aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/power/freezing-of-tasks.txt160
-rw-r--r--Documentation/power/kernel_threads.txt40
-rw-r--r--Documentation/power/swsusp.txt18
-rw-r--r--arch/i386/kernel/apm.c2
-rw-r--r--arch/i386/kernel/io_apic.c1
-rw-r--r--drivers/block/loop.c8
-rw-r--r--drivers/block/pktcdvd.c1
-rw-r--r--drivers/char/apm-emulation.c12
-rw-r--r--drivers/char/hvc_console.c1
-rw-r--r--drivers/edac/edac_mc.c1
-rw-r--r--drivers/ieee1394/ieee1394_core.c3
-rw-r--r--drivers/ieee1394/nodemgr.c1
-rw-r--r--drivers/input/gameport/gameport.c1
-rw-r--r--drivers/input/serio/serio.c1
-rw-r--r--drivers/input/touchscreen/ucb1400_ts.c1
-rw-r--r--drivers/macintosh/therm_adt746x.c1
-rw-r--r--drivers/macintosh/windfarm_core.c1
-rw-r--r--drivers/md/md.c1
-rw-r--r--drivers/media/dvb/dvb-core/dvb_frontend.c1
-rw-r--r--drivers/media/video/cx88/cx88-tvaudio.c1
-rw-r--r--drivers/media/video/msp3400-kthreads.c6
-rw-r--r--drivers/media/video/tvaudio.c2
-rw-r--r--drivers/media/video/video-buf-dvb.c1
-rw-r--r--drivers/media/video/vivi.c1
-rw-r--r--drivers/mfd/ucb1x00-ts.c1
-rw-r--r--drivers/mmc/card/queue.c7
-rw-r--r--drivers/mtd/mtd_blkdevs.c3
-rw-r--r--drivers/mtd/ubi/wl.c1
-rw-r--r--drivers/net/wireless/airo.c3
-rw-r--r--drivers/net/wireless/libertas/main.c1
-rw-r--r--drivers/pcmcia/cs.c1
-rw-r--r--drivers/pnp/pnpbios/core.c1
-rw-r--r--drivers/scsi/libsas/sas_scsi_host.c3
-rw-r--r--drivers/scsi/scsi_error.c3
-rw-r--r--drivers/usb/atm/ueagle-atm.c1
-rw-r--r--drivers/usb/core/hub.c1
-rw-r--r--drivers/usb/gadget/file_storage.c3
-rw-r--r--drivers/usb/storage/usb.c3
-rw-r--r--drivers/video/ps3fb.c1
-rw-r--r--drivers/w1/w1.c1
-rw-r--r--fs/cifs/cifsfs.c1
-rw-r--r--fs/cifs/connect.c1
-rw-r--r--fs/jffs2/background.c1
-rw-r--r--fs/lockd/svc.c2
-rw-r--r--fs/nfs/callback.c2
-rw-r--r--fs/nfsd/nfssvc.c2
-rw-r--r--fs/xfs/linux-2.6/xfs_super.c1
-rw-r--r--include/linux/freezer.h14
-rw-r--r--init/do_mounts_initrd.c7
-rw-r--r--kernel/audit.c1
-rw-r--r--kernel/exit.c6
-rw-r--r--kernel/fork.c2
-rw-r--r--kernel/rcutorture.c4
-rw-r--r--kernel/rtmutex-tester.c1
-rw-r--r--kernel/sched.c3
-rw-r--r--kernel/softirq.c3
-rw-r--r--kernel/softlockup.c2
-rw-r--r--kernel/workqueue.c4
-rw-r--r--mm/pdflush.c1
-rw-r--r--mm/vmscan.c1
-rw-r--r--net/bluetooth/bnep/core.c2
-rw-r--r--net/bluetooth/cmtp/core.c2
-rw-r--r--net/bluetooth/hidp/core.c2
-rw-r--r--net/bluetooth/rfcomm/core.c2
-rw-r--r--net/core/pktgen.c2
65 files changed, 256 insertions, 113 deletions
diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt
new file mode 100644
index 00000000000..af1a282c71a
--- /dev/null
+++ b/Documentation/power/freezing-of-tasks.txt
@@ -0,0 +1,160 @@
+Freezing of tasks
+ (C) 2007 Rafael J. Wysocki <rjw@sisk.pl>, GPL
+
+I. What is the freezing of tasks?
+
+The freezing of tasks is a mechanism by which user space processes and some
+kernel threads are controlled during hibernation or system-wide suspend (on some
+architectures).
