakeup GDT.  We set these up as Big Real Mode,
+	 * that is, with limits set to 4 GB.  At least the Lenovo
+	 * Thinkpad X61 is known to need this for the video BIOS
+	 * initialization quirk to work; this is likely to also
+	 * be the case for other laptops or integrated video devices.
+	 */
+
 	/* GDT[0]: GDT self-pointer */
 	header->wakeup_gdt[0] =
 		(u64)(sizeof(header->wakeup_gdt) - 1) +
 		((u64)(acpi_wakeup_address +
 			((char *)&header->wakeup_gdt - (char *)acpi_realmode))
 				<< 16);
-	/* GDT[1]: real-mode-like code segment */
-	header->wakeup_gdt[1] = (0x009bULL << 40) +
-		((u64)acpi_wakeup_address << 16) + 0xffff;
-	/* GDT[2]: real-mode-like data segment */
-	header->wakeup_gdt[2] = (0x0093ULL << 40) +
-		((u64)acpi_wakeup_address << 16) + 0xffff;
+	/* GDT[1]: big real mode-like code segment */
+	header->wakeup_gdt[1] =
+		GDT_ENTRY(0x809b, acpi_wakeup_address, 0xfffff);
+	/* GDT[2]: big real mode-like data segment */
+	header->wakeup_gdt[2] =
+		GDT_ENTRY(0x8093, acpi_wakeup_address, 0xfffff);
 
 #ifndef CONFIG_64BIT
 	store_gdt((struct desc_ptr *)&header->pmode_gdt);
@@ -140,6 +158,8 @@ static int __init acpi_sleep_setup(char *str)
 			acpi_realmode_flags |= 2;
 		if (strncmp(str, "s3_beep", 7) == 0)
 			acpi_realmode_flags |= 4;
+		if (strncmp(str, "old_ordering", 12) == 0)
+			acpi_old_suspend_ordering();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 65c7857..2763cb3 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1,6 +1,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/kprobes.h>
 #include <linux/mm.h>
@@ -143,7 +143,7 @@ static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
 #ifdef CONFIG_X86_64
 
 extern char __vsyscall_0;
-static inline const unsigned char*const * find_nop_table(void)
+const unsigned char *const *find_nop_table(void)
 {
 	return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	       boot_cpu_data.x86 < 6 ? k8_nops : p6_nops;
@@ -162,7 +162,7 @@ static const struct nop {
 	{ -1, NULL }
 };
 
-static const unsigned char*const * find_nop_table(void)
+const unsigned char *const *find_nop_table(void)
 {
 	const unsigned char *const *noptable = intel_nops;
 	int i;
@@ -279,7 +279,7 @@ struct smp_alt_module {
 	struct list_head next;
 };
 static LIST_HEAD(smp_alt_modules);
-static DEFINE_SPINLOCK(smp_alt);
+static DEFINE_MUTEX(smp_alt);
 static int smp_mode = 1;	/* protected by smp_alt */
 
 void alternatives_smp_module_add(struct module *mod, char *name,
@@ -312,12 +312,12 @@ void alternatives_smp_module_add(struct module *mod, char *name,
 		__func__, smp->locks, smp->locks_end,
 		smp->text, smp->text_end, smp->name);
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 	list_add_tail(&smp->next, &smp_alt_modules);
 	if (boot_cpu_has(X86_FEATURE_UP))
 		alternatives_smp_unlock(smp->locks, smp->locks_end,
 					smp->text, smp->text_end);
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_module_del(struct module *mod)
@@ -327,17 +327,17 @@ void alternatives_smp_module_del(struct module *mod)
 	if (smp_alt_once || noreplace_smp)
 		return;
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 	list_for_each_entry(item, &smp_alt_modules, next) {
 		if (mod != item->mod)
 			continue;
 		list_del(&item->next);
-		spin_unlock(&smp_alt);
+		mutex_unlock(&smp_alt);
 		DPRINTK("%s: %s\n", __func__, item->name);
 		kfree(item);
 		return;
 	}
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_switch(int smp)
@@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 
 	/*
 	 * Avoid unnecessary switches because it forces JIT based VMs to
@@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp)
 						mod->text, mod->text_end);
 	}
 	smp_mode = smp;
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 #endif
diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index cb54d9e..3410196 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -1374,6 +1374,10 @@ void __init smp_intr_init(void)
 
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+
+	/* IPI for single call function */
+	set_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
+				call_function_single_interrupt);
 }
 #endif
 
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 00e6d13..bf9b441 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -204,6 +204,7 @@
 #include <linux/module.h>
 
 #include <linux/poll.h>
+#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/stddef.h>
 #include <linux/timer.h>
@@ -1212,9 +1213,9 @@ static int suspend(int vetoable)
 	if (err != APM_SUCCESS)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
-	device_power_up();
+	device_power_up(PMSG_RESUME);
 	local_irq_enable();
-	device_resume();
+	device_resume(PMSG_RESUME);
 	queue_event(APM_NORMAL_RESUME, NULL);
 	spin_lock(&user_list_lock);
 	for (as = user_list; as != NULL; as = as->next) {
@@ -1239,7 +1240,7 @@ static void standby(void)
 		apm_error("standby", err);
 
 	local_irq_disable();
-	device_power_up();
+	device_power_up(PMSG_RESUME);
 	local_irq_enable();
 }
 
@@ -1325,7 +1326,7 @@ static void check_events(void)
 			ignore_bounce = 1;
 			if ((event != APM_NORMAL_RESUME)
 			    || (ignore_normal_resume == 0)) {
-				device_resume();
+				device_resume(PMSG_RESUME);
 				queue_event(event, NULL);
 			}
 			ignore_normal_resume = 0;
@@ -1549,10 +1550,12 @@ static int do_open(struct inode *inode, struct file *filp)
 {
 	struct apm_user *as;
 
