Merge branch 'for-4.5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq

Pull workqueue fixes from Tejun Heo:
 "Workqueue fixes for v4.5-rc3.

   - Remove a spurious triggering of flush dependency warning.

   - Officially break local execution guarantee of unbound work items
     and add a debug feature to flush out usages which depend on it.

   - Work around CPU -> NODE mapping becoming invalid on CPU offline.

  The branch is young but pushing out early as stable kernels are being
  affected"

* 'for-4.5-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
  workqueue: handle NUMA_NO_NODE for unbound pool_workqueue lookup
  workqueue: implement "workqueue.debug_force_rr_cpu" debug feature
  workqueue: schedule WORK_CPU_UNBOUND work on wq_unbound_cpumask CPUs
  Revert "workqueue: make sure delayed work run in local cpu"
  workqueue: skip flush dependency checks for legacy workqueues

Documentation/kernel-parameters.txt

@@ -4235,6 +4235,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			The default value of this parameter is determined by
 			the config option CONFIG_WQ_POWER_EFFICIENT_DEFAULT.
 
+	workqueue.debug_force_rr_cpu
+			Workqueue used to implicitly guarantee that work
+			items queued without explicit CPU specified are put
+			on the local CPU.  This guarantee is no longer true
+			and while local CPU is still preferred work items
+			may be put on foreign CPUs.  This debug option
+			forces round-robin CPU selection to flush out
+			usages which depend on the now broken guarantee.
+			When enabled, memory and cache locality will be
+			impacted.
+
 	x2apic_phys	[X86-64,APIC] Use x2apic physical mode instead of
 			default x2apic cluster mode on platforms
 			supporting x2apic.

include/linux/workqueue.h

@@ -311,6 +311,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -411,12 +412,12 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
-	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
 #define create_freezable_workqueue(name)				\
-	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
-			1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND |	\
+			WQ_MEM_RECLAIM, 1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
+	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 

kernel/workqueue.c

@@ -301,7 +301,23 @@ static DEFINE_SPINLOCK(wq_mayday_lock);	/* protects wq->maydays list */
 static LIST_HEAD(workqueues);		/* PR: list of all workqueues */
 static bool workqueue_freezing;		/* PL: have wqs started freezing? */
 
-static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */
+/* PL: allowable cpus for unbound wqs and work items */
+static cpumask_var_t wq_unbound_cpumask;
+
+/* CPU where unbound work was last round robin scheduled from this CPU */
+static DEFINE_PER_CPU(int, wq_rr_cpu_last);
+
+/*
+ * Local execution of unbound work items is no longer guaranteed.  The
+ * following always forces round-robin CPU selection on unbound work items
+ * to uncover usages which depend on it.
+ */
+#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU
+static bool wq_debug_force_rr_cpu = true;
+#else
+static bool wq_debug_force_rr_cpu = false;
+#endif
+module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644);
 
 /* the per-cpu worker pools */
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS],
@@ -570,6 +586,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq,
 						  int node)
 {
 	assert_rcu_or_wq_mutex_or_pool_mutex(wq);
+
+	/*
+	 * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a
+	 * delayed item is pending.  The plan is to keep CPU -> NODE
+	 * mapping valid and stable across CPU on/offlines.  Once that
+	 * happens, this workaround can be removed.
+	 */
+	if (unlikely(node == NUMA_NO_NODE))
+		return wq->dfl_pwq;
+
 	return rcu_dereference_raw(wq->numa_pwq_tbl[node]);
 }
 
@@ -1298,6 +1324,39 @@ static bool is_chained_work(struct workqueue_struct *wq)
 	return worker && worker->current_pwq->wq == wq;
 }
 
+/*
+ * When queueing an unbound work item to a wq, prefer local CPU if allowed
+ * by wq_unbound_cpumask.  Otherwise, round robin among the allowed ones to
+ * avoid perturbing sensitive tasks.
+ */
+static int wq_select_unbound_cpu(int cpu)
+{
+	static bool printed_dbg_warning;
+	int new_cpu;
+
+	if (likely(!wq_debug_force_rr_cpu)) {
+		if (cpumask_test_cpu(cpu, wq_unbound_cpumask))
+			return cpu;
+	} else if (!printed_dbg_warning) {
+		pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n");
+		printed_dbg_warning = true;
+	}
+
+	if (cpumask_empty(wq_unbound_cpumask))
+		return cpu;
+
+	new_cpu = __this_cpu_read(wq_rr_cpu_last);
+	new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask);
+	if (unlikely(new_cpu >= nr_cpu_ids)) {
+		new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask);
+		if (unlikely(new_cpu >= nr_cpu_ids))
+			return cpu;
+	}
+	__this_cpu_write(wq_rr_cpu_last, new_cpu);
+
+	return new_cpu;
+}
+
 static void __queue_work(int cpu, struct workqueue_struct *wq,
 			 struct work_struct *work)
 {
@@ -1323,7 +1382,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 		return;
 retry:
 	if (req_cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
+		cpu = wq_select_unbound_cpu(raw_smp_processor_id());
 
 	/* pwq which will be used unless @work is executing elsewhere */
 	if (!(wq->flags & WQ_UNBOUND))
@@ -1464,13 +1523,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 	timer_stats_timer_set_start_info(&dwork->timer);
 
 	dwork->wq = wq;
-	/* timer isn't guaranteed to run in this cpu, record earlier */
-	if (cpu == WORK_CPU_UNBOUND)
-		cpu = raw_smp_processor_id();
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
 
-	add_timer_on(timer, cpu);
+	if (unlikely(cpu != WORK_CPU_UNBOUND))
+		add_timer_on(timer, cpu);
+	else
+		add_timer(timer);
 }
 
 /**
@@ -2355,7 +2414,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq,
 	WARN_ONCE(current->flags & PF_MEMALLOC,
 		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  current->pid, current->comm, target_wq->name, target_func);
-	WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+	WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
+			      (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
 		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  worker->current_pwq->wq->name, worker->current_func,
 		  target_wq->name, target_func);

lib/Kconfig.debug

@@ -1400,6 +1400,21 @@ config RCU_EQS_DEBUG
 
 endmenu # "RCU Debugging"
 
+config DEBUG_WQ_FORCE_RR_CPU
+	bool "Force round-robin CPU selection for unbound work items"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  Workqueue used to implicitly guarantee that work items queued
+	  without explicit CPU specified are put on the local CPU.  This
+	  guarantee is no longer true and while local CPU is still
+	  preferred work items may be put on foreign CPUs.  Kernel
+	  parameter "workqueue.debug_force_rr_cpu" is added to force
+	  round-robin CPU selection to flush out usages which depend on the
+	  now broken guarantee.  This config option enables the debug
+	  feature by default.  When enabled, memory and cache locality will
+	  be impacted.
+
 config DEBUG_BLOCK_EXT_DEVT
         bool "Force extended block device numbers and spread them"
 	depends on DEBUG_KERNEL