intel_crtc_set_config is an unwidly beast and is in serious need of
some function extraction. To facilitate that, introduce a struct to
keep track of all the state involved. Atm it doesn't do much more than
keep track of all the allocated memory.
v2: Apply some bikeshed to intel_set_config_free, as suggested by
Jesse Barnes.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Many BIOSen forget to turn on the pipe A after resume (because they
actually don't turn on anything), so we have to do that ourselves when
sanitizing the hw state.
I've discovered this due to the recent addition of a pipe WARN that
takes the force quirk into account.
v2: Actually try to enable the pipe with a proper configuration instead
of simpyl switching it on with whatever random state the bios left it
in after resume.
v3: Fixup rebase conflict - the load_detect functions have lost their
encoder argument.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We now track the connector state in encoder->connectors_active, and
because the DP output can't be cloned, that is sufficient to track the
link state. Hence use this instead of adding yet another modeset state
variable with dubious semantics at driver load and resume time.
Also, connectors_active should only ever be set when the encoder is
linked to a crtc, hence convert that crtc test into a WARN.
v2: Rebase on top of struct intel_dp moving.
v3: The rebase accidentally killed the newly-introduced intel_dp->port
Noticed by Paulo Zanoni.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Afaict this has been used for two things:
- To prevent the crtc enable code from being run twice. We have now
intel_crtc->active to track this in a more precise way.
- To ensure the code copes correctly with the unknown hw state after
boot and resume. Thanks to the hw state readout and sanitize code we
have now a better way to handle this.
The only thing it still does is complicate our modeset state space.
Having outlived its usefullness, let it just die.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Atm we can only check the connector state after a dpms call - while
doing modeset with the copy&pasted crtc helper code things are too
ill-defined for proper checking. But the idea is very much to call
this check from the modeset code, too.
v2: Fix dpms check and don't presume that if the hw isn't on that it
must not be linked up with an encoder (it could simply be switched off
with the dpms state).
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of resetting a few things and hoping that this will work
out.
To properly disable the output pipelines at the initial modeset after
resume or boot up we need to have an accurate picture of which outputs
are enabled and connected to which crtcs. Otherwise we risk disabling
things at the wrong time, which can lead to hangs (or at least royally
confused panels), both requiring a walk to the reset button to fix.
Hence read out the hw state with the freshly introduce get_hw_state
functions and then sanitize it afterwards.
For a full modeset readout (which would allow us to avoid the initial
modeset at boot up) a few things are still missing:
- Reading out the mode from the pipe, especially the dotclock
computation is quite some fun.
- Reading out the parameters for the stolen memory framebuffer and
wrapping it up.
- Reading out the pch pll connections - luckily the disable code
simply bails out if the crtc doesn't have a pch pll attached (even
for configurations that would need one).
This patch here turned up tons of smelly stuff around resume: We
restore tons of register in seemingly random way (well, not quite, but
we're not too careful either), which leaves the hw in a rather
ill-defined state: E.g. the port registers are sometimes
unconditionally restore (lvds, crt), leaving us with an active
encoder/connector but no active pipe connected to it. Luckily the hw
state sanitizer detects this madness and fixes things up a bit.
v2: When checking whether an encoder with active connectors has a crtc
wire up to it, check for both the crtc _and_ it's active state.
v3:
- Extract intel_sanitize_encoder.
- Manually disable active encoders without an active pipe.
v4: Correclty fix up the pipe<->plane mapping on machines where we
switch pipes/planes. Noticed by Chris Wilson, who also provided the
fixup.
v5: Spelling fix in a comment, noticed by Paulo Zanoni
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Similar to the sdvo code we poke the dvo encoder whether the output is
active. Safe that dvo encoders are not standardized, so this requires
a new callback into the dvo chip driver.
Hence implement that for all 6 dvo drivers.
v2: With the newly added ns2501 we now have 6 dvo drivers instead of
just 5 ...
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
SDVO is the first real special case - we support multiple outputs on
the same encoder and the encoder dpms state isn't the same as when
just disabling the outputs when the encoder is cloned.
Hence we need a real connector get_hw_state function which inquires
the sdvo encoder about its active outputs.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Note that even though this connector is cloneable we still can use the
exact same test to check whether the connector is on or whether the
encoder is enabled - both the dpms code and the encoder disable/enable
frob the exact same hw state.
For dvo/sdvo outputs, this will be different.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Also add some macros to make the pipe computation a bit easier.
v2: I've mixed up the CPT and !CPT PORT_TO_PIPE macro variants ...
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It is all glorious if we try really hard to only enable/disable an
entire display pipe to ensure that everyting happens in the right
order. But if we don't know the output configuration when the driver
takes over, this will all be for vain because we'll make the hw angry
right on the first modeset - we don't know what outputs/ports are
enabled and hence have to disable everything in a rather ad-hoc way.
Hence we need to be able to read out the current hw state, so that we
can properly tear down the current hw state on the first modeset.
Obviously this is also a nice preparation for the fastboot work, where
we try to avoid the modeset on driver load if it matches what the hw
is currently using.
Furthermore we'll be using these functions to cross-check the actual
hw state with what we think it should be, to ensure that the modeset
state machine actually works as advertised.
This patch only contains the interface definitions and a little helper
for the simple case where we have a 1:1 encoder to connector mapping.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is the first tiny step towards cross-checking the entire modeset
state machine with WARNs. A crtc can only be enabled when it's
actually in use, i.e. crtc->active imlies crtc->enabled.
Unfortunately we can't (yet) check this when disabling the crtc,
because the crtc helpers are a bit slopy with updating state and
unconditionally update crtc->enabled before changing the hw state.
Fixing that requires quite some more work.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of going through the crtc helper function tables.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the new infrastructure we're doing this when enabling/disabling
the entire display pipe.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- We don't have the ->get_crtc callback.
- Call intel_encoder->disable directly.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Together with the static helper functions drm_crtc_prepare_encoders
and drm_encoder_disable (which will be simplified in the next patch,
but for now are 1:1 copies). Again, no changes beside new names for
these functions.
Also call our new set_mode instead of the crtc helper one now in all
the places we've done so far.
v2: Call the function just intel_set_mode to better differentia it
from intel_crtc_mode_set which really only does the ->mode_set step of
the entire modeset sequence on one crtc. Whereas this function does
the global change.
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Also kill the error-path, we have a fixed connector->encoder mapping.
Unfortunately we can't rip out all the ->best_encoder callbacks, these
are all still used by the fb_helper. Neat helper layering violation there.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And the following static functions required by it:
drm_encoder_crtc_ok, drm_crtc_helper_disable
No changes safe for the s/drm/intel prefix change.
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We no longer need them. And now that all encoders are converted, we
can finally move the cpt modeset check to the right place - at the end
of the crtc_enable function.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
All encoders are now converted so there's no need for these checks any
more.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Yeah, big patch but I couldn't come up with a neat idea of how to
split it up further, that wouldn't break dpms on cloned configs
somehow. But the changes in dvo/sdvo/crt are all pretty much
orthonogal, so it's not too bad a patch.
These are the only encoders that support cloning, which requires a few
special changes compared to the previous patches.
- Compute the desired state of the display pipe by walking all
connected encoders and checking whether any has active connectors.
To make this clearer, drop the old mode parameter to the crtc dpms
function and rename it to intel_crtc_update_dpms.
- There's the curious case of intel_crtc->dpms_mode. With the previous
patches to remove the overlay pipe A code and to rework the load
detect pipe code, the big users are gone. We still keep it to avoid
enabling the pipe twice, but we duplicate this logic with
crtc->active, too. Still, leave this for now and just push a fake
dpms mode into it that reflects the state of the display pipe.
Changes in the encoder dpms functions:
- We clamp the dpms state to the supported range right away. This is
escpecially important for the VGA outputs, where only older hw
supports the intermediate states. This (and the crt->adpa_reg patch)
allows us to unify the crt dpms code again between all variants
(gmch, vlv and pch).
- We only enable/disable the output for dvo/sdvo and leave the encoder
running. The encoder will be disabled/enabled when we switch the
state of the entire output pipeline (which will happen right away
for non-cloned setups). This way the duplication is reduced and
strange interaction when disabling output ports at the wrong time
avoided.
The dpms code for all three types of connectors contains a bit of
duplicated logic, but I think keeping these special cases separate is
simpler: CRT is the only one that hanldes intermediate dpms state
(which requires extra logic to enable/disable things in the right
order), and introducing some abstraction just to share the code
between dvo and sdvo smells like overkill. We can do that once someone
bothers to implement cloning for the more modern outputs. But I doubt
that this will ever happen.
v2: s/crtc/crt/_set_dpms, noticed by Paulo Zanoni.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Similar to crt, this doesn't convert the dpms functions.
Also similar to crt, we don't switch of the display pipe
for the intermediate modes, only DPMS_OFF is truely off.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
CRT is the first output which can be cloned, hence we cannot (yet)
move the dpms handling over to disable/enable. This requires some more
smarts in intel_crtc_dpms first to set the display pipe status
depening upon encoder->connectors_active of all connected encoders.
Because that will happen in a separate step, don't touch the dpms
functions, yet.
v2: Be careful about clearing the _DISABLE flags for intermediate dpms
modes - otherwise we might clobber the crt state when another (cloned)
connector gets enabled.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
DP is the first encoder which isn't simple. As
commit d240f20f54
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Fri Aug 13 15:43:26 2010 -0700
drm/i915: make sure eDP PLL is enabled at the right time
discovered, we need to enable the eDP PLL for the cpu port _before_ we
enable the pipes and planes. After a few more commits the current
solution is to enable the PLL in the dp mode_set function (because
this is the only encoder callback the crtc helper code calls before it
calls the crtc's commit function).
Now I suspect that we actually should enable/disable the entire cpu
eDP port before/after planes, but thanks to how the crtc helper code
assumes that you can disable an encoder without disabling it's crtc
right away, this won't work.
The result is that the current prepare/commit hooks don't touch the
eDP PLL, but instead it get's frobbed in dp_mode_set and in the dp
dpms function. Hence we need to keep things (at least for now)
bug-for-bug compatible by using our own special dp dpms function and
keep everything else more-or-less as-is (just using our own
infrastrucutre now).
This mess can only be cleaned up once we control the entire modeset
sequence and can move things around freely.
v2: Squash unsupported dpms modes to OFF at the beginning of the DP
dpms function.
v3: Need to set the dpms state to off in dp_disable, otherwise this
breaks the newly added WARNs ...
v4: Rebased against edp panel off sequence changes in 3.6-rc2
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the previous patch LVDS is also a simple case. Treat it
accordingly.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like hdmi tv outputs are simple: They only have 2 states and can't be
cloned. Hence give it the same treatment.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I've picked hdmi as the first encoder to convert because it's rather
simple:
- no cloning possible
- no differences between prepare/commit and dpms off/on switching.
A few changes are required to do so:
- Split up the dpms code into an enable/disable function and wire it
up with the intel encoder.
- Noop out the existing encoder prepare/commit functions used by the
crtc helper - our crtc enable/disable code now calls back into the
encoder enable/disable code at the right spot.
- Create new helper functions to handle dpms changes.
- Add intel_encoder->connectors_active to better track dpms state. Atm
this is unused, but it will be useful to correctly disable the
entire display pipe for cloned configurations. Also note that for
now this is only useful in the dpms code - thanks to the crtc
helper's dpms confusion across a modeset operation we can't (yet)
rely on this having a sensible value in all circumstances.
- Rip out the encoder helper dpms callback, if this is still getting
called somewhere we have a bug. The slight issue with that is that
the crtc helper abuses dpms off to disable unused functions. Hence
we also need to implement a default encoder disable function to do
just that with the new encoder->disable callback.