+	lock_kernel();
 	as = kmalloc(sizeof(*as), GFP_KERNEL);
 	if (as == NULL) {
 		printk(KERN_ERR "apm: cannot allocate struct of size %d bytes\n",
 		       sizeof(*as));
+		       unlock_kernel();
 		return -ENOMEM;
 	}
 	as->magic = APM_BIOS_MAGIC;
@@ -1574,6 +1577,7 @@ static int do_open(struct inode *inode, struct file *filp)
 	user_list = as;
 	spin_unlock(&user_list_lock);
 	filp->private_data = as;
+	unlock_kernel();
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index bd182b76..7c36fb8 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -200,6 +200,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		 * benefit in doing so.
 		 */
 		if (!rdmsrl_safe(MSR_K8_TSEG_ADDR, &tseg)) {
+		    printk(KERN_DEBUG "tseg: %010llx\n", tseg);
 		    if ((tseg>>PMD_SHIFT) <
 				(max_low_pfn_mapped>>(PMD_SHIFT-PAGE_SHIFT)) ||
 			((tseg>>PMD_SHIFT) <
diff --git a/arch/x86/kernel/cpu/centaur_64.c b/arch/x86/kernel/cpu/centaur_64.c
index 2026d21..1d181c4 100644
--- a/arch/x86/kernel/cpu/centaur_64.c
+++ b/arch/x86/kernel/cpu/centaur_64.c
@@ -16,16 +16,6 @@ static void __cpuinit early_init_centaur(struct cpuinfo_x86 *c)
 
 static void __cpuinit init_centaur(struct cpuinfo_x86 *c)
 {
-	/* Cache sizes */
-	unsigned n;
-
-	n = c->extended_cpuid_level;
-	if (n >= 0x80000008) {
-		unsigned eax = cpuid_eax(0x80000008);
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-	}
-
 	if (c->x86 == 0x6 && c->x86_model >= 0xf) {
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index e7bf3c2..c6bee77 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -98,7 +98,7 @@ int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 
 void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 {
-	unsigned int n, dummy, eax, ebx, ecx, edx;
+	unsigned int n, dummy, ebx, ecx, edx;
 
 	n = c->extended_cpuid_level;
 
@@ -121,11 +121,6 @@ void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 		printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
 		c->x86_cache_size, ecx & 0xFF);
 	}
-	if (n >= 0x80000008) {
-		cpuid(0x80000008, &eax, &dummy, &dummy, &dummy);
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-	}
 }
 
 void __cpuinit detect_ht(struct cpuinfo_x86 *c)
@@ -314,6 +309,13 @@ static void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
+	if (c->extended_cpuid_level >= 0x80000008) {
+		u32 eax = cpuid_eax(0x80000008);
+
+		c->x86_virt_bits = (eax >> 8) & 0xff;
+		c->x86_phys_bits = eax & 0xff;
+	}
+
 	/* Assume all 64-bit CPUs support 32-bit syscall */
 	set_cpu_cap(c, X86_FEATURE_SYSCALL32);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fe9224c..70609ef 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -226,6 +226,10 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 
 	if (cpu_has_bts)
 		ds_init_intel(c);
+
+#ifdef CONFIG_X86_NUMAQ
+	numaq_tsc_disable();
+#endif
 }
 
 static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
diff --git a/arch/x86/kernel/cpu/intel_64.c b/arch/x86/kernel/cpu/intel_64.c
index 02f7733..1019c58 100644
--- a/arch/x86/kernel/cpu/intel_64.c
+++ b/arch/x86/kernel/cpu/intel_64.c
@@ -54,9 +54,6 @@ static void __cpuinit srat_detect_node(void)
 
 static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
-	/* Cache sizes */
-	unsigned n;
-
 	init_intel_cacheinfo(c);
 	if (c->cpuid_level > 9) {
 		unsigned eax = cpuid_eax(10);
@@ -78,13 +75,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 	if (cpu_has_bts)
 		ds_init_intel(c);
 
-	n = c->extended_cpuid_level;
-	if (n >= 0x80000008) {
-		unsigned eax = cpuid_eax(0x80000008);
-		c->x86_virt_bits = (eax >> 8) & 0xff;
-		c->x86_phys_bits = eax & 0xff;
-	}
-
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
 	if (c->x86 == 6)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 501ca1c..c4a7ec3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/rcupdate.h>
 #include <linux/kallsyms.h>
@@ -363,7 +364,7 @@ static void mcheck_check_cpu(void *info)
 
 static void mcheck_timer(struct work_struct *work)
 {
-	on_each_cpu(mcheck_check_cpu, NULL, 1, 1);
+	on_each_cpu(mcheck_check_cpu, NULL, 1);
 
 	/*
 	 * Alert userspace if needed.  If we logged an MCE, reduce the
@@ -532,10 +533,12 @@ static int open_exclu;	/* already open exclusive? */
 
 static int mce_open(struct inode *inode, struct file *file)
 {
+	lock_kernel();
 	spin_lock(&mce_state_lock);
 
 	if (open_exclu || (open_count && (file->f_flags & O_EXCL))) {
 		spin_unlock(&mce_state_lock);
+		unlock_kernel();
 		return -EBUSY;
 	}
 
@@ -544,6 +547,7 @@ static int mce_open(struct inode *inode, struct file *file)
 	open_count++;
 
 	spin_unlock(&mce_state_lock);
+	unlock_kernel();
 
 	return nonseekable_open(inode, file);
 }
@@ -617,7 +621,7 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize,
 	 * Collect entries that were still getting written before the
 	 * synchronize.
 	 */
-	on_each_cpu(collect_tscs, cpu_tsc, 1, 1);
+	on_each_cpu(collect_tscs, cpu_tsc, 1);
 	for (i = next; i < MCE_LOG_LEN; i++) {
 		if (mcelog.entry[i].finished &&
 		    mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) {
@@ -742,7 +746,7 @@ static void mce_restart(void)
 	if (next_interval)
 		cancel_delayed_work(&mcheck_work);
 	/* Timer race is harmless here */
-	on_each_cpu(mce_init, NULL, 1, 1);
+	on_each_cpu(mce_init, NULL, 1);
 	next_interval = check_interval * HZ;
 	if (next_interval)
 		schedule_delayed_work(&mcheck_work,
diff --git a/arch/x86/kernel/cpu/mcheck/non-fatal.c b/arch/x86/kernel/cpu/mcheck/non-fatal.c
index 00ccb6c..cc1fccd 100644
--- a/arch/x86/kernel/cpu/mcheck/non-fatal.c
+++ b/arch/x86/kernel/cpu/mcheck/non-fatal.c
@@ -59,7 +59,7 @@ static DECLARE_DELAYED_WORK(mce_work, mce_work_fn);
 
 static void mce_work_fn(struct work_struct *work)
 {
-	on_each_cpu(mce_checkregs, NULL, 1, 1);
+	on_each_cpu(mce_checkregs, NULL, 1);
 	schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE));
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 105afe1..6f23969 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -223,7 +223,7 @@ static void set_mtrr(unsigned int reg, unsigned long base,
 	atomic_set(&data.gate,0);
 
 	/*  Start the ball rolling on other CPUs  */
-	if (smp_call_function(ipi_handler, &data, 1, 0) != 0)
+	if (smp_call_function(ipi_handler, &data, 0) != 0)
 		panic("mtrr: timed out waiting for other CPUs\n");
 
 	local_irq_save(flags);
@@ -1682,7 +1682,7 @@ void mtrr_ap_init(void)
  */
 void mtrr_save_state(void)
 {
-	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
+	smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1);
 }
 
 static int __init mtrr_init_finialize(void)
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 2e9bef6..6d4bdc0 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -189,7 +189,7 @@ void disable_lapic_nmi_watchdog(void)
 	if (atomic_read(&nmi_active) <= 0)
 		return;
 
-	on_each_cpu(stop_apic_nmi_watchdog, NULL, 0, 1);
+	on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
 
 	if (wd_ops)
 		wd_ops->unreserve();
@@ -213,7 +213,7 @@ void enable_lapic_nmi_watchdog(void)
 		return;
 	}
 
-	on_each_cpu(setup_apic_nmi_watchdog, NULL, 0, 1);
+	on_each_cpu(setup_apic_nmi_watchdog, NULL, 1);
 	touch_nmi_watchdog();
 }
 
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index daff52a..2de5fa2 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -33,6 +33,7 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
+#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/smp_lock.h>
@@ -95,7 +96,7 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
 	for (; count; count -= 16) {
 		cmd.eax = pos;
 		cmd.ecx = pos >> 32;
-		smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
+		smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1);
 		if (copy_to_user(tmp, &cmd, 16))
 			return -EFAULT;
 		tmp += 16;
@@ -107,15 +108,23 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
 
 static int cpuid_open(struct inode *inode, struct file *file)
 {
-	unsigned int cpu = iminor(file->f_path.dentry->d_inode);
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
-
-	if (cpu >= NR_CPUS || !cpu_online(cpu))
-		return -ENXIO;	/* No such CPU */
+	unsigned int cpu;
+	struct cpuinfo_x86 *c;
+	int ret = 0;
+	
+	lock_kernel();
+
+	cpu = iminor(file->f_path.dentry->d_inode);
+	if (cpu >= NR_CPUS || !cpu_online(cpu)) {
+		ret = -ENXIO;	/* No such CPU */
+		goto out;
+	}
+	c = &cpu_data(cpu);
 	if (c->cpuid_level < 0)
-		return -EIO;	/* CPUID not supported */
-
-	return 0;
+		ret = -EIO;	/* CPUID not supported */
+out:
+	unlock_kernel();
+	return ret;
 }
 
 /*
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index a5383ae..28c2918 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1049,11 +1049,6 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align)
 #endif
 
 /*
- * Last pfn which the user wants to use.
- */
-unsigned long __initdata end_user_pfn = MAX_ARCH_PFN;
-
-/*
  * Find the highest page frame number we have available
  */
 static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
@@ -1085,8 +1080,6 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 
 	if (last_pfn > max_arch_pfn)
 		last_pfn = max_arch_pfn;
-	if (last_pfn > end_user_pfn)
-		last_pfn = end_user_pfn;
 
 	printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
 			 last_pfn, max_arch_pfn);
@@ -1131,12 +1124,6 @@ int __init e820_find_active_region(const struct e820entry *ei,
 	if (*ei_endpfn > last_pfn)
 		*ei_endpfn = last_pfn;
 
-	/* Obey end_user_pfn to save on memmap */
-	if (*ei_startpfn >= end_user_pfn)
-		return 0;
-	if (*ei_endpfn > end_user_pfn)
-		*ei_endpfn = end_user_pfn;
-
 	return 1;
 }
 
@@ -1201,7 +1188,6 @@ static int __init parse_memopt(char *p)
 
 	userdef = 1;
 	mem_size = memparse(p, &p);
-	end_user_pfn = mem_size>>PAGE_SHIFT;
 	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
 	return 0;
@@ -1245,10 +1231,9 @@ static int __init parse_memmap_opt(char *p)
 	} else if (*p == '$') {
 		start_at = memparse(p+1, &p);
 		e820_add_region(start_at, mem_size, E820_RESERVED);
-	} else {
-		end_user_pfn = (mem_size >> PAGE_SHIFT);
+	} else
 		e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
-	}
+
 	return *p == '\0' ? 0 : -EINVAL;
 }
 early_param("memmap", parse_memmap_opt);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index a4665f3..a0e11c0 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -120,7 +120,18 @@ static struct chipset early_qrk[] __initdata = {
 	{}
 };
 
-static void __init check_dev_quirk(int num, int slot, int func)
+/**
+ * check_dev_quirk - apply early quirks to a given PCI device
+ * @num: bus number
+ * @slot: slot number
+ * @func: PCI function
+ *
+ * Check the vendor & device ID against the early quirks table.
+ *
+ * If the device is single function, let early_quirks() know so we don't
+ * poke at this device again.
+ */
+static int __init check_dev_quirk(int num, int slot, int func)
 {
 	u16 class;
 	u16 vendor;
@@ -131,7 +142,7 @@ static void __init check_dev_quirk(int num, int slot, int func)
 	class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE);
 
 	if (class == 0xffff)
-		return;
+		return -1; /* no class, treat as single function */
 
 	vendor = read_pci_config_16(num, slot, func, PCI_VENDOR_ID);
 
@@ -154,7 +165,9 @@ static void __init check_dev_quirk(int num, int slot, int func)
 	type = read_pci_config_byte(num, slot, func,
 				    PCI_HEADER_TYPE);
 	if (!(type & 0x80))
-		return;
+		return -1;
+
+	return 0;
 }
 
 void __init early_quirks(void)
@@ -167,6 +180,9 @@ void __init early_quirks(void)
 	/* Poor man's PCI discovery */
 	for (num = 0; num < 32; num++)
 		for (slot = 0; slot < 32; slot++)
-			for (func = 0; func < 8; func++)
-				check_dev_quirk(num, slot, func);
+			for (func = 0; func < 8; func++) {
+				/* Only probe function 0 on single fn devices */
+				if (check_dev_quirk(num, slot, func))
+					break;
+			}
 }
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 643fd86..ff9e735 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -196,7 +196,7 @@ static struct console simnow_console = {
 static struct console *early_console = &early_vga_console;
 static int early_console_initialized;
 
-void early_printk(const char *fmt, ...)
+asmlinkage void early_printk(const char *fmt, ...)
 {
 	char buf[512];
 	int n;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index cfe28a7..6bc07f0 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -51,6 +51,7 @@
 #include <asm/percpu.h>
 #include <asm/dwarf2.h>
 #include <asm/processor-flags.h>
+#include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
 
 /*
@@ -1111,6 +1112,77 @@ ENDPROC(xen_failsafe_callback)
 
 #endif	/* CONFIG_XEN */
 
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %eax
+	subl $MCOUNT_INSN_SIZE, %eax
+
+.globl mcount_call
+mcount_call:
+	call ftrace_stub
+
+	popl %edx
+	popl %ecx
+	popl %eax
+
+	ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %eax
+	movl 0x4(%ebp), %edx
+	subl $MCOUNT_INSN_SIZE, %eax
+
+.globl ftrace_call
+ftrace_call:
+	call ftrace_stub
+
+	popl %edx
+	popl %ecx
+	popl %eax
+
+.globl ftrace_stub
+ftrace_stub:
+	ret
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
+ENTRY(mcount)
+	cmpl $ftrace_stub, ftrace_trace_function
+	jnz trace
+.globl ftrace_stub
+ftrace_stub:
+	ret
+
+	/* taken from glibc */
+trace:
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %eax
+	movl 0x4(%ebp), %edx
+	subl $MCOUNT_INSN_SIZE, %eax
+
+	call *ftrace_trace_function
+
+	popl %edx
+	popl %ecx
+	popl %eax
+
+	jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
+
 .section .rodata,"a"
 #include "syscall_table_32.S"
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index bb4e22f..ae63e58 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -51,9 +51,115 @@
 #include <asm/page.h>
 #include <asm/irqflags.h>
 #include <asm/paravirt.h>
+#include <asm/ftrace.h>
 
 	.code64
 
+#ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(mcount)
+
+	subq $0x38, %rsp
+	movq %rax, (%rsp)
+	movq %rcx, 8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8, 40(%rsp)
+	movq %r9, 48(%rsp)
+
+	movq 0x38(%rsp), %rdi
+	subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl mcount_call
+mcount_call:
+	call ftrace_stub
+
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq 8(%rsp), %rcx
+	movq (%rsp), %rax
+	addq $0x38, %rsp
+
+	retq
+END(mcount)
+
+ENTRY(ftrace_caller)
+
+	/* taken from glibc */
+	subq $0x38, %rsp
+	movq %rax, (%rsp)
+	movq %rcx, 8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8, 40(%rsp)
+	movq %r9, 48(%rsp)
+
+	movq 0x38(%rsp), %rdi
+	movq 8(%rbp), %rsi
+	subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl ftrace_call
+ftrace_call:
+	call ftrace_stub
+
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq 8(%rsp), %rcx
+	movq (%rsp), %rax
+	addq $0x38, %rsp
+
+.globl ftrace_stub
+ftrace_stub:
+	retq
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+ENTRY(mcount)
+	cmpq $ftrace_stub, ftrace_trace_function
+	jnz trace
+.globl ftrace_stub
+ftrace_stub:
+	retq
+
+trace:
+	/* taken from glibc */
+	subq $0x38, %rsp
+	movq %rax, (%rsp)
+	movq %rcx, 8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8, 40(%rsp)
+	movq %r9, 48(%rsp)
+
+	movq 0x38(%rsp), %rdi
+	movq 8(%rbp), %rsi
+	subq $MCOUNT_INSN_SIZE, %rdi
+
+	call   *ftrace_trace_function
+
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq 8(%rsp), %rcx
+	movq (%rsp), %rax
+	addq $0x38, %rsp
+
+	jmp ftrace_stub
+END(mcount)
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
+
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
 #endif	
@@ -710,6 +816,9 @@ END(invalidate_interrupt\num)
 ENTRY(call_function_interrupt)
 	apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
 END(call_function_interrupt)
+ENTRY(call_function_single_interrupt)
+	apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt
+END(call_function_single_interrupt)
 ENTRY(irq_move_cleanup_interrupt)
 	apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt
 END(irq_move_cleanup_interrupt)
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
new file mode 100644
index 0000000..ab115cd
--- /dev/null
+++ b/arch/x86/kernel/ftrace.c
@@ -0,0 +1,141 @@
+/*
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes to Ingo Molnar, for suggesting the idea.
+ * Mathieu Desnoyers, for suggesting postponing the modifications.
+ * Arjan van de Ven, for keeping me straight, and explaining to me
+ * the dangers of modifying code on the run.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/hardirq.h>
+#include <linux/ftrace.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/list.h>
+
+#include <asm/alternative.h>
+#include <asm/ftrace.h>
+
+
+/* Long is fine, even if it is only 4 bytes ;-) */
+static long *ftrace_nop;
+
+union ftrace_code_union {
+	char code[MCOUNT_INSN_SIZE];
+	struct {
+		char e8;
+		int offset;
+	} __attribute__((packed));
+};
+
+
+static int notrace ftrace_calc_offset(long ip, long addr)
+{
+	return (int)(addr - ip);
+}
+
+notrace unsigned char *ftrace_nop_replace(void)
+{
+	return (char *)ftrace_nop;
+}
+
+notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+{
+	static union ftrace_code_union calc;
+
+	calc.e8		= 0xe8;
+	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
+
+	/*
+	 * No locking needed, this must be called via kstop_machine
+	 * which in essence is like running on a uniprocessor machine.
+	 */
+	return calc.code;
+}
+
+notrace int
+ftrace_modify_code(unsigned long ip, unsigned char *old_code,
+		   unsigned char *new_code)
+{
+	unsigned replaced;
+	unsigned old = *(unsigned *)old_code; /* 4 bytes */
+	unsigned new = *(unsigned *)new_code; /* 4 bytes */
+	unsigned char newch = new_code[4];
+	int faulted = 0;
+
+	/*
+	 * Note: Due to modules and __init, code can
+	 *  disappear and change, we need to protect against faulting
+	 *  as well as code changing.
+	 *
+	 * No real locking needed, this code is run through
+	 * kstop_machine.
+	 */
+	asm volatile (
+		"1: lock\n"
+		"   cmpxchg %3, (%2)\n"
+		"   jnz 2f\n"
+		"   movb %b4, 4(%2)\n"
+		"2:\n"
+		".section .fixup, \"ax\"\n"
+		"3:	movl $1, %0\n"
+		"	jmp 2b\n"
+		".previous\n"
+		_ASM_EXTABLE(1b, 3b)
+		: "=r"(faulted), "=a"(replaced)
+		: "r"(ip), "r"(new), "c"(newch),
+		  "0"(faulted), "a"(old)
+		: "memory");
+	sync_core();
+
+	if (replaced != old && replaced != new)
+		faulted = 2;
+
+	return faulted;
+}
+
+notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	int ret;
+
+	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = ftrace_modify_code(ip, old, new);
+
+	return ret;
+}
+
+notrace int ftrace_mcount_set(unsigned long *data)
+{
+	unsigned long ip = (long)(&mcount_call);
+	unsigned long *addr = data;
+	unsigned char old[MCOUNT_INSN_SIZE], *new;
+
+	/*
+	 * Replace the mcount stub with a pointer to the
+	 * ip recorder function.
+	 */
+	memcpy(old, &mcount_call, MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(ip, *addr);
+	*addr = ftrace_modify_code(ip, old, new);
+
+	return 0;
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	const unsigned char *const *noptable = find_nop_table();
+
+	/* This is running in kstop_machine */
+
+	ftrace_mcount_set(data);
+
+	ftrace_nop = (unsigned long *)noptable[MCOUNT_INSN_SIZE];
+
+	return 0;
+}
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ea230ec..0ea6a19 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -36,26 +36,15 @@ static inline void hpet_writel(unsigned long d, unsigned long a)
 }
 
 #ifdef CONFIG_X86_64
-
 #include <asm/pgtable.h>
-
-static inline void hpet_set_mapping(void)
-{
-	set_fixmap_nocache(FIX_HPET_BASE, hpet_address);
-	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
-	hpet_virt_address = (void __iomem *)fix_to_virt(FIX_HPET_BASE);
-}
-
-static inline void hpet_clear_mapping(void)
-{
-	hpet_virt_address = NULL;
-}
-
-#else
+#endif
 
 static inline void hpet_set_mapping(void)
 {
 	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+#ifdef CONFIG_X86_64
+	__set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VSYSCALL_NOCACHE);
+#endif
 }
 
 static inline void hpet_clear_mapping(void)
@@ -63,7 +52,6 @@ static inline void hpet_clear_mapping(void)
 	iounmap(hpet_virt_address);
 	hpet_virt_address = NULL;
 }
-#endif
 
 /*
  * HPET command line enable / disable
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index deb4378..dd7ebee 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -1,7 +1,14 @@
 #include <linux/module.h>
+
 #include <asm/checksum.h>
-#include <asm/desc.h>
 #include <asm/pgtable.h>
+#include <asm/desc.h>
+#include <asm/ftrace.h>
+
+#ifdef CONFIG_FTRACE
+/* mcount is defined in assembly */
+EXPORT_SYMBOL(mcount);
+#endif
 
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_partial_copy_generic);
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 382208d..a82065b 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -59,13 +59,6 @@ static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 static DEFINE_SPINLOCK(ioapic_lock);
 static DEFINE_SPINLOCK(vector_lock);
 
-static bool mask_ioapic_irq_2 __initdata;
-
-void __init force_mask_ioapic_irq_2(void)
-{
-	mask_ioapic_irq_2 = true;
-}
-
 int timer_through_8259 __initdata;
 
 /*
@@ -1576,7 +1569,7 @@ void /*__init*/ print_local_APIC(void *dummy)
 
 void print_all_local_APICs(void)
 {
-	on_each_cpu(print_local_APIC, NULL, 1, 1);
+	on_each_cpu(print_local_APIC, NULL, 1);
 }
 
 void /*__init*/ print_PIC(void)
@@ -2186,9 +2179,6 @@ static inline void __init check_timer(void)
 	printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
 		vector, apic1, pin1, apic2, pin2);
 
-	if (mask_ioapic_irq_2)
-		mask_IO_APIC_irq(2);
-
 	/*
 	 * Some BIOS writers are clueless and report the ExtINTA
 	 * I/O APIC input from the cascaded 8259A as the timer
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 2db0f98..39f0be3 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -96,13 +96,6 @@ static int no_timer_check;
 
 static int disable_timer_pin_1 __initdata;
 
-static bool mask_ioapic_irq_2 __initdata;
-
-void __init force_mask_ioapic_irq_2(void)
-{
-	mask_ioapic_irq_2 = true;
-}
-
 int timer_through_8259 __initdata;
 
 /* Where if anywhere is the i8259 connect in external int mode */
@@ -1314,7 +1307,7 @@ void __apicdebuginit print_local_APIC(void * dummy)
 
 void print_all_local_APICs (void)
 {
-	on_each_cpu(print_local_APIC, NULL, 1, 1);
+	on_each_cpu(print_local_APIC, NULL, 1);
 }
 
 void __apicdebuginit print_PIC(void)
@@ -2020,9 +2013,6 @@ static inline void __init check_timer(void)
 	apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
 		cfg->vector, apic1, pin1, apic2, pin2);
 
-	if (mask_ioapic_irq_2)
-		mask_IO_APIC_irq(2);
-
 	/*
 	 * Some BIOS writers are clueless and report the ExtINTA
 	 * I/O APIC input from the cascaded 8259A as the timer
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 31f49e8..0373e88 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -199,6 +199,10 @@ void __init native_init_IRQ(void)
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
+	/* IPI for generic single function call */
+	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
+			call_function_single_interrupt);
+
 	/* Low priority IPI to cleanup after moving an irq */
 	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 #endif
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 21f2bae..a844957 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -68,7 +68,7 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 		load_LDT(pc);
 		mask = cpumask_of_cpu(smp_processor_id());
 		if (!cpus_equal(current->mm->cpu_vm_mask, mask))
-			smp_call_function(flush_ldt, current->mm, 1, 1);
+			smp_call_function(flush_ldt, current->mm, 1);
 		preempt_enable();
 #else
 		load_LDT(pc);
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index f496017..8864230 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -11,6 +11,8 @@
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/numa.h>
+#include <linux/ftrace.h>
+
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
@@ -107,6 +109,8 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
 
+	tracer_disable();
+
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 7830dc4..9dd9262 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -11,6 +11,8 @@
 #include <linux/string.h>
 #include <linux/reboot.h>
 #include <linux/numa.h>
+#include <linux/ftrace.h>
+
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -184,6 +186,8 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
 
+	tracer_disable();
+
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c
index 9758fea..56b9331 100644
--- a/arch/x86/kernel/microcode.c
+++ b/arch/x86/kernel/microcode.c
@@ -76,6 +76,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/cpumask.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -423,6 +424,7 @@ out:
 
 static int microcode_open (struct inode *unused1, struct file *unused2)
 {
+	cycle_kernel_lock();
 	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
 }
 
@@ -489,7 +491,7 @@ MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 #define microcode_dev_exit() do { } while(0)
 #endif
 
-static long get_next_ucode_from_buffer(void **mc, void *buf,
+static long get_next_ucode_from_buffer(void **mc, const u8 *buf,
 	unsigned long size, long offset)
 {
 	microcode_header_t *mc_header;
@@ -523,7 +525,7 @@ static int cpu_request_microcode(int cpu)
 	char name[30];
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	const struct firmware *firmware;
-	void *buf;
+	const u8 *buf;
 	unsigned long size;
 	long offset = 0;
 	int error;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 1f3abe0..a153b39 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -117,12 +117,20 @@ static int msr_open(struct inode *inode, struct file *file)
 {
 	unsigned int cpu = iminor(file->f_path.dentry->d_inode);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	int ret = 0;
 
-	if (cpu >= NR_CPUS || !cpu_online(cpu))
-		return -ENXIO;	/* No such CPU */
-	if (!cpu_has(c, X86_FEATURE_MSR))
-		return -EIO;	/* MSR not supported */
+	lock_kernel();
+	cpu = iminor(file->f_path.dentry->d_inode);
 
+	if (cpu >= NR_CPUS || !cpu_online(cpu)) {
+		ret = -ENXIO;	/* No such CPU */
+		goto out;
+	}
+	c = &cpu_data(cpu);
+	if (!cpu_has(c, X86_FEATURE_MSR))
+		ret = -EIO;	/* MSR not supported */
+out:
+	unlock_kernel();
 	return 0;
 }
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 716b892..ec024b3 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -130,7 +130,7 @@ int __init check_nmi_watchdog(void)
 
 #ifdef CONFIG_SMP
 	if (nmi_watchdog == NMI_LOCAL_APIC)
-		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0);
+		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
 #endif
 
 	for_each_possible_cpu(cpu)
@@ -272,7 +272,7 @@ static void __acpi_nmi_enable(void *__unused)
 void acpi_nmi_enable(void)
 {
 	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-		on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
+		on_each_cpu(__acpi_nmi_enable, NULL, 1);
 }
 
 static void __acpi_nmi_disable(void *__unused)
@@ -286,7 +286,7 @@ static void __acpi_nmi_disable(void *__unused)
 void acpi_nmi_disable(void)
 {
 	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-		on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
+		on_each_cpu(__acpi_nmi_disable, NULL, 1);
 }
 
 void setup_apic_nmi_watchdog(void *unused)
diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c
index f0f1de1..a23e823 100644
--- a/arch/x86/kernel/numaq_32.c
+++ b/arch/x86/kernel/numaq_32.c
@@ -93,12 +93,13 @@ int __init get_memcfg_numaq(void)
 	return 1;
 }
 
-static int __init numaq_tsc_disable(void)
+void __init numaq_tsc_disable(void)
 {
+	if (!found_numaq)
+		return;
+
 	if (num_online_nodes() > 1) {
 		printk(KERN_DEBUG "NUMAQ: disabling TSC\n");
 		setup_clear_cpu_cap(X86_FEATURE_TSC);
 	}
-	return 0;
 }
-arch_initcall(numaq_tsc_disable);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index d0d18db..c3fe784 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -630,6 +630,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 	struct pci_dev *dev;
 	void *gatt;
 	int i, error;
+	unsigned long start_pfn, end_pfn;
 
 	printk(KERN_INFO "PCI-DMA: Disabling AGP.\n");
 	aper_size = aper_base = info->aper_size = 0;
@@ -674,6 +675,13 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 	printk(KERN_INFO "PCI-DMA: aperture base @ %x size %u KB\n",
 	       aper_base, aper_size>>10);
+
+	/* need to map that range */
+	end_pfn = (aper_base>>PAGE_SHIFT) + (aper_size>>PAGE_SHIFT);
+	if (end_pfn > max_low_pfn_mapped) {
+		start_pfn = (aper_base>>PAGE_SHIFT);
+		init_memory_mapping(start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
+	}
 	return 0;
 
  nommu:
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 4061d63..4d629c6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -7,6 +7,12 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
+#include <asm/system.h>
+
+unsigned long idle_halt;
+EXPORT_SYMBOL(idle_halt);
+unsigned long idle_nomwait;
+EXPORT_SYMBOL(idle_nomwait);
 
 struct kmem_cache *task_xstate_cachep;
 
@@ -132,7 +138,7 @@ void cpu_idle_wait(void)
 {
 	smp_mb();
 	/* kick all the CPUs so that they exit out of pm_idle */
-	smp_call_function(do_nothing, NULL, 0, 1);
+	smp_call_function(do_nothing, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
@@ -325,7 +331,27 @@ static int __init idle_setup(char *str)
 		pm_idle = poll_idle;
 	} else if (!strcmp(str, "mwait"))
 		force_mwait = 1;
-	else
+	else if (!strcmp(str, "halt")) {
+		/*
+		 * When the boot option of idle=halt is added, halt is
+		 * forced to be used for CPU idle. In such case CPU C2/C3
+		 * won't be used again.
+		 * To continue to load the CPU idle driver, don't touch
+		 * the boot_option_idle_override.
+		 */
+		pm_idle = default_idle;
+		idle_halt = 1;
+		return 0;
+	} else if (!strcmp(str, "nomwait")) {
+		/*
+		 * If the boot option of "idle=nomwait" is added,
+		 * it means that mwait will be disabled for CPU C2/C3
+		 * states. In such case it won't touch the variable
+		 * of boot_option_idle_override.
+		 */
+		idle_nomwait = 1;
+		return 0;
+	} else
 		return -1;
 
 	boot_option_idle_override = 1;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9a139f6..0c3927a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -142,7 +142,10 @@ void cpu_idle(void)
 
 			local_irq_disable();
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
+			/* Don't trace irqs off for idle */
+			stop_critical_timings();
 			pm_idle();
+			start_critical_timings();
 		}
 		tick_nohz_restart_sched_tick();
 		preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index db5eb96..a8e5362 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -134,7 +134,10 @@ void cpu_idle(void)
 			 */
 			local_irq_disable();
 			enter_idle();
+			/* Don't trace irqs off for idle */
+			stop_critical_timings();
 			pm_idle();
+			start_critical_timings();
 			/* In many cases the interrupt that ended idle
 			   has already called exit_idle. But some idle
 			   loops can be woken up without interrupt. */
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 79bdcd1..d138588 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -266,6 +266,8 @@ static void old_ich_force_enable_hpet_user(struct pci_dev *dev)
 		hpet_print_force_info();
 }
 
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB_1,
+			 old_ich_force_enable_hpet_user);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0,
 			 old_ich_force_enable_hpet_user);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2e78a14..6121ffd 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -684,6 +684,11 @@ void __init setup_arch(char **cmdline_p)
 		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 	}
 
+#ifdef CONFIG_PCI
+	if (pci_early_dump_regs)
+		early_dump_pci_devices();
+#endif
+
 	finish_e820_parsing();
 
 #ifdef CONFIG_X86_32
@@ -851,6 +856,14 @@ void __init setup_arch(char **cmdline_p)
 	init_cpu_to_node();
 #endif
 
+#ifdef CONFIG_X86_NUMAQ
+	/*
+	 * need to check online nodes num, call it
+	 * here before time_init/tsc_init
+	 */
+	numaq_tsc_disable();
+#endif
+
 	init_apic_mappings();
 	ioapic_init_mappings();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 5fc310f..cac6843 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -343,23 +343,23 @@ static const cpumask_t cpu_mask_none;
 /*
  * Returns a pointer to the bitmask of CPUs on Node 'node'.
  */
-cpumask_t *_node_to_cpumask_ptr(int node)
+const cpumask_t *_node_to_cpumask_ptr(int node)
 {
 	if (node_to_cpumask_map == NULL) {
 		printk(KERN_WARNING
 			"_node_to_cpumask_ptr(%d): no node_to_cpumask_map!\n",
 			node);
 		dump_stack();
-		return &cpu_online_map;
+		return (const cpumask_t *)&cpu_online_map;
 	}
 	if (node >= nr_node_ids) {
 		printk(KERN_WARNING
 			"_node_to_cpumask_ptr(%d): node > nr_node_ids(%d)\n",
 			node, nr_node_ids);
 		dump_stack();
-		return (cpumask_t *)&cpu_mask_none;
+		return &cpu_mask_none;
 	}
-	return (cpumask_t *)&node_to_cpumask_map[node];
+	return &node_to_cpumask_map[node];
 }
 EXPORT_SYMBOL(_node_to_cpumask_ptr);
 
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 0cb7aad..361b7a4 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -121,132 +121,23 @@ static void native_smp_send_reschedule(int cpu)
 	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
 }
 
-/*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-};
-
-void lock_ipi_call_lock(void)
+void native_send_call_func_single_ipi(int cpu)
 {
-	spin_lock_irq(&call_lock);
-}
-
-void unlock_ipi_call_lock(void)
-{
-	spin_unlock_irq(&call_lock);
-}
-
-static struct call_data_struct *call_data;
-
-static void __smp_call_function(void (*func) (void *info), void *info,
-				int nonatomic, int wait)
-{
-	struct call_data_struct data;
-	int cpus = num_online_cpus() - 1;
-
-	if (!cpus)
-		return;
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb();
-
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_IPI_allbutself(CALL_FUNCTION_VECTOR);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
+	send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_SINGLE_VECTOR);
 }
 
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.  Must not include the current cpu.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
-  * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-static int
-native_smp_call_function_mask(cpumask_t mask,
-			      void (*func)(void *), void *info,
-			      int wait)
+void native_send_call_func_ipi(cpumask_t mask)
 {
-	struct call_data_struct data;
 	cpumask_t allbutself;
-	int cpus;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	/* Holding any lock stops cpus from going down. */
-	spin_lock(&call_lock);
 
 	allbutself = cpu_online_map;
 	cpu_clear(smp_processor_id(), allbutself);
 
-	cpus_and(mask, mask, allbutself);
-	cpus = cpus_weight(mask);
-
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
-	}
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	wmb();
-
-	/* Send a message to other CPUs */
 	if (cpus_equal(mask, allbutself) &&
 	    cpus_equal(cpu_online_map, cpu_callout_map))
 		send_IPI_allbutself(CALL_FUNCTION_VECTOR);
 	else
 		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-	spin_unlock(&call_lock);
-
-	return 0;
 }
 
 static void stop_this_cpu(void *dummy)
@@ -268,18 +159,13 @@ static void stop_this_cpu(void *dummy)
 
 static void native_smp_send_stop(void)
 {
-	int nolock;
 	unsigned long flags;
 
 	if (reboot_force)
 		return;
 
-	/* Don't deadlock on the call lock in panic */
-	nolock = !spin_trylock(&call_lock);
+	smp_call_function(stop_this_cpu, NULL, 0);
 	local_irq_save(flags);
-	__smp_call_function(stop_this_cpu, NULL, 0, 0);
-	if (!nolock)
-		spin_unlock(&call_lock);
 	disable_local_APIC();
 	local_irq_restore(flags);
 }
@@ -301,33 +187,28 @@ void smp_reschedule_interrupt(struct pt_regs *regs)
 
 void smp_call_function_interrupt(struct pt_regs *regs)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
-
 	ack_APIC_irq();
-	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
-	 */
-	mb();
-	atomic_inc(&call_data->started);
-	/*
-	 * At this point the info structure may be out of scope unless wait==1
-	 */
 	irq_enter();
-	(*func)(info);
+	generic_smp_call_function_interrupt();
 #ifdef CONFIG_X86_32
 	__get_cpu_var(irq_stat).irq_call_count++;
 #else
 	add_pda(irq_call_count, 1);
 #endif
 	irq_exit();
+}
 
-	if (wait) {
-		mb();
-		atomic_inc(&call_data->finished);
-	}
+void smp_call_function_single_interrupt(struct pt_regs *regs)
+{
+	ack_APIC_irq();
+	irq_enter();
+	generic_smp_call_function_single_interrupt();
+#ifdef CONFIG_X86_32
+	__get_cpu_var(irq_stat).irq_call_count++;
+#else
+	add_pda(irq_call_count, 1);
+#endif
+	irq_exit();
 }
 
