Merge tag 'wq-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue updates from Tejun Heo:

 - Concurrency-managed per-cpu work items that hog CPUs and delay the
   execution of other work items are now automatically detected and
   excluded from concurrency management. Reporting on such work items
   can also be enabled through a config option.

 - Added tools/workqueue/wq_monitor.py which improves visibility into
   workqueue usages and behaviors.

 - Arnd's minimal fix for gcc-13 enum warning on 32bit compiles,
   superseded by commit afa4bb77 in mainline.

* tag 'wq-for-6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: Disable per-cpu CPU hog detection when wq_cpu_intensive_thresh_us is 0
  workqueue: Fix WARN_ON_ONCE() triggers in worker_enter_idle()
  workqueue: fix enum type for gcc-13
  workqueue: Track and monitor per-workqueue CPU time usage
  workqueue: Report work funcs that trigger automatic CPU_INTENSIVE mechanism
  workqueue: Automatically mark CPU-hogging work items CPU_INTENSIVE
  workqueue: Improve locking rule description for worker fields
  workqueue: Move worker_set/clr_flags() upwards
  workqueue: Re-order struct worker fields
  workqueue: Add pwq->stats[] and a monitoring script
  Further upgrade queue_work_on() comment

Documentation/admin-guide/kernel-parameters.txt

@@ -6972,6 +6972,18 @@
 			it can be updated at runtime by writing to the
 			corresponding sysfs file.
 
+	workqueue.cpu_intensive_thresh_us=
+			Per-cpu work items which run for longer than this
+			threshold are automatically considered CPU intensive
+			and excluded from concurrency management to prevent
+			them from noticeably delaying other per-cpu work
+			items. Default is 10000 (10ms).
+
+			If CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel
+			will report the work functions which violate this
+			threshold repeatedly. They are likely good
+			candidates for using WQ_UNBOUND workqueues instead.
+
 	workqueue.disable_numa
 			By default, all work items queued to unbound
 			workqueues are affine to the NUMA nodes they're

Documentation/core-api/workqueue.rst

@@ -348,6 +348,37 @@ Guidelines
   level of locality in wq operations and work item execution.
 
 
+Monitoring
+==========
+
+Use tools/workqueue/wq_monitor.py to monitor workqueue operations: ::
+
+  $ tools/workqueue/wq_monitor.py events
+                              total  infl  CPUtime  CPUhog  CMwake  mayday rescued
+  events                      18545     0      6.1       0       5       -       -
+  events_highpri                  8     0      0.0       0       0       -       -
+  events_long                     3     0      0.0       0       0       -       -
+  events_unbound              38306     0      0.1       -       -       -       -
+  events_freezable                0     0      0.0       0       0       -       -
+  events_power_efficient      29598     0      0.2       0       0       -       -
+  events_freezable_power_        10     0      0.0       0       0       -       -
+  sock_diag_events                0     0      0.0       0       0       -       -
+
+                              total  infl  CPUtime  CPUhog  CMwake  mayday rescued
+  events                      18548     0      6.1       0       5       -       -
+  events_highpri                  8     0      0.0       0       0       -       -
+  events_long                     3     0      0.0       0       0       -       -
+  events_unbound              38322     0      0.1       -       -       -       -
+  events_freezable                0     0      0.0       0       0       -       -
+  events_power_efficient      29603     0      0.2       0       0       -       -
+  events_freezable_power_        10     0      0.0       0       0       -       -
+  sock_diag_events                0     0      0.0       0       0       -       -
+
+  ...
+
+See the command's help message for more info.
+
+
 Debugging
 =========
 
@@ -387,6 +418,7 @@ the stack trace of the offending worker thread. ::
 The work item's function should be trivially visible in the stack
 trace.
 
+
 Non-reentrance Conditions
 =========================
 

kernel/sched/core.c

@@ -5670,6 +5670,9 @@ void scheduler_tick(void)
 
 	perf_event_task_tick();
 
+	if (curr->flags & PF_WQ_WORKER)
+		wq_worker_tick(curr);
+
 #ifdef CONFIG_SMP
 	rq->idle_balance = idle_cpu(cpu);
 	trigger_load_balance(rq);

kernel/workqueue_internal.h

@@ -28,13 +28,18 @@ struct worker {
 		struct hlist_node	hentry;	/* L: while busy */
 	};
 
-	struct work_struct	*current_work;	/* L: work being processed */
-	work_func_t		current_func;	/* L: current_work's fn */
-	struct pool_workqueue	*current_pwq;	/* L: current_work's pwq */
-	unsigned int		current_color;	/* L: current_work's color */
-	struct list_head	scheduled;	/* L: scheduled works */
+	struct work_struct	*current_work;	/* K: work being processed and its */
+	work_func_t		current_func;	/* K: function */
+	struct pool_workqueue	*current_pwq;	/* K: pwq */
+	u64			current_at;	/* K: runtime at start or last wakeup */
+	unsigned int		current_color;	/* K: color */
+
+	int			sleeping;	/* S: is worker sleeping? */
 
