Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Manually resolve conflict in include/mtd/Kbuild

Signed-off-by: David Woodhouse <dwmw2@infradead.org>

59 files changed, 2878 insertions, 1470 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index d62ec66c1af..aacaafb28b9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -8,7 +8,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
-	    hrtimer.o rwsem.o
+	    hrtimer.o rwsem.o latency.o
 
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
@@ -49,7 +49,7 @@ obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
-obj-$(CONFIG_TASKSTATS) += taskstats.o
+obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/acct.c b/kernel/acct.c
index 2a7c933651c..0aad5ca36a8 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -483,10 +483,14 @@ static void do_acct_process(struct file *file)
 	ac.ac_ppid = current->parent->tgid;
 #endif
 
-	read_lock(&tasklist_lock);	/* pin current->signal */
+	mutex_lock(&tty_mutex);
+	/* FIXME: Whoever is responsible for current->signal locking needs
+	   to use the same locking all over the kernel and document it */
+	read_lock(&tasklist_lock);
 	ac.ac_tty = current->signal->tty ?
 		old_encode_dev(tty_devnum(current->signal->tty)) : 0;
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&tty_mutex);
 
 	spin_lock_irq(&current->sighand->siglock);
 	ac.ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
@@ -598,33 +602,3 @@ void acct_process(void)
 	do_acct_process(file);
 	fput(file);
 }
-
-
-/**
- * acct_update_integrals - update mm integral fields in task_struct
- * @tsk: task_struct for accounting
- */
-void acct_update_integrals(struct task_struct *tsk)
-{
-	if (likely(tsk->mm)) {
-		long delta =
-			cputime_to_jiffies(tsk->stime) - tsk->acct_stimexpd;
-
-		if (delta == 0)
-			return;
-		tsk->acct_stimexpd = tsk->stime;
-		tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
-		tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
-	}
-}
-
-/**
- * acct_clear_integrals - clear the mm integral fields in task_struct
- * @tsk: task_struct whose accounting fields are cleared
- */
-void acct_clear_integrals(struct task_struct *tsk)
-{
-	tsk->acct_stimexpd = 0;
-	tsk->acct_rss_mem1 = 0;
-	tsk->acct_vm_mem1 = 0;
-}
diff --git a/kernel/audit.c b/kernel/audit.c
index 963fd15c962..f9889ee7782 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -244,7 +244,7 @@ static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sid)
 		char *ctx = NULL;
 		u32 len;
 		int rc;
-		if ((rc = selinux_ctxid_to_string(sid, &ctx, &len)))
+		if ((rc = selinux_sid_to_string(sid, &ctx, &len)))
 			return rc;
 		else
 			audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
@@ -267,7 +267,7 @@ static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sid)
 		char *ctx = NULL;
 		u32 len;
 		int rc;
-		if ((rc = selinux_ctxid_to_string(sid, &ctx, &len)))
+		if ((rc = selinux_sid_to_string(sid, &ctx, &len)))
 			return rc;
 		else
 			audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
@@ -293,7 +293,7 @@ static int audit_set_enabled(int state, uid_t loginuid, u32 sid)
 		char *ctx = NULL;
 		u32 len;
 		int rc;
-		if ((rc = selinux_ctxid_to_string(sid, &ctx, &len)))
+		if ((rc = selinux_sid_to_string(sid, &ctx, &len)))
 			return rc;
 		else
 			audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
@@ -321,7 +321,7 @@ static int audit_set_failure(int state, uid_t loginuid, u32 sid)
 		char *ctx = NULL;
 		u32 len;
 		int rc;
