X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fcpu.c;h=2eff3f63abed6c91c2bbcb1c8d0eccbb97d54c7d;hb=0c11b4de5d81771ba0fdc8a5d13d59ed01d41252;hp=27dd3ee47099dd49c26790adf40b42efa1b950a3;hpb=bd5349cfd2b9bbb10a3dbcd3fe5cbaabe0b2ab9e;p=safe%2Fjmp%2Flinux-2.6

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 27dd3ee..2eff3f6 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -15,9 +15,8 @@
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
 
-/* This protects CPUs going up and down... */
+/* Serializes the updates to cpu_online_map, cpu_present_map */
 static DEFINE_MUTEX(cpu_add_remove_lock);
-static DEFINE_MUTEX(cpu_bitmask_lock);
 
 static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
 
@@ -26,52 +25,123 @@ static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
  */
 static int cpu_hotplug_disabled;
 
-#ifdef CONFIG_HOTPLUG_CPU
+static struct {
+	struct task_struct *active_writer;
+	struct mutex lock; /* Synchronizes accesses to refcount, */
+	/*
+	 * Also blocks the new readers during
+	 * an ongoing cpu hotplug operation.
+	 */
+	int refcount;
+	wait_queue_head_t writer_queue;
+} cpu_hotplug;
 
-/* Crappy recursive lock-takers in cpufreq! Complain loudly about idiots */
-static struct task_struct *recursive;
-static int recursive_depth;
+#define writer_exists() (cpu_hotplug.active_writer != NULL)
 
-void lock_cpu_hotplug(void)
+void __init cpu_hotplug_init(void)
 {
-	struct task_struct *tsk = current;
-
-	if (tsk == recursive) {
-		static int warnings = 10;
-		if (warnings) {
-			printk(KERN_ERR "Lukewarm IQ detected in hotplug locking\n");
-			WARN_ON(1);
-			warnings--;
-		}
-		recursive_depth++;
+	cpu_hotplug.active_writer = NULL;
+	mutex_init(&cpu_hotplug.lock);
+	cpu_hotplug.refcount = 0;
+	init_waitqueue_head(&cpu_hotplug.writer_queue);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+void get_online_cpus(void)
+{
+	might_sleep();
+	if (cpu_hotplug.active_writer == current)
 		return;
-	}
-	mutex_lock(&cpu_bitmask_lock);
-	recursive = tsk;
+	mutex_lock(&cpu_hotplug.lock);
+	cpu_hotplug.refcount++;
+	mutex_unlock(&cpu_hotplug.lock);
+
 }
-EXPORT_SYMBOL_GPL(lock_cpu_hotplug);
+EXPORT_SYMBOL_GPL(get_online_cpus);
 
-void unlock_cpu_hotplug(void)
+void put_online_cpus(void)
 {
-	WARN_ON(recursive != current);
-	if (recursive_depth) {
-		recursive_depth--;
+	if (cpu_hotplug.active_writer == current)
 		return;
-	}
-	mutex_unlock(&cpu_bitmask_lock);
-	recursive = NULL;
+	mutex_lock(&cpu_hotplug.lock);
+	cpu_hotplug.refcount--;
+
+	if (unlikely(writer_exists()) && !cpu_hotplug.refcount)
+		wake_up(&cpu_hotplug.writer_queue);
+
+	mutex_unlock(&cpu_hotplug.lock);
+
 }
-EXPORT_SYMBOL_GPL(unlock_cpu_hotplug);
+EXPORT_SYMBOL_GPL(put_online_cpus);
 
 #endif	/* CONFIG_HOTPLUG_CPU */
 
+/*
+ * The following two API's must be used when attempting
+ * to serialize the updates to cpu_online_map, cpu_present_map.
+ */
+void cpu_maps_update_begin(void)
+{
+	mutex_lock(&cpu_add_remove_lock);
+}
+
+void cpu_maps_update_done(void)
+{
+	mutex_unlock(&cpu_add_remove_lock);
+}
+
+/*
+ * This ensures that the hotplug operation can begin only when the
+ * refcount goes to zero.
+ *
+ * Note that during a cpu-hotplug operation, the new readers, if any,
+ * will be blocked by the cpu_hotplug.lock
+ *
+ * Since cpu_maps_update_begin is always called after invoking
+ * cpu_maps_update_begin, we can be sure that only one writer is active.
+ *
+ * Note that theoretically, there is a possibility of a livelock:
+ * - Refcount goes to zero, last reader wakes up the sleeping
+ *   writer.
+ * - Last reader unlocks the cpu_hotplug.lock.
+ * - A new reader arrives at this moment, bumps up the refcount.
+ * - The writer acquires the cpu_hotplug.lock finds the refcount
+ *   non zero and goes to sleep again.
+ *
+ * However, this is very difficult to achieve in practice since
+ * get_online_cpus() not an api which is called all that often.
+ *
+ */
+static void cpu_hotplug_begin(void)
+{
+	DECLARE_WAITQUEUE(wait, current);
+
+	mutex_lock(&cpu_hotplug.lock);
+
+	cpu_hotplug.active_writer = current;
+	add_wait_queue_exclusive(&cpu_hotplug.writer_queue, &wait);
+	while (cpu_hotplug.refcount) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		mutex_unlock(&cpu_hotplug.lock);
+		schedule();
+		mutex_lock(&cpu_hotplug.lock);
+	}
+	remove_wait_queue_locked(&cpu_hotplug.writer_queue, &wait);
+}
+
+static void cpu_hotplug_done(void)
+{
+	cpu_hotplug.active_writer = NULL;
+	mutex_unlock(&cpu_hotplug.lock);
+}
 /* Need to know about CPUs going up/down? */
 int __cpuinit register_cpu_notifier(struct notifier_block *nb)
 {
 	int ret;
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	ret = raw_notifier_chain_register(&cpu_chain, nb);
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 	return ret;
 }
 
