linux/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c, branch v5.15Mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
https://git.shady.money/linux/atom?h=v5.152021-09-16T13:56:24Zdrm/amdgpu: add amdgpu_amdkfd_resume_iommu2021-09-16T13:56:24ZJames ZhuJames.Zhu@amd.com2021-09-07T15:27:31Zurn:sha1:8066008482e533e91934bee49765bf8b4a7c40db
Add amdgpu_amdkfd_resume_iommu for amdgpu.
Bug: https://bugzilla.kernel.org/show_bug.cgi?id=211277
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
drm/amd/amdgpu embed hw_fence into amdgpu_job2021-08-16T19:16:58ZJack ZhangJack.Zhang1@amd.com2021-05-12T07:06:35Zurn:sha1:c530b02f39850a639b72d01ebbf7e5d745c60831
Why: Previously hw fence is alloced separately with job.
It caused historical lifetime issues and corner cases.
The ideal situation is to take fence to manage both job
and fence's lifetime, and simplify the design of gpu-scheduler.
How:
We propose to embed hw_fence into amdgpu_job.
1. We cover the normal job submission by this method.
2. For ib_test, and submit without a parent job keep the
legacy way to create a hw fence separately.
v2:
use AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT to show that the fence is
embedded in a job.
v3:
remove redundant variable ring in amdgpu_job
v4:
add tdr sequence support for this feature. Add a job_run_counter to
indicate whether this job is a resubmit job.
v5
add missing handling in amdgpu_fence_enable_signaling
Signed-off-by: Jingwen Chen <Jingwen.Chen2@amd.com>
Signed-off-by: Jack Zhang <Jack.Zhang7@hotmail.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed by: Monk Liu <monk.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: report pcie bandwidth to the kfd2021-07-23T14:07:59ZJonathan Kimjonathan.kim@amd.com2021-06-02T13:46:16Zurn:sha1:933048103837710b6996d5487e5fcbc320b81503
Similar to xGMI reporting the min/max bandwidth between direct peers, PCIe
will report the min/max bandwidth to the KFD.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: report xgmi bandwidth between direct peers to the kfd2021-07-23T14:07:59ZJonathan Kimjonathan.kim@amd.com2021-05-12T16:30:41Zurn:sha1:3f46c4e9ce25bbcb9d619dbce57c8737c856b272
Report the min/max bandwidth in megabytes to the kfd for direct
xgmi connections only. Indirect peers will report 0 since
indirect route is unknown.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Merge drm/drm-next into drm-misc-next2021-05-22T05:17:05ZThomas Zimmermanntzimmermann@suse.de2021-05-22T05:17:05Zurn:sha1:304ba5dca49a21e6f4040494c669134787145118
Backmerging from drm/drm-next to the patches for AMD devices
for v5.14.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
drm/amdgpu: Add early fini callback2021-05-20T03:48:50ZAndrey Grodzovskyandrey.grodzovsky@amd.com2021-05-20T03:20:57Zurn:sha1:e9669fb7826270bd73554208b49b6353ab3d856f
Use it to call disply code dependent on device->drv_data
before it's set to NULL on device unplug
v5:
Move HW finilization into this callback to prevent MMIO accesses
post cpi remove.
v7:
Split kfd suspend from device exit to expdite HW related
stuff to amdgpu_pci_remove
v8:
Squash previous KFD commit into this commit to avoid compile break.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210520032057.497334-1-andrey.grodzovsky@amd.com
drm/amdkfd: heavy-weight flush TLB after unmap2021-05-20T02:37:50ZPhilip YangPhilip.Yang@amd.com2021-05-13T16:30:48Zurn:sha1:765385ec00a94382b509c75867e2a40fa599a26d
Need do a heavy-weight TLB flush to make sure we have no more dirty data
in the cache for the unmapped pages.
Define enum TLB_FLUSH_TYPE, add flush_type parameter to
amdgpu_amdkfd_flush_gpu_tlb_pasid.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: use amdgpu_bo_user bo for metadata and tiling flag2021-04-09T20:45:31ZNirmoy Dasnirmoy.das@amd.com2021-03-08T13:03:35Zurn:sha1:cc1bcf85b0112ad660e70464d00d3e36e103cedd
Tiling flag and metadata are only needed for BOs created by
amdgpu_gem_object_create(), so we can remove those from the
base class.
v2: * squash tiling_flags and metadata relared patches into one
* use BUG_ON for non ttm_bo_type_device type when accessing
tiling_flags and metadata._
v3: *include to_amdgpu_bo_user
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: use amdgpu_bo_create_user() for when possible2021-04-09T20:45:28ZNirmoy Dasnirmoy.das@amd.com2021-03-09T07:31:25Zurn:sha1:22b40f7a3ad17176b05413893228a82823bbe9e5
Use amdgpu_bo_create_user() for all the BO allocations for
ttm_bo_type_device type.
v2: include amdgpu_amdkfd_alloc_gws() as well it calls amdgpu_bo_create()
for ttm_bo_type_device
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: allow variable BO struct creation2021-04-09T20:45:12ZNirmoy Dasnirmoy.das@amd.com2021-03-08T13:00:06Zurn:sha1:9fd5543e9552acff859af7f154bd3402b7983dc5
Allow allocating BO structures with different structure size
than struct amdgpu_bo.
v2: Check bo_ptr_size in all amdgpu_bo_create() caller.
Signed-off-by: Nirmoy Das <nirmoy.das@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>