cgroup: use cgroup_subsys_state as the primary subsystem interface handle

cgroup is currently in the process of transitioning to using css (cgroup_subsys_state) as the primary handle instead of cgroup in subsystem API. For hierarchy iterators, this is beneficial because

* In most cases, css is the only thing subsystems care about anyway.

* On the planned unified hierarchy, iterations for different subsystems will need to skip over different subtrees of the hierarchy depending on which subsystems are enabled on each cgroup. Passing around css makes it unnecessary to explicitly specify the subsystem in question as css is intersection between cgroup and subsystem

* For the planned unified hierarchy, css's would need to be created and destroyed dynamically independent from cgroup hierarchy. Having cgroup core manage css iteration makes enforcing deref rules a lot easier.

Most subsystem conversions are straight-forward. Noteworthy changes are

* blkio: cgroup_to_blkcg() is no longer used. Removed.

* freezer: cgroup_freezer() is no longer used. Removed.

* devices: cgroup_to_devcgroup() is no longer used. Removed.

Signed-off-by Tejun Heo <[email protected]>

Cc Li Zefan <[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Balbir Singh <[email protected]>

Cc Aristeu Rozanski <[email protected]>

Cc Matt Helsley <matthltc-r/[email protected]>

Cc Vivek Goyal <[email protected]>

Cc Jens Axboe <axboe-tSWWG44O7X1aa/[email protected]>

---
 block/blk-cgroup.c       |   8 +--
 block/blk-cgroup.h       |  25 ++++-----
 block/blk-throttle.c     |   8 +--
 include/linux/cgroup.h   |  88 ++++++++++++++++---------------
 kernel/cgroup.c          | 131 ++++++++++++++++++++++++++---------------------
 kernel/cgroup_freezer.c  |  25 ++++-----
 kernel/cpuset.c          |  58 ++++++++++-----------
 mm/memcontrol.c          |  20 ++++----
 security/device_cgroup.c |  11 ++--
 9 files changed, 187 insertions(+), 187 deletions(-)

block/blk-cgroup.c +4 -4

index f46f3c6..4b40640 100644
@@ -614,7 +614,7 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off)
 {
 	struct blkcg_policy *pol = blkcg_policy[pd->plid];
 	struct blkcg_gq *pos_blkg;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 	u64 sum;
 
 	lockdep_assert_held(pd->blkg->q->queue_lock);

@@ -622,7 +622,7 @@ u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off)
 	sum = blkg_stat_read((void *)pd + off);
 
 	rcu_read_lock();
-	blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) {
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
 		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
 		struct blkg_stat *stat = (void *)pos_pd + off;
 

@@ -649,7 +649,7 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd,
 {
 	struct blkcg_policy *pol = blkcg_policy[pd->plid];
 	struct blkcg_gq *pos_blkg;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 	struct blkg_rwstat sum;
 	int i;
 

@@ -658,7 +658,7 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd,
 	sum = blkg_rwstat_read((void *)pd + off);
 
 	rcu_read_lock();
-	blkg_for_each_descendant_pre(pos_blkg, pos_cgrp, pd_to_blkg(pd)) {
+	blkg_for_each_descendant_pre(pos_blkg, pos_css, pd_to_blkg(pd)) {
 		struct blkg_policy_data *pos_pd = blkg_to_pd(pos_blkg, pol);
 		struct blkg_rwstat *rwstat = (void *)pos_pd + off;
 		struct blkg_rwstat tmp;

block/blk-cgroup.h +9 -16

index b6802c4..8555386 100644
@@ -184,11 +184,6 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 	return css ? container_of(css, struct blkcg, css) : NULL;
 }
 
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup)
-{
-	return css_to_blkcg(cgroup_css(cgroup, blkio_subsys_id));
-}
-
 static inline struct blkcg *task_blkcg(struct task_struct *tsk)
 {
 	return css_to_blkcg(task_css(tsk, blkio_subsys_id));

@@ -289,32 +284,31 @@ struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q,
 /**
  * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants
  * @d_blkg: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
  * @p_blkg: target blkg to walk descendants of
  *
  * Walk @c_blkg through the descendants of @p_blkg.  Must be used with RCU
  * read locked.  If called under either blkcg or queue lock, the iteration
  * is guaranteed to include all and only online blkgs.  The caller may
- * update @pos_cgrp by calling cgroup_rightmost_descendant() to skip
- * subtree.
+ * update @pos_css by calling css_rightmost_descendant() to skip subtree.
  */
-#define blkg_for_each_descendant_pre(d_blkg, pos_cgrp, p_blkg)		\
-	cgroup_for_each_descendant_pre((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
-		if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
+#define blkg_for_each_descendant_pre(d_blkg, pos_css, p_blkg)		\
+	css_for_each_descendant_pre((pos_css), &(p_blkg)->blkcg->css)	\
+		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
 /**
  * blkg_for_each_descendant_post - post-order walk of a blkg's descendants
  * @d_blkg: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
  * @p_blkg: target blkg to walk descendants of
  *
  * Similar to blkg_for_each_descendant_pre() but performs post-order
  * traversal instead.  Synchronization rules are the same.
  */
-#define blkg_for_each_descendant_post(d_blkg, pos_cgrp, p_blkg)		\
-	cgroup_for_each_descendant_post((pos_cgrp), (p_blkg)->blkcg->css.cgroup) \
-		if (((d_blkg) = __blkg_lookup(cgroup_to_blkcg(pos_cgrp), \
+#define blkg_for_each_descendant_post(d_blkg, pos_css, p_blkg)		\
+	css_for_each_descendant_post((pos_css), &(p_blkg)->blkcg->css)	\
+		if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css),	\
 					      (p_blkg)->q, false)))
 
 /**

@@ -577,7 +571,6 @@ static inline int blkcg_activate_policy(struct request_queue *q,
 static inline void blkcg_deactivate_policy(struct request_queue *q,
 					   const struct blkcg_policy *pol) { }
 
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
 static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
 
 static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,

block/blk-throttle.c +4 -4

index 88bcfb6..8cefa7f 100644
@@ -1349,7 +1349,7 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 	struct throtl_grp *tg;
 	struct throtl_service_queue *sq;
 	struct blkcg_gq *blkg;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 	int ret;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);

@@ -1380,7 +1380,7 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 	 * blk-throttle.
 	 */
 	tg_update_has_rules(tg);
-	blkg_for_each_descendant_pre(blkg, pos_cgrp, ctx.blkg)
+	blkg_for_each_descendant_pre(blkg, pos_css, ctx.blkg)
 		tg_update_has_rules(blkg_to_tg(blkg));
 
 	/*

@@ -1623,7 +1623,7 @@ void blk_throtl_drain(struct request_queue *q)
 {
 	struct throtl_data *td = q->td;
 	struct blkcg_gq *blkg;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 	struct bio *bio;
 	int rw;
 

@@ -1636,7 +1636,7 @@ void blk_throtl_drain(struct request_queue *q)
 	 * better to walk service_queue tree directly but blkg walk is
 	 * easier.
 	 */
-	blkg_for_each_descendant_post(blkg, pos_cgrp, td->queue->root_blkg)
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg)
 		tg_drain_bios(&blkg_to_tg(blkg)->service_queue);
 
 	tg_drain_bios(&td_root_tg(td)->service_queue);

include/linux/cgroup.h +46 -42

index df6ab19..7fba0d0 100644
@@ -780,68 +780,72 @@ static inline struct cgroup *cgroup_from_id(struct cgroup_subsys *ss, int id)
 	return idr_find(&ss->root->cgroup_idr, id);
 }
 
-struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp);
+struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
+					   struct cgroup_subsys_state *parent);
 
 /**
- * cgroup_for_each_child - iterate through children of a cgroup
- * @pos: the cgroup * to use as the loop cursor
- * @cgrp: cgroup whose children to walk
+ * css_for_each_child - iterate through children of a css
+ * @pos: the css * to use as the loop cursor
+ * @parent: css whose children to walk
  *
- * Walk @cgrp's children.  Must be called under rcu_read_lock().  A child
- * cgroup which hasn't finished ->css_online() or already has finished
+ * Walk @parent's children.  Must be called under rcu_read_lock().  A child
+ * css which hasn't finished ->css_online() or already has finished
  * ->css_offline() may show up during traversal and it's each subsystem's
  * responsibility to verify that each @pos is alive.
  *
  * If a subsystem synchronizes against the parent in its ->css_online() and
- * before starting iterating, a cgroup which finished ->css_online() is
+ * before starting iterating, a css which finished ->css_online() is
  * guaranteed to be visible in the future iterations.
  *
  * It is allowed to temporarily drop RCU read lock during iteration.  The
  * caller is responsible for ensuring that @pos remains accessible until
  * the start of the next iteration by, for example, bumping the css refcnt.
  */
-#define cgroup_for_each_child(pos, cgrp)				\
-	for ((pos) = cgroup_next_child(NULL, (cgrp)); (pos);		\
-	     (pos) = cgroup_next_child((pos), (cgrp)))
+#define css_for_each_child(pos, parent)					\
+	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
+	     (pos) = css_next_child((pos), (parent)))
 
-struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
-					  struct cgroup *cgroup);
-struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos);
+struct cgroup_subsys_state *
+css_next_descendant_pre(struct cgroup_subsys_state *pos,
+			struct cgroup_subsys_state *css);
+
+struct cgroup_subsys_state *
+css_rightmost_descendant(struct cgroup_subsys_state *pos);
 
 /**
- * cgroup_for_each_descendant_pre - pre-order walk of a cgroup's descendants
- * @pos: the cgroup * to use as the loop cursor
- * @cgroup: cgroup whose descendants to walk
+ * css_for_each_descendant_pre - pre-order walk of a css's descendants
+ * @pos: the css * to use as the loop cursor
+ * @root: css whose descendants to walk
  *
- * Walk @cgroup's descendants.  Must be called under rcu_read_lock().  A
- * descendant cgroup which hasn't finished ->css_online() or already has
+ * Walk @root's descendants.  Must be called under rcu_read_lock().  A
+ * descendant css which hasn't finished ->css_online() or already has
  * finished ->css_offline() may show up during traversal and it's each
  * subsystem's responsibility to verify that each @pos is alive.
  *
  * If a subsystem synchronizes against the parent in its ->css_online() and
  * before starting iterating, and synchronizes against @pos on each
- * iteration, any descendant cgroup which finished ->css_online() is
+ * iteration, any descendant css which finished ->css_online() is
  * guaranteed to be visible in the future iterations.
  *
  * In other words, the following guarantees that a descendant can't escape
  * state updates of its ancestors.
  *
- * my_online(@cgrp)
+ * my_online(@css)
  * {
- *	Lock @cgrp->parent and @cgrp;
- *	Inherit state from @cgrp->parent;
+ *	Lock @css's parent and @css;
+ *	Inherit state from the parent;
  *	Unlock both.
  * }
  *
- * my_update_state(@cgrp)
+ * my_update_state(@css)
  * {
- *	Lock @cgrp;
- *	Update @cgrp's state;
- *	Unlock @cgrp;
+ *	Lock @css;
+ *	Update @css's state;
+ *	Unlock @css;
  *
- *	cgroup_for_each_descendant_pre(@pos, @cgrp) {
+ *	css_for_each_descendant_pre(@pos, @css) {
  *		Lock @pos;
- *		Verify @pos is alive and inherit state from @pos->parent;
+ *		Verify @pos is alive and inherit state from @pos's parent;
  *		Unlock @pos;
  *	}
  * }

@@ -852,8 +856,7 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos);
  * visible by walking order and, as long as inheriting operations to the
  * same @pos are atomic to each other, multiple updates racing each other
  * still result in the correct state.  It's guaranateed that at least one
- * inheritance happens for any cgroup after the latest update to its
- * parent.
+ * inheritance happens for any css after the latest update to its parent.
  *
  * If checking parent's state requires locking the parent, each inheriting
  * iteration should lock and unlock both @pos->parent and @pos.

