[PATCH 3/6] drm/amdpgu: add common functions for BACO feature in PP

Change-Id: I088260c27bc2a84b4e0abd96aca9a981dd52f7b6 Signed-off-by: Jim Qu Reviewed-by: Alex Deucher Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/powerplay/hwmgr/Makefile | 2 +- .../gpu/drm/amd/powerplay/hwmgr/common_baco.c | 98 +++ .../gpu/drm/amd/powerplay/hwmgr/comm

[PATCH 6/6] drm/amdgpu: use BACO reset if platform support

It will fall back to use mode1 reset if platform does not support BACO feature. Change-Id: If145e0868c37d76091e0782a49b82c5a935d2367 Signed-off-by: Jim Qu Reviewed-by: Alex Deucher Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/amdgpu/soc15.c | 62 -- 1 file cha

[PATCH 5/6] drm/amdgpu: expose BACO interfaces to upper level from PP

Change-Id: Id9601a47afcd39107c94b6ae62577549e21a45ae Signed-off-by: Jim Qu Reviewed-by: Alex Deucher Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 54 +++ .../drm/amd/powerplay/hwmgr/vega10_hwmgr.c| 4 ++ 2 files changed, 58 insertions(+) d

[PATCH 4/6] drm/amdgpu: add BACO interfaces for vega10

V2: delay 20ms before BACO out. V3: rename function to vega10_baco_xxx Change-Id: Ibd2b78a723ba56a90fe78b052b27d0ab0e45f0e5 Signed-off-by: Jim Qu Reviewed-by: Alex Deucher Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/powerplay/hwmgr/Makefile | 2 +- .../gpu/drm/amd/powerplay/hwmgr/veg

[PATCH 0/6] Enable BACO function for VGf10

Bus Alive Chip Off Power mode(BACO) refers to the case in which the power consumption in the GPU is at its lowest level while keeping the PCIe config space alive. Jim Qu (6): drm/amdgpu: update nbio v6.1 register/master to support BACO drm/amdgpu: add BACO interfaces in pm and hwmgr function t

[PATCH 2/6] drm/amdgpu: add BACO interfaces in pm and hwmgr function table

Change-Id: I55e58b4627e6d5935dbe56657bef65f37b2a39b3 Signed-off-by: Jim Qu Reviewed-by: Alex Deucher Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/include/kgd_pp_interface.h | 3 +++ drivers/gpu/drm/amd/powerplay/inc/hwmgr.h | 8 2 files changed, 11 insertions(+) diff --git

[PATCH 1/6] drm/amdgpu: update nbio v6.1 register/master to support BACO

Change-Id: I119c30c8b70911be59d2e42501ad7aa7dffcfe61 Signed-off-by: Jim Qu Reviewed-by: Alex Deucher Reviewed-by: Hawking Zhang --- drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_offset.h | 2 ++ drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_6_1_sh_mask.h | 4 2 files changed, 6 inse

Re: After Vega 56/64 GPU hang I unable reboot system

On Thu, 10 Jan 2019 at 01:35, Grodzovsky, Andrey wrote: > > I think the 'verbose' flag causes it do dump so much output, maybe try > without it in ALL the commands above. > Are you are aware of any particular application during which run this happens > ? > Last logs related to situation when I

[PATCH] drm/amdgpu: Add missing power attribute to APU check

Add missing power_average to visible check for power attributesi for APUs. Was missed before. Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/am

Re: [PATCH] WIP: drm/amd/display: dc/irq: use dce_6_0_{d,sh_mask}.h

Hi, just not to keep you engaged on this, I've got the vblank irq handling working now. I had exactly to replicate in dce60_irq_service.c the behavior of commit b10d51f8 ("drm/amd/display: Add interrupt entries for VBLANK isr.") and behavior of b57de80a ("drm/amd/display: Register on VLBLANK ISR."

Re: [PATCH libdrm] amdgpu: add a faster BO list API

On Wed, Jan 9, 2019 at 1:41 PM Christian König < ckoenig.leichtzumer...@gmail.com> wrote: > Am 09.01.19 um 17:14 schrieb Marek Olšák: > > On Wed, Jan 9, 2019 at 8:09 AM Christian König < > ckoenig.leichtzumer...@gmail.com> wrote: > >> Am 09.01.19 um 13:36 schrieb Marek Olšák: >> >> >> >> On Wed, J

Re: After Vega 56/64 GPU hang I unable reboot system

Can you launch Poton from command line appending GALLIUM_DDEBUG=1000 before the command ? This should create MESA debug info in ~/ddebug_dumps/ Andrey On 01/09/2019 04:12 PM, Mikhail Gavrilov wrote: > On Thu, 10 Jan 2019 at 01:35, Grodzovsky, Andrey > wrote: >> I think the 'verbose' flag cause

