On 2018年09月10日 06:44, Willem de Bruijn wrote:
From: Willem de Bruijn <will...@google.com>
Implement ethtool .set_coalesce (-C) and .get_coalesce (-c) handlers.
Interrupt moderation is currently not supported, so these accept and
display the default settings of 0 usec and 1 frame.
Toggle tx napi through a bit in tx-frames. So as to not interfere
with possible future interrupt moderation, use bit 10, well outside
the reasonable range of real interrupt moderation values.
Changes are not atomic. The tx IRQ, napi BH and transmit path must
be quiesced when switching modes. Only allow changing this setting
when the device is down.
I cook a fixup, and it looks works in my setup:
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b320b6b14749..9181c3f2f832 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2204,10 +2204,17 @@ static int virtnet_set_coalesce(struct
net_device *dev,
return -EINVAL;
if (napi_weight ^ vi->sq[0].napi.weight) {
- if (dev->flags & IFF_UP)
- return -EBUSY;
- for (i = 0; i < vi->max_queue_pairs; i++)
+ for (i = 0; i < vi->max_queue_pairs; i++) {
+ struct netdev_queue *txq =
+ netdev_get_tx_queue(vi->dev, i);
+
+ virtnet_napi_tx_disable(&vi->sq[i].napi);
+ __netif_tx_lock_bh(txq);
vi->sq[i].napi.weight = napi_weight;
+ __netif_tx_unlock_bh(txq);
+ virtnet_napi_tx_enable(vi, vi->sq[i].vq,
+ &vi->sq[i].napi);
+ }
}
return 0;
The only left case is the speculative tx polling in RX NAPI. I think we
don't need to care in this case since it was not a must for correctness.
Link: https://patchwork.ozlabs.org/patch/948149/
Suggested-by: Jason Wang <jasow...@redhat.com>
Signed-off-by: Willem de Bruijn <will...@google.com>
---
drivers/net/virtio_net.c | 52 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 52 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 765920905226..b320b6b14749 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -66,6 +66,8 @@ DECLARE_EWMA(pkt_len, 0, 64)
#define VIRTNET_DRIVER_VERSION "1.0.0"
+static const u32 ethtool_coalesce_napi_mask = (1UL << 10);
+
static const unsigned long guest_offloads[] = {
VIRTIO_NET_F_GUEST_TSO4,
VIRTIO_NET_F_GUEST_TSO6,
@@ -2181,6 +2183,54 @@ static int virtnet_get_link_ksettings(struct net_device
*dev,
return 0;
}
+static int virtnet_set_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *ec)
+{
+ const struct ethtool_coalesce ec_default = {
+ .cmd = ETHTOOL_SCOALESCE,
+ .rx_max_coalesced_frames = 1,
I think rx part is no necessary.
Thanks
+ .tx_max_coalesced_frames = 1,
+ };
+ struct virtnet_info *vi = netdev_priv(dev);
+ int i, napi_weight = 0;
+
+ if (ec->tx_max_coalesced_frames & ethtool_coalesce_napi_mask) {
+ ec->tx_max_coalesced_frames &= ~ethtool_coalesce_napi_mask;
+ napi_weight = NAPI_POLL_WEIGHT;
+ }
+
+ /* disallow changes to fields not explicitly tested above */
+ if (memcmp(ec, &ec_default, sizeof(ec_default)))
+ return -EINVAL;
+
+ if (napi_weight ^ vi->sq[0].napi.weight) {
+ if (dev->flags & IFF_UP)
+ return -EBUSY;
+ for (i = 0; i < vi->max_queue_pairs; i++)
+ vi->sq[i].napi.weight = napi_weight;
+ }
+
+ return 0;
+}
+
+static int virtnet_get_coalesce(struct net_device *dev,
+ struct ethtool_coalesce *ec)
+{
+ const struct ethtool_coalesce ec_default = {
+ .cmd = ETHTOOL_GCOALESCE,
+ .rx_max_coalesced_frames = 1,
+ .tx_max_coalesced_frames = 1,
+ };
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ memcpy(ec, &ec_default, sizeof(ec_default));
+
+ if (vi->sq[0].napi.weight)
+ ec->tx_max_coalesced_frames |= ethtool_coalesce_napi_mask;
+
+ return 0;
+}
+
static void virtnet_init_settings(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
@@ -2219,6 +2269,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = {
.get_ts_info = ethtool_op_get_ts_info,
.get_link_ksettings = virtnet_get_link_ksettings,
.set_link_ksettings = virtnet_set_link_ksettings,
+ .set_coalesce = virtnet_set_coalesce,
+ .get_coalesce = virtnet_get_coalesce,
};
static void virtnet_freeze_down(struct virtio_device *vdev)
