All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Eugenio Pérez" <eperezma@redhat.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: "virtualization@lists.linux-foundation.org"
	<virtualization@lists.linux-foundation.org>,
	"Eugenio Pérez" <eperezma@redhat.com>,
	"Linux Next Mailing List" <linux-next@vger.kernel.org>,
	"Stephen Rothwell" <sfr@canb.auug.org.au>,
	"kvm list" <kvm@vger.kernel.org>,
	"Halil Pasic" <pasic@linux.ibm.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"Cornelia Huck" <cohuck@redhat.com>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>
Subject: [PATCH v4 2/7] vhost: use batched version by default
Date: Wed,  1 Apr 2020 20:31:13 +0200	[thread overview]
Message-ID: <20200401183118.8334-3-eperezma@redhat.com> (raw)
In-Reply-To: <20200401183118.8334-1-eperezma@redhat.com>

From: "Michael S. Tsirkin" <mst@redhat.com>

As testing shows no performance change, switch to that now.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
---
 drivers/vhost/vhost.c | 251 +-----------------------------------------
 drivers/vhost/vhost.h |   4 -
 2 files changed, 2 insertions(+), 253 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 56593ba6decc..6ca658c21e15 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2038,253 +2038,6 @@ static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc)
 	return next;
 }
 
-static int get_indirect(struct vhost_virtqueue *vq,
-			struct iovec iov[], unsigned int iov_size,
-			unsigned int *out_num, unsigned int *in_num,
-			struct vhost_log *log, unsigned int *log_num,
-			struct vring_desc *indirect)
-{
-	struct vring_desc desc;
-	unsigned int i = 0, count, found = 0;
-	u32 len = vhost32_to_cpu(vq, indirect->len);
-	struct iov_iter from;
-	int ret, access;
-
-	/* Sanity check */
-	if (unlikely(len % sizeof desc)) {
-		vq_err(vq, "Invalid length in indirect descriptor: "
-		       "len 0x%llx not multiple of 0x%zx\n",
-		       (unsigned long long)len,
-		       sizeof desc);
-		return -EINVAL;
-	}
-
-	ret = translate_desc(vq, vhost64_to_cpu(vq, indirect->addr), len, vq->indirect,
-			     UIO_MAXIOV, VHOST_ACCESS_RO);
-	if (unlikely(ret < 0)) {
-		if (ret != -EAGAIN)
-			vq_err(vq, "Translation failure %d in indirect.\n", ret);
-		return ret;
-	}
-	iov_iter_init(&from, READ, vq->indirect, ret, len);
-
-	/* We will use the result as an address to read from, so most
-	 * architectures only need a compiler barrier here. */
-	read_barrier_depends();
-
-	count = len / sizeof desc;
-	/* Buffers are chained via a 16 bit next field, so
-	 * we can have at most 2^16 of these. */
-	if (unlikely(count > USHRT_MAX + 1)) {
-		vq_err(vq, "Indirect buffer length too big: %d\n",
-		       indirect->len);
-		return -E2BIG;
-	}
-
-	do {
-		unsigned iov_count = *in_num + *out_num;
-		if (unlikely(++found > count)) {
-			vq_err(vq, "Loop detected: last one at %u "
-			       "indirect size %u\n",
-			       i, count);
-			return -EINVAL;
-		}
-		if (unlikely(!copy_from_iter_full(&desc, sizeof(desc), &from))) {
-			vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
-			       i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
-			return -EINVAL;
-		}
-		if (unlikely(desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) {
-			vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
-			       i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc);
-			return -EINVAL;
-		}
-
-		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
-			access = VHOST_ACCESS_WO;
-		else
-			access = VHOST_ACCESS_RO;
-
-		ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
-				     vhost32_to_cpu(vq, desc.len), iov + iov_count,
-				     iov_size - iov_count, access);
-		if (unlikely(ret < 0)) {
-			if (ret != -EAGAIN)
-				vq_err(vq, "Translation failure %d indirect idx %d\n",
-					ret, i);
-			return ret;
-		}
-		/* If this is an input descriptor, increment that count. */
-		if (access == VHOST_ACCESS_WO) {
-			*in_num += ret;
-			if (unlikely(log && ret)) {
-				log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
-				log[*log_num].len = vhost32_to_cpu(vq, desc.len);
-				++*log_num;
-			}
-		} else {
-			/* If it's an output descriptor, they're all supposed
-			 * to come before any input descriptors. */
-			if (unlikely(*in_num)) {
-				vq_err(vq, "Indirect descriptor "
-				       "has out after in: idx %d\n", i);
-				return -EINVAL;
-			}
-			*out_num += ret;
-		}
-	} while ((i = next_desc(vq, &desc)) != -1);
-	return 0;
-}
-
-/* This looks in the virtqueue and for the first available buffer, and converts
- * it to an iovec for convenient access.  Since descriptors consist of some
- * number of output then some number of input descriptors, it's actually two
- * iovecs, but we pack them into one and note how many of each there were.
- *
- * This function returns the descriptor number found, or vq->num (which is
- * never a valid descriptor number) if none was found.  A negative code is
- * returned on error. */
