[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAFuZdDJRuQOhQQN79cgNERJQnMuOkQx4W-eTGcotCCUMk5HULA@mail.gmail.com>
Date: Mon, 14 Jul 2025 21:52:30 -0700
From: Carlos Llamas <cmllamas@...gle.com>
To: Tiffany Yang <ynaffit@...gle.com>
Cc: linux-kernel@...r.kernel.org, keescook@...gle.com, kernel-team@...roid.com,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>, Arve Hjønnevåg <arve@...roid.com>,
Todd Kjos <tkjos@...roid.com>, Martijn Coenen <maco@...roid.com>,
Joel Fernandes <joelagnelf@...dia.com>, Christian Brauner <brauner@...nel.org>,
Suren Baghdasaryan <surenb@...gle.com>, Brendan Higgins <brendan.higgins@...ux.dev>,
David Gow <davidgow@...gle.com>, Rae Moar <rmoar@...gle.com>, linux-kselftest@...r.kernel.org,
kunit-dev@...glegroups.com
Subject: Re: [PATCH v3 6/6] binder: encapsulate individual alloc test cases
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 <ynaffit@...gle.com>
> ---
Great job here. Thanks!
Acked-by: Carlos Llamas <cmllamas@...gle.com>
Powered by blists - more mailing lists