Merge branches 'cpuinfo.2020.11.06a', 'doc.2020.11.06a', 'fixes.2020.11.19b', 'lockdep.2020.11.02a', 'tasks.2020.11.06a' and 'torture.2020.11.06a' into HEAD

cpuinfo.2020.11.06a: Speedups for /proc/cpuinfo.
doc.2020.11.06a: Documentation updates.
fixes.2020.11.19b: Miscellaneous fixes.
lockdep.2020.11.02a: Lockdep-RCU updates to avoid "unused variable".
tasks.2020.11.06a: Tasks-RCU updates.
torture.2020.11.06a': Torture-test updates.

kernel/locking/locktorture.c

@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/torture.h>
+#include <linux/reboot.h>
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
@@ -60,6 +61,7 @@ static struct task_struct **reader_tasks;
 
 static bool lock_is_write_held;
 static bool lock_is_read_held;
+static unsigned long last_lock_release;
 
 struct lock_stress_stats {
 	long n_lock_fail;
@@ -74,6 +76,7 @@ static void lock_torture_cleanup(void);
  */
 struct lock_torture_ops {
 	void (*init)(void);
+	void (*exit)(void);
 	int (*writelock)(void);
 	void (*write_delay)(struct torture_random_state *trsp);
 	void (*task_boost)(struct torture_random_state *trsp);
@@ -90,12 +93,13 @@ struct lock_torture_cxt {
 	int nrealwriters_stress;
 	int nrealreaders_stress;
 	bool debug_lock;
+	bool init_called;
 	atomic_t n_lock_torture_errors;
 	struct lock_torture_ops *cur_ops;
 	struct lock_stress_stats *lwsa; /* writer statistics */
 	struct lock_stress_stats *lrsa; /* reader statistics */
 };
-static struct lock_torture_cxt cxt = { 0, 0, false,
+static struct lock_torture_cxt cxt = { 0, 0, false, false,
 				       ATOMIC_INIT(0),
 				       NULL, NULL};
 /*
@@ -571,6 +575,11 @@ static void torture_percpu_rwsem_init(void)
 	BUG_ON(percpu_init_rwsem(&pcpu_rwsem));
 }
 
+static void torture_percpu_rwsem_exit(void)
+{
+	percpu_free_rwsem(&pcpu_rwsem);
+}
+
 static int torture_percpu_rwsem_down_write(void) __acquires(pcpu_rwsem)
 {
 	percpu_down_write(&pcpu_rwsem);
@@ -595,6 +604,7 @@ static void torture_percpu_rwsem_up_read(void) __releases(pcpu_rwsem)
 
 static struct lock_torture_ops percpu_rwsem_lock_ops = {
 	.init		= torture_percpu_rwsem_init,
+	.exit		= torture_percpu_rwsem_exit,
 	.writelock	= torture_percpu_rwsem_down_write,
 	.write_delay	= torture_rwsem_write_delay,
 	.task_boost     = torture_boost_dummy,
@@ -632,6 +642,7 @@ static int lock_torture_writer(void *arg)
 		lwsp->n_lock_acquired++;
 		cxt.cur_ops->write_delay(&rand);
 		lock_is_write_held = false;
+		WRITE_ONCE(last_lock_release, jiffies);
 		cxt.cur_ops->writeunlock();
 
 		stutter_wait("lock_torture_writer");
@@ -786,9 +797,10 @@ static void lock_torture_cleanup(void)
 
 	/*
 	 * Indicates early cleanup, meaning that the test has not run,
-	 * such as when passing bogus args when loading the module. As
-	 * such, only perform the underlying torture-specific cleanups,
-	 * and avoid anything related to locktorture.
+	 * such as when passing bogus args when loading the module.
+	 * However cxt->cur_ops.init() may have been invoked, so beside
+	 * perform the underlying torture-specific cleanups, cur_ops.exit()
+	 * will be invoked if needed.
 	 */
 	if (!cxt.lwsa && !cxt.lrsa)
 		goto end;
@@ -828,6 +840,11 @@ static void lock_torture_cleanup(void)
 	cxt.lrsa = NULL;
 
 end:
+	if (cxt.init_called) {
+		if (cxt.cur_ops->exit)
+			cxt.cur_ops->exit();
+		cxt.init_called = false;
+	}
 	torture_cleanup_end();
 }
 
@@ -868,14 +885,17 @@ static int __init lock_torture_init(void)
 		goto unwind;
 	}
 
-	if (nwriters_stress == 0 && nreaders_stress == 0) {
+	if (nwriters_stress == 0 &&
+	    (!cxt.cur_ops->readlock || nreaders_stress == 0)) {
 		pr_alert("lock-torture: must run at least one locking thread\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
 
-	if (cxt.cur_ops->init)
+	if (cxt.cur_ops->init) {
 		cxt.cur_ops->init();
+		cxt.init_called = true;
+	}
 
 	if (nwriters_stress >= 0)
 		cxt.nrealwriters_stress = nwriters_stress;
@@ -1038,6 +1058,10 @@ static int __init lock_torture_init(void)
 unwind:
 	torture_init_end();
 	lock_torture_cleanup();
+	if (shutdown_secs) {
+		WARN_ON(!IS_MODULE(CONFIG_LOCK_TORTURE_TEST));
+		kernel_power_off();
+	}
 	return firsterr;
 }
 

kernel/rcu/Kconfig

@@ -221,19 +221,23 @@ config RCU_NOCB_CPU
 	  Use this option to reduce OS jitter for aggressive HPC or
 	  real-time workloads.	It can also be used to offload RCU
 	  callback invocation to energy-efficient CPUs in battery-powered
-	  asymmetric multiprocessors.
+	  asymmetric multiprocessors.  The price of this reduced jitter
+	  is that the overhead of call_rcu() increases and that some
+	  workloads will incur significant increases in context-switch
+	  rates.
 
 	  This option offloads callback invocation from the set of CPUs
 	  specified at boot time by the rcu_nocbs parameter.  For each
 	  such CPU, a kthread ("rcuox/N") will be created to invoke
 	  callbacks, where the "N" is the CPU being offloaded, and where
-	  the "p" for RCU-preempt (PREEMPTION kernels) and "s" for RCU-sched
-	  (!PREEMPTION kernels).  Nothing prevents this kthread from running
-	  on the specified CPUs, but (1) the kthreads may be preempted
-	  between each callback, and (2) affinity or cgroups can be used
-	  to force the kthreads to run on whatever set of CPUs is desired.
+	  the "x" is "p" for RCU-preempt (PREEMPTION kernels) and "s" for
+	  RCU-sched (!PREEMPTION kernels).  Nothing prevents this kthread
+	  from running on the specified CPUs, but (1) the kthreads may be
+	  preempted between each callback, and (2) affinity or cgroups can
+	  be used to force the kthreads to run on whatever set of CPUs is
+	  desired.
 
-	  Say Y here if you want to help to debug reduced OS jitter.
+	  Say Y here if you need reduced OS jitter, despite added overhead.
 	  Say N here if you are unsure.
 
 config TASKS_TRACE_RCU_READ_MB

kernel/rcu/rcu.h

@@ -533,4 +533,20 @@ static inline bool rcu_is_nocb_cpu(int cpu) { return false; }
 static inline void rcu_bind_current_to_nocb(void) { }
 #endif
 
+#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_RCU)
+void show_rcu_tasks_classic_gp_kthread(void);
+#else
+static inline void show_rcu_tasks_classic_gp_kthread(void) {}
+#endif
+#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_RUDE_RCU)
+void show_rcu_tasks_rude_gp_kthread(void);
+#else
+static inline void show_rcu_tasks_rude_gp_kthread(void) {}
+#endif
+#if !defined(CONFIG_TINY_RCU) && defined(CONFIG_TASKS_TRACE_RCU)
+void show_rcu_tasks_trace_gp_kthread(void);
+#else
+static inline void show_rcu_tasks_trace_gp_kthread(void) {}
+#endif
+
 #endif /* __LINUX_RCU_H */

kernel/rcu/rcu_segcblist.h

@@ -62,7 +62,7 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
 /* Is the specified rcu_segcblist offloaded?  */
 static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
 {
-	return rsclp->offloaded;
+	return IS_ENABLED(CONFIG_RCU_NOCB_CPU) && rsclp->offloaded;
 }
 
 /*

kernel/rcu/rcuscale.c

@@ -38,6 +38,7 @@
 #include <asm/byteorder.h>
 #include <linux/torture.h>
 #include <linux/vmalloc.h>
+#include <linux/rcupdate_trace.h>
 
 #include "rcu.h"
 
@@ -294,6 +295,35 @@ static struct rcu_scale_ops tasks_ops = {
 	.name		= "tasks"
 };
 
+/*
+ * Definitions for RCU-tasks-trace scalability testing.
+ */
+
+static int tasks_trace_scale_read_lock(void)
+{
+	rcu_read_lock_trace();
+	return 0;
+}
+
+static void tasks_trace_scale_read_unlock(int idx)
+{
+	rcu_read_unlock_trace();
+}
+
+static struct rcu_scale_ops tasks_tracing_ops = {
+	.ptype		= RCU_TASKS_FLAVOR,
+	.init		= rcu_sync_scale_init,
+	.readlock	= tasks_trace_scale_read_lock,
+	.readunlock	= tasks_trace_scale_read_unlock,
+	.get_gp_seq	= rcu_no_completed,
+	.gp_diff	= rcu_seq_diff,
+	.async		= call_rcu_tasks_trace,
+	.gp_barrier	= rcu_barrier_tasks_trace,
+	.sync		= synchronize_rcu_tasks_trace,
+	.exp_sync	= synchronize_rcu_tasks_trace,
+	.name		= "tasks-tracing"
+};
+
 static unsigned long rcuscale_seq_diff(unsigned long new, unsigned long old)
 {
 	if (!cur_ops->gp_diff)
@@ -754,7 +784,7 @@ rcu_scale_init(void)
 	long i;
 	int firsterr = 0;
 	static struct rcu_scale_ops *scale_ops[] = {
-		&rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops,
+		&rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops, &tasks_tracing_ops
 	};
 
 	if (!torture_init_begin(scale_type, verbose))
@@ -772,7 +802,6 @@ rcu_scale_init(void)
 		for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
 			pr_cont(" %s", scale_ops[i]->name);
 		pr_cont("\n");
-		WARN_ON(!IS_MODULE(CONFIG_RCU_SCALE_TEST));
 		firsterr = -EINVAL;
 		cur_ops = NULL;
 		goto unwind;
@@ -846,6 +875,10 @@ rcu_scale_init(void)
 unwind:
 	torture_init_end();
 	rcu_scale_cleanup();
+	if (shutdown) {
+		WARN_ON(!IS_MODULE(CONFIG_RCU_SCALE_TEST));
+		kernel_power_off();
+	}
 	return firsterr;
 }
 

kernel/rcu/rcutorture.c

@@ -317,6 +317,7 @@ struct rcu_torture_ops {
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
 	void (*stats)(void);
+	void (*gp_kthread_dbg)(void);
 	int (*stall_dur)(void);
 	int irq_capable;
 	int can_boost;
@@ -466,6 +467,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
+	.gp_kthread_dbg	= show_rcu_gp_kthreads,
 	.stall_dur	= rcu_jiffies_till_stall_check,
 	.irq_capable	= 1,
 	.can_boost	= rcu_can_boost(),
@@ -693,6 +695,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.exp_sync	= synchronize_rcu_mult_test,
 	.call		= call_rcu_tasks,
 	.cb_barrier	= rcu_barrier_tasks,
+	.gp_kthread_dbg	= show_rcu_tasks_classic_gp_kthread,
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
@@ -762,6 +765,7 @@ static struct rcu_torture_ops tasks_rude_ops = {
 	.exp_sync	= synchronize_rcu_tasks_rude,
 	.call		= call_rcu_tasks_rude,
 	.cb_barrier	= rcu_barrier_tasks_rude,
+	.gp_kthread_dbg	= show_rcu_tasks_rude_gp_kthread,
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
@@ -800,6 +804,7 @@ static struct rcu_torture_ops tasks_tracing_ops = {
 	.exp_sync	= synchronize_rcu_tasks_trace,
 	.call		= call_rcu_tasks_trace,
 	.cb_barrier	= rcu_barrier_tasks_trace,
+	.gp_kthread_dbg	= show_rcu_tasks_trace_gp_kthread,
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
@@ -912,7 +917,8 @@ static int rcu_torture_boost(void *arg)
 		oldstarttime = boost_starttime;
 		while (time_before(jiffies, oldstarttime)) {
 			schedule_timeout_interruptible(oldstarttime - jiffies);
-			stutter_wait("rcu_torture_boost");
+			if (stutter_wait("rcu_torture_boost"))
+				sched_set_fifo_low(current);
 			if (torture_must_stop())
 				goto checkwait;
 		}
@@ -932,7 +938,8 @@ static int rcu_torture_boost(void *arg)
 								 jiffies);
 				call_rcu_time = jiffies;
 			}
-			stutter_wait("rcu_torture_boost");
+			if (stutter_wait("rcu_torture_boost"))
+				sched_set_fifo_low(current);
 			if (torture_must_stop())
 				goto checkwait;
 		}
@@ -964,7 +971,8 @@ static int rcu_torture_boost(void *arg)
 		}
 
 		/* Go do the stutter. */
-checkwait:	stutter_wait("rcu_torture_boost");
+checkwait:	if (stutter_wait("rcu_torture_boost"))
+			sched_set_fifo_low(current);
 	} while (!torture_must_stop());
 
 	/* Clean up and exit. */
@@ -987,6 +995,7 @@ rcu_torture_fqs(void *arg)
 {
 	unsigned long fqs_resume_time;
 	int fqs_burst_remaining;
+	int oldnice = task_nice(current);
 
