1 files changed, 121 insertions, 33 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 40e5e3dd253e..da6f5213fb74 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -83,6 +83,9 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nesting = 1,
 	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
 	.dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
+#ifdef CONFIG_RCU_NOCB_CPU
+	.cblist.flags = SEGCBLIST_SOFTIRQ_ONLY,
+#endif
 };
 static struct rcu_state rcu_state = {
 	.level = { &rcu_state.node[0] },
@@ -100,8 +103,10 @@ static struct rcu_state rcu_state = {
 static bool dump_tree;
 module_param(dump_tree, bool, 0444);
 /* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */
-static bool use_softirq = true;
+static bool use_softirq = !IS_ENABLED(CONFIG_PREEMPT_RT);
+#ifndef CONFIG_PREEMPT_RT
 module_param(use_softirq, bool, 0444);
+#endif
 /* Control rcu_node-tree auto-balancing at boot time. */
 static bool rcu_fanout_exact;
 module_param(rcu_fanout_exact, bool, 0444);
@@ -644,7 +649,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	rdp = this_cpu_ptr(&rcu_data);
-	do_nocb_deferred_wakeup(rdp);
 	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
@@ -678,6 +682,50 @@ void rcu_idle_enter(void)
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
 #ifdef CONFIG_NO_HZ_FULL
+
+#if !defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)
+/*
+ * An empty function that will trigger a reschedule on
+ * IRQ tail once IRQs get re-enabled on userspace/guest resume.
+ */
+static void late_wakeup_func(struct irq_work *work)
+{
+}
+
+static DEFINE_PER_CPU(struct irq_work, late_wakeup_work) =
+	IRQ_WORK_INIT(late_wakeup_func);
+
+/*
+ * If either:
+ *
+ * 1) the task is about to enter in guest mode and $ARCH doesn't support KVM generic work
+ * 2) the task is about to enter in user mode and $ARCH doesn't support generic entry.
+ *
+ * In these cases the late RCU wake ups aren't supported in the resched loops and our
+ * last resort is to fire a local irq_work that will trigger a reschedule once IRQs
+ * get re-enabled again.
+ */
+noinstr static void rcu_irq_work_resched(void)
+{
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+	if (IS_ENABLED(CONFIG_GENERIC_ENTRY) && !(current->flags & PF_VCPU))
+		return;
+
+	if (IS_ENABLED(CONFIG_KVM_XFER_TO_GUEST_WORK) && (current->flags & PF_VCPU))
+		return;
+
+	instrumentation_begin();
+	if (do_nocb_deferred_wakeup(rdp) && need_resched()) {
+		irq_work_queue(this_cpu_ptr(&late_wakeup_work));
+	}
+	instrumentation_end();
+}
+
+#else
+static inline void rcu_irq_work_resched(void) { }
+#endif
+
 /**
  * rcu_user_enter - inform RCU that we are resuming userspace.
  *
@@ -692,8 +740,16 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter);
 noinstr void rcu_user_enter(void)
 {
 	lockdep_assert_irqs_disabled();
+
+	/*
+	 * Other than generic entry implementation, we may be past the last
+	 * rescheduling opportunity in the entry code. Trigger a self IPI
+	 * that will fire and reschedule once we resume in user/guest mode.
+	 */
+	rcu_irq_work_resched();
 	rcu_eqs_enter(true);
 }
+
 #endif /* CONFIG_NO_HZ_FULL */
 
 /**
@@ -1495,6 +1551,8 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
 	if (!rcu_segcblist_pend_cbs(&rdp->cblist))
 		return false;
 
+	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPreAcc"));
+
 	/*
 	 * Callbacks are often registered with incomplete grace-period
 	 * information.  Something about the fact that getting exact
@@ -1515,6 +1573,8 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp)
 	else
 		trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB"));
 
+	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPostAcc"));
+
 	return ret;
 }
 
