On the preinstall stage we should just disable all the interrupts, but
we currently enable all the south display interrupts due to the way we
touch SDEIER at the IRQ handlers (note: they are still masked and our
IRQ handler is disabled). Instead of doing that, let's make the
preinstall stage just disable all the south interrupts, and do the
proper interrupt dance/ordering at the postinstall stage, including an
assert to check if everything is behaving as expected.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
After all, we call ibx_irq_preinstall from gen8_irq_preinstall.
v2: - Rebase.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just like ibx_irq_preinstall. We'll call this from somewhere else in
the next patch.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The duplicate was at an _uninstall function, so rename it to
gen5_gt_irq_reset.
v2: - Rebase.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Same as SERR_INT and the other IIR registers: reset on
preinstall/uninstall and WARN for non-zero values at postinstall. This
one also doesn't need double-clear.
v2: - Remove the is_zero assertion (Ben).
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The SERR_INT register is very similar to the other IIR registers, so
let's zero it at preinstall/uninstall and WARN for a non-zero value at
postinstall, just like we do with the other IIR registers. For this
one, there's no need to double-clear since it can't store more than
one interrupt.
v2: - Remove the is_zero assertion (Ben).
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It should already be masked and disabled and zeroed at the preinstall
and uninstall stages. Also, the current code just writes to IIR once,
and this is not a guarantee that it will be cleared, so it's wrong
anyway.
The whole reason for the paranoia is that we're going to start calling
the IRQ preinstall/postinstall/uninstall from the runtime PM
callbacks, so we need to make sure everything is behaving as expected.
v2: - Change the original DRM_ERROR to WARN and clear IIR in case it's
not zero (Ben).
- Improve commit message (Daniel).
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And the equivalent GEN8_IRQ_INIT_NDX macro. These macros are for the
postinstall functions. The next patch will improve this macro.
v2: - Adjust to the new POSTING_READ scheme (Ben).
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The IRQ_INIT and IRQ_FINI macros are basically the same thing, with
the exception that IRQ_FINI doesn't properly clear IIR twice and
doesn't have as many POSTING_READs as IRQ_INIT. So rename the INIT
macro to IRQ_RESET and use it everywhere.
v2: - Fix error in the commit message (Chris).
- Adjust to the new POSTING_READ scheme (Ben).
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's the only thing missing, apparently.
v2: - Fix typo (Ben).
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Same as the _INIT macro: the goal is to reuse the GEN8 macros, but
there are still some slight differences.
v2: - Rebase.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And rename it to GEN5_IRQ_INIT.
We have discussed doing equivalent changes on July 2013, and I even
sent a patch series for this: "[PATCH 00/15] Unify interrupt register
init/reset". Now that the BDW code was merged, I have one more
argument in favor of these changes.
Here's what really changes with the Gen 5 IRQ init code:
- We now clear the IIR registers at preinstall (they are also
cleared at postinstall, but we will change that later).
- We have an additional POSTING_READ at the IMR register.
v2: - Fix typo in commit message.
- Add POSTING_READ calls to the macros (Ben, Daniel, Jani).
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This interrupt gets initialized with a different IER value, so it was
not using the macro. The problem is that we plan to modify the macro
to make it do additional things, and we want the SDE interrupts
updated too. So let's make sure we call the macro, then, after it, we
do the necessary SDE-specific changes.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The goal is to reuse the GEN8 macros, but a few changes are needed, so
let's make things easier to review.
I could also use these macros on older code, but since I plan to
change how the interrupts are initialized, we'll risk breaking the
older code in the next commits, so I'll leave this out for now.
v2: - Rebase.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Pull all the gmch platform hotplug interrupt handling into one
function.
v2: Move the IIR check to the caller
s/drm_i915_private_t/struct drm_i915_private/
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add posting read comment suggested by Chris.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Extract all this logic into a new helper function
semaphore_wait_to_signaller_ring because:
- The current code has way too much magic.
- The current code doesn't look at bi16, which encodes VECS signallers
on HSW. Those are just added after the fact, so can't be encoded in
a neat formula.
- The current logic can't blow up since it limits its value range
sufficiently, but that's a bit too tricky to rely on in my opinion.
Especially when we start to add bdw support.
- I'm not a big fan of the explicit ring->semaphore_register list, but
I think it's more robust to use the same mapping both when
constructing the semaphore commands and when decoding them.
- Finally add a FIXME comment about lack of broadwell support here,
like in the earlier ipehr semaphore cmd detection function.
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
[danvet: Actually drop the untrue claim in the commit message Chris
pointed out.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently not an issue since we don't emit sempahores, but better
not forget about those.
As a little prep work extract the ipehr decoding for cleaner control
flow. And apply a bit of polish.
Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Also drop any unnecessary casts. No functional changes.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This reverts commit 2754436913.
Conflicts:
drivers/gpu/drm/i915/i915_irq.c
The partial application of interrupt masking without regard to other
pathways for adjusting the RPS frequency results in completely disabling
the PM interrupts. This leads to excessive power consumption as the GPU
is kept at max clocks (until the failsafe mechanism fires of explicitly
downclocking the GPU when all requests are idle). Or equally as bad for
the UX, the GPU is kept at minimum clocks and prevented from upclocking
in response to a requirement for more power.
Testcase: pm_rps/blocking
Cc: Deepak S <deepak.s@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by:Deepak S <deepak.s@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTOOOnAAoJEHm+PkMAQRiGsBAH/2PAOL3TbOG6tEedxQrTwsr2
muRIRTVWawjT8/npbHupxGnAyAVdmdffBHpmCmcftKdKNryT3YZW8/JWoYc+WSlo
3vTDJHDOYAe6yCBjjhYwcu150THBQdOymOi5mbbclo0XWYG18jd3+abYprRH6SiD
XqNSzYqoiv91JHBAWKBIpo1cyRDuwoM7+jZ7gX41r2800EL7loY3e08cPDDNU6HA
CKaLXMwLwYTefE+Wnr+4UUr08NbNBbBUKLUSXVqKKIpd+MtbyhV1SnWzz8VQSkag
K/uzsnGnE7nrqoepMSx3nXxzOWxUSY2EMbwhEjaKK4xBq9C9pzv3sG/o2/IyopU=
=Nuom
-----END PGP SIGNATURE-----
Merge tag 'v3.14' into drm-intel-next-queued
Linux 3.14
The vt-d w/a merged late in 3.14-rc needs a bit of fine-tuning, hence
backmerge.
Conflicts:
drivers/gpu/drm/i915/i915_gem_gtt.c
drivers/gpu/drm/i915/intel_ddi.c
drivers/gpu/drm/i915/intel_dp.c
All trivial adjacent lines changed type conflicts, so trivial git
doesn't even show them in the merg commit.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As Broadwell has an increased virtual address size, it requires more
than 32 bits to store offsets into its address space. This includes the
debug registers to track the current HEAD of the individual rings, which
may be anywhere within the per-process address spaces. In order to find
the full location, we need to read the high bits from a second register.
We then also need to expand our storage to keep track of the larger
address.
v2: Carefully read the two registers to catch wraparound between
the reads.
v3: Use a WARN_ON rather than loop indefinitely on an unstable
register read.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Timo Aaltonen <tjaalton@ubuntu.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Drop spurious hunk which conflicted.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we use different rps events for different platforms or due to wa,
we might end up needing this logic in a lot of places. Instead of
this let's use a variable in dev_priv to track the enabled PM
interrupts.
v2: Initialize pm_rps_events in intel_irq_init() (Ville).
Signed-off-by: Deepak S <deepak.s@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Frob the commit message a bit since the English was a bit too
garbled ;-) ]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There's an entire pile of issues in here:
- Use the main RING_HEAD register, not ACTHD. ACTHD points at the gtt
offset of the batch buffer when a batch is executed. Semaphores are
always emitted to the main ring, so we always want to look at that.
- Mask the obtained HEAD pointer with the actual ring size, which is
much smaller. Together with the above issue this resulted us in
trying to dereference a pointer way outside of the ring mmio
mapping. The resulting invalid access in interrupt context
(hangcheck is executed from timers) lead to a full blown kernel
panic. The fbcon panic handler then tried to frob our driver harder,
resulting in a full machine hang at least on my snb here where I've
stumbled over this.
- Handle ring wrapping correctly and be a bit more explicit about how
many dwords we're scanning. We probably should also scan more than
just 4 ...
- Space out some of teh computations for readability.
This reduces hard-hangs on my snb here. Mika and QA both say that it
doesn't completel remove them, but at least for me it's a clear
improvement in stability.
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
References: https://bugs.freedesktop.org/show_bug.cgi?id=74100
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The names of the struct members for RPS are stupid. Every time I need to
do anything in this code I have to spend a significant amount of time to
remember what it all means. By renaming the variables (and adding the
comments) I hope to clear up the situation. Indeed doing this make some
upcoming patches more readable.
I've avoided ILK because it's possible that the naming used for Ironlake
matches what is in the docs. I believe the ILK power docs were never
published, and I am too lazy to dig them up.
v2: leave rp0, and rp1 in the names. It is useful to have these limits
available at times. min_freq and max_freq (which may be equal to rp0, or
rp1 depending on the platform) represent the actual HW min and max.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When other platforms add runtime PM support they will also need to
disable interrupts, so move the variable to the runtime PM struct.
Also notice that the longer-term goal is to completely kill the
regsave struct, and I even have patches for that.
v2: - Rebase.
v3: - Rebase.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Conflicts:
drivers/gpu/drm/i915/Makefile
Makefile cleanup in drm-intel-next conflicts with a build-fix to move
intel_opregion under CONFIG_ACPI.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We need to enable interrupt processing before all the modeset
state is set up. But that means we can fall over when we get a pipe
underrun. This shouldn't happen as long as the bios works correctly
but as usual this turns out to be wishful thinking.
So disable error interrupts at irq install time and rely on the
re-enabling code in the modeset functions to take care of this.
Note that due to the SDE interrupt handling race we must
uncondtionally enable all interrupt sources in SDEIER, hence no need
to enable the SERR bit specifically.
On gmch platforms we don't have an explicit enable/mask bit for fifo
underruns. Fixing this up would require a bit of software tracking,
hence is material for a separate patch. To make this possible we need
to switch all gmch platforms to the new pipestat interrupt handling
scheme Imre implemented for vlv, and then also add a safe form of sw
state checking to __cpu_fifo_underrun_reporting_enabled a bit.
v2: Also handle the ilk/snb cpu fifo underrun bits accordingly.
Spotted by Ville.
v3: Also handle the south interrupt underrun bits on ibx. Again
spotted by Ville.
Reported-by: Rob Clark <robdclark@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: stable@vger.kernel.org
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
The display interrupts changed on BDW, so the current ILK-HSW specific
code in ilk_pipe_in_vblank_locked() doesn't work there. Add the required
bits for BDW, and while at it, change the existing code to use nicer
looking vblank status bit macros.
Also remove the now stale __raw_i915_read16() definition which was
left over from the failed gen2 ISR experiment.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=73962
Tested-by: Lu Hua <huax.lu@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
On HSW the scanline counter seems to behave differently depending on
the output type. eDP on port A does what you would expect an the normal
+1 fixup is sufficient to cover it. But on HDMI outputs we seem to need
a +2 fixup. Just assume we always need the +2 fixup and accept the
slight inaccuracy on eDP.
This fixes a regression introduced in:
commit 8072bfa604
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon Oct 28 21:22:52 2013 +0200
drm/radeon: Move the early vblank IRQ fixup to radeon_get_crtc_scanoutpos()
That commit removed the heuristic that tried to fix up the timestamps
for vblank interrupts that fire a bit too early. Since then the vblank
timestamp code would treat some vblank interrupts as spurious since the
scanline counter would indicate that vblank_start wasn't reached yet.
That in turn lead to incorrect vblank event sequence numbers being
reported to userspace, which lead to unsteady framerate in applications
such as XBMC which uses them for timing purposes.
v2: Remember to call ilk_pipe_in_vblank_locked() on HSW too (Mika)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=75725
Tested-by: bugzilla1@gmx.com
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Introduced in
commit e0e33f8ff6f0b6d286afc314802be4993341bd47
Author: Imre Deak <imre.deak@intel.com>
Date: Tue Mar 4 19:23:07 2014 +0200
The impact was luckily minimal, due to the extra check we do against a
software pipestat IRQ mask.
Caught by Fengguang's 0-day tester.
Cc: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJTHSaRAAoJEHm+PkMAQRiG7G8IAJHElwFDNSQE7Y9MmbicrAMG
kfjhBtBpTaVrJKQXegCNUwDaLLyC4oLIxDheW84oPXbrEGDLqPtBov/hrcFkHVr4
lh/ZYk02nYtcfpN0JnL/Yj2oKHVmBWs0vFlM7StSFsJCj10DoCVQQdmAJ8XODTPo
CXMapk+UikTX1TlIO8+B5toyl3R1OqPmW211UV1vQVLKy66hu+MKVN/V+/EyopL0
1jO81EDpaRaeIJh1/okcyUoIq9pqLkAWNpeQ7uyXZ+Sfivt9RXwLYKmAB3lP20Hc
ZMIIoHSCyYRFjxLlQvt02bA9nY4wTY7YN5kZ2kk65y7TFfhcGsCw1Sc69iyCoKs=
=CJcA
-----END PGP SIGNATURE-----
Merge tag 'v3.14-rc6' into drm-intel-next-queued
Linux 3.14-rc6
I need the hdmi/dvi-dual link fixes in 3.14 to avoid ugly conflicts
when merging Ville's new hdmi cloning support into my -next tree
Conflicts:
drivers/gpu/drm/i915/Makefile
drivers/gpu/drm/i915/intel_dp.c
Makefile cleanup conflicts with an acpi build fix, intel_dp.c is
trivial.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Based on an early draft from Jesse.
Add support for powering on/off the dynamic power wells on VLV by
registering its display and dpio dynamic power wells with the power
domain framework.
For now power on all PHY TX lanes regardless of the actual lane
configuration. Later this can be optimized when the PHY side setup
enables only the required lanes. Atm, it enables all lanes in all
cases.
v2:
- undef function local COND macro after its last use (Ville)
- Take dev_priv->irq_lock around the whole sequence of
intel_set_cpu_fifo_underrun_reporting_nolock() and
valleyview_disable_display_irqs(). They are short and releasing
the lock in between only makes proving correctness more difficult.
- sanitize local var names in vlv_power_well_enabled()
v3:
- rebase on latest -nightly
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: Resolve conflict due to my changes in the previous patch.
Also throw in an assert_spin_locked for safety. And finally appease
checkpatch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Needed by the next patch, wanting to set the underrun reporting as part
of a bigger dev_priv->irq_lock'ed sequence.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: Use more customary __ prefix instead of _nolock postfix.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We'll need to disable/re-enable the display-side IRQs when turning
off/on the VLV display power well. Factor out the helper functions
for this. For now keep the display IRQs enabled by default, so the
functionality doesn't change. This will be changed to enable/disable
the IRQs on-demand when adding support for VLV power wells in an
upcoming patch.
v2:
- take the irq spin lock for the whole enable/disable sequence as
these can be called with interrupts enabled
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is a left-over from
commit b7e634cc8d
Author: Imre Deak <imre.deak@intel.com>
Date: Tue Feb 4 21:35:45 2014 +0200
drm/i915: vlv: don't unmask IIR[DISPLAY_PIPE_A/B_VBLANK] interrupt
where we stopped unmasking the vblank IRQs, but left them enabled in the
IER register. Disable them in IER too.
v2:
- remove comment becoming stale after this change (Ville)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Consistency throughout the code base is good and remove some room for
mistakes (as explained in the "drm/i915: Use a pipe variable to cycle
through the pipes" commit)
So, let's replace the for_each_pipe(i) occurences by for_each_pipe(pipe)
when it's reasonable and practical to do so (eg. when there isn't another
pipe variable already).
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-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>
We capture error state not only when the GPU hangs but also on
other situations as in interrupt errors and in situations where
we can kick things forward without GPU reset. There will be log
entry on most of these cases. But as error state capture might be
only thing we have, if dmesg was not captured. Or as in GEN4 case,
interrupt error can trigger error state capture without log entry,
the exact reason why capture was made is hard to decipher.
v2: Split out the the error code stuff to separate patch (Ben)
References: https://bugs.freedesktop.org/show_bug.cgi?id=74193
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Fix the execbuf rebind performance regression due to topic/ppgtt (Chris).
- Fix up the connector cleanup ordering for sdvod i2c and dp aux devices (Imre).
- Try to preserve the firmware modeset config on driver load. And a bit of prep
work for smooth takeover of the fb contents (Jesse).
- Prep cleanup for larger gtt address spaces on bdw (Ben).
- Improve our vblank_wait code to make hsw modesets faster (Paulo).
- Display debugfs file (Jesse).
- DRRS prep work from Vandana Kannan.
- pipestat interrupt handler to fix a few races around vblank/pageflip handling
on byt (Imre).
- Improve display fuse handling for display-less SKUs (Damien).
- Drop locks while stalling for the gpu when serving pagefaults to improve
interactivity (Chris).
- And as usual piles of other improvements and small fixes all over.
* tag 'drm-intel-next-2014-02-14' of ssh://git.freedesktop.org/git/drm-intel: (65 commits)
drm/i915: fix NULL deref in the load detect code
drm/i915: Only bind each object rather than for every execbuffer
drm/i915: Directly return the vma from bind_to_vm
drm/i915: Simplify i915_gem_object_ggtt_unpin
drm/i915: Allow blocking in the PDE alloc when running low on gtt space
drm/i915: Don't allocate context pages as mappable
drm/i915: Handle set_cache_level errors in the status page setup
drm/i915: Don't pin the status page as mappable
drm/i915: Don't set PIN_MAPPABLE for legacy ringbuffers
drm/i915: Handle set_cache_level errors in the pipe control scratch setup
drm/i915: split PIN_GLOBAL out from PIN_MAPPABLE
drm/i915: Consolidate binding parameters into flags
drm/i915: sdvo: add i2c sysfs symlink to the connector's directory
drm/i915: sdvo: fix error path in sdvo_connector_init
drm/i915: dp: fix order of dp aux i2c device cleanup
drm/i915: add unregister callback to connector
drm/i915: don't reference null pointer at i915_sink_crc
drm/i915/lvds: Remove dead code from failing case
drm/i915: don't preserve inherited configs with nothing on v2
drm/i915/bdw: Split up PPGTT cleanup
...
Apparently we've missed a few more than what Fengguang's 0-day tester
recently reported in i915_irq.c ... Makes sparse happy again (ignore
some spurious stuff about ksyms of exported functions).
Cc: kbuild test robot <fengguang.wu@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Yet more steps towards atomic modeset from Ville.
- DP panel power sequencing improvements from Paulo.
- irq code cleanups from Ville.
- 5.4 GHz dp lane clock support for bdw/hsw from Todd.
- Clock readout support for hsw/bdw (aka fastboot) from Jesse.
- Make pipe underruns report at ERROR level (Ville). This is to check our
improved watermarks code.
- Full ppgtt support from Ben for gen7.
- More fbc fixes and improvements from Ville all over the place, unfortunately
not yet enabled by default on more platforms.
- w/a cleanups from Ville.
- HiZ stall optimization settings (Chia-I Wu).
- Display register mmio offset refactor patch from Antti.
- RPS improvements for corner-cases from Jeff McGee.
* tag 'drm-intel-next-2014-02-07' of ssh://git.freedesktop.org/git/drm-intel: (166 commits)
drm/i915: Update rps interrupt limits
drm/i915: Restore rps/rc6 on reset
drm/i915: Prevent recursion by retiring requests when the ring is full
drm/i915: Generate a hang error code
drm/i915: unify FLIP_DONE macro names
drm/i915: vlv: s/spin_lock_irqsave/spin_lock/ in irq handler
drm/i915: factor out valleyview_pipestat_irq_handler
drm/i915: vlv: don't unmask IIR[DISPLAY_PIPE_A/B_VBLANK] interrupt
drm/i915: Reorganize display pipe register accesses
drm/i915: Treat using a purged buffer as a source of EFAULT
drm/i915: Convert EFAULT into a silent SIGBUS
drm/i915: release mutex in i915_gem_init()'s error path
drm/i915: check for oom when allocating private_default_ctx
drm/i915/vlv: WA to fix Voltage not getting dropped to Vmin when Gfx is power gated.
drm/i915: Get rid of acthd based guilty batch search
drm/i915: Use hangcheck score to find guilty context
drm/i915: Drop WaDisablePSDDualDispatchEnable:ivb for IVB GT2
drm/i915: Fix IVB GT2 WaDisableDopClockGating and WaDisablePSDDualDispatchEnable
drm/i915: Don't access snooped pages through the GTT (even for error capture)
drm/i915: Only print information for filing bug reports once
...
