[PATCH RFC 2/5] workqueue: add WQ_AFFN_CACHE_SHARD affinity scope

[Breno Leitao <leitao@debian.org>]

On systems where many CPUs share one LLC, unbound workqueues using
WQ_AFFN_CACHE collapse to a single worker pool, causing heavy spinlock
contention on pool->lock. For example, Chuck Lever measured 39% of
cycles lost to native_queued_spin_lock_slowpath on a 12-core shared-L3
NFS-over-RDMA system.

The existing affinity hierarchy (cpu, smt, cache, numa, system) offers
no intermediate option between per-LLC and per-SMT-core granularity.

Add WQ_AFFN_CACHE_SHARD, which subdivides each LLC into groups of at
most wq_cache_shard_size CPUs (default 8, tunable via boot parameter).
CPUs are distributed across shards as evenly as possible -- for example,
72 CPUs with max shard size 8 produces 9 shards of 8 each.

The implementation follows the same comparator pattern as other affinity
scopes: cpu_cache_shard_id() computes a per-CPU shard index on the fly
from the already-initialized WQ_AFFN_CACHE topology, and
cpus_share_cache_shard() is passed to init_pod_type().

Benchmark on NVIDIA Grace (72 CPUs, single LLC, 50k items/thread):

  cpu          3433158 items/sec  p50=16416  p90=17376  p95=17664 ns
  smt          3449709 items/sec  p50=16576  p90=17504  p95=17792 ns
  cache_shard  2939917 items/sec  p50=8192   p90=11488  p95=12512 ns
  cache        602096 items/sec   p50=53056  p90=56320  p95=57248 ns
  numa         599090 items/sec   p50=53152  p90=56448  p95=57376 ns
  system       598865 items/sec   p50=53184  p90=56481  p95=57408 ns

cache_shard delivers ~5x the throughput and ~6.5x lower p50 latency
compared to cache scope on this 72-core single-LLC system.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
---
 include/linux/workqueue.h |  1 +
 kernel/workqueue.c        | 60 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index a4749f56398fd..41c946109c7d0 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -133,6 +133,7 @@ enum wq_affn_scope {
 	WQ_AFFN_CPU,			/* one pod per CPU */
 	WQ_AFFN_SMT,			/* one pod poer SMT */
 	WQ_AFFN_CACHE,			/* one pod per LLC */
+	WQ_AFFN_CACHE_SHARD,		/* synthetic sub-LLC shards */
 	WQ_AFFN_NUMA,			/* one pod per NUMA node */
 	WQ_AFFN_SYSTEM,			/* one pod across the whole system */
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 028afc3d14e59..6be884eb3450d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -409,6 +409,7 @@ static const char * const wq_affn_names[WQ_AFFN_NR_TYPES] = {
 	[WQ_AFFN_CPU]		= "cpu",
 	[WQ_AFFN_SMT]		= "smt",
 	[WQ_AFFN_CACHE]		= "cache",
+	[WQ_AFFN_CACHE_SHARD]	= "cache_shard",
 	[WQ_AFFN_NUMA]		= "numa",
 	[WQ_AFFN_SYSTEM]	= "system",
 };
@@ -431,6 +432,9 @@ module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh
 static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT);
 module_param_named(power_efficient, wq_power_efficient, bool, 0444);
 
+static unsigned int wq_cache_shard_size = 8;
+module_param_named(cache_shard_size, wq_cache_shard_size, uint, 0444);
+
 static bool wq_online;			/* can kworkers be created yet? */
 static bool wq_topo_initialized __read_mostly = false;
 
@@ -8106,6 +8110,56 @@ static bool __init cpus_share_numa(int cpu0, int cpu1)
 	return cpu_to_node(cpu0) == cpu_to_node(cpu1);
 }
 
+/**
+ * cpu_cache_shard_id - compute the shard index for a CPU within its LLC pod
+ * @cpu: the CPU to look up
+ *
+ * Returns a shard index that is unique within the CPU's LLC pod. CPUs in
+ * the same LLC are divided into shards no larger than wq_cache_shard_size,
+ * distributed as evenly as possible. E.g., 20 CPUs with max shard size 8
+ * gives 3 shards of 7+7+6.
+ */
+static int __init cpu_cache_shard_id(int cpu)
+{
+	struct wq_pod_type *cache_pt = &wq_pod_types[WQ_AFFN_CACHE];
+	const struct cpumask *pod_cpus;
+	int nr_cpus, nr_shards, shard_size, remainder, c;
+	int pos = 0;
+
+	/* CPUs in the same LLC as @cpu */
+	pod_cpus = cache_pt->pod_cpus[cache_pt->cpu_pod[cpu]];
+	/* Total number of CPUs sharing this LLC */
+	nr_cpus = cpumask_weight(pod_cpus);
+	/* Number of shards to split this LLC into */
+	nr_shards = DIV_ROUND_UP(nr_cpus, wq_cache_shard_size);
+	/* Minimum number of CPUs per shard */
+	shard_size = nr_cpus / nr_shards;
+	/* First @remainder shards get one extra CPU */
+	remainder = nr_cpus % nr_shards;
+
+	/* Find position of @cpu within its cache pod */
+	for_each_cpu(c, pod_cpus) {
+		if (c == cpu)
+			break;
+		pos++;
+	}
+
+	/*
+	 * Map position to shard index. The first @remainder shards have
+	 * (shard_size + 1) CPUs, the rest have @shard_size CPUs.
+	 */
+	if (pos < remainder * (shard_size + 1))
+		return pos / (shard_size + 1);
+	return remainder + (pos - remainder * (shard_size + 1)) / shard_size;
+}
+
+static bool __init cpus_share_cache_shard(int cpu0, int cpu1)
+{
+	if (!cpus_share_cache(cpu0, cpu1))
+		return false;
+	return cpu_cache_shard_id(cpu0) == cpu_cache_shard_id(cpu1);
+}
+
 /**
  * workqueue_init_topology - initialize CPU pods for unbound workqueues
  *
@@ -8118,9 +8172,15 @@ void __init workqueue_init_topology(void)
 	struct workqueue_struct *wq;
 	int cpu;
 
+	if (!wq_cache_shard_size) {
+		pr_warn("workqueue: cache_shard_size must be > 0, setting to 1\n");
+		wq_cache_shard_size = 1;
+	}
+
 	init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share);
 	init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt);
 	init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache);
+	init_pod_type(&wq_pod_types[WQ_AFFN_CACHE_SHARD], cpus_share_cache_shard);
 	init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa);
 
 	wq_topo_initialized = true;

-- 
2.52.0