similar to: [RFC PATCH V3 0/5] Hi:

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Changes from V1: - instead of pinning pages, use MMU notifier to invalidate vmaps and remap duing

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through vmap() and resigter MMU notifier for invalidation. Test shows about 24% improvement on TX PPS. TCP_STREAM doesn't see obvious improvement.

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through vmap() and resigter MMU notifier for invalidation. Test shows about 24% improvement on TX PPS. TCP_STREAM doesn't see obvious improvement.

On Sat, Dec 29, 2018 at 08:46:56PM +0800, Jason Wang wrote: > It was noticed that the copy_user() friends that was used to access > virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of software checks, > speculation barrier, hardware feature toggling (e.g SMAP). The > extra cost will be more obvious when transferring small

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Please review Jason Wang (3): vhost: generalize adding used elem vhost: fine grain userspace memory

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. Test shows about 24% improvement on TX PPS. It should benefit other cases as well. Please review Jason Wang (3): vhost: generalize adding used elem vhost: fine grain userspace memory

On Thu, Dec 13, 2018 at 06:10:22PM +0800, Jason Wang wrote: > It was noticed that the copy_user() friends that was used to access > virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of software check, > speculation barrier, hardware feature toggling (e.g SMAP). The > extra cost will be more obvious when transferring small

On Thu, Dec 13, 2018 at 06:10:22PM +0800, Jason Wang wrote: > It was noticed that the copy_user() friends that was used to access > virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of software check, > speculation barrier, hardware feature toggling (e.g SMAP). The > extra cost will be more obvious when transferring small

This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM doesn't see obvious

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling like SMAP. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM

Hi: This series tries to access virtqueue metadata through kernel virtual address instead of copy_user() friends since they had too much overheads like checks, spec barriers or even hardware feature toggling like SMAP. This is done through setup kernel address through direct mapping and co-opreate VM management with MMU notifiers. Test shows about 23% improvement on TX PPS. TCP_STREAM

Hi: Per request from Michael and Jason, the metadata accelreation is reverted in this version and rework in next version. Please review. Thanks Jason Wang (2): Revert "vhost: access vq metadata through kernel virtual address" vhost: re-introducing metadata acceleration through kernel virtual address drivers/vhost/vhost.c | 202 +++++++++++++++++++++++++-----------------

Hi: Per request from Michael and Jason, the metadata accelreation is reverted in this version and rework in next version. Please review. Thanks Jason Wang (2): Revert "vhost: access vq metadata through kernel virtual address" vhost: re-introducing metadata acceleration through kernel virtual address drivers/vhost/vhost.c | 202 +++++++++++++++++++++++++-----------------

On Fri, Dec 14, 2018 at 11:57:35AM +0800, Jason Wang wrote: > > On 2018/12/13 ??11:44, Michael S. Tsirkin wrote: > > On Thu, Dec 13, 2018 at 06:10:22PM +0800, Jason Wang wrote: > > > It was noticed that the copy_user() friends that was used to access > > > virtqueue metdata tends to be very expensive for dataplane > > > implementation like vhost since it

On Fri, Dec 14, 2018 at 11:57:35AM +0800, Jason Wang wrote: > > On 2018/12/13 ??11:44, Michael S. Tsirkin wrote: > > On Thu, Dec 13, 2018 at 06:10:22PM +0800, Jason Wang wrote: > > > It was noticed that the copy_user() friends that was used to access > > > virtqueue metdata tends to be very expensive for dataplane > > > implementation like vhost since it

On Thu, Sep 05, 2019 at 08:27:35PM +0800, Jason Wang wrote: > It was reported that metadata acceleration introduces several issues, > so this patch reverts commit ff466032dc9e5a61217f22ea34b2df932786bbfc, > 73f628ec9e6bcc45b77c53fe6d0c0ec55eaf82af and > 0b4a7092ffe568a55bf8f3cefdf79ff666586d91. > > We will rework it on the next version. > > Cc: Jason Gunthorpe <jgg at

On Mon, Dec 24, 2018 at 03:53:16PM +0800, Jason Wang wrote: > > On 2018/12/14 ??8:36, Michael S. Tsirkin wrote: > > On Fri, Dec 14, 2018 at 11:57:35AM +0800, Jason Wang wrote: > > > On 2018/12/13 ??11:44, Michael S. Tsirkin wrote: > > > > On Thu, Dec 13, 2018 at 06:10:22PM +0800, Jason Wang wrote: > > > > > It was noticed that the copy_user()

On Mon, Dec 24, 2018 at 03:53:16PM +0800, Jason Wang wrote: > > On 2018/12/14 ??8:36, Michael S. Tsirkin wrote: > > On Fri, Dec 14, 2018 at 11:57:35AM +0800, Jason Wang wrote: > > > On 2018/12/13 ??11:44, Michael S. Tsirkin wrote: > > > > On Thu, Dec 13, 2018 at 06:10:22PM +0800, Jason Wang wrote: > > > > > It was noticed that the copy_user()

On Wed, Mar 06, 2019 at 02:18:12AM -0500, Jason Wang wrote: > It was noticed that the copy_user() friends that was used to access > virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of software checks, > speculation barrier, hardware feature toggling (e.g SMAP). The > extra cost will be more obvious when transferring small

On Wed, Mar 06, 2019 at 02:18:12AM -0500, Jason Wang wrote: > It was noticed that the copy_user() friends that was used to access > virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of software checks, > speculation barrier, hardware feature toggling (e.g SMAP). The > extra cost will be more obvious when transferring small