Age | Commit message (Collapse) | Author | Files | Lines |
|
|
|
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
This will need to get modified when the ioctl expands, and so is only
here for reference/to make Daniel happy.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
By adding another testcase that follows up with a gpu read. This
checks whether the kernel properly tracks the pending write and
doesn't lose it (or sync up to the wrong seqno).
For some odd reason only the cpu mmap variant blows up, the gtt one
works here. I need to look into that some more.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
I must have checked in the wrong version the first time.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
so get rid of the remants. perhaps we'll use it again someday.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Only compile tested.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
this context test requiring libdrm updates
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
This wraps libdrm functionality to exec with contexts. This patch
shouldn't be applied until libdrm for contexts is updated.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
We want context APIs in order to use our super context test.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
In all fairness if the test worked, he would have found this earlier
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Due to the way we calculate the workload by doubling it each time we
might end up with almost twice as much as we want. Hence increase our
fudge by 1.5 to account for that.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50666
|
|
We need to hold forcewake lock in order to be able to read GT registers.
Otherwise, when the GPU is in RC6 mode, we'll read all zeros.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
|
|
This allows the tests to run on the prototype boards.
|
|
|
|
|
|
When looking at the pwrite/pread/wc performance, it is useful to judge
that against the performance of an ordinary CPU mmap.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
|
|
It didn't fail properly.
|
|
- call it sysfs_l3_parity for more consistency
- add .gitignore for intel_l3_parity
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
... with timeout=0. We have special code in the kernel to optimize
that one.
|
|
While we have that testcase, let's cross-check the busy ioctl.
|
|
Using BEGIN_BATCH can lead to a nice inf recursion through require_space
-> flush_batch -> BEGIN_BATCH.
Also fix things up to always require BATCH_RESERVED. We need 2 dwords
for the gen5 workaround and 2 dwords for MI_BB_END.
|
|
When I've first tried this it somehow failed, but I can't reproduce
this any more. I guess I've hunted a ghost.
|
|
duuh
|
|
|
|
- start at 1 iterations
- actually adjust the number of iterations like the comment claims
|
|
- widht/height are in pixel, and the cmd uses 32bit, so we need to
adjust this.
- we write to the buffer, set the right reloc domain.
|
|
also assign the timeout value unconditionally, we want to know it even
when we've timeout out.
|
|
... we need to do this libdrm depency dance. Or just copy&paste it.
|
|
Assures that signals interrupting the wait works properly. Because of
the scheduling around signals, interrupted waits will *seem* faster as
the GPU continues to work while all the CPU scheduling stuff happens.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
|
|
Oops, I've frobbed this to test the check but committed the wrong
version.
|
|
... so that it's easier to get the kernel configuration right.
|
|
We've broken this way too often in the past.
|
|
QA's test rig does that.
|
|
We want testcase to return non-zero if they fail ...
|
|
|
|
And bring back some frame indication that actually works.
|
|
We should get more kms tests soon, and not needing to copy-paste a
nice test pattern should be useful.
That establishes a firm depency of i-g-t on cairo over everything, but
I don't care so much about that.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
And fix it up to not leak open fds, which kills all the master only
stuff.
|