Re: [Intel-gfx] [PATCH v6 09/14] drm/i915/gvt: Add 64K huge gtt support

2018-05-14 Thread Du, Changbin
Hi Auld, On Mon, May 14, 2018 at 09:31:54PM +0100, Matthew Auld wrote: > On 8 May 2018 at 10:05, <changbin...@intel.com> wrote: > > From: Changbin Du <changbin...@intel.com> > > > > Finally, this add the first huge gtt support for GVTg - 64K pages. Since > &g

Re: [Intel-gfx] [PATCH v6 10/14] drm/i915/kvmgt: Support setting dma map for huge pages

2018-05-14 Thread Du, Changbin
Hi Auld, Thanks for your review. On Thu, May 10, 2018 at 03:31:03PM +0100, Matthew Auld wrote: > On 8 May 2018 at 10:05, <changbin...@intel.com> wrote: > > From: Changbin Du <changbin...@intel.com> > > +static int gvt_dma_map_page(struct intel_vg

Re: [Intel-gfx] ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/guc: Don't enable GuC when vGPU is active

2018-01-16 Thread Du, Changbin
e: > > > > On 2018.01.15 12:07:28 +0200, Joonas Lahtinen wrote: > > > > > On Fri, 2018-01-12 at 14:08 +0800, Du, Changbin wrote: > > > > > > On Fri, Jan 12, 2018 at 11:32:30AM +0530, Sagar Arun Kamble wrote: > > > > > > > Is skl-g

Re: [Intel-gfx] ✗ Fi.CI.BAT: failure for series starting with [1/2] drm/i915/guc: Don't enable GuC when vGPU is active

2018-01-11 Thread Du, Changbin
On Fri, Jan 12, 2018 at 11:32:30AM +0530, Sagar Arun Kamble wrote: > Is skl-gvtdvm not having vGPU active? > > It has flag X86_FEATURE_HYPERVISOR set however it might be set on host too > so relying intel_vgpu_active(). > Do you mean flag X86_FEATURE_HYPERVISOR is set on host, too? This is weird

Re: [Intel-gfx] [PATCH] drm/i915: Do not enable movntdqa optimization in hypervisor guest

2017-12-24 Thread Du, Changbin
On Fri, Dec 22, 2017 at 11:11:15AM +, Chris Wilson wrote: > Quoting changbin...@intel.com (2017-12-22 06:31:49) > > From: Changbin Du <changbin...@intel.com> > > > > Our QA reported a problem caused by movntdqa instructions. Currently, > > the KVM hype

Re: [Intel-gfx] Accelerated read from WC mem (i915_memcpy_from_wc()) may not work in virtualization world

2017-12-21 Thread Du, Changbin
On Thu, Dec 21, 2017 at 10:56:38AM +, Chris Wilson wrote: > Quoting Du, Changbin (2017-12-21 09:52:16) > > Hi Chris, > > Our QA reported a problem caused by movntdqa instructions. Currently, the > > KVM > > hypervisor doesn't support VEX-prefix instr

Re: [Intel-gfx] Accelerated read from WC mem (i915_memcpy_from_wc()) may not work in virtualization world

2017-12-21 Thread Du, Changbin
On Thu, Dec 21, 2017 at 10:58:38AM +, Chris Wilson wrote: > Quoting Du, Changbin (2017-12-21 09:52:16) > > Hi Chris, > > Our QA reported a problem caused by movntdqa instructions. Currently, the > > KVM > > hypervisor doesn't support VEX-prefix instr

[Intel-gfx] Accelerated read from WC mem (i915_memcpy_from_wc()) may not work in virtualization world

2017-12-21 Thread Du, Changbin
Hi Chris, Our QA reported a problem caused by movntdqa instructions. Currently, the KVM hypervisor doesn't support VEX-prefix instructions emulation. If users passthrough a GPU to guest with vfio option 'x-no-mmap=on', then all access to the BARs will be trapped and emulated. The KVM hypervisor

Re: [Intel-gfx] [PATCH v15 4/7] drm/i915/gvt: Add opregion support

2017-10-10 Thread Du, Changbin
On Tue, Oct 10, 2017 at 05:50:04PM +0800, Tina Zhang wrote: > Windows guest driver needs vbt in opregion, to configure the setting > for display. Without opregion support, the display registers won't > be set and this blocks display model to get the correct information > of the guest display