 	VERBOSE_TOROUT_STRING("rcu_torture_fqs task started");
 	do {
@@ -1002,7 +1011,8 @@ rcu_torture_fqs(void *arg)
 			udelay(fqs_holdoff);
 			fqs_burst_remaining -= fqs_holdoff;
 		}
-		stutter_wait("rcu_torture_fqs");
+		if (stutter_wait("rcu_torture_fqs"))
+			sched_set_normal(current, oldnice);
 	} while (!torture_must_stop());
 	torture_kthread_stopping("rcu_torture_fqs");
 	return 0;
@@ -1022,9 +1032,11 @@ rcu_torture_writer(void *arg)
 	bool gp_cond1 = gp_cond, gp_exp1 = gp_exp, gp_normal1 = gp_normal;
 	bool gp_sync1 = gp_sync;
 	int i;
+	int oldnice = task_nice(current);
 	struct rcu_torture *rp;
 	struct rcu_torture *old_rp;
 	static DEFINE_TORTURE_RANDOM(rand);
+	bool stutter_waited;
 	int synctype[] = { RTWS_DEF_FREE, RTWS_EXP_SYNC,
 			   RTWS_COND_GET, RTWS_SYNC };
 	int nsynctypes = 0;
@@ -1143,7 +1155,8 @@ rcu_torture_writer(void *arg)
 				       !rcu_gp_is_normal();
 		}
 		rcu_torture_writer_state = RTWS_STUTTER;
-		if (stutter_wait("rcu_torture_writer") &&
+		stutter_waited = stutter_wait("rcu_torture_writer");
+		if (stutter_waited &&
 		    !READ_ONCE(rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
 		    !torture_must_stop() &&
@@ -1155,6 +1168,8 @@ rcu_torture_writer(void *arg)
 					rcu_ftrace_dump(DUMP_ALL);
 					WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count);
 				}
+		if (stutter_waited)
+			sched_set_normal(current, oldnice);
 	} while (!torture_must_stop());
 	rcu_torture_current = NULL;  // Let stats task know that we are done.
 	/* Reset expediting back to unexpedited. */
@@ -1594,7 +1609,8 @@ rcu_torture_stats_print(void)
 			sched_show_task(wtp);
 			splatted = true;
 		}
-		show_rcu_gp_kthreads();
+		if (cur_ops->gp_kthread_dbg)
+			cur_ops->gp_kthread_dbg();
 		rcu_ftrace_dump(DUMP_ALL);
 	}
 	rtcv_snap = rcu_torture_current_version;
@@ -1913,7 +1929,9 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	unsigned long stopat;
 	static DEFINE_TORTURE_RANDOM(trs);
 
-	if  (cur_ops->call && cur_ops->sync && cur_ops->cb_barrier) {
+	if (!cur_ops->sync)
+		return; // Cannot do need_resched() forward progress testing without ->sync.
+	if (cur_ops->call && cur_ops->cb_barrier) {
 		init_rcu_head_on_stack(&fcs.rh);
 		selfpropcb = true;
 	}
@@ -2103,6 +2121,7 @@ static struct notifier_block rcutorture_oom_nb = {
 /* Carry out grace-period forward-progress testing. */
 static int rcu_torture_fwd_prog(void *args)
 {
+	int oldnice = task_nice(current);
 	struct rcu_fwd *rfp = args;
 	int tested = 0;
 	int tested_tries = 0;
@@ -2121,7 +2140,8 @@ static int rcu_torture_fwd_prog(void *args)
 			rcu_torture_fwd_prog_cr(rfp);
 
 		/* Avoid slow periods, better to test when busy. */
-		stutter_wait("rcu_torture_fwd_prog");
+		if (stutter_wait("rcu_torture_fwd_prog"))
+			sched_set_normal(current, oldnice);
 	} while (!torture_must_stop());
 	/* Short runs might not contain a valid forward-progress attempt. */
 	WARN_ON(!tested && tested_tries >= 5);
@@ -2137,8 +2157,8 @@ static int __init rcu_torture_fwd_prog_init(void)
 
 	if (!fwd_progress)
 		return 0; /* Not requested, so don't do it. */
-	if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 ||
-	    cur_ops == &rcu_busted_ops) {
+	if ((!cur_ops->sync && !cur_ops->call) ||
+	    !cur_ops->stall_dur || cur_ops->stall_dur() <= 0 || cur_ops == &rcu_busted_ops) {
 		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test");
 		return 0;
 	}
@@ -2472,7 +2492,8 @@ rcu_torture_cleanup(void)
 		return;
 	}
 
-	show_rcu_gp_kthreads();
+	if (cur_ops->gp_kthread_dbg)
+		cur_ops->gp_kthread_dbg();
 	rcu_torture_read_exit_cleanup();
 	rcu_torture_barrier_cleanup();
 	rcu_torture_fwd_prog_cleanup();
@@ -2484,13 +2505,13 @@ rcu_torture_cleanup(void)
 			torture_stop_kthread(rcu_torture_reader,
 					     reader_tasks[i]);
 		kfree(reader_tasks);
+		reader_tasks = NULL;
 	}
 
 	if (fakewriter_tasks) {
-		for (i = 0; i < nfakewriters; i++) {
+		for (i = 0; i < nfakewriters; i++)
 			torture_stop_kthread(rcu_torture_fakewriter,
 					     fakewriter_tasks[i]);
-		}
 		kfree(fakewriter_tasks);
 		fakewriter_tasks = NULL;
 	}
@@ -2647,7 +2668,6 @@ rcu_torture_init(void)
 		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
 			pr_cont(" %s", torture_ops[i]->name);
 		pr_cont("\n");
-		WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST));
 		firsterr = -EINVAL;
 		cur_ops = NULL;
 		goto unwind;
@@ -2815,6 +2835,10 @@ rcu_torture_init(void)
 unwind:
 	torture_init_end();
 	rcu_torture_cleanup();
+	if (shutdown_secs) {
+		WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST));
+		kernel_power_off();
+	}
 	return firsterr;
 }
 

kernel/rcu/refscale.c

@@ -658,7 +658,6 @@ ref_scale_init(void)
 		for (i = 0; i < ARRAY_SIZE(scale_ops); i++)
 			pr_cont(" %s", scale_ops[i]->name);
 		pr_cont("\n");
-		WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST));
 		firsterr = -EINVAL;
 		cur_ops = NULL;
 		goto unwind;
@@ -681,6 +680,12 @@ ref_scale_init(void)
 	// Reader tasks (default to ~75% of online CPUs).
 	if (nreaders < 0)
 		nreaders = (num_online_cpus() >> 1) + (num_online_cpus() >> 2);
+	if (WARN_ONCE(loops <= 0, "%s: loops = %ld, adjusted to 1\n", __func__, loops))
+		loops = 1;
+	if (WARN_ONCE(nreaders <= 0, "%s: nreaders = %d, adjusted to 1\n", __func__, nreaders))
+		nreaders = 1;
+	if (WARN_ONCE(nruns <= 0, "%s: nruns = %d, adjusted to 1\n", __func__, nruns))
+		nruns = 1;
 	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (!reader_tasks) {
@@ -712,6 +717,10 @@ ref_scale_init(void)
 unwind:
 	torture_init_end();
 	ref_scale_cleanup();
+	if (shutdown) {
+		WARN_ON(!IS_MODULE(CONFIG_RCU_REF_SCALE_TEST));
+		kernel_power_off();
+	}
 	return firsterr;
 }
 

kernel/rcu/srcutree.c

@@ -177,11 +177,13 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static)
 	INIT_DELAYED_WORK(&ssp->work, process_srcu);
 	if (!is_static)
 		ssp->sda = alloc_percpu(struct srcu_data);
+	if (!ssp->sda)
+		return -ENOMEM;
 	init_srcu_struct_nodes(ssp, is_static);
 	ssp->srcu_gp_seq_needed_exp = 0;
 	ssp->srcu_last_gp_end = ktime_get_mono_fast_ns();
 	smp_store_release(&ssp->srcu_gp_seq_needed, 0); /* Init done. */
-	return ssp->sda ? 0 : -ENOMEM;
+	return 0;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -906,7 +908,7 @@ static void __synchronize_srcu(struct srcu_struct *ssp, bool do_norm)
 {
 	struct rcu_synchronize rcu;
 
