19 files changed, 202 insertions, 232 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 45d79ea890ae..5fed98ca0e1f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -65,7 +65,8 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
    get them easily into strings. */
 asm("\t.section .rodata, \"a\"\nintelnops: "
 	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
-	GENERIC_NOP7 GENERIC_NOP8);
+	GENERIC_NOP7 GENERIC_NOP8
+    "\t.previous");
 extern const unsigned char intelnops[];
 static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
 	NULL,
@@ -83,7 +84,8 @@ static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
 #ifdef K8_NOP1
 asm("\t.section .rodata, \"a\"\nk8nops: "
 	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
-	K8_NOP7 K8_NOP8);
+	K8_NOP7 K8_NOP8
+    "\t.previous");
 extern const unsigned char k8nops[];
 static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
 	NULL,
@@ -101,7 +103,8 @@ static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
 #ifdef K7_NOP1
 asm("\t.section .rodata, \"a\"\nk7nops: "
 	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
-	K7_NOP7 K7_NOP8);
+	K7_NOP7 K7_NOP8
+    "\t.previous");
 extern const unsigned char k7nops[];
 static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 	NULL,
@@ -119,7 +122,8 @@ static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 #ifdef P6_NOP1
 asm("\t.section .rodata, \"a\"\np6nops: "
 	P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
-	P6_NOP7 P6_NOP8);
+	P6_NOP7 P6_NOP8
+    "\t.previous");
 extern const unsigned char p6nops[];
 static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
 	NULL,
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 027e5c003b16..170d2f5523b2 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -143,14 +143,6 @@ static void __init check_config(void)
 #endif
 
 /*
- * If we configured ourselves for a TSC, we'd better have one!
- */
-#ifdef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
-		panic("Kernel compiled for Pentium+, requires TSC feature!");
-#endif
-
-/*
  * If we were told we had a good local APIC, check for buggy Pentia,
  * i.e. all B steppings and the C2 stepping of P54C when using their
  * integrated APIC (see 11AP erratum in "Pentium Processor
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
index f2b5a621d27b..8a85c93bd62a 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c
@@ -63,7 +63,7 @@ static struct cpufreq_frequency_table speedstep_freqs[] = {
  */
 static int speedstep_smi_ownership (void)
 {
-	u32 command, result, magic;
+	u32 command, result, magic, dummy;
 	u32 function = GET_SPEEDSTEP_OWNER;
 	unsigned char magic_data[] = "Copyright (c) 1999 Intel Corporation";
 
@@ -73,8 +73,11 @@ static int speedstep_smi_ownership (void)
 	dprintk("trying to obtain ownership with command %x at port %x\n", command, smi_port);
 
 	__asm__ __volatile__(
+		"push %%ebp\n"
 		"out %%al, (%%dx)\n"
-		: "=D" (result)
+		"pop %%ebp\n"
+		: "=D" (result), "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy),
+			"=S" (dummy)
 		: "a" (command), "b" (function), "c" (0), "d" (smi_port),
 			"D" (0), "S" (magic)
 		: "memory"
@@ -96,7 +99,7 @@ static int speedstep_smi_ownership (void)
  */
 static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high)
 {
-	u32 command, result = 0, edi, high_mhz, low_mhz;
+	u32 command, result = 0, edi, high_mhz, low_mhz, dummy;
 	u32 state=0;
 	u32 function = GET_SPEEDSTEP_FREQS;
 
@@ -109,10 +112,12 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high)
 
 	dprintk("trying to determine frequencies with command %x at port %x\n", command, smi_port);
 
-	__asm__ __volatile__("movl $0, %%edi\n"
+	__asm__ __volatile__(
+		"push %%ebp\n"
 		"out %%al, (%%dx)\n"
-		: "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi)
-		: "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0)
+		"pop %%ebp"
+		: "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi), "=S" (dummy)
+		: "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0)
 	);
 
 	dprintk("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz);
@@ -135,16 +140,18 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high)
 static int speedstep_get_state (void)
 {
 	u32 function=GET_SPEEDSTEP_STATE;
-	u32 result, state, edi, command;
+	u32 result, state, edi, command, dummy;
 
 	command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff);
 
 	dprintk("trying to determine current setting with command %x at port %x\n", command, smi_port);
 
-	__asm__ __volatile__("movl $0, %%edi\n"
+	__asm__ __volatile__(
+		"push %%ebp\n"
 		"out %%al, (%%dx)\n"
-		: "=a" (result), "=b" (state), "=D" (edi)
-		: "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0)
+		"pop %%ebp\n"
+		: "=a" (result), "=b" (state), "=D" (edi), "=c" (dummy), "=d" (dummy), "=S" (dummy)
+		: "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0), "D" (0)
 	);
 
 	dprintk("state is %x, result is %x\n", state, result);
@@ -160,7 +167,7 @@ static int speedstep_get_state (void)
  */
 static void speedstep_set_state (unsigned int state)
 {
-	unsigned int result = 0, command, new_state;
+	unsigned int result = 0, command, new_state, dummy;
 	unsigned long flags;
 	unsigned int function=SET_SPEEDSTEP_STATE;
 	unsigned int retry = 0;
@@ -182,10 +189,12 @@ static void speedstep_set_state (unsigned int state)
 		}
 		retry++;
 		__asm__ __volatile__(
-			"movl $0, %%edi\n"
+			"push %%ebp\n"
 			"out %%al, (%%dx)\n"
-			: "=b" (new_state), "=D" (result)
-			: "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0)
+			"pop %%ebp"
+			: "=b" (new_state), "=D" (result), "=c" (dummy), "=a" (dummy),
+				"=d" (dummy), "=S" (dummy)
+			: "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0)
 			);
 	} while ((new_state != state) && (retry <= SMI_TRIES));
 
@@ -195,7 +204,7 @@ static void speedstep_set_state (unsigned int state)
 	if (new_state == state) {
 		dprintk("change to %u MHz succeeded after %u tries with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result);
 	} else {
-		printk(KERN_ERR "cpufreq: change failed with new_state %u and result %u\n", new_state, result);
+		printk(KERN_ERR "cpufreq: change to state %u failed with new_state %u and result %u\n", state, new_state, result);
 	}
 
 	return;
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 103d61a59b19..3e18db4cefee 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -176,12 +176,13 @@ static inline void k8_enable_fixed_iorrs(void)
 }
 
 /**
- * Checks and updates an fixed-range MTRR if it differs from the value it
- * should have. If K8 extentions are wanted, update the K8 SYSCFG MSR also.
- * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information
- * \param msr MSR address of the MTTR which should be checked and updated
- * \param changed pointer which indicates whether the MTRR needed to be changed
- * \param msrwords pointer to the MSR values which the MSR should have
+ * set_fixed_range - checks & updates a fixed-range MTRR if it differs from the value it should have
+ * @msr: MSR address of the MTTR which should be checked and updated
+ * @changed: pointer which indicates whether the MTRR needed to be changed
+ * @msrwords: pointer to the MSR values which the MSR should have
+ *
+ * If K8 extentions are wanted, update the K8 SYSCFG MSR also.
+ * See AMD publication no. 24593, chapter 7.8.1, page 233 for more information.
  */
 static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
 {
@@ -199,12 +200,15 @@ static void set_fixed_range(int msr, bool *changed, unsigned int *msrwords)
 	}
 }
 
+/**
+ * generic_get_free_region - Get a free MTRR.
+ * @base: The starting (base) address of the region.
+ * @size: The size (in bytes) of the region.
+ * @replace_reg: mtrr index to be replaced; set to invalid value if none.
+ *
+ * Returns: The index of the region on success, else negative on error.
+ */
 int generic_get_free_region(unsigned long base, unsigned long size, int replace_reg)
-/*  [SUMMARY] Get a free MTRR.
-    <base> The starting (base) address of the region.
-    <size> The size (in bytes) of the region.
-    [RETURNS] The index of the region on success, else -1 on error.
-*/
 {
 	int i, max;
 	mtrr_type ltype;
@@ -249,8 +253,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 }
 
 /**
- * Checks and updates the fixed-range MTRRs if they differ from the saved set
- * \param frs pointer to fixed-range MTRR values, saved by get_fixed_ranges()
+ * set_fixed_ranges - checks & updates the fixed-range MTRRs if they differ from the saved set
+ * @frs: pointer to fixed-range MTRR values, saved by get_fixed_ranges()
  */
 static int set_fixed_ranges(mtrr_type * frs)
 {
@@ -294,13 +298,13 @@ static bool set_mtrr_var_ranges(unsigned int index, struct mtrr_var_range *vr)
 
 static u32 deftype_lo, deftype_hi;
 
+/**
+ * set_mtrr_state - Set the MTRR state for this CPU.
+ *
+ * NOTE: The CPU must already be in a safe state for MTRR changes.
+ * RETURNS: 0 if no changes made, else a mask indicating what was changed.
+ */
 static unsigned long set_mtrr_state(void)
-/*  [SUMMARY] Set the MTRR state for this CPU.
-    <state> The MTRR state information to read.
-    <ctxt> Some relevant CPU context.
-    [NOTE] The CPU must already be in a safe state for MTRR changes.
-    [RETURNS] 0 if no changes made, else a mask indication what was changed.
-*/
 {
 	unsigned int i;
 	unsigned long change_mask = 0;
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 9b838324b818..b943e10ad814 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -652,9 +652,6 @@ static void probe_nmi_watchdog(void)
 			wd_ops = &p6_wd_ops;
 			break;
 		case 15:
-			if (boot_cpu_data.x86_model > 0x4)
-				return;
-
 			wd_ops = &p4_wd_ops;
 			break;
 		default:
@@ -670,8 +667,10 @@ int lapic_watchdog_init(unsigned nmi_hz)
 {
 	if (!wd_ops) {
 		probe_nmi_watchdog();
-		if (!wd_ops)
+		if (!wd_ops) {
+			printk(KERN_INFO "NMI watchdog: CPU not supported\n");
 			return -1;
+		}
 
 		if (!wd_ops->reserve()) {
 			printk(KERN_ERR
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 235fd6c77504..36652ea1a265 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -133,13 +133,16 @@ static void hpet_reserve_platform_timers(unsigned long id)
 #ifdef CONFIG_HPET_EMULATE_RTC
 	hpet_reserve_timer(&hd, 1);
 #endif
+
 	hd.hd_irq[0] = HPET_LEGACY_8254;
 	hd.hd_irq[1] = HPET_LEGACY_RTC;
 
-       for (i = 2; i < nrtimers; timer++, i++)
-	       hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >>
-		       Tn_INT_ROUTE_CNF_SHIFT;
+	for (i = 2; i < nrtimers; timer++, i++)
+		hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >>
+			Tn_INT_ROUTE_CNF_SHIFT;
+
 	hpet_alloc(&hd);
+
 }
 #else
 static void hpet_reserve_platform_timers(unsigned long id) { }
diff --git a/arch/x86/kernel/io_delay.c b/arch/x86/kernel/io_delay.c
index c706a3061553..5921e5f0a640 100644
--- a/arch/x86/kernel/io_delay.c
+++ b/arch/x86/kernel/io_delay.c
@@ -78,6 +78,14 @@ static struct dmi_system_id __initdata io_delay_0xed_port_dmi_table[] = {
 	},
 	{
 		.callback	= dmi_io_delay_0xed_port,
+		.ident		= "HP Pavilion dv6000",
+		.matches	= {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
+			DMI_MATCH(DMI_BOARD_NAME, "30B8")
+		}
+	},
+	{
+		.callback	= dmi_io_delay_0xed_port,
 		.ident		= "HP Pavilion tx1000",
 		.matches	= {
 			DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 236d2f8f7ddc..576a03db4511 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -233,6 +233,7 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 
 void arch_crash_save_vmcoreinfo(void)
 {
+	VMCOREINFO_SYMBOL(phys_base);
 	VMCOREINFO_SYMBOL(init_level4_pgt);
 
 #ifdef CONFIG_NUMA
diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c
index 027fc067b399..b402c0f3f192 100644
--- a/arch/x86/kernel/mfgpt_32.c
+++ b/arch/x86/kernel/mfgpt_32.c
@@ -30,6 +30,7 @@
 
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/module.h>
 #include <asm/geode.h>
 
 static struct mfgpt_timer_t {
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index faf3229f8fb3..700e4647dd30 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -615,8 +615,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
  nommu:
 	/* Should not happen anymore */
-	printk(KERN_ERR "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
-	       KERN_ERR "PCI-DMA: 32bit PCI IO may malfunction.\n");
+	printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
+	       KERN_WARNING "falling back to iommu=soft.\n");
 	return -1;
 }
 
@@ -692,9 +692,9 @@ void __init gart_iommu_init(void)
 	    !gart_iommu_aperture ||
 	    (no_agp && init_k8_gatt(&info) < 0)) {
 		if (end_pfn > MAX_DMA32_PFN) {
-			printk(KERN_ERR "WARNING more than 4GB of memory "
-					"but GART IOMMU not available.\n"
-			       KERN_ERR "WARNING 32bit PCI may malfunction.\n");
+			printk(KERN_WARNING "More than 4GB of memory "
+			       	          "but GART IOMMU not available.\n"
+			       KERN_WARNING "falling back to iommu=soft.\n");
 		}
 		return;
 	}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index be3c7a299f02..43930e73f657 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -82,7 +82,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
  */
 void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
-static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
 void disable_hlt(void)
 {
@@ -190,9 +189,6 @@ void cpu_idle(void)
 		while (!need_resched()) {
 			void (*idle)(void);
 
-			if (__get_cpu_var(cpu_idle_state))
-				__get_cpu_var(cpu_idle_state) = 0;
-
 			check_pgt_cache();
 			rmb();
 			idle = pm_idle;
@@ -220,40 +216,19 @@ static void do_nothing(void *unused)
 {
 }
 
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
 void cpu_idle_wait(void)
 {
-	unsigned int cpu, this_cpu = get_cpu();
-	cpumask_t map, tmp = current->cpus_allowed;
-
-	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
-	put_cpu();
-
-	cpus_clear(map);
-	for_each_online_cpu(cpu) {
-		per_cpu(cpu_idle_state, cpu) = 1;
-		cpu_set(cpu, map);
-	}
-
-	__get_cpu_var(cpu_idle_state) = 0;
-
-	wmb();
-	do {
-		ssleep(1);
-		for_each_online_cpu(cpu) {
-			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
-				cpu_clear(cpu, map);
-		}
-		cpus_and(map, map, cpu_online_map);
-		/*
-		 * We waited 1 sec, if a CPU still did not call idle
-		 * it may be because it is in idle and not waking up
-		 * because it has nothing to do.
-		 * Give all the remaining CPUS a kick.
-		 */
-		smp_call_function_mask(map, do_nothing, NULL, 0);
-	} while (!cpus_empty(map));
-
-	set_cpus_allowed(current, tmp);
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 0, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3baf9b9f4c87..46c4c546b499 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -63,7 +63,6 @@ EXPORT_SYMBOL(boot_option_idle_override);
  */
 void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
-static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
 
@@ -173,9 +172,6 @@ void cpu_idle(void)
 		while (!need_resched()) {
 			void (*idle)(void);
 
-			if (__get_cpu_var(cpu_idle_state))
-				__get_cpu_var(cpu_idle_state) = 0;
-
 			rmb();
 			idle = pm_idle;
 			if (!idle)
@@ -207,40 +203,19 @@ static void do_nothing(void *unused)
 {
 }
 
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
 void cpu_idle_wait(void)
 {
-	unsigned int cpu, this_cpu = get_cpu();
-	cpumask_t map, tmp = current->cpus_allowed;
-
-	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
-	put_cpu();
-
-	cpus_clear(map);
-	for_each_online_cpu(cpu) {
-		per_cpu(cpu_idle_state, cpu) = 1;
-		cpu_set(cpu, map);
-	}
-
-	__get_cpu_var(cpu_idle_state) = 0;
-
-	wmb();
-	do {
-		ssleep(1);
-		for_each_online_cpu(cpu) {
-			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
-				cpu_clear(cpu, map);
-		}
-		cpus_and(map, map, cpu_online_map);
-		/*
-		 * We waited 1 sec, if a CPU still did not call idle
-		 * it may be because it is in idle and not waking up
-		 * because it has nothing to do.
-		 * Give all the remaining CPUS a kick.
-		 */
-		smp_call_function_mask(map, do_nothing, 0, 0);
-	} while (!cpus_empty(map));
-
-	set_cpus_allowed(current, tmp);
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 0, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index d5904eef1d31..eb92ccbb3502 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -600,21 +600,6 @@ static int ptrace_bts_read_record(struct task_struct *child,
 	return sizeof(ret);
 }
 
-static int ptrace_bts_write_record(struct task_struct *child,
-				   const struct bts_struct *in)
-{
-	int retval;
-
-	if (!child->thread.ds_area_msr)
-		return -ENXIO;
-
-	retval = ds_write_bts((void *)child->thread.ds_area_msr, in);
-	if (retval)
-		return retval;
-
-	return sizeof(*in);
-}
-
 static int ptrace_bts_clear(struct task_struct *child)
 {
 	if (!child->thread.ds_area_msr)
@@ -657,75 +642,6 @@ static int ptrace_bts_drain(struct task_struct *child,
 	return end;
 }
 
-static int ptrace_bts_realloc(struct task_struct *child,
-			      int size, int reduce_size)
-{
-	unsigned long rlim, vm;
-	int ret, old_size;
-
-	if (size < 0)
-		return -EINVAL;
-
-	old_size = ds_get_bts_size((void *)child->thread.ds_area_msr);
-	if (old_size < 0)
-		return old_size;
-
-	ret = ds_free((void **)&child->thread.ds_area_msr);
-	if (ret < 0)
-		goto out;
-
-	size >>= PAGE_SHIFT;
-	old_size >>= PAGE_SHIFT;
-
-	current->mm->total_vm  -= old_size;
-	current->mm->locked_vm -= old_size;
-
-	if (size == 0)
-		goto out;
-
-	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
-	vm = current->mm->total_vm  + size;
-	if (rlim < vm) {
-		ret = -ENOMEM;
-
-		if (!reduce_size)
-			goto out;
-
-		size = rlim - current->mm->total_vm;
-		if (size <= 0)
-			goto out;
-	}
-
-	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
-	vm = current->mm->locked_vm  + size;
-	if (rlim < vm) {
-		ret = -ENOMEM;
-
-		if (!reduce_size)
-			goto out;
-
-		size = rlim - current->mm->locked_vm;
-		if (size <= 0)
-			goto out;
-	}
-
-	ret = ds_allocate((void **)&child->thread.ds_area_msr,
-			  size << PAGE_SHIFT);
-	if (ret < 0)
-		goto out;
-
-	current->mm->total_vm  += size;
-	current->mm->locked_vm += size;
-
-out:
-	if (child->thread.ds_area_msr)
-		set_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-	else
-		clear_tsk_thread_flag(child, TIF_DS_AREA_MSR);
-
-	return ret;
-}
-
 static int ptrace_bts_config(struct task_struct *child,
 			     long cfg_size,
 			     const struct ptrace_bts_config __user *ucfg)
@@ -828,6 +744,91 @@ static int ptrace_bts_status(struct task_struct *child,
 	return sizeof(cfg);
 }
 
+
+static int ptrace_bts_write_record(struct task_struct *child,
+				   const struct bts_struct *in)
+{
+	int retval;
+
+	if (!child->thread.ds_area_msr)
+		return -ENXIO;
+
+	retval = ds_write_bts((void *)child->thread.ds_area_msr, in);
+	if (retval)
+		return retval;
+
+	return sizeof(*in);
+}
+
+static int ptrace_bts_realloc(struct task_struct *child,
+			      int size, int reduce_size)
+{
+	unsigned long rlim, vm;
+	int ret, old_size;
+
+	if (size < 0)
+		return -EINVAL;
+
+	old_size = ds_get_bts_size((void *)child->thread.ds_area_msr);
+	if (old_size < 0)
+		return old_size;
+
+	ret = ds_free((void **)&child->thread.ds_area_msr);
+	if (ret < 0)
+		goto out;
+
+	size >>= PAGE_SHIFT;
+	old_size >>= PAGE_SHIFT;
+
+	current->mm->total_vm  -= old_size;
+	current->mm->locked_vm -= old_size;
+
+	if (size == 0)
+		goto out;
+
+	rlim = current->signal->rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
+	vm = current->mm->total_vm  + size;
+	if (rlim < vm) {
+		ret = -ENOMEM;
+
+		if (!reduce_size)
+			goto out;
+
+		size = rlim - current->mm->total_vm;
+		if (size <= 0)
+			goto out;
+	}
+
+	rlim = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
+	vm = current->mm->locked_vm  + size;
+	if (rlim < vm) {
+		ret = -ENOMEM;
+
+		if (!reduce_size)
+			goto out;
+
+		size = rlim - current->mm->locked_vm;
+		if (size <= 0)
+			goto out;
+	}
+
+	ret = ds_allocate((void **)&child->thread.ds_area_msr,
+			  size << PAGE_SHIFT);
+	if (ret < 0)
+		goto out;
+
+	current->mm->total_vm  += size;
+	current->mm->locked_vm += size;
+
+out:
+	if (child->thread.ds_area_msr)
+		set_tsk_thread_flag(child, TIF_DS_AREA_MSR);
+	else
+		clear_tsk_thread_flag(child, TIF_DS_AREA_MSR);
+
+	return ret;
+}
+
 void ptrace_bts_take_timestamp(struct task_struct *tsk,
 			       enum bts_qualifier qualifier)
 {
diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c
index a1d7071a51c9..2b3e5d45176b 100644
--- a/arch/x86/kernel/setup_32.c
+++ b/arch/x86/kernel/setup_32.c
@@ -406,8 +406,6 @@ static unsigned long __init setup_memory(void)
 	 */
 	min_low_pfn = PFN_UP(init_pg_tables_end);
 
-	find_max_pfn();
-
 	max_low_pfn = find_max_low_pfn();
 
 #ifdef CONFIG_HIGHMEM
@@ -764,12 +762,13 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled)
 		efi_init();
 
-	max_low_pfn = setup_memory();
-
 	/* update e820 for memory not covered by WB MTRRs */
+	find_max_pfn();
 	mtrr_bp_init();
 	if (mtrr_trim_uncached_memory(max_pfn))
-		max_low_pfn = setup_memory();
+		find_max_pfn();
+
+	max_low_pfn = setup_memory();
 
 #ifdef CONFIG_VMI
 	/*
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index 7637dc91c79b..f4f7ecfb898c 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -801,7 +801,7 @@ static void __cpuinit srat_detect_node(void)
 	/* Don't do the funky fallback heuristics the AMD version employs
 	   for now. */
 	node = apicid_to_node[apicid];
-	if (node == NUMA_NO_NODE)
+	if (node == NUMA_NO_NODE || !node_online(node))
 		node = first_node(node_online_map);
 	numa_set_node(cpu, node);
 
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9d406cdc847f..071ff4798236 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -140,6 +140,9 @@ static int enable_single_step(struct task_struct *child)
  */
 static void write_debugctlmsr(struct task_struct *child, unsigned long val)
 {
+	if (child->thread.debugctlmsr == val)
+		return;
+
 	child->thread.debugctlmsr = val;
 
 	if (child != current)
@@ -165,11 +168,11 @@ static void enable_step(struct task_struct *child, bool block)
 		write_debugctlmsr(child,
 				  child->thread.debugctlmsr | DEBUGCTLMSR_BTF);
 	} else {
-	    write_debugctlmsr(child,
-			      child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
+		write_debugctlmsr(child,
+				  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
 
-	    if (!child->thread.debugctlmsr)
-		    clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+		if (!child->thread.debugctlmsr)
+			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
 	}
 }
 
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 022bcaa3b42e..ab6bf375a307 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -92,7 +92,7 @@ int do_set_thread_area(struct task_struct *p, int idx,
 asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
 {
 	int ret = do_set_thread_area(current, -1, u_info, 1);
-	prevent_tail_call(ret);
+	asmlinkage_protect(1, ret, u_info);
 	return ret;
 }
 
@@ -142,7 +142,7 @@ int do_get_thread_area(struct task_struct *p, int idx,
 asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
 {
 	int ret = do_get_thread_area(current, -1, u_info);
-	prevent_tail_call(ret);
+	asmlinkage_protect(1, ret, u_info);
 	return ret;
 }
 
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index f14cfd9d1f94..c2241e04ea5f 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -256,9 +256,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data)
 						ref_freq, freq->new);
 			if (!(freq->flags & CPUFREQ_CONST_LOOPS)) {
 				tsc_khz = cpu_khz;
-				preempt_disable();
-				set_cyc2ns_scale(cpu_khz, smp_processor_id());
-				preempt_enable();
+				set_cyc2ns_scale(cpu_khz, freq->cpu);
 				/*
 				 * TSC based sched_clock turns
 				 * to junk w/ cpufreq
diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index 947554ddabb6..d3bebaaad842 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -148,9 +148,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 			mark_tsc_unstable("cpufreq changes");
 	}
 
-	preempt_disable();
-	set_cyc2ns_scale(tsc_khz_ref, smp_processor_id());
-	preempt_enable();
+	set_cyc2ns_scale(tsc_khz_ref, freq->cpu);
 
 	return 0;
 }