[PATCH 2/6] drm/amdgpu: pin shared GWS, GDS and OA resources

2016-07-26 Thread Christian König
From: Christian König <christian.koe...@amd.com> They can't move anyway, but just to be clean here. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 21 + drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 21 +---

Re: [PATCH] drm/amdgpu: increase timeout of IB test

2016-07-26 Thread Christian König
um 09:28 schrieb zhoucm1: CQE has found timeout when they cherry-pick your timeout patch. I also found ib_test could be timeout after gpu reset. 1s maybe too long for a simple testing command, but I just think that doesn't matter to judge timeout. Regards, David On 2016年07月26日 15:24, Christian

Re: [PATCH 00/13] shadow page table support

2016-07-25 Thread Christian König
First of all patches #10 and #11 look like bug fixes to existing code to me. So we should fix those problems before working on anything else. Patch #10 is Reviewed-by: Christian König <christian.koe...@amd.com> Patch #11: list_for_each_entry(s_job, >ring_mirror_l

Re: [PATCH] drm/amdgpu: free handles after fini the context

2016-07-25 Thread Christian König
-by: Leo Liu <leo@amd.com> Reviewed-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 7 +++ 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu

Re: [PATCH 00/13] shadow page table support

2016-07-26 Thread Christian König
Am 26.07.2016 um 07:33 schrieb zhoucm1: On 2016年07月26日 10:40, zhoucm1 wrote: 1. We add an optional "shadow" flag so that when a BO in VRAM is allocated we also allocate a shadow BO in GART. 2. We have another "backup" flag that says on the next command submission the BO is backed up from

Re: [PATCH 00/10] GART table recovery

2016-08-02 Thread Christian König
Well you have been hardworking during my vacation :) Looks pretty good to me, but hope that I can get a closer look tomorrow. Is there any particular order the three sets must be applied? Regards, Christian. Am 02.08.2016 um 10:00 schrieb Chunming Zhou: gart table is stored in one bo which

Re: [PATCH 1/2] drm/ttm: add interface to export kernel_zone max memory size in ttm

2016-08-02 Thread Christian König
t. Reviewed-by: Alex Deucher <alexander.deuc...@amd.com> A bit commit message would be nice, e.g. something like "Add a function to get the maximum memory used by the kernel zone." With that fixed he patch is Reviewed-by: Christian König <christian.koe...@amd.com> as well. Reg

Re: [PATCH] drm/amdgpu/gfx8: remove stale function declaration

2016-08-03 Thread Christian König
Am 02.08.2016 um 03:58 schrieb zhoucm1: On 2016年08月02日 02:30, Alex Deucher wrote: This got leftover somehow when I cleaned this up. Signed-off-by: Alex Deucher <alexander.deuc...@amd.com> Reviewed-by: Chunming Zhou <david1.z...@amd.com> Reviewed-by: Christian König &l

Re: [PATCH] Add freesync ioctl interface

2016-08-03 Thread Christian König
Am 03.08.2016 um 03:04 schrieb Dave Airlie: On 2 August 2016 at 12:26, Hawking Zhang wrote: Change-Id: I38cb3a80e75a904cee875ae47bc0a39a3d471aca Signed-off-by: Hawking Zhang --- include/drm/amdgpu_drm.h | 15 +++ 1 file changed, 15

Re: [PATCH] drm/amdgpu: print more accurate error messages on IB submission failure

2016-08-03 Thread Christian König
ander.deuc...@amd.com> If you haven't already committed it the patch is Reviewed-by: Christian König <christian.koe...@amd.com> as well. Regards, Christian. --- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 17 + 1 file changed, 13 insertions(+), 4 deletions(-) diff --gi

Re: [PATCH 1/4] drm/amd/amdgpu: Cleanup register access in VCE v3

2016-08-11 Thread Christian König
Am 11.08.2016 um 16:32 schrieb Tom St Denis: Signed-off-by: Tom St Denis <tom.stde...@amd.com> Reviewed-by: Christian König <christian.koe...@amd.com> Regards, Christian. --- drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 145 ++ 1 file changed, 4

Re: [PATCH 1/6] drm/amd/amdgpu: fix indentation in vce3 CG

2016-08-03 Thread Christian König
Am 03.08.2016 um 17:51 schrieb Tom St Denis: Signed-off-by: Tom St Denis <tom.stde...@amd.com> This one is Reviewed-by: Christian König <christian.koe...@amd.com>. For the rest I'm not deep enough into the topic to judge. Regards, Christian. --- drivers/gpu/drm/amd/amdgpu/vce

