On Tue, Feb 02, 2021 at 05:17:13PM -0500, Willem de Bruijn wrote:

On Tue, Feb 2, 2021 at 9:08 AM Michael S. Tsirkin [off-list ref] wrote:

quoted

On Mon, Dec 28, 2020 at 11:22:32AM -0500, Willem de Bruijn wrote:

quoted

From: Willem de Bruijn <willemb@google.com>

Add optional PTP hardware timestamp offload for virtio-net.

Accurate RTT measurement requires timestamps close to the wire.
Introduce virtio feature VIRTIO_NET_F_RX_TSTAMP. If negotiated, the
virtio-net header is expanded with room for a timestamp. A host may
pass receive timestamps for all or some packets. A timestamp is valid
if non-zero.

The timestamp straddles (virtual) hardware domains. Like PTP, use
international atomic time (CLOCK_TAI) as global clock base. It is
guest responsibility to sync with host, e.g., through kvm-clock.

Signed-off-by: Willem de Bruijn <willemb@google.com>
---
 drivers/net/virtio_net.c        | 20 +++++++++++++++++++-
 include/uapi/linux/virtio_net.h | 12 ++++++++++++
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b917b7333928..57744bb6a141 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c

@@ -204,6 +204,9 @@ struct virtnet_info {
      /* Guest will pass tx path info to the host */
      bool has_tx_hash;

+     /* Host will pass CLOCK_TAI receive time to the guest */
+     bool has_rx_tstamp;
+
      /* Has control virtqueue */
      bool has_cvq;

@@ -292,6 +295,13 @@ static inline struct virtio_net_hdr_mrg_rxbuf *skb_vnet_hdr(struct sk_buff *skb)
      return (struct virtio_net_hdr_mrg_rxbuf *)skb->cb;
 }

+static inline struct virtio_net_hdr_v12 *skb_vnet_hdr_12(struct sk_buff *skb)
+{
+     BUILD_BUG_ON(sizeof(struct virtio_net_hdr_v12) > sizeof(skb->cb));
+
+     return (void *)skb->cb;
+}
+
 /*
  * private is used to chain pages for big packets, put the whole
  * most recent used list in the beginning for reuse

@@ -1082,6 +1092,9 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
              goto frame_err;
      }

+     if (vi->has_rx_tstamp)
+             skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(skb_vnet_hdr_12(skb)->tstamp);
+
      skb_record_rx_queue(skb, vq2rxq(rq->vq));
      skb->protocol = eth_type_trans(skb, dev);
      pr_debug("Receiving skb proto 0x%04x len %i type %i\n",

@@ -3071,6 +3084,11 @@ static int virtnet_probe(struct virtio_device *vdev)
              vi->hdr_len = sizeof(struct virtio_net_hdr_v1_hash);
      }

+     if (virtio_has_feature(vdev, VIRTIO_NET_F_RX_TSTAMP)) {
+             vi->has_rx_tstamp = true;
+             vi->hdr_len = sizeof(struct virtio_net_hdr_v12);
+     }
+
      if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) ||
          virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
              vi->any_header_sg = true;

@@ -3261,7 +3279,7 @@ static struct virtio_device_id id_table[] = {
      VIRTIO_NET_F_CTRL_MAC_ADDR, \
      VIRTIO_NET_F_MTU, VIRTIO_NET_F_CTRL_GUEST_OFFLOADS, \
      VIRTIO_NET_F_SPEED_DUPLEX, VIRTIO_NET_F_STANDBY, \
-     VIRTIO_NET_F_TX_HASH
+     VIRTIO_NET_F_TX_HASH, VIRTIO_NET_F_RX_TSTAMP

 static unsigned int features[] = {
      VIRTNET_FEATURES,

diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index f6881b5b77ee..0ffe2eeebd4a 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h

@@ -57,6 +57,7 @@
                                       * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23        /* Set MAC address */

+#define VIRTIO_NET_F_RX_TSTAMP         55    /* Host sends TAI receive time */
 #define VIRTIO_NET_F_TX_HASH   56    /* Guest sends hash report */
 #define VIRTIO_NET_F_HASH_REPORT  57 /* Supports hash report */
 #define VIRTIO_NET_F_RSS       60    /* Supports RSS RX steering */

@@ -182,6 +183,17 @@ struct virtio_net_hdr_v1_hash {
      };
 };

+struct virtio_net_hdr_v12 {
+     struct virtio_net_hdr_v1 hdr;
+     struct {
+             __le32 value;
+             __le16 report;
+             __le16 flow_state;
+     } hash;
+     __virtio32 reserved;

Does endian-ness matter? If not - just u32?

I suppose it does not matter as long as this is reserved. Should it be
__le32, at least?

One can safely assign 0 to any value.

quoted

quoted

+     __virtio64 tstamp;
+};
+

Given it's only available in modern devices, I think we
can make this __le64 tstamp.

Actually, would it be possible to make new features available on
legacy devices? There is nothing in the features bits precluding it.

I think it won't be possible: you are using feature bit 55,
legacy devices have up to 32 feature bits. And of course the
header looks a bit differently for legacy, you would have to add special
code to handle that when mergeable buffers are off.

I have a revised patchset almost ready. I suppose I should send it as
RFC again, and simultaneously file an OASIS ballot for each feature?

that would be great.

-- 
MST