[PATCH V9 1/2] cgroup/rstat: Avoid flushing if there is an ongoing overlapping flush

[Jesper Dangaard Brouer]

This patch reintroduces and generalizes the "stats_flush_ongoing" concept
to avoid redundant flushes if there is an ongoing flush, addressing lock
contention issues on the global cgroup rstat lock.

At Cloudflare, we observed significant performance degradation due to
lock contention on the rstat lock, primarily caused by kswapd. The
specific mem_cgroup_flush_stats() call inlined in shrink_node, which
takes the rstat lock, is particularly problematic.

On our 12 NUMA node machines, each with a kswapd kthread per NUMA node, we
noted severe lock contention on the rstat lock, causing 12 CPUs to waste
cycles spinning every time kswapd runs. Fleet-wide stats (/proc/N/schedstat)
for kthreads revealed that we are burning an average of 20,000 CPU cores
fleet-wide on kswapd, primarily due to spinning on the rstat lock.

Here's a brief overview of the issue:
- __alloc_pages_slowpath calls wake_all_kswapds, causing all kswapdN threads
  to wake up simultaneously.
- The kswapd thread invokes shrink_node (via balance_pgdat), triggering the
  cgroup rstat flush operation as part of its work.
- balance_pgdat() has a NULL value in target_mem_cgroup, causing
  mem_cgroup_flush_stats() to flush with root_mem_cgroup.

The kernel previously addressed this with a "stats_flush_ongoing" concept,
which was removed in commit 7d7ef0a4686a ("mm: memcg: restore subtree stats
flushing"). This patch reintroduces and generalizes the concept to apply to
all users of cgroup rstat, not just memcg.

If there is an ongoing rstat flush and the current cgroup is a descendant, a
new flush is unnecessary. To ensure callers still receive updated stats,
they wait for the ongoing flush to complete before returning, but with a
timeout, as stats may already be inaccurate due to continuous updates.

Lock yielding causes complications for ongoing flushers. Therefore, we limit
which cgroup can become ongoing flusher to top-level, as lock yielding
allows others to obtain the lock without being the ongoing flusher, leading
to a situation where a cgroup that isn't a descendant obtains the lock via
yielding. Thus, we prefer an ongoing flusher with many descendants. If and
when the lock yielding is removed, such as when changing this to a mutex,
we can simplify this code.

This change significantly reduces lock contention, especially in
environments with multiple NUMA nodes, thereby improving overall system
performance.

Fixes: 7d7ef0a4686a ("mm: memcg: restore subtree stats flushing").
Signed-off-by: Jesper Dangaard Brouer <hawk@xxxxxxxxxx>
---
V9:
 - Fix logic for 'already_contended'
 - Didn't address the refcnt suggestion, need more input from experts
 - I'll deploy this ASAP to my production experiment hosts and report back

V8: https://lore.kernel.org/all/172139415725.3084888.13770938453137383953.stgit@firesoul
V7: https://lore.kernel.org/all/172070450139.2992819.13210624094367257881.stgit@firesoul
V6: https://lore.kernel.org/all/172052399087.2357901.4955042377343593447.stgit@firesoul/
V5: https://lore.kernel.org/all/171956951930.1897969.8709279863947931285.stgit@firesoul/
V4: https://lore.kernel.org/all/171952312320.1810550.13209360603489797077.stgit@firesoul/
V3: https://lore.kernel.org/all/171943668946.1638606.1320095353103578332.stgit@firesoul/
V2: https://lore.kernel.org/all/171923011608.1500238.3591002573732683639.stgit@firesoul/
V1: https://lore.kernel.org/all/171898037079.1222367.13467317484793748519.stgit@firesoul/
RFC: https://lore.kernel.org/all/171895533185.1084853.3033751561302228252.stgit@firesoul/


 include/linux/cgroup-defs.h |    2 +
 kernel/cgroup/rstat.c       |  113 ++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 103 insertions(+), 12 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index b36690ca0d3f..a33b37514c29 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -548,6 +548,8 @@ struct cgroup {
 #ifdef CONFIG_BPF_SYSCALL
 	struct bpf_local_storage __rcu  *bpf_cgrp_storage;
 #endif
+	/* completion queue for cgrp_rstat_ongoing_flusher */
+	struct completion flush_done;
 
 	/* All ancestors including self */
 	struct cgroup *ancestors[];
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index fb8b49437573..463f9807ec7e 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -2,6 +2,7 @@
 #include "cgroup-internal.h"
 
 #include <linux/sched/cputime.h>
+#include <linux/completion.h>
 
 #include <linux/bpf.h>
 #include <linux/btf.h>
@@ -11,6 +12,7 @@
 
 static DEFINE_SPINLOCK(cgroup_rstat_lock);
 static DEFINE_PER_CPU(raw_spinlock_t, cgroup_rstat_cpu_lock);
+static struct cgroup *cgrp_rstat_ongoing_flusher = NULL;
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
 
@@ -279,17 +281,32 @@ __bpf_hook_end();
  * value -1 is used when obtaining the main lock else this is the CPU
  * number processed last.
  */
-static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop)
+static inline bool __cgroup_rstat_trylock(struct cgroup *cgrp, int cpu_in_loop)
+{
+	bool locked;
+
+	locked = spin_trylock_irq(&cgroup_rstat_lock);
+	if (!locked)
+		trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, true);
+	else
+		trace_cgroup_rstat_locked(cgrp, cpu_in_loop, false);
+
+	return locked;
+}
+
+static inline void __cgroup_rstat_lock(struct cgroup *cgrp, int cpu_in_loop,
+				       bool already_contended)
 	__acquires(&cgroup_rstat_lock)
 {
-	bool contended;
+	bool locked = false;
 