Conflicts:
drivers/gpu/drm/i915/intel_dp.c
Just a bit of polish which I hope will help me with massaging some
internal patches to use Imre's reworked pipestat handling:
- Don't check for underrun reporting or enable pipestat interrupts
twice.
- Frob the comments a bit.
- Do the iir PIPE_EVENT to pipe mapping explicitly with a switch. We
only have one place which does this, so better to make it explicit.
v2: Ville noticed that I've broken the logic a bit with trying to
avoid checking whether we're interested in a given pipe twice. push
the PIPESTAT read down after we've computed the mask of interesting
bits first to avoid that duplication properly.
v3: Squash in fixups from Imre on irc.
Cc: Imre Deak <imre.deak@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Atm we call the handlers for pending pipestat interrupt events even if
they aren't explicitly enabled by i915_enable_pipestat(). This isn't an
issue for events other than the vblank start event, since those are
always enabled anyways. Otoh, we enable the vblank start event
on-demand, so we'll end up calling the vblank handler at times when they
are disabled.
I haven't checked if this causes any real problem, but for consistency
and to remove some overhead we should still fix this by clearing /
handling only the enabled interrupt events. Also this is a dependency
for the upcoming VLV power domain patchset where we need to disable all
the pipestat interrupts whenever the display power well is off.
v2:
- inline the status->enable mask mapping (Ville)
- don't check for invalid PSR bit on platforms other than VLV (Ville)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Frob conflict due to different merge order.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
At least on VLV we can't get at the pipestat status bits by simply right
shifting the corresponding enable bits. The mapping between enable and
status bits for the sprite0,1 flip done and the PSR events don't follow
this rule, so we need to map them separately.
The PSR enable for pipe A is DPFLIPSTAT[22], but I haven't added support
for this, since there is no user of it atm. Until support is added WARN
if someone tries to enable PSR interrupts, or tries to enable the same
(1 << 6) bit on pipe B, which MBZ.
v2:
- inline the status->enable mask mapping (Ville)
- fix bogus use of status bits in enable mask (Ville)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There isn't any PSR interrupt enable bit for pipe A, so we couldn't
enable it through the current API. Passing the corresponding status bits
solves this and also makes the mapping between enable and status bits
simpler on VLV (addressed in an upcoming patch).
Except of checking for invalid status bit arguments, no functional
change.
v2: split out the low level parts of i915_enable_pipestat accepting
separate enabled and status masks, to make the non-standard mapping
between those masks stand out more (added in the next patch)
(Jesse,Daniel)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we make sure that all the dev_priv->info usages are wrapped by
INTEL_INFO(), we can easily modify the ->info field to be structure and
not a pointer while keeping the const protection in the INTEL_INFO()
macro.
v2: Rebased onto latest drm-nightly
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We don't have all the drm_crtc&co hanging around in that case.
This regression has been introduced in
commit 391f75e2bf
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed Sep 25 19:55:26 2013 +0300
drm/i915: Fix pre-CTG vblank counter
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=69521
Cc: stable@vger.kernel.org (for 3.13 only)
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
s/FLIPDONE/FLIP_DONE/ to make all FLIP_DONE macro names consistent.
No functional change.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This will be used by other platforms too, so factor it out.
The only functional change is the reordeing of gmbus_irq_handler() wrt.
the hotplug handling, but since it only schedules a work, it isn't an
issue.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: Don't keep on using the private_t typedef.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Bspec and the code suggests that the interrupt signaled by IIR[7,5]
(DISPLAY_PIPE_A/B_VBLANK) is a first level IRQ flag for the second
level PIPEA/BSTAT[2] (Start of Vertical Blank) interrupt. Measuring
the relative timings of when IIR[7] and PIPEASTAT[1,2] get set and
checking the effect of unmasking different pipestat and IIR events
shows that this isn't so:
First, ISR/IIR[7] gets set independently of PIPEASTAT[18] (Start of
Vertical Blank Enable) or any other pipestat enable bit, so it isn't
a first level IRQ bit showing the state of PIPEASTAT[2], but is
connected directly to the timing generator.
Second, setting only PIPEASTAT[18] and leaving all other pipestat events
disabled, IIR[6] (DISPLAY_PIPE_A_EVENT) gets set close to the moment when
PIPEASTAT[2] gets set, so the former is a first level interrupt flag for
the latter. The bspec is rather unclear about this, but I also assume
that IIR[6] signals all pipestat A events, except PIPEASTAT[31] (FIFO
Under-run Status).
Third, IIR[7] is set close to the moment when PIPEASTAT[1] (Framestart
Interrupt) gets set, in the mode I used about 12usec after PIPEASTAT[2]
and IIR[6] gets set. This means the IIR[7] isn't marking the start of
vblank, but rather signals the framestart event.
Based on the above, we don't need to unmask IIR[7] when waiting for
start of vblank events, but we can rely on IIR[6] being always unmasked,
which will signal when PIPEASTAT[2] gets set. Doing this will also get
rid of the overhead of getting an interrupt and servicing IIR[7], which
is atm raised always some time after IIR[6]/PIPEASTAT[2] is raised.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we enter RC6 and GFX Clocks are off, the voltage remains higher
than Vmin. When we try to set the freq to RPn, it might fail since the
Gfx clocks are down. So to fix this in Gfx idle, Bring the GFX clock up
and set the freq to RPn then move GFx down.
v2: remove vlv_update_rps_cur_delay function. Update commit message (Daniel)
v3: Fix the timeout during wait for gfx clock (Jesse)
v4: addressed comments on set freq and punit wait (Ville)
v5: use wait_for while waiting for GFX clk to be up. (Daniel)
update cur_delay before requesting min_delay. (Ville)
v6: use wait_for while waiting for punit. (Ville)
Signed-off-by: Deepak S <deepak.s@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With full ppgtt using acthd is not enough to find guilty
batch buffer. We get multiple false positives as acthd is
per vm.
Instead of scanning which vm was running on a ring,
to find corressponding context, use a different, simpler,
strategy of finding batches that caused gpu hang:
If hangcheck has declared ring to be hung, find first non complete
request on that ring and claim it was guilty.
v2: Rebase
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=73652
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When current delay is already at max delay, Let's disable the PM UP
THRESHOLD INTRRUPTS, so that we will not get further interrupts until
current delay is less than max delay, Also request for the PM DOWN
THRESHOLD INTRRUPTS to indicate the decrease in clock freq. and
viceversa for PM DOWN THRESHOLD INTRRUPTS.
v2: Use bool variables (Daniel)
v3: Fix Interrupt masking bit (Deepak)
v4: Use existing symbolic constants in i915_reg.h (Daniel)
v5: Add pm interrupt mask after new_delay calculation (Ville)
Signed-off-by: Deepak S <deepak.s@intel.com>
[danvet: Pass new_delay by value as suggested by Ville. Also appease
checkpatch.]
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With 20+ module parameters, I think referring to them via a struct
improves clarity over just having a bunch of globals. While at it, move
the parameter initialization and definitions into a new file
i915_params.c to reduce clutter in i915_drv.c.
Apart from the ill-named i915_enable_rc6, i915_enable_fbc and
i915_enable_ppgtt parameters, for which we lose the "i915_" prefix
internally, the module parameters now look the same both on the kernel
command line and in code. For example, "i915.modeset".
The downsides of the change are losing static on a couple of variables
and not having the initialization and module_param_named() right next to
each other. On the other hand, all module parameters are now defined in
one place at i915_params.c. Plus you can do this to find all module
parameter references:
$ git grep "i915\." -- drivers/gpu/drm/i915
v2:
- move the definitions into a new file
- s/i915_params/i915/
- make i915_try_reset i915.reset, for consistency
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I want to see these without having full debugs enabled.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: fix the gen8 irq handler as spotted by Paulo in his review.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently we print all pipe underruns on GMCH platforms. Hook up the
same logic we use on PCH platforms where we disable the underrun
reporting after the first underrun.
Underruns don't actually generate interrupts themselves on GMCH
platforms, we just can detect them whenever we service other
interrupts. So we don't have any enable bits to worry about. We just
need to remember to clear the underrun status when enabling underrun
reporting.
Note that the underrun handling needs to be moved to the non-locked
pipe_stats[] loop in the interrupt handlers to avoid having to rework
the locking in intel_set_cpu_fifo_underrun_reporting().
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Not sure anyone cares about this information. I suppose most people
would just look at /proc/interrupts instead.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
irq_received is used as a boolean in i965_irq_handler(), so make it
bool. This also makes i965_irq_handler() closer to i915_irq_handler().
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewd-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Add intel_hpd_irq_uninstall() which will cancel the hotplug re-enable
timer.
Also s/i915_reenable_hotplug_timer_func/intel_hpd_irq_reenable/
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Atm, we don't print these events for all platforms and for VLV/G4X we
also print them for DP AUX completion events which is unnecessary spam.
Fix both issues.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On pre-PCH platforms ISR doesn't seem to be an actual ISR, at least as
far as display interrupts are concerned. Instead it sort of looks like
some ISR bits just directly reflect the corresponding bit from PIPESTAT.
The bit appears in the ISR only if the PIPESTAT interrupt is enabled. So
in that sense it sort of looks a bit like the south interrupt scheme on
PCH platforms. So it goes something a bit like this:
PIPESTAT.status & PIPESTAT.enable -> ISR -> IMR -> IIR -> IER -> actual
interrupt
In any case that means the intel_pipe_in_vblank_locked() doesn't actually
work for pre-PCH platforms. As a last resort, add a similar kludge as radeon
has that fixes things up if we got called from the vblank interrupt,
but the scanline counter value indicates that we're not quite there yet.
We know that the scanline counter increments at hsync but is otherwise
accurate, so we can limit the kludge to the line just prior to vblank
start, instead of the relative distance that radeon uses.
Reviewed-by: mario.kleiner.de@gmail.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Preparation for moving the early vblank IRQ logic into
radeon_get_crtc_scanoutpos().
v2: Fix radeon_drv.c compile warning (Mario)
Reviewed-by: mario.kleiner.de@gmail.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
The scanline counter counts lines in the current field, not the entire
frame. But the crtc_ timings are the values for the entire frame. Divide
the vertical timings by 2 to make them match the scanline counter.
The rounding was carefully chosen to make it do the right thing wrt. the
observed scanline counter and ISR vblank bit behaviour.
Reviewed-by: mario.kleiner.de@gmail.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Rather than using crtc->hwmode, just pass the relevant mode to
drm_calc_vbltimestamp_from_scanoutpos(). This removes the last hwmode
usage from core drm.
Reviewed-by: mario.kleiner.de@gmail.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Conflicts are getting out of hand, and now we have to shuffle even
more in -next which was also shuffled in -fixes (the call for
drm_mode_config_reset needs to move yet again).
So do a proper backmerge. I wanted to wait with this for the 3.13
relaese, but alas let's just do this now.
Conflicts:
drivers/gpu/drm/i915/i915_reg.h
drivers/gpu/drm/i915/intel_ddi.c
drivers/gpu/drm/i915/intel_display.c
drivers/gpu/drm/i915/intel_pm.c
Besides the conflict around the forcewake get/put (where we chaged the
called function in -fixes and added a new parameter in -next) code all
the current conflicts are of the adjacent lines changed type.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We were apparently relying on the defaults on BDW, which resulted in no
hotplug or AUX interrupts. So be sure to call the ibx_irq_preinstall to
enable all interrupts.
v2: use preinstall instead of redundant SDIER write
References: https://bugs.freedesktop.org/show_bug.cgi?id=72834
References: https://bugs.freedesktop.org/show_bug.cgi?id=72833
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel thought that this was an opportune moment to include which pins
and bits ended up being stuck in the WARN.
Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Disabling the hotplug IRQ is a two-step process. First, inside the IRQ
handler we mark the rogue hotplug pin for disabling. Then later in the
hotplug worker, we actually disable the hotplug pin. So we should not
WARN about the rogue hotplug IRQ being sent until after we have
completed disabling the pin.
References: https://bugzilla.redhat.com/show_bug.cgi?id=1051170
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It seems that hardware that is broken enough to emit a hotplug IRQ even
though the pin is surposedly disable, will do so indefinitely.
Note: There's a good chance the underlying issue has been fixed with
commit 0ce99f749b
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri Jul 26 11:27:49 2013 +0200
drm/i915: fix gen4 digital port hotplug definitions
References: https://bugzilla.redhat.com/show_bug.cgi?id=1051170
Link: https://bugzilla.redhat.com/attachment.cgi?id=847786
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add note about the potential fix.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We specifically exclude original gen4 (i.e. i965g/gm), so update the
naming for consistency. Spotted while reviewing related code due to a
report from Jesse about byt needing again different values.
v2: g4x, not gm45 since this also applies to the desktop version.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
My OCD just couldn't let this slide. Spotted while reviewing Ville's
patch to only flip planes when we have FBC.
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Looks like 830M doesn't quite like it when you try to move a plane from
one pipe to another. It seems that the plane's old pipe has to be active
even if the plane is already disabled, otherwise the relevant register
just won't accept new values.
The following commit:
commit 1f1c2e2468
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu Nov 28 17:30:01 2013 +0200
drm/i915: Swap primary planes on gen2 for FBC
caused a regression on 830M. It will attempt to swap the planes when the
driver is loaded, but at that time only pipe A might be active, so plane
A gets disabled, but plane B won't get enabled since pipe B is not
active when we try to move the plane over to pipe A.
There's no reason to swap planes on 830M since it doesn't support
FBC. Change the logic a bit to limit the plane swapping to platforms
which actually support FBC. This should avoid getting a black screen on
830M.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The plan is to merge PC8 and D3 into a single feature, and when we're
in D3 we won't get any hotplug interrupt anyway, so leaving them
enable doesn't make sense, and it also brings us a problem. The
problem is that we get a hotplug interrupt right when we we wake up
from D3, when we're still waking up everything. If we fully disable
interrupts we won't get this hotplug interrupt, so we won't have
problems.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Only plane A is FBC capable on gen2 (like gen3), but the panel fitter
is hooked up to pipe B, so we want to prefer pipe B + plane A.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add the code comment Chris requested in his review.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now we have this everywhere. Next up would be to wire up the DP
hotplug pin to speed up panel power sequencing for eDP panels ...
I've decided to leave the has_aux_irq logic in the code, it should
come handy for hw bringup.
For testing/fail-safety the dp aux code already has a timeout when
waiting for interrupts to signal completion and screams rather loud if
they don't arrive in time. Given that we need a real piece of hw to
talk to anyway this is probably as good as it gets.
v2: Don't check the dp aux channel bits on i965 machines, they have a
different meaning there. Yay for reusing bits at will! Spotted by
Jani.
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Pull in Jani's backlight rework branch. This was merged through a
separate branch to be able to sort out the Broadwell conflicts
properly before pulling it into the main development branch.
Conflicts:
drivers/gpu/drm/i915/intel_display.c
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
reset_counter will be incremented twice per successful
reset. Odd values mean reset is in progress and even values
mean that reset has completed.
Reset status ioctl introduced in following commit
needs to deliver global reset count to userspace so
use reset_counter to derive the actual reset count
for the gpu
Note that reset in progress is enough to increment
the counter.
v2: wedged equals reset in progress (Daniel Vetter)
v3: Fixed stale comments (Damien Lespiau)
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
So here's the Broadwell pull request. From a kernel driver pov there's
two areas with big changes in Broadwell:
- Completely new enumerated interrupt bits. On the plus side it now looks
fairly unform and sane.
- Completely new pagetable layout.
To ensure minimal impact on existing platforms we've refactored both the
irq and low-level gtt handling code a lot in anticipation of the bdw push.
So now bdw enabling in these areas just plugs in a bunch of vfuncs.
Otherwise it's all fairly harmless adjusting of switch cases and
if-ladders to shovel bdw into the right blocks. So minimized impact on
existing platforms. I've also merged the bdw-stage1 branch into our
-nightly integration branch for the past week to make sure we don't break
anything.
Note that there's still quite a flurry or patches floating around, but
I've figured I'll push this out. I plan to keep the bdw fixes separate
from my usual -fixes stream so that you can reject them easily in case it
still looks like too much churn. Also, bdw is for now hidden behind the
preliminary hw enabling module option. So there's no real pressure to get
follow-up patches all into 3.13.
* tag 'bdw-stage1-2013-11-08-v2' of git://people.freedesktop.org/~danvet/drm-intel: (75 commits)
drm/i915: Mask the vblank interrupt on bdw by default
drm/i915: Wire up cpu fifo underrun reporting support for bdw
drm/i915: Optimize gen8_enable|disable_vblank functions
drm/i915: Wire up pipe CRC support for bdw
drm/i915: Wire up PCH interrupts for bdw
drm/i915: Wire up port A aux channel
drm/i915: Fix up the bdw pipe interrupt enable lists
drm/i915: Optimize pipe irq handling on bdw
drm/i915/bdw: Take render error interrupt out of the mask
drm/i915/bdw: Add BDW PCH check first
drm/i915: Use hsw_crt_get_config on BDW
drm/i915/bdw: Change dp aux timeout to 600us on DDIA
drm/i915/bdw: Enable trickle feed on Broadwell
drm/i915/bdw: WaSingleSubspanDispatchOnAALinesAndPoints
drm/i915/bdw: conservative SBE VUE cache mode
drm/i915/bdw: Limit SDE poly depth FIFO to 2
drm/i915/bdw: Sampler power bypass disable
ddrm/i915/bdw: Disable centroid pixel perf optimization
drm/i915/bdw: BWGTLB clock gate disable
drm/i915/bdw: Implement edp PSR workarounds
...
Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
HW engineers have listened and given us again a real interrupt with
masking and status regs. Yay!
For consistency with other platforms call the #define FIFO_UNDERRUN.
Eventually we also might need to have some enable/disable functions
for bdw display interrupts, but for now open-coding seems to be good
enough.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Let's cache the IMR value like on other platforms. This is needed to
implement the underrun reporting since then we'll have two places that
change the same register at runtime.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The layout of the CRC registers is the same as on hsw, only the
interrupt handling has changed a bit. So trivial to wire up, yay!
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Gives us hotplug, gmbus, dp aux and south errors (underrun
reporting!).
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Useful for dp aux to work better. Also stop enabling the port A
hotplug event - eDP panels are expected to fire that interupt and
we're not really ready to deal with them. This is consistent with how
we handle port A on ilk-hsw.
The more important bit is that we must delay the enabling of hotplug
interrupts until all the encoders are fully set up. But we need irq
support earlier than that, hence hotplug interrupts can only be
enabled in the ->hpd_irq_setup callback.
v2: Drop the _HOTPLUG, it isn't (Ville).
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Pipe underrun can't just be enabled, we need some support code like
on ilk-hsw to make this happen. So drop it for now.
- CRC error is a special mode of the CRC hardware that we don't use,
so again drop it. Real CRC support for bdw will be added later.
- All the other error bits are about faults, so rename the #define and
adjust the output.
v2: Use pipe_name as pointed out by Ville. Ville's comment was on a
previous patch, but it was easier to squash in here.
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We have a per-pipe bit in the master irq control register, so use it.
This allows us to drop the masks for aggregate interrupt bits and be a
bit more explicit in the code. It also removes one indentation level.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The interrupt handling implementation remains the same as previous
generations with the 4 types of registers, status, identity, mask, and
enable. However the layout of where the bits go have changed entirely.
To address these changes, all of the interrupt vfuncs needed special
gen8 code.
The way it works is there is a top level status register now which
informs the interrupt service routine which unit caused the interrupt,
and therefore which interrupt registers to read to process the
interrupt. For display the division is quite logical, a set of interrupt
registers for each pipe, and in addition to those, a set each for "misc"
and port.
For GT the things get a bit hairy, as seen by the code. Each of the GT
units has it's own bits defined. They all look *very similar* and
resides in 16 bits of a GT register. As an example, RCS and BCS share
register 0. To compact the code a bit, at a slight expense to
complexity, this is exactly how the code works as well. 2 structures are
added to the ring buffer so that our ring buffer interrupt handling code
knows which ring shares the interrupt registers, and a shift value (ie.
the top or bottom 16 bits of the register).
The above allows us to kept the interrupt register caching scheme, the
per interrupt enables, and the code to mask and unmask interrupts
relatively clean (again at the cost of some more complexity).