-	/* 64 bytes boundary on 64bit, 32 on 32bit */
+	/* used by the scheduler to determine a worker's last known identity */
+	work_func_t		last_func;	/* K: last work's fn */
+
+	struct list_head	scheduled;	/* L: scheduled works */
 
 	struct task_struct	*task;		/* I: worker task */
 	struct worker_pool	*pool;		/* A: the associated pool */
@@ -42,10 +47,9 @@ struct worker {
 	struct list_head	node;		/* A: anchored at pool->workers */
 						/* A: runs through worker->node */
 
-	unsigned long		last_active;	/* L: last active timestamp */
+	unsigned long		last_active;	/* K: last active timestamp */
 	unsigned int		flags;		/* X: flags */
 	int			id;		/* I: worker id */
-	int			sleeping;	/* None */
 
 	/*
 	 * Opaque string set with work_set_desc().  Printed out with task
@@ -55,9 +59,6 @@ struct worker {
 
 	/* used only by rescuers to point to the target workqueue */
 	struct workqueue_struct	*rescue_wq;	/* I: the workqueue to rescue */
-
-	/* used by the scheduler to determine a worker's last known identity */
-	work_func_t		last_func;
 };
 
 /**
@@ -76,6 +77,7 @@ static inline struct worker *current_wq_worker(void)
  */
 void wq_worker_running(struct task_struct *task);
 void wq_worker_sleeping(struct task_struct *task);
+void wq_worker_tick(struct task_struct *task);
 work_func_t wq_worker_last_func(struct task_struct *task);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */

lib/Kconfig.debug

@@ -1134,6 +1134,19 @@ config WQ_WATCHDOG
 	  state.  This can be configured through kernel parameter
 	  "workqueue.watchdog_thresh" and its sysfs counterpart.
 
+config WQ_CPU_INTENSIVE_REPORT
+	bool "Report per-cpu work items which hog CPU for too long"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here to enable reporting of concurrency-managed per-cpu work
+	  items that hog CPUs for longer than
+	  workqueue.cpu_intensive_threshold_us. Workqueue automatically
+	  detects and excludes them from concurrency management to prevent
+	  them from stalling other per-cpu work items. Occassional
+	  triggering may not necessarily indicate a problem. Repeated
+	  triggering likely indicates that the work item should be switched
+	  to use an unbound workqueue.
+
 config TEST_LOCKUP
 	tristate "Test module to generate lockups"
 	depends on m

tools/workqueue/wq_monitor.py

+#!/usr/bin/env drgn
+#
+# Copyright (C) 2023 Tejun Heo <tj@kernel.org>
+# Copyright (C) 2023 Meta Platforms, Inc. and affiliates.
+
+desc = """
+This is a drgn script to monitor workqueues. For more info on drgn, visit
+https://github.com/osandov/drgn.
+
+  total    Total number of work items executed by the workqueue.
+
+  infl     The number of currently in-flight work items.
+
+  CPUtime  Total CPU time consumed by the workqueue in seconds. This is
+           sampled from scheduler ticks and only provides ballpark
+           measurement. "nohz_full=" CPUs are excluded from measurement.
+
+  CPUitsv  The number of times a concurrency-managed work item hogged CPU
+           longer than the threshold (workqueue.cpu_intensive_thresh_us)
+           and got excluded from concurrency management to avoid stalling
+           other work items.
+
+  CMwake   The number of concurrency-management wake-ups while executing a
+           work item of the workqueue.
+
+  mayday   The number of times the rescuer was requested while waiting for
+           new worker creation.
+
+  rescued  The number of work items executed by the rescuer.
+"""
+
+import sys
+import signal
+import os
+import re
+import time
+import json
+
+import drgn
+from drgn.helpers.linux.list import list_for_each_entry,list_empty
+from drgn.helpers.linux.cpumask import for_each_possible_cpu
+
+import argparse
+parser = argparse.ArgumentParser(description=desc,
+                                 formatter_class=argparse.RawTextHelpFormatter)
+parser.add_argument('workqueue', metavar='REGEX', nargs='*',
+                    help='Target workqueue name patterns (all if empty)')
+parser.add_argument('-i', '--interval', metavar='SECS', type=float, default=1,
+                    help='Monitoring interval (0 to print once and exit)')
+parser.add_argument('-j', '--json', action='store_true',
+                    help='Output in json')
+args = parser.parse_args()
+
+def err(s):
+    print(s, file=sys.stderr, flush=True)
+    sys.exit(1)
+
+workqueues              = prog['workqueues']
+
+WQ_UNBOUND              = prog['WQ_UNBOUND']
+WQ_MEM_RECLAIM          = prog['WQ_MEM_RECLAIM']
+
+PWQ_STAT_STARTED        = prog['PWQ_STAT_STARTED']      # work items started execution
+PWQ_STAT_COMPLETED      = prog['PWQ_STAT_COMPLETED']	# work items completed execution
+PWQ_STAT_CPU_TIME       = prog['PWQ_STAT_CPU_TIME']     # total CPU time consumed
+PWQ_STAT_CPU_INTENSIVE  = prog['PWQ_STAT_CPU_INTENSIVE'] # wq_cpu_intensive_thresh_us violations
+PWQ_STAT_CM_WAKEUP      = prog['PWQ_STAT_CM_WAKEUP']    # concurrency-management worker wakeups
+PWQ_STAT_MAYDAY         = prog['PWQ_STAT_MAYDAY']	# maydays to rescuer
+PWQ_STAT_RESCUED        = prog['PWQ_STAT_RESCUED']	# linked work items executed by rescuer
+PWQ_NR_STATS            = prog['PWQ_NR_STATS']
+
+class WqStats:
+    def __init__(self, wq):
+        self.name = wq.name.string_().decode()
+        self.unbound = wq.flags & WQ_UNBOUND != 0
+        self.mem_reclaim = wq.flags & WQ_MEM_RECLAIM != 0
+        self.stats = [0] * PWQ_NR_STATS
+        for pwq in list_for_each_entry('struct pool_workqueue', wq.pwqs.address_of_(), 'pwqs_node'):
+            for i in range(PWQ_NR_STATS):
+                self.stats[i] += int(pwq.stats[i])
+
+    def dict(self, now):
+        return { 'timestamp'            : now,
+                 'name'                 : self.name,
+                 'unbound'              : self.unbound,
+                 'mem_reclaim'          : self.mem_reclaim,
+                 'started'              : self.stats[PWQ_STAT_STARTED],
+                 'completed'            : self.stats[PWQ_STAT_COMPLETED],
+                 'cpu_time'             : self.stats[PWQ_STAT_CPU_TIME],
+                 'cpu_intensive'        : self.stats[PWQ_STAT_CPU_INTENSIVE],
+                 'cm_wakeup'            : self.stats[PWQ_STAT_CM_WAKEUP],
+                 'mayday'               : self.stats[PWQ_STAT_MAYDAY],
+                 'rescued'              : self.stats[PWQ_STAT_RESCUED], }
+
+    def table_header_str():
+        return f'{"":>24} {"total":>8} {"infl":>5} {"CPUtime":>8} '\
+            f'{"CPUitsv":>7} {"CMwake":>7} {"mayday":>7} {"rescued":>7}'
+
+    def table_row_str(self):
+        cpu_intensive = '-'
+        cm_wakeup = '-'
+        mayday = '-'
+        rescued = '-'
+
+        if not self.unbound:
+            cpu_intensive = str(self.stats[PWQ_STAT_CPU_INTENSIVE])
+            cm_wakeup = str(self.stats[PWQ_STAT_CM_WAKEUP])
+
+        if self.mem_reclaim:
+            mayday = str(self.stats[PWQ_STAT_MAYDAY])
+            rescued = str(self.stats[PWQ_STAT_RESCUED])
+
+        out = f'{self.name[-24:]:24} ' \
+              f'{self.stats[PWQ_STAT_STARTED]:8} ' \
+              f'{max(self.stats[PWQ_STAT_STARTED] - self.stats[PWQ_STAT_COMPLETED], 0):5} ' \
+              f'{self.stats[PWQ_STAT_CPU_TIME] / 1000000:8.1f} ' \
+              f'{cpu_intensive:>7} ' \
+              f'{cm_wakeup:>7} ' \
+              f'{mayday:>7} ' \
+              f'{rescued:>7} '
+        return out.rstrip(':')
+
+exit_req = False
+
+def sigint_handler(signr, frame):
+    global exit_req
+    exit_req = True
+
+def main():
+    # handle args
+    table_fmt = not args.json
+    interval = args.interval
+
+    re_str = None
+    if args.workqueue:
+        for r in args.workqueue:
+            if re_str is None:
+                re_str = r
+            else:
+                re_str += '|' + r
+
+    filter_re = re.compile(re_str) if re_str else None
+
+    # monitoring loop
+    signal.signal(signal.SIGINT, sigint_handler)
+
+    while not exit_req:
+        now = time.time()
+
+        if table_fmt:
+            print()
+            print(WqStats.table_header_str())
+
+        for wq in list_for_each_entry('struct workqueue_struct', workqueues.address_of_(), 'list'):
+            stats = WqStats(wq)
+            if filter_re and not filter_re.search(stats.name):
+                continue
+            if table_fmt:
+                print(stats.table_row_str())
+            else:
+                print(stats.dict(now))
+
+        if interval == 0:
+            break
+        time.sleep(interval)
+
+if __name__ == "__main__":
+    main()