All of lore.kernel.org
 help / color / mirror / Atom feed
From: Cornelia Huck <cornelia.huck@de.ibm.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: qemu-devel@nongnu.org, mst@redhat.com
Subject: Re: [Qemu-devel] [PATCH 05/10] virtio: slim down allocation of VirtQueueElements
Date: Tue, 19 Jan 2016 16:54:58 +0100	[thread overview]
Message-ID: <20160119165458.0afc3bb8.cornelia.huck@de.ibm.com> (raw)
In-Reply-To: <1452861718-25806-6-git-send-email-pbonzini@redhat.com>

On Fri, 15 Jan 2016 13:41:53 +0100
Paolo Bonzini <pbonzini@redhat.com> wrote:

> Build the addresses and s/g lists on the stack, and then copy them
> to a VirtQueueElement that is just as big as required to contain this
> particular s/g list.  The cost of the copy is minimal compared to that
> of a large malloc.
> 
> When virtqueue_map is used on the destination side of migration or on
> loadvm, the iovecs have already been split at memory region boundary,
> so we can just reuse the out_num/in_num we find in the file.
> 
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>  hw/virtio/virtio.c | 82 +++++++++++++++++++++++++++++++++---------------------
>  1 file changed, 51 insertions(+), 31 deletions(-)
> 

>      /* Collect all the descriptors */
>      do {
> -        struct iovec *sg;
> +        hwaddr pa = vring_desc_addr(vdev, desc_pa, i);
> +        size_t len = vring_desc_len(vdev, desc_pa, i);
> 
>          if (vring_desc_flags(vdev, desc_pa, i) & VRING_DESC_F_WRITE) {
> -            if (elem->in_num >= VIRTQUEUE_MAX_SIZE) {
> -                error_report("Too many write descriptors in indirect table");
> -                exit(1);
> -            }
> -            elem->in_addr[elem->in_num] = vring_desc_addr(vdev, desc_pa, i);
> -            sg = &elem->in_sg[elem->in_num++];
> +            virtqueue_map_desc(&in_num, addr + out_num, iov + out_num,
> +                               VIRTQUEUE_MAX_SIZE - out_num, 1, pa, len);

Minor nit: I'd probably use 'true' here...

>          } else {
> -            if (elem->out_num >= VIRTQUEUE_MAX_SIZE) {
> -                error_report("Too many read descriptors in indirect table");
> +            if (in_num) {
> +                error_report("Incorrect order for descriptors");
>                  exit(1);
>              }
> -            elem->out_addr[elem->out_num] = vring_desc_addr(vdev, desc_pa, i);
> -            sg = &elem->out_sg[elem->out_num++];
> +            virtqueue_map_desc(&out_num, addr, iov,
> +                               VIRTQUEUE_MAX_SIZE, 0, pa, len);

...and 'false' here.

>          }
> 
> -        sg->iov_len = vring_desc_len(vdev, desc_pa, i);
> -
>          /* If we've got too many, that implies a descriptor loop. */
> -        if ((elem->in_num + elem->out_num) > max) {
> +        if ((in_num + out_num) > max) {
>              error_report("Looped descriptor");
>              exit(1);
>          }
>      } while ((i = virtqueue_next_desc(vdev, desc_pa, i, max)) != max);

Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>

  reply	other threads:[~2016-01-19 15:55 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-01-15 12:41 [Qemu-devel] [PATCH 00/10] virtio/vring: optimization patches Paolo Bonzini
2016-01-15 12:41 ` [Qemu-devel] [PATCH 01/10] virtio: move VirtQueueElement at the beginning of the structs Paolo Bonzini
2016-01-19 12:09   ` Cornelia Huck
2016-01-19 13:22     ` Paolo Bonzini
2016-01-19 14:01       ` Cornelia Huck
2016-01-15 12:41 ` [Qemu-devel] [PATCH 02/10] virtio: move allocation to virtqueue_pop/vring_pop Paolo Bonzini
2016-01-19 12:22   ` Cornelia Huck
2016-01-19 13:16     ` Paolo Bonzini
2016-01-15 12:41 ` [Qemu-devel] [PATCH 03/10] virtio: introduce qemu_get/put_virtqueue_element Paolo Bonzini
2016-01-19 12:30   ` Cornelia Huck
2016-01-15 12:41 ` [Qemu-devel] [PATCH 04/10] virtio: introduce virtqueue_alloc_element Paolo Bonzini
2016-01-19 12:40   ` Cornelia Huck
2016-01-15 12:41 ` [Qemu-devel] [PATCH 05/10] virtio: slim down allocation of VirtQueueElements Paolo Bonzini
2016-01-19 15:54   ` Cornelia Huck [this message]
2016-01-15 12:41 ` [Qemu-devel] [PATCH 06/10] vring: " Paolo Bonzini
2016-01-19 15:58   ` Cornelia Huck
2016-01-15 12:41 ` [Qemu-devel] [PATCH 07/10] virtio: combine the read of a descriptor Paolo Bonzini
2016-01-19 16:07   ` Cornelia Huck
2016-01-15 12:41 ` [Qemu-devel] [PATCH 08/10] virtio: cache used_idx in a VirtQueue field Paolo Bonzini
2016-01-19 16:11   ` Cornelia Huck
2016-01-15 12:41 ` [Qemu-devel] [PATCH 09/10] virtio: read avail_idx from VQ only when necessary Paolo Bonzini
2016-01-19 16:20   ` Cornelia Huck
2016-01-19 16:54   ` Michael S. Tsirkin
2016-01-19 18:48     ` Paolo Bonzini
2016-01-20 17:32       ` Cornelia Huck
2016-01-21 21:40       ` Vincenzo Maffione
2016-01-15 12:41 ` [Qemu-devel] [PATCH 10/10] virtio: combine write of an entry into used ring Paolo Bonzini
2016-01-19 16:26   ` Cornelia Huck
2016-01-31 10:28 [Qemu-devel] [PATCH v2 00/10] virtio/vring: optimization patches Paolo Bonzini
2016-01-31 10:29 ` [Qemu-devel] [PATCH 05/10] virtio: slim down allocation of VirtQueueElements Paolo Bonzini

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=20160119165458.0afc3bb8.cornelia.huck@de.ibm.com \
    --to=cornelia.huck@de.ibm.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.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.