diff options
| author | José Roberto de Souza <[email protected]> | 2024-03-13 10:13:18 -0700 |
|---|---|---|
| committer | Matthew Brost <[email protected]> | 2024-03-13 15:46:26 -0700 |
| commit | 58480c1c912ff8146d067301a0d04cca318b4a66 (patch) | |
| tree | 5e14c97ac1d47f75fd7817696e592ab1b41d5147 /tools/perf/scripts/python/bin/stackcollapse-report | |
| parent | cf2cbbc76dc4272fa156f4991fab1024b5815451 (diff) | |
drm/xe: Skip VMAs pin when requesting signal to the last XE_EXEC
Doing a XE_EXEC with num_batch_buffer == 0 makes signals passed as
argument to be signaled when the last real XE_EXEC is completed.
But to do that it was first pinning all VMAs in drm_gpuvm_exec_lock(),
this patch remove this pinning as it is not required.
This change also help Mesa implementing memory over-commiting recovery
as it needs to unbind not needed VMAs when the whole VM can't fit
in GPU memory but it can only do the unbiding when the last XE_EXEC
is completed.
So with this change Mesa can get the signal it want without getting
out-of-memory errors.
Fixes: eb9702ad2986 ("drm/xe: Allow num_batch_buffer / num_binds == 0 in IOCTLs")
Cc: Thomas Hellstrom <[email protected]>
Co-developed-by: Matthew Brost <[email protected]>
Signed-off-by: José Roberto de Souza <[email protected]>
Reviewed-by: Matthew Brost <[email protected]>
Signed-off-by: Matthew Brost <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]
Diffstat (limited to 'tools/perf/scripts/python/bin/stackcollapse-report')
0 files changed, 0 insertions, 0 deletions