linux_dsm_epyc7002/include/linux/freezer.h

302 lines
8.6 KiB
C
Raw Normal View History

/* Freezer declarations */
#ifndef FREEZER_H_INCLUDED
#define FREEZER_H_INCLUDED
#include <linux/debug_locks.h>
[PATCH] freezer.h uses task_struct fields freezer.h uses task_struct fields so it should include sched.h. CC [M] fs/jfs/jfs_txnmgr.o In file included from fs/jfs/jfs_txnmgr.c:49: include/linux/freezer.h: In function 'frozen': include/linux/freezer.h:9: error: dereferencing pointer to incomplete type include/linux/freezer.h:9: error: 'PF_FROZEN' undeclared (first use in this function) include/linux/freezer.h:9: error: (Each undeclared identifier is reported only once include/linux/freezer.h:9: error: for each function it appears in.) include/linux/freezer.h: In function 'freezing': include/linux/freezer.h:17: error: dereferencing pointer to incomplete type include/linux/freezer.h:17: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'freeze': include/linux/freezer.h:26: error: dereferencing pointer to incomplete type include/linux/freezer.h:26: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'do_not_freeze': include/linux/freezer.h:34: error: dereferencing pointer to incomplete type include/linux/freezer.h:34: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'thaw_process': include/linux/freezer.h:43: error: dereferencing pointer to incomplete type include/linux/freezer.h:43: error: 'PF_FROZEN' undeclared (first use in this function) include/linux/freezer.h:44: warning: implicit declaration of function 'wake_up_process' include/linux/freezer.h: In function 'frozen_process': include/linux/freezer.h:55: error: dereferencing pointer to incomplete type include/linux/freezer.h:55: error: dereferencing pointer to incomplete type include/linux/freezer.h:55: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h:55: error: 'PF_FROZEN' undeclared (first use in this function) fs/jfs/jfs_txnmgr.c: In function 'freezing': include/linux/freezer.h:18: warning: control reaches end of non-void function make[2]: *** [fs/jfs/jfs_txnmgr.o] Error 1 Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Acked-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 17:18:58 +07:00
#include <linux/sched.h>
#include <linux/wait.h>
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
#include <linux/atomic.h>
[PATCH] freezer.h uses task_struct fields freezer.h uses task_struct fields so it should include sched.h. CC [M] fs/jfs/jfs_txnmgr.o In file included from fs/jfs/jfs_txnmgr.c:49: include/linux/freezer.h: In function 'frozen': include/linux/freezer.h:9: error: dereferencing pointer to incomplete type include/linux/freezer.h:9: error: 'PF_FROZEN' undeclared (first use in this function) include/linux/freezer.h:9: error: (Each undeclared identifier is reported only once include/linux/freezer.h:9: error: for each function it appears in.) include/linux/freezer.h: In function 'freezing': include/linux/freezer.h:17: error: dereferencing pointer to incomplete type include/linux/freezer.h:17: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'freeze': include/linux/freezer.h:26: error: dereferencing pointer to incomplete type include/linux/freezer.h:26: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'do_not_freeze': include/linux/freezer.h:34: error: dereferencing pointer to incomplete type include/linux/freezer.h:34: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h: In function 'thaw_process': include/linux/freezer.h:43: error: dereferencing pointer to incomplete type include/linux/freezer.h:43: error: 'PF_FROZEN' undeclared (first use in this function) include/linux/freezer.h:44: warning: implicit declaration of function 'wake_up_process' include/linux/freezer.h: In function 'frozen_process': include/linux/freezer.h:55: error: dereferencing pointer to incomplete type include/linux/freezer.h:55: error: dereferencing pointer to incomplete type include/linux/freezer.h:55: error: 'PF_FREEZE' undeclared (first use in this function) include/linux/freezer.h:55: error: 'PF_FROZEN' undeclared (first use in this function) fs/jfs/jfs_txnmgr.c: In function 'freezing': include/linux/freezer.h:18: warning: control reaches end of non-void function make[2]: *** [fs/jfs/jfs_txnmgr.o] Error 1 Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com> Acked-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-10 17:18:58 +07:00
#ifdef CONFIG_FREEZER
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
extern atomic_t system_freezing_cnt; /* nr of freezing conds in effect */
extern bool pm_freezing; /* PM freezing in effect */
extern bool pm_nosig_freezing; /* PM nosig freezing in effect */
/*
* Timeout for stopping processes
*/
extern unsigned int freeze_timeout_msecs;
/*
* Check if a process has been frozen
*/
static inline bool frozen(struct task_struct *p)
{
return p->flags & PF_FROZEN;
}