Re: [PATCH] drm/amdgpu: Fix memory trashing if UVD ring test fails

2016-08-03 Thread Christian König
Am 03.08.2016 um 20:39 schrieb Jay Cornwall: fence_put was called on an uninitialized variable. Signed-off-by: Jay Cornwall <j...@jcornwall.me> Good catch, patch is Reviewed-by: Christian König <christian.koe...@amd.com> Regards, Christian. --- drivers/gpu/drm/amd/amdgpu/amdg

Re: [PATCH 00/13] shadow page table support

2016-08-04 Thread Christian König
Am 04.08.2016 um 08:05 schrieb zhoucm1: On 2016年08月03日 21:39, Christian König wrote: Doubling all the page table updates clearly doesn't sound like a good idea to me. Could you tell me why it isn't a good idea? I though the overhead is the least, and we don't need to sync between bo and its

Re: [PATCH 0/6] drm: Explicit target vblank seqno for page flips

2016-08-04 Thread Christian König
Nice, looking forward to this for quite a while now. I'm rather busy and not so deep into the display stuff anyway, so the whole set is Acked-by: Christian König <christian.koe...@amd.com>. Let me know if I should take a deeper look as well. Regards, Christian. Am 04.08.2016 um

Re: [PATCH 00/13] shadow page table support

2016-08-03 Thread Christian König
Patch #1 looks like a fix to me, please add my rb and push ASAP. You should separate such fixes from bugger sets, send out individually and maybe ping Alex to review and add them to his fixes branch. Patch #2: + amdgpu_ttm_placement_init(adev, , +

Re: [PATCH 00/11] add recovery entity

2016-08-03 Thread Christian König
Well that is a clear NAK to this whole approach. Submitting the recovery jobs to the scheduler is reentrant because the scheduler is the one who originally signaled us of a timeout. Why not submit the recovery jobs to the hardware ring directly? Regards, Christian. Am 28.07.2016 um 12:13

Re: [PATCH 3/4] drm/amd/amdgpu: VCE v2 register cleanup

2016-08-12 Thread Christian König
Dito, using WREG32_FIELD is clearly easier to read. If the additional register writes are really an issue we could adjust the macro to skip those if the value didn't changed. Regards, Christian. Am 12.08.2016 um 03:52 schrieb zhoucm1: Agree with Tom. On 2016年08月12日 00:09, Deucher,

Re: Adjusting memory speed according to display

2016-08-12 Thread Christian König
To output audio over HDMI you need to output a video signal as well. This creates additional pressure on the memory bandwith because the hardware now needs to handle two video signals instead of one. You need to connect your screen to the output of the amplifier to avoid this. Regards,

Re: [PATCH 00/18] shadow page table support V3

2016-08-12 Thread Christian König
Patch #1-#4 are Reviewed-by: Christian König <christian.koe...@amd.com>, please commit those so that we can consider them as done. Patch #5: +int amdgpu_bo_sync_between_bo_and_shadow(struct amdgpu_device *adev, +struct amdgpu_ring

[PATCH 5/6] drm/amdgpu: stop splitting PTE commands into smaller ones

2016-08-12 Thread Christian König
From: Christian König <christian.koe...@amd.com> It doesn't make much sense to create bigger commands first which we then need to split into smaller one again. Just make sure the commands we create aren't to big in the first place. Signed-off-by: Christian König <christian.koe..

[PATCH 3/6] drm/amdgpu: cleanup the write_pte implementations

2016-08-12 Thread Christian König
From: Christian König <christian.koe...@amd.com> We don't need the gart mapping handling here any more. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h| 10 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 20 ++--

[PATCH 4/6] drm/amdgpu: remove AMDGPU_VM_NO_FLUSH define

2016-08-12 Thread Christian König
From: Christian König <christian.koe...@amd.com> Not used any more. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/dr

[PATCH 1/6] drm/amdgpu: write PTEs directly into the IB.

2016-08-12 Thread Christian König
From: Christian König <christian.koe...@amd.com> Write the PTEs at the end of the IB instead of directly into the SDMA commands. This can save quite some CPU cycles building the entries. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdg

Re: 答复: 答复: [PATCH] drm/amd/amdgpu: S3 resume fail

2016-08-13 Thread Christian König
Michel is correct your patch will probably break resume in some cases. Please enable lockdep debugging during your kernel compile and take a look what is deadlocking here and why instead of trying to band aid over the real problem. Regards, Christian. Am 13.08.2016 um 08:56 schrieb Qu, Jim:

Re: Reverted another change to fix buffer move hangs (was Re: [PATCH] drm/ttm: partial revert "cleanup ttm_tt_(unbind|destroy)" v2)