-	RCU_LOCKDEP_WARN(lock_is_held(&ssp->dep_map) ||
+	RCU_LOCKDEP_WARN(lockdep_is_held(ssp) ||
 			 lock_is_held(&rcu_bh_lock_map) ||
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),

kernel/rcu/tasks.h

@@ -290,7 +290,7 @@ static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
 		".C"[!!data_race(rtp->cbs_head)],
 		s);
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
+#endif // #ifndef CONFIG_TINY_RCU
 
 static void exit_tasks_rcu_finish_trace(struct task_struct *t);
 
@@ -335,23 +335,18 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 
 	// Start off with initial wait and slowly back off to 1 HZ wait.
 	fract = rtp->init_fract;
-	if (fract > HZ)
-		fract = HZ;
 
-	for (;;) {
+	while (!list_empty(&holdouts)) {
 		bool firstreport;
 		bool needreport;
 		int rtst;
 
-		if (list_empty(&holdouts))
-			break;
-
 		/* Slowly back off waiting for holdouts */
 		set_tasks_gp_state(rtp, RTGS_WAIT_SCAN_HOLDOUTS);
-		schedule_timeout_idle(HZ/fract);
+		schedule_timeout_idle(fract);
 
-		if (fract > 1)
-			fract--;
+		if (fract < HZ)
+			fract++;
 
 		rtst = READ_ONCE(rcu_task_stall_timeout);
 		needreport = rtst > 0 && time_after(jiffies, lastreport + rtst);
@@ -560,7 +555,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 static int __init rcu_spawn_tasks_kthread(void)
 {
 	rcu_tasks.gp_sleep = HZ / 10;
-	rcu_tasks.init_fract = 10;
+	rcu_tasks.init_fract = HZ / 10;
 	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
 	rcu_tasks.pertask_func = rcu_tasks_pertask;
 	rcu_tasks.postscan_func = rcu_tasks_postscan;
@@ -571,12 +566,13 @@ static int __init rcu_spawn_tasks_kthread(void)
 }
 core_initcall(rcu_spawn_tasks_kthread);
 
-#ifndef CONFIG_TINY_RCU
-static void show_rcu_tasks_classic_gp_kthread(void)
+#if !defined(CONFIG_TINY_RCU)
+void show_rcu_tasks_classic_gp_kthread(void)
 {
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks, "");
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
+EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread);
+#endif // !defined(CONFIG_TINY_RCU)
 
 /* Do the srcu_read_lock() for the above synchronize_srcu().  */
 void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu)
@@ -598,7 +594,6 @@ void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu)
 }
 
 #else /* #ifdef CONFIG_TASKS_RCU */
-static inline void show_rcu_tasks_classic_gp_kthread(void) { }
 void exit_tasks_rcu_start(void) { }
 void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
@@ -699,16 +694,14 @@ static int __init rcu_spawn_tasks_rude_kthread(void)
 }
 core_initcall(rcu_spawn_tasks_rude_kthread);
 
-#ifndef CONFIG_TINY_RCU
-static void show_rcu_tasks_rude_gp_kthread(void)
+#if !defined(CONFIG_TINY_RCU)
+void show_rcu_tasks_rude_gp_kthread(void)
 {
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_rude, "");
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
-
-#else /* #ifdef CONFIG_TASKS_RUDE_RCU */
-static void show_rcu_tasks_rude_gp_kthread(void) {}
-#endif /* #else #ifdef CONFIG_TASKS_RUDE_RCU */
+EXPORT_SYMBOL_GPL(show_rcu_tasks_rude_gp_kthread);
+#endif // !defined(CONFIG_TINY_RCU)
+#endif /* #ifdef CONFIG_TASKS_RUDE_RCU */
 
 ////////////////////////////////////////////////////////////////////////
 //
@@ -1183,12 +1176,12 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 {
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
 		rcu_tasks_trace.gp_sleep = HZ / 10;
-		rcu_tasks_trace.init_fract = 10;
+		rcu_tasks_trace.init_fract = HZ / 10;
 	} else {
 		rcu_tasks_trace.gp_sleep = HZ / 200;
 		if (rcu_tasks_trace.gp_sleep <= 0)
 			rcu_tasks_trace.gp_sleep = 1;
-		rcu_tasks_trace.init_fract = HZ / 5;
+		rcu_tasks_trace.init_fract = HZ / 200;
 		if (rcu_tasks_trace.init_fract <= 0)
 			rcu_tasks_trace.init_fract = 1;
 	}
@@ -1202,8 +1195,8 @@ static int __init rcu_spawn_tasks_trace_kthread(void)
 }
 core_initcall(rcu_spawn_tasks_trace_kthread);
 
-#ifndef CONFIG_TINY_RCU
-static void show_rcu_tasks_trace_gp_kthread(void)
+#if !defined(CONFIG_TINY_RCU)
+void show_rcu_tasks_trace_gp_kthread(void)
 {
 	char buf[64];
 
@@ -1213,11 +1206,11 @@ static void show_rcu_tasks_trace_gp_kthread(void)
 		data_race(n_heavy_reader_attempts));
 	show_rcu_tasks_generic_gp_kthread(&rcu_tasks_trace, buf);
 }
-#endif /* #ifndef CONFIG_TINY_RCU */
+EXPORT_SYMBOL_GPL(show_rcu_tasks_trace_gp_kthread);
+#endif // !defined(CONFIG_TINY_RCU)
 
 #else /* #ifdef CONFIG_TASKS_TRACE_RCU */
 static void exit_tasks_rcu_finish_trace(struct task_struct *t) { }
-static inline void show_rcu_tasks_trace_gp_kthread(void) {}
 #endif /* #else #ifdef CONFIG_TASKS_TRACE_RCU */
 
 #ifndef CONFIG_TINY_RCU

kernel/rcu/tree.c

@@ -177,7 +177,7 @@ module_param(rcu_unlock_delay, int, 0444);
  * per-CPU. Object size is equal to one page. This value
  * can be changed at boot time.
  */
-static int rcu_min_cached_objs = 2;
+static int rcu_min_cached_objs = 5;
 module_param(rcu_min_cached_objs, int, 0444);
 
 /* Retrieve RCU kthreads priority for rcutorture */
@@ -554,12 +554,12 @@ static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param
 	return ret;
 }
 
-static struct kernel_param_ops first_fqs_jiffies_ops = {
+static const struct kernel_param_ops first_fqs_jiffies_ops = {
 	.set = param_set_first_fqs_jiffies,
 	.get = param_get_ulong,
 };
 
-static struct kernel_param_ops next_fqs_jiffies_ops = {
+static const struct kernel_param_ops next_fqs_jiffies_ops = {
 	.set = param_set_next_fqs_jiffies,
 	.get = param_get_ulong,
 };
@@ -936,8 +936,8 @@ void __rcu_irq_enter_check_tick(void)
 {
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 
-	 // Enabling the tick is unsafe in NMI handlers.
-	if (WARN_ON_ONCE(in_nmi()))
+	// If we're here from NMI there's nothing to do.
+	if (in_nmi())
 		return;
 
