cgroup: use subsystem-specific rstat locks to avoid contention

It is possible to eliminate contention between subsystems when
updating/flushing stats by using subsystem-specific locks. Let the existing
rstat locks be dedicated to the cgroup base stats and rename them to
reflect that. Add similar locks to the cgroup_subsys struct for use with
individual subsystems.

Lock initialization is done in the new function ss_rstat_init(ss) which
replaces cgroup_rstat_boot(void). If NULL is passed to this function, the
global base stat locks will be initialized. Otherwise, the subsystem locks
will be initialized.

Change the existing lock helper functions to accept a reference to a css.
Then within these functions, conditionally select the appropriate locks
based on the subsystem affiliation of the given css. Add helper functions
for this selection routine to avoid repeated code.

Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 71 insertions, 32 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index c161d34be634..b14e61c64a34 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -272,7 +272,7 @@ int cgroup_task_count(const struct cgroup *cgrp);
  */
 int css_rstat_init(struct cgroup_subsys_state *css);
 void css_rstat_exit(struct cgroup_subsys_state *css);
-void cgroup_rstat_boot(void);
+int ss_rstat_init(struct cgroup_subsys *ss);
 void cgroup_base_stat_cputime_show(struct seq_file *seq);
 
 /*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 45097dc9e099..44baa0318713 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6088,6 +6088,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early)
 		css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL);
 		BUG_ON(css->id < 0);
 
+		BUG_ON(ss_rstat_init(ss));
 		BUG_ON(css_rstat_init(css));
 	}
 
@@ -6167,7 +6168,7 @@ int __init cgroup_init(void)
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files));
 
-	cgroup_rstat_boot();
+	BUG_ON(ss_rstat_init(NULL));
 
 	get_user_ns(init_cgroup_ns.user_ns);
 
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 6ce134a7294d..0bb609e73bde 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -9,8 +9,8 @@
 
 #include <trace/events/cgroup.h>
 
-static DEFINE_SPINLOCK(cgroup_rstat_lock);
-static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
+static DEFINE_SPINLOCK(rstat_base_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, rstat_base_cpu_lock);
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
 
@@ -26,8 +26,24 @@ static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu(
 	return per_cpu_ptr(cgrp->rstat_base_cpu, cpu);
 }
 
+static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
+{
+	if (ss)
+		return &ss->rstat_ss_lock;
+
+	return &rstat_base_lock;
+}
+
+static raw_spinlock_t *ss_rstat_cpu_lock(struct cgroup_subsys *ss, int cpu)
+{
+	if (ss)
+		return per_cpu_ptr(ss->rstat_ss_cpu_lock, cpu);
+
+	return per_cpu_ptr(&rstat_base_cpu_lock, cpu);
+}
+
 /*
- * Helper functions for rstat per CPU lock (cgroup_rstat_cpu_lock).
+ * Helper functions for rstat per CPU locks.
  *
  * This makes it easier to diagnose locking issues and contention in
  * production environments. The parameter @fast_path determine the
@@ -35,21 +51,23 @@ static struct cgroup_rstat_base_cpu *cgroup_rstat_base_cpu(
  * operations without handling high-frequency fast-path "update" events.
  */
 static __always_inline
-unsigned long _css_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu,
-				     struct cgroup_subsys_state *css, const bool fast_path)
+unsigned long _css_rstat_cpu_lock(struct cgroup_subsys_state *css, int cpu,
+		const bool fast_path)
 {
 	struct cgroup *cgrp = css->cgroup;
+	raw_spinlock_t *cpu_lock;
 	unsigned long flags;
 	bool contended;
 
 	/*
-	 * The _irqsave() is needed because cgroup_rstat_lock is
-	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring
-	 * this lock with the _irq() suffix only disables interrupts on
-	 * a non-PREEMPT_RT kernel. The raw_spinlock_t below disables
-	 * interrupts on both configurations. The _irqsave() ensures
-	 * that interrupts are always disabled and later restored.
+	 * The _irqsave() is needed because the locks used for flushing are
+	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring this lock
+	 * with the _irq() suffix only disables interrupts on a non-PREEMPT_RT
+	 * kernel. The raw_spinlock_t below disables interrupts on both
+	 * configurations. The _irqsave() ensures that interrupts are always
+	 * disabled and later restored.
 	 */
+	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
 	contended = !raw_spin_trylock_irqsave(cpu_lock, flags);
 	if (contended) {
 		if (fast_path)
@@ -69,17 +87,18 @@ unsigned long _css_rstat_cpu_lock(raw_spinlock_t *cpu_lock, int cpu,
 }
 
 static __always_inline
-void _css_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu,
-			      struct cgroup_subsys_state *css, unsigned long flags,
-			      const bool fast_path)
+void _css_rstat_cpu_unlock(struct cgroup_subsys_state *css, int cpu,
+		unsigned long flags, const bool fast_path)
 {
 	struct cgroup *cgrp = css->cgroup;
+	raw_spinlock_t *cpu_lock;
 
 	if (fast_path)
 		trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false);
 	else
 		trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false);
 
+	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
 	raw_spin_unlock_irqrestore(cpu_lock, flags);
 }
 
