linux.git/drivers/gpu/drm/amd/amdkfd, branch v5.14

drm/amdkfd: fix random KFDSVMRangeTest.SetGetAttributesTest test failure

2021-08-16T19:59:41+00:00

KFDSVMRangeTest.SetGetAttributesTest randomly fails in stress test.

Note: Google Test filter = KFDSVMRangeTest.*
[==========] Running 18 tests from 1 test case.
[----------] Global test environment set-up.
[----------] 18 tests from KFDSVMRangeTest
[ RUN      ] KFDSVMRangeTest.BasicSystemMemTest
[       OK ] KFDSVMRangeTest.BasicSystemMemTest (30 ms)
[ RUN      ] KFDSVMRangeTest.SetGetAttributesTest
[          ] Get default atrributes
/home/yifan/brahma/libhsakmt/tests/kfdtest/src/KFDSVMRangeTest.cpp:154: Failure
Value of: expectedDefaultResults[i]
  Actual: 4294967295
Expected: outputAttributes[i].value
Which is: 0
/home/yifan/brahma/libhsakmt/tests/kfdtest/src/KFDSVMRangeTest.cpp:154: Failure
Value of: expectedDefaultResults[i]
  Actual: 4294967295
Expected: outputAttributes[i].value
Which is: 0
/home/yifan/brahma/libhsakmt/tests/kfdtest/src/KFDSVMRangeTest.cpp:152: Failure
Value of: expectedDefaultResults[i]
  Actual: 4
Expected: outputAttributes[i].type
Which is: 2
[          ] Setting/Getting atrributes
[  FAILED  ]

the root cause is that svm work queue has not finished when svm_range_get_attr is called, thus
some garbage svm interval tree data make svm_range_get_attr get wrong result. Flush work queue before
iterate svm interval tree.

Signed-off-by: Yifan Zhang 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

Revert "drm/amdkfd: Add heavy-weight TLB flush after unmapping"

2021-07-13T15:59:41+00:00

This reverts commit 1098d658bef05e5fee634aab0b6a1fa590cfca24.

Reason for revert: it causes regressions on several Asics.

Signed-off-by: Eric Huang 
Signed-off-by: Alex Deucher

Revert "drm/amdkfd: Make TLB flush conditional on mapping"

2021-07-13T15:59:22+00:00

This reverts commit 31f33243788dcbae8bd2819ed83923a73f7dfd30.

Reason for revert: it causes regressions on several Asics.

Signed-off-by: Eric Huang 
Signed-off-by: Alex Deucher

Revert "drm/amdkfd: Add memory sync before TLB flush on unmap"

2021-07-13T15:59:07+00:00

This reverts commit 3be4dca197010d1328df8b11febc8c40491be498.

Reason for revert: it causes regressions on several Asics.

Signed-off-by: Eric Huang 
Signed-off-by: Alex Deucher

drm/amdkfd: handle fault counters on invalid address

2021-07-13T15:48:13+00:00

prange is NULL if vm fault retry on invalid address, for this case, can
not use prange to get pdd, use adev to get gpuidx and then get pdd
instead, then increase pdd vm fault counter.

Signed-off-by: Philip Yang 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: Maintain svm_bo reference in page->zone_device_data

2021-07-01T04:05:41+00:00

Each zone-device page holds a reference to the SVM BO that manages its
backing storage. This is necessary to correctly hold on to the BO in
case zone_device pages are shared with a child-process.

Signed-off-by: Alex Sierra 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: add invalid pages debug at vram migration

2021-07-01T04:05:41+00:00

This is for debug purposes only.
It conditionally generates partial migrations to test mixed
CPU/GPU memory domain pages in a prange easily.

Signed-off-by: Alex Sierra 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: skip migration for pages already in VRAM

2021-07-01T04:05:41+00:00

Migration skipped for pages that are already in VRAM
domain. These could be the result of previous partial
migrations to SYS RAM, and prefetch back to VRAM.
Ex. Coherent pages in VRAM that were not written/invalidated after
a copy-on-write.

Signed-off-by: Alex Sierra 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: skip invalid pages during migrations

2021-07-01T04:05:41+00:00

Invalid pages can be the result of pages that have been migrated
already due to copy-on-write procedure or pages that were never
migrated to VRAM in first place. This is not an issue anymore,
as pranges now support mixed memory domains (CPU/GPU).

Signed-off-by: Alex Sierra 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher

drm/amdkfd: classify and map mixed svm range pages in GPU

2021-07-01T04:05:41+00:00

[Why]
svm ranges can have mixed pages from device or system memory.
A good example is, after a prange has been allocated in VRAM and a
copy-on-write is triggered by a fork. This invalidates some pages
inside the prange. Endding up in mixed pages.

[How]
By classifying each page inside a prange, based on its type. Device or
system memory, during dma mapping call. If page corresponds
to VRAM domain, a flag is set to its dma_addr entry for each GPU.
Then, at the GPU page table mapping. All group of contiguous pages within
the same type are mapped with their proper pte flags.

v2:
Instead of using ttm_res to calculate vram pfns in the svm_range. It is now
done by setting the vram real physical address into drm_addr array.
This makes more flexible VRAM management, plus removes the need to have
a BO reference in the svm_range.

v3:
Remove mapping member from svm_range

Signed-off-by: Alex Sierra 
Reviewed-by: Felix Kuehling 
Signed-off-by: Alex Deucher