 	RCU_LOCKDEP_WARN(rcu_dynticks_curr_cpu_in_eqs(),
@@ -1101,8 +1101,11 @@ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp)
  * CPU can safely enter RCU read-side critical sections.  In other words,
  * if the current CPU is not in its idle loop or is in an interrupt or
  * NMI handler, return true.
+ *
+ * Make notrace because it can be called by the internal functions of
+ * ftrace, and making this notrace removes unnecessary recursion calls.
  */
-bool rcu_is_watching(void)
+notrace bool rcu_is_watching(void)
 {
 	bool ret;
 
@@ -1157,7 +1160,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	preempt_disable_notrace();
 	rdp = this_cpu_ptr(&rcu_data);
 	rnp = rdp->mynode;
-	if (rdp->grpmask & rcu_rnp_online_cpus(rnp))
+	if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1)
 		ret = true;
 	preempt_enable_notrace();
 	return ret;
@@ -1611,8 +1614,7 @@ static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	bool ret = false;
 	bool need_qs;
-	const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-			       rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 
@@ -1723,6 +1725,7 @@ static void rcu_strict_gp_boundary(void *unused)
  */
 static bool rcu_gp_init(void)
 {
+	unsigned long firstseq;
 	unsigned long flags;
 	unsigned long oldmask;
 	unsigned long mask;
@@ -1766,6 +1769,12 @@ static bool rcu_gp_init(void)
 	 */
 	rcu_state.gp_state = RCU_GP_ONOFF;
 	rcu_for_each_leaf_node(rnp) {
+		smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
+		firstseq = READ_ONCE(rnp->ofl_seq);
+		if (firstseq & 0x1)
+			while (firstseq == READ_ONCE(rnp->ofl_seq))
+				schedule_timeout_idle(1);  // Can't wake unless RCU is watching.
+		smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values.
 		raw_spin_lock(&rcu_state.ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@@ -2056,8 +2065,7 @@ static void rcu_gp_cleanup(void)
 		needgp = true;
 	}
 	/* Advance CBs to reduce false positives below. */
-	offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-		    rcu_segcblist_is_offloaded(&rdp->cblist);
+	offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
 	if ((offloaded || !rcu_accelerate_cbs(rnp, rdp)) && needgp) {
 		WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT);
 		WRITE_ONCE(rcu_state.gp_req_activity, jiffies);
@@ -2256,8 +2264,7 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 	unsigned long flags;
 	unsigned long mask;
 	bool needwake = false;
-	const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-			       rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
 	struct rcu_node *rnp;
 
 	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
@@ -2407,6 +2414,7 @@ int rcutree_dead_cpu(unsigned int cpu)
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
 		return 0;
 
+	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1);
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 	/* Do any needed no-CB deferred wakeups from this CPU. */
@@ -2425,8 +2433,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 {
 	int div;
 	unsigned long flags;
-	const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-			       rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
 	long bl, count;
@@ -2683,8 +2690,7 @@ static __latent_entropy void rcu_core(void)
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
-	const bool offloaded = IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-			       rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
 
 	if (cpu_is_offline(smp_processor_id()))
 		return;
@@ -2986,8 +2992,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 				   rcu_segcblist_n_cbs(&rdp->cblist));
 
 	/* Go handle any RCU core processing required. */
-	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-	    unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
+	if (unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
 		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
 	} else {
 		__call_rcu_core(rdp, head, flags);
@@ -3092,6 +3097,9 @@ struct kfree_rcu_cpu_work {
  *	In order to save some per-cpu space the list is singular.
  *	Even though it is lockless an access has to be protected by the
  *	per-cpu lock.
+ * @page_cache_work: A work to refill the cache when it is empty
+ * @work_in_progress: Indicates that page_cache_work is running
+ * @hrtimer: A hrtimer for scheduling a page_cache_work
  * @nr_bkv_objs: number of allocated objects at @bkvcache.
  *
  * This is a per-CPU structure.  The reason that it is not included in
@@ -3108,6 +3116,11 @@ struct kfree_rcu_cpu {
 	bool monitor_todo;
 	bool initialized;
 	int count;
+
+	struct work_struct page_cache_work;
+	atomic_t work_in_progress;
+	struct hrtimer hrtimer;
+
 	struct llist_head bkvcache;
 	int nr_bkv_objs;
 };
@@ -3225,10 +3238,10 @@ static void kfree_rcu_work(struct work_struct *work)
 			}
 			rcu_lock_release(&rcu_callback_map);
 
-			krcp = krc_this_cpu_lock(&flags);
+			raw_spin_lock_irqsave(&krcp->lock, flags);
 			if (put_cached_bnode(krcp, bkvhead[i]))
 				bkvhead[i] = NULL;
-			krc_this_cpu_unlock(krcp, flags);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
 
 			if (bkvhead[i])
 				free_page((unsigned long) bkvhead[i]);
@@ -3355,6 +3368,57 @@ static void kfree_rcu_monitor(struct work_struct *work)
 		raw_spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
+static enum hrtimer_restart
+schedule_page_work_fn(struct hrtimer *t)
+{
+	struct kfree_rcu_cpu *krcp =
+		container_of(t, struct kfree_rcu_cpu, hrtimer);
+
+	queue_work(system_highpri_wq, &krcp->page_cache_work);
+	return HRTIMER_NORESTART;
+}
+
+static void fill_page_cache_func(struct work_struct *work)
+{
+	struct kvfree_rcu_bulk_data *bnode;
+	struct kfree_rcu_cpu *krcp =
+		container_of(work, struct kfree_rcu_cpu,
+			page_cache_work);
+	unsigned long flags;
+	bool pushed;
+	int i;
+
+	for (i = 0; i < rcu_min_cached_objs; i++) {
+		bnode = (struct kvfree_rcu_bulk_data *)
+			__get_free_page(GFP_KERNEL | __GFP_NOWARN);
+
+		if (bnode) {
+			raw_spin_lock_irqsave(&krcp->lock, flags);
+			pushed = put_cached_bnode(krcp, bnode);
+			raw_spin_unlock_irqrestore(&krcp->lock, flags);
+
+			if (!pushed) {
+				free_page((unsigned long) bnode);
+				break;
+			}
+		}
+	}
+
+	atomic_set(&krcp->work_in_progress, 0);
+}
+
+static void
+run_page_cache_worker(struct kfree_rcu_cpu *krcp)
+{
+	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
+			!atomic_xchg(&krcp->work_in_progress, 1)) {
+		hrtimer_init(&krcp->hrtimer, CLOCK_MONOTONIC,
+			HRTIMER_MODE_REL);
+		krcp->hrtimer.function = schedule_page_work_fn;
+		hrtimer_start(&krcp->hrtimer, 0, HRTIMER_MODE_REL);
+	}
+}
+
 static inline bool
 kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 {
@@ -3371,32 +3435,8 @@ kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 	if (!krcp->bkvhead[idx] ||
 			krcp->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) {
 		bnode = get_cached_bnode(krcp);
-		if (!bnode) {
-			/*
-			 * To keep this path working on raw non-preemptible
-			 * sections, prevent the optional entry into the
-			 * allocator as it uses sleeping locks. In fact, even
-			 * if the caller of kfree_rcu() is preemptible, this
-			 * path still is not, as krcp->lock is a raw spinlock.
-			 * With additional page pre-allocation in the works,
-			 * hitting this return is going to be much less likely.
-			 */
-			if (IS_ENABLED(CONFIG_PREEMPT_RT))
-				return false;
-
-			/*
-			 * NOTE: For one argument of kvfree_rcu() we can
-			 * drop the lock and get the page in sleepable
-			 * context. That would allow to maintain an array
-			 * for the CONFIG_PREEMPT_RT as well if no cached
-			 * pages are available.
-			 */
-			bnode = (struct kvfree_rcu_bulk_data *)
-				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		}
-
 		/* Switch to emergency path. */
-		if (unlikely(!bnode))
+		if (!bnode)
 			return false;
 
 		/* Initialize the new block. */
@@ -3460,12 +3500,10 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		goto unlock_return;
 	}
 
-	/*
-	 * Under high memory pressure GFP_NOWAIT can fail,
-	 * in that case the emergency path is maintained.
-	 */
 	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
 	if (!success) {
+		run_page_cache_worker(krcp);
+
 		if (head == NULL)
 			// Inline if kvfree_rcu(one_arg) call.
 			goto unlock_return;
@@ -3575,7 +3613,7 @@ void __init kfree_rcu_scheduler_running(void)
  * During early boot, any blocking grace-period wait automatically
  * implies a grace period.  Later on, this is never the case for PREEMPTION.
  *
- * Howevr, because a context switch is a grace period for !PREEMPTION, any
+ * However, because a context switch is a grace period for !PREEMPTION, any
  * blocking grace-period wait automatically implies a grace period if
  * there is only one CPU online at any point time during execution of
  * either synchronize_rcu() or synchronize_rcu_expedited().  It is OK to
@@ -3591,7 +3629,20 @@ static int rcu_blocking_is_gp(void)
 		return rcu_scheduler_active == RCU_SCHEDULER_INACTIVE;
 	might_sleep();  /* Check for RCU read-side critical section. */
 	preempt_disable();
-	ret = num_online_cpus() <= 1;
+	/*
+	 * If the rcu_state.n_online_cpus counter is equal to one,
+	 * there is only one CPU, and that CPU sees all prior accesses
+	 * made by any CPU that was online at the time of its access.
+	 * Furthermore, if this counter is equal to one, its value cannot
+	 * change until after the preempt_enable() below.
+	 *
+	 * Furthermore, if rcu_state.n_online_cpus is equal to one here,
+	 * all later CPUs (both this one and any that come online later
+	 * on) are guaranteed to see all accesses prior to this point
+	 * in the code, without the need for additional memory barriers.
+	 * Those memory barriers are provided by CPU-hotplug code.
+	 */
+	ret = READ_ONCE(rcu_state.n_online_cpus) <= 1;
 	preempt_enable();
 	return ret;
 }
@@ -3636,7 +3687,7 @@ void synchronize_rcu(void)
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_rcu() in RCU read-side critical section");
 	if (rcu_blocking_is_gp())
-		return;
+		return;  // Context allows vacuous grace periods.
 	if (rcu_gp_is_expedited())
 		synchronize_rcu_expedited();
 	else
@@ -3715,13 +3766,13 @@ static int rcu_pending(int user)
 		return 1;
 
 	/* Does this CPU have callbacks ready to invoke? */
-	if (rcu_segcblist_ready_cbs(&rdp->cblist))
+	if (!rcu_segcblist_is_offloaded(&rdp->cblist) &&
+	    rcu_segcblist_ready_cbs(&rdp->cblist))
 		return 1;
 
 	/* Has RCU gone idle with this CPU needing another grace period? */
 	if (!gp_in_progress && rcu_segcblist_is_enabled(&rdp->cblist) &&
-	    (!IS_ENABLED(CONFIG_RCU_NOCB_CPU) ||
-	     !rcu_segcblist_is_offloaded(&rdp->cblist)) &&
+	    !rcu_segcblist_is_offloaded(&rdp->cblist) &&
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
@@ -3977,6 +4028,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	rcu_prepare_kthreads(cpu);
 	rcu_spawn_cpu_nocb_kthread(cpu);
+	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1);
 
 	return 0;
 }
@@ -4065,6 +4117,9 @@ void rcu_cpu_starting(unsigned int cpu)
 
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
+	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+	WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+	smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask);
 	newcpu = !(rnp->expmaskinitnext & mask);
@@ -4075,13 +4130,18 @@ void rcu_cpu_starting(unsigned int cpu)
 	rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
 	rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq);
 	rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags);
-	if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+
+	/* An incoming CPU should never be blocking a grace period. */
+	if (WARN_ON_ONCE(rnp->qsmask & mask)) { /* RCU waiting on incoming CPU? */
 		rcu_disable_urgency_upon_qs(rdp);
 		/* Report QS -after- changing ->qsmaskinitnext! */
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 	} else {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
+	smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+	WARN_ON_ONCE(rnp->ofl_seq & 0x1);
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
 
@@ -4109,6 +4169,9 @@ void rcu_report_dead(unsigned int cpu)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
+	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+	WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+	smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
 	raw_spin_lock(&rcu_state.ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq);
@@ -4121,6 +4184,9 @@ void rcu_report_dead(unsigned int cpu)
 	WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	raw_spin_unlock(&rcu_state.ofl_lock);
+	smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier().
+	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
+	WARN_ON_ONCE(rnp->ofl_seq & 0x1);
 
 	rdp->cpu_started = false;
 }
@@ -4457,24 +4523,14 @@ static void __init kfree_rcu_batch_init(void)
 
 	for_each_possible_cpu(cpu) {
 		struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
-		struct kvfree_rcu_bulk_data *bnode;
 
 		for (i = 0; i < KFREE_N_BATCHES; i++) {
 			INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
 			krcp->krw_arr[i].krcp = krcp;
 		}
 
-		for (i = 0; i < rcu_min_cached_objs; i++) {
-			bnode = (struct kvfree_rcu_bulk_data *)
-				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-
-			if (bnode)
-				put_cached_bnode(krcp, bnode);
-			else
-				pr_err("Failed to preallocate for %d CPU!\n", cpu);
-		}
-
 		INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
+		INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
 		krcp->initialized = true;
 	}
 	if (register_shrinker(&kfree_rcu_shrinker))

kernel/rcu/tree.h

@@ -56,6 +56,7 @@ struct rcu_node {
 				/*  Initialized from ->qsmaskinitnext at the */
 				/*  beginning of each grace period. */
 	unsigned long qsmaskinitnext;
+	unsigned long ofl_seq;	/* CPU-hotplug operation sequence count. */
 				/* Online CPUs for next grace period. */
 	unsigned long expmask;	/* CPUs or groups that need to check in */
 				/*  to allow the current expedited GP */
@@ -298,6 +299,7 @@ struct rcu_state {
 						/* Hierarchy levels (+1 to */
 						/*  shut bogus gcc warning) */
 	int ncpus;				/* # CPUs seen so far. */
+	int n_online_cpus;			/* # CPUs online for RCU. */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 

kernel/rcu/tree_plugin.h

@@ -628,7 +628,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			set_tsk_need_resched(current);
 			set_preempt_need_resched();
 			if (IS_ENABLED(CONFIG_IRQ_WORK) && irqs_were_disabled &&
-			    !rdp->defer_qs_iw_pending && exp) {
+			    !rdp->defer_qs_iw_pending && exp && cpu_online(rdp->cpu)) {
 				// Get scheduler to re-evaluate and call hooks.
 				// If !IRQ_WORK, FQS scan will eventually IPI.
 				init_irq_work(&rdp->defer_qs_iw,

kernel/rcu/tree_stall.h

@@ -13,6 +13,7 @@
 
 /* panic() on RCU Stall sysctl. */
 int sysctl_panic_on_rcu_stall __read_mostly;
+int sysctl_max_rcu_stall_to_panic __read_mostly;
 
