Merge tag 'rcu.2022.03.13a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Fix idle detection (Neeraj Upadhyay) and missing access marking
   detected by KCSAN.

 - Reduce coupling between rcu_barrier() and CPU-hotplug operations, so
   that rcu_barrier() no longer needs to do cpus_read_lock(). This may
   also someday allow system boot to bring CPUs online concurrently.

 - Enable more aggressive movement to per-CPU queueing when reacting to
   excessive lock contention due to workloads placing heavy update-side
   stress on RCU tasks.

 - Improvements to RCU priority boosting, including changes from Neeraj
   Upadhyay, Zqiang, and Alison Chaiken.

 - Various fixes improving test robustness and debug information.

 - Add tests for SRCU size transitions, further compress torture.sh
   build products, and improve debug output.

 - Miscellaneous fixes.

* tag 'rcu.2022.03.13a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (49 commits)
  rcu: Replace cpumask_weight with cpumask_empty where appropriate
  rcu: Remove __read_mostly annotations from rcu_scheduler_active externs
  rcu: Uninline multi-use function: finish_rcuwait()
  rcu: Mark writes to the rcu_segcblist structure's ->flags field
  kasan: Record work creation stack trace with interrupts enabled
  rcu: Inline __call_rcu() into call_rcu()
  rcu: Add mutex for rcu boost kthread spawning and affinity setting
  rcu: Fix description of kvfree_rcu()
  MAINTAINERS:  Add Frederic and Neeraj to their RCU files
  rcutorture: Provide non-power-of-two Tasks RCU scenarios
  rcutorture: Test SRCU size transitions
  torture: Make torture.sh help message match reality
  rcu-tasks: Set ->percpu_enqueue_shift to zero upon contention
  rcu-tasks: Use order_base_2() instead of ilog2()
  rcu: Create and use an rcu_rdp_cpu_online()
  rcu: Make rcu_barrier() no longer block CPU-hotplug operations
  rcu: Rework rcu_barrier() and callback-migration logic
  rcu: Refactor rcu_barrier() empty-list handling
  rcu: Kill rnp->ofl_seq and use only rcu_state.ofl_lock for exclusion
  torture: Change KVM environment variable to RCUTORTURE
  ...

Author: torvalds

Documentation/admin-guide/kernel-parameters.txt

@@ -4504,6 +4504,8 @@
 			(the least-favored priority).  Otherwise, when
 			RCU_BOOST is not set, valid values are 0-99 and
 			the default is zero (non-realtime operation).
+			When RCU_NOCB_CPU is set, also adjust the
+			priority of NOCB callback kthreads.
 
 	rcutree.rcu_nocb_gp_stride= [KNL]
 			Set the number of NOCB callback kthreads in

MAINTAINERS

@@ -16324,6 +16324,8 @@ F:	tools/testing/selftests/resctrl/
 
 READ-COPY UPDATE (RCU)
 M:	"Paul E. McKenney" <paulmck@kernel.org>
+M:	Frederic Weisbecker <frederic@kernel.org> (kernel/rcu/tree_nocb.h)
+M:	Neeraj Upadhyay <quic_neeraju@quicinc.com> (kernel/rcu/tasks.h)
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

include/linux/rcupdate.h

@@ -84,7 +84,7 @@ static inline int rcu_preempt_depth(void)
 
 /* Internal to kernel */
 void rcu_init(void);
-extern int rcu_scheduler_active __read_mostly;
+extern int rcu_scheduler_active;
 void rcu_sched_clock_irq(int user);
 void rcu_report_dead(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
@@ -924,7 +924,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  *
  *     kvfree_rcu(ptr);
  *
- * where @ptr is a pointer to kvfree().
+ * where @ptr is the pointer to be freed by kvfree().
  *
  * Please note, head-less way of freeing is permitted to
  * use from a context that has to follow might_sleep()

include/linux/rcutree.h

@@ -62,7 +62,7 @@ static inline void rcu_irq_exit_check_preempt(void) { }
 void exit_rcu(void);
 
 void rcu_scheduler_starting(void);
-extern int rcu_scheduler_active __read_mostly;
+extern int rcu_scheduler_active;
 void rcu_end_inkernel_boot(void);
 bool rcu_inkernel_boot_has_ended(void);
 bool rcu_is_watching(void);

include/linux/rcuwait.h

@@ -47,11 +47,7 @@ static inline void prepare_to_rcuwait(struct rcuwait *w)
 	rcu_assign_pointer(w->task, current);
 }
 
-static inline void finish_rcuwait(struct rcuwait *w)
-{
-        rcu_assign_pointer(w->task, NULL);
-	__set_current_state(TASK_RUNNING);
-}
+extern void finish_rcuwait(struct rcuwait *w);
 
 #define rcuwait_wait_event(w, condition, state)				\
 ({									\

include/trace/events/rcu.h

@@ -794,16 +794,15 @@ TRACE_EVENT_RCU(rcu_torture_read,
  * Tracepoint for rcu_barrier() execution.  The string "s" describes
  * the rcu_barrier phase:
  *	"Begin": rcu_barrier() started.
+ *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"EarlyExit": rcu_barrier() piggybacked, thus early exit.
  *	"Inc1": rcu_barrier() piggyback check counter incremented.
- *	"OfflineNoCBQ": rcu_barrier() found offline no-CBs CPU with callbacks.
- *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
- *	"OnlineNQ": rcu_barrier() found online CPU, no callbacks.
+ *	"Inc2": rcu_barrier() piggyback check counter incremented.
  *	"IRQ": An rcu_barrier_callback() callback posted on remote CPU.
  *	"IRQNQ": An rcu_barrier_callback() callback found no callbacks.
- *	"CB": An rcu_barrier_callback() invoked a callback, not the last.
  *	"LastCB": An rcu_barrier_callback() invoked the last callback.
- *	"Inc2": rcu_barrier() piggyback check counter incremented.
+ *	"NQ": rcu_barrier() found a CPU with no callbacks.
+ *	"OnlineQ": rcu_barrier() found online CPU with callbacks.
  * The "cpu" argument is the CPU or -1 if meaningless, the "cnt" argument
  * is the count of remaining callbacks, and "done" is the piggybacking count.
  */

kernel/rcu/rcu_segcblist.h

@@ -56,13 +56,13 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
 static inline void rcu_segcblist_set_flags(struct rcu_segcblist *rsclp,
 					   int flags)
 {
-	rsclp->flags |= flags;
+	WRITE_ONCE(rsclp->flags, rsclp->flags | flags);
 }
 
 static inline void rcu_segcblist_clear_flags(struct rcu_segcblist *rsclp,
 					     int flags)
 {
-	rsclp->flags &= ~flags;
+	WRITE_ONCE(rsclp->flags, rsclp->flags & ~flags);
 }
 
 static inline bool rcu_segcblist_test_flags(struct rcu_segcblist *rsclp,

kernel/rcu/rcutorture.c

@@ -284,7 +284,7 @@ static atomic_t barrier_cbs_invoked;	/* Barrier callbacks invoked. */
 static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */
 static DECLARE_WAIT_QUEUE_HEAD(barrier_wq);
 
-static bool rcu_fwd_cb_nodelay;		/* Short rcu_torture_delay() delays. */
+static atomic_t rcu_fwd_cb_nodelay;	/* Short rcu_torture_delay() delays. */
 
 /*
  * Allocate an element from the rcu_tortures pool.
@@ -387,7 +387,7 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp)
 	 * period, and we want a long delay occasionally to trigger
 	 * force_quiescent_state. */
 
-	if (!READ_ONCE(rcu_fwd_cb_nodelay) &&
+	if (!atomic_read(&rcu_fwd_cb_nodelay) &&
 	    !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
 		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
@@ -674,6 +674,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.cbflood_max	= 50000,
 	.irq_capable	= 1,
 	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcu"
@@ -708,6 +709,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
+	.cbflood_max	= 50000,
 	.irq_capable	= 1,
 	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcud"
@@ -997,7 +999,7 @@ static int rcu_torture_boost(void *arg)
 			goto checkwait;
 
