[v12,00/10] implement packed virtqueues

  This is a basic implementation of packed virtqueues as specified in the
Virtio 1.1 draft. A compiled version of the current draft is available
at https://github.com/oasis-tcs/virtio-docs.git (or as .pdf at
https://github.com/oasis-tcs/virtio-docs/blob/master/virtio-v1.1-packed-wd10.pdf

A packed virtqueue is different from a split virtqueue in that it
consists of only a single descriptor ring that replaces available and
used ring, index and descriptor pointers.

Each descriptor is readable and writable and has a flags field. These flags
will mark if a descriptor is available or used.  To detect new available descriptors
even after the ring has wrapped, device and driver each have a
single-bit wrap counter that is flipped from 0 to 1 and vice versa every time
the last descriptor in the ring is used/made available.

With this patch set I see performance equal or slightly better (+2-3%) in a PVP
scenario compared to split virtqueues (v18.11 in host) 

regards,
Jens 


v11->v12:
 * add a patch to disable control vq when packed vq is enabled.
   I have a patch to support this but it needs a bit more work
   and I think it shouldn't stop this series from being applied
 * rework mergeable receive buffer code to be more efficient, by
   batching descriptor refill, similar to what Maxime proposed for
   split virtqueues
 * removed unnecessary checks in virtio_recv_mergeable_pkts_packed
   (Maxime) 
 * Did not merge receive functions as Maxime suggested because it seemed
   to cause a small performance regression
 * Move event_flags_shadow from patch 3 to 1 (Maxime)
 * Did not merge xmit functions and call _split/_packed functions from
   there because it seemed to cause small performance drop (-0.5%)
   (Maxime)

v10-v11:
 * this version includes some fixes from Tiwei, so I added his
   Signed-off-by to some of the patches
 * fix hang with mergable rx buffers (Tiwei)
 * clean-up code and simplify buffer handling (Tiwei)
 * rebase to current virtio-next master branch

v9-v10:
 * don't mix index into buffer list and descriptors
 * whitespace and formatting issues
 * remove "VQ:" in dump virtqueue patch
 * add extra packed vring struct to virtqueue and change function
   prototypes and code accordingly
 * move wrap_counters to virtqueue
 * make if-conditions for packed and !packed more clear in
   set_rxtx_funcs()
 * initialize wrap counters in first patch, instead of rx and tx
   implementation patch
 * make virtio-user not supported with packed virtqueues, to
   be fixed in other patch set?

v8-v9:
 * fix virtio_ring_free_chain_packed() to handle descriptors
   correctly in case of out-of-order
 * fix check in virtqueue_xmit_cleanup_packed() to improve performance

v7->v8:
 * move desc_is_used change to correct patch
 * remove trailing newline
 * correct xmit code, flags update and memory barrier
 * move packed desc init to dedicated function, split
   and packed variant


Jens Freimann (9):
  net/virtio: vring init for packed queues
  net/virtio: add packed virtqueue defines
  net/virtio: add packed virtqueue helpers
  net/virtio: dump packed virtqueue data
  net/virtio: implement transmit path for packed queues
  net/virtio: implement receive path for packed queues
  net/virtio: add virtio send command packed queue support
  net/virtio-user: ctrl virtqueue not supported with packed vqs
  net/virtio: enable packed virtqueues by default

Yuanhan Liu (1):
  net/virtio-user: add option to use packed queues

 drivers/net/virtio/virtio_ethdev.c            | 227 +++++--
 drivers/net/virtio/virtio_ethdev.h            |   8 +
 drivers/net/virtio/virtio_pci.h               |   7 +
 drivers/net/virtio/virtio_ring.h              |  64 +-
 drivers/net/virtio/virtio_rxtx.c              | 620 +++++++++++++++++-
 .../net/virtio/virtio_user/virtio_user_dev.c  |  25 +-
 .../net/virtio/virtio_user/virtio_user_dev.h  |   2 +-
 drivers/net/virtio/virtio_user_ethdev.c       |  14 +-
 drivers/net/virtio/virtqueue.c                |  22 +
 drivers/net/virtio/virtqueue.h                | 122 +++-
 10 files changed, 1035 insertions(+), 76 deletions(-)
  

