In order to accommodate the requirements of re-enabling FBC after
page-flipping, but to avoid doing so and incurring the cost of a wait
for vblank in the middle of a page-flip sequence, we defer the actual
enablement by 50ms. If any request to disable FBC arrive within that
interval, the enablement is cancelled and we are saved from blocking on
the wait.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Page-flipping updates the scanout address, nukes the FBC compressed
image and so forces an FBC update so that the displayed image remains
consistent. However, page-flipping does not update the FBC registers
themselves, which remain pointing to both the old address and the old
CPU fence. Future updates to the new front-buffer (scanout) are then
undetected!

This first approach to demonstrate the issue and highlight the fix,
simply disables FBC upon page-flip (a recompression will be forced on
every flip so FBC becomes immaterial) and then re-enables FBC in the
page-flip finish work function, so that the FBC registers are now
pointing to the new framebuffer and front-buffer rendering works once
more.

Ideally, we want to only re-enable FBC after page-flipping is complete,
as otherwise we are just wasting cycles and power (with needless
recompression) whilst the page-flipping application is still running.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=33487Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Persistent mode is intended for use with front-buffer rendering, such as
X, where it is necessary to detect writes to the scanout either by the
GPU or through the CPU's fence, and recompress the dirty regions on the
fly. (By comparison to the back-buffer rendering, the scanout is always
recompressed after a page-flip.)

References: https://bugs.freedesktop.org/show_bug.cgi?id=33487
References: https://bugs.freedesktop.org/show_bug.cgi?id=31742Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

...and this requirement is enforced by intel_update_fbc() so we can
remove the later check from g4x_enable_fbc() and ironlake_enable_fbc().
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

The cfb_pitch was only used for 8xx_enable_fbc(), every later routine
was just overwriting the value with itself thanks to a copy'n'paste
error.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

...to ensure that any pending FBC enable tasklet is cancelled.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

As the enable/disable routines will be gain additional complexity in
future patches, it is necessary that all callers do not bypass the
generic interface by calling into the chipset routines directly. to do
this we make the chipset routines static, so there is no choice.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

According to the hardware documentation, GDRST is exactly the same as on
Sandybridge.  So simply enable the existing code.
Signed-off-by: NKenneth Graunke <kenneth@whitecape.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

On sinks with a DPCD rev of 1.1 or greater, we can send sink power
management commands to address 0x600 per section 5.1.5 of the
DisplayPort 1.1a spec.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NKeith Packard <keithp@keithp.com>

When checking link status during a hot plug event or detecting sink
presence, we need to retry 3 times per the spec (section 9.1 of the 1.1a
DisplayPort spec).  Consolidate the retry code into a
native_aux_read_retry function for use by get_link_status and _detect.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NKeith Packard <keithp@keithp.com>

We currently use this when a hot plug event is received, only checking
the link status and re-training if we had previously configured a link.
However if we want to preserve the DP configuration across both hot plug
and DPMS events (which we do for userspace apps that don't respond to
hot plug uevents), we need to unconditionally check the link and try to
bring it up on hot plug.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NKeith Packard <keithp@keithp.com>

If ->detect is called too soon after a hot plug event, the sink may not
be ready yet.  So try up to 3 times with 1ms sleeps in between tries to
get the data (spec dictates that receivers must be ready to respond within
1ms and that sources should try 3 times).

See section 9.1 of the 1.1a DisplayPort spec.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NKeith Packard <keithp@keithp.com>

When a hotplug event is received, we need to check the receiver cap bits
in case they've changed (as they might with a hub or chain config).
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Makes it easier to search for DP related constants.
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Especially after a hotplug or power status change, the sink may not
reply immediately to a link status query.  So retry 3 times per the spec
to really make sure nothing is there.

See section 9.1 of the 1.1a DisplayPort spec.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NKeith Packard <keithp@keithp.com>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Now that we track bpp on a per-pipe basis, we can use the actual value
rather than assuming 24bpp.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

This will catch bad fb configs earlier.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

To properly drive a framebuffer with a new depth or bpp, dither settings
and link bandwidth calculations may change, so make sure we go through a
full mode set in that case.
Reported-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

The Intel HDMI encoder can support 8bpc or 12bpc.  Set the appropriate
value based on the pipe bpp when configuring the output.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

The pipe may be driving various bpp values depending on the display
configuration, so take that into account when calculating link bandwidth
requirements.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Updating the planes is device specific, so create a new display callback
and use it in pipe_set_base.  (In fact we could go even further, valid
display plane bits have changed with each generation, as has tiled
buffer handling.)
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Figuring out which pipe bpp to use is a bit painful.  It depends on both
the encoder and display configuration attached to a pipe.  For instance,
to drive a 24bpp framebuffer out to an 18bpp panel, we need to use 6bpc
on the pipe but also enable dithering.  But driving that same
framebuffer to a DisplayPort output on another pipe means using 8bpc and
no dithering.

