Use words insteads of acronym for better understanding.
Signed-off-by: Yong Zhao
---
include/uapi/drm/amdgpu_drm.h | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index d65f9b4ba05c..0072ddb59747 100644
This is convenient for multiple teams to obtain the information. Also,
add device info by using dev_info().
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b
This is convenient for multiple teams to obtain the information.
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
Delete two printings which are not very useful, and change one from
pr_info() to pr_debug().
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 2 --
2 files changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/gpu
Add more detail while turning off the printing by default, because it
is very useful.
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 2 +-
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd
People are inclined to think of the previous pr_warn message as an
error, so use pre_debug instead.
Change-Id: I3ac565a2bd3b8d57345812104c872183898d237f
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_events.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a
, causing unnecessary confusion.
Replace all occurrences of ALLOC_MEM_FLAGS_* with
KFD_IOC_ALLOC_MEM_FLAGS_* to solve the problem.
Change-Id: Iced6ed3698167296c97b14e7e4569883859d619c
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 6 ++--
.../gpu/drm/amd/amdgpu
Add "CP" to AMDGPU_GEM_CREATE_MQD_GFX9 to indicate it is only for CP MQD.
Change-Id: Ie69cd3ba477e4bac161ea5b20ec2919a35f3528e
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 6 +++---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c| 7 +--
includ
, causing unnecessary confusion.
Replace all occurrences of ALLOC_MEM_FLAGS_* by
KFD_IOC_ALLOC_MEM_FLAGS_* to solve the problem.
Change-Id: Iced6ed3698167296c97b14e7e4569883859d619c
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 9 +++--
.../gpu/drm/amd/amdgpu
Because too many things are involved in this workaround, we need more
comments to avoid pitfalls.
Change-Id: I5d7917296dd5f5edb45921118cf8e7d778d40de1
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c| 5 -
.../gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c| 18
Because too many things are involved in this workaround, we need more
comments to avoid pitfalls.
Change-Id: I5d7917296dd5f5edb45921118cf8e7d778d40de1
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 5 -
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 17
Because two many things are involved in this workaround, we need more
comments to avoid pitfalls.
Change-Id: I5d7917296dd5f5edb45921118cf8e7d778d40de1
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 5 -
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 16
Given we can query all the asic specific information from amdgpu_gfx_config,
we can make get_tile_config() generic.
Change-Id: I1080fec4d50c51bc84bb49b0145f8fec50081fce
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 3 ++
.../drm/amd/amdgpu
The two members will be used by KFD later.
Change-Id: I36a605e359b242f2fe546fb67f8e402c48a62342
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h | 2 ++
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 5 +
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 5 +
3 files changed, 12
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
---
drivers/gpu/drm/amd/amdgpu
Those printings are duplicated or useless.
Change-Id: I88fbe8f5748bbd0a20bcf1f6ca67b9dde99733fe
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 --
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 4 +---
2 files changed, 1 insertion(+), 5
The name is easier to understand the code.
Change-Id: I9064dab1d022e02780023131f940fff578a06b72
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 38 +--
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 2 +-
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c
: I84fd2f7e63d6b7f664580b425a78d3e995ce9abc
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 79 ++-
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 2 -
.../amd/amdkfd/kfd_process_queue_manager.c| 16 ++--
3 files changed, 29 insertions(+), 68 deletions(-)
diff --git a
The queues represented in queue_bitmap are only CP queues.
Change-Id: I7e6a75de39718d7c4da608166b85b9377d06d1b3
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 4 ++--
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c| 12 ++--
.../gpu/drm/amd
The previous code of calculating active CP queues is problematic if
some SDMA queues are inactive. Fix that by counting CP queues directly.
Change-Id: I5ffaa75a95cbebc984558199ba2f3db6909c52a9
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 47
When the queue creation failed, some resources were not freed. Fix it.
Change-Id: Ia24b6ad31528dceddfd4d1c58bb1d22c35d3eabf
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd
Please disregard the patch 5 and 6, as I have a new version for them.
Yong
On 2020-02-05 6:39 p.m., Yong Zhao wrote:
One minor fix added.
Yong
On 2020-02-05 6:28 p.m., Yong Zhao wrote:
The sdma_queue_count was only used for inferring whether we should
unmap SDMA queues under HWS mode. In
Those printings are duplicated or useless.
Change-Id: I88fbe8f5748bbd0a20bcf1f6ca67b9dde99733fe
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 --
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 4 +---
2 files changed, 1 insertion(+), 5
mapping, we can just send only necessary engines during unmapping.
