RE: [PATCH] drm/amdgpu: Increase timout on emulator to tenfold instead of twice

[AMD Official Use Only - Internal Distribution Only] Reviewed-by: Hawking Zhang Regards, Hawking -Original Message- From: amd-gfx On Behalf Of Yong Zhao Sent: Wednesday, February 26, 2020 09:01 To: amd-gfx@lists.freedesktop.org Cc: Zhao, Yong Subject: [PATCH] drm/amdgpu: Increase

[PATCH] drm/amdgpu/sriov: Use kiq to copy the gpu clock

For vega10 sriov, the register is blocked, use copy data command to fix the issue. Signed-off-by: Emily Deng --- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 68 +-- 1 file changed, 58 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

RE: [PATCH] drm/amdgpu: Fix check for DPM when returning max clock

Reviewed-by: Evan Quan -Original Message- From: amd-gfx On Behalf Of Kent Russell Sent: Wednesday, February 26, 2020 4:20 AM To: amd-gfx@lists.freedesktop.org Cc: Russell, Kent Subject: [PATCH] drm/amdgpu: Fix check for DPM when returning max clock pp_funcs may not exist, while dpm

[PATCH] drm/amdgpu: Write blocked CP registers using RLC on VF

This change programs CP_ME_CNTL and RLC_CSIB_* through RLC Signed-off-by: Rohit Khaire --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 8 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index

[PATCH] drm/amdgpu: Increase timout on emulator to tenfold instead of twice

Since emulators are slower, sometime some operations like flushing tlb through FM need more than twice the regular timout of 100ms, so increase the timeout to 1s on emulators. Change-Id: Idf1ff571dd2fe69d3a236d916262ad65f86c44e8 Signed-off-by: Yong Zhao ---

Re: [PATCH 1/2] drm/amdgpu/powerplay: Refactor SMU message handling for safety

Hey Alex, The reason I didn't transition the other code is that I have no hardware to test with. I'll go ahead and do it, but someone with the hardware should at least ensure it boots properly (vega20, and something on smu_v12_0). With that, I'm good with doing it, I just don't want to risk

Re: [PATCH] drm/amdgpu: fix the gfx hang while use per-ib secure flag

On 2020-02-25 8:57 a.m., Huang Rui wrote: > Since 6643ba1 frame control packets are only issued in presence of secure > IB(s). > This causes hangs on some hardware (eg: Raven1). This patch restores the > unconditionnal frame control packets issuing, that's to keep the per-IB logic > regarding the

Re: [PATCH] drm/amdgpu: fix the gfx hang while use per-ib secure flag

Thanks for fixing this Ray. I think we can simplify the logic introduced in this patch. Regards, Luben On 2020-02-25 8:57 a.m., Huang Rui wrote: > Since 6643ba1 frame control packets are only issued in presence of secure > IB(s). > This causes hangs on some hardware (eg: Raven1). This patch

Re: [PATCH] drm/amdgpu: Fix check for DPM when returning max clock

On Tue, Feb 25, 2020 at 3:20 PM Kent Russell wrote: > > pp_funcs may not exist, while dpm may be enabled. This change ensures > that KFD topology will report the same as pp_dpm_sclk, as the conditions > for reporting them will be the same. > > Otherwise, we may see the issue where KFD reports

[PATCH 2/2] drm/amdgpu/display: Fix Pollock Variant Detection

From: Aly-Tawfik Problem Description: Currently we are checking internal fused rev id with pci rev id. However, fused internal rev id is the same on all raven2 parts (in which Dali and Pollock were based on too), thus Pollock detection fails Fix: use the pci rev to preform the detection for

[PATCH 1/2] drm/amdgpu/display: fix pci revision id fetching

From: Aly-Tawfik Use the pci revision id rather than the asic silicon revision id. Signed-off-by: Aly-Tawfik Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git

[PATCH] drm/amdgpu: Fix check for DPM when returning max clock

pp_funcs may not exist, while dpm may be enabled. This change ensures that KFD topology will report the same as pp_dpm_sclk, as the conditions for reporting them will be the same. Otherwise, we may see the issue where KFD reports "100MHz" in topology as the max speed, while DPM is working

Re: [PATCH 2/2] drm/amdgpu/smu: Add message sending lock

On Wed, Feb 19, 2020 at 2:19 PM Matt Coffin wrote: > > This adds a message lock to the smu_send_smc_msg* implementations to > protect against concurrent access to the mmu registers used to > communicate with the SMU Missing your signed-off-by. Also you need to move the mutex init and

Re: [PATCH 1/2] drm/amdgpu/powerplay: Refactor SMU message handling for safety

On Wed, Feb 19, 2020 at 2:19 PM Matt Coffin wrote: > > Move the responsibility for reading argument registers into the > smu_send_smc_msg* implementations, so that adding a message-sending lock > to protect the SMU registers will result in the lock still being held > when the argument is read. >

[PATCH 2/2] drm/amdgpu/display: don't call drm_dp_mst_connector_late_register (v2)

Nothing else calls it. Not sure it's necessary. v2: remove unused port variable. Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git

[PATCH 1/2] drm/amdgpu/display: move the setting of the aux dev

We need to move this into late init to avoid it being NULL once we switch the init order. Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git

Re: [PATCH] drm/ttm: fix leaking fences via ttm_buffer_object_transfer

Am 25.02.20 um 20:11 schrieb Alex Deucher: On Tue, Feb 25, 2020 at 2:09 PM Christian König wrote: Am 25.02.20 um 19:56 schrieb Alex Deucher: From: Ahzo Set the drm_device to NULL, so that the newly created buffer object doesn't appear to use the embedded gem object. This is necessary,

Re: [PATCH] drm/ttm: fix leaking fences via ttm_buffer_object_transfer

On Tue, Feb 25, 2020 at 2:09 PM Christian König wrote: > > Am 25.02.20 um 19:56 schrieb Alex Deucher: > > From: Ahzo > > > > Set the drm_device to NULL, so that the newly created buffer object > > doesn't appear to use the embedded gem object. > > > > This is necessary, because otherwise no

Re: [PATCH] drm/ttm: fix leaking fences via ttm_buffer_object_transfer

Am 25.02.20 um 19:56 schrieb Alex Deucher: From: Ahzo Set the drm_device to NULL, so that the newly created buffer object doesn't appear to use the embedded gem object. This is necessary, because otherwise no corresponding dma_resv_fini for the dma_resv_init is called, resulting in a memory

RE: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

[AMD Official Use Only - Internal Distribution Only] Hi Alex: The patch set is verified on Ubuntu, and I'll try it out on Chrome as well. Thanks a lot! Regards, Jerry -Original Message- From: Alex Deucher Sent: February 25, 2020 1:42 PM To: Zuo, Jerry Cc: Liu, Zhan ;

[PATCH] drm/ttm: fix leaking fences via ttm_buffer_object_transfer

From: Ahzo Set the drm_device to NULL, so that the newly created buffer object doesn't appear to use the embedded gem object. This is necessary, because otherwise no corresponding dma_resv_fini for the dma_resv_init is called, resulting in a memory leak. The dma_resv_fini in

Re: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

On Tue, Feb 25, 2020 at 1:32 PM Alex Deucher wrote: > > On Tue, Feb 25, 2020 at 1:30 PM Zuo, Jerry wrote: > > > > [AMD Official Use Only - Internal Distribution Only] > > > > Hi Alex: > > > > It happened when a MST monitor is attached, either in driver load or > > hotplug later. > > I

Re: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

On Tue, Feb 25, 2020 at 1:30 PM Zuo, Jerry wrote: > > [AMD Official Use Only - Internal Distribution Only] > > Hi Alex: > > It happened when a MST monitor is attached, either in driver load or > hotplug later. I think I found the issue. I'll send a patch shortly. Alex > > Regards, >

Re: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

On Tue, Feb 25, 2020 at 1:20 PM Liu, Zhan wrote: > > > > -Original Message- > > From: Liu, Zhan > > Sent: 2020/February/25, Tuesday 10:10 AM > > To: Alex Deucher ; Wentland, Harry > > > > Cc: amd-gfx list ; Maling list - DRI > > developers ; Deucher, Alexander > > ; Broadworth, Mark > >