- Note that we drop the cpt modeset verification in the commit
callback, too. The right place to do this would be in the crtc's
enable function, _after_ all the encoders are set up. But because
not all encoders are converted yet, we can't do that. Hence disable
this check temporarily as a minor concession to bisectability.
v2: Squash the dpms mode to only the supported values -
connector->dpms is for internal tracking only, we can hence avoid
needless state-changes a bit whithout causing harm.
v3: Apply bikeshed to disable|enable_ddi, suggested by Paulo Zanoni.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just prep work, not yet put to some use.
Note that because we're still using the crtc helper to switch modes
(and their complicated way to do partial modesets), we need to call
the encoder's disable function unconditionally.
But once this is cleaned up we shouldn't call the encoder's disable
function unconditionally any more, because then we know that we'll
only call it if the encoder is actually enabled. Also note that we
then need to be careful about which crtc we're filtering the encoder
list on: We want to filter on the crtc of the _current_ mode, not the
one we're about to set up.
For the enabling side we need to do the same trick. And again, we
should be able to simplify this quite a bit when things have settled
into place.
Also note that this simply does not take cloning into account, so dpms
needs to be handled specially for the few outputs where we even bother
with it.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just impendance matching with the the crtc helper stuff.
... and somehow the design of this all ended up in this commit here,
too ;-)
The big plan is that this new set of crtc display_funcs take full
responsibility of modeset operations for the entire display output
pipeline (by calling down into object-specific callbacks and
functions). The platform-specific callbacks simply know best what the
proper order is.
This has the drawback that we can't do minimal change-overs any more
if a modeset just disables one encoder in a cloned configuration
(because we will only expose a disable/enable action that takes
down/sets up the entire crtc including all encoders). Imo that's the
only sane way to do it though:
- The use-case for this is pretty minimal, even when presenting (at
least sane people) should use a dual-screen output so that you can
see your notes on your panel. Clone mode is imo BS.
- With all the clone mode constrains, shared resources, and special
ordering requirements (which differ even on the same platform
sometimes for different outputs) there's no way we'd get this right
for all cases. Especially since this is a under-used feature.
- And to top it off: On haswell even dp link re-training requires us
to take down the entire display pipe - otherwise the chip dies.
So the only sane way is to do a full modeset on every crtc where the
output config changes in any way.
To support global modeset (i.e. set the configuration for all crtcs at
once) we'd then add one more function to allocate global and shared
objects in the best ways (e.g. fdi links, pch plls, ...). The crtc
functions would then simply use the pre-allocated stuff (and shouldn't
be able to fail, ever). We could even do all the object pinning in
there (and maybe try to defragment the global gtt if we fail)!
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Because that's what we're essentially calling. This is the first step
in untangling the crtc_helper induced dpms handling mess we have - at
the crtc level we only have 2 states and the magic is just in
selecting which one (and atm there isn't even much magic, but on
recent platforms where not even the crt output has more than 2 states
we could do better).
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The original patch was actually incorrect in stubbing out the sysfs for
l3 parity.
commit 5ab3633d69
Author: Hunt Xu <mhuntxu@gmail.com>
Date: Sun Jul 1 03:45:07 2012 +0000
drm/i915: make rc6 in sysfs functions conditional
Unfortunately Hunt didn't respond to my review comments, and Daniel
sucked in the patch again ignoring. Worst of all, I'm too lazy to write
the patch for what I originally wanted, which was to keep rc6 sysfs even
without CONFIG_PM. This simpler patch does enough to enable us to add
more sysfs entries though.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Previously intel_panel_setup_backlight() would create a sysfs backlight
interface with max brightness of 1 if it was unable to figure out the max
backlight brightness. This rendered the backlight interface useless.
Do not create a dysfunctional backlight interface to begin with.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Tested-by: David Woodhouse <David.Woodhouse@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The same designer from the previous patch has told us to never read
FORCEWAKE. We only do this for the POSTING_READ(), so simply change that
to something within the same cacheline (for no reason in particular
other than it sounds nice). In the _mt case we can leverage
the gtfifodbg check for the POSTING_READ.
This partially reverts
commit 6af2d180f8
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu Jul 26 16:24:50 2012 +0200
drm/i915: fix forcewake related hangs on snb
v2: commit message, comments about posting read from (Daniel)
Note: vlv forcewake doesn't need any changes for this special
treatment since FORCEWAKE_VLV is in a totally different register
range, and the readback FORCEWAKE_ACK_VLV readback that follows is in
the same range.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Added note.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A designer familiar with the hardware has stated that the forcewake
timeout can theoretically be as high as a little over 1ms. Therefore we
modify our code to use 2ms (appropriate fudge and because we don't want
to round down).
Hopefully this can't prevent spurious timeouts.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Acked-by: Chris Wilson <chris@chris-wilson.oc.uk>
[danvet: again fix conflict with vlv patch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As part of the advice given to us from the hardware designers regarding
the maximum wait time on the forcewake handshake we need to move from us
granularity to ms granularity. In earlier patches to do this, Jani
noticed that wait_for_us was properly converted to use cpu_relax(), but
wait_for was not.
The issue has existed since the introduction of the macro:
commit 913d8d1100
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat Aug 7 11:01:35 2010 +0100
drm/i915: Ensure that while(INREG()) are bounded (v2)
CC: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.oc.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's used all over the place, and we want to be able to play around with
the value, apparently. Note that it doesn't touch other timeouts of the
same value (like gtfifo, and thread C0 wait).
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.oc.uk>
[danvet: fixup conflict with vlv forcewake patches.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The sdvo hotplug support check and activation has worked by coincidence for
TMDS0. The boolean value returned by intel_sdvo_supports_hotplug() was
masked with a bit shifted by device number, which also should have been one
of SDVO_OUTPUT_* bits instead. Boolean true masked with 1 shifted by 0 just
happened to match SDVO_OUTPUT_TMDS0...
Get hotplug support as a bit mask, check the correct bits for support, and
use the correct bits for activating hotplug support.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Simon Farnsworth <simon.farnsworth@onelan.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Avoid constant wakeups caused by noisy irq lines when we don't even care
about the irq. This should be particularly useful for i945g/gm where the
hotplug has been disabled:
commit 768b107e4b
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri May 4 11:29:56 2012 +0200
drm/i915: disable sdvo hotplug on i945g/gm
v2: While at it, remove the bogus hotplug_active read, and do not mask
hotplug_active[0] before checking whether the irq is needed, per discussion
with Daniel on IRC.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=38442
Tested-by: Dominik Köppl <dominik@devwork.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For code consolidation and future maintainability.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-and-Tested-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
<ickle> danvet: in the force wake, both DRM_ERRORs have the same string.
<ickle> useful for .txt shrinkage, horrible for debugging
Acked-by: Paul Menzel <paulepanter@users.sourceforge.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For some odd reasons, the vlv forcewake code is rather different from
all other platforms, with no clear justification. Adjust things:
- Don't check whether the gt is awake already (and bail out early), we
need to grab a forcewake anyway. Otherwise the chip might go to
sleep too early. And this would also screw up our forcewake
accounting.
- Like all other platforms, check whether the gt has cleared the
forcewake bit in the _ACK register before setting it again.
- Use _MASKED_BIT_ENABLE/DISABLE macros
- Only use bit0 of the forcewake reg, not all 16 bits.
- check the gtfifodb reg like on all other platforms in _put.
- Drop the POSTING_READs for consistency.
v2: Failure to git add ... again.
v3: Fixup the spelling fail a bit.
Tested-by: "Purushothaman, Vijay A" <vijay.a.purushothaman@intel.com>
Tested-by: "Widawsky, Benjamin" <benjamin.widawsky@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We've had and still have too many issues where the gpu turbo doesn't
quite to what it's supposed to do (or what we want it to do).
Adding a tracepoint to track when the desired gpu frequency changes
should help a lot in characterizing and understanding problematic
workloads.
Also, this should be fairly interesting for power tuning (and
especially noticing when the gpu is stuck in high frequencies, as has
happened in the past) and hence for integration into powertop and
similar tools.
Cc: Arjan van de Ven <arjan@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Paul Menzel <paulepanter@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like with the equivalent change for gen6+ rps state, this helps in
clarifying the code (and in fixing a few places that have fallen through
the cracks in the locking review).
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From Bspec, Vol 2a, Section 1.9.3.4 "PIPE_CONTROL", intro section
detailing the various workarounds:
"[DevIVB {W/A}, DevHSW {W/A}]: Pipe_control with CS-stall bit
set must be issued before a pipe-control command that has the State
Cache Invalidate bit set."
Note that public Bspec has different numbering, it's Vol2Part1,
Section 1.10.4.1 "PIPE_CONTROL" there.
There's also a second workaround for the PIPE_CONTROL command itself:
"[DevIVB, DevVLV, DevHSW] {WA}: Every 4th PIPE_CONTROL command, not
counting the PIPE_CONTROL with only read-cache-invalidate bit(s) set,
must have a CS_STALL bit set"
For simplicity we simply set the CS_STALL bit on every pipe_control on
gen7+
Note that this massively helps on some hsw machines, together with the
following patch to unconditionally set the CS_STALL bit on every
pipe_control it prevents a gpu hang every few seconds.
This is a regression that has been introduced in the pipe_control
cleanup:
commit 6c6cf5aa9c
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Jul 20 18:02:28 2012 +0100
drm/i915: Only apply the SNB pipe control w/a to gen6
It looks like the massive snb pipe_control workaround also papered
over any issues on ivb and hsw.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
[danvet: squashed both workarounds together, pimped commit message
with Bsepc citations, regression commit citation and changed the
comment in the code a bit to clarify that we unconditionally set
CS_STALL to avoid being hurt by trying to be clever.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since gen 7+ now run the new gen7_render_ring_flush function.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For now, just a copy of gen6_render_ring_flush. Different gens have
different workarounds, so we want different functions.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise it just won't compile ...
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@gmail.com>
Avoid constant wakeups caused by noisy irq lines when we don't even care
about the irq. This should be particularly useful for i945g/gm where the
hotplug has been disabled:
commit 768b107e4b
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri May 4 11:29:56 2012 +0200
drm/i915: disable sdvo hotplug on i945g/gm
v2: While at it, remove the bogus hotplug_active read, and do not mask
hotplug_active[0] before checking whether the irq is needed, per discussion
with Daniel on IRC.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=38442
Tested-by: Dominik Köppl <dominik@devwork.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In order to setup the i2c channel, we power up the panel
via ironlake_edp_panel_vdd_on, however it requires
intel_dp->panel_power_up_delay to be initialised,
which hasn't been setup yet.
So move things around so we set the panel power up
values first then init the i2c stuff.
This is one step to fixing the eDP panel in the MBP
from uninitialised state.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes:
"New stuff for -next. Highlights:
- prep patches for the modeset rework. Note that one of those patches
touches the fb helper in the common drm code.
- hasw hdmi audio support (Wang Xingchao)
- improved instdone dumping for gen7 (Ben)
- unbound tracking and a few follow-up patches from Chris
- dma_buf->begin/end_cpu_access plus fix for drm/udl (Dave)
- improve mmio error reporting for hsw
- prep patch for WQ_NON_REENTRANT removal (Tejun Heo)
"
* 'for-airlied' of git://people.freedesktop.org/~danvet/drm-intel: (41 commits)
drm/i915: Remove __GFP_NO_KSWAPD
drm/i915: disable rc6 on ilk when vt-d is enabled
drm/i915: Avoid unbinding due to an interrupted pin_and_fence during execbuffer
drm/i915: Use new INSTDONE registers (Gen7+)
drm/i915: Add new INSTDONE registers
drm/i915: Extract reading INSTDONE
drm/i915: Use a non-blocking wait for set-to-domain ioctl
drm/i915: Juggle code order to ease flow of the next patch
drm/i915: Use cpu relocations if the object is in the GTT but not mappable
drm/i915: Extract general object init routine
drm/i915: Protect private gem objects from truncate (such as imported dmabuf)
drm/i915: Only pwrite through the GTT if there is space in the aperture
i915: use alloc_ordered_workqueue() instead of explicit UNBOUND w/ max_active = 1
drm/i915: Find unclaimed MMIO writes.
drm/i915: Add ERR_INT to gen7 error state
drm/i915: Cantiga+ cannot handle a hsync front porch of 0
drm/i915: fix reassignment of variable "intel_dp->DP"
drm/i915: Try harder to allocate an mmap_offset
drm/i915: Show pin count in debugfs
drm/i915: Show (count, size) of purgeable objects in i915_gem_objects
...
