On Mon, Jul 14, 2025 at 11:53:19AM -0700, Tiffany Yang wrote:
> Each case tested by the binder allocator test is defined by 3 parameters:
> the end alignment type of each requested buffer allocation, whether those
> buffers share the front or back pages of the allotted address space, and
> the order in which those buffers should be released. The alignment type
> represents how a binder buffer may be laid out within or across page
> boundaries and relative to other buffers, and it's used along with
> whether the buffers cover part (sharing the front pages) of or all
> (sharing the back pages) of the vma to calculate the sizes passed into
> each test.
>
> binder_alloc_test_alloc recursively generates each possible arrangement
> of alignment types and then tests that the binder_alloc code tracks pages
> correctly when those buffers are allocated and then freed in every
> possible order at both ends of the address space. While they provide
> comprehensive coverage, they are poor candidates to be represented as
> KUnit test cases, which must be statically enumerated. For 5 buffers and
> 5 end alignment types, the test case array would have 750,000 entries.
> This change structures the recursive calls into meaningful test cases so
> that failures are easier to interpret.
>
> Signed-off-by: Tiffany Yang <ynaf...@google.com>
> ---

Great job here. Thanks!

Acked-by: Carlos Llamas <cmlla...@google.com>

Reply via email to