linux-kernel - Re: [PATCH v4 6/6] binder: encapsulate individual alloc test cases

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <202507162326.5A827E93C@keescook>
Date: Wed, 16 Jul 2025 23:32:10 -0700
From: Kees Cook <kees@...nel.org>
To: Tiffany Yang <ynaffit@...gle.com>
Cc: linux-kernel@...r.kernel.org, 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>,
	Carlos Llamas <cmllamas@...gle.com>,
	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 v4 6/6] binder: encapsulate individual alloc test cases

On Wed, Jul 16, 2025 at 06:10:09PM -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.
> 
> Cc: Kees Cook <kees@...nel.org>
> Acked-by: Carlos Llamas <cmllamas@...gle.com>
> Signed-off-by: Tiffany Yang <ynaffit@...gle.com>
> [...]
> +struct binder_alloc_test_case_info {
> +	char alignments[ALIGNMENTS_BUFLEN];
> +	struct seq_buf alignments_sb;

This really screams for a struct-based way to in-place declare a
seq_buf. The current macro only works on the stack. I think this
will work; I'll send a patch once I get it tested:

#define DECLARE_SEQ_BUF(NAME, SIZE)		\
	char NAME##_buffer[size];		\
	struct seq_buf NAME = {			\
		.buffer = &NAME##_buffer,	\
		.size = SIZE,			\
	}

But yes, this and the seq_buf_init below is correct.

Reviewed-by: Kees Cook <kees@...nel.org>

-- 
Kees Cook