 		/* Wait for the next test interval. */
-		oldstarttime = boost_starttime;
+		oldstarttime = READ_ONCE(boost_starttime);
 		while (time_before(jiffies, oldstarttime)) {
 			schedule_timeout_interruptible(oldstarttime - jiffies);
 			if (stutter_wait("rcu_torture_boost"))
@@ -1041,10 +1043,11 @@ static int rcu_torture_boost(void *arg)
 		 * interval.  Besides, we are running at RT priority,
 		 * so delays should be relatively rare.
 		 */
-		while (oldstarttime == boost_starttime && !kthread_should_stop()) {
+		while (oldstarttime == READ_ONCE(boost_starttime) && !kthread_should_stop()) {
 			if (mutex_trylock(&boost_mutex)) {
 				if (oldstarttime == boost_starttime) {
-					boost_starttime = jiffies + test_boost_interval * HZ;
+					WRITE_ONCE(boost_starttime,
+						   jiffies + test_boost_interval * HZ);
 					n_rcu_torture_boosts++;
 				}
 				mutex_unlock(&boost_mutex);
@@ -1276,7 +1279,7 @@ rcu_torture_writer(void *arg)
 		boot_ended = rcu_inkernel_boot_has_ended();
 		stutter_waited = stutter_wait("rcu_torture_writer");
 		if (stutter_waited &&
-		    !READ_ONCE(rcu_fwd_cb_nodelay) &&
+		    !atomic_read(&rcu_fwd_cb_nodelay) &&
 		    !cur_ops->slow_gps &&
 		    !torture_must_stop() &&
 		    boot_ended)
@@ -2180,7 +2183,6 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 	for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--)
 		if (rfp->n_launders_hist[i].n_launders > 0)
 			break;
-	mutex_lock(&rcu_fwd_mutex); // Serialize histograms.
 	pr_alert("%s: Callback-invocation histogram %d (duration %lu jiffies):",
 		 __func__, rfp->rcu_fwd_id, jiffies - rfp->rcu_fwd_startat);
 	gps_old = rfp->rcu_launder_gp_seq_start;
@@ -2193,7 +2195,6 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 		gps_old = gps;
 	}
 	pr_cont("\n");
-	mutex_unlock(&rcu_fwd_mutex);
 }
 
 /* Callback function for continuous-flood RCU callbacks. */
@@ -2281,6 +2282,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	unsigned long stopat;
 	static DEFINE_TORTURE_RANDOM(trs);
 
+	pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
 	if (!cur_ops->sync)
 		return; // Cannot do need_resched() forward progress testing without ->sync.
 	if (cur_ops->call && cur_ops->cb_barrier) {
@@ -2289,7 +2291,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	}
 
 	/* Tight loop containing cond_resched(). */
-	WRITE_ONCE(rcu_fwd_cb_nodelay, true);
+	atomic_inc(&rcu_fwd_cb_nodelay);
 	cur_ops->sync(); /* Later readers see above write. */
 	if  (selfpropcb) {
 		WRITE_ONCE(fcs.stop, 0);
@@ -2325,6 +2327,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 	if (selfpropcb) {
 		WRITE_ONCE(fcs.stop, 1);
 		cur_ops->sync(); /* Wait for running CB to complete. */
+		pr_alert("%s: Waiting for CBs: %pS() %d\n", __func__, cur_ops->cb_barrier, rfp->rcu_fwd_id);
 		cur_ops->cb_barrier(); /* Wait for queued callbacks. */
 	}
 
@@ -2333,7 +2336,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 		destroy_rcu_head_on_stack(&fcs.rh);
 	}
 	schedule_timeout_uninterruptible(HZ / 10); /* Let kthreads recover. */
-	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+	atomic_dec(&rcu_fwd_cb_nodelay);
 }
 
 /* Carry out call_rcu() forward-progress testing. */
@@ -2353,13 +2356,14 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 	unsigned long stopat;
 	unsigned long stoppedat;
 
