public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: aerosouund <aerosound161@gmail.com>
To: passt-dev@passt.top
Cc: eperezma@redhat.com, Ammar Yasser <aerosound161@gmail.com>
Subject: [PATCH 6/7] tap: Implement the pasta vhost-net to-guest path
Date: Sat,  5 Sep 2026 00:28:25 +0300	[thread overview]
Message-ID: <20260904212826.41027-7-aerosound161@gmail.com> (raw)
In-Reply-To: <20260904212826.41027-1-aerosound161@gmail.com>

From: Ammar Yasser <aerosound161@gmail.com>

Add a vhost argument to tap_send_frames_pasta(). Callers pass it to say
whether this send should go through vhost-net, and when it does sending
goes through tap_send_frames_vhost(), which takes a descriptor from the
queue shared with the kernel for each iov and points it at that iov's
base address, chaining the bufs_per_frame descriptors of a frame
together so the guest receives it in one go.

tx_reap() reclaims the descriptors the kernel has finished with, walking
each used chain to its end so that every descriptor in it is counted as
free again.

Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Signed-off-by: Ammar Yasser <aerosound161@gmail.com>
---
 tap.c | 145 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 142 insertions(+), 3 deletions(-)

diff --git a/tap.c b/tap.c
index c730535..0f51e62 100644
--- a/tap.c
+++ b/tap.c
@@ -359,12 +359,146 @@ void tap_icmp6_send(const struct ctx *c,
 	tap_send_single(c, buf, l4len + ((char *)icmp6h - buf));
 }
 
+/**
+ * tx_reap() - Reclaim the descriptors the kernel has already processed
+ */
+static void tx_reap(void)
+{
+	struct vring_used *used = &vring_used_all[1].used;
+	uint16_t used_idx = le16toh(used->idx);
+
+	smp_rmb();
+
+	/* increment last_used_idx until it reaches the kernel's used index */
+	while (vhost_vq_state[1].last_used_idx != used_idx) {
+		uint16_t last_used, desc_id;
+
+		last_used = vhost_vq_state[1].last_used_idx % VHOST_NDESCS;
+		desc_id = le32toh(used->ring[last_used].id);
+
+		for (;;) {
+			/* keep going until we find a descriptor without the
+			 * next flag
+			 */
+			vhost_vq_state[1].num_free++;
+			if (!(le16toh(vring_desc[1][desc_id].flags) &
+			      VRING_DESC_F_NEXT))
+				break;
+
+			/* this descriptor wasn't the last, set desc_id to the
+			 * next one and keep going
+			 */
+			desc_id = le16toh(vring_desc[1][desc_id].next);
+		}
+
+		vhost_vq_state[1].last_used_idx++;
+	}
+}
+
+/**
+ * tap_send_frames_vhost() - Send multiple frames to the pasta tap
+ * @c:			Execution context
+ * @iov:		Array of buffers
+ * @bufs_per_frame:	Number of buffers (iovec entries) per frame
+ * @nframes:		Number of frames to send
+ *
+ * @iov must have total length @bufs_per_frame * @nframes, with each set of
+ * @bufs_per_frame contiguous buffers representing a single frame.
+ *
+ * Return: number of frames successfully sent
+ */
+static size_t tap_send_frames_vhost(const struct ctx *c,
+				    const struct iovec *iov,
+				    size_t bufs_per_frame, size_t nframes)
+{
+	struct vring_avail *avail = &vring_avail_all[1].avail;
+	size_t processed_frames = 0;
+	size_t i;
+
+	/* reclaim descriptors if we don't have enough available buffers to
+	 * perform this send
+	 */
+	if (vhost_vq_state[1].num_free < bufs_per_frame * nframes)
+		tx_reap();
+
+	for (i = 0; i < nframes; i++) {
+		uint16_t head;
+		size_t j;
+
+		/* it's likely that tx_reap returned to us less than
+		 * bufs_per_frame descs
+		 */
+		if (vhost_vq_state[1].num_free < bufs_per_frame)
+			break;
+
+		/* set the index of the avail ring in the tx queue to be our
+		 * last_used_idx
+		 */
+		head = vhost_vq_state[1].next_free % VHOST_NDESCS;
+		avail->ring[(avail->idx + i) % VHOST_NDESCS] = htole16(head);
+
+		/* we will be consuming bufs_per_frame descriptors for every
+		 * frame, decrement the local num_free
+		 */
+		vhost_vq_state[1].num_free -= bufs_per_frame;
+
+		for (j = 0; j < bufs_per_frame; ++j) {
+			uint16_t next = vhost_vq_state[1].next_free %
+					VHOST_NDESCS;
+			/* get the last_used_idx descriptor */
+			struct vring_desc *desc = &vring_desc[1][next];
+			const struct iovec *iov_i;
+
+			/* the iov variable contains the iovecs for all frames
+			 * we will send. access a single fragment of a frame
+			 * (each fragment is one of tcp_iov_parts) denoted by
+			 * iov at index i (index of the frame being processed)
+			 * * bufs_per_frame plus j (the index of the fragment
+			 * being processed)
+			 */
+			iov_i = &iov[i * bufs_per_frame + j];
+
+			/* set that descriptor's address to the base of the iov
+			 * and set the VRING_DESC_F_NEXT flag on the descriptor
+			 * if its not the last frame fragment, so that the
+			 * guest would recieve the entire frame in one go.
+			 */
+			desc->addr = (uint64_t)iov_i->iov_base;
+			desc->len = iov_i->iov_len;
+			desc->flags = (j == bufs_per_frame - 1) ?
+				      0 : htole16(VRING_DESC_F_NEXT);
+
+			vhost_vq_state[1].next_free++;
+		}
+
+		processed_frames++;
+	}
+
+	/* we didn't process any frames, no need to notify the kernel */
+	if (!processed_frames)
+		return 0;
+
+	smp_wmb();
+
+	/* we will have used nframes descriptor chains */
+	avail->idx = htole16(le16toh(avail->idx) + processed_frames);
+
+	vhost_kick(&vring_used_all[1].used, c->vhost.vq[1].kick_fd);
+
+	/* wait until the kernel finishes processing this send */
+	while (avail->idx != vring_used_all[1].used.idx)
+		;
+
+	return processed_frames;
+}
+
 /**
  * tap_send_frames_pasta() - Send multiple frames to the pasta tap
  * @c:			Execution context
  * @iov:		Array of buffers
  * @bufs_per_frame:	Number of buffers (iovec entries) per frame
  * @nframes:		Number of frames to send
+ * @vhost:		Send through vhost-net rather than writing to the tap
  *
  * @iov must have total length @bufs_per_frame * @nframes, with each set of
  * @bufs_per_frame contiguous buffers representing a single frame.
@@ -375,11 +509,15 @@ void tap_icmp6_send(const struct ctx *c,
  */
 static size_t tap_send_frames_pasta(const struct ctx *c,
 				    const struct iovec *iov,
-				    size_t bufs_per_frame, size_t nframes)
+				    size_t bufs_per_frame, size_t nframes,
+				    bool vhost)
 {
 	size_t nbufs = bufs_per_frame * nframes;
 	size_t i;
 