2016-08-13 Thread Christian König
Am 13.08.2016 um 01:22 schrieb Felix Kuehling: [CC Kent FYI] On 16-08-11 04:31 PM, Deucher, Alexander wrote: -Original Message- From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Felix Kuehling Sent: Thursday, August 11, 2016 3:52 PM To: Michel Dänzer; Christian

Re: [PATCH drm/amdgpu] Fixing copy-paste errors and removing unneeded newlines

2016-08-10 Thread Christian König
Am 10.08.2016 um 09:02 schrieb Alexandre Demers: Signed-off-by: Alexandre Demers <alexandre.f.dem...@gmail.com> Reviewed-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/dce_v8_0.c | 8 +++- 1 file changed, 3 insertions(+), 5 deletions(-)

Re: [PATCH 06/19] drm/amdgpu: implement vm recovery function from shadow

2016-08-11 Thread Christian König
Am 05.08.2016 um 11:38 schrieb Chunming Zhou: Change-Id: I46783043eecbe9fc9c2ce9230be1085aca3731bd Signed-off-by: Chunming Zhou --- drivers/gpu/drm/amd/amdgpu/amdgpu.h| 4 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 48 ++ 2 files

Re: radeon VS amdgpu: _afmt_init() behavior if kzalloc fails

2016-08-12 Thread Christian König
Hi guys, yeah, agree totally. When we fail to allocate anything during module or device initialization we should cleanup properly and abort loading the module. On the other hand the only time I actually run into such a problem was while constantly loading and unloading the radeon module to

Re: [PATCH 1/6] drm/amdgpu: write PTEs directly into the IB.

2016-08-12 Thread Christian König
Am 12.08.2016 um 17:46 schrieb Alex Deucher: On Fri, Aug 12, 2016 at 9:52 AM, Christian König <deathsim...@vodafone.de> wrote: From: Christian König <christian.koe...@amd.com> Write the PTEs at the end of the IB instead of directly into the SDMA commands. This can save quite som

[PATCH] drm/amdgpu: fix coding style in amdgpu_object.c

2016-08-12 Thread Christian König
From: Christian König <christian.koe...@amd.com> Just a few 80 chars problems. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 86 +- 1 file changed, 49 insertions(+), 37 deletions(-) diff --g

Re: [PATCH] Add freesync ioctl interface

2016-08-10 Thread Christian König
Am 10.08.2016 um 05:19 schrieb Michel Dänzer: On 09/08/16 07:44 PM, Christian König wrote: Am 09.08.2016 um 12:03 schrieb Michel Dänzer: On 09/08/16 06:31 PM, Christian König wrote: Am 09.08.2016 um 10:27 schrieb Michel Dänzer: On 09/08/16 05:12 PM, Christian König wrote: [SNIP] This would

[PATCH 3/7] drm/amdgpu: add begin/end_use ring callbacks

2016-07-21 Thread Christian König
From: Christian König <christian.koe...@amd.com> For manual UVD/VCE power and clock gating. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 10 ++ 2 files changed, 1

[PATCH 6/7] drm/amdgpu: move UVD IB test into common code v2

2016-07-21 Thread Christian König
From: Christian König <christian.koe...@amd.com> Since we now raise the clocks from begin_use() we don't need a separate function for each hw generation any more. v2: remove unintentional lowering of the UVD clocks, fix typos for CIK hw. Signed-off-by: Christian König <christian.koe..

[PATCH 4/7] drm/amdgpu: use begin/end_use for UVD power/clock gating

2016-07-21 Thread Christian König
From: Christian König <christian.koe...@amd.com> This fixes turning power and clock on when it is actually needed. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 15 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h | 2

Re: [PATCH 00/13] shadow page table support

2016-08-05 Thread Christian König
Am 05.08.2016 um 04:43 schrieb zhoucm1: On 2016年08月04日 17:52, Christian König wrote: Am 04.08.2016 um 08:05 schrieb zhoucm1: On 2016年08月03日 21:39, Christian König wrote: Doubling all the page table updates clearly doesn't sound like a good idea to me. Could you tell me why it isn't

Re: [PATCH 00/13] shadow page table support

2016-08-05 Thread Christian König
Am 05.08.2016 um 11:12 schrieb zhoucm1: On 2016年08月05日 16:56, Christian König wrote: Am 05.08.2016 um 04:43 schrieb zhoucm1: On 2016年08月04日 17:52, Christian König wrote: Am 04.08.2016 um 08:05 schrieb zhoucm1: On 2016年08月03日 21:39, Christian König wrote: Doubling all the page table

Re: [PATCH] drm/ttm: Wait for a BO to become idle before unbinding it from GTT

2016-08-05 Thread Christian König
d-off-by: Michel Dänzer <michel.daen...@amd.com> Ah, yes of course. Good catch, patch is Reviewed-by: Christian König <christian.koe...@amd.com>. Regards, Christian. --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 ++-- drivers/gpu/drm/nouveau/nouveau_bo.c| 4 +

Re: [PATCH 0/7] Minor DP aux transaction fixes

2016-08-06 Thread Christian König
is Reviewed-by: Christian König <christian.koe...@amd.com>. Regards, Christian. Lyude (7): drm/dp_helper: Print first error received on failure in drm_dp_dpcd_access() drm/radeon: Don't print error on aux transaction timeouts drm/radeon: Don't retry 7 times in radeon_dp_dpcd()

Re: [PATCH] Add freesync ioctl interface

2016-08-09 Thread Christian König
Am 09.08.2016 um 12:03 schrieb Michel Dänzer: On 09/08/16 06:31 PM, Christian König wrote: Am 09.08.2016 um 10:27 schrieb Michel Dänzer: On 09/08/16 05:12 PM, Christian König wrote: Am 09.08.2016 um 04:44 schrieb Michel Dänzer: I was basically thinking out loud that doing this via different

Re: [PATCH] Add freesync ioctl interface

2016-08-09 Thread Christian König
Am 09.08.2016 um 04:44 schrieb Michel Dänzer: On 08/08/16 06:55 PM, Christian König wrote: [SNIP] Who said that games need to be able to enable/disable it in the kernel side? The assumption is that some games (and maybe other apps, e.g. compositors) won't work correctly with variable refresh

Re: [PATCH] Add freesync ioctl interface

2016-08-09 Thread Christian König
Am 09.08.2016 um 10:27 schrieb Michel Dänzer: On 09/08/16 05:12 PM, Christian König wrote: Am 09.08.2016 um 04:44 schrieb Michel Dänzer: I was basically thinking out loud that doing this via different modes might be quite natural, *if* games allowed choosing a specific mode. But unfortunately

[PATCH 3/6] drm/amdgpu: rename amdgpu_vm_update_params

2016-08-09 Thread Christian König
From: Christian König <christian.koe...@amd.com> Well those are actually page table entry parameters. This also makes the variable names used a bit shorter. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdg

[PATCH 5/6] drm/amdgpu: flip frag_ptes and update_pts

2016-08-09 Thread Christian König
From: Christian König <christian.koe...@amd.com> We can add the fragment params before we split the update for the page tables. That should save a few CPU cycles for larger updates. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgp

[PATCH 6/6] drm/amdgpu: use more than 64KB fragment size if possible

2016-08-09 Thread Christian König
From: Christian König <christian.koe...@amd.com> We align to 64KB, but when userspace aligns even more we can easily use more. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 1 file changed, 8 insertions(+),

[PATCH 4/6] drm/amdgpu: add adev to the pte_update_params

2016-08-09 Thread Christian König
From: Christian König <christian.koe...@amd.com> No need to carry that forward as a separate parameter. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 65 +++--- 1 file changed, 29 insertions(+),

Re: [PATCH 3/3] drm/amd/amdgpu: Simplify bitfield operations in gfx v8

2016-08-09 Thread Christian König
Am 09.08.2016 um 16:27 schrieb Tom St Denis: This patch introduces a new macro WREG32_FIELD which is used to write to a register with a new value in a field. It's designed to replace the pattern: tmp = RREG32(mmFoo); tmp &= ~REG__FIELD_MASK; tmp |= new_value << REG__FIELD__SHIFT; WREG32(mmFoo,

Re: [PATCH 6/6] drm/amdgpu: use more than 64KB fragment size if possible

2016-08-09 Thread Christian König
Am 09.08.2016 um 17:49 schrieb Jay Cornwall: On 2016-08-09 07:52, Christian König wrote: From: Christian König <christian.koe...@amd.com> We align to 64KB, but when userspace aligns even more we can easily use more. Signed-off-by: Christian König <christian.koe...@amd.com> ---

Re: [PATCH] Add freesync ioctl interface

2016-08-08 Thread Christian König
Am 08.08.2016 um 09:43 schrieb Michel Dänzer: On 04.08.2016 17:22, Christian König wrote: Am 04.08.2016 um 08:41 schrieb Michel Dänzer: On 03.08.2016 10:04, Dave Airlie wrote: On 2 August 2016 at 12:26, Hawking Zhang <hawking.zh...@amd.com> wrote: @@ -706,4 +708,17 @@

Re: [PATCH 00/19] shadow page table support V2

2016-08-08 Thread Christian König
ation object first and the crash when it wants to free the shadow. Additional to that do we really need the placement here? That looks quite odd. Patch #2, #3 is Reviewed-by: Christian König <christian.koe...@amd.com>. Patch #4: +enum amdgpu_shadow_flag { + AMDGPU_SHADOW_FLA

