[Intel-gfx] [igt-dev] [PATCH i-g-t] i915/gem_create: Verify that all new objects are clear

[Chris Wilson]

Quoting Matthew Auld (2019-02-17 18:35:05)
> On Thu, 14 Feb 2019 at 18:32, Chris Wilson <chris at chris-wilson.co.uk> wrote:
> >
> > The kernel must not return stale information back to userspace when they
> > create a new object. For that purpose, we always clear objects on
> > creation, so verify that this is so.
> >
> > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > Cc: Matthew Auld <matthew.auld at intel.com>
> > ---
> >  tests/i915/gem_create.c | 71 +++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 71 insertions(+)
> >
> > diff --git a/tests/i915/gem_create.c b/tests/i915/gem_create.c
> > index 25c5e8088..9de2263d5 100644
> > --- a/tests/i915/gem_create.c
> > +++ b/tests/i915/gem_create.c
> > @@ -44,6 +44,7 @@
> >  #include <sys/stat.h>
> >  #include <sys/time.h>
> >  #include <getopt.h>
> > +#include <pthread.h>
> >
> >  #include <drm.h>
> >
> > @@ -141,6 +142,73 @@ static void invalid_nonaligned_size(int fd)
> >         gem_close(fd, handle);
> >  }
> >
> > +static uint64_t get_npages(uint64_t *global, uint64_t npages)
> > +{
> > +       uint64_t try, old, max;
> > +
> > +       max = *global;
> > +       do {
> > +               old = max;
> > +               try = npages % (max / 2);
> > +               max -= try;
> > +       } while ((max = __sync_val_compare_and_swap(global, old, max)) != old);
> > +
> > +       return try;
> > +}
> > +
> > +struct thread_clear {
> > +       uint64_t max;
> > +       int timeout;
> > +       int i915;
> > +};
> > +
> > +static void *thread_clear(void *data)
> > +{
> > +       struct thread_clear *arg = data;
> > +       int i915 = arg->i915;
> > +
> > +       igt_until_timeout(arg->timeout) {
> > +               uint32_t handle;
> > +               uint64_t npages;
> > +
> > +               npages = random();
> > +               npages <<= 32;
> > +               npages |= random();
> > +               npages = get_npages(&arg->max, npages);
> > +
> > +               handle = gem_create(i915, npages << 12);
> > +               for (uint64_t page = 0; page < npages; page++) {
> > +                       uint64_t x;
> > +
> > +                       gem_read(i915, handle,
> > +                                       page % (4096 - sizeof(x)),
> > +                                       &x, sizeof(x));
> 
> Don't we also want to read some values outside of the first page, or
> am I missing something?

No it was meant to be advancing each page, and then byte within page.

With the trivial page * 4096 + ...?
-Chris