-int vhost_get_vq_desc(struct vhost_virtqueue *vq,
-		      struct iovec iov[], unsigned int iov_size,
-		      unsigned int *out_num, unsigned int *in_num,
-		      struct vhost_log *log, unsigned int *log_num)
-{
-	struct vring_desc desc;
-	unsigned int i, head, found = 0;
-	u16 last_avail_idx;
-	__virtio16 avail_idx;
-	__virtio16 ring_head;
-	int ret, access;
-
-	/* Check it isn't doing very strange things with descriptor numbers. */
-	last_avail_idx = vq->last_avail_idx;
-
-	if (vq->avail_idx == vq->last_avail_idx) {
-		if (unlikely(vhost_get_avail_idx(vq, &avail_idx))) {
-			vq_err(vq, "Failed to access avail idx at %p\n",
-				&vq->avail->idx);
-			return -EFAULT;
-		}
-		vq->avail_idx = vhost16_to_cpu(vq, avail_idx);
-
-		if (unlikely((u16)(vq->avail_idx - last_avail_idx) > vq->num)) {
-			vq_err(vq, "Guest moved used index from %u to %u",
-				last_avail_idx, vq->avail_idx);
-			return -EFAULT;
-		}
-
-		/* If there's nothing new since last we looked, return
-		 * invalid.
-		 */
-		if (vq->avail_idx == last_avail_idx)
-			return vq->num;
-
-		/* Only get avail ring entries after they have been
-		 * exposed by guest.
-		 */
-		smp_rmb();
-	}
-
-	/* Grab the next descriptor number they're advertising, and increment
-	 * the index we've seen. */
-	if (unlikely(vhost_get_avail_head(vq, &ring_head, last_avail_idx))) {
-		vq_err(vq, "Failed to read head: idx %d address %p\n",
-		       last_avail_idx,
-		       &vq->avail->ring[last_avail_idx % vq->num]);
-		return -EFAULT;
-	}
-
-	head = vhost16_to_cpu(vq, ring_head);
-
-	/* If their number is silly, that's an error. */
-	if (unlikely(head >= vq->num)) {
-		vq_err(vq, "Guest says index %u > %u is available",
-		       head, vq->num);
-		return -EINVAL;
-	}
-
-	/* When we start there are none of either input nor output. */
-	*out_num = *in_num = 0;
-	if (unlikely(log))
-		*log_num = 0;
-
-	i = head;
-	do {
-		unsigned iov_count = *in_num + *out_num;
-		if (unlikely(i >= vq->num)) {
-			vq_err(vq, "Desc index is %u > %u, head = %u",
-			       i, vq->num, head);
-			return -EINVAL;
-		}
-		if (unlikely(++found > vq->num)) {
-			vq_err(vq, "Loop detected: last one at %u "
-			       "vq size %u head %u\n",
-			       i, vq->num, head);
-			return -EINVAL;
-		}
-		ret = vhost_get_desc(vq, &desc, i);
-		if (unlikely(ret)) {
-			vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
-			       i, vq->desc + i);
-			return -EFAULT;
-		}
-		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) {
-			ret = get_indirect(vq, iov, iov_size,
-					   out_num, in_num,
-					   log, log_num, &desc);
-			if (unlikely(ret < 0)) {
-				if (ret != -EAGAIN)
-					vq_err(vq, "Failure detected "
-						"in indirect descriptor at idx %d\n", i);
-				return ret;
-			}
-			continue;
-		}
-
-		if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE))
-			access = VHOST_ACCESS_WO;
-		else
-			access = VHOST_ACCESS_RO;
-		ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr),
-				     vhost32_to_cpu(vq, desc.len), iov + iov_count,
-				     iov_size - iov_count, access);
-		if (unlikely(ret < 0)) {
-			if (ret != -EAGAIN)
-				vq_err(vq, "Translation failure %d descriptor idx %d\n",
-					ret, i);
-			return ret;
-		}
-		if (access == VHOST_ACCESS_WO) {
-			/* If this is an input descriptor,
-			 * increment that count. */
-			*in_num += ret;
-			if (unlikely(log && ret)) {
-				log[*log_num].addr = vhost64_to_cpu(vq, desc.addr);
-				log[*log_num].len = vhost32_to_cpu(vq, desc.len);
-				++*log_num;
-			}
-		} else {
-			/* If it's an output descriptor, they're all supposed
-			 * to come before any input descriptors. */
-			if (unlikely(*in_num)) {
-				vq_err(vq, "Descriptor has out after in: "
-				       "idx %d\n", i);
-				return -EINVAL;
-			}
-			*out_num += ret;
-		}
-	} while ((i = next_desc(vq, &desc)) != -1);
-
-	/* On success, increment avail index. */
-	vq->last_avail_idx++;
-
-	/* Assume notifications from guest are disabled at this point,
-	 * if they aren't we would need to update avail_event index. */
-	BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
-	return head;
-}
-EXPORT_SYMBOL_GPL(vhost_get_vq_desc);
-
 static struct vhost_desc *peek_split_desc(struct vhost_virtqueue *vq)
 {
 	BUG_ON(!vq->ndescs);
@@ -2495,7 +2248,7 @@ static int fetch_descs(struct vhost_virtqueue *vq)
  * This function returns the descriptor number found, or vq->num (which is
  * never a valid descriptor number) if none was found.  A negative code is
  * returned on error. */
-int vhost_get_vq_desc_batch(struct vhost_virtqueue *vq,
+int vhost_get_vq_desc(struct vhost_virtqueue *vq,
 		      struct iovec iov[], unsigned int iov_size,
 		      unsigned int *out_num, unsigned int *in_num,
 		      struct vhost_log *log, unsigned int *log_num)
@@ -2570,7 +2323,7 @@ int vhost_get_vq_desc_batch(struct vhost_virtqueue *vq,
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(vhost_get_vq_desc_batch);
+EXPORT_SYMBOL_GPL(vhost_get_vq_desc);
 
 /* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
 void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n)
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 20bb95661f94..e5f295e5ffcc 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -187,10 +187,6 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg
 bool vhost_vq_access_ok(struct vhost_virtqueue *vq);
 bool vhost_log_access_ok(struct vhost_dev *);
 
-int vhost_get_vq_desc_batch(struct vhost_virtqueue *,
-		      struct iovec iov[], unsigned int iov_count,
-		      unsigned int *out_num, unsigned int *in_num,
-		      struct vhost_log *log, unsigned int *log_num);
 int vhost_get_vq_desc(struct vhost_virtqueue *,
 		      struct iovec iov[], unsigned int iov_count,
 		      unsigned int *out_num, unsigned int *in_num,
-- 
2.18.1


  parent reply	other threads:[~2020-04-01 18:32 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-01 18:31 [PATCH v4 0/7] vhost: Reset batched descriptors on SET_VRING_BASE call Eugenio Pérez
2020-04-01 18:31 ` [PATCH v4 1/7] vhost: option to fetch descriptors through an independent struct Eugenio Pérez
2020-04-01 18:31 ` Eugenio Pérez [this message]
2020-04-01 18:31 ` [PATCH v4 3/7] vhost: batching fetches Eugenio Pérez
2020-04-01 18:31 ` [PATCH v4 4/7] tools/virtio: Add --batch option Eugenio Pérez
2020-04-01 18:31 ` [PATCH v4 5/7] tools/virtio: Add --batch=random option Eugenio Pérez
2020-04-01 18:31 ` [PATCH v4 6/7] tools/virtio: Add --reset=random Eugenio Pérez
2020-04-01 18:31 ` [PATCH v4 7/7] tools/virtio: Make --reset reset ring idx Eugenio Pérez
2020-04-02 13:27   ` Michael S. Tsirkin

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=20200401183118.8334-3-eperezma@redhat.com \
    --to=eperezma@redhat.com \
    --cc=borntraeger@de.ibm.com \
    --cc=cohuck@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-next@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=sfr@canb.auug.org.au \
    --cc=virtualization@lists.linux-foundation.org \
    /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.