Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 717 insertions, 0 deletions

diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
new file mode 100644
index 000000000..389874f44
--- /dev/null
+++ b/drivers/char/apm-emulation.c
@@ -0,0 +1,717 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * bios-less APM driver for ARM Linux
+ *  Jamey Hicks <jamey@crl.dec.com>
+ *  adapted from the APM BIOS driver for Linux by Stephen Rothwell (sfr@linuxcare.com)
+ *
+ * APM 1.2 Reference:
+ *   Intel Corporation, Microsoft Corporation. Advanced Power Management
+ *   (APM) BIOS Interface Specification, Revision 1.2, February 1996.
+ *
+ * This document is available from Microsoft at:
+ *    http://www.microsoft.com/whdc/archive/amp_12.mspx
+ */
+#include <linux/module.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/miscdevice.h>
+#include <linux/apm_bios.h>
+#include <linux/capability.h>
+#include <linux/sched.h>
+#include <linux/suspend.h>
+#include <linux/apm-emulation.h>
+#include <linux/freezer.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/init.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+#include <linux/delay.h>
+
+/*
+ * One option can be changed at boot time as follows:
+ *	apm=on/off			enable/disable APM
+ */
+
+/*
+ * Maximum number of events stored
+ */
+#define APM_MAX_EVENTS		16
+
+struct apm_queue {
+	unsigned int		event_head;
+	unsigned int		event_tail;
+	apm_event_t		events[APM_MAX_EVENTS];
+};
+
+/*
+ * thread states (for threads using a writable /dev/apm_bios fd):
+ *
+ * SUSPEND_NONE:	nothing happening
+ * SUSPEND_PENDING:	suspend event queued for thread and pending to be read
+ * SUSPEND_READ:	suspend event read, pending acknowledgement
+ * SUSPEND_ACKED:	acknowledgement received from thread (via ioctl),
+ *			waiting for resume
+ * SUSPEND_ACKTO:	acknowledgement timeout
+ * SUSPEND_DONE:	thread had acked suspend and is now notified of
+ *			resume
+ *
+ * SUSPEND_WAIT:	this thread invoked suspend and is waiting for resume
+ *
+ * A thread migrates in one of three paths:
+ *	NONE -1-> PENDING -2-> READ -3-> ACKED -4-> DONE -5-> NONE
+ *				    -6-> ACKTO -7-> NONE
+ *	NONE -8-> WAIT -9-> NONE
+ *
+ * While in PENDING or READ, the thread is accounted for in the
+ * suspend_acks_pending counter.
+ *
+ * The transitions are invoked as follows:
+ *	1: suspend event is signalled from the core PM code
+ *	2: the suspend event is read from the fd by the userspace thread
+ *	3: userspace thread issues the APM_IOC_SUSPEND ioctl (as ack)
+ *	4: core PM code signals that we have resumed
+ *	5: APM_IOC_SUSPEND ioctl returns
+ *
+ *	6: the notifier invoked from the core PM code timed out waiting
+ *	   for all relevant threds to enter ACKED state and puts those
+ *	   that haven't into ACKTO
+ *	7: those threads issue APM_IOC_SUSPEND ioctl too late,
+ *	   get an error
+ *
+ *	8: userspace thread issues the APM_IOC_SUSPEND ioctl (to suspend),
+ *	   ioctl code invokes pm_suspend()
+ *	9: pm_suspend() returns indicating resume
+ */
+enum apm_suspend_state {
+	SUSPEND_NONE,
+	SUSPEND_PENDING,
+	SUSPEND_READ,
+	SUSPEND_ACKED,
+	SUSPEND_ACKTO,
+	SUSPEND_WAIT,
+	SUSPEND_DONE,
+};
+
+/*
+ * The per-file APM data
+ */
+struct apm_user {
+	struct list_head	list;
+
+	unsigned int		suser: 1;
+	unsigned int		writer: 1;
+	unsigned int		reader: 1;
+
+	int			suspend_result;
+	enum apm_suspend_state	suspend_state;
+
+	struct apm_queue	queue;
+};
+
+/*
+ * Local variables
+ */
+static atomic_t suspend_acks_pending = ATOMIC_INIT(0);
+static atomic_t userspace_notification_inhibit = ATOMIC_INIT(0);
+static int apm_disabled;
+static struct task_struct *kapmd_tsk;
+
+static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue);
+static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue);
+
+/*
+ * This is a list of everyone who has opened /dev/apm_bios
+ */
+static DECLARE_RWSEM(user_list_lock);
+static LIST_HEAD(apm_user_list);
+
+/*
+ * kapmd info.  kapmd provides us a process context to handle
+ * "APM" events within - specifically necessary if we're going
+ * to be suspending the system.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(kapmd_wait);
+static DEFINE_SPINLOCK(kapmd_queue_lock);
+static struct apm_queue kapmd_queue;
+
+static DEFINE_MUTEX(state_lock);
+
+
+/*
+ * This allows machines to provide their own "apm get power status" function.