+	if (vhost)
+		return tap_send_frames_vhost(c, iov, bufs_per_frame, nframes);
+
 	for (i = 0; i < nbufs; i += bufs_per_frame) {
 		ssize_t rc = writev(c->fd_tap, iov + i, bufs_per_frame);
 		size_t framelen = iov_size(iov + i, bufs_per_frame);
@@ -515,7 +653,7 @@ void tap_send_single(const struct ctx *c, const void *data, size_t l2len)
 		iov[iovcnt].iov_len = l2len;
 		iovcnt++;
 
-		m = tap_send_frames_pasta(c, iov, iovcnt, 1);
+		m = tap_send_frames_pasta(c, iov, iovcnt, 1, false);
 		break;
 	case MODE_VU:
 		vu_send_single(c, data, l2len);
@@ -553,7 +691,8 @@ size_t tap_send_frames(const struct ctx *c, const struct iovec *iov,
 
 	switch (c->mode) {
 	case MODE_PASTA:
-		m = tap_send_frames_pasta(c, iov, bufs_per_frame, nframes);
+		m = tap_send_frames_pasta(c, iov, bufs_per_frame, nframes,
+					  c->vhost.fd != -1);
 		break;
 	case MODE_PASST:
 		m = tap_send_frames_passt(c, iov, bufs_per_frame, nframes);
-- 
2.39.5 (Apple Git-154)


      parent reply	other threads:[~2026-09-04 21:29 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-04 21:28 [PATCH 0/7] Add vhost-net kernel support to pasta aerosouund
2026-09-04 21:28 ` [PATCH 1/7] tap: Move the tap_hdr file to a separate file aerosouund
2026-09-05  1:52   ` David Gibson
2026-09-04 21:28 ` [PATCH 5/7] tap, tcp, udp: Prepare the to-guest path for vhost-net aerosouund
2026-09-04 21:28 ` aerosouund [this message]

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=20260904212826.41027-7-aerosound161@gmail.com \
    --to=aerosound161@gmail.com \
    --cc=eperezma@redhat.com \
    --cc=passt-dev@passt.top \
    /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.
Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).