Re: [Qemu-devel] [PATCH V4 00/19] Support more virtio queues

[Michael S. Tsirkin]

On Wed, Mar 18, 2015 at 05:34:50PM +0800, Jason Wang wrote:
> We current limit the max virtio queues to 64. This is not sufficient
> to support multiqueue devices (e.g recent Linux support up to 256
> tap queues). So this series tries to let virtio to support more queues.
> 
> No much works need to be done except:
> 
> - Introducing transport specific queue limitation.
> - Let each virtio transport to use specific limit.
> - Speedup the MSI-X masking and unmasking through per vector queue
>   list, and increase the maximum MSI-X vectors supported by qemu.
> - With the above enhancements, increase the maximum number of
>   virtqueues supported by PCI from 64 to 513.
> - Compat the changes for legacy machine types.

What are the compatibility considerations here?


> With this patch, we can support up to 256 queues. Since x86 can only
> allow about 240 interrupt vectors for MSI-X, current Linux driver can
> only have about 80 queue pairs has their private MSI-X interrupt
> vectors. With sharing IRQ with queue pairs (RFC posted in
> https://lkml.org/lkml/2014/12/25/169), Linux driver can have up
> to about 186 queue pairs has their private MSI-X interrupt vectors.
> 
> Stress/migration test on virtio-pci, compile test on other
> targets. And make check on s390x-softmmu and ppc64-softmmu.
> 
> Cc: Paolo Bonzini <address@hidden>
> Cc: Richard Henderson <address@hidden>
> Cc: Michael S. Tsirkin <address@hidden>
> Cc: Alexander Graf <address@hidden>
> Cc: Keith Busch <address@hidden>
> Cc: Kevin Wolf <address@hidden>
> Cc: Stefan Hajnoczi <address@hidden>
> Cc: Christian Borntraeger <address@hidden>
> Cc: Cornelia Huck <address@hidden>
> Cc: Amit Shah <address@hidden>
> Cc: address@hidden
> 
> Please review
> 
> Thanks
> 
> Changes from V3:
> - rebase to master and target to 2.4
> - handling compat issues for spapr
> - fixes for hmp command completion when we have a nic with 256 queues
> - using VIRTIO_NO_VECTOR instead of 0 for invalid virtqueue in
>   virtio-ccw
> - fix compile issues for ppc64-softmmu
> - don't export VIRTIO_CCW_QUEUE_MAX by introducing a gsi limit and
>   inherit in ccw
> - use transport specific queue limit in virtio-serial
> - correct the stale comment for AdapterRoutes and move it to ccw patch
> - replace 128 with queue_max + 64 and add a comment for this in
>   virtio_ccw_notify()
> 
> Changes from V2:
> - move transport specific limitation to their implementation. (The
>   left is VIRTIO_CCW_QUEUE_MAX since I fail to find a common header
>   files other than virtio.h)
> - use virtio_get_queue_max() if possible in virtio.c
> - AdapterRoutes should use ccw limit
> - introduce a vector to queue mapping for virito devices and speedup
>   the MSI-X masking and unmasking through this.
> 
> Changes from V1:
> - add a validation against the bus limitation
> - switch to use a bus specific queue limit instead of a global one,
>   this will allow us to just increase the limit of one transport
>   without disturbing others.
> - only increase the queue limit of virtio-pci
> - limit the maximum number of virtio queues to 64 for legacy machine
>   types
> 
> Jason Wang (19):
>   pc: add 2.4 machine types
>   spapr: add machine type specific instance init function
>   ppc: spapr: add 2.4 machine type
>   monitor: replace the magic number 255 with MAX_QUEUE_NUM
>   monitor: check return value of qemu_find_net_clients_except()
>   virtio-ccw: using VIRTIO_NO_VECTOR instead of 0 for invalid virtqueue
>   virtio-net: validate backend queue numbers against bus limitation
>   virtio-net: fix the upper bound when trying to delete queues
>   virito: introduce bus specific queue limit
>   virtio-ccw: introduce ccw specific queue limit
>   virtio-s390: switch to bus specific queue limit
>   virtio-mmio: switch to bus specific queue limit
>   virtio-pci: switch to use bus specific queue limit
>   virtio: introduce vector to virtqueues mapping
>   virtio: introduce virtio_queue_get_index()
>   virtio-pci: speedup MSI-X masking and unmasking
>   virtio-pci: increase the maximum number of virtqueues to 513
>   pci: remove hard-coded bar size in msix_init_exclusive_bar()
>   virtio-pci: introduce auto_msix_bar_size property
> 
>  hw/block/nvme.c                |  2 +-
>  hw/char/virtio-serial-bus.c    |  2 +-
>  hw/i386/pc_piix.c              | 42 ++++++++++++++++++++---
>  hw/i386/pc_q35.c               | 39 +++++++++++++++++++--
>  hw/misc/ivshmem.c              |  2 +-
>  hw/net/virtio-net.c            |  9 ++++-
>  hw/pci/msix.c                  | 18 ++++------
>  hw/ppc/spapr.c                 | 70 +++++++++++++++++++++++++++++++++++--
>  hw/s390x/s390-virtio-bus.c     |  7 ++--
>  hw/s390x/s390-virtio-ccw.c     |  7 ++--
>  hw/s390x/virtio-ccw.c          | 20 +++++++----
>  hw/scsi/virtio-scsi.c          |  4 +--
>  hw/virtio/virtio-mmio.c        |  7 ++--
>  hw/virtio/virtio-pci.c         | 78 
> ++++++++++++++++++++++++++++--------------
>  hw/virtio/virtio-pci.h         |  3 ++
>  hw/virtio/virtio.c             | 75 +++++++++++++++++++++++++++++++---------
>  include/hw/compat.h            | 11 ++++++
>  include/hw/pci/msix.h          |  2 +-
>  include/hw/s390x/s390_flic.h   |  4 ++-
>  include/hw/virtio/virtio-bus.h |  2 ++
>  include/hw/virtio/virtio.h     |  7 ++--
>  monitor.c                      | 25 ++++++++------
>  22 files changed, 339 insertions(+), 97 deletions(-)
> 
> -- 
> 2.1.0