Merge branch 'exp.2022.05.11a' into HEAD

exp.2022.05.11a: Expedited-grace-period latency-reduction updates.

8 files changed, 236 insertions, 36 deletions

diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 65d45c00fd1b79..1c630e573548df 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -220,6 +220,20 @@ config RCU_BOOST_DELAY
 
 	  Accept the default if unsure.
 
+config RCU_EXP_KTHREAD
+	bool "Perform RCU expedited work in a real-time kthread"
+	depends on RCU_BOOST && RCU_EXPERT
+	default !PREEMPT_RT && NR_CPUS <= 32
+	help
+	  Use this option to further reduce the latencies of expedited
+	  grace periods at the expense of being more disruptive.
+
+	  This option is disabled by default on PREEMPT_RT=y kernels which
+	  disable expedited grace periods after boot by unconditionally
+	  setting rcupdate.rcu_normal_after_boot=1.
+
+	  Accept the default if unsure.
+
 config RCU_NOCB_CPU
 	bool "Offload RCU callback processing from boot-selected CPUs"
 	depends on TREE_RCU
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 68092e1db64bde..9b64e55d4f6159 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -82,6 +82,20 @@ config RCU_CPU_STALL_TIMEOUT
 	  RCU grace period persists, additional CPU stall warnings are
 	  printed at more widely spaced intervals.
 
+config RCU_EXP_CPU_STALL_TIMEOUT
+	int "Expedited RCU CPU stall timeout in milliseconds"
+	depends on RCU_STALL_COMMON
+	range 0 21000
+	default 20 if ANDROID
+	default 0 if !ANDROID
+	help
+	  If a given expedited RCU grace period extends more than the
+	  specified number of milliseconds, a CPU stall warning is printed.
+	  If the RCU grace period persists, additional CPU stall warnings
+	  are printed at more widely spaced intervals.  A value of zero
+	  says to use the RCU_CPU_STALL_TIMEOUT value converted from
+	  seconds to milliseconds.
+
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index a985dfc2ce26e3..152492d5271564 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -210,7 +210,9 @@ static inline bool rcu_stall_is_suppressed_at_boot(void)
 extern int rcu_cpu_stall_ftrace_dump;
 extern int rcu_cpu_stall_suppress;
 extern int rcu_cpu_stall_timeout;
+extern int rcu_exp_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
+int rcu_exp_jiffies_till_stall_check(void);
 
 static inline bool rcu_stall_is_suppressed(void)
 {
@@ -536,7 +538,12 @@ int rcu_get_gp_kthreads_prio(void);
 void rcu_fwd_progress_check(unsigned long j);
 void rcu_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
+#ifdef CONFIG_RCU_EXP_KTHREAD
+extern struct kthread_worker *rcu_exp_gp_kworker;
+extern struct kthread_worker *rcu_exp_par_gp_kworker;
+#else /* !CONFIG_RCU_EXP_KTHREAD */
 extern struct workqueue_struct *rcu_par_gp_wq;
+#endif /* CONFIG_RCU_EXP_KTHREAD */
 void rcu_gp_slow_register(atomic_t *rgssp);
 void rcu_gp_slow_unregister(atomic_t *rgssp);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 75a35b7adbfa8e..c25ba442044a6e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4526,6 +4526,51 @@ static int rcu_pm_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+#ifdef CONFIG_RCU_EXP_KTHREAD
+struct kthread_worker *rcu_exp_gp_kworker;
+struct kthread_worker *rcu_exp_par_gp_kworker;
+
+static void __init rcu_start_exp_gp_kworkers(void)
+{
+	const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker";
+	const char *gp_kworker_name = "rcu_exp_gp_kthread_worker";
+	struct sched_param param = { .sched_priority = kthread_prio };
+
+	rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name);
+	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
+		pr_err("Failed to create %s!\n", gp_kworker_name);
+		return;
+	}
+
+	rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name);
+	if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) {
+		pr_err("Failed to create %s!\n", par_gp_kworker_name);
+		kthread_destroy_worker(rcu_exp_gp_kworker);
+		return;
+	}
+
+	sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, &param);
+	sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO,
+				   &param);
+}
+
+static inline void rcu_alloc_par_gp_wq(void)
+{
+}
+#else /* !CONFIG_RCU_EXP_KTHREAD */
+struct workqueue_struct *rcu_par_gp_wq;
+
+static void __init rcu_start_exp_gp_kworkers(void)
+{
+}
+
+static inline void rcu_alloc_par_gp_wq(void)
+{
+	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
+	WARN_ON(!rcu_par_gp_wq);
+}
+#endif /* CONFIG_RCU_EXP_KTHREAD */
+
 /*
  * Spawn the kthreads that handle RCU's grace periods.
  */
@@ -4562,6 +4607,8 @@ static int __init rcu_spawn_gp_kthread(void)
 	rcu_spawn_cpu_nocb_kthread(smp_processor_id());
 	rcu_spawn_one_boost_kthread(rdp->mynode);
 	rcu_spawn_core_kthreads();
+	/* Create kthread worker for expedited GPs */
+	rcu_start_exp_gp_kworkers();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);
@@ -4807,7 +4854,6 @@ static void __init rcu_dump_rcu_node_tree(void)
 }
 
 struct workqueue_struct *rcu_gp_wq;
-struct workqueue_struct *rcu_par_gp_wq;
 
 static void __init kfree_rcu_batch_init(void)
 {
@@ -4872,8 +4918,7 @@ void __init rcu_init(void)
 	/* Create workqueue for Tree SRCU and for expedited GPs. */
 	rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_gp_wq);
-	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
-	WARN_ON(!rcu_par_gp_wq);
+	rcu_alloc_par_gp_wq();
 
 	/* Fill in default value for rcutree.qovld boot parameter. */
 	/* -After- the rcu_node ->lock fields are initialized! */
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8aa5bf74e796a1..2ccf5845957df4 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -10,6 +10,7 @@
  */
 
 #include <linux/cache.h>
+#include <linux/kthread.h>
 #include <linux/spinlock.h>
 #include <linux/rtmutex.h>
 #include <linux/threads.h>
@@ -23,7 +24,11 @@
 /* Communicate arguments to a workqueue handler. */
 struct rcu_exp_work {
 	unsigned long rew_s;
+#ifdef CONFIG_RCU_EXP_KTHREAD
+	struct kthread_work rew_work;
+#else
 	struct work_struct rew_work;
+#endif /* CONFIG_RCU_EXP_KTHREAD */
 };
 
 /* RCU's kthread states for tracing. */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 60197ea24ceb9c..0f70f62039a909 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -334,15 +334,13 @@ fastpath:
  * Select the CPUs within the specified rcu_node that the upcoming
  * expedited grace period needs to wait for.
  */
-static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
+static void __sync_rcu_exp_select_node_cpus(struct rcu_exp_work *rewp)
 {
 	int cpu;
 	unsigned long flags;
 	unsigned long mask_ofl_test;
 	unsigned long mask_ofl_ipi;
 	int ret;
-	struct rcu_exp_work *rewp =
-		container_of(wp, struct rcu_exp_work, rew_work);
 	struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -417,13 +415,119 @@ retry_ipi:
 		rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
 }
 