When I pulled-in today's drm-intel-next into linux-next (next-20120824)
I saw this build-breakage:
drivers/gpu/drm/i915/i915_gem.c: In function 'i915_gem_object_get_pages_gtt':
drivers/gpu/drm/i915/i915_gem.c:1778:40: error: '__GFP_NO_KSWAPD' undeclared (first use in this function)
drivers/gpu/drm/i915/i915_gem.c:1778:40: note: each undeclared identifier is reported only once for each function it appears in
This is caused by commit ba099ef165f8 ("mm: remove __GFP_NO_KSWAPD")
and commit b6beae2c2014 ("mm: remove __GFP_NO_KSWAPD fixes") in
linux-next (next-20120824).
Fix this by removing __GFP_NO_KSWAPD from drm/i915 driver.
Signed-off-by: Sedat Dilek <sedat.dilek@gmail.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There was some merge conflicts in -next and they weren't so pretty, so
backmerge now to avoid them.
Conflicts:
drivers/gpu/drm/i915/i915_gem.c
drivers/gpu/drm/i915/intel_modes.c
It blows up. And hopefully this is the root-cause of the mysterious
rc6 related hang on ilk. For reference, the commit that enabled rc6 on
ilk again is:
commit 456470eb58
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Aug 8 23:35:40 2012 +0200
drm/i915: enable rc6 on ilk again
Reported-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we need to stall in order to complete the pin_and_fence operation
during execbuffer reservation, there is a high likelihood that the
operation will be interrupted by a signal (thanks X!). In order to
simplify the cleanup along that error path, the object was
unconditionally unbound and the error propagated. However, being
interrupted here is far more common than I would like and so we can
strive to avoid the extra work by eliminating the forced unbind.
v2: In discussion over the indecent colour of the new functions and
unwind path, we realised that we can use the new unreserve function to
clean up the code even further.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Using the extracted INSTDONE reading, and our new register definitions,
update our hangcheck detection and error collection to use it. This
primarily means changing == to memcmp, and changing = to memcpy.
Hopefully this will give more info on error dump, and provide more
accurate hangcheck detection (both are actually TBD).
Also, remove the reading of instdone1 from the ring error collection
function, and just crap everything in capture_error_state (that could be
split into a separate patch if it wasn't so trivial).
v2: Now assuming i915_get_extra_instdone does the memset we can clean up the
code a bit (Jani)
v3: use ARRAY_SIZE as requested earlier by Jani (didn't change sizeof)
Updated commit msg
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
INSTDONE is used in many places, and it varies from generation to
generation. This provides a good reason for us to extract the logic to
read the relevant information.
The patch has no functional change. It's prep for some new stuff.
v2: move the memset inside of i915_get_extra_instdone (Jani)
v3,4: bugs caught by (Jani)
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This board is incorrectly detected as having an LVDS connector,
resulting in the VGA output (the only available output on the board)
showing the console only in the top-left 1024x768 pixels, and an extra
LVDS connector appearing in X.
It's a desktop Mini-ITX board using an Atom D525 CPU with an NM10
chipset.
I've had this board for about a year, but this is the first time I
noticed the issue because I've been running it headless for most of its
life.
Signed-off-by: Calvin Walton <calvin.walton@kepstin.ca>
The principal use for set-to-domain is for userspace to serialise
operations with a particular buffer, for example to maintain coherency
with a CPU map or to ratelimit its rendering by waiting on all previous
operations before continuing. As such we tend to hold the struct_mutex
for long periods during the synchronisation and so cause contention
issues with other users of the graphics device, even for independent
operations as memory management. An example is the contention between
compiz and X which causes jitter in the display and a drop in peak
throughput.
The ultimate solution would be a set of fine grained locks and lockless
operations, but an intermediate step is to first attempt the
synchronisation for set-to-domain without holding the mutex. This
introduces a number of race conditions, so we limit it use to the ioctl
periphery where we have no dependent state and can safely complete with
a locked synchronisation afterwards.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Move the wait-for-rendering logic around in the file so that we can
group it together with the subsequent variations. The general goal is to
have the lower level routines clustered together and then the higher
level logic building upon those low level routines that came before.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The current layout is to place the per-process tables at the end of the
GTT. However, this is currently using a hardcoded maximum size for the GTT
and not taking in account limitations imposed by the BIOS. Use the value
for the total number of entries allocated in the table as provided by
the configuration registers.
Reported-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Matthew Garret <mjg@redhat.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This prevents the case of unbinding the object in order to process the
relocations through the GTT and then rebinding it only to then proceed
to use cpu relocations as the object is now in the CPU write domain. By
choosing to use cpu relocations up front, we can therefore avoid the
rebind penalty.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we wish to create specialised object constructions in the near
future that share the same basic GEM object struct, export the default
initializer.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If the object has no backing shmemfs filp, then we obviously cannot
perform a truncation operation upon it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Avoid stalling and waiting for the GPU by checking to see if there is
sufficient inactive space in the aperture for us to bind the buffer
prior to writing through the GTT. If there is inadequate space we will
have to stall waiting for the GPU, and incur overheads moving objects
about. Instead, only incur the clflush overhead on the target object by
writing through shmem.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Neither the drm core nor any of the drivers really need the raw_edid field
of struct drm_display_info for anything. Instead of being useful, it
creates confusion about who is responsible for freeing the memory it points
to and setting the field to NULL afterwards, leading to memory leaks and
dangling pointers.
Remove the raw_edid field, and fix drivers as necessary.
Reported-by: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The EDID returned by drm_get_edid() was never freed.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This is an equivalent conversion and will ease scheduled removal of
WQ_NON_REENTRANT.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is already fixed for ILK and SNB in the below commit but somehow
IVB is missed.
commit ab2f9df10d
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Mon Feb 27 12:40:10 2012 -0800
drm/i915: fix color order for BGR formats on SNB
Had the wrong bits and field definitions.
Signed-off-by: Vijay Purushothaman <vijay.a.purushothaman@intel.com>
Reviewed-by: Antti Koskipää <antti.koskipaa@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Wrong order of parameters passed-in when calling hdmi/adpa
/lvds_pipe_enabled(), 2nd and 3rd parameters are reversed.
This bug was indroduced by
commit 1519b9956e
Author: Keith Packard <keithp@keithp.com>
Date: Sat Aug 6 10:35:34 2011 -0700
drm/i915: Fix PCH port pipe select in CPT disable paths
The reachable tag for this commit is v3.1-rc1-3-g1519b99
Signed-off-by: Anhua Xu <anhua.xu@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=44876
Tested-by: Daniel Schroeder <sec@dschroeder.info>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
ERR_INT on HSW will display unclaimed MMIO accesses. This can be either
the result of a driver bug writing to an invalid addresses, or the
result of RC6.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Tested-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Antti Koskipaa <antti.koskipaa@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
ERR_INT can generate interrupts. However since most of the conditions seem
quite fatal the patch opts to simply report it in error state instead of
adding more complexity to the interrupt handler for little gain (the
bits are sticky anyway).
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Tested-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Antti Koskipaa <antti.koskipaa@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This addresses WaPruneModeWithIncorrectHsyncOffset.
Bugzilla: http://bugs.freedesktop.org/show_bug.cgi?id=50236
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In intel_dp_mode_set we OR in the exact same bits twice at the same
spot. Kill one of the redundant assignments.
This little regression was introduced by:
commit 417e822dee
Author: Keith Packard <keithp@keithp.com>
Date: Tue Nov 1 19:54:11 2011 -0700
drm/i915: Treat PCH eDP like DP in most places
PCH eDP has many of the same needs as regular PCH DP connections,
including the DP_CTl bit settings, the TRANS_DP_CTL register.
The reachable tag for this commit is: v3.1-5461-g417e822
Signed-off-by: Anhua Xu <anhua.xu@intel.com>
[danvet: Improved the commit message somewhat and ensured the diff is
clearer.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Given the persistence of an offset for the lifetime of an object, itis
easy to contemplate how the mmap space becomes badly fragmented to the
point that further allocations fail with ENOSPC. Our only recourse at
this point is to try to purge the objects to release some space and
reattempt the allocation.
References: https://bugs.freedesktop.org/show_bug.cgi?id=39552
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A pair of universally true checks that just need to be put in the right
place depending on where in the patch sequence you go. Note that
i915_gem_object_put_pages_gtt() already gains the
BUG_ON(obj->gtt_space), but on reflection that needed to migrate to
put_pages().
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When dealing with a working set larger than the GATT, or even the
mappable aperture when touching through the GTT, we end up with evicting
objects only to rebind them at a new offset again later. Moving an
object into and out of the GTT requires clflushing the pages, thus
causing a double-clflush penalty for rebinding.
To avoid having to clflush on rebinding, we can track the pages as they
are evicted from the GTT and only relinquish those pages on memory
pressure.
As usual, if it were not for the handling of out-of-memory condition and
having to manually shrink our own bo caches, it would be a net reduction
of code. Alas.
Note: The patch also contains a few changes to the last-hope
evict_everything logic in i916_gem_execbuffer.c - we no longer try to
only evict the purgeable stuff in a first try (since that's superflous
and only helps in OOM corner-cases, not fragmented-gtt trashing
situations).
Also, the extraction of the get_pages retry loop from bind_to_gtt (and
other callsites) to get_pages should imo have been a separate patch.
v2: Ditch the newly added put_pages (for unbound objects only) in
i915_gem_reset. A quick irc discussion hasn't revealed any important
reason for this, so if we need this, I'd like to have a git blame'able
explanation for it.
v3: Undo the s/drm_malloc_ab/kmalloc/ in get_pages that Chris noticed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Split out code movements and rant a bit in the commit message
with a few Notes. Done v2]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
James Bottomley reported [1] a massive power regression, due to the
enabling of semaphores by default in 3.5. A workaround for him is to
again disable semaphores. And indeed, his system has a very hard time
to enter rc6 with semaphores enabled.
Ben Widawsky run around with a kill-a-watt a lot and noticed:
- There are indeed a few rare systems that seem to have a hard time
entering rc6 when desktop-idle.
- One machine, The Indestructible Toshiba regressed in this behaviour
between 3.5 and 3.6 in a merge commit! So rc6 behaviour with the
current setting seems to be highly timing dependent and not robust
at all.
- The behaviour James reported wrt semaphores seems to be a freak
timing thing that only happens on his specific machine, confirming
that enabling semaphores shouldn't reduce rc6 residency.
Now furthermore the Google ChromeOS guys reported [2] a while ago that
at least on some machines a simply a blinking cursor can keep the gpu
turbo at the highest frequency. This is because the current rps limits
used on snb/ivb are highly asymmetric.
On the theory that gpu turbo and rc6 tuning values are related, we've
tried whether the much saner looking (since much less asymmetric) rps
tuning values used for hsw would also help entering rc6 more robustly.
And it seems to mostly work, and we don't really have the resources to
through-roughly tune things in any better way: The values from the
ChromeOS ppl seem to fare a bit worse for James' machine, so I guess
we better stick with something vpg (the gpu hw/windows group)
provided, hoping that they've done their jobs.
Reference[1]: http://lists.freedesktop.org/archives/dri-devel/2012-July/025675.html
Reference[2]: http://lists.freedesktop.org/archives/intel-gfx/2012-July/018692.html
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=53393
Tested-by: Ben Widawsky <ben@bwidawsk.net>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Prep work to make Chris Wilson's unbound tracking patch a bit easier
to read. Alas, I'd have preferred that moving the page allocation
retry loop from bind to get_pages would have been a separate patch,
too. But that looks like real work ;-)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Added new haswell_write_eld() to initialize Haswell HDMI audio registers
to generate an unsolicited response to the audio controller driver to
indicate that the controller sequence should start.
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Wang Xingchao <xingchao.wang@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In order for udl vmap to work properly, we need to push the object
into the CPU domain before we start copying the data to the USB device.
This along with the udl change avoids userspace explicit mapping to
be used.
v2: add a flag for userspace to query to know if Intel kernel driver can
deal with the vmap flushing properly. In theory udl would need a flag also,
but I intend to push the patches very close to each other and other drivers
should do the right thing from the start.
I've added a test to my intel-gpu-tools prime branch, however testing
this is a bit messy since the only way to get udl to vmap is to rendering
something. I've tested this with real code as well to make sure it works.
Signed-off-by: Dave Airlie <airlied@redhat.com>
[danvet: resolved conflict, which required reallocating the PARAM
number to 21.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is left over from the old PLL sharing code and isn't useful now
that PLLs are shared when possible.
Signed-off-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
New-ish devices have 3 pipes, so let's not just hardcode 2 but use the
for_each_pipe() macro and make struct intel_display_error_state is big
enough.
V2: Also add the number of pipes emitted (Chris Wilson)
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>
Use _PIPE macro to get correct register definition for IBX/CPT, discard
old variable "i" way.
Signed-off-by: Wang Xingchao <xingchao.wang@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
[danvet: Added the DIP_PORT_SEL #define from a preceeding patch in the
series that needs more work.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
HDMI audio related registers will be configured in write_eld callback.
Signed-off-by: Wang Xingchao <xingchao.wang@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Simply to make the ilk+ crtc disable path clearer and more symmetric
with the enable function.
Also switch to intel_crtc for the enable function.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... and move a few others only used by i915_dma.c into the dri1
dungeon.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
All dvo drivers only support 2 dpms states, and our dvo driver
even switches of the dvo port for anything else than DPMS_ON. Hence
ditch this complexity and simply use bool enable.
While reading through this code I've noticed that the mode_set
function of ch7017 is a bit peculiar - it disable the lvds again, even
though the crtc helper code should have done that ... This might be to
work around an issue at driver load, we pretty much ignore the hw
state when taking over.
v2: Also do the conversion for the new ns2501 driver.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since it's redundant - we can get the attached encoder in the
functions themselves.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A few things need adjustement:
- Change the dpms state by calling the dpms connector function and
not some crtc helper internal callbacks. Otherwise this will break
once we switch to our own dpms handling.
- Instead of tracking and restoring intel_crtc->dpms_mode use the
connector's dpms variable - the former relies on the dpms compuation
rules used by the crtc helper. And it would break when the encoder
is cloned and the other output has a different dpms state. But luckily
no one is crazy enough for that.
- Properly clear the connector -> encoder -> crtc linking, even when
failing (note that the crtc helper removes the encoder -> crtc link
in disabled_unused_functions for us).
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that all affected i830M systems have the pipe A quirk set,
we don't need to do any special dances in the overlay code any
longer. And reading through the code I'm rather dubios that it
actually does what it claims to do ...
As a nice benefit this rips out a users of the crtc helper dpms
callback.
v2: As suggested by Chris Wilson, replace the code by an appropriate
WARN to ensure that the pipe A is indeed running.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the pipe A quirk properly fixed up for i830M, this shouldn't be
required any longer.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For some odd reason we've missed i830 and a i855 variant. Also
kill the two now redundant i830 entries.
v2: Don't add the missing 855 id to the pipe A quirk list, we seem to
lack justification for it.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Wrong order of parameters passed-in when calling hdmi/adpa
/lvds_pipe_enabled(), 2nd and 3rd parameters are reversed.
This bug was indroduced by
commit 1519b9956e
Author: Keith Packard <keithp@keithp.com>
Date: Sat Aug 6 10:35:34 2011 -0700
drm/i915: Fix PCH port pipe select in CPT disable paths
The reachable tag for this commit is v3.1-rc1-3-g1519b99
Signed-off-by: Anhua Xu <anhua.xu@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
GMBUS was enabled over bit-banging as the default in commits:
commit c3dfefa0a6
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue Feb 14 22:37:25 2012 +0100
drm/i915: reenable gmbus on gen3+ again
and
commit 0fb3f969c8
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri Mar 2 19:38:30 2012 +0100
drm/i915: enable gmbus on gen2
Unfortunately, GMBUS seems to fail on some CRT displays. Add a bit-banging
fallback to CRT EDID reads.
LKML-Reference: <201207251020.47637.maciej.rutecki@gmail.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=45881
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Tested-by: Alex Ferrando <alferpal@gmail.com>
Cc: stable@vger.kernel.org (for 3.4+3.5)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Refactor the connector update part of intel_ddc_get_modes() into a separate
intel_connector_update_modes() function for reuse. No functional changes.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=45881
Tested-by: Alex Ferrando <alferpal@gmail.com>
Cc: stable@vger.kernel.org (for 3.4+3.5)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
They've changed it ... for no apparent reason. Meh.
V2: remove unused 'is_hsw' field.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
After reset we unconditionally reinitialize lists. If the context switch
hasn't yet completed before the suspend, the default context object will
end up on lists that are going to go away when we resume.
The patch forces the context switch to be synchronous before suspend
assuring that the active/inactive tracking is correct at the time of
resume.
References: https://bugs.freedesktop.org/show_bug.cgi?id=52429
Tested-by: Guang A Yang <guang.a.yang@intel.com>
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>
The EDID returned by drm_get_edid() was never freed.
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEcBAABAgAGBQJQLWtvAAoJEHm+PkMAQRiG/DYH+wd0FqfEuYkYk4KPyAPuhKpX
zX7HYfLvyJE/ZYIdrhjq1E6Xm2KNr7gtX7/Rdzi2W38M9sjbYzwG1UGIw51qnxWy
yZJH9BGkfyQgQPeuDGohfB6DkDy2JWr2eqMDvakjOwgBsIzji0PQD/f3UvndhtUa
c+tTj/kjavHE1Yr2Wy6OnRZz3Uc0hIMn/Q0JqtbCs3LUgEV1KA4OEAe56XNz4Ku4
WE+FFaGFPvtriQsQON+ohPS5IC8jzQGK/0vbrJ4lWjFnZy4gvZXnborTOwD0WSQG
fbsNuxp1AaM2/pqfMwXm1w0ADvwOITHNiwwXf9id6DoK81QwTFpUdvKpn6yB6gQ=
=rurr
-----END PGP SIGNATURE-----
Merge tag 'v3.6-rc2' into drm-intel-next
Backmerge Linux 3.6-rc2 to resolve a few funny conflicts before we put
even more madness on top:
- drivers/gpu/drm/i915/i915_irq.c: Just a spurious WARN removed in
-fixes, that has been changed in a variable-rename in -next, too.
- drivers/gpu/drm/i915/intel_ringbuffer.c: -next remove scratch_addr
(since all their users have been extracted in another fucntion),
-fixes added another user for a hw workaroudn.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When invalidating the TLBs it is documentated as requiring a post-sync
write. Failure to do so seems to result in a GPU hang.
Exposure to this hang on IVB seems to be a result of removing the extra
stalls required for SNB pipecontrol workarounds:
commit 6c6cf5aa9c
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Jul 20 18:02:28 2012 +0100
drm/i915: Only apply the SNB pipe control w/a to gen6
Note: Manually switch the pipe_control cmd to 4 dwords to avoid a
(silent) functional conflict with -next. This way will get a loud (but
conflict with next (since the scratch_addr has been deleted there).
Reported-and-tested-by: yex.tian@intel.com
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=53322
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: added note about merge conflict with -next.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
eDP is tons of fun. It turns out that at least the new MacBook Air 5,1
model absolutely doesn't like the new force vdd dance we've introduced
in
commit 6cb49835da
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Sun May 20 17:14:50 2012 +0200
drm/i915: enable vdd when switching off the eDP panel
But that patch also tried to fix some neat edp sequence issue with the
force_vdd timings. Closer inspection reveals that we've raised
force_vdd only to do the aux channel communication dp_sink_dpms. If we
move the edp_panel_off below that, we don't need any force_vdd for the
disable sequence, which makes the Air happy.
Unfortunately the reporter of the original bug that the above commit
fixed is travelling, so we can't test whether this regresses things.
But my theory is that since we don't check for any power-off ->
force_vdd-on delays in edp_panel_vdd_on, this was the actual
root-cause of this failure. With that force_vdd dance completely
eliminated, I'm hopeful the original bug stays fixed, too.
For reference the old bug, which hopefully doesn't get broken by this:
https://bugzilla.kernel.org/show_bug.cgi?id=43163
In any case, regression fixers win over plain bugfixes, so this needs
to go in asap.
v2: The crucial pieces seems to be to clear the force_vdd flag
uncoditionally, too, in edp_panel_off. Looks like this is left behind
by the firmware somehow.
v3: The Apple firmware seems to switch off the panel on it's own, hence
we still need to keep force_vdd on, but properly clear it when switching
the panel off.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=45671
Tested-by: Roberto Romer <sildurin@gmail.com>
Tested-by: Daniel Wagner <wagi@monom.org>
Tested-by: Keith Packard <keithp@keithp.com>
Cc: stable@vger.kernel.org
Cc: Keith Packard <keithp@keithp.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
i2c_add_adapter() may do i2c transfers on the bus to detect supported
devices. Therefore the adapter needs to be all set before adding it. This
was not the case for the bit-banging fallback, resulting in an oops if the
device detection GMBUS transfers timed out. Fix the issue by calling
i2c_add_adapter() only after intel_gpio_setup().
LKML-Reference: <5021F00B.7000503@ionic.de>
Tested-by: Mihai Moldovan <ionic@ionic.de>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since forcewake is now protected by a spinlock, we don't need to grab
dev->struct_mutex any more. This way we can also get rid of a stale
comment, noticed by Ben Widawsky while reviewing some locking changes.
v2: Kill the unused variable ret, noticed by Fengguang Wu.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This has originally been introduced to not oversubscribe the dp links
in
commit 885a5fb5b1
Author: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Tue Jan 12 05:38:31 2010 +0800
drm/i915: fix pixel color depth setting on eDP
Since then we've fixed up the dp link bandwidth calculation code and
should now automatically fall back to 6bpc dithering. So this is
unnecessary.
Furthermore it seems to break the new MacbookPro with retina display,
hence let's just rip this out.
Reported-by: Benoit Gschwind <gschwind@gnu-log.net>
Cc: Benoit Gschwind <gschwind@gnu-log.net>
Cc: Francois Rigaut <frigaut@gmail.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: stable@vger.kernel.org
Tested-by: Benoit Gschwind <gschwind@gnu-log.net>
Tested-by: Bernhard Froemel <froemel at vmars tuwien.ac.at>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
--
Testing feedback highgly welcome, and thanks for Benoit for finding
out that the bpc computations are busted.
-Daniel
When you reopen the lid on a laptop with PCH, the panel suddenly goes
blank sometimes. It seems because BLC_PWM_CPU_CTL register is cleared
to zero when BLC_PWM_CPU_CTL2 and BLC_PWM_PCH_CTL1 registers are
enabled.
This patch fixes the problem by moving the call of the function setting
BLC_PWM_CPU_CTL after enabling other two registers.
Reported-and-tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we don't find the exact refresh rate, go with the next one. This
makes some modes work for me. They won't have the best settings, but
will at least have something. Just returning from this function when
we don't find the perfect settings does not help us at all.
Version 2:
- Remove duplicate lines on the clock table.
- Add back debug message with refresh, p, n2 and r2.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- intel_encoder->type is INTEL_OUTPUT_SOMETHING
- drm_encoder->encoder_type is DRM_MODE_ENCODER_SOMETHING
Here we're using intel_encoder, so compare the oranges against
oranges. While at it, rename the variable to "intel_encoder" so we
keep our naming standards used everywhere.
Luckily this was not a bug because both DRM_MODE_ENCODER_DAC and
INTEL_OUTPUT_ANALOG are defined as 1. This is the only case where the
drm definition matches the intel definition.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Avoid the forcewake overhead when simply retiring requests, as often the
last seen seqno is good enough to satisfy the retirment process and will
be promptly re-run in any case. Only ensure that we force the coherent
seqno read when we are explicitly waiting upon a completion event to be
sure that none go missing, and also for when we are reporting seqno
values in case of error or debugging.
This greatly reduces the load for userspace using the busy-ioctl to
track active buffers, for instance halving the CPU used by X in pushing
the pixels from a software render (flash). The effect will be even more
magnified with userptr and so providing a zero-copy upload path in that
instance, or in similar instances where X is simply compositing DRI
buffers.
v2: Reverse the polarity of the tachyon stream. Daniel suggested that
'force' was too generic for the parameter name and that 'lazy_coherency'
better encapsulated the semantics of it being an optimization and its
purpose. Also notice that gen6_get_seqno() is only used by gen6/7
chipsets and so the test for IS_GEN6 || IS_GEN7 is redundant in that
function.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I have the faint hope that the total absence of any locking for the
rps code wasn't too good an idea and could very well have caused some
rc6 related regressions.
Unfortunately we've never managed to reproduce these issues on any of
our own machines, so the only way to go about this is to enable it and
see what happens.
While at it, kill some stale comments and improve the logging.
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We change the drps/ips sw/hw state from different callers: Our own irq
handler, the external intel-ips module and from process context. Most
of these callers don't take any lock at all.
Protect everything by making the mchdev_lock irqsave and grabbing it in
all relevant callsites. Note that we have to convert a few sleeps in the
drps enable/disable code to delays, but alas, I'm not volunteering to
restructure the code around a few work items.
For paranoia add a spin_locked assert to ironlake_set_drps, too.
v2: Move one access inside the lock protection. Caught by the
dev_priv->ips mass-rename ...
v3: Resolve rebase conflict.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Like all the other drps/ips stuff. Hence add the corresponding check,
give the function a preciser prefix and move the single reg clearing into
the rps handling function, too.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's only ever a pointer to the global mchdev_lock, and we don't use
it at all.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This way it's easier so see what belongs together, and what is used
by the ilk ips code. Also add some comments that explain the locking.
Note that (cur|min|max)_delay need to be duplicated, because
they're also used by the ips code.
v2: Missed one place that the dev_priv->ips change caught ...
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's no fun if your shell hangs when the driver has gone on vacation
and you want to know why ...
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Take the dev->struct_mutex around access the corresponding state
(and adjusting the rps hw state).
- Add an assert to gen6_set_rps to ensure we don't forget about this
in the future.
- Don't set up the min/max_freq files if it doesn't apply to the hw.
And do the same for the gen6+ cache sharing file while at it.
v2: Move the gen6+ checks into the read/write callbacks. Thanks to the
awesome drm midlayer we can't check that when registering the debugfs
files, because the driver is not yet fully set up, specifically the
->load callback hasn't run yet.
Oh how I despise this disaster ...
v3: Also add a WARN_ON(mutex_is_locked) in set_rps to check the
locking.
v4: Use mutex_lock_interruptible, suggested by Chris Wilson.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (for v2)
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The update_gfx_val function called from mark_busy wasn't taking the
mchdev_lock, as it should have. Also sprinkle a few spinlock asserts
over the code to document things better.
Things are still rather confusing, especially since a few variables
in dev_priv are used by both the gen6+ rps code and the ilk ips code.
But protected by totally different locks. Follow-on patches will clean
that up.
v2: Don't add a deadlock ... hence split up update_gfx_val into a
wrapper that grabs the lock and an internal __ variant for callsites
within intel_pm.c that already have taken the lock.
v3: Mark the internal helper as static, noticed by Ben Widawsky.
v4: Damien Lespiau had questions about the safety of the ips setup
sequence, explain in a comment why it works.
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By looking at the current way we're using these definitions I don't
think this commit will fix any bug, but programmers from the future
are evil and will certainly find ways to combine macro expansion with
operator precedence to introduce bugs that are hard to find.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It's the only part of the i915_reg.h file that looks totally wrongly
indented, so I assume my editor config is the correct one.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Don't rely on previous values already set on the register. Everything
we're not explicitly setting should be zero for now.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Correctly erase the values previously set and also check for 6bpc and
10bpc.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
During my tests, everything worked even if the wrong polarity was set.
Still, we should try to set the correct values.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Mask the value before changing it and also select DVI when needed.
DVI was working in cases where the BIOS was setting the correct value
because we were not masking the value before changing it.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Handy for lazy people like me, or when people forget to add the output
of lspci -nn.
v2: Chris Wilson noticed that we have this duplicated already in the
i915_capabilites debugfs file. But there \n as separator looks better,
which would be a bit verbose in dmesg. Abuse the preprocessor to
extract this all.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes:
"- Regression fixer for an OOPS at boot when i915.ko is built-in and
CONFIG_PM=n, introduce in 3.5 (patch from Hunt Xu)
- Regression fixer for occlusion query failures, the required w/a wasn't
applied in all cases (thanks to Eric for tracking this on down).
- dmar vs. dma_buf imprt fix (Dave Airlie)
- 2 patches to fight down forcewake issues on snb. This is the stuff I've
talked about 2 weeks ago already, it's a minefield. Investigation still
going on, but afaict this is the best we have for now.
- a few minor things to keep coverty&compiler happy (Alan, Davendra,
Stéphane)
- tons of hsw pci ids - this one is a bit late because internal approval
sometimes takes a while, but ppl in charge finally agreed that world+dog
already knows about ult and crw haswell variants ;-)
Wrt regressions I'm aware of:
- the power regression due to semaphores=1. Ben is running around with a
killawatt, unfortunately we have a hard time reproducing this one. And
this /shouldn't/ increase power usage. Ben has turned up a few odds bits
though already.
- the lvds fix in 3.6-rc1 broke a backlight after lid close/open (but can
be resurrected with a modeset cycle). I guess we anger the bios - I'm
still looking into this one.
- gmbus broke edid reading on an odd-ball monitor, we need to fall-back.
Due to vacation (both mine&the reporter's) this is stalling for a final
patch and a tested-by on it. But issue is fully diagnosed."
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel:
drm/i915: correctly order the ring init sequence
drm/i915: add more Haswell PCI IDs
drm/i915: make rc6 in sysfs functions conditional
drm/i915: Workaround hang with BSD and forcewake on SandyBridge
drm/i915: Make intel_panel_get_backlight static.
i915: don't map imported dma-bufs for dmar.
drm/i915: remove unused variable
drm/i915: Don't forget to apply SNB PIPE_CONTROL GTT workaround.
drm/i915: fix forcewake related hangs on snb
i915: Remove silly test
i915: fix error path leak in intel_sdvo_write_cmd
vlv: it might be wise if we initialised the flag value...
In commit
commit 20b46e59dd
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu Jul 26 11:16:14 2012 +0200
drm/i915: Only set the down rps limit when at the loweset frequency
The computation for the new desired frequency was extracted, but since
the desired frequency was passed-by value, the adjustments didn't
propgate back. Fix this.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Userspace tries to estimate the cost of ring switching based on whether
the GPU and GEM supports semaphores. (If we have multiple rings and no
semaphores, userspace assumes that the cost of switching rings between
batches is exorbitant and will endeavour to keep the next batch on the
active ring - as a coarse approximation to tracking both destination and
source surfaces.) Currently userspace has to guess whether semaphores
exist based on the chipset generation and the module parameter,
i915.semaphores. This is a crude and inaccurate guess as the defaults
internally depend upon other chipset features being enabled or disabled,
nor does it extend well into the future. By exporting a HAS_SEMAPHORES
parameter, we can easily query the driver and obtain an accurate answer.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We may only start to set up the new register values after having
confirmed that the ring is truely off. Otherwise the hw might lose the
newly written register values. This is caught later on in the init
sequence, when we check whether the register writes have stuck.
Cc: stable@vger.kernel.org
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50522
Tested-by: Yang Guang <guang.a.yang@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The requirements for the sync flush to be emitted prior to the render
cache flush is only true for SandyBridge. On IvyBridge and friends we
can just emit the flushes with an inline CS stall.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Also properly indent the HB IDs.
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Commit 0136db586c merges rc6 information
into the power group. However, when compiled with CONFIG_PM not set,
modprobing i915 would taint since power_group_name is defined as NULL.
This patch makes these rc6 in sysfs functions conditional upon the
definition of the CONFIG_PM macro to avoid the above-mentioned problem.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=45181
Cc: stable@vger.kernel.org
Tested-by: Kris Karas <bugs-a12@moonlit-rail.com>
Signed-off-by: Hunt Xu <mhuntxu@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For reasons that are not apparent to anybody, 990bbdadab (drm/i915:
Group the GT routines together in both code and vtable) breaks the use
of the BitStream Decoder ring on SandyBridge. The active ingredient of
that patch is the conversion from a udelay(10) to a udelay(1) in the
busy-wait loop of waiting for the forcewake acknowledge. If we restore
that udelay(10) or insert another udelay(1) afterwards (or any wait
longer than 250ns) everything works again. An alternative is also to
remove any delay from the busy-wait loop.
Given that in the atomic sections we want to complete the wait as quick
as possible to avoid blocking the CPU for too long, it makes sense to
remove the delay altogether and simply spin on the exit condition until
it completes. So we replace the udelay(1) with cpu_relax().
Papers over regression from
commit 990bbdadab
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon Jul 2 11:51:02 2012 -0300
drm/i915: Group the GT routines together in both code and vtable
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51738
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This function isn't used outside of intel_panel.c, so make it static.
Signed-off-by: Stéphane Marchesin <marcheu@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The exporter should have given us pages in the correct place, avoid
the prepare object mapping phase on dmar systems.
This fixes an oops on a GM45/R600 machine, when running the intel/radeon
tests.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
the following warning was produced,
drivers/gpu/drm/i915/i915_gem_context.c: In function ‘i915_switch_context’:
drivers/gpu/drm/i915/i915_gem_context.c:454:6: warning: unused variable ‘ret’ [-Wunused-variable]
fix up by removing it
Signed-off-by: Devendra Naga <devendra.aaru@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If a buffer that was the target of a PIPE_CONTROL from userland was a
reused one that hadn't been evicted which had not previously had this
workaround applied, then the early return for a correct
presumed_offset in this function meant we would not bind it into the
GTT and the write would land somewhere else.
Fixes reproducible failures with GL_EXT_timer_query usage in apitrace,
and I also expect it to fix the intermittent OQ issues on snb that
danvet's been working on.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=48019
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=52932
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Carl Worth <cworth@cworth.org>
Tested-by: Carl Worth <cworth@cworth.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... by adding seemingly redudant posting reads.
This little dragon lair exploded the first time around when we've
refactored the code a bit to use the common wait_for_atomic_us in
"drm/i915: Group the GT routines together in both code and vtable",
which caused QA to file fdo bug #51738.
Chris Wilson entertained a few approaches to fixing #51738: Replacing
the udelay(1) with the previously-used udelay(10) (or any other
"sufficiently larger" delay), adding a posting read, or ditching the
delay completely and using cpu_relax. We went with the cpu_relax and
"915: Workaround hang with BSD and forcewake on SandyBridge". Which
blew up in fdo bug #52424, but adding the posting read while still
using cpu_relax seems to also fix that, it looks like the
posting read is the important ingriedient to fix these rc6 related
hangs on snb.
