Merge tag 'cgroup-for-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:

 - The locking around cpuset hotplug processing has always been a bit of
   mess which was worked around by making hotplug processing
   asynchronous. The asynchronity isn't great and led to other issues.

   We tried to make the behavior synchronous a while ago but that led to
   lockdep splats. Waiman took another stab at cleaning up and making it
   synchronous. The patch has been in -next for well over a month and
   there haven't been any complaints, so fingers crossed.

 - Tracepoints added to help understanding rstat lock contentions.

 - A bunch of minor changes - doc updates, code cleanups and selftests.

* tag 'cgroup-for-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (24 commits)
  cgroup/rstat: add cgroup_rstat_cpu_lock helpers and tracepoints
  selftests/cgroup: Drop define _GNU_SOURCE
  docs: cgroup-v1: Update page cache removal functions
  selftests/cgroup: fix uninitialized variables in test_zswap.c
  selftests/cgroup: cpu_hogger init: use {} instead of {NULL}
  selftests/cgroup: fix clang warnings: uninitialized fd variable
  selftests/cgroup: fix clang build failures for abs() calls
  cgroup/cpuset: Remove outdated comment in sched_partition_write()
  cgroup/cpuset: Fix incorrect top_cpuset flags
  cgroup/cpuset: Avoid clearing CS_SCHED_LOAD_BALANCE twice
  cgroup/cpuset: Statically initialize more members of top_cpuset
  cgroup: Avoid unnecessary looping in cgroup_no_v1()
  cgroup, legacy_freezer: update comment for freezer_css_offline()
  docs, cgroup: add entries for pids to cgroup-v2.rst
  cgroup: don't call cgroup1_pidlist_destroy_all() for v2
  cgroup_freezer: update comment for freezer_css_online()
  cgroup/rstat: desc member cgrp in cgroup_rstat_flush_release
  cgroup/rstat: add cgroup_rstat_lock helpers and tracepoints
  cgroup/pids: Remove superfluous zeroing
  docs: cgroup-v1: Fix description for css_online
  ...

Author: torvalds

Documentation/admin-guide/cgroup-v1/cgroups.rst

@@ -570,7 +570,7 @@ visible to cgroup_for_each_child/descendant_*() iterators. The
 subsystem may choose to fail creation by returning -errno. This
 callback can be used to implement reliable state sharing and
 propagation along the hierarchy. See the comment on
-cgroup_for_each_descendant_pre() for details.
+cgroup_for_each_live_descendant_pre() for details.
 
 ``void css_offline(struct cgroup *cgrp);``
 (cgroup_mutex held by caller)

Documentation/admin-guide/cgroup-v1/memcg_test.rst

@@ -102,7 +102,7 @@ Under below explanation, we assume CONFIG_SWAP=y.
 	The logic is very clear. (About migration, see below)
 
 	Note:
-	  __remove_from_page_cache() is called by remove_from_page_cache()
+	  __filemap_remove_folio() is called by filemap_remove_folio()
 	  and __remove_mapping().
 
 6. Shmem(tmpfs) Page Cache

Documentation/admin-guide/cgroup-v2.rst

@@ -1058,12 +1058,15 @@ cpufreq governor about the minimum desired frequency which should always be
 provided by a CPU, as well as the maximum desired frequency, which should not
 be exceeded by a CPU.
 
-WARNING: cgroup2 doesn't yet support control of realtime processes and
-the cpu controller can only be enabled when all RT processes are in
-the root cgroup.  Be aware that system management software may already
-have placed RT processes into nonroot cgroups during the system boot
-process, and these processes may need to be moved to the root cgroup
-before the cpu controller can be enabled.
+WARNING: cgroup2 doesn't yet support control of realtime processes. For
+a kernel built with the CONFIG_RT_GROUP_SCHED option enabled for group
+scheduling of realtime processes, the cpu controller can only be enabled
+when all RT processes are in the root cgroup.  This limitation does
+not apply if CONFIG_RT_GROUP_SCHED is disabled.  Be aware that system
+management software may already have placed RT processes into nonroot
+cgroups during the system boot process, and these processes may need
+to be moved to the root cgroup before the cpu controller can be enabled
+with a CONFIG_RT_GROUP_SCHED enabled kernel.
 
