Merge branch 'cpus4096-for-linus-3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'cpus4096-for-linus-3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (77 commits)
  x86: setup_per_cpu_areas() cleanup
  cpumask: fix compile error when CONFIG_NR_CPUS is not defined
  cpumask: use alloc_cpumask_var_node where appropriate
  cpumask: convert shared_cpu_map in acpi_processor* structs to cpumask_var_t
  x86: use cpumask_var_t in acpi/boot.c
  x86: cleanup some remaining usages of NR_CPUS where s/b nr_cpu_ids
  sched: put back some stack hog changes that were undone in kernel/sched.c
  x86: enable cpus display of kernel_max and offlined cpus
  ia64: cpumask fix for is_affinity_mask_valid()
  cpumask: convert RCU implementations, fix
  xtensa: define __fls
  mn10300: define __fls
  m32r: define __fls
  h8300: define __fls
  frv: define __fls
  cris: define __fls
  cpumask: CONFIG_DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
  cpumask: zero extra bits in alloc_cpumask_var_node
  cpumask: replace for_each_cpu_mask_nr with for_each_cpu in kernel/time/
  cpumask: convert mm/
  ...

7 files changed, 135 insertions, 58 deletions

diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 34948362f41..0cc2fd31e37 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -826,6 +826,11 @@ static int acpi_processor_add(struct acpi_device *device)
 	if (!pr)
 		return -ENOMEM;
 
+	if (!alloc_cpumask_var(&pr->throttling.shared_cpu_map, GFP_KERNEL)) {
+		kfree(pr);
+		return -ENOMEM;
+	}
+
 	pr->handle = device->handle;
 	strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
@@ -845,10 +850,8 @@ static int acpi_processor_remove(struct acpi_device *device, int type)
 
 	pr = acpi_driver_data(device);
 
-	if (pr->id >= nr_cpu_ids) {
-		kfree(pr);
-		return 0;
-	}
+	if (pr->id >= nr_cpu_ids)
+		goto free;
 
 	if (type == ACPI_BUS_REMOVAL_EJECT) {
 		if (acpi_processor_handle_eject(pr))
@@ -873,6 +876,9 @@ static int acpi_processor_remove(struct acpi_device *device, int type)
 
 	per_cpu(processors, pr->id) = NULL;
 	per_cpu(processor_device_array, pr->id) = NULL;
+
+free:
+	free_cpumask_var(pr->throttling.shared_cpu_map);
 	kfree(pr);
 
 	return 0;
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 0d7b772bef5..846e227592d 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -588,12 +588,15 @@ int acpi_processor_preregister_performance(
 	int count, count_target;
 	int retval = 0;
 	unsigned int i, j;
-	cpumask_t covered_cpus;
+	cpumask_var_t covered_cpus;
 	struct acpi_processor *pr;
 	struct acpi_psd_package *pdomain;
 	struct acpi_processor *match_pr;
 	struct acpi_psd_package *match_pdomain;
 
+	if (!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))
+		return -ENOMEM;
+
 	mutex_lock(&performance_mutex);
 
 	retval = 0;
@@ -617,7 +620,7 @@ int acpi_processor_preregister_performance(
 		}
 
 		pr->performance = percpu_ptr(performance, i);
-		cpu_set(i, pr->performance->shared_cpu_map);
+		cpumask_set_cpu(i, pr->performance->shared_cpu_map);
 		if (acpi_processor_get_psd(pr)) {
 			retval = -EINVAL;
 			continue;
@@ -650,18 +653,18 @@ int acpi_processor_preregister_performance(
 		}
 	}
 
-	cpus_clear(covered_cpus);
+	cpumask_clear(covered_cpus);
 	for_each_possible_cpu(i) {
 		pr = per_cpu(processors, i);
 		if (!pr)
 			continue;
 
-		if (cpu_isset(i, covered_cpus))
+		if (cpumask_test_cpu(i, covered_cpus))
 			continue;
 
 		pdomain = &(pr->performance->domain_info);
-		cpu_set(i, pr->performance->shared_cpu_map);
-		cpu_set(i, covered_cpus);
+		cpumask_set_cpu(i, pr->performance->shared_cpu_map);
+		cpumask_set_cpu(i, covered_cpus);
 		if (pdomain->num_processors <= 1)
 			continue;
 
@@ -699,8 +702,8 @@ int acpi_processor_preregister_performance(
 				goto err_ret;
 			}
 
-			cpu_set(j, covered_cpus);
-			cpu_set(j, pr->performance->shared_cpu_map);
+			cpumask_set_cpu(j, covered_cpus);
+			cpumask_set_cpu(j, pr->performance->shared_cpu_map);
 			count++;
 		}
 
@@ -718,8 +721,8 @@ int acpi_processor_preregister_performance(
 
 			match_pr->performance->shared_type = 
 					pr->performance->shared_type;
-			match_pr->performance->shared_cpu_map =
-				pr->performance->shared_cpu_map;
+			cpumask_copy(match_pr->performance->shared_cpu_map,
+				     pr->performance->shared_cpu_map);
 		}
 	}
 
@@ -731,14 +734,15 @@ err_ret:
 
 		/* Assume no coordination on any error parsing domain info */
 		if (retval) {
-			cpus_clear(pr->performance->shared_cpu_map);
-			cpu_set(i, pr->performance->shared_cpu_map);
+			cpumask_clear(pr->performance->shared_cpu_map);
+			cpumask_set_cpu(i, pr->performance->shared_cpu_map);
 			pr->performance->shared_type = CPUFREQ_SHARED_TYPE_ALL;
 		}
 		pr->performance = NULL; /* Will be set for real in register */
 	}
 
 	mutex_unlock(&performance_mutex);
+	free_cpumask_var(covered_cpus);
 	return retval;
 }
 EXPORT_SYMBOL(acpi_processor_preregister_performance);
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index a0c38c94a8a..d27838171f4 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -61,11 +61,14 @@ static int acpi_processor_update_tsd_coord(void)
 	int count, count_target;
 	int retval = 0;
 	unsigned int i, j;
-	cpumask_t covered_cpus;
+	cpumask_var_t covered_cpus;
 	struct acpi_processor *pr, *match_pr;
 	struct acpi_tsd_package *pdomain, *match_pdomain;
 	struct acpi_processor_throttling *pthrottling, *match_pthrottling;
 
+	if (!alloc_cpumask_var(&covered_cpus, GFP_KERNEL))
+		return -ENOMEM;
+
 	/*
 	 * Now that we have _TSD data from all CPUs, lets setup T-state
 	 * coordination between all CPUs.
@@ -91,19 +94,19 @@ static int acpi_processor_update_tsd_coord(void)
 	if (retval)
 		goto err_ret;
 
-	cpus_clear(covered_cpus);
+	cpumask_clear(covered_cpus);
 	for_each_possible_cpu(i) {
 		pr = per_cpu(processors, i);
 		if (!pr)
 			continue;
 
-		if (cpu_isset(i, covered_cpus))
+		if (cpumask_test_cpu(i, covered_cpus))
 			continue;
 		pthrottling = &pr->throttling;
 
 		pdomain = &(pthrottling->domain_info);
-		cpu_set(i, pthrottling->shared_cpu_map);
-		cpu_set(i, covered_cpus);
+		cpumask_set_cpu(i, pthrottling->shared_cpu_map);
+		cpumask_set_cpu(i, covered_cpus);
 		/*
 		 * If the number of processor in the TSD domain is 1, it is
 		 * unnecessary to parse the coordination for this CPU.
@@ -144,8 +147,8 @@ static int acpi_processor_update_tsd_coord(void)
 				goto err_ret;
 			}
 
-			cpu_set(j, covered_cpus);
-			cpu_set(j, pthrottling->shared_cpu_map);
+			cpumask_set_cpu(j, covered_cpus);
+			cpumask_set_cpu(j, pthrottling->shared_cpu_map);
 			count++;
 		}
 		for_each_possible_cpu(j) {
@@ -165,12 +168,14 @@ static int acpi_processor_update_tsd_coord(void)
 			 * If some CPUS have the same domain, they
 			 * will have the same shared_cpu_map.
 			 */
-			match_pthrottling->shared_cpu_map =
-				pthrottling->shared_cpu_map;
+			cpumask_copy(match_pthrottling->shared_cpu_map,
+				     pthrottling->shared_cpu_map);
 		}
 	}
 
 err_ret:
+	free_cpumask_var(covered_cpus);
+
 	for_each_possible_cpu(i) {
 		pr = per_cpu(processors, i);
 		if (!pr)
@@ -182,8 +187,8 @@ err_ret:
 		 */
 		if (retval) {
 			pthrottling = &(pr->throttling);
-			cpus_clear(pthrottling->shared_cpu_map);
-			cpu_set(i, pthrottling->shared_cpu_map);
+			cpumask_clear(pthrottling->shared_cpu_map);
+			cpumask_set_cpu(i, pthrottling->shared_cpu_map);
 			pthrottling->shared_type = DOMAIN_COORD_TYPE_SW_ALL;
 		}
 	}
@@ -567,7 +572,7 @@ static int acpi_processor_get_tsd(struct acpi_processor *pr)
 	pthrottling = &pr->throttling;
 	pthrottling->tsd_valid_flag = 1;
 	pthrottling->shared_type = pdomain->coord_type;
-	cpu_set(pr->id, pthrottling->shared_cpu_map);
+	cpumask_set_cpu(pr->id, pthrottling->shared_cpu_map);
 	/*
 	 * If the coordination type is not defined in ACPI spec,
 	 * the tsd_valid_flag will be clear and coordination type
@@ -826,7 +831,7 @@ static int acpi_processor_get_throttling_ptc(struct acpi_processor *pr)
 
 static int acpi_processor_get_throttling(struct acpi_processor *pr)
 {
-	cpumask_t saved_mask;
+	cpumask_var_t saved_mask;
 	int ret;
 
 	if (!pr)
@@ -834,14 +839,20 @@ static int acpi_processor_get_throttling(struct acpi_processor *pr)
 
 	if (!pr->flags.throttling)
 		return -ENODEV;
+
+	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	/*
 	 * Migrate task to the cpu pointed by pr.
 	 */
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pr->id));
+	cpumask_copy(saved_mask, &current->cpus_allowed);
+	/* FIXME: use work_on_cpu() */
+	set_cpus_allowed_ptr(current, cpumask_of(pr->id));
 	ret = pr->throttling.acpi_processor_get_throttling(pr);
 	/* restore the previous state */
-	set_cpus_allowed_ptr(current, &saved_mask);
+	set_cpus_allowed_ptr(current, saved_mask);
+	free_cpumask_var(saved_mask);
 
 	return ret;
 }
@@ -986,13 +997,13 @@ static int acpi_processor_set_throttling_ptc(struct acpi_processor *pr,
 
 int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 {
-	cpumask_t saved_mask;
+	cpumask_var_t saved_mask;
 	int ret = 0;
 	unsigned int i;
 	struct acpi_processor *match_pr;
 	struct acpi_processor_throttling *p_throttling;
 	struct throttling_tstate t_state;
-	cpumask_t online_throttling_cpus;
+	cpumask_var_t online_throttling_cpus;
 
 	if (!pr)
 		return -EINVAL;
@@ -1003,17 +1014,25 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 	if ((state < 0) || (state > (pr->throttling.state_count - 1)))
 		return -EINVAL;
 
-	saved_mask = current->cpus_allowed;
+	if (!alloc_cpumask_var(&saved_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (!alloc_cpumask_var(&online_throttling_cpus, GFP_KERNEL)) {
+		free_cpumask_var(saved_mask);
+		return -ENOMEM;
+	}
+
+	cpumask_copy(saved_mask, &current->cpus_allowed);
 	t_state.target_state = state;
 	p_throttling = &(pr->throttling);
-	cpus_and(online_throttling_cpus, cpu_online_map,
-			p_throttling->shared_cpu_map);
+	cpumask_and(online_throttling_cpus, cpu_online_mask,
+		    p_throttling->shared_cpu_map);
 	/*
 	 * The throttling notifier will be called for every
 	 * affected cpu in order to get one proper T-state.
 	 * The notifier event is THROTTLING_PRECHANGE.
 	 */
-	for_each_cpu_mask_nr(i, online_throttling_cpus) {
+	for_each_cpu(i, online_throttling_cpus) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_PRECHANGE,
 							&t_state);
@@ -1025,7 +1044,8 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 	 * it can be called only for the cpu pointed by pr.
 	 */
 	if (p_throttling->shared_type == DOMAIN_COORD_TYPE_SW_ANY) {
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(pr->id));
+		/* FIXME: use work_on_cpu() */
+		set_cpus_allowed_ptr(current, cpumask_of(pr->id));
 		ret = p_throttling->acpi_processor_set_throttling(pr,
 						t_state.target_state);
 	} else {
@@ -1034,7 +1054,7 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 		 * it is necessary to set T-state for every affected
 		 * cpus.
 		 */
-		for_each_cpu_mask_nr(i, online_throttling_cpus) {
+		for_each_cpu(i, online_throttling_cpus) {
 			match_pr = per_cpu(processors, i);
 			/*
 			 * If the pointer is invalid, we will report the
@@ -1056,7 +1076,8 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 				continue;
 			}
 			t_state.cpu = i;
-			set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
+			/* FIXME: use work_on_cpu() */
+			set_cpus_allowed_ptr(current, cpumask_of(i));
 			ret = match_pr->throttling.
 				acpi_processor_set_throttling(
 				match_pr, t_state.target_state);
@@ -1068,13 +1089,16 @@ int acpi_processor_set_throttling(struct acpi_processor *pr, int state)
 	 * affected cpu to update the T-states.
 	 * The notifier event is THROTTLING_POSTCHANGE
 	 */
-	for_each_cpu_mask_nr(i, online_throttling_cpus) {
+	for_each_cpu(i, online_throttling_cpus) {
 		t_state.cpu = i;
 		acpi_processor_throttling_notifier(THROTTLING_POSTCHANGE,
 							&t_state);
 	}
 	/* restore the previous state */
-	set_cpus_allowed_ptr(current, &saved_mask);
+	/* FIXME: use work_on_cpu() */
+	set_cpus_allowed_ptr(current, saved_mask);
+	free_cpumask_var(online_throttling_cpus);
+	free_cpumask_var(saved_mask);
 	return ret;
 }
 
@@ -1120,7 +1144,7 @@ int acpi_processor_get_throttling_info(struct acpi_processor *pr)
 	if (acpi_processor_get_tsd(pr)) {
 		pthrottling = &pr->throttling;
 		pthrottling->tsd_valid_flag = 0;
-		cpu_set(pr->id, pthrottling->shared_cpu_map);
+		cpumask_set_cpu(pr->id, pthrottling->shared_cpu_map);
 		pthrottling->shared_type = DOMAIN_COORD_TYPE_SW_ALL;
 	}
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4259072f5bd..719ee5c1c8d 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -128,10 +128,54 @@ print_cpus_func(online);
 print_cpus_func(possible);
 print_cpus_func(present);
 
+/*
+ * Print values for NR_CPUS and offlined cpus
+ */
+static ssize_t print_cpus_kernel_max(struct sysdev_class *class, char *buf)
+{
+	int n = snprintf(buf, PAGE_SIZE-2, "%d\n", NR_CPUS - 1);
+	return n;
+}
+static SYSDEV_CLASS_ATTR(kernel_max, 0444, print_cpus_kernel_max, NULL);
+
+/* arch-optional setting to enable display of offline cpus >= nr_cpu_ids */
+unsigned int total_cpus;
+
+static ssize_t print_cpus_offline(struct sysdev_class *class, char *buf)
+{
+	int n = 0, len = PAGE_SIZE-2;
+	cpumask_var_t offline;
+
+	/* display offline cpus < nr_cpu_ids */
+	if (!alloc_cpumask_var(&offline, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_complement(offline, cpu_online_mask);
+	n = cpulist_scnprintf(buf, len, offline);
+	free_cpumask_var(offline);
+
+	/* display offline cpus >= nr_cpu_ids */
+	if (total_cpus && nr_cpu_ids < total_cpus) {
+		if (n && n < len)
+			buf[n++] = ',';
+
+		if (nr_cpu_ids == total_cpus-1)
+			n += snprintf(&buf[n], len - n, "%d", nr_cpu_ids);
+		else
+			n += snprintf(&buf[n], len - n, "%d-%d",
+						      nr_cpu_ids, total_cpus-1);
+	}
+
+	n += snprintf(&buf[n], len - n, "\n");
+	return n;
+}
+static SYSDEV_CLASS_ATTR(offline, 0444, print_cpus_offline, NULL);
+
 static struct sysdev_class_attribute *cpu_state_attr[] = {
 	&attr_online_map,
 	&attr_possible_map,
 	&attr_present_map,
+	&attr_kernel_max,
+	&attr_offline,
 };
 
 static int cpu_states_init(void)
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index 757035ea246..3128a5090db 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -659,12 +659,12 @@ static inline int find_next_online_cpu(struct ehca_comp_pool *pool)
 
 	WARN_ON_ONCE(!in_interrupt());
 	if (ehca_debug_level >= 3)
-		ehca_dmp(&cpu_online_map, sizeof(cpumask_t), "");
+		ehca_dmp(cpu_online_mask, cpumask_size(), "");
 
 	spin_lock_irqsave(&pool->last_cpu_lock, flags);
-	cpu = next_cpu_nr(pool->last_cpu, cpu_online_map);
+	cpu = cpumask_next(pool->last_cpu, cpu_online_mask);
 	if (cpu >= nr_cpu_ids)
-		cpu = first_cpu(cpu_online_map);
+		cpu = cpumask_first(cpu_online_mask);
 	pool->last_cpu = cpu;
 	spin_unlock_irqrestore(&pool->last_cpu_lock, flags);
 
@@ -855,7 +855,7 @@ static int __cpuinit comp_pool_callback(struct notifier_block *nfb,
 	case CPU_UP_CANCELED_FROZEN:
 		ehca_gen_dbg("CPU: %x (CPU_CANCELED)", cpu);
 		cct = per_cpu_ptr(pool->cpu_comp_tasks, cpu);
-		kthread_bind(cct->task, any_online_cpu(cpu_online_map));
+		kthread_bind(cct->task, cpumask_any(cpu_online_mask));
 		destroy_comp_task(pool, cpu);
 		break;
 	case CPU_ONLINE:
@@ -902,7 +902,7 @@ int ehca_create_comp_pool(void)
 		return -ENOMEM;
 
 	spin_lock_init(&pool->last_cpu_lock);
-	pool->last_cpu = any_online_cpu(cpu_online_map);
+	pool->last_cpu = cpumask_any(cpu_online_mask);
 
 	pool->cpu_comp_tasks = alloc_percpu(struct ehca_cpu_comp_task);
 	if (pool->cpu_comp_tasks == NULL) {
@@ -934,10 +934,9 @@ void ehca_destroy_comp_pool(void)
 
 	unregister_hotcpu_notifier(&comp_pool_callback_nb);
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_online(i))
-			destroy_comp_task(pool, i);
-	}
+	for_each_online_cpu(i)
+		destroy_comp_task(pool, i);
+
 	free_percpu(pool->cpu_comp_tasks);
 	kfree(pool);
 }
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index 239d4e8068a..23173982b32 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -1679,7 +1679,7 @@ static int find_best_unit(struct file *fp,
 	 * InfiniPath chip to that processor (we assume reasonable connectivity,
 	 * for now).  This code assumes that if affinity has been set
 	 * before this point, that at most one cpu is set; for now this
-	 * is reasonable.  I check for both cpus_empty() and cpus_full(),
+	 * is reasonable.  I check for both cpumask_empty() and cpumask_full(),
 	 * in case some kernel variant sets none of the bits when no
 	 * affinity is set.  2.6.11 and 12 kernels have all present
 	 * cpus set.  Some day we'll have to fix it up further to handle
@@ -1688,11 +1688,11 @@ static int find_best_unit(struct file *fp,
 	 * information.  There may be some issues with dual core numbering
 	 * as well.  This needs more work prior to release.
 	 */
-	if (!cpus_empty(current->cpus_allowed) &&
-	    !cpus_full(current->cpus_allowed)) {
+	if (!cpumask_empty(&current->cpus_allowed) &&
+	    !cpumask_full(&current->cpus_allowed)) {
 		int ncpus = num_online_cpus(), curcpu = -1, nset = 0;
 		for (i = 0; i < ncpus; i++)
-			if (cpu_isset(i, current->cpus_allowed)) {
+			if (cpumask_test_cpu(i, &current->cpus_allowed)) {
 				ipath_cdbg(PROC, "%s[%u] affinity set for "
 					   "cpu %d/%d\n", current->comm,
 					   current->pid, i, ncpus);
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index 7ff824496b3..7e6b5a3b328 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -481,7 +481,7 @@ void pnpbios_calls_init(union pnp_bios_install_struct *header)
 
 	set_base(bad_bios_desc, __va((unsigned long)0x40 << 4));
 	_set_limit((char *)&bad_bios_desc, 4095 - (0x40 << 4));
-	for (i = 0; i < NR_CPUS; i++) {
+	for_each_possible_cpu(i) {
 		struct desc_struct *gdt = get_cpu_gdt_table(i);
 		if (!gdt)
 			continue;