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA		(5 * HZ)
@@ -106,6 +107,11 @@ early_initcall(check_cpu_stall_init);
 /* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
 static void panic_on_rcu_stall(void)
 {
+	static int cpu_stall;
+
+	if (++cpu_stall < sysctl_max_rcu_stall_to_panic)
+		return;
+
 	if (sysctl_panic_on_rcu_stall)
 		panic("RCU Stall\n");
 }
@@ -249,13 +255,16 @@ static bool check_slow_task(struct task_struct *t, void *arg)
 
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
+ * sections, printing out the tid of each of the first few of them.
  */
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
+	__releases(rnp->lock)
 {
+	int i = 0;
 	int ndetected = 0;
 	struct rcu_stall_chk_rdr rscr;
 	struct task_struct *t;
+	struct task_struct *ts[8];
 
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
@@ -264,6 +273,14 @@ 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) {
+		get_task_struct(t);
+		ts[i++] = t;
+		if (i >= ARRAY_SIZE(ts))
+			break;
+	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	for (i--; i; i--) {
+		t = ts[i];
 		if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr))
 			pr_cont(" P%d", t->pid);
 		else
@@ -273,6 +290,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 				".q"[rscr.rs.b.need_qs],
 				".e"[rscr.rs.b.exp_hint],
 				".l"[rscr.on_blkd_list]);
+		put_task_struct(t);
 		ndetected++;
 	}
 	pr_cont("\n");
@@ -293,8 +311,9 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
  * Because preemptible RCU does not exist, we never have to check for
  * tasks blocked within RCU read-side critical sections.
  */
-static int rcu_print_task_stall(struct rcu_node *rnp)
+static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags)
 {
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	return 0;
 }
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
@@ -472,7 +491,6 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
 	rcu_for_each_leaf_node(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		ndetected += rcu_print_task_stall(rnp);
 		if (rnp->qsmask != 0) {
 			for_each_leaf_node_possible_cpu(rnp, cpu)
 				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
@@ -480,7 +498,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps)
 					ndetected++;
 				}
 		}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock.
 	}
 
 	for_each_possible_cpu(cpu)

kernel/scftorture.c

@@ -59,9 +59,10 @@ torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (s), 0=disable");
 torture_param(int, shutdown_secs, 0, "Shutdown time (ms), <= zero to disable.");
 torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s.");
-torture_param(int, stutter_cpus, 5, "Number of jiffies to change CPUs under test, 0=disable");
+torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
 torture_param(bool, use_cpus_read_lock, 0, "Use cpus_read_lock() to exclude CPU hotplug.");
 torture_param(int, verbose, 0, "Enable verbose debugging printk()s");
+torture_param(int, weight_resched, -1, "Testing weight for resched_cpu() operations.");
 torture_param(int, weight_single, -1, "Testing weight for single-CPU no-wait operations.");
 torture_param(int, weight_single_wait, -1, "Testing weight for single-CPU operations.");
 torture_param(int, weight_many, -1, "Testing weight for multi-CPU no-wait operations.");
@@ -82,6 +83,7 @@ torture_param(bool, shutdown, SCFTORT_SHUTDOWN, "Shutdown at end of torture test
 struct scf_statistics {
 	struct task_struct *task;
 	int cpu;
+	long long n_resched;
 	long long n_single;
 	long long n_single_ofl;
 	long long n_single_wait;
@@ -97,12 +99,15 @@ static struct task_struct *scf_torture_stats_task;
 static DEFINE_PER_CPU(long long, scf_invoked_count);
 
 // Data for random primitive selection
-#define SCF_PRIM_SINGLE		0
-#define SCF_PRIM_MANY		1
-#define SCF_PRIM_ALL		2
-#define SCF_NPRIMS		(2 * 3) // Need wait and no-wait versions of each.
+#define SCF_PRIM_RESCHED	0
+#define SCF_PRIM_SINGLE		1
+#define SCF_PRIM_MANY		2
+#define SCF_PRIM_ALL		3
+#define SCF_NPRIMS		7 // Need wait and no-wait versions of each,
+				  //  except for SCF_PRIM_RESCHED.
 
 static char *scf_prim_name[] = {
+	"resched_cpu",
 	"smp_call_function_single",
 	"smp_call_function_many",
 	"smp_call_function",
@@ -136,6 +141,8 @@ static char *bangstr = "";
 
 static DEFINE_TORTURE_RANDOM_PERCPU(scf_torture_rand);
 
+extern void resched_cpu(int cpu); // An alternative IPI vector.
+
 // Print torture statistics.  Caller must ensure serialization.
 static void scf_torture_stats_print(void)
 {
@@ -148,6 +155,7 @@ static void scf_torture_stats_print(void)
 	for_each_possible_cpu(cpu)
 		invoked_count += data_race(per_cpu(scf_invoked_count, cpu));
 	for (i = 0; i < nthreads; i++) {
+		scfs.n_resched += scf_stats_p[i].n_resched;
 		scfs.n_single += scf_stats_p[i].n_single;
 		scfs.n_single_ofl += scf_stats_p[i].n_single_ofl;
 		scfs.n_single_wait += scf_stats_p[i].n_single_wait;
@@ -160,8 +168,8 @@ static void scf_torture_stats_print(void)
 	if (atomic_read(&n_errs) || atomic_read(&n_mb_in_errs) ||
 	    atomic_read(&n_mb_out_errs) || atomic_read(&n_alloc_errs))
 		bangstr = "!!! ";
-	pr_alert("%s %sscf_invoked_count %s: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ",
-		 SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count,
+	pr_alert("%s %sscf_invoked_count %s: %lld resched: %lld single: %lld/%lld single_ofl: %lld/%lld many: %lld/%lld all: %lld/%lld ",
+		 SCFTORT_FLAG, bangstr, isdone ? "VER" : "ver", invoked_count, scfs.n_resched,
 		 scfs.n_single, scfs.n_single_wait, scfs.n_single_ofl, scfs.n_single_wait_ofl,
 		 scfs.n_many, scfs.n_many_wait, scfs.n_all, scfs.n_all_wait);
 	torture_onoff_stats();
@@ -314,6 +322,13 @@ static void scftorture_invoke_one(struct scf_statistics *scfp, struct torture_ra
 		}
 	}
 	switch (scfsp->scfs_prim) {
+	case SCF_PRIM_RESCHED:
+		if (IS_BUILTIN(CONFIG_SCF_TORTURE_TEST)) {
+			cpu = torture_random(trsp) % nr_cpu_ids;
+			scfp->n_resched++;
+			resched_cpu(cpu);
+		}
+		break;
 	case SCF_PRIM_SINGLE:
 		cpu = torture_random(trsp) % nr_cpu_ids;
 		if (scfsp->scfs_wait)
@@ -421,6 +436,7 @@ static int scftorture_invoker(void *arg)
 			was_offline = false;
 		}
 		cond_resched();
+		stutter_wait("scftorture_invoker");
 	} while (!torture_must_stop());
 
