* Re: [kraxel@redhat.com: Re: [PATCH v9 5/7] vfio: Define vfio based dma-buf operations] [not found] <20170623092553.7cckmv43fmdxnbmq@zhen-hp.sh.intel.com> @ 2017-06-23 9:34 ` Zhi Wang 0 siblings, 0 replies; 2+ messages in thread From: Zhi Wang @ 2017-06-23 9:34 UTC (permalink / raw) To: Gerd Hoffmann Cc: Wang, Zhenyu Z, linux-kernel@vger.kernel.org, intel-gfx, kwankhede, Zhiyuan Lv, intel-gvt-dev@lists.freedesktop.org Hi Gred and Alex: Thanks for the reply! It would be better that kernel only provides functions instead of maintaining states from my point of view. If there is any existing async notification channel in vfio device fd? like reporting device events from vfio to QEMU? If so, It would be nice if we can extend that channel and notify the userspace application that guest framebuffer changed via that channel. So userspace application even doesn't need to call the ioctl periodically. :) If VM runs a single-buffered application. Thanks, Zhi. On Fri, 2017-06-23 at 15:49 +0800, Zhi Wang wrote: >> Hi: >> Thanks for the discussions! If the userspace application has >> already maintained a LRU list, it looks like we don't need >> generation >> anymore, > generation isn't required, things are working just fine without that. > It is just a small optimization, userspace can skip the LRU lookup > altogether if the generation didn't change. > > But of couse that only pays off if the kernel doesn't has to put much > effort into maintaining the generation id. Something simple like > increasing it each time the guest writes a register which affects > plane_info. > > If you think it doesn't make sense from the driver point of view we can > drop the generation. > > cheers, > Gerd _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx ^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [kraxel@redhat.com: Re: [Intel-gfx] [PATCH v9 5/7] vfio: Define vfio based dma-buf operations] @ 2017-06-23 9:34 ` Zhi Wang 0 siblings, 0 replies; 2+ messages in thread From: Zhi Wang @ 2017-06-23 9:34 UTC (permalink / raw) To: Gerd Hoffmann Cc: Alex Williamson, Wang, Zhenyu Z, intel-gfx, linux-kernel@vger.kernel.org, Zhang, Tina, kwankhede, Zhiyuan Lv, intel-gvt-dev@lists.freedesktop.org Hi Gred and Alex: Thanks for the reply! It would be better that kernel only provides functions instead of maintaining states from my point of view. If there is any existing async notification channel in vfio device fd? like reporting device events from vfio to QEMU? If so, It would be nice if we can extend that channel and notify the userspace application that guest framebuffer changed via that channel. So userspace application even doesn't need to call the ioctl periodically. :) If VM runs a single-buffered application. Thanks, Zhi. On Fri, 2017-06-23 at 15:49 +0800, Zhi Wang wrote: >> Hi: >> Thanks for the discussions! If the userspace application has >> already maintained a LRU list, it looks like we don't need >> generation >> anymore, > generation isn't required, things are working just fine without that. > It is just a small optimization, userspace can skip the LRU lookup > altogether if the generation didn't change. > > But of couse that only pays off if the kernel doesn't has to put much > effort into maintaining the generation id. Something simple like > increasing it each time the guest writes a register which affects > plane_info. > > If you think it doesn't make sense from the driver point of view we can > drop the generation. > > cheers, > Gerd ^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2017-06-23 9:47 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
[not found] <20170623092553.7cckmv43fmdxnbmq@zhen-hp.sh.intel.com>
2017-06-23 9:34 ` [kraxel@redhat.com: Re: [PATCH v9 5/7] vfio: Define vfio based dma-buf operations] Zhi Wang
2017-06-23 9:34 ` [kraxel@redhat.com: Re: [Intel-gfx] " Zhi Wang
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.