Merge branches 'fixes.2020.04.27a', 'kfree_rcu.2020.04.27a', 'rcu-tasks.2020.04.27a', 'stall.2020.04.27a' and 'torture.2020.05.07a' into HEAD

fixes.2020.04.27a:  Miscellaneous fixes.
kfree_rcu.2020.04.27a:  Changes related to kfree_rcu().
rcu-tasks.2020.04.27a:  Addition of new RCU-tasks flavors.
stall.2020.04.27a:  RCU CPU stall-warning updates.
torture.2020.05.07a:  Torture-test updates.

kernel/fork.c

@@ -1683,6 +1683,11 @@ static inline void rcu_copy_process(struct task_struct *p)
 	INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
 	p->rcu_tasks_idle_cpu = -1;
 #endif /* #ifdef CONFIG_TASKS_RCU */
+#ifdef CONFIG_TASKS_TRACE_RCU
+	p->trc_reader_nesting = 0;
+	p->trc_reader_special.s = 0;
+	INIT_LIST_HEAD(&p->trc_holdout_list);
+#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */
 }
 
 struct pid *pidfd_pid(const struct file *file)

kernel/rcu/Kconfig

@@ -70,13 +70,37 @@ config TREE_SRCU
 	help
 	  This option selects the full-fledged version of SRCU.
 
+config TASKS_RCU_GENERIC
+	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
+	select SRCU
+	help
+	  This option enables generic infrastructure code supporting
+	  task-based RCU implementations.  Not for manual selection.
+
 config TASKS_RCU
 	def_bool PREEMPTION
-	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
 	  only voluntary context switch (not preemption!), idle, and
-	  user-mode execution as quiescent states.
+	  user-mode execution as quiescent states.  Not for manual selection.
+
+config TASKS_RUDE_RCU
+	def_bool 0
+	help
+	  This option enables a task-based RCU implementation that uses
+	  only context switch (including preemption) and user-mode
+	  execution as quiescent states.  It forces IPIs and context
+	  switches on all online CPUs, including idle ones, so use
+	  with caution.
+
+config TASKS_TRACE_RCU
+	def_bool 0
+	help
+	  This option enables a task-based RCU implementation that uses
+	  explicit rcu_read_lock_trace() read-side markers, and allows
+	  these readers to appear in the idle loop as well as on the CPU
+	  hotplug code paths.  It can force IPIs on online CPUs, including
+	  idle ones, so use with caution.
 
 config RCU_STALL_COMMON
 	def_bool TREE_RCU
@@ -210,4 +234,22 @@ config RCU_NOCB_CPU
 	  Say Y here if you want to help to debug reduced OS jitter.
 	  Say N here if you are unsure.
 
+config TASKS_TRACE_RCU_READ_MB
+	bool "Tasks Trace RCU readers use memory barriers in user and idle"
+	depends on RCU_EXPERT
+	default PREEMPT_RT || NR_CPUS < 8
+	help
+	  Use this option to further reduce the number of IPIs sent
+	  to CPUs executing in userspace or idle during tasks trace
+	  RCU grace periods.  Given that a reasonable setting of
+	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
+	  eliminates such IPIs for many workloads, proper setting
+	  of this Kconfig option is important mostly for aggressive
+	  real-time installations and for battery-powered devices,
+	  hence the default chosen above.
+
+	  Say Y here if you hate IPIs.
+	  Say N here if you hate read-side memory barriers.
+	  Take the default if you are unsure.
+
 endmenu # "RCU Subsystem"

kernel/rcu/Kconfig.debug

@@ -29,6 +29,8 @@ config RCU_PERF_TEST
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  This option provides a kernel module that runs performance
@@ -46,6 +48,8 @@ config RCU_TORTURE_TEST
 	select TORTURE_TEST
 	select SRCU
 	select TASKS_RCU
+	select TASKS_RUDE_RCU
+	select TASKS_TRACE_RCU
 	default n
 	help
 	  This option provides a kernel module that runs torture tests

kernel/rcu/rcu.h

@@ -431,6 +431,7 @@ bool rcu_gp_is_expedited(void);  /* Internal RCU use. */
 void rcu_expedite_gp(void);
 void rcu_unexpedite_gp(void);
 void rcupdate_announce_bootup_oddness(void);
+void show_rcu_tasks_gp_kthreads(void);
 void rcu_request_urgent_qs_task(struct task_struct *t);
 #endif /* #else #ifdef CONFIG_TINY_RCU */
 
@@ -441,6 +442,8 @@ void rcu_request_urgent_qs_task(struct task_struct *t);
 enum rcutorture_type {
 	RCU_FLAVOR,
 	RCU_TASKS_FLAVOR,
+	RCU_TASKS_RUDE_FLAVOR,
+	RCU_TASKS_TRACING_FLAVOR,
 	RCU_TRIVIAL_FLAVOR,
 	SRCU_FLAVOR,
 	INVALID_RCU_FLAVOR
@@ -454,6 +457,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long secs,
 			       unsigned long c_old,
 			       unsigned long c);
+void rcu_gp_set_torture_wait(int duration);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 					  int *flags, unsigned long *gp_seq)
@@ -471,6 +475,7 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 #define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
 	do { } while (0)
 #endif
+static inline void rcu_gp_set_torture_wait(int duration) { }
 #endif
 
 #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST)
@@ -498,6 +503,7 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 #endif
 
 #ifdef CONFIG_TINY_RCU
+static inline bool rcu_dynticks_zero_in_eqs(int cpu, int *vp) { return false; }
 static inline unsigned long rcu_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
 static inline unsigned long
@@ -507,6 +513,7 @@ static inline void show_rcu_gp_kthreads(void) { }
 static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 static inline void rcu_fwd_progress_check(unsigned long j) { }
 #else /* #ifdef CONFIG_TINY_RCU */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp);
 unsigned long rcu_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);

kernel/rcu/rcuperf.c

@@ -88,6 +88,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
 torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?");
+torture_param(int, kfree_mult, 1, "Multiple of kfree_obj size to allocate.");
 
 static char *perf_type = "rcu";
 module_param(perf_type, charp, 0444);
@@ -635,7 +636,7 @@ kfree_perf_thread(void *arg)
 		}
 
 		for (i = 0; i < kfree_alloc_num; i++) {
-			alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL);
+			alloc_ptr = kmalloc(kfree_mult * sizeof(struct kfree_obj), GFP_KERNEL);
 			if (!alloc_ptr)
 				return -ENOMEM;
 
@@ -722,6 +723,8 @@ kfree_perf_init(void)
 		schedule_timeout_uninterruptible(1);
 	}
 
+	pr_alert("kfree object size=%lu\n", kfree_mult * sizeof(struct kfree_obj));
+
 	kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]),
 			       GFP_KERNEL);
 	if (kfree_reader_tasks == NULL) {

kernel/rcu/rcutorture.c

@@ -20,7 +20,7 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/smp.h>
-#include <linux/rcupdate.h>
+#include <linux/rcupdate_wait.h>
 #include <linux/interrupt.h>
 #include <linux/sched/signal.h>
 #include <uapi/linux/sched/types.h>
@@ -45,12 +45,25 @@
 #include <linux/sched/sysctl.h>
 #include <linux/oom.h>
 #include <linux/tick.h>
+#include <linux/rcupdate_trace.h>
 
 #include "rcu.h"
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
 #define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
@@ -102,6 +115,9 @@ 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, stall_cpu_block, 0, "Sleep while stalling.");
+torture_param(int, stall_gp_kthread, 0,
+	      "Grace-period kthread stall duration (s).");
 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");
@@ -665,6 +681,11 @@ static void rcu_tasks_torture_deferred_free(struct rcu_torture *p)
 	call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb);
 }
 
+static void synchronize_rcu_mult_test(void)
+{
+	synchronize_rcu_mult(call_rcu_tasks, call_rcu);
+}
+
 static struct rcu_torture_ops tasks_ops = {
 	.ttype		= RCU_TASKS_FLAVOR,
 	.init		= rcu_sync_torture_init,
@@ -674,7 +695,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
-	.exp_sync	= synchronize_rcu_tasks,
+	.exp_sync	= synchronize_rcu_mult_test,
 	.call		= call_rcu_tasks,
 	.cb_barrier	= rcu_barrier_tasks,
 	.fqs		= NULL,
@@ -725,6 +746,72 @@ static struct rcu_torture_ops trivial_ops = {
 	.name		= "trivial"
 };
 
+/*
+ * Definitions for rude RCU-tasks torture testing.
+ */
+
+static void rcu_tasks_rude_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks_rude(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_rude_ops = {
+	.ttype		= RCU_TASKS_RUDE_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= rcu_torture_read_lock_trivial,
+	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
+	.readunlock	= rcu_torture_read_unlock_trivial,
+	.get_gp_seq	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_rude_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks_rude,
+	.exp_sync	= synchronize_rcu_tasks_rude,
+	.call		= call_rcu_tasks_rude,
+	.cb_barrier	= rcu_barrier_tasks_rude,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.name		= "tasks-rude"
+};
+
+/*
+ * Definitions for tracing RCU-tasks torture testing.
+ */
+
+static int tasks_tracing_torture_read_lock(void)
+{
+	rcu_read_lock_trace();
+	return 0;
+}
+
+static void tasks_tracing_torture_read_unlock(int idx)
+{
+	rcu_read_unlock_trace();
+}
+
+static void rcu_tasks_tracing_torture_deferred_free(struct rcu_torture *p)
+{
+	call_rcu_tasks_trace(&p->rtort_rcu, rcu_torture_cb);
+}
+
+static struct rcu_torture_ops tasks_tracing_ops = {
+	.ttype		= RCU_TASKS_TRACING_FLAVOR,
+	.init		= rcu_sync_torture_init,
+	.readlock	= tasks_tracing_torture_read_lock,
+	.read_delay	= srcu_read_delay,  /* just reuse srcu's version. */
+	.readunlock	= tasks_tracing_torture_read_unlock,
+	.get_gp_seq	= rcu_no_completed,
+	.deferred_free	= rcu_tasks_tracing_torture_deferred_free,
+	.sync		= synchronize_rcu_tasks_trace,
+	.exp_sync	= synchronize_rcu_tasks_trace,
+	.call		= call_rcu_tasks_trace,
+	.cb_barrier	= rcu_barrier_tasks_trace,
+	.fqs		= NULL,
+	.stats		= NULL,
+	.irq_capable	= 1,
+	.slow_gps	= 1,
+	.name		= "tasks-tracing"
+};
+
 static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
 {
 	if (!cur_ops->gp_diff)
@@ -734,7 +821,7 @@ static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
 
 static bool __maybe_unused torturing_tasks(void)
 {
-	return cur_ops == &tasks_ops;
+	return cur_ops == &tasks_ops || cur_ops == &tasks_rude_ops;
 }
 
 /*
@@ -833,7 +920,7 @@ static int rcu_torture_boost(void *arg)
 
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
-		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
+		while (time_before(jiffies, oldstarttime)) {
 			schedule_timeout_interruptible(oldstarttime - jiffies);
 			stutter_wait("rcu_torture_boost");
 			if (torture_must_stop())
@@ -843,7 +930,7 @@ static int rcu_torture_boost(void *arg)
 		/* Do one boost-test interval. */
 		endtime = oldstarttime + test_boost_duration * HZ;
 		call_rcu_time = jiffies;
-		while (ULONG_CMP_LT(jiffies, endtime)) {
+		while (time_before(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
 			if (!smp_load_acquire(&rbi.inflight)) {
 				/* RCU core before ->inflight = 1. */
@@ -914,7 +1001,7 @@ rcu_torture_fqs(void *arg)
 	VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
 	do {
 		fqs_resume_time = jiffies + fqs_stutter * HZ;
-		while (ULONG_CMP_LT(jiffies, fqs_resume_time) &&
+		while (time_before(jiffies, fqs_resume_time) &&
 		       !kthread_should_stop()) {
 			schedule_timeout_interruptible(1);
 		}
@@ -1147,6 +1234,7 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 				  struct torture_random_state *trsp,
 				  struct rt_read_seg *rtrsp)
 {
+	unsigned long flags;
 	int idxnew = -1;
 	int idxold = *readstate;
 	int statesnew = ~*readstate & newstate;
@@ -1181,8 +1269,15 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		rcu_read_unlock_bh();
 	if (statesold & RCUTORTURE_RDR_SCHED)
 		rcu_read_unlock_sched();
-	if (statesold & RCUTORTURE_RDR_RCU)
+	if (statesold & RCUTORTURE_RDR_RCU) {
+		bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
+
+		if (lockit)
+			raw_spin_lock_irqsave(&current->pi_lock, flags);
 		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+		if (lockit)
+			raw_spin_unlock_irqrestore(&current->pi_lock, flags);
+	}
 
 	/* Delay if neither beginning nor end and there was a change. */
 	if ((statesnew || statesold) && *readstate && newstate)
@@ -1283,6 +1378,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
 				  srcu_read_lock_held(srcu_ctlp) ||
+				  rcu_read_lock_trace_held() ||
 				  torturing_tasks());
 	if (p == NULL) {
 		/* Wait for rcu_torture_writer to get underway */
@@ -1444,9 +1540,9 @@ rcu_torture_stats_print(void)
 		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
 	pr_cont("barrier: %ld/%ld:%ld\n",
-		n_barrier_successes,
-		n_barrier_attempts,
-		n_rcu_torture_barrier_error);
+		data_race(n_barrier_successes),
+		data_race(n_barrier_attempts),
+		data_race(n_rcu_torture_barrier_error));
 
 	pr_alert("%s%s ", torture_type, TORTURE_FLAG);
 	if (atomic_read(&n_rcu_torture_mberror) ||
@@ -1536,6 +1632,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "test_boost=%d/%d test_boost_interval=%d "
 		 "test_boost_duration=%d shutdown_secs=%d "
 		 "stall_cpu=%d stall_cpu_holdoff=%d stall_cpu_irqsoff=%d "
+		 "stall_cpu_block=%d "
 		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
@@ -1544,6 +1641,7 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 test_boost, cur_ops->can_boost,
 		 test_boost_interval, test_boost_duration, shutdown_secs,
 		 stall_cpu, stall_cpu_holdoff, stall_cpu_irqsoff,
+		 stall_cpu_block,
 		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff);
 }
@@ -1599,6 +1697,7 @@ static int rcutorture_booster_init(unsigned int cpu)
  */
 static int rcu_torture_stall(void *args)
 {
+	int idx;
 	unsigned long stop_at;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
@@ -1607,26 +1706,37 @@ static int rcu_torture_stall(void *args)
 		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
 		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
 	}
-	if (!kthread_should_stop()) {
+	if (!kthread_should_stop() && stall_gp_kthread > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin GP stall");
+		rcu_gp_set_torture_wait(stall_gp_kthread * HZ);
+		for (idx = 0; idx < stall_gp_kthread + 2; idx++) {
+			if (kthread_should_stop())
+				break;
+			schedule_timeout_uninterruptible(HZ);
+		}
+	}
+	if (!kthread_should_stop() && stall_cpu > 0) {
+		VERBOSE_TOROUT_STRING("rcu_torture_stall begin CPU stall");
 		stop_at = ktime_get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
-		rcu_read_lock();
+		idx = cur_ops->readlock();
 		if (stall_cpu_irqsoff)
 			local_irq_disable();
-		else
+		else if (!stall_cpu_block)
 			preempt_disable();
 		pr_alert("rcu_torture_stall start on CPU %d.\n",
-			 smp_processor_id());
+			 raw_smp_processor_id());
 		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
 				    stop_at))
-			continue;  /* Induce RCU CPU stall warning. */
+			if (stall_cpu_block)
+				schedule_timeout_uninterruptible(HZ);
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
-		else
+		else if (!stall_cpu_block)
 			preempt_enable();
-		rcu_read_unlock();
-		pr_alert("rcu_torture_stall end.\n");
+		cur_ops->readunlock(idx);
 	}
+	pr_alert("rcu_torture_stall end.\n");
 	torture_shutdown_absorb("rcu_torture_stall");
 	while (!kthread_should_stop())
 		schedule_timeout_interruptible(10 * HZ);
@@ -1636,7 +1746,7 @@ static int rcu_torture_stall(void *args)
 /* Spawn CPU-stall kthread, if stall_cpu specified. */
 static int __init rcu_torture_stall_init(void)
 {
-	if (stall_cpu <= 0)
+	if (stall_cpu <= 0 && stall_gp_kthread <= 0)
 		return 0;
 	return torture_create_kthread(rcu_torture_stall, NULL, stall_task);
 }
@@ -1692,8 +1802,8 @@ struct rcu_fwd {
 	unsigned long rcu_launder_gp_seq_start;
 };
 
-struct rcu_fwd *rcu_fwds;
-bool rcu_fwd_emergency_stop;
+static struct rcu_fwd *rcu_fwds;
+static bool rcu_fwd_emergency_stop;
 
 static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 {
@@ -2400,7 +2510,8 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&busted_srcud_ops, &tasks_ops, &trivial_ops,
+		&busted_srcud_ops, &tasks_ops, &tasks_rude_ops,
+		&tasks_tracing_ops, &trivial_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose))

kernel/rcu/tree.c

@@ -238,7 +238,9 @@ void rcu_softirq_qs(void)
 
 /*
  * Record entry into an extended quiescent state.  This is only to be
- * called when not already in an extended quiescent state.
+ * called when not already in an extended quiescent state, that is,
+ * RCU is watching prior to the call to this function and is no longer
+ * watching upon return.
  */
 static void rcu_dynticks_eqs_enter(void)
 {
@@ -250,8 +252,9 @@ static void rcu_dynticks_eqs_enter(void)
 	 * critical sections, and we also must force ordering with the
 	 * next idle sojourn.
 	 */
+	rcu_dynticks_task_trace_enter();  // Before ->dynticks update!
 	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
-	/* Better be in an extended quiescent state! */
+	// RCU is no longer watching.  Better be in extended quiescent state!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     (seq & RCU_DYNTICK_CTRL_CTR));
 	/* Better not have special action (TLB flush) pending! */
@@ -261,7 +264,8 @@ static void rcu_dynticks_eqs_enter(void)
 
 /*
  * Record exit from an extended quiescent state.  This is only to be
- * called from an extended quiescent state.
+ * called from an extended quiescent state, that is, RCU is not watching
+ * prior to the call to this function and is watching upon return.
  */
 static void rcu_dynticks_eqs_exit(void)
 {
@@ -274,6 +278,8 @@ static void rcu_dynticks_eqs_exit(void)
 	 * critical section.
 	 */
 	seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks);
+	// RCU is now watching.  Better not be in an extended quiescent state!
+	rcu_dynticks_task_trace_exit();  // After ->dynticks update!
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     !(seq & RCU_DYNTICK_CTRL_CTR));
 	if (seq & RCU_DYNTICK_CTRL_MASK) {
@@ -345,6 +351,28 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap)
 	return snap != rcu_dynticks_snap(rdp);
 }
 
+/*
+ * Return true if the referenced integer is zero while the specified
+ * CPU remains within a single extended quiescent state.
+ */
+bool rcu_dynticks_zero_in_eqs(int cpu, int *vp)
+{
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	int snap;
+
+	// If not quiescent, force back to earlier extended quiescent state.
+	snap = atomic_read(&rdp->dynticks) & ~(RCU_DYNTICK_CTRL_MASK |
+					       RCU_DYNTICK_CTRL_CTR);
+
+	smp_rmb(); // Order ->dynticks and *vp reads.
+	if (READ_ONCE(*vp))
+		return false;  // Non-zero, so report failure;
+	smp_rmb(); // Order *vp read and ->dynticks re-read.
+
+	// If still in the same extended quiescent state, we are good!
+	return snap == (atomic_read(&rdp->dynticks) & ~RCU_DYNTICK_CTRL_MASK);
+}
+
 /*
  * Set the special (bottom) bit of the specified CPU so that it
  * will take special action (such as flushing its TLB) on the
@@ -584,6 +612,7 @@ static void rcu_eqs_enter(bool user)
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
 		     rdp->dynticks_nesting == 0);
 	if (rdp->dynticks_nesting != 1) {
+		// RCU will still be watching, so just do accounting and leave.
 		rdp->dynticks_nesting--;
 		return;
 	}
@@ -596,7 +625,9 @@ static void rcu_eqs_enter(bool user)
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 	WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */
+	// RCU is watching here ...
 	rcu_dynticks_eqs_enter();
+	// ... but is no longer watching here.
 	rcu_dynticks_task_enter();
 }
 
@@ -676,7 +707,9 @@ static __always_inline void rcu_nmi_exit_common(bool irq)
 	if (irq)
 		rcu_prepare_for_idle();
 
+	// RCU is watching here ...
 	rcu_dynticks_eqs_enter();
+	// ... but is no longer watching here.
 
 	if (irq)
 		rcu_dynticks_task_enter();
@@ -751,11 +784,14 @@ static void rcu_eqs_exit(bool user)
 	oldval = rdp->dynticks_nesting;
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
 	if (oldval) {
+		// RCU was already watching, so just do accounting and leave.
 		rdp->dynticks_nesting++;
 		return;
 	}
 	rcu_dynticks_task_exit();
+	// RCU is not watching here ...
 	rcu_dynticks_eqs_exit();
+	// ... but is watching here.
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
@@ -832,7 +868,9 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 		if (irq)
 			rcu_dynticks_task_exit();
 
+		// RCU is not watching here ...
 		rcu_dynticks_eqs_exit();
+		// ... but is watching here.
 