Popular theories as to why this is like it is include:
- A herd of pink elephants got royally angered somehow.
- The gpu has internally different functional units and judging by the
register offsets, the forcewake request register and the forcewake
ack registers are _not_ in the same functional unit (or at least
aren't reached through the same routes). Hence the posting read
syncs up with the wrong block and gets the entire gpu confused.
- ...
As a minimal ducttape fix for 3.6, let's just put these posting reads
into place again. We can try fancier approaches (like adding back the
cpu_relax instead of the udelay) in -next.
This (re-)fixes a regression introduced in
commit 990bbdadab
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon Jul 2 11:51:02 2012 -0300
drm/i915: Group the GT routines together in both code and vtable
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Du Yan <yanx.du@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=52424
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51738u
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We should not hit this under any sane conditions, but still, this does not
looks right.
CC: Chris Wilson <chris@chris-wilson.co.uk>
CC: Daniel Vetter <daniel.vetter@ffwll.ch>
CC: stable@vger.kernel.org
Reported-by: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com>
Reviewed-by: Chris Wlison <chris@chris-wilson.co.uk>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We believe to have squashed all issues around the gen6+ rps interrupt
generation and why the gpu sometimes got stuck. With that cleared up,
there's no user left for the sanitize_pm infrastructure, so let's just
rip it out.
Note that 'intel_reg_write 0xa014 0x13070000' is the w/a if we find
ourselves stuck again.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The power docs say that when the gt leaves rc6, it is in the lowest
frequency and only about 25 usec later will switch to the frequency
selected in GEN6_RPNSWREQ. If the downclock limit expires in that
window and the down limit is set to the lowest possible frequency, the
hw will not send the down interrupt. Which leads to a too high gpu
clock and wasted power.
Chris Wilson already worked on this with
commit 7b9e0ae6da
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat Apr 28 08:56:39 2012 +0100
drm/i915: Always update RPS interrupts thresholds along with
frequency
but got the logic inverted: The current code set the down limit as
long as we haven't reached it. Instead of only once with reached the
lowest frequency.
Note that we can't always set the downclock limit to 0, because
otherwise the hw will keep on bugging us with downclock request irqs
once the lowest level is reached.
For similar reasons also always set the upclock limit, otherwise the
hw might poke us again with interrupts.
v2: Chris Wilson noticed that the limit reg is also computed in
sanitize_pm. To avoid duplication, extract the code into a common
function.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By selecting the cache level (essentially whether or not the CPU snoops
any updates to the bo, and on more recent machines whether it resides
inside the CPU's last-level-cache) a userspace driver is able to then
manage all of its memory within buffer objects, if it so desires. This
enables the userspace driver to accelerate uploads and more importantly
downloads from the GPU and to able to mix CPU and GPU rendering/activity
efficiently.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Added code comment about where we plan to stuff platform
specific cacheing control bits in the ioctl struct.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Several functions of the GPU have the restriction that differing memory
domains cannot be placed next to each other (as the GPU may prefetch
beyond the end of one domain and hang as it crosses into the other
domain). We use the facility of the drm_mm to mark ranges with a
particular color that corresponds to the cache attributes of those pages
in order to prevent allocating adjacent blocks of differing memory
types.
v2: Rebase ontop of drm_mm coloring v2.
v3: Fix rebinding existing gtt_space and add a verification routine.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drv_priv->gmbus is an array. Comparing it with NULL is somewhat less useful
than a chocolate teapot.
Possibly we should be testing bus != NULL each iteration of the loop
instead ?
gcc could help by warning too!
Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise our initial behaviour is "randomly save a bogus PLL
choice" as far as I can see.
Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel writes: (this pull is the one with the bad patch dropped)
First pile of fixes for 3.6 already, and I'm afraid it's a bit larger than
what I'd wish for. But I've moved all the feature-y stuff to -next, so
this really is all -fixes. Most of it is handling fallout from the hw
context stuff, discovered now that mesa git has started using them for
real. Otherwise all just small fixes:
- unbreak modeset=0 on gen6+ (regressed in next)
- const mismatch fix for ->mode_fixup
- simplify overly clever lvds modeset code (current code can totally
confuse backlights, resulting in broken panels until a full power draw
restores them).
- fix some fallout from the flushing_list disabling (regression only
introduced in -next)
- DP link train improvements (this also kills the last 3.2 dp regression
afaik)
- bugfix for the new ddc VGA detection on newer platforms
- minor backlight fixes (one of them a -next regression)
- only enable the required PM interrupts (to avoid waking up the cpu
unnecessarily)
- some really minor bits (workaround clarification, make coverty happy,
hsw init fix)
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel: (23 commits)
drm/i915: unbreak lastclose for failed driver init
drm/i915: Set the context before setting up regs for the context.
drm/i915: constify mode in crtc_mode_fixup
drm/i915/lvds: ditch ->prepare special case
drm/i915: dereferencing an error pointer
drm/i915: fix invalid reference handling of the default ctx obj
drm/i915: Add -EIO to the list of known errors for __wait_seqno
drm/i915: Flush the context object from the CPU caches upon switching
drm/i915: Make the lock for pageflips interruptible
drm/i915: don't forget the PCH backlight registers
drm/i915: Insert a flush between batches if the breadcrumb was dropped
drm/i915: missing error case in init status page
drm/i915: mask tiled bit when updating ILK sprites
drm/i915: try to train DP even harder
drm/i915: kill intel_ddc_probe
drm/i915: check whether we actually received an edid in detect_ddc
drm/i915: fix up PCH backlight #define mixup
drm/i915: Add comments to explain the BSD tail write workaround
drm/i915: Disable the BLT on pre-production SNB hardware
drm/i915: initialize power wells in modeset_init_hw
...
Originally I had a macro specifically for DPF support, and Daniel, with
good reason asked me to change it to this. It's not the way I would have
gone (and indeed I didn't), but for now there is no distinction as all
platforms with L3 also have DPF.
Note: The good reasons are that dpf is a l3$ feature (at least on
currrent hw), hence I don't expect one to go without the other.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: added note]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Basic context support on HSW is no different than previous generations.
The size of the context object changes, but that's about it.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As suggested by Daniel, rip out the independent timers for device and
crtc busyness and integrate the manual powermanagement of the display
engine into the GEM core and its request tracking. The benefits are that
the code is a lot smaller, fewer moving parts and should fit more neatly
into the overall activity tracking of the driver.
v2: Complete overhaul and removal of the racy timers and workers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By moving the function to intel_ringbuffer and currying the appropriate
parameter, hopefully we make the callsites easier to read and
understand.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise once we use the buffer with a BLT command on gen2/3, we will
always regard future command submissions as continuing the fenced
access. However, now that we flush/invalidate between every batch we can
drop this pessimism.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we unconditionally flush and invalidate between every batch
buffer, we no longer need the complex logic to decide which domains
require flushing. Remove it and rejoice.
v2 (danvet): Keep around the flip waiting logic. It's gross and
broken, I know, but we can't just kill that thing ... even if we just
keep it around as a reminder that things are broken.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Rely instead on the insertion of the implicit flush before the seqno
breadcrumb.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As the flush is either performed explictly immediately after the
execbuffer dispatch, or before the serialisation of last_fenced_seqno we
can forgo the explict i915_gem_flush_ring().
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is now handled by a global flag to ensure we emit a flush before
the next serialisation point (if we failed to queue one previously).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we guarantee to emit a flush before emitting the breadcrumb or
the next batchbuffer, there is no further need for the flushing list.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we always flush the GPU cache prior to emitting the breadcrumb, we no
longer have to worry about the deferred flush causing the
pending_gpu_write to be delayed. So we can instead utilize the known
last_write_seqno to hopefully minimise the wait times.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we move to lazily clearing the GPU write domain only when the buffer
becomes inactive, this leaves a window of opportunity for
i915_gem_object_pin_to_display_plane() to detect a seemingly
inconsistent value. This function is special as it tries to pipeline the
operation to avoid the stall and so may not retires the buffer and we
may not get the opportunity to clear the write domain. However, we know
all is good, so drop the assertion.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Request preallocation was added to i915_add_request() in order to
support the overlay. However, not all users care and can quite happily
ignore the failure to allocate the request as they will simply repeat
the request in the future.
By pushing the allocation down into i915_add_request(), we can then
remove some rather ugly error handling in the callers.
v2: Nullify request->file_priv otherwise we chase a garbage pointer
when retiring requests.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the base addresses shifting around, this is easier to handle.
Also move to the real reg offset on vlv.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The intention is to help select which engine to use for copies with
interoperating clients - such as a GL client making a request to the X
server to perform a SwapBuffers, which may require copying from the
active GL back buffer to the X front buffer.
We choose to report a mask of the active rings to future proof the
interface against any changes which may allow for the object to reside
upon multiple rings.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: bikeshed away the write ring mask and add the explanation
Chris sent in a follow-up mail why we decided to use masks.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The interface's immediate purpose is to do synchronous timestamp queries
as required by GL_TIMESTAMP. The GPU has a register for reading the
timestamp but because that would normally require root access through
libpciaccess, the IOCTL can provide this service instead.
Currently the implementation whitelists only the render ring timestamp
register, because that is the only thing we need to expose at this time.
v2: make size implicit based on the register offset
Add a generation check
Reviewed-by: Eric Anholt <eric@anholt.net>
Cc: Jacek Lawrynowicz <jacek.lawrynowicz@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: fixup the ioctl numerb:]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch adds support for the ns2501 DVO, found in some older Fujitsu/Siemens Labtops.
It is in the state of "works for me".
Includes now proper DPMS support. Includes switching between resolutions -
from 640x480 to 1024x768.
Currently assumes that the native display resolution is 1024x768.
The ns2501 seems to be rather critical - if the output PLL is not
running, the chip doesn't seem to be clocked and then doesn't react
on i2c messages. Thus, a quick'n-dirty trick ensures that the DVO
is active before submitting any i2c messages to it. This is
probably to be reviewed.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=17902
Signed-off-by: Thomas Richter <thor@math.tu-berlin.de>
[danvet: fixup whitespace fail.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This will be needed for Haswell, but already has its uses here.
This patch started as a small patch written patch by Shobhit Kumar,
but it has changed so much that none of its original lines remain.
Credits-to: Shobhit Kumar <shobhit.kumar@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We have some common code that we always run before calling
intel_dp_set_link_train. This common code sets the correct training
patterns to the DP variable. If we add more calls to
intel_dp_set_link_train, we'll also have to duplicate this common
code. So instead of repeating this code whenever we call
intel_dp_set_link_train, we move the code to inside the function: now
we check which training pattern we're going to set and then we set the
DP register according to it.
One of the side-effects of this change is that now we never forget to
mask the training pattern bits before changing them. It looks like
this was working before because we were first masking the bits, then
writing 00, 01 and then 11.
This patch also enables us to use the intel_dp_set_link_train function
when disabling link training: in this case we need to avoid writing
the DP_TRAINING_LANE*_SET AUX commands.
As a bonus, the big intel_dp_{start,complete}_link_train functions
will get smaller and a little bit easier to read.
Version 2 changes:
- Rewrite commit message.
- Also clear the training pattern bits before changing them.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of having a giant if cascade to figure this out according to
the passed-in register. We could do quite a bit more cleaning up and
all by using the port at more places, but I think this should be part
of a bigger rework to introduce a struct intel_digital_port which
would keep track of all these things. I guess this will be part of
some haswell-DP-induced refactoring.
For now this rips out the big cascade, which is what annoyed me so
much.
v2: Add port variable name back for the func decl (I've tried to trick
myself below the 80 char limit).
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Intel hw only has one MUX for encoders, so outputs are either not
cloneable or all in the same group of cloneable outputs. This neatly
simplifies the code and allows us to ditch some ugly if cascades in
the dp and hdmi init code (well, we need these if cascades for other
stuff still, but that can be taken care of in follow-up patches).