-	contended = !spin_trylock_irq(&cgroup_rstat_lock);
-	if (contended) {
-		trace_cgroup_rstat_lock_contended(cgrp, cpu_in_loop, contended);
+	if (!already_contended) /* Skip trylock if already contended */
+		locked = __cgroup_rstat_trylock(cgrp, cpu_in_loop);
+
+	if (!locked) {
 		spin_lock_irq(&cgroup_rstat_lock);
+		trace_cgroup_rstat_locked(cgrp, cpu_in_loop, true);
 	}
-	trace_cgroup_rstat_locked(cgrp, cpu_in_loop, contended);
 }
 
 static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
@@ -299,6 +316,71 @@ static inline void __cgroup_rstat_unlock(struct cgroup *cgrp, int cpu_in_loop)
 	spin_unlock_irq(&cgroup_rstat_lock);
 }
 
+#define MAX_WAIT	msecs_to_jiffies(100)
+/**
+ * cgroup_rstat_trylock_flusher - Trylock that checks for on ongoing flusher
+ * @cgrp: target cgroup
+ *
+ * Function return value follow trylock semantics. Returning true when lock is
+ * obtained. Returning false when not locked and it detected flushing can be
+ * skipped as another ongoing flusher took care of the flush.
+ */
+static bool cgroup_rstat_trylock_flusher(struct cgroup *cgrp)
+{
+	struct cgroup *ongoing;
+	bool locked;
+
+	/*
+	 * Check if ongoing flusher is already taking care of this, if
+	 * we are a descendant skip work, but wait for ongoing flusher
+	 * to complete work.
+	 */
+retry:
+	ongoing = READ_ONCE(cgrp_rstat_ongoing_flusher);
+	if (ongoing && cgroup_is_descendant(cgrp, ongoing)) {
+		wait_for_completion_interruptible_timeout(
+			&ongoing->flush_done, MAX_WAIT);
+		/* TODO: Add tracepoint here */
+		return false;
+	}
+
+	locked = __cgroup_rstat_trylock(cgrp, -1);
+	if (!locked) {
+		/* Contended: Handle losing race for ongoing flusher */
+		if (!ongoing && READ_ONCE(cgrp_rstat_ongoing_flusher))
+			goto retry;
+
+		__cgroup_rstat_lock(cgrp, -1, true);
+	}
+	/*
+	 * Obtained lock, record this cgrp as the ongoing flusher.
+	 * Due to lock yielding, we might obtain lock while another
+	 * ongoing flusher (that isn't a parent) owns ongoing_flusher.
+	 */
+	if (!READ_ONCE(cgrp_rstat_ongoing_flusher)) {
+		/*
+		 * Limit to top-level as lock yielding allows others to obtain
+		 * lock without being ongoing_flusher. Leading to cgroup that
+		 * isn't descendant to obtain lock via yielding. So, prefer
+		 * ongoing_flusher with many descendants.
+		 */
+		if (cgrp->level < 2) {
+			reinit_completion(&cgrp->flush_done);
+			WRITE_ONCE(cgrp_rstat_ongoing_flusher, cgrp);
+		}
+	}
+	return true;
+}
+
+static void cgroup_rstat_unlock_flusher(struct cgroup *cgrp)
+{
+	if (cgrp == READ_ONCE(cgrp_rstat_ongoing_flusher)) {
+		WRITE_ONCE(cgrp_rstat_ongoing_flusher, NULL);
+		complete_all(&cgrp->flush_done);
+	}
+	__cgroup_rstat_unlock(cgrp, -1);
+}
+
 /* see cgroup_rstat_flush() */
 static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
@@ -328,7 +410,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 			__cgroup_rstat_unlock(cgrp, cpu);
 			if (!cond_resched())
 				cpu_relax();
-			__cgroup_rstat_lock(cgrp, cpu);
+			__cgroup_rstat_lock(cgrp, cpu, false);
 		}
 	}
 }
@@ -350,9 +432,11 @@ __bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp)
 {
 	might_sleep();
 
-	__cgroup_rstat_lock(cgrp, -1);
+	if (!cgroup_rstat_trylock_flusher(cgrp))
+		return;
+
 	cgroup_rstat_flush_locked(cgrp);
-	__cgroup_rstat_unlock(cgrp, -1);
+	cgroup_rstat_unlock_flusher(cgrp);
 }
 
 /**
@@ -368,8 +452,11 @@ void cgroup_rstat_flush_hold(struct cgroup *cgrp)
 	__acquires(&cgroup_rstat_lock)
 {
 	might_sleep();
-	__cgroup_rstat_lock(cgrp, -1);
-	cgroup_rstat_flush_locked(cgrp);
+
+	if (cgroup_rstat_trylock_flusher(cgrp))
+		cgroup_rstat_flush_locked(cgrp);
+	else
+		__cgroup_rstat_lock(cgrp, -1, false);
 }
 
 /**
@@ -379,7 +466,7 @@ void cgroup_rstat_flush_hold(struct cgroup *cgrp)
 void cgroup_rstat_flush_release(struct cgroup *cgrp)
 	__releases(&cgroup_rstat_lock)
 {
-	__cgroup_rstat_unlock(cgrp, -1);
+	cgroup_rstat_unlock_flusher(cgrp);
 }
 
 int cgroup_rstat_init(struct cgroup *cgrp)
@@ -401,6 +488,8 @@ int cgroup_rstat_init(struct cgroup *cgrp)
 		u64_stats_init(&rstatc->bsync);
 	}
 
+	init_completion(&cgrp->flush_done);
+
 	return 0;
 }