 		if (irq)
 			rcu_cleanup_after_idle();
@@ -842,9 +880,16 @@ static __always_inline void rcu_nmi_enter_common(bool irq)
 		   rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE &&
 		   READ_ONCE(rdp->rcu_urgent_qs) &&
 		   !READ_ONCE(rdp->rcu_forced_tick)) {
+		// We get here only if we had already exited the extended
+		// quiescent state and this was an interrupt (not an NMI).
+		// Therefore, (1) RCU is already watching and (2) The fact
+		// that we are in an interrupt handler and that the rcu_node
+		// lock is an irq-disabled lock prevents self-deadlock.
+		// So we can safely recheck under the lock.
 		raw_spin_lock_rcu_node(rdp->mynode);
-		// Recheck under lock.
 		if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) {
+			// A nohz_full CPU is in the kernel and RCU
+			// needs a quiescent state.  Turn on the tick!
 			WRITE_ONCE(rdp->rcu_forced_tick, true);
 			tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU);
 		}
@@ -1486,6 +1531,31 @@ static void rcu_gp_slow(int delay)
 		schedule_timeout_uninterruptible(delay);
 }
 
+static unsigned long sleep_duration;
+
+/* Allow rcutorture to stall the grace-period kthread. */
+void rcu_gp_set_torture_wait(int duration)
+{
+	if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST) && duration > 0)
+		WRITE_ONCE(sleep_duration, duration);
+}
+EXPORT_SYMBOL_GPL(rcu_gp_set_torture_wait);
+
+/* Actually implement the aforementioned wait. */
+static void rcu_gp_torture_wait(void)
+{
+	unsigned long duration;
+
+	if (!IS_ENABLED(CONFIG_RCU_TORTURE_TEST))
+		return;
+	duration = xchg(&sleep_duration, 0UL);
+	if (duration > 0) {
+		pr_alert("%s: Waiting %lu jiffies\n", __func__, duration);
+		schedule_timeout_uninterruptible(duration);
+		pr_alert("%s: Wait complete\n", __func__);
+	}
+}
+
 /*
  * Initialize a new grace period.  Return false if no grace period required.
  */
@@ -1693,6 +1763,7 @@ static void rcu_gp_fqs_loop(void)
 		rcu_state.gp_state = RCU_GP_WAIT_FQS;
 		ret = swait_event_idle_timeout_exclusive(
 				rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j);
+		rcu_gp_torture_wait();
 		rcu_state.gp_state = RCU_GP_DOING_FQS;
 		/* Locking provides needed memory barriers. */
 		/* If grace period done, leave loop. */
@@ -1847,6 +1918,7 @@ static int __noreturn rcu_gp_kthread(void *unused)
 			swait_event_idle_exclusive(rcu_state.gp_wq,
 					 READ_ONCE(rcu_state.gp_flags) &
 					 RCU_GP_FLAG_INIT);
+			rcu_gp_torture_wait();
 			rcu_state.gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init())
@@ -2837,6 +2909,8 @@ struct kfree_rcu_cpu {
 	struct delayed_work monitor_work;
 	bool monitor_todo;
 	bool initialized;
+	// Number of objects for which GP not started
+	int count;
 };
 
 static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc);
@@ -2950,6 +3024,8 @@ static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp)
 				krcp->head = NULL;
 			}
 
+			WRITE_ONCE(krcp->count, 0);
+
 			/*
 			 * One work is per one batch, so there are two "free channels",
 			 * "bhead_free" and "head_free" the batch can handle. It can be
@@ -3086,6 +3162,8 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		krcp->head = head;
 	}
 
+	WRITE_ONCE(krcp->count, krcp->count + 1);
+
 	// Set timer to drain after KFREE_DRAIN_JIFFIES.
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 	    !krcp->monitor_todo) {
@@ -3100,6 +3178,56 @@ unlock_return:
 }
 EXPORT_SYMBOL_GPL(kfree_call_rcu);
 
+static unsigned long
+kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu;
+	unsigned long count = 0;
+
+	/* Snapshot count of all CPUs */
+	for_each_online_cpu(cpu) {
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count += READ_ONCE(krcp->count);
+	}
+
+	return count;
+}
+
+static unsigned long
+kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
+{
+	int cpu, freed = 0;
+	unsigned long flags;
+
+	for_each_online_cpu(cpu) {
+		int count;
+		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
+
+		count = krcp->count;
+		spin_lock_irqsave(&krcp->lock, flags);
+		if (krcp->monitor_todo)
+			kfree_rcu_drain_unlock(krcp, flags);
+		else
+			spin_unlock_irqrestore(&krcp->lock, flags);
+
+		sc->nr_to_scan -= count;
+		freed += count;
+
+		if (sc->nr_to_scan <= 0)
+			break;
+	}
+
+	return freed;
+}
+
+static struct shrinker kfree_rcu_shrinker = {
+	.count_objects = kfree_rcu_shrink_count,
+	.scan_objects = kfree_rcu_shrink_scan,
+	.batch = 0,
+	.seeks = DEFAULT_SEEKS,
+};
+
 void __init kfree_rcu_scheduler_running(void)
 {
 	int cpu;
@@ -4021,6 +4149,8 @@ static void __init kfree_rcu_batch_init(void)
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
 		krcp->initialized = true;
 	}
+	if (register_shrinker(&kfree_rcu_shrinker))
+		pr_err("Failed to register kfree_rcu() shrinker!\n");
 }
 
 void __init rcu_init(void)

kernel/rcu/tree.h

@@ -455,6 +455,8 @@ static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
+static void rcu_dynticks_task_trace_enter(void);
+static void rcu_dynticks_task_trace_exit(void);
 
 /* Forward declarations for tree_stall.h */
 static void record_gp_stall_check_time(void);

kernel/rcu/tree_exp.h

@@ -639,6 +639,7 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
  */
 static void rcu_exp_handler(void *unused)
 {
+	int depth = rcu_preempt_depth();
 	unsigned long flags;
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
@@ -649,7 +650,7 @@ static void rcu_exp_handler(void *unused)
 	 * critical section.  If also enabled or idle, immediately
 	 * report the quiescent state, otherwise defer.
 	 */
-	if (!rcu_preempt_depth()) {
+	if (!depth) {
 		if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
@@ -673,7 +674,7 @@ static void rcu_exp_handler(void *unused)
 	 * can have caused this quiescent state to already have been
 	 * reported, so we really do need to check ->expmask.
 	 */
-	if (rcu_preempt_depth() > 0) {
+	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
 			rdp->exp_deferred_qs = true;
@@ -683,30 +684,8 @@ static void rcu_exp_handler(void *unused)
 		return;
 	}
 
-	/*
-	 * The final and least likely case is where the interrupted
-	 * code was just about to or just finished exiting the RCU-preempt
-	 * read-side critical section, and no, we can't tell which.
-	 * So either way, set ->deferred_qs to flag later code that
-	 * a quiescent state is required.
-	 *
-	 * If the CPU is fully enabled (or if some buggy RCU-preempt
-	 * read-side critical section is being used from idle), just
-	 * invoke rcu_preempt_deferred_qs() to immediately report the
-	 * quiescent state.  We cannot use rcu_read_unlock_special()
-	 * because we are in an interrupt handler, which will cause that
-	 * function to take an early exit without doing anything.
-	 *
-	 * Otherwise, force a context switch after the CPU enables everything.
-	 */
-	rdp->exp_deferred_qs = true;
-	if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
-	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
-		rcu_preempt_deferred_qs(t);
-	} else {
-		set_tsk_need_resched(t);
-		set_preempt_need_resched();
-	}
+	// Finally, negative nesting depth should not happen.
+	WARN_ON_ONCE(1);
 }
 
 /* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */

kernel/rcu/tree_plugin.h

@@ -331,6 +331,7 @@ void rcu_note_context_switch(bool preempt)
 	rcu_qs();
 	if (rdp->exp_deferred_qs)
 		rcu_report_exp_rdp(rdp);
+	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
@@ -345,9 +346,7 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp)
 	return READ_ONCE(rnp->gp_tasks) != NULL;
 }
 
