srcu: Make Tiny SRCU use full-sized grace-period counters

This commit makes Tiny SRCU use full-sized grace-period counters to
further avoid counter-wrap issues when using polled grace-period APIs.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

include/linux/srcutiny.h

@@ -15,10 +15,10 @@
 
 struct srcu_struct {
 	short srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
-	unsigned short srcu_idx;	/* Current reader array element in bit 0x2. */
-	unsigned short srcu_idx_max;	/* Furthest future srcu_idx request. */
 	u8 srcu_gp_running;		/* GP workqueue running? */
 	u8 srcu_gp_waiting;		/* GP waiting for readers? */
+	unsigned long srcu_idx;		/* Current reader array element in bit 0x2. */
+	unsigned long srcu_idx_max;	/* Furthest future srcu_idx request. */
 	struct swait_queue_head srcu_wq;
 					/* Last srcu_read_unlock() wakes GP. */
 	struct rcu_head *srcu_cb_head;	/* Pending callbacks: Head. */
@@ -82,7 +82,7 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 	int idx;
 
 	idx = ((data_race(READ_ONCE(ssp->srcu_idx)) + 1) & 0x2) >> 1;
-	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd) gp: %hu->%hu\n",
+	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd) gp: %lu->%lu\n",
 		 tt, tf, idx,
 		 data_race(READ_ONCE(ssp->srcu_lock_nesting[!idx])),
 		 data_race(READ_ONCE(ssp->srcu_lock_nesting[idx])),

kernel/rcu/srcutiny.c

@@ -117,7 +117,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	struct srcu_struct *ssp;
 
 	ssp = container_of(wp, struct srcu_struct, srcu_work);
-	if (ssp->srcu_gp_running || USHORT_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
+	if (ssp->srcu_gp_running || ULONG_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
 		return; /* Already running or nothing to do. */
 
 	/* Remove recently arrived callbacks and wait for readers. */
@@ -150,17 +150,17 @@ void srcu_drive_gp(struct work_struct *wp)
 	 * straighten that out.
 	 */
 	WRITE_ONCE(ssp->srcu_gp_running, false);
-	if (USHORT_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
+	if (ULONG_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max)))
 		schedule_work(&ssp->srcu_work);
 }
 EXPORT_SYMBOL_GPL(srcu_drive_gp);
 
 static void srcu_gp_start_if_needed(struct srcu_struct *ssp)
 {
-	unsigned short cookie;
+	unsigned long cookie;
 
 	cookie = get_state_synchronize_srcu(ssp);
-	if (USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
+	if (ULONG_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie))
 		return;
 	WRITE_ONCE(ssp->srcu_idx_max, cookie);
 	if (!READ_ONCE(ssp->srcu_gp_running)) {
@@ -215,7 +215,7 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp)
 	barrier();
 	ret = (READ_ONCE(ssp->srcu_idx) + 3) & ~0x1;
 	barrier();
-	return ret & USHRT_MAX;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_srcu);
 
@@ -240,10 +240,10 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu);
  */
 bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie)
 {
-	unsigned short cur_s = READ_ONCE(ssp->srcu_idx);
+	unsigned long cur_s = READ_ONCE(ssp->srcu_idx);
 
 	barrier();
-	return USHORT_CMP_GE(cur_s, cookie) || USHORT_CMP_LT(cur_s, cookie - 3);
+	return ULONG_CMP_GE(cur_s, cookie) || ULONG_CMP_LT(cur_s, cookie - 3);
 }
 EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu);