Re: [PATCH] drm/amdgpu: Update MMHUB power gating register settings

2018-01-11 Thread Yong Zhao
ails of what this does. I'm hoping Eric can also review this with more power-management experience. Regards,    Felix On 2018-01-10 03:10 PM, Yong Zhao wrote: The new register settings are needed to fix a tlb invalidation issue when MMHUB power gating is turned on for Raven

[PATCH] drm/amdgpu: Update MMHUB power gating register settings

2018-01-10 Thread Yong Zhao
The new register settings are needed to fix a tlb invalidation issue when MMHUB power gating is turned on for Raven. Change-Id: I846befbb2fcbddf40ca4ecbdc06da1cd442e3554 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.

[PATCH 2/2] drm/amdkfd: avoid calling execute_queues_cpsch() when destroying an unactive queue

2018-01-02 Thread Yong Zhao
Signed-off-by: Yong Zhao <yong.z...@amd.com> Reviewed-by: Oak Zeng <oak.z...@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 10 +- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/dri

[PATCH 1/2] drm/amdkfd: Fix return value 0 when execute_queues_cpsch actually fails

2018-01-02 Thread Yong Zhao
Signed-off-by: Yong Zhao <yong.z...@amd.com> Reviewed-by: Oak Zeng <oak.z...@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/dr

[PATCH] drm/amdgpu: Fix a bug that vm size is wrong on Raven

2017-12-14 Thread Yong Zhao
Change-Id: Id522c1cbadb8c069720f4e64a31cff42cd014733 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

Re: [PATCH] drm/amdgpu: Fix a bug that vm size is wrong on Raven

2017-12-14 Thread Yong Zhao
: NAK, that really circumvents the intention of the patch to adjust the number of levels based on the vm_size. Christian. Am 14.12.2017 um 03:25 schrieb Yong Zhao: Change-Id: Id522c1cbadb8c069720f4e64a31cff42cd014733 Signed-off-by: Yong Zhao <yong.z...@amd.com> ---   drivers/gpu/drm/amd/

[PATCH] drm/amdgpu: Fix a bug that vm size is wrong on Raven

2017-12-13 Thread Yong Zhao
Change-Id: Id522c1cbadb8c069720f4e64a31cff42cd014733 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

[PATCH] drm/amdkfd: Delete a useless parameter from create_queue function pointer

2017-11-24 Thread Yong Zhao
Signed-off-by: Yong Zhao <yong.z...@amd.com> Reviewed-by: Felix Kuehling <felix.kuehl...@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 13 +++-- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-- drivers/gpu/drm/amd/amdkfd/kfd_process_que

[PATCH] drm/amdkfd: Delete a useless parameter from create_queue function pointer

2017-11-24 Thread Yong Zhao
Change-Id: Ia5c74ad567c30e206ed804b204fdf8a0f8a75a19 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 14 -- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-- drivers/gpu/drm/amd/amdkfd/kfd_process_queue_man

[PATCH] drm/amdkfd: Delete a useless parameter from create_queue function pointer

2017-11-24 Thread Yong Zhao
Change-Id: Ia5c74ad567c30e206ed804b204fdf8a0f8a75a19 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 14 -- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 3 +-- drivers/gpu/drm/amd/amdkfd/kfd_process_queue_man

[PATCH] drm/amdgpu: Set the correct value for PDEs/PTEs of ATC memory on Raven

2017-10-06 Thread Yong Zhao
From: Yong Zhao <yong.z...@amd.com> Without the additional bits set in PDEs/PTEs, the ATC memory access would have failed on Raven. Change-Id: I28429ef6d39cdb01dc6f17fea4264ee22d7121d4 Signed-off-by: Yong Zhao <yong.z...@amd.com> Acked-by: Alex Deucher <alexander.deuc...@amd.co

Re: [PATCH] drm/amdgpu: Set the correct value for PDEs/PTEs of ATC memory

2017-10-05 Thread Yong Zhao
Hi Christian, Do you have a minute to review this change? Yong On 2017-09-27 02:46 PM, Alex Deucher wrote: On Tue, Sep 26, 2017 at 7:30 PM, Yong Zhao <yong.z...@amd.com> wrote: From: Yong Zhao <yong.z...@amd.com> Without the additional bits set in PDEs/PTEs, the ATC memory