@@ -1765,7 +1825,7 @@ static bool rcu_gp_init(void)
 	 * go offline later.  Please also refer to "Hotplug CPU" section
 	 * of RCU's Requirements documentation.
 	 */
-	rcu_state.gp_state = RCU_GP_ONOFF;
+	WRITE_ONCE(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);
@@ -1831,7 +1891,7 @@ static bool rcu_gp_init(void)
 	 * The grace period cannot complete until the initialization
 	 * process finishes, because this kthread handles both.
 	 */
-	rcu_state.gp_state = RCU_GP_INIT;
+	WRITE_ONCE(rcu_state.gp_state, RCU_GP_INIT);
 	rcu_for_each_node_breadth_first(rnp) {
 		rcu_gp_slow(gp_init_delay);
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -1930,17 +1990,22 @@ static void rcu_gp_fqs_loop(void)
 	ret = 0;
 	for (;;) {
 		if (!ret) {
-			rcu_state.jiffies_force_qs = jiffies + j;
+			WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j);
+			/*
+			 * jiffies_force_qs before RCU_GP_WAIT_FQS state
+			 * update; required for stall checks.
+			 */
+			smp_wmb();
 			WRITE_ONCE(rcu_state.jiffies_kick_kthreads,
 				   jiffies + (j ? 3 * j : 2));
 		}
 		trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 				       TPS("fqswait"));
-		rcu_state.gp_state = RCU_GP_WAIT_FQS;
+		WRITE_ONCE(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;
+		WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS);
 		/* Locking provides needed memory barriers. */
 		/* If grace period done, leave loop. */
 		if (!READ_ONCE(rnp->qsmask) &&
@@ -2054,7 +2119,7 @@ static void rcu_gp_cleanup(void)
 	trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end"));
 	rcu_seq_end(&rcu_state.gp_seq);
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq);
-	rcu_state.gp_state = RCU_GP_IDLE;
+	WRITE_ONCE(rcu_state.gp_state, RCU_GP_IDLE);
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(&rcu_data);
 	if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
@@ -2093,12 +2158,12 @@ static int __noreturn rcu_gp_kthread(void *unused)
 		for (;;) {
 			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
 					       TPS("reqwait"));
-			rcu_state.gp_state = RCU_GP_WAIT_GPS;
+			WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_GPS);
 			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;
+			WRITE_ONCE(rcu_state.gp_state, RCU_GP_DONE_GPS);
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init())
 				break;
@@ -2113,9 +2178,9 @@ static int __noreturn rcu_gp_kthread(void *unused)
 		rcu_gp_fqs_loop();
 
 		/* Handle grace-period end. */
-		rcu_state.gp_state = RCU_GP_CLEANUP;
+		WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANUP);
 		rcu_gp_cleanup();
-		rcu_state.gp_state = RCU_GP_CLEANED;
+		WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANED);
 	}
 }
 
@@ -2430,11 +2495,12 @@ int rcutree_dead_cpu(unsigned int cpu)
 static void rcu_do_batch(struct rcu_data *rdp)
 {
 	int div;
+	bool __maybe_unused empty;
 	unsigned long flags;
 	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
-	long bl, count;
+	long bl, count = 0;
 	long pending, tlimit = 0;
 
 	/* If no callbacks are ready, just return. */
@@ -2471,14 +2537,18 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
 	if (offloaded)
 		rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
+
+	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued"));
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
 	/* Invoke callbacks. */
 	tick_dep_set_task(current, TICK_DEP_BIT_RCU);
 	rhp = rcu_cblist_dequeue(&rcl);
+
 	for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
 		rcu_callback_t f;
 
+		count++;
 		debug_rcu_head_unqueue(rhp);
 
 		rcu_lock_acquire(&rcu_callback_map);
@@ -2492,21 +2562,19 @@ static void rcu_do_batch(struct rcu_data *rdp)
 
 		/*
 		 * Stop only if limit reached and CPU has something to do.
-		 * Note: The rcl structure counts down from zero.
 		 */
-		if (-rcl.len >= bl && !offloaded &&
+		if (count >= bl && !offloaded &&
 		    (need_resched() ||
 		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
 			break;
 		if (unlikely(tlimit)) {
 			/* only call local_clock() every 32 callbacks */
-			if (likely((-rcl.len & 31) || local_clock() < tlimit))
+			if (likely((count & 31) || local_clock() < tlimit))
 				continue;
 			/* Exceeded the time limit, so leave. */
 			break;
 		}
-		if (offloaded) {
-			WARN_ON_ONCE(in_serving_softirq());
+		if (!in_serving_softirq()) {
 			local_bh_enable();
 			lockdep_assert_irqs_enabled();
 			cond_resched_tasks_rcu_qs();
@@ -2517,15 +2585,13 @@ static void rcu_do_batch(struct rcu_data *rdp)
 
 	local_irq_save(flags);
 	rcu_nocb_lock(rdp);
-	count = -rcl.len;
 	rdp->n_cbs_invoked += count;
 	trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
 			    is_idle_task(current), rcu_is_callbacks_kthread());
 
 	/* Update counts and requeue any remaining callbacks. */
 	rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
-	smp_mb(); /* List handling before counting for rcu_barrier(). */
-	rcu_segcblist_insert_count(&rdp->cblist, &rcl);
+	rcu_segcblist_add_len(&rdp->cblist, -count);
 
 	/* Reinstate batch limit if we have worked down the excess. */
 	count = rcu_segcblist_n_cbs(&rdp->cblist);
@@ -2543,9 +2609,12 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	 * The following usually indicates a double call_rcu().  To track
 	 * this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.
 	 */
-	WARN_ON_ONCE(count == 0 && !rcu_segcblist_empty(&rdp->cblist));
+	empty = rcu_segcblist_empty(&rdp->cblist);
+	WARN_ON_ONCE(count == 0 && !empty);
 	WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-		     count != 0 && rcu_segcblist_empty(&rdp->cblist));
+		     count != 0 && empty);
+	WARN_ON_ONCE(count == 0 && rcu_segcblist_n_segment_cbs(&rdp->cblist) != 0);
+	WARN_ON_ONCE(!empty && rcu_segcblist_n_segment_cbs(&rdp->cblist) == 0);
 
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
@@ -2566,6 +2635,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 void rcu_sched_clock_irq(int user)
 {
 	trace_rcu_utilization(TPS("Start scheduler-tick"));
+	lockdep_assert_irqs_disabled();
 	raw_cpu_inc(rcu_data.ticks_this_gp);
 	/* The load-acquire pairs with the store-release setting to true. */
 	if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) {
@@ -2579,6 +2649,7 @@ void rcu_sched_clock_irq(int user)
 	rcu_flavor_sched_clock_irq(user);
 	if (rcu_pending(user))
 		invoke_rcu_core();
+	lockdep_assert_irqs_disabled();
 
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
@@ -2688,7 +2759,7 @@ 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 = rcu_segcblist_is_offloaded(&rdp->cblist);
+	const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);
 
 	if (cpu_is_offline(smp_processor_id()))
 		return;
@@ -2708,17 +2779,17 @@ static __latent_entropy void rcu_core(void)
 
 	/* No grace period and unregistered callbacks? */
 	if (!rcu_gp_in_progress() &&
-	    rcu_segcblist_is_enabled(&rdp->cblist) && !offloaded) {
-		local_irq_save(flags);
+	    rcu_segcblist_is_enabled(&rdp->cblist) && do_batch) {
+		rcu_nocb_lock_irqsave(rdp, flags);
 		if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 			rcu_accelerate_cbs_unlocked(rnp, rdp);
-		local_irq_restore(flags);
+		rcu_nocb_unlock_irqrestore(rdp, flags);
 	}
 
 	rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
 
 	/* If there are callbacks ready, invoke them. */
-	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist) &&
+	if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) &&
 	    likely(READ_ONCE(rcu_scheduler_fully_active)))
 		rcu_do_batch(rdp);
 
@@ -2941,6 +3012,7 @@ static void check_cb_ovld(struct rcu_data *rdp)
 static void
 __call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
+	static atomic_t doublefrees;
 	unsigned long flags;
 	struct rcu_data *rdp;
 	bool was_alldone;
@@ -2954,8 +3026,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 		 * Use rcu:rcu_callback trace event to find the previous
 		 * time callback was passed to __call_rcu().
 		 */
-		WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pS()!!!\n",
-			  head, head->func);
+		if (atomic_inc_return(&doublefrees) < 4) {
+			pr_err("%s(): Double-freed CB %p->%pS()!!!  ", __func__, head, head->func);
+			mem_dump_obj(head);
+		}
 		WRITE_ONCE(head->func, rcu_leak_callback);
 		return;
 	}
@@ -2989,6 +3063,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 		trace_rcu_callback(rcu_state.name, head,
 				   rcu_segcblist_n_cbs(&rdp->cblist));
 
+	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued"));
+
 	/* Go handle any RCU core processing required. */
 	if (unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) {
 		__call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */
@@ -3498,6 +3574,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		goto unlock_return;
 	}
 
+	kasan_record_aux_stack(ptr);
 	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
 	if (!success) {
 		run_page_cache_worker(krcp);
@@ -3747,6 +3824,8 @@ static int rcu_pending(int user)
 	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
 
+	lockdep_assert_irqs_disabled();
+
 	/* Check for CPU stalls, if enabled. */
 	check_cpu_stall(rdp);
 
@@ -4001,12 +4080,18 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rcu_state.n_force_qs;
 	rdp->blimit = blimit;
-	if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */
-	    !rcu_segcblist_is_offloaded(&rdp->cblist))
-		rcu_segcblist_init(&rdp->cblist);  /* Re-enable callbacks. */
 	rdp->dynticks_nesting = 1;	/* CPU not up, no tearing. */
 	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
+	/*
+	 * Lock in case the CB/GP kthreads are still around handling
+	 * old callbacks (longer term we should flush all callbacks
+	 * before completing CPU offline)
+	 */
+	rcu_nocb_lock(rdp);
+	if (rcu_segcblist_empty(&rdp->cblist)) /* No early-boot CBs? */
+		rcu_segcblist_init(&rdp->cblist);  /* Re-enable callbacks. */
+	rcu_nocb_unlock(rdp);
 
 	/*
 	 * Add CPU to leaf rcu_node pending-online bitmask.  Any needed
@@ -4159,6 +4244,9 @@ void rcu_report_dead(unsigned int cpu)
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	// Do any dangling deferred wakeups.
+	do_nocb_deferred_wakeup(rdp);
+
 	/* QS for any half-done expedited grace period. */
 	preempt_disable();
 	rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));