Re: [Intel-gfx] [PATCH v2] drm/i915: Add interface to reserve fence registers for vGPU

2017-09-04 Thread Du, Changbin
On Fri, Sep 01, 2017 at 11:59:53AM +0100, Chris Wilson wrote: > Quoting changbin...@intel.com (2017-09-01 08:08:26) > > diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c > > b/drivers/gpu/drm/i915/i915_gem_fence_reg.c > > index 5fe2cd8..429ce5f 100644 > > ---

Re: [Intel-gfx] [PATCH] drm/i915: Add interface to reserve fence registers for vGPU

2017-08-30 Thread Du, Changbin
Hi chris, On Wed, Aug 30, 2017 at 10:27:18AM +0100, Chris Wilson wrote: > Quoting changbin...@intel.com (2017-08-30 09:54:21) > > This patch added two new api to the fence management code: > > - i915_reserve_one_fence() will try to find a free fence from fence_list > >and force-remove vma

Re: [Intel-gfx] [PATCH] drm/i915: prevent generating unusable gvt build which no mpt module is selected

2017-05-26 Thread Du, Changbin
On Fri, May 26, 2017 at 12:58:55PM +0300, Jani Nikula wrote: > On Thu, 25 May 2017, "Du, Changbin" <changbin...@intel.com> wrote: > >> Note: > >>select should be used with care. select will force > >>a symbol to a value without visiting t

Re: [Intel-gfx] [PATCH] drm/i915: prevent generating unusable gvt build which no mpt module is selected

2017-05-25 Thread Du, Changbin
Hi, Jani, just relized you are in i915 team. :) > > +menu "Intel GVT-g graphics virtualization host support" > > + depends on DRM_I915 > > + depends on 64BIT > > + > > config DRM_I915_GVT > > -bool "Enable Intel GVT-g graphics virtualization host support" > > -depends on

Re: [Intel-gfx] [PATCH] drm/i915: prevent generating unusable gvt build which no mpt module is selected

2017-05-24 Thread Du, Changbin
On Wed, May 24, 2017 at 10:21:31AM +0100, Chris Wilson wrote: > On Wed, May 24, 2017 at 04:50:39PM +0800, changbin...@intel.com wrote: > > From: Changbin Du <changbin...@intel.com> > > > > At least we need one MPT module (currently only have one) selected > >

Re: [Intel-gfx] [PATCH v2] drm/i915: make context status notifier head be per engine

2017-03-16 Thread Du, Changbin
> > > Since intel_gvt_init() is called at early initialization stage and > > > require the status notifier head has been initiated, I initiate it in > > > intel_engine_setup(). > > > > > > v2: remove a redundant newline. (chris) > > > &

Re: [Intel-gfx] [PATCH] drm/i915: make context status notifier head be per engine

2017-03-12 Thread Du, Changbin
hi, chris, On Fri, Mar 10, 2017 at 05:17:17PM +, Chris Wilson wrote: > On Thu, Mar 09, 2017 at 07:27:24PM +0800, changbin...@intel.com wrote: > > From: Changbin Du <changbin...@intel.com> > > > > GVTg has introduced the context status notifier to schedule the GVTg

Re: [Intel-gfx] [RFC PATCH] drm/i915: make context status notifier head be per engine

2017-03-09 Thread Du, Changbin
hi, is there any comments for this? I'd like hear chris and daniel's comments. :) Thanks, Changbin On Thu, Mar 02, 2017 at 07:23:05PM +0800, changbin...@intel.com wrote: > From: Changbin Du <changbin...@intel.com> > > hi, Daniel, Chris and All, > As you know, GVTg introduced

Re: [Intel-gfx] [PATCH] drm/i915: check if execlist_port is empty before using its content

2016-12-25 Thread Du, Changbin
> On Fri, Dec 23, 2016 at 01:46:36PM +0800, changbin...@intel.com wrote: > > From: "Du, Changbin" <changbin...@intel.com> > > > > This patch fix a crash in function reset_common_ring. In this case, > > the port[0].request is null when reset the rende