All of lore.kernel.org
 help / color / mirror / Atom feed
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: virtualization@lists.linux-foundation.org
Cc: netdev@vger.kernel.org, mst@redhat.com, jasowang@redhat.com,
	Willem de Bruijn <willemb@google.com>
Subject: [PATCH rfc 3/3] virtio-net: support transmit timestamp
Date: Mon, 28 Dec 2020 11:22:33 -0500	[thread overview]
Message-ID: <20201228162233.2032571-4-willemdebruijn.kernel@gmail.com> (raw)
In-Reply-To: <20201228162233.2032571-1-willemdebruijn.kernel@gmail.com>

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

Add optional delivery time (SO_TXTIME) offload for virtio-net.

The Linux TCP/IP stack tries to avoid bursty transmission and network
congestion through pacing: computing an skb delivery time based on
congestion information. Userspace protocol implementations can achieve
the same with SO_TXTIME. This may also reduce scheduling jitter and
improve RTT estimation.

Pacing can be implemented in ETF or FQ qdiscs or offloaded to NIC
hardware. Allow guests to offload for the same reasons.

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        | 24 +++++++++++++++++-------
 include/uapi/linux/virtio_net.h |  1 +
 2 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 57744bb6a141..d40be688aed0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -207,6 +207,9 @@ struct virtnet_info {
 	/* Host will pass CLOCK_TAI receive time to the guest */
 	bool has_rx_tstamp;
 
+	/* Guest will pass CLOCK_TAI delivery time to the host */
+	bool has_tx_tstamp;
+
 	/* Has control virtqueue */
 	bool has_cvq;
 
@@ -1550,7 +1553,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct virtio_net_hdr_v1_hash *ht;
+	struct virtio_net_hdr_v12 *h12;
 	int num_sg;
 	unsigned hdr_len = vi->hdr_len;
 	bool can_push;
@@ -1575,13 +1578,15 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
 
-	ht = (void *)hdr;
+	h12 = (void *)hdr;
 	if (vi->has_tx_hash) {
-		ht->hash_value = cpu_to_virtio32(vi->vdev, skb->hash);
-		ht->hash_report = skb->l4_hash ? VIRTIO_NET_HASH_REPORT_L4 :
-						 VIRTIO_NET_HASH_REPORT_OTHER;
-		ht->hash_state = VIRTIO_NET_HASH_STATE_DEFAULT;
+		h12->hash.value = cpu_to_virtio32(vi->vdev, skb->hash);
+		h12->hash.report = skb->l4_hash ? VIRTIO_NET_HASH_REPORT_L4 :
+						  VIRTIO_NET_HASH_REPORT_OTHER;
+		h12->hash.flow_state = VIRTIO_NET_HASH_STATE_DEFAULT;
 	}
+	if (vi->has_tx_tstamp)
+		h12->tstamp = cpu_to_virtio64(vi->vdev, skb->tstamp);
 
 	sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2));
 	if (can_push) {
@@ -3089,6 +3094,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 		vi->hdr_len = sizeof(struct virtio_net_hdr_v12);
 	}
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_TX_TSTAMP)) {
+		vi->has_tx_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;
@@ -3279,7 +3289,7 @@ 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_RX_TSTAMP
+	VIRTIO_NET_F_TX_HASH, VIRTIO_NET_F_RX_TSTAMP, VIRTIO_NET_F_TX_TSTAMP
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 0ffe2eeebd4a..da017a47791d 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_TX_TSTAMP	  54	/* Guest sets TAI delivery time */
 #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 */
-- 
2.29.2.729.g45daf8777d-goog


WARNING: multiple messages have this Message-ID (diff)
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: virtualization@lists.linux-foundation.org
Cc: netdev@vger.kernel.org, Willem de Bruijn <willemb@google.com>,
	mst@redhat.com
Subject: [PATCH rfc 3/3] virtio-net: support transmit timestamp
Date: Mon, 28 Dec 2020 11:22:33 -0500	[thread overview]
Message-ID: <20201228162233.2032571-4-willemdebruijn.kernel@gmail.com> (raw)
In-Reply-To: <20201228162233.2032571-1-willemdebruijn.kernel@gmail.com>

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

Add optional delivery time (SO_TXTIME) offload for virtio-net.