Change-Id: I84fd2f7e63d6b7f664580b425a78d3e995ce9abc
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 131 +-
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 4 +-
.../amd/amdkfd/kf
MAX_SDMA_ENGINE_NUM will be used in more than one place.
Change-Id: I99c84086ee62612b373c547a9d29bc4a69e7c72e
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h| 2 +-
drivers/gpu/drm/amd/include/kgd_kfd_interface.h | 1 +
2 files changed, 2 insertions(+), 1 deletion
One minor fix added.
Yong
On 2020-02-05 6:28 p.m., Yong Zhao wrote:
The sdma_queue_count was only used for inferring whether we should
unmap SDMA queues under HWS mode. In contrast, We mapped active queues
rather than all in map_queues_cpsch(). In order to match the map and unmap
for SDMA
Those printings are duplicated or useless.
Change-Id: I88fbe8f5748bbd0a20bcf1f6ca67b9dde99733fe
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 --
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 4 +---
2 files changed, 1 insertion(+), 5
When the queue creation is failed, some resources were not freed. Fix it.
Change-Id: Ia24b6ad31528dceddfd4d1c58bb1d22c35d3eabf
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd
The queues represented in queue_bitmap are only CP queues.
Change-Id: I7e6a75de39718d7c4da608166b85b9377d06d1b3
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 4 ++--
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c| 12 ++--
.../gpu/drm/amd
sdma_queue_count to active_sdma_queue_count to reflect the new
usage.
Change-Id: I9f1c3305dad044a3c779ec0730fcf7554050de8b
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 54 ---
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 5 +-
.../amd/amdkfd
The previous code of calculating active CP queues is problematic if
some SDMA queues are inactive. Fix that by counting CP queues directly.
Change-Id: I5ffaa75a95cbebc984558199ba2f3db6909c52a9
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 45
The name is easier to understand the code.
Change-Id: I9064dab1d022e02780023131f940fff578a06b72
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 38 +--
.../drm/amd/amdkfd/kfd_device_queue_manager.h | 2 +-
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c
True. It is a bug too. I am looking into it.
Yong
On 2020-01-30 5:51 p.m., Felix Kuehling wrote:
On 2020-01-30 17:29, Yong Zhao wrote:
The sdma_queue_count increment should be done before
execute_queues_cpsch(), which calls pm_calc_rlib_size() where
sdma_queue_count is used to calculate
more than the
actual compute queue number, because the queue_count has been
incremented while sdma_queue_count has not. This patch fixes that.
Change-Id: I20353e657efd505353d0dd9f7eb2fab5085e7202
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 10 ++
1
Reviewed-by: Yong Zhao
On 2020-01-17 8:37 p.m., Felix Kuehling wrote:
Use a more meaningful variable name for the invalidation request
that is distinct from the tmp variable that gets overwritten when
acquiring the invalidation semaphore.
Fixes: 00f607f38d82 ("drm/amdgpu: invalidate
The warning was introduced in
commit b4267f2e687ff5e0402ab915c9a4d47f9a4eb73e
Author: Yong Zhao
Date: Fri Dec 13 11:31:48 2019 -0500
drm/amdkfd: Improve function get_sdma_rlc_reg_offset()
Change-Id: I87da4f1ad8a190327a4a71f0ff78812cb942d6e0
Signed-off-by: Yong Zhao
---
drivers/gpu/drm
SW scheduler is previously called non HW scheduler, or non HWS. This
message is useful when triaging issues from dmesg.
Change-Id: I625518c88c043df5f60409d1ca520e7fc032251f
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 1 +
1 file changed, 1 insertion
The SOC15_REG_OFFSET() macro needs to dereference adev->reg_offset[IP]
pointer, which is NULL when there are fewer than 8 sdma engines. Avoid
that by not initializing the array regardless.
Change-Id: Iabae9bff7546b344720905d5d4a5cfc066a79d25
Signed-off-by: Yong Zhao
---
.../drm/amd/amd
One comment inline.
On 2020-01-02 4:11 p.m., Alex Sierra wrote:
[Why]
Avoid reclaim filesystem while eviction lock is held called from
MMU notifier.
[How]
Setting PF_MEMALLOC_NOFS flags while eviction mutex is locked.
Using memalloc_nofs_save / memalloc_nofs_restore API.
Change-Id: I5531c93378
See one inline comment. Other than that:
Acked-by: Yong Zhao
On 2020-01-02 4:11 p.m., Alex Sierra wrote:
This can be used directly from amdgpu and amdkfd to invalidate
TLB through pasid.
It supports gmc v7, v8, v9 and v10.
Change-Id: I6563a8eba2e42d1a67fa2547156c20da41d1e490
Signed-off-by
On 2019-12-20 6:50 p.m., Yong Zhao wrote:
Inline.
On 2019-12-20 4:35 p.m., Felix Kuehling wrote:
On 2019-12-20 1:24, Alex Sierra wrote:
[Why]
TLB flush method has been deprecated using kfd2kgd interface.
This implementation is now on the amdgpu_amdkfd API.
[How]
TLB flush functions now
On 2019-12-20 1:24 a.m., Alex Sierra wrote:
This can be used directly from amdgpu and amdkfd to invalidate
TLB through pasid.
It supports gmc v7, v8, v9 and v10.
Change-Id: I6563a8eba2e42d1a67fa2547156c20da41d1e490
Signed-off-by: Alex Sierra
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h | 6
Inline.
On 2019-12-20 4:35 p.m., Felix Kuehling wrote:
On 2019-12-20 1:24, Alex Sierra wrote:
[Why]
TLB flush method has been deprecated using kfd2kgd interface.
This implementation is now on the amdgpu_amdkfd API.
[How]
TLB flush functions now implemented in amdgpu_amdkfd.
Change-Id: Ic51ccc
One style comment inline.
Yong
On 2019-12-20 1:24 a.m., Alex Sierra wrote:
[Why]
Avoid reclaim filesystem while eviction lock is held called from
MMU notifier.
[How]
Setting PF_MEMALLOC_NOFS flags while eviction mutex is locked.
Using memalloc_nofs_save / memalloc_nofs_restore API.
Change-Id:
This prevents the NULL pointer access when there are fewer than 8 sdma
engines.
Change-Id: Iabae9bff7546b344720905d5d4a5cfc066a79d25
Signed-off-by: Yong Zhao
---
.../drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c | 64 ---
1 file changed, 42 insertions(+), 22 deletions(-)
diff --git
The first one was already fixed and pushed a week ago.
Regards,
Yong
On 2019-12-12 7:25 p.m., Felix Kuehling wrote:
I agree with Christian's comments on patch 1. With those fixed, the
series is
Reviewed-by: Felix Kuehling
Regards,
Felix
On 2019-12-02 20:42, Yong Zhao wrote:
The log will be useful for easily getting the CU info on various
emulation models or ASICs.
Change-Id: Ic1c914938aa3445d8dbfdf6a237bc1d58b0d5267
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drivers/gpu/drm/amd
The log will be useful for easily getting the CU info on various
emulation models or ASICs.
Change-Id: Ic1c914938aa3445d8dbfdf6a237bc1d58b0d5267
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c| 6 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c | 6
Not sure whether we should add the issue ticket info here.
Reviewed-by: Yong Zhao
On 2019-12-03 3:45 p.m., James Zhu wrote:
SPI limits total CS waves in flight per SE to no more than 32 * num_cu and
we need to stuff 40 waves on a CU to completely clean the SGPR. This is
accomplished in the
Adjust the exposed function prototype so that the caller does not need
to know the MMHUB number.
Change-Id: I4420d1715984f703954f074682b075fc59e2a330
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 6 ++
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
Adjust the exposed function prototype so that the caller does not need
to know the MMHUB number.
Change-Id: I4420d1715984f703954f074682b075fc59e2a330
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 6 ++
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.h
Since Arcturus has it own function pointer, we can move Arcturus
specific logic to there rather than leaving it entangled with
other GFX9 chips.
Change-Id: I7df7c004a0c8ac0616ded0e65144670df50f92a7
Signed-off-by: Yong Zhao
---
.../drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c | 20
Pushed. Thanks!
Yong
On 2019-11-21 11:21 p.m., Liu, Zhan wrote:
Looks good to me.
Reviewed-by: Zhan Liu
-Original Message-
From: amd-gfx On Behalf Of
Yong Zhao
Sent: 2019/November/21, Thursday 4:25 PM
To: amd-gfx@lists.freedesktop.org
Cc: Zhao, Yong
Subject: [PATCH] drm/amdkfd
Its counterparty is called pm_create_runlist_ib(). The new name makes
it easier to navigate in the code.
Accordingly, Add rl_ to the variable names to indicate it is runlist.
Change-Id: Id63bfebeb8a5ed6aaefbebe98858d84724fd26be
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd
This is consistent with the calling sequence in unmap_queues_cpsch().
