srcu: Convert ->srcu_lock_count and ->srcu_unlock_count to atomic

NMI-safe variants of srcu_read_lock() and srcu_read_unlock() are needed
by printk(), which on many architectures entails read-modify-write
atomic operations.  This commit prepares Tree SRCU for this change by
making both ->srcu_lock_count and ->srcu_unlock_count by atomic_long_t.

[ paulmck: Apply feedback from John Ogness. ]

Link: https://lore.kernel.org/all/20220910221947.171557773@linutronix.de/

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Petr Mladek <pmladek@suse.com>

Author: paulmckrcu

include/linux/srcutree.h

@@ -23,8 +23,8 @@ struct srcu_struct;
  */
 struct srcu_data {
 	/* Read-side state. */
-	unsigned long srcu_lock_count[2];	/* Locks per CPU. */
-	unsigned long srcu_unlock_count[2];	/* Unlocks per CPU. */
+	atomic_long_t srcu_lock_count[2];	/* Locks per CPU. */
+	atomic_long_t srcu_unlock_count[2];	/* Unlocks per CPU. */
 
 	/* Update-side state. */
 	spinlock_t __private lock ____cacheline_internodealigned_in_smp;

kernel/rcu/srcutree.c

@@ -417,7 +417,7 @@ static unsigned long srcu_readers_lock_idx(struct srcu_struct *ssp, int idx)
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
+		sum += atomic_long_read(&cpuc->srcu_lock_count[idx]);
 	}
 	return sum;
 }
@@ -434,7 +434,7 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
+		sum += atomic_long_read(&cpuc->srcu_unlock_count[idx]);
 	}
 	return sum;
 }
@@ -503,10 +503,10 @@ static bool srcu_readers_active(struct srcu_struct *ssp)
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *cpuc = per_cpu_ptr(ssp->sda, cpu);
 
-		sum += READ_ONCE(cpuc->srcu_lock_count[0]);
-		sum += READ_ONCE(cpuc->srcu_lock_count[1]);
-		sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
-		sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
+		sum += atomic_long_read(&cpuc->srcu_lock_count[0]);
+		sum += atomic_long_read(&cpuc->srcu_lock_count[1]);
+		sum -= atomic_long_read(&cpuc->srcu_unlock_count[0]);
+		sum -= atomic_long_read(&cpuc->srcu_unlock_count[1]);
 	}
 	return sum;
 }
@@ -636,7 +636,7 @@ int __srcu_read_lock(struct srcu_struct *ssp)
 	int idx;
 
 	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
-	this_cpu_inc(ssp->sda->srcu_lock_count[idx]);
+	this_cpu_inc(ssp->sda->srcu_lock_count[idx].counter);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -650,7 +650,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 {
 	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	this_cpu_inc(ssp->sda->srcu_unlock_count[idx]);
+	this_cpu_inc(ssp->sda->srcu_unlock_count[idx].counter);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -1687,17 +1687,17 @@ void srcu_torture_stats_print(struct srcu_struct *ssp, char *tt, char *tf)
 			struct srcu_data *sdp;
 
 			sdp = per_cpu_ptr(ssp->sda, cpu);
-			u0 = data_race(sdp->srcu_unlock_count[!idx]);
-			u1 = data_race(sdp->srcu_unlock_count[idx]);
+			u0 = data_race(atomic_long_read(&sdp->srcu_unlock_count[!idx]));
+			u1 = data_race(atomic_long_read(&sdp->srcu_unlock_count[idx]));
 
 			/*
 			 * Make sure that a lock is always counted if the corresponding
 			 * unlock is counted.
 			 */
 			smp_rmb();
 
-			l0 = data_race(sdp->srcu_lock_count[!idx]);
-			l1 = data_race(sdp->srcu_lock_count[idx]);
+			l0 = data_race(atomic_long_read(&sdp->srcu_lock_count[!idx]));
+			l1 = data_race(atomic_long_read(&sdp->srcu_lock_count[idx]));
 
 			c0 = l0 - u0;
 			c1 = l1 - u1;