[PATCH] drm/ttm: partial revert "cleanup ttm_tt_(unbind|destroy)" v2

2016-07-22 Thread Christian König
From: Christian König <christian.koe...@amd.com> We still need to unbind explicitely during a move. This partial reverts commit ff20caa0bcbfef9f7686f8d1868a3b990921afd6. v2: remove unnecessary check and unused variable Signed-off-by: Christian König <christian.koe...@amd.com> ---

Re: [PATCH 00/10] GART table recovery

2016-08-03 Thread Christian König
Well patch #10 is incorrect. The SA BO will be set to NULL by amdgpu_sa_bo_free(), so it can't be freed twice and so you can't reference the fence twice. Additional to that the whole approach here of restoring the GART from the backup using the SDMA won't work either. For the SDMA to work you

Re: [PATCH] drm/amd/amdgpu: Add more config data for debugfs

2016-08-15 Thread Christian König
;tom.stde...@amd.com> Acked-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 ++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

Re: fix possible bad kref_put in amdgpu_uvd_ring_end_use

2016-08-16 Thread Christian König
NAK, we already merged a patch to avoid the fence_put() in general when the ring test fails. Regards, Christian. Am 16.08.2016 um 08:33 schrieb Matthew Macy: Clang identified this when I was merging up 4.8-rc1/rc2. I usually just disable warnings as they pop up as I treat the drivers as

[PATCH 1/5] drm/radeon: fix radeon_move_blit on 32bit systems

2016-08-17 Thread Christian König
From: Christian König <christian.koe...@amd.com> This bug seems to be present for a very long time. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/radeon/radeon_ttm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gp

[PATCH 2/5] drm/amdgpu: fix amdgpu_move_blit on 32bit systems

2016-08-17 Thread Christian König
From: Christian König <christian.koe...@amd.com> This bug seems to be present for a very long time. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers

[PATCH 4/5] drm/amdgpu: fix sdma_v2_4_ring_test_ib

2016-08-17 Thread Christian König
From: Christian König <christian.koe...@amd.com> Typo in checking the return code. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sd

[PATCH 3/5] drm/amdgpu: fix lru size grouping

2016-08-17 Thread Christian König
From: Christian König <christian.koe...@amd.com> Adding a BO can make it the insertion point for larger sizes as well. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8 +

[PATCH 5/5] drm/amdgpu: fix timeout value check in amd_sched_job_recovery

2016-08-17 Thread Christian König
From: Christian König <christian.koe...@amd.com> Could be that we don't actually have a timeout set. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dri

Re: Kernel deadlock in amdgpu_job_submit

2016-08-17 Thread Christian König
[11160.387924] [] amd_sched_entity_push_job+0x77/0x110 [amdgpu] [11160.387927] [] ? wake_atomic_t_function+0x60/0x60 [11160.387943] [] amdgpu_job_submit+0x84/0xc0 [amdgpu] [11160.387953] [] amdgpu_copy_buffer+0x14a/0x1c0 [amdgpu] [11160.387963] [] amdgpu_move_blit+0x9d/0x140 [amdgpu] It's

Re: [PATCH 0/8] shadow page table support V5 ---> shadow bo support

2016-08-17 Thread Christian König
error_free; Throw a DRM_ERROR("") in there. Tom *From:* amd-gfx <amd-gfx-boun...@lists.freedesktop.org> on behalf of Christian König <deathsim...@vodafone.de> *Sent:* Wednesday, August 17, 2016 1

Re: [PATCH 0/8] shadow page table support V5 ---> shadow bo support

2016-08-17 Thread Christian König
Patch #1: Could be that we need to add another module parameter to control this, but I think for now that should be sufficient. Patch is Reviewed-by: Christian König <christian.koe...@amd.com> Patch #2: + if (direct_submit) { + r = amdgpu_ib_schedule(ring, job-&g

Re: [PATCH 1/6] drm/amdgpu: add support for BO_VAs without BO

2017-02-02 Thread Christian König
Am 30.01.2017 um 15:43 schrieb Nicolai Hähnle: On 30.01.2017 13:57, Christian König wrote: From: Christian König <christian.koe...@amd.com> For PRT support we need mappings which aren't backed by any memory. Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers

[PATCH 1/6] drm/amdgpu: add support for BO_VAs without BO v2

2017-02-02 Thread Christian König
From: Christian König <christian.koe...@amd.com> For PRT support we need mappings which aren't backed by any memory. v2: fix parameter checking Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 20 ++-- 1 file