+ */
+void (*apm_get_power_status)(struct apm_power_info *);
+EXPORT_SYMBOL(apm_get_power_status);
+
+
+/*
+ * APM event queue management.
+ */
+static inline int queue_empty(struct apm_queue *q)
+{
+	return q->event_head == q->event_tail;
+}
+
+static inline apm_event_t queue_get_event(struct apm_queue *q)
+{
+	q->event_tail = (q->event_tail + 1) % APM_MAX_EVENTS;
+	return q->events[q->event_tail];
+}
+
+static void queue_add_event(struct apm_queue *q, apm_event_t event)
+{
+	q->event_head = (q->event_head + 1) % APM_MAX_EVENTS;
+	if (q->event_head == q->event_tail) {
+		static int notified;
+
+		if (notified++ == 0)
+		    printk(KERN_ERR "apm: an event queue overflowed\n");
+		q->event_tail = (q->event_tail + 1) % APM_MAX_EVENTS;
+	}
+	q->events[q->event_head] = event;
+}
+
+static void queue_event(apm_event_t event)
+{
+	struct apm_user *as;
+
+	down_read(&user_list_lock);
+	list_for_each_entry(as, &apm_user_list, list) {
+		if (as->reader)
+			queue_add_event(&as->queue, event);
+	}
+	up_read(&user_list_lock);
+	wake_up_interruptible(&apm_waitqueue);
+}
+
+static ssize_t apm_read(struct file *fp, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct apm_user *as = fp->private_data;
+	apm_event_t event;
+	int i = count, ret = 0;
+
+	if (count < sizeof(apm_event_t))
+		return -EINVAL;
+
+	if (queue_empty(&as->queue) && fp->f_flags & O_NONBLOCK)
+		return -EAGAIN;
+
+	wait_event_interruptible(apm_waitqueue, !queue_empty(&as->queue));
+
+	while ((i >= sizeof(event)) && !queue_empty(&as->queue)) {
+		event = queue_get_event(&as->queue);
+
+		ret = -EFAULT;
+		if (copy_to_user(buf, &event, sizeof(event)))
+			break;
+
+		mutex_lock(&state_lock);
+		if (as->suspend_state == SUSPEND_PENDING &&
+		    (event == APM_SYS_SUSPEND || event == APM_USER_SUSPEND))
+			as->suspend_state = SUSPEND_READ;
+		mutex_unlock(&state_lock);
+
+		buf += sizeof(event);
+		i -= sizeof(event);
+	}
+
+	if (i < count)
+		ret = count - i;
+
+	return ret;
+}
+
+static __poll_t apm_poll(struct file *fp, poll_table * wait)
+{
+	struct apm_user *as = fp->private_data;
+
+	poll_wait(fp, &apm_waitqueue, wait);
+	return queue_empty(&as->queue) ? 0 : EPOLLIN | EPOLLRDNORM;
+}
+
+/*
+ * apm_ioctl - handle APM ioctl
+ *
+ * APM_IOC_SUSPEND
+ *   This IOCTL is overloaded, and performs two functions.  It is used to:
+ *     - initiate a suspend
+ *     - acknowledge a suspend read from /dev/apm_bios.