@@ -866,25 +869,26 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos);
  * caller is responsible for ensuring that @pos remains accessible until
  * the start of the next iteration by, for example, bumping the css refcnt.
  */
-#define cgroup_for_each_descendant_pre(pos, cgroup)			\
-	for (pos = cgroup_next_descendant_pre(NULL, (cgroup)); (pos);	\
-	     pos = cgroup_next_descendant_pre((pos), (cgroup)))
+#define css_for_each_descendant_pre(pos, css)				\
+	for ((pos) = css_next_descendant_pre(NULL, (css)); (pos);	\
+	     (pos) = css_next_descendant_pre((pos), (css)))
 
-struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
-					   struct cgroup *cgroup);
+struct cgroup_subsys_state *
+css_next_descendant_post(struct cgroup_subsys_state *pos,
+			 struct cgroup_subsys_state *css);
 
 /**
- * cgroup_for_each_descendant_post - post-order walk of a cgroup's descendants
- * @pos: the cgroup * to use as the loop cursor
- * @cgroup: cgroup whose descendants to walk
+ * css_for_each_descendant_post - post-order walk of a css's descendants
+ * @pos: the css * to use as the loop cursor
+ * @css: css whose descendants to walk
  *
- * Similar to cgroup_for_each_descendant_pre() but performs post-order
+ * Similar to css_for_each_descendant_pre() but performs post-order
  * traversal instead.  Note that the walk visibility guarantee described in
  * pre-order walk doesn't apply the same to post-order walks.
  */
-#define cgroup_for_each_descendant_post(pos, cgroup)			\
-	for (pos = cgroup_next_descendant_post(NULL, (cgroup)); (pos);	\
-	     pos = cgroup_next_descendant_post((pos), (cgroup)))
+#define css_for_each_descendant_post(pos, css)				\
+	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
+	     (pos) = css_next_descendant_post((pos), (css)))
 
 /* A cgroup_iter should be treated as an opaque object */
 struct cgroup_iter {

kernel/cgroup.c +73 -58

index 7b53b58..850ad87 100644
@@ -2807,8 +2807,8 @@ static void cgroup_cfts_prepare(void)
 	/*
 	 * Thanks to the entanglement with vfs inode locking, we can't walk
 	 * the existing cgroups under cgroup_mutex and create files.
-	 * Instead, we use cgroup_for_each_descendant_pre() and drop RCU
-	 * read lock before calling cgroup_addrm_files().
+	 * Instead, we use css_for_each_descendant_pre() and drop RCU read
+	 * lock before calling cgroup_addrm_files().
 	 */
 	mutex_lock(&cgroup_mutex);
 }

@@ -2818,10 +2818,11 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 {
 	LIST_HEAD(pending);
 	struct cgroup_subsys *ss = cfts[0].ss;
-	struct cgroup *cgrp, *root = &ss->root->top_cgroup;
+	struct cgroup *root = &ss->root->top_cgroup;
 	struct super_block *sb = ss->root->sb;
 	struct dentry *prev = NULL;
 	struct inode *inode;
+	struct cgroup_subsys_state *css;
 	u64 update_before;
 	int ret = 0;
 

@@ -2854,7 +2855,9 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 
 	/* add/rm files for all cgroups created before */
 	rcu_read_lock();
-	cgroup_for_each_descendant_pre(cgrp, root) {
+	css_for_each_descendant_pre(css, cgroup_css(root, ss->subsys_id)) {
+		struct cgroup *cgrp = css->cgroup;
+
 		if (cgroup_is_dead(cgrp))
 			continue;
 

@@ -3030,17 +3033,21 @@ static void cgroup_enable_task_cg_lists(void)
 }
 
 /**
- * cgroup_next_child - find the next child of a given cgroup
- * @pos: the current position (%NULL to initiate traversal)
- * @cgrp: cgroup whose descendants to walk
+ * css_next_child - find the next child of a given css
+ * @pos_css: the current position (%NULL to initiate traversal)
+ * @parent_css: css whose children to walk
  *
- * This function returns the next child of @cgrp and should be called under
- * RCU read lock.  The only requirement is that @cgrp and @pos are
- * accessible.  The next sibling is guaranteed to be returned regardless of
- * their states.
+ * This function returns the next child of @parent_css and should be called
+ * under RCU read lock.  The only requirement is that @parent_css and
+ * @pos_css are accessible.  The next sibling is guaranteed to be returned
+ * regardless of their states.
  */
-struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp)
+struct cgroup_subsys_state *
+css_next_child(struct cgroup_subsys_state *pos_css,
+	       struct cgroup_subsys_state *parent_css)
 {
+	struct cgroup *pos = pos_css ? pos_css->cgroup : NULL;
+	struct cgroup *cgrp = parent_css->cgroup;
 	struct cgroup *next;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());

@@ -3074,59 +3081,64 @@ struct cgroup *cgroup_next_child(struct cgroup *pos, struct cgroup *cgrp)
 				break;
 	}
 
-	if (&next->sibling != &cgrp->children)
-		return next;
-	return NULL;
+	if (&next->sibling == &cgrp->children)
+		return NULL;
+
+	if (parent_css->ss)
+		return cgroup_css(next, parent_css->ss->subsys_id);
+	else
+		return &next->dummy_css;
 }
-EXPORT_SYMBOL_GPL(cgroup_next_child);
+EXPORT_SYMBOL_GPL(css_next_child);
 
 /**
- * cgroup_next_descendant_pre - find the next descendant for pre-order walk
+ * css_next_descendant_pre - find the next descendant for pre-order walk
  * @pos: the current position (%NULL to initiate traversal)
- * @cgroup: cgroup whose descendants to walk
+ * @root: css whose descendants to walk
  *
- * To be used by cgroup_for_each_descendant_pre().  Find the next
- * descendant to visit for pre-order traversal of @cgroup's descendants.
+ * To be used by css_for_each_descendant_pre().  Find the next descendant
+ * to visit for pre-order traversal of @root's descendants.
  *
  * While this function requires RCU read locking, it doesn't require the
  * whole traversal to be contained in a single RCU critical section.  This
  * function will return the correct next descendant as long as both @pos
- * and @cgroup are accessible and @pos is a descendant of @cgroup.
+ * and @root are accessible and @pos is a descendant of @root.
  */
-struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos,
-					  struct cgroup *cgroup)
+struct cgroup_subsys_state *
+css_next_descendant_pre(struct cgroup_subsys_state *pos,
+			struct cgroup_subsys_state *root)
 {
-	struct cgroup *next;
+	struct cgroup_subsys_state *next;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	/* if first iteration, pretend we just visited @cgroup */
+	/* if first iteration, pretend we just visited @root */
 	if (!pos)
-		pos = cgroup;
+		pos = root;
 
 	/* visit the first child if exists */
-	next = cgroup_next_child(NULL, pos);
+	next = css_next_child(NULL, pos);
 	if (next)
 		return next;
 
 	/* no child, visit my or the closest ancestor's next sibling */
-	while (pos != cgroup) {
-		next = cgroup_next_child(pos, pos->parent);
+	while (pos != root) {
+		next = css_next_child(pos, css_parent(pos));
 		if (next)
 			return next;
-		pos = pos->parent;
+		pos = css_parent(pos);
 	}
 
 	return NULL;
 }
-EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre);
+EXPORT_SYMBOL_GPL(css_next_descendant_pre);
 
 /**
- * cgroup_rightmost_descendant - return the rightmost descendant of a cgroup
- * @pos: cgroup of interest
+ * css_rightmost_descendant - return the rightmost descendant of a css
+ * @pos: css of interest
  *
- * Return the rightmost descendant of @pos.  If there's no descendant,
- * @pos is returned.  This can be used during pre-order traversal to skip
+ * Return the rightmost descendant of @pos.  If there's no descendant, @pos
+ * is returned.  This can be used during pre-order traversal to skip
  * subtree of @pos.
  *
  * While this function requires RCU read locking, it doesn't require the

@@ -3134,9 +3146,10 @@ EXPORT_SYMBOL_GPL(cgroup_next_descendant_pre);
  * function will return the correct rightmost descendant as long as @pos is
  * accessible.
  */
-struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos)
+struct cgroup_subsys_state *
+css_rightmost_descendant(struct cgroup_subsys_state *pos)
 {
-	struct cgroup *last, *tmp;
+	struct cgroup_subsys_state *last, *tmp;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 

@@ -3144,62 +3157,64 @@ struct cgroup *cgroup_rightmost_descendant(struct cgroup *pos)
 		last = pos;
 		/* ->prev isn't RCU safe, walk ->next till the end */
 		pos = NULL;
-		cgroup_for_each_child(tmp, last)
+		css_for_each_child(tmp, last)
 			pos = tmp;
 	} while (pos);
 
 	return last;
 }
-EXPORT_SYMBOL_GPL(cgroup_rightmost_descendant);
+EXPORT_SYMBOL_GPL(css_rightmost_descendant);
 
-static struct cgroup *cgroup_leftmost_descendant(struct cgroup *pos)
+static struct cgroup_subsys_state *
+css_leftmost_descendant(struct cgroup_subsys_state *pos)
 {
-	struct cgroup *last;
+	struct cgroup_subsys_state *last;
 
 	do {
 		last = pos;
-		pos = cgroup_next_child(NULL, pos);
+		pos = css_next_child(NULL, pos);
 	} while (pos);
 
 	return last;
 }
 
 /**
- * cgroup_next_descendant_post - find the next descendant for post-order walk
+ * css_next_descendant_post - find the next descendant for post-order walk
  * @pos: the current position (%NULL to initiate traversal)
- * @cgroup: cgroup whose descendants to walk
+ * @root: css whose descendants to walk
  *
- * To be used by cgroup_for_each_descendant_post().  Find the next
- * descendant to visit for post-order traversal of @cgroup's descendants.
+ * To be used by css_for_each_descendant_post().  Find the next descendant
+ * to visit for post-order traversal of @root's descendants.
  *
  * While this function requires RCU read locking, it doesn't require the
  * whole traversal to be contained in a single RCU critical section.  This
  * function will return the correct next descendant as long as both @pos
  * and @cgroup are accessible and @pos is a descendant of @cgroup.
  */
-struct cgroup *cgroup_next_descendant_post(struct cgroup *pos,
-					   struct cgroup *cgroup)
+struct cgroup_subsys_state *
+css_next_descendant_post(struct cgroup_subsys_state *pos,
+			 struct cgroup_subsys_state *root)
 {
-	struct cgroup *next;
+	struct cgroup_subsys_state *next;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
 	/* if first iteration, visit the leftmost descendant */
 	if (!pos) {
-		next = cgroup_leftmost_descendant(cgroup);
-		return next != cgroup ? next : NULL;
+		next = css_leftmost_descendant(root);
+		return next != root ? next : NULL;
 	}
 
 	/* if there's an unvisited sibling, visit its leftmost descendant */
-	next = cgroup_next_child(pos, pos->parent);
+	next = css_next_child(pos, css_parent(pos));
 	if (next)
-		return cgroup_leftmost_descendant(next);
+		return css_leftmost_descendant(next);
 
 	/* no sibling left, visit parent */
-	next = pos->parent;
-	return next != cgroup ? next : NULL;
+	next = css_parent(pos);
+	return next != root ? next : NULL;
 }
-EXPORT_SYMBOL_GPL(cgroup_next_descendant_post);
+EXPORT_SYMBOL_GPL(css_next_descendant_post);
 
 void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
 	__acquires(css_set_lock)

@@ -4540,9 +4555,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	/*
 	 * Mark @cgrp dead.  This prevents further task migration and child
 	 * creation by disabling cgroup_lock_live_group().  Note that
-	 * CGRP_DEAD assertion is depended upon by cgroup_next_child() to
+	 * CGRP_DEAD assertion is depended upon by css_next_child() to
 	 * resume iteration after dropping RCU read lock.  See
-	 * cgroup_next_child() for details.
+	 * css_next_child() for details.
 	 */
 	set_bit(CGRP_DEAD, &cgrp->flags);
 

kernel/cgroup_freezer.c +10 -15

index 19613ba..98ca48d 100644
@@ -50,11 +50,6 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
 	return css ? container_of(css, struct freezer, css) : NULL;
 }
 
-static inline struct freezer *cgroup_freezer(struct cgroup *cgroup)
-{
-	return css_freezer(cgroup_css(cgroup, freezer_subsys_id));
-}
-
 static inline struct freezer *task_freezer(struct task_struct *task)
 {
 	return css_freezer(task_css(task, freezer_subsys_id));

@@ -120,7 +115,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
 	/*
 	 * The following double locking and freezing state inheritance
 	 * guarantee that @cgroup can never escape ancestors' freezing
-	 * states.  See cgroup_for_each_descendant_pre() for details.
+	 * states.  See css_for_each_descendant_pre() for details.
 	 */
 	if (parent)
 		spin_lock_irq(&parent->lock);

