Merge branch 'master'

27 files changed, 506 insertions, 204 deletions

diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index 65656c033d70..5b9ed21216cf 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y := head.o init_task.o vmlinux.lds
 obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o \
 		ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \
 		pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \
-		quirks.o i8237.o topology.o
+		quirks.o i8237.o topology.o alternative.o
 
 obj-y				+= cpu/
 obj-y				+= timers/
diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
new file mode 100644
index 000000000000..5cbd6f99fb2a
--- /dev/null
+++ b/arch/i386/kernel/alternative.c
@@ -0,0 +1,321 @@
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <asm/alternative.h>
+#include <asm/sections.h>
+
+#define DEBUG 0
+#if DEBUG
+# define DPRINTK(fmt, args...) printk(fmt, args)
+#else
+# define DPRINTK(fmt, args...)
+#endif
+
+/* Use inline assembly to define this because the nops are defined
+   as inline assembly strings in the include files and we cannot
+   get them easily into strings. */
+asm("\t.data\nintelnops: "
+	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
+	GENERIC_NOP7 GENERIC_NOP8);
+asm("\t.data\nk8nops: "
+	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
+	K8_NOP7 K8_NOP8);
+asm("\t.data\nk7nops: "
+	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
+	K7_NOP7 K7_NOP8);
+
+extern unsigned char intelnops[], k8nops[], k7nops[];
+static unsigned char *intel_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	intelnops,
+	intelnops + 1,
+	intelnops + 1 + 2,
+	intelnops + 1 + 2 + 3,
+	intelnops + 1 + 2 + 3 + 4,
+	intelnops + 1 + 2 + 3 + 4 + 5,
+	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
+	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+static unsigned char *k8_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	k8nops,
+	k8nops + 1,
+	k8nops + 1 + 2,
+	k8nops + 1 + 2 + 3,
+	k8nops + 1 + 2 + 3 + 4,
+	k8nops + 1 + 2 + 3 + 4 + 5,
+	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
+	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+static unsigned char *k7_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	k7nops,
+	k7nops + 1,
+	k7nops + 1 + 2,
+	k7nops + 1 + 2 + 3,
+	k7nops + 1 + 2 + 3 + 4,
+	k7nops + 1 + 2 + 3 + 4 + 5,
+	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
+	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+static struct nop {
+	int cpuid;
+	unsigned char **noptable;
+} noptypes[] = {
+	{ X86_FEATURE_K8, k8_nops },
+	{ X86_FEATURE_K7, k7_nops },
+	{ -1, NULL }
+};
+
+
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+extern struct alt_instr __smp_alt_instructions[], __smp_alt_instructions_end[];
+extern u8 *__smp_locks[], *__smp_locks_end[];
+
+extern u8 __smp_alt_begin[], __smp_alt_end[];
+
+
+static unsigned char** find_nop_table(void)
+{
+	unsigned char **noptable = intel_nops;
+	int i;
+
+	for (i = 0; noptypes[i].cpuid >= 0; i++) {
+		if (boot_cpu_has(noptypes[i].cpuid)) {
+			noptable = noptypes[i].noptable;
+			break;
+		}
+	}
+	return noptable;
+}
+
+/* Replace instructions with better alternatives for this CPU type.
+   This runs before SMP is initialized to avoid SMP problems with
+   self modifying code. This implies that assymetric systems where
+   APs have less capabilities than the boot processor are not handled.
+   Tough. Make sure you disable such features by hand. */
+
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
+{
+	unsigned char **noptable = find_nop_table();
+	struct alt_instr *a;
+	int diff, i, k;
+
+	DPRINTK("%s: alt table %p -> %p\n", __FUNCTION__, start, end);
+	for (a = start; a < end; a++) {
+		BUG_ON(a->replacementlen > a->instrlen);
+		if (!boot_cpu_has(a->cpuid))
+			continue;
+		memcpy(a->instr, a->replacement, a->replacementlen);
+		diff = a->instrlen - a->replacementlen;
+		/* Pad the rest with nops */
+		for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
+			k = diff;
+			if (k > ASM_NOP_MAX)
+				k = ASM_NOP_MAX;
+			memcpy(a->instr + i, noptable[k], k);
+		}
+	}
+}
+
+static void alternatives_smp_save(struct alt_instr *start, struct alt_instr *end)
+{
+	struct alt_instr *a;
+
+	DPRINTK("%s: alt table %p-%p\n", __FUNCTION__, start, end);
+	for (a = start; a < end; a++) {
+		memcpy(a->replacement + a->replacementlen,
+		       a->instr,
+		       a->instrlen);
+	}
+}
+
+static void alternatives_smp_apply(struct alt_instr *start, struct alt_instr *end)
+{
+	struct alt_instr *a;
+
+	for (a = start; a < end; a++) {
+		memcpy(a->instr,
+		       a->replacement + a->replacementlen,
+		       a->instrlen);
+	}
+}
+
+static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end)
+{
+	u8 **ptr;
+
