Merge branches 'doc.2017.10.20a', 'fixes.2017.10.19a', 'stall.2017.10.09a' and 'torture.2017.10.09a' into HEAD

doc.2017.10.20a: Documentation updates.
fixes.2017.10.19a: Miscellaneous fixes.
stall.2017.10.09a: RCU CPU stall-warning updates.
torture.2017.10.09a: Torture-test updates.

Documentation/admin-guide/kernel-parameters.txt

@@ -3539,6 +3539,9 @@
 	rcutorture.stall_cpu_holdoff= [KNL]
 			Time to wait (s) after boot before inducing stall.
 
+	rcutorture.stall_cpu_irqsoff= [KNL]
+			Disable interrupts while stalling if set.
+
 	rcutorture.stat_interval= [KNL]
 			Time (s) between statistics printk()s.
 

include/linux/irq_work.h

@@ -33,10 +33,7 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
 #define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), }
 
 bool irq_work_queue(struct irq_work *work);
-
-#ifdef CONFIG_SMP
 bool irq_work_queue_on(struct irq_work *work, int cpu);
-#endif
 
 void irq_work_tick(void);
 void irq_work_sync(struct irq_work *work);

kernel/irq_work.c

@@ -56,7 +56,6 @@ void __weak arch_irq_work_raise(void)
 	 */
 }
 
-#ifdef CONFIG_SMP
 /*
  * Enqueue the irq_work @work on @cpu unless it's already pending
  * somewhere.
@@ -68,6 +67,8 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(cpu));
 
+#ifdef CONFIG_SMP
+
 	/* Arch remote IPI send/receive backend aren't NMI safe */
 	WARN_ON_ONCE(in_nmi());
 
@@ -78,10 +79,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
 		arch_send_call_function_single_ipi(cpu);
 
+#else /* #ifdef CONFIG_SMP */
+	irq_work_queue(work);
+#endif /* #else #ifdef CONFIG_SMP */
+
 	return true;
 }
-EXPORT_SYMBOL_GPL(irq_work_queue_on);
-#endif
 
 /* Enqueue the irq work @work on the current CPU */
 bool irq_work_queue(struct irq_work *work)

kernel/rcu/rcu.h

@@ -203,6 +203,21 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 extern int rcu_cpu_stall_suppress;
 int rcu_jiffies_till_stall_check(void);
 
+#define rcu_ftrace_dump_stall_suppress() \
+do { \
+	if (!rcu_cpu_stall_suppress) \
+		rcu_cpu_stall_suppress = 3; \
+} while (0)
+
+#define rcu_ftrace_dump_stall_unsuppress() \
+do { \
+	if (rcu_cpu_stall_suppress == 3) \
+		rcu_cpu_stall_suppress = 0; \
+} while (0)
+
+#else /* #endif #ifdef CONFIG_RCU_STALL_COMMON */
+#define rcu_ftrace_dump_stall_suppress()
+#define rcu_ftrace_dump_stall_unsuppress()
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
 /*
@@ -220,8 +235,12 @@ do { \
 	static atomic_t ___rfd_beenhere = ATOMIC_INIT(0); \
 	\
 	if (!atomic_read(&___rfd_beenhere) && \
-	    !atomic_xchg(&___rfd_beenhere, 1)) \
+	    !atomic_xchg(&___rfd_beenhere, 1)) { \
+		tracing_off(); \
+		rcu_ftrace_dump_stall_suppress(); \
 		ftrace_dump(oops_dump_mode); \
+		rcu_ftrace_dump_stall_unsuppress(); \
+	} \
 } while (0)
 
 void rcu_early_boot_tests(void);

kernel/rcu/rcu_segcblist.c

@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/rcupdate.h>
 
 #include "rcu_segcblist.h"
 

kernel/rcu/rcutorture.c

@@ -51,6 +51,7 @@
 #include <asm/byteorder.h>
 #include <linux/torture.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/debug.h>
 
 #include "rcu.h"
 
