srcu: Check for srcu_read_lock_lite() across all CPUs

If srcu_read_lock_lite() is used on a given srcu_struct structure, then
the grace-period processing must do synchronize_rcu() instead of smp_mb()
between the scans of the ->srcu_unlock_count[] and ->srcu_lock_count[]
counters.  Currently, it does that by testing the SRCU_READ_FLAVOR_LITE
bit of the ->srcu_reader_flavor mask, which works well.  But only if
the CPU running that srcu_struct structure's grace period has previously
executed srcu_read_lock_lite(), which might not be the case, especially
just after that srcu_struct structure has been created and initialized.

This commit therefore updates the srcu_readers_unlock_idx() function
to OR together the ->srcu_reader_flavor masks from all CPUs, and
then make the srcu_readers_active_idx_check() function that test the
SRCU_READ_FLAVOR_LITE bit in the resulting mask.

Note that the srcu_readers_unlock_idx() function is already scanning all
the CPUs to sum up the ->srcu_unlock_count[] fields and that this is on
the grace-period slow path, hence no concerns about the small amount of
extra work.

Reported-by: Neeraj Upadhyay <Neeraj.Upadhyay@amd.com>
Closes: https://lore.kernel.org/all/d07e8f4a-d5ff-4c8e-8e61-50db285c57e9@amd.com/
Fixes: c0f08d6 ("srcu: Add srcu_read_lock_lite() and srcu_read_unlock_lite()")
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Neeraj Upadhyay <Neeraj.Upadhyay@amd.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

Author: paulmckrcu

kernel/rcu/srcutree.c

@@ -458,7 +458,7 @@ static bool srcu_readers_lock_idx(struct srcu_struct *ssp, int idx, bool gp, uns
  * Returns approximate total of the readers' ->srcu_unlock_count[] values
  * for the rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx, unsigned long *rdm)
 {
 	int cpu;
 	unsigned long mask = 0;
@@ -468,11 +468,11 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
 		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
 		sum += atomic_long_read(&sdp->srcu_unlock_count[idx]);
-		if (IS_ENABLED(CONFIG_PROVE_RCU))
-			mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
+		mask = mask | READ_ONCE(sdp->srcu_reader_flavor);
 	}
 	WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && (mask & (mask - 1)),
 		  "Mixed reader flavors for srcu_struct at %ps.\n", ssp);
+	*rdm = mask;
 	return sum;
 }
 
@@ -482,10 +482,12 @@ static unsigned long srcu_readers_unlock_idx(struct srcu_struct *ssp, int idx)
  */
 static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx)
 {
-	bool did_gp = !!(raw_cpu_read(ssp->sda->srcu_reader_flavor) & SRCU_READ_FLAVOR_LITE);
+	bool did_gp;
+	unsigned long rdm;
 	unsigned long unlocks;
 
-	unlocks = srcu_readers_unlock_idx(ssp, idx);
+	unlocks = srcu_readers_unlock_idx(ssp, idx, &rdm);
+	did_gp = !!(rdm & SRCU_READ_FLAVOR_LITE);
 
 	/*
 	 * Make sure that a lock is always counted if the corresponding