+ *   Only when everyone who has opened /dev/apm_bios with write permission
+ *   has acknowledge does the actual suspend happen.
+ */
+static long
+apm_ioctl(struct file *filp, u_int cmd, u_long arg)
+{
+	struct apm_user *as = filp->private_data;
+	int err = -EINVAL;
+
+	if (!as->suser || !as->writer)
+		return -EPERM;
+
+	switch (cmd) {
+	case APM_IOC_SUSPEND:
+		mutex_lock(&state_lock);
+
+		as->suspend_result = -EINTR;
+
+		switch (as->suspend_state) {
+		case SUSPEND_READ:
+			/*
+			 * If we read a suspend command from /dev/apm_bios,
+			 * then the corresponding APM_IOC_SUSPEND ioctl is
+			 * interpreted as an acknowledge.
+			 */
+			as->suspend_state = SUSPEND_ACKED;
+			atomic_dec(&suspend_acks_pending);
+			mutex_unlock(&state_lock);
+
+			/*
+			 * suspend_acks_pending changed, the notifier needs to
+			 * be woken up for this
+			 */
+			wake_up(&apm_suspend_waitqueue);
+
+			/*
+			 * Wait for the suspend/resume to complete.  If there
+			 * are pending acknowledges, we wait here for them.
+			 * wait_event_freezable() is interruptible and pending
+			 * signal can cause busy looping.  We aren't doing
+			 * anything critical, chill a bit on each iteration.
+			 */
+			while (wait_event_freezable(apm_suspend_waitqueue,
+					as->suspend_state != SUSPEND_ACKED))
+				msleep(10);
+			break;
+		case SUSPEND_ACKTO:
+			as->suspend_result = -ETIMEDOUT;
+			mutex_unlock(&state_lock);
+			break;
+		default:
+			as->suspend_state = SUSPEND_WAIT;
+			mutex_unlock(&state_lock);
+
+			/*
+			 * Otherwise it is a request to suspend the system.
+			 * Just invoke pm_suspend(), we'll handle it from
+			 * there via the notifier.
+			 */
+			as->suspend_result = pm_suspend(PM_SUSPEND_MEM);
+		}
+
+		mutex_lock(&state_lock);
+		err = as->suspend_result;
+		as->suspend_state = SUSPEND_NONE;
+		mutex_unlock(&state_lock);
+		break;
+	}
+
+	return err;
+}
+
+static int apm_release(struct inode * inode, struct file * filp)
+{
+	struct apm_user *as = filp->private_data;
+
+	filp->private_data = NULL;
+
+	down_write(&user_list_lock);
+	list_del(&as->list);
+	up_write(&user_list_lock);
+
+	/*
+	 * We are now unhooked from the chain.  As far as new
+	 * events are concerned, we no longer exist.
