Merge tag 'rcu.2021.11.01a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Miscellaneous fixes

 - Torture-test updates for smp_call_function(), most notably improved
   checking of module parameters.

 - Tasks-trace RCU updates that fix a number of rare but important
   race-condition bugs.

 - Other torture-test updates, most notably better checking of module
   parameters. In addition, rcutorture may once again be run on
   CONFIG_PREEMPT_RT kernels.

 - Torture-test scripting updates, most notably specifying the new
   CONFIG_KCSAN_STRICT kconfig option rather than maintaining an
   ever-changing list of individual KCSAN kconfig options.

* tag 'rcu.2021.11.01a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (46 commits)
  rcu: Fix rcu_dynticks_curr_cpu_in_eqs() vs noinstr
  rcu: Always inline rcu_dynticks_task*_{enter,exit}()
  torture: Make kvm-remote.sh print size of downloaded tarball
  torture: Allot 1G of memory for scftorture runs
  tools/rcu: Add an extract-stall script
  scftorture: Warn on individual scf_torture_init() error conditions
  scftorture: Count reschedule IPIs
  scftorture: Account for weight_resched when checking for all zeroes
  scftorture: Shut down if nonsensical arguments given
  scftorture: Allow zero weight to exclude an smp_call_function*() category
  rcu: Avoid unneeded function call in rcu_read_unlock()
  rcu-tasks: Update comments to cond_resched_tasks_rcu_qs()
  rcu-tasks: Fix IPI failure handling in trc_wait_for_one_reader
  rcu-tasks: Fix read-side primitives comment for call_rcu_tasks_trace
  rcu-tasks: Clarify read side section info for rcu_tasks_rude GP primitives
  rcu-tasks: Correct comparisons for CPU numbers in show_stalled_task_trace
  rcu-tasks: Correct firstreport usage in check_all_holdout_tasks_trace
  rcu-tasks: Fix s/rcu_add_holdout/trc_add_holdout/ typo in comment
  rcu-tasks: Move RTGS_WAIT_CBS to beginning of rcu_tasks_kthread() loop
  rcu-tasks: Fix s/instruction/instructions/ typo in comment
  ...

1 files changed, 16 insertions, 20 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index bce848e50512..ef8d36f580fc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -327,7 +327,7 @@ static void rcu_dynticks_eqs_online(void)
  */
 static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
 {
-	return !(atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
+	return !(arch_atomic_read(this_cpu_ptr(&rcu_data.dynticks)) & 0x1);
 }
 
 /*
@@ -1219,8 +1219,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
 	unsigned long jtsq;
-	bool *rnhqp;
-	bool *ruqp;
 	struct rcu_node *rnp = rdp->mynode;
 
 	/*
@@ -1285,17 +1283,15 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * is set way high.
 	 */
 	jtsq = READ_ONCE(jiffies_to_sched_qs);
-	ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu);
-	rnhqp = per_cpu_ptr(&rcu_data.rcu_need_heavy_qs, rdp->cpu);
-	if (!READ_ONCE(*rnhqp) &&
+	if (!READ_ONCE(rdp->rcu_need_heavy_qs) &&
 	    (time_after(jiffies, rcu_state.gp_start + jtsq * 2) ||
 	     time_after(jiffies, rcu_state.jiffies_resched) ||
 	     rcu_state.cbovld)) {
-		WRITE_ONCE(*rnhqp, true);
+		WRITE_ONCE(rdp->rcu_need_heavy_qs, true);
 		/* Store rcu_need_heavy_qs before rcu_urgent_qs. */
-		smp_store_release(ruqp, true);
+		smp_store_release(&rdp->rcu_urgent_qs, true);
 	} else if (time_after(jiffies, rcu_state.gp_start + jtsq)) {
-		WRITE_ONCE(*ruqp, true);
+		WRITE_ONCE(rdp->rcu_urgent_qs, true);
 	}
 
 	/*
@@ -1309,7 +1305,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (tick_nohz_full_cpu(rdp->cpu) &&
 	    (time_after(jiffies, READ_ONCE(rdp->last_fqs_resched) + jtsq * 3) ||
 	     rcu_state.cbovld)) {
-		WRITE_ONCE(*ruqp, true);
+		WRITE_ONCE(rdp->rcu_urgent_qs, true);
 		resched_cpu(rdp->cpu);
 		WRITE_ONCE(rdp->last_fqs_resched, jiffies);
 	}
@@ -1779,6 +1775,8 @@ static noinline_for_stack bool rcu_gp_init(void)
 	 */
 	WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF);
 	rcu_for_each_leaf_node(rnp) {
+		// Wait for CPU-hotplug operations that might have
+		// started before this grace period did.
 		smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values.
 		firstseq = READ_ONCE(rnp->ofl_seq);
 		if (firstseq & 0x1)
@@ -1907,7 +1905,7 @@ static void rcu_gp_fqs(bool first_time)
 	struct rcu_node *rnp = rcu_get_root();
 
 	WRITE_ONCE(rcu_state.gp_activity, jiffies);
-	rcu_state.n_force_qs++;
+	WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1);
 	if (first_time) {
 		/* Collect dyntick-idle snapshots. */
 		force_qs_rnp(dyntick_save_progress_counter);
@@ -2358,7 +2356,7 @@ rcu_check_quiescent_state(struct rcu_data *rdp)
 int rcutree_dying_cpu(unsigned int cpu)
 {
 	bool blkd;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_node *rnp = rdp->mynode;
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
@@ -2550,7 +2548,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
 	if (count == 0 && rdp->qlen_last_fqs_check != 0) {
 		rdp->qlen_last_fqs_check = 0;
-		rdp->n_force_qs_snap = rcu_state.n_force_qs;
+		rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 	} else if (count < rdp->qlen_last_fqs_check - qhimark)
 		rdp->qlen_last_fqs_check = count;
 
@@ -2898,10 +2896,10 @@ static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head,
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = DEFAULT_MAX_RCU_BLIMIT;
-			if (rcu_state.n_force_qs == rdp->n_force_qs_snap &&
+			if (READ_ONCE(rcu_state.n_force_qs) == rdp->n_force_qs_snap &&
 			    rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
 				rcu_force_quiescent_state();
-			rdp->n_force_qs_snap = rcu_state.n_force_qs;
+			rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 			rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
 		}
 	}
@@ -4128,10 +4126,9 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->qlen_last_fqs_check = 0;
-	rdp->n_force_qs_snap = rcu_state.n_force_qs;
+	rdp->n_force_qs_snap = READ_ONCE(rcu_state.n_force_qs);
 	rdp->blimit = blimit;
 	rdp->dynticks_nesting = 1;	/* CPU not up, no tearing. */
-	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
 
 	/*
@@ -4251,6 +4248,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	mask = rdp->grpmask;
 	WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1);
 	WARN_ON_ONCE(!(rnp->ofl_seq & 0x1));
+	rcu_dynticks_eqs_online();
 	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);
@@ -4296,9 +4294,7 @@ void rcu_report_dead(unsigned int cpu)
 	do_nocb_deferred_wakeup(rdp);
 
 	/* QS for any half-done expedited grace period. */
-	preempt_disable();
-	rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
-	preempt_enable();
+	rcu_report_exp_rdp(rdp);
 	rcu_preempt_deferred_qs(current);
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */