Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mingo/linux-2.6-sched-devel: (62 commits)
  sched: build fix
  sched: better rt-group documentation
  sched: features fix
  sched: /debug/sched_features
  sched: add SCHED_FEAT_DEADLINE
  sched: debug: show a weight tree
  sched: fair: weight calculations
  sched: fair-group: de-couple load-balancing from the rb-trees
  sched: fair-group scheduling vs latency
  sched: rt-group: optimize dequeue_rt_stack
  sched: debug: add some debug code to handle the full hierarchy
  sched: fair-group: SMP-nice for group scheduling
  sched, cpuset: customize sched domains, core
  sched, cpuset: customize sched domains, docs
  sched: prepatory code movement
  sched: rt: multi level group constraints
  sched: task_group hierarchy
  sched: fix the task_group hierarchy for UID grouping
  sched: allow the group scheduler to have multiple levels
  sched: mix tasks and groups
  ...

14 files changed, 201 insertions, 137 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 07cf7711356..87a693cf2bb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -117,6 +117,9 @@ config ARCH_HAS_CPU_RELAX
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool X86_64 || (X86_SMP && !X86_VOYAGER)
 
+config HAVE_CPUMASK_OF_CPU_MAP
+	def_bool X86_64_SMP
+
 config ARCH_HIBERNATION_POSSIBLE
 	def_bool y
 	depends on !SMP || !X86_VOYAGER
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 9366fb68d8d..c2502eb9aa8 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -91,7 +91,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 
 	/* Make sure we are running on right CPU */
 	saved_mask = current->cpus_allowed;
-	retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (retval)
 		return -1;
 
@@ -128,7 +128,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 		 cx->address);
 
 out:
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return retval;
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index a962dcb9c40..e2d870de837 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -192,9 +192,9 @@ static void drv_read(struct drv_cmd *cmd)
 	cpumask_t saved_mask = current->cpus_allowed;
 	cmd->val = 0;
 
-	set_cpus_allowed(current, cmd->mask);
+	set_cpus_allowed_ptr(current, &cmd->mask);
 	do_drv_read(cmd);
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 }
 
 static void drv_write(struct drv_cmd *cmd)
@@ -203,30 +203,30 @@ static void drv_write(struct drv_cmd *cmd)
 	unsigned int i;
 
 	for_each_cpu_mask(i, cmd->mask) {
-		set_cpus_allowed(current, cpumask_of_cpu(i));
+		set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
 		do_drv_write(cmd);
 	}
 
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return;
 }
 
-static u32 get_cur_val(cpumask_t mask)
+static u32 get_cur_val(const cpumask_t *mask)
 {
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
 
-	if (unlikely(cpus_empty(mask)))
+	if (unlikely(cpus_empty(*mask)))
 		return 0;
 
-	switch (per_cpu(drv_data, first_cpu(mask))->cpu_feature) {
+	switch (per_cpu(drv_data, first_cpu(*mask))->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = per_cpu(drv_data, first_cpu(mask))->acpi_data;
+		perf = per_cpu(drv_data, first_cpu(*mask))->acpi_data;
 		cmd.addr.io.port = perf->control_register.address;
 		cmd.addr.io.bit_width = perf->control_register.bit_width;
 		break;
@@ -234,7 +234,7 @@ static u32 get_cur_val(cpumask_t mask)
 		return 0;
 	}
 
-	cmd.mask = mask;
+	cmd.mask = *mask;
 
 	drv_read(&cmd);
 
@@ -271,7 +271,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
 	unsigned int retval;
 
 	saved_mask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (get_cpu() != cpu) {
 		/* We were not able to run on requested processor */
 		put_cpu();
@@ -329,7 +329,7 @@ static unsigned int get_measured_perf(unsigned int cpu)
 	retval = per_cpu(drv_data, cpu)->max_freq * perf_percent / 100;
 
 	put_cpu();
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 
 	dprintk("cpu %d: performance percent %d\n", cpu, perf_percent);
 	return retval;
@@ -347,13 +347,13 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 		return 0;
 	}
 
-	freq = extract_freq(get_cur_val(cpumask_of_cpu(cpu)), data);
+	freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
 	dprintk("cur freq = %u\n", freq);
 
 	return freq;
 }
 
-static unsigned int check_freqs(cpumask_t mask, unsigned int freq,
+static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
 				struct acpi_cpufreq_data *data)
 {
 	unsigned int cur_freq;
@@ -449,7 +449,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	drv_write(&cmd);
 
 	if (acpi_pstate_strict) {
-		if (!check_freqs(cmd.mask, freqs.new, data)) {
+		if (!check_freqs(&cmd.mask, freqs.new, data)) {
 			dprintk("acpi_cpufreq_target failed (%d)\n",
 				policy->cpu);
 			return -EAGAIN;
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index c99d59d8ef2..46d4034d9f3 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -478,12 +478,12 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi
 
 static int check_supported_cpu(unsigned int cpu)
 {
-	cpumask_t oldmask = CPU_MASK_ALL;
+	cpumask_t oldmask;
 	u32 eax, ebx, ecx, edx;
 	unsigned int rc = 0;
 
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 	if (smp_processor_id() != cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", cpu);
@@ -528,7 +528,7 @@ static int check_supported_cpu(unsigned int cpu)
 	rc = 1;
 
 out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	return rc;
 }
 
@@ -1015,7 +1015,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i
 /* Driver entry point to switch to the target frequency */
 static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation)
 {
-	cpumask_t oldmask = CPU_MASK_ALL;
+	cpumask_t oldmask;
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
 	u32 checkfid;
 	u32 checkvid;
@@ -1030,7 +1030,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(pol->cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
 
 	if (smp_processor_id() != pol->cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1085,7 +1085,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 	ret = 0;
 
 err_out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	return ret;
 }
 
@@ -1104,7 +1104,7 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
 static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data;
-	cpumask_t oldmask = CPU_MASK_ALL;
+	cpumask_t oldmask;
 	int rc;
 
 	if (!cpu_online(pol->cpu))
@@ -1145,7 +1145,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(pol->cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
 
 	if (smp_processor_id() != pol->cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
@@ -1164,7 +1164,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		fidvid_msr_init();
 
 	/* run on any CPU again */
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cpus = cpumask_of_cpu(pol->cpu);
@@ -1205,7 +1205,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	return 0;
 
 err_out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	powernow_k8_cpu_exit_acpi(data);
 
 	kfree(data);
@@ -1242,10 +1242,11 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	if (!data)
 		return -EINVAL;
 
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (smp_processor_id() != cpu) {
-		printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu);
-		set_cpus_allowed(current, oldmask);
+		printk(KERN_ERR PFX
+			"limiting to CPU %d failed in powernowk8_get\n", cpu);
+		set_cpus_allowed_ptr(current, &oldmask);
 		return 0;
 	}
 
@@ -1253,13 +1254,14 @@ static unsigned int powernowk8_get (unsigned int cpu)
 		goto out;
 
 	if (cpu_family == CPU_HW_PSTATE)
-		khz = find_khz_freq_from_pstate(data->powernow_table, data->currpstate);
+		khz = find_khz_freq_from_pstate(data->powernow_table,
+						data->currpstate);
 	else
 		khz = find_khz_freq_from_fid(data->currfid);
 
 
 out:
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 	return khz;
 }
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 3031f119619..908dd347c67 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -315,7 +315,7 @@ static unsigned int get_cur_freq(unsigned int cpu)
 	cpumask_t saved_mask;
 
 	saved_mask = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (smp_processor_id() != cpu)
 		return 0;
 
@@ -333,7 +333,7 @@ static unsigned int get_cur_freq(unsigned int cpu)
 		clock_freq = extract_clock(l, cpu, 1);
 	}
 
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return clock_freq;
 }
 
@@ -487,7 +487,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 		else
 			cpu_set(j, set_mask);
 
-		set_cpus_allowed(current, set_mask);
+		set_cpus_allowed_ptr(current, &set_mask);
 		preempt_disable();
 		if (unlikely(!cpu_isset(smp_processor_id(), set_mask))) {
 			dprintk("couldn't limit to CPUs in this domain\n");
@@ -555,7 +555,8 @@ static int centrino_target (struct cpufreq_policy *policy,
 
 		if (!cpus_empty(covered_cpus)) {
 			for_each_cpu_mask(j, covered_cpus) {
-				set_cpus_allowed(current, cpumask_of_cpu(j));
+				set_cpus_allowed_ptr(current,
+						     &cpumask_of_cpu(j));
 				wrmsr(MSR_IA32_PERF_CTL, oldmsr, h);
 			}
 		}
@@ -569,12 +570,12 @@ static int centrino_target (struct cpufreq_policy *policy,
 			cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 		}
 	}
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return 0;
 
 migrate_end:
 	preempt_enable();
-	set_cpus_allowed(current, saved_mask);
+	set_cpus_allowed_ptr(current, &saved_mask);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 14d68aa301e..1b50244b1fd 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -229,22 +229,22 @@ static unsigned int speedstep_detect_chipset (void)
 	return 0;
 }
 
-static unsigned int _speedstep_get(cpumask_t cpus)
+static unsigned int _speedstep_get(const cpumask_t *cpus)
 {
 	unsigned int speed;
 	cpumask_t cpus_allowed;
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed(current, cpus);
+	set_cpus_allowed_ptr(current, cpus);
 	speed = speedstep_get_processor_frequency(speedstep_processor);
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 	dprintk("detected %u kHz as current frequency\n", speed);
 	return speed;
 }
 
 static unsigned int speedstep_get(unsigned int cpu)
 {
-	return _speedstep_get(cpumask_of_cpu(cpu));
+	return _speedstep_get(&cpumask_of_cpu(cpu));
 }
 
 /**
@@ -267,7 +267,7 @@ static int speedstep_target (struct cpufreq_policy *policy,
 	if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate))
 		return -EINVAL;
 
-	freqs.old = _speedstep_get(policy->cpus);
+	freqs.old = _speedstep_get(&policy->cpus);
 	freqs.new = speedstep_freqs[newstate].frequency;
 	freqs.cpu = policy->cpu;
 
@@ -285,12 +285,12 @@ static int speedstep_target (struct cpufreq_policy *policy,
 	}
 
 	/* switch to physical CPU where state is to be changed */
-	set_cpus_allowed(current, policy->cpus);
+	set_cpus_allowed_ptr(current, &policy->cpus);
 
 	speedstep_set_state(newstate);
 
 	/* allow to be run on all CPUs */
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	for_each_cpu_mask(i, policy->cpus) {
 		freqs.cpu = i;
@@ -326,7 +326,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 #endif
 
 	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed(current, policy->cpus);
+	set_cpus_allowed_ptr(current, &policy->cpus);
 
 	/* detect low and high frequency and transition latency */
 	result = speedstep_get_freqs(speedstep_processor,
@@ -334,12 +334,12 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 				     &speedstep_freqs[SPEEDSTEP_HIGH].frequency,
 				     &policy->cpuinfo.transition_latency,
 				     &speedstep_set_state);
-	set_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, &cpus_allowed);
 	if (result)
 		return result;
 
 	/* get current speed setting */
-	speed = _speedstep_get(policy->cpus);
+	speed = _speedstep_get(&policy->cpus);
 	if (!speed)
 		return -EIO;
 
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 1b889860eb7..26d615dcb14 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -129,7 +129,7 @@ struct _cpuid4_info {
 	union _cpuid4_leaf_ebx ebx;
 	union _cpuid4_leaf_ecx ecx;
 	unsigned long size;
-	cpumask_t shared_cpu_map;
+	cpumask_t shared_cpu_map;	/* future?: only cpus/node is needed */
 };
 
 unsigned short			num_cache_leaves;
@@ -451,8 +451,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 }
 
 /* pointer to _cpuid4_info array (for each cache leaf) */
-static struct _cpuid4_info *cpuid4_info[NR_CPUS];
-#define CPUID4_INFO_IDX(x,y)    (&((cpuid4_info[x])[y]))
+static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
+#define CPUID4_INFO_IDX(x, y)    (&((per_cpu(cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
@@ -474,7 +474,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 			if (cpu_data(i).apicid >> index_msb ==
 			    c->apicid >> index_msb) {
 				cpu_set(i, this_leaf->shared_cpu_map);
-				if (i != cpu && cpuid4_info[i])  {
+				if (i != cpu && per_cpu(cpuid4_info, i))  {
 					sibling_leaf = CPUID4_INFO_IDX(i, index);
 					cpu_set(cpu, sibling_leaf->shared_cpu_map);
 				}
@@ -505,8 +505,8 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
 	for (i = 0; i < num_cache_leaves; i++)
 		cache_remove_shared_cpu_map(cpu, i);
 
-	kfree(cpuid4_info[cpu]);
-	cpuid4_info[cpu] = NULL;
+	kfree(per_cpu(cpuid4_info, cpu));
+	per_cpu(cpuid4_info, cpu) = NULL;
 }
 
 static int __cpuinit detect_cache_attributes(unsigned int cpu)
@@ -519,13 +519,13 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 	if (num_cache_leaves == 0)
 		return -ENOENT;
 
-	cpuid4_info[cpu] = kzalloc(
+	per_cpu(cpuid4_info, cpu) = kzalloc(
 	    sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
-	if (cpuid4_info[cpu] == NULL)
+	if (per_cpu(cpuid4_info, cpu) == NULL)
 		return -ENOMEM;
 
 	oldmask = current->cpus_allowed;
-	retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (retval)
 		goto out;
 
@@ -542,12 +542,12 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 		}
 		cache_shared_cpu_map_setup(cpu, j);
 	}
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, &oldmask);
 
 out:
 	if (retval) {
-		kfree(cpuid4_info[cpu]);
-		cpuid4_info[cpu] = NULL;
+		kfree(per_cpu(cpuid4_info, cpu));
+		per_cpu(cpuid4_info, cpu) = NULL;
 	}
 
 	return retval;
@@ -561,7 +561,7 @@ out:
 extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
 
 /* pointer to kobject for cpuX/cache */
-static struct kobject * cache_kobject[NR_CPUS];
+static DEFINE_PER_CPU(struct kobject *, cache_kobject);
 
 struct _index_kobject {
 	struct kobject kobj;
@@ -570,8 +570,8 @@ struct _index_kobject {
 };
 
 /* pointer to array of kobjects for cpuX/cache/indexY */
-static struct _index_kobject *index_kobject[NR_CPUS];
-#define INDEX_KOBJECT_PTR(x,y)    (&((index_kobject[x])[y]))
+static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
+#define INDEX_KOBJECT_PTR(x, y)    (&((per_cpu(index_kobject, x))[y]))
 
 #define show_one_plus(file_name, object, val)				\
 static ssize_t show_##file_name						\
@@ -591,11 +591,32 @@ static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf)
 	return sprintf (buf, "%luK\n", this_leaf->size / 1024);
 }
 
-static ssize_t show_shared_cpu_map(struct _cpuid4_info *this_leaf, char *buf)
+static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
+					int type, char *buf)
 {
-	char mask_str[NR_CPUS];
-	cpumask_scnprintf(mask_str, NR_CPUS, this_leaf->shared_cpu_map);
-	return sprintf(buf, "%s\n", mask_str);
+	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
+	int n = 0;
+
+	if (len > 1) {
+		cpumask_t *mask = &this_leaf->shared_cpu_map;
+
+		n = type?
+			cpulist_scnprintf(buf, len-2, *mask):
+			cpumask_scnprintf(buf, len-2, *mask);
+		buf[n++] = '\n';
+		buf[n] = '\0';
+	}
+	return n;
+}
+
+static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf)
+{
+	return show_shared_cpu_map_func(leaf, 0, buf);
+}
+
+static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
+{
+	return show_shared_cpu_map_func(leaf, 1, buf);
 }
 
 static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
@@ -633,6 +654,7 @@ define_one_ro(ways_of_associativity);
 define_one_ro(number_of_sets);
 define_one_ro(size);
 define_one_ro(shared_cpu_map);
+define_one_ro(shared_cpu_list);
 
 static struct attribute * default_attrs[] = {
 	&type.attr,
@@ -643,6 +665,7 @@ static struct attribute * default_attrs[] = {
 	&number_of_sets.attr,
 	&size.attr,
 	&shared_cpu_map.attr,
+	&shared_cpu_list.attr,
 	NULL
 };
 
@@ -684,10 +707,10 @@ static struct kobj_type ktype_percpu_entry = {
 
 static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
 {
-	kfree(cache_kobject[cpu]);
-	kfree(index_kobject[cpu]);
-	cache_kobject[cpu] = NULL;
-	index_kobject[cpu] = NULL;
+	kfree(per_cpu(cache_kobject, cpu));
+	kfree(per_cpu(index_kobject, cpu));
+	per_cpu(cache_kobject, cpu) = NULL;
+	per_cpu(index_kobject, cpu) = NULL;
 	free_cache_attributes(cpu);
 }
 
@@ -703,13 +726,14 @@ static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu)
 		return err;
 
 	/* Allocate all required memory */
-	cache_kobject[cpu] = kzalloc(sizeof(struct kobject), GFP_KERNEL);
-	if (unlikely(cache_kobject[cpu] == NULL))
+	per_cpu(cache_kobject, cpu) =
+		kzalloc(sizeof(struct kobject), GFP_KERNEL);
+	if (unlikely(per_cpu(cache_kobject, cpu) == NULL))
 		goto err_out;
 
-	index_kobject[cpu] = kzalloc(
+	per_cpu(index_kobject, cpu) = kzalloc(
 	    sizeof(struct _index_kobject ) * num_cache_leaves, GFP_KERNEL);
-	if (unlikely(index_kobject[cpu] == NULL))
+	if (unlikely(per_cpu(index_kobject, cpu) == NULL))
 		goto err_out;
 
 	return 0;
@@ -733,7 +757,8 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	if (unlikely(retval < 0))
 		return retval;
 
-	retval = kobject_init_and_add(cache_kobject[cpu], &ktype_percpu_entry,
+	retval = kobject_init_and_add(per_cpu(cache_kobject, cpu),
+				      &ktype_percpu_entry,
 				      &sys_dev->kobj, "%s", "cache");
 	if (retval < 0) {
 		cpuid4_cache_sysfs_exit(cpu);
@@ -745,13 +770,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 		this_object->cpu = cpu;
 		this_object->index = i;
 		retval = kobject_init_and_add(&(this_object->kobj),
-					      &ktype_cache, cache_kobject[cpu],
+					      &ktype_cache,
+					      per_cpu(cache_kobject, cpu),
 					      "index%1lu", i);
 		if (unlikely(retval)) {
 			for (j = 0; j < i; j++) {
 				kobject_put(&(INDEX_KOBJECT_PTR(cpu,j)->kobj));
 			}
-			kobject_put(cache_kobject[cpu]);
+			kobject_put(per_cpu(cache_kobject, cpu));
 			cpuid4_cache_sysfs_exit(cpu);
 			break;
 		}
@@ -760,7 +786,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 	if (!retval)
 		cpu_set(cpu, cache_dev_map);
 
-	kobject_uevent(cache_kobject[cpu], KOBJ_ADD);
+	kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
 	return retval;
 }
 
@@ -769,7 +795,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 	unsigned int cpu = sys_dev->id;
 	unsigned long i;
 
-	if (cpuid4_info[cpu] == NULL)
+	if (per_cpu(cpuid4_info, cpu) == NULL)
 		return;
 	if (!cpu_isset(cpu, cache_dev_map))
 		return;
@@ -777,7 +803,7 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
 
 	for (i = 0; i < num_cache_leaves; i++)
 		kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
-	kobject_put(cache_kobject[cpu]);
+	kobject_put(per_cpu(cache_kobject, cpu));
 	cpuid4_cache_sysfs_exit(cpu);
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 32671da8184..7c9a813e119 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -251,18 +251,18 @@ struct threshold_attr {
 	ssize_t(*store) (struct threshold_block *, const char *, size_t count);
 };
 
-static cpumask_t affinity_set(unsigned int cpu)
+static void affinity_set(unsigned int cpu, cpumask_t *oldmask,
+					   cpumask_t *newmask)
 {
-	cpumask_t oldmask = current->cpus_allowed;
-	cpumask_t newmask = CPU_MASK_NONE;
-	cpu_set(cpu, newmask);
-	set_cpus_allowed(current, newmask);
-	return oldmask;
+	*oldmask = current->cpus_allowed;
+	cpus_clear(*newmask);
+	cpu_set(cpu, *newmask);
+	set_cpus_allowed_ptr(current, newmask);
 }
 
-static void affinity_restore(cpumask_t oldmask)
+static void affinity_restore(const cpumask_t *oldmask)
 {
-	set_cpus_allowed(current, oldmask);
+	set_cpus_allowed_ptr(current, oldmask);
 }
 
 #define SHOW_FIELDS(name)                                           \
@@ -277,15 +277,15 @@ static ssize_t store_interrupt_enable(struct threshold_block *b,
 				      const char *buf, size_t count)
 {
 	char *end;
-	cpumask_t oldmask;
+	cpumask_t oldmask, newmask;
 	unsigned long new = simple_strtoul(buf, &end, 0);
 	if (end == buf)
 		return -EINVAL;
 	b->interrupt_enable = !!new;
 
-	oldmask = affinity_set(b->cpu);
+	affinity_set(b->cpu, &oldmask, &newmask);
 	threshold_restart_bank(b, 0, 0);
-	affinity_restore(oldmask);
+	affinity_restore(&oldmask);
 
 	return end - buf;
 }
@@ -294,7 +294,7 @@ static ssize_t store_threshold_limit(struct threshold_block *b,
 				     const char *buf, size_t count)
 {
 	char *end;
-	cpumask_t oldmask;
+	cpumask_t oldmask, newmask;
 	u16 old;
 	unsigned long new = simple_strtoul(buf, &end, 0);
 	if (end == buf)
@@ -306,9 +306,9 @@ static ssize_t store_threshold_limit(struct threshold_block *b,
 	old = b->threshold_limit;
 	b->threshold_limit = new;
 
-	oldmask = affinity_set(b->cpu);
+	affinity_set(b->cpu, &oldmask, &newmask);
 	threshold_restart_bank(b, 0, old);
-	affinity_restore(oldmask);
+	affinity_restore(&oldmask);
 
 	return end - buf;
 }
@@ -316,10 +316,10 @@ static ssize_t store_threshold_limit(struct threshold_block *b,
 static ssize_t show_error_count(struct threshold_block *b, char *buf)
 {
 	u32 high, low;
-	cpumask_t oldmask;
-	oldmask = affinity_set(b->cpu);
+	cpumask_t oldmask, newmask;
+	affinity_set(b->cpu, &oldmask, &newmask);
 	rdmsr(b->address, low, high);
-	affinity_restore(oldmask);
+	affinity_restore(&oldmask);
 	return sprintf(buf, "%x\n",
 		       (high & 0xFFF) - (THRESHOLD_MAX - b->threshold_limit));
 }
@@ -327,10 +327,10 @@ static ssize_t show_error_count(struct threshold_block *b, char *buf)
 static ssize_t store_error_count(struct threshold_block *b,
 				 const char *buf, size_t count)
 {
-	cpumask_t oldmask;
-	oldmask = affinity_set(b->cpu);
+	cpumask_t oldmask, newmask;
+	affinity_set(b->cpu, &oldmask, &newmask);
 	threshold_restart_bank(b, 1, 0);
-	affinity_restore(oldmask);
+	affinity_restore(&oldmask);
 	return 1;
 }
 
@@ -468,7 +468,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 {
 	int i, err = 0;
 	struct threshold_bank *b = NULL;
-	cpumask_t oldmask = CPU_MASK_NONE;
+	cpumask_t oldmask, newmask;
 	char name[32];
 
 	sprintf(name, "threshold_bank%i", bank);
@@ -519,10 +519,10 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
 
-	oldmask = affinity_set(cpu);
+	affinity_set(cpu, &oldmask, &newmask);
 	err = allocate_threshold_blocks(cpu, bank, 0,
 					MSR_IA32_MC0_MISC + bank * 4);
-	affinity_restore(oldmask);
+	affinity_restore(&oldmask);
 
 	if (err)
 		goto out_free;
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index b54464b2665..9ba11d07920 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -785,7 +785,7 @@ static void __clear_irq_vector(int irq)
 		per_cpu(vector_irq, cpu)[vector] = -1;
 
 	cfg->vector = 0;
-	cfg->domain = CPU_MASK_NONE;
+	cpus_clear(cfg->domain);
 }
 
 void __setup_vector_irq(int cpu)
diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c
index 25cf6dee4e5..69729e38b78 100644
--- a/arch/x86/kernel/microcode.c
+++ b/arch/x86/kernel/microcode.c
@@ -402,7 +402,7 @@ static int do_microcode_update (void)
 
 			if (!uci->valid)
 				continue;
-			set_cpus_allowed(current, cpumask_of_cpu(cpu));
+			set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 			error = get_maching_microcode(new_mc, cpu);
 			if (error < 0)
 				goto out;
@@ -416,7 +416,7 @@ out:
 		vfree(new_mc);
 	if (cursor < 0)
 		error = cursor;
-	set_cpus_allowed(current, old);
+	set_cpus_allowed_ptr(current, &old);
 	return error;
 }
 
@@ -579,7 +579,7 @@ static int apply_microcode_check_cpu(int cpu)
 		return 0;
 
 	old = current->cpus_allowed;
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 	/* Check if the microcode we have in memory matches the CPU */
 	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
@@ -610,7 +610,7 @@ static int apply_microcode_check_cpu(int cpu)
 			" sig=0x%x, pf=0x%x, rev=0x%x\n",
 			cpu, uci->sig, uci->pf, uci->rev);
 
-	set_cpus_allowed(current, old);
+	set_cpus_allowed_ptr(current, &old);
 	return err;
 }
 
@@ -621,13 +621,13 @@ static void microcode_init_cpu(int cpu, int resume)
 
 	old = current->cpus_allowed;
 
-	set_cpus_allowed(current, cpumask_of_cpu(cpu));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	mutex_lock(&microcode_mutex);
 	collect_cpu_info(cpu);
 	if (uci->valid && system_state == SYSTEM_RUNNING && !resume)
 		cpu_request_microcode(cpu);
 	mutex_unlock(&microcode_mutex);
-	set_cpus_allowed(current, old);
+	set_cpus_allowed_ptr(current, &old);
 }
 
 static void microcode_fini_cpu(int cpu)
@@ -657,14 +657,14 @@ static ssize_t reload_store(struct sys_device *dev, const char *buf, size_t sz)
 		old = current->cpus_allowed;
 
 		get_online_cpus();
-		set_cpus_allowed(current, cpumask_of_cpu(cpu));
+		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 		mutex_lock(&microcode_mutex);
 		if (uci->valid)
 			err = cpu_request_microcode(cpu);
 		mutex_unlock(&microcode_mutex);
 		put_online_cpus();
-		set_cpus_allowed(current, old);
+		set_cpus_allowed_ptr(current, &old);
 	}
 	if (err)
 		return err;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9692202d3bf..19c9386ac11 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -420,7 +420,7 @@ static void native_machine_shutdown(void)
 		reboot_cpu_id = smp_processor_id();
 
 	/* Make certain I only run on the appropriate processor */
-	set_cpus_allowed(current, cpumask_of_cpu(reboot_cpu_id));
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(reboot_cpu_id));
 
 	/* O.K Now that I'm on the appropriate processor,
 	 * stop all of the others.
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ed157c90412..0d1f44ae6ee 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -54,6 +54,24 @@ static void __init setup_per_cpu_maps(void)
 #endif
 }
 
+#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP
+cpumask_t *cpumask_of_cpu_map __read_mostly;
+EXPORT_SYMBOL(cpumask_of_cpu_map);
+
+/* requires nr_cpu_ids to be initialized */
+static void __init setup_cpumask_of_cpu(void)
+{
+	int i;
+
+	/* alloc_bootmem zeroes memory */
+	cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids);
+	for (i = 0; i < nr_cpu_ids; i++)
+		cpu_set(i, cpumask_of_cpu_map[i]);
+}
+#else
+static inline void setup_cpumask_of_cpu(void) { }
+#endif
+
 #ifdef CONFIG_X86_32
 /*
  * Great future not-so-futuristic plan: make i386 and x86_64 do it
@@ -70,7 +88,7 @@ EXPORT_SYMBOL(__per_cpu_offset);
  */
 void __init setup_per_cpu_areas(void)
 {
-	int i;
+	int i, highest_cpu = 0;
 	unsigned long size;
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -104,10 +122,18 @@ void __init setup_per_cpu_areas(void)
 		__per_cpu_offset[i] = ptr - __per_cpu_start;
 #endif
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+
+		highest_cpu = i;
 	}
 
+	nr_cpu_ids = highest_cpu + 1;
+	printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d\n", NR_CPUS, nr_cpu_ids);
+
 	/* Setup percpu data maps */
 	setup_per_cpu_maps();
+
+	/* Setup cpumask_of_cpu map */
+	setup_cpumask_of_cpu();
 }
 
 #endif
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index cb317018635..9a6892200b2 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -386,9 +386,10 @@ static int __init split_nodes_by_size(struct bootnode *nodes, u64 *addr,
  * Sets up the system RAM area from start_pfn to end_pfn according to the
  * numa=fake command-line option.
  */
+static struct bootnode nodes[MAX_NUMNODES] __initdata;
+
 static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
 {
-	struct bootnode nodes[MAX_NUMNODES];
 	u64 size, addr = start_pfn << PAGE_SHIFT;
 	u64 max_addr = end_pfn << PAGE_SHIFT;
 	int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 1f11cf0a307..cc48d3fde54 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -23,8 +23,8 @@
 #include "op_x86_model.h"
 
 static struct op_x86_model_spec const *model;
-static struct op_msrs cpu_msrs[NR_CPUS];
-static unsigned long saved_lvtpc[NR_CPUS];
+static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
+static DEFINE_PER_CPU(unsigned long, saved_lvtpc);
 
 static int nmi_start(void);
 static void nmi_stop(void);
@@ -89,7 +89,7 @@ static int profile_exceptions_notify(struct notifier_block *self,
 
 	switch (val) {
 	case DIE_NMI:
-		if (model->check_ctrs(args->regs, &cpu_msrs[cpu]))
+		if (model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu)))
 			ret = NOTIFY_STOP;
 		break;
 	default:
@@ -126,7 +126,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs)
 static void nmi_save_registers(void *dummy)
 {
 	int cpu = smp_processor_id();
-	struct op_msrs *msrs = &cpu_msrs[cpu];
+	struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
 	nmi_cpu_save_registers(msrs);
 }
 
