Commit 384f77f4 authored Apr 12, 2018 by Paul E. McKenney

rcu: The rcu_gp_cleanup() function does not need cpu_needs_another_gp()

All of the cpu_needs_another_gp() function's checks (except for
newly arrived callbacks) have been subsumed into the rcu_gp_cleanup()
function's scan of the rcu_node tree. This commit therefore drops the
call to cpu_needs_another_gp(). The check for newly arrived callbacks
is supplied by rcu_accelerate_cbs(). Any needed advancing (as in the
earlier rcu_advance_cbs() call) will be supplied when the corresponding
CPU becomes aware of the end of the now-completed grace period.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Nicholas Piggin <npiggin@gmail.com>

parent 665f08f1

kernel/rcu/tree.c

+2 −4

Original line number	Diff line number	Diff line
		@@ -2150,11 +2150,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
		needgp = true;
		}
		/* Advance CBs to reduce false positives below. */
		needgp = rcu_advance_cbs(rsp, rnp, rdp) \|\| needgp;
		if (needgp \|\| cpu_needs_another_gp(rsp, rdp)) {
		if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
		trace_rcu_grace_period(rsp->name,
		READ_ONCE(rsp->gpnum),
		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
		TPS("newreq"));
		}
		WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);

Admin message