Merge branch 'for-3.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup update from Tejun Heo:
 "cpuset got simplified a bit.  cgroup core got a fix on unified
  hierarchy and grew some effective css related interfaces which will be
  used for blkio support for writeback IO traffic which is currently
  being worked on"

* 'for-3.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: implement cgroup_get_e_css()
  cgroup: add cgroup_subsys->css_e_css_changed()
  cgroup: add cgroup_subsys->css_released()
  cgroup: fix the async css offline wait logic in cgroup_subtree_control_write()
  cgroup: restructure child_subsys_mask handling in cgroup_subtree_control_write()
  cgroup: separate out cgroup_calc_child_subsys_mask() from cgroup_refresh_child_subsys_mask()
  cpuset: lock vs unlock typo
  cpuset: simplify cpuset_node_allowed API
  cpuset: convert callback_mutex to a spinlock

include/linux/cgroup.h

@@ -638,8 +638,10 @@ struct cgroup_subsys {
 	struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css);
 	int (*css_online)(struct cgroup_subsys_state *css);
 	void (*css_offline)(struct cgroup_subsys_state *css);
+	void (*css_released)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
+	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
 	int (*can_attach)(struct cgroup_subsys_state *css,
 			  struct cgroup_taskset *tset);
@@ -934,6 +936,8 @@ void css_task_iter_end(struct css_task_iter *it);
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
+struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
+					     struct cgroup_subsys *ss);
 struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
 						       struct cgroup_subsys *ss);
 

include/linux/cpuset.h

@@ -48,29 +48,16 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 void cpuset_init_current_mems_allowed(void);
 int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
-extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask);
-extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask);
+extern int __cpuset_node_allowed(int node, gfp_t gfp_mask);
 
-static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
+static inline int cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
-	return nr_cpusets() <= 1 ||
-		__cpuset_node_allowed_softwall(node, gfp_mask);
+	return nr_cpusets() <= 1 || __cpuset_node_allowed(node, gfp_mask);
 }
 
-static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
+static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
-	return nr_cpusets() <= 1 ||
-		__cpuset_node_allowed_hardwall(node, gfp_mask);
-}
-
-static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
-{
-	return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask);
-}
-
-static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
-{
-	return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask);
+	return cpuset_node_allowed(zone_to_nid(z), gfp_mask);
 }
 
 extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
@@ -179,22 +166,12 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 	return 1;
 }
 
-static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
-{
-	return 1;
-}
-
-static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
-{
-	return 1;
-}
-
-static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_node_allowed(int node, gfp_t gfp_mask)
 {
 	return 1;
 }
 
-static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
 	return 1;
 }

kernel/cgroup.c

@@ -277,6 +277,10 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 	if (!(cgrp->root->subsys_mask & (1 << ss->id)))
 		return NULL;
 
+	/*
+	 * This function is used while updating css associations and thus
+	 * can't test the csses directly.  Use ->child_subsys_mask.
+	 */
 	while (cgroup_parent(cgrp) &&
 	       !(cgroup_parent(cgrp)->child_subsys_mask & (1 << ss->id)))
 		cgrp = cgroup_parent(cgrp);
@@ -284,6 +288,39 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp,
 	return cgroup_css(cgrp, ss);
 }
 
+/**
+ * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem
+ * @cgrp: the cgroup of interest
+ * @ss: the subsystem of interest
+ *
+ * Find and get the effective css of @cgrp for @ss.  The effective css is
+ * defined as the matching css of the nearest ancestor including self which
+ * has @ss enabled.  If @ss is not mounted on the hierarchy @cgrp is on,
+ * the root css is returned, so this function always returns a valid css.
+ * The returned css must be put using css_put().
+ */
+struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp,
+					     struct cgroup_subsys *ss)
+{
+	struct cgroup_subsys_state *css;
+
+	rcu_read_lock();
+
+	do {
+		css = cgroup_css(cgrp, ss);
+
+		if (css && css_tryget_online(css))
+			goto out_unlock;
+		cgrp = cgroup_parent(cgrp);
+	} while (cgrp);
+
+	css = init_css_set.subsys[ss->id];
+	css_get(css);
+out_unlock:
+	rcu_read_unlock();
+	return css;
+}
+
 /* convenient tests for these bits */
 static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 {
@@ -1019,31 +1056,30 @@ static void cgroup_put(struct cgroup *cgrp)
 }
 
 /**
- * cgroup_refresh_child_subsys_mask - update child_subsys_mask
+ * cgroup_calc_child_subsys_mask - calculate child_subsys_mask
  * @cgrp: the target cgroup
+ * @subtree_control: the new subtree_control mask to consider
  *
  * On the default hierarchy, a subsystem may request other subsystems to be
  * enabled together through its ->depends_on mask.  In such cases, more
  * subsystems than specified in "cgroup.subtree_control" may be enabled.
  *
- * This function determines which subsystems need to be enabled given the
- * current @cgrp->subtree_control and records it in
- * @cgrp->child_subsys_mask.  The resulting mask is always a superset of
- * @cgrp->subtree_control and follows the usual hierarchy rules.
+ * This function calculates which subsystems need to be enabled if
+ * @subtree_control is to be applied to @cgrp.  The returned mask is always
+ * a superset of @subtree_control and follows the usual hierarchy rules.
  */
-static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp)
+static unsigned int cgroup_calc_child_subsys_mask(struct cgroup *cgrp,
+						  unsigned int subtree_control)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
-	unsigned int cur_ss_mask = cgrp->subtree_control;
+	unsigned int cur_ss_mask = subtree_control;
 	struct cgroup_subsys *ss;
 	int ssid;
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	if (!cgroup_on_dfl(cgrp)) {
-		cgrp->child_subsys_mask = cur_ss_mask;
-		return;
-	}
+	if (!cgroup_on_dfl(cgrp))
+		return cur_ss_mask;
 
 	while (true) {
 		unsigned int new_ss_mask = cur_ss_mask;
@@ -1067,7 +1103,20 @@ static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp)
 		cur_ss_mask = new_ss_mask;
 	}
 
-	cgrp->child_subsys_mask = cur_ss_mask;
+	return cur_ss_mask;
+}
+
+/**
+ * cgroup_refresh_child_subsys_mask - update child_subsys_mask
+ * @cgrp: the target cgroup
+ *
+ * Update @cgrp->child_subsys_mask according to the current
+ * @cgrp->subtree_control using cgroup_calc_child_subsys_mask().
+ */
+static void cgroup_refresh_child_subsys_mask(struct cgroup *cgrp)
+{
+	cgrp->child_subsys_mask =
+		cgroup_calc_child_subsys_mask(cgrp, cgrp->subtree_control);
 }
 
 /**
@@ -2641,7 +2690,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 					    loff_t off)
 {
 	unsigned int enable = 0, disable = 0;
-	unsigned int css_enable, css_disable, old_ctrl, new_ctrl;
+	unsigned int css_enable, css_disable, old_sc, new_sc, old_ss, new_ss;
 	struct cgroup *cgrp, *child;
 	struct cgroup_subsys *ss;
 	char *tok;
@@ -2693,36 +2742,6 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 				ret = -ENOENT;
 				goto out_unlock;
 			}
-
-			/*
-			 * @ss is already enabled through dependency and
-			 * we'll just make it visible.  Skip draining.
-			 */
-			if (cgrp->child_subsys_mask & (1 << ssid))
-				continue;
-
-			/*
-			 * Because css offlining is asynchronous, userland
-			 * might try to re-enable the same controller while
-			 * the previous instance is still around.  In such
-			 * cases, wait till it's gone using offline_waitq.
-			 */
-			cgroup_for_each_live_child(child, cgrp) {
-				DEFINE_WAIT(wait);
-
-				if (!cgroup_css(child, ss))
-					continue;
-
-				cgroup_get(child);
-				prepare_to_wait(&child->offline_waitq, &wait,
-						TASK_UNINTERRUPTIBLE);
-				cgroup_kn_unlock(of->kn);
-				schedule();
-				finish_wait(&child->offline_waitq, &wait);
-				cgroup_put(child);
-
-				return restart_syscall();
-			}
 		} else if (disable & (1 << ssid)) {
 			if (!(cgrp->subtree_control & (1 << ssid))) {
 				disable &= ~(1 << ssid);
@@ -2758,18 +2777,47 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	 * subsystems than specified may need to be enabled or disabled
 	 * depending on subsystem dependencies.
 	 */
-	cgrp->subtree_control |= enable;
-	cgrp->subtree_control &= ~disable;
+	old_sc = cgrp->subtree_control;
+	old_ss = cgrp->child_subsys_mask;
+	new_sc = (old_sc | enable) & ~disable;
+	new_ss = cgroup_calc_child_subsys_mask(cgrp, new_sc);
 
-	old_ctrl = cgrp->child_subsys_mask;
-	cgroup_refresh_child_subsys_mask(cgrp);
-	new_ctrl = cgrp->child_subsys_mask;
-
-	css_enable = ~old_ctrl & new_ctrl;
-	css_disable = old_ctrl & ~new_ctrl;
+	css_enable = ~old_ss & new_ss;
+	css_disable = old_ss & ~new_ss;
 	enable |= css_enable;
 	disable |= css_disable;
 
+	/*
+	 * Because css offlining is asynchronous, userland might try to
+	 * re-enable the same controller while the previous instance is
+	 * still around.  In such cases, wait till it's gone using
+	 * offline_waitq.
+	 */
+	for_each_subsys(ss, ssid) {
+		if (!(css_enable & (1 << ssid)))
+			continue;
+
+		cgroup_for_each_live_child(child, cgrp) {
+			DEFINE_WAIT(wait);
+
+			if (!cgroup_css(child, ss))
+				continue;
+
+			cgroup_get(child);
+			prepare_to_wait(&child->offline_waitq, &wait,
+					TASK_UNINTERRUPTIBLE);
+			cgroup_kn_unlock(of->kn);
+			schedule();
+			finish_wait(&child->offline_waitq, &wait);
+			cgroup_put(child);
+
+			return restart_syscall();
+		}
+	}
+
+	cgrp->subtree_control = new_sc;
+	cgrp->child_subsys_mask = new_ss;
+
 	/*
 	 * Create new csses or make the existing ones visible.  A css is
 	 * created invisible if it's being implicitly enabled through
@@ -2825,6 +2873,24 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 		}
 	}
 