-/* Bias and limit values for ->rcu_read_lock_nesting. */
-#define RCU_NEST_BIAS INT_MAX
-#define RCU_NEST_NMAX (-INT_MAX / 2)
+/* limit value for ->rcu_read_lock_nesting. */
 #define RCU_NEST_PMAX (INT_MAX / 2)
 
 static void rcu_preempt_read_enter(void)
@@ -355,9 +354,9 @@ static void rcu_preempt_read_enter(void)
 	current->rcu_read_lock_nesting++;
 }
 
-static void rcu_preempt_read_exit(void)
+static int rcu_preempt_read_exit(void)
 {
-	current->rcu_read_lock_nesting--;
+	return --current->rcu_read_lock_nesting;
 }
 
 static void rcu_preempt_depth_set(int val)
@@ -390,21 +389,15 @@ void __rcu_read_unlock(void)
 {
 	struct task_struct *t = current;
 
-	if (rcu_preempt_depth() != 1) {
-		rcu_preempt_read_exit();
-	} else {
+	if (rcu_preempt_read_exit() == 0) {
 		barrier();  /* critical section before exit code. */
-		rcu_preempt_depth_set(-RCU_NEST_BIAS);
-		barrier();  /* assign before ->rcu_read_unlock_special load */
 		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
-		barrier();  /* ->rcu_read_unlock_special load before assign */
-		rcu_preempt_depth_set(0);
 	}
 	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
 		int rrln = rcu_preempt_depth();
 
-		WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX);
+		WARN_ON_ONCE(rrln < 0 || rrln > RCU_NEST_PMAX);
 	}
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -556,7 +549,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
-	       rcu_preempt_depth() <= 0;
+	       rcu_preempt_depth() == 0;
 }
 
 /*
@@ -569,16 +562,11 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 static void rcu_preempt_deferred_qs(struct task_struct *t)
 {
 	unsigned long flags;
-	bool couldrecurse = rcu_preempt_depth() >= 0;
 
 	if (!rcu_preempt_need_deferred_qs(t))
 		return;
-	if (couldrecurse)
-		rcu_preempt_depth_set(rcu_preempt_depth() - RCU_NEST_BIAS);
 	local_irq_save(flags);
 	rcu_preempt_deferred_qs_irqrestore(t, flags);
-	if (couldrecurse)
-		rcu_preempt_depth_set(rcu_preempt_depth() + RCU_NEST_BIAS);
 }
 
 /*
@@ -615,19 +603,18 @@ static void rcu_read_unlock_special(struct task_struct *t)
 		struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 		struct rcu_node *rnp = rdp->mynode;
 
-		exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) ||
-		      (rdp->grpmask & READ_ONCE(rnp->expmask)) ||
-		      tick_nohz_full_cpu(rdp->cpu);
+		exp = (t->rcu_blocked_node &&
+		       READ_ONCE(t->rcu_blocked_node->exp_tasks)) ||
+		      (rdp->grpmask & READ_ONCE(rnp->expmask));
 		// Need to defer quiescent state until everything is enabled.
-		if (irqs_were_disabled && use_softirq &&
-		    (in_interrupt() ||
-		     (exp && !t->rcu_read_unlock_special.b.deferred_qs))) {
-			// Using softirq, safe to awaken, and we get
-			// no help from enabling irqs, unlike bh/preempt.
+		if (use_softirq && (in_irq() || (exp && !irqs_were_disabled))) {
+			// Using softirq, safe to awaken, and either the
+			// wakeup is free or there is an expedited GP.
 			raise_softirq_irqoff(RCU_SOFTIRQ);
 		} else {
 			// Enabling BH or preempt does reschedule, so...
-			// Also if no expediting or NO_HZ_FULL, slow is OK.
+			// Also if no expediting, slow is OK.
+			// Plus nohz_full CPUs eventually get tick enabled.
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
@@ -640,7 +627,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 				irq_work_queue_on(&rdp->defer_qs_iw, rdp->cpu);
 			}
 		}
-		t->rcu_read_unlock_special.b.deferred_qs = true;
 		local_irq_restore(flags);
 		return;
 	}
@@ -699,7 +685,7 @@ static void rcu_flavor_sched_clock_irq(int user)
 	} else if (rcu_preempt_need_deferred_qs(t)) {
 		rcu_preempt_deferred_qs(t); /* Report deferred QS. */
 		return;
-	} else if (!rcu_preempt_depth()) {
+	} else if (!WARN_ON_ONCE(rcu_preempt_depth())) {
 		rcu_qs(); /* Report immediate QS. */
 		return;
 	}
@@ -854,8 +840,7 @@ void rcu_note_context_switch(bool preempt)
 	this_cpu_write(rcu_data.rcu_urgent_qs, false);
 	if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs)))
 		rcu_momentary_dyntick_idle();
-	if (!preempt)
-		rcu_tasks_qs(current);
+	rcu_tasks_qs(current, preempt);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 }
@@ -2568,3 +2553,21 @@ static void rcu_dynticks_task_exit(void)
 	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
+
+/* Turn on heavyweight RCU tasks trace readers on idle/user entry. */
+static void rcu_dynticks_task_trace_enter(void)
+{
+#ifdef CONFIG_TASKS_RCU_TRACE
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+		current->trc_reader_special.b.need_mb = true;
+#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
+}
+
+/* Turn off heavyweight RCU tasks trace readers on idle/user exit. */
+static void rcu_dynticks_task_trace_exit(void)
+{
+#ifdef CONFIG_TASKS_RCU_TRACE
+	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB))
+		current->trc_reader_special.b.need_mb = false;
+#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */
+}

kernel/rcu/tree_stall.h

@@ -15,10 +15,12 @@
 int sysctl_panic_on_rcu_stall __read_mostly;
 
 #ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#define RCU_STALL_DELAY_DELTA		(5 * HZ)
 #else
-#define RCU_STALL_DELAY_DELTA	       0
+#define RCU_STALL_DELAY_DELTA		0
 #endif
+#define RCU_STALL_MIGHT_DIV		8
+#define RCU_STALL_MIGHT_MIN		(2 * HZ)
 
 /* Limit-check stall timeouts specified at boottime and runtime. */
 int rcu_jiffies_till_stall_check(void)
@@ -40,6 +42,36 @@ int rcu_jiffies_till_stall_check(void)
 }
 EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
 
+/**
+ * rcu_gp_might_be_stalled - Is it likely that the grace period is stalled?
+ *
+ * Returns @true if the current grace period is sufficiently old that
+ * it is reasonable to assume that it might be stalled.  This can be
+ * useful when deciding whether to allocate memory to enable RCU-mediated
+ * freeing on the one hand or just invoking synchronize_rcu() on the other.
+ * The latter is preferable when the grace period is stalled.
+ *
+ * Note that sampling of the .gp_start and .gp_seq fields must be done
+ * carefully to avoid false positives at the beginnings and ends of
+ * grace periods.
+ */
+bool rcu_gp_might_be_stalled(void)
+{
+	unsigned long d = rcu_jiffies_till_stall_check() / RCU_STALL_MIGHT_DIV;
+	unsigned long j = jiffies;
+
+	if (d < RCU_STALL_MIGHT_MIN)
+		d = RCU_STALL_MIGHT_MIN;
+	smp_mb(); // jiffies before .gp_seq to avoid false positives.
+	if (!rcu_gp_in_progress())
+		return false;
+	// Long delays at this point avoids false positive, but a delay
+	// of ULONG_MAX/4 jiffies voids your no-false-positive warranty.
+	smp_mb(); // .gp_seq before second .gp_start
+	// And ditto here.
+	return !time_before(j, READ_ONCE(rcu_state.gp_start) + d);
+}
+
 /* Don't do RCU CPU stall warnings during long sysrq printouts. */
 void rcu_sysrq_start(void)
 {
@@ -104,8 +136,8 @@ static void record_gp_stall_check_time(void)
 
