linux-toradex.git/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c, branch v6.10 Linux kernel for Apalis and Colibri modules drm/amdkfd: Let VRAM allocations go to GTT domain on small APUs 2024-05-20T21:17:53+00:00 Lang Yu Lang.Yu@amd.com 2024-04-26T06:56:35+00:00 eb853413d02c8d9b27942429b261a9eef228f005 Small APUs(i.e., consumer, embedded products) usually have a small carveout device memory which can't satisfy most compute workloads memory allocation requirements. We can't even run a Basic MNIST Example with a default 512MB carveout. https://github.com/pytorch/examples/tree/main/mnist. Error Log: "torch.cuda.OutOfMemoryError: HIP out of memory. Tried to allocate 84.00 MiB. GPU 0 has a total capacity of 512.00 MiB of which 0 bytes is free. Of the allocated memory 103.83 MiB is allocated by PyTorch, and 22.17 MiB is reserved by PyTorch but unallocated" Though we can change BIOS settings to enlarge carveout size, which is inflexible and may bring complaint. On the other hand, the memory resource can't be effectively used between host and device. The solution is MI300A approach, i.e., let VRAM allocations go to GTT. Then device and host can flexibly and effectively share memory resource. v2: Report local_mem_size_private as 0. (Felix) Signed-off-by: Lang Yu <Lang.Yu@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Small APUs(i.e., consumer, embedded products) usually have a small
carveout device memory which can't satisfy most compute workloads
memory allocation requirements.

We can't even run a Basic MNIST Example with a default 512MB carveout.
https://github.com/pytorch/examples/tree/main/mnist. Error Log:

"torch.cuda.OutOfMemoryError: HIP out of memory. Tried to allocate
84.00 MiB. GPU 0 has a total capacity of 512.00 MiB of which 0 bytes
is free. Of the allocated memory 103.83 MiB is allocated by PyTorch,
and 22.17 MiB is reserved by PyTorch but unallocated"

Though we can change BIOS settings to enlarge carveout size,
which is inflexible and may bring complaint. On the other hand,
the memory resource can't be effectively used between host and device.

The solution is MI300A approach, i.e., let VRAM allocations go to GTT.
Then device and host can flexibly and effectively share memory resource.

v2: Report local_mem_size_private as 0. (Felix)

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: prepare to handle pasid poison consumption 2024-04-26T21:22:42+00:00 YiPeng Chai YiPeng.Chai@amd.com 2024-04-22T09:40:03+00:00 bfa579b38b865879223f61f6ae295c939d4f7d11 Prepare to handle pasid poison consumption. Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Prepare to handle pasid poison consumption.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: make reset method configurable for RAS poison 2024-03-20T17:38:15+00:00 Tao Zhou tao.zhou1@amd.com 2024-03-12T03:30:09+00:00 2fc46e0b2fe8802c98a68d5c903e0109e1d4a49c Each RAS block has different requirement for gpu reset in poison consumption handling. Add support for mmhub RAS poison consumption handling. v2: remove the mmhub poison support for kfd int v10. Signed-off-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Each RAS block has different requirement for gpu reset in poison
consumption handling.
Add support for mmhub RAS poison consumption handling.

v2: remove the mmhub poison support for kfd int v10.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: support utcl2 RAS poison query for mmhub 2024-03-20T17:38:14+00:00 Tao Zhou tao.zhou1@amd.com 2024-03-11T08:53:53+00:00 d8070c4241087d8c1ad3fc21632bac268dd7578a Support the query for both gfxhub and mmhub, also replace xcc_id with hub_inst. Signed-off-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Support the query for both gfxhub and mmhub, also replace
xcc_id with hub_inst.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: retire gfx ras query_utcl2_poison_status 2024-03-20T17:37:36+00:00 Tao Zhou tao.zhou1@amd.com 2024-02-19T07:55:24+00:00 71a8d61ebc38f0f1b96011518fefd0a1e07efa74 Replace it with related interface in gfxhub functions. v2: replace node id with xcc id. get node id for query_utcl2_poison_status Signed-off-by: Tao Zhou <tao.zhou1@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Replace it with related interface in gfxhub functions.