Most of the GT units mentioned above are command streamers, and so the
symmetry should work quite well for even the yet to be implemented rings
which Broadwell adds.
v2: Fixes up a couple of bugs, and is more verbose about errors in the
Broadwell interrupt handler.
v3: fix DE_MISC IER offset
v4: Simplify interrupts:
I totally misread the docs the first time I implemented interrupts, and
so this should greatly simplify the mess. Unlike GEN6, we never touch
the regular mask registers in irq_get/put.
v5: Rebased on to of recent pch hotplug setup changes.
v6: Fixup on top of moving num_pipes to intel_info.
v7: Rebased on top of Egbert Eich's hpd irq handling rework. Also
wired up ibx_hpd_irq_setup for gen8.
v8: Rebase on top of Jani's asle handling rework.
v9: Rebase on top of Ben's VECS enabling for Haswell, where he
unfortunately went OCD on the gt irq #defines. Not that they're still
not yet fully consistent:
- Used the GT_RENDER_ #defines + bdw shifts.
- Dropped the shift from the L3_PARITY stuff, seemed clearer.
- s/irq_refcount/irq_refcount.gt/
v10: Squash in VECS enabling patches and the gen8_gt_irq_handler
refactoring from Zhao Yakui <yakui.zhao@intel.com>
v11: Rebase on top of the interrupt cleanups in upstream.
v12: Rebase on top of Ben's DPF changes in upstream.
v13: Drop bdw from the HAS_L3_DPF feature flag for now, it's unclear what
exactly needs to be done. Requested by Ben.
v14: Fix the patch.
- Drop the mask of reserved bits and assorted logic, it doesn't match
the spec.
- Do the posting read inconditionally instead of commenting it out.
- Add a GEN8_MASTER_IRQ_CONTROL definition and use it.
- Fix up the GEN8_PIPE interrupt defines and give the GEN8_ prefixes -
we actually will need to use them.
- Enclose macros in do {} while (0) (checkpatch).
- Clear DE_MISC interrupt bits only after having processed them.
- Fix whitespace fail (checkpatch).
- Fix overtly long lines where appropriate (checkpatch).
- Don't use typedef'ed private_t (maintainer-scripts).
- Align the function parameter list correctly.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net> (v4)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
bikeshed
Bit a bit -fixes pull request in the merge window than usual dua to two
feauture-y things:
- Display CRCs are now enabled on all platforms, including the odd DP case
on gm45/vlv. Since this is a testing-only feature it should ever hurt,
but I figured it'll help with regression-testing -fixes. So I left it
in and didn't postpone it to 3.14.
- Display power well refactoring from Imre. Would have caused major pain
conflict with the bdw stage 1 patches if I'd postpone this to -next.
It's only an relatively small interface rework, so shouldn't cause pain.
It's also been in my tree since almost 3 weeks already.
That accounts for about two thirds of the pull, otherwise just bugfixes:
- vlv backlight fix from Jesse/Jani
- vlv vblank timestamp fix from Jesse
- improved edp detection through vbt from Ville (fixes a vlv issue)
- eDP vdd fix from Paulo
- fixes for dvo lvds on i830M
- a few smaller things all over
Note: This contains a backmerge of v3.12. Since the -internal branch
always applied on top of -nightly I need that unified base to merge bdw
patches. So you'll get a conflict with radeon connector props when pulling
this (and nouveau/master will also conflict a bit when Ben doesn't
rebase). The backmerge itself only had conflicts in drm/i915.
There's also a tiny conflict between Jani's backlight fix and your sysfs
lifetime fix in drm-next.
* tag 'drm-intel-fixes-2013-11-07' of git://people.freedesktop.org/~danvet/drm-intel: (940 commits)
drm/i915/vlv: use per-pipe backlight controls v2
drm/i915: make backlight functions take a connector
drm/i915: move opregion asle request handling to a work queue
drm/i915/vlv: use PIPE_START_VBLANK interrupts on VLV
drm/i915: Make intel_dp_is_edp() less specific
drm/i915: Give names to the VBT child device type bits
drm/i915/vlv: enable HDA display audio for Valleyview2
drm/i915/dvo: call ->mode_set callback only when the port is running
drm/i915: avoid unclaimed registers when capturing the error state
drm/i915: Enable DP port CRC for the "auto" source on g4x/vlv
drm/i915: scramble reset support for DP port CRC on vlv
drm/i915: scramble reset support for DP port CRC on g4x
drm/i916: add "auto" pipe CRC source
...
Conflicts:
MAINTAINERS
drivers/gpu/drm/i915/intel_panel.c
drivers/gpu/drm/nouveau/core/subdev/mc/base.c
drivers/gpu/drm/radeon/atombios_encoders.c
drivers/gpu/drm/radeon/radeon_connectors.c
Make the cur_delay limiting code a bit less prone to typo errors
by using clamp_t().
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When the hardware frame counter reads 0xffffff and we're already past
vblank start, we'd return 0x1000000 as the vblank counter value. Once
we'd cross into the next frame's active portion, the vblank counter
would wrap to 0. So we're reporting two different vblank counter values
for the same frame.
Fix the problem by masking the cooked value by 0xffffff to make sure
the counter wraps already after vblank start.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This fixes a mismatch between our vblank enable code and our IRQ
handler. Also, since vblank start events come in before page flips
reliably, it also fixes the kms_flip plain-flip test on my BYT system.
Spotted-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Move the ktime_get() clock readouts and potential preempt_disable()
calls from drm core into kms driver to make it compatible with the
api changes in the drm core.
The intel-kms driver needs to take the uncore.lock inside
i915_get_crtc_scanoutpos() and intel_pipe_in_vblank().
This is incompatible with the preempt_disable() on a
PREEMPT_RT patched kernel, as regular spin locks must not
be taken within a preempt_disable'd section. Lock contention
on the uncore.lock also introduced too much uncertainty in vblank
timestamps.
Push the ktime_get() timestamping for scanoutpos queries and
potential preempt_disable_rt() into i915_get_crtc_scanoutpos(),
so these problems can be avoided:
1. First lock the uncore.lock (might sleep on a PREEMPT_RT kernel).
2. preempt_disable_rt() (will be added by the rt-linux folks).
3. ktime_get() a timestamp before scanout pos query.
4. Do all mmio reads as fast as possible without grabbing any new locks!
5. ktime_get() a post-query timestamp.
6. preempt_enable_rt()
7. Unlock the uncore.lock.
This reduces timestamp uncertainty on a low-end HP Atom Mini netbook
with Intel GMA-950 nicely:
Before: 3-8 usecs with spikes > 20 usecs, triggering query retries.
After : Typically 1 usec (98% of all samples), occassionally 2 usecs
(2% of all samples), with maximum of 3 usecs (a handful).
v2: Fix formatting of new multi-line code comments.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
- Use a for_each_loop and add the corresponding #defines.
- Drop the _ILK postfix on the existing DE_PIPE_VBLANK macro for
consistency with everything else.
- Also use macros (and add the missing one for plane flips) for the
ivb display interrupt handler.
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Drop the useless parens that Ville spotted.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Request by Ville in his review of the CRC stuff. This converts
everything but ilk_display_irq_handler since that needs a bit more
than a simple search&replace to look nice.
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise QA will report this as a real hang when running igt
ZZ_missed_irq.
v2: Actually test the right stuff and really shut up the DRM_ERROR
output ...
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70747
Tested-by: lu hua <huax.lu@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- CRC support from Damien and He Shuang. Long term this should allow us to
test an awful lot modesetting corner cases automatically. So for me as
the maintainer this is really big.
- HDMI audio fix from Jani.
- VLV dpll computation code refactoring from Ville.
- Fixups for the gpu booster from last time around (Chris).
- Some cleanups in the context code from Ben.
- More watermark work from Ville (we'll be getting there ...).
- vblank timestamp improvements from Ville.
- CONFIG_FB=n support, including drm core changes to make the fbdev
helpers optional.
- DP link training improvements (Jani).
- mmio vtable from Ben, prep work for future hw.
* tag 'drm-intel-next-2013-10-18' of git://people.freedesktop.org/~danvet/drm-intel: (132 commits)
drm/i915/dp: don't mention eDP bpp clamping if it doesn't affect bpp
drm/i915: remove dead code in ironlake_crtc_mode_set
drm/i915: crc support for hsw
drm/i915: fix CRC debugfs setup
drm/i915: wait one vblank when disabling CRCs
drm/i915: use ->get_vblank_counter for the crc frame counter
drm/i915: wire up CRC interrupt for ilk/snb
drm/i915: add CRC #defines for ilk/snb
drm/i915: extract display_pipe_crc_update
drm/i915: don't Oops in debugfs for I915_FBDEV=n
drm/i915: set HDMI pixel clock in audio configuration
drm/i915: pass mode to ELD write vfuncs
cpufreq: Add dummy cpufreq_cpu_get/put for CONFIG_CPU_FREQ=n
drm/i915: check gem bo size when creating framebuffers
drm/i915: Use unsigned long for obj->user_pin_count
drm/i915: prevent tiling changes on framebuffer backing storage
drm/i915: grab dev->struct_mutex around framebuffer_init
drm/i915: vlv: fix VGA hotplug after modeset
drm: add support for additional stereo 3D modes
drm/i915: preserve dispaly init order on ByT
...
So drm was abusing device lifetimes, by having embedded device structures
in the minor and connector it meant that the lifetime of the internal drm
objects (drm_minor and drm_connector) were tied to the lifetime of the device
files in sysfs, so if something kept those files opened the current code
would kfree the objects and things would go downhill from there.
Now in reality there is no need for these lifetimes to be so intertwined,
especailly with hotplugging of devices where we wish to remove the sysfs
and userspace facing pieces before we can unwind the internal objects due
to open userspace files or mmaps, so split the objects out so the struct
device is no longer embedded and do what fbdev does and just allocate
and remove the sysfs inodes separately.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel pointed out that it was hard to get anything lockless to work
correctly, so don't even try for this non critical piece of code and
just use a spin lock.
v2: Make intel_pipe_crc->opened a bool
v3: Use assert_spin_locked() instead of a comment (Daniel Vetter)
v4: Use spin_lock_irq() in the debugfs functions (they can only be
called from process context),
Use spin_lock() in the pipe_crc_update() function that can only be
called from an interrupt handler,
Use wait_event_interruptible_lock_irq() when waiting for data in the
cicular buffer to ensure proper locking around the condition we are
waiting for. (Daniel Vetter)
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Give them an _irq_handler postfix, like all the other irq stuff.