@@ -89,6 +90,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
 torture_param(int, stall_cpu_holdoff, 10,
 	     "Time to wait before starting stall (s).");
+torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling.");
 torture_param(int, stat_interval, 60,
 	     "Number of seconds between stats printk()s");
 torture_param(int, stutter, 5, "Number of seconds to run/halt test");
@@ -1239,6 +1241,7 @@ rcu_torture_stats_print(void)
 	long pipesummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	long batchsummary[RCU_TORTURE_PIPE_LEN + 1] = { 0 };
 	static unsigned long rtcv_snap = ULONG_MAX;
+	static bool splatted;
 	struct task_struct *wtp;
 
 	for_each_possible_cpu(cpu) {
@@ -1324,6 +1327,10 @@ rcu_torture_stats_print(void)
 			 gpnum, completed, flags,
 			 wtp == NULL ? ~0UL : wtp->state,
 			 wtp == NULL ? -1 : (int)task_cpu(wtp));
+		if (!splatted && wtp) {
+			sched_show_task(wtp);
+			splatted = true;
+		}
 		show_rcu_gp_kthreads();
 		rcu_ftrace_dump(DUMP_ALL);
 	}
@@ -1357,7 +1364,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d "
 		 "test_boost=%d/%d test_boost_interval=%d "
 		 "test_boost_duration=%d shutdown_secs=%d "
-		 "stall_cpu=%d stall_cpu_holdoff=%d "
+		 "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
 		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
@@ -1365,7 +1372,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
 		 test_boost, cur_ops->can_boost,
 		 test_boost_interval, test_boost_duration, shutdown_secs,
-		 stall_cpu, stall_cpu_holdoff,
+		 stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
 		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff);
 }
@@ -1430,12 +1437,19 @@ static int rcu_torture_stall(void *args)
 	if (!kthread_should_stop()) {
 		stop_at = get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
-		pr_alert("rcu_torture_stall start.\n");
 		rcu_read_lock();
-		preempt_disable();
+		if (stall_cpu_irqsoff)
+			local_irq_disable();
+		else
+			preempt_disable();
+		pr_alert("rcu_torture_stall start on CPU %d.\n",
+			 smp_processor_id());
 		while (ULONG_CMP_LT(get_seconds(), stop_at))
 			continue;  /* Induce RCU CPU stall warning. */
-		preempt_enable();
+		if (stall_cpu_irqsoff)
+			local_irq_enable();
+		else
+			preempt_enable();
 		rcu_read_unlock();
 		pr_alert("rcu_torture_stall end.\n");
 	}

kernel/rcu/tree.c

@@ -534,8 +534,8 @@ module_param(rcu_kick_kthreads, bool, 0644);
  * How long the grace period must be before we start recruiting
  * quiescent-state help from rcu_note_context_switch().
  */
-static ulong jiffies_till_sched_qs = HZ / 20;
-module_param(jiffies_till_sched_qs, ulong, 0644);
+static ulong jiffies_till_sched_qs = HZ / 10;
+module_param(jiffies_till_sched_qs, ulong, 0444);
 
 static bool rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
@@ -837,6 +837,9 @@ static void rcu_eqs_enter(bool user)
  * We crowbar the ->dynticks_nesting field to zero to allow for
  * the possibility of usermode upcalls having messed up our count
  * of interrupt nesting level during the prior busy period.
+ *
+ * If you add or remove a call to rcu_idle_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_idle_enter(void)
 {
@@ -852,6 +855,9 @@ void rcu_idle_enter(void)
  * is permitted between this call and rcu_user_exit(). This way the
  * CPU doesn't need to maintain the tick for RCU maintenance purposes
  * when the CPU runs in userspace.
+ *
+ * If you add or remove a call to rcu_user_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_user_enter(void)
 {
@@ -875,6 +881,9 @@ void rcu_user_enter(void)
  * Use things like work queues to work around this limitation.
  *
  * You have been warned.
+ *
+ * If you add or remove a call to rcu_irq_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_irq_exit(void)
 {
@@ -899,6 +908,9 @@ void rcu_irq_exit(void)
 