+	 */
+	mutex_lock(&state_lock);
+	if (as->suspend_state == SUSPEND_PENDING ||
+	    as->suspend_state == SUSPEND_READ)
+		atomic_dec(&suspend_acks_pending);
+	mutex_unlock(&state_lock);
+
+	wake_up(&apm_suspend_waitqueue);
+
+	kfree(as);
+	return 0;
+}
+
+static int apm_open(struct inode * inode, struct file * filp)
+{
+	struct apm_user *as;
+
+	as = kzalloc_obj(*as);
+	if (as) {
+		/*
+		 * XXX - this is a tiny bit broken, when we consider BSD
+		 * process accounting. If the device is opened by root, we
+		 * instantly flag that we used superuser privs. Who knows,
+		 * we might close the device immediately without doing a
+		 * privileged operation -- cevans
+		 */
+		as->suser = capable(CAP_SYS_ADMIN);
+		as->writer = (filp->f_mode & FMODE_WRITE) == FMODE_WRITE;
+		as->reader = (filp->f_mode & FMODE_READ) == FMODE_READ;
+
+		down_write(&user_list_lock);
+		list_add(&as->list, &apm_user_list);
+		up_write(&user_list_lock);
+
+		filp->private_data = as;
+	}
+
+	return as ? 0 : -ENOMEM;
+}
+
+static const struct file_operations apm_bios_fops = {
+	.owner		= THIS_MODULE,
+	.read		= apm_read,
+	.poll		= apm_poll,
+	.unlocked_ioctl	= apm_ioctl,
+	.open		= apm_open,
+	.release	= apm_release,
+	.llseek		= noop_llseek,
+};
+
+static struct miscdevice apm_device = {
+	.minor		= APM_MINOR_DEV,
+	.name		= "apm_bios",
+	.fops		= &apm_bios_fops
+};
+
+
+#ifdef CONFIG_PROC_FS
+/*
+ * Arguments, with symbols from linux/apm_bios.h.
+ *
+ *   0) Linux driver version (this will change if format changes)
+ *   1) APM BIOS Version.  Usually 1.0, 1.1 or 1.2.
+ *   2) APM flags from APM Installation Check (0x00):
+ *	bit 0: APM_16_BIT_SUPPORT
+ *	bit 1: APM_32_BIT_SUPPORT
+ *	bit 2: APM_IDLE_SLOWS_CLOCK
+ *	bit 3: APM_BIOS_DISABLED
+ *	bit 4: APM_BIOS_DISENGAGED
+ *   3) AC line status
+ *	0x00: Off-line
+ *	0x01: On-line
+ *	0x02: On backup power (BIOS >= 1.1 only)
+ *	0xff: Unknown
+ *   4) Battery status
+ *	0x00: High
+ *	0x01: Low
+ *	0x02: Critical
+ *	0x03: Charging
+ *	0x04: Selected battery not present (BIOS >= 1.2 only)
+ *	0xff: Unknown
+ *   5) Battery flag
+ *	bit 0: High
+ *	bit 1: Low
+ *	bit 2: Critical
+ *	bit 3: Charging
+ *	bit 7: No system battery
+ *	0xff: Unknown
+ *   6) Remaining battery life (percentage of charge):
+ *	0-100: valid
+ *	-1: Unknown
+ *   7) Remaining battery life (time units):
+ *	Number of remaining minutes or seconds
+ *	-1: Unknown
+ *   8) min = minutes; sec = seconds
+ */
+static int proc_apm_show(struct seq_file *m, void *v)
+{
+	static const char driver_version[] = "1.13";	/* no spaces */
+
+	struct apm_power_info info;
+	char *units;
+
+	info.ac_line_status = 0xff;
+	info.battery_status = 0xff;
+	info.battery_flag   = 0xff;
+	info.battery_life   = -1;
+	info.time	    = -1;
+	info.units	    = -1;
+
+	if (apm_get_power_status)
+		apm_get_power_status(&info);
+
+	switch (info.units) {
+	default:	units = "?";	break;
+	case 0: 	units = "min";	break;
+	case 1: 	units = "sec";	break;
+	}
+
+	seq_printf(m, "%s 1.2 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
+		     driver_version, APM_32_BIT_SUPPORT,
+		     info.ac_line_status, info.battery_status,
+		     info.battery_flag, info.battery_life,
+		     info.time, units);
+
+	return 0;
+}
+#endif
+
+static int kapmd(void *arg)