The Linux TCP/IP stack tries to avoid bursty transmission and network
congestion through pacing: computing an skb delivery time based on
congestion information. Userspace protocol implementations can achieve
the same with SO_TXTIME. This may also reduce scheduling jitter and
improve RTT estimation.

Pacing can be implemented in ETF or FQ qdiscs or offloaded to NIC
hardware. Allow guests to offload for the same reasons.

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        | 24 +++++++++++++++++-------
 include/uapi/linux/virtio_net.h |  1 +
 2 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 57744bb6a141..d40be688aed0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -207,6 +207,9 @@ struct virtnet_info {
 	/* Host will pass CLOCK_TAI receive time to the guest */
 	bool has_rx_tstamp;
 
+	/* Guest will pass CLOCK_TAI delivery time to the host */
+	bool has_tx_tstamp;
+
 	/* Has control virtqueue */
 	bool has_cvq;
 
@@ -1550,7 +1553,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
 	const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest;
 	struct virtnet_info *vi = sq->vq->vdev->priv;
-	struct virtio_net_hdr_v1_hash *ht;
+	struct virtio_net_hdr_v12 *h12;
 	int num_sg;
 	unsigned hdr_len = vi->hdr_len;
 	bool can_push;
@@ -1575,13 +1578,15 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 	if (vi->mergeable_rx_bufs)
 		hdr->num_buffers = 0;
 
-	ht = (void *)hdr;
+	h12 = (void *)hdr;
 	if (vi->has_tx_hash) {
-		ht->hash_value = cpu_to_virtio32(vi->vdev, skb->hash);
-		ht->hash_report = skb->l4_hash ? VIRTIO_NET_HASH_REPORT_L4 :
-						 VIRTIO_NET_HASH_REPORT_OTHER;
-		ht->hash_state = VIRTIO_NET_HASH_STATE_DEFAULT;
+		h12->hash.value = cpu_to_virtio32(vi->vdev, skb->hash);
+		h12->hash.report = skb->l4_hash ? VIRTIO_NET_HASH_REPORT_L4 :
+						  VIRTIO_NET_HASH_REPORT_OTHER;
+		h12->hash.flow_state = VIRTIO_NET_HASH_STATE_DEFAULT;
 	}
+	if (vi->has_tx_tstamp)
+		h12->tstamp = cpu_to_virtio64(vi->vdev, skb->tstamp);
 
 	sg_init_table(sq->sg, skb_shinfo(skb)->nr_frags + (can_push ? 1 : 2));
 	if (can_push) {
@@ -3089,6 +3094,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 		vi->hdr_len = sizeof(struct virtio_net_hdr_v12);
 	}
 
+	if (virtio_has_feature(vdev, VIRTIO_NET_F_TX_TSTAMP)) {
+		vi->has_tx_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;
@@ -3279,7 +3289,7 @@ 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_RX_TSTAMP
+	VIRTIO_NET_F_TX_HASH, VIRTIO_NET_F_RX_TSTAMP, VIRTIO_NET_F_TX_TSTAMP
 
 static unsigned int features[] = {
 	VIRTNET_FEATURES,
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 0ffe2eeebd4a..da017a47791d 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_TX_TSTAMP	  54	/* Guest sets TAI delivery time */
 #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 */
-- 
2.29.2.729.g45daf8777d-goog