 
 CPU Interface Files
@@ -2190,11 +2193,25 @@ PID Interface Files
 	Hard limit of number of processes.
 
   pids.current
-	A read-only single value file which exists on all cgroups.
+	A read-only single value file which exists on non-root cgroups.
 
 	The number of processes currently in the cgroup and its
 	descendants.
 
+  pids.peak
+	A read-only single value file which exists on non-root cgroups.
+
+	The maximum value that the number of processes in the cgroup and its
+	descendants has ever reached.
+
+  pids.events
+	A read-only flat-keyed file which exists on non-root cgroups. The
+	following entries are defined. Unless specified otherwise, a value
+	change in this file generates a file modified event.
+
+	  max
+		Number of times fork failed because limit was hit.
+
 Organisational operations are not blocked by cgroup policies, so it is
 possible to have pids.current > pids.max.  This can be done by either
 setting the limit to be smaller than pids.current, or attaching enough

include/linux/cgroup.h

@@ -690,7 +690,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
 void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
 void cgroup_rstat_flush(struct cgroup *cgrp);
 void cgroup_rstat_flush_hold(struct cgroup *cgrp);
-void cgroup_rstat_flush_release(void);
+void cgroup_rstat_flush_release(struct cgroup *cgrp);
 
 /*
  * Basic resource stats.

include/linux/cpuset.h

@@ -70,7 +70,6 @@ extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
-extern void cpuset_wait_for_hotplug(void);
 extern void inc_dl_tasks_cs(struct task_struct *task);
 extern void dec_dl_tasks_cs(struct task_struct *task);
 extern void cpuset_lock(void);
@@ -185,8 +184,6 @@ static inline void cpuset_update_active_cpus(void)
 	partition_sched_domains(1, NULL, NULL);
 }
 
-static inline void cpuset_wait_for_hotplug(void) { }
-
 static inline void inc_dl_tasks_cs(struct task_struct *task) { }
 static inline void dec_dl_tasks_cs(struct task_struct *task) { }
 static inline void cpuset_lock(void) { }

include/trace/events/cgroup.h

@@ -204,6 +204,98 @@ DEFINE_EVENT(cgroup_event, cgroup_notify_frozen,
 	TP_ARGS(cgrp, path, val)
 );
 
+DECLARE_EVENT_CLASS(cgroup_rstat,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended),
+
+	TP_STRUCT__entry(
+		__field(	int,		root			)
+		__field(	int,		level			)
+		__field(	u64,		id			)
+		__field(	int,		cpu			)
+		__field(	bool,		contended		)
+	),
+
+	TP_fast_assign(
+		__entry->root = cgrp->root->hierarchy_id;
+		__entry->id = cgroup_id(cgrp);
+		__entry->level = cgrp->level;
+		__entry->cpu = cpu;
+		__entry->contended = contended;
+	),
+
+	TP_printk("root=%d id=%llu level=%d cpu=%d lock contended:%d",
+		  __entry->root, __entry->id, __entry->level,
+		  __entry->cpu, __entry->contended)
+);
+
+/* Related to global: cgroup_rstat_lock */
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_lock_contended,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_locked,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+/* Related to per CPU: cgroup_rstat_cpu_lock */
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
+DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath,
+
+	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
+
+	TP_ARGS(cgrp, cpu, contended)
+);
+
 #endif /* _TRACE_CGROUP_H */
 
 /* This part must be outside protection */

kernel/cgroup/cgroup-v1.c

@@ -1335,6 +1335,7 @@ static int __init cgroup_no_v1(char *str)
 				continue;
 
 			cgroup_no_v1_mask |= 1 << i;
+			break;
 		}
 	}
 	return 1;

kernel/cgroup/cgroup.c

@@ -5368,7 +5368,8 @@ static void css_free_rwork_fn(struct work_struct *work)
 	} else {
 		/* cgroup free path */
 		atomic_dec(&cgrp->root->nr_cgrps);
-		cgroup1_pidlist_destroy_all(cgrp);
+		if (!cgroup_on_dfl(cgrp))
+			cgroup1_pidlist_destroy_all(cgrp);
 		cancel_work_sync(&cgrp->release_agent_work);
 		bpf_cgrp_storage_free(cgrp);