@@ -262,7 +257,7 @@ out:
 static void update_if_frozen(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
-	struct cgroup *pos;
+	struct cgroup_subsys_state *pos;
 	struct cgroup_iter it;
 	struct task_struct *task;
 

@@ -275,8 +270,8 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 		goto out_unlock;
 
 	/* are all (live) children frozen? */
-	cgroup_for_each_child(pos, css->cgroup) {
-		struct freezer *child = cgroup_freezer(pos);
+	css_for_each_child(pos, css) {
+		struct freezer *child = css_freezer(pos);
 
 		if ((child->state & CGROUP_FREEZER_ONLINE) &&
 		    !(child->state & CGROUP_FROZEN))

@@ -309,13 +304,13 @@ out_unlock:
 static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
 			struct seq_file *m)
 {
-	struct cgroup *pos;
+	struct cgroup_subsys_state *pos;
 
 	rcu_read_lock();
 
 	/* update states bottom-up */
-	cgroup_for_each_descendant_post(pos, css->cgroup)
-		update_if_frozen(cgroup_css(pos, freezer_subsys_id));
+	css_for_each_descendant_post(pos, css)
+		update_if_frozen(pos);
 	update_if_frozen(css);
 
 	rcu_read_unlock();

@@ -396,7 +391,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze,
  */
 static void freezer_change_state(struct freezer *freezer, bool freeze)
 {
-	struct cgroup *pos;
+	struct cgroup_subsys_state *pos;
 
 	/* update @freezer */
 	spin_lock_irq(&freezer->lock);

@@ -409,8 +404,8 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 	 * CGROUP_FREEZING_PARENT.
 	 */
 	rcu_read_lock();
-	cgroup_for_each_descendant_pre(pos, freezer->css.cgroup) {
-		struct freezer *pos_f = cgroup_freezer(pos);
+	css_for_each_descendant_pre(pos, &freezer->css) {
+		struct freezer *pos_f = css_freezer(pos);
 		struct freezer *parent = parent_freezer(pos_f);
 
 		/*

kernel/cpuset.c +29 -29

index 89b76e1..be4f503 100644
@@ -210,29 +210,29 @@ static struct cpuset top_cpuset = {
 /**
  * cpuset_for_each_child - traverse online children of a cpuset
  * @child_cs: loop cursor pointing to the current child
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
  * @parent_cs: target cpuset to walk children of
  *
  * Walk @child_cs through the online children of @parent_cs.  Must be used
  * with RCU read locked.
  */
-#define cpuset_for_each_child(child_cs, pos_cgrp, parent_cs)		\
-	cgroup_for_each_child((pos_cgrp), (parent_cs)->css.cgroup)	\
-		if (is_cpuset_online(((child_cs) = cgroup_cs((pos_cgrp)))))
+#define cpuset_for_each_child(child_cs, pos_css, parent_cs)		\
+	css_for_each_child((pos_css), &(parent_cs)->css)		\
+		if (is_cpuset_online(((child_cs) = css_cs((pos_css)))))
 
 /**
  * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants
  * @des_cs: loop cursor pointing to the current descendant
- * @pos_cgrp: used for iteration
+ * @pos_css: used for iteration
  * @root_cs: target cpuset to walk ancestor of
  *
  * Walk @des_cs through the online descendants of @root_cs.  Must be used
- * with RCU read locked.  The caller may modify @pos_cgrp by calling
- * cgroup_rightmost_descendant() to skip subtree.
+ * with RCU read locked.  The caller may modify @pos_css by calling
+ * css_rightmost_descendant() to skip subtree.
  */
-#define cpuset_for_each_descendant_pre(des_cs, pos_cgrp, root_cs)	\
-	cgroup_for_each_descendant_pre((pos_cgrp), (root_cs)->css.cgroup) \
-		if (is_cpuset_online(((des_cs) = cgroup_cs((pos_cgrp)))))
+#define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs)	\
+	css_for_each_descendant_pre((pos_css), &(root_cs)->css)		\
+		if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))
 
 /*
  * There are two global mutexes guarding cpuset structures - cpuset_mutex

@@ -430,7 +430,7 @@ static void free_trial_cpuset(struct cpuset *trial)
 
 static int validate_change(struct cpuset *cur, struct cpuset *trial)
 {
-	struct cgroup *cgrp;
+	struct cgroup_subsys_state *css;
 	struct cpuset *c, *par;
 	int ret;
 

@@ -438,7 +438,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 
 	/* Each of our child cpusets must be a subset of us */
 	ret = -EBUSY;
-	cpuset_for_each_child(c, cgrp, cur)
+	cpuset_for_each_child(c, css, cur)
 		if (!is_cpuset_subset(c, trial))
 			goto out;
 

@@ -459,7 +459,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * overlap
 	 */
 	ret = -EINVAL;
-	cpuset_for_each_child(c, cgrp, par) {
+	cpuset_for_each_child(c, css, par) {
 		if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
 		    c != cur &&
 		    cpumask_intersects(trial->cpus_allowed, c->cpus_allowed))

@@ -508,13 +508,13 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
 				    struct cpuset *root_cs)
 {
 	struct cpuset *cp;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) {
+	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
 		/* skip the whole subtree if @cp doesn't have any CPU */
 		if (cpumask_empty(cp->cpus_allowed)) {
-			pos_cgrp = cgroup_rightmost_descendant(pos_cgrp);
+			pos_css = css_rightmost_descendant(pos_css);
 			continue;
 		}
 

@@ -589,7 +589,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	struct sched_domain_attr *dattr;  /* attributes for custom domains */
 	int ndoms = 0;		/* number of sched domains in result */
 	int nslot;		/* next empty doms[] struct cpumask slot */
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 
 	doms = NULL;
 	dattr = NULL;

@@ -618,7 +618,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 	csn = 0;
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_cgrp, &top_cpuset) {
+	cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
 		/*
 		 * Continue traversing beyond @cp iff @cp has some CPUs and
 		 * isn't load balancing.  The former is obvious.  The

@@ -635,7 +635,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			csa[csn++] = cp;
 
 		/* skip @cp's subtree */
-		pos_cgrp = cgroup_rightmost_descendant(pos_cgrp);
+		pos_css = css_rightmost_descendant(pos_css);
 	}
 	rcu_read_unlock();
 

@@ -886,16 +886,16 @@ static void update_tasks_cpumask_hier(struct cpuset *root_cs,
 				      bool update_root, struct ptr_heap *heap)
 {
 	struct cpuset *cp;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 
 	if (update_root)
 		update_tasks_cpumask(root_cs, heap);
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) {
+	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
 		/* skip the whole subtree if @cp have some CPU */
 		if (!cpumask_empty(cp->cpus_allowed)) {
-			pos_cgrp = cgroup_rightmost_descendant(pos_cgrp);
+			pos_css = css_rightmost_descendant(pos_css);
 			continue;
 		}
 		if (!css_tryget(&cp->css))

@@ -1143,16 +1143,16 @@ static void update_tasks_nodemask_hier(struct cpuset *root_cs,
 				       bool update_root, struct ptr_heap *heap)
 {
 	struct cpuset *cp;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 
 	if (update_root)
 		update_tasks_nodemask(root_cs, heap);
 
 	rcu_read_lock();
-	cpuset_for_each_descendant_pre(cp, pos_cgrp, root_cs) {
+	cpuset_for_each_descendant_pre(cp, pos_css, root_cs) {
 		/* skip the whole subtree if @cp have some CPU */
 		if (!nodes_empty(cp->mems_allowed)) {
-			pos_cgrp = cgroup_rightmost_descendant(pos_cgrp);
+			pos_css = css_rightmost_descendant(pos_css);
 			continue;
 		}
 		if (!css_tryget(&cp->css))

@@ -1973,7 +1973,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *parent = parent_cs(cs);
 	struct cpuset *tmp_cs;
-	struct cgroup *pos_cgrp;
+	struct cgroup_subsys_state *pos_css;
 
 	if (!parent)
 		return 0;

@@ -2005,7 +2005,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	 * (and likewise for mems) to the new cgroup.
 	 */
 	rcu_read_lock();
-	cpuset_for_each_child(tmp_cs, pos_cgrp, parent) {
+	cpuset_for_each_child(tmp_cs, pos_css, parent) {
 		if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) {
 			rcu_read_unlock();
 			goto out_unlock;

@@ -2252,10 +2252,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	/* if cpus or mems changed, we need to propagate to descendants */
 	if (cpus_updated || mems_updated) {
 		struct cpuset *cs;
-		struct cgroup *pos_cgrp;
+		struct cgroup_subsys_state *pos_css;
 
 		rcu_read_lock();
-		cpuset_for_each_descendant_pre(cs, pos_cgrp, &top_cpuset) {
+		cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
 			if (!css_tryget(&cs->css))
 				continue;
 			rcu_read_unlock();

mm/memcontrol.c +9 -11

index ab64dfc..2285319 100644
@@ -1082,7 +1082,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
 		struct mem_cgroup *last_visited)
 {
-	struct cgroup *prev_cgroup, *next_cgroup;
+	struct cgroup_subsys_state *prev_css, *next_css;
 
 	/*
 	 * Root is not visited by cgroup iterators so it needs an

@@ -1091,11 +1091,9 @@ static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
 	if (!last_visited)
 		return root;
 
-	prev_cgroup = (last_visited == root) ? NULL
-		: last_visited->css.cgroup;
+	prev_css = (last_visited == root) ? NULL : &last_visited->css;
 skip_node:
-	next_cgroup = cgroup_next_descendant_pre(
-			prev_cgroup, root->css.cgroup);
+	next_css = css_next_descendant_pre(prev_css, &root->css);
 
 	/*
 	 * Even if we found a group we have to make sure it is

@@ -1104,13 +1102,13 @@ skip_node:
 	 * last_visited css is safe to use because it is
 	 * protected by css_get and the tree walk is rcu safe.
 	 */
-	if (next_cgroup) {
-		struct mem_cgroup *mem = mem_cgroup_from_cont(
-				next_cgroup);
+	if (next_css) {
+		struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
+
 		if (css_tryget(&mem->css))
 			return mem;
 		else {
-			prev_cgroup = next_cgroup;
+			prev_css = next_css;
 			goto skip_node;
 		}
 	}

@@ -4939,10 +4937,10 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
  */
 static inline bool __memcg_has_children(struct mem_cgroup *memcg)
 {
-	struct cgroup *pos;
+	struct cgroup_subsys_state *pos;
 
 	/* bounce at first found */
-	cgroup_for_each_child(pos, memcg->css.cgroup)
+	css_for_each_child(pos, &memcg->css)
 		return true;
 	return false;
 }

security/device_cgroup.c +3 -8

index e0ca464..9bf230a 100644
@@ -56,11 +56,6 @@ static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
 	return s ? container_of(s, struct dev_cgroup, css) : NULL;
 }
 
-static inline struct dev_cgroup *cgroup_to_devcgroup(struct cgroup *cgroup)
-{
-	return css_to_devcgroup(cgroup_css(cgroup, devices_subsys_id));
-}
-
 static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
 {
 	return css_to_devcgroup(task_css(task, devices_subsys_id));

@@ -447,13 +442,13 @@ static void revalidate_active_exceptions(struct dev_cgroup *devcg)
 static int propagate_exception(struct dev_cgroup *devcg_root,
 			       struct dev_exception_item *ex)
 {
-	struct cgroup *root = devcg_root->css.cgroup, *pos;
+	struct cgroup_subsys_state *pos;
 	int rc = 0;
 
 	rcu_read_lock();
 
-	cgroup_for_each_descendant_pre(pos, root) {
-		struct dev_cgroup *devcg = cgroup_to_devcgroup(pos);
+	css_for_each_descendant_pre(pos, &devcg_root->css) {
+		struct dev_cgroup *devcg = css_to_devcgroup(pos);
 
 		/*
 		 * Because devcgroup_mutex is held, no devcg will become

Signature · 1 line

1.8.3.1

cgroup is currently in the process of transitioning to using css (cgroup_subsys_state) as the primary handle instead of cgroup in subsystem API. For hierarchy iterators, this is beneficial because

* In most cases, css is the only thing subsystems care about anyway.

* On the planned unified hierarchy, iterations for different subsystems will need to skip over different subtrees of the hierarchy depending on which subsystems are enabled on each cgroup. Passing around css makes it unnecessary to explicitly specify the subsystem in question as css is intersection between cgroup and subsystem

* For the planned unified hierarchy, css's would need to be created and destroyed dynamically independent from cgroup hierarchy. Having cgroup core manage css iteration makes enforcing deref rules a lot easier.

Most subsystem conversions are straight-forward. Noteworthy changes are

* blkio: cgroup_to_blkcg() is no longer used. Removed.

* freezer: cgroup_freezer() is no longer used. Removed.

* devices: cgroup_to_devcgroup() is no longer used. Removed.

Signed-off-by Tejun Heo <[email protected]>

Cc Li Zefan <[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Balbir Singh <[email protected]>

Cc Aristeu Rozanski <[email protected]>

Cc Matt Helsley <matthltc-r/[email protected]>

Cc Vivek Goyal <[email protected]>

Cc Jens Axboe <axboe-tSWWG44O7X1aa/[email protected]>

---
 block/blk-cgroup.c       |   8 +--
 block/blk-cgroup.h       |  25 ++++-----
 block/blk-throttle.c     |   8 +--

cgroup is currently in the process of transitioning to using css (cgroup_subsys_state) as the primary handle instead of cgroup in subsystem API. For hierarchy iterators, this is beneficial because

* In most cases, css is the only thing subsystems care about anyway.

* On the planned unified hierarchy, iterations for different subsystems will need to skip over different subtrees of the hierarchy depending on which subsystems are enabled on each cgroup. Passing around css makes it unnecessary to explicitly specify the subsystem in question as css is intersection between cgroup and subsystem

* For the planned unified hierarchy, css's would need to be created and destroyed dynamically independent from cgroup hierarchy. Having cgroup core manage css iteration makes enforcing deref rules a lot easier.

Most subsystem conversions are straight-forward. Noteworthy changes are

* blkio: cgroup_to_blkcg() is no longer used. Removed.

* freezer: cgroup_freezer() is no longer used. Removed.

* devices: cgroup_to_devcgroup() is no longer used. Removed.

For some reason, cgroup_advance_iter() is standing lonely all away from its iter comrades. Relocate it.

Quoted 3 lines · Tejun Heo

For some reason, cgroup_advance_iter() is standing lonely all away from its iter comrades. Relocate it.

There're some other functions that are in the same situation. Do you think it's better to relocate them, or just leave it as it is?

Quoted 3 lines · Tejun Heo

For some reason, cgroup_advance_iter() is standing lonely all away from its iter comrades. Relocate it.

There're some other functions that are in the same situation. Do you think it's better to relocate them, or just leave it as it is?

cgroup now has multiple iterators and it's quite confusing to have something which walks over tasks of a single cgroup cgroup_iter. Let's rename it to cgroup_task_iter.

While at it, reformat / update comments and replace the overview comment above the interface function decls with proper function comments. Such overview can be useful but function comments should be more than enough here.

This is pure rename and doesn't introduce any functional changes.

Signed-off-by Tejun Heo <[email protected]>

Cc Matt Helsley <matthltc-r/[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Balbir Singh <[email protected]>

---
 include/linux/cgroup.h  |  31 ++++---------
 kernel/cgroup.c         | 114 ++++++++++++++++++++++++++++++++----------------
 kernel/cgroup_freezer.c |  24 +++++-----
 mm/memcontrol.c         |  10 ++---
 4 files changed, 102 insertions(+), 77 deletions(-)

include/linux/cgroup.h +8 -23

index 7fba0d0..4478336 100644
@@ -890,31 +890,16 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
 	     (pos) = css_next_descendant_post((pos), (css)))
 
-/* A cgroup_iter should be treated as an opaque object */
-struct cgroup_iter {
-	struct list_head *cset_link;
-	struct list_head *task;
+/* A cgroup_task_iter should be treated as an opaque object */
+struct cgroup_task_iter {
+	struct list_head		*cset_link;
+	struct list_head		*task;
 };
 
-/*
- * To iterate across the tasks in a cgroup:
- *
- * 1) call cgroup_iter_start to initialize an iterator
- *
- * 2) call cgroup_iter_next() to retrieve member tasks until it
- *    returns NULL or until you want to end the iteration
- *
- * 3) call cgroup_iter_end() to destroy the iterator.
- *
- * Or, call cgroup_scan_tasks() to iterate through every task in a
- * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling
- * the test_task() callback, but not while calling the process_task()
- * callback.
- */
-void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it);
-struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
-					struct cgroup_iter *it);
-void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
+void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it);
+struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
+					  struct cgroup_task_iter *it);
+void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);

kernel/cgroup.c +77 -37

index 1085439..7a4f89b 100644
@@ -367,9 +367,11 @@ static struct cgrp_cset_link init_cgrp_cset_link;
 static int cgroup_init_idr(struct cgroup_subsys *ss,
 			   struct cgroup_subsys_state *css);
 
-/* css_set_lock protects the list of css_set objects, and the
- * chain of tasks off each css_set.  Nests outside task->alloc_lock
- * due to cgroup_iter_start() */
+/*
+ * css_set_lock protects the list of css_set objects, and the chain of
+ * tasks off each css_set.  Nests outside task->alloc_lock due to
+ * cgroup_task_iter_start().
+ */
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 

@@ -394,10 +396,12 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 	return key;
 }
 
-/* We don't maintain the lists running through each css_set to its
- * task until after the first call to cgroup_iter_start(). This
- * reduces the fork()/exit() overhead for people who have cgroups
- * compiled into their kernel but not actually in use */
+/*
+ * We don't maintain the lists running through each css_set to its task
+ * until after the first call to cgroup_task_iter_start().  This reduces
+ * the fork()/exit() overhead for people who have cgroups compiled into
+ * their kernel but not actually in use.
+ */
 static int use_task_css_set_links __read_mostly;
 
 static void __put_css_set(struct css_set *cset, int taskexit)

@@ -2975,10 +2979,10 @@ int cgroup_task_count(const struct cgroup *cgrp)
 }
 
 /*
- * To reduce the fork() overhead for systems that are not actually
- * using their cgroups capability, we don't maintain the lists running
- * through each css_set to its tasks until we see the list actually
- * used - in other words after the first call to cgroup_iter_start().
+ * To reduce the fork() overhead for systems that are not actually using
+ * their cgroups capability, we don't maintain the lists running through
+ * each css_set to its tasks until we see the list actually used - in other
+ * words after the first call to cgroup_task_iter_start().
  */
 static void cgroup_enable_task_cg_lists(void)
 {

@@ -3192,11 +3196,15 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 }
 EXPORT_SYMBOL_GPL(css_next_descendant_post);
 
-/*
- * Advance a list_head iterator.  The iterator should be positioned at
- * the start of a css_set
+/**
+ * cgroup_advance_task_iter - advance a task itererator to the next css_set
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the iterator to advance
+ *
+ * Advance @it to the next css_set to walk.
  */
-static void cgroup_advance_iter(struct cgroup *cgrp, struct cgroup_iter *it)
+static void cgroup_advance_task_iter(struct cgroup *cgrp,
+				     struct cgroup_task_iter *it)
 {
 	struct list_head *l = it->cset_link;
 	struct cgrp_cset_link *link;

@@ -3216,7 +3224,21 @@ static void cgroup_advance_iter(struct cgroup *cgrp, struct cgroup_iter *it)
 	it->task = cset->tasks.next;
 }
 
-void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
+/**
+ * cgroup_task_iter_start - initiate task iteration
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the task iterator to use
+ *
+ * Initiate iteration through the tasks of @cgrp.  The caller can call
+ * cgroup_task_iter_next() to walk through the tasks until the function
+ * returns NULL.  On completion of iteration, cgroup_task_iter_end() must
+ * be called.
+ *
+ * Note that this function acquires a lock which is released when the
+ * iteration finishes.  The caller can't sleep while iteration is in
+ * progress.
+ */
+void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it)
 	__acquires(css_set_lock)
 {
 	/*

@@ -3229,11 +3251,20 @@ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
 
 	read_lock(&css_set_lock);
 	it->cset_link = &cgrp->cset_links;
-	cgroup_advance_iter(cgrp, it);
+	cgroup_advance_task_iter(cgrp, it);
 }
 
-struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
-					struct cgroup_iter *it)
+/**
+ * cgroup_task_iter_next - return the next task for the iterator
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the task iterator being iterated
+ *
+ * The "next" function for task iteration.  @it should have been
+ * initialized via cgroup_task_iter_start().  Returns NULL when the
+ * iteration reaches the end.
+ */
+struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
+					  struct cgroup_task_iter *it)
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;

@@ -3247,16 +3278,25 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 	l = l->next;
 	link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link);
 	if (l == &link->cset->tasks) {
-		/* We reached the end of this task list - move on to
-		 * the next cg_cgroup_link */
-		cgroup_advance_iter(cgrp, it);
+		/*
+		 * We reached the end of this task list - move on to the
+		 * next cgrp_cset_link.
+		 */
+		cgroup_advance_task_iter(cgrp, it);
 	} else {
 		it->task = l;
 	}
 	return res;
 }
 
-void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
+/**
+ * cgroup_task_iter_end - finish task iteration
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the task iterator to finish
+ *
+ * Finish task iteration started by cgroup_task_iter_start().
+ */
+void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it)
 	__releases(css_set_lock)
 {
 	read_unlock(&css_set_lock);

@@ -3305,7 +3345,7 @@ static inline int started_after(void *p1, void *p2)
  * Iterate through all the tasks in a cgroup, calling test_task() for each,
  * and if it returns true, call process_task() for it also.
  * The test_task pointer may be NULL, meaning always true (select all tasks).
- * Effectively duplicates cgroup_iter_{start,next,end}()
+ * Effectively duplicates cgroup_task_iter_{start,next,end}()
  * but does not lock css_set_lock for the call to process_task().
  * The struct cgroup_scanner may be embedded in any structure of the caller's
  * creation.

@@ -3326,7 +3366,7 @@ static inline int started_after(void *p1, void *p2)
 int cgroup_scan_tasks(struct cgroup_scanner *scan)
 {
 	int retval, i;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *p, *dropped;
 	/* Never dereference latest_task, since it's not refcounted */
 	struct task_struct *latest_task = NULL;

@@ -3361,8 +3401,8 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 	 * guarantees forward progress and that we don't miss any tasks.
 	 */
 	heap->size = 0;
-	cgroup_iter_start(scan->cgrp, &it);
-	while ((p = cgroup_iter_next(scan->cgrp, &it))) {
+	cgroup_task_iter_start(scan->cgrp, &it);
+	while ((p = cgroup_task_iter_next(scan->cgrp, &it))) {
 		/*
 		 * Only affect tasks that qualify per the caller's callback,
 		 * if he provided one

@@ -3395,7 +3435,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 		 * the heap and wasn't inserted
 		 */
 	}
-	cgroup_iter_end(scan->cgrp, &it);
+	cgroup_task_iter_end(scan->cgrp, &it);
 
 	if (heap->size) {
 		for (i = 0; i < heap->size; i++) {

@@ -3601,7 +3641,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	pid_t *array;
 	int length;
 	int pid, n = 0; /* used for populating the array */
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *tsk;
 	struct cgroup_pidlist *l;
 

@@ -3616,8 +3656,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	if (!array)
 		return -ENOMEM;
 	/* now, populate the array */
-	cgroup_iter_start(cgrp, &it);
-	while ((tsk = cgroup_iter_next(cgrp, &it))) {
+	cgroup_task_iter_start(cgrp, &it);
+	while ((tsk = cgroup_task_iter_next(cgrp, &it))) {
 		if (unlikely(n == length))
 			break;
 		/* get tgid or pid for procs or tasks file respectively */

@@ -3628,7 +3668,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 		if (pid > 0) /* make sure to only use valid results */
 			array[n++] = pid;
 	}
-	cgroup_iter_end(cgrp, &it);
+	cgroup_task_iter_end(cgrp, &it);
 	length = n;
 	/* now sort & (if procs) strip out duplicates */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);

@@ -3662,7 +3702,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 {
 	int ret = -EINVAL;
 	struct cgroup *cgrp;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *tsk;
 
 	/*

@@ -3676,8 +3716,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	ret = 0;
 	cgrp = dentry->d_fsdata;
 