+static void rcu_exp_sel_wait_wake(unsigned long s);
+
+#ifdef CONFIG_RCU_EXP_KTHREAD
+static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
+{
+	struct rcu_exp_work *rewp =
+		container_of(wp, struct rcu_exp_work, rew_work);
+
+	__sync_rcu_exp_select_node_cpus(rewp);
+}
+
+static inline bool rcu_gp_par_worker_started(void)
+{
+	return !!READ_ONCE(rcu_exp_par_gp_kworker);
+}
+
+static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
+{
+	kthread_init_work(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
+	/*
+	 * Use rcu_exp_par_gp_kworker, because flushing a work item from
+	 * another work item on the same kthread worker can result in
+	 * deadlock.
+	 */
+	kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work);
+}
+
+static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
+{
+	kthread_flush_work(&rnp->rew.rew_work);
+}
+
+/*
+ * Work-queue handler to drive an expedited grace period forward.
+ */
+static void wait_rcu_exp_gp(struct kthread_work *wp)
+{
+	struct rcu_exp_work *rewp;
+
+	rewp = container_of(wp, struct rcu_exp_work, rew_work);
+	rcu_exp_sel_wait_wake(rewp->rew_s);
+}
+
+static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew)
+{
+	kthread_init_work(&rew->rew_work, wait_rcu_exp_gp);
+	kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work);
+}
+
+static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
+{
+}
+#else /* !CONFIG_RCU_EXP_KTHREAD */
+static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
+{
+	struct rcu_exp_work *rewp =
+		container_of(wp, struct rcu_exp_work, rew_work);
+
+	__sync_rcu_exp_select_node_cpus(rewp);
+}
+
+static inline bool rcu_gp_par_worker_started(void)
+{
+	return !!READ_ONCE(rcu_par_gp_wq);
+}
+
+static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
+{
+	int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
+
+	INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
+	/* If all offline, queue the work on an unbound CPU. */
+	if (unlikely(cpu > rnp->grphi - rnp->grplo))
+		cpu = WORK_CPU_UNBOUND;
+	else
+		cpu += rnp->grplo;
+	queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+}
+
+static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
+{
+	flush_work(&rnp->rew.rew_work);
+}
+
+/*
+ * Work-queue handler to drive an expedited grace period forward.
+ */
+static void wait_rcu_exp_gp(struct work_struct *wp)
+{
+	struct rcu_exp_work *rewp;
+
+	rewp = container_of(wp, struct rcu_exp_work, rew_work);
+	rcu_exp_sel_wait_wake(rewp->rew_s);
+}
+
+static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew)
+{
+	INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp);
+	queue_work(rcu_gp_wq, &rew->rew_work);
+}
+
+static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew)
+{
+	destroy_work_on_stack(&rew->rew_work);
+}
+#endif /* CONFIG_RCU_EXP_KTHREAD */
+
 /*
  * Select the nodes that the upcoming expedited grace period needs
  * to wait for.
  */
 static void sync_rcu_exp_select_cpus(void)
 {
-	int cpu;
 	struct rcu_node *rnp;
 
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("reset"));
@@ -435,28 +539,21 @@ static void sync_rcu_exp_select_cpus(void)
 		rnp->exp_need_flush = false;
 		if (!READ_ONCE(rnp->expmask))
 			continue; /* Avoid early boot non-existent wq. */
-		if (!READ_ONCE(rcu_par_gp_wq) ||
+		if (!rcu_gp_par_worker_started() ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
 		    rcu_is_last_leaf_node(rnp)) {
-			/* No workqueues yet or last leaf, do direct call. */
+			/* No worker started yet or last leaf, do direct call. */
 			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
 			continue;
 		}
-		INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-		cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1);
-		/* If all offline, queue the work on an unbound CPU. */
-		if (unlikely(cpu > rnp->grphi - rnp->grplo))
-			cpu = WORK_CPU_UNBOUND;
-		else
-			cpu += rnp->grplo;
-		queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+		sync_rcu_exp_select_cpus_queue_work(rnp);
 		rnp->exp_need_flush = true;
 	}
 
-	/* Wait for workqueue jobs (if any) to complete. */
+	/* Wait for jobs (if any) to complete. */
 	rcu_for_each_leaf_node(rnp)
 		if (rnp->exp_need_flush)
-			flush_work(&rnp->rew.rew_work);
+			sync_rcu_exp_select_cpus_flush_work(rnp);
 }
 
 /*
@@ -496,7 +593,7 @@ static void synchronize_rcu_expedited_wait(void)
 	struct rcu_node *rnp_root = rcu_get_root();
 
 	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
-	jiffies_stall = rcu_jiffies_till_stall_check();
+	jiffies_stall = rcu_exp_jiffies_till_stall_check();
 	jiffies_start = jiffies;
 	if (tick_nohz_full_enabled() && rcu_inkernel_boot_has_ended()) {
 		if (synchronize_rcu_expedited_wait_once(1))
@@ -571,7 +668,7 @@ static void synchronize_rcu_expedited_wait(void)
 				dump_cpu_task(cpu);
 			}
 		}
-		jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
+		jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3;
 	}
 }
 
@@ -622,17 +719,6 @@ static void rcu_exp_sel_wait_wake(unsigned long s)
 	rcu_exp_wait_wake(s);
 }
 
-/*
- * Work-queue handler to drive an expedited grace period forward.
- */
-static void wait_rcu_exp_gp(struct work_struct *wp)
-{
-	struct rcu_exp_work *rewp;
-
-	rewp = container_of(wp, struct rcu_exp_work, rew_work);
-	rcu_exp_sel_wait_wake(rewp->rew_s);
-}
-
 #ifdef CONFIG_PREEMPT_RCU
 
 /*
@@ -848,20 +934,19 @@ void synchronize_rcu_expedited(void)
 	} else {
 		/* Marshall arguments & schedule the expedited grace period. */
 		rew.rew_s = s;
-		INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
-		queue_work(rcu_gp_wq, &rew.rew_work);
+		synchronize_rcu_expedited_queue_work(&rew);
 	}
 
 	/* Wait for expedited grace period to complete. */
 	rnp = rcu_get_root();
 	wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
 		   sync_exp_work_done(s));
-	smp_mb(); /* Workqueue actions happen before return. */
+	smp_mb(); /* Work actions happen before return. */
 
 	/* Let the next expedited grace period start. */
 	mutex_unlock(&rcu_state.exp_mutex);
 
 	if (likely(!boottime))
-		destroy_work_on_stack(&rew.rew_work);
+		synchronize_rcu_expedited_destroy_work(&rew);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 268dd79c58e72a..a001e1e7a99269 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -25,6 +25,34 @@ int sysctl_max_rcu_stall_to_panic __read_mostly;
 #define RCU_STALL_MIGHT_DIV		8
 #define RCU_STALL_MIGHT_MIN		(2 * HZ)
 
+int rcu_exp_jiffies_till_stall_check(void)
+{
+	int cpu_stall_timeout = READ_ONCE(rcu_exp_cpu_stall_timeout);
+	int exp_stall_delay_delta = 0;
+	int till_stall_check;
+
+	// Zero says to use rcu_cpu_stall_timeout, but in milliseconds.
+	if (!cpu_stall_timeout)
+		cpu_stall_timeout = jiffies_to_msecs(rcu_jiffies_till_stall_check());
+
+	// Limit check must be consistent with the Kconfig limits for
+	// CONFIG_RCU_EXP_CPU_STALL_TIMEOUT, so check the allowed range.
+	// The minimum clamped value is "2UL", because at least one full
+	// tick has to be guaranteed.
+	till_stall_check = clamp(msecs_to_jiffies(cpu_stall_timeout), 2UL, 21UL * HZ);
+
+	if (cpu_stall_timeout && jiffies_to_msecs(till_stall_check) != cpu_stall_timeout)
+		WRITE_ONCE(rcu_exp_cpu_stall_timeout, jiffies_to_msecs(till_stall_check));
+
+#ifdef CONFIG_PROVE_RCU
+	/* Add extra ~25% out of till_stall_check. */
+	exp_stall_delay_delta = ((till_stall_check * 25) / 100) + 1;
+#endif
+
+	return till_stall_check + exp_stall_delay_delta;
+}
+EXPORT_SYMBOL_GPL(rcu_exp_jiffies_till_stall_check);
+
 /* Limit-check stall timeouts specified at boottime and runtime. */
 int rcu_jiffies_till_stall_check(void)
 {
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 180ff9c41fa87e..fc7fef57560646 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -506,6 +506,8 @@ EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 module_param(rcu_cpu_stall_suppress, int, 0644);
 int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 module_param(rcu_cpu_stall_timeout, int, 0644);
+int rcu_exp_cpu_stall_timeout __read_mostly = CONFIG_RCU_EXP_CPU_STALL_TIMEOUT;
+module_param(rcu_exp_cpu_stall_timeout, int, 0644);
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
 // Suppress boot-time RCU CPU stall warnings and rcutorture writer stall