Re: [PATCH] drm/ttm: clean up the inteface which is not used

Am 25.03.20 um 16:34 schrieb Huang Rui: invalidate_caches is actually not used, so clean it up. Signed-off-by: Huang Rui Already had the same patch around for a while, looks like I've just forgot to commit it. Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

Re: [PATCH] drm/ttm: clean up the inteface which is not used

On Wed, Mar 25, 2020 at 1:20 PM Christian König wrote: > > Am 25.03.20 um 16:34 schrieb Huang Rui: > > invalidate_caches is actually not used, so clean it up. > > > > Signed-off-by: Huang Rui > > Already had the same patch around for a while, looks like I've just > forgot to commit it. > >

Re: [PATCH -next] drm/amdgpu/uvd7: remove unnecessary conversion to bool

On Wed, Mar 25, 2020 at 4:17 AM Chen Zhou wrote: > > The conversion to bool is not needed, remove it. > > Signed-off-by: Chen Zhou Applied. Thanks! Alex > --- > drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git

[PATCH] drm/amd/amdgpu: Fix SMUIO/PWR Confusion

The PWR block was merged into the SMUIO block by revision 12 so we add that to the smuio_12_0_0 headers and then create a new smio_10_0_0 that raven1 can use in conjunction with the pwr_10_0 headers. Signed-off-by: Tom St Denis --- .../asic_reg/smuio/smuio_10_0_0_offset.h | 27

Re: [PATCH] drm/amd/amdgpu: Fix SMUIO/PWR Confusion (v2)

On 2020-03-25 3:28 p.m., Deucher, Alexander wrote: [AMD Public Use] While you are at it, can you clean up the local defines of these registers in

Re: [PATCH] drm/amd/amdgpu: Fix SMUIO/PWR Confusion (v2)

On Wed, Mar 25, 2020 at 3:22 PM Tom St Denis wrote: > > The PWR block was merged into the SMUIO block by revision 12 so we add > that to the smuio_12_0_0 headers. > > (v2): Drop nonsensical smuio_10_0_0 header > > Signed-off-by: Tom St Denis Reviewed-by: Alex Deucher > --- >

Re: [PATCH 2/2] drm/amd/amdgpu: Move PWR_MISC_CNTL_STATUS to its own header

On Wed, Mar 25, 2020 at 2:08 PM Tom St Denis wrote: > > The register is part of the PWR block not the GC block. Move to > its own header. > > Signed-off-by: Tom St Denis Series is: Reviewed-by: Alex Deucher > --- > .../amd/include/asic_reg/gc/gc_9_1_offset.h | 2 -- >

rv200 video corruption caused by what? kernel? Xserver? DDX? Mesa?

01:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] RV200 [Radeon 7500/7500 LE] [1002:5157] Debian Buster and Mageia 7 are OK, but with Fedora 30 and Tumbleweed with kernels newer than 5.3.x, solid background and mouse pointer are all that paint properly:

Re: [PATCH] drm/amd/amdgpu: Fix SMUIO/PWR Confusion (v2)

[AMD Public Use] While you are at it, can you clean up the local defines of these registers in drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c drivers/gpu/drm/amd/powerplay/smu_v12_0.c drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c and verify that the appropriate offset is used for both Renoir and

Re: [PATCH] drm/ttm: clean up the inteface which is not used

Am 25.03.20 um 18:27 schrieb Alex Deucher: On Wed, Mar 25, 2020 at 1:20 PM Christian König wrote: Am 25.03.20 um 16:34 schrieb Huang Rui: invalidate_caches is actually not used, so clean it up. Signed-off-by: Huang Rui Already had the same patch around for a while, looks like I've just

Re: rv200 video corruption caused by what? kernel? Xserver? DDX? Mesa?