RE: [PATCH] SWDEV-220585 - Navi12 L1 policy GC regs WAR #1

Thanks Alex! From: Deucher, Alexander Sent: February 25, 2020 1:16 PM To: Khaire, Rohit ; amd-gfx@lists.freedesktop.org Subject: Re: [PATCH] SWDEV-220585 - Navi12 L1 policy GC regs WAR #1 [AMD Public Use] Please fix up the patch title. E.g., drm/amdgpu: Don't write GCVM_L2_CNTL* regs on

RE: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

> -Original Message- > From: Liu, Zhan > Sent: 2020/February/25, Tuesday 10:10 AM > To: Alex Deucher ; Wentland, Harry > > Cc: amd-gfx list ; Maling list - DRI > developers ; Deucher, Alexander > ; Broadworth, Mark > > Subject: RE: [PATCH 13/15] drm/amdgpu/display: split dp connector >

Re: [PATCH] SWDEV-220585 - Navi12 L1 policy GC regs WAR #1

[AMD Public Use] Please fix up the patch title. E.g., drm/amdgpu: Don't write GCVM_L2_CNTL* regs on navi12 VF With that fixed, patch is: Reviewed-by: Alex deuc...@amd.com> From: amd-gfx on behalf of Rohit Khaire Sent: Friday, February 21, 2020 3:24 PM To:

Re: [PATCH 6/6] drm/amdkfd: Delete unnecessary unmap queue package submissions

[AMD Official Use Only - Internal Distribution Only] Thanks! I will update the commit message before pushing. It should be the way how SDMA queue count were used to unmap SDMA engines according to the previous understanding was wrong. Regards, Yong From:

Re: [PATCH 6/6] drm/amdkfd: Delete unnecessary unmap queue package submissions

As I understand it, the SDMA queue counting wasn't incorrect. The main change here is that you no longer send separate unmap packets for SDMA queues, and that makes SDMA queue counting unnecessary. That said, this patch series is a nice cleanup and improvement. The series is Reviewed-by:

Re: [PATCH] drm/amdgpu: add VM update fences back to the root PD v2

On 2020-02-19 10:02, Christian König wrote: Add update fences to the root PD while mapping BOs. Otherwise PDs freed during the mapping won't wait for updates to finish and can cause corruptions. v2: rebased on drm-misc-next Signed-off-by: Christian König Fixes: 90b69cdc5f159 drm/amdgpu: stop

Re: [PATCH] drm/amdgpu: log TA versions on init

Hi Hawking, The goal here was to know about the TA versions from just the dmesg only, its helpful as we don't have to ask the user to query data again as dmesg is the first thing that is usually shared for issues. For now I will add it to the debugfs. Bhawan On 2020-02-25 1:29 a.m., Zhang,

Re: [PATCH 2/3] drm/radeon: Inline drm_get_pci_dev

On Sat, Feb 22, 2020 at 12:54 PM Daniel Vetter wrote: > > It's the last user, and more importantly, it's the last non-legacy > user of anything in drm_pci.c. > > The only tricky bit is the agp initialization. But a close look shows > that radeon does not use the drm_agp midlayer (the main use of

Re: [PATCH -next] drm/amd/powerplay: Use bitwise instead of arithmetic operator for flags

On Sun, Feb 23, 2020 at 10:21 PM Quan, Evan wrote: > > Thanks. Reviewed-by: Evan Quan > Applied. Thanks! Alex > -Original Message- > From: Chen Zhou > Sent: Friday, February 21, 2020 8:22 PM > To: Quan, Evan ; Deucher, Alexander > ; Koenig, Christian ; > Zhou, David(ChunMing) ;

Re: [PATCH] drm/amd/amdgpu: Add gfxoff debugfs entry

On Mon, Feb 24, 2020 at 9:41 AM Tom St Denis wrote: > > > On 2020-02-21 1:59 p.m., Alex Deucher wrote: > > On Fri, Feb 21, 2020 at 1:45 PM Tom St Denis wrote: > >> Write a 32-bit value of zero to disable GFXOFF and write a 32-bit > >> value of non-zero to enable GFXOFF. > >> > >> Signed-off-by:

RE: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

> -Original Message- > From: Alex Deucher > Sent: 2020/February/25, Tuesday 9:07 AM > To: Wentland, Harry > Cc: amd-gfx list ; Maling list - DRI > developers ; Deucher, Alexander > ; Broadworth, Mark > ; Liu, Zhan > Subject: Re: [PATCH 13/15] drm/amdgpu/display: split dp connector >

Re: [PATCH] radeon, amdgpu: allow for symbolic errno output when reporting drm_edid_to_sad errors

Please send a proper patch using git format-patch. Thanks! Alex On Thu, Feb 20, 2020 at 9:04 PM Darren Salt wrote: > > This fixes some kernel log text when CONFIG_SYMBOLIC_ERRNAMES=Y. > > Signed-off-by: Darren Salt > ___ > amd-gfx mailing list >

Re: [PATCH -next] drm/amd/display: remove set but not used variable 'mc_vm_apt_default'

On Fri, Feb 21, 2020 at 10:33 AM YueHaibing wrote: > > drivers/gpu/drm/amd/amdgpu/../display/dc/dcn21/dcn21_hubp.c: > In function hubp21_set_vm_system_aperture_settings: > drivers/gpu/drm/amd/amdgpu/../display/dc/dcn21/dcn21_hubp.c:343:23: > warning: variable mc_vm_apt_default set but not used

Re: [PATCH] drm/amdgpu: stop disable the scheduler during HW fini

On 2/25/20 2:16 PM, Nirmoy wrote: Acked-by: Nirmoy Das Please change that to Tested-by: Nirmoy Das ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH 2/2] drm/amdgpu: add DFCstate control pptable func for arct

This is the callback function that is going to be invoked when amdgpu_dpm_set_df_cstate is called to toggle DFCstate Signed-off-by: Hawking Zhang --- drivers/gpu/drm/amd/powerplay/arcturus_ppt.c | 23 1 file changed, 23 insertions(+) diff --git

[PATCH 1/2] drm/amdgpu: update arcturus ppsmc header to 54.15.0

two new smc messages added for arcturus with pmfw 54.15.0 Signed-off-by: Hawking Zhang --- drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h | 6 +- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h

RE: [PATCH] drm/amdgpu: fix the gfx hang while use per-ib secure flag

[AMD Official Use Only - Internal Distribution Only] Reviewed: Aaron Liu -Original Message- From: Huang, Ray Sent: Tuesday, February 25, 2020 9:58 PM To: amd-gfx@lists.freedesktop.org Cc: Deucher, Alexander ; Koenig, Christian ; Liu, Aaron ; Tuikov, Luben ; Pelloux-prayer,

Re: [PATCH] drm/amdgpu: fix the gfx hang while use per-ib secure flag

On Tue, Feb 25, 2020 at 8:58 AM Huang Rui wrote: > > Since 6643ba1 frame control packets are only issued in presence of secure > IB(s). > This causes hangs on some hardware (eg: Raven1). This patch restores the > unconditionnal frame control packets issuing, that's to keep the per-IB logic >

Re: [PATCH] drm/amdgpu: fix the gfx hang while use per-ib secure flag

Hi Ray, I confirm that this fixes the hang I had when running libdrm's amdgpu_test. Thanks! Tested-by: Pierre-Eric Pelloux-Prayer On 25/02/2020 14:57, Huang Rui wrote: > Since 6643ba1 frame control packets are only issued in presence of secure > IB(s). > This causes hangs on some hardware

Re: [PATCH 13/15] drm/amdgpu/display: split dp connector registration (v3)

On Mon, Feb 24, 2020 at 4:09 PM Harry Wentland wrote: > > On 2020-02-07 4:17 p.m., Alex Deucher wrote: > > Split into init and register functions to avoid a segfault > > in some configs when the load/unload callbacks are removed. > > > > Looks like MST is completely broken with this change with a

[PATCH] drm/amdgpu: fix the gfx hang while use per-ib secure flag

Since 6643ba1 frame control packets are only issued in presence of secure IB(s). This causes hangs on some hardware (eg: Raven1). This patch restores the unconditionnal frame control packets issuing, that's to keep the per-IB logic regarding the secure flag. Fixes: 6643ba1 drm/amdgpu: Move to a

Re: [PATCH] drm/amdgpu: use amdgpu_ring_test_helper when possible

Am 25.02.20 um 14:42 schrieb Nirmoy Das: amdgpu_ring_test_helper already handles ring->sched.ready correctly Signed-off-by: Nirmoy Das Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 9 ++---

Re: [PATCH 6/6] drm/amdkfd: Delete unnecessary unmap queue package submissions

[AMD Public Use] Series is: Acked-by: Alex Deucher From: amd-gfx on behalf of Yong Zhao Sent: Monday, February 24, 2020 5:18 PM To: amd-gfx@lists.freedesktop.org Cc: Zhao, Yong Subject: [PATCH 6/6] drm/amdkfd: Delete unnecessary unmap queue package

[PATCH] drm/amdgpu: use amdgpu_ring_test_helper when possible

amdgpu_ring_test_helper already handles ring->sched.ready correctly Signed-off-by: Nirmoy Das --- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 2 +- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 9 ++--- drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 6 ++ 3 files changed, 5 insertions(+), 12

Re: [PATCH] drm/amdgpu: stop disable the scheduler during HW fini

Hi Dennis, Can you please test this patch on vega20 for SWDEV-223117 Regards, Nirmoy On 2/25/20 2:07 PM, Christian König wrote: When we stop the HW for example for GPU reset we should not stop the front-end scheduler. Otherwise we run into intermediate failures during command submission.

Re: [PATCH] drm/amdgpu: stop disable the scheduler during HW fini

Hi Christian, I tested with amdgpu_test which does a GPU reset as well because of deadlock_tests. Reset was fine I could run amdgpu_test multiple times. dmesg: Feb 25 14:32:20 brihaspati kernel: [drm:gfx_v9_0_priv_reg_irq [amdgpu]] *ERROR* Illegal register access in command stream Feb 25

Re: [PATCH] drm/amdgpu: stop disable the scheduler during HW fini

Am 25.02.20 um 14:16 schrieb Nirmoy: Acked-by: Nirmoy Das Could you test it as well? I only did a quick round of smoke tests, but somebody should probably run a gpu reset test as well. Thanks in advance, Christian. On 2/25/20 2:07 PM, Christian König wrote: When we stop the HW for

Re: [PATCH] drm/amdgpu: add VM update fences back to the root PD v2

Reviewed-by: xinhui pan > 2020年2月25日 20:45，Christian König 写道： > > Am 19.02.20 um 16:02 schrieb Christian König: >> Add update fences to the root PD while mapping BOs. >> >> Otherwise PDs freed during the mapping won't wait for >> updates to finish and can cause corruptions. >> >> v2:

Re: [PATCH] drm/amdgpu: stop disable the scheduler during HW fini

Acked-by: Nirmoy Das On 2/25/20 2:07 PM, Christian König wrote: When we stop the HW for example for GPU reset we should not stop the front-end scheduler. Otherwise we run into intermediate failures during command submission. The scheduler should only be stopped in very few cases: 1. We can't

[PATCH] drm/amdgpu: stop disable the scheduler during HW fini

When we stop the HW for example for GPU reset we should not stop the front-end scheduler. Otherwise we run into intermediate failures during command submission. The scheduler should only be stopped in very few cases: 1. We can't get the hardware working in ring or IB test after a GPU reset. 2.

Re: [PATCH] drm/amdgpu: add VM update fences back to the root PD v2

Am 19.02.20 um 16:02 schrieb Christian König: Add update fences to the root PD while mapping BOs. Otherwise PDs freed during the mapping won't wait for updates to finish and can cause corruptions. v2: rebased on drm-misc-next Signed-off-by: Christian König Fixes: 90b69cdc5f159 drm/amdgpu:

Re: [PATCH] drm/amdgpu: cleanup amdgpu_ring_fini

Am 25.02.20 um 12:19 schrieb Nirmoy Das: cleanup amdgpu_ring_fini to check the prerequisites before changing ring->sched.ready Signed-off-by: Nirmoy Das Reviewed-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

[PATCH] drm/amdgpu: cleanup amdgpu_ring_fini

cleanup amdgpu_ring_fini to check the prerequisites before changing ring->sched.ready Signed-off-by: Nirmoy Das --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

Re: [PATCH] drm/amdgpu: do not modify ring before doing ring validation

On 2/25/20 12:08 PM, Christian König wrote: Am 25.02.20 um 12:03 schrieb Nirmoy: On 2/25/20 11:52 AM, Christian König wrote: Am 25.02.20 um 11:39 schrieb Nirmoy Das: changing ring->sched.ready should be done only if the ring is initialized I don't think that this makes much difference.

Re: [PATCH] drm/amdgpu: do not modify ring before doing ring validation

Am 25.02.20 um 12:03 schrieb Nirmoy: On 2/25/20 11:52 AM, Christian König wrote: Am 25.02.20 um 11:39 schrieb Nirmoy Das: changing ring->sched.ready should be done only if the ring is initialized I don't think that this makes much difference. When the rings are freed the hardware and

RE: [PATCH] drm/amdgpu: Add Arcturus D342 page retire support

[AMD Public Use] case CHIP_ARCTURUS: + return __get_eeprom_i2c_addr_arct(adev, i2c_addr); + break; This 'break' is not needed. Please remove it. Regards, Guchun From: amd-gfx On Behalf Of Zhang, Hawking Sent: Tuesday, February 25, 2020 6:42

Re: [PATCH] drm/amdgpu: do not modify ring before doing ring validation

On 2/25/20 11:52 AM, Christian König wrote: Am 25.02.20 um 11:39 schrieb Nirmoy Das: changing ring->sched.ready should be done only if the ring is initialized I don't think that this makes much difference. When the rings are freed the hardware and software stack needs to be disabled quite

RE: [PATCH] drm/amdgpu: Add a chunk ID for spm trace

[AMD Official Use Only - Internal Distribution Only] Yes, it’s SPM_VMID. There is VMFault with 0 if KMD doesn’t update SPM_VMID with current job since the default value of SPM_VMID is 0. Thanks Jacob From: Koenig, Christian Sent: Tuesday, February 25, 2020 6:56

Re: [PATCH] drm/amdgpu: Add a chunk ID for spm trace

Hi Jacob, well first of all we can't rely on the correct behavior of Vulkan. In the kernel you have to always assume that userspace is not doing the right thing. If there is any other UMD applications, such as OCL, and OCL driver doesn’t update the SPM_VMID before enable SPM, there is

Re: [PATCH] drm/amdgpu: do not modify ring before doing ring validation

Am 25.02.20 um 11:39 schrieb Nirmoy Das: changing ring->sched.ready should be done only if the ring is initialized I don't think that this makes much difference. When the rings are freed the hardware and software stack needs to be disabled quite some time before. Christian.

RE: [PATCH] drm/amdgpu: Add Arcturus D342 page retire support

[AMD Official Use Only - Internal Distribution Only] Please fix your coding style in the follow if/else code segment by removing the unnecessary {}. Other than that, the patch is Reviewed-by: Hawking Zhang + if (strnstr(atom_ctx->vbios_version, + "D342", +

[PATCH] drm/amdgpu: do not modify ring before doing ring validation

changing ring->sched.ready should be done only if the ring is initialized Signed-off-by: Nirmoy Das --- drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c

[PATCH] drm/amdgpu: Add Arcturus D342 page retire support

Add support for detecting Arcturus SKU to resolve the correct bad page retirement EEPROM I2C address. Thank you, John Clements 0001-drm-amdgpu-Add-Arcturus-D342-page-retire-support.patch Description: 0001-drm-amdgpu-Add-Arcturus-D342-page-retire-support.patch