[pull] amdgpu drm-fixes-5.0

Hi Dave, Daniel, Fixes for 5.0. Highlights: - Powerplay fixes - Virtual display pinning fixes - Golden register updates for vega - Pitch and gem size validation fixes - Fix for error case in sr-iov init - Disable page tables in system memory on RV due to issues with IOMMU reported on some platf

Re: After Vega 56/64 GPU hang I unable reboot system

On 01/09/2019 02:36 PM, Mikhail Gavrilov wrote: > On Mon, 7 Jan 2019 at 23:47, Grodzovsky, Andrey > wrote: >> I see 'no active waves' print meaning it's not shader hang. >> >> We can try and estimate around which commands the hang occurred - in >> addition to what you already print please also d

[bug report] drm/amd/dc: Add dc display driver (v2)

Hello Harry Wentland, This is a semi-automatic email about new static checker warnings. The patch 4562236b3bc0: "drm/amd/dc: Add dc display driver (v2)" from Sep 12, 2017, leads to the following Smatch complaint: drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc.c:754 construct() error:

Re: [PATCH] WIP: drm/amd/display: dc/irq: use dce_6_0_{d,sh_mask}.h

Ah-ha! (Meaning self-checking and trying to self-correct myself) I've seen that commit b10d51f8 ("drm/amd/display: Add interrupt entries for VBLANK isr.") required to be complemented by b57de80a ("drm/amd/display: Register on VLBLANK ISR.") which changed vblank irq control in dce110_register_irq_h

Re: [PATCH libdrm] amdgpu: add a faster BO list API

Am 09.01.19 um 17:14 schrieb Marek Olšák: On Wed, Jan 9, 2019 at 8:09 AM Christian König > wrote: Am 09.01.19 um 13:36 schrieb Marek Olšák: On Wed, Jan 9, 2019, 5:28 AM Christian König mailto:ckoenig.leichtzumer...@gmail.com> wrote:

Re: [PATCH libdrm] amdgpu: add a faster BO list API

On Wed, Jan 9, 2019 at 8:09 AM Christian König < ckoenig.leichtzumer...@gmail.com> wrote: > Am 09.01.19 um 13:36 schrieb Marek Olšák: > > > > On Wed, Jan 9, 2019, 5:28 AM Christian König < > ckoenig.leichtzumer...@gmail.com wrote: > >> Looks good, but I'm wondering what's the actual improvement? >

Re: [PATCH v5 1/2] drm/sched: Refactor ring mirror list handling.

On 01/09/2019 05:22 AM, Christian König wrote: > Am 07.01.19 um 20:47 schrieb Grodzovsky, Andrey: >> >> On 01/07/2019 09:13 AM, Christian König wrote: >>> Am 03.01.19 um 18:42 schrieb Grodzovsky, Andrey: On 01/03/2019 11:20 AM, Grodzovsky, Andrey wrote: > On 01/03/2019 03:54 AM, Koenig,

RE: [PATCH 1/2] drm/amdgpu: Add NBIO SMN headers v2

The series is reviewed by me too. Reviewed-by: Felix Kuehling From: amd-gfx On Behalf Of Deucher, Alexander Sent: Wednesday, January 09, 2019 10:06 AM To: Russell, Kent ; amd-gfx@lists.freedesktop.org Subject: Re: [PATCH 1/2] drm/amdgpu: Add NBIO SMN headers v2 Series is: Reviewed-by: Alex

Re: [PATCH 1/2] drm/amdgpu: Add NBIO SMN headers v2

Series is: Reviewed-by: Alex Deucher From: amd-gfx on behalf of Russell, Kent Sent: Wednesday, January 9, 2019 9:43:51 AM To: amd-gfx@lists.freedesktop.org Cc: Russell, Kent Subject: [PATCH 1/2] drm/amdgpu: Add NBIO SMN headers v2 We need these offsets for PC

[PATCH 2/2] drm/amdgpu: Add sysfs file for PCIe usage v4

Add a sysfs file that reports the number of bytes transmitted and received in the last second. This can be used to approximate the PCIe bandwidth usage over the last second. v2: Clarify use of mps as estimation of bandwidth v3: Don't make the file on APUs v4: Early exit for APUs in the read functi

[PATCH 1/2] drm/amdgpu: Add NBIO SMN headers v2

We need these offsets for PCIE perf counters, so include them as well as the the previously-used defines from the nbio_*.c files v2: Return NBIF definitions back to previous files Signed-off-by: Kent Russell --- drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c | 6 +-- drivers/gpu/drm/amd/am