Note that this changes two things:
- dvo can now be cloned with sdvo, but dvo is gen2 whereas sdvo is
gen3+, so no problem. Note that the old code had a bug and didn't
allow cloning crt with dvo (but only the other way round).
- sdvo-lvds can now be cloned with sdvo-non-tv. Spec says this won't
work, but the only reason I've found is that you can't use the
panel-fitter (used for lvds upscaling) with anything else. But we
don't use the panel fitter for sdvo-lvds. Imo this part of Bspec is
a) rather confusing b) mostly as a guideline to implementors (i.e.
explicitly stating what is already implicit from the spec, without
always going into the details of why). So I think we can ignore this
- worst case we'll get a bug report from a user with with sdvo-lvds
and sdvo-tmds and have to add that special case back in.
Because sdvo lvds is a bit special explain in comments why sdvo LVDS
outputs can be cloned, but native LVDS and eDP can't be cloned - we
use the panel fitter for the later, but not for sdvo.
Note that this also uncoditionally initializes the panel_vdd work used
by eDP. Trying to be clever doesn't buy us anything (but strange bugs)
and this way we can kill the is_edp check.
v2: Incorporate review from Paulo
- Add in a missing space.
- Pimp comment message to address his concerns.
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Splitting them up between pch and gmch variants just makes it harder
to find things. Especially since the hotplug bits are actually valid
on earlier chips, too.
v2: Fixed the comment as pointed out by Paulo Zanoni.
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When bug hunting, I found the interface to do_switch() overly
complicated and I believe festered the earlier bug. This aims to make
the code a little clearer.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Move the DP structure to shared location so that it can be used from
within the ddi module.
Changes from Paulo:
- Move less code to intel_drv.h
- Remove #include statement
- Replace a tab with a space in train_set
Signed-off-by: Shobhit Kumar <shobhit.kumar@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We now refuse to load on gen6+ if kms is not enabled:
commit 26394d9251
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon Mar 26 21:33:18 2012 +0200
drm/i915: refuse to load on gen6+ without kms
Which results in the drm core calling our lastclose function to clean
up the mess, but that one is neatly broken for such failure cases
since kms has been introduced in
commit 79e539453b
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Fri Nov 7 14:24:08 2008 -0800
DRM: i915: add mode setting support
Reported-and-tested-by: Paulo Zanoni <przanoni@gmail.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Fixes failures in transform feedback on gen7 because our SOL_RESET
flag was setting the transform feedback offsets in the old context
(occasionally happened to be ours) instead of the new context.
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
LVDS is the first output where dpms on/off and prepare/commit don't
perfectly match. Now the idea behind this special case seems to be
that for simple resolution changes on the LVDS we don't need to stop
the pipe, because (at least on newer chips) we can adjust the panel
fitter on the fly.
There are a few problems with the current code though:
- We still stop and restart the pipe unconditionally, because the crtc
helper code isn't flexible enough.
- We show some ugly flickering, especially when changing crtcs (this
the crtc helper would actually take into account, but we don't
implement the encoder->get_crtc callback required to make this work
properly).
So it doesn't even work as advertised. I agree that it would be nice
to do resolution changes on LVDS (and also eDP) whithout blacking the
screen where the panel fitter allows to do that. But imo we should
implement this as a special case a few layers up in the mode set code,
akin to how we already detect simple framebuffer changes (and only
update the required registers with ->mode_set_base).
Until this is all in place, make our lives easier and just rip it out.
Also note that this seems to fix actual bugs with enabling the lvds
output, see:
http://lists.freedesktop.org/archives/intel-gfx/2012-July/018614.html
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Giacomo Comes <comes@naic.edu>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Takashi Iwai <tiwai@suse.de>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We need to check that "ctx" is a valid pointer before dereferencing it.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Otherwise we end up trying to unpin a freed object and BUG.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This prevents a WARN introduced with
commit de2b998552
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jul 4 22:52:50 2012 +0200
drm/i915: don't return a spurious -EIO from intel_ring_begin
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The issue is that we stale data in the CPU caches, when we come to
swap-out the object, the CPU may short-circuit the reads from those
cacheline and so corrupt the context object.
Secondary, leaving the context object as being marked in the CPU write
domain whilst on the GPU active list is a bad idea and will throw
warnings later.
Note: Thanks to calling set_to_gtt_domain with write = false and not
setting any gpu write domain when putting a context object onto the
active list (when we switch away from it) the set_to_gtt_domain call
won't block.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Added a note to the commit message and a comment in the code
to explain the clever non-blocking trick.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we take the struct_mutex lock to access the command-stream, there is
a possibility that we may need to wait for a GPU hang and so should make
the lock both interruptible and error-checking.
References: https://bugs.freedesktop.org/show_bug.cgi?id=50069
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we enable/disable the CPU backlight registers we can't forget to
enable/disable the PCH backlight registers. Since we're using the CPU
registers we should also unset the override bit.
Fixes a regression on the following commit:
drm/i915: properly enable the blc controller on the right pipe
The commit just deleted the code that sets the PCH registers, so it
was relying on the values set by the BIOS. I told my BIOS to boot on
the DVI monitor instead of the LVDS panel, so I noticed the bug.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we drop the breadcrumb request after a batch due to a signal for
example we aim to fix it up at the next opportunity. In this case we
emit a second batchbuffer with no waits upon the first and so no
opportunity to insert the missing request, so we need to emit the
missing flush for coherency. (Note that that invalidating the render
cache is the same as flushing it, so there should have been no
observable corruption.)
Note that beside simply adding the missing flush, avoiding potential
render corruption, this will also fix at least parts of the problem
introduced by some funny interaction of these two commits:
commit de2b998552
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jul 4 22:52:50 2012 +0200
drm/i915: don't return a spurious -EIO from intel_ring_begin
which allowed intel_ring_begin to return -ERESTARTSYS and
commit cc889e0f6c
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jun 13 20:45:19 2012 +0200
drm/i915: disable flushing_list/gpu_write_list
which essentially disabled the flushing list.
The issue happens when we submit a batch & emit it, but get
interrupted (thanks to the first patch) while trying to emit the
flush. On the next batch we still assume that the full gpu domain
handling is in effect and hence compute the invalidate&flushing
domains. But thanks to the 2nd patch we totally ignore these and only
invalidate all gpu domains, presuming that any required flushes have
been issued already. Which is wrong and eventually results in us
updating the new write_domain values with the computed
pending_write_domain values, which leaves an object with write_domain
== 0 on the gpu_write_list.
As soon as we try to unbind that object, things blow up.
Fix this by emitting the missing flush according to the new
ring->gpu_caches_dirty flag.
Note that this does _not_ fix all the current cases where we end up
with an object on the flushing_list that can't be flushed.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=52040
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add bug explanation to commit message.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Or going from tiled to untiled may break.
Signed-off-by: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
While debugging Haswell link train failures I observed that we never
try the maximum voltage configuration more than once consecutively. We
start the training, the monitor keeps telling us to increase the
voltage, then when we reach the maximum we just go back to the start
(because of the "memset" above "voltage_tries = 0"). When we reach
this point, we keep alternating between the maximum and the minimum
voltages until we give up.
The DP spec suggests that we should try the same voltage 5 times
before giving up. This patch makes us try the maximum voltage at
least 5 times before going back to the minimum voltages.
This patch does not fix any particular bug I'm aware of.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We have way too much lying hardware to rely on a simple "does someone
answer on the ddc i2c address?" check. And now it's unused, so just
kill it.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Somehow detect_ddc manages to fall through all checks when we think
that something responds on the ddc i2c address, but the edid read
failed. Fix this up by explicitly checking for this case.
This fixes a regression on newer chips because since
commit aaa377302b
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Sat Jun 16 15:30:32 2012 +0200
drm/i915/crt: Do not rely upon the HPD presence pin
we use ddc detection also on hotplug capable platforms. And one of
these reads all 0s for any i2c transaction if nothing is connected to
the vga port.
v2: Implement Chris Wilson's review:
- simplify logic, default to "nothing detected"
- kill stale comment
- BUG_ON(!crt->type != ANALOG)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51900
Tested-by: Yang Guang <guang.a.yang@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I so totally suck.
This can cause a black screen if (for whatever reason) the bios
hasn't set this bit itself.
This regression has been introduced in
commit 7cf4160148
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue Jun 5 10:07:09 2012 +0200
drm/i915: clear up backlight #define confusion on gen4+
Tested-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Having had to dive into the bspec to understand what each stage of the
workaround meant, and how that the ring broadcasting IDLE corresponded
with the GT powering down the ring (i.e. rc6) add comments to aide
the next reader.
And since the register "is used to control all aspects of PSMI and power
saving functions" that makes it quite interesting to inspect with
regards to RC6 hangs, so add it to the error-state.
v2: Rediscover the piece of magic, set the RNCID to 0 before waiting for
the ring to wake up.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It never quite worked despite the numerous workarounds, yet I still see
people trying to use this hardware and filing bug reports. As we no
longer even try to implement the workarounds, since 6a233c7887
(drm/i915/ringbuffer: kill snb blt workaround), simply disable the ring.
v2: Add a message to inform the user about the limited capabilities of
their pre-production hardware.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This initializes power wells within the modeset_init_hw routine.
Testing has shown that this works for both driver load time and for
suspend-resume code paths.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There is little point waking up every 10ms to service an interrupt which
we then promptly ignore. So only program the the PMIER to enable
interrupts for those events which we do handle, not all of them!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Cc: Eugeni Dodonov <eugeni.dodonov@intel.com>
Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There were some fields missed. Daniel pointed this out in review, and I
know I fixed it, but something happened somehow and some time.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
*sigh* the docs had it spelled wrong, corrected it, and then proceeded
to re-do the original error. The original code preserved this history,
and this patch attempts to keep in sync with the current docs.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEcBAABAgAGBQJQAfWKAAoJEHm+PkMAQRiG/DwIAIullMhkDhD/GJcn24ZbUJoa
v6zRPK2hIavuKH/6bUoUiXT346PUYgVnRMhetuYKJFURz6KX/nmlxve/iXNn/WP1
9hnxhE+zcnp2qKI83c3Yok09eed1KnGY5hWQkqXM2gzji/OU0pCKchOcL01l//uz
iiWpNAXEVUnT92CafnHlZ55f/MWVqRFmDKi3Ty1YKSskhojQ6NOPsWCxrTxKVbim
2YPXc3D+xLHzF12ufVgla20AF4KnK8m+tFugniRAqArIagpzBUP1x1wk0RN5PyBD
FTP8lv7bSfBusp41/mPDB66WAe9EfQBoWQY6jloJjp0i8xnMyH5V05pImBV5NwU=
=O+gl
-----END PGP SIGNATURE-----
Merge tag 'v3.5-rc7' into drm-next
Merge Linus tree into drm to fixup conflicts in radeon code for further
testing before upstream merge.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Conflicts:
drivers/gpu/drm/i915/i915_dma.c
drivers/gpu/drm/i915/intel_display.c
drivers/gpu/drm/radeon/radeon_gart.c
All leftover users either haven't set DRIVER_HAVE_DMA, in which
case this will never be called, or use the drm_core implementation.
Call that directly in the only callsite.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The passed mode must not be modified by the operation, make it const.
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
In order to support snoopable memory on non-LLC architectures (so that
we can bind vgem objects into the i915 GATT for example), we have to
avoid the prefetcher on the GPU from crossing memory domains and so
prevent allocation of a snoopable PTE immediately following an uncached
PTE. To do that, we need to extend the range allocator with support for
tracking and segregating different node colours.