@@ -134,10 +134,10 @@ static void free_msrs(void)
 {
 	int i;
 	for_each_possible_cpu(i) {
-		kfree(cpu_msrs[i].counters);
-		cpu_msrs[i].counters = NULL;
-		kfree(cpu_msrs[i].controls);
-		cpu_msrs[i].controls = NULL;
+		kfree(per_cpu(cpu_msrs, i).counters);
+		per_cpu(cpu_msrs, i).counters = NULL;
+		kfree(per_cpu(cpu_msrs, i).controls);
+		per_cpu(cpu_msrs, i).controls = NULL;
 	}
 }
 
@@ -149,13 +149,15 @@ static int allocate_msrs(void)
 
 	int i;
 	for_each_possible_cpu(i) {
-		cpu_msrs[i].counters = kmalloc(counters_size, GFP_KERNEL);
-		if (!cpu_msrs[i].counters) {
+		per_cpu(cpu_msrs, i).counters = kmalloc(counters_size,
+								GFP_KERNEL);
+		if (!per_cpu(cpu_msrs, i).counters) {
 			success = 0;
 			break;
 		}
-		cpu_msrs[i].controls = kmalloc(controls_size, GFP_KERNEL);
-		if (!cpu_msrs[i].controls) {
+		per_cpu(cpu_msrs, i).controls = kmalloc(controls_size,
+								GFP_KERNEL);
+		if (!per_cpu(cpu_msrs, i).controls) {
 			success = 0;
 			break;
 		}
@@ -170,11 +172,11 @@ static int allocate_msrs(void)
 static void nmi_cpu_setup(void *dummy)
 {
 	int cpu = smp_processor_id();
-	struct op_msrs *msrs = &cpu_msrs[cpu];
+	struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
 	spin_lock(&oprofilefs_lock);
 	model->setup_ctrs(msrs);
 	spin_unlock(&oprofilefs_lock);
-	saved_lvtpc[cpu] = apic_read(APIC_LVTPC);
+	per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC);
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
@@ -203,13 +205,15 @@ static int nmi_setup(void)
 	 */
 
 	/* Assume saved/restored counters are the same on all CPUs */
-	model->fill_in_addresses(&cpu_msrs[0]);
+	model->fill_in_addresses(&per_cpu(cpu_msrs, 0));
 	for_each_possible_cpu(cpu) {
 		if (cpu != 0) {
-			memcpy(cpu_msrs[cpu].counters, cpu_msrs[0].counters,
+			memcpy(per_cpu(cpu_msrs, cpu).counters,
+				per_cpu(cpu_msrs, 0).counters,
 				sizeof(struct op_msr) * model->num_counters);
 
-			memcpy(cpu_msrs[cpu].controls, cpu_msrs[0].controls,
+			memcpy(per_cpu(cpu_msrs, cpu).controls,
+				per_cpu(cpu_msrs, 0).controls,
 				sizeof(struct op_msr) * model->num_controls);
 		}
 
@@ -249,7 +253,7 @@ static void nmi_cpu_shutdown(void *dummy)
 {
 	unsigned int v;
 	int cpu = smp_processor_id();
-	struct op_msrs *msrs = &cpu_msrs[cpu];
+	struct op_msrs *msrs = &__get_cpu_var(cpu_msrs);
 
 	/* restoring APIC_LVTPC can trigger an apic error because the delivery
 	 * mode and vector nr combination can be illegal. That's by design: on
@@ -258,23 +262,24 @@ static void nmi_cpu_shutdown(void *dummy)
 	 */
 	v = apic_read(APIC_LVTERR);
 	apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
-	apic_write(APIC_LVTPC, saved_lvtpc[cpu]);
+	apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
 	apic_write(APIC_LVTERR, v);
 	nmi_restore_registers(msrs);
 }
 
 static void nmi_shutdown(void)
 {
+	struct op_msrs *msrs = &__get_cpu_var(cpu_msrs);
 	nmi_enabled = 0;
 	on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
 	unregister_die_notifier(&profile_exceptions_nb);
-	model->shutdown(cpu_msrs);
+	model->shutdown(msrs);
 	free_msrs();
 }
 
 static void nmi_cpu_start(void *dummy)
 {
-	struct op_msrs const *msrs = &cpu_msrs[smp_processor_id()];
+	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
 	model->start(msrs);
 }
 
@@ -286,7 +291,7 @@ static int nmi_start(void)
 
 static void nmi_cpu_stop(void *dummy)
 {
-	struct op_msrs const *msrs = &cpu_msrs[smp_processor_id()];
+	struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
 	model->stop(msrs);
 }