similar to: [PATCH net-next 0/3] vhost: accelerate metadata access through vmap()

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 V2: - fix buggy range overlapping check - tear down MMU notifier during vhost ioctl to make sure

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 V2: - fix buggy range overlapping check - tear down MMU notifier during vhost ioctl to make sure

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

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

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 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

On Tue, Dec 25, 2018 at 06:05:25PM +0800, Jason Wang wrote: > > On 2018/12/25 ??2:10, Michael S. Tsirkin wrote: > > 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

On Tue, Dec 25, 2018 at 06:05:25PM +0800, Jason Wang wrote: > > On 2018/12/25 ??2:10, Michael S. Tsirkin wrote: > > 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

On Wed, Dec 26, 2018 at 11:57:32AM +0800, Jason Wang wrote: > > On 2018/12/25 ??8:50, Michael S. Tsirkin wrote: > > On Tue, Dec 25, 2018 at 06:05:25PM +0800, Jason Wang wrote: > > > On 2018/12/25 ??2:10, Michael S. Tsirkin wrote: > > > > On Mon, Dec 24, 2018 at 03:53:16PM +0800, Jason Wang wrote: > > > > > On 2018/12/14 ??8:36, Michael S. Tsirkin

On Wed, Dec 26, 2018 at 11:57:32AM +0800, Jason Wang wrote: > > On 2018/12/25 ??8:50, Michael S. Tsirkin wrote: > > On Tue, Dec 25, 2018 at 06:05:25PM +0800, Jason Wang wrote: > > > On 2018/12/25 ??2:10, Michael S. Tsirkin wrote: > > > > On Mon, Dec 24, 2018 at 03:53:16PM +0800, Jason Wang wrote: > > > > > On 2018/12/14 ??8:36, Michael S. Tsirkin

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 packets. This patch tries to eliminate those overhead by pin vq metadata pages and

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 +++++++++++++++++++++++++-----------------