+	pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
 	if (READ_ONCE(rcu_fwd_emergency_stop))
 		return; /* Get out of the way quickly, no GP wait! */
 	if (!cur_ops->call)
 		return; /* Can't do call_rcu() fwd prog without ->call. */
 
 	/* Loop continuously posting RCU callbacks. */
-	WRITE_ONCE(rcu_fwd_cb_nodelay, true);
+	atomic_inc(&rcu_fwd_cb_nodelay);
 	cur_ops->sync(); /* Later readers see above write. */
 	WRITE_ONCE(rfp->rcu_fwd_startat, jiffies);
 	stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES;
@@ -2414,6 +2418,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 	n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb);
 	cver = READ_ONCE(rcu_torture_current_version) - cver;
 	gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
+	pr_alert("%s: Waiting for CBs: %pS() %d\n", __func__, cur_ops->cb_barrier, rfp->rcu_fwd_id);
 	cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */
 	(void)rcu_torture_fwd_prog_cbfree(rfp);
 
@@ -2427,11 +2432,13 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 			 n_launders, n_launders_sa,
 			 n_max_gps, n_max_cbs, cver, gps);
 		atomic_long_add(n_max_cbs, &rcu_fwd_max_cbs);
+		mutex_lock(&rcu_fwd_mutex); // Serialize histograms.
 		rcu_torture_fwd_cb_hist(rfp);
+		mutex_unlock(&rcu_fwd_mutex);
 	}
 	schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
-	WRITE_ONCE(rcu_fwd_cb_nodelay, false);
+	atomic_dec(&rcu_fwd_cb_nodelay);
 }
 
 
@@ -2511,7 +2518,7 @@ static int rcu_torture_fwd_prog(void *args)
 			firsttime = false;
 			WRITE_ONCE(rcu_fwd_seq, rcu_fwd_seq + 1);
 		} else {
-			while (READ_ONCE(rcu_fwd_seq) == oldseq)
+			while (READ_ONCE(rcu_fwd_seq) == oldseq && !torture_must_stop())
 				schedule_timeout_interruptible(1);
 			oldseq = READ_ONCE(rcu_fwd_seq);
 		}
@@ -2905,8 +2912,10 @@ rcu_torture_cleanup(void)
 	int i;
 
 	if (torture_cleanup_begin()) {
-		if (cur_ops->cb_barrier != NULL)
+		if (cur_ops->cb_barrier != NULL) {
+			pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier);
 			cur_ops->cb_barrier();
+		}
 		return;
 	}
 	if (!cur_ops) {
@@ -2961,8 +2970,10 @@ rcu_torture_cleanup(void)
 	 * Wait for all RCU callbacks to fire, then do torture-type-specific
 	 * cleanup operations.
 	 */
-	if (cur_ops->cb_barrier != NULL)
+	if (cur_ops->cb_barrier != NULL) {
+		pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier);
 		cur_ops->cb_barrier();
+	}
 	if (cur_ops->cleanup != NULL)
 		cur_ops->cleanup();
 

kernel/rcu/tasks.h

@@ -123,7 +123,7 @@ static struct rcu_tasks rt_name =							\
 	.call_func = call,								\
 	.rtpcpu = &rt_name ## __percpu,							\
 	.name = n,									\
-	.percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS) + 1,				\
+	.percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS),				\
 	.percpu_enqueue_lim = 1,							\
 	.percpu_dequeue_lim = 1,							\
 	.barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex),		\
@@ -302,7 +302,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 	if (unlikely(needadjust)) {
 		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
 		if (rtp->percpu_enqueue_lim != nr_cpu_ids) {
-			WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1);
+			WRITE_ONCE(rtp->percpu_enqueue_shift, 0);
 			WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids);
 			smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids);
 			pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
@@ -417,7 +417,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
 	if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) {
 		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
 		if (rtp->percpu_enqueue_lim > 1) {
-			WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids) + 1);
+			WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids));
 			smp_store_release(&rtp->percpu_enqueue_lim, 1);
 			rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu();
 			pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name);