Merge commit 'v2.6.32-rc5' into perf/probes

Conflicts:
	kernel/trace/trace_event_profile.c

Merge reason: update to -rc5 and resolve conflict.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

32 files changed, 199 insertions, 183 deletions

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 8c44c232efcb..59cdfa4686b2 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -48,7 +48,7 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 	 * P4, Core and beyond CPUs
 	 */
 	if (c->x86_vendor == X86_VENDOR_INTEL &&
-	    (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 14)))
+	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 14)))
 			flags->bm_control = 0;
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 64970b9885f2..dc69f28489f5 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -227,17 +227,14 @@ static struct irq_cfg *get_one_free_irq_cfg(int node)
 
 	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
 	if (cfg) {
-		if (!alloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
+		if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
 			kfree(cfg);
 			cfg = NULL;
-		} else if (!alloc_cpumask_var_node(&cfg->old_domain,
+		} else if (!zalloc_cpumask_var_node(&cfg->old_domain,
 							  GFP_ATOMIC, node)) {
 			free_cpumask_var(cfg->domain);
 			kfree(cfg);
 			cfg = NULL;
-		} else {
-			cpumask_clear(cfg->domain);
-			cpumask_clear(cfg->old_domain);
 		}
 	}
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index cb66a22d98ad..7ff61d6a188a 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -508,14 +508,14 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
 /*
  * proc handler for /proc/sys/kernel/nmi
  */
-int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
+int proc_nmi_enabled(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos)
 {
 	int old_state;
 
 	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
 	old_state = nmi_watchdog_enabled;
-	proc_dointvec(table, write, file, buffer, length, ppos);
+	proc_dointvec(table, write, buffer, length, ppos);
 	if (!!old_state == !!nmi_watchdog_enabled)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 7029f0e2acad..472763d92098 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -98,8 +98,9 @@ static struct notifier_block mce_raise_nb = {
 };
 
 /* Inject mce on current CPU */
-static int raise_local(struct mce *m)
+static int raise_local(void)
 {
+	struct mce *m = &__get_cpu_var(injectm);
 	int context = MCJ_CTX(m->inject_flags);
 	int ret = 0;
 	int cpu = m->extcpu;
@@ -167,12 +168,12 @@ static void raise_mce(struct mce *m)
 			}
 			cpu_relax();
 		}
-		raise_local(m);
+		raise_local();
 		put_cpu();
 		put_online_cpus();
 	} else
 #endif
-		raise_local(m);
+		raise_local();
 }
 
 /* Error injection interface */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 2f5aab26320e..b1598a9436d0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -85,6 +85,18 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
+static void default_decode_mce(struct mce *m)
+{
+	pr_emerg("No human readable MCE decoding support on this CPU type.\n");
+	pr_emerg("Run the message through 'mcelog --ascii' to decode.\n");
+}
+
+/*
+ * CPU/chipset specific EDAC code can register a callback here to print
+ * MCE errors in a human-readable form:
+ */
+void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce;
+EXPORT_SYMBOL(x86_mce_decode_callback);
 
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
@@ -165,49 +177,46 @@ void mce_log(struct mce *mce)
 	set_bit(0, &mce_need_notify);
 }
 
