From: "Michael S. Tsirkin" <mst@redhat.com>
To: Jason Wang <jasowang@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>,
Alexander Graf <agraf@suse.de>,
qemu-ppc@nongnu.org, qemu-devel@nongnu.org,
Richard Henderson <rth@twiddle.net>
Subject: Re: [Qemu-devel] [PATCH V7 15/16] virtio-pci: increase the maximum number of virtqueues to 513
Date: Mon, 27 Apr 2015 13:02:24 +0200 [thread overview]
Message-ID: <20150427130035-mutt-send-email-mst@redhat.com> (raw)
In-Reply-To: <1429770109-23873-16-git-send-email-jasowang@redhat.com>
On Thu, Apr 23, 2015 at 02:21:48PM +0800, Jason Wang wrote:
> This patch increases the maximum number of virtqueues for pci from 64
> to 513. This will allow booting a virtio-net-pci device with 256 queue
> pairs on recent Linux host (which supports up to 256 tuntap queue pairs).
>
> To keep migration compatibility, 64 was kept for legacy machine
> types. This is because qemu in fact allows guest to probe the limit of
> virtqueues through trying to set queue_sel. So for legacy machine
> type, we should make sure setting queue_sel to more than 63 won't
> make effect.
This isn't a documented interface, and no guest that I know of does
this. Accordingly, I think we should drop everything except the
hw/virtio/virtio-pci.c change.
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Richard Henderson <rth@twiddle.net>
> Cc: Michael S. Tsirkin <mst@redhat.com>
> Cc: Alexander Graf <agraf@suse.de>
> Cc: qemu-ppc@nongnu.org
> Signed-off-by: Jason Wang <jasowang@redhat.com>
> ---
> hw/i386/pc_piix.c | 5 +++++
> hw/i386/pc_q35.c | 5 +++++
> hw/ppc/spapr.c | 5 +++++
> hw/virtio/virtio-pci.c | 6 +++++-
> 4 files changed, 20 insertions(+), 1 deletion(-)
>
> diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
> index 212e263..6e098ce 100644
> --- a/hw/i386/pc_piix.c
> +++ b/hw/i386/pc_piix.c
> @@ -49,6 +49,7 @@
> #include "hw/acpi/acpi.h"
> #include "cpu.h"
> #include "qemu/error-report.h"
> +#include "hw/virtio/virtio-bus.h"
> #ifdef CONFIG_XEN
> # include <xen/hvm/hvm_info_table.h>
> #endif
> @@ -312,6 +313,10 @@ static void pc_init_pci(MachineState *machine)
>
> static void pc_compat_2_3(MachineState *machine)
> {
> + ObjectClass *klass = object_class_by_name("virtio-pci-bus");
> + VirtioBusClass *k = VIRTIO_BUS_CLASS(klass);
> +
> + k->queue_max = 64;
> }
>
> static void pc_compat_2_2(MachineState *machine)
> diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
> index e67f2de..ff7c414 100644
> --- a/hw/i386/pc_q35.c
> +++ b/hw/i386/pc_q35.c
> @@ -45,6 +45,7 @@
> #include "hw/usb.h"
> #include "hw/cpu/icc_bus.h"
> #include "qemu/error-report.h"
> +#include "include/hw/virtio/virtio-bus.h"
>
> /* ICH9 AHCI has 6 ports */
> #define MAX_SATA_PORTS 6
> @@ -291,6 +292,10 @@ static void pc_q35_init(MachineState *machine)
>
> static void pc_compat_2_3(MachineState *machine)
> {
> + ObjectClass *klass = object_class_by_name("virtio-pci-bus");
> + VirtioBusClass *k = VIRTIO_BUS_CLASS(klass);
> +
> + k->queue_max = 64;
> }
>
> static void pc_compat_2_2(MachineState *machine)
> diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
> index 8e43aa2..ee8f6a3 100644
> --- a/hw/ppc/spapr.c
> +++ b/hw/ppc/spapr.c
> @@ -50,6 +50,7 @@
> #include "hw/pci/pci.h"
> #include "hw/scsi/scsi.h"
> #include "hw/virtio/virtio-scsi.h"
> +#include "hw/virtio/virtio-bus.h"
>
> #include "exec/address-spaces.h"
> #include "hw/usb.h"
> @@ -1827,6 +1828,10 @@ static const TypeInfo spapr_machine_info = {
>
> static void spapr_compat_2_3(Object *obj)
> {
> + ObjectClass *klass = object_class_by_name("virtio-pci-bus");
> + VirtioBusClass *k = VIRTIO_BUS_CLASS(klass);
> +
> + k->queue_max = 64;
> }
>
> static void spapr_compat_2_2(Object *obj)
> diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
> index 7d01500..c510cb7 100644
> --- a/hw/virtio/virtio-pci.c
> +++ b/hw/virtio/virtio-pci.c
> @@ -42,7 +42,11 @@
> * configuration space */
> #define VIRTIO_PCI_CONFIG_SIZE(dev) VIRTIO_PCI_CONFIG_OFF(msix_enabled(dev))
>
> -#define VIRTIO_PCI_QUEUE_MAX 64
> +/* The number was chose to be greater than both the the number of max
> + * vcpus supported by host and the number of max tuntap queues support
> + * by host and also leave some spaces for future.
> + */
> +#define VIRTIO_PCI_QUEUE_MAX 1024
>
> static void virtio_pci_bus_new(VirtioBusState *bus, size_t bus_size,
> VirtIOPCIProxy *dev);
> --
> 2.1.0
next prev parent reply other threads:[~2015-04-27 11:02 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-04-23 6:21 [Qemu-devel] [PATCH V7 00/16] Support more virtio queues Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 01/16] virtio-net: fix the upper bound when trying to delete queues Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 02/16] pc: add 2.4 machine types Jason Wang
2015-04-27 11:03 ` Michael S. Tsirkin
2015-04-28 3:12 ` Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 03/16] spapr: add machine type specific instance init function Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 04/16] ppc: spapr: add 2.4 machine type Jason Wang
2015-04-27 11:03 ` Michael S. Tsirkin
2015-04-27 13:14 ` Alexander Graf
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 05/16] monitor: replace the magic number 255 with MAX_QUEUE_NUM Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 06/16] monitor: check return value of qemu_find_net_clients_except() Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 07/16] virtio-ccw: using VIRTIO_NO_VECTOR instead of 0 for invalid virtqueue Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 08/16] virtio: introduce bus specific queue limit Jason Wang
2015-04-27 11:05 ` Michael S. Tsirkin
2015-04-28 3:14 ` Jason Wang
2015-04-28 5:13 ` Michael S. Tsirkin
2015-04-28 6:13 ` Jason Wang
2015-04-28 7:14 ` Michael S. Tsirkin
2015-04-28 8:04 ` Cornelia Huck
2015-04-28 8:16 ` Michael S. Tsirkin
2015-04-28 10:40 ` Cornelia Huck
2015-04-28 10:55 ` Michael S. Tsirkin
2015-04-28 11:39 ` Cornelia Huck
2015-04-28 12:47 ` Michael S. Tsirkin
2015-04-28 13:33 ` Cornelia Huck
2015-04-28 14:40 ` Michael S. Tsirkin
2015-05-13 7:51 ` Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 09/16] virtio-ccw: introduce ccw " Jason Wang
2015-04-23 10:59 ` Cornelia Huck
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 10/16] virtio-s390: switch to bus " Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 11/16] virtio-mmio: " Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 12/16] virtio-pci: switch to use " Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 13/16] virtio: introduce vector to virtqueues mapping Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 14/16] virtio-pci: speedup MSI-X masking and unmasking Jason Wang
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 15/16] virtio-pci: increase the maximum number of virtqueues to 513 Jason Wang
2015-04-23 11:24 ` Cornelia Huck
2015-04-28 3:05 ` Jason Wang
2015-04-27 11:02 ` Michael S. Tsirkin [this message]
2015-04-28 3:12 ` Jason Wang
2015-04-28 7:17 ` Michael S. Tsirkin
2015-05-13 7:47 ` Jason Wang
2015-05-13 8:16 ` Michael S. Tsirkin
2015-05-14 18:54 ` Eduardo Habkost
2015-04-23 6:21 ` [Qemu-devel] [PATCH V7 16/16] pci: remove hard-coded bar size in msix_init_exclusive_bar() Jason Wang
2015-04-23 11:27 ` [Qemu-devel] [PATCH V7 00/16] Support more virtio queues Cornelia Huck
2015-04-28 3:14 ` Jason Wang
2015-04-27 19:06 ` 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=20150427130035-mutt-send-email-mst@redhat.com \
--to=mst@redhat.com \
--cc=agraf@suse.de \
--cc=jasowang@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
--cc=rth@twiddle.net \
/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 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 NNTP newsgroup(s).