 	VERBOSE_SCFTORTOUT("scftorture_invoker %d ended", scfp->cpu);
@@ -433,8 +449,8 @@ static void
 scftorture_print_module_parms(const char *tag)
 {
 	pr_alert(SCFTORT_FLAG
-		 "--- %s:  verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter_cpus=%d use_cpus_read_lock=%d, weight_single=%d, weight_single_wait=%d, weight_many=%d, weight_many_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag,
-		 verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter_cpus, use_cpus_read_lock, weight_single, weight_single_wait, weight_many, weight_many_wait, weight_all, weight_all_wait);
+		 "--- %s:  verbose=%d holdoff=%d longwait=%d nthreads=%d onoff_holdoff=%d onoff_interval=%d shutdown_secs=%d stat_interval=%d stutter=%d use_cpus_read_lock=%d, weight_resched=%d, weight_single=%d, weight_single_wait=%d, weight_many=%d, weight_many_wait=%d, weight_all=%d, weight_all_wait=%d\n", tag,
+		 verbose, holdoff, longwait, nthreads, onoff_holdoff, onoff_interval, shutdown, stat_interval, stutter, use_cpus_read_lock, weight_resched, weight_single, weight_single_wait, weight_many, weight_many_wait, weight_all, weight_all_wait);
 }
 
 static void scf_cleanup_handler(void *unused)
@@ -475,6 +491,7 @@ static int __init scf_torture_init(void)
 {
 	long i;
 	int firsterr = 0;
+	unsigned long weight_resched1 = weight_resched;
 	unsigned long weight_single1 = weight_single;
 	unsigned long weight_single_wait1 = weight_single_wait;
 	unsigned long weight_many1 = weight_many;
@@ -487,9 +504,10 @@ static int __init scf_torture_init(void)
 
 	scftorture_print_module_parms("Start of test");
 
-	if (weight_single == -1 && weight_single_wait == -1 &&
+	if (weight_resched == -1 && weight_single == -1 && weight_single_wait == -1 &&
 	    weight_many == -1 && weight_many_wait == -1 &&
 	    weight_all == -1 && weight_all_wait == -1) {
+		weight_resched1 = 2 * nr_cpu_ids;
 		weight_single1 = 2 * nr_cpu_ids;
 		weight_single_wait1 = 2 * nr_cpu_ids;
 		weight_many1 = 2;
@@ -497,6 +515,8 @@ static int __init scf_torture_init(void)
 		weight_all1 = 1;
 		weight_all_wait1 = 1;
 	} else {
+		if (weight_resched == -1)
+			weight_resched1 = 0;
 		if (weight_single == -1)
 			weight_single1 = 0;
 		if (weight_single_wait == -1)
@@ -517,6 +537,10 @@ static int __init scf_torture_init(void)
 		firsterr = -EINVAL;
 		goto unwind;
 	}
+	if (IS_BUILTIN(CONFIG_SCF_TORTURE_TEST))
+		scf_sel_add(weight_resched1, SCF_PRIM_RESCHED, false);
+	else if (weight_resched1)
+		VERBOSE_SCFTORTOUT_ERRSTRING("built as module, weight_resched ignored");
 	scf_sel_add(weight_single1, SCF_PRIM_SINGLE, false);
 	scf_sel_add(weight_single_wait1, SCF_PRIM_SINGLE, true);
 	scf_sel_add(weight_many1, SCF_PRIM_MANY, false);
@@ -535,6 +559,11 @@ static int __init scf_torture_init(void)
 		if (firsterr)
 			goto unwind;
 	}
+	if (stutter > 0) {
+		firsterr = torture_stutter_init(stutter, stutter);
+		if (firsterr)
+			goto unwind;
+	}
 
 	// Worker tasks invoking smp_call_function().
 	if (nthreads < 0)

kernel/sysctl.c

@@ -2650,6 +2650,17 @@ static struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
+#if defined(CONFIG_TREE_RCU)
+	{
+		.procname	= "max_rcu_stall_to_panic",
+		.data		= &sysctl_max_rcu_stall_to_panic,
+		.maxlen		= sizeof(sysctl_max_rcu_stall_to_panic),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+#endif
 #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
 	{
 		.procname	= "stack_erasing",

kernel/torture.c

@@ -602,18 +602,29 @@ static int stutter_gap;
  */
 bool stutter_wait(const char *title)
 {
-	int spt;
+	ktime_t delay;
+	unsigned int i = 0;
 	bool ret = false;
+	int spt;
 
 	cond_resched_tasks_rcu_qs();
 	spt = READ_ONCE(stutter_pause_test);
 	for (; spt; spt = READ_ONCE(stutter_pause_test)) {
-		ret = true;
+		if (!ret) {
+			sched_set_normal(current, MAX_NICE);
+			ret = true;
+		}
 		if (spt == 1) {
 			schedule_timeout_interruptible(1);
 		} else if (spt == 2) {
-			while (READ_ONCE(stutter_pause_test))
+			while (READ_ONCE(stutter_pause_test)) {
+				if (!(i++ & 0xffff)) {
+					set_current_state(TASK_INTERRUPTIBLE);
+					delay = 10 * NSEC_PER_USEC;
+					schedule_hrtimeout(&delay, HRTIMER_MODE_REL);
+				}
 				cond_resched();
+			}
 		} else {
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
 		}
@@ -629,20 +640,27 @@ EXPORT_SYMBOL_GPL(stutter_wait);
  */
 static int torture_stutter(void *arg)
 {
+	ktime_t delay;
+	DEFINE_TORTURE_RANDOM(rand);
 	int wtime;
 
 	VERBOSE_TOROUT_STRING("torture_stutter task started");
 	do {
 		if (!torture_must_stop() && stutter > 1) {
 			wtime = stutter;
-			if (stutter > HZ + 1) {
+			if (stutter > 2) {
 				WRITE_ONCE(stutter_pause_test, 1);
-				wtime = stutter - HZ - 1;
-				schedule_timeout_interruptible(wtime);
-				wtime = HZ + 1;
+				wtime = stutter - 3;
+				delay = ktime_divns(NSEC_PER_SEC * wtime, HZ);
+				delay += (torture_random(&rand) >> 3) % NSEC_PER_MSEC;
+				set_current_state(TASK_INTERRUPTIBLE);
+				schedule_hrtimeout(&delay, HRTIMER_MODE_REL);
+				wtime = 2;
 			}
 			WRITE_ONCE(stutter_pause_test, 2);
-			schedule_timeout_interruptible(wtime);
+			delay = ktime_divns(NSEC_PER_SEC * wtime, HZ);
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule_hrtimeout(&delay, HRTIMER_MODE_REL);
 		}
 		WRITE_ONCE(stutter_pause_test, 0);
 		if (!torture_must_stop())