dma-buf: Code rework and performance improvements for system heap
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v7 Latest5 patches 2 repliesIn review
- v65 patches 0 repliesSuperseded
- v57 patches 11 repliesSuperseded
Earlier versions · 5
| Version | Posted | Patches | Replies | Status |
|---|---|---|---|---|
| v4 posting 2/2 | 7 patches | 4 replies | Superseded | |
| v4 posting 1/2 | 7 patches | 0 replies | Superseded | |
| v3 | 7 patches | 10 replies | Superseded | |
| v2 | 6 patches | 0 replies | Superseded | |
| v1 RFC | 6 patches | 4 replies | Superseded |
Patches in v7 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/5 | dma-buf: system_heap: Rework system heap to use sgtables instead of pagelistsdrivers/ | +303 | 0 replies | |
| 2/5 | dma-buf: heaps: Move heap-helper logic into the cma_heap implementationdrivers/ | +270 | 4 replies | |
| 3/5 | dma-buf: heaps: Remove heap-helpers codedrivers/ drivers/ drivers/ | +0 | 0 replies | |
| 4/5 | dma-buf: heaps: Skip sync if not mappeddrivers/ drivers/ | +20 | 0 replies | |
| 5/5 | dma-buf: system_heap: Allocate higher order pages if availabledrivers/ | +71 | 0 replies |
Reviews trailers per patch
All 5 patches have a Reviewed-by or Acked-by.
| Patch | Brian Starkey |
|---|---|
| 1/5 | R-b |
| 2/5 | R-b |
| 3/5 | R-b |
| 4/5 | R-b |
| 5/5 | R-b |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes.
Cover letter [PATCH v7 0/5] dma-buf: Code rework and performance improvements for system heap
Hey All,
So Sumit noted a flub I made in adapting the last series to
the new dma-buf-map code that is in drm-misc-next. Thus I wanted to send this (hopefully) last revision of my patch series of performance optimizations to the dma-buf system heap, once again against drm-misc-next.
This series reworks the system heap to use sgtables, and then consolidates the pagelist method from the heap-helpers into the CMA heap. After which the heap-helpers logic is removed (as it is unused). I'd still like to find a better way to avoid some of the logic duplication in implementing the entire dma_buf_ops handlers per heap. But unfortunately that code is tied somewhat to how the buffer's memory is tracked. As more heaps show up I think we'll have a better idea how to best share code, so for now I think this is ok.
After this, the series introduces an optimization that Ørjan Eide implemented for ION that avoids calling sync on attachments that don't have a mapping.
Finally, an optimization to use larger order pages for the system heap. This change brings us closer to the current performance of the ION allocation code (though there still is a gap due to ION using a mix of deferred-freeing and page pools, I'll be looking at integrating those eventually).
This version of the series does not include the system-uncached heap as Daniel wanted further demonstration that it is useful with devices that use the mesa stack. I'm working on such a justification but I don't want to hold up these rework patches in the meantime.
thanks
-john
New in v7:
* Fixed the incorrect adaptation to the dma-buf-map usage
John Stultz (5):
dma-buf: system_heap: Rework system heap to use sgtables instead of
pagelists
dma-buf: heaps: Move heap-helper logic into the cma_heap
implementation
dma-buf: heaps: Remove heap-helpers code
dma-buf: heaps: Skip sync if not mapped
dma-buf: system_heap: Allocate higher order pages if available
drivers/dma-buf/heaps/Makefile | 1 - drivers/dma-buf/heaps/cma_heap.c | 329 +++++++++++++++++---- drivers/dma-buf/heaps/heap-helpers.c | 274 ------------------ drivers/dma-buf/heaps/heap-helpers.h | 53 ---- drivers/dma-buf/heaps/system_heap.c | 414 ++++++++++++++++++++++++--- 5 files changed, 647 insertions(+), 424 deletions(-) delete mode 100644 drivers/dma-buf/heaps/heap-helpers.c delete mode 100644 drivers/dma-buf/heaps/heap-helpers.h
Signature · 6 lines
2.17.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel