On 22/09/17 22:39, Arnd Bergmann wrote:
> On Fri, Sep 22, 2017 at 9:17 PM, Arnd Bergmann <arnd@xxxxxxxx> wrote:
>> On Fri, Sep 22, 2017 at 7:21 PM, Joe Perches <joe@xxxxxxxxxxx> wrote:
>>> On Fri, 2017-09-22 at 09:48 +0200, Arnd Bergmann wrote:
>>>> On Fri, Sep 22, 2017 at 1:11 AM, Colin Ian King
>>
>>>> text data bss dec hex filename
>>>> 18220 176 0 18396 47dc build/tmp/lib/lz4/lz4_decompress-after.o
>>>> 22297 0 0 22297 5719 build/tmp/lib/lz4/lz4_decompress-before.o
>>>
>>> Perhaps not so much a gcc bug as an opportunity
>>> for gcc to add an additional optimization.
>>>
>>> gcc would have to verify that the const array is
>>> not initialized with some variable or argument like:
>>>
>>> int foo(int a)
>>> {
>>> const int array[] = {1, a};
>>> ...
>>> }
>>
>> It depends. With a 10KB different in .text size, my guess is that this
>> is a case where gcc does the right optimization in principle, but
>> fails to do what was intended in some corner cases.
>
> I found the problem: "gcc -fsanitze=kernel-address --param asan-stack=1"
> produces lots of expensive checks here with gcc-5 or higher.
>
> Disabling it makes a big difference:
>
> upstream:
> gcc-7.0.0 --fsanitze=kernel-address --param asan-stack=1: 31789 bytes
> gcc-7.0.0: 16535 bytes
>
> patched:
> gcc-7.0.0 --fsanitze=kernel-address --param asan-stack=1: 20351 bytes
> gcc-7.0.0: 14490 bytes
>
> Arnd
>
Nice catch!
--
To unsubscribe from this list: send the line "unsubscribe kernel-janitors" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
