[Intel-gfx] [PATCH v2 0/3] drm/i915: Replace kmap() with kmap_local_page()

[Fabio M. De Francesco]

kmap() has been deprecated in favor of kmap_local_page().

There are two main problems with kmap(): (1) It comes with an overhead as
mapping space is restricted and protected by a global lock for
synchronization and (2) it also requires global TLB invalidation when the
kmap’s pool wraps and it might block when the mapping space is fully
utilized until a slot becomes available.

With kmap_local_page() the mappings are per thread, CPU local, can take
page faults, and can be called from any context (including interrupts).

The tasks can be preempted and, when they are scheduled to run again, the
kernel virtual addresses are restored and so they are still valid.

Furthermore, kmap_local_page() is faster than kmap() in kernels with
HIGHMEM enabled.

Thread locality implies that the kernel virtual addresses returned by
kmap_local_page() are only valid in the context of the callers. This
constraint is never violated with the conversions in this series,
because the pointers are never handed to other threads, so the local
mappings are allowed and preferred.

Therefore, replace kmap() with kmap_local_page() in drm/i915/,
drm/i915/gem/, drm/i915/gt/.

Suggested-by: Ira Weiny <ira.weiny at intel.com>
Signed-off-by: Fabio M. De Francesco <fmdefrancesco at gmail.com>

v1->v2: Do some changes in the text of the cover letter and in the
commit messages. There are no changes in the code of any of the three
patches.

Fabio M. De Francesco (3):
  drm/i915: Replace kmap() with kmap_local_page()
  drm/i915/gt: Replace kmap() with kmap_local_page()
  drm/i915/gem: Replace kmap() with kmap_local_page()

 drivers/gpu/drm/i915/gem/i915_gem_shmem.c          |  6 ++----
 drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c |  8 ++++----
 drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c       |  4 ++--
 drivers/gpu/drm/i915/gt/shmem_utils.c              | 11 ++++-------
 drivers/gpu/drm/i915/i915_gem.c                    |  8 ++++----
 5 files changed, 16 insertions(+), 21 deletions(-)

--
2.40.0