Merge tag 'cgroup-for-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup updates from Tejun Heo:
 "Several core optimizations:

   - threadgroup_rwsem write locking is skipped when configuring
     controllers in empty subtrees.

     Combined with CLONE_INTO_CGROUP, this allows the common static
     usage pattern to not grab threadgroup_rwsem at all (glibc still
     doesn't seem ready for CLONE_INTO_CGROUP unfortunately).

   - threadgroup_rwsem used to be put into non-percpu mode by default
     due to latency concerns in specific use cases. There's no reason
     for everyone else to pay for it. Make the behavior optional.

   - psi no longer allocates memory when disabled.

  ... along with some code cleanups"

* tag 'cgroup-for-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup: Skip subtree root in cgroup_update_dfl_csses()
  cgroup: remove "no" prefixed mount options
  cgroup: Make !percpu threadgroup_rwsem operations optional
  cgroup: Add "no" prefixed mount options
  cgroup: Elide write-locking threadgroup_rwsem when updating csses on an empty subtree
  cgroup.c: remove redundant check for mixable cgroup in cgroup_migrate_vet_dst
  cgroup.c: add helper __cset_cgroup_from_root to cleanup duplicated codes
  psi: dont alloc memory for psi by default

2 files changed, 18 insertions, 5 deletions

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 187b54a9567e..4bcf56b3491c 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -89,19 +89,32 @@ enum {
 	CGRP_ROOT_NS_DELEGATE	= (1 << 3),
 
 	/*
+	 * Reduce latencies on dynamic cgroup modifications such as task
+	 * migrations and controller on/offs by disabling percpu operation on
+	 * cgroup_threadgroup_rwsem. This makes hot path operations such as
+	 * forks and exits into the slow path and more expensive.
+	 *
+	 * The static usage pattern of creating a cgroup, enabling controllers,
+	 * and then seeding it with CLONE_INTO_CGROUP doesn't require write
+	 * locking cgroup_threadgroup_rwsem and thus doesn't benefit from
+	 * favordynmod.
+	 */
+	CGRP_ROOT_FAVOR_DYNMODS = (1 << 4),
+
+	/*
 	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
 	 */
-	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
+	CGRP_ROOT_CPUSET_V2_MODE = (1 << 16),
 
 	/*
 	 * Enable legacy local memory.events.
 	 */
-	CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 5),
+	CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 17),
 
 	/*
 	 * Enable recursive subtree protection
 	 */
-	CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 6),
+	CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18),
 };
 
 /* cftype->flags */
@@ -480,7 +493,7 @@ struct cgroup {
 	struct work_struct release_agent_work;
 
 	/* used to track pressure stalls */
-	struct psi_group psi;
+	struct psi_group *psi;
 
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0d1ada8968d7..ed53bfe7c46c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -674,7 +674,7 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 
 static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
 {
-	return &cgrp->psi;
+	return cgrp->psi;
 }
 
 bool cgroup_psi_enabled(void);