Merge tag 'cgroup-for-7.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - Last cycle deferred css teardown on cgroup removal until the cgroup
   depopulated, so a css is not taken offline while tasks can still
   reference it. Disabling a controller through cgroup.subtree_control
   still had the same problem. This reworks the deferral from per-cgroup
   to per-css so that path is covered too.

 - New RDMA controller monitoring files: rdma.peak for per-device peak
   usage and rdma.events / rdma.events.local for resource-limit
   exhaustion. The max-limit parser was rewritten, fixing two input
   parsing bugs.

 - cpuset: fix a sched-domain leak on the domain-rebuild failure path
   and skip a redundant hardwall ancestor scan on v2.

 - Misc: pair the remaining lockless cgroup.max.* reads with WRITE_ONCE,
   assorted selftest robustness fixes, and doc path corrections.

* tag 'cgroup-for-7.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (22 commits)
  cgroup: Migrate tasks to the root css when a controller is rebound
  docs: cgroup: Fix stale source file paths
  cgroup/cpuset: Free sched domains on rebuild guard failure
  cgroup: pair max limit READ_ONCE() with WRITE_ONCE()
  selftests/cgroup: enable memory controller in hugetlb memcg test
  cgroup/rdma: Drop unnecessary READ_ONCE() on event counters
  cgroup: Defer kill_css_finish() in cgroup_apply_control_disable()
  cgroup: Add per-subsys-css kill_css_finish deferral
  cgroup: Move populated counters to cgroup_subsys_state
  cgroup: Annotate unlocked nr_populated_* accesses with READ_ONCE/WRITE_ONCE
  cgroup: Inline cgroup_has_tasks() in cgroup.h
  cgroup/rdma: document rdma.peak, rdma.events and rdma.events.local
  cgroup/rdma: add rdma.events.local for per-cgroup allocation failure attribution
  cgroup/rdma: add rdma.events to track resource limit exhaustion
  cgroup/rdma: add rdma.peak for per-device peak usage tracking
  selftests/cgroup: check malloc return value in alloc_anon functions
  cgroup/cpuset: Skip hardwall ancestor scan in cpuset v2 in cpuset_current_node_allowed()
  selftests/cgroup: fix misleading debug message in test_cgfreezer_time_child
  selftests/cgroup: fix child process escaping to parent cleanup in test_cpucg_nice
  selftests/cgroup: Add NULL check after malloc in cgroup_util.c
  ...

16 files changed, 532 insertions, 211 deletions

diff --git a/Documentation/admin-guide/cgroup-v1/cgroups.rst b/Documentation/admin-guide/cgroup-v1/cgroups.rst
index 463f98453323..e501f45ea93f 100644
--- a/Documentation/admin-guide/cgroup-v1/cgroups.rst
+++ b/Documentation/admin-guide/cgroup-v1/cgroups.rst
@@ -525,7 +525,7 @@ cgroup. It may also be taken to prevent cgroups from being
 modified, but more specific locks may be more appropriate in that
 situation.
 
-See kernel/cgroup.c for more details.
+See kernel/cgroup/cgroup.c for more details.
 
 Subsystems can take/release the cgroup_mutex via the functions
 cgroup_lock()/cgroup_unlock().
diff --git a/Documentation/admin-guide/cgroup-v1/memcg_test.rst b/Documentation/admin-guide/cgroup-v1/memcg_test.rst
index 7c7cd457cf69..ebedbc3c3f9c 100644
--- a/Documentation/admin-guide/cgroup-v1/memcg_test.rst
+++ b/Documentation/admin-guide/cgroup-v1/memcg_test.rst
@@ -321,7 +321,7 @@ Under below explanation, we assume CONFIG_SWAP=y.
 ----------------------
 
 	Memory controller implements memory thresholds using cgroups notification
-	API. You can use tools/cgroup/cgroup_event_listener.c to test it.
+	API. You can use samples/cgroup/cgroup_event_listener.c to test it.
 
 	(Shell-A) Create cgroup and run event listener::
 
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 6efd0095ed99..993446ab66d0 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -2785,6 +2785,59 @@ RDMA Interface Files
 	  mlx4_0 hca_handle=1 hca_object=20
 	  ocrdma1 hca_handle=1 hca_object=23
 
+  rdma.peak
+	A read-only nested-keyed file that exists for all the cgroups
+	except root.  It shows the historical high watermark of
+	resource usage per device since the cgroup was created.
+
+	An example for mlx4 and ocrdma device follows::
+
+	  mlx4_0 hca_handle=1 hca_object=20
+	  ocrdma1 hca_handle=0 hca_object=23
+
+  rdma.events
+	A read-only nested-keyed file which exists on non-root
+	cgroups.  The following nested keys are defined.
+
+	  max
+		The number of times a process in this cgroup or its
+		descendants attempted an RDMA resource allocation that
+		was rejected because a rdma.max limit in the subtree
+		was reached.  This is a hierarchical counter: the event
+		is propagated upward to all ancestor cgroups.  A value
+		change in this file generates a file modified event.
+
+	  alloc_fail
+		The number of RDMA resource allocation attempts that
+		originated in this cgroup or its descendants and failed
+		due to a rdma.max limit being reached.  This is a
+		hierarchical counter propagated upward.
+
+	An example for mlx4 device follows::
+
+	  mlx4_0 hca_handle.max=5 hca_handle.alloc_fail=3 hca_object.max=0 hca_object.alloc_fail=0
+
+  rdma.events.local
+	Similar to rdma.events but the fields in the file are local
+	to the cgroup i.e. not hierarchical.  The file modified event
+	generated on this file reflects only the local events.
+
+	The following nested keys are defined.
+
+	  max
+		The number of times a process in this cgroup or its
+		descendants attempted an RDMA resource allocation that
+		was rejected because this cgroup's own rdma.max limit
+		was reached.
+	  alloc_fail
+		The number of RDMA resource allocation attempts
+		originating from this cgroup that failed due to this
+		cgroup's or an ancestor's rdma.max limit.
+
+	An example for mlx4 device follows::
+
+	  mlx4_0 hca_handle.max=5 hca_handle.alloc_fail=0 hca_object.max=0 hca_object.alloc_fail=0
+
 DMEM
 ----
 
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 50a784da7a81..de2cd6238c2a 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -254,6 +254,18 @@ struct cgroup_subsys_state {
 	int nr_descendants;
 
 	/*
+	 * Hierarchical populated state. For cgroup->self, nr_populated_csets
+	 * counts populated csets linked via cgrp_cset_link.
+	 * nr_populated_children counts immediate-child csses whose own
+	 * populated state is nonzero. Protected by css_set_lock.
+	 */
+	int nr_populated_csets;
+	int nr_populated_children;
+
+	/* deferred kill_css_finish() queued by css_update_populated() */
+	struct work_struct kill_finish_work;
+
+	/*
 	 * A singly-linked list of css structures to be rstat flushed.
 	 * This is a scratch field to be used exclusively by
 	 * css_rstat_flush().
@@ -504,17 +516,12 @@ struct cgroup {
 	int max_descendants;
 
 	/*
-	 * Each non-empty css_set associated with this cgroup contributes
-	 * one to nr_populated_csets.  The counter is zero iff this cgroup
-	 * doesn't have any tasks.
-	 *
-	 * All children which have non-zero nr_populated_csets and/or
-	 * nr_populated_children of their own contribute one to either
-	 * nr_populated_domain_children or nr_populated_threaded_children
-	 * depending on their type.  Each counter is zero iff all cgroups
-	 * of the type in the subtree proper don't have any tasks.
+	 * Domain/threaded split of self.nr_populated_children: each counts
+	 * immediate-child cgroups whose subtree is populated and sums to
+	 * self.nr_populated_children. Kept as separate fields to allow readers
+	 * like cgroup_can_be_thread_root() unlocked access. Protected by
+	 * css_set_lock; updated by css_update_populated().
 	 */
-	int nr_populated_csets;
 	int nr_populated_domain_children;
 	int nr_populated_threaded_children;
 
@@ -611,9 +618,6 @@ struct cgroup {
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
 
-	/* defers killing csses after removal until cgroup is depopulated */
-	struct work_struct finish_destroy_work;
-
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c5648fcf74e2..f2aa46a4f871 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -640,11 +640,32 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 	return cgroup_is_descendant(cset->dfl_cgrp, ancestor);
 }
 
