similar to: [PATCH] vhost: Fix vhost_copy_to_user()

On 2018?04?11? 21:30, Eric Auger wrote: > vhost_copy_to_user is used to copy vring used elements to userspace. > We should use VHOST_ADDR_USED instead of VHOST_ADDR_DESC. > > Fixes: f88949138058 ("vhost: introduce O(1) vq metadata cache") > Signed-off-by: Eric Auger <eric.auger at redhat.com> > > --- > > This fixes a stall observed when running an aarch64

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: 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 +++++++++++++++++++++++++-----------------

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

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 Thu, Sep 05, 2019 at 08:27:36PM +0800, Jason Wang wrote: > This is a rework on the commit 7f466032dc9e ("vhost: access vq > metadata through kernel virtual address"). > > It was noticed that the copy_to/from_user() friends that was used to > access virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of

On Thu, Sep 05, 2019 at 08:27:36PM +0800, Jason Wang wrote: > This is a rework on the commit 7f466032dc9e ("vhost: access vq > metadata through kernel virtual address"). > > It was noticed that the copy_to/from_user() friends that was used to > access virtqueue metdata tends to be very expensive for dataplane > implementation like vhost since it involves lots of

sparse warns about converting void * to void __user *. This is not new but only got noticed now that vhost is built on more systems. This is just a question of __user tags missing in a couple of places, so fix it up. Fixes: f88949138058 ("vhost: introduce O(1) vq metadata cache") Reported-by: kbuild test robot <lkp at intel.com> Signed-off-by: Michael S. Tsirkin <mst at

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.

Hi all: This series try to fix several issues introduced by meta data accelreation series. Please review. Changes from V1: - Try not use RCU to syncrhonize MMU notifier with vhost worker - set dirty pages after no readers - return -EAGAIN only when we find the range is overlapped with metadata Jason Wang (9): vhost: don't set uaddr for invalid address vhost: validate MMU notifier

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

On Wed, Jul 31, 2019 at 04:46:53AM -0400, Jason Wang wrote: > We used to use RCU to synchronize MMU notifier with worker. This leads > calling synchronize_rcu() in invalidate_range_start(). But on a busy > system, there would be many factors that may slow down the > synchronize_rcu() which makes it unsuitable to be called in MMU > notifier. > > A solution is SRCU but its

On Wed, Jul 31, 2019 at 04:46:53AM -0400, Jason Wang wrote: > We used to use RCU to synchronize MMU notifier with worker. This leads > calling synchronize_rcu() in invalidate_range_start(). But on a busy > system, there would be many factors that may slow down the > synchronize_rcu() which makes it unsuitable to be called in MMU > notifier. > > A solution is SRCU but its

Hi all: This series try to fix several issues introduced by meta data accelreation series. Please review. Changes from V3: - remove the unnecessary patch Changes from V2: - use seqlck helper to synchronize MMU notifier with vhost worker Changes from V1: - try not use RCU to syncrhonize MMU notifier with vhost worker - set dirty pages after no readers - return -EAGAIN only when we find the

Hi all: This series try to fix several issues introduced by meta data accelreation series. Please review. Changes from V3: - remove the unnecessary patch Changes from V2: - use seqlck helper to synchronize MMU notifier with vhost worker Changes from V1: - try not use RCU to syncrhonize MMU notifier with vhost worker - set dirty pages after no readers - return -EAGAIN only when we find the

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