+	for (ptr = start; ptr < end; ptr++) {
+		if (*ptr < text)
+			continue;
+		if (*ptr > text_end)
+			continue;
+		**ptr = 0xf0; /* lock prefix */
+	};
+}
+
+static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end)
+{
+	unsigned char **noptable = find_nop_table();
+	u8 **ptr;
+
+	for (ptr = start; ptr < end; ptr++) {
+		if (*ptr < text)
+			continue;
+		if (*ptr > text_end)
+			continue;
+		**ptr = noptable[1][0];
+	};
+}
+
+struct smp_alt_module {
+	/* what is this ??? */
+	struct module	*mod;
+	char		*name;
+
+	/* ptrs to lock prefixes */
+	u8		**locks;
+	u8		**locks_end;
+
+	/* .text segment, needed to avoid patching init code ;) */
+	u8		*text;
+	u8		*text_end;
+
+	struct list_head next;
+};
+static LIST_HEAD(smp_alt_modules);
+static DEFINE_SPINLOCK(smp_alt);
+
+static int smp_alt_once = 0;
+static int __init bootonly(char *str)
+{
+	smp_alt_once = 1;
+	return 1;
+}
+__setup("smp-alt-boot", bootonly);
+
+void alternatives_smp_module_add(struct module *mod, char *name,
+				 void *locks, void *locks_end,
+				 void *text,  void *text_end)
+{
+	struct smp_alt_module *smp;
+	unsigned long flags;
+
+	if (smp_alt_once) {
+		if (boot_cpu_has(X86_FEATURE_UP))
+			alternatives_smp_unlock(locks, locks_end,
+						text, text_end);
+		return;
+	}
+
+	smp = kzalloc(sizeof(*smp), GFP_KERNEL);
+	if (NULL == smp)
+		return; /* we'll run the (safe but slow) SMP code then ... */
+
+	smp->mod	= mod;
+	smp->name	= name;
+	smp->locks	= locks;
+	smp->locks_end	= locks_end;
+	smp->text	= text;
+	smp->text_end	= text_end;
+	DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n",
+		__FUNCTION__, smp->locks, smp->locks_end,
+		smp->text, smp->text_end, smp->name);
+
+	spin_lock_irqsave(&smp_alt, flags);
+	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_irqrestore(&smp_alt, flags);
+}
+
+void alternatives_smp_module_del(struct module *mod)
+{
+	struct smp_alt_module *item;
+	unsigned long flags;
+
+	if (smp_alt_once)
+		return;
+
+	spin_lock_irqsave(&smp_alt, flags);
+	list_for_each_entry(item, &smp_alt_modules, next) {
+		if (mod != item->mod)
+			continue;
+		list_del(&item->next);
+		spin_unlock_irqrestore(&smp_alt, flags);
+		DPRINTK("%s: %s\n", __FUNCTION__, item->name);
+		kfree(item);
+		return;
+	}
+	spin_unlock_irqrestore(&smp_alt, flags);
+}
+
+void alternatives_smp_switch(int smp)
+{
+	struct smp_alt_module *mod;
+	unsigned long flags;
+
+	if (smp_alt_once)
+		return;
+	BUG_ON(!smp && (num_online_cpus() > 1));
+
+	spin_lock_irqsave(&smp_alt, flags);
+	if (smp) {
+		printk(KERN_INFO "SMP alternatives: switching to SMP code\n");
+		clear_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+		clear_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
+		alternatives_smp_apply(__smp_alt_instructions,
+				       __smp_alt_instructions_end);
+		list_for_each_entry(mod, &smp_alt_modules, next)
+			alternatives_smp_lock(mod->locks, mod->locks_end,
+					      mod->text, mod->text_end);
+	} else {
+		printk(KERN_INFO "SMP alternatives: switching to UP code\n");
+		set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+		set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
+		apply_alternatives(__smp_alt_instructions,
+				   __smp_alt_instructions_end);
+		list_for_each_entry(mod, &smp_alt_modules, next)
+			alternatives_smp_unlock(mod->locks, mod->locks_end,
+						mod->text, mod->text_end);
+	}
+	spin_unlock_irqrestore(&smp_alt, flags);
+}
+
+void __init alternative_instructions(void)
+{
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
+
+	/* switch to patch-once-at-boottime-only mode and free the
+	 * tables in case we know the number of CPUs will never ever
+	 * change */
+#ifdef CONFIG_HOTPLUG_CPU
+	if (num_possible_cpus() < 2)
+		smp_alt_once = 1;
+#else
+	smp_alt_once = 1;
+#endif
+
+	if (smp_alt_once) {
+		if (1 == num_possible_cpus()) {
+			printk(KERN_INFO "SMP alternatives: switching to UP code\n");
+			set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability);
+			set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability);
+			apply_alternatives(__smp_alt_instructions,
+					   __smp_alt_instructions_end);
+			alternatives_smp_unlock(__smp_locks, __smp_locks_end,
+						_text, _etext);
+		}
+		free_init_pages("SMP alternatives",
+				(unsigned long)__smp_alt_begin,
+				(unsigned long)__smp_alt_end);
+	} else {
+		alternatives_smp_save(__smp_alt_instructions,
+				      __smp_alt_instructions_end);
+		alternatives_smp_module_add(NULL, "core kernel",
+					    __smp_locks, __smp_locks_end,
+					    _text, _etext);
+		alternatives_smp_switch(0);
+	}
+}
diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 776c90989e06..eb5279d23b7f 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -38,6 +38,7 @@
 #include <asm/i8253.h>
 