Change-Id: Ieb6714422c812d4f6ebbece34e339871471e4b5e
Signed-off-by: Yong Zhao
---
.../drm/amd/amdkfd/kfd_device_queue_manager.c | 18 +++--
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 20
The functions are the same as update_mqd().
Change-Id: Ic8d8f23cdde6b7806ab766ddf3d71fa668cca5fb
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 16 ++--
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 16 ++--
drivers/gpu/drm/amd
In the mqd_diq_sdma buffer, there should be only one HIQ mqd. All DIQs
should be allocate using the regular way.
Change-Id: Ibf3eb33604d0ec30501c244228cdb3b24615b699
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c | 2 +-
drivers/gpu/drm/amd/amdkfd
It is the same as KFD_MQD_TYPE_CP, so delete it. As a result, we will
have one less mqd mananger per device.
Change-Id: Iaa98fc17be06b216de7a826c3577f44bc0536b4c
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +-
drivers/gpu/drm/amd/amdkfd
After the recent cleanup, the functionalities provided by the previous
kfd_kernel_queue_*.c are actually all packet manager related. So rename
them to reflect that.
Change-Id: I6544ccb38da827c747544c0787aa949df20edbb0
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/Makefile
After the recent cleanup, the functionalities provided by the previous
kfd_kernel_queue_*.c are actually all packet manager related. So rename
them to reflect that.
Change-Id: I6544ccb38da827c747544c0787aa949df20edbb0
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/Makefile
Oh, I did not realize the part inside of the file. I think v9->ai is
better, because the packet format header uses ai. Also v9 will give
people an impression of gfx9.
Yong
On 2019-11-13 5:19 p.m., Felix Kuehling wrote:
On 2019-11-13 5:09 p.m., Yong Zhao wrote:
After the recent cleanup,
After the recent cleanup, the functionalities provided by the previous
kfd_kernel_queue_*.c are actually all packet manager related. So rename
them to reflect that.
Change-Id: I6544ccb38da827c747544c0787aa949df20edbb0
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/Makefile
: I9515fdece70110067cda66e2d24d6768b4846c2f
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c | 8 ++---
drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 30
drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h | 34 +--
.../gpu/drm/amd/amdkfd/kfd_packet_manager.c | 28
files
is the PM4 packet writer functions that are called by the
kfd_packet_manager. It may make sense to rename them to reflect
that. Maybe kfd_packet_manager_*.c
Regards,
Felix
On 2019-11-12 5:18 p.m., Yong Zhao wrote:
The ops_asic_specific function pointers are actually quite generic
The only difference that CIK kernel queue functions are different from
VI is avoid allocating eop_mem. We can achieve that by using a if
condition.
Change-Id: Iea9cbc82f603ff008a906c5ee32325ddcd02d963
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/Makefile | 1 -
drivers/gpu
The ops_asic_specific function pointers are actually quite generic after
using a simple if condition. Eliminate it by code refactoring.
Change-Id: Icb891289cca31acdbe2d2eea76a426f1738b9c08
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 63
Hi Felix,
See one thing inline I am not too sure.
Yong
On 2019-11-12 4:30 p.m., Felix Kuehling wrote:
On 2019-11-12 4:26 p.m., Yong Zhao wrote:
Adapt the change from 1cd106ecfc1f04
The change is:
drm/amdkfd: Stop using GFP_NOIO explicitly
This is no longer needed with the
This is done for other GFX in commit bb2d2128a54c4. Port it to GFX10.
Change-Id: I9e04872be3af0e90f5f6930226896b1ea545f3d9
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 11 ++-
1 file changed, 2 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu
Adapt the change from 1cd106ecfc1f04
The change is:
drm/amdkfd: Stop using GFP_NOIO explicitly
This is no longer needed with the memalloc_nofs_save/restore in
dqm_lock/unlock
Change-Id: I42450b2c149d2b1842be99a8f355c829a0079e7c
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd
workgroup context data writes from m->cp_hqd_cntl_stack_size, so we
should deduct it when calculating the used size.
Change-Id: I5252e25662c3b8221f451c39115bf084d1911eae
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c | 3 ++-
1 file changed, 2 insertions(+)
Ported from gfx9.
Change-Id: I388dc7c609ed724a6d600840f8e7317d9c2c877d
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
b/drivers/gpu/drm
Given control stack is now in the userspace context save restore area
on GFX10, the same as GFX8, it is not needed to copy it back to userspace.
Change-Id: I063ddc3026eefa57713ec47b466a90f9bf9d49b8
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 14
nline near the end of the
patch. I should have mentioned it here. Please fix that before you submit.