- Shuffle the DEBUG_FS=n dummy functions around a bit. This is prep
work to extract all the crc debug stuff into intel_display_testing.c
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And throw in a tiny for_each_pipe refactoring for gen2.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Should work down to gen2. The #defines for the interrupt sources are
already there in PIPESTAT and are the same on all gmch platforms for
gen2 up to vlv.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
hw designers decided to change the CRC registers and coalesce them all
into one. Otherwise nothing changed. I've opted for a new hsw_ version
to grab the crc sample since hsw+1 will have the same crc registers,
but different interrupt source registers. So this little helper
function will come handy there.
Also refactor the display error handler with a neat pipe loop.
v2: Use for_each_pipe.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Suggested by Ville.
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We enable the interrupt unconditionally and only control it
through the enable bit in the CRC control register.
v2: Extract per-platform helpers to compute the register values.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The ringbuffer update logic should always be the same, but different
platforms have different amounts of CRC registers. Hence extract it.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Also use #ifdef to keep consistent with all other such cases.
Cc: Damien Lespiau <damien.lespiau@intel.com>
Acked-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
seq_file is not quite the right interface for these ones. We have a
circular buffer with a new entry per vblank on one side and a process
wanting to dequeue the CRC with a read().
It's quite racy to wait for vblank in user land and then try to read a
pipe_crc file, sometimes the CRC interrupt hasn't been fired and we end
up with an EOF.
So, let's have the read on the pipe_crc file block until the interrupt
gives us a new entry. At that point we can wake the reading process.
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This shouldn't happen as the buffer is freed after disable pipe CRCs,
but better be safe than sorry.
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There are a few good properties to a circular buffer, for instance it
has a number of entries (before we were always dumping the full buffer).
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There are several points in the display pipeline where CRCs can be
computed on the bits flowing there. For instance, it's usually possible
to compute the CRCs of the primary plane, the sprite plane or the CRCs
of the bits after the panel fitter (collectively called pipe CRCs).
v2: Quite a bit of rework here and there (Damien)
Signed-off-by: Shuang He <shuang.he@intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Fix intermediate compile file reported by Wu Fengguang's
kernel builder.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Gen2 doesn't have a hardware frame counter that can be read out. Just
provide a stub .get_vblank_counter() that always returns 0 instead of
trying to read non-existing registers.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Gen2 doesn't have the pixelcount register that gen3 and gen4 have.
Instead we must use the scanline counter like we do for ctg+.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The DSL register increments at the start of horizontal sync, so it
manages to miss the entire active portion of the current line.
Improve the get_scanoutpos accuracy a bit when the scanout position is
close to the start or end of vblank. We can do that by double checking
the DSL value against the vblank status bit from ISR.
Cc: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: mario.kleiner.de@gmail.com
Tested-by: mario.kleiner.de@gmail.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The reported scanout position must be relative to the end of vblank.
Currently we manage to fumble that in a few ways.
First we don't consider the case when vtotal != vbl_end. While that
isn't very common (happens maybe only w/ old panel fitting hardware),
we can fix it easily enough.
The second issue is that on pre-CTG hardware we convert the pixel count
to horizontal/vertical components at the very beginning, and then forget
to adjust the horizontal component to be relative to vbl_end. So instead
we should keep our numbers in the pixel count domain while we're
adjusting the position to be relative to vbl_end. Then when we do the
conversion in the end, both vertical _and_ horizontal components will
come out correct.
v2: Change position to int from u32 to avoid sign issues
Cc: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: mario.kleiner.de@gmail.com
Tested-by: mario.kleiner.de@gmail.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We have all the information we need in the mode structure, so going and
reading it from the hardware is pointless, and slower.
We never populated ->get_vblank_timestamp() in the UMS case, and as that
is the only way we'd ever call ->get_scanout_position(), we can
completely ignore UMS in i915_get_crtc_scanoutpos().
Also reorganize intel_irq_init() a bit to clarify the KMS vs. UMS
situation.
v2: Drop UMS code
Cc: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: mario.kleiner.de@gmail.com
Tested-by: mario.kleiner.de@gmail.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The old style frame counter increments at the start of active video.
However for i915_get_vblank_counter() we want a counter that increments
at the start of vblank.
Fortunately the low frame counter register also contains the pixel
counter for the current frame. We can can compare that against the
vblank start pixel count to determine if we need to increment the
frame counter by 1 to get the correct answer.
Also reorganize the function pointer assignments in intel_irq_init() a
bit to avoid confusing people.
Cc: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We lost the ability to capture the first error for a stuck ring in the
recent hangcheck robustification. Whilst both error states are
interesting (why does the GPU not recover is also essential to debug),
our primary goal is to fix the initial hang and so we need to capture
the first error state upon taking hangcheck action.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
After applying wait-boost we often find ourselves stuck at higher clocks
than required. The current threshold value requires the GPU to be
continuously and completely idle for 313ms before it is dropped by one
bin. Conversely, we require the GPU to be busy for an average of 90% over
a 84ms period before we upclock. So the current thresholds almost never
downclock the GPU, and respond very slowly to sudden demands for more
power. It is easy to observe that we currently lock into the wrong bin
and both underperform in benchmarks and consume more power than optimal
(just by repeating the task and measuring the different results).
An alternative approach, as discussed in the bspec, is to use a
continuous threshold for upclocking, and an average value for downclocking.
This is good for quickly detecting and reacting to state changes within a
frame, however it fails with the common throttling method of waiting
upon the outstanding frame - at least it is difficult to choose a
threshold that works well at 15,000fps and at 60fps. So continue to use
average busy/idle loads to determine frequency change.
v2: Use 3 power zones to keep frequencies low in steady-state mostly
idle (e.g. scrolling, interactive 2D drawing), and frequencies high
for demanding games. In between those end-states, we use a
fast-reclocking algorithm to converge more quickly on the desired bin.
v3: Bug fixes - make sure we reset adj after switching power zones.
v4: Tune - drop the continuous busy thresholds as it prevents us from
choosing the right frequency for glxgears style swap benchmarks. Instead
the goal is to be able to find the right clocks irrespective of the
wait-boost.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Stéphane Marchesin <stephane.marchesin@gmail.com>
Cc: Owen Taylor <otaylor@redhat.com>
Cc: "Meng, Mengmeng" <mengmeng.meng@intel.com>
Cc: "Zhuang, Lena" <lena.zhuang@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we encounter a situation where the CPU blocks waiting for results
from the GPU, give the GPU a kick to boost its the frequency.
This should work to reduce user interface stalls and to quickly promote
mesa to high frequencies - but the cost is that our requested frequency
stalls high (as we do not idle for long enough before rc6 to start
reducing frequencies, nor are we aggressive at down clocking an
underused GPU). However, this should be mitigated by rc6 itself powering
off the GPU when idle, and that energy use is dependent upon the workload
of the GPU in addition to its frequency (e.g. the math or sampler
functions only consume power when used). Still, this is likely to
adversely affect light workloads.
In particular, this nearly eliminates the highly noticeable wake-up lag
in animations from idle. For example, expose or workspace transitions.
(However, given the situation where we fail to downclock, our requested
frequency is almost always the maximum, except for Baytrail where we
manually downclock upon idling. This often masks the latency of
upclocking after being idle, so animations are typically smooth - at the
cost of increased power consumption.)
Stéphane raised the concern that this will punish good applications and
reward bad applications - but due to the nature of how mesa performs its
client throttling, I believe all mesa applications will be roughly
equally affected. To address this concern, and to prevent applications
like compositors from permanently boosting the RPS state, we ratelimit the
frequency of the wait-boosts each client recieves.
Unfortunately, this techinique is ineffective with Ironlake - which also
has dynamic render power states and suffers just as dramatically. For
Ironlake, the thermal/power headroom is shared with the CPU through
Intelligent Power Sharing and the intel-ips module. This leaves us with
no GPU boost frequencies available when coming out of idle, and due to
hardware limitations we cannot change the arbitration between the CPU and
GPU quickly enough to be effective.
v2: Limit each client to receiving a single boost for each active period.
Tested by QA to only marginally increase power, and to demonstrably
increase throughput in games. No latency measurements yet.
v3: Cater for front-buffer rendering with manual throttling.
v4: Tidy up.
v5: Sadly the compositor needs frequent boosts as it may never idle, but
due to its picking mechanism (using ReadPixels) may require frequent
waits. Those waits, along with the waits for the vrefresh swap, conspire
to keep the GPU at low frequencies despite the interactive latency. To
overcome this we ditch the one-boost-per-active-period and just ratelimit
the number of wait-boosts each client can receive.
Reported-and-tested-by: Paul Neumann <paul104x@yahoo.de>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68716
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Stéphane Marchesin <stephane.marchesin@gmail.com>
Cc: Owen Taylor <otaylor@redhat.com>
Cc: "Meng, Mengmeng" <mengmeng.meng@intel.com>
Cc: "Zhuang, Lena" <lena.zhuang@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: No extern for function prototypes in headers.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we switched to always using a timeout in conjunction with
wait_seqno, we lost the ability to detect missed interrupts. Since, we
have had issues with interrupts on a number of generations, and they are
required to be delivered in a timely fashion for a smooth UX, it is
important that we do log errors found in the wild and prevent the
display stalling for upwards of 1s every time the seqno interrupt is
missed.