-	cgroup_iter_start(cgrp, &it);
-	while ((tsk = cgroup_iter_next(cgrp, &it))) {
+	cgroup_task_iter_start(cgrp, &it);
+	while ((tsk = cgroup_task_iter_next(cgrp, &it))) {
 		switch (tsk->state) {
 		case TASK_RUNNING:
 			stats->nr_running++;

@@ -3697,7 +3737,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 			break;
 		}
 	}
-	cgroup_iter_end(cgrp, &it);
+	cgroup_task_iter_end(cgrp, &it);
 
 err:
 	return ret;

@@ -5128,7 +5168,7 @@ void cgroup_fork(struct task_struct *child)
  * Adds the task to the list running through its css_set if necessary and
  * call the subsystem fork() callbacks.  Has to be after the task is
  * visible on the task list in case we race with the first call to
- * cgroup_iter_start() - to guarantee that the new task ends up on its
+ * cgroup_task_iter_start() - to guarantee that the new task ends up on its
  * list.
  */
 void cgroup_post_fork(struct task_struct *child)

kernel/cgroup_freezer.c +12 -12

index 98ca48d..c9177f8 100644
@@ -258,7 +258,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
 	struct cgroup_subsys_state *pos;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *task;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());

@@ -279,9 +279,9 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	}
 
 	/* are all tasks frozen? */
-	cgroup_iter_start(css->cgroup, &it);
+	cgroup_task_iter_start(css->cgroup, &it);
 
-	while ((task = cgroup_iter_next(css->cgroup, &it))) {
+	while ((task = cgroup_task_iter_next(css->cgroup, &it))) {
 		if (freezing(task)) {
 			/*
 			 * freezer_should_skip() indicates that the task

@@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 
 	freezer->state |= CGROUP_FROZEN;
 out_iter_end:
-	cgroup_iter_end(css->cgroup, &it);
+	cgroup_task_iter_end(css->cgroup, &it);
 out_unlock:
 	spin_unlock_irq(&freezer->lock);
 }

@@ -323,25 +323,25 @@ static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
 static void freeze_cgroup(struct freezer *freezer)
 {
 	struct cgroup *cgroup = freezer->css.cgroup;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *task;
 
-	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it)))
+	cgroup_task_iter_start(cgroup, &it);
+	while ((task = cgroup_task_iter_next(cgroup, &it)))
 		freeze_task(task);
-	cgroup_iter_end(cgroup, &it);
+	cgroup_task_iter_end(cgroup, &it);
 }
 
 static void unfreeze_cgroup(struct freezer *freezer)
 {
 	struct cgroup *cgroup = freezer->css.cgroup;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *task;
 
-	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it)))
+	cgroup_task_iter_start(cgroup, &it);
+	while ((task = cgroup_task_iter_next(cgroup, &it)))
 		__thaw_task(task);
-	cgroup_iter_end(cgroup, &it);
+	cgroup_task_iter_end(cgroup, &it);
 }
 
 /**

mm/memcontrol.c +5 -5

index 2285319..00b055d 100644
@@ -1800,11 +1800,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct cgroup *cgroup = iter->css.cgroup;
-		struct cgroup_iter it;
+		struct cgroup_task_iter it;
 		struct task_struct *task;
 
-		cgroup_iter_start(cgroup, &it);
-		while ((task = cgroup_iter_next(cgroup, &it))) {
+		cgroup_task_iter_start(cgroup, &it);
+		while ((task = cgroup_task_iter_next(cgroup, &it))) {
 			switch (oom_scan_process_thread(task, totalpages, NULL,
 							false)) {
 			case OOM_SCAN_SELECT:

@@ -1817,7 +1817,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 			case OOM_SCAN_CONTINUE:
 				continue;
 			case OOM_SCAN_ABORT:
-				cgroup_iter_end(cgroup, &it);
+				cgroup_task_iter_end(cgroup, &it);
 				mem_cgroup_iter_break(memcg, iter);
 				if (chosen)
 					put_task_struct(chosen);

@@ -1834,7 +1834,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				get_task_struct(chosen);
 			}
 		}
-		cgroup_iter_end(cgroup, &it);
+		cgroup_task_iter_end(cgroup, &it);
 	}
 
 	if (!chosen)

Signature · 1 line

1.8.3.1

cgroup now has multiple iterators and it's quite confusing to have something which walks over tasks of a single cgroup cgroup_iter. Let's rename it to cgroup_task_iter.

While at it, reformat / update comments and replace the overview comment above the interface function decls with proper function comments. Such overview can be useful but function comments should be more than enough here.

This is pure rename and doesn't introduce any functional changes.

Signed-off-by Tejun Heo <[email protected]>

Cc Matt Helsley <matthltc-r/[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Balbir Singh <[email protected]>

---
 include/linux/cgroup.h  |  31 ++++---------
 kernel/cgroup.c         | 114 ++++++++++++++++++++++++++++++++----------------
 kernel/cgroup_freezer.c |  24 +++++-----
 mm/memcontrol.c         |  10 ++---
 4 files changed, 102 insertions(+), 77 deletions(-)

include/linux/cgroup.h +8 -23

index 7fba0d0..4478336 100644
@@ -890,31 +890,16 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
 	     (pos) = css_next_descendant_post((pos), (css)))
 
-/* A cgroup_iter should be treated as an opaque object */
-struct cgroup_iter {
-	struct list_head *cset_link;
-	struct list_head *task;
+/* A cgroup_task_iter should be treated as an opaque object */
+struct cgroup_task_iter {
+	struct list_head		*cset_link;
+	struct list_head		*task;
 };
 
-/*
- * To iterate across the tasks in a cgroup:
- *
- * 1) call cgroup_iter_start to initialize an iterator
- *
- * 2) call cgroup_iter_next() to retrieve member tasks until it
- *    returns NULL or until you want to end the iteration
- *
- * 3) call cgroup_iter_end() to destroy the iterator.
- *
- * Or, call cgroup_scan_tasks() to iterate through every task in a
- * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling
- * the test_task() callback, but not while calling the process_task()
- * callback.
- */
-void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it);
-struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
-					struct cgroup_iter *it);
-void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
+void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it);
+struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
+					  struct cgroup_task_iter *it);
+void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);

kernel/cgroup.c +77 -37

index 1085439..7a4f89b 100644
@@ -367,9 +367,11 @@ static struct cgrp_cset_link init_cgrp_cset_link;
 static int cgroup_init_idr(struct cgroup_subsys *ss,
 			   struct cgroup_subsys_state *css);
 
-/* css_set_lock protects the list of css_set objects, and the
- * chain of tasks off each css_set.  Nests outside task->alloc_lock
- * due to cgroup_iter_start() */
+/*
+ * css_set_lock protects the list of css_set objects, and the chain of
+ * tasks off each css_set.  Nests outside task->alloc_lock due to
+ * cgroup_task_iter_start().
+ */
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;
 

@@ -394,10 +396,12 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 	return key;
 }
 
-/* We don't maintain the lists running through each css_set to its
- * task until after the first call to cgroup_iter_start(). This
- * reduces the fork()/exit() overhead for people who have cgroups
- * compiled into their kernel but not actually in use */
+/*
+ * We don't maintain the lists running through each css_set to its task
+ * until after the first call to cgroup_task_iter_start().  This reduces
+ * the fork()/exit() overhead for people who have cgroups compiled into
+ * their kernel but not actually in use.
+ */
 static int use_task_css_set_links __read_mostly;
 
 static void __put_css_set(struct css_set *cset, int taskexit)

@@ -2975,10 +2979,10 @@ int cgroup_task_count(const struct cgroup *cgrp)
 }
 
 /*
- * To reduce the fork() overhead for systems that are not actually
- * using their cgroups capability, we don't maintain the lists running
- * through each css_set to its tasks until we see the list actually
- * used - in other words after the first call to cgroup_iter_start().
+ * To reduce the fork() overhead for systems that are not actually using
+ * their cgroups capability, we don't maintain the lists running through
+ * each css_set to its tasks until we see the list actually used - in other
+ * words after the first call to cgroup_task_iter_start().
  */
 static void cgroup_enable_task_cg_lists(void)
 {

@@ -3192,11 +3196,15 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 }
 EXPORT_SYMBOL_GPL(css_next_descendant_post);
 
-/*
- * Advance a list_head iterator.  The iterator should be positioned at
- * the start of a css_set
+/**
+ * cgroup_advance_task_iter - advance a task itererator to the next css_set
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the iterator to advance
+ *
+ * Advance @it to the next css_set to walk.
  */
-static void cgroup_advance_iter(struct cgroup *cgrp, struct cgroup_iter *it)
+static void cgroup_advance_task_iter(struct cgroup *cgrp,
+				     struct cgroup_task_iter *it)
 {
 	struct list_head *l = it->cset_link;
 	struct cgrp_cset_link *link;

@@ -3216,7 +3224,21 @@ static void cgroup_advance_iter(struct cgroup *cgrp, struct cgroup_iter *it)
 	it->task = cset->tasks.next;
 }
 
-void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
+/**
+ * cgroup_task_iter_start - initiate task iteration
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the task iterator to use
+ *
+ * Initiate iteration through the tasks of @cgrp.  The caller can call
+ * cgroup_task_iter_next() to walk through the tasks until the function
+ * returns NULL.  On completion of iteration, cgroup_task_iter_end() must
+ * be called.
+ *
+ * Note that this function acquires a lock which is released when the
+ * iteration finishes.  The caller can't sleep while iteration is in
+ * progress.
+ */
+void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it)
 	__acquires(css_set_lock)
 {
 	/*

@@ -3229,11 +3251,20 @@ void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it)
 
 	read_lock(&css_set_lock);
 	it->cset_link = &cgrp->cset_links;
-	cgroup_advance_iter(cgrp, it);
+	cgroup_advance_task_iter(cgrp, it);
 }
 
-struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
-					struct cgroup_iter *it)
+/**
+ * cgroup_task_iter_next - return the next task for the iterator
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the task iterator being iterated
+ *
+ * The "next" function for task iteration.  @it should have been
+ * initialized via cgroup_task_iter_start().  Returns NULL when the
+ * iteration reaches the end.
+ */
+struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
+					  struct cgroup_task_iter *it)
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;

@@ -3247,16 +3278,25 @@ struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
 	l = l->next;
 	link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link);
 	if (l == &link->cset->tasks) {
-		/* We reached the end of this task list - move on to
-		 * the next cg_cgroup_link */
-		cgroup_advance_iter(cgrp, it);
+		/*
+		 * We reached the end of this task list - move on to the
+		 * next cgrp_cset_link.
+		 */
+		cgroup_advance_task_iter(cgrp, it);
 	} else {
 		it->task = l;
 	}
 	return res;
 }
 
-void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it)
+/**
+ * cgroup_task_iter_end - finish task iteration
+ * @cgrp: the cgroup to walk tasks of
+ * @it: the task iterator to finish
+ *
+ * Finish task iteration started by cgroup_task_iter_start().
+ */
+void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it)
 	__releases(css_set_lock)
 {
 	read_unlock(&css_set_lock);

@@ -3305,7 +3345,7 @@ static inline int started_after(void *p1, void *p2)
  * Iterate through all the tasks in a cgroup, calling test_task() for each,
  * and if it returns true, call process_task() for it also.
  * The test_task pointer may be NULL, meaning always true (select all tasks).
- * Effectively duplicates cgroup_iter_{start,next,end}()
+ * Effectively duplicates cgroup_task_iter_{start,next,end}()
  * but does not lock css_set_lock for the call to process_task().
  * The struct cgroup_scanner may be embedded in any structure of the caller's
  * creation.

