Skip to content

V
V8
Switch branch/tag
  1. 30 Aug, 2022 1 commit
  3. 26 Aug, 2022 1 commit
  5. 25 Aug, 2022 3 commits
  7. 24 Aug, 2022 4 commits
  9. 23 Aug, 2022 3 commits
  11. 22 Aug, 2022 3 commits
  13. 19 Aug, 2022 1 commit
    • Anton Bikineev's avatar
      cppgc: Avoid fragmentation in NormalPageMemoryRegion · 1d3a1c6f
      Anton Bikineev authored 
      NormalPageMemoryRegion is a span of 10 pages, all of which must belong
to the same space. This requirement imposes a fragmentation issue for virtual space, which is not ideal for the current 2GB cage
configuration.

The CL fixes this by mixing pages of different spaces inside the same
NormalPageMemoryRegion. With cage it's actually not necessary anymore
to have NormalPageMemoryRegion, but we keep it to allow the code to be
uniform for cage/non-cage configurations.

There is no type confusion across spaces, since pages (even empty) are
never shared between spaces. In addition, the shared cage puts an
additional memory constraint on the GC. So, there is no security benefit
in having NormalPageMemoryRegion assigned to a single space.

Savings in reserved address space:
cnn:2021: 14%
facebook_infinite_scroll:2018: 23%

Bug: chromium:1325007, chromium:1352649
Change-Id: I7b49032d581dd56feb8633734a1f37803e9526c6
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3840749Reviewed-by: 's avatarMichael Lippautz <mlippautz@chromium.org>
Commit-Queue: Anton Bikineev <bikineev@chromium.org>
Cr-Commit-Position: refs/heads/main@{#82584}
      1d3a1c6f
  15. 18 Aug, 2022 3 commits
  17. 17 Aug, 2022 1 commit
  19. 16 Aug, 2022 2 commits
  21. 15 Aug, 2022 1 commit
  23. 12 Aug, 2022 3 commits
    • Nico Hartmann's avatar
      Revert "[heap] Rework Worklist base type" · 54ef0d87
      Nico Hartmann authored 
      This reverts commit a19316d9.

Reason for revert: https://ci.chromium.org/ui/p/v8/builders/ci/V8%20Linux64%20UBSan/22670/overview

Original change's description:
> [heap] Rework Worklist base type
>
> Worklist uses a singly-linked list of segments to hold entries.
> Segment size was based on a compile-time constant but already stored
> in the segment itself.
>
> Rework the segments to query `malloc_usable_size()` on allocation and
> adjust the capacity properly. For PartitionAlloc, it turns out that
> there's ~20% more capacity available for the 64-element segments.
>
> This slows down actual allocation of the segments with the upside of
> improving utilization and requiring 20% less segments.
>
> Change-Id: Ib8595c3fb9fb75b02e4022f6c525bb59a2df7ab7
> Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3826047
> Commit-Queue: Anton Bikineev <bikineev@chromium.org>
> Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
> Reviewed-by: Anton Bikineev <bikineev@chromium.org>
> Cr-Commit-Position: refs/heads/main@{#82432}

Change-Id: I14994e11ff5ffaba70b93d977d40dd2f6e9e5d35
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3829474
Owners-Override: Nico Hartmann <nicohartmann@chromium.org>
Commit-Queue: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com>
Auto-Submit: Nico Hartmann <nicohartmann@chromium.org>
Bot-Commit: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com>
Cr-Commit-Position: refs/heads/main@{#82438}
      54ef0d87
    • Omer Katz's avatar
      [heap] Implement SimulateFullSpace for PagedNewSpace · 0cd0e4bb
      Omer Katz authored 
      The existing version for paged spaces simply reset the freelist, which
doesn't work for tests that require actual objects in the space.
The version for new space also doesn't work because it assumes
everything after top is free space.

Fill the space with FixedArray by iterating over the freelist and
creating an object in place of each freelist entry.
This method actually fills the space, so that we can also use it to
force page promotion.

Bug: v8:12612
Change-Id: Ie0d73e846bbf688ea52030be29e0587b2f37ed4e
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3823135Reviewed-by: 's avatarMichael Lippautz <mlippautz@chromium.org>
Commit-Queue: Omer Katz <omerkatz@chromium.org>
Cr-Commit-Position: refs/heads/main@{#82437}
      0cd0e4bb
    • Michael Lippautz's avatar
      [heap] Rework Worklist base type · a19316d9
      Michael Lippautz authored 
      Worklist uses a singly-linked list of segments to hold entries.
Segment size was based on a compile-time constant but already stored
in the segment itself.

Rework the segments to query `malloc_usable_size()` on allocation and
adjust the capacity properly. For PartitionAlloc, it turns out that
there's ~20% more capacity available for the 64-element segments.

This slows down actual allocation of the segments with the upside of
improving utilization and requiring 20% less segments.

Change-Id: Ib8595c3fb9fb75b02e4022f6c525bb59a2df7ab7
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3826047
Commit-Queue: Anton Bikineev <bikineev@chromium.org>
Commit-Queue: Michael Lippautz <mlippautz@chromium.org>
Reviewed-by: 's avatarAnton Bikineev <bikineev@chromium.org>
Cr-Commit-Position: refs/heads/main@{#82432}
      a19316d9
  25. 10 Aug, 2022 3 commits
  27. 09 Aug, 2022 4 commits
  29. 04 Aug, 2022 1 commit
  31. 01 Aug, 2022 1 commit
  33. 27 Jul, 2022 1 commit
  35. 26 Jul, 2022 1 commit
  37. 19 Jul, 2022 3 commits