@@ -81,9 +151,9 @@ EXPORT_SYMBOL(register_cpu_notifier);
 
 void unregister_cpu_notifier(struct notifier_block *nb)
 {
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	raw_notifier_chain_unregister(&cpu_chain, nb);
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 }
 EXPORT_SYMBOL(unregister_cpu_notifier);
 
@@ -97,17 +167,26 @@ static inline void check_for_tasks(int cpu)
 		    (!cputime_eq(p->utime, cputime_zero) ||
 		     !cputime_eq(p->stime, cputime_zero)))
 			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\
-				(state = %ld, flags = %lx) \n",
-				 p->comm, p->pid, cpu, p->state, p->flags);
+				(state = %ld, flags = %x) \n",
+				 p->comm, task_pid_nr(p), cpu,
+				 p->state, p->flags);
 	}
 	write_unlock_irq(&tasklist_lock);
 }
 
+struct take_cpu_down_param {
+	unsigned long mod;
+	void *hcpu;
+};
+
 /* Take this CPU down. */
-static int take_cpu_down(void *unused)
+static int take_cpu_down(void *_param)
 {
+	struct take_cpu_down_param *param = _param;
 	int err;
 
+	raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+				param->hcpu);
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
 	if (err < 0)
@@ -120,11 +199,17 @@ static int take_cpu_down(void *unused)
 }
 
 /* Requires cpu_add_remove_lock to be held */
-static int _cpu_down(unsigned int cpu)
+static int _cpu_down(unsigned int cpu, int tasks_frozen)
 {
-	int err;
+	int err, nr_calls = 0;
 	struct task_struct *p;
 	cpumask_t old_allowed, tmp;
+	void *hcpu = (void *)(long)cpu;
+	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+	struct take_cpu_down_param tcd_param = {
+		.mod = mod,
+		.hcpu = hcpu,
+	};
 
 	if (num_online_cpus() == 1)
 		return -EBUSY;
@@ -132,12 +217,17 @@ static int _cpu_down(unsigned int cpu)
 	if (!cpu_online(cpu))
 		return -EINVAL;
 
-	err = raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
-						(void *)(long)cpu);
+	cpu_hotplug_begin();
+	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
+					hcpu, -1, &nr_calls);
 	if (err == NOTIFY_BAD) {
+		nr_calls--;
+		__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
+					  hcpu, nr_calls, NULL);
 		printk("%s: attempt to take down CPU %u failed\n",
 				__FUNCTION__, cpu);
-		return -EINVAL;
+		err = -EINVAL;
+		goto out_release;
 	}
 
 	/* Ensure that we are not runnable on dying cpu */
@@ -146,22 +236,20 @@ static int _cpu_down(unsigned int cpu)
 	cpu_clear(cpu, tmp);
 	set_cpus_allowed(current, tmp);
 
-	mutex_lock(&cpu_bitmask_lock);
-	p = __stop_machine_run(take_cpu_down, NULL, cpu);
-	mutex_unlock(&cpu_bitmask_lock);
+	p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
 
-	if (IS_ERR(p)) {
+	if (IS_ERR(p) || cpu_online(cpu)) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
-		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
-				(void *)(long)cpu) == NOTIFY_BAD)
+		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
+					    hcpu) == NOTIFY_BAD)
 			BUG();
 
-		err = PTR_ERR(p);
-		goto out_allowed;
-	}
-
-	if (cpu_online(cpu))
+		if (IS_ERR(p)) {
+			err = PTR_ERR(p);
+			goto out_allowed;
+		}
 		goto out_thread;
+	}
 
 	/* Wait for it to sleep (leaving idle task). */
 	while (!idle_cpu(cpu))
@@ -170,13 +258,9 @@ static int _cpu_down(unsigned int cpu)
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
 