 	WRITE_ONCE(rcu_state.gp_start, j);
 	j1 = rcu_jiffies_till_stall_check();
-	/* Record ->gp_start before ->jiffies_stall. */
-	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+	smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq.
+	WRITE_ONCE(rcu_state.jiffies_stall, j + j1);
 	rcu_state.jiffies_resched = j + j1 / 2;
 	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
 }
@@ -192,14 +224,40 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
+// Communicate task state back to the RCU CPU stall warning request.
+struct rcu_stall_chk_rdr {
+	int nesting;
+	union rcu_special rs;
+	bool on_blkd_list;
+};
+
+/*
+ * Report out the state of a not-running task that is stalling the
+ * current RCU grace period.
+ */
+static bool check_slow_task(struct task_struct *t, void *arg)
+{
+	struct rcu_node *rnp;
+	struct rcu_stall_chk_rdr *rscrp = arg;
+
+	if (task_curr(t))
+		return false; // It is running, so decline to inspect it.
+	rscrp->nesting = t->rcu_read_lock_nesting;
+	rscrp->rs = t->rcu_read_unlock_special;
+	rnp = t->rcu_blocked_node;
+	rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry);
+	return true;
+}
+
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
  * sections, printing out the tid of each.
  */
 static int rcu_print_task_stall(struct rcu_node *rnp)
 {
-	struct task_struct *t;
 	int ndetected = 0;
+	struct rcu_stall_chk_rdr rscr;
+	struct task_struct *t;
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
@@ -208,7 +266,15 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
+		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
+			pr_cont(" P%d", t->pid);
+		else
+			pr_cont(" P%d/%d:%c%c%c%c",
+				t->pid, rscr.nesting,
+				".b"[rscr.rs.b.blocked],
+				".q"[rscr.rs.b.need_qs],
+				".e"[rscr.rs.b.exp_hint],
+				".l"[rscr.on_blkd_list]);
 		ndetected++;
 	}
 	pr_cont("\n");
@@ -299,6 +365,16 @@ static const char *gp_state_getname(short gs)
 	return gp_state_names[gs];
 }
 
+/* Is the RCU grace-period kthread being starved of CPU time? */
+static bool rcu_is_gp_kthread_starving(unsigned long *jp)
+{
+	unsigned long j = jiffies - READ_ONCE(rcu_state.gp_activity);
+
+	if (jp)
+		*jp = j;
+	return j > 2 * HZ;
+}
+
 /*
  * Print out diagnostic information for the specified stalled CPU.
  *
@@ -313,6 +389,7 @@ static const char *gp_state_getname(short gs)
 static void print_cpu_stall_info(int cpu)
 {
 	unsigned long delta;
+	bool falsepositive;
 	char fast_no_hz[72];
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	char *ticks_title;
@@ -333,7 +410,9 @@ static void print_cpu_stall_info(int cpu)
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+	falsepositive = rcu_is_gp_kthread_starving(NULL) &&
+			rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s%s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -345,8 +424,9 @@ static void print_cpu_stall_info(int cpu)
 	       rcu_dynticks_snap(rdp) & 0xfff,
 	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz);
+	       data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+	       fast_no_hz,
+	       falsepositive ? " (false positive?)" : "");
 }
 
 /* Complain about starvation of grace-period kthread.  */
@@ -355,8 +435,7 @@ static void rcu_check_gp_kthread_starvation(void)
 	struct task_struct *gpk = rcu_state.gp_kthread;
 	unsigned long j;
 
-	j = jiffies - READ_ONCE(rcu_state.gp_activity);
-	if (j > 2 * HZ) {
+	if (rcu_is_gp_kthread_starving(&j)) {
 		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rcu_state.name, j,
 		       (long)rcu_seq_current(&rcu_state.gp_seq),
@@ -364,6 +443,7 @@ static void rcu_check_gp_kthread_starvation(void)
 		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
 		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
 		if (gpk) {
+			pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name);
 			pr_err("RCU grace-period kthread stack dump:\n");
 			sched_show_task(gpk);
 			wake_up_process(gpk);
@@ -426,8 +506,6 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 			       rcu_state.name, j - gpa, j, gpa,
 			       data_race(jiffies_till_next_fqs),
 			       rcu_get_root()->qsmask);
-			/* In this case, the current CPU might be at fault. */
-			sched_show_task(current);
 		}
 	}
 	/* Rewrite if needed in case of slow consoles. */
@@ -615,7 +693,7 @@ void show_rcu_gp_kthreads(void)
 		if (rcu_segcblist_is_offloaded(&rdp->cblist))
 			show_rcu_nocb_state(rdp);
 	}
-	/* sched_show_task(rcu_state.gp_kthread); */
+	show_rcu_tasks_gp_kthreads();
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
 

kernel/rcu/update.c

@@ -41,6 +41,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/kprobes.h>
 #include <linux/slab.h>
+#include <linux/irq_work.h>
 
 #define CREATE_TRACE_POINTS
 
@@ -51,6 +52,19 @@
 #endif
 #define MODULE_PARAM_PREFIX "rcupdate."
 
+#ifndef data_race
+#define data_race(expr)							\
+	({								\
+		expr;							\
+	})
+#endif
+#ifndef ASSERT_EXCLUSIVE_WRITER
+#define ASSERT_EXCLUSIVE_WRITER(var) do { } while (0)
+#endif
+#ifndef ASSERT_EXCLUSIVE_ACCESS
+#define ASSERT_EXCLUSIVE_ACCESS(var) do { } while (0)
+#endif
+
 #ifndef CONFIG_TINY_RCU
 module_param(rcu_expedited, int, 0);
 module_param(rcu_normal, int, 0);
@@ -501,370 +515,6 @@ int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls.
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress_at_boot);
 module_param(rcu_cpu_stall_suppress_at_boot, int, 0444);
 
-#ifdef CONFIG_TASKS_RCU
-
-/*
- * Simple variant of RCU whose quiescent states are voluntary context
- * switch, cond_resched_rcu_qs(), user-space execution, and idle.
- * As such, grace periods can take one good long time.  There are no
- * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
- * because this implementation is intended to get the system into a safe
- * state for some of the manipulations involved in tracing and the like.
- * Finally, this implementation does not support high call_rcu_tasks()
- * rates from multiple CPUs.  If this is required, per-CPU callback lists
- * will be needed.
- */
-
-/* Global list of callbacks and associated lock. */
-static struct rcu_head *rcu_tasks_cbs_head;
-static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);
-static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock);
-
-/* Track exiting tasks in order to allow them to be waited for. */
-DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
-
-/* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
-#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
-static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
-module_param(rcu_task_stall_timeout, int, 0644);
-
-static struct task_struct *rcu_tasks_kthread_ptr;
-
-/**
- * call_rcu_tasks() - Queue an RCU for invocation task-based grace period
- * @rhp: structure to be used for queueing the RCU updates.
- * @func: actual callback function to be invoked after the grace period
- *
- * The callback function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed. call_rcu_tasks() assumes
- * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
- * or transition to usermode execution.  As such, there are no read-side
- * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
- * this primitive is intended to determine that all tasks have passed
- * through a safe state, not so much for data-strcuture synchronization.
- *
- * See the description of call_rcu() for more detailed information on
- * memory ordering guarantees.
- */
-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
-{
-	unsigned long flags;
-	bool needwake;
-
-	rhp->next = NULL;
-	rhp->func = func;
-	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
-	needwake = !rcu_tasks_cbs_head;
-	WRITE_ONCE(*rcu_tasks_cbs_tail, rhp);
-	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 && READ_ONCE(rcu_tasks_kthread_ptr))
-		wake_up(&rcu_tasks_cbs_wq);
-}
-EXPORT_SYMBOL_GPL(call_rcu_tasks);
-
-/**
- * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed.
- *
- * Control will return to the caller some time after a full rcu-tasks
- * grace period has elapsed, in other words after all currently
- * executing rcu-tasks read-side critical sections have elapsed.  These
- * read-side critical sections are delimited by calls to schedule(),
- * cond_resched_tasks_rcu_qs(), idle execution, userspace execution, calls
- * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched().
- *
- * This is a very specialized primitive, intended only for a few uses in
- * tracing and other situations requiring manipulation of function
- * preambles and profiling hooks.  The synchronize_rcu_tasks() function
- * is not (yet) intended for heavy use from multiple CPUs.
- *
- * Note that this guarantee implies further memory-ordering guarantees.
- * On systems with more than one CPU, when synchronize_rcu_tasks() returns,
- * each CPU is guaranteed to have executed a full memory barrier since the
- * end of its last RCU-tasks read-side critical section whose beginning
- * preceded the call to synchronize_rcu_tasks().  In addition, each CPU
- * having an RCU-tasks read-side critical section that extends beyond
- * the return from synchronize_rcu_tasks() is guaranteed to have executed
- * a full memory barrier after the beginning of synchronize_rcu_tasks()
- * and before the beginning of that RCU-tasks read-side critical section.
- * Note that these guarantees include CPUs that are offline, idle, or
- * executing in user mode, as well as CPUs that are executing in the kernel.
- *
- * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned
- * to its caller on CPU B, then both CPU A and CPU B are guaranteed
- * to have executed a full memory barrier during the execution of
- * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU
- * (but again only if the system has more than one CPU).
- */
-void synchronize_rcu_tasks(void)
-{
-	/* Complain if the scheduler has not started.  */
-	RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE,
-			 "synchronize_rcu_tasks called too soon");
-
-	/* Wait for the grace period. */
-	wait_rcu_gp(call_rcu_tasks);
-}
-EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
-
-/**
- * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks.
- *
- * Although the current implementation is guaranteed to wait, it is not
- * obligated to, for example, if there are no pending callbacks.
- */
-void rcu_barrier_tasks(void)
-{
-	/* There is only one callback queue, so this is easy.  ;-) */
-	synchronize_rcu_tasks();
-}
-EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
-
-/* See if tasks are still holding out, complain if so. */
-static void check_holdout_task(struct task_struct *t,
-			       bool needreport, bool *firstreport)
-{
-	int cpu;
-
-	if (!READ_ONCE(t->rcu_tasks_holdout) ||
-	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
-	    !READ_ONCE(t->on_rq) ||
-	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
-	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
-		WRITE_ONCE(t->rcu_tasks_holdout, false);
-		list_del_init(&t->rcu_tasks_holdout_list);
-		put_task_struct(t);
-		return;
-	}
-	rcu_request_urgent_qs_task(t);
-	if (!needreport)
-		return;
-	if (*firstreport) {
-		pr_err("INFO: rcu_tasks detected stalls on tasks:\n");
-		*firstreport = false;
-	}
-	cpu = task_cpu(t);
-	pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n",
-		 t, ".I"[is_idle_task(t)],
-		 "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)],
-		 t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout,
-		 t->rcu_tasks_idle_cpu, cpu);
-	sched_show_task(t);
-}
-
-/* RCU-tasks kthread that detects grace periods and invokes callbacks. */
-static int __noreturn rcu_tasks_kthread(void *arg)
-{
-	unsigned long flags;
-	struct task_struct *g, *t;
-	unsigned long lastreport;
-	struct rcu_head *list;
-	struct rcu_head *next;
-	LIST_HEAD(rcu_tasks_holdouts);
-	int fract;
-
-	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
-	housekeeping_affine(current, HK_FLAG_RCU);
-
-	/*
-	 * Each pass through the following loop makes one check for
-	 * newly arrived callbacks, and, if there are some, waits for
-	 * one RCU-tasks grace period and then invokes the callbacks.
-	 * This loop is terminated by the system going down.  ;-)
-	 */
-	for (;;) {
-
-		/* Pick up any new callbacks. */
-		raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);
-		list = rcu_tasks_cbs_head;
-		rcu_tasks_cbs_head = NULL;
-		rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;
-		raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
-
-		/* If there were none, wait a bit and start over. */
-		if (!list) {
-			wait_event_interruptible(rcu_tasks_cbs_wq,
-						 READ_ONCE(rcu_tasks_cbs_head));
-			if (!rcu_tasks_cbs_head) {
-				WARN_ON(signal_pending(current));
-				schedule_timeout_interruptible(HZ/10);
-			}
-			continue;
-		}
-
-		/*
-		 * Wait for all pre-existing t->on_rq and t->nvcsw
-		 * transitions to complete.  Invoking synchronize_rcu()
-		 * suffices because all these transitions occur with
-		 * interrupts disabled.  Without this synchronize_rcu(),
-		 * a read-side critical section that started before the
-		 * grace period might be incorrectly seen as having started
-		 * after the grace period.
-		 *
-		 * This synchronize_rcu() also dispenses with the
-		 * need for a memory barrier on the first store to
-		 * ->rcu_tasks_holdout, as it forces the store to happen
-		 * after the beginning of the grace period.
-		 */
-		synchronize_rcu();
-
-		/*
-		 * There were callbacks, so we need to wait for an
-		 * RCU-tasks grace period.  Start off by scanning
-		 * the task list for tasks that are not already
-		 * voluntarily blocked.  Mark these tasks and make
-		 * a list of them in rcu_tasks_holdouts.
-		 */
-		rcu_read_lock();
-		for_each_process_thread(g, t) {
-			if (t != current && READ_ONCE(t->on_rq) &&
-			    !is_idle_task(t)) {
-				get_task_struct(t);
-				t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
-				WRITE_ONCE(t->rcu_tasks_holdout, true);
-				list_add(&t->rcu_tasks_holdout_list,
-					 &rcu_tasks_holdouts);
-			}
-		}
-		rcu_read_unlock();
-
-		/*
-		 * Wait for tasks that are in the process of exiting.
-		 * This does only part of the job, ensuring that all
-		 * tasks that were previously exiting reach the point
-		 * where they have disabled preemption, allowing the
-		 * later synchronize_rcu() to finish the job.
-		 */
-		synchronize_srcu(&tasks_rcu_exit_srcu);
-
-		/*
-		 * Each pass through the following loop scans the list
-		 * of holdout tasks, removing any that are no longer
-		 * holdouts.  When the list is empty, we are done.
-		 */
-		lastreport = jiffies;
-
-		/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
-		fract = 10;
-
-		for (;;) {
-			bool firstreport;
-			bool needreport;
-			int rtst;
-			struct task_struct *t1;
-
-			if (list_empty(&rcu_tasks_holdouts))
-				break;
-
-			/* Slowly back off waiting for holdouts */
-			schedule_timeout_interruptible(HZ/fract);
-
-			if (fract > 1)
-				fract--;
-
-			rtst = READ_ONCE(rcu_task_stall_timeout);
-			needreport = rtst > 0 &&
-				     time_after(jiffies, lastreport + rtst);
-			if (needreport)
-				lastreport = jiffies;
-			firstreport = true;
-			WARN_ON(signal_pending(current));
-			list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts,
-						rcu_tasks_holdout_list) {
-				check_holdout_task(t, needreport, &firstreport);
-				cond_resched();
-			}
-		}
-
-		/*
-		 * Because ->on_rq and ->nvcsw are not guaranteed
-		 * to have a full memory barriers prior to them in the
-		 * schedule() path, memory reordering on other CPUs could
-		 * cause their RCU-tasks read-side critical sections to
-		 * extend past the end of the grace period.  However,
-		 * because these ->nvcsw updates are carried out with
-		 * interrupts disabled, we can use synchronize_rcu()
-		 * to force the needed ordering on all such CPUs.
-		 *
-		 * This synchronize_rcu() also confines all
-		 * ->rcu_tasks_holdout accesses to be within the grace
-		 * period, avoiding the need for memory barriers for
-		 * ->rcu_tasks_holdout accesses.
-		 *
-		 * In addition, this synchronize_rcu() waits for exiting
-		 * tasks to complete their final preempt_disable() region
-		 * of execution, cleaning up after the synchronize_srcu()
-		 * above.
-		 */
-		synchronize_rcu();
-
-		/* Invoke the callbacks. */
-		while (list) {
-			next = list->next;
-			local_bh_disable();
-			list->func(list);
-			local_bh_enable();
-			list = next;
-			cond_resched();
-		}
-		/* Paranoid sleep to keep this from entering a tight loop */
-		schedule_timeout_uninterruptible(HZ/10);
-	}
-}
-
-/* Spawn rcu_tasks_kthread() at core_initcall() time. */
-static int __init rcu_spawn_tasks_kthread(void)
-{
-	struct task_struct *t;
-
-	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
-	if (WARN_ONCE(IS_ERR(t), "%s: Could not start Tasks-RCU grace-period kthread, OOM is now expected behavior\n", __func__))
-		return 0;
-	smp_mb(); /* Ensure others see full kthread. */
-	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
-	return 0;
-}
-core_initcall(rcu_spawn_tasks_kthread);
-
-/* Do the srcu_read_lock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
-{
-	preempt_disable();
-	current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu);
-	preempt_enable();
-}
-
-/* Do the srcu_read_unlock() for the above synchronize_srcu().  */
-void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
-{
-	preempt_disable();
-	__srcu_read_unlock(&tasks_rcu_exit_srcu, current->rcu_tasks_idx);
-	preempt_enable();
-}
-
-#endif /* #ifdef CONFIG_TASKS_RCU */
-
-#ifndef CONFIG_TINY_RCU
-
-/*
- * Print any non-default Tasks RCU settings.
- */
-static void __init rcu_tasks_bootup_oddness(void)
-{
-#ifdef CONFIG_TASKS_RCU
-	if (rcu_task_stall_timeout != RCU_TASK_STALL_TIMEOUT)
-		pr_info("\tTasks-RCU CPU stall warnings timeout set to %d (rcu_task_stall_timeout).\n", rcu_task_stall_timeout);
-	else
-		pr_info("\tTasks RCU enabled.\n");
-#endif /* #ifdef CONFIG_TASKS_RCU */
-}
-
-#endif /* #ifndef CONFIG_TINY_RCU */
-
 #ifdef CONFIG_PROVE_RCU
 