+
+II. How does it work?
+
+There are four per-task flags used for that, PF_NOFREEZE, PF_FROZEN, TIF_FREEZE
+and PF_FREEZER_SKIP (the last one is auxiliary). The tasks that have
+PF_NOFREEZE unset (all user space processes and some kernel threads) are
+regarded as 'freezable' and treated in a special way before the system enters a
+suspend state as well as before a hibernation image is created (in what follows
+we only consider hibernation, but the description also applies to suspend).
+
+Namely, as the first step of the hibernation procedure the function
+freeze_processes() (defined in kernel/power/process.c) is called. It executes
+try_to_freeze_tasks() that sets TIF_FREEZE for all of the freezable tasks and
+sends a fake signal to each of them. A task that receives such a signal and has
+TIF_FREEZE set, should react to it by calling the refrigerator() function
+(defined in kernel/power/process.c), which sets the task's PF_FROZEN flag,
+changes its state to TASK_UNINTERRUPTIBLE and makes it loop until PF_FROZEN is
+cleared for it. Then, we say that the task is 'frozen' and therefore the set of
+functions handling this mechanism is called 'the freezer' (these functions are
+defined in kernel/power/process.c and include/linux/freezer.h). User space
+processes are generally frozen before kernel threads.
+
+It is not recommended to call refrigerator() directly. Instead, it is
+recommended to use the try_to_freeze() function (defined in
+include/linux/freezer.h), that checks the task's TIF_FREEZE flag and makes the
+task enter refrigerator() if the flag is set.
+
+For user space processes try_to_freeze() is called automatically from the
+signal-handling code, but the freezable kernel threads need to call it
+explicitly in suitable places. The code to do this may look like the following:
+
+ do {
+ hub_events();
+ wait_event_interruptible(khubd_wait,
+ !list_empty(&hub_event_list));
+ try_to_freeze();
+ } while (!signal_pending(current));
+
+(from drivers/usb/core/hub.c::hub_thread()).
+
+If a freezable kernel thread fails to call try_to_freeze() after the freezer has
+set TIF_FREEZE for it, the freezing of tasks will fail and the entire
+hibernation operation will be cancelled. For this reason, freezable kernel
+threads must call try_to_freeze() somewhere.
+
+After the system memory state has been restored from a hibernation image and
+devices have been reinitialized, the function thaw_processes() is called in
+order to clear the PF_FROZEN flag for each frozen task. Then, the tasks that
+have been frozen leave refrigerator() and continue running.
+
+III. Which kernel threads are freezable?
+
+Kernel threads are not freezable by default. However, a kernel thread may clear
+PF_NOFREEZE for itself by calling set_freezable() (the resetting of PF_NOFREEZE
+directly is strongly discouraged). From this point it is regarded as freezable
+and must call try_to_freeze() in a suitable place.
+
+IV. Why do we do that?
+
+Generally speaking, there is a couple of reasons to use the freezing of tasks:
+
+1. The principal reason is to prevent filesystems from being damaged after
+hibernation. At the moment we have no simple means of checkpointing
+filesystems, so if there are any modifications made to filesystem data and/or
+metadata on disks, we cannot bring them back to the state from before the
+modifications. At the same time each hibernation image contains some
+filesystem-related information that must be consistent with the state of the
+on-disk data and metadata after the system memory state has been restored from
+the image (otherwise the filesystems will be damaged in a nasty way, usually
+making them almost impossible to repair). We therefore freeze tasks that might
+cause the on-disk filesystems' data and metadata to be modified after the
+hibernation image has been created and before the system is finally powered off.
+The majority of these are user space processes, but if any of the kernel threads
+may cause something like this to happen, they have to be freezable.
+
+2. The second reason is to prevent user space processes and some kernel threads
+from interfering with the suspending and resuming of devices. A user space
+process running on a second CPU while we are suspending devices may, for
+example, be troublesome and without the freezing of tasks we would need some
+safeguards against race conditions that might occur in such a case.
+
+Although Linus Torvalds doesn't like the freezing of tasks, he said this in one
+of the discussions on LKML (http://lkml.org/lkml/2007/4/27/608):
+
+"RJW:> Why we freeze tasks at all or why we freeze kernel threads?
+
+Linus: In many ways, 'at all'.
+
+I _do_ realize the IO request queue issues, and that we cannot actually do
+s2ram with some devices in the middle of a DMA. So we want to be able to
+avoid *that*, there's no question about that. And I suspect that stopping
+user threads and then waiting for a sync is practically one of the easier
+ways to do so.
