vhost: replace SMP with thread fence for control path

Simply replace the smp barriers with atomic thread fence for vhost control
path, if there are no synchronization points.

Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
index b83cf63..c69b105 100644 (file)
--- a/lib/librte_vhost/vhost.c
+++ b/lib/librte_vhost/vhost.c
@@ -106,7 +106,7 @@ __vhost_log_write(struct virtio_net *dev, uint64_t addr, uint64_t len)
                return;
 
        /* To make sure guest memory updates are committed before logging */
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        page = addr / VHOST_LOG_PAGE;
        while (page * VHOST_LOG_PAGE < addr + len) {
@@ -144,7 +144,7 @@ __vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
        if (unlikely(!dev->log_base))
                return;
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        log_base = (unsigned long *)(uintptr_t)dev->log_base;
 
@@ -163,7 +163,7 @@ __vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
 #endif
        }
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        vq->log_cache_nb_elem = 0;
 }
@@ -190,7 +190,7 @@ vhost_log_cache_page(struct virtio_net *dev, struct vhost_virtqueue *vq,
                 * No more room for a new log cache entry,
                 * so write the dirty log map directly.
                 */
-               rte_smp_wmb();
+               rte_atomic_thread_fence(__ATOMIC_RELEASE);
                vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
 
                return;
@@ -1097,11 +1097,11 @@ rte_vhost_clr_inflight_desc_split(int vid, uint16_t vring_idx,
        if (unlikely(idx >= vq->size))
                return -1;
 
-       rte_smp_mb();
+       rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
 
        vq->inflight_split->desc[idx].inflight = 0;
 
-       rte_smp_mb();
+       rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
 
        vq->inflight_split->used_idx = last_used_idx;
        return 0;
@@ -1140,11 +1140,11 @@ rte_vhost_clr_inflight_desc_packed(int vid, uint16_t vring_idx,
        if (unlikely(head >= vq->size))
                return -1;
 
-       rte_smp_mb();
+       rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
 
        inflight_info->desc[head].inflight = 0;
 
-       rte_smp_mb();
+       rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
 
        inflight_info->old_free_head = inflight_info->free_head;
        inflight_info->old_used_idx = inflight_info->used_idx;
@@ -1330,7 +1330,7 @@ vhost_enable_notify_packed(struct virtio_net *dev,
                        vq->avail_wrap_counter << 15;
        }
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        vq->device_event->flags = flags;
        return 0;

diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 361c9f7..23e11ff 100644 (file)
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -728,7 +728,7 @@ static __rte_always_inline void
 vhost_vring_call_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
 {
        /* Flush used->idx update before we read avail->flags. */
-       rte_smp_mb();
+       rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
 
        /* Don't kick guest if we don't reach index specified by guest. */
        if (dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX)) {
@@ -770,7 +770,7 @@ vhost_vring_call_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
        bool signalled_used_valid, kick = false;
 
        /* Flush used desc update. */
-       rte_smp_mb();
+       rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
 
        if (!(dev->features & (1ULL << VIRTIO_RING_F_EVENT_IDX))) {
                if (vq->driver_event->flags !=
@@ -796,7 +796,7 @@ vhost_vring_call_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
                goto kick;
        }
 
-       rte_smp_rmb();
+       rte_atomic_thread_fence(__ATOMIC_ACQUIRE);
 
        off_wrap = vq->driver_event->off_wrap;
        off = off_wrap & ~(1 << 15);

diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 45c8ac0..6e94a9b 100644 (file)
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -1690,7 +1690,7 @@ vhost_check_queue_inflights_split(struct virtio_net *dev,
 
        if (inflight_split->used_idx != used->idx) {
                inflight_split->desc[last_io].inflight = 0;
-               rte_smp_mb();
+               rte_atomic_thread_fence(__ATOMIC_SEQ_CST);
                inflight_split->used_idx = used->idx;
        }
 

diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.c
index e145fcb..fec08b2 100644 (file)
--- a/lib/librte_vhost/virtio_net.c
+++ b/lib/librte_vhost/virtio_net.c
@@ -1663,7 +1663,7 @@ uint16_t rte_vhost_poll_enqueue_completed(int vid, uint16_t queue_id,
                        queue_id, 0, count - vq->async_last_pkts_n);
        n_pkts_cpl += vq->async_last_pkts_n;
 
-       rte_smp_wmb();
+       rte_atomic_thread_fence(__ATOMIC_RELEASE);
 
        while (likely((n_pkts_put < count) && n_inflight)) {
                uint16_t info_idx = (start_idx + n_pkts_put) & (vq_size - 1);