drm/gpusvm: let drm_gpusvm_get_pages() map an array of pages

Browse source

With the N:1 drm_gpusvm_pages layout, one CPU range mirrored on several
drm_devices, the caller had to invoke get_pages() once per device and
repeat the HMM fault every time.

Make get_pages() take a contiguous array of drm_gpusvm_pages plus a
count: fault once, then DMA map each instance by
drm_gpusvm_dma_map_pages() under a single read_retry gate. xe range and
userptr callers are updated.

Document the N:1 array usage in the Overview, showing how get_pages()
and drm_gpusvm_range_set_unmapped() take the whole array and its count
while the unmap and free paths stay per-instance.

Suggested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Honglei Huang <honghuan@amd.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260905133142.3628027-4-honghuan@amd.com

...

This commit is contained in:

Honglei Huang 2026-09-05 21:31:39 +08:00 • committed by Matthew Brost

parent 1ae616edb6

commit cc2a6cbd68

4 changed files with 110 additions and 35 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

140

drivers/gpu/drm/drm_gpusvm.c

View file

2

drivers/gpu/drm/xe/xe_svm.c

View file

2

drivers/gpu/drm/xe/xe_userptr.c

View file

1

include/drm/drm_gpusvm.h

View file