-/* no synchronization, the result can only be used as a hint */
+/*
+ * Populated counters: writes happen under css_set_lock. The accessors below
+ * may read unlocked. What an unpopulated result means depends on context:
+ *
+ * - No lock held. Just a snapshot. May race with concurrent updates and is
+ *   useful only as a hint.
+ *
+ * - cgroup_mutex held. Migration into the cgroup is blocked, so an observed
+ *   !populated stays !populated until cgroup_mutex is dropped.
+ *
+ * - CSS_DYING set. The css can no longer be repopulated, so !populated is
+ *   sticky once observed.
+ */
+static inline bool cgroup_has_tasks(struct cgroup *cgrp)
+{
+	return READ_ONCE(cgrp->self.nr_populated_csets);
+}
+
+static inline bool css_is_populated(struct cgroup_subsys_state *css)
+{
+	return READ_ONCE(css->nr_populated_csets) || READ_ONCE(css->nr_populated_children);
+}
+
 static inline bool cgroup_is_populated(struct cgroup *cgrp)
 {
-	return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children +
-		cgrp->nr_populated_threaded_children;
+	return css_is_populated(&cgrp->self);
 }
 
 /* returns ino associated with a cgroup */
diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h
index 80edae03c313..404e746552ca 100644
--- a/include/linux/cgroup_rdma.h
+++ b/include/linux/cgroup_rdma.h
@@ -24,6 +24,10 @@ struct rdma_cgroup {
 	 * that belongs to this cgroup.
 	 */
 	struct list_head		rpools;
+
+	/* Handles for rdma.events[.local] */
+	struct cgroup_file		events_file;
+	struct cgroup_file		events_local_file;
 };
 
 struct rdmacg_device {
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 6152add0c5eb..38f8d9df8fbc 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -197,6 +197,14 @@ static u32 cgrp_dfl_implicit_ss_mask;
 /* some controllers can be threaded on the default hierarchy */
 static u32 cgrp_dfl_threaded_ss_mask;
 
+/*
+ * Set across rebind_subsystems() to the controllers leaving a hierarchy.
+ * Guarded by cgroup_mutex. Makes find_existing_css_set() resolve them to the
+ * root css so the affected tasks are migrated there before
+ * cgroup_apply_control_disable() kills the per-cgroup csses.
+ */
+static u32 cgroup_rebind_ss_mask;
+
 /* The list of hierarchy roots */
 LIST_HEAD(cgroup_roots);
 static int cgroup_root_count;
@@ -264,7 +272,6 @@ static void cgroup_finalize_control(struct cgroup *cgrp, int ret);
 static void css_task_iter_skip(struct css_task_iter *it,
 			       struct task_struct *task);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
-static void cgroup_finish_destroy(struct cgroup *cgrp);
 static void kill_css_sync(struct cgroup_subsys_state *css);
 static void kill_css_finish(struct cgroup_subsys_state *css);
 static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
@@ -376,11 +383,6 @@ static void cgroup_idr_remove(struct idr *idr, int id)
 	spin_unlock_bh(&cgroup_idr_lock);
 }
 
-static bool cgroup_has_tasks(struct cgroup *cgrp)
-{
-	return cgrp->nr_populated_csets;
-}
-
 static bool cgroup_is_threaded(struct cgroup *cgrp)
 {
 	return cgrp->dom_cgrp != cgrp;
@@ -409,7 +411,7 @@ static bool cgroup_can_be_thread_root(struct cgroup *cgrp)
 		return false;
 
 	/* can only have either domain or threaded children */
-	if (cgrp->nr_populated_domain_children)
+	if (READ_ONCE(cgrp->nr_populated_domain_children))
 		return false;
 
 	/* and no domain controllers can be enabled */
@@ -761,62 +763,76 @@ static bool css_set_populated(struct css_set *cset)
 }
 
 /**
- * cgroup_update_populated - update the populated count of a cgroup
- * @cgrp: the target cgroup
- * @populated: inc or dec populated count
- *
- * One of the css_sets associated with @cgrp is either getting its first
- * task or losing the last.  Update @cgrp->nr_populated_* accordingly.  The
- * count is propagated towards root so that a given cgroup's
- * nr_populated_children is zero iff none of its descendants contain any
- * tasks.
- *
- * @cgrp's interface file "cgroup.populated" is zero if both
- * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and
- * 1 otherwise.  When the sum changes from or to zero, userland is notified
- * that the content of the interface file has changed.  This can be used to
- * detect when @cgrp and its descendants become populated or empty.
+ * css_update_populated - update the populated state of a css and ancestors
+ * @css: leaf css whose own populated count is changing
+ * @populated: inc or dec
+ *
+ * One of the css_sets pinned by @css is getting its first task or losing the
+ * last. Propagate the transition up the parent chain so that a css's
+ * nr_populated_children is zero iff none of its descendants contain any tasks.
+ *
+ * For a cgroup->self walk, also runs cgroup-side bookkeeping at each level:
+ * domain/threaded child split, deferred-destroy trigger, and notification via
+ * "cgroup.populated" (zero iff cgrp->self has neither populated csets nor
+ * populated children; userland is notified on transitions).
  */
-static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
+static void css_update_populated(struct cgroup_subsys_state *css, bool populated)
 {
-	struct cgroup *child = NULL;
+	struct cgroup_subsys_state *child = NULL;
 	int adj = populated ? 1 : -1;
 