 /*
  * Wrapper for rcu_irq_exit() where interrupts are enabled.
+ *
+ * If you add or remove a call to rcu_irq_exit_irqson(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_irq_exit_irqson(void)
 {
@@ -971,6 +983,9 @@ static void rcu_eqs_exit(bool user)
  * allow for the possibility of usermode upcalls messing up our count
  * of interrupt nesting level during the busy period that is just
  * now starting.
+ *
+ * If you add or remove a call to rcu_idle_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_idle_exit(void)
 {
@@ -987,6 +1002,9 @@ void rcu_idle_exit(void)
  *
  * Exit RCU idle mode while entering the kernel because it can
  * run a RCU read side critical section anytime.
+ *
+ * If you add or remove a call to rcu_user_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_user_exit(void)
 {
@@ -1012,6 +1030,9 @@ void rcu_user_exit(void)
  * Use things like work queues to work around this limitation.
  *
  * You have been warned.
+ *
+ * If you add or remove a call to rcu_irq_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_irq_enter(void)
 {
@@ -1037,6 +1058,9 @@ void rcu_irq_enter(void)
 
 /*
  * Wrapper for rcu_irq_enter() where interrupts are enabled.
+ *
+ * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_irq_enter_irqson(void)
 {
@@ -1055,6 +1079,9 @@ void rcu_irq_enter_irqson(void)
  * that the CPU is active.  This implementation permits nested NMIs, as
  * long as the nesting level does not overflow an int.  (You will probably
  * run out of stack space first.)
+ *
+ * If you add or remove a call to rcu_nmi_enter(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_nmi_enter(void)
 {
@@ -1087,6 +1114,9 @@ void rcu_nmi_enter(void)
  * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
  * to let the RCU grace-period handling know that the CPU is back to
  * being RCU-idle.
+ *
+ * If you add or remove a call to rcu_nmi_exit(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
  */
 void rcu_nmi_exit(void)
 {
@@ -1206,6 +1236,22 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 	return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1;
 }
 
+/*
+ * We are reporting a quiescent state on behalf of some other CPU, so
+ * it is our responsibility to check for and handle potential overflow
+ * of the rcu_node ->gpnum counter with respect to the rcu_data counters.
+ * After all, the CPU might be in deep idle state, and thus executing no
+ * code whatsoever.
+ */
+static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
+{
+	lockdep_assert_held(&rnp->lock);
+	if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
+		WRITE_ONCE(rdp->gpwrap, true);
+	if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
+		rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
+}
+
 /*
  * Snapshot the specified CPU's dynticks counter so that we can later
  * credit them with an implicit quiescent state.  Return 1 if this CPU
@@ -1216,14 +1262,33 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 	rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
 	if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
-		if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
-				 rdp->mynode->gpnum))
-			WRITE_ONCE(rdp->gpwrap, true);
+		rcu_gpnum_ovf(rdp->mynode, rdp);
 		return 1;
 	}
 	return 0;
 }
 
+/*
+ * Handler for the irq_work request posted when a grace period has
+ * gone on for too long, but not yet long enough for an RCU CPU
+ * stall warning.  Set state appropriately, but just complain if
+ * there is unexpected state on entry.
+ */
+static void rcu_iw_handler(struct irq_work *iwp)
+{
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	rdp = container_of(iwp, struct rcu_data, rcu_iw);
+	rnp = rdp->mynode;
+	raw_spin_lock_rcu_node(rnp);
+	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
+		rdp->rcu_iw_gpnum = rnp->gpnum;
+		rdp->rcu_iw_pending = false;
+	}
+	raw_spin_unlock_rcu_node(rnp);
+}
+
 /*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
@@ -1235,8 +1300,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	unsigned long jtsq;
 	bool *rnhqp;
 	bool *ruqp;
-	unsigned long rjtsc;
-	struct rcu_node *rnp;
+	struct rcu_node *rnp = rdp->mynode;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -1249,34 +1313,25 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		rdp->dynticks_fqs++;
+		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
 	}
 
-	/* Compute and saturate jiffies_till_sched_qs. */
-	jtsq = jiffies_till_sched_qs;
-	rjtsc = rcu_jiffies_till_stall_check();
-	if (jtsq > rjtsc / 2) {
-		WRITE_ONCE(jiffies_till_sched_qs, rjtsc);
-		jtsq = rjtsc / 2;
-	} else if (jtsq < 1) {
-		WRITE_ONCE(jiffies_till_sched_qs, 1);
-		jtsq = 1;
-	}
-
 	/*
 	 * Has this CPU encountered a cond_resched_rcu_qs() since the
 	 * beginning of the grace period?  For this to be the case,
 	 * the CPU has to have noticed the current grace period.  This
 	 * might not be the case for nohz_full CPUs looping in the kernel.
 	 */
-	rnp = rdp->mynode;
+	jtsq = jiffies_till_sched_qs;
 	ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
 	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
 	    READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
 	    READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
-	} else {
+	} else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
 		/* Load rcu_qs_ctr before store to rcu_urgent_qs. */
 		smp_store_release(ruqp, true);
 	}
@@ -1285,6 +1340,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
 		rdp->offline_fqs++;
+		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
 	}
 
@@ -1304,10 +1360,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * updates are only once every few jiffies, the probability of
 	 * lossage (and thus of slight grace-period extension) is
 	 * quite low.
-	 *
-	 * Note that if the jiffies_till_sched_qs boot/sysfs parameter
-	 * is set too high, we override with half of the RCU CPU stall
-	 * warning delay.
 	 */
 	rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu);
 	if (!READ_ONCE(*rnhqp) &&
@@ -1316,15 +1368,26 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		WRITE_ONCE(*rnhqp, true);
 		/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
 		smp_store_release(ruqp, true);
-		rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
+		rdp->rsp->jiffies_resched += jtsq; /* Re-enable beating. */
 	}
 
 	/*
-	 * If more than halfway to RCU CPU stall-warning time, do
-	 * a resched_cpu() to try to loosen things up a bit.
+	 * If more than halfway to RCU CPU stall-warning time, do a
+	 * resched_cpu() to try to loosen things up a bit.  Also check to
+	 * see if the CPU is getting hammered with interrupts, but only
+	 * once per grace period, just to keep the IPIs down to a dull roar.
 	 */
-	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2)
+	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
 		resched_cpu(rdp->cpu);
+		if (IS_ENABLED(CONFIG_IRQ_WORK) &&
+		    !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum &&
+		    (rnp->ffmask & rdp->grpmask)) {
+			init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
+			rdp->rcu_iw_pending = true;
+			rdp->rcu_iw_gpnum = rnp->gpnum;
+			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
+		}
+	}
 
 	return 0;
 }
@@ -1513,6 +1576,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 {
 	int cpu;
 	unsigned long flags;
+	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	long totqlen = 0;
 
@@ -1528,7 +1592,9 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	 */
 	pr_err("INFO: %s self-detected stall on CPU", rsp->name);
 	print_cpu_stall_info_begin();
+	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
 	print_cpu_stall_info(rsp, smp_processor_id());
+	raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
 	print_cpu_stall_info_end();
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
@@ -1922,6 +1988,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->core_needs_qs = need_gp;
 		zero_cpu_stall_ticks(rdp);
 		WRITE_ONCE(rdp->gpwrap, false);
+		rcu_gpnum_ovf(rnp, rdp);
 	}
 	return ret;
 }
@@ -3700,6 +3767,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
+	rdp->rcu_iw_pending = false;
+	rdp->rcu_iw_gpnum = rnp->gpnum - 1;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
@@ -3737,10 +3806,24 @@ static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
  */
 int rcutree_online_cpu(unsigned int cpu)
 {
-	sync_sched_exp_online_cleanup(cpu);
-	rcutree_affinity_setting(cpu, -1);
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		rnp = rdp->mynode;
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		rnp->ffmask |= rdp->grpmask;
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
 	if (IS_ENABLED(CONFIG_TREE_SRCU))
 		srcu_online_cpu(cpu);
+	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
+		return 0; /* Too early in boot for scheduler work. */
+	sync_sched_exp_online_cleanup(cpu);
+	rcutree_affinity_setting(cpu, -1);
 	return 0;
 }
 
@@ -3750,6 +3833,19 @@ int rcutree_online_cpu(unsigned int cpu)
  */
 int rcutree_offline_cpu(unsigned int cpu)
 {
+	unsigned long flags;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp;
+
+	for_each_rcu_flavor(rsp) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		rnp = rdp->mynode;
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		rnp->ffmask &= ~rdp->grpmask;
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+
 	rcutree_affinity_setting(cpu, cpu);
 	if (IS_ENABLED(CONFIG_TREE_SRCU))
 		srcu_offline_cpu(cpu);
@@ -4198,8 +4294,7 @@ void __init rcu_init(void)
 	for_each_online_cpu(cpu) {
 		rcutree_prepare_cpu(cpu);
 		rcu_cpu_starting(cpu);
-		if (IS_ENABLED(CONFIG_TREE_SRCU))
-			srcu_online_cpu(cpu);
+		rcutree_online_cpu(cpu);
 	}
 }
 

kernel/rcu/tree.h

@@ -103,6 +103,7 @@ struct rcu_node {
 				/* Online CPUs for next expedited GP. */
 				/*  Any CPU that has ever been online will */
 				/*  have its bit set. */
+	unsigned long ffmask;	/* Fully functional CPUs. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
 	int	grplo;		/* lowest-numbered CPU or group here. */
@@ -285,6 +286,10 @@ struct rcu_data {
 
 	/* 8) RCU CPU stall data. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
+	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
+	struct irq_work rcu_iw;		/* Check for non-irq activity. */
+	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
+	unsigned long rcu_iw_gpnum;	/* ->gpnum associated with ->rcu_iw. */
 
 	int cpu;
 	struct rcu_state *rsp;

kernel/rcu/tree_plugin.h

@@ -54,6 +54,7 @@ DEFINE_PER_CPU(char, rcu_cpu_has_work);
  * This probably needs to be excluded from -rt builds.
  */
 #define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
+#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1)
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
@@ -530,7 +531,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 		/* Unboost if we were boosted. */
 		if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
-			rt_mutex_unlock(&rnp->boost_mtx);
+			rt_mutex_futex_unlock(&rnp->boost_mtx);
 
 		/*
 		 * If this was the last task on the expedited lists,
@@ -911,8 +912,6 @@ void exit_rcu(void)
 
 #ifdef CONFIG_RCU_BOOST
 
-#include "../locking/rtmutex_common.h"
-
 static void rcu_wake_cond(struct task_struct *t, int status)
 {
 	/*
@@ -1507,7 +1506,7 @@ static void rcu_prepare_for_idle(void)
 	rdtp->last_accelerate = jiffies;
 	for_each_rcu_flavor(rsp) {
 		rdp = this_cpu_ptr(rsp->rda);
-		if (rcu_segcblist_pend_cbs(&rdp->cblist))
+		if (!rcu_segcblist_pend_cbs(&rdp->cblist))
 			continue;
 		rnp = rdp->mynode;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
@@ -1671,6 +1670,7 @@ static void print_cpu_stall_info_begin(void)
  */
 static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 {
+	unsigned long delta;
 	char fast_no_hz[72];
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_dynticks *rdtp = rdp->dynticks;
@@ -1685,11 +1685,15 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	pr_err("\t%d-%c%c%c: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n",
+	delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum;
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%llx/%d softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
 	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
+	       !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
+			rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
+				"!."[!delta],
 	       ticks_value, ticks_title,
 	       rcu_dynticks_snap(rdtp) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,

kernel/rcu/update.c

@@ -494,6 +494,7 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 #endif
 
 int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
 static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 
 module_param(rcu_cpu_stall_suppress, int, 0644);
@@ -575,7 +576,6 @@ DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
 static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
 module_param(rcu_task_stall_timeout, int, 0644);
 
-static void rcu_spawn_tasks_kthread(void);
 static struct task_struct *rcu_tasks_kthread_ptr;
 
 /**
@@ -600,7 +600,6 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
 {
 	unsigned long flags;
 	bool needwake;
-	bool havetask = READ_ONCE(rcu_tasks_kthread_ptr);
 
 	rhp->next = NULL;
 	rhp->func = func;
@@ -610,11 +609,8 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
 	rcu_tasks_cbs_tail = &rhp->next;
 	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
 	/* We can't create the thread unless interrupts are enabled. */
-	if ((needwake && havetask) ||
-	    (!havetask && !irqs_disabled_flags(flags))) {
-		rcu_spawn_tasks_kthread();
+	if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))
 		wake_up(&rcu_tasks_cbs_wq);
-	}
 }
 EXPORT_SYMBOL_GPL(call_rcu_tasks);
 