[PATCH] drm/amdgpu: Set the correct value for PDEs/PTEs of ATC memory

2017-09-26 Thread Yong Zhao
From: Yong Zhao <yong.z...@amd.com> Without the additional bits set in PDEs/PTEs, the ATC memory access would have failed. Change-Id: I28429ef6d39cdb01dc6f17fea4264ee22d7121d4 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 18 ++

[PATCH 2/2] drm/amdgpu: Add copy_pte_num_dw member in amdgpu_vm_pte_funcs

2017-09-19 Thread Yong Zhao
Use it to replace the hard coded value in amdgpu_vm_bo_update_mapping(). Change-Id: I85d89d401b8dbcf01ca9c55c281e552db874fde5 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h| 4 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +- drivers/gpu/d

[PATCH 1/2] drm/amdgpu: Fix a bug in amdgpu_fill_buffer()

2017-09-19 Thread Yong Zhao
structure amdgpu_vm_pte_funcs. Change-Id: I37c588a57cb63f1a8251fb5ead2eff4b39e047c9 Signed-off-by: Yong Zhao <yong.z...@amd.com> Reviewed-by: Christian König <christian.koe...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 7 +++ drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8

[PATCH 1/2] drm/amdgpu: Correct bytes limit for SDMA 3.0 copy and fill

2017-09-18 Thread Yong Zhao
Change-Id: I10fc5efbc303056c5c5c4dc4f4dd2c3186595a91 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_

Re: [PATCH 1/2] drm/amdgpu: Add a parameter to amdgpu_bo_create()

2017-07-28 Thread Yong Zhao
Got it. On 2017-07-28 05:01 AM, Christian König wrote: Am 27.07.2017 um 21:48 schrieb Yong Zhao: The parameter init_value contains the value to which we initialized VRAM bo when AMDGPU_GEM_CREATE_VRAM_CLEARED flag is set. Change-Id: I9ef3b9dd3ca9b98cc25dd2eaff68fbe1129c3e3c Signed-off

[PATCH 2/2] drm/amdgpu: Support IOMMU on Raven

2017-07-26 Thread Yong Zhao
We achieved that by setting the PTEs to 2 (the SYSTEM bit is set) when the corresponding addresses are not occupied by gpu driver allocated buffers. Change-Id: I995c11c7a25bdaf7a16700d9e08a8fe287d49417 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_am

[PATCH 1/2] drm/amdgpu: Add support for filling a buffer with 64 bit value

2017-07-26 Thread Yong Zhao
That function will be used later to support setting a page table block with 64 bit value. Change-Id: Ib142ebd4163d6e23670a3f0ceed536d59133b942 Signed-off-by: Yong Zhao <yong.z...@amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 19 +-- drivers/gpu/drm/amd/

Changes for enabling ATS support from PTE

2017-07-25 Thread Yong Zhao
Hi there, Attached are two patches made to amdgpu in order to support ATS on Raven. Please review them. Regards, Yong >From 0657ddb14a16d1b809c419b51e805287fb6a9989 Mon Sep 17 00:00:00 2001 From: Yong Zhao <yong.z...@amd.com> Date: Thu, 20 Jul 2017 18:44:10 -0400 Subject: [PATCH

Re: [PATCH 06/12] drm/amdgpu: Correctly establish the suspend/resume hook for amdkfd

2017-07-06 Thread Yong Zhao
sense to stick to the previous design which kept the kfd suspend/resume inside your IP block suspend/resume. Regards, Yong On 2017-07-06 05:06 PM, Alex Deucher wrote: On Mon, Jul 3, 2017 at 5:11 PM, Felix Kuehling <felix.kuehl...@amd.com> wrote: From: Yong Zhao <yong.z...@amd.com

Re: [PATCH 06/12] drm/amdgpu: Correctly establish the suspend/resume hook for amdkfd

2017-07-06 Thread Yong Zhao
On 2017-07-06 05:44 PM, Alex Deucher wrote: On Thu, Jul 6, 2017 at 5:33 PM, Yong Zhao <yong.z...@amd.com> wrote: Hi Alex, As far as I know, we never tested suspend/resume on the setting you mentioned. Theoretically it should work. Are the kfd s/r entry points global or per GPU? If yo