The same designer from the previous patch has told us to never read
FORCEWAKE. We only do this for the POSTING_READ(), so simply change that
to something within the same cacheline (for no reason in particular
other than it sounds nice). In the _mt case we can leverage
the gtfifodbg check for the POSTING_READ.
This partially reverts
commit 6af2d180f8
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu Jul 26 16:24:50 2012 +0200
drm/i915: fix forcewake related hangs on snb
v2: commit message, comments about posting read from (Daniel)
Note: vlv forcewake doesn't need any changes for this special
treatment since FORCEWAKE_VLV is in a totally different register
range, and the readback FORCEWAKE_ACK_VLV readback that follows is in
the same range.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Added note.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A designer familiar with the hardware has stated that the forcewake
timeout can theoretically be as high as a little over 1ms. Therefore we
modify our code to use 2ms (appropriate fudge and because we don't want
to round down).
Hopefully this can't prevent spurious timeouts.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Acked-by: Chris Wilson <chris@chris-wilson.oc.uk>
[danvet: again fix conflict with vlv patch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's used all over the place, and we want to be able to play around with
the value, apparently. Note that it doesn't touch other timeouts of the
same value (like gtfifo, and thread C0 wait).
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.oc.uk>
[danvet: fixup conflict with vlv forcewake patches.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
<ickle> danvet: in the force wake, both DRM_ERRORs have the same string.
<ickle> useful for .txt shrinkage, horrible for debugging
Acked-by: Paul Menzel <paulepanter@users.sourceforge.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For some odd reasons, the vlv forcewake code is rather different from
all other platforms, with no clear justification. Adjust things:
- Don't check whether the gt is awake already (and bail out early), we
need to grab a forcewake anyway. Otherwise the chip might go to
sleep too early. And this would also screw up our forcewake
accounting.
- Like all other platforms, check whether the gt has cleared the
forcewake bit in the _ACK register before setting it again.
- Use _MASKED_BIT_ENABLE/DISABLE macros
- Only use bit0 of the forcewake reg, not all 16 bits.
- check the gtfifodb reg like on all other platforms in _put.
- Drop the POSTING_READs for consistency.
v2: Failure to git add ... again.
v3: Fixup the spelling fail a bit.
Tested-by: "Purushothaman, Vijay A" <vijay.a.purushothaman@intel.com>
Tested-by: "Widawsky, Benjamin" <benjamin.widawsky@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We've had and still have too many issues where the gpu turbo doesn't
quite to what it's supposed to do (or what we want it to do).
Adding a tracepoint to track when the desired gpu frequency changes
should help a lot in characterizing and understanding problematic
workloads.
Also, this should be fairly interesting for power tuning (and
especially noticing when the gpu is stuck in high frequencies, as has
happened in the past) and hence for integration into powertop and
similar tools.
Cc: Arjan van de Ven <arjan@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Paul Menzel <paulepanter@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like with the equivalent change for gen6+ rps state, this helps in
clarifying the code (and in fixing a few places that have fallen through
the cracks in the locking review).
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes:
"New stuff for -next. Highlights:
- prep patches for the modeset rework. Note that one of those patches
touches the fb helper in the common drm code.
- hasw hdmi audio support (Wang Xingchao)
- improved instdone dumping for gen7 (Ben)
- unbound tracking and a few follow-up patches from Chris
- dma_buf->begin/end_cpu_access plus fix for drm/udl (Dave)
- improve mmio error reporting for hsw
- prep patch for WQ_NON_REENTRANT removal (Tejun Heo)
"
* 'for-airlied' of git://people.freedesktop.org/~danvet/drm-intel: (41 commits)
drm/i915: Remove __GFP_NO_KSWAPD
drm/i915: disable rc6 on ilk when vt-d is enabled
drm/i915: Avoid unbinding due to an interrupted pin_and_fence during execbuffer
drm/i915: Use new INSTDONE registers (Gen7+)
drm/i915: Add new INSTDONE registers
drm/i915: Extract reading INSTDONE
drm/i915: Use a non-blocking wait for set-to-domain ioctl
drm/i915: Juggle code order to ease flow of the next patch
drm/i915: Use cpu relocations if the object is in the GTT but not mappable
drm/i915: Extract general object init routine
drm/i915: Protect private gem objects from truncate (such as imported dmabuf)
drm/i915: Only pwrite through the GTT if there is space in the aperture
i915: use alloc_ordered_workqueue() instead of explicit UNBOUND w/ max_active = 1
drm/i915: Find unclaimed MMIO writes.
drm/i915: Add ERR_INT to gen7 error state
drm/i915: Cantiga+ cannot handle a hsync front porch of 0
drm/i915: fix reassignment of variable "intel_dp->DP"
drm/i915: Try harder to allocate an mmap_offset
drm/i915: Show pin count in debugfs
drm/i915: Show (count, size) of purgeable objects in i915_gem_objects
...
There was some merge conflicts in -next and they weren't so pretty, so
backmerge now to avoid them.
Conflicts:
drivers/gpu/drm/i915/i915_gem.c
drivers/gpu/drm/i915/intel_modes.c
It blows up. And hopefully this is the root-cause of the mysterious
rc6 related hang on ilk. For reference, the commit that enabled rc6 on
ilk again is:
commit 456470eb58
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Aug 8 23:35:40 2012 +0200
drm/i915: enable rc6 on ilk again
Reported-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Avoid stalling and waiting for the GPU by checking to see if there is
sufficient inactive space in the aperture for us to bind the buffer
prior to writing through the GTT. If there is inadequate space we will
have to stall waiting for the GPU, and incur overheads moving objects
about. Instead, only incur the clflush overhead on the target object by
writing through shmem.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
James Bottomley reported [1] a massive power regression, due to the
enabling of semaphores by default in 3.5. A workaround for him is to
again disable semaphores. And indeed, his system has a very hard time
to enter rc6 with semaphores enabled.
Ben Widawsky run around with a kill-a-watt a lot and noticed:
- There are indeed a few rare systems that seem to have a hard time
entering rc6 when desktop-idle.
- One machine, The Indestructible Toshiba regressed in this behaviour
between 3.5 and 3.6 in a merge commit! So rc6 behaviour with the
current setting seems to be highly timing dependent and not robust
at all.
- The behaviour James reported wrt semaphores seems to be a freak
timing thing that only happens on his specific machine, confirming
that enabling semaphores shouldn't reduce rc6 residency.
Now furthermore the Google ChromeOS guys reported [2] a while ago that
at least on some machines a simply a blinking cursor can keep the gpu
turbo at the highest frequency. This is because the current rps limits
used on snb/ivb are highly asymmetric.
On the theory that gpu turbo and rc6 tuning values are related, we've
tried whether the much saner looking (since much less asymmetric) rps
tuning values used for hsw would also help entering rc6 more robustly.
And it seems to mostly work, and we don't really have the resources to
through-roughly tune things in any better way: The values from the
ChromeOS ppl seem to fare a bit worse for James' machine, so I guess
we better stick with something vpg (the gpu hw/windows group)
provided, hoping that they've done their jobs.
Reference[1]: http://lists.freedesktop.org/archives/dri-devel/2012-July/025675.html
Reference[2]: http://lists.freedesktop.org/archives/intel-gfx/2012-July/018692.html
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=53393
Tested-by: Ben Widawsky <ben@bwidawsk.net>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEcBAABAgAGBQJQLWtvAAoJEHm+PkMAQRiG/DYH+wd0FqfEuYkYk4KPyAPuhKpX
zX7HYfLvyJE/ZYIdrhjq1E6Xm2KNr7gtX7/Rdzi2W38M9sjbYzwG1UGIw51qnxWy
yZJH9BGkfyQgQPeuDGohfB6DkDy2JWr2eqMDvakjOwgBsIzji0PQD/f3UvndhtUa
c+tTj/kjavHE1Yr2Wy6OnRZz3Uc0hIMn/Q0JqtbCs3LUgEV1KA4OEAe56XNz4Ku4
WE+FFaGFPvtriQsQON+ohPS5IC8jzQGK/0vbrJ4lWjFnZy4gvZXnborTOwD0WSQG
fbsNuxp1AaM2/pqfMwXm1w0ADvwOITHNiwwXf9id6DoK81QwTFpUdvKpn6yB6gQ=
=rurr
-----END PGP SIGNATURE-----
Merge tag 'v3.6-rc2' into drm-intel-next
Backmerge Linux 3.6-rc2 to resolve a few funny conflicts before we put
even more madness on top:
- drivers/gpu/drm/i915/i915_irq.c: Just a spurious WARN removed in
-fixes, that has been changed in a variable-rename in -next, too.
- drivers/gpu/drm/i915/intel_ringbuffer.c: -next remove scratch_addr
(since all their users have been extracted in another fucntion),
-fixes added another user for a hw workaroudn.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I have the faint hope that the total absence of any locking for the
rps code wasn't too good an idea and could very well have caused some
rc6 related regressions.
Unfortunately we've never managed to reproduce these issues on any of
our own machines, so the only way to go about this is to enable it and
see what happens.
While at it, kill some stale comments and improve the logging.
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We change the drps/ips sw/hw state from different callers: Our own irq
handler, the external intel-ips module and from process context. Most
of these callers don't take any lock at all.
Protect everything by making the mchdev_lock irqsave and grabbing it in
all relevant callsites. Note that we have to convert a few sleeps in the
drps enable/disable code to delays, but alas, I'm not volunteering to
restructure the code around a few work items.
For paranoia add a spin_locked assert to ironlake_set_drps, too.
v2: Move one access inside the lock protection. Caught by the
dev_priv->ips mass-rename ...
v3: Resolve rebase conflict.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's only ever a pointer to the global mchdev_lock, and we don't use
it at all.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This way it's easier so see what belongs together, and what is used
by the ilk ips code. Also add some comments that explain the locking.
Note that (cur|min|max)_delay need to be duplicated, because
they're also used by the ips code.
v2: Missed one place that the dev_priv->ips change caught ...
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Take the dev->struct_mutex around access the corresponding state
(and adjusting the rps hw state).
- Add an assert to gen6_set_rps to ensure we don't forget about this
in the future.
- Don't set up the min/max_freq files if it doesn't apply to the hw.
And do the same for the gen6+ cache sharing file while at it.
v2: Move the gen6+ checks into the read/write callbacks. Thanks to the
awesome drm midlayer we can't check that when registering the debugfs
files, because the driver is not yet fully set up, specifically the
->load callback hasn't run yet.
Oh how I despise this disaster ...
v3: Also add a WARN_ON(mutex_is_locked) in set_rps to check the
locking.
v4: Use mutex_lock_interruptible, suggested by Chris Wilson.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (for v2)
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The update_gfx_val function called from mark_busy wasn't taking the
mchdev_lock, as it should have. Also sprinkle a few spinlock asserts
over the code to document things better.
Things are still rather confusing, especially since a few variables
in dev_priv are used by both the gen6+ rps code and the ilk ips code.
But protected by totally different locks. Follow-on patches will clean
that up.
v2: Don't add a deadlock ... hence split up update_gfx_val into a
wrapper that grabs the lock and an internal __ variant for callsites
within intel_pm.c that already have taken the lock.
v3: Mark the internal helper as static, noticed by Ben Widawsky.
v4: Damien Lespiau had questions about the safety of the ips setup
sequence, explain in a comment why it works.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In commit
commit 20b46e59dd
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu Jul 26 11:16:14 2012 +0200
drm/i915: Only set the down rps limit when at the loweset frequency
The computation for the new desired frequency was extracted, but since
the desired frequency was passed-by value, the adjustments didn't
propgate back. Fix this.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... by adding seemingly redudant posting reads.
This little dragon lair exploded the first time around when we've
refactored the code a bit to use the common wait_for_atomic_us in
"drm/i915: Group the GT routines together in both code and vtable",
which caused QA to file fdo bug #51738.
Chris Wilson entertained a few approaches to fixing #51738: Replacing
the udelay(1) with the previously-used udelay(10) (or any other
"sufficiently larger" delay), adding a posting read, or ditching the
delay completely and using cpu_relax. We went with the cpu_relax and
"915: Workaround hang with BSD and forcewake on SandyBridge". Which
blew up in fdo bug #52424, but adding the posting read while still
using cpu_relax seems to also fix that, it looks like the
posting read is the important ingriedient to fix these rc6 related
hangs on snb.
Popular theories as to why this is like it is include:
- A herd of pink elephants got royally angered somehow.
- The gpu has internally different functional units and judging by the
register offsets, the forcewake request register and the forcewake
ack registers are _not_ in the same functional unit (or at least
aren't reached through the same routes). Hence the posting read
syncs up with the wrong block and gets the entire gpu confused.
- ...
As a minimal ducttape fix for 3.6, let's just put these posting reads
into place again. We can try fancier approaches (like adding back the
cpu_relax instead of the udelay) in -next.
This (re-)fixes a regression introduced in
commit 990bbdadab
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon Jul 2 11:51:02 2012 -0300
drm/i915: Group the GT routines together in both code and vtable
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Du Yan <yanx.du@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=52424
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51738u
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We believe to have squashed all issues around the gen6+ rps interrupt
generation and why the gpu sometimes got stuck. With that cleared up,
there's no user left for the sanitize_pm infrastructure, so let's just
rip it out.
Note that 'intel_reg_write 0xa014 0x13070000' is the w/a if we find
ourselves stuck again.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The power docs say that when the gt leaves rc6, it is in the lowest
frequency and only about 25 usec later will switch to the frequency
selected in GEN6_RPNSWREQ. If the downclock limit expires in that
window and the down limit is set to the lowest possible frequency, the
hw will not send the down interrupt. Which leads to a too high gpu
clock and wasted power.
Chris Wilson already worked on this with
commit 7b9e0ae6da
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat Apr 28 08:56:39 2012 +0100
drm/i915: Always update RPS interrupts thresholds along with
frequency
but got the logic inverted: The current code set the down limit as
long as we haven't reached it. Instead of only once with reached the
lowest frequency.
Note that we can't always set the downclock limit to 0, because
otherwise the hw will keep on bugging us with downclock request irqs
once the lowest level is reached.
For similar reasons also always set the upclock limit, otherwise the
hw might poke us again with interrupts.
v2: Chris Wilson noticed that the limit reg is also computed in
sanitize_pm. To avoid duplication, extract the code into a common
function.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As suggested by Daniel, rip out the independent timers for device and
crtc busyness and integrate the manual powermanagement of the display
engine into the GEM core and its request tracking. The benefits are that
the code is a lot smaller, fewer moving parts and should fit more neatly
into the overall activity tracking of the driver.
v2: Complete overhaul and removal of the racy timers and workers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This initializes power wells within the modeset_init_hw routine.
Testing has shown that this works for both driver load time and for
suspend-resume code paths.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There is little point waking up every 10ms to service an interrupt which
we then promptly ignore. So only program the the PMIER to enable
interrupts for those events which we do handle, not all of them!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Eugeni Dodonov <eugeni.dodonov@intel.com>
Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This pollutes dmesg output even if we do not have FBC for the device, so
move the DRM_DEBUG_KMS statement lower.
v2: just kill the message as suggested by Daniel.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
While creating the new enable/disable_gt_powersave functions in
commit 8090c6b9da
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Sun Jun 24 16:42:32 2012 +0200
drm/i915: wrap up gt powersave enabling functions
I've botched up the handling of ironlake_disable_rc6. Fix this up by
calling it at the right place. Note though that ironlake_disable_rc6
does a bit more than just disabling rc6 - it also tears down all the
allocated context objects.
Hence we need to move intel_teardown_rc6 out and directly call it from
intel_modeset_cleanup.
Also properly mark ironlake_enable_rc6 as static and kill the un-used
declaration in i915_drv.h.
Note: In review a question popped out why disable_rc6 also tears down
the backing object and why we should move that out - it's simply for
consistency with gen6+ rps code, which does it that way.
Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This commit moves force wake support routines into intel_pm modules, and
exports the gen6_gt_check_fifodbg routine (used in I915_READ).
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For Haswell, on some of the early hardware revisions, it is possible to
run into issues when RC6 state is enabled and when pipes change state.
v2: add comment saying that this is for early revisions only.
v3: beautify as suggested by Daniel Vetter.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is based on Ivy Bridge clock gating for now, but is subject to
changes in the future.
Note: Compared to the ivb clock gating this drops the the IDICOS
medium uncore sharing tuned in
commit 208482232d
Author: Ben Widawsky <ben@bwidawsk.net>
Date: Fri May 4 18:58:59 2012 -0700
drm/i915: set IDICOS to medium uncore resources
Eugeni wants to benchmark the effect of this first.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
[danvet: added note]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We weren't disabling RC6 bits when bringing down RPS.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It should be working so let's turn it on by default and catch any possible
issues faster.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just a cosmetic change to simplify the if statement.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Most of the RPS and RC6 enabling functionality is similar to what we had
on Gen6/Gen7, so we preserve most of the registers.
Note that Haswell only has RC6, so account for that as well. As suggested
by Daniel Vetter, to reduce the amount of changes in the patch, we still
write the RC6p/RC6pp thresholds, but those are ignored on Haswell.
Note: Some discussion about the nature of the new tuning constants
popped up in review - the answer is that we don't know why they've
changed, but the guide from VPG with the magic numbers simply has
different values now.
v2: Squash fix for ?: vs | operation precende bug into this patch.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Added note to commit message. Squashed fix.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tidy up the routines for interacting with the GT (in particular the
forcewake dance) which are scattered throughout the code in a single
structure.
v2: use wait_for_atomic for polling.
v3: *really* use wait_for_atomic for polling.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The enable functions grabbed dev->struct_mutex themselves, whereas
the disable functions expected dev->struct_mutex to be held by the
caller. Move the locking out to the (currently only) callsite of
intel_enable_gt_powersave to make this more consistent.
Originally this was prep work for future patches, but I've chased down
a totally wrong alley. Still, I think this is a sensible
clarification.
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of calling each one for each generation indiviudally.
Notice that we've already managed to be inconsistent, the resume path
is missing an IS_VLV check. As a nice benefit we can mark all the
platform specific enable/disable functions as static and hide them in
intel_pm.c
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Enable the on-chip messaging between the display engine and the GT.
v2: use bit definitions for DPFLIPSTAT reg
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Prevents a possible hang: WaDisableL3Bank2xClockGate.
v2: only apply to VLV, IVB doesn't need this anymore
References: https://bugs.freedesktop.org/show_bug.cgi?id=50245
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Another required workaround for a potential hang:
WaDisableTDLUnitClockGating.
v2: only apply this to VLV, IVB doesn't need it anymore (Eugeni)
References: https://bugs.freedesktop.org/show_bug.cgi?id=50245
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
According to the bspec for MBCTL:
Driver must set bit in the following scenarios:
- to realod teh h/w boot context every time it gets loaded through OS
- after an FLR clears the register (BIOS won't run afterwards)
References: https://bugs.freedesktop.org/show_bug.cgi?id=50237
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The RCBP workaround still applies on these chips, and we need VDS as well.
v2: remove MB boot fetch that snuck in (Daniel)
add workaround tags to comments for easier internal tracking (Daniel)
v3: only apply RCPB and VDS on SNB and VLV, IVB doesn't need them (Eugeni)
References: https://bugs.freedesktop.org/show_bug.cgi?id=50251
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I'm seeing about a 5% FPS improvement across various benchmarks on my
IVB i3. Rumor has it that the higher end parts show even more benefit.
This derives from a patch originally given to me by Bernard. The docs
are confusing about the definition names (ie. medium really seems like
max), but it would seem it gives more cache to the GT at the expense of
uncore. This configuration makes the split most in favor of the GT. I've
not tried the other IDICOS values.
Cc: "Kilarski, Bernard R" <bernard.r.kilarski@intel.com>
Acked-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we switch on/off the primary plane if it is completely obscured by an
overlapping video sprite, we also nee to make sure that we update the
FBC configuration at the same time.
v2: Not all crtcs are intel_crtcs, as spotted by Daniel.
v3: Boot testing rules.
References: https://bugs.freedesktop.org/show_bug.cgi?id=50238
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We still don't understand why this fails exactly, but if fails way
too often for a simple debug information. Furthermore the current
ducttape should prevent the gpu from getting stuck at low frequencies.
Hence tune down the dmesg noise.
Note that the known failure case is that the register read returns 0
when the gpu gets confused.
v2: Add comments about the known failure case.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Media turbo requests can either use RPVSWREQ or RPNSWREQ to indicate
what the interrupt handler should do. Since we only deal with the
latter in our turbo code, make the media engine use that for turbo
requests.
Cc: stable@vger.kernel.org.
Tested-by: Joe Bloggsian <joebloggsian@gmail.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In order to avoid missed down-interrupts when coming out of RC6, it is
advised that we always reset the down-threshold upon a PM event. This is
due to that the PM unit goes through a little dance when coming out of
RC6, it first brings the GPU up at the lowest frequency then a short
time later it restores the thresholds. During that interval, the
down-interval may expire and the interrupt be suppressed.
Now aware of the dance taking place within the GPU when coming out of
RC6, one wonders what other writes need to be queued in the fifo buffer
in order to be properly sequenced; setting the RP state appears to be
one.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=44006
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In many places we wish to iterate over the rings associated with the
GPU, so refactor them to use a common macro.
Along the way, there are a few code removals that should be side-effect
free and some rearrangement which should only have a cosmetic impact,
such as error-state.
Note that this slightly changes the semantics in the hangcheck code:
We now always cycle through all enabled rings instead of
short-circuiting the logic.
v2: Pull in a couple of suggestions from Ben and Daniel for
intel_ring_initialized() and not removing the warning (just moving them
to a new home, closer to the error).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Added note to commit message about the small behaviour
change, suggested by Ben Widawsky.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The line time can be programmed according to the number of horizontal
pixels vs effective pixel rate ratio.
v2: improve comment as per Chris Wilson suggestion
v3: incorporate latest changes in specs.
v4: move into wm update routine, also mention that the same routine can
program IPS watermarks. We do not have their enablement code yet, nor
handle the required clock settings at the moment, so this patch won't
program those values for now.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>