Rather than continue to fix up the timeouts to work around the interface
impedence in wait_event_*(), open code the combination of
wait_event[_interruptible][_timeout], and use the exposed timer to
poll for seqno should we detect a lost interrupt.
v2: In order to satisfy the debug requirement of logging missed
interrupts with the real world requirments of making machines work even
if interrupts are hosed, we revert to polling after detecting a missed
interrupt.
v3: Throw in a debugfs interface to simulate broken hw not reporting
interrupts.
v4: s/EGAIN/EAGAIN/ (Imre)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
[danvet: Don't use the struct typedef in new code.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We only wish to know the value of seqno when emitting the tracepoint, so
move the query from a parameter to the macro to inside the conditional
macro body so that the query is only evaluated when required.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.14 (GNU/Linux)
iQEcBAABAgAGBQJSQMORAAoJEHm+PkMAQRiGj14H/1bjhtfNjPdX7MVQAzA+WpwX
s7h1IQu2Si9S5S1lBiM2sBTOssVcmfheO9x4yqm7JNOD1RnssWKOM3q+zVOLstwd
GD3gluJPeraD5EyYSqEJ9ILPQ3gbxb4wOlT0Z291TW6E8XhLRr0RTOJPksRsgvLH
Ckm9uJh6ArS6ZXfXiaDQfd+xHAQJkUfW6nMSA0g9ZO9C6KIDRvcbUmrY3m4HhfIk
mK0TXCBs+AXGDIjTEB8JgIQL/5y1Qn0c4R+2uTU/4YWwyLvJTV1e44kGoleukMMT
6Pw/TNlUEN161dbSaqCyF3sfXHDYQ5valycI2PDgitMtPSxbzsU1VDizS8+daRg=
=lEmF
-----END PGP SIGNATURE-----
Merge tag 'v3.12-rc2' into drm-intel-next
Backmerge Linux 3.12-rc2 to prep for a bunch of -next patches:
- Header cleanup in intel_drv.h, both changed in -fixes and my current
-next pile.
- Cursor handling cleanup for -next which depends upon the cursor
handling fix merged into -rc2.
All just trivial conflicts of the "changed adjacent lines" type:
drivers/gpu/drm/i915/i915_gem.c
drivers/gpu/drm/i915/intel_display.c
drivers/gpu/drm/i915/intel_drv.h
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We currently disable the ERR_INT interrupts while running the IRQ
handler because we fear that if we do an unclaimed register access
from inside the IRQ handler we'll keep triggering the IRQ handler
forever.
The problem is that since we always disable the ERR_INT interrupts at
the IRQ handler, when we get a FIFO underrun we'll always print both
messages:
- "uncleared fifo underrun on pipe A"
- "Pipe A FIFO underrun"
Because the "was_enabled" variable from
ivybridge_set_fifo_underrun_reporting will always be false (since we
disable ERR int at the IRQ handler!).
Instead of actually fixing ivybridge_set_fifo_underrun_reporting,
let's just remove the "disable ERR_INT during the IRQ handler" code.
As far as we know we shouldn't really be triggering ERR_INT interrupts
from the IRQ handler, so if we ever get stuck in the endless loop of
interrupts we can git-bisect and revert (and we can even bisect and
revert this patch in case I'm just wrong). As a bonus, our IRQ handler
is now simpler and a few nanoseconds faster.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We'd only ever used this define to denote whether or not we have the
dynamic parity feature (DPF) and never to determine whether or not L3
exists. Baytrail is a good example of where L3 exists, and not DPF.
This patch provides clarify in the code for future use cases which might
want to actually query whether or not L3 exists.
v2: Add /* DPF == dynamic parity feature */
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Certain HSW SKUs have a second bank of L3. This L3 remapping has a
separate register set, and interrupt from the first "slice". A slice is
simply a term to define some subset of the GPU's l3 cache. This patch
implements both the interrupt handler, and ability to communicate with
userspace about this second slice.
v2: Remove redundant check about non-existent slice.
Change warning about interrupts of unknown slices to WARN_ON_ONCE
Handle the case where we get 2 slice interrupts concurrently, and switch
the tracking of interrupts to be non-destructive (all Ville)
Don't enable/mask the second slice parity interrupt for ivb/vlv (even
though all docs I can find claim it's rsvd) (Ville + Bryan)
Keep BYT excluded from L3 parity
v3: Fix the slice = ffs to be decremented by one (found by Ville). When
I initially did my testing on the series, I was using 1-based slice
counting, so this code was correct. Not sure why my simpler tests that
I've been running since then didn't pick it up sooner.
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This reduces dmesg noise when there's a glitch on the hpd line, or there
are more than one connectors on the same hpd line and only one of them
changes.
While at it, switch to use the friendly status names instead of numbers.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
My g33 here seems to be shockingly good at hitting them all. This time
around kms_flip/flip-vs-panning-vs-hang blows up:
intel_crtc_wait_for_pending_flips correctly checks for gpu hangs and
if a gpu hang is pending aborts the wait for outstanding flips so that
the setcrtc call will succeed and release the crtc mutex. And the gpu
hang handler needs that lock in intel_display_handle_reset to be able
to complete outstanding flips.
The problem is that we can race in two ways:
- Waiters on the dev_priv->pending_flip_queue aren't woken up after
we've the reset as pending, but before we actually start the reset
work. This means that the waiter doesn't notice the pending reset
and hence will keep on hogging the locks.
Like with dev->struct_mutex and the ring->irq_queue wait queues we
there need to wake up everyone that potentially holds a lock which
the reset handler needs.
- intel_display_handle_reset was called _after_ we've already
signalled the completion of the reset work. Which means a waiter
could sneak in, grab the lock and never release it (since the
pageflips won't ever get released).
Similar to resetting the gem state all the reset work must complete
before we update the reset counter. Contrary to the gem reset we
don't need to have a second explicit wake up call since that will
have happened already when completing the pageflips. We also don't
have any issues that the completion happens while the reset state is
still pending - wait_for_pending_flips is only there to ensure we
display the right frame. After a gpu hang&reset events such
guarantees are out the window anyway. This is in contrast to the gem
code where too-early wake-up would result in unnecessary restarting
of ioctls.
Also, since we've gotten these various deadlocks and ordering
constraints wrong so often throw copious amounts of comments at the
code.
This deadlock regression has been introduced in the commit which added
the pageflip reset logic to the gpu hang work:
commit 96a02917a0
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon Feb 18 19:08:49 2013 +0200
drm/i915: Finish page flips and update primary planes after a GPU reset
v2:
- Add comments to explain how the wake_up serves as memory barriers
for the atomic_t reset counter.
- Improve the comments a bit as suggested by Chris Wilson.
- Extract the wake_up calls before/after the reset into a little
i915_error_wake_up and unconditionally wake up the
pending_flip_queue waiters, again as suggested by Chris Wilson.
v3: Throw copious amounts of comments at i915_error_wake_up as
suggested by Chris Wilson.
Cc: stable@vger.kernel.org
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Score and action reveals what all the rings were doing
and why hang was declared. Add idle state so that
we can distinguish between waiting and idle ring.
v2: - add idle as a hangcheck action
- consensed hangcheck status to single line (Chris)
- mark active explicitly when we are making progress (Chris)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since we've started to clean up pending flips when the gpu hangs in
commit 96a02917a0
Author: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon Feb 18 19:08:49 2013 +0200
drm/i915: Finish page flips and update primary planes after a GPU reset
the gpu reset work now also grabs modeset locks. But since work items
on our private work queue are not allowed to do that due to the
flush_workqueue from the pageflip code this results in a neat
deadlock:
INFO: task kms_flip:14676 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kms_flip D ffff88019283a5c0 0 14676 13344 0x00000004
ffff88018e62dbf8 0000000000000046 ffff88013bdb12e0 ffff88018e62dfd8
ffff88018e62dfd8 00000000001d3b00 ffff88019283a5c0 ffff88018ec21000
ffff88018f693f00 ffff88018eece000 ffff88018e62dd60 ffff88018eece898
Call Trace:
[<ffffffff8138ee7b>] schedule+0x60/0x62
[<ffffffffa046c0dd>] intel_crtc_wait_for_pending_flips+0xb2/0x114 [i915]
[<ffffffff81050ff4>] ? finish_wait+0x60/0x60
[<ffffffffa0478041>] intel_crtc_set_config+0x7f3/0x81e [i915]
[<ffffffffa031780a>] drm_mode_set_config_internal+0x4f/0xc6 [drm]
[<ffffffffa0319cf3>] drm_mode_setcrtc+0x44d/0x4f9 [drm]
[<ffffffff810e44da>] ? might_fault+0x38/0x86
[<ffffffffa030d51f>] drm_ioctl+0x2f9/0x447 [drm]
[<ffffffff8107a722>] ? trace_hardirqs_off+0xd/0xf
[<ffffffffa03198a6>] ? drm_mode_setplane+0x343/0x343 [drm]
[<ffffffff8112222f>] ? mntput_no_expire+0x3e/0x13d
[<ffffffff81117f33>] vfs_ioctl+0x18/0x34
[<ffffffff81118776>] do_vfs_ioctl+0x396/0x454
[<ffffffff81396b37>] ? sysret_check+0x1b/0x56
[<ffffffff81118886>] SyS_ioctl+0x52/0x7d
[<ffffffff81396b12>] system_call_fastpath+0x16/0x1b
2 locks held by kms_flip/14676:
#0: (&dev->mode_config.mutex){+.+.+.}, at: [<ffffffffa0316545>] drm_modeset_lock_all+0x22/0x59 [drm]
#1: (&crtc->mutex){+.+.+.}, at: [<ffffffffa031656b>] drm_modeset_lock_all+0x48/0x59 [drm]
INFO: task kworker/u8:4:175 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
kworker/u8:4 D ffff88018de9a5c0 0 175 2 0x00000000
Workqueue: i915 i915_error_work_func [i915]
ffff88018e37dc30 0000000000000046 ffff8801938ab8a0 ffff88018e37dfd8
ffff88018e37dfd8 00000000001d3b00 ffff88018de9a5c0 ffff88018ec21018
0000000000000246 ffff88018e37dca0 000000005a865a86 ffff88018de9a5c0
Call Trace:
[<ffffffff8138ee7b>] schedule+0x60/0x62
[<ffffffff8138f23d>] schedule_preempt_disabled+0x9/0xb
[<ffffffff8138d0cd>] mutex_lock_nested+0x205/0x3b1
[<ffffffffa0477094>] ? intel_display_handle_reset+0x7e/0xbd [i915]
[<ffffffffa0477094>] ? intel_display_handle_reset+0x7e/0xbd [i915]
[<ffffffffa0477094>] intel_display_handle_reset+0x7e/0xbd [i915]
[<ffffffffa044e0a2>] i915_error_work_func+0x128/0x147 [i915]
[<ffffffff8104a89a>] process_one_work+0x1d4/0x35a
[<ffffffff8104a821>] ? process_one_work+0x15b/0x35a
[<ffffffff8104b4a5>] worker_thread+0x144/0x1f0
[<ffffffff8104b361>] ? rescuer_thread+0x275/0x275
[<ffffffff8105076d>] kthread+0xac/0xb4
[<ffffffff81059d30>] ? finish_task_switch+0x3b/0xc0
[<ffffffff810506c1>] ? __kthread_parkme+0x60/0x60
[<ffffffff81396a6c>] ret_from_fork+0x7c/0xb0
[<ffffffff810506c1>] ? __kthread_parkme+0x60/0x60
3 locks held by kworker/u8:4/175:
#0: (i915){.+.+.+}, at: [<ffffffff8104a821>] process_one_work+0x15b/0x35a
#1: ((&dev_priv->gpu_error.work)){+.+.+.}, at: [<ffffffff8104a821>] process_one_work+0x15b/0x35a
#2: (&crtc->mutex){+.+.+.}, at: [<ffffffffa0477094>] intel_display_handle_reset+0x7e/0xbd [i915]
This blew up while running kms_flip/flip-vs-panning-vs-hang-interruptible
on one of my older machines.
Unfortunately (despite the proper lockdep annotations for
flush_workqueue) lockdep still doesn't detect this correctly, so we
need to rely on chance to discover these bugs.
Apply the usual bugfix and schedule the reset work on the system
workqueue to keep our own driver workqueue free of any modeset lock
grabbing.
Note that this is not a terribly serious regression since before the
offending commit we'd simply have stalled userspace forever due to
failing to abort all outstanding pageflips.
v2: Add a comment as requested by Chris.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Historically we've run our own driver hotplug handling in our own
work-queue, which then launched the drm core hotplug handling in the
system workqueue. This is important since we flush our own driver
workqueue in the pageflip code while hodling modeset locks, and only
the drm hotplug code grabbed these locks. But with
commit 69787f7da6
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue Oct 23 18:23:34 2012 +0000
drm: run the hpd irq event code directly
this was changed and now we could deadlock in our flip handler if
there's a hotplug work blocking the progress of the crucial unpin
works. So this broke the careful deadlock avoidance implemented in
commit b4a98e57fc
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu Nov 1 09:26:26 2012 +0000
drm/i915: Flush outstanding unpin tasks before pageflipping
Since the rule thus far has been that work items on our own workqueue
may never grab modeset locks simply restore that rule again.
v2: Add a comment to the declaration of dev_priv->wq to warn readers
about the tricky implications of using it. Suggested by Chris Wilson.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Stuart Abercrombie <sabercrombie@chromium.org>
Reported-by: Stuart Abercrombie <sabercrombie@chromium.org>
References: http://permalink.gmane.org/gmane.comp.freedesktop.xorg.drivers.intel/26239
Cc: stable@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Squash in a comment at the place where we schedule the work.
Requested after-the-fact by Chris on irc since the hpd work isn't the
only place we botch this.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We already have a big splashing *ERROR* for all the relevant cases of
hangs, so this one here is redudant. And it results in an unclean
dmesg when running with simulated hangs. Regression has been
introduced in
commit 05407ff889
Author: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Thu May 30 09:04:29 2013 +0300
drm/i915: detect hang using per ring hangcheck_score
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68641
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch allows PC8+ states on Haswell. These states can only be
reached when all the display outputs are disabled, and they allow some
more power savings.
The fact that the graphics device is allowing PC8+ doesn't mean that
the machine will actually enter PC8+: all the other devices also need
to allow PC8+.
For now this option is disabled by default. You need i915.allow_pc8=1
if you want it.
This patch adds a big comment inside i915_drv.h explaining how it
works and how it tracks things. Read it.
v2: (this is not really v2, many previous versions were already sent,
but they had different names)
- Use the new functions to enable/disable GTIMR and GEN6_PMIMR
- Rename almost all variables and functions to names suggested by
Chris
- More WARNs on the IRQ handling code
- Also disable PC8 when there's GPU work to do (thanks to Ben for
the help on this), so apps can run caster
- Enable PC8 on a delayed work function that is delayed for 5
seconds. This makes sure we only enable PC8+ if we're really
idle
- Make sure we're not in PC8+ when suspending
v3: - WARN if IRQs are disabled on __wait_seqno
- Replace some DRM_ERRORs with WARNs
- Fix calls to restore GT and PM interrupts
- Use intel_mark_busy instead of intel_ring_advance to disable PC8
v4: - Use the force_wake, Luke!
v5: - Remove the "IIR is not zero" WARNs
- Move the force_wake chunk to its own patch
- Only restore what's missing from RC6, not everything
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Because hsw_pm_irq_handler does exactly what gen6_rps_irq_handler does
and also processes the 2 additional VEBOX bits. So merge those
functions and wrap the VEBOX bits on a HAS_VEBOX check. This
check isn't really necessary since the bits are reserved on
SNB/IVB/VLV, but it's a good documentation on who uses them.
v2: - Change IS_HASWELL check to HAS_VEBOX
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It seems we've been doing this ever since we started processing the
RPS events on a work queue, on commit "drm/i915: move gen6 rps
handling to workqueue", 4912d04193.
The problem is: when we add work to the queue, instead of just masking
the bits we queued and leaving all the others on their current state,
we mask the bits we queued and unmask all the others. This basically
means we'll be unmasking a bunch of interrupts we're not going to
process. And if you look at gen6_pm_rps_work, we unmask back only
GEN6_PM_RPS_EVENTS, which means the bits we unmasked when adding work
to the queue will remain unmasked after we process the queue.
Notice that even though we unmask those unrelated interrupts, we never
enable them on IER, so they don't fire our interrupt handler, they
just stay there on IIR waiting to be cleared when something else
triggers the interrupt handler.
So this patch does what seems to make more sense: mask only the bits
we add to the queue, without unmasking anything else, and so we'll
unmask them after we process the queue.
As a side effect we also have to remove that WARN, because it is not
only making sure we don't mask useful interrupts, it is also making
sure we do unmask useless interrupts! That piece of code should not be
responsible for knowing which bits should be unmasked, so just don't
assert anything, and trust that snb_disable_pm_irq should be doing the
right thing.
With i915.enable_pc8=1 I was getting ocasional "GEN6_PMIIR is not 0"
error messages due to the fact that we unmask those unrelated
interrupts but don't enable them.
Note: if bugs start bisecting to this patch, then it probably means
someone was relying on the fact that we unmask everything by accident,
then we should fix gen5_gt_irq_postinstall or whoever needs the
accidentally unmasked interrupts. Or maybe I was just wrong and we
need to revert this patch :)
Note: This started to be a more real issue with the addition of the
VEBOX support since now we do enable more than just the minimal set of
RPS interrupts in the IER register. Which means after the first rps
interrupt has happened we will never mask the VEBOX user interrupts
again and so will blow through cpu time needlessly when running video
workloads.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Add note that this started to matter with VEBOX much more.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On SNB/IVB/VLV we only call gen6_rps_irq_handler if one of the IIR
bits set is part of GEN6_PM_RPS_EVENTS, but at gen6_rps_irq_handler we
add all the enabled IIR bits to the work queue, not only the ones that
are part of GEN6_PM_RPS_EVENTS. But then gen6_pm_rps_work only
processes GEN6_PM_RPS_EVENTS, so it's useless to add anything that's
not GEN6_PM_RPS_EVENTS to the work queue.
As a bonus, gen6_rps_irq_handler looks more similar to
hsw_pm_irq_handler, so we may be able to merge them in the future.
v2: - Add a WARN in case we queued something we're not going to
process.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If the error interrupts are already disabled, don't disable and
reenable them. This is going to be needed when we're in PC8+, where
all the interrupts are disabled so we won't risk re-enabling
DE_ERR_INT_IVB.
v2: Use dev_priv->irq_mask (Chris)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just like irq_mask and gt_irq_mask, use it to track the status of
GEN6_PMIMR so we don't need to read it again every time we call
snb_update_pm_irq.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I did some brief tests and the "new_val = pmimr" condition usually
happens a few times after exiting games.
Note: This is also prep work to track the GEN6_PMIMR register state in
dev_priv->pm_imr. This happens in the next patch.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
[danvet: Add note to explain why we want this, as per the discussion
between Chris and Paulo.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just like we're doing with the other IMR changes.
One of the functional changes is that not every caller was doing the
POSTING_READ.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just like the functions that touch DEIMR and SDEIMR, but for GTIMR.
The new functions contain a POSTING_READ(GTIMR) which was not present
at the 2 callers inside i915_irq.c.
The implementation is based on ibx_display_interrupt_update.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Although I could not reproduce this (different compiler version,
perhaps), reportedly we get:
drivers/gpu/drm/i915/i915_irq.c:1943:27: warning: ‘score’ may be used
uninitialized in this function [-Wuninitialized]
Drop the 'score' variable altogether as it's not really needed.
Reported-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The short lowercase names are bound to collide. The default warnings
don't even warn about shadowing.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's been there since i8xx_irq_handler() was added in
commit c2798b19ba
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun Apr 22 21:13:57 2012 +0100
drm/i915: i8xx interrupt handler
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For HPD storm detection we now mask out individual interrupt source
bits. We have already seen a case where HPD interrupt enable bits
were assigned to the wrong pins. To track these conditions more
easily add some debugging messages.
v2: Spelling fixes as suggested by Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Egbert Eich <eich@suse.de>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently, the register access code is split between i915_drv.c and
intel_pm.c. It only bares a superficial resemblance to the reset of the
powermanagement code, so move it all into its own file. This is to ease
further patches to enforce serialised register access.
v2: Scan for random abuse of I915_WRITE_NOTRACE
v3: Take the opportunity to rename the GT functions as uncore. Uncore is
the term used by the hardware design (and bspec) for all functions
outside of the GPU (and CPU) cores in what is also known as the System
Agent.
v4: Rebase onto SNB rc6 fixes
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Wrestle patch into applying and inline
intel_uncore_early_sanitize (plus move the old comment to the new
function). Also keep the _santize postfix for intel_uncore_sanitize.]
[danvet: Squash in fixup spotted by Chris on irc: We need to call
intel_pm_init before intel_uncore_sanitize since the later will call
cancel_work on the delayed rps setup work the former initializes.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Make the uevent strings part of the user API for people who wish to
write their own listeners.
v2: Make a space in the string concatenation. (Chad)
Use the "UEVENT" suffix intead of "EVENT" (Chad)
Make kernel-doc parseable Docbook comments (Daniel)
v3: Undid reset change introduced in last submission (Daniel)
Fixed up comments to address removal changes.
Thanks to Daniel Vetter for a majority of the parity error comments.
CC: Chad Versace <chad.versace@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Paulo Zanoni