@@ -3326,7 +3366,7 @@ static inline int started_after(void *p1, void *p2)
 int cgroup_scan_tasks(struct cgroup_scanner *scan)
 {
 	int retval, i;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *p, *dropped;
 	/* Never dereference latest_task, since it's not refcounted */
 	struct task_struct *latest_task = NULL;

@@ -3361,8 +3401,8 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 	 * guarantees forward progress and that we don't miss any tasks.
 	 */
 	heap->size = 0;
-	cgroup_iter_start(scan->cgrp, &it);
-	while ((p = cgroup_iter_next(scan->cgrp, &it))) {
+	cgroup_task_iter_start(scan->cgrp, &it);
+	while ((p = cgroup_task_iter_next(scan->cgrp, &it))) {
 		/*
 		 * Only affect tasks that qualify per the caller's callback,
 		 * if he provided one

@@ -3395,7 +3435,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 		 * the heap and wasn't inserted
 		 */
 	}
-	cgroup_iter_end(scan->cgrp, &it);
+	cgroup_task_iter_end(scan->cgrp, &it);
 
 	if (heap->size) {
 		for (i = 0; i < heap->size; i++) {

@@ -3601,7 +3641,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	pid_t *array;
 	int length;
 	int pid, n = 0; /* used for populating the array */
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *tsk;
 	struct cgroup_pidlist *l;
 

@@ -3616,8 +3656,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	if (!array)
 		return -ENOMEM;
 	/* now, populate the array */
-	cgroup_iter_start(cgrp, &it);
-	while ((tsk = cgroup_iter_next(cgrp, &it))) {
+	cgroup_task_iter_start(cgrp, &it);
+	while ((tsk = cgroup_task_iter_next(cgrp, &it))) {
 		if (unlikely(n == length))
 			break;
 		/* get tgid or pid for procs or tasks file respectively */

@@ -3628,7 +3668,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 		if (pid > 0) /* make sure to only use valid results */
 			array[n++] = pid;
 	}
-	cgroup_iter_end(cgrp, &it);
+	cgroup_task_iter_end(cgrp, &it);
 	length = n;
 	/* now sort & (if procs) strip out duplicates */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);

@@ -3662,7 +3702,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 {
 	int ret = -EINVAL;
 	struct cgroup *cgrp;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *tsk;
 
 	/*

@@ -3676,8 +3716,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	ret = 0;
 	cgrp = dentry->d_fsdata;
 
-	cgroup_iter_start(cgrp, &it);
-	while ((tsk = cgroup_iter_next(cgrp, &it))) {
+	cgroup_task_iter_start(cgrp, &it);
+	while ((tsk = cgroup_task_iter_next(cgrp, &it))) {
 		switch (tsk->state) {
 		case TASK_RUNNING:
 			stats->nr_running++;

@@ -3697,7 +3737,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 			break;
 		}
 	}
-	cgroup_iter_end(cgrp, &it);
+	cgroup_task_iter_end(cgrp, &it);
 
 err:
 	return ret;

@@ -5128,7 +5168,7 @@ void cgroup_fork(struct task_struct *child)
  * Adds the task to the list running through its css_set if necessary and
  * call the subsystem fork() callbacks.  Has to be after the task is
  * visible on the task list in case we race with the first call to
- * cgroup_iter_start() - to guarantee that the new task ends up on its
+ * cgroup_task_iter_start() - to guarantee that the new task ends up on its
  * list.
  */
 void cgroup_post_fork(struct task_struct *child)

kernel/cgroup_freezer.c +12 -12

index 98ca48d..c9177f8 100644
@@ -258,7 +258,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
 	struct cgroup_subsys_state *pos;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *task;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());

@@ -279,9 +279,9 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	}
 
 	/* are all tasks frozen? */
-	cgroup_iter_start(css->cgroup, &it);
+	cgroup_task_iter_start(css->cgroup, &it);
 
-	while ((task = cgroup_iter_next(css->cgroup, &it))) {
+	while ((task = cgroup_task_iter_next(css->cgroup, &it))) {
 		if (freezing(task)) {
 			/*
 			 * freezer_should_skip() indicates that the task

@@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 
 	freezer->state |= CGROUP_FROZEN;
 out_iter_end:
-	cgroup_iter_end(css->cgroup, &it);
+	cgroup_task_iter_end(css->cgroup, &it);
 out_unlock:
 	spin_unlock_irq(&freezer->lock);
 }

@@ -323,25 +323,25 @@ static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
 static void freeze_cgroup(struct freezer *freezer)
 {
 	struct cgroup *cgroup = freezer->css.cgroup;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *task;
 
-	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it)))
+	cgroup_task_iter_start(cgroup, &it);
+	while ((task = cgroup_task_iter_next(cgroup, &it)))
 		freeze_task(task);
-	cgroup_iter_end(cgroup, &it);
+	cgroup_task_iter_end(cgroup, &it);
 }
 
 static void unfreeze_cgroup(struct freezer *freezer)
 {
 	struct cgroup *cgroup = freezer->css.cgroup;
-	struct cgroup_iter it;
+	struct cgroup_task_iter it;
 	struct task_struct *task;
 
-	cgroup_iter_start(cgroup, &it);
-	while ((task = cgroup_iter_next(cgroup, &it)))
+	cgroup_task_iter_start(cgroup, &it);
+	while ((task = cgroup_task_iter_next(cgroup, &it)))
 		__thaw_task(task);
-	cgroup_iter_end(cgroup, &it);
+	cgroup_task_iter_end(cgroup, &it);
 }
 
 /**

mm/memcontrol.c +5 -5

index 2285319..00b055d 100644
@@ -1800,11 +1800,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct cgroup *cgroup = iter->css.cgroup;
-		struct cgroup_iter it;
+		struct cgroup_task_iter it;
 		struct task_struct *task;
 
-		cgroup_iter_start(cgroup, &it);
-		while ((task = cgroup_iter_next(cgroup, &it))) {
+		cgroup_task_iter_start(cgroup, &it);
+		while ((task = cgroup_task_iter_next(cgroup, &it))) {
 			switch (oom_scan_process_thread(task, totalpages, NULL,
 							false)) {
 			case OOM_SCAN_SELECT:

@@ -1817,7 +1817,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 			case OOM_SCAN_CONTINUE:
 				continue;
 			case OOM_SCAN_ABORT:
-				cgroup_iter_end(cgroup, &it);
+				cgroup_task_iter_end(cgroup, &it);
 				mem_cgroup_iter_break(memcg, iter);
 				if (chosen)
 					put_task_struct(chosen);

@@ -1834,7 +1834,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				get_task_struct(chosen);
 			}
 		}
-		cgroup_iter_end(cgroup, &it);
+		cgroup_task_iter_end(cgroup, &it);
 	}
 
 	if (!chosen)

Signature · 1 line

1.8.3.1

Currently all cgroup_task_iter functions require @cgrp to be passed in, which is superflous and increases chance of usage error. Make cgroup_task_iter remember the cgroup being iterated and drop @cgrp argument from next and end functions.

This patch doesn't introduce any behavior differences.

Signed-off-by Tejun Heo <[email protected]>

Cc Matt Helsley <matthltc-r/[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Balbir Singh <[email protected]>

---
 include/linux/cgroup.h  |  6 +++---
 kernel/cgroup.c         | 32 +++++++++++++++-----------------
 kernel/cgroup_freezer.c | 12 ++++++------
 mm/memcontrol.c         |  6 +++---
 4 files changed, 27 insertions(+), 29 deletions(-)

include/linux/cgroup.h +3 -3

index 4478336..2b10152 100644
@@ -892,14 +892,14 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 
 /* A cgroup_task_iter should be treated as an opaque object */
 struct cgroup_task_iter {
+	struct cgroup			*origin_cgrp;
 	struct list_head		*cset_link;
 	struct list_head		*task;
 };
 
 void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it);
-struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
-					  struct cgroup_task_iter *it);
-void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it);
+struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it);
+void cgroup_task_iter_end(struct cgroup_task_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);

kernel/cgroup.c +15 -17

index 7a4f89b..7adaaa6 100644
@@ -3198,13 +3198,11 @@ EXPORT_SYMBOL_GPL(css_next_descendant_post);
 
 /**
  * cgroup_advance_task_iter - advance a task itererator to the next css_set
- * @cgrp: the cgroup to walk tasks of
  * @it: the iterator to advance
  *
  * Advance @it to the next css_set to walk.
  */
-static void cgroup_advance_task_iter(struct cgroup *cgrp,
-				     struct cgroup_task_iter *it)
+static void cgroup_advance_task_iter(struct cgroup_task_iter *it)
 {
 	struct list_head *l = it->cset_link;
 	struct cgrp_cset_link *link;

@@ -3213,7 +3211,7 @@ static void cgroup_advance_task_iter(struct cgroup *cgrp,
 	/* Advance to the next non-empty css_set */
 	do {
 		l = l->next;
-		if (l == &cgrp->cset_links) {
+		if (l == &it->origin_cgrp->cset_links) {
 			it->cset_link = NULL;
 			return;
 		}

@@ -3250,21 +3248,22 @@ void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it)
 		cgroup_enable_task_cg_lists();
 
 	read_lock(&css_set_lock);
+
+	it->origin_cgrp = cgrp;
 	it->cset_link = &cgrp->cset_links;
-	cgroup_advance_task_iter(cgrp, it);
+
+	cgroup_advance_task_iter(it);
 }
 
 /**
  * cgroup_task_iter_next - return the next task for the iterator
- * @cgrp: the cgroup to walk tasks of
  * @it: the task iterator being iterated
  *
  * The "next" function for task iteration.  @it should have been
  * initialized via cgroup_task_iter_start().  Returns NULL when the
  * iteration reaches the end.
  */
-struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
-					  struct cgroup_task_iter *it)
+struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it)
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;

@@ -3282,7 +3281,7 @@ struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
 		 * We reached the end of this task list - move on to the
 		 * next cgrp_cset_link.
 		 */
-		cgroup_advance_task_iter(cgrp, it);
+		cgroup_advance_task_iter(it);
 	} else {
 		it->task = l;
 	}

@@ -3291,12 +3290,11 @@ struct task_struct *cgroup_task_iter_next(struct cgroup *cgrp,
 
 /**
  * cgroup_task_iter_end - finish task iteration
- * @cgrp: the cgroup to walk tasks of
  * @it: the task iterator to finish
  *
  * Finish task iteration started by cgroup_task_iter_start().
  */
-void cgroup_task_iter_end(struct cgroup *cgrp, struct cgroup_task_iter *it)
+void cgroup_task_iter_end(struct cgroup_task_iter *it)
 	__releases(css_set_lock)
 {
 	read_unlock(&css_set_lock);

@@ -3402,7 +3400,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 	 */
 	heap->size = 0;
 	cgroup_task_iter_start(scan->cgrp, &it);
-	while ((p = cgroup_task_iter_next(scan->cgrp, &it))) {
+	while ((p = cgroup_task_iter_next(&it))) {
 		/*
 		 * Only affect tasks that qualify per the caller's callback,
 		 * if he provided one

@@ -3435,7 +3433,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
 		 * the heap and wasn't inserted
 		 */
 	}
-	cgroup_task_iter_end(scan->cgrp, &it);
+	cgroup_task_iter_end(&it);
 
 	if (heap->size) {
 		for (i = 0; i < heap->size; i++) {

@@ -3657,7 +3655,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 		return -ENOMEM;
 	/* now, populate the array */
 	cgroup_task_iter_start(cgrp, &it);
-	while ((tsk = cgroup_task_iter_next(cgrp, &it))) {
+	while ((tsk = cgroup_task_iter_next(&it))) {
 		if (unlikely(n == length))
 			break;
 		/* get tgid or pid for procs or tasks file respectively */

@@ -3668,7 +3666,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 		if (pid > 0) /* make sure to only use valid results */
 			array[n++] = pid;
 	}
-	cgroup_task_iter_end(cgrp, &it);
+	cgroup_task_iter_end(&it);
 	length = n;
 	/* now sort & (if procs) strip out duplicates */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);

@@ -3717,7 +3715,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	cgrp = dentry->d_fsdata;
 
 	cgroup_task_iter_start(cgrp, &it);
-	while ((tsk = cgroup_task_iter_next(cgrp, &it))) {
+	while ((tsk = cgroup_task_iter_next(&it))) {
 		switch (tsk->state) {
 		case TASK_RUNNING:
 			stats->nr_running++;

@@ -3737,7 +3735,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 			break;
 		}
 	}
-	cgroup_task_iter_end(cgrp, &it);
+	cgroup_task_iter_end(&it);
 
 err:
 	return ret;

kernel/cgroup_freezer.c +6 -6

index c9177f8..e0ab9bf 100644
@@ -281,7 +281,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	/* are all tasks frozen? */
 	cgroup_task_iter_start(css->cgroup, &it);
 
-	while ((task = cgroup_task_iter_next(css->cgroup, &it))) {
+	while ((task = cgroup_task_iter_next(&it))) {
 		if (freezing(task)) {
 			/*
 			 * freezer_should_skip() indicates that the task