 /*
@@ -935,6 +585,8 @@ late_initcall(rcu_verify_early_boot_tests);
 void rcu_early_boot_tests(void) {}
 #endif /* CONFIG_PROVE_RCU */
 
+#include "tasks.h"
+
 #ifndef CONFIG_TINY_RCU
 
 /*

kernel/sched/core.c

@@ -2566,6 +2566,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2639,6 +2641,52 @@ out:
 	return success;
 }
 
+/**
+ * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
+ * @p: Process for which the function is to be invoked.
+ * @func: Function to invoke.
+ * @arg: Argument to function.
+ *
+ * If the specified task can be quickly locked into a definite state
+ * (either sleeping or on a given runqueue), arrange to keep it in that
+ * state while invoking @func(@arg).  This function can use ->on_rq and
+ * task_curr() to work out what the state is, if required.  Given that
+ * @func can be invoked with a runqueue lock held, it had better be quite
+ * lightweight.
+ *
+ * Returns:
+ *	@false if the task slipped out from under the locks.
+ *	@true if the task was locked onto a runqueue or is sleeping.
+ *		However, @func can override this by returning @false.
+ */
+bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
+{
+	bool ret = false;
+	struct rq_flags rf;
+	struct rq *rq;
+
+	lockdep_assert_irqs_enabled();
+	raw_spin_lock_irq(&p->pi_lock);
+	if (p->on_rq) {
+		rq = __task_rq_lock(p, &rf);
+		if (task_rq(p) == rq)
+			ret = func(p, arg);
+		rq_unlock(rq, &rf);
+	} else {
+		switch (p->state) {
+		case TASK_RUNNING:
+		case TASK_WAKING:
+			break;
+		default:
+			smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
+			if (!p->on_rq)
+				ret = func(p, arg);
+		}
+	}
+	raw_spin_unlock_irq(&p->pi_lock);
+	return ret;
+}
+
 /**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.

kernel/trace/Kconfig

@@ -158,6 +158,7 @@ config FUNCTION_TRACER
 	select CONTEXT_SWITCH_TRACER
 	select GLOB
 	select TASKS_RCU if PREEMPTION
+	select TASKS_RUDE_RCU
 	help
 	  Enable the kernel to trace every kernel function. This is done
 	  by using a compiler feature to insert a small, 5-byte No-Operation

kernel/trace/ftrace.c

@@ -160,17 +160,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 	op->saved_func(ip, parent_ip, op, regs);
 }
 
-static void ftrace_sync(struct work_struct *work)
-{
-	/*
-	 * This function is just a stub to implement a hard force
-	 * of synchronize_rcu(). This requires synchronizing
-	 * tasks even in userspace and idle.
-	 *
-	 * Yes, function tracing is rude.
-	 */
-}
-
 static void ftrace_sync_ipi(void *data)
 {
 	/* Probably not needed, but do it anyway */
@@ -256,7 +245,7 @@ static void update_ftrace_function(void)
 	 * Make sure all CPUs see this. Yes this is slow, but static
 	 * tracing is slow and nasty to have enabled.
 	 */
-	schedule_on_each_cpu(ftrace_sync);
+	synchronize_rcu_tasks_rude();
 	/* Now all cpus are using the list ops. */
 	function_trace_op = set_function_trace_op;
 	/* Make sure the function_trace_op is visible on all CPUs */
@@ -2932,7 +2921,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		/*
 		 * When the kernel is preeptive, tasks can be preempted
@@ -5887,7 +5876,7 @@ ftrace_graph_release(struct inode *inode, struct file *file)
 		 * infrastructure to do the synchronization, thus we must do it
 		 * ourselves.
 		 */
-		schedule_on_each_cpu(ftrace_sync);
+		synchronize_rcu_tasks_rude();
 
 		free_ftrace_hash(old_hash);
 	}