workqueue: Merge branch 'for-6.5-fixes' into for-6.6

Unbound workqueue execution locality improvement patchset is about to
applied which will cause merge conflicts with changes in for-6.5-fixes.
Let's avoid future merge conflict by pulling in for-6.5-fixes.

Signed-off-by: Tejun Heo <tj@kernel.org>

1 files changed, 42 insertions, 1 deletions

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a90f1e642548..ae975a7c9f69 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -52,6 +52,7 @@
 #include <linux/sched/debug.h>
 #include <linux/nmi.h>
 #include <linux/kvm_para.h>
+#include <linux/delay.h>
 
 #include "workqueue_internal.h"
 
@@ -338,8 +339,10 @@ static cpumask_var_t *wq_numa_possible_cpumask;
  * Per-cpu work items which run for longer than the following threshold are
  * automatically considered CPU intensive and excluded from concurrency
  * management to prevent them from noticeably delaying other per-cpu work items.
+ * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter.
+ * The actual value is initialized in wq_cpu_intensive_thresh_init().
  */
-static unsigned long wq_cpu_intensive_thresh_us = 10000;
+static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX;
 module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644);
 
 static bool wq_disable_numa;
@@ -6516,6 +6519,42 @@ void __init workqueue_init_early(void)
 	       !system_freezable_power_efficient_wq);
 }
 
+static void __init wq_cpu_intensive_thresh_init(void)
+{
+	unsigned long thresh;
+	unsigned long bogo;
+
+	/* if the user set it to a specific value, keep it */
+	if (wq_cpu_intensive_thresh_us != ULONG_MAX)
+		return;
+
+	/*
+	 * The default of 10ms is derived from the fact that most modern (as of
+	 * 2023) processors can do a lot in 10ms and that it's just below what
+	 * most consider human-perceivable. However, the kernel also runs on a
+	 * lot slower CPUs including microcontrollers where the threshold is way
+	 * too low.
+	 *
+	 * Let's scale up the threshold upto 1 second if BogoMips is below 4000.
+	 * This is by no means accurate but it doesn't have to be. The mechanism
+	 * is still useful even when the threshold is fully scaled up. Also, as
+	 * the reports would usually be applicable to everyone, some machines
+	 * operating on longer thresholds won't significantly diminish their
+	 * usefulness.
+	 */
+	thresh = 10 * USEC_PER_MSEC;
+
+	/* see init/calibrate.c for lpj -> BogoMIPS calculation */
+	bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1);
+	if (bogo < 4000)
+		thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC);
+
+	pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n",
+		 loops_per_jiffy, bogo, thresh);
+
+	wq_cpu_intensive_thresh_us = thresh;
+}
+
 /**
  * workqueue_init - bring workqueue subsystem fully online
  *
@@ -6531,6 +6570,8 @@ void __init workqueue_init(void)
 	struct worker_pool *pool;
 	int cpu, bkt;
 
+	wq_cpu_intensive_thresh_init();
+
 	/*
 	 * It'd be simpler to initialize NUMA in workqueue_init_early() but
 	 * CPU to node mapping may not be available that early on some