@@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 
 	freezer->state |= CGROUP_FROZEN;
 out_iter_end:
-	cgroup_task_iter_end(css->cgroup, &it);
+	cgroup_task_iter_end(&it);
 out_unlock:
 	spin_unlock_irq(&freezer->lock);
 }

@@ -327,9 +327,9 @@ static void freeze_cgroup(struct freezer *freezer)
 	struct task_struct *task;
 
 	cgroup_task_iter_start(cgroup, &it);
-	while ((task = cgroup_task_iter_next(cgroup, &it)))
+	while ((task = cgroup_task_iter_next(&it)))
 		freeze_task(task);
-	cgroup_task_iter_end(cgroup, &it);
+	cgroup_task_iter_end(&it);
 }
 
 static void unfreeze_cgroup(struct freezer *freezer)

@@ -339,9 +339,9 @@ static void unfreeze_cgroup(struct freezer *freezer)
 	struct task_struct *task;
 
 	cgroup_task_iter_start(cgroup, &it);
-	while ((task = cgroup_task_iter_next(cgroup, &it)))
+	while ((task = cgroup_task_iter_next(&it)))
 		__thaw_task(task);
-	cgroup_task_iter_end(cgroup, &it);
+	cgroup_task_iter_end(&it);
 }
 
 /**

mm/memcontrol.c +3 -3

index 00b055d..5a5f4dc 100644
@@ -1804,7 +1804,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		struct task_struct *task;
 
 		cgroup_task_iter_start(cgroup, &it);
-		while ((task = cgroup_task_iter_next(cgroup, &it))) {
+		while ((task = cgroup_task_iter_next(&it))) {
 			switch (oom_scan_process_thread(task, totalpages, NULL,
 							false)) {
 			case OOM_SCAN_SELECT:

@@ -1817,7 +1817,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 			case OOM_SCAN_CONTINUE:
 				continue;
 			case OOM_SCAN_ABORT:
-				cgroup_task_iter_end(cgroup, &it);
+				cgroup_task_iter_end(&it);
 				mem_cgroup_iter_break(memcg, iter);
 				if (chosen)
 					put_task_struct(chosen);

@@ -1834,7 +1834,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				get_task_struct(chosen);
 			}
 		}
-		cgroup_task_iter_end(cgroup, &it);
+		cgroup_task_iter_end(&it);
 	}
 
 	if (!chosen)

Signature · 1 line

1.8.3.1

cgroup is in the process of converting to css (cgroup_subsys_state) from cgroup as the principal subsystem interface handle. This is mostly to prepare for the unified hierarchy support where css's will be created and destroyed dynamically but also helps cleaning up subsystem implementations as css is usually what they are interested in anyway.

This patch converts task iterators to deal with css instead of cgroup. Note that under unified hierarchy, different sets of tasks will be considered belonging to a given cgroup depending on the subsystem in question and making the iterators deal with css instead cgroup provides them with enough information about the iteration.

While at it, fix several function comment formats in cpuset.c.

This patch doesn't introduce any behavior differences.

Signed-off-by Tejun Heo <[email protected]>

Cc Li Zefan <[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Michal Hocko <[email protected]>

Cc Balbir Singh <[email protected]>

Cc Matt Helsley <matthltc-r/[email protected]>

---
 include/linux/cgroup.h  |  21 ++++-----
 kernel/cgroup.c         | 112 ++++++++++++++++++++++++------------------------
 kernel/cgroup_freezer.c |  26 ++++++-----
 kernel/cpuset.c         |  41 ++++++++----------
 mm/memcontrol.c         |  11 +++--
 5 files changed, 104 insertions(+), 107 deletions(-)

include/linux/cgroup.h +11 -10

index 2e9a799..6f6d87b 100644
@@ -881,21 +881,22 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
 	     (pos) = css_next_descendant_post((pos), (css)))
 
-/* A cgroup_task_iter should be treated as an opaque object */
-struct cgroup_task_iter {
-	struct cgroup			*origin_cgrp;
+/* A css_task_iter should be treated as an opaque object */
+struct css_task_iter {
+	struct cgroup_subsys_state	*origin_css;
 	struct list_head		*cset_link;
 	struct list_head		*task;
 };
 
-void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it);
-struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it);
-void cgroup_task_iter_end(struct cgroup_task_iter *it);
+void css_task_iter_start(struct cgroup_subsys_state *css,
+			 struct css_task_iter *it);
+struct task_struct *css_task_iter_next(struct css_task_iter *it);
+void css_task_iter_end(struct css_task_iter *it);
 
-int cgroup_scan_tasks(struct cgroup *cgrp,
-		      bool (*test)(struct task_struct *, void *),
-		      void (*process)(struct task_struct *, void *),
-		      void *data, struct ptr_heap *heap);
+int css_scan_tasks(struct cgroup_subsys_state *css,
+		   bool (*test)(struct task_struct *, void *),
+		   void (*process)(struct task_struct *, void *),
+		   void *data, struct ptr_heap *heap);
 
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);

kernel/cgroup.c +57 -55

index 4e354b59..c61b24f 100644
@@ -370,7 +370,7 @@ static int cgroup_init_idr(struct cgroup_subsys *ss,
 /*
  * css_set_lock protects the list of css_set objects, and the chain of
  * tasks off each css_set.  Nests outside task->alloc_lock due to
- * cgroup_task_iter_start().
+ * css_task_iter_start().
  */
 static DEFINE_RWLOCK(css_set_lock);
 static int css_set_count;

@@ -398,9 +398,9 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[])
 
 /*
  * We don't maintain the lists running through each css_set to its task
- * until after the first call to cgroup_task_iter_start().  This reduces
- * the fork()/exit() overhead for people who have cgroups compiled into
- * their kernel but not actually in use.
+ * until after the first call to css_task_iter_start().  This reduces the
+ * fork()/exit() overhead for people who have cgroups compiled into their
+ * kernel but not actually in use.
  */
 static int use_task_css_set_links __read_mostly;
 

@@ -2982,7 +2982,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
  * To reduce the fork() overhead for systems that are not actually using
  * their cgroups capability, we don't maintain the lists running through
  * each css_set to its tasks until we see the list actually used - in other
- * words after the first call to cgroup_task_iter_start().
+ * words after the first call to css_task_iter_start().
  */
 static void cgroup_enable_task_cg_lists(void)
 {

@@ -3197,12 +3197,12 @@ css_next_descendant_post(struct cgroup_subsys_state *pos,
 EXPORT_SYMBOL_GPL(css_next_descendant_post);
 
 /**
- * cgroup_advance_task_iter - advance a task itererator to the next css_set
+ * css_advance_task_iter - advance a task itererator to the next css_set
  * @it: the iterator to advance
  *
  * Advance @it to the next css_set to walk.
  */
-static void cgroup_advance_task_iter(struct cgroup_task_iter *it)
+static void css_advance_task_iter(struct css_task_iter *it)
 {
 	struct list_head *l = it->cset_link;
 	struct cgrp_cset_link *link;

@@ -3211,7 +3211,7 @@ static void cgroup_advance_task_iter(struct cgroup_task_iter *it)
 	/* Advance to the next non-empty css_set */
 	do {
 		l = l->next;
-		if (l == &it->origin_cgrp->cset_links) {
+		if (l == &it->origin_css->cgroup->cset_links) {
 			it->cset_link = NULL;
 			return;
 		}

@@ -3223,47 +3223,48 @@ static void cgroup_advance_task_iter(struct cgroup_task_iter *it)
 }
 
 /**
- * cgroup_task_iter_start - initiate task iteration
- * @cgrp: the cgroup to walk tasks of
+ * css_task_iter_start - initiate task iteration
+ * @css: the css to walk tasks of
  * @it: the task iterator to use
  *
- * Initiate iteration through the tasks of @cgrp.  The caller can call
- * cgroup_task_iter_next() to walk through the tasks until the function
- * returns NULL.  On completion of iteration, cgroup_task_iter_end() must
- * be called.
+ * Initiate iteration through the tasks of @css.  The caller can call
+ * css_task_iter_next() to walk through the tasks until the function
+ * returns NULL.  On completion of iteration, css_task_iter_end() must be
+ * called.
  *
  * Note that this function acquires a lock which is released when the
  * iteration finishes.  The caller can't sleep while iteration is in
  * progress.
  */
-void cgroup_task_iter_start(struct cgroup *cgrp, struct cgroup_task_iter *it)
+void css_task_iter_start(struct cgroup_subsys_state *css,
+			 struct css_task_iter *it)
 	__acquires(css_set_lock)
 {
 	/*
-	 * The first time anyone tries to iterate across a cgroup,
-	 * we need to enable the list linking each css_set to its
-	 * tasks, and fix up all existing tasks.
+	 * The first time anyone tries to iterate across a css, we need to
+	 * enable the list linking each css_set to its tasks, and fix up
+	 * all existing tasks.
 	 */
 	if (!use_task_css_set_links)
 		cgroup_enable_task_cg_lists();
 
 	read_lock(&css_set_lock);
 
-	it->origin_cgrp = cgrp;
-	it->cset_link = &cgrp->cset_links;
+	it->origin_css = css;
+	it->cset_link = &css->cgroup->cset_links;
 
-	cgroup_advance_task_iter(it);
+	css_advance_task_iter(it);
 }
 
 /**
- * cgroup_task_iter_next - return the next task for the iterator
+ * css_task_iter_next - return the next task for the iterator
  * @it: the task iterator being iterated
  *
  * The "next" function for task iteration.  @it should have been
- * initialized via cgroup_task_iter_start().  Returns NULL when the
- * iteration reaches the end.
+ * initialized via css_task_iter_start().  Returns NULL when the iteration
+ * reaches the end.
  */
-struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it)
+struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;

@@ -3281,7 +3282,7 @@ struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it)
 		 * We reached the end of this task list - move on to the
 		 * next cgrp_cset_link.
 		 */
-		cgroup_advance_task_iter(it);
+		css_advance_task_iter(it);
 	} else {
 		it->task = l;
 	}

@@ -3289,12 +3290,12 @@ struct task_struct *cgroup_task_iter_next(struct cgroup_task_iter *it)
 }
 
 /**
- * cgroup_task_iter_end - finish task iteration
+ * css_task_iter_end - finish task iteration
  * @it: the task iterator to finish
  *
- * Finish task iteration started by cgroup_task_iter_start().
+ * Finish task iteration started by css_task_iter_start().
  */
-void cgroup_task_iter_end(struct cgroup_task_iter *it)
+void css_task_iter_end(struct css_task_iter *it)
 	__releases(css_set_lock)
 {
 	read_unlock(&css_set_lock);

@@ -3335,24 +3336,24 @@ static inline int started_after(void *p1, void *p2)
 }
 
 /**
- * cgroup_scan_tasks - iterate though all the tasks in a cgroup
- * @cgrp: the cgroup to iterate tasks of
+ * css_scan_tasks - iterate though all the tasks in a css
+ * @css: the css to iterate tasks of
  * @test: optional test callback
  * @process: process callback
  * @data: data passed to @test and @process
  * @heap: optional pre-allocated heap used for task iteration
  *
- * Iterate through all the tasks in a cgroup, calling @test for each, and
- * if it returns %true, call @process for it also.
+ * Iterate through all the tasks in @css, calling @test for each, and if it
+ * returns %true, call @process for it also.
  *
  * @test may be NULL, meaning always true (select all tasks), which
- * effectively duplicates cgroup_task_iter_{start,next,end}() but does not
+ * effectively duplicates css_task_iter_{start,next,end}() but does not
  * lock css_set_lock for the call to @process.
  *
  * It is guaranteed that @process will act on every task that is a member
- * of @cgrp for the duration of this call.  This function may or may not
- * call @process for tasks that exit or move to a different cgroup during
- * the call, or are forked or move into the cgroup during the call.
+ * of @css for the duration of this call.  This function may or may not
+ * call @process for tasks that exit or move to a different css during the
+ * call, or are forked or move into the css during the call.
  *
  * Note that @test may be called with locks held, and may in some
  * situations be called multiple times for the same task, so it should be