 #include <mach_apic.h>
+#include <mach_apicdef.h>
 #include <mach_ipi.h>
 
 #include "io_ports.h"
diff --git a/arch/i386/kernel/cpu/centaur.c b/arch/i386/kernel/cpu/centaur.c
index f52669ecb93f..bd75629dd262 100644
--- a/arch/i386/kernel/cpu/centaur.c
+++ b/arch/i386/kernel/cpu/centaur.c
@@ -4,6 +4,7 @@
 #include <asm/processor.h>
 #include <asm/msr.h>
 #include <asm/e820.h>
+#include <asm/mtrr.h>
 #include "cpu.h"
 
 #ifdef CONFIG_X86_OOSTORE
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index e6bd095ae108..7e3d6b6a4e96 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -25,9 +25,10 @@ EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
 DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]);
 EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack);
 
-static int cachesize_override __devinitdata = -1;
-static int disable_x86_fxsr __devinitdata = 0;
-static int disable_x86_serial_nr __devinitdata = 1;
+static int cachesize_override __cpuinitdata = -1;
+static int disable_x86_fxsr __cpuinitdata;
+static int disable_x86_serial_nr __cpuinitdata = 1;
+static int disable_x86_sep __cpuinitdata;
 
 struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {};
 
@@ -59,7 +60,7 @@ static int __init cachesize_setup(char *str)
 }
 __setup("cachesize=", cachesize_setup);
 
-int __devinit get_model_name(struct cpuinfo_x86 *c)
+int __cpuinit get_model_name(struct cpuinfo_x86 *c)
 {
 	unsigned int *v;
 	char *p, *q;
@@ -89,7 +90,7 @@ int __devinit get_model_name(struct cpuinfo_x86 *c)
 }
 
 
-void __devinit display_cacheinfo(struct cpuinfo_x86 *c)
+void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
 {
 	unsigned int n, dummy, ecx, edx, l2size;
 
@@ -130,7 +131,7 @@ void __devinit display_cacheinfo(struct cpuinfo_x86 *c)
 /* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */
 
 /* Look up CPU names by table lookup. */
-static char __devinit *table_lookup_model(struct cpuinfo_x86 *c)
+static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
 {
 	struct cpu_model_info *info;
 
@@ -151,7 +152,7 @@ static char __devinit *table_lookup_model(struct cpuinfo_x86 *c)
 }
 
 
-static void __devinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
+static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early)
 {
 	char *v = c->x86_vendor_id;
 	int i;
@@ -187,6 +188,14 @@ static int __init x86_fxsr_setup(char * s)
 __setup("nofxsr", x86_fxsr_setup);
 
 
+static int __init x86_sep_setup(char * s)
+{
+	disable_x86_sep = 1;
+	return 1;
+}
+__setup("nosep", x86_sep_setup);
+
+
 /* Standard macro to see if a specific flag is changeable */
 static inline int flag_is_changeable_p(u32 flag)
 {
@@ -210,7 +219,7 @@ static inline int flag_is_changeable_p(u32 flag)
 
 
 /* Probe for the CPUID instruction */
-static int __devinit have_cpuid_p(void)
+static int __cpuinit have_cpuid_p(void)
 {
 	return flag_is_changeable_p(X86_EFLAGS_ID);
 }
@@ -254,7 +263,7 @@ static void __init early_cpu_detect(void)
 	}
 }
 
-void __devinit generic_identify(struct cpuinfo_x86 * c)
+void __cpuinit generic_identify(struct cpuinfo_x86 * c)
 {
 	u32 tfms, xlvl;
 	int junk;
@@ -307,7 +316,7 @@ void __devinit generic_identify(struct cpuinfo_x86 * c)
 #endif
 }
 
-static void __devinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
+static void __cpuinit squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) {
 		/* Disable processor serial number */
@@ -335,7 +344,7 @@ __setup("serialnumber", x86_serial_nr_setup);
 /*
  * This does the hard work of actually picking apart the CPU stuff...
  */
-void __devinit identify_cpu(struct cpuinfo_x86 *c)
+void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 {
 	int i;
 
@@ -405,6 +414,10 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 		clear_bit(X86_FEATURE_XMM, c->x86_capability);
 	}
 
+	/* SEP disabled? */
+	if (disable_x86_sep)
+		clear_bit(X86_FEATURE_SEP, c->x86_capability);
+
 	if (disable_pse)
 		clear_bit(X86_FEATURE_PSE, c->x86_capability);
 
@@ -417,7 +430,7 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 		else
 			/* Last resort... */
 			sprintf(c->x86_model_id, "%02x/%02x",
-				c->x86_vendor, c->x86_model);
+				c->x86, c->x86_model);
 	}
 
 	/* Now the feature flags better reflect actual CPU features! */
@@ -453,7 +466,7 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 }
 
 #ifdef CONFIG_X86_HT
-void __devinit detect_ht(struct cpuinfo_x86 *c)
+void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 {
 	u32 	eax, ebx, ecx, edx;
 	int 	index_msb, core_bits;
@@ -500,7 +513,7 @@ void __devinit detect_ht(struct cpuinfo_x86 *c)
 }
 #endif
 
-void __devinit print_cpu_info(struct cpuinfo_x86 *c)
+void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
 {
 	char *vendor = NULL;
 
@@ -523,7 +536,7 @@ void __devinit print_cpu_info(struct cpuinfo_x86 *c)
 		printk("\n");
 }
 
-cpumask_t cpu_initialized __devinitdata = CPU_MASK_NONE;
+cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
 
 /* This is hacky. :)
  * We're emulating future behavior.
@@ -570,7 +583,7 @@ void __init early_cpu_init(void)
  * and IDT. We reload them nevertheless, this function acts as a
  * 'CPU state barrier', nothing should get across.
  */
-void __devinit cpu_init(void)
+void __cpuinit cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	struct tss_struct * t = &per_cpu(init_tss, cpu);
@@ -670,7 +683,7 @@ void __devinit cpu_init(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-void __devinit cpu_uninit(void)
+void __cpuinit cpu_uninit(void)
 {
 	int cpu = raw_smp_processor_id();
 	cpu_clear(cpu, cpu_initialized);
diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
index e11a09207ec8..3d5110b65cc3 100644
--- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c
@@ -1145,9 +1145,7 @@ static int __cpuinit powernowk8_init(void)
 {
 	unsigned int i, supported_cpus = 0;
 
-	for (i=0; i<NR_CPUS; i++) {
-		if (!cpu_online(i))
-			continue;
+	for_each_cpu(i) {
 		if (check_supported_cpu(i))
 			supported_cpus++;
 	}
diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c
index 8c0120186b9f..5386b29bb5a5 100644
--- a/arch/i386/kernel/cpu/intel.c
+++ b/arch/i386/kernel/cpu/intel.c
@@ -29,7 +29,7 @@ extern int trap_init_f00f_bug(void);
 struct movsl_mask movsl_mask __read_mostly;
 #endif
 