-	/* Move it here so it can run. */
-	kthread_bind(p, get_cpu());
-	put_cpu();
-
 	/* CPU is completely dead: tell everyone.  Too late to complain. */
-	if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD,
-			(void *)(long)cpu) == NOTIFY_BAD)
+	if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD | mod,
+				    hcpu) == NOTIFY_BAD)
 		BUG();
 
 	check_for_tasks(cpu);
@@ -185,6 +269,8 @@ out_thread:
 	err = kthread_stop(p);
 out_allowed:
 	set_cpus_allowed(current, old_allowed);
+out_release:
+	cpu_hotplug_done();
 	return err;
 }
 
@@ -192,28 +278,32 @@ int cpu_down(unsigned int cpu)
 {
 	int err = 0;
 
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	if (cpu_hotplug_disabled)
 		err = -EBUSY;
 	else
-		err = _cpu_down(cpu);
+		err = _cpu_down(cpu, 0);
 
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 	return err;
 }
 #endif /*CONFIG_HOTPLUG_CPU*/
 
 /* Requires cpu_add_remove_lock to be held */
-static int __devinit _cpu_up(unsigned int cpu)
+static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 {
-	int ret;
+	int ret, nr_calls = 0;
 	void *hcpu = (void *)(long)cpu;
+	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 
 	if (cpu_online(cpu) || !cpu_present(cpu))
 		return -EINVAL;
 
-	ret = raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
+	cpu_hotplug_begin();
+	ret = __raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE | mod, hcpu,
+							-1, &nr_calls);
 	if (ret == NOTIFY_BAD) {
+		nr_calls--;
 		printk("%s: attempt to bring up CPU %u failed\n",
 				__FUNCTION__, cpu);
 		ret = -EINVAL;
@@ -221,60 +311,55 @@ static int __devinit _cpu_up(unsigned int cpu)
 	}
 
 	/* Arch-specific enabling code. */
-	mutex_lock(&cpu_bitmask_lock);
 	ret = __cpu_up(cpu);
-	mutex_unlock(&cpu_bitmask_lock);
 	if (ret != 0)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
 	/* Now call notifier in preparation. */
-	raw_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
+	raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
 
 out_notify:
 	if (ret != 0)
-		raw_notifier_call_chain(&cpu_chain,
-				CPU_UP_CANCELED, hcpu);
+		__raw_notifier_call_chain(&cpu_chain,
+				CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
+	cpu_hotplug_done();
 
 	return ret;
 }
 
-int __devinit cpu_up(unsigned int cpu)
+int __cpuinit cpu_up(unsigned int cpu)
 {
 	int err = 0;
+	if (!cpu_isset(cpu, cpu_possible_map)) {
+		printk(KERN_ERR "can't online cpu %d because it is not "
+			"configured as may-hotadd at boot time\n", cpu);
+#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) || defined(CONFIG_S390)
+		printk(KERN_ERR "please check additional_cpus= boot "
+				"parameter\n");
+#endif
+		return -EINVAL;
+	}
 
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	if (cpu_hotplug_disabled)
 		err = -EBUSY;
 	else
-		err = _cpu_up(cpu);
+		err = _cpu_up(cpu, 0);
 
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 	return err;
 }
 
-#ifdef CONFIG_SUSPEND_SMP
+#ifdef CONFIG_PM_SLEEP_SMP
 static cpumask_t frozen_cpus;
 
 int disable_nonboot_cpus(void)
 {
-	int cpu, first_cpu, error;
+	int cpu, first_cpu, error = 0;
 
-	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;
-	}
+	cpu_maps_update_begin();
+	first_cpu = first_cpu(cpu_online_map);
 	/* 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
 	 */
@@ -283,7 +368,7 @@ int disable_nonboot_cpus(void)
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
 			continue;
-		error = _cpu_down(cpu);
+		error = _cpu_down(cpu, 1);
 		if (!error) {
 			cpu_set(cpu, frozen_cpus);
 			printk("CPU%d is down\n", cpu);
@@ -298,32 +383,33 @@ int disable_nonboot_cpus(void)
 		/* 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");
+		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
 	}
-out:
-	mutex_unlock(&cpu_add_remove_lock);
+	cpu_maps_update_done();
 	return error;
 }
 
-void enable_nonboot_cpus(void)
+void __ref enable_nonboot_cpus(void)
 {
 	int cpu, error;
 
 	/* Allow everyone to use the CPU hotplug again */
-	mutex_lock(&cpu_add_remove_lock);
+	cpu_maps_update_begin();
 	cpu_hotplug_disabled = 0;
-	mutex_unlock(&cpu_add_remove_lock);
+	if (cpus_empty(frozen_cpus))
+		goto out;
 
 	printk("Enabling non-boot CPUs ...\n");
 	for_each_cpu_mask(cpu, frozen_cpus) {
-		error = cpu_up(cpu);
+		error = _cpu_up(cpu, 1);
 		if (!error) {
 			printk("CPU%d is up\n", cpu);
 			continue;
 		}
-		printk(KERN_WARNING "Error taking CPU%d up: %d\n",
-			cpu, error);
+		printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
 	}
 	cpus_clear(frozen_cpus);
+out:
+	cpu_maps_update_done();
 }
-#endif
+#endif /* CONFIG_PM_SLEEP_SMP */