[PATCH 2/6] drm/amdgpu: add basic PRT support

2017-02-02 Thread Christian König
From: Christian König <christian.koe...@amd.com> Future hardware generations can handle PRT flags on a per page basis, but current hardware can only turn it on globally. Add the basic handling for both, a global callback to enable/disable triggered by setting a per mapping flag. Sign

[PATCH 5/6] drm/amdgpu: implement PRT for GFX7 v2

2017-02-02 Thread Christian König
From: Christian König <christian.koe...@amd.com> Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: set correct register Signed-off-by: Junwei Zhang <jerry.zh...@amd.com> Signed-off-by: Christian König <christian

[PATCH 6/6] drm/amdgpu: implement PRT for GFX8 v2

2017-02-02 Thread Christian König
From: Christian König <christian.koe...@amd.com> Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: set correct register Signed-off-by: Junwei Zhang <jerry.zh...@amd.com> Signed-off-by: Christian König <christian

[PATCH 4/6] drm/amdgpu: implement PRT for GFX6 v2

2017-02-02 Thread Christian König
From: Christian König <christian.koe...@amd.com> Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: write to the correct register, adjust bits to that hw generation Signed-off-by: Christian König <christian.koe...@amd.com> ---

PRT support for amdgpu v2

2017-02-02 Thread Christian König
Hi guys, a bunch of bug fixes, but still completely untested since I'm on sick leave. Bas maybe you could give it a try with radv. Regards, Christian. ___ amd-gfx mailing list amd-gfx@lists.freedesktop.org

[PATCH 3/6] drm/amdgpu: IOCTL interface for PRT support v3

2017-02-02 Thread Christian König
apping is made. v2: disable PRT support delayed and on all error paths v3: PRT and other permissions are mutal exclusive, PRT mappings don't need a BO. Signed-off-by: Junwei Zhang <jerry.zh...@amd.com> Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/a

Re: PRT support for amdgpu

2017-02-02 Thread Christian König
Am 02.02.2017 um 10:33 schrieb Nicolai Hähnle: On 02.02.2017 10:29, Bas Nieuwenhuizen wrote: On Thu, Feb 2, 2017, at 10:18, Nicolai Hähnle wrote: On 02.02.2017 02:49, Dave Airlie wrote: I think we would require a fully open source user for this sort of thing, there are way to many corner

Re: [PATCH] drm/radeon: Fix vram_size/visible values in DRM_RADEON_GEM_INFO ioctl

2017-01-31 Thread Christian König
e. Reviewed-by: Christian König <christian.koe...@amd.com> for this one as well the mesa patch. Regards, Christian. --- drivers/gpu/drm/radeon/radeon_drv.c | 3 ++- drivers/gpu/drm/radeon/radeon_gem.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/r

Re: PRT support for amdgpu

2017-01-31 Thread Christian König
Am 31.01.2017 um 17:09 schrieb Alex Deucher: On Mon, Jan 30, 2017 at 7:57 AM, Christian König <deathsim...@vodafone.de> wrote: Hi Dave and Bas, Hi Dave and Bas, the following set of patches is a proposal for adding support for partial resident textures (PRT) to the amdgpu kernel

Re: PRT support for amdgpu

2017-01-31 Thread Christian König
Am 31.01.2017 um 14:06 schrieb Bas Nieuwenhuizen: On Mon, Jan 30, 2017, at 13:57, Christian König wrote: Hi Dave and Bas, Hi Dave and Bas, the following set of patches is a proposal for adding support for partial resident textures (PRT) to the amdgpu kernel module. The basic idea behind PRT

Re: [PATCH 3/6] drm/amdgpu: IOCTL interface for PRT support v3

2017-02-05 Thread Christian König
mplete. In what case would it be useful to map/unmap earlier than next CS?) - Bas On Thu, Feb 2, 2017, at 11:25, Christian König wrote: From: Junwei Zhang <jerry.zh...@amd.com> Till GFX8 we can only enable PRT support globally, but with the next hardware generation we can do this on a pe

Re: [PATCH] drm/amdgpu/virt: skip VM fault handler for VF (v2)

2017-02-07 Thread Christian König
Yeah, the src_data is unfortunately not completed (you simply can't have all the bits of a 40bit address+flags in a 32bit dw). But it's the best we can do, so the patch is Reviewed-by: Christian König <christian.koe...@amd.com> as well. Regards, Christian. Am 07.02.2017 um 08:03 s

Re: [PATCH 1/2] drm/amdgpu: don't clean the framebuffer for VF

2017-02-07 Thread Christian König
I think you mean loading KMS multiple times by “reuse”. No, as far as I know the fb emulation can be initialized multiple times without driver reload. I can’t see a case that fb_probe is invoked out of loading KMS, is there? I'm not so deeply into this, but I knew that you can certainly