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
extern bool freezing_slow_path(struct task_struct *p);
/*
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
* Check if there is a request to freeze a process
*/
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
static inline bool freezing(struct task_struct *p)
{
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
if (likely(!atomic_read(&system_freezing_cnt)))
return false;
return freezing_slow_path(p);
}
container freezer: implement freezer cgroup subsystem This patch implements a new freezer subsystem in the control groups framework. It provides a way to stop and resume execution of all tasks in a cgroup by writing in the cgroup filesystem. The freezer subsystem in the container filesystem defines a file named freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the cgroup. Subsequently writing "RUNNING" will unfreeze the tasks in the cgroup. Reading will return the current state. * Examples of usage : # mkdir /containers/freezer # mount -t cgroup -ofreezer freezer /containers # mkdir /containers/0 # echo $some_pid > /containers/0/tasks to get status of the freezer subsystem : # cat /containers/0/freezer.state RUNNING to freeze all tasks in the container : # echo FROZEN > /containers/0/freezer.state # cat /containers/0/freezer.state FREEZING # cat /containers/0/freezer.state FROZEN to unfreeze all tasks in the container : # echo RUNNING > /containers/0/freezer.state # cat /containers/0/freezer.state RUNNING This is the basic mechanism which should do the right thing for user space task in a simple scenario. It's important to note that freezing can be incomplete. In that case we return EBUSY. This means that some tasks in the cgroup are busy doing something that prevents us from completely freezing the cgroup at this time. After EBUSY, the cgroup will remain partially frozen -- reflected by freezer.state reporting "FREEZING" when read. The state will remain "FREEZING" until one of these things happens: 1) Userspace cancels the freezing operation by writing "RUNNING" to the freezer.state file 2) Userspace retries the freezing operation by writing "FROZEN" to the freezer.state file (writing "FREEZING" is not legal and returns EIO) 3) The tasks that blocked the cgroup from entering the "FROZEN" state disappear from the cgroup's set of tasks. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: export thaw_process] Signed-off-by: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Acked-by: Serge E. Hallyn <serue@us.ibm.com> Tested-by: Matt Helsley <matthltc@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 10:27:21 +07:00
/* Takes and releases task alloc lock using task_lock() */
extern void __thaw_task(struct task_struct *t);
extern bool __refrigerator(bool check_kthr_stop);
extern int freeze_processes(void);
extern int freeze_kernel_threads(void);
extern void thaw_processes(void);
extern void thaw_kernel_threads(void);
/*
* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION
* If try_to_freeze causes a lockdep warning it means the caller may deadlock
*/
static inline bool try_to_freeze_unsafe(void)
{
might_sleep();
if (likely(!freezing(current)))
return false;
return __refrigerator(false);
}
static inline bool try_to_freeze(void)
{
if (!(current->flags & PF_NOFREEZE))
debug_check_no_locks_held();
return try_to_freeze_unsafe();
}
extern bool freeze_task(struct task_struct *p);
extern bool set_freezable(void);
container freezer: implement freezer cgroup subsystem This patch implements a new freezer subsystem in the control groups framework. It provides a way to stop and resume execution of all tasks in a cgroup by writing in the cgroup filesystem. The freezer subsystem in the container filesystem defines a file named freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the cgroup. Subsequently writing "RUNNING" will unfreeze the tasks in the cgroup. Reading will return the current state. * Examples of usage : # mkdir /containers/freezer # mount -t cgroup -ofreezer freezer /containers # mkdir /containers/0 # echo $some_pid > /containers/0/tasks to get status of the freezer subsystem : # cat /containers/0/freezer.state RUNNING to freeze all tasks in the container : # echo FROZEN > /containers/0/freezer.state # cat /containers/0/freezer.state FREEZING # cat /containers/0/freezer.state FROZEN to unfreeze all tasks in the container : # echo RUNNING > /containers/0/freezer.state # cat /containers/0/freezer.state RUNNING This is the basic mechanism which should do the right thing for user space task in a simple scenario. It's important to note that freezing can be incomplete. In that case we return EBUSY. This means that some tasks in the cgroup are busy doing something that prevents us from completely freezing the cgroup at this time. After EBUSY, the cgroup will remain partially frozen -- reflected by freezer.state reporting "FREEZING" when read. The state will remain "FREEZING" until one of these things happens: 1) Userspace cancels the freezing operation by writing "RUNNING" to the freezer.state file 2) Userspace retries the freezing operation by writing "FROZEN" to the freezer.state file (writing "FREEZING" is not legal and returns EIO) 3) The tasks that blocked the cgroup from entering the "FROZEN" state disappear from the cgroup's set of tasks. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: export thaw_process] Signed-off-by: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Acked-by: Serge E. Hallyn <serue@us.ibm.com> Tested-by: Matt Helsley <matthltc@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 10:27:21 +07:00
#ifdef CONFIG_CGROUP_FREEZER
extern bool cgroup_freezing(struct task_struct *task);
container freezer: implement freezer cgroup subsystem This patch implements a new freezer subsystem in the control groups framework. It provides a way to stop and resume execution of all tasks in a cgroup by writing in the cgroup filesystem. The freezer subsystem in the container filesystem defines a file named freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the cgroup. Subsequently writing "RUNNING" will unfreeze the tasks in the cgroup. Reading will return the current state. * Examples of usage : # mkdir /containers/freezer # mount -t cgroup -ofreezer freezer /containers # mkdir /containers/0 # echo $some_pid > /containers/0/tasks to get status of the freezer subsystem : # cat /containers/0/freezer.state RUNNING to freeze all tasks in the container : # echo FROZEN > /containers/0/freezer.state # cat /containers/0/freezer.state FREEZING # cat /containers/0/freezer.state FROZEN to unfreeze all tasks in the container : # echo RUNNING > /containers/0/freezer.state # cat /containers/0/freezer.state RUNNING This is the basic mechanism which should do the right thing for user space task in a simple scenario. It's important to note that freezing can be incomplete. In that case we return EBUSY. This means that some tasks in the cgroup are busy doing something that prevents us from completely freezing the cgroup at this time. After EBUSY, the cgroup will remain partially frozen -- reflected by freezer.state reporting "FREEZING" when read. The state will remain "FREEZING" until one of these things happens: 1) Userspace cancels the freezing operation by writing "RUNNING" to the freezer.state file 2) Userspace retries the freezing operation by writing "FROZEN" to the freezer.state file (writing "FREEZING" is not legal and returns EIO) 3) The tasks that blocked the cgroup from entering the "FROZEN" state disappear from the cgroup's set of tasks. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: export thaw_process] Signed-off-by: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Acked-by: Serge E. Hallyn <serue@us.ibm.com> Tested-by: Matt Helsley <matthltc@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 10:27:21 +07:00
#else /* !CONFIG_CGROUP_FREEZER */
static inline bool cgroup_freezing(struct task_struct *task)
Freezer: Fix buggy resume test for tasks frozen with cgroup freezer When the cgroup freezer is used to freeze tasks we do not want to thaw those tasks during resume. Currently we test the cgroup freezer state of the resuming tasks to see if the cgroup is FROZEN. If so then we don't thaw the task. However, the FREEZING state also indicates that the task should remain frozen. This also avoids a problem pointed out by Oren Ladaan: the freezer state transition from FREEZING to FROZEN is updated lazily when userspace reads or writes the freezer.state file in the cgroup filesystem. This means that resume will thaw tasks in cgroups which should be in the FROZEN state if there is no read/write of the freezer.state file to trigger this transition before suspend. NOTE: Another "simple" solution would be to always update the cgroup freezer state during resume. However it's a bad choice for several reasons: Updating the cgroup freezer state is somewhat expensive because it requires walking all the tasks in the cgroup and checking if they are each frozen. Worse, this could easily make resume run in N^2 time where N is the number of tasks in the cgroup. Finally, updating the freezer state from this code path requires trickier locking because of the way locks must be ordered. Instead of updating the freezer state we rely on the fact that lazy updates only manage the transition from FREEZING to FROZEN. We know that a cgroup with the FREEZING state may actually be FROZEN so test for that state too. This makes sense in the resume path even for partially-frozen cgroups -- those that really are FREEZING but not FROZEN. Reported-by: Oren Ladaan <orenl@cs.columbia.edu> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Cc: stable@kernel.org Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
2010-03-27 05:51:44 +07:00
{
return false;
Freezer: Fix buggy resume test for tasks frozen with cgroup freezer When the cgroup freezer is used to freeze tasks we do not want to thaw those tasks during resume. Currently we test the cgroup freezer state of the resuming tasks to see if the cgroup is FROZEN. If so then we don't thaw the task. However, the FREEZING state also indicates that the task should remain frozen. This also avoids a problem pointed out by Oren Ladaan: the freezer state transition from FREEZING to FROZEN is updated lazily when userspace reads or writes the freezer.state file in the cgroup filesystem. This means that resume will thaw tasks in cgroups which should be in the FROZEN state if there is no read/write of the freezer.state file to trigger this transition before suspend. NOTE: Another "simple" solution would be to always update the cgroup freezer state during resume. However it's a bad choice for several reasons: Updating the cgroup freezer state is somewhat expensive because it requires walking all the tasks in the cgroup and checking if they are each frozen. Worse, this could easily make resume run in N^2 time where N is the number of tasks in the cgroup. Finally, updating the freezer state from this code path requires trickier locking because of the way locks must be ordered. Instead of updating the freezer state we rely on the fact that lazy updates only manage the transition from FREEZING to FROZEN. We know that a cgroup with the FREEZING state may actually be FROZEN so test for that state too. This makes sense in the resume path even for partially-frozen cgroups -- those that really are FREEZING but not FROZEN. Reported-by: Oren Ladaan <orenl@cs.columbia.edu> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Cc: stable@kernel.org Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
2010-03-27 05:51:44 +07:00
}
container freezer: implement freezer cgroup subsystem This patch implements a new freezer subsystem in the control groups framework. It provides a way to stop and resume execution of all tasks in a cgroup by writing in the cgroup filesystem. The freezer subsystem in the container filesystem defines a file named freezer.state. Writing "FROZEN" to the state file will freeze all tasks in the cgroup. Subsequently writing "RUNNING" will unfreeze the tasks in the cgroup. Reading will return the current state. * Examples of usage : # mkdir /containers/freezer # mount -t cgroup -ofreezer freezer /containers # mkdir /containers/0 # echo $some_pid > /containers/0/tasks to get status of the freezer subsystem : # cat /containers/0/freezer.state RUNNING to freeze all tasks in the container : # echo FROZEN > /containers/0/freezer.state # cat /containers/0/freezer.state FREEZING # cat /containers/0/freezer.state FROZEN to unfreeze all tasks in the container : # echo RUNNING > /containers/0/freezer.state # cat /containers/0/freezer.state RUNNING This is the basic mechanism which should do the right thing for user space task in a simple scenario. It's important to note that freezing can be incomplete. In that case we return EBUSY. This means that some tasks in the cgroup are busy doing something that prevents us from completely freezing the cgroup at this time. After EBUSY, the cgroup will remain partially frozen -- reflected by freezer.state reporting "FREEZING" when read. The state will remain "FREEZING" until one of these things happens: 1) Userspace cancels the freezing operation by writing "RUNNING" to the freezer.state file 2) Userspace retries the freezing operation by writing "FROZEN" to the freezer.state file (writing "FREEZING" is not legal and returns EIO) 3) The tasks that blocked the cgroup from entering the "FROZEN" state disappear from the cgroup's set of tasks. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: export thaw_process] Signed-off-by: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Matt Helsley <matthltc@us.ibm.com> Acked-by: Serge E. Hallyn <serue@us.ibm.com> Tested-by: Matt Helsley <matthltc@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 10:27:21 +07:00
#endif /* !CONFIG_CGROUP_FREEZER */
/*
* The PF_FREEZER_SKIP flag should be set by a vfork parent right before it
* calls wait_for_completion(&vfork) and reset right after it returns from this
* function. Next, the parent should call try_to_freeze() to freeze itself
* appropriately in case the child has exited before the freezing of tasks is
* complete. However, we don't want kernel threads to be frozen in unexpected
* places, so we allow them to block freeze_processes() instead or to set
* PF_NOFREEZE if needed. Fortunately, in the ____call_usermodehelper() case the
* parent won't really block freeze_processes(), since ____call_usermodehelper()
* (the child) does a little before exec/exit and it can't be frozen before
* waking up the parent.
