On 15 February 2017 at 14:14, Alex Bennée <alex.ben...@linaro.org> wrote: > I guess it would be easier to remove the asserts if we had run test > cases that explicitly exercised all this code. What are you currently > running to test this code?
The cover letter has a pointer to the tests I've been using (plus the usual "run a random stellaris image"). I think the benefit of the asserts is in warding off future bugs; so I think they're worth keeping where we know something should never happen but the code is complicated enough that perhaps a future patch might put things in a state where the impossible does happen. Also, number of assert()s is to some extent a coding style issue, and in this patchset I'm really taking Michael's code and doing a review/cleanup pass on it, so I've tried not to do too much rework of the "well I wouldn't have put quite this many asserts in" flavour. thanks -- PMM