Searched hist:"3 edfa30f" (Results 1 – 5 of 5) sorted by relevance
/openbmc/linux/drivers/gpu/drm/msm/ |
H A D | msm_gem_shrinker.c | 3edfa30f Mon Nov 16 11:48:51 CST 2020 Rob Clark <robdclark@chromium.org> drm/msm/shrinker: Only iterate dontneed objs
In situations where the GPU is mostly idle, all or nearly all buffer objects will be in the inactive list. But if the system is under memory pressure (from something other than GPU), we could still get a lot of shrinker calls. Which results in traversing a list of thousands of objs and in the end finding nothing to shrink. Which isn't so efficient.
Instead split the inactive_list into two lists, one inactive objs which are shrinkable, and a second one for those that are not. This way we can avoid traversing objs which we know are not shrinker candidates.
v2: Fix inverted logic think-o
Signed-off-by: Rob Clark <robdclark@chromium.org>
|
H A D | msm_debugfs.c | 3edfa30f Mon Nov 16 11:48:51 CST 2020 Rob Clark <robdclark@chromium.org> drm/msm/shrinker: Only iterate dontneed objs
In situations where the GPU is mostly idle, all or nearly all buffer objects will be in the inactive list. But if the system is under memory pressure (from something other than GPU), we could still get a lot of shrinker calls. Which results in traversing a list of thousands of objs and in the end finding nothing to shrink. Which isn't so efficient.
Instead split the inactive_list into two lists, one inactive objs which are shrinkable, and a second one for those that are not. This way we can avoid traversing objs which we know are not shrinker candidates.
v2: Fix inverted logic think-o
Signed-off-by: Rob Clark <robdclark@chromium.org>
|
H A D | msm_drv.h | 3edfa30f Mon Nov 16 11:48:51 CST 2020 Rob Clark <robdclark@chromium.org> drm/msm/shrinker: Only iterate dontneed objs
In situations where the GPU is mostly idle, all or nearly all buffer objects will be in the inactive list. But if the system is under memory pressure (from something other than GPU), we could still get a lot of shrinker calls. Which results in traversing a list of thousands of objs and in the end finding nothing to shrink. Which isn't so efficient.
Instead split the inactive_list into two lists, one inactive objs which are shrinkable, and a second one for those that are not. This way we can avoid traversing objs which we know are not shrinker candidates.
v2: Fix inverted logic think-o
Signed-off-by: Rob Clark <robdclark@chromium.org>
|
H A D | msm_gem.c | 3edfa30f Mon Nov 16 11:48:51 CST 2020 Rob Clark <robdclark@chromium.org> drm/msm/shrinker: Only iterate dontneed objs
In situations where the GPU is mostly idle, all or nearly all buffer objects will be in the inactive list. But if the system is under memory pressure (from something other than GPU), we could still get a lot of shrinker calls. Which results in traversing a list of thousands of objs and in the end finding nothing to shrink. Which isn't so efficient.
Instead split the inactive_list into two lists, one inactive objs which are shrinkable, and a second one for those that are not. This way we can avoid traversing objs which we know are not shrinker candidates.
v2: Fix inverted logic think-o
Signed-off-by: Rob Clark <robdclark@chromium.org>
|
H A D | msm_drv.c | 3edfa30f Mon Nov 16 11:48:51 CST 2020 Rob Clark <robdclark@chromium.org> drm/msm/shrinker: Only iterate dontneed objs
In situations where the GPU is mostly idle, all or nearly all buffer objects will be in the inactive list. But if the system is under memory pressure (from something other than GPU), we could still get a lot of shrinker calls. Which results in traversing a list of thousands of objs and in the end finding nothing to shrink. Which isn't so efficient.
Instead split the inactive_list into two lists, one inactive objs which are shrinkable, and a second one for those that are not. This way we can avoid traversing objs which we know are not shrinker candidates.
v2: Fix inverted logic think-o
Signed-off-by: Rob Clark <robdclark@chromium.org>
|