-void __weak decode_mce(struct mce *m)
-{
-	return;
-}
-
 static void print_mce(struct mce *m)
 {
-	printk(KERN_EMERG
-	       "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
+	pr_emerg("CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n",
 	       m->extcpu, m->mcgstatus, m->bank, m->status);
+
 	if (m->ip) {
-		printk(KERN_EMERG "RIP%s %02x:<%016Lx> ",
-		       !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
-		       m->cs, m->ip);
+		pr_emerg("RIP%s %02x:<%016Lx> ",
+			!(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "",
+				m->cs, m->ip);
+
 		if (m->cs == __KERNEL_CS)
 			print_symbol("{%s}", m->ip);
-		printk(KERN_CONT "\n");
+		pr_cont("\n");
 	}
-	printk(KERN_EMERG "TSC %llx ", m->tsc);
+
+	pr_emerg("TSC %llx ", m->tsc);
 	if (m->addr)
-		printk(KERN_CONT "ADDR %llx ", m->addr);
+		pr_cont("ADDR %llx ", m->addr);
 	if (m->misc)
-		printk(KERN_CONT "MISC %llx ", m->misc);
-	printk(KERN_CONT "\n");
-	printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
-			m->cpuvendor, m->cpuid, m->time, m->socketid,
-			m->apicid);
+		pr_cont("MISC %llx ", m->misc);
+
+	pr_cont("\n");
+	pr_emerg("PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
+		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid);
 
-	decode_mce(m);
+	/*
+	 * Print out human-readable details about the MCE error,
+	 * (if the CPU has an implementation for that):
+	 */
+	x86_mce_decode_callback(m);
 }
 
 static void print_mce_head(void)
 {
-	printk(KERN_EMERG "\nHARDWARE ERROR\n");
+	pr_emerg("\nHARDWARE ERROR\n");
 }
 
 static void print_mce_tail(void)
 {
-	printk(KERN_EMERG "This is not a software problem!\n"
-#if (!defined(CONFIG_EDAC) || !defined(CONFIG_CPU_SUP_AMD))
-	       "Run through mcelog --ascii to decode and contact your hardware vendor\n"
-#endif
-	       );
+	pr_emerg("This is not a software problem!\n");
 }
 
 #define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -221,6 +230,7 @@ static atomic_t mce_fake_paniced;
 static void wait_for_panic(void)
 {
 	long timeout = PANIC_TIMEOUT*USEC_PER_SEC;
+
 	preempt_disable();
 	local_irq_enable();
 	while (timeout-- > 0)
@@ -288,6 +298,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 static int msr_to_offset(u32 msr)
 {
 	unsigned bank = __get_cpu_var(injectm.bank);
+
 	if (msr == rip_msr)
 		return offsetof(struct mce, ip);
 	if (msr == MSR_IA32_MCx_STATUS(bank))
@@ -305,13 +316,25 @@ static int msr_to_offset(u32 msr)
 static u64 mce_rdmsrl(u32 msr)
 {
 	u64 v;
+
 	if (__get_cpu_var(injectm).finished) {
 		int offset = msr_to_offset(msr);
+
 		if (offset < 0)
 			return 0;
 		return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
 	}
-	rdmsrl(msr, v);
+
+	if (rdmsrl_safe(msr, &v)) {
+		WARN_ONCE(1, "mce: Unable to read msr %d!\n", msr);
+		/*
+		 * Return zero in case the access faulted. This should
+		 * not happen normally but can happen if the CPU does
+		 * something weird, or if the code is buggy.
+		 */
+		v = 0;
+	}
+
 	return v;
 }
 
@@ -319,6 +342,7 @@ static void mce_wrmsrl(u32 msr, u64 v)
 {
 	if (__get_cpu_var(injectm).finished) {
 		int offset = msr_to_offset(msr);
+
 		if (offset >= 0)
 			*(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
 		return;
@@ -415,7 +439,7 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
 		m->ip = mce_rdmsrl(rip_msr);
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC 
+#ifdef CONFIG_X86_LOCAL_APIC
 /*
  * Called after interrupts have been reenabled again
  * when a MCE happened during an interrupts off region
@@ -1172,6 +1196,7 @@ static int mce_banks_init(void)
 		return -ENOMEM;
 	for (i = 0; i < banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
+
 		b->ctl = -1ULL;
 		b->init = 1;
 	}
@@ -1203,6 +1228,7 @@ static int __cpuinit mce_cap_init(void)
 	banks = b;
 	if (!mce_banks) {
 		int err = mce_banks_init();
+
 		if (err)
 			return err;
 	}
@@ -1237,6 +1263,7 @@ static void mce_init(void)
 
 	for (i = 0; i < banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
+
 		if (!b->init)
 			continue;
 		wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
@@ -1626,6 +1653,7 @@ static int mce_disable(void)
 
 	for (i = 0; i < banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
+
 		if (b->init)
 			wrmsrl(MSR_IA32_MCx_CTL(i), 0);
 	}
@@ -1911,6 +1939,7 @@ static void mce_disable_cpu(void *h)
 		cmci_clear();
 	for (i = 0; i < banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
+
 		if (b->init)
 			wrmsrl(MSR_IA32_MCx_CTL(i), 0);
 	}
@@ -1928,6 +1957,7 @@ static void mce_reenable_cpu(void *h)
 		cmci_reenable();
 	for (i = 0; i < banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
+
 		if (b->init)
 			wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
 	}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 889f665fe93d..7c785634af2b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
+#include <linux/sched.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 63a56d147e4a..b3a1dba75330 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -34,20 +34,31 @@
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL		(300 * HZ)
 
-static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
-static DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
-static DEFINE_PER_CPU(bool, thermal_throttle_active);
+/*
+ * Current thermal throttling state:
+ */
+struct thermal_state {
+	bool			is_throttled;
+
+	u64			next_check;
+	unsigned long		throttle_count;
+	unsigned long		last_throttle_count;
+};
+
+static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
-static atomic_t therm_throt_en		= ATOMIC_INIT(0);
+static atomic_t therm_throt_en	= ATOMIC_INIT(0);
 
 #ifdef CONFIG_SYSFS
 #define define_therm_throt_sysdev_one_ro(_name)				\
 	static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL)
 
 #define define_therm_throt_sysdev_show_func(name)			\
-static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev,	\
-					struct sysdev_attribute *attr,	\
-					      char *buf)		\
+									\
+static ssize_t therm_throt_sysdev_show_##name(				\
+			struct sys_device *dev,				\
+			struct sysdev_attribute *attr,			\
+			char *buf)					\
 {									\
 	unsigned int cpu = dev->id;					\
 	ssize_t ret;							\
@@ -55,7 +66,7 @@ static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev,	\
 	preempt_disable();	/* CPU hotplug */			\
 	if (cpu_online(cpu))						\
 		ret = sprintf(buf, "%lu\n",				\
-			      per_cpu(thermal_throttle_##name, cpu));	\
+			      per_cpu(thermal_state, cpu).name);	\
 	else								\
 		ret = 0;						\
 	preempt_enable();						\
@@ -63,11 +74,11 @@ static ssize_t therm_throt_sysdev_show_##name(struct sys_device *dev,	\
 	return ret;							\
 }
 
-define_therm_throt_sysdev_show_func(count);
-define_therm_throt_sysdev_one_ro(count);
+define_therm_throt_sysdev_show_func(throttle_count);
+define_therm_throt_sysdev_one_ro(throttle_count);
 
 static struct attribute *thermal_throttle_attrs[] = {
-	&attr_count.attr,
+	&attr_throttle_count.attr,
 	NULL
 };
 
@@ -93,33 +104,39 @@ static struct attribute_group thermal_throttle_attr_group = {
  *          1 : Event should be logged further, and a message has been
  *              printed to the syslog.
  */
-static int therm_throt_process(int curr)
+static int therm_throt_process(bool is_throttled)
 {
-	unsigned int cpu = smp_processor_id();
-	__u64 tmp_jiffs = get_jiffies_64();
-	bool was_throttled = __get_cpu_var(thermal_throttle_active);
-	bool is_throttled = __get_cpu_var(thermal_throttle_active) = curr;
+	struct thermal_state *state;
+	unsigned int this_cpu;
+	bool was_throttled;
+	u64 now;
+
+	this_cpu = smp_processor_id();
+	now = get_jiffies_64();
+	state = &per_cpu(thermal_state, this_cpu);
+
+	was_throttled = state->is_throttled;
+	state->is_throttled = is_throttled;
 
 	if (is_throttled)
-		__get_cpu_var(thermal_throttle_count)++;
+		state->throttle_count++;
 
-	if (!(was_throttled ^ is_throttled) &&
-	    time_before64(tmp_jiffs, __get_cpu_var(next_check)))
+	if (time_before64(now, state->next_check) &&
+			state->throttle_count != state->last_throttle_count)
 		return 0;
 
-	__get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL;
+	state->next_check = now + CHECK_INTERVAL;
+	state->last_throttle_count = state->throttle_count;
 
 	/* if we just entered the thermal event */
 	if (is_throttled) {
-		printk(KERN_CRIT "CPU%d: Temperature above threshold, "
-		       "cpu clock throttled (total events = %lu)\n",
-		       cpu, __get_cpu_var(thermal_throttle_count));
+		printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count);
 
 		add_taint(TAINT_MACHINE_CHECK);
 		return 1;
 	}
 	if (was_throttled) {
-		printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
+		printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu);
 		return 1;
 	}
 
@@ -213,7 +230,7 @@ static void intel_thermal_interrupt(void)
 	__u64 msr_val;
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
-	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT))
+	if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0))
 		mce_log_therm_throt_event(msr_val);
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index f04e72527604..3c1b12d461d1 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -96,17 +96,24 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	unsigned long long base, size;
 	char *ptr;
 	char line[LINE_SIZE];
+	int length;
 	size_t linelen;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (!len)
-		return -EINVAL;
 
 	memset(line, 0, LINE_SIZE);
-	if (len > LINE_SIZE)
-		len = LINE_SIZE;
-	if (copy_from_user(line, buf, len - 1))
+
+	length = len;
+	length--;
+
+	if (length > LINE_SIZE - 1)
+		length = LINE_SIZE - 1;
+
+	if (length < 0)
+		return -EINVAL;
+
+	if (copy_from_user(line, buf, length))
 		return -EFAULT;
 
 	linelen = strlen(line);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a3c7adb06b78..b5801c311846 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1790,6 +1790,9 @@ void smp_perf_pending_interrupt(struct pt_regs *regs)
 void set_perf_event_pending(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
+	if (!x86_pmu.apic || !x86_pmu_initialized())
+		return;
+
 	apic->send_IPI_self(LOCAL_PENDING_VECTOR);
 #endif
 }
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index bca5fba91c9e..f7dd2a7c3bf4 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -5,7 +5,6 @@
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
-#include <linux/utsname.h>
 #include <linux/hardirq.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 54b0a3276766..a071e6be177e 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -5,7 +5,6 @@
 #include <linux/kallsyms.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
-#include <linux/utsname.h>
 #include <linux/hardirq.h>
 #include <linux/kdebug.h>
 #include <linux/module.h>
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 85419bb7d4ab..d17d482a04f4 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1378,8 +1378,8 @@ static unsigned long ram_alignment(resource_size_t pos)
 	if (mb < 16)
 		return 1024*1024;
 
-	/* To 32MB for anything above that */
-	return 32*1024*1024;
+	/* To 64MB for anything above that */
+	return 64*1024*1024;
 }
 
 #define MAX_RESOURCE_SIZE ((resource_size_t)-1)
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 2acfd3fdc0cc..b9c830c12b4a 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -178,6 +178,11 @@ asmlinkage void early_printk(const char *fmt, ...)
 
 static inline void early_console_register(struct console *con, int keep_early)
 {
+	if (early_console->index != -1) {
+		printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n",
+		       con->name);
+		return;
+	}
 	early_console = con;
 	if (keep_early)
 		early_console->flags &= ~CON_BOOT;
@@ -201,8 +206,11 @@ static int __init setup_early_printk(char *buf)
 
 	while (*buf != '\0') {
 		if (!strncmp(buf, "serial", 6)) {
-			early_serial_init(buf + 6);
+			buf += 6;
+			early_serial_init(buf);
 			early_console_register(&early_serial_console, keep);
+			if (!strncmp(buf, ",ttyS", 5))
+				buf += 5;
 		}
 		if (!strncmp(buf, "ttyS", 4)) {
 			early_serial_init(buf + 4);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index b766e8c7252d..050c278481b1 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -79,7 +79,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE)
  * any particular GDT layout, because we load our own as soon as we
  * can.
  */
-.section .text.head,"ax",@progbits
+__HEAD
 ENTRY(startup_32)
 	/* test KEEP_SEGMENTS flag to see if the bootloader is asking
 		us to not reload segments */
@@ -608,7 +608,7 @@ ENTRY(initial_code)
 /*
  * BSS section
  */
-.section ".bss.page_aligned","wa"
+__PAGE_ALIGNED_BSS
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
 swapper_pg_pmd:
@@ -626,7 +626,7 @@ ENTRY(empty_zero_page)
  * This starts the data section.
  */
 #ifdef CONFIG_X86_PAE
-.section ".data.page_aligned","wa"
+__PAGE_ALIGNED_DATA
 	/* Page-aligned for the benefit of paravirt? */
 	.align PAGE_SIZE_asm
 ENTRY(swapper_pg_dir)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index fa54f78e2a05..780cd928fcd5 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -40,7 +40,7 @@ L4_START_KERNEL = pgd_index(__START_KERNEL_map)
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
 	.text
-	.section .text.head
+	__HEAD
 	.code64
 	.globl startup_64
 startup_64:
@@ -418,7 +418,7 @@ ENTRY(phys_base)
 ENTRY(idt_table)
 	.skip IDT_ENTRIES * 16
 
-	.section .bss.page_aligned, "aw", @nobits
+	__PAGE_ALIGNED_BSS
 	.align PAGE_SIZE
 ENTRY(empty_zero_page)
 	.skip PAGE_SIZE
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 43cec6bdda63..9c3bd4a2050e 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -10,6 +10,16 @@
 EXPORT_SYMBOL(mcount);
 #endif
 
+/*
+ * Note, this is a prototype to get at the symbol for
+ * the export, but dont use it from C code, it is used
+ * by assembly code and is not using C calling convention!
+ */
+#ifndef CONFIG_X86_CMPXCHG64
+extern void cmpxchg8b_emu(void);
+EXPORT_SYMBOL(cmpxchg8b_emu);
+#endif
+
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_partial_copy_generic);
 
diff --git a/arch/x86/kernel/init_task.c b/arch/x86/kernel/init_task.c
index 270ff83efc11..3a54dcb9cd0e 100644
--- a/arch/x86/kernel/init_task.c
+++ b/arch/x86/kernel/init_task.c
@@ -20,9 +20,8 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
  * way process stacks are handled. This is done by having a special
  * "init_task" linker map entry..
  */
-union thread_union init_thread_union
-	__attribute__((__section__(".data.init_task"))) =
-		{ INIT_THREAD_INFO(init_task) };
+union thread_union init_thread_union __init_task_data =
+	{ INIT_THREAD_INFO(init_task) };
 
 /*
  * Initial task structure.
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 74656d1d4e30..04bbd5278568 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -63,10 +63,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
 	seq_printf(p, "  Spurious interrupts\n");
-	seq_printf(p, "%*s: ", prec, "CNT");
+	seq_printf(p, "%*s: ", prec, "PMI");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
-	seq_printf(p, "  Performance counter interrupts\n");
+	seq_printf(p, "  Performance monitoring interrupts\n");
 	seq_printf(p, "%*s: ", prec, "PND");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 71f1d99a635d..ec6ef60cbd17 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -67,8 +67,8 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 #ifdef CONFIG_SMP
 		preempt_disable();
 		load_LDT(pc);
-		if (!cpus_equal(current->mm->cpu_vm_mask,
-				cpumask_of_cpu(smp_processor_id())))
+		if (!cpumask_equal(mm_cpumask(current->mm),
+				   cpumask_of(smp_processor_id())))
 			smp_call_function(flush_ldt, current->mm, 1);
 		preempt_enable();
 #else
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 64b838eac18c..b2a71dca5642 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -35,7 +35,7 @@ int iommu_detected __read_mostly = 0;
 
 /*
  * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA ranslation for
+ * If this variable is 1, IOMMU implementations do no DMA translation for
  * devices and allow every device to access to whole physical memory. This is
  * useful if a user want to use an IOMMU only for KVM device assignment to
  * guests and not for driver dma translation.
@@ -311,7 +311,7 @@ void pci_iommu_shutdown(void)
 	amd_iommu_shutdown();
 }
 /* Must execute after PCI subsystem */
-fs_initcall(pci_iommu_init);
+rootfs_initcall(pci_iommu_init);
 
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 98a827ee9ed7..a7f1b64f86e0 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -16,6 +16,7 @@
 #include <linux/agp_backend.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
 #include <linux/pci.h>
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 847ab4160315..5284cd2b5776 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -555,10 +555,8 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 void __init init_c1e_mask(void)
 {
 	/* If we're using c1e_idle, we need to allocate c1e_mask. */
-	if (pm_idle == c1e_idle) {
-		alloc_cpumask_var(&c1e_mask, GFP_KERNEL);
-		cpumask_clear(c1e_mask);
-	}
+	if (pm_idle == c1e_idle)
+		zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
 }
 
 static int __init idle_setup(char *str)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 27349f92a6d7..a1a3cdda06e1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -4,6 +4,7 @@
 #include <linux/pm.h>
 #include <linux/efi.h>
 #include <linux/dmi.h>
+#include <linux/sched.h>
 #include <linux/tboot.h>
 #include <acpi/reboot.h>
 #include <asm/io.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 09c5e077dff7..565ebc65920e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1059,12 +1059,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 #endif
 	current_thread_info()->cpu = 0;  /* needed? */
 	for_each_possible_cpu(i) {
-		alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
-		alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
-		alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
-		cpumask_clear(per_cpu(cpu_core_map, i));
-		cpumask_clear(per_cpu(cpu_sibling_map, i));
-		cpumask_clear(cpu_data(i).llc_shared_map);
+		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
 	}
 	set_cpu_sibling_map(0);
 
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index e293ac56c723..be2573448ed9 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -38,7 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs)
 #ifdef CONFIG_FRAME_POINTER
 		return *(unsigned long *)(regs->bp + sizeof(long));
 #else
-		unsigned long *sp = (unsigned long *)regs->sp;
+		unsigned long *sp =
+			(unsigned long *)kernel_stack_pointer(regs);
 		/*
 		 * Return address is either directly at stack pointer
 		 * or above a saved flags. Eflags has bits 22-31 zero,
@@ -93,7 +94,6 @@ static struct irqaction irq0  = {
 
 void __init setup_default_timer_irq(void)
 {
-	irq0.mask = cpumask_of_cpu(0);
 	setup_irq(0, &irq0);
 }
 
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index 699f7eeb896a..cd022121cab6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -3,8 +3,16 @@
 #include <asm/trampoline.h>
 #include <asm/e820.h>
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
+#define __trampinit
+#define __trampinitdata
+#else
+#define __trampinit __cpuinit
+#define __trampinitdata __cpuinitdata
+#endif
+
 /* ready for x86_64 and x86 */
-unsigned char *__cpuinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
 
 void __init reserve_trampoline_memory(void)
 {
@@ -26,7 +34,7 @@ void __init reserve_trampoline_memory(void)
  * bootstrap into the page concerned. The caller
  * has made sure it's suitably aligned.
  */
-unsigned long __cpuinit setup_trampoline(void)
+unsigned long __trampinit setup_trampoline(void)
 {
 	memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
 	return virt_to_phys(trampoline_base);
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 596d54c660a5..3af2dff58b21 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -32,8 +32,12 @@
 #include <asm/segment.h>
 #include <asm/processor-flags.h>
 
+#ifdef CONFIG_ACPI_SLEEP
+.section .rodata, "a", @progbits
+#else
 /* We can free up the trampoline after bootup if cpu hotplug is not supported. */
 __CPUINITRODATA
+#endif
 .code16
 
 ENTRY(trampoline_data)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9346e102338d..7e37dcee0cc3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -14,7 +14,6 @@
 #include <linux/spinlock.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
-#include <linux/utsname.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -73,11 +72,9 @@ char ignore_fpu_irq;
 
 /*
  * The IDT has to be page-aligned to simplify the Pentium
- * F0 0F bug workaround.. We have a special link segment
- * for this.
+ * F0 0F bug workaround.
  */
-gate_desc idt_table[NR_VECTORS]
-	__attribute__((__section__(".data.idt"))) = { { { { 0, 0 } } }, };
+gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, };
 #endif
 
 DECLARE_BITMAP(used_vectors, NR_VECTORS);
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 027b5b498993..f37930954d15 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -114,7 +114,7 @@ void __cpuinit check_tsc_sync_source(int cpu)
 		return;
 
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
-		pr_info("Skipping synchronization checks as TSC is reliable.\n");
+		printk_once(KERN_INFO "Skipping synchronization checks as TSC is reliable.\n");
 		return;
 	}
 
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 31e6f6cfe53e..d430e4c30193 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -648,7 +648,7 @@ static inline int __init activate_vmi(void)
 
 	pv_info.paravirt_enabled = 1;
 	pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-	pv_info.name = "vmi";
+	pv_info.name = "vmi [deprecated]";
 
 	pv_init_ops.patch = vmi_patch;
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index a46acccec38a..92929fb3f9fa 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -65,17 +65,11 @@ SECTIONS
 #endif
 
 	/* Text and read-only data */
-
-	/* bootstrapping code */
-	.text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
-		_text = .;
-		*(.text.head)
-	} :text = 0x9090
-
-	/* The rest of the text */
 	.text :  AT(ADDR(.text) - LOAD_OFFSET) {
+		_text = .;
+		/* bootstrapping code */
+		HEAD_TEXT
 #ifdef CONFIG_X86_32
-		/* not really needed, already page aligned */
 		. = ALIGN(PAGE_SIZE);
 		*(.text.page_aligned)
 #endif
@@ -94,13 +88,7 @@ SECTIONS
 
 	NOTES :text :note
 
-	/* Exception table */
-	. = ALIGN(16);
-	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
-		__start___ex_table = .;
-		*(__ex_table)
-		__stop___ex_table = .;
-	} :text = 0x9090
+	EXCEPTION_TABLE(16) :text = 0x9090
 
 	RO_DATA(PAGE_SIZE)
 
@@ -118,7 +106,6 @@ SECTIONS
 #endif
 
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
-		*(.data.idt)
 
 		CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES)
 
@@ -135,24 +122,21 @@ SECTIONS
 #ifdef CONFIG_X86_64
 
 #define VSYSCALL_ADDR (-10*1024*1024)
-#define VSYSCALL_PHYS_ADDR ((LOADADDR(.data) + SIZEOF(.data) + \
-                            PAGE_SIZE - 1) & ~(PAGE_SIZE - 1))
-#define VSYSCALL_VIRT_ADDR ((ADDR(.data) + SIZEOF(.data) + \
-                            PAGE_SIZE - 1) & ~(PAGE_SIZE - 1))
 
-#define VLOAD_OFFSET (VSYSCALL_ADDR - VSYSCALL_PHYS_ADDR)
+#define VLOAD_OFFSET (VSYSCALL_ADDR - __vsyscall_0 + LOAD_OFFSET)
 #define VLOAD(x) (ADDR(x) - VLOAD_OFFSET)
 
-#define VVIRT_OFFSET (VSYSCALL_ADDR - VSYSCALL_VIRT_ADDR)
+#define VVIRT_OFFSET (VSYSCALL_ADDR - __vsyscall_0)
 #define VVIRT(x) (ADDR(x) - VVIRT_OFFSET)
 
+	. = ALIGN(4096);
+	__vsyscall_0 = .;
+
 	. = VSYSCALL_ADDR;
-	.vsyscall_0 : AT(VSYSCALL_PHYS_ADDR) {
+	.vsyscall_0 : AT(VLOAD(.vsyscall_0)) {
 		*(.vsyscall_0)
 	} :user
 
-	__vsyscall_0 = VSYSCALL_VIRT_ADDR;
-
 	. = ALIGN(CONFIG_X86_L1_CACHE_BYTES);
 	.vsyscall_fn : AT(VLOAD(.vsyscall_fn)) {
 		*(.vsyscall_fn)
@@ -192,11 +176,9 @@ SECTIONS
 		*(.vsyscall_3)
 	}
 
-	. = VSYSCALL_VIRT_ADDR + PAGE_SIZE;
+	. = __vsyscall_0 + PAGE_SIZE;
 
 #undef VSYSCALL_ADDR
-#undef VSYSCALL_PHYS_ADDR
-#undef VSYSCALL_VIRT_ADDR
 #undef VLOAD_OFFSET
 #undef VLOAD
 #undef VVIRT_OFFSET
@@ -219,36 +201,12 @@ SECTIONS
 	PERCPU_VADDR(0, :percpu)
 #endif
 
-	.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
-		_sinittext = .;
-		INIT_TEXT
-		_einittext = .;
-	}
+	INIT_TEXT_SECTION(PAGE_SIZE)
 #ifdef CONFIG_X86_64
 	:init
 #endif
 
-	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
-		INIT_DATA
-	}
-
-	. = ALIGN(16);
-	.init.setup : AT(ADDR(.init.setup) - LOAD_OFFSET) {
-		__setup_start = .;
-		*(.init.setup)
-		__setup_end = .;
-	}
-	.initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-		__initcall_start = .;
-		INITCALLS
-		__initcall_end = .;
-	}
-
-	.con_initcall.init : AT(ADDR(.con_initcall.init) - LOAD_OFFSET) {
-		__con_initcall_start = .;
-		*(.con_initcall.init)
-		__con_initcall_end = .;
-	}
+	INIT_DATA_SECTION(16)
 
 	.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
 		__x86_cpu_dev_start = .;
@@ -256,8 +214,6 @@ SECTIONS
 		__x86_cpu_dev_end = .;
 	}
 
-	SECURITY_INIT
-
 	. = ALIGN(8);
 	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
 		__parainstructions = .;
@@ -288,15 +244,6 @@ SECTIONS
 		EXIT_DATA
 	}
 
-#ifdef CONFIG_BLK_DEV_INITRD
-	. = ALIGN(PAGE_SIZE);
-	.init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) {
-		__initramfs_start = .;
-		*(.init.ramfs)
-		__initramfs_end = .;
-	}
-#endif
-
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
 	PERCPU(PAGE_SIZE)
 #endif
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index cf53a78e2dcf..8cb4974ff599 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -228,19 +228,11 @@ static long __vsyscall(3) venosys_1(void)
 }
 
 #ifdef CONFIG_SYSCTL
-
-static int
-vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp,
-		       void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	return proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
-}
-
 static ctl_table kernel_table2[] = {
 	{ .procname = "vsyscall64",
 	  .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int),
 	  .mode = 0644,
-	  .proc_handler = vsyscall_sysctl_change },
+	  .proc_handler = proc_dointvec },
 	{}
 };