As pointed out by Dan Carpenter, it was seemingly possible to hit an error
whilst mapping the buffer for the regs (except the only likely error
returns should not happen during init) and so leak a pin count on the
bo. To handle this we would need to reacquire the struct mutex, so for
simplicity rearrange for the lock to be held for the entire function.
For extra pedagogy, test that we only call init once.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Keith Packard <keithp@keithp.com>

When auditing the locking in i915_gem.c (for a prospective change which
I then abandoned), I noticed two places where struct_mutex is not held
across GEM object manipulations that would usually require it.

Since one is in initial setup and the other in driver unload, I'm
guessing the mutex is not required for either; but post a patch in case
it is.

Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Keith Packard <keithp@keithp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

The code paths for modesetting are growing in complexity as we may need
to move the buffers around in order to fit the scanout in the aperture.
Therefore we face a choice as to whether to thread the interruptible status
through the entire pinning and unbinding code paths or to add a flag to
the device when we may not be interrupted by a signal. This does the
latter and so fixes a few instances of modesetting failures under stress.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Dave Airlie spotted that we had a potential bug should we ever rearrange
the drm_i915_gem_object so not the base drm_gem_object was not its first
member. He noticed that we often convert the return of
drm_gem_object_lookup() immediately into drm_i915_gem_object and then
check the result for nullity. This is only valid when the base object is
the first member and so the superobject has the same address. Play safe
instead and use the compiler to convert back to the original return
address for sanity testing.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

We had some conversions over to the _PIPE macros, but didn't get
everything.  So hide the per-pipe regs with an _ (still used in a few
places for legacy) and add a few _PIPE based macros, then make sure
everyone uses them.

[update: remove usage of non-existent no-op macro]
[update 2: keep modesetting suspend/resume code, update to new reg names]
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[ickle: stylistic cleanups for checkpatch and taste]
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

A lot of minor tweaks to fix the tracepoints, improve the outputting for
ftrace, and to generally make the tracepoints useful again. It is a start
and enough to begin identifying performance issues and gaps in our
coverage.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

The bulk of the change is to convert the growing list of rings into an
array so that the relationship between the rings and the semaphore sync
registers can be easily computed.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

With this change, every batchbuffer can use all available fences (save
pinned and scanout, of course) without ever stalling the gpu!

In theory. Currently the actual pipelined update of the register is
disabled due to some stability issues. However, just the deferred update
is a significant win.

Based on a series of patches by Daniel Vetter.

The premise is that before every access to a buffer through the GTT we
have to declare whether we need a register or not. If the access is by
the GPU, a pipelined update to the register is made via the ringbuffer,
and we track the last seqno of the batches that access it. If by the
CPU we wait for the last GPU access and update the register (either
to clear or to set it for the current buffer).

One advantage of being able to pipeline changes is that we can defer the
actual updating of the fence register until we first need to access the
object through the GTT, i.e. we can eliminate the stall on set_tiling.
This is important as the userspace bo cache does not track the tiling
status of active buffers which generate frequent stalls on gen3 when
enabling tiling for an already bound buffer.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>

A glorified s/obj_priv/obj/ with a net reduction of over a 100 lines and
many characters!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

a00b10c360b35d6431a "Only enforce fence limits inside the GTT" also
added a fenceable/mappable disdinction when binding/pinning buffers.
This only complicates the code with no pratical gain:

- In execbuffer this matters on for g33/pineview, as this is the only
  chip that needs fences and has an unmappable gtt area. But fences
  are only possible in the mappable part of the gtt, so need_fence
  implies need_mappable. And need_mappable is only set independantly
  with relocations which implies (for sane userspace) that the buffer
  is untiled.

- The overlay code is only really used on i8xx, which doesn't have
  unmappable gtt. And it doesn't support tiled buffers, currently.

- For all other buffers it's a bug to pass in a tiled bo.

In short, this disdinction doesn't have any practical gain.

I've also reverted mapping the overlay and context pages as possibly
unmappable. It's not worth being overtly clever here, all the big
gains from unmappable are for execbuf bos.

Also add a comment for a clever optimization that confused me
while reading the original patch by Chris Wilson.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>