*/
/**
* freezer_do_not_count - tell freezer to ignore %current
*
* Tell freezers to ignore the current task when determining whether the
* target frozen state is reached. IOW, the current task will be
* considered frozen enough by freezers.
*
* The caller shouldn't do anything which isn't allowed for a frozen task
* until freezer_cont() is called. Usually, freezer[_do_not]_count() pair
* wrap a scheduling operation and nothing much else.
*/
static inline void freezer_do_not_count(void)
{
current->flags |= PF_FREEZER_SKIP;
}
/**
* freezer_count - tell freezer to stop ignoring %current
*
* Undo freezer_do_not_count(). It tells freezers that %current should be
* considered again and tries to freeze if freezing condition is already in
* effect.
*/
static inline void freezer_count(void)
{
current->flags &= ~PF_FREEZER_SKIP;
/*
* If freezing is in progress, the following paired with smp_mb()
* in freezer_should_skip() ensures that either we see %true
* freezing() or freezer_should_skip() sees !PF_FREEZER_SKIP.
*/
smp_mb();
try_to_freeze();
}
/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
static inline void freezer_count_unsafe(void)
{
current->flags &= ~PF_FREEZER_SKIP;
smp_mb();
try_to_freeze_unsafe();
}
/**
* freezer_should_skip - whether to skip a task when determining frozen
* state is reached
* @p: task in quesion
*
* This function is used by freezers after establishing %true freezing() to
* test whether a task should be skipped when determining the target frozen
* state is reached. IOW, if this function returns %true, @p is considered
* frozen enough.
*/
static inline bool freezer_should_skip(struct task_struct *p)
{
/*
* The following smp_mb() paired with the one in freezer_count()
* ensures that either freezer_count() sees %true freezing() or we
* see cleared %PF_FREEZER_SKIP and return %false. This makes it
* impossible for a task to slip frozen state testing after
* clearing %PF_FREEZER_SKIP.
*/
smp_mb();
return p->flags & PF_FREEZER_SKIP;
}
/*
* These functions are intended to be used whenever you want allow a sleeping
* task to be frozen. Note that neither return any clear indication of
* whether a freeze event happened while in this function.
*/
/* Like schedule(), but should not block the freezer. */
static inline void freezable_schedule(void)
{
freezer_do_not_count();
schedule();
freezer_count();
}
/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
static inline void freezable_schedule_unsafe(void)
{
freezer_do_not_count();
schedule();
freezer_count_unsafe();
}
/*
* Like freezable_schedule_timeout(), but should not block the freezer. Do not
* call this with locks held.
*/
static inline long freezable_schedule_timeout(long timeout)
{
long __retval;
freezer_do_not_count();
__retval = schedule_timeout(timeout);
freezer_count();
return __retval;
}
/*
* Like schedule_timeout_interruptible(), but should not block the freezer. Do not
* call this with locks held.
*/
static inline long freezable_schedule_timeout_interruptible(long timeout)
{
long __retval;
freezer_do_not_count();
__retval = schedule_timeout_interruptible(timeout);
freezer_count();
return __retval;
}
/* Like schedule_timeout_killable(), but should not block the freezer. */
static inline long freezable_schedule_timeout_killable(long timeout)
{
long __retval;
freezer_do_not_count();
__retval = schedule_timeout_killable(timeout);
freezer_count();
return __retval;
}
/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
static inline long freezable_schedule_timeout_killable_unsafe(long timeout)
{
long __retval;
freezer_do_not_count();
__retval = schedule_timeout_killable(timeout);
freezer_count_unsafe();
return __retval;
}
/*
* Like schedule_hrtimeout_range(), but should not block the freezer. Do not
* call this with locks held.
*/
static inline int freezable_schedule_hrtimeout_range(ktime_t *expires,
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 04:20:51 +07:00
u64 delta, const enum hrtimer_mode mode)
{
int __retval;
freezer_do_not_count();
__retval = schedule_hrtimeout_range(expires, delta, mode);
freezer_count();
return __retval;
}
/*
* Freezer-friendly wrappers around wait_event_interruptible(),
* wait_event_killable() and wait_event_interruptible_timeout(), originally
* defined in <linux/wait.h>
*/
/* DO NOT ADD ANY NEW CALLERS OF THIS FUNCTION */
#define wait_event_freezekillable_unsafe(wq, condition) \
({ \
int __retval; \
freezer_do_not_count(); \
__retval = wait_event_killable(wq, (condition)); \
freezer_count_unsafe(); \
__retval; \
})
#else /* !CONFIG_FREEZER */
static inline bool frozen(struct task_struct *p) { return false; }
freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE Using TIF_FREEZE for freezing worked when there was only single freezing condition (the PM one); however, now there is also the cgroup_freezer and single bit flag is getting clumsy. thaw_processes() is already testing whether cgroup freezing in in effect to avoid thawing tasks which were frozen by both PM and cgroup freezers. This is racy (nothing prevents race against cgroup freezing) and fragile. A much simpler way is to test actual freeze conditions from freezing() - ie. directly test whether PM or cgroup freezing is in effect. This patch adds variables to indicate whether and what type of freezing conditions are in effect and reimplements freezing() such that it directly tests whether any of the two freezing conditions is active and the task should freeze. On fast path, freezing() is still very cheap - it only tests system_freezing_cnt. This makes the clumsy dancing aroung TIF_FREEZE unnecessary and freeze/thaw operations more usual - updating state variables for the new state and nudging target tasks so that they notice the new state and comply. As long as the nudging happens after state update, it's race-free. * This allows use of freezing() in freeze_task(). Replace the open coded tests with freezing(). * p != current test is added to warning printing conditions in try_to_freeze_tasks() failure path. This is necessary as freezing() is now true for the task which initiated freezing too. -v2: Oleg pointed out that re-freezing FROZEN cgroup could increment system_freezing_cnt. Fixed. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Paul Menage <paul@paulmenage.org> (for the cgroup portions)
2011-11-22 03:32:25 +07:00
static inline bool freezing(struct task_struct *p) { return false; }
static inline void __thaw_task(struct task_struct *t) {}
static inline bool __refrigerator(bool check_kthr_stop) { return false; }
static inline int freeze_processes(void) { return -ENOSYS; }
static inline int freeze_kernel_threads(void) { return -ENOSYS; }
static inline void thaw_processes(void) {}
static inline void thaw_kernel_threads(void) {}
static inline bool try_to_freeze_nowarn(void) { return false; }
static inline bool try_to_freeze(void) { return false; }
static inline void freezer_do_not_count(void) {}
static inline void freezer_count(void) {}
static inline int freezer_should_skip(struct task_struct *p) { return 0; }
static inline void set_freezable(void) {}
#define freezable_schedule() schedule()
#define freezable_schedule_unsafe() schedule()
#define freezable_schedule_timeout(timeout) schedule_timeout(timeout)
#define freezable_schedule_timeout_interruptible(timeout) \
schedule_timeout_interruptible(timeout)
#define freezable_schedule_timeout_killable(timeout) \
schedule_timeout_killable(timeout)
#define freezable_schedule_timeout_killable_unsafe(timeout) \
schedule_timeout_killable(timeout)
#define freezable_schedule_hrtimeout_range(expires, delta, mode) \
schedule_hrtimeout_range(expires, delta, mode)
#define wait_event_freezekillable_unsafe(wq, condition) \
wait_event_killable(wq, condition)
#endif /* !CONFIG_FREEZER */
#endif /* FREEZER_H_INCLUDED */