Thanks,
Felix
Change-Id: I553045ff9fcb3676900c92d10426f2ceb3660005
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 12 ++--
drivers/gpu/drm/
ping
On 2019-11-01 4:10 p.m., Zhao, Yong wrote:
Change-Id: I75da23bba90231762cf58da3170f5bb77ece45ed
Signed-off-by: Yong Zhao
---
.../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c | 14 +++---
drivers/gpu/drm/amd/amdkfd
ping
On 2019-11-01 4:12 p.m., Zhao, Yong wrote:
create_cp_queue() could also work with SDMA queues, so we should rename
it.
Change-Id: I76cbaed8fa95dd9062d786cbc1dd037ff041da9d
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 6 +++---
1 file changed, 3
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.
Change-Id: I846befbb2fcbddf40ca4ecbdc06da1cd442e3554
Signed-off-by:
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
---
drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 61 ++---
1 file changed
Signed-off-by: Yong Zhao
Reviewed-by: Oak Zeng
---
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/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
Signed-off-by: Yong Zhao
Reviewed-by: Oak Zeng
---
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/drm/amd/amdkfd/kfd_device_queue_manager.c
index
Change-Id: Id522c1cbadb8c069720f4e64a31cff42cd014733
Signed-off-by: Yong Zhao
---
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
index 709587d..93500e6
wrote:
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
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.
Change-Id: Id522c1cbadb8c069720f4e64a31cff42cd014733
Signed-off-by: Yong Zhao
---
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
index 709587d..3b9eb1a
Signed-off-by: Yong Zhao
Reviewed-by: Felix Kuehling
---
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_queue_manager.c | 6 ++
3 files changed, 6 insertions
Change-Id: Ia5c74ad567c30e206ed804b204fdf8a0f8a75a19
Signed-off-by: Yong Zhao
---
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_manager.c | 3 +--
3 files
Change-Id: Ia5c74ad567c30e206ed804b204fdf8a0f8a75a19
Signed-off-by: Yong Zhao
---
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_manager.c | 3 +--
3 files
From: Yong Zhao
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
Acked-by: Alex Deucher
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 9 ++---
drivers/gpu/drm/amd
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 wrote:
From: Yong Zhao
Without the additional bits set in PDEs/PTEs, the ATC memory access
would have failed.
Change-Id
From: Yong Zhao
Without the additional bits set in PDEs/PTEs, the ATC memory access
would have failed.
Change-Id: I28429ef6d39cdb01dc6f17fea4264ee22d7121d4
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 18 +++---
1 file changed, 15 insertions(+), 3
Use it to replace the hard coded value in amdgpu_vm_bo_update_mapping().
Change-Id: I85d89d401b8dbcf01ca9c55c281e552db874fde5
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h| 4
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +-
drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 2
structure amdgpu_vm_pte_funcs.
Change-Id: I37c588a57cb63f1a8251fb5ead2eff4b39e047c9
Signed-off-by: Yong Zhao
Reviewed-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 7 +++
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 5 +++-
Change-Id: I10fc5efbc303056c5c5c4dc4f4dd2c3186595a91
Signed-off-by: Yong Zhao
---
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_v3_0.c
index 728c0d8..4e7fe07
/PDEs
a single operation can set separately in amdgpu_vm_pte_funcs
structure.
Change-Id: I37c588a57cb63f1a8251fb5ead2eff4b39e047c9
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 6 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 8
drivers/gpu/drm/amd/amdgpu
: I37c588a57cb63f1a8251fb5ead2eff4b39e047c9
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 2180ed3..257361a 100644
--- a/drivers/gpu/drm/amd
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-by
We achieved that by setting S(SYSTEM) and P(PDE as PTE) bit to 1 for
PDEs and setting S bit to 1 for PTEs when the corresponding addresses
are not occupied by gpu driver allocated buffers.
Change-Id: I52e41b6e93243dbbd08d97781da1c9a60ce1f9a4
Signed-off-by: Yong Zhao
---
drivers/gpu/drm/amd
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-by: Yong Zhao
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 3 ++-
drivers/gpu/drm/amd/amdgpu
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
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c| 2 +-
drivers
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
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 19 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h | 2 +-
2 files
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
Date: Thu, 20 Jul 2017 18:44:10 -0400
Subject: [PATCH 1/2] drm/amdgpu: Add supp
more 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 wrote:
From: Yong Zhao
Signed-off-by: Yong Zhao
Reviewed-by:
1 - 100 of 101 matches
Mail list logo