v2: replace node id with xcc id.
    get node id for query_utcl2_poison_status

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Init zone device and drm client after mode-1 reset on reload 2024-03-20T17:12:57+00:00 Ahmad Rehman Ahmad.Rehman@amd.com 2024-03-04T21:56:00+00:00 f679fd6057fbf5ab34aaee28d58b7f81af0cbf48 In passthrough environment, when amdgpu is reloaded after unload, mode-1 is triggered after initializing the necessary IPs, That init does not include KFD, and KFD init waits until the reset is completed. KFD init is called in the reset handler, but in this case, the zone device and drm client is not initialized, causing app to create kernel panic. v2: Removing the init KFD condition from amdgpu_amdkfd_drm_client_create. As the previous version has the potential of creating DRM client twice. v3: v2 patch results in SDMA engine hung as DRM open causes VM clear to SDMA before SDMA init. Adding the condition to in drm client creation, on top of v1, to guard against drm client creation call multiple times. Signed-off-by: Ahmad Rehman <Ahmad.Rehman@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
In passthrough environment, when amdgpu is reloaded after unload, mode-1
is triggered after initializing the necessary IPs, That init does not
include KFD, and KFD init waits until the reset is completed. KFD init
is called in the reset handler, but in this case, the zone device and
drm client is not initialized, causing app to create kernel panic.

v2: Removing the init KFD condition from amdgpu_amdkfd_drm_client_create.
As the previous version has the potential of creating DRM client twice.

v3: v2 patch results in SDMA engine hung as DRM open causes VM clear to SDMA
before SDMA init. Adding the condition to in drm client creation, on top of v1,
to guard against drm client creation call multiple times.

Signed-off-by: Ahmad Rehman <Ahmad.Rehman@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Skip packet submission on fatal error 2024-02-26T16:14:31+00:00 Lijo Lazar lijo.lazar@amd.com 2024-02-22T09:24:50+00:00 e1f6746f339c9514c0564bab02c3f8847f4aa44b If fatal error is detected, packet submission won't go through. Return error in such cases. Also, avoid waiting for fence when fatal error is detected. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Asad Kamal <asad.kamal@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
If fatal error is detected, packet submission won't go through. Return
error in such cases. Also, avoid waiting for fence when fatal error is
detected.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: move the drm client creation behind drm device registration 2024-01-29T20:35:13+00:00 Le Ma le.ma@amd.com 2024-01-25T04:00:34+00:00 c0125b848abecfbc944bebe2cab076f09455b230 This patch is to eliminate interrupt warning below: "[drm] Fence fallback timer expired on ring sdma0.0". An early vm pt clearing job is sent to SDMA ahead of interrupt enabled. And re-locating the drm client creation following after drm_dev_register looks like a more proper flow. v2: wrap the drm client creation Fixes: 1819200166ce ("drm/amdkfd: Export DMABufs from KFD using GEM handles") Signed-off-by: Le Ma <le.ma@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
This patch is to eliminate interrupt warning below:

  "[drm] Fence fallback timer expired on ring sdma0.0".

An early vm pt clearing job is sent to SDMA ahead of interrupt enabled.
And re-locating the drm client creation following after drm_dev_register
looks like a more proper flow.

v2: wrap the drm client creation

Fixes: 1819200166ce ("drm/amdkfd: Export DMABufs from KFD using GEM handles")
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Support passing poison consumption ras block to SRIOV 2024-01-25T19:58:03+00:00 YiPeng Chai YiPeng.Chai@amd.com 2024-01-23T08:08:11+00:00 ed1e1e42fd68b073fc47aefe94d70364f3a43e97 Support passing poison consumption ras blocks to SRIOV. Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Support passing poison consumption ras blocks
to SRIOV.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Enable GFXOFF for Compute on GFX11 2024-01-18T20:46:56+00:00 Ori Messinger Ori.Messinger@amd.com 2023-11-22T05:12:13+00:00 776b0953aba8b10cc2903c958d60334c9703dc34 On GFX version 11, GFXOFF was disabled due to a MES KIQ firmware issue, which has since been fixed after version 64. This patch only re-enables GFXOFF for GFX version 11 if the GPU's MES KIQ firmware version is newer than version 64. V2: Keep GFXOFF disabled on GFX11 if MES KIQ is below version 64. V3: Add parentheses to avoid GCC warning for parentheses: "suggest parentheses around comparison in operand of ‘&’" V4: Remove "V3" from commit title V5: Change commit description and insert 'Acked-by' Signed-off-by: Ori Messinger <Ori.Messinger@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
On GFX version 11, GFXOFF was disabled due to a MES KIQ firmware
issue, which has since been fixed after version 64.
This patch only re-enables GFXOFF for GFX version 11 if the GPU's
MES KIQ firmware version is newer than version 64.

V2: Keep GFXOFF disabled on GFX11 if MES KIQ is below version 64.
V3: Add parentheses to avoid GCC warning for parentheses:
"suggest parentheses around comparison in operand of ‘&’"
V4: Remove "V3" from commit title
V5: Change commit description and insert 'Acked-by'

Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>