Commit db0c2bf6 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup 

* 'for-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
  cgroup: fix to allow mounting a hierarchy by name
  cgroup: move assignement out of condition in cgroup_attach_proc()
  cgroup: Remove task_lock() from cgroup_post_fork()
  cgroup: add sparse annotation to cgroup_iter_start() and cgroup_iter_end()
  cgroup: mark cgroup_rmdir_waitq and cgroup_attach_proc() as static
  cgroup: only need to check oldcgrp==newgrp once
  cgroup: remove redundant get/put of task struct
  cgroup: remove redundant get/put of old css_set from migrate
  cgroup: Remove unnecessary task_lock before fetching css_set on migration
  cgroup: Drop task_lock(parent) on cgroup_fork()
  cgroups: remove redundant get/put of css_set from css_set_check_fetched()
  resource cgroups: remove bogus cast
  cgroup: kill subsys->can_attach_task(), pre_attach() and attach_task()
  cgroup, cpuset: don't use ss->pre_attach()
  cgroup: don't use subsys->can_attach_task() or ->attach_task()
  cgroup: introduce cgroup_taskset and use it in subsys->can_attach(), cancel_attach() and attach()
  cgroup: improve old cgroup handling in cgroup_attach_proc()
  cgroup: always lock threadgroup during migration
  threadgroup: extend threadgroup_lock() to cover exit and exec
  threadgroup: rename signal->threadgroup_fork_lock to ->group_rwsem
  ...

Fix up conflict in kernel/cgroup.c due to commit e0197aae: "cgroups:
fix a css_set not found bug in cgroup_attach_proc" that already
mentioned that the bug is fixed (differently) in Tejun's cgroup
patchset. This one, in other words.
parents ac69e092 0d19ea86

Documentation/cgroups/cgroups.txt

+21 −30
Original line number Diff line number Diff line
@@ -594,53 +594,44 @@ rmdir() will fail with it. From this behavior, pre_destroy() can be 
called multiple times against a cgroup.



int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,

	       struct task_struct *task)

	       struct cgroup_taskset *tset)

(cgroup_mutex held by caller)



Called prior to moving a task into a cgroup; if the subsystem

returns an error, this will abort the attach operation.  If a NULL

task is passed, then a successful result indicates that *any*

unspecified task can be moved into the cgroup. Note that this isn't

called on a fork. If this method returns 0 (success) then this should

remain valid while the caller holds cgroup_mutex and it is ensured that either

Called prior to moving one or more tasks into a cgroup; if the

subsystem returns an error, this will abort the attach operation.

@tset contains the tasks to be attached and is guaranteed to have at

least one task in it.



If there are multiple tasks in the taskset, then:

  - it's guaranteed that all are from the same thread group

  - @tset contains all tasks from the thread group whether or not

    they're switching cgroups

  - the first task is the leader



Each @tset entry also contains the task's old cgroup and tasks which

aren't switching cgroup can be skipped easily using the

cgroup_taskset_for_each() iterator. Note that this isn't called on a

fork. If this method returns 0 (success) then this should remain valid

while the caller holds cgroup_mutex and it is ensured that either

attach() or cancel_attach() will be called in future.



int can_attach_task(struct cgroup *cgrp, struct task_struct *tsk);

(cgroup_mutex held by caller)



As can_attach, but for operations that must be run once per task to be

attached (possibly many when using cgroup_attach_proc). Called after

can_attach.



void cancel_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,

	       struct task_struct *task, bool threadgroup)

		   struct cgroup_taskset *tset)

(cgroup_mutex held by caller)



Called when a task attach operation has failed after can_attach() has succeeded.

A subsystem whose can_attach() has some side-effects should provide this

function, so that the subsystem can implement a rollback. If not, not necessary.

This will be called only about subsystems whose can_attach() operation have

succeeded.



void pre_attach(struct cgroup *cgrp);

(cgroup_mutex held by caller)



For any non-per-thread attachment work that needs to happen before

attach_task. Needed by cpuset.

succeeded. The parameters are identical to can_attach().



void attach(struct cgroup_subsys *ss, struct cgroup *cgrp,

	    struct cgroup *old_cgrp, struct task_struct *task)

	    struct cgroup_taskset *tset)

(cgroup_mutex held by caller)



Called after the task has been attached to the cgroup, to allow any

post-attachment activity that requires memory allocations or blocking.



void attach_task(struct cgroup *cgrp, struct task_struct *tsk);

(cgroup_mutex held by caller)



As attach, but for operations that must be run once per task to be attached,

like can_attach_task. Called before attach. Currently does not support any

subsystem that might need the old_cgrp for every thread in the group.

The parameters are identical to can_attach().



void fork(struct cgroup_subsy *ss, struct task_struct *task)

block/blk-cgroup.c

+28 −17
Original line number Diff line number Diff line
@@ -30,8 +30,10 @@ EXPORT_SYMBOL_GPL(blkio_root_cgroup); 


static struct cgroup_subsys_state *blkiocg_create(struct cgroup_subsys *,

						  struct cgroup *);

static int blkiocg_can_attach_task(struct cgroup *, struct task_struct *);

static void blkiocg_attach_task(struct cgroup *, struct task_struct *);

static int blkiocg_can_attach(struct cgroup_subsys *, struct cgroup *,

			      struct cgroup_taskset *);

static void blkiocg_attach(struct cgroup_subsys *, struct cgroup *,

			   struct cgroup_taskset *);

static void blkiocg_destroy(struct cgroup_subsys *, struct cgroup *);

static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *);
@@ -44,8 +46,8 @@ static int blkiocg_populate(struct cgroup_subsys *, struct cgroup *); 
struct cgroup_subsys blkio_subsys = {

	.name = "blkio",

	.create = blkiocg_create,

	.can_attach_task = blkiocg_can_attach_task,

	.attach_task = blkiocg_attach_task,

	.can_attach = blkiocg_can_attach,

	.attach = blkiocg_attach,

	.destroy = blkiocg_destroy,

	.populate = blkiocg_populate,

#ifdef CONFIG_BLK_CGROUP
@@ -1626,30 +1628,39 @@ done: 
 * of the main cic data structures.  For now we allow a task to change

 * its cgroup only if it's the only owner of its ioc.

 */

static int blkiocg_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk)

static int blkiocg_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,

			      struct cgroup_taskset *tset)

{

	struct task_struct *task;

	struct io_context *ioc;

	int ret = 0;



	/* task_lock() is needed to avoid races with exit_io_context() */

	task_lock(tsk);

	ioc = tsk->io_context;

	cgroup_taskset_for_each(task, cgrp, tset) {

		task_lock(task);

		ioc = task->io_context;

		if (ioc && atomic_read(&ioc->nr_tasks) > 1)

			ret = -EINVAL;

	task_unlock(tsk);



		task_unlock(task);

		if (ret)

			break;

	}

	return ret;

}



static void blkiocg_attach_task(struct cgroup *cgrp, struct task_struct *tsk)

static void blkiocg_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,

			   struct cgroup_taskset *tset)

{

	struct task_struct *task;

	struct io_context *ioc;



	task_lock(tsk);

	ioc = tsk->io_context;

	cgroup_taskset_for_each(task, cgrp, tset) {

		task_lock(task);

		ioc = task->io_context;

		if (ioc)

			ioc->cgroup_changed = 1;

	task_unlock(tsk);

		task_unlock(task);

	}

}



void blkio_policy_register(struct blkio_policy_type *blkiop)

include/linux/cgroup.h

+25 −6
Original line number Diff line number Diff line
@@ -456,6 +456,28 @@ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); 
void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);

void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);



/*

 * Control Group taskset, used to pass around set of tasks to cgroup_subsys

 * methods.

 */

struct cgroup_taskset;

struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);

struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);

struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset);

int cgroup_taskset_size(struct cgroup_taskset *tset);



/**

 * cgroup_taskset_for_each - iterate cgroup_taskset

 * @task: the loop cursor

 * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all

 * @tset: taskset to iterate

 */

#define cgroup_taskset_for_each(task, skip_cgrp, tset)			\

	for ((task) = cgroup_taskset_first((tset)); (task);		\

	     (task) = cgroup_taskset_next((tset)))			\

		if (!(skip_cgrp) ||					\

		    cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp))



/*

 * Control Group subsystem type.

 * See Documentation/cgroups/cgroups.txt for details
@@ -467,14 +489,11 @@ struct cgroup_subsys { 
	int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);

	void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);

	int (*can_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,

			  struct task_struct *tsk);

	int (*can_attach_task)(struct cgroup *cgrp, struct task_struct *tsk);

			  struct cgroup_taskset *tset);

	void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,

			      struct task_struct *tsk);

	void (*pre_attach)(struct cgroup *cgrp);

	void (*attach_task)(struct cgroup *cgrp, struct task_struct *tsk);

			      struct cgroup_taskset *tset);

	void (*attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,

		       struct cgroup *old_cgrp, struct task_struct *tsk);

		       struct cgroup_taskset *tset);

	void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);

	void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,

			struct cgroup *old_cgrp, struct task_struct *task);

include/linux/init_task.h

+4 −5
Original line number Diff line number Diff line
@@ -23,11 +23,10 @@ extern struct files_struct init_files; 
extern struct fs_struct init_fs;



#ifdef CONFIG_CGROUPS

#define INIT_THREADGROUP_FORK_LOCK(sig)					\

	.threadgroup_fork_lock =					\

		__RWSEM_INITIALIZER(sig.threadgroup_fork_lock),

#define INIT_GROUP_RWSEM(sig)						\

	.group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),

#else

#define INIT_THREADGROUP_FORK_LOCK(sig)

#define INIT_GROUP_RWSEM(sig)

#endif



#define INIT_SIGNALS(sig) {						\
@@ -46,7 +45,7 @@ extern struct fs_struct init_fs; 
	},								\

	.cred_guard_mutex =						\

		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\

	INIT_THREADGROUP_FORK_LOCK(sig)					\

	INIT_GROUP_RWSEM(sig)						\

}



extern struct nsproxy init_nsproxy;

include/linux/sched.h

+54 −19
Original line number Diff line number Diff line
@@ -637,13 +637,15 @@ struct signal_struct { 
#endif

#ifdef CONFIG_CGROUPS

	/*

	 * The threadgroup_fork_lock prevents threads from forking with

	 * CLONE_THREAD while held for writing. Use this for fork-sensitive

	 * threadgroup-wide operations. It's taken for reading in fork.c in

	 * copy_process().

	 * Currently only needed write-side by cgroups.

	 * group_rwsem prevents new tasks from entering the threadgroup and

	 * member tasks from exiting,a more specifically, setting of

	 * PF_EXITING.  fork and exit paths are protected with this rwsem

	 * using threadgroup_change_begin/end().  Users which require

	 * threadgroup to remain stable should use threadgroup_[un]lock()

	 * which also takes care of exec path.  Currently, cgroup is the

	 * only user.

	 */

	struct rw_semaphore threadgroup_fork_lock;

	struct rw_semaphore group_rwsem;

#endif



	int oom_adj;		/* OOM kill score adjustment (bit shift) */
@@ -2394,29 +2396,62 @@ static inline void unlock_task_sighand(struct task_struct *tsk, 
	spin_unlock_irqrestore(&tsk->sighand->siglock, *flags);

}



/* See the declaration of threadgroup_fork_lock in signal_struct. */

#ifdef CONFIG_CGROUPS

static inline void threadgroup_fork_read_lock(struct task_struct *tsk)

static inline void threadgroup_change_begin(struct task_struct *tsk)

{

	down_read(&tsk->signal->threadgroup_fork_lock);

	down_read(&tsk->signal->group_rwsem);

}

static inline void threadgroup_fork_read_unlock(struct task_struct *tsk)

static inline void threadgroup_change_end(struct task_struct *tsk)

{

	up_read(&tsk->signal->threadgroup_fork_lock);

	up_read(&tsk->signal->group_rwsem);

}

static inline void threadgroup_fork_write_lock(struct task_struct *tsk)



/**

 * threadgroup_lock - lock threadgroup

 * @tsk: member task of the threadgroup to lock

 *

 * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter

 * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or

 * perform exec.  This is useful for cases where the threadgroup needs to

 * stay stable across blockable operations.

 *

 * fork and exit paths explicitly call threadgroup_change_{begin|end}() for

 * synchronization.  While held, no new task will be added to threadgroup

 * and no existing live task will have its PF_EXITING set.

 *

 * During exec, a task goes and puts its thread group through unusual

 * changes.  After de-threading, exclusive access is assumed to resources

 * which are usually shared by tasks in the same group - e.g. sighand may

 * be replaced with a new one.  Also, the exec'ing task takes over group

 * leader role including its pid.  Exclude these changes while locked by

 * grabbing cred_guard_mutex which is used to synchronize exec path.

 */

static inline void threadgroup_lock(struct task_struct *tsk)

{

	down_write(&tsk->signal->threadgroup_fork_lock);

	/*

	 * exec uses exit for de-threading nesting group_rwsem inside

	 * cred_guard_mutex. Grab cred_guard_mutex first.

	 */

	mutex_lock(&tsk->signal->cred_guard_mutex);

	down_write(&tsk->signal->group_rwsem);

}

static inline void threadgroup_fork_write_unlock(struct task_struct *tsk)



/**

 * threadgroup_unlock - unlock threadgroup

 * @tsk: member task of the threadgroup to unlock

 *

 * Reverse threadgroup_lock().

 */

static inline void threadgroup_unlock(struct task_struct *tsk)

{

	up_write(&tsk->signal->threadgroup_fork_lock);

	up_write(&tsk->signal->group_rwsem);

	mutex_unlock(&tsk->signal->cred_guard_mutex);

}

#else

static inline void threadgroup_fork_read_lock(struct task_struct *tsk) {}

static inline void threadgroup_fork_read_unlock(struct task_struct *tsk) {}

static inline void threadgroup_fork_write_lock(struct task_struct *tsk) {}

static inline void threadgroup_fork_write_unlock(struct task_struct *tsk) {}

static inline void threadgroup_change_begin(struct task_struct *tsk) {}

static inline void threadgroup_change_end(struct task_struct *tsk) {}

static inline void threadgroup_lock(struct task_struct *tsk) {}

static inline void threadgroup_unlock(struct task_struct *tsk) {}

#endif



#ifndef __HAVE_THREAD_FUNCTIONS

CRA Git | Maintained and supported by SUSTech CRA and CCSE