On Wed, Mar 25, 2020 at 11:36 AM Felix Miata wrote: > > 01:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. > [AMD/ATI] RV200 [Radeon 7500/7500 LE] [1002:5157] > > Debian Buster and Mageia 7 are OK, but with Fedora 30 and Tumbleweed with > kernels newer than 5.3.x, solid

[PATCH 2/2] drm/amd/amdgpu: Move PWR_MISC_CNTL_STATUS to its own header

The register is part of the PWR block not the GC block. Move to its own header. Signed-off-by: Tom St Denis --- .../amd/include/asic_reg/gc/gc_9_1_offset.h | 2 -- .../amd/include/asic_reg/gc/gc_9_1_sh_mask.h | 5 .../include/asic_reg/pwr/pwr_10_0_offset.h| 27 +

[PATCH 1/2] drm/amd/amdgpu: Add missing SMUIO v12 register to headers

This register is needed by umr. Signed-off-by: Tom St Denis --- .../asic_reg/smuio/smuio_12_0_0_offset.h | 27 ++ .../asic_reg/smuio/smuio_12_0_0_sh_mask.h | 28 +++ 2 files changed, 55 insertions(+) create mode 100644

[PATCH] drm/amd/amdgpu: Fix SMUIO/PWR Confusion (v2)

The PWR block was merged into the SMUIO block by revision 12 so we add that to the smuio_12_0_0 headers. (v2): Drop nonsensical smuio_10_0_0 header Signed-off-by: Tom St Denis --- .../gpu/drm/amd/include/asic_reg/smuio/smuio_12_0_0_offset.h | 3 +++

Re: rv200 video corruption caused by what? kernel? Xserver? DDX? Mesa?

Felix Miata composed on 2020-03-25 19:30 (UTC-0400): > Alex Deucher composed on 2020-03-25 13:22 (UTC-0400): >> Felix Miata wrote: >>> 01:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. >>> [AMD/ATI] RV200 [Radeon 7500/7500 LE] [1002:5157] >>> Debian Buster and Mageia 7

Re: rv200 video corruption caused by what? kernel? Xserver? DDX? Mesa?

Alex Deucher composed on 2020-03-25 13:22 (UTC-0400): > Felix Miata wrote: >> 01:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. >> [AMD/ATI] RV200 [Radeon 7500/7500 LE] [1002:5157] >> Debian Buster and Mageia 7 are OK, but with Fedora 30 and Tumbleweed with >> kernels

[RFC PATCH 2/2] drm/amdgpu: use new job alloc variation if possible

If we scheduler IB directly, then alloc job ibs in direct ib pool. Signed-off-by: xinhui pan --- drivers/gpu/drm/amd/amdgpu/amdgpu_jpeg.c| 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c

[RFC PATCH 0/2] add direct IB pool

druing gpu recovery, we alloc ibs for ring tests to test if recovery succeed or not. As gpu recovery parked the gpu scheduler thread, any pending jobs hold the ib resource has no chance to free. So the ring test above got stuck if no ib to alloc. If we schedule IBs directly in job_submit_direct,

[RFC PATCH 1/2] drm/amdgpu: add direct ib pool

Another ib poll for direct submit. Any jobs schedule IBs without dependence on gpu scheduler should use this pool firstly. Signed-off-by: xinhui pan --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 12

RE: [PATCH 2/4] SWDEV-227334 - No need support vcn decode

Reviewed-by: Monk Liu _ Monk Liu|GPU Virtualization Team |AMD -Original Message- From: amd-gfx On Behalf Of Deng, Emily Sent: Thursday, March 26, 2020 11:16 AM To: Deng, Emily ; amd-gfx@lists.freedesktop.org Subject: RE: [PATCH 2/4] SWDEV-227334 -

Re: [PATCH] drm/amdgpu: fix the missing braces

On Wed, Mar 25, 2020 at 11:47:08PM +0800, Das, Nirmoy wrote: > Hi Ray, > > I pushed a fix few minutes ago :) > No problem, that's fine. I should have looked at the mail list firstly. Thanks, Ray > > Regards, > > Nirmoy > > On 3/25/20 4:39 PM, Huang Rui wrote: > > The braces are missed

Re: [PATCH] drm/ttm: clean up the inteface which is not used

On Thu, Mar 26, 2020 at 01:30:31AM +0800, Christian König wrote: > Am 25.03.20 um 18:27 schrieb Alex Deucher: > > On Wed, Mar 25, 2020 at 1:20 PM Christian König > > wrote: > >> Am 25.03.20 um 16:34 schrieb Huang Rui: > >>> invalidate_caches is actually not used, so clean it up. > >>> > >>>

Re: [RFC PATCH 1/2] drm/amdgpu: add direct ib pool

Yeah that's on my TODO list for quite a while as well. But we even need three IB pools. One very small for the IB tests, one for direct VM updates and one for the rest. So please make the pool a parameter to ib_get() and not the hack you have below. Thanks, Christian. Am 26.03.2020 03:02

RE: [PATCH 2/4] SWDEV-227334 - No need support vcn decode

[AMD Official Use Only - Internal Distribution Only] Ping. Best wishes Emily Deng >-Original Message- >From: amd-gfx On Behalf Of Emily >Deng >Sent: Wednesday, March 25, 2020 4:33 PM >To: amd-gfx@lists.freedesktop.org >Cc: Deng, Emily >Subject: [PATCH 2/4] SWDEV-227334 - No need

RE: [RFC PATCH 0/2] add direct IB pool

That sounds a roughly doable plan to me , although we didn't hit this issue in our virtualization stress test but like a possible issue. >>> So the ring test above got stuck if no ib to alloc. Why there is IB alloc happened in ring test ? I remember there is no IB allocated for ring test, are

RE: [PATCH] SWDEV-227226 [AWS][Linux]ReallyQuick test failed, guest dmesg and host dmesg have error

[AMD Official Use Only - Internal Distribution Only] Ping.. -Original Message- From: Jiawei Sent: Wednesday, March 25, 2020 4:32 PM To: amd-gfx@lists.freedesktop.org Cc: Gu, JiaWei (Will) Subject: [PATCH] SWDEV-227226 [AWS][Linux]ReallyQuick test failed, guest dmesg and host

Re: [RFC PATCH 1/1] drm/amdgpu: rework sched_list generation

On Tue, Mar 24, 2020 at 07:40:10PM +0800, Nirmoy Das wrote: > Generate HW IP's sched_list in amdgpu_ring_init() instead of > amdgpu_ctx.c. This makes amdgpu_ctx_init_compute_sched(), > ring.has_high_prio and amdgpu_ctx_init_sched() unnecessary. > This patch also stores sched_list for all HW IPs in

[PATCH 1/1] drm/amdgpu: add missing if clause guard

Fixes: 635f3790ac964 (drm/amdgpu: don't try to reserve training bo for sriov) compilation warning: drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c: In function ‘amdgpu_ttm_init’: drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c:1862:2: warning: this ‘if’ clause does not guard... [-Wmisleading-indentation] 1862

Re: [PATCH 4/4] SWDEV-226663 - Ignore the not supported error from psp

On Wed, Mar 25, 2020 at 4:33 AM Emily Deng wrote: > > As the VCN firmware will not use > vf vmr now. And new psp policy won't support set tmr > now. > For driver compatible issue, ignore the not support error. > > Signed-off-by: Emily Deng Please fix the patch title. With that fixed:

[PATCH] drm/ttm: clean up the inteface which is not used

invalidate_caches is actually not used, so clean it up. Signed-off-by: Huang Rui --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c| 6 -- drivers/gpu/drm/nouveau/nouveau_bo.c | 7 --- drivers/gpu/drm/qxl/qxl_ttm.c | 6 -- drivers/gpu/drm/radeon/radeon_ttm.c

Re: [PATCH 1/4] SWDEV-227605 - Virtual display need to support multiple ctrcs

Please fix the subject to be "drm/amdgpu: " rather than SWDEV- Alex On Wed, Mar 25, 2020 at 4:24 AM Emily Deng wrote: > > The crtc num is determined by virtual_display parameter. > > Signed-off-by: Emily Deng > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 3 ++- > 1 file changed, 2

Re: [PATCH 2/4] SWDEV-227334 - No need support vcn decode

On 2020-03-25 04:32, Emily Deng wrote: > As no need to support vcn decode feature, so diable the > ring. "diable" --> "disable" > > Signed-off-by: Emily Deng > --- > drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 4 > 1 file changed, 4 insertions(+) > > diff --git

Re: [PATCH 2/4] drm/amdgpu: Add AQUIRE_MEM PACKET3 fields defintion

On 2020-03-25 10:29, Andrey Grodzovsky wrote: > Add this for gfx10 and gfx9. > > Signed-off-by: Andrey Grodzovsky > --- > drivers/gpu/drm/amd/amdgpu/nvd.h| 48 > + > drivers/gpu/drm/amd/amdgpu/soc15d.h | 25 ++- > 2 files changed, 72

Re: [PATCH 2/4] SWDEV-227334 - No need support vcn decode

On Wed, Mar 25, 2020 at 4:33 AM Emily Deng wrote: > > As no need to support vcn decode feature, so diable the > ring. > > Signed-off-by: Emily Deng Please fix the patch title prefix to drm/amdgpu. An additional comment below. > --- > drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 4 > 1 file

Re: [PATCH 3/4] SWDEV-227979 - Add 4k resolution for virtual display

On Wed, Mar 25, 2020 at 4:33 AM Emily Deng wrote: > > Add 4k resolution for virtual connector. > > Signed-off-by: Emily Deng Please fix the patch title. With that fixed: Reviewed-by: Alex Deucher > --- > drivers/gpu/drm/amd/amdgpu/dce_virtual.c | 10 +++--- > 1 file changed, 7

Re: [PATCH 1/1] drm/amdgpu: add missing if clause guard

[AMD Public Use] Reviewed-by: Alex Deucher From: Nirmoy Das Sent: Wednesday, March 25, 2020 11:24 AM To: amd-gfx@lists.freedesktop.org Cc: Liu, Monk ; Koenig, Christian ; Deucher, Alexander ; Das, Nirmoy Subject: [PATCH 1/1] drm/amdgpu: add missing if clause

Re: [PATCH 4/4] SWDEV-226663 - Ignore the not supported error from psp

On 2020-03-25 04:33, Emily Deng wrote: > As the VCN firmware will not use > vf vmr now. And new psp policy won't support set tmr > now. > For driver compatible issue, ignore the not support error. The line wrap is a bit off here. > > Signed-off-by: Emily Deng > --- >

[PATCH] drm/amdgpu: fix the missing braces

The braces are missed around amdgpu_ttm_training_reserve_vram_init(). Signed-off-by: Huang Rui --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

Re: [PATCH 1/4] drm/radeon: remove unneeded header include path

On Tue, Mar 24, 2020 at 9:14 PM Masahiro Yamada wrote: > > On Wed, Mar 25, 2020 at 4:42 AM Alex Deucher wrote: > > > > On Tue, Mar 24, 2020 at 12:48 PM Masahiro Yamada > > wrote: > > > > > > Hi, > > > > > > I think this series is a good clean-up. > > > > > > Could you take a look at this

Re: [PATCH 4/4] drm/amdgpu: Add a UAPI flag for user to call mem_sync

On Wed, Mar 25, 2020 at 10:30 AM Andrey Grodzovsky wrote: > > This flag used to avoid calling mem_sync without need. > > Signed-off-by: Andrey Grodzovsky > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 +++ > drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 4 >

Re: [PATCH 2/2] drm/amdgpu: add full TMZ support into amdgpu_ttm_map_buffer v2

On Mon, Mar 23, 2020 at 08:24:03PM +0800, Christian König wrote: > Am 23.03.20 um 09:29 schrieb Huang Rui: > > On Sun, Mar 22, 2020 at 04:48:35PM +0100, Christian König wrote: > >> This should allow us to also support VRAM->GTT moves. > >> > >> v2: fix missing vram_base_adjustment > >> > >>

Re: [PATCH] drm/amdgpu: fix the missing braces

Hi Ray, I pushed a fix few minutes ago :) Regards, Nirmoy On 3/25/20 4:39 PM, Huang Rui wrote: The braces are missed around amdgpu_ttm_training_reserve_vram_init(). Signed-off-by: Huang Rui --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 ++- 1 file changed, 2 insertions(+), 1

[PATCH 0/4] Invalidate and flush caches at the beginning of every gfx IB

This patchset introduces AQUIRE_MEM packet submission at the begining of each gfx IB if requested by user mode client. This is helpful in solving issues with cache coherency during amdgpu_test and Vulkan CTS tests. Andrey Grodzovsky (4): drm/amdgpu: Add new ring callback to insert memory

[PATCH 2/4] drm/amdgpu: Add AQUIRE_MEM PACKET3 fields defintion

Add this for gfx10 and gfx9. Signed-off-by: Andrey Grodzovsky --- drivers/gpu/drm/amd/amdgpu/nvd.h| 48 + drivers/gpu/drm/amd/amdgpu/soc15d.h | 25 ++- 2 files changed, 72 insertions(+), 1 deletion(-) diff --git

[PATCH 4/4] drm/amdgpu: Add a UAPI flag for user to call mem_sync

This flag used to avoid calling mem_sync without need. Signed-off-by: Andrey Grodzovsky --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 4 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 3 +++ include/uapi/drm/amdgpu_drm.h | 2 ++ 4 files

[PATCH 1/4] drm/amdgpu: Add new ring callback to insert memory sync

Used to flush and invalidate various caches. Signed-off-by: Andrey Grodzovsky --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 448c76c..ef9c444 100644 ---

Re: [PATCH] drm/amdgpu: fix hpd bo size calculation error

[AMD Public Use] Reviewed-by: Alex Deucher From: Wang, Kevin(Yang) Sent: Wednesday, March 25, 2020 6:44 AM To: Koenig, Christian ; Deucher, Alexander ; Zhang, Hawking Cc: amd-gfx@lists.freedesktop.org Subject: Re: [PATCH] drm/amdgpu: fix hpd bo size

rv200 video corruption caused by what? kernel? Xserver? DDX? Mesa?

01:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] RV200 [Radeon 7500/7500 LE] [1002:5157] Debian Buster and Mageia 7 are OK, but with Fedora 30 and Tumbleweed with kernels newer than 5.3.x, solid background and mouse pointer are all that paint properly:

RE: [PATCH] drm/amd/powerplay: unload mp1 for Arcturus RAS baco reset

[AMD Official Use Only - Internal Distribution Only] Reviewed-by: Feifei Xu -Original Message- From: amd-gfx On Behalf Of Evan Quan Sent: 2020年3月25日 16:12 To: amd-gfx@lists.freedesktop.org Cc: Quan, Evan Subject: [PATCH] drm/amd/powerplay: unload mp1 for Arcturus RAS baco reset

Re: [PATCH] drm/amdgpu: Check entity rq

> 2020年3月25日 15:48，Koenig, Christian 写道： > > Am 25.03.20 um 06:47 schrieb xinhui pan: >> Hit panic during GPU recovery test. drm_sched_entity_select_rq might >> set NULL to rq. So add a check like drm_sched_job_init does. > > NAK, the rq should never be set to NULL in the first place. > >

[PATCH] drm/amd/powerplay: unload mp1 for Arcturus RAS baco reset

This sequence is recommended by PMFW team for the baco reset with PMFW reloaded. And it seems able to address the random failure seen on Arcturus. Change-Id: Ic5a83ad46466a12533e9f704ad06348852156e78 Signed-off-by: Evan Quan --- drivers/gpu/drm/amd/powerplay/smu_v11_0.c | 6 ++ 1 file

[PATCH 4/4] SWDEV-226663 - Ignore the not supported error from psp

As the VCN firmware will not use vf vmr now. And new psp policy won't support set tmr now. For driver compatible issue, ignore the not support error. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 6 +- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git

[PATCH 2/4] SWDEV-227334 - No need support vcn decode

As no need to support vcn decode feature, so diable the ring. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 4 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c index ec8091a..febd4c2 100644

[PATCH] drm/amdgpu: added xgmi ras error reset sequence

[AMD Official Use Only - Internal Distribution Only] Submitting patch to clear xgmi ras error counters inbetween ras error query 0001-drm-amdgpu-added-xgmi-ras-error-reset-sequence.patch Description: 0001-drm-amdgpu-added-xgmi-ras-error-reset-sequence.patch

[PATCH] drm/amdgpu: disable ras query and injection during gpu reset

[AMD Official Use Only - Internal Distribution Only] Submitting patch to disable ras debugfs features during the entire GPU reset cycle 0001-drm-amdgpu-disable-ras-query-during-gpu-reset.patch Description: 0001-drm-amdgpu-disable-ras-query-during-gpu-reset.patch

RE: [PATCH] drm/amdgpu: added xgmi ras error reset sequence

[AMD Official Use Only - Internal Distribution Only] + case CHIP_VEGA20: + default: I'd suggest do nothing for default case. Other than that the patch is Reviewed-by: Hawking Zhang Regards, Hawking From: Clements, John Sent: Wednesday, March 25, 2020 14:50 To:

[PATCH 1/4] SWDEV-227605 - Virtual display need to support multiple ctrcs

The crtc num is determined by virtual_display parameter. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index

Re: [PATCH 1/4] drm/amdgpu: don't try to reserve training bo for sriov

Am 24.03.20 um 11:58 schrieb Monk Liu: 1) SRIOV guest KMD doesn't care training buffer 2) if we resered training buffer that will overlap with IP discovery reservation because training buffer is at vram_size - 0x8000 and IP discovery is at ()vram_size - 0x1 => vram_size -1) Signed-off-by:

Re: [PATCH] drm/amdgpu: Check entity rq

Am 25.03.20 um 06:47 schrieb xinhui pan: Hit panic during GPU recovery test. drm_sched_entity_select_rq might set NULL to rq. So add a check like drm_sched_job_init does. NAK, the rq should never be set to NULL in the first place. How did that happened? Regards, Christian. Cc: Christian

[PATCH -next] drm/amdgpu/uvd7: remove unnecessary conversion to bool

The conversion to bool is not needed, remove it. Signed-off-by: Chen Zhou --- drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 0995378..20f10a5 100644

[PATCH 3/4] SWDEV-227979 - Add 4k resolution for virtual display

Add 4k resolution for virtual connector. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/dce_virtual.c | 10 +++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index

RE: [PATCH 7/7] drm/amdgpu: postpone entering fullaccess mode

[AMD Official Use Only - Internal Distribution Only] Series Reviewed-by: Emily Deng >-Original Message- >From: amd-gfx On Behalf Of Monk Liu >Sent: Wednesday, March 25, 2020 11:59 AM >To: amd-gfx@lists.freedesktop.org >Cc: Liu, Monk >Subject: [PATCH 7/7] drm/amdgpu: postpone entering

[PATCH] drm/amdgpu: fix hpd bo size calculation error

the HPD bo size calculation error. the "mem.size" can't present actual BO size all time. Signed-off-by: Kevin Wang --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git

Re: [PATCH] drm/amdgpu: fix hpd bo size calculation error

[AMD Official Use Only - Internal Distribution Only] thanks chris. @Deucher, Alexander @Zhang, Hawking from the view of driver, could you help me review it, then give me a RB. thanks. Best Regards, Kevin

RE: [PATCH 3/4] SWDEV-227979 - Add 4k resolution for virtual display

Reviewed-by: Monk Liu < monk@amd.com> _ Monk Liu|GPU Virtualization Team |AMD -Original Message- From: amd-gfx On Behalf Of Emily Deng Sent: Wednesday, March 25, 2020 4:33 PM To: amd-gfx@lists.freedesktop.org Cc: Deng, Emily Subject: [PATCH 3/4]

RE: [PATCH 4/4] SWDEV-226663 - Ignore the not supported error from psp

Reviewed-by: Monk Liu < monk@amd.com> _ Monk Liu|GPU Virtualization Team |AMD -Original Message- From: amd-gfx On Behalf Of Emily Deng Sent: Wednesday, March 25, 2020 4:33 PM To: amd-gfx@lists.freedesktop.org Cc: Deng, Emily Subject: [PATCH 4/4]

Re: [PATCH] drm/amdgpu: Check entity rq

> 2020年3月25日 17:23，Pan, Xinhui 写道： > > > >> 2020年3月25日 15:48，Koenig, Christian 写道： >> >> Am 25.03.20 um 06:47 schrieb xinhui pan: >>> Hit panic during GPU recovery test. drm_sched_entity_select_rq might >>> set NULL to rq. So add a check like drm_sched_job_init does. >> >> NAK, the rq

Re: [PATCH] drm/amdgpu: Check entity rq

On 3/25/20 10:23 AM, Pan, Xinhui wrote: 2020年3月25日 15:48，Koenig, Christian 写道： Am 25.03.20 um 06:47 schrieb xinhui pan: Hit panic during GPU recovery test. drm_sched_entity_select_rq might set NULL to rq. So add a check like drm_sched_job_init does. NAK, the rq should never be set to NULL

Re: [PATCH] drm/amdgpu: Check entity rq

Hi guys, thanks for pointing this out Nirmoy. Yeah, could be that I forgot to commit the patch. Currently I don't know at which end of the chaos I should start to clean up. Christian. Am 25.03.2020 12:09 schrieb "Das, Nirmoy" : Hi Xinhui, Can you please check if you can reproduce the crash

Re: [PATCH] drm/amdgpu: fix hpd bo size calculation error

Good catch! mem.size is actually the backing store size (usually in pages). Patch is Acked-by: Christian König Am 25.03.2020 11:19 schrieb "Wang, Kevin(Yang)" : the HPD bo size calculation error. the "mem.size" can't present actual BO size all time. Signed-off-by: Kevin Wang ---

Re: [RFC PATCH 1/1] drm/amdgpu: rework sched_list generation

On 3/24/20 7:41 PM, Christian König wrote: Am 24.03.20 um 12:40 schrieb Nirmoy Das: Generate HW IP's sched_list in amdgpu_ring_init() instead of amdgpu_ctx.c. This makes amdgpu_ctx_init_compute_sched(), ring.has_high_prio and amdgpu_ctx_init_sched() unnecessary. This patch also stores

RE: [PATCH 1/4] SWDEV-227605 - Virtual display need to support multiple ctrcs

Reviewed-by: Monk Liu < monk@amd.com> _ Monk Liu|GPU Virtualization Team |AMD -Original Message- From: amd-gfx On Behalf Of Emily Deng Sent: Wednesday, March 25, 2020 4:25 PM To: amd-gfx@lists.freedesktop.org Cc: Deng, Emily Subject: [PATCH 1/4]

[PATCH] drm/amdgpu: Check entity rq

gpu recover will call sdma suspend/resume. In this period, ring will be disabled. So the vm_pte_scheds(sdma.instance[X].ring.sched)->ready will be false. If we submit any jobs in this ring-disabled period. We fail to pick up a rq for vm entity and entity->rq will set to NULL.

Re: [PATCH] drm/amdgpu: Check entity rq

Hi Xinhui, Can you please check if you can reproduce the crash with https://lists.freedesktop.org/archives/amd-gfx/2020-February/046414.html Christian fix it earlier, I think he forgot to push it. Regards, Nirmoy On 3/25/20 12:07 PM, xinhui pan wrote: gpu recover will call sdma

Re: [PATCH] drm/amdgpu: Check entity rq

[AMD Official Use Only - Internal Distribution Only] well, submit job with HW disabled shluld be no harm. The only concern is that we might use up IBs if we park scheduler during recovery. I have saw recovery stuck in sa new functuon. ring test alloc IBs to test if recovery succeed or not. But

Re: [PATCH] drm/amdgpu: Check entity rq

well, submit job with HW disabled shluld be no harm. The only concern is that we might use up IBs if we park scheduler thread during recovery. I have saw recovery stuck in sa new functuon. ring test alloc IBs to test if recovery succeed or not. But if there is no enough IBs it will wait