-void __devinit early_intel_workaround(struct cpuinfo_x86 *c)
+void __cpuinit early_intel_workaround(struct cpuinfo_x86 *c)
 {
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return;
@@ -44,7 +44,7 @@ void __devinit early_intel_workaround(struct cpuinfo_x86 *c)
  *	This is called before we do cpu ident work
  */
  
-int __devinit ppro_with_ram_bug(void)
+int __cpuinit ppro_with_ram_bug(void)
 {
 	/* Uses data from early_cpu_detect now */
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
@@ -62,7 +62,7 @@ int __devinit ppro_with_ram_bug(void)
  * P4 Xeon errata 037 workaround.
  * Hardware prefetcher may cause stale data to be loaded into the cache.
  */
-static void __devinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
+static void __cpuinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
 {
 	unsigned long lo, hi;
 
@@ -81,7 +81,7 @@ static void __devinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
 /*
  * find out the number of processor cores on the die
  */
-static int __devinit num_cpu_cores(struct cpuinfo_x86 *c)
+static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c)
 {
 	unsigned int eax, ebx, ecx, edx;
 
@@ -96,7 +96,7 @@ static int __devinit num_cpu_cores(struct cpuinfo_x86 *c)
 		return 1;
 }
 
-static void __devinit init_intel(struct cpuinfo_x86 *c)
+static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 {
 	unsigned int l2 = 0;
 	char *p = NULL;
@@ -205,7 +205,7 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 * c, unsigned int size)
 	return size;
 }
 
-static struct cpu_dev intel_cpu_dev __devinitdata = {
+static struct cpu_dev intel_cpu_dev __cpuinitdata = {
 	.c_vendor	= "Intel",
 	.c_ident 	= { "GenuineIntel" },
 	.c_models = {
diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c
index ffe58cee0c48..ce61921369e5 100644
--- a/arch/i386/kernel/cpu/intel_cacheinfo.c
+++ b/arch/i386/kernel/cpu/intel_cacheinfo.c
@@ -174,7 +174,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
 	unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
 
-	if (c->cpuid_level > 4) {
+	if (c->cpuid_level > 3) {
 		static int is_initialized;
 
 		if (is_initialized == 0) {
@@ -330,7 +330,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 		}
 	}
 }
-static void __devinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
+static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
 {
 	struct _cpuid4_info	*this_leaf, *sibling_leaf;
 	int sibling;
diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c
index 89a85af33d28..5cfbd8011698 100644
--- a/arch/i386/kernel/cpu/proc.c
+++ b/arch/i386/kernel/cpu/proc.c
@@ -40,7 +40,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		/* Other (Linux-defined) */
 		"cxmmx", "k6_mtrr", "cyrix_arr", "centaur_mcr",
 		NULL, NULL, NULL, NULL,
-		"constant_tsc", NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+		"constant_tsc", "up", NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c
index d49dbe8dc96b..e3c5fca0aa8a 100644
--- a/arch/i386/kernel/crash.c
+++ b/arch/i386/kernel/crash.c
@@ -105,7 +105,7 @@ static int crash_nmi_callback(struct pt_regs *regs, int cpu)
 		return 1;
 	local_irq_disable();
 
-	if (!user_mode(regs)) {
+	if (!user_mode_vm(regs)) {
 		crash_fixup_ss_esp(&fixed_regs, regs);
 		regs = &fixed_regs;
 	}
diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 4d704724b2f5..cfc683f153b9 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -226,6 +226,10 @@ ENTRY(system_call)
 	pushl %eax			# save orig_eax
 	SAVE_ALL
 	GET_THREAD_INFO(%ebp)
+	testl $TF_MASK,EFLAGS(%esp)
+	jz no_singlestep
+	orl $_TIF_SINGLESTEP,TI_flags(%ebp)
+no_singlestep:
 					# system call tracing in operation / emulation
 	/* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */
 	testw $(_TIF_SYSCALL_EMU|_TIF_SYSCALL_TRACE|_TIF_SECCOMP|_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index e0b7c632efbc..3debc2e26542 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -450,7 +450,6 @@ int_msg:
 
 .globl boot_gdt_descr
 .globl idt_descr
-.globl cpu_gdt_descr
 
 	ALIGN
 # early boot GDT descriptor (must use 1:1 address mapping)
@@ -470,8 +469,6 @@ cpu_gdt_descr:
 	.word GDT_ENTRIES*8-1
 	.long cpu_gdt_table
 
-	.fill NR_CPUS-1,8,0		# space for the other GDT descriptors
-
 /*
  * The boot_gdt_table must mirror the equivalent in setup.S and is
  * used only for booting.
@@ -485,7 +482,7 @@ ENTRY(boot_gdt_table)
 /*
  * The Global Descriptor Table contains 28 quadwords, per-CPU.
  */
-	.align PAGE_SIZE_asm
+	.align L1_CACHE_BYTES
 ENTRY(cpu_gdt_table)
 	.quad 0x0000000000000000	/* NULL descriptor */
 	.quad 0x0000000000000000	/* 0x0b reserved */
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 39d9a5fa907e..311b4e7266f1 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -351,8 +351,8 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 {
 	int i, j;
 	Dprintk("Rotating IRQs among CPUs.\n");
-	for (i = 0; i < NR_CPUS; i++) {
-		for (j = 0; cpu_online(i) && (j < NR_IRQS); j++) {
+	for_each_online_cpu(i) {
+		for (j = 0; j < NR_IRQS; j++) {
 			if (!irq_desc[j].action)
 				continue;
 			/* Is it a significant load ?  */
@@ -381,7 +381,7 @@ static void do_irq_balance(void)
 	unsigned long imbalance = 0;
 	cpumask_t allowed_mask, target_cpu_mask, tmp;
 
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		int package_index;
 		CPU_IRQ(i) = 0;
 		if (!cpu_online(i))
@@ -422,9 +422,7 @@ static void do_irq_balance(void)
 		}
 	}
 	/* Find the least loaded processor package */
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_online(i))
-			continue;
+	for_each_online_cpu(i) {
 		if (i != CPU_TO_PACKAGEINDEX(i))
 			continue;
 		if (min_cpu_irq > CPU_IRQ(i)) {
@@ -441,9 +439,7 @@ tryanothercpu:
 	 */
 	tmp_cpu_irq = 0;
 	tmp_loaded = -1;
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_online(i))
-			continue;
+	for_each_online_cpu(i) {
 		if (i != CPU_TO_PACKAGEINDEX(i))
 			continue;
 		if (max_cpu_irq <= CPU_IRQ(i)) 
@@ -619,9 +615,7 @@ static int __init balanced_irq_init(void)
 	if (smp_num_siblings > 1 && !cpus_empty(tmp))
 		physical_balance = 1;
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_online(i))
-			continue;
+	for_each_online_cpu(i) {
 		irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
 		irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
 		if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
@@ -638,9 +632,11 @@ static int __init balanced_irq_init(void)
 	else 
 		printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq");
 failed:
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_cpu(i) {
 		kfree(irq_cpu_data[i].irq_delta);
+		irq_cpu_data[i].irq_delta = NULL;
 		kfree(irq_cpu_data[i].last_irq);
+		irq_cpu_data[i].last_irq = NULL;
 	}
 	return 0;
 }
@@ -1761,7 +1757,8 @@ static void __init setup_ioapic_ids_from_mpc(void)
 	 * Don't check I/O APIC IDs for xAPIC systems.  They have
 	 * no meaning without the serial APIC bus.
 	 */
-	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 < 15))
+	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		|| APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
 		return;
 	/*
 	 * This is broken; anything with a real cpu count has to
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 694a13997637..7a59050242a7 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -84,9 +84,9 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
-	down(&kprobe_mutex);
+	mutex_lock(&kprobe_mutex);
 	free_insn_slot(p->ainsn.insn);
-	up(&kprobe_mutex);
+	mutex_unlock(&kprobe_mutex);
 }
 
 static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
diff --git a/arch/i386/kernel/module.c b/arch/i386/kernel/module.c
index 5149c8a621f0..470cf97e7cd3 100644
--- a/arch/i386/kernel/module.c
+++ b/arch/i386/kernel/module.c
@@ -104,26 +104,38 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 	return -ENOEXEC;
 }
 
-extern void apply_alternatives(void *start, void *end); 
-
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	const Elf_Shdr *s;
+	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
-	/* look for .altinstructions to patch */ 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { 
-		void *seg; 		
-		if (strcmp(".altinstructions", secstrings + s->sh_name))
-			continue;
-		seg = (void *)s->sh_addr; 
-		apply_alternatives(seg, seg + s->sh_size); 
-	} 	
+		if (!strcmp(".text", secstrings + s->sh_name))
+			text = s;
+		if (!strcmp(".altinstructions", secstrings + s->sh_name))
+			alt = s;
+		if (!strcmp(".smp_locks", secstrings + s->sh_name))
+			locks= s;
+	}
+
+	if (alt) {
+		/* patch .altinstructions */
+		void *aseg = (void *)alt->sh_addr;
+		apply_alternatives(aseg, aseg + alt->sh_size);
+	}
+	if (locks && text) {
+		void *lseg = (void *)locks->sh_addr;
+		void *tseg = (void *)text->sh_addr;
+		alternatives_smp_module_add(me, me->name,
+					    lseg, lseg + locks->sh_size,
+					    tseg, tseg + text->sh_size);
+	}
 	return 0;
 }
 
 void module_arch_cleanup(struct module *mod)
 {
+	alternatives_smp_module_del(mod);
 }
diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index e6e2f43db85e..8d8aa9d1796d 100644
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -828,6 +828,8 @@ void __init find_smp_config (void)
 		smp_scan_config(address, 0x400);
 }
 
+int es7000_plat;
+
 /* --------------------------------------------------------------------------
                             ACPI-based MP Configuration
    -------------------------------------------------------------------------- */
@@ -935,7 +937,8 @@ void __init mp_register_ioapic (
 	mp_ioapics[idx].mpc_apicaddr = address;
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 < 15))
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		&& !APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
 		tmpid = io_apic_get_unique_id(idx, id);
 	else
 		tmpid = id;
@@ -1011,8 +1014,6 @@ void __init mp_override_legacy_irq (
 	return;
 }
 
-int es7000_plat;
-
 void __init mp_config_acpi_legacy_irqs (void)
 {
 	struct mpc_config_intsrc intsrc;
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index be87c5e2ee95..9074818b9473 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -143,7 +143,7 @@ static int __init check_nmi_watchdog(void)
 	local_irq_enable();
 	mdelay((10*1000)/nmi_hz); // wait 10 ticks
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++) {
+	for_each_cpu(cpu) {
 #ifdef CONFIG_SMP
 		/* Check cpu_callin_map here because that is set
 		   after the timer is started. */
@@ -510,7 +510,7 @@ void touch_nmi_watchdog (void)
 	 * Just reset the alert counters, (other CPUs might be
 	 * spinning on locks we hold):
 	 */
-	for (i = 0; i < NR_CPUS; i++)
+	for_each_cpu(i)
 		alert_counter[i] = 0;
 
 	/*
@@ -543,7 +543,7 @@ void nmi_watchdog_tick (struct pt_regs * regs)
 			/*
 			 * die_nmi will return ONLY if NOTIFY_STOP happens..
 			 */
-			die_nmi(regs, "NMI Watchdog detected LOCKUP");
+			die_nmi(regs, "BUG: NMI Watchdog detected LOCKUP");
 	} else {
 		last_irq_sums[cpu] = sum;
 		alert_counter[cpu] = 0;
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 0480454ebffa..299e61674084 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -295,7 +295,7 @@ void show_regs(struct pt_regs * regs)
 	printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id());
 	print_symbol("EIP is at %s\n", regs->eip);
 
-	if (user_mode(regs))
+	if (user_mode_vm(regs))
 		printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp);
 	printk(" EFLAGS: %08lx    %s  (%s %.*s)\n",
 	       regs->eflags, print_tainted(), system_utsname.release,
diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index 5c1fb6aada5b..506462ef36a0 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -34,10 +34,10 @@
 
 /*
  * Determines which flags the user has access to [1 = access, 0 = no access].
- * Prohibits changing ID(21), VIP(20), VIF(19), VM(17), IOPL(12-13), IF(9).
+ * Prohibits changing ID(21), VIP(20), VIF(19), VM(17), NT(14), IOPL(12-13), IF(9).
  * Also masks reserved bits (31-22, 15, 5, 3, 1).
  */
-#define FLAG_MASK 0x00054dd5
+#define FLAG_MASK 0x00050dd5
 
 /* set's the trap flag. */
 #define TRAP_FLAG 0x100
diff --git a/arch/i386/kernel/semaphore.c b/arch/i386/kernel/semaphore.c
index 7455ab643943..967dc74df9ee 100644
--- a/arch/i386/kernel/semaphore.c
+++ b/arch/i386/kernel/semaphore.c
@@ -110,11 +110,11 @@ asm(
 ".align	4\n"
 ".globl	__write_lock_failed\n"
 "__write_lock_failed:\n\t"
-	LOCK "addl	$" RW_LOCK_BIAS_STR ",(%eax)\n"
+	LOCK_PREFIX "addl	$" RW_LOCK_BIAS_STR ",(%eax)\n"
 "1:	rep; nop\n\t"
 	"cmpl	$" RW_LOCK_BIAS_STR ",(%eax)\n\t"
 	"jne	1b\n\t"
-	LOCK "subl	$" RW_LOCK_BIAS_STR ",(%eax)\n\t"
+	LOCK_PREFIX "subl	$" RW_LOCK_BIAS_STR ",(%eax)\n\t"
 	"jnz	__write_lock_failed\n\t"
 	"ret"
 );
@@ -124,11 +124,11 @@ asm(
 ".align	4\n"
 ".globl	__read_lock_failed\n"
 "__read_lock_failed:\n\t"
-	LOCK "incl	(%eax)\n"
+	LOCK_PREFIX "incl	(%eax)\n"
 "1:	rep; nop\n\t"
 	"cmpl	$1,(%eax)\n\t"
 	"js	1b\n\t"
-	LOCK "decl	(%eax)\n\t"
+	LOCK_PREFIX "decl	(%eax)\n\t"
 	"js	__read_lock_failed\n\t"
 	"ret"
 );
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index ab62a9f4701e..2d8782960f41 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -1377,101 +1377,6 @@ static void __init register_memory(void)
 		pci_mem_start, gapstart, gapsize);
 }
 
-/* Use inline assembly to define this because the nops are defined 
-   as inline assembly strings in the include files and we cannot 
-   get them easily into strings. */
-asm("\t.data\nintelnops: " 
-    GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
-    GENERIC_NOP7 GENERIC_NOP8); 
-asm("\t.data\nk8nops: " 
-    K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
-    K8_NOP7 K8_NOP8); 
-asm("\t.data\nk7nops: " 
-    K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
-    K7_NOP7 K7_NOP8); 
-    
-extern unsigned char intelnops[], k8nops[], k7nops[];
-static unsigned char *intel_nops[ASM_NOP_MAX+1] = { 
-     NULL,
-     intelnops,
-     intelnops + 1,
-     intelnops + 1 + 2,
-     intelnops + 1 + 2 + 3,
-     intelnops + 1 + 2 + 3 + 4,
-     intelnops + 1 + 2 + 3 + 4 + 5,
-     intelnops + 1 + 2 + 3 + 4 + 5 + 6,
-     intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-}; 
-static unsigned char *k8_nops[ASM_NOP_MAX+1] = { 
-     NULL,
-     k8nops,
-     k8nops + 1,
-     k8nops + 1 + 2,
-     k8nops + 1 + 2 + 3,
-     k8nops + 1 + 2 + 3 + 4,
-     k8nops + 1 + 2 + 3 + 4 + 5,
-     k8nops + 1 + 2 + 3 + 4 + 5 + 6,
-     k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-}; 
-static unsigned char *k7_nops[ASM_NOP_MAX+1] = { 
-     NULL,
-     k7nops,
-     k7nops + 1,
-     k7nops + 1 + 2,
-     k7nops + 1 + 2 + 3,
-     k7nops + 1 + 2 + 3 + 4,
-     k7nops + 1 + 2 + 3 + 4 + 5,
-     k7nops + 1 + 2 + 3 + 4 + 5 + 6,
-     k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
-}; 
-static struct nop { 
-     int cpuid; 
-     unsigned char **noptable; 
-} noptypes[] = { 
-     { X86_FEATURE_K8, k8_nops }, 
-     { X86_FEATURE_K7, k7_nops }, 
-     { -1, NULL }
-}; 
-
-/* Replace instructions with better alternatives for this CPU type.
-
-   This runs before SMP is initialized to avoid SMP problems with
-   self modifying code. This implies that assymetric systems where
-   APs have less capabilities than the boot processor are not handled. 
-   Tough. Make sure you disable such features by hand. */ 
-void apply_alternatives(void *start, void *end) 
-{ 
-	struct alt_instr *a; 
-	int diff, i, k;
-        unsigned char **noptable = intel_nops; 
-	for (i = 0; noptypes[i].cpuid >= 0; i++) { 
-		if (boot_cpu_has(noptypes[i].cpuid)) { 
-			noptable = noptypes[i].noptable;
-			break;
-		}
-	} 
-	for (a = start; (void *)a < end; a++) { 
-		if (!boot_cpu_has(a->cpuid))
-			continue;
-		BUG_ON(a->replacementlen > a->instrlen); 
-		memcpy(a->instr, a->replacement, a->replacementlen); 
-		diff = a->instrlen - a->replacementlen; 
-		/* Pad the rest with nops */
-		for (i = a->replacementlen; diff > 0; diff -= k, i += k) {
-			k = diff;
-			if (k > ASM_NOP_MAX)
-				k = ASM_NOP_MAX;
-			memcpy(a->instr + i, noptable[k], k); 
-		} 
-	}
-} 
-
-void __init alternative_instructions(void)
-{
-	extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-	apply_alternatives(__alt_instructions, __alt_instructions_end);
-}
-
 static char * __init machine_specific_memory_setup(void);
 