 	lockdep_assert_held(&css_set_lock);
 
 	do {
-		bool was_populated = cgroup_is_populated(cgrp);
+		/* non-NULL only on the cgroup->self walk */
+		struct cgroup *cgrp = css_is_self(css) ? css->cgroup : NULL;
+		bool was_populated = css_is_populated(css);
 
 		if (!child) {
-			cgrp->nr_populated_csets += adj;
+			WRITE_ONCE(css->nr_populated_csets,
+				   css->nr_populated_csets + adj);
 		} else {
-			if (cgroup_is_threaded(child))
-				cgrp->nr_populated_threaded_children += adj;
-			else
-				cgrp->nr_populated_domain_children += adj;
+			WRITE_ONCE(css->nr_populated_children,
+				   css->nr_populated_children + adj);
+			if (cgrp) {
+				if (cgroup_is_threaded(child->cgroup))
+					WRITE_ONCE(cgrp->nr_populated_threaded_children,
+						   cgrp->nr_populated_threaded_children + adj);
+				else
+					WRITE_ONCE(cgrp->nr_populated_domain_children,
+						   cgrp->nr_populated_domain_children + adj);
+			}
 		}
 
-		if (was_populated == cgroup_is_populated(cgrp))
+		if (was_populated == css_is_populated(css))
 			break;
 
 		/*
-		 * Subtree just emptied below an offlined cgrp. Fire deferred
-		 * destroy. The transition is one-shot.
+		 * Pair with smp_mb() in kill_css_sync(). Either we observe
+		 * CSS_DYING and queue, or the caller observes our decrement
+		 * and fires synchronously.
+		 */
+		smp_mb();
+
+		/*
+		 * Subtree just emptied below a dying css. Fire deferred kill.
+		 * The transition is one-shot for a dying css.
 		 */
-		if (was_populated && !css_is_online(&cgrp->self)) {
-			cgroup_get(cgrp);
-			WARN_ON_ONCE(!queue_work(cgroup_offline_wq,
-						 &cgrp->finish_destroy_work));
+		if (was_populated && css_is_dying(css)) {
+			css_get(css);
+			WARN_ON_ONCE(!queue_work(cgroup_offline_wq, &css->kill_finish_work));
 		}
 
-		cgroup1_check_for_release(cgrp);
-		TRACE_CGROUP_PATH(notify_populated, cgrp,
-				  cgroup_is_populated(cgrp));
-		cgroup_file_notify(&cgrp->events_file);
+		if (cgrp) {
+			cgroup1_check_for_release(cgrp);
+			TRACE_CGROUP_PATH(notify_populated, cgrp,
+					  cgroup_is_populated(cgrp));
+			cgroup_file_notify(&cgrp->events_file);
+		}
 
-		child = cgrp;
-		cgrp = cgroup_parent(cgrp);
-	} while (cgrp);
+		child = css;
+		css = css->parent;
+	} while (css);
 }
 
 /**
@@ -824,17 +840,27 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated)
  * @cset: target css_set
  * @populated: whether @cset is populated or depopulated
  *
- * @cset is either getting the first task or losing the last.  Update the
- * populated counters of all associated cgroups accordingly.
+ * @cset is either getting the first task or losing the last. Update the
+ * populated counters along each linked cgroup's self chain and each
+ * subsystem css that @cset pins.
  */
 static void css_set_update_populated(struct css_set *cset, bool populated)
 {
 	struct cgrp_cset_link *link;
+	struct cgroup_subsys *ss;
+	int ssid;
 
 	lockdep_assert_held(&css_set_lock);
 
 	list_for_each_entry(link, &cset->cgrp_links, cgrp_link)
-		cgroup_update_populated(link->cgrp, populated);
+		css_update_populated(&link->cgrp->self, populated);
+
+	for_each_subsys(ss, ssid) {
+		struct cgroup_subsys_state *css = cset->subsys[ssid];
+
+		if (css)
+			css_update_populated(css, populated);
+	}
 }
 
 /*
@@ -1065,7 +1091,15 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 	 * won't change, so no need for locking.
 	 */
 	for_each_subsys(ss, i) {
-		if (root->subsys_mask & (1UL << i)) {
+		if (unlikely(cgroup_rebind_ss_mask & (1UL << i))) {
+			/*
+			 * @ss is leaving this hierarchy and its per-cgroup
+			 * csses are about to be killed. Resolve to the
+			 * surviving root css so the tasks are migrated there.
+			 */
+			template[i] = cgroup_css(&root->cgrp, ss);
+			WARN_ON_ONCE(!template[i]);
+		} else if (root->subsys_mask & (1UL << i)) {
 			/*
 			 * @ss is in this hierarchy, so we want the
 			 * effective css from @cgrp.
@@ -1835,11 +1869,17 @@ int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask)
 		struct cgroup *scgrp = &cgrp_dfl_root.cgrp;
 
 		/*
-		 * Controllers from default hierarchy that need to be rebound
-		 * are all disabled together in one go.
+		 * Controllers leaving the default hierarchy are disabled
+		 * together. cgroup_rebind_ss_mask makes cgroup_apply_control()
+		 * migrate their tasks to the root css, so the per-cgroup csses
+		 * are unpopulated when cgroup_finalize_control() kills them.
+		 * Clear it before cgroup_finalize_control(), which does no
+		 * css_set lookup.
 		 */
 		cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask;
+		cgroup_rebind_ss_mask = dfl_disable_ss_mask;
 		WARN_ON(cgroup_apply_control(scgrp));
+		cgroup_rebind_ss_mask = 0;
 		cgroup_finalize_control(scgrp, 0);
 	}
 
@@ -1853,9 +1893,14 @@ int rebind_subsystems(struct cgroup_root *dst_root, u32 ss_mask)
 		WARN_ON(!css || cgroup_css(dcgrp, ss));
 
 		if (src_root != &cgrp_dfl_root) {
-			/* disable from the source */
+			/*
+			 * Disable from the source, migrating its tasks to the
+			 * root css first (see cgroup_rebind_ss_mask).
+			 */
 			src_root->subsys_mask &= ~(1 << ssid);
+			cgroup_rebind_ss_mask = 1 << ssid;
 			WARN_ON(cgroup_apply_control(scgrp));
+			cgroup_rebind_ss_mask = 0;
 			cgroup_finalize_control(scgrp, 0);
 		}
 
@@ -2051,16 +2096,6 @@ static int cgroup_reconfigure(struct fs_context *fc)
 	return 0;
 }
 
-static void cgroup_finish_destroy_work_fn(struct work_struct *work)
-{
-	struct cgroup *cgrp = container_of(work, struct cgroup, finish_destroy_work);
-
-	cgroup_lock();
-	cgroup_finish_destroy(cgrp);
-	cgroup_unlock();
-	cgroup_put(cgrp);
-}
-
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
@@ -2087,7 +2122,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 #endif
 
 	init_waitqueue_head(&cgrp->offline_waitq);
-	INIT_WORK(&cgrp->finish_destroy_work, cgroup_finish_destroy_work_fn);
 	INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
 }
 
@@ -2192,7 +2226,7 @@ int cgroup_setup_root(struct cgroup_root *root, u32 ss_mask)
 	hash_for_each(css_set_table, i, cset, hlist) {
 		link_css_set(&tmp_links, cset, root_cgrp);
 		if (css_set_populated(cset))
-			cgroup_update_populated(root_cgrp, true);
+			css_update_populated(&root_cgrp->self, true);
 	}
 	spin_unlock_irq(&css_set_lock);
 
@@ -3230,7 +3264,7 @@ restart:
 			struct cgroup_subsys_state *css = cgroup_css(dsct, ss);
 			DEFINE_WAIT(wait);
 