 struct smp_ops smp_ops = {
@@ -338,7 +219,8 @@ struct smp_ops smp_ops = {
 
 	.smp_send_stop = native_smp_send_stop,
 	.smp_send_reschedule = native_smp_send_reschedule,
-	.smp_call_function_mask = native_smp_call_function_mask,
+
+	.send_call_func_ipi = native_send_call_func_ipi,
+	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
-
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 6cd002f..23c3b3d 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -328,12 +328,12 @@ static void __cpuinit start_secondary(void *unused)
 	 * lock helps us to not include this cpu in a currently in progress
 	 * smp_call_function().
 	 */
-	lock_ipi_call_lock();
+	ipi_call_lock_irq();
 #ifdef CONFIG_X86_IO_APIC
 	setup_vector_irq(smp_processor_id());
 #endif
 	cpu_set(smp_processor_id(), cpu_online_map);
-	unlock_ipi_call_lock();
+	ipi_call_unlock_irq();
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 
 	setup_secondary_clock();
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
index 3449064..99941b3 100644
--- a/arch/x86/kernel/smpcommon.c
+++ b/arch/x86/kernel/smpcommon.c
@@ -25,59 +25,3 @@ __cpuinit void init_gdt(int cpu)
 	per_cpu(cpu_number, cpu) = cpu;
 }
 #endif
-
-/**
- * smp_call_function(): Run a function on all other CPUs.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: Unused.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function(void (*func) (void *info), void *info, int nonatomic,
-		      int wait)
-{
-	return smp_call_function_mask(cpu_online_map, func, info, wait);
-}
-EXPORT_SYMBOL(smp_call_function);
-
-/**
- * smp_call_function_single - Run a function on a specific CPU
- * @cpu: The target CPU.  Cannot be the calling CPU.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @nonatomic: Unused.
- * @wait: If true, wait until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- */
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int nonatomic, int wait)
-{
-	/* prevent preemption and reschedule on another processor */
-	int ret;
-	int me = get_cpu();
-	if (cpu == me) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-		put_cpu();
-		return 0;
-	}
-
-	ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait);
-
-	put_cpu();
-	return ret;
-}
-EXPORT_SYMBOL(smp_call_function_single);
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index c28c342..a03e7f6 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -74,6 +74,7 @@ void save_stack_trace(struct stack_trace *trace)
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
+EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
@@ -81,3 +82,4 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index 9bb2363..fec1ece 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -238,6 +238,6 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
+	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
index 5039d0f..dcbf7a1 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -275,5 +275,5 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-	on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
+	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c
index 74e9929..2696a68 100644
--- a/arch/x86/kernel/traps_64.c
+++ b/arch/x86/kernel/traps_64.c
@@ -105,30 +105,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
 
 void printk_address(unsigned long address, int reliable)
 {
-#ifdef CONFIG_KALLSYMS
-	unsigned long offset = 0, symsize;
-	const char *symname;
-	char *modname;
-	char *delim = ":";
-	char namebuf[KSYM_NAME_LEN];
-	char reliab[4] = "";
-
-	symname = kallsyms_lookup(address, &symsize, &offset,
-					&modname, namebuf);
-	if (!symname) {
-		printk(" [<%016lx>]\n", address);
-		return;
-	}
-	if (!reliable)
-		strcpy(reliab, "? ");
-
-	if (!modname)
-		modname = delim = "";
-	printk(" [<%016lx>] %s%s%s%s%s+0x%lx/0x%lx\n",
-		address, reliab, delim, modname, delim, symname, offset, symsize);
-#else
-	printk(" [<%016lx>]\n", address);
-#endif
+	printk(" [<%016lx>] %s%pS\n", address, reliable ? "": "? ", (void *) address);
 }
 
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 3c36f92..7603c05 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -358,6 +358,7 @@ static cycle_t read_tsc(void)
 		ret : clocksource_tsc.cycle_last;
 }
 
+#ifdef CONFIG_X86_64
 static cycle_t __vsyscall_fn vread_tsc(void)
 {
 	cycle_t ret = (cycle_t)vget_cycles();
@@ -365,6 +366,7 @@ static cycle_t __vsyscall_fn vread_tsc(void)
 	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
 		ret : __vsyscall_gtod_data.clock.cycle_last;
 }
+#endif
 
 static struct clocksource clocksource_tsc = {
 	.name                   = "tsc",
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 2674f57..cdb2363 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -49,16 +49,14 @@ SECTIONS
   	_etext = .;			/* End of text section */
   } :text = 0x9090
 
+  NOTES :text :note
+
   . = ALIGN(16);		/* Exception table */
   __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
   	__start___ex_table = .;
 	 *(__ex_table)
   	__stop___ex_table = .;
-  }
-
-  NOTES :text :note
-
-  BUG_TABLE :text
+  } :text = 0x9090
 
   RODATA
 
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index fd246e2..63e5c1a 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -19,7 +19,7 @@ PHDRS {
 	data PT_LOAD FLAGS(7);	/* RWE */
 	user PT_LOAD FLAGS(7);	/* RWE */
 	data.init PT_LOAD FLAGS(7);	/* RWE */
-	note PT_NOTE FLAGS(4);	/* R__ */
+	note PT_NOTE FLAGS(0);	/* ___ */
 }
 SECTIONS
 {
@@ -40,16 +40,14 @@ SECTIONS
 	_etext = .;		/* End of text section */
   } :text = 0x9090
 
+  NOTES :text :note
+
   . = ALIGN(16);		/* Exception table */
   __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
   	__start___ex_table = .;
 	 *(__ex_table)
   	__stop___ex_table = .;
-  }
-
-  NOTES :text :note
-
-  BUG_TABLE :text
+  } :text = 0x9090
 
   RODATA
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index c87cbd8..0b8b669 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -42,7 +42,8 @@
 #include <asm/topology.h>
 #include <asm/vgtod.h>
 
-#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
+#define __vsyscall(nr) \
+		__attribute__ ((unused, __section__(".vsyscall_" #nr))) notrace
 #define __syscall_clobber "r11","cx","memory"
 
 /*
@@ -278,7 +279,7 @@ cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
 {
 	long cpu = (long)arg;
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
-		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1);
+		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);
 	return NOTIFY_DONE;
 }
 
@@ -301,7 +302,7 @@ static int __init vsyscall_init(void)
 #ifdef CONFIG_SYSCTL
 	register_sysctl_table(kernel_root_table2);
 #endif
-	on_each_cpu(cpu_vsyscall_init, NULL, 0, 1);
+	on_each_cpu(cpu_vsyscall_init, NULL, 1);
 	hotcpu_notifier(cpu_vsyscall_notifier, 0);
 	return 0;
 }
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 2f306a8..b545f37 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -2,13 +2,20 @@
    All C exports should go in the respective C files. */
 
 #include <linux/module.h>
-#include <net/checksum.h>
 #include <linux/smp.h>
 
+#include <net/checksum.h>
+
 #include <asm/processor.h>
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
+#include <asm/uaccess.h>
 #include <asm/desc.h>
+#include <asm/ftrace.h>
+
+#ifdef CONFIG_FTRACE
+/* mcount is defined in assembly */
+EXPORT_SYMBOL(mcount);
+#endif
 
 EXPORT_SYMBOL(kernel_thread);