+{
+	do {
+		apm_event_t event;
+
+		wait_event_interruptible(kapmd_wait,
+				!queue_empty(&kapmd_queue) || kthread_should_stop());
+
+		if (kthread_should_stop())
+			break;
+
+		spin_lock_irq(&kapmd_queue_lock);
+		event = 0;
+		if (!queue_empty(&kapmd_queue))
+			event = queue_get_event(&kapmd_queue);
+		spin_unlock_irq(&kapmd_queue_lock);
+
+		switch (event) {
+		case 0:
+			break;
+
+		case APM_LOW_BATTERY:
+		case APM_POWER_STATUS_CHANGE:
+			queue_event(event);
+			break;
+
+		case APM_USER_SUSPEND:
+		case APM_SYS_SUSPEND:
+			pm_suspend(PM_SUSPEND_MEM);
+			break;
+
+		case APM_CRITICAL_SUSPEND:
+			atomic_inc(&userspace_notification_inhibit);
+			pm_suspend(PM_SUSPEND_MEM);
+			atomic_dec(&userspace_notification_inhibit);
+			break;
+		}
+	} while (1);
+
+	return 0;
+}
+
+static int apm_suspend_notifier(struct notifier_block *nb,
+				unsigned long event,
+				void *dummy)
+{
+	struct apm_user *as;
+	int err;
+	unsigned long apm_event;
+
+	/* short-cut emergency suspends */
+	if (atomic_read(&userspace_notification_inhibit))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case PM_SUSPEND_PREPARE:
+	case PM_HIBERNATION_PREPARE:
+		apm_event = (event == PM_SUSPEND_PREPARE) ?
+			APM_USER_SUSPEND : APM_USER_HIBERNATION;
+		/*
+		 * Queue an event to all "writer" users that we want
+		 * to suspend and need their ack.
+		 */
+		mutex_lock(&state_lock);
+		down_read(&user_list_lock);
+
+		list_for_each_entry(as, &apm_user_list, list) {
+			if (as->suspend_state != SUSPEND_WAIT && as->reader &&
+			    as->writer && as->suser) {
+				as->suspend_state = SUSPEND_PENDING;
+				atomic_inc(&suspend_acks_pending);
+				queue_add_event(&as->queue, apm_event);
+			}
+		}
+
+		up_read(&user_list_lock);
+		mutex_unlock(&state_lock);
+		wake_up_interruptible(&apm_waitqueue);
+
+		/*
+		 * Wait for the suspend_acks_pending variable to drop to
+		 * zero, meaning everybody acked the suspend event (or the
+		 * process was killed.)
+		 *
+		 * If the app won't answer within a short while we assume it
+		 * locked up and ignore it.
+		 */
+		err = wait_event_interruptible_timeout(
+			apm_suspend_waitqueue,
+			atomic_read(&suspend_acks_pending) == 0,
+			5*HZ);
+
+		/* timed out */
+		if (err == 0) {
+			/*
+			 * Move anybody who timed out to "ack timeout" state.
+			 *
+			 * We could time out and the userspace does the ACK
+			 * right after we time out but before we enter the
+			 * locked section here, but that's fine.
+			 */
+			mutex_lock(&state_lock);
+			down_read(&user_list_lock);
+			list_for_each_entry(as, &apm_user_list, list) {
+				if (as->suspend_state == SUSPEND_PENDING ||
+				    as->suspend_state == SUSPEND_READ) {
+					as->suspend_state = SUSPEND_ACKTO;
+					atomic_dec(&suspend_acks_pending);
+				}
+			}
+			up_read(&user_list_lock);
+			mutex_unlock(&state_lock);
+		}
+
+		/* let suspend proceed */
+		if (err >= 0)
+			return NOTIFY_OK;
+
+		/* interrupted by signal */
+		return notifier_from_errno(err);
+
+	case PM_POST_SUSPEND:
+	case PM_POST_HIBERNATION:
+		apm_event = (event == PM_POST_SUSPEND) ?
+			APM_NORMAL_RESUME : APM_HIBERNATION_RESUME;
+		/*
+		 * Anyone on the APM queues will think we're still suspended.
+		 * Send a message so everyone knows we're now awake again.
