On 04/26/2017 04:43 AM, David Gibson wrote:
> On Tue, Apr 25, 2017 at 04:06:17PM +0200, Cédric Le Goater wrote:
>> On 04/25/2017 03:31 PM, Peter Maydell wrote:
>>> On 25 April 2017 at 07:51, Cédric Le Goater <c...@kaod.org> wrote:
>>>> Currenlty, the code relies on the fact that open() handles NULL
>>>> filenames but that can cause an error with new clang:
>>>>
>>>> hw/core/loader.c:67:15: runtime error: null pointer passed as argument 1,
>>>> which is declared to never be null
>>>
>>> This isn't "new clang", incidentally, it's just clang with the
>>> runtime-static-analysis enabled, which causes warnings to be
>>> printed at runtime for undefined behaviours. You can enable
>>> this by passing configure --extra-cflags=-fsanitize=undefined .
>>> (I have clang 3.8.0 here.)
>>
>> OK. So I have now reproduced the issue on a f24. That made be
>> realize that the IPMI tests check for the arch they are being
>> run on and that more changes are required for them to run on
>> ppc64.
>>
>> We can drop patch 1/2. Tell me if you want a resend.
>
> No, that's fine. A patch to enable the tests on ppc properly ASAP
> would be great, though.
Yes, it would. I need to understand what is behind :
qtest_irq_intercept_in(...)
C.
