[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum numbe
From: |
Jason Wang |
Subject: |
Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513 |
Date: |
Wed, 08 Apr 2015 16:10:43 +0800 |
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.6.0 |
On 04/08/2015 12:54 AM, Alexander Graf wrote:
> On 04/01/2015 10:15 AM, 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.
>>
>> 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.
>>
>> Cc: Paolo Bonzini <address@hidden>
>> Cc: Richard Henderson <address@hidden>
>> Cc: Michael S. Tsirkin <address@hidden>
>> Cc: Alexander Graf <address@hidden>
>> Cc: address@hidden
>> Signed-off-by: Jason Wang <address@hidden>
>> ---
>> hw/i386/pc_piix.c | 5 +++++
>> hw/i386/pc_q35.c | 5 +++++
>> hw/ppc/spapr.c | 5 +++++
>> hw/virtio/virtio-pci.c | 2 +-
>> 4 files changed, 16 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 9a5242a..02e3ce8 100644
>> --- a/hw/virtio/virtio-pci.c
>> +++ b/hw/virtio/virtio-pci.c
>> @@ -42,7 +42,7 @@
>> * configuration space */
>> #define VIRTIO_PCI_CONFIG_SIZE(dev)
>> VIRTIO_PCI_CONFIG_OFF(msix_enabled(dev))
>> -#define VIRTIO_PCI_QUEUE_MAX 64
>> +#define VIRTIO_PCI_QUEUE_MAX 513
>
> 513 is an interesting number. Any particular reason for it? Maybe this
> was mentioned before and I just missed it ;)
>
>
> Alex
>
>
The number were chose to match kernel limit for tuntap queues. Recent
kernel allow up to 256 queues for tuntap, so 513 is in fact 256 * 2 plus
1 control vq.
- [Qemu-devel] [PATCH V5 15/18] virtio-pci: speedup MSI-X masking and unmasking, (continued)
- [Qemu-devel] [PATCH V5 15/18] virtio-pci: speedup MSI-X masking and unmasking, Jason Wang, 2015/04/01
- [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Jason Wang, 2015/04/01
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Alexander Graf, 2015/04/07
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Luigi Rizzo, 2015/04/07
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Alexander Graf, 2015/04/07
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Jason Wang, 2015/04/08
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Alexander Graf, 2015/04/08
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Jason Wang, 2015/04/08
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Jason Wang, 2015/04/08
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Michael S. Tsirkin, 2015/04/08
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513,
Jason Wang <=
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Alexander Graf, 2015/04/08
- Re: [Qemu-devel] [PATCH V5 16/18] virtio-pci: increase the maximum number of virtqueues to 513, Jason Wang, 2015/04/08
[Qemu-devel] [PATCH V5 17/18] pci: remove hard-coded bar size in msix_init_exclusive_bar(), Jason Wang, 2015/04/01
[Qemu-devel] [PATCH V5 18/18] virtio-pci: introduce auto_msix_bar_size property, Jason Wang, 2015/04/01
Re: [Qemu-devel] [PATCH V5 00/18] Support more virtio queues, Cornelia Huck, 2015/04/02