@@ -853,27 +849,18 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	}
 }
 
-/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */
-static void rcu_spawn_tasks_kthread(void)
+/* Spawn rcu_tasks_kthread() at core_initcall() time. */
+static int __init rcu_spawn_tasks_kthread(void)
 {
-	static DEFINE_MUTEX(rcu_tasks_kthread_mutex);
 	struct task_struct *t;
 
-	if (READ_ONCE(rcu_tasks_kthread_ptr)) {
-		smp_mb(); /* Ensure caller sees full kthread. */
-		return;
-	}
-	mutex_lock(&rcu_tasks_kthread_mutex);
-	if (rcu_tasks_kthread_ptr) {
-		mutex_unlock(&rcu_tasks_kthread_mutex);
-		return;
-	}
 	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
 	BUG_ON(IS_ERR(t));
 	smp_mb(); /* Ensure others see full kthread. */
 	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
-	mutex_unlock(&rcu_tasks_kthread_mutex);
+	return 0;
 }
+core_initcall(rcu_spawn_tasks_kthread);
 
 /* Do the srcu_read_lock() for the above synchronize_srcu().  */
 void exit_tasks_rcu_start(void)

kernel/sched/core.c

@@ -505,8 +505,7 @@ void resched_cpu(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	if (!raw_spin_trylock_irqsave(&rq->lock, flags))
-		return;
+	raw_spin_lock_irqsave(&rq->lock, flags);
 	resched_curr(rq);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
@@ -4842,6 +4841,7 @@ int __sched _cond_resched(void)
 		preempt_schedule_common();
 		return 1;
 	}
+	rcu_all_qs();
 	return 0;
 }
 EXPORT_SYMBOL(_cond_resched);
@@ -5165,6 +5165,7 @@ void sched_show_task(struct task_struct *p)
 	show_stack(p, NULL);
 	put_task_stack(p);
 }
+EXPORT_SYMBOL_GPL(sched_show_task);
 
 static inline bool
 state_filter_match(unsigned long state_filter, struct task_struct *p)

tools/testing/selftests/rcutorture/bin/config_override.sh

@@ -42,7 +42,7 @@ else
 	exit 1
 fi
 
-T=/tmp/config_override.sh.$$
+T=${TMPDIR-/tmp}/config_override.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 

tools/testing/selftests/rcutorture/bin/configcheck.sh

@@ -19,7 +19,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/abat-chk-config.sh.$$
+T=${TMPDIR-/tmp}/abat-chk-config.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 

tools/testing/selftests/rcutorture/bin/configinit.sh

@@ -32,7 +32,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/configinit.sh.$$
+T=${TMPDIR-/tmp}/configinit.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 

tools/testing/selftests/rcutorture/bin/kvm-build.sh

@@ -35,7 +35,7 @@ then
 	exit 1
 fi
 
-T=/tmp/test-linux.sh.$$
+T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 

tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh

@@ -38,7 +38,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/kvm-test-1-run.sh.$$
+T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 

tools/testing/selftests/rcutorture/bin/kvm.sh

@@ -30,7 +30,7 @@
 scriptname=$0
 args="$*"
 
-T=/tmp/kvm.sh.$$
+T=${TMPDIR-/tmp}/kvm.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 
@@ -222,7 +222,7 @@ do
 		exit 1
 	fi
 done
-sort -k2nr $T/cfgcpu > $T/cfgcpu.sort
+sort -k2nr $T/cfgcpu -T="$T" > $T/cfgcpu.sort
 
 # Use a greedy bin-packing algorithm, sorting the list accordingly.
 awk < $T/cfgcpu.sort > $T/cfgcpu.pack -v ncpus=$cpus '

tools/testing/selftests/rcutorture/bin/parse-build.sh

@@ -28,7 +28,7 @@
 
 F=$1
 title=$2
-T=/tmp/parse-build.sh.$$
+T=${TMPDIR-/tmp}/parse-build.sh.$$
 trap 'rm -rf $T' 0
 mkdir $T
 

tools/testing/selftests/rcutorture/bin/parse-torture.sh

@@ -27,7 +27,7 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-T=/tmp/parse-torture.sh.$$
+T=${TMPDIR-/tmp}/parse-torture.sh.$$
 file="$1"
 title="$2"