srcu: Expedited grace periods with reduced memory contention

Commit f60d231a87c5 ("srcu: Crude control of expedited grace periods")
introduced a per-srcu_struct atomic counter to track outstanding
requests for grace periods.  This works, but represents a memory-contention
bottleneck.  This commit therefore uses the srcu_node combining tree
to remove this bottleneck.

This commit adds new ->srcu_gp_seq_needed_exp fields to the
srcu_data, srcu_node, and srcu_struct structures, which track the
farthest-in-the-future grace period that must be expedited, which in
turn requires that all nearer-term grace periods also be expedited.
Requests for expediting start with the srcu_data structure, run up
through the srcu_node tree, and end at the srcu_struct structure.
Note that it may be necessary to expedite a grace period that just
now started, and this is handled by a new srcu_funnel_exp_start()
function, which is invoked when the grace period itself is already
in its way, but when that grace period was not marked as expedited.

A new srcu_get_delay() function returns zero if there is at least one
expedited SRCU grace period in flight, or SRCU_INTERVAL otherwise.
This function is used to calculate delays:  Normal grace periods
are allowed to extend in order to cover more requests with a given
grace-period computation, which decreases per-request overhead.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Mike Galbraith <efault@gmx.de>

1 files changed, 3 insertions, 1 deletions

diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 3865717df124..86df48d3e97b 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -43,6 +43,7 @@ struct srcu_data {
 	spinlock_t lock ____cacheline_internodealigned_in_smp;
 	struct rcu_segcblist srcu_cblist;	/* List of callbacks.*/
 	unsigned long srcu_gp_seq_needed;	/* Furthest future GP needed. */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	bool srcu_cblist_invoking;		/* Invoking these CBs? */
 	struct delayed_work work;		/* Context for CB invoking. */
 	struct rcu_head srcu_barrier_head;	/* For srcu_barrier() use. */
@@ -63,6 +64,7 @@ struct srcu_node {
 						/*  is > ->srcu_gq_seq. */
 	unsigned long srcu_data_have_cbs[4];	/* Which srcu_data structs */
 						/*  have CBs for given GP? */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	struct srcu_node *srcu_parent;		/* Next up in tree. */
 	int grplo;				/* Least CPU for node. */
 	int grphi;				/* Biggest CPU for node. */
@@ -81,7 +83,7 @@ struct srcu_struct {
 	unsigned int srcu_idx;			/* Current rdr array element. */
 	unsigned long srcu_gp_seq;		/* Grace-period seq #. */
 	unsigned long srcu_gp_seq_needed;	/* Latest gp_seq needed. */
-	atomic_t srcu_exp_cnt;			/* # ongoing expedited GPs. */
+	unsigned long srcu_gp_seq_needed_exp;	/* Furthest future exp GP. */
 	struct srcu_data __percpu *sda;		/* Per-CPU srcu_data array. */
 	unsigned long srcu_barrier_seq;		/* srcu_barrier seq #. */
 	struct mutex srcu_barrier_mutex;	/* Serialize barrier ops. */