[PATCH 5.5 034/367] rcu: Use *_ONCE() to protect lockless ->expmask accesses

[Greg Kroah-Hartman]

From: Paul E. McKenney <paulmck@xxxxxxxxxx>

commit 15c7c972cd26d89a26788e609c53b5a465324a6c upstream.

The rcu_node structure's ->expmask field is accessed locklessly when
starting a new expedited grace period and when reporting an expedited
RCU CPU stall warning.  This commit therefore handles the former by
taking a snapshot of ->expmask while the lock is held and the latter
by applying READ_ONCE() to lockless reads and WRITE_ONCE() to the
corresponding updates.

Link: https://lore.kernel.org/lkml/CANpmjNNmSOagbTpffHr4=Yedckx9Rm2NuGqC9UqE+AOz5f1-ZQ@xxxxxxxxxxxxxx
Reported-by: syzbot+134336b86f728d6e55a0@xxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Acked-by: Marco Elver <elver@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 kernel/rcu/tree_exp.h |   19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -134,7 +134,7 @@ static void __maybe_unused sync_exp_rese
 	rcu_for_each_node_breadth_first(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
-		rnp->expmask = rnp->expmaskinit;
+		WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
@@ -211,7 +211,7 @@ static void __rcu_report_exp_rnp(struct
 		rnp = rnp->parent;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
-		rnp->expmask &= ~mask;
+		WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
 	}
 }
 
@@ -241,7 +241,7 @@ static void rcu_report_exp_cpu_mult(stru
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
-	rnp->expmask &= ~mask;
+	WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask);
 	__rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */
 }
 
@@ -372,12 +372,10 @@ static void sync_rcu_exp_select_node_cpu
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 
 	/* IPI the remaining CPUs for expedited quiescent state. */
-	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
+	for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) {
 		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
-		if (!(mask_ofl_ipi & mask))
-			continue;
 retry_ipi:
 		if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) {
 			mask_ofl_test |= mask;
@@ -491,7 +489,7 @@ static void synchronize_sched_expedited_
 				struct rcu_data *rdp;
 
 				mask = leaf_node_cpu_bit(rnp, cpu);
-				if (!(rnp->expmask & mask))
+				if (!(READ_ONCE(rnp->expmask) & mask))
 					continue;
 				ndetected++;
 				rdp = per_cpu_ptr(&rcu_data, cpu);
@@ -503,7 +501,8 @@ static void synchronize_sched_expedited_
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
 			jiffies - jiffies_start, rcu_state.expedited_sequence,
-			rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
+			READ_ONCE(rnp_root->expmask),
+			".T"[!!rnp_root->exp_tasks]);
 		if (ndetected) {
 			pr_err("blocking rcu_node structures:");
 			rcu_for_each_node_breadth_first(rnp) {
@@ -513,7 +512,7 @@ static void synchronize_sched_expedited_
 					continue;
 				pr_cont(" l=%u:%d-%d:%#lx/%c",
 					rnp->level, rnp->grplo, rnp->grphi,
-					rnp->expmask,
+					READ_ONCE(rnp->expmask),
 					".T"[!!rnp->exp_tasks]);
 			}
 			pr_cont("\n");
@@ -521,7 +520,7 @@ static void synchronize_sched_expedited_
 		rcu_for_each_leaf_node(rnp) {
 			for_each_leaf_node_possible_cpu(rnp, cpu) {
 				mask = leaf_node_cpu_bit(rnp, cpu);
-				if (!(rnp->expmask & mask))
+				if (!(READ_ONCE(rnp->expmask) & mask))
 					continue;
 				dump_cpu_task(cpu);
 			}