Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Alex Kogan <alex.kogan@oracle.com>
To:     linux@armlinux.org.uk, peterz@infradead.org, mingo@redhat.com,
        will.deacon@arm.com, arnd@arndb.de, longman@redhat.com,
        linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org,
        linux-kernel@vger.kernel.org, tglx@linutronix.de, bp@alien8.de,
        hpa@zytor.com, x86@kernel.org, guohanjun@huawei.com,
        jglauber@marvell.com
Cc:     steven.sistare@oracle.com, daniel.m.jordan@oracle.com,
        alex.kogan@oracle.com, dave.dice@oracle.com,
        rahul.x.yadav@oracle.com
Subject: [PATCH v5 4/5] locking/qspinlock: Introduce starvation avoidance into CNA
Date:   Wed, 16 Oct 2019 00:29:02 -0400
Message-Id: <20191016042903.61081-5-alex.kogan@oracle.com>
In-Reply-To: <20191016042903.61081-1-alex.kogan@oracle.com>
References: <20191016042903.61081-1-alex.kogan@oracle.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Keep track of the number of intra-node lock handoffs, and force
inter-node handoff once this number reaches a preset threshold.

Signed-off-by: Alex Kogan <alex.kogan@oracle.com>
Reviewed-by: Steve Sistare <steven.sistare@oracle.com>
---
 kernel/locking/qspinlock.c     |  3 +++
 kernel/locking/qspinlock_cna.h | 30 +++++++++++++++++++++++++++---
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 6d8c4a52e44e..1d0d884308ef 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -597,6 +597,9 @@ EXPORT_SYMBOL(queued_spin_lock_slowpath);
 #if !defined(_GEN_CNA_LOCK_SLOWPATH) && defined(CONFIG_NUMA_AWARE_SPINLOCKS)
 #define _GEN_CNA_LOCK_SLOWPATH
 
+#undef pv_init_node
+#define pv_init_node			cna_init_node
+
 #undef pv_wait_head_or_lock
 #define pv_wait_head_or_lock		cna_pre_scan
 
diff --git a/kernel/locking/qspinlock_cna.h b/kernel/locking/qspinlock_cna.h
index 4d095f742d31..b92a6f9a19db 100644
--- a/kernel/locking/qspinlock_cna.h
+++ b/kernel/locking/qspinlock_cna.h
@@ -50,9 +50,19 @@ struct cna_node {
 	struct mcs_spinlock	mcs;
 	int			numa_node;
 	u32			encoded_tail;
-	u32			pre_scan_result; /* 0 or an encoded tail */
+	u32			pre_scan_result; /* 0, 1 or an encoded tail */
+	u32			intra_count;
 };
 
+/*
+ * Controls the threshold for the number of intra-node lock hand-offs. It can
+ * be tuned and depend, e.g., on the number of CPUs per node. For now,
+ * choose a value that provides reasonable long-term fairness without
+ * sacrificing performance compared to a version that does not have any
+ * fairness guarantees.
+ */
+#define INTRA_NODE_HANDOFF_THRESHOLD (1 << 16)
+
 static void __init cna_init_nodes_per_cpu(unsigned int cpu)
 {
 	struct mcs_spinlock *base = per_cpu_ptr(&qnodes[0].mcs, cpu);
@@ -86,6 +96,11 @@ static void __init cna_init_nodes(void)
 }
 early_initcall(cna_init_nodes);
 
+static __always_inline void cna_init_node(struct mcs_spinlock *node)
+{
+	((struct cna_node *)node)->intra_count = 0;
+}
+
 static inline bool cna_try_change_tail(struct qspinlock *lock, u32 val,
 				       struct mcs_spinlock *node)
 {
@@ -215,7 +230,13 @@ __always_inline u32 cna_pre_scan(struct qspinlock *lock,
 {
 	struct cna_node *cn = (struct cna_node *)node;
 
-	cn->pre_scan_result = cna_scan_main_queue(node, node);
+	/*
+	 * setting @pre_scan_result to 1 indicates that no post-scan
+	 * should be made in cna_pass_lock()
+	 */
+	cn->pre_scan_result =
+		cn->intra_count == INTRA_NODE_HANDOFF_THRESHOLD ?
+			1 : cna_scan_main_queue(node, node);
 
 	return 0;
 }
@@ -234,7 +255,7 @@ static inline void cna_pass_lock(struct mcs_spinlock *node,
 	 * pre-scan, and if so, try to find it in post-scan starting from the
 	 * node where pre-scan stopped (stored in @pre_scan_result)
 	 */
-	if (scan > 0)
+	if (scan > 1)
 		scan = cna_scan_main_queue(node, decode_tail(scan));
 
 	if (!scan) { /* if found a successor from the same numa node */
@@ -245,6 +266,9 @@ static inline void cna_pass_lock(struct mcs_spinlock *node,
 		 * to pass the lock
 		 */
 		val = node->locked + (node->locked == 0);
+		/* inc @intra_count if the secondary queue is not empty */
+		((struct cna_node *)next_holder)->intra_count =
+			cn->intra_count + (node->locked > 1);
 	} else if (node->locked > 1) {	  /* if secondary queue is not empty */
 		/* next holder will be the first node in the secondary queue */
 		tail_2nd = decode_tail(node->locked);
-- 
2.11.0 (Apple Git-81)