Re: [PATCH xf86-video-ati 1/2] Only call drmmode_uevent_init if RandR is enabled

Series is: Reviewed-by: Alex Deucher From: amd-gfx on behalf of Michel Dänzer Sent: Wednesday, January 9, 2019 5:43:22 AM To: amd-gfx@lists.freedesktop.org Subject: [PATCH xf86-video-ati 1/2] Only call drmmode_uevent_init if RandR is enabled From: Michel Dän

[PATCH 1/3] drm/amdgpu: enable IH ring 1 and ring 2 v3

The entries are ignored for now, but it at least stops crashing the hardware when somebody tries to push something to the other IH rings. v2: limit ring size, add TODO comment v3: only program rings if they are actually allocated Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amd

[PATCH 2/3] drm/amdgpu: add support for processing IH ring 1 & 2

Previously we only added the ring buffer memory, now add the handling as well. Signed-off-by: Christian König Acked-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 33 + drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h | 4 ++- 2 files changed, 36 insertions(+), 1

[PATCH 3/3] drm/amdgpu: add support for self irq on Vega10 v2

This finally enables processing of ring 1 & 2. v2: fix copy&paste error Signed-off-by: Christian König Reviewed-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/vega10_ih.c | 80 -- 1 file changed, 74 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu

Re: [PATCH libdrm] amdgpu: add a faster BO list API

Am 09.01.19 um 13:36 schrieb Marek Olšák: On Wed, Jan 9, 2019, 5:28 AM Christian König wrote: Looks good, but I'm wondering what's the actual improvement? No malloc calls and 1 less for loop copying the bo list. Yeah, but didn't we want to ge

RE: [PATCH] drm/amdgpu: Add sysfs file for PCIe usage v3

> -Original Message- > From: Alex Deucher > Sent: Tuesday, January 08, 2019 11:26 AM > To: Kuehling, Felix > Cc: Russell, Kent ; amd-gfx@lists.freedesktop.org; > Deucher, Alexander > Subject: Re: [PATCH] drm/amdgpu: Add sysfs file for PCIe usage v3 > > On Tue, Jan 8, 2019 at 11:02 AM

Re: [PATCH libdrm] amdgpu: add a faster BO list API

On Wed, Jan 9, 2019, 5:28 AM Christian König < ckoenig.leichtzumer...@gmail.com wrote: > Looks good, but I'm wondering what's the actual improvement? > No malloc calls and 1 less for loop copying the bo list. Marek > Christian. > > Am 07.01.19 um 20:31 schrieb Marek Olšák: > > From: Marek Olšá

[PATCH xf86-video-ati 1/2] Only call drmmode_uevent_init if RandR is enabled

From: Michel Dänzer There's no point in listening for hotplug events if RandR is disabled, as there's no other mechanism for them to be propagated. We were already mostly ignoring them in that case. Inspired by https://gitlab.freedesktop.org/xorg/driver/xf86-video-intel/commit/1a489142c8e6a48283

[PATCH xf86-video-ati 2/2] Only call drmmode_validate_leases if RandR is enabled

From: Michel Dänzer It would crash if RandR is disabled, e.g. because Xinerama is enabled. Bugzilla: https://bugs.freedesktop.org/109230 Signed-off-by: Michel Dänzer --- src/drmmode_display.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/drmmode_display.c b/src/drmm

Re: [PATCH libdrm] amdgpu: add a faster BO list API

Looks good, but I'm wondering what's the actual improvement? Christian. Am 07.01.19 um 20:31 schrieb Marek Olšák: From: Marek Olšák --- amdgpu/amdgpu-symbol-check | 3 ++ amdgpu/amdgpu.h| 56 +- amdgpu/amdgpu_bo.c | 36 +

Re: [PATCH v5 1/2] drm/sched: Refactor ring mirror list handling.

Am 07.01.19 um 20:47 schrieb Grodzovsky, Andrey: On 01/07/2019 09:13 AM, Christian König wrote: Am 03.01.19 um 18:42 schrieb Grodzovsky, Andrey: On 01/03/2019 11:20 AM, Grodzovsky, Andrey wrote: On 01/03/2019 03:54 AM, Koenig, Christian wrote: Am 21.12.18 um 21:36 schrieb Grodzovsky, Andrey:

Re: [PATCH AUTOSEL 4.20 034/117] drm/amdgpu: Correct get_crtc_scanoutpos behavior when vpos >= vtotal

On 2019-01-08 8:25 p.m., Sasha Levin wrote: > From: Nicholas Kazlauskas > > [ Upstream commit 520f08df45fbe300ed650da786a74093d658b7e1 ] > > When variable refresh rate is active [...] Variable refresh rate (FreeSync) support is only landing in 5.0, therefore this fix isn't needed in older kerne