[PATCH] virtio_ring: use smp_store_mb

["Michael S. Tsirkin" <mst@redhat.com>]

We need a full barrier after writing out event index, using smp_store_mb
there seems better than open-coding.
As usual, we need a wrapper to account for strong barriers/non smp.

It's tempting to use this in vhost as well, for that, we'll
need a variant of smp_store_mb that works on __user pointers.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---

Seems to give a speedup on my box but I'm less sure about this one.  E.g. as
xchng faster than mfence on all/most intel CPUs? Anyone has an opinion?

 include/linux/virtio_ring.h  | 14 ++++++++++++++
 drivers/virtio/virtio_ring.c | 15 +++++++++------
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 0135c16..8912189 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -47,6 +47,20 @@ static inline void virtio_wmb(bool weak_barriers)
 		wmb();
 }
 
+static inline void virtio_store_mb(bool weak_barriers,
+				   __virtio16 *p, __virtio16 v)
+{
+#ifdef CONFIG_SMP
+	if (weak_barriers)
+		smp_store_mb(*p, v);
+	else
+#endif
+	{
+		WRITE_ONCE(*p, v);
+		mb();
+	}
+}
+
 static inline __virtio16 virtio_load_acquire(bool weak_barriers, __virtio16 *p)
 {
 	if (!weak_barriers) {
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index f822cab..b0aea67 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -517,10 +517,10 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	/* If we expect an interrupt for the next entry, tell host
 	 * by writing event index and flush out the write before
 	 * the read in the next get_buf call. */
-	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
-		vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx);
-		virtio_mb(vq->weak_barriers);
-	}
+	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
+		virtio_store_mb(vq->weak_barriers,
+				&vring_used_event(&vq->vring),
+				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
 
 #ifdef DEBUG
 	vq->last_add_time_valid = false;
@@ -653,8 +653,11 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 	}
 	/* TODO: tune this threshold */
 	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
-	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs);
-	virtio_mb(vq->weak_barriers);
+
+	virtio_store_mb(vq->weak_barriers,
+			&vring_used_event(&vq->vring),
+			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
+
 	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
 		END_USE(vq);
 		return false;
-- 
MST