So split out and enhance the code to handle the various cases, returning
an appropriate pipe bpp as well as whether dithering should be enabled.

Save the resulting pipe bpp in the intel_crtc struct for use by encoders
in calculating bandwidth requirements (defaults to 24bpp on pre-ILK).
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

This may not be the default value, so pull the bpc out of the pipe reg
and write it to the DP transcoder so proper dithering and signaling
occurs.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

This prevents us from setting reserved or incorrect bits on CougarPoint.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

These bits are reserved on ILK+ (ILK+ provides this feature in the
transcoder and pipe configuration instead, which we already set).
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Oh boy.  That was a bad gamble.  PDISP has changed.

This reverts commit cdf81a23.
Signed-off-by: NDave Airlie <airlied@redhat.com>

Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

In an attempt to fix 38862 and 38863.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Tested-by: NKenneth Graunke <kenneth@whitecape.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

CE variant requires a different chremap setup.

Fixes:
https://bugzilla.kernel.org/show_bug.cgi?id=35472Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Cc: stable@kernel.org
Signed-off-by: NDave Airlie <airlied@redhat.com>

This lets us make the various IRQ functions static and helps avoid
problems like the one fixed in "drm/i915: Use chipset-specific irq
installers" where one of the exported functions was called rather than
the chipset specific version.

This also fixes a UMS-mode bug -- the correct irq functions for IRL
and later chips were only getting loaded in the KMS path.
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NKeith Packard <keithp@keithp.com>

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

The vbios rom is >64k on a lot of modern asics.  Increase
the fetch size for atrm to make sure we don't miss part
of a larger rom.
Signed-off-by: NAlex Deucher <alexdeucher@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

They use the same register interfaces, so we can simply enable the
existing code on IVB.

v2:
  - resolve conflict with ring freq scaling, we can enable it too
v3:
  - resolve conflict again, this time on drm-intel-next
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Reported-by: NPavel Roskin <proski@gnu.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=38777
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Lots of register access in these functions, some of which requires the
struct mutex.

These functions now hold the struct mutex across the calls to
i915_save_display and i915_restore_display, and so the internal mutex
calls in those functions have been removed. To ensure that no-one else
was calling them (and hence violating the new required locking
invarient), those functions have been made static.

gen6_enable_rps locks the struct mutex, and so i915_restore_state
unlocks the mutex around calls to that function.
Reviewed-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Provide a parameter to disable hanghcheck. This is useful mostly for
developers trying to debug known problems, and probably should not be
touched by normal users.
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NKeith Packard <keithp@keithp.com>

The ring frequency scaling table tells the PCU to treat certain GPU
frequencies as if they were a given CPU frequency for purposes of
scaling the ring frequency.  Normally the PCU will scale the ring
frequency based on the CPU P-state, but with the table present, it will
also take the GPU frequency into account.

The main downside of keeping the ring frequency high while the CPU is
at a low frequency (or asleep altogether) is increased power
consumption.  But then if you're keeping your GPU busy, you probably
want the extra performance.

v2:
  - add units to debug table header (from Eric)
  - use tsc_khz as a fallback if the cpufreq driver doesn't give us a freq
    (from Chris)
v3:
  - fix comments & debug output
  - remove unneeded force wake get/put
Reviewed-by: NBen Widawsky <ben@bwidawsk.net>
Tested-by: NEric Anholt <eric@anholt.net>
Reviewed-by: NEric Anholt <eric@anholt.net>
Signed-off-by: NJesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: NKeith Packard <keithp@keithp.com>

Konstantin Belousov pointed out that 4697995b replaced the generic
i915_driver_irq_*install() functions with chipset specific routines
accessible only through driver->irq_*install(). So update the sanity
check in i915_request_wait() to match.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NKeith Packard <keithp@keithp.com>

The failure is as follows:

1. Userspace gets forcewake lock, lock count >=1
2. GPU hang/reset occurs (forcewake bit is reset)
3. count is now incorrect

The failure can only occur when using the forcewake userspace lock.

This has the unfortunate consequence of messing up the driver as well as
userspace, unless userspace closes the debugfs file, the kernel will
never end up waking the GT since the refcount will be > 1.

The solution is to try to recover the correct forcewake state based on
the refcount. There is a period of time where userspace reads/writes may
occur after the reset, before the GT has been forcewaked. The interface
was never designed to be a perfect solution for userspace reads/writes,
and the kernel portion is fixed by this patch.
Suggested-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NBen Widawsky <ben@bwidawsk.net>
Signed-off-by: NKeith Packard <keithp@keithp.com>