+	/*
+	 * The effective csses of all the descendants (excluding @cgrp) may
+	 * have changed.  Subsystems can optionally subscribe to this event
+	 * by implementing ->css_e_css_changed() which is invoked if any of
+	 * the effective csses seen from the css's cgroup may have changed.
+	 */
+	for_each_subsys(ss, ssid) {
+		struct cgroup_subsys_state *this_css = cgroup_css(cgrp, ss);
+		struct cgroup_subsys_state *css;
+
+		if (!ss->css_e_css_changed || !this_css)
+			continue;
+
+		css_for_each_descendant_pre(css, this_css)
+			if (css != this_css)
+				ss->css_e_css_changed(css);
+	}
+
 	kernfs_activate(cgrp->kn);
 	ret = 0;
 out_unlock:
@@ -2832,9 +2898,8 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 
 err_undo_css:
-	cgrp->subtree_control &= ~enable;
-	cgrp->subtree_control |= disable;
-	cgroup_refresh_child_subsys_mask(cgrp);
+	cgrp->subtree_control = old_sc;
+	cgrp->child_subsys_mask = old_ss;
 
 	for_each_subsys(ss, ssid) {
 		if (!(enable & (1 << ssid)))
@@ -4370,6 +4435,8 @@ static void css_release_work_fn(struct work_struct *work)
 	if (ss) {
 		/* css release path */
 		cgroup_idr_remove(&ss->css_idr, css->id);
+		if (ss->css_released)
+			ss->css_released(css);
 	} else {
 		/* cgroup release path */
 		cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);

mm/hugetlb.c

@@ -582,7 +582,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						MAX_NR_ZONES - 1, nodemask) {
-		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) {
+		if (cpuset_zone_allowed(zone, htlb_alloc_mask(h))) {
 			page = dequeue_huge_page_node(h, zone_to_nid(zone));
 			if (page) {
 				if (avoid_reserve)

mm/oom_kill.c

@@ -233,7 +233,7 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist,
 	/* Check this allocation failure is caused by cpuset's wall function */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 			high_zoneidx, nodemask)
-		if (!cpuset_zone_allowed_softwall(zone, gfp_mask))
+		if (!cpuset_zone_allowed(zone, gfp_mask))
 			cpuset_limited = true;
 
 	if (cpuset_limited) {

mm/page_alloc.c

@@ -1990,7 +1990,7 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 
 	/*
 	 * Scan zonelist, looking for a zone with enough free.
-	 * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c.
+	 * See also __cpuset_node_allowed() comment in kernel/cpuset.c.
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						high_zoneidx, nodemask) {
@@ -2001,7 +2001,7 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
 				continue;
 		if (cpusets_enabled() &&
 			(alloc_flags & ALLOC_CPUSET) &&
-			!cpuset_zone_allowed_softwall(zone, gfp_mask))
+			!cpuset_zone_allowed(zone, gfp_mask))
 				continue;
 		/*
 		 * Distribute pages in proportion to the individual
@@ -2529,7 +2529,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 			alloc_flags |= ALLOC_HARDER;
 		/*
 		 * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
-		 * comment for __cpuset_node_allowed_softwall().
+		 * comment for __cpuset_node_allowed().
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
 	} else if (unlikely(rt_task(current)) && !in_interrupt())

mm/slab.c

@@ -3015,7 +3015,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 		nid = zone_to_nid(zone);
 
-		if (cpuset_zone_allowed_hardwall(zone, flags) &&
+		if (cpuset_zone_allowed(zone, flags | __GFP_HARDWALL) &&
 			get_node(cache, nid) &&
 			get_node(cache, nid)->free_objects) {
 				obj = ____cache_alloc_node(cache,

mm/slub.c

@@ -1665,7 +1665,8 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 
 			n = get_node(s, zone_to_nid(zone));
 
-			if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+			if (n && cpuset_zone_allowed(zone,
+						     flags | __GFP_HARDWALL) &&
 					n->nr_partial > s->min_partial) {
 				object = get_partial_node(s, n, c, flags);
 				if (object) {

mm/vmscan.c

@@ -2405,7 +2405,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		 * to global LRU.
 		 */
 		if (global_reclaim(sc)) {
-			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+			if (!cpuset_zone_allowed(zone,
+						 GFP_KERNEL | __GFP_HARDWALL))
 				continue;
 
 			lru_pages += zone_reclaimable_pages(zone);
@@ -3388,7 +3389,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!populated_zone(zone))
 		return;
 
-	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
 	if (pgdat->kswapd_max_order < order) {