@@ -94,7 +113,6 @@ void _css_rstat_cpu_unlock(raw_spinlock_t *cpu_lock, int cpu,
  */
 __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 {
-	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
 	unsigned long flags;
 
 	/*
@@ -115,7 +133,7 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 	if (data_race(css_rstat_cpu(css, cpu)->updated_next))
 		return;
 
-	flags = _css_rstat_cpu_lock(cpu_lock, cpu, css, true);
+	flags = _css_rstat_cpu_lock(css, cpu, true);
 
 	/* put @css and all ancestors on the corresponding updated lists */
 	while (true) {
@@ -143,7 +161,7 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 		css = parent;
 	}
 
-	_css_rstat_cpu_unlock(cpu_lock, cpu, css, flags, true);
+	_css_rstat_cpu_unlock(css, cpu, flags, true);
 }
 
 /**
@@ -171,11 +189,11 @@ static struct cgroup_subsys_state *css_rstat_push_children(
 	child->rstat_flush_next = NULL;
 
 	/*
-	 * The cgroup_rstat_lock must be held for the whole duration from
+	 * The subsystem rstat lock must be held for the whole duration from
 	 * here as the rstat_flush_next list is being constructed to when
 	 * it is consumed later in css_rstat_flush().
 	 */
-	lockdep_assert_held(&cgroup_rstat_lock);
+	lockdep_assert_held(ss_rstat_lock(head->ss));
 
 	/*
 	 * Notation: -> updated_next pointer
@@ -245,12 +263,11 @@ next_level:
 static struct cgroup_subsys_state *css_rstat_updated_list(
 		struct cgroup_subsys_state *root, int cpu)
 {
-	raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu);
 	struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu);
 	struct cgroup_subsys_state *head = NULL, *parent, *child;
 	unsigned long flags;
 
-	flags = _css_rstat_cpu_lock(cpu_lock, cpu, root, false);
+	flags = _css_rstat_cpu_lock(root, cpu, false);
 
 	/* Return NULL if this subtree is not on-list */
 	if (!rstatc->updated_next)
@@ -287,7 +304,7 @@ static struct cgroup_subsys_state *css_rstat_updated_list(
 	if (child != root)
 		head = css_rstat_push_children(head, child, cpu);
 unlock_ret:
-	_css_rstat_cpu_unlock(cpu_lock, cpu, root, flags, false);
+	_css_rstat_cpu_unlock(root, cpu, flags, false);
 	return head;
 }
 
@@ -314,7 +331,7 @@ __weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
 __bpf_hook_end();
 
 /*
- * Helper functions for locking cgroup_rstat_lock.
+ * Helper functions for locking.
  *
  * This makes it easier to diagnose locking issues and contention in
  * production environments.  The parameter @cpu_in_loop indicate lock
@@ -324,27 +341,31 @@ __bpf_hook_end();
  */
 static inline void __css_rstat_lock(struct cgroup_subsys_state *css,
 		int cpu_in_loop)
-	__acquires(&cgroup_rstat_lock)
+	__acquires(ss_rstat_lock(css->ss))
 {
 	struct cgroup *cgrp = css->cgroup;
+	spinlock_t *lock;
 	bool contended;
 
-	contended = !spin_trylock_irq(&cgroup_rstat_lock);
+	lock = ss_rstat_lock(css->ss);
+	contended = !spin_trylock_irq(lock);
 	if (contended) {
 		trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended);
-		spin_lock_irq(&cgroup_rstat_lock);
+		spin_lock_irq(lock);
 	}
 	trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended);
 }
 
 static inline void __css_rstat_unlock(struct cgroup_subsys_state *css,
 				      int cpu_in_loop)
-	__releases(&cgroup_rstat_lock)
+	__releases(ss_rstat_lock(css->ss))
 {
 	struct cgroup *cgrp = css->cgroup;
+	spinlock_t *lock;
 
+	lock = ss_rstat_lock(css->ss);
 	trace_cgroup_rstat_unlock(cgrp, cpu_in_loop, false);
-	spin_unlock_irq(&cgroup_rstat_lock);
+	spin_unlock_irq(lock);
 }
 
 /**
@@ -466,12 +487,29 @@ void css_rstat_exit(struct cgroup_subsys_state *css)
 	css->rstat_cpu = NULL;
 }
 
-void __init cgroup_rstat_boot(void)
+/**
+ * ss_rstat_init - subsystem-specific rstat initialization
+ * @ss: target subsystem
+ *
+ * If @ss is NULL, the static locks associated with the base stats
+ * are initialized. If @ss is non-NULL, the subsystem-specific locks
+ * are initialized.
+ */
+int __init ss_rstat_init(struct cgroup_subsys *ss)
 {
 	int cpu;
 
+	if (ss) {
+		ss->rstat_ss_cpu_lock = alloc_percpu(raw_spinlock_t);
+		if (!ss->rstat_ss_cpu_lock)
+			return -ENOMEM;
+	}
+
+	spin_lock_init(ss_rstat_lock(ss));
 	for_each_possible_cpu(cpu)
-		raw_spin_lock_init(per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu));
+		raw_spin_lock_init(ss_rstat_cpu_lock(ss, cpu));
+
+	return 0;
 }
 
 /*