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

  parent reply	other threads:[~2020-12-28 16:23 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-28 16:22 [PATCH rfc 0/3] virtio-net: add tx-hash, rx-tstamp and tx-tstamp Willem de Bruijn
2020-12-28 16:22 ` Willem de Bruijn
2020-12-28 16:22 ` [PATCH rfc 1/3] virtio-net: support transmit hash report Willem de Bruijn
2020-12-28 16:22   ` Willem de Bruijn
2020-12-28 16:28   ` Michael S. Tsirkin
2020-12-28 16:28     ` Michael S. Tsirkin
2020-12-28 16:47     ` Willem de Bruijn
2020-12-28 16:47       ` Willem de Bruijn
2020-12-28 17:22       ` Michael S. Tsirkin
2020-12-28 17:22         ` Michael S. Tsirkin
2020-12-29  1:19         ` Willem de Bruijn
2020-12-29  1:19           ` Willem de Bruijn
2020-12-28 21:36   ` Michael S. Tsirkin
2020-12-28 21:36     ` Michael S. Tsirkin
2020-12-29  1:23     ` Willem de Bruijn
2020-12-29  1:23       ` Willem de Bruijn
2020-12-28 16:22 ` [PATCH rfc 2/3] virtio-net: support receive timestamp Willem de Bruijn
2020-12-28 16:22   ` Willem de Bruijn
2020-12-28 17:28   ` Michael S. Tsirkin
2020-12-28 17:28     ` Michael S. Tsirkin
2020-12-28 19:30     ` Willem de Bruijn
2020-12-28 19:30       ` Willem de Bruijn
2020-12-28 21:32       ` Michael S. Tsirkin
2020-12-28 21:32         ` Michael S. Tsirkin
2020-12-29  1:05         ` Willem de Bruijn
2020-12-29  1:05           ` Willem de Bruijn
2020-12-29  9:17           ` Jason Wang
2020-12-29  9:17             ` Jason Wang
2020-12-29 14:20             ` Willem de Bruijn
2020-12-29 14:20               ` Willem de Bruijn
2020-12-30  8:38               ` Jason Wang
2020-12-30  8:38                 ` Jason Wang
2020-12-28 22:59   ` Jakub Kicinski
2020-12-29  0:57     ` Willem de Bruijn
2020-12-29  0:57       ` Willem de Bruijn
2020-12-30  8:44       ` Jason Wang
2020-12-30  8:44         ` Jason Wang
2020-12-30 12:30       ` Richard Cochran
2021-02-02 13:05   ` kernel test robot
2021-02-02 13:05     ` kernel test robot
2021-02-02 13:05     ` kernel test robot
2021-02-02 14:08   ` Michael S. Tsirkin
2021-02-02 14:08     ` Michael S. Tsirkin
2021-02-02 22:17     ` Willem de Bruijn
2021-02-02 22:17       ` Willem de Bruijn
2021-02-02 23:02       ` Michael S. Tsirkin
2021-02-02 23:02         ` Michael S. Tsirkin
2021-02-02 23:43         ` Willem de Bruijn
2021-02-02 23:43           ` Willem de Bruijn
2020-12-28 16:22 ` Willem de Bruijn [this message]
2020-12-28 16:22   ` [PATCH rfc 3/3] virtio-net: support transmit timestamp Willem de Bruijn
2020-12-30 12:38   ` Richard Cochran
2020-12-30 15:25     ` Willem de Bruijn
2020-12-30 15:25       ` Willem de Bruijn
2021-02-02 13:47   ` kernel test robot
2021-02-02 13:47     ` kernel test robot
2021-02-02 13:47     ` kernel test robot
2020-12-28 17:29 ` [PATCH rfc 0/3] virtio-net: add tx-hash, rx-tstamp and tx-tstamp Michael S. Tsirkin
2020-12-28 17:29   ` Michael S. Tsirkin
2020-12-28 19:51   ` Willem de Bruijn
2020-12-28 19:51     ` Willem de Bruijn
2020-12-28 21:38     ` Michael S. Tsirkin
2020-12-28 21:38       ` Michael S. Tsirkin
2020-12-29  1:14       ` Willem de Bruijn
2020-12-29  1:14         ` Willem de Bruijn
2021-01-06 20:32         ` Willem de Bruijn
2021-01-06 20:32           ` Willem de Bruijn

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201228162233.2032571-4-willemdebruijn.kernel@gmail.com \
    --to=willemdebruijn.kernel@gmail.com \
    --cc=jasowang@redhat.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=willemb@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.