@@ -3363,13 +3364,13 @@ static inline int started_after(void *p1, void *p2)
  * temporary heap will be used (allocation of which may cause this function
  * to fail).
  */
-int cgroup_scan_tasks(struct cgroup *cgrp,
-		      bool (*test)(struct task_struct *, void *),
-		      void (*process)(struct task_struct *, void *),
-		      void *data, struct ptr_heap *heap)
+int css_scan_tasks(struct cgroup_subsys_state *css,
+		   bool (*test)(struct task_struct *, void *),
+		   void (*process)(struct task_struct *, void *),
+		   void *data, struct ptr_heap *heap)
 {
 	int retval, i;
-	struct cgroup_task_iter it;
+	struct css_task_iter it;
 	struct task_struct *p, *dropped;
 	/* Never dereference latest_task, since it's not refcounted */
 	struct task_struct *latest_task = NULL;

@@ -3390,7 +3391,7 @@ int cgroup_scan_tasks(struct cgroup *cgrp,
 
  again:
 	/*
-	 * Scan tasks in the cgroup, using the @test callback to determine
+	 * Scan tasks in the css, using the @test callback to determine
 	 * which are of interest, and invoking @process callback on the
 	 * ones which need an update.  Since we don't want to hold any
 	 * locks during the task updates, gather tasks to be processed in a

@@ -3401,8 +3402,8 @@ int cgroup_scan_tasks(struct cgroup *cgrp,
 	 * guarantees forward progress and that we don't miss any tasks.
 	 */
 	heap->size = 0;
-	cgroup_task_iter_start(cgrp, &it);
-	while ((p = cgroup_task_iter_next(&it))) {
+	css_task_iter_start(css, &it);
+	while ((p = css_task_iter_next(&it))) {
 		/*
 		 * Only affect tasks that qualify per the caller's callback,
 		 * if he provided one

@@ -3435,7 +3436,7 @@ int cgroup_scan_tasks(struct cgroup *cgrp,
 		 * the heap and wasn't inserted
 		 */
 	}
-	cgroup_task_iter_end(&it);
+	css_task_iter_end(&it);
 
 	if (heap->size) {
 		for (i = 0; i < heap->size; i++) {

@@ -3478,7 +3479,8 @@ static void cgroup_transfer_one_task(struct task_struct *task, void *data)
  */
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from)
 {
-	return cgroup_scan_tasks(from, NULL, cgroup_transfer_one_task, to, NULL);
+	return css_scan_tasks(&from->dummy_css, NULL, cgroup_transfer_one_task,
+			      to, NULL);
 }
 
 /*

@@ -3632,7 +3634,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	pid_t *array;
 	int length;
 	int pid, n = 0; /* used for populating the array */
-	struct cgroup_task_iter it;
+	struct css_task_iter it;
 	struct task_struct *tsk;
 	struct cgroup_pidlist *l;
 

@@ -3647,8 +3649,8 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 	if (!array)
 		return -ENOMEM;
 	/* now, populate the array */
-	cgroup_task_iter_start(cgrp, &it);
-	while ((tsk = cgroup_task_iter_next(&it))) {
+	css_task_iter_start(&cgrp->dummy_css, &it);
+	while ((tsk = css_task_iter_next(&it))) {
 		if (unlikely(n == length))
 			break;
 		/* get tgid or pid for procs or tasks file respectively */

@@ -3659,7 +3661,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
 		if (pid > 0) /* make sure to only use valid results */
 			array[n++] = pid;
 	}
-	cgroup_task_iter_end(&it);
+	css_task_iter_end(&it);
 	length = n;
 	/* now sort & (if procs) strip out duplicates */
 	sort(array, length, sizeof(pid_t), cmppid, NULL);

@@ -3693,7 +3695,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 {
 	int ret = -EINVAL;
 	struct cgroup *cgrp;
-	struct cgroup_task_iter it;
+	struct css_task_iter it;
 	struct task_struct *tsk;
 
 	/*

@@ -3707,8 +3709,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	ret = 0;
 	cgrp = dentry->d_fsdata;
 
-	cgroup_task_iter_start(cgrp, &it);
-	while ((tsk = cgroup_task_iter_next(&it))) {
+	css_task_iter_start(&cgrp->dummy_css, &it);
+	while ((tsk = css_task_iter_next(&it))) {
 		switch (tsk->state) {
 		case TASK_RUNNING:
 			stats->nr_running++;

@@ -3728,7 +3730,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 			break;
 		}
 	}
-	cgroup_task_iter_end(&it);
+	css_task_iter_end(&it);
 
 err:
 	return ret;

kernel/cgroup_freezer.c +12 -14

index e0ab9bf..5cd2b6d 100644
@@ -258,7 +258,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
 	struct cgroup_subsys_state *pos;
-	struct cgroup_task_iter it;
+	struct css_task_iter it;
 	struct task_struct *task;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());

@@ -279,9 +279,9 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	}
 
 	/* are all tasks frozen? */
-	cgroup_task_iter_start(css->cgroup, &it);
+	css_task_iter_start(css, &it);
 
-	while ((task = cgroup_task_iter_next(&it))) {
+	while ((task = css_task_iter_next(&it))) {
 		if (freezing(task)) {
 			/*
 			 * freezer_should_skip() indicates that the task

@@ -296,7 +296,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 
 	freezer->state |= CGROUP_FROZEN;
 out_iter_end:
-	cgroup_task_iter_end(&it);
+	css_task_iter_end(&it);
 out_unlock:
 	spin_unlock_irq(&freezer->lock);
 }

@@ -322,26 +322,24 @@ static int freezer_read(struct cgroup_subsys_state *css, struct cftype *cft,
 
 static void freeze_cgroup(struct freezer *freezer)
 {
-	struct cgroup *cgroup = freezer->css.cgroup;
-	struct cgroup_task_iter it;
+	struct css_task_iter it;
 	struct task_struct *task;
 
-	cgroup_task_iter_start(cgroup, &it);
-	while ((task = cgroup_task_iter_next(&it)))
+	css_task_iter_start(&freezer->css, &it);
+	while ((task = css_task_iter_next(&it)))
 		freeze_task(task);
-	cgroup_task_iter_end(&it);
+	css_task_iter_end(&it);
 }
 
 static void unfreeze_cgroup(struct freezer *freezer)
 {
-	struct cgroup *cgroup = freezer->css.cgroup;
-	struct cgroup_task_iter it;
+	struct css_task_iter it;
 	struct task_struct *task;
 
-	cgroup_task_iter_start(cgroup, &it);
-	while ((task = cgroup_task_iter_next(&it)))
+	css_task_iter_start(&freezer->css, &it);
+	while ((task = css_task_iter_next(&it)))
 		__thaw_task(task);
-	cgroup_task_iter_end(&it);
+	css_task_iter_end(&it);
 }
 
 /**

kernel/cpuset.c +19 -22

index 6fe23f2..39e5217 100644
@@ -832,8 +832,8 @@ static struct cpuset *effective_nodemask_cpuset(struct cpuset *cs)
  * @tsk: task to test
  * @data: cpuset to @tsk belongs to
  *
- * Called by cgroup_scan_tasks() for each task in a cgroup whose
- * cpus_allowed mask needs to be changed.
+ * Called by css_scan_tasks() for each task in a cgroup whose cpus_allowed
+ * mask needs to be changed.
  *
  * We don't need to re-check for the cgroup/cpuset membership, since we're
  * holding cpuset_mutex at this point.

@@ -849,27 +849,26 @@ static void cpuset_change_cpumask(struct task_struct *tsk, void *data)
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
- * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
+ * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
  *
  * Called with cpuset_mutex held
  *
- * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
+ * The css_scan_tasks() function will scan all the tasks in a cgroup,
  * calling callback functions for each.
  *
- * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * No return value. It's guaranteed that css_scan_tasks() always returns 0
  * if @heap != NULL.
  */
 static void update_tasks_cpumask(struct cpuset *cs, struct ptr_heap *heap)
 {
-	cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_cpumask, cs,
-			  heap);
+	css_scan_tasks(&cs->css, NULL, cpuset_change_cpumask, cs, heap);
 }
 
 /*
  * update_tasks_cpumask_hier - Update the cpumasks of tasks in the hierarchy.
  * @root_cs: the root cpuset of the hierarchy
  * @update_root: update root cpuset or not?
- * @heap: the heap used by cgroup_scan_tasks()
+ * @heap: the heap used by css_scan_tasks()
  *
  * This will update cpumasks of tasks in @root_cs and all other empty cpusets
  * which take on cpumask of @root_cs.

@@ -1082,11 +1081,10 @@ static void *cpuset_being_rebound;
 /**
  * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
- * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
+ * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
  *
- * Called with cpuset_mutex held
- * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
- * if @heap != NULL.
+ * Called with cpuset_mutex held.  No return value. It's guaranteed that
+ * css_scan_tasks() always returns 0 if @heap != NULL.
  */
 static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
 {

@@ -1109,8 +1107,7 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
 	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
 	 * is idempotent.  Also migrate pages in each mm to new nodes.
 	 */
-	cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_nodemask, &arg,
-			  heap);
+	css_scan_tasks(&cs->css, NULL, cpuset_change_nodemask, &arg, heap);
 
 	/*
 	 * All the tasks' nodemasks have been updated, update

@@ -1126,7 +1123,7 @@ static void update_tasks_nodemask(struct cpuset *cs, struct ptr_heap *heap)
  * update_tasks_nodemask_hier - Update the nodemasks of tasks in the hierarchy.
  * @cs: the root cpuset of the hierarchy
  * @update_root: update the root cpuset or not?
- * @heap: the heap used by cgroup_scan_tasks()
+ * @heap: the heap used by css_scan_tasks()
  *
  * This will update nodemasks of tasks in @root_cs and all other empty cpusets
  * which take on nodemask of @root_cs.

@@ -1254,12 +1251,12 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
 	return 0;
 }
 
-/*
+/**
  * cpuset_change_flag - make a task's spread flags the same as its cpuset's
  * @tsk: task to be updated
  * @data: cpuset to @tsk belongs to
  *
- * Called by cgroup_scan_tasks() for each task in a cgroup.
+ * Called by css_scan_tasks() for each task in a cgroup.
  *
  * We don't need to re-check for the cgroup/cpuset membership, since we're
  * holding cpuset_mutex at this point.

@@ -1271,22 +1268,22 @@ static void cpuset_change_flag(struct task_struct *tsk, void *data)
 	cpuset_update_task_spread_flag(cs, tsk);
 }
 
-/*
+/**
  * update_tasks_flags - update the spread flags of tasks in the cpuset.
  * @cs: the cpuset in which each task's spread flags needs to be changed
- * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
+ * @heap: if NULL, defer allocating heap memory to css_scan_tasks()
  *
  * Called with cpuset_mutex held
  *
- * The cgroup_scan_tasks() function will scan all the tasks in a cgroup,
+ * The css_scan_tasks() function will scan all the tasks in a cgroup,
  * calling callback functions for each.
  *
- * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * No return value. It's guaranteed that css_scan_tasks() always returns 0
  * if @heap != NULL.
  */
 static void update_tasks_flags(struct cpuset *cs, struct ptr_heap *heap)
 {
-	cgroup_scan_tasks(cs->css.cgroup, NULL, cpuset_change_flag, cs, heap);
+	css_scan_tasks(&cs->css, NULL, cpuset_change_flag, cs, heap);
 }
 
 /*

mm/memcontrol.c +5 -6

index 5a5f4dc..95106a9 100644
@@ -1799,12 +1799,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
 	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
-		struct cgroup *cgroup = iter->css.cgroup;
-		struct cgroup_task_iter it;
+		struct css_task_iter it;
 		struct task_struct *task;
 
-		cgroup_task_iter_start(cgroup, &it);
-		while ((task = cgroup_task_iter_next(&it))) {
+		css_task_iter_start(&iter->css, &it);
+		while ((task = css_task_iter_next(&it))) {
 			switch (oom_scan_process_thread(task, totalpages, NULL,
 							false)) {
 			case OOM_SCAN_SELECT:

@@ -1817,7 +1816,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 			case OOM_SCAN_CONTINUE:
 				continue;
 			case OOM_SCAN_ABORT:
-				cgroup_task_iter_end(&it);
+				css_task_iter_end(&it);
 				mem_cgroup_iter_break(memcg, iter);
 				if (chosen)
 					put_task_struct(chosen);

@@ -1834,7 +1833,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				get_task_struct(chosen);
 			}
 		}
-		cgroup_task_iter_end(&it);
+		css_task_iter_end(&it);
 	}
 
 	if (!chosen)

Signature · 1 line

1.8.3.1