-			if (!css || !percpu_ref_is_dying(&css->refcnt))
+			if (!css || !css_is_dying(css))
 				continue;
 
 			cgroup_get_live(dsct);
@@ -3398,7 +3432,8 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp)
 			if (css->parent &&
 			    !(cgroup_ss_mask(dsct) & (1 << ss->id))) {
 				kill_css_sync(css);
-				kill_css_finish(css);
+				if (!css_is_populated(css))
+					kill_css_finish(css);
 			} else if (!css_visible(css)) {
 				css_clear_dir(css);
 				if (ss->css_reset)
@@ -3726,7 +3761,7 @@ static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of,
 	if (!cgrp)
 		return -ENOENT;
 
-	cgrp->max_descendants = descendants;
+	WRITE_ONCE(cgrp->max_descendants, descendants);
 
 	cgroup_kn_unlock(of->kn);
 
@@ -3769,7 +3804,7 @@ static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of,
 	if (!cgrp)
 		return -ENOENT;
 
-	cgrp->max_depth = depth;
+	WRITE_ONCE(cgrp->max_depth, depth);
 
 	cgroup_kn_unlock(of->kn);
 
@@ -5684,6 +5719,22 @@ static void css_release(struct percpu_ref *ref)
 	queue_work(cgroup_release_wq, &css->destroy_work);
 }
 
+/*
+ * Deferred kill_css_finish() fired from css_update_populated() once a dying
+ * css's hierarchical populated state drops to zero. Pinned by css_get() at the
+ * queue site; matched by css_put() here.
+ */
+static void kill_css_finish_work_fn(struct work_struct *work)
+{
+	struct cgroup_subsys_state *css =
+		container_of(work, struct cgroup_subsys_state, kill_finish_work);
+
+	cgroup_lock();
+	kill_css_finish(css);
+	cgroup_unlock();
+	css_put(css);
+}
+
 static void init_and_link_css(struct cgroup_subsys_state *css,
 			      struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
@@ -5697,6 +5748,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
+	INIT_WORK(&css->kill_finish_work, kill_css_finish_work_fn);
 	css->serial_nr = css_serial_nr_next++;
 	atomic_set(&css->online_cnt, 0);
 
@@ -6074,6 +6126,13 @@ static void kill_css_sync(struct cgroup_subsys_state *css)
 	css->flags |= CSS_DYING;
 
 	/*
+	 * Pair with smp_mb() in css_update_populated(). Either our
+	 * caller observes the walker's decrement and fires
+	 * synchronously, or the walker observes CSS_DYING and queues.
+	 */
+	smp_mb();
+
+	/*
 	 * This must happen before css is disassociated with its cgroup.
 	 * See seq_css() for details.
 	 */
@@ -6148,9 +6207,9 @@ static void kill_css_finish(struct cgroup_subsys_state *css)
  * - This function: synchronous user-visible state teardown plus kill_css_sync()
  *   on each subsystem css.
  *
- * - cgroup_finish_destroy(): kicks the percpu_ref kill via kill_css_finish() on
- *   each subsystem css. Fires once @cgrp's subtree is fully drained, either
- *   inline here or from cgroup_update_populated().
+ * - For each subsys css: fire kill_css_finish() synchronously if the subtree is
+ *   already drained, otherwise rely on css_update_populated() to queue
+ *   kill_finish_work when the last populated cset under the css empties.
  *
  * - The percpu_ref kill chain: css_killed_ref_fn -> css_killed_work_fn ->
  *   ->css_offline() -> release/free.
@@ -6228,29 +6287,14 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	/* put the base reference */
 	percpu_ref_kill(&cgrp->self.refcnt);
 
-	if (!cgroup_is_populated(cgrp))
-		cgroup_finish_destroy(cgrp);
+	for_each_css(css, ssid, cgrp) {
+		if (!css_is_populated(css))
+			kill_css_finish(css);
+	}
 
 	return 0;
 };
 
