srcu: Make Tiny SRCU use multi-bit grace-period counter

There is a need for a polling interface for SRCU grace periods.  This
polling needs to distinguish between an SRCU instance being idle on the
one hand or in the middle of a grace period on the other.  This commit
therefore converts the Tiny SRCU srcu_struct structure's srcu_idx from
a defacto boolean to a free-running counter, using the bottom bit to
indicate that a grace period is in progress.  The second-from-bottom
bit is thus used as the index returned by srcu_read_lock().

Link: https://lore.kernel.org/rcu/20201112201547.GF3365678@moria.home.lan/
Reported-by: Kent Overstreet <kent.overstreet@gmail.com>
[ paulmck: Fix ->srcu_lock_nesting[] indexing per Neeraj Upadhyay. ]
Reviewed-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

include/linux/srcutiny.h

@@ -15,7 +15,7 @@
 
 struct srcu_struct {
 	short srcu_lock_nesting[2];	/* srcu_read_lock() nesting depth. */
-	short srcu_idx;			/* Current reader array element. */
+	unsigned short srcu_idx;	/* Current reader array element in bit 0x2. */
 	u8 srcu_gp_running;		/* GP workqueue running? */
 	u8 srcu_gp_waiting;		/* GP waiting for readers? */
 	struct swait_queue_head srcu_wq;
@@ -59,7 +59,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp)
 {
 	int idx;
 
-	idx = READ_ONCE(ssp->srcu_idx);
+	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1);
 	return idx;
 }
@@ -80,7 +80,7 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp,
 {
 	int idx;
 
-	idx = READ_ONCE(ssp->srcu_idx) & 0x1;
+	idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1;
 	pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n",
 		 tt, tf, idx,
 		 READ_ONCE(ssp->srcu_lock_nesting[!idx]),

kernel/rcu/srcutiny.c

@@ -124,11 +124,12 @@ void srcu_drive_gp(struct work_struct *wp)
 	ssp->srcu_cb_head = NULL;
 	ssp->srcu_cb_tail = &ssp->srcu_cb_head;
 	local_irq_enable();
-	idx = ssp->srcu_idx;
-	WRITE_ONCE(ssp->srcu_idx, !ssp->srcu_idx);
+	idx = (ssp->srcu_idx & 0x2) / 2;
+	WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
 	WRITE_ONCE(ssp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
 	swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx]));
 	WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+	WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1);
 
 	/* Invoke the callbacks we removed above. */
 	while (lh) {