-		if ((rc = selinux_ctxid_to_string(sid, &ctx, &len)))
+		if ((rc = selinux_sid_to_string(sid, &ctx, &len)))
 			return rc;
 		else
 			audit_log(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE,
@@ -538,7 +538,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		if (status_get->mask & AUDIT_STATUS_PID) {
 			int old   = audit_pid;
 			if (sid) {
-				if ((err = selinux_ctxid_to_string(
+				if ((err = selinux_sid_to_string(
 						sid, &ctx, &len)))
 					return err;
 				else
@@ -576,7 +576,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 						 "user pid=%d uid=%u auid=%u",
 						 pid, uid, loginuid);
 				if (sid) {
-					if (selinux_ctxid_to_string(
+					if (selinux_sid_to_string(
 							sid, &ctx, &len)) {
 						audit_log_format(ab, 
 							" ssid=%u", sid);
@@ -614,7 +614,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 					   loginuid, sid);
 		break;
 	case AUDIT_SIGNAL_INFO:
-		err = selinux_ctxid_to_string(audit_sig_sid, &ctx, &len);
+		err = selinux_sid_to_string(audit_sig_sid, &ctx, &len);
 		if (err)
 			return err;
 		sig_data = kmalloc(sizeof(*sig_data) + len, GFP_KERNEL);
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a44879b0c72..1a58a81fb09 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -1398,7 +1398,7 @@ static void audit_log_rule_change(uid_t loginuid, u32 sid, char *action,
 	if (sid) {
 		char *ctx = NULL;
 		u32 len;
-		if (selinux_ctxid_to_string(sid, &ctx, &len))
+		if (selinux_sid_to_string(sid, &ctx, &len))
 			audit_log_format(ab, " ssid=%u", sid);
 		else
 			audit_log_format(ab, " subj=%s", ctx);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 1bd8827a010..10514763175 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -385,7 +385,7 @@ static int audit_filter_rules(struct task_struct *tsk,
 			   logged upon error */
 			if (f->se_rule) {
 				if (need_sid) {
-					selinux_task_ctxid(tsk, &sid);
+					selinux_get_task_sid(tsk, &sid);
 					need_sid = 0;
 				}
 				result = selinux_audit_rule_match(sid, f->type,
@@ -817,6 +817,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		audit_log_format(ab, " success=%s exit=%ld", 
 				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
 				 context->return_code);
+
+	mutex_lock(&tty_mutex);
 	if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name)
 		tty = tsk->signal->tty->name;
 	else
@@ -838,6 +840,9 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		  context->gid,
 		  context->euid, context->suid, context->fsuid,
 		  context->egid, context->sgid, context->fsgid, tty);
+
+	mutex_unlock(&tty_mutex);
+
 	audit_log_task_info(ab, tsk);
 	if (context->filterkey) {
 		audit_log_format(ab, " key=");
@@ -898,7 +903,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 			if (axi->osid != 0) {
 				char *ctx = NULL;
 				u32 len;
-				if (selinux_ctxid_to_string(
+				if (selinux_sid_to_string(
 						axi->osid, &ctx, &len)) {
 					audit_log_format(ab, " osid=%u",
 							axi->osid);
@@ -1005,7 +1010,7 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts
 		if (n->osid != 0) {
 			char *ctx = NULL;
 			u32 len;
-			if (selinux_ctxid_to_string(
+			if (selinux_sid_to_string(
 				n->osid, &ctx, &len)) {
 				audit_log_format(ab, " osid=%u", n->osid);
 				call_panic = 2;
diff --git a/kernel/capability.c b/kernel/capability.c
index c7685ad00a9..edb845a6e84 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -133,7 +133,7 @@ static inline int cap_set_all(kernel_cap_t *effective,
      int found = 0;
 
      do_each_thread(g, target) {
-             if (target == current || target->pid == 1)
+             if (target == current || is_init(target))
                      continue;
              found = 1;
 	     if (security_capset_check(target, effective, inheritable,
diff --git a/kernel/compat.c b/kernel/compat.c
index 126dee9530a..b4fbd838cd7 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -22,9 +22,12 @@
 #include <linux/security.h>
 #include <linux/timex.h>
 #include <linux/migrate.h>
+#include <linux/posix-timers.h>
 
 #include <asm/uaccess.h>
 
+extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
+
 int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
@@ -601,6 +604,30 @@ long compat_sys_clock_getres(clockid_t which_clock,
 	return err;
 } 
 
+static long compat_clock_nanosleep_restart(struct restart_block *restart)
+{
+	long err;
+	mm_segment_t oldfs;
+	struct timespec tu;
+	struct compat_timespec *rmtp = (struct compat_timespec *)(restart->arg1);
+
+	restart->arg1 = (unsigned long) &tu;
+	oldfs = get_fs();
+	set_fs(KERNEL_DS);
+	err = clock_nanosleep_restart(restart);
+	set_fs(oldfs);
+
+	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
+	    put_compat_timespec(&tu, rmtp))
+		return -EFAULT;
+
+	if (err == -ERESTART_RESTARTBLOCK) {
+		restart->fn = compat_clock_nanosleep_restart;
+		restart->arg1 = (unsigned long) rmtp;
+	}
+	return err;
+}
+
 long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 			    struct compat_timespec __user *rqtp,
 			    struct compat_timespec __user *rmtp)
@@ -608,6 +635,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 	long err;
 	mm_segment_t oldfs;
 	struct timespec in, out; 
+	struct restart_block *restart;
 
 	if (get_compat_timespec(&in, rqtp)) 
 		return -EFAULT;
@@ -618,9 +646,16 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 				  (struct timespec __user *) &in,
 				  (struct timespec __user *) &out);
 	set_fs(oldfs);
+
 	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
 	    put_compat_timespec(&out, rmtp))
 		return -EFAULT;
+
+	if (err == -ERESTART_RESTARTBLOCK) {
+		restart = &current_thread_info()->restart_block;
+		restart->fn = compat_clock_nanosleep_restart;
+		restart->arg1 = (unsigned long) rmtp;
+	}
 	return err;	
 } 
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index f230f9ae01c..32c96628463 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -21,6 +21,11 @@ static DEFINE_MUTEX(cpu_bitmask_lock);
 
 static __cpuinitdata BLOCKING_NOTIFIER_HEAD(cpu_chain);
 
+/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
+ * Should always be manipulated under cpu_add_remove_lock
+ */
+static int cpu_hotplug_disabled;
+
 #ifdef CONFIG_HOTPLUG_CPU
 
 /* Crappy recursive lock-takers in cpufreq! Complain loudly about idiots */
@@ -108,30 +113,25 @@ static int take_cpu_down(void *unused)
 	return 0;
 }
 
-int cpu_down(unsigned int cpu)
+/* Requires cpu_add_remove_lock to be held */
+static int _cpu_down(unsigned int cpu)
 {
 	int err;
 	struct task_struct *p;
 	cpumask_t old_allowed, tmp;
 
-	mutex_lock(&cpu_add_remove_lock);
-	if (num_online_cpus() == 1) {
-		err = -EBUSY;
-		goto out;
-	}
+	if (num_online_cpus() == 1)
+		return -EBUSY;
 
-	if (!cpu_online(cpu)) {
-		err = -EINVAL;
-		goto out;
-	}
+	if (!cpu_online(cpu))
+		return -EINVAL;
 
 	err = blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
 						(void *)(long)cpu);
 	if (err == NOTIFY_BAD) {
 		printk("%s: attempt to take down CPU %u failed\n",
 				__FUNCTION__, cpu);
-		err = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	/* Ensure that we are not runnable on dying cpu */
@@ -179,22 +179,32 @@ out_thread:
 	err = kthread_stop(p);
 out_allowed:
 	set_cpus_allowed(current, old_allowed);
-out:
+	return err;
+}
+
+int cpu_down(unsigned int cpu)
+{
+	int err = 0;
+
+	mutex_lock(&cpu_add_remove_lock);
+	if (cpu_hotplug_disabled)
+		err = -EBUSY;
+	else
+		err = _cpu_down(cpu);
+
 	mutex_unlock(&cpu_add_remove_lock);
 	return err;
 }
 #endif /*CONFIG_HOTPLUG_CPU*/
 
-int __devinit cpu_up(unsigned int cpu)
+/* Requires cpu_add_remove_lock to be held */
+static int __devinit _cpu_up(unsigned int cpu)
 {
 	int ret;
 	void *hcpu = (void *)(long)cpu;
 
-	mutex_lock(&cpu_add_remove_lock);
-	if (cpu_online(cpu) || !cpu_present(cpu)) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (cpu_online(cpu) || !cpu_present(cpu))
+		return -EINVAL;
 
 	ret = blocking_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
 	if (ret == NOTIFY_BAD) {
@@ -219,7 +229,95 @@ out_notify:
 	if (ret != 0)
 		blocking_notifier_call_chain(&cpu_chain,
 				CPU_UP_CANCELED, hcpu);
+
+	return ret;
+}
+
+int __devinit cpu_up(unsigned int cpu)
+{
+	int err = 0;
+
+	mutex_lock(&cpu_add_remove_lock);
+	if (cpu_hotplug_disabled)
+		err = -EBUSY;
+	else
+		err = _cpu_up(cpu);
+
+	mutex_unlock(&cpu_add_remove_lock);
+	return err;
+}
+
+#ifdef CONFIG_SUSPEND_SMP
+static cpumask_t frozen_cpus;
+
+int disable_nonboot_cpus(void)
+{
+	int cpu, first_cpu, error;
+
+	mutex_lock(&cpu_add_remove_lock);
+	first_cpu = first_cpu(cpu_present_map);
+	if (!cpu_online(first_cpu)) {
+		error = _cpu_up(first_cpu);
+		if (error) {
+			printk(KERN_ERR "Could not bring CPU%d up.\n",
+				first_cpu);
+			goto out;
+		}
+	}
+	error = set_cpus_allowed(current, cpumask_of_cpu(first_cpu));
+	if (error) {
+		printk(KERN_ERR "Could not run on CPU%d\n", first_cpu);
+		goto out;
+	}
+	/* We take down all of the non-boot CPUs in one shot to avoid races
+	 * with the userspace trying to use the CPU hotplug at the same time
+	 */
+	cpus_clear(frozen_cpus);
+	printk("Disabling non-boot CPUs ...\n");
+	for_each_online_cpu(cpu) {
+		if (cpu == first_cpu)
+			continue;
+		error = _cpu_down(cpu);
+		if (!error) {
+			cpu_set(cpu, frozen_cpus);
+			printk("CPU%d is down\n", cpu);
+		} else {
+			printk(KERN_ERR "Error taking CPU%d down: %d\n",
+				cpu, error);
+			break;
+		}
+	}
+	if (!error) {
+		BUG_ON(num_online_cpus() > 1);
+		/* Make sure the CPUs won't be enabled by someone else */
+		cpu_hotplug_disabled = 1;
+	} else {
+		printk(KERN_ERR "Non-boot CPUs are not disabled");
+	}
 out:
 	mutex_unlock(&cpu_add_remove_lock);
-	return ret;
+	return error;
+}
+
+void enable_nonboot_cpus(void)
+{
+	int cpu, error;
+
+	/* Allow everyone to use the CPU hotplug again */
+	mutex_lock(&cpu_add_remove_lock);
+	cpu_hotplug_disabled = 0;
+	mutex_unlock(&cpu_add_remove_lock);
+
+	printk("Enabling non-boot CPUs ...\n");
+	for_each_cpu_mask(cpu, frozen_cpus) {
+		error = cpu_up(cpu);
+		if (!error) {
+			printk("CPU%d is up\n", cpu);
+			continue;
+		}
+		printk(KERN_WARNING "Error taking CPU%d up: %d\n",
+			cpu, error);
+	}
+	cpus_clear(frozen_cpus);
 }
+#endif
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4ea6f0dc2fc..9d850ae13b1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -240,7 +240,7 @@ static struct super_block *cpuset_sb;
  * A cpuset can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cpusets is empty.  Since all
  * tasks in the system use _some_ cpuset, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cpuset
+ * least one task in the system (init), therefore, top_cpuset
  * always has either children cpusets and/or using tasks.  So we don't
  * need a special hack to ensure that top_cpuset cannot be deleted.
  *
@@ -289,7 +289,6 @@ static struct inode *cpuset_new_inode(mode_t mode)
 		inode->i_mode = mode;
 		inode->i_uid = current->fsuid;
 		inode->i_gid = current->fsgid;
-		inode->i_blksize = PAGE_CACHE_SIZE;
 		inode->i_blocks = 0;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info;
@@ -378,7 +377,7 @@ static int cpuset_fill_super(struct super_block *sb, void *unused_data,
 		inode->i_op = &simple_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directories start off with i_nlink == 2 (for "." entry) */
-		inode->i_nlink++;
+		inc_nlink(inode);
 	} else {
 		return -ENOMEM;
 	}
@@ -913,6 +912,10 @@ static int update_nodemask(struct cpuset *cs, char *buf)
 	int fudge;
 	int retval;
 
+	/* top_cpuset.mems_allowed tracks node_online_map; it's read-only */
+	if (cs == &top_cpuset)
+		return -EACCES;
+
 	trialcs = *cs;
 	retval = nodelist_parse(buf, trialcs.mems_allowed);
 	if (retval < 0)
@@ -1222,7 +1225,12 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
 
 	task_lock(tsk);
 	oldcs = tsk->cpuset;
-	if (!oldcs) {
+	/*
+	 * After getting 'oldcs' cpuset ptr, be sure still not exiting.
+	 * If 'oldcs' might be the top_cpuset due to the_top_cpuset_hack
+	 * then fail this attach_task(), to avoid breaking top_cpuset.count.
+	 */
+	if (tsk->flags & PF_EXITING) {
 		task_unlock(tsk);
 		mutex_unlock(&callback_mutex);
 		put_task_struct(tsk);
@@ -1557,7 +1565,7 @@ static int cpuset_create_file(struct dentry *dentry, int mode)
 		inode->i_fop = &simple_dir_operations;
 
 		/* start off with i_nlink == 2 (for "." entry) */
-		inode->i_nlink++;
+		inc_nlink(inode);
 	} else if (S_ISREG(mode)) {
 		inode->i_size = 0;
 		inode->i_fop = &cpuset_file_operations;
@@ -1590,7 +1598,7 @@ static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
 	error = cpuset_create_file(dentry, S_IFDIR | mode);
 	if (!error) {
 		dentry->d_fsdata = cs;
-		parent->d_inode->i_nlink++;
+		inc_nlink(parent->d_inode);
 		cs->dentry = dentry;
 	}
 	dput(dentry);
@@ -2025,7 +2033,7 @@ int __init cpuset_init(void)
 	}
 	root = cpuset_mount->mnt_sb->s_root;
 	root->d_fsdata = &top_cpuset;
-	root->d_inode->i_nlink++;
+	inc_nlink(root->d_inode);
 	top_cpuset.dentry = root;
 	root->d_inode->i_op = &cpuset_dir_inode_operations;
 	number_of_cpusets = 1;
@@ -2037,33 +2045,104 @@ out:
 	return err;
 }
 
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_MEMORY_HOTPLUG)
 /*
- * The top_cpuset tracks what CPUs and Memory Nodes are online,
- * period.  This is necessary in order to make cpusets transparent
- * (of no affect) on systems that are actively using CPU hotplug
- * but making no active use of cpusets.
- *
- * This handles CPU hotplug (cpuhp) events.  If someday Memory
- * Nodes can be hotplugged (dynamically changing node_online_map)
- * then we should handle that too, perhaps in a similar way.
+ * If common_cpu_mem_hotplug_unplug(), below, unplugs any CPUs
+ * or memory nodes, we need to walk over the cpuset hierarchy,
+ * removing that CPU or node from all cpusets.  If this removes the
+ * last CPU or node from a cpuset, then the guarantee_online_cpus()
+ * or guarantee_online_mems() code will use that emptied cpusets
+ * parent online CPUs or nodes.  Cpusets that were already empty of
+ * CPUs or nodes are left empty.
+ *
+ * This routine is intentionally inefficient in a couple of regards.
+ * It will check all cpusets in a subtree even if the top cpuset of
+ * the subtree has no offline CPUs or nodes.  It checks both CPUs and
+ * nodes, even though the caller could have been coded to know that
+ * only one of CPUs or nodes needed to be checked on a given call.
+ * This was done to minimize text size rather than cpu cycles.
+ *
+ * Call with both manage_mutex and callback_mutex held.
+ *
+ * Recursive, on depth of cpuset subtree.
  */
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int cpuset_handle_cpuhp(struct notifier_block *nb,
-				unsigned long phase, void *cpu)
+static void guarantee_online_cpus_mems_in_subtree(const struct cpuset *cur)
+{
+	struct cpuset *c;
+
+	/* Each of our child cpusets mems must be online */
+	list_for_each_entry(c, &cur->children, sibling) {
+		guarantee_online_cpus_mems_in_subtree(c);
+		if (!cpus_empty(c->cpus_allowed))
+			guarantee_online_cpus(c, &c->cpus_allowed);
+		if (!nodes_empty(c->mems_allowed))
+			guarantee_online_mems(c, &c->mems_allowed);
+	}
+}
+
+/*
+ * The cpus_allowed and mems_allowed nodemasks in the top_cpuset track
+ * cpu_online_map and node_online_map.  Force the top cpuset to track