+
+So in practice, the 'at all' may become a 'why freeze kernel threads?' and
+freezing user threads I don't find really objectionable."
+
+Still, there are kernel threads that may want to be freezable. For example, if
+a kernel that belongs to a device driver accesses the device directly, it in
+principle needs to know when the device is suspended, so that it doesn't try to
+access it at that time. However, if the kernel thread is freezable, it will be
+frozen before the driver's .suspend() callback is executed and it will be
+thawed after the driver's .resume() callback has run, so it won't be accessing
+the device while it's suspended.
+
+3. Another reason for freezing tasks is to prevent user space processes from
+realizing that hibernation (or suspend) operation takes place. Ideally, user
+space processes should not notice that such a system-wide operation has occurred
+and should continue running without any problems after the restore (or resume
+from suspend). Unfortunately, in the most general case this is quite difficult
+to achieve without the freezing of tasks. Consider, for example, a process
+that depends on all CPUs being online while it's running. Since we need to
+disable nonboot CPUs during the hibernation, if this process is not frozen, it
+may notice that the number of CPUs has changed and may start to work incorrectly
+because of that.
+
+V. Are there any problems related to the freezing of tasks?
+
+Yes, there are.
+
+First of all, the freezing of kernel threads may be tricky if they depend one
+on another. For example, if kernel thread A waits for a completion (in the
+TASK_UNINTERRUPTIBLE state) that needs to be done by freezable kernel thread B
+and B is frozen in the meantime, then A will be blocked until B is thawed, which
+may be undesirable. That's why kernel threads are not freezable by default.
+
+Second, there are the following two problems related to the freezing of user
+space processes:
+1. Putting processes into an uninterruptible sleep distorts the load average.
+2. Now that we have FUSE, plus the framework for doing device drivers in
+userspace, it gets even more complicated because some userspace processes are
+now doing the sorts of things that kernel threads do
+(https://lists.linux-foundation.org/pipermail/linux-pm/2007-May/012309.html).
+
+The problem 1. seems to be fixable, although it hasn't been fixed so far. The
+other one is more serious, but it seems that we can work around it by using
+hibernation (and suspend) notifiers (in that case, though, we won't be able to
+avoid the realization by the user space processes that the hibernation is taking
+place).
+
+There are also problems that the freezing of tasks tends to expose, although
+they are not directly related to it. For example, if request_firmware() is
+called from a device driver's .resume() routine, it will timeout and eventually
+fail, because the user land process that should respond to the request is frozen
+at this point. So, seemingly, the failure is due to the freezing of tasks.
+Suppose, however, that the firmware file is located on a filesystem accessible
+only through another device that hasn't been resumed yet. In that case,
+request_firmware() will fail regardless of whether or not the freezing of tasks
+is used. Consequently, the problem is not really related to the freezing of
+tasks, since it generally exists anyway. [The solution to this particular
+problem is to keep the firmware in memory after it's loaded for the first time
+and upload if from memory to the device whenever necessary.]
diff --git a/Documentation/power/kernel_threads.txt b/Documentation/power/kernel_threads.txt
deleted file mode 100644
index fb57784986b..00000000000
--- a/Documentation/power/kernel_threads.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-KERNEL THREADS
-
-
-Freezer
-
-Upon entering a suspended state the system will freeze all
-tasks. This is done by delivering pseudosignals. This affects
-kernel threads, too. To successfully freeze a kernel thread
-the thread has to check for the pseudosignal and enter the
-refrigerator. Code to do this looks like this:
-
- do {
- hub_events();
- wait_event_interruptible(khubd_wait, !list_empty(&hub_event_list));
- try_to_freeze();
- } while (!signal_pending(current));
-
-from drivers/usb/core/hub.c::hub_thread()
-
-
-The Unfreezable
-
-Some kernel threads however, must not be frozen. The kernel must
-be able to finish pending IO operations and later on be able to
-write the memory image to disk. Kernel threads needed to do IO
-must stay awake. Such threads must mark themselves unfreezable
-like this:
-
- /*
- * This thread doesn't need any user-level access,
- * so get rid of all our resources.
- */
- daemonize("usb-storage");
-
- current->flags |= PF_NOFREEZE;
-
-from drivers/usb/storage/usb.c::usb_stor_control_thread()
-
-Such drivers are themselves responsible for staying quiet during
-the actual snapshotting.
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index 152b510d1bb..aea7e920966 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -140,21 +140,11 @@ should be sent to the mailing list available through the suspend2
website, and not to the Linux Kernel Mailing List. We are working
toward merging suspend2 into the mainline kernel.
-Q: A kernel thread must voluntarily freeze itself (call 'refrigerator').
-I found some kernel threads that don't do it, and they don't freeze
-so the system can't sleep. Is this a known behavior?
-
-A: All such kernel threads need to be fixed, one by one. Select the
-place where the thread is safe to be frozen (no kernel semaphores
-should be held at that point and it must be safe to sleep there), and
-add:
-
- try_to_freeze();
-
-If the thread is needed for writing the image to storage, you should
-instead set the PF_NOFREEZE process flag when creating the thread (and
-be very careful).
+Q: What is the freezing of tasks and why are we using it?
+A: The freezing of tasks is a mechanism by which user space processes and some
+kernel threads are controlled during hibernation or system-wide suspend (on some
+architectures). See freezing-of-tasks.txt for details.
Q: What is the difference between "platform" and "shutdown"?
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 4112afe712b..47001d50a08 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -222,6 +222,7 @@
#include <linux/capability.h>
#include <linux/device.h>
#include <linux/kernel.h>
+#include <linux/freezer.h>
#include <linux/smp.h>
#include <linux/dmi.h>
#include <linux/suspend.h>
@@ -2311,7 +2312,6 @@ static int __init apm_init(void)
remove_proc_entry("apm", NULL);
return err;
}
- kapmd_task->flags |= PF_NOFREEZE;
wake_up_process(kapmd_task);
if (num_online_cpus() > 1 && !smp ) {
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 7f8b7af2b95..21db8f56c9a 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -667,6 +667,7 @@ static int balanced_irq(void *unused)
set_pending_irq(i, cpumask_of_cpu(0));
}
+ set_freezable();
for ( ; ; ) {
time_remaining = schedule_timeout_interruptible(time_remaining);
try_to_freeze();
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4503290da40..06eaa11cbc2 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -68,6 +68,7 @@
#include <linux/loop.h>
#include <linux/compat.h>
#include <linux/suspend.h>
+#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h> /* for invalidate_bdev() */
#include <linux/completion.h>
@@ -600,13 +601,6 @@ static int loop_thread(void *data)
struct loop_device *lo = data;
struct bio *bio;
- /*
- * loop can be used in an encrypted device,
- * hence, it mustn't be stopped at all
- * because it could be indirectly used during suspension
- */
- current->flags |= PF_NOFREEZE;
-
set_user_nice(current, -20);
while (!kthread_should_stop() || lo->lo_bio) {
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 7c294a40002..31be33e4f11 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -1593,6 +1593,7 @@ static int kcdrwd(void *foobar)
long min_sleep_time, residue;
set_user_nice(current, -20);
+ set_freezable();
for (;;) {
DECLARE_WAITQUEUE(wait, current);
diff --git a/drivers/char/apm-emulation.c b/drivers/char/apm-emulation.c
index 179c7a3b6e7..ec116df919d 100644
--- a/drivers/char/apm-emulation.c
+++ b/drivers/char/apm-emulation.c
@@ -20,6 +20,7 @@
#include <linux/sched.h>
#include <linux/pm.h>
#include <linux/apm-emulation.h>
+#include <linux/freezer.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/list.h>
@@ -329,13 +330,8 @@ apm_ioctl(struct inode * inode, struct file *filp, u_int cmd, u_long arg)
/*
* Wait for the suspend/resume to complete. If there
* are pending acknowledges, we wait here for them.
- *
- * Note: we need to ensure that the PM subsystem does
- * not kick us out of the wait when it suspends the
- * threads.
*/
flags = current->flags;
- current->flags |= PF_NOFREEZE;
wait_event(apm_suspend_waitqueue,
as->suspend_state == SUSPEND_DONE);
@@ -365,13 +361,8 @@ apm_ioctl(struct inode * inode, struct file *filp, u_int cmd, u_long arg)
/*
* Wait for the suspend/resume to complete. If there
* are pending acknowledges, we wait here for them.
- *
- * Note: we need to ensure that the PM subsystem does
- * not kick us out of the wait when it suspends the
- * threads.
*/
flags = current->flags;
- current->flags |= PF_NOFREEZE;
wait_event_interruptible(apm_suspend_waitqueue,
as->suspend_state == SUSPEND_DONE);
@@ -598,7 +589,6 @@ static int __init apm_init(void)
kapmd_tsk = NULL;
return ret;
}
- kapmd_tsk->flags |= PF_NOFREEZE;
wake_up_process(kapmd_tsk);
#ifdef CONFIG_PROC_FS
diff --git a/drivers/char/hvc_console.c b/drivers/char/hvc_console.c
index b3ab42e0dd4..83c1151ec7a 100644
--- a/drivers/char/hvc_console.c
+++ b/drivers/char/hvc_console.c
@@ -679,6 +679,7 @@ static int khvcd(void *unused)
int poll_mask;
struct hvc_struct *hp;
+ set_freezable();
__set_current_state(TASK_RUNNING);
do {
poll_mask = 0;
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 7b622300d0e..804875de580 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -1906,6 +1906,7 @@ static void do_edac_check(void)
static int edac_kernel_thread(void *arg)
{
+ set_freezable();
while (!kthread_should_stop()) {
do_edac_check();
diff --git a/drivers/ieee1394/ieee1394_core.c b/drivers/ieee1394/ieee1394_core.c
index 0fc8c6e559e..ee45259573c 100644
--- a/drivers/ieee1394/ieee1394_core.c
+++ b/drivers/ieee1394/ieee1394_core.c
@@ -30,6 +30,7 @@
#include <linux/moduleparam.h>
#include <linux/bitops.h>
#include <linux/kdev_t.h>
+#include <linux/freezer.h>
#include <linux/suspend.h>
#include <linux/kthread.h>
#include <linux/preempt.h>
@@ -1128,8 +1129,6 @@ static int hpsbpkt_thread(void *__hi)
struct list_head tmp;
int may_schedule;
- current->flags |= PF_NOFREEZE;
-
while (!kthread_should_stop()) {
INIT_LIST_HEAD(&tmp);
diff --git a/drivers/ieee1394/nodemgr.c b/drivers/ieee1394/nodemgr.c
index 51a12062ed3..2ffd53461db 100644
--- a/drivers/ieee1394/nodemgr.c
+++ b/drivers/ieee1394/nodemgr.c
@@ -1699,6 +1699,7 @@ static int nodemgr_host_thread(void *__hi)
unsigned int g, generation = 0;
int i, reset_cycles = 0;
+ set_freezable();
/* Setup our device-model entries */
nodemgr_create_host_dev_files(host);
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index bd686a2a517..20896d5e5f0 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -445,6 +445,7 @@ static struct gameport *gameport_get_pending_child(struct gameport *parent)
static int gameport_thread(void *nothing)
{
+ set_freezable();
do {
gameport_handle_event();
wait_event_interruptible(gameport_wait,
diff --git a/drivers/input/serio/serio.c b/drivers/input/serio/serio.c
index a8f3bc1dff2..372ca493119 100644
--- a/drivers/input/serio/serio.c
+++ b/drivers/input/serio/serio.c
@@ -384,6 +384,7 @@ static struct serio *serio_get_pending_child(struct serio *parent)
static int serio_thread(void *nothing)
{
+ set_freezable();
do {
serio_handle_event();
wait_event_interruptible(serio_wait,
diff --git a/drivers/input/touchscreen/ucb1400_ts.c b/drivers/input/touchscreen/ucb1400_ts.c
index f0cbcdb008e..36f94401915 100644
--- a/drivers/input/touchscreen/ucb1400_ts.c
+++ b/drivers/input/touchscreen/ucb1400_ts.c
@@ -292,6 +292,7 @@ static int ucb1400_ts_thread(void *_ucb)
sched_setscheduler(tsk, SCHED_FIFO, &param);
+ set_freezable();
while (!kthread_should_stop()) {
unsigned int x, y, p;
long timeout;
diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index bd55e6ab99f..f25685b9b7c 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -335,6 +335,7 @@ static int monitor_task(void *arg)
{
struct thermostat* th = arg;
+ set_freezable();
while(!kthread_should_stop()) {
try_to_freeze();
msleep_interruptible(2000);
diff --git a/drivers/macintosh/windfarm_core.c b/drivers/macintosh/windfarm_core.c
index 4fcb245ba18..e18d265d5d3 100644
--- a/drivers/macintosh/windfarm_core.c
+++ b/drivers/macintosh/windfarm_core.c
@@ -92,6 +92,7 @@ static int wf_thread_func(void *data)
DBG("wf: thread started\n");
+ set_freezable();
while(!kthread_should_stop()) {
if (time_after_eq(jiffies, next)) {
wf_notify(WF_EVENT_TICK, NULL);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 33beaa7da08..9aefc4a023d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4642,7 +4642,6 @@ static int md_thread(void * arg)
* many dirty RAID5 blocks