On 12/13/18 1:34 PM, Jens Freimann wrote:
> This is a basic implementation of packed virtqueues as specified in the
> Virtio 1.1 draft. A compiled version of the current draft is available
> at https://github.com/oasis-tcs/virtio-docs.git (or as .pdf at
> https://github.com/oasis-tcs/virtio-docs/blob/master/virtio-v1.1-packed-wd10.pdf
> 
> A packed virtqueue is different from a split virtqueue in that it
> consists of only a single descriptor ring that replaces available and
> used ring, index and descriptor pointers.
> 
> Each descriptor is readable and writable and has a flags field. These flags
> will mark if a descriptor is available or used.  To detect new available descriptors
> even after the ring has wrapped, device and driver each have a
> single-bit wrap counter that is flipped from 0 to 1 and vice versa every time
> the last descriptor in the ring is used/made available.
> 
> With this patch set I see performance equal or slightly better (+2-3%) in a PVP
> scenario compared to split virtqueues (v18.11 in host)
> 
> regards,
> Jens
> 
> 
> v11->v12:
>   * add a patch to disable control vq when packed vq is enabled.
>     I have a patch to support this but it needs a bit more work
>     and I think it shouldn't stop this series from being applied
>   * rework mergeable receive buffer code to be more efficient, by
>     batching descriptor refill, similar to what Maxime proposed for
>     split virtqueues
>   * removed unnecessary checks in virtio_recv_mergeable_pkts_packed
>     (Maxime)
>   * Did not merge receive functions as Maxime suggested because it seemed
>     to cause a small performance regression
>   * Move event_flags_shadow from patch 3 to 1 (Maxime)
>   * Did not merge xmit functions and call _split/_packed functions from
>     there because it seemed to cause small performance drop (-0.5%)
>     (Maxime)
> 
> v10-v11:
>   * this version includes some fixes from Tiwei, so I added his
>     Signed-off-by to some of the patches
>   * fix hang with mergable rx buffers (Tiwei)
>   * clean-up code and simplify buffer handling (Tiwei)
>   * rebase to current virtio-next master branch
> 
> v9-v10:
>   * don't mix index into buffer list and descriptors
>   * whitespace and formatting issues
>   * remove "VQ:" in dump virtqueue patch
>   * add extra packed vring struct to virtqueue and change function
>     prototypes and code accordingly
>   * move wrap_counters to virtqueue
>   * make if-conditions for packed and !packed more clear in
>     set_rxtx_funcs()
>   * initialize wrap counters in first patch, instead of rx and tx
>     implementation patch
>   * make virtio-user not supported with packed virtqueues, to
>     be fixed in other patch set?
> 
> v8-v9:
>   * fix virtio_ring_free_chain_packed() to handle descriptors
>     correctly in case of out-of-order
>   * fix check in virtqueue_xmit_cleanup_packed() to improve performance
> 
> v7->v8:
>   * move desc_is_used change to correct patch
>   * remove trailing newline
>   * correct xmit code, flags update and memory barrier
>   * move packed desc init to dedicated function, split
>     and packed variant
> 
> 
> Jens Freimann (9):
>    net/virtio: vring init for packed queues
>    net/virtio: add packed virtqueue defines
>    net/virtio: add packed virtqueue helpers
>    net/virtio: dump packed virtqueue data
>    net/virtio: implement transmit path for packed queues

Note that the series build is broken until this patch.

>    net/virtio: implement receive path for packed queues
>    net/virtio: add virtio send command packed queue support
>    net/virtio-user: ctrl virtqueue not supported with packed vqs
>    net/virtio: enable packed virtqueues by default
> 
> Yuanhan Liu (1):
>    net/virtio-user: add option to use packed queues
> 
>   drivers/net/virtio/virtio_ethdev.c            | 227 +++++--
>   drivers/net/virtio/virtio_ethdev.h            |   8 +
>   drivers/net/virtio/virtio_pci.h               |   7 +
>   drivers/net/virtio/virtio_ring.h              |  64 +-
>   drivers/net/virtio/virtio_rxtx.c              | 620 +++++++++++++++++-
>   .../net/virtio/virtio_user/virtio_user_dev.c  |  25 +-
>   .../net/virtio/virtio_user/virtio_user_dev.h  |   2 +-
>   drivers/net/virtio/virtio_user_ethdev.c       |  14 +-
>   drivers/net/virtio/virtqueue.c                |  22 +
>   drivers/net/virtio/virtqueue.h                | 122 +++-
>   10 files changed, 1035 insertions(+), 76 deletions(-)
>
  

On Thu, Dec 13, 2018 at 05:38:02PM +0100, Maxime Coquelin wrote:
>
>
>On 12/13/18 1:34 PM, Jens Freimann wrote:
>>This is a basic implementation of packed virtqueues as specified in the
>>Virtio 1.1 draft. A compiled version of the current draft is available
>>at https://github.com/oasis-tcs/virtio-docs.git (or as .pdf at
>>https://github.com/oasis-tcs/virtio-docs/blob/master/virtio-v1.1-packed-wd10.pdf
>>
>>A packed virtqueue is different from a split virtqueue in that it
>>consists of only a single descriptor ring that replaces available and
>>used ring, index and descriptor pointers.
>>
>>Each descriptor is readable and writable and has a flags field. These flags
>>will mark if a descriptor is available or used.  To detect new available descriptors
>>even after the ring has wrapped, device and driver each have a
>>single-bit wrap counter that is flipped from 0 to 1 and vice versa every time
>>the last descriptor in the ring is used/made available.
>>
>>With this patch set I see performance equal or slightly better (+2-3%) in a PVP
>>scenario compared to split virtqueues (v18.11 in host)
>>
>>regards,
>>Jens
>>
>>
>>v11->v12:
>>  * add a patch to disable control vq when packed vq is enabled.
>>    I have a patch to support this but it needs a bit more work
>>    and I think it shouldn't stop this series from being applied
>>  * rework mergeable receive buffer code to be more efficient, by
>>    batching descriptor refill, similar to what Maxime proposed for
>>    split virtqueues
>>  * removed unnecessary checks in virtio_recv_mergeable_pkts_packed
>>    (Maxime)
>>  * Did not merge receive functions as Maxime suggested because it seemed
>>    to cause a small performance regression
>>  * Move event_flags_shadow from patch 3 to 1 (Maxime)
>>  * Did not merge xmit functions and call _split/_packed functions from
>>    there because it seemed to cause small performance drop (-0.5%)
>>    (Maxime)
>>
>>v10-v11:
>>  * this version includes some fixes from Tiwei, so I added his
>>    Signed-off-by to some of the patches
>>  * fix hang with mergable rx buffers (Tiwei)
>>  * clean-up code and simplify buffer handling (Tiwei)
>>  * rebase to current virtio-next master branch
>>
>>v9-v10:
>>  * don't mix index into buffer list and descriptors
>>  * whitespace and formatting issues
>>  * remove "VQ:" in dump virtqueue patch
>>  * add extra packed vring struct to virtqueue and change function
>>    prototypes and code accordingly
>>  * move wrap_counters to virtqueue
>>  * make if-conditions for packed and !packed more clear in
>>    set_rxtx_funcs()
>>  * initialize wrap counters in first patch, instead of rx and tx
>>    implementation patch
>>  * make virtio-user not supported with packed virtqueues, to
>>    be fixed in other patch set?
>>
>>v8-v9:
>>  * fix virtio_ring_free_chain_packed() to handle descriptors
>>    correctly in case of out-of-order
>>  * fix check in virtqueue_xmit_cleanup_packed() to improve performance
>>
>>v7->v8:
>>  * move desc_is_used change to correct patch
>>  * remove trailing newline
>>  * correct xmit code, flags update and memory barrier
>>  * move packed desc init to dedicated function, split
>>    and packed variant
>>
>>
>>Jens Freimann (9):
>>   net/virtio: vring init for packed queues
>>   net/virtio: add packed virtqueue defines
>>   net/virtio: add packed virtqueue helpers
>>   net/virtio: dump packed virtqueue data
>>   net/virtio: implement transmit path for packed queues
>
>Note that the series build is broken until this patch.

I usually run 'git rebase -x "make"' to avoid. Must have missed it
this time, but will fix it.

regards,
Jens