Re: [PATCH 07/21] drm/amdgpu:fix gart table vram pin

2017-02-07 Thread Christian König
ddr && amdgpu_sriov_vf(adev)) { + /* it's a resume call, gart already pin */ + return 0; + } BR Monk -Original Message- From: Christian König [mailto:deathsim...@vodafone.de] Sent: Monday, February 06, 2017 10:31 PM To: Liu, Monk <monk@amd

Re: 答复: 答复: [PATCH] drm/amdgpu:fix amdgpu_sa_bo_new error

2017-02-08 Thread Christian König
is really adding to much delay at bootup. *发件人:* Michel Dänzer <mic...@daenzer.net> *发送时间:* 2017年2月8日 23:52:02 *收件人:* Christian König; Liu, Monk *抄送:* amd-gfx@lists.freedesktop.org *主题:* Re: 答复: [PATCH] drm/amdgpu:fix

[PATCH 1/6] drm/amdgpu: add support for BO_VAs without BO v2

2017-02-08 Thread Christian König
From: Christian König <christian.koe...@amd.com> For PRT support we need mappings which aren't backed by any memory. v2: fix parameter checking Signed-off-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 20 ++-- 1 file

[PATCH 4/6] drm/amdgpu: implement PRT for GFX6 v2

2017-02-08 Thread Christian König
From: Christian König <christian.koe...@amd.com> Enable/disable the handling globally for now and print a warning when we enable it for the first time. v2: write to the correct register, adjust bits to that hw generation v3: fix compilation, add the missing register bit definitions Sign

[PATCH 2/6] drm/amdgpu: add basic PRT support

2017-02-08 Thread Christian König
From: Christian König <christian.koe...@amd.com> Future hardware generations can handle PRT flags on a per page basis, but current hardware can only turn it on globally. Add the basic handling for both, a global callback to enable/disable triggered by setting a per mapping flag. Sign

PRT support for amdgpu v3

2017-02-08 Thread Christian König
Hi guys, ok I finally found time to write an unit test for this and hammered out the last few bugs. Seems to work fine on my Tonga now. Please note that this set is based on "fix race in GEM VA map IOCTL v2", without that patch you will run into a NULL pointer dereference during PRT mapping.

[PATCH 3/6] drm/amdgpu: IOCTL interface for PRT support v4

2017-02-08 Thread Christian König
apping is made. v2: disable PRT support delayed and on all error paths v3: PRT and other permissions are mutal exclusive, PRT mappings don't need a BO. v4: update PRT mappings durign CS as well, make va_flags 64bit Signed-off-by: Junwei Zhang <jerry.zh...@amd.com> Signed-off-by: Chr

Re: 答复: [PATCH] drm/amdgpu:fix amdgpu_sa_bo_new error

2017-02-08 Thread Christian König
? *发件人:* Michel Dänzer <mic...@daenzer.net> *发送时间:* 2017年2月8日 23:19:23 *收件人:* Christian König; Liu, Monk *抄送:* amd-gfx@lists.freedesktop.org *主题:* Re: [PATCH] drm/amdgpu:fix amdgpu_sa_bo_new error On 08/02/17 07:52 PM, Christian König wrote: > Am 08.02.2017 um 10:41 schrieb

Re: 答复: 答复: SPAM //答复: [PATCH 09/20] drm/amdgpu:implement SRIOV gpu_reset

2017-02-08 Thread Christian König
. suspend the VM with glxgears running do you mean turn VM into s3 mode ? if so we not get that step, the S3 suspend/resume function is not supported by SRIOV vf case. *发件人:* Christian König <deathsim...@vodafone.de&

Re: [PATCH] drm/amdgpu: shut up #warning for compile testing

2017-02-02 Thread Christian König
Am 02.02.2017 um 07:09 schrieb Michel Dänzer: [SNIP] OTOH the people running the kernel aren't always the same people building it, so the downside is that this would potentially delay getting X86_PAT enabled. And exactly for this reason I would rather like to keep the warning. Regards,

Re: [PATCH 07/21] drm/amdgpu:fix gart table vram pin

2017-02-06 Thread Christian König
, Christian. Am 06.02.2017 um 15:25 schrieb Liu, Monk: E looks like I missed the part of S3 function But if this is from a GPU reset , we also shouldn't continue run this function otherwise GPU reset will fail (SRIOV reset test) BR Monk -Original Message- From: Christian König

Re: SPAM //答复: [PATCH 09/20] drm/amdgpu:implement SRIOV gpu_reset

2017-02-08 Thread Christian König
+ /* now we are okay to resume SMC/CP/SDMA */ + amdgpu_resume_late(adev); As I wrote in the other thread as well calling amdgpu_resume() without proper suspend will just mess up a whole bunch of internal structures. So a clear NAK on that approach. If you don't need the hw stop

Re: [PATCH] drm/amdgpu:fix amdgpu_sa_bo_new error

2017-02-08 Thread Christian König
o amdgpu_ib_ring_tests(). With that changed the patch is Reviewed-by: Christian König <christian.koe...@amd.com>. Regards, Christian. r = amdgpu_ib_ring_tests(adev); if (r) DRM_ERROR("ib ring test failed (%d).\n", r); _

Re: [PATCH] drm/amdgpu: clear framebuffer with GPU

2017-02-08 Thread Christian König
m push this one is Reviewed-by: Christian König <christian.koe...@amd.com> as well. Regards, Christian. Signed-off-by: Pixel Ding <pixel.d...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/

Re: [PATCH libdrm 2/2] amdgpu: add amdgpu_bo_va_op_raw

2017-02-08 Thread Christian König
Am 08.02.2017 um 13:55 schrieb Nicolai Hähnle: On 08.02.2017 13:44, Nicolai Hähnle wrote: On 08.02.2017 13:39, Christian König wrote: Am 08.02.2017 um 13:34 schrieb Nicolai Hähnle: From: Nicolai Hähnle <nicolai.haeh...@amd.com> This variant allows the caller full control over flags an

Re: [PATCH libdrm 2/2] amdgpu: add amdgpu_bo_va_op_raw

2017-02-08 Thread Christian König
Am 08.02.2017 um 13:34 schrieb Nicolai Hähnle: From: Nicolai Hähnle <nicolai.haeh...@amd.com> This variant allows the caller full control over flags and size, and allows passing a NULL bo (for PRT support). Cc: Christian König <christian.koe...@amd.com> Cc: Bas Nieu

Re: [PATCH 07/21] drm/amdgpu:fix gart table vram pin

2017-02-06 Thread Christian König
A bug NAK on this! amdgpu_gart_table_vram_unpin() must be called during suspend. Otherwise the GART table can be corrupted and we run into a whole bunch of problems. We could add a "BUG_ON(adev->gart.table_addr != NULL);" here to double check that, but just ignoring that something went

Re: [PATCH 01/21] drm/amdgpu:fix typo

2017-02-06 Thread Christian König
Am 04.02.2017 um 11:21 schrieb Monk Liu: Change-Id: I68729b1d32d5e300b8f03a923d2065d51dbe6f7a Signed-off-by: Monk Liu <monk@amd.com> Reviewed-by: Christian König <christian.koe...@amd.com> for this one. --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++-- 1 fil

Re: [PATCH 03/21] drm/amdgpu:fix scheduler hw reset

2017-02-06 Thread Christian König
Am 06.02.2017 um 04:18 schrieb Zhou, David(ChunMing): I'm curious what problem this patch fix? Any crash? My impression list_for will check if the list is empty, am I wrong? Yeah, I agree as well. list_for won't do anything if the list is empty. So this patch doesn't has any effect as far as

Re: [PATCH 2/2] drm/amdgpu/virt: schedule work to handle vm fault for VF

2017-02-06 Thread Christian König
Hi Pixel, yeah agree with David here, but even busy waiting for the KIQ register read is not really an option in the interrupt handler. Additional to that when we have a VM fault we usually see a mass storm of them. So allocating and scheduling a work item for each fault like you do here

Re: [PATCH 4/6] drm/amdgpu: implement PRT for GFX6 v2

2017-02-06 Thread Christian König
Software Development _ -Original Message- From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf Of Nicolai H?hnle Sent: Friday, February 03, 2017 22:37 To: Christian König; amd-gfx@lists.freedesktop.org Cc: b...@basnieuwenhuizen.nl Subject

Re: [PATCH 05/21] drm/amdgpu:BUG if gpu_reste and asic_reset from VF

2017-02-06 Thread Christian König
Am 04.02.2017 um 11:34 schrieb Monk Liu: for SRIOV vf, Guest couldn't really access PCI registers so gpu_reset() and asic_reset should be avoided. for suspend it could run for SRIOV because cg/pg routine already modified for SRIOV vf case, besides we should remove the req/rel gpu access around

Re: [PATCH 02/13] drm/amdgpu: doorbell registers need only be set once

2017-02-06 Thread Christian König
Am 04.02.2017 um 05:51 schrieb Andres Rodriguez: The CP_MEC_DOORBELL_RANGE_* and CP_PQ_STATUS.DOORBELL_ENABLE registers are not HQD specific. They only need to be set once if at least 1 pipe requested doorbell support. Signed-off-by: Andres Rodriguez ---

  1   2   3   4   5   6   7   8   9   10   >