 #ifdef CONFIG_MCA
@@ -1554,6 +1459,16 @@ void __init setup_arch(char **cmdline_p)
 
 	parse_cmdline_early(cmdline_p);
 
+#ifdef CONFIG_EARLY_PRINTK
+	{
+		char *s = strstr(*cmdline_p, "earlyprintk=");
+		if (s) {
+			setup_early_printk(strchr(s, '=') + 1);
+			printk("early console enabled\n");
+		}
+	}
+#endif
+
 	max_low_pfn = setup_memory();
 
 	/*
@@ -1578,19 +1493,6 @@ void __init setup_arch(char **cmdline_p)
 	 * NOTE: at this point the bootmem allocator is fully available.
 	 */
 
-#ifdef CONFIG_EARLY_PRINTK
-	{
-		char *s = strstr(*cmdline_p, "earlyprintk=");
-		if (s) {
-			extern void setup_early_printk(char *);
-
-			setup_early_printk(strchr(s, '=') + 1);
-			printk("early console enabled\n");
-		}
-	}
-#endif
-
-
 	dmi_scan_machine();
 
 #ifdef CONFIG_X86_GENERICARCH
diff --git a/arch/i386/kernel/signal.c b/arch/i386/kernel/signal.c
index 963616d364ec..5c352c3a9e7f 100644
--- a/arch/i386/kernel/signal.c
+++ b/arch/i386/kernel/signal.c
@@ -123,7 +123,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax
 	  err |= __get_user(tmp, &sc->seg);				\
 	  loadsegment(seg,tmp); }
 
-#define	FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | X86_EFLAGS_DF | \
+#define	FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_RF |		 \
+			 X86_EFLAGS_OF | X86_EFLAGS_DF |		 \
 			 X86_EFLAGS_TF | X86_EFLAGS_SF | X86_EFLAGS_ZF | \
 			 X86_EFLAGS_AF | X86_EFLAGS_PF | X86_EFLAGS_CF)
 
@@ -582,9 +583,6 @@ static void fastcall do_signal(struct pt_regs *regs)
 	if (!user_mode(regs))
 		return;
 
-	if (try_to_freeze())
-		goto no_signal;
-
 	if (test_thread_flag(TIF_RESTORE_SIGMASK))
 		oldset = &current->saved_sigmask;
 	else
@@ -613,7 +611,6 @@ static void fastcall do_signal(struct pt_regs *regs)
 		return;
 	}
 
-no_signal:
 	/* Did we come from a system call? */
 	if (regs->orig_eax >= 0) {
 		/* Restart the system call - no handlers present */
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 7007e1783797..4c470e99a742 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -899,6 +899,7 @@ static int __devinit do_boot_cpu(int apicid, int cpu)
 	unsigned short nmi_high = 0, nmi_low = 0;
 
 	++cpucount;
+	alternatives_smp_switch(1);
 
 	/*
 	 * We can't use kernel_thread since we must avoid to
@@ -1368,6 +1369,8 @@ void __cpu_die(unsigned int cpu)
 		/* They ack this in play_dead by setting CPU_DEAD */
 		if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
 			printk ("CPU %d is now offline\n", cpu);
+			if (1 == num_online_cpus())
+				alternatives_smp_switch(0);
 			return;
 		}
 		msleep(100);
diff --git a/arch/i386/kernel/topology.c b/arch/i386/kernel/topology.c
index 67a0e1baa28b..296355292c7c 100644
--- a/arch/i386/kernel/topology.c
+++ b/arch/i386/kernel/topology.c
@@ -41,6 +41,15 @@ int arch_register_cpu(int num){
 		parent = &node_devices[node].node;
 #endif /* CONFIG_NUMA */
 
+	/*
+	 * CPU0 cannot be offlined due to several
+	 * restrictions and assumptions in kernel. This basically
+	 * doesnt add a control file, one cannot attempt to offline
+	 * BSP.
+	 */
+	if (!num)
+		cpu_devices[num].cpu.no_control = 1;
+
 	return register_cpu(&cpu_devices[num].cpu, num, parent);
 }
 
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index b814dbdcc91e..de5386b01d38 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -99,6 +99,8 @@ int register_die_notifier(struct notifier_block *nb)
 {
 	int err = 0;
 	unsigned long flags;
+
+	vmalloc_sync_all();
 	spin_lock_irqsave(&die_notifier_lock, flags);
 	err = notifier_chain_register(&i386die_chain, nb);
 	spin_unlock_irqrestore(&die_notifier_lock, flags);
@@ -112,12 +114,30 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p)
 		p < (void *)tinfo + THREAD_SIZE - 3;
 }
 
-static void print_addr_and_symbol(unsigned long addr, char *log_lvl)
+/*
+ * Print CONFIG_STACK_BACKTRACE_COLS address/symbol entries per line.
+ */
+static inline int print_addr_and_symbol(unsigned long addr, char *log_lvl,
+					int printed)
 {
-	printk(log_lvl);
+	if (!printed)
+		printk(log_lvl);
+
+#if CONFIG_STACK_BACKTRACE_COLS == 1
 	printk(" [<%08lx>] ", addr);
+#else
+	printk(" <%08lx> ", addr);
+#endif
 	print_symbol("%s", addr);
-	printk("\n");
+
+	printed = (printed + 1) % CONFIG_STACK_BACKTRACE_COLS;
+
+	if (printed)
+		printk("  ");
+	else
+		printk("\n");
+
+	return printed;
 }
 
 static inline unsigned long print_context_stack(struct thread_info *tinfo,
@@ -125,20 +145,24 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
 				char *log_lvl)
 {
 	unsigned long addr;
+	int printed = 0; /* nr of entries already printed on current line */
 
 #ifdef	CONFIG_FRAME_POINTER
 	while (valid_stack_ptr(tinfo, (void *)ebp)) {
 		addr = *(unsigned long *)(ebp + 4);
-		print_addr_and_symbol(addr, log_lvl);
+		printed = print_addr_and_symbol(addr, log_lvl, printed);
 		ebp = *(unsigned long *)ebp;
 	}
 #else
 	while (valid_stack_ptr(tinfo, stack)) {
 		addr = *stack++;
 		if (__kernel_text_address(addr))
-			print_addr_and_symbol(addr, log_lvl);
+			printed = print_addr_and_symbol(addr, log_lvl, printed);
 	}
 #endif
+	if (printed)
+		printk("\n");
+
 	return ebp;
 }
 
@@ -166,8 +190,7 @@ static void show_trace_log_lvl(struct task_struct *task,
 		stack = (unsigned long*)context->previous_esp;
 		if (!stack)
 			break;
-		printk(log_lvl);
-		printk(" =======================\n");
+		printk("%s =======================\n", log_lvl);
 	}
 }
 
@@ -194,21 +217,17 @@ static void show_stack_log_lvl(struct task_struct *task, unsigned long *esp,
 	for(i = 0; i < kstack_depth_to_print; i++) {
 		if (kstack_end(stack))
 			break;
-		if (i && ((i % 8) == 0)) {
-			printk("\n");
-			printk(log_lvl);
-			printk("       ");
-		}
+		if (i && ((i % 8) == 0))
+			printk("\n%s       ", log_lvl);
 		printk("%08lx ", *stack++);
 	}
-	printk("\n");
-	printk(log_lvl);
-	printk("Call Trace:\n");
+	printk("\n%sCall Trace:\n", log_lvl);
 	show_trace_log_lvl(task, esp, log_lvl);
 }
 
 void show_stack(struct task_struct *task, unsigned long *esp)
 {
+	printk("       ");
 	show_stack_log_lvl(task, esp, "");
 }
 
@@ -233,7 +252,7 @@ void show_registers(struct pt_regs *regs)
 
 	esp = (unsigned long) (&regs->esp);
 	savesegment(ss, ss);
-	if (user_mode(regs)) {
+	if (user_mode_vm(regs)) {
 		in_kernel = 0;
 		esp = regs->esp;
 		ss = regs->xss & 0xffff;
@@ -333,6 +352,8 @@ void die(const char * str, struct pt_regs * regs, long err)
 	static int die_counter;
 	unsigned long flags;
 
+	oops_enter();
+
 	if (die.lock_owner != raw_smp_processor_id()) {
 		console_verbose();
 		spin_lock_irqsave(&die.lock, flags);
@@ -385,6 +406,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 		ssleep(5);
 		panic("Fatal exception");
 	}
+	oops_exit();
 	do_exit(SIGSEGV);
 }
 
@@ -623,7 +645,7 @@ void die_nmi (struct pt_regs *regs, const char *msg)
 	/* If we are in kernel we are probably nested up pretty bad
 	 * and might aswell get out now while we still can.
 	*/
-	if (!user_mode(regs)) {
+	if (!user_mode_vm(regs)) {
 		current->thread.trap_no = 2;
 		crash_kexec(regs);
 	}
@@ -694,6 +716,7 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code)
 
 void set_nmi_callback(nmi_callback_t callback)
 {
+	vmalloc_sync_all();
 	rcu_assign_pointer(nmi_callback, callback);
 }
 EXPORT_SYMBOL_GPL(set_nmi_callback);
diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S
index 4710195b6b74..3f21c6f6466d 100644
--- a/arch/i386/kernel/vmlinux.lds.S
+++ b/arch/i386/kernel/vmlinux.lds.S
@@ -68,6 +68,26 @@ SECTIONS
 	*(.data.init_task)
   }
 
+  /* might get freed after init */
+  . = ALIGN(4096);
+  __smp_alt_begin = .;
+  __smp_alt_instructions = .;
+  .smp_altinstructions : AT(ADDR(.smp_altinstructions) - LOAD_OFFSET) {
+	*(.smp_altinstructions)
+  }
+  __smp_alt_instructions_end = .;
+  . = ALIGN(4);
+  __smp_locks = .;
+  .smp_locks : AT(ADDR(.smp_locks) - LOAD_OFFSET) {
+	*(.smp_locks)
+  }
+  __smp_locks_end = .;
+  .smp_altinstr_replacement : AT(ADDR(.smp_altinstr_replacement) - LOAD_OFFSET) {
+	*(.smp_altinstr_replacement)
+  }
+  . = ALIGN(4096);
+  __smp_alt_end = .;
+
   /* will be freed after init */
   . = ALIGN(4096);		/* Init code and data */
   __init_begin = .;
diff --git a/arch/i386/kernel/vsyscall-sysenter.S b/arch/i386/kernel/vsyscall-sysenter.S
index 76b728159403..3b62baa6a371 100644
--- a/arch/i386/kernel/vsyscall-sysenter.S
+++ b/arch/i386/kernel/vsyscall-sysenter.S
@@ -21,6 +21,9 @@
  * instruction clobbers %esp, the user's %esp won't even survive entry
  * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
  * arg6 from the stack.
+ *
+ * You can not use this vsyscall for the clone() syscall because the
+ * three dwords on the parent stack do not get copied to the child.
  */
 	.text
 	.globl __kernel_vsyscall