-/**
- * cgroup_finish_destroy - deferred half of @cgrp destruction
- * @cgrp: cgroup whose subtree just became empty
- *
- * See cgroup_destroy_locked() for the rationale.
- */
-static void cgroup_finish_destroy(struct cgroup *cgrp)
-{
-	struct cgroup_subsys_state *css;
-	int ssid;
-
-	lockdep_assert_held(&cgroup_mutex);
-
-	for_each_css(css, ssid, cgrp)
-		kill_css_finish(css);
-}
-
 int cgroup_rmdir(struct kernfs_node *kn)
 {
 	struct cgroup *cgrp;
diff --git a/kernel/cgroup/cpuset-v1.c b/kernel/cgroup/cpuset-v1.c
index 7308e9b02495..3e9968dd91e9 100644
--- a/kernel/cgroup/cpuset-v1.c
+++ b/kernel/cgroup/cpuset-v1.c
@@ -312,7 +312,7 @@ void cpuset1_hotplug_update_tasks(struct cpuset *cs,
 	 * This is full cgroup operation which will also call back into
 	 * cpuset. Execute it asynchronously using workqueue.
 	 */
-	if (is_empty && cs->css.cgroup->nr_populated_csets &&
+	if (is_empty && cgroup_has_tasks(cs->css.cgroup) &&
 	    css_tryget_online(&cs->css)) {
 		struct cpuset_remove_tasks_struct *s;
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c9e14fda3d6f..591e3aa487fc 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -432,7 +432,7 @@ static inline bool partition_is_populated(struct cpuset *cs,
 	 * nr_populated_domain_children may include populated
 	 * csets from descendants that are partitions.
 	 */
-	if (cs->css.cgroup->nr_populated_csets ||
+	if (cgroup_has_tasks(cs->css.cgroup) ||
 	    cs->attach_in_progress)
 		return true;
 
@@ -1004,8 +1004,11 @@ void rebuild_sched_domains_locked(void)
 	* prevent the panic.
 	*/
 	for (i = 0; doms && i < ndoms; i++) {
-		if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask)))
+		if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) {
+			free_sched_domains(doms, ndoms);
+			kfree(attr);
 			return;
+		}
 	}
 
 	/* Have scheduler rebuild the domains */
@@ -4236,6 +4239,9 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
 	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
 		return false;
 
+	if (cpuset_v2())
+		return true;
+
 	/* Not hardwall and node outside mems_allowed: scan up cpusets */
 	spin_lock_irqsave(&callback_lock, flags);
 
diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c
index 4fdab4cf49e0..5e82a03b3270 100644
--- a/kernel/cgroup/rdma.c
+++ b/kernel/cgroup/rdma.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/limits.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/cgroup.h>
@@ -17,6 +18,22 @@
 
 #define RDMACG_MAX_STR "max"
 
+enum rdmacg_limit_tokens {
+	RDMACG_HCA_HANDLE_VAL,
+	RDMACG_HCA_HANDLE_MAX,
+	RDMACG_HCA_OBJECT_VAL,
+	RDMACG_HCA_OBJECT_MAX,
+	NR_RDMACG_LIMIT_TOKENS,
+};
+
+static const match_table_t rdmacg_limit_tokens = {
+	{ RDMACG_HCA_HANDLE_VAL,	"hca_handle=%d"	},
+	{ RDMACG_HCA_HANDLE_MAX,	"hca_handle=max"	},
+	{ RDMACG_HCA_OBJECT_VAL,	"hca_object=%d"	},
+	{ RDMACG_HCA_OBJECT_MAX,	"hca_object=max"	},
+	{ NR_RDMACG_LIMIT_TOKENS,	NULL			},
+};
+
 /*
  * Protects list of resource pools maintained on per cgroup basis
  * and rdma device list.
@@ -27,6 +44,7 @@ static LIST_HEAD(rdmacg_devices);
 enum rdmacg_file_type {
 	RDMACG_RESOURCE_TYPE_MAX,
 	RDMACG_RESOURCE_TYPE_STAT,
+	RDMACG_RESOURCE_TYPE_PEAK,
 };
 
 /*
@@ -43,6 +61,7 @@ static char const *rdmacg_resource_names[] = {
 struct rdmacg_resource {
 	int max;
 	int usage;
+	int peak;
 };
 
 /*
@@ -62,6 +81,12 @@ struct rdmacg_resource_pool {
 	u64			usage_sum;
 	/* total number counts which are set to max */
 	int			num_max_cnt;
+
+	/* per-resource event counters */
+	u64			events_max[RDMACG_RESOURCE_MAX];
+	u64			events_alloc_fail[RDMACG_RESOURCE_MAX];
+	u64			events_local_max[RDMACG_RESOURCE_MAX];
+	u64			events_local_alloc_fail[RDMACG_RESOURCE_MAX];
 };
 
 static struct rdma_cgroup *css_rdmacg(struct cgroup_subsys_state *css)
@@ -109,6 +134,26 @@ static void free_cg_rpool_locked(struct rdmacg_resource_pool *rpool)
 	kfree(rpool);
 }
 
+static bool rpool_has_persistent_state(struct rdmacg_resource_pool *rpool)
+{
+	int i;
+
+	/*
+	 * Keep the rpool alive if any peak value is non-zero,
+	 * so that rdma.peak persists as a historical high-
+	 * watermark even after all resources are freed.
+	 */
+	for (i = 0; i < RDMACG_RESOURCE_MAX; i++) {
+		if (rpool->resources[i].peak ||
+		    rpool->events_max[i] ||
+		    rpool->events_local_max[i] ||
+		    rpool->events_alloc_fail[i] ||
+		    rpool->events_local_alloc_fail[i])
+			return true;
+	}
+	return false;
+}
+
 static struct rdmacg_resource_pool *
 find_cg_rpool_locked(struct rdma_cgroup *cg,
 		     struct rdmacg_device *device)
@@ -187,11 +232,67 @@ uncharge_cg_locked(struct rdma_cgroup *cg,
 	rpool->usage_sum--;
 	if (rpool->usage_sum == 0 &&
 	    rpool->num_max_cnt == RDMACG_RESOURCE_MAX) {
-		/*
-		 * No user of the rpool and all entries are set to max, so
-		 * safe to delete this rpool.
-		 */
-		free_cg_rpool_locked(rpool);
+		if (!rpool_has_persistent_state(rpool)) {
+			/*
+			 * No user of the rpool and all entries are set to max, so
+			 * safe to delete this rpool.
+			 */
+			free_cg_rpool_locked(rpool);
+		}
+	}
+}
+
+/**
+ * rdmacg_event_locked - fire event when resource allocation exceeds limit
+ * @cg: requesting cgroup
+ * @over_cg: cgroup whose limit was exceeded
+ * @device: rdma device
+ * @index: resource type index
+ *
+ * Must be called under rdmacg_mutex. Updates event counters in the
+ * resource pools of @cg and @over_cg, propagates hierarchical max
+ * events from @over_cg (including itself) upward, and notifies
+ * userspace via cgroup_file_notify().
+ */
+static void rdmacg_event_locked(struct rdma_cgroup *cg,
+				struct rdma_cgroup *over_cg,
+				struct rdmacg_device *device,
+				enum rdmacg_resource_type index)
+{
+	struct rdmacg_resource_pool *rpool;
+	struct rdma_cgroup *p;
+
+	lockdep_assert_held(&rdmacg_mutex);
+
+	/* Increment local alloc_fail in requesting cgroup */
+	rpool = find_cg_rpool_locked(cg, device);
+	if (rpool) {
+		rpool->events_local_alloc_fail[index]++;
+		cgroup_file_notify(&cg->events_local_file);
+	}
+
+	/* Increment local max in the over-limit cgroup */
+	rpool = find_cg_rpool_locked(over_cg, device);
+	if (rpool) {
+		rpool->events_local_max[index]++;
+		cgroup_file_notify(&over_cg->events_local_file);
+	}
+
+	/* Propagate hierarchical max events upward */
+	for (p = over_cg; parent_rdmacg(p); p = parent_rdmacg(p)) {
+		rpool = get_cg_rpool_locked(p, device);
+		if (!IS_ERR(rpool)) {
+			rpool->events_max[index]++;
+			cgroup_file_notify(&p->events_file);
+		}
+	}
+	/* Propagate hierarchical alloc_fail from requesting cgroup upward */
+	for (p = cg; parent_rdmacg(p); p = parent_rdmacg(p)) {
+		rpool = get_cg_rpool_locked(p, device);
+		if (!IS_ERR(rpool)) {
+			rpool->events_alloc_fail[index]++;
+			cgroup_file_notify(&p->events_file);
+		}
 	}
 }
 
@@ -293,12 +394,20 @@ int rdmacg_try_charge(struct rdma_cgroup **rdmacg,
 			}
 		}
 	}
+	/* Update peak only after all charges succeed */
+	for (p = cg; p; p = parent_rdmacg(p)) {
+		rpool = find_cg_rpool_locked(p, device);
+		if (rpool && rpool->resources[index].usage > rpool->resources[index].peak)
+			rpool->resources[index].peak = rpool->resources[index].usage;
+	}
 	mutex_unlock(&rdmacg_mutex);
 
 	*rdmacg = cg;
 	return 0;
 
 err:
+	if (ret == -EAGAIN)
+