+		 */
+		queue_event(apm_event);
+
+		/*
+		 * Finally, wake up anyone who is sleeping on the suspend.
+		 */
+		mutex_lock(&state_lock);
+		down_read(&user_list_lock);
+		list_for_each_entry(as, &apm_user_list, list) {
+			if (as->suspend_state == SUSPEND_ACKED) {
+				/*
+				 * TODO: maybe grab error code, needs core
+				 * changes to push the error to the notifier
+				 * chain (could use the second parameter if
+				 * implemented)
+				 */
+				as->suspend_result = 0;
+				as->suspend_state = SUSPEND_DONE;
+			}
+		}
+		up_read(&user_list_lock);
+		mutex_unlock(&state_lock);
+
+		wake_up(&apm_suspend_waitqueue);
+		return NOTIFY_OK;
+
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static struct notifier_block apm_notif_block = {
+	.notifier_call = apm_suspend_notifier,
+};
+
+static int __init apm_init(void)
+{
+	int ret;
+
+	if (apm_disabled) {
+		printk(KERN_NOTICE "apm: disabled on user request.\n");
+		return -ENODEV;
+	}
+
+	kapmd_tsk = kthread_create(kapmd, NULL, "kapmd");
+	if (IS_ERR(kapmd_tsk)) {
+		ret = PTR_ERR(kapmd_tsk);
+		kapmd_tsk = NULL;
+		goto out;
+	}
+	wake_up_process(kapmd_tsk);
+
+#ifdef CONFIG_PROC_FS
+	proc_create_single("apm", 0, NULL, proc_apm_show);
+#endif
+
+	ret = misc_register(&apm_device);
+	if (ret)
+		goto out_stop;
+
+	ret = register_pm_notifier(&apm_notif_block);
+	if (ret)
+		goto out_unregister;
+
+	return 0;
+
+ out_unregister:
+	misc_deregister(&apm_device);
+ out_stop:
+	remove_proc_entry("apm", NULL);
+	kthread_stop(kapmd_tsk);
+ out:
+	return ret;
+}
+
+static void __exit apm_exit(void)
+{
+	unregister_pm_notifier(&apm_notif_block);
+	misc_deregister(&apm_device);
+	remove_proc_entry("apm", NULL);
+
+	kthread_stop(kapmd_tsk);
+}
+
+module_init(apm_init);
+module_exit(apm_exit);
+
+MODULE_AUTHOR("Stephen Rothwell");
+MODULE_DESCRIPTION("Advanced Power Management");
+MODULE_LICENSE("GPL");
+
+#ifndef MODULE
+static int __init apm_setup(char *str)
+{
+	while ((str != NULL) && (*str != '\0')) {
+		if (strncmp(str, "off", 3) == 0)
+			apm_disabled = 1;
+		if (strncmp(str, "on", 2) == 0)
+			apm_disabled = 0;
+		str = strchr(str, ',');
+		if (str != NULL)
+			str += strspn(str, ", \t");
+	}
+	return 1;
+}
+
+__setup("apm=", apm_setup);
+#endif
+
+/**
+ * apm_queue_event - queue an APM event for kapmd
+ * @event: APM event
+ *
+ * Queue an APM event for kapmd to process and ultimately take the
+ * appropriate action.  Only a subset of events are handled:
+ *   %APM_LOW_BATTERY
+ *   %APM_POWER_STATUS_CHANGE
+ *   %APM_USER_SUSPEND
+ *   %APM_SYS_SUSPEND
+ *   %APM_CRITICAL_SUSPEND
+ */
+void apm_queue_event(apm_event_t event)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&kapmd_queue_lock, flags);
+	queue_add_event(&kapmd_queue, event);
+	spin_unlock_irqrestore(&kapmd_queue_lock, flags);
+
+	wake_up_interruptible(&kapmd_wait);
+}
+EXPORT_SYMBOL(apm_queue_event);