Re: [PATCH] drm/amdkfd: Change WARN to pr_debug when same userptr BOs got invalidated by mmu.

On 4/10/2023 2:58 PM, Felix Kuehling wrote: On 2023-04-10 10:36, Xiaogang.Chen wrote: From: Xiaogang Chen During KFD restore evicted userptr BOs mmu invalidate callback may invalidate same userptr BOs that have been just restored. When KFD restore process detects it KFD will reschedule

drm/amdgpu/gfx9: change the reference clock for raven/raven2

[AMD Official Use Only - General] Due to switch to golden tsc register to get clock counter for raven/ raven2. Chang the reference clock from 25MHZ to 100MHZ. Signed-off-by: Jesse Zhang jesse.zh...@amd.com diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c

drm/amdgpu/gfx9: switch to golden tsc registers for raven/raven2

[AMD Official Use Only - General] Due to raven/raven2 maybe enable sclk slow down, they cannot get clock count by the RLC at the auto level of dpm performance. So switch to golden tsc register. Signed-off-by: Jesse Zhang mailto:jesse.zh...@amd.com>> Signed-off-by: Evan Quan

Re: [PATCH] drm/sched: Check scheduler ready before calling timeout handling

On 2023-04-11 17:39, Alex Deucher wrote: > On Thu, Apr 6, 2023 at 4:01 PM Luben Tuikov wrote: >> >> From: Vitaly Prosyak >> >> During an IGT GPU reset test we see the following oops, >> >> [ +0.03] [ cut here ] >> [ +0.00] WARNING: CPU: 9 PID: 0 at

[PATCH v3 3/7] drm/amdgpu: Switch to fdinfo helper

From: Rob Clark Signed-off-by: Rob Clark --- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c| 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c | 16 ++-- drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.h | 2 +- 3 files changed, 9 insertions(+), 12 deletions(-) diff --git

[PATCH v3 0/7] drm: fdinfo memory stats

From: Rob Clark Similar motivation to other similar recent attempt[1]. But with an attempt to have some shared code for this. As well as documentation. It is probably a bit UMA-centric, I guess devices with VRAM might want some placement stats as well. But this seems like a reasonable start.

[linux-next:master] BUILD REGRESSION 009795d283d1f9f043e5a4ff97d4140cde17e2d3

tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master branch HEAD: 009795d283d1f9f043e5a4ff97d4140cde17e2d3 Add linux-next specific files for 20230411 Error/Warning reports: https://lore.kernel.org/oe-kbuild-all/202303161521.jbgbafjj-...@intel.com https

Re: [PATCH] drm/sched: Check scheduler ready before calling timeout handling

On Thu, Apr 6, 2023 at 4:01 PM Luben Tuikov wrote: > > From: Vitaly Prosyak > > During an IGT GPU reset test we see the following oops, > > [ +0.03] [ cut here ] > [ +0.00] WARNING: CPU: 9 PID: 0 at kernel/workqueue.c:1656 > __queue_delayed_work+0x6d/0xa0 > [

[PATCH V2] drm/amdgpu/gfx11: update gpu_clock_counter logic

This code was written prior to previous updates to this logic for other chips. The RSC registers are part of SMUIO which is an always on block so there is no need to disable gfxoff. Additionally add the carryover and preemption checks. v2: rebase Signed-off-by: Alex Deucher ---

RE: [PATCH] radeon: avoid double free in ci_dpm_init()

[Public] > -Original Message- > From: Nikita Zhandarovich > Sent: Monday, April 3, 2023 2:28 PM > To: Deucher, Alexander > Cc: Nikita Zhandarovich ; Koenig, Christian > ; Pan, Xinhui ; David > Airlie ; Daniel Vetter ; amd- > g...@lists.freedesktop.org; dri-de...@lists.freedesktop.org;

RE: [PATCH] drm/amdgpu: use sdma_v6 single packet invalidation

[Public] > -Original Message- > From: YuBiao Wang > Sent: Tuesday, April 11, 2023 3:17 AM > To: amd-gfx@lists.freedesktop.org > Cc: Quan, Evan ; Chen, Horace > ; Tuikov, Luben ; > Koenig, Christian ; Deucher, Alexander > ; Zhang, Hawking > ; Liu, Monk ; Xu, Feifei > ; Wang, Yang(Kevin) ;

Re: [PATCH v3 8/9] drm/amdgpu: map wptr BO into GART

On 11/04/2023 11:29, Christian König wrote: Am 10.04.23 um 02:00 schrieb Bas Nieuwenhuizen: On Wed, Mar 29, 2023 at 6:05 PM Shashank Sharma wrote: From: Arvind Yadav To support oversubscription, MES expects WPTR BOs to be mapped to GART, before they are submitted to usermode queues. Cc:

RE: [PATCH] drm/amdgpu: fix introduce gc_*_mes_2.bin v2

[AMD Official Use Only - General] > -Original Message- > From: Ma, Li > Sent: Monday, April 10, 2023 10:36 PM > To: amd-gfx@lists.freedesktop.org > Cc: Deucher, Alexander ; Zhang, Yifan > ; Huang, Tim ; Du, > Xiaojian ; Ma, Li > Subject: [PATCH] drm/amdgpu: fix introduce gc_*_mes_2.bin

Re: [PATCH 2/5] drm/amd/display: Move three variable assignments behind condition checks in trigger_hotplug()

Am 11.04.23 um 15:43 schrieb Markus Elfring: Date: Tue, 11 Apr 2023 11:39:02 +0200 The address of a data structure member was determined before a corresponding null pointer check in the implementation of the function “trigger_hotplug”. Thus avoid the risk for undefined behaviour by moving the

[PATCH 5/5] drm/amd/display: Move an expression into a return statement in dcn201_link_encoder_create()

Date: Tue, 11 Apr 2023 14:04:57 +0200 The address of a data structure member was determined before a corresponding null pointer check in the implementation of the function “dcn201_link_encoder_create”. Thus avoid the risk for undefined behaviour by moving the usage of an expression into a return

Re: [PATCH 1/5] drm/amdgpu: Move a variable assignment behind a null pointer check in amdgpu_ras_interrupt_dispatch()

>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c >> @@ -1730,11 +1730,12 @@ int amdgpu_ras_interrupt_dispatch(struct >> amdgpu_device *adev, >>   struct ras_dispatch_if *info) >>   { >>   struct ras_manager *obj = amdgpu_ras_find_obj(adev, >head); >> -    struct ras_ih_data *data =

Re: [PATCH] drm/amd/pm: remove unused num_of_active_display variable

Applied. Thanks! On Sun, Apr 9, 2023 at 8:48 PM Quan, Evan wrote: > > [AMD Official Use Only - General] > > Reviewed-by: Evan Quan > > > -Original Message- > > From: Tom Rix > > Sent: Saturday, April 1, 2023 12:41 AM > > To: Quan, Evan ; Deucher, Alexander > > ; Koenig, Christian > >

Re: [PATCH v2 1/2] drm: Spelling s/sempahore/semaphore/

On 4/11/23 06:52, Geert Uytterhoeven wrote: Fix misspellings of "semaphore". Signed-off-by: Geert Uytterhoeven Series is Reviewed-by: Hamza Mahfooz --- drivers/gpu/drm/i915/i915_request.c | 2 +- drivers/gpu/drm/radeon/cik.c| 2 +- drivers/gpu/drm/radeon/r600.c | 2 +-

Re: [PATCH 1/5] drm/amdgpu: Move a variable assignment behind a null pointer check in amdgpu_ras_interrupt_dispatch()

Am 2023-04-11 um 09:42 schrieb Markus Elfring: Date: Tue, 11 Apr 2023 10:52:48 +0200 The address of a data structure member was determined before a corresponding null pointer check in the implementation of the function “amdgpu_ras_interrupt_dispatch”. Thus avoid the risk for undefined

Re: [PATCH v2 3/3] drm/amdgpu: Add support for querying the max ibs in a submission. (v2)

Bas Nieuwenhuizen ezt írta (időpont: 2023. ápr. 11., Ke 10:25): > On Tue, Apr 11, 2023 at 10:10 AM Christian König > wrote: > > > > Am 09.04.23 um 20:59 schrieb Bas Nieuwenhuizen: > > > We need to introduce a new version of the info struct because > > > libdrm_amdgpu forgot any versioning info

[PATCH 1/2] drm: Spelling s/sempahore/semaphore/

Fix misspellings of "semaphore". Signed-off-by: Geert Uytterhoeven --- drivers/gpu/drm/i915/i915_request.c | 2 +- drivers/gpu/drm/radeon/cik.c| 2 +- drivers/gpu/drm/radeon/r600.c | 2 +- include/drm/task_barrier.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-)

[PATCH 0/5] drm/amd: Adjustments for three function implementations

Date: Tue, 11 Apr 2023 14:36:36 +0200 Some update suggestions were taken into account from static source code analysis. Markus Elfring (5) amdgpu: Move a variable assignment behind a null pointer check in amdgpu_ras_interrupt_dispatch() display: Move three variable assignments behind

[PATCH 1/5] drm/amdgpu: Move a variable assignment behind a null pointer check in amdgpu_ras_interrupt_dispatch()

Date: Tue, 11 Apr 2023 10:52:48 +0200 The address of a data structure member was determined before a corresponding null pointer check in the implementation of the function “amdgpu_ras_interrupt_dispatch”. Thus avoid the risk for undefined behaviour by moving the assignment for the variable

Re: [PATCH 2/2] drm: Spelling s/randevouz/rendez-vouz/

On Tue, Apr 11, 2023 at 7:44 AM Geert Uytterhoeven wrote: > > Fix a misspelling of "rendez-vouz". > > Signed-off-by: Geert Uytterhoeven > --- > include/drm/task_barrier.h | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/include/drm/task_barrier.h

[PATCH 4/5] drm/amd/display: Delete a redundant statement in trigger_hotplug()

Date: Tue, 11 Apr 2023 13:26:35 +0200 An immediate return is performed by this function after a null pointer was detected for the member “dc_link” in the data structure “amdgpu_dm_connector”. This check was repeated within one if branch. Thus omit such a redundant statement. Signed-off-by:

Re: [PATCH v2 3/3] drm/amdgpu: Add support for querying the max ibs in a submission. (v2)

Christian König ezt írta (időpont: 2023. ápr. 11., Ke 11:23): > Am 11.04.23 um 11:06 schrieb Timur Kristóf: > > > > Bas Nieuwenhuizen ezt írta (időpont: 2023. ápr. > 11., Ke 10:25): > >> On Tue, Apr 11, 2023 at 10:10 AM Christian König >> wrote: >> > >> > Am 09.04.23 um 20:59 schrieb Bas

Re: [PATCH 2/2] drm: Spelling s/randevouz/rendez-vouz/

Hi Marc, On Tue, Apr 11, 2023 at 12:49 PM Marc Dionne wrote: > On Tue, Apr 11, 2023 at 7:44 AM Geert Uytterhoeven > wrote: > > > > Fix a misspelling of "rendez-vouz". > > > > Signed-off-by: Geert Uytterhoeven > > --- a/include/drm/task_barrier.h > > +++ b/include/drm/task_barrier.h > > @@

[PATCH 2/5] drm/amd/display: Move three variable assignments behind condition checks in trigger_hotplug()

Date: Tue, 11 Apr 2023 11:39:02 +0200 The address of a data structure member was determined before a corresponding null pointer check in the implementation of the function “trigger_hotplug”. Thus avoid the risk for undefined behaviour by moving the assignment for three local variables behind

[PATCH 2/2] drm: Spelling s/randevouz/rendez-vouz/

Fix a misspelling of "rendez-vouz". Signed-off-by: Geert Uytterhoeven --- include/drm/task_barrier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/drm/task_barrier.h b/include/drm/task_barrier.h index 217c1cf21c1ab7d5..59ead429acb2afb0 100644 ---

[PATCH v2 1/2] drm: Spelling s/sempahore/semaphore/

Fix misspellings of "semaphore". Signed-off-by: Geert Uytterhoeven --- drivers/gpu/drm/i915/i915_request.c | 2 +- drivers/gpu/drm/radeon/cik.c| 2 +- drivers/gpu/drm/radeon/r600.c | 2 +- include/drm/task_barrier.h | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-)

[PATCH v2 2/2] drm: Spelling s/randevouz/rendez-vous/

Fix a misspelling of "rendez-vous". Signed-off-by: Geert Uytterhoeven --- v2: - s/vouz/vous/. --- include/drm/task_barrier.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/drm/task_barrier.h b/include/drm/task_barrier.h index 217c1cf21c1ab7d5..f6e6ed52968133d2

[PATCH 3/5] drm/amd/display: Delete three unnecessary variable initialisations in trigger_hotplug()

Date: Tue, 11 Apr 2023 12:34:42 +0200 The variables “link”, “wr_buf” and “ret” will eventually be set to appropriate values a bit later. Thus omit the explicit initialisation at the beginning. Signed-off-by: Markus Elfring --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 6

RE: [PATCH v2] drm/amd/display: Add logging for DP link traning Test Pattern Seqeunces

[AMD Official Use Only - General] Reviewed-by: Fangzhi Zuo > -Original Message- > From: SHANMUGAM, SRINIVASAN > Sent: Monday, April 10, 2023 1:36 PM > To: Wentland, Harry ; Zuo, Jerry > ; Li, Sun peng (Leo) ; Deucher, > Alexander > Cc: amd-gfx@lists.freedesktop.org > Subject: RE:

Re: [PATCH v2 1/3] drm/amdgpu: Reject submissions with too many IBs.

Am 09.04.23 um 20:59 schrieb Bas Nieuwenhuizen: Instead of failing somewhere in the scheduler after the ioctl has already succeeded. Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2498 Signed-off-by: Bas Nieuwenhuizen --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 9 +

Re: [PATCH v3 0/9] AMDGPU Usermode queues

On 11/04/2023 12:00, Bas Nieuwenhuizen wrote: On Tue, Apr 11, 2023 at 11:48 AM Shashank Sharma wrote: On 11/04/2023 11:37, Christian König wrote: Am 10.04.23 um 16:26 schrieb Shashank Sharma: On 10/04/2023 16:04, Bas Nieuwenhuizen wrote: On Mon, Apr 10, 2023 at 4:01 PM Shashank Sharma

RE: [PATCH Review V2 2/2] drm/amdgpu: correct ras enabled flag

[AMD Official Use Only - General] Thanks, It's a typo, I have fixed it before be merged. Regards, Stanley > -Original Message- > From: Lazar, Lijo > Sent: Tuesday, April 11, 2023 6:08 PM > To: Yang, Stanley ; amd-gfx@lists.freedesktop.org; > Zhang, Hawking ; Zhou1, Tao > ; Chen, Guchun

RE: [PATCH Review V2 2/2] drm/amdgpu: correct ras enabled flag

[AMD Official Use Only - General] > if (adev->gmc.xmgi. This looks like a typo. Should be gmc.xgmi Thanks, Lijo -Original Message- From: amd-gfx On Behalf Of Stanley.Yang Sent: Tuesday, April 11, 2023 3:03 PM To: amd-gfx@lists.freedesktop.org; Zhang, Hawking ; Zhou1, Tao ; Chen,

Re: [PATCH v3 0/9] AMDGPU Usermode queues

On Tue, Apr 11, 2023 at 11:48 AM Shashank Sharma wrote: > > > On 11/04/2023 11:37, Christian König wrote: > > Am 10.04.23 um 16:26 schrieb Shashank Sharma: > >> > >> On 10/04/2023 16:04, Bas Nieuwenhuizen wrote: > >>> On Mon, Apr 10, 2023 at 4:01 PM Shashank Sharma > >>> wrote: > > On

Re: [PATCH v3 0/9] AMDGPU Usermode queues

On 11/04/2023 11:37, Christian König wrote: Am 10.04.23 um 16:26 schrieb Shashank Sharma: On 10/04/2023 16:04, Bas Nieuwenhuizen wrote: On Mon, Apr 10, 2023 at 4:01 PM Shashank Sharma wrote: On 10/04/2023 15:46, Bas Nieuwenhuizen wrote: On Mon, Apr 10, 2023 at 3:40 PM Sharma, Shashank

Re: [PATCH v3 0/9] AMDGPU Usermode queues

Am 10.04.23 um 16:26 schrieb Shashank Sharma: On 10/04/2023 16:04, Bas Nieuwenhuizen wrote: On Mon, Apr 10, 2023 at 4:01 PM Shashank Sharma wrote: On 10/04/2023 15:46, Bas Nieuwenhuizen wrote: On Mon, Apr 10, 2023 at 3:40 PM Sharma, Shashank wrote: [AMD Official Use Only - General]

RE: [PATCH Review V2 2/2] drm/amdgpu: correct ras enabled flag

[AMD Official Use Only - General] You might consider use ! adev->gmc.xmgi.num_physical_nodes, apart from that Series is Reviewed-by: Hawking Zhang Regards, Hawking -Original Message- From: Stanley.Yang Sent: Tuesday, April 11, 2023 17:33 To: amd-gfx@lists.freedesktop.org; Zhang,

[PATCH Review V2 2/2] drm/amdgpu: correct ras enabled flag

XGMI RAS should be according to the gmc xgmi physical nodes number, XGMI RAS should not be enabled if xgmi num_physical_nodes is zero. Change-Id: Idf3600b30584b10b528e7237d103d84d5097b7e0 Signed-off-by: Stanley.Yang --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 7 +++ 1 file changed, 7

[PATCH Review V2 1/2] drm/amdgpu: fix unexpected block id

Aldebaran supports VCN and JPEG RAS, it reports unexpected block id message during VCN and JPEG RAS initialization if VCN and JPEG block id not defined. Change-Id: Icceb43556eec802f11c2077c1c58a1e92c9df599 Signed-off-by: Stanley.Yang --- drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 4

Re: [PATCH v3 8/9] drm/amdgpu: map wptr BO into GART

Am 10.04.23 um 02:00 schrieb Bas Nieuwenhuizen: On Wed, Mar 29, 2023 at 6:05 PM Shashank Sharma wrote: From: Arvind Yadav To support oversubscription, MES expects WPTR BOs to be mapped to GART, before they are submitted to usermode queues. Cc: Alex Deucher Cc: Christian Koenig Cc:

Re: [PATCH v2 3/3] drm/amdgpu: Add support for querying the max ibs in a submission. (v2)

Am 11.04.23 um 11:06 schrieb Timur Kristóf: Bas Nieuwenhuizen ezt írta (időpont: 2023. ápr. 11., Ke 10:25): On Tue, Apr 11, 2023 at 10:10 AM Christian König wrote: > > Am 09.04.23 um 20:59 schrieb Bas Nieuwenhuizen: > > We need to introduce a new version of the info

Re: [PATCH] drm/sched: Check scheduler ready before calling timeout handling

Am 06.04.23 um 22:00 schrieb Luben Tuikov: From: Vitaly Prosyak During an IGT GPU reset test we see the following oops, [ +0.03] [ cut here ] [ +0.00] WARNING: CPU: 9 PID: 0 at kernel/workqueue.c:1656 __queue_delayed_work+0x6d/0xa0 [ +0.04] Modules

Re: [PATCH v2 3/3] drm/amdgpu: Add support for querying the max ibs in a submission. (v2)

On Tue, Apr 11, 2023 at 10:10 AM Christian König wrote: > > Am 09.04.23 um 20:59 schrieb Bas Nieuwenhuizen: > > We need to introduce a new version of the info struct because > > libdrm_amdgpu forgot any versioning info in amdgpu_query_hw_ip_info > > so the mesa<->libdrm_amdgpu interface can't

[PATCH] drm/amdgpu: use sdma_v6 single packet invalidation

From: Pierre-Eric Pelloux-Prayer This achieves the same result as the sequence used in emit_flush_gpu_tlb but the invalidation is now a single packet instead of the 3 packets required to implement reg_write_reg_wait. Signed-off-by: Pierre-Eric Pelloux-Prayer Reviewed-by: Christian König ---

Re: [PATCH v2 3/3] drm/amdgpu: Add support for querying the max ibs in a submission. (v2)

Am 09.04.23 um 20:59 schrieb Bas Nieuwenhuizen: We need to introduce a new version of the info struct because libdrm_amdgpu forgot any versioning info in amdgpu_query_hw_ip_info so the mesa<->libdrm_amdgpu interface can't handle increasing the size. This info would be used by radv to figure out

Re: [PATCH v2 2/3] drm/amdgpu: Simplify amdgpu_hw_ip_info.

Am 09.04.23 um 20:59 schrieb Bas Nieuwenhuizen: We have a list of all rings, so no sense writing the same loop N times. With how often this gets called and how small the ring list is the performance of this shouldn't matter. Note that some of the loops included some checking wrt harvesting.

[PATCH] drm/amdgpu: add gfx v11_0_3 fed irq handling for sriov

Add gfx v11_0_3 fed irq handling for sriov. Signed-off-by: YiPeng Chai Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c | 14 +++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0_3.c

RE: [PATCH Review 2/2] drm/amdgpu: correct ras enabled flag

[AMD Official Use Only - General] Thanks Hawking. I will update. Regards, Stanley From: Zhang, Hawking Sent: Tuesday, April 11, 2023 12:05 PM To: Yang, Stanley ; amd-gfx@lists.freedesktop.org; Zhou1, Tao Cc: Yang, Stanley Subject: Re: [PATCH Review 2/2] drm/amdgpu: correct ras enabled flag

RE: [PATCH Review 1/2] drm/admgpu: fix unexpected block id

[AMD Official Use Only - General] Hi Guchun, Thanks, will update. Regards, Stanley > -Original Message- > From: Chen, Guchun > Sent: Tuesday, April 11, 2023 12:48 PM > To: Yang, Stanley ; amd-gfx@lists.freedesktop.org; > Zhang, Hawking ; Zhou1, Tao > > Cc: Yang, Stanley > Subject:

RE: [PATCH] drm/amdgpu: use sdma_v6 single packet invalidation

[AMD Official Use Only - General] Reviewed-by: Monk Liu Hi guys, please chime in if with questions or concerns, this patch looks good to me. Thanks --- Monk Liu | Cloud GPU & Virtualization Software | AMD

[PATCH] drm/amdgpu: use sdma_v6 single packet invalidation

From: Pierre-Eric Pelloux-Prayer Send this patch on behalf of Pierre-Eric. This achieves the same result as the sequence used in emit_flush_gpu_tlb but the invalidation is now a single packet instead of the 3 packets required to implement reg_write_reg_wait. Signed-off-by: Pierre-Eric