This will be used by i915 to segregate memory domains within the GTT.
v2: Now with more drm_mm helpers and less driver interference.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dave Airlie <airlied@redhat.com
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@gmail.com>
Daniel writes:
New pull for -next. Highlights:
- rc6/turbo support for hsw (Eugeni)
- improve corner-case of the reset handling code - gpu reset handling
should be rock-solid now
- support for fb offset > 4096 pixels on gen4+ (yeah, you need some fairly
big screens to hit that)
- the "Flush Me Harder" patch to fix the gen6+ fallout from disabling the
flushing_list
- no more /dev/agpgart on gen6+!
- HAS_PCH_xxx improvements from Paulo
- a few minor bits&pieces all over, most of it in thew hsw code
* tag 'drm-intel-next-2012-07-06' of git://people.freedesktop.org/~danvet/drm-intel: (40 commits)
drm/i915: program FDI_RX TP and FDI delays
drm/i915: introduce for_each_encoder_on_crtc
drm/i915: adjust framebuffer base address on gen4+
drm/i915: introduce crtc->dspaddr_offset
drm/i915: Reject page flips with changed format/offset/pitch
drm/i915: Zero initialize mode_cmd
drm/i915: don't return a spurious -EIO from intel_ring_begin
drm/i915: properly SIGBUS on I/O errors
drm/i915: don't hang userspace when the gpu reset is stuck
drm/i915: non-interruptible sleeps can't handle -EAGAIN
drm/i915: don't trylock in the gpu reset code
drm/i915: fix PIPE_DDI_PORT_MASK
drm/i915: prevent bogus intel_update_fbc notifications
drm/i915: re-initialize DDI buffer translations after resume
drm/i915: don't ironlake_init_pch_refclk() on LPT
drm/i915: get rid of dev_priv->info->has_pch_split
drm/i915: add PCH_NONE to enum intel_pch
drm/i915: prefer wide & slow to fast & narrow in DP configs
drm/i915: fix up ilk rc6 disabling confusion
drm/i915: move force wake support into intel_pm
...
This is required for a stable FDI connection.
v2: fix and simplify the FDI_RX_MISC bits as noticed by Paulo Zanoni.
CC: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We already have this pattern at quite a few places, and moving part of
the modeset helper stuff into the driver will add more.
v2: Don't clobber the crtc struct name with the macro parameter ...
v3: Convert two more places noticed by Paulo Zanoni.
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The tileoffset register only supports a limited offset in x/y of 4096,
so for giant screen configuration with a shared fb we wrap around.
Fix this by computing a linear offset in tiles (pages) and only use
the tileoffset register to offset within the tile.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
To avoid recomputing the display framebuffer offset on gen2/3
pageflips. This is also prep work to do similar trickery on gen4+
Also:
- kill "Start", such upper-case remnants from the ddx must surely die.
- rename "Offset" to linear_offset, to make it clearer that on gen4+
this is only used by the hw for linear buffers, for tiled buffers it
uses the TILEOFF register.
- call DSAPADDR DSPLINOFF on gen4+ for the same reason (and because
the documentation really renamed the register).
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
MI display flips can't handle some changes in the framebuffer
format or layout. Return an error in such cases.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Zero initialize the mode_cmd structure when creating the kernel
framebuffer. Avoids having uninitialized data in offsets[0] for
instance.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The issue with this check is that it results in userspace receiving an
-EIO while the gpu reset hasn't completed, resulting in fallback to sw
rendering or worse.
Now there's also a stern comment in intel_ring_wait_seqno saying that
intel_ring_begin should not return -EAGAIN, ever, because some callers
can't handle that. But after an audit of the callsites I don't see any
issues. I guess the last problematic spot disappeared with the removal
of the pipelined fencing code.
So do the right thing and call check_wedge, which should properly
decide whether an -EAGAIN or -EIO is appropriate if wedged is set.
Note that the early check for a wedged gpu before touching the ring is
rather important (and it took me quite some time of acting like the
densest doofus to figure that out): If we don't do that and the gpu
died for good, not having been resurrect by the reset code, userspace
can merrily fill up the entire ring until it notices that something is
amiss.
Allowing userspace to emit more render, despite that we know that it
will fail can't lead to anything good (and by experience can lead to
all sorts of havoc, including angering the OOM gods and hard-hanging
the hw for good).
v2: Fix EAGAIN mispell, noticed by Chris Wilson.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of looping endless with no hope of ever serving that
page-fault. We only need to break out of this loop when the gpu died,
to run the reset work (and hopefully resurrect it).
To clarify questions Chris raised on irc: This is about handling I/O
errors not from our own code, but e.g. when the disk died when trying
to swap in a gem bo. So this patch remidies the issue that the current
handling only handles gpu-death-induced cases of -EIO. Admittedly,
dying disks are much rarer than hanging gpus ...To clarify questions
Chris raised on irc: This is about handling I/O errors not from our
own code, but e.g. when the disk died when trying to swap in a gem bo.
So this patch remidies the issue that the current handling only
handles gpu-death-induced cases of -EIO. Admittedly, dying disks are
much rarer than hanging gpus ...
This seems to have been lost in:
commit d9bc7e9f32
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon Feb 7 13:09:31 2011 +0000
drm/i915: Fix infinite loop regression from 21dd3734
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the gpu reset no longer using a trylock we've increased the
chances of userspace getting stuck quite a bit. To make that
(hopefully) rare case more paletable time out when waiting for the gpu
reset code to complete and signal this little issue to the caller by
returning -EIO.
This should help userspace to somewhat gracefully fall back and
hopefully allow the user to grab some logs and reboot the machine
(instead of staring at a frozen X screen in agony).
Suggested by Chris Wilson because I've been stubborn about allowing
the gpu reset code no to fail, ever (by removing the trylock).
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
So don't return -EAGAIN, even in the case of a gpu hang. Remap it to
-EIO instead. Note that this isn't really an issue with
interruptability, but more that we have quite a few codepaths (mostly
around kms stuff) that simply can't handle any errors and hence not
even -EAGAIN. Instead of adding proper failure paths so that we could
restart these ioctls we've opted for the cheap way out of sleeping
non-interruptibly. Which works everywhere but when the gpu dies,
which this patch fixes.
So essentially interruptible == false means 'wait for the gpu or die
trying'.'
This patch is a bit ugly because intel_ring_begin is all non-interruptible
and hence only returns -EIO. But as the comment in there says,
auditing all the callsites would be a pain.
To avoid duplicating code, reuse i915_gem_check_wedge in __wait_seqno
and intel_wait_ring_buffer. Also use the opportunity to clarify the
different cases in i915_gem_check_wedge a bit with comments.
v2: Don't access dev_priv->mm.interruptible from check_wedge - we
might not hold dev->struct_mutex, making this racy. Instead pass
interruptible in as a parameter. I've noticed this because I've hit a
BUG_ON(!mutex_is_locked) at the top of check_wedge. This has been
added in
commit b4aca0106c
Author: Ben Widawsky <ben@bwidawsk.net>
Date: Wed Apr 25 20:50:12 2012 -0700
drm/i915: extract some common olr+wedge code
although that commit is missing any justification for this. I guess
it's just copy&paste, because the same commit add the same BUG_ON
check to check_olr, where it indeed makes sense.
But in check_wedge everything we access is protected by other means,
so this is superflous. And because it now gets in the way (we add a
new caller in __wait_seqno, which can be called without
dev->struct_mutext) let's just remove it.
v3: Group all the i915_gem_check_wedge refactoring into this patch, so
that this patch here is all about not returning -EAGAIN to callsites
that can't handle syscall restarting.
v4: Add clarification what interuptible == fales means in our code,
requested by Ben Widawsky.
v5: Fix EAGAIN mispell noticed by Chris Wilson.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Simply failing to reset the gpu because someone else might still hold
the mutex isn't a great idea - I see reliable silent reset failures.
And gpu reset simply needs to be reliable and Just Work.
"But ... the deadlocks!"
We already kick all processes waiting for the gpu before launching the
reset work item. New waiters need to check the wedging state anyway
and then bail out. If we have places that can deadlock, we simply need
to fix them.
"But ... testing!"
We have the gpu hangman, and if the current gpu load gem_exec_nop
isn't good enough to hit a specific case, we can add a new one.
"But ... don't we return -EAGAIN for non-interruptible calls to
wait_seqno now?"
Yep, but this problem already exists in the current code. A follow up
patch will remedy this by returning -EIO for non-interruptible sleeps
if the gpu died and the low-level wait bails out with -EAGAIN.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Only bits 30:28, bit 31 is PIPE_DDI_FUNC_ENABLE.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This pollutes dmesg output even if we do not have FBC for the device, so
move the DRM_DEBUG_KMS statement lower.
v2: just kill the message as suggested by Daniel.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is necessary for the modesetting to work correctly after a
suspend-resume cycle. Without this, the pipes and clocks got the correct
configuration, but the underlying DDI buffers configuration was lost.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This function is used to set the PCH_DREF_CONTROL register, which does
not exist on LPT anymore.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Previously we had has_pch_split to tell us whether we had a PCH or not
and we also had dev_priv->pch_type to tell us which kind of PCH it
was, but it could only be used if we were 100% sure we did have a PCH.
Now that PCH_NONE was added to dev_priv->pch_type we don't need
has_pch_split anymore: we can just check for pch_type != PCH_NONE.
The HAS_PCH_{IBX,CPT,LPT} macros use dev_priv->pch_type, so they can
only be called after intel_detect_pch. The HAS_PCH_SPLIT macro looks
at dev_priv->info->has_pch_split, which is available earlier.
Since the goal is to implement HAS_PCH_SPLIT using dev_priv->pch_type
instead of dev_priv->info->has_pch_split, we need to make sure that
intel_detect_pch is called before any calls to HAS_PCH_SPLIT are made.
So we moved the intel_detect_pch call to an earlier stage.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And rely on the fact that it's 0 to assume that machines without a PCH
will have PCH_NONE as dev_priv->pch_type.
Just today I finally realized that HAS_PCH_IBX is true for machines
without a PCH. IMHO this is totally counter-intuitive and I don't
think it's a good idea to assume that we're going to check for
HAS_PCH_IBX only after we check for HAS_PCH_SPLIT.
I believe that in the future we'll have more PCH types and checks
like:
if (HAS_PCH_IBX(dev) || HAS_PCH_CPT(dev))
will become more and more common. There's a good chance that we may
break non-PCH machines by adding these checks in code that runs on all
machines. I also believe that the HAS_PCH_SPLIT check will become less
common as we add more and more different PCH types. We'll probably
start replacing checks like:
if (HAS_PCH_SPLIT(dev))
foo();
else
bar();
with:
if (HAS_PCH_NEW(dev))
baz();
else if (HAS_PCH_OLD(dev) || HAS_PCH_IBX(dev))
foo();
else
bar();
and this may break gen 2/3/4.
As far as we have investigated, this patch will affect the behavior of
intel_hdmi_dpms and intel_dp_link_down on gen 4. In both functions the
code inside the HAS_PCH_IBX check is for IBX-specific workarounds, so
we should be safe. If we start bisecting gen 2/3/4 bugs to this commit
we should consider replacing the HAS_PCH_IBX checks with something
else.
V2: Improve commit message, list possible side effects and solution.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
High frequency link configurations have the potential to cause trouble
with long and/or cheap cables, so prefer slow and wide configurations
instead. This patch has the potential to cause trouble for eDP
configurations that lie about available lanes, so if we run into that we
can make it conditional on eDP.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45801
Tested-by: peter@colberg.org
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
While creating the new enable/disable_gt_powersave functions in
commit 8090c6b9da
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Sun Jun 24 16:42:32 2012 +0200
drm/i915: wrap up gt powersave enabling functions
I've botched up the handling of ironlake_disable_rc6. Fix this up by
calling it at the right place. Note though that ironlake_disable_rc6
does a bit more than just disabling rc6 - it also tears down all the
allocated context objects.
Hence we need to move intel_teardown_rc6 out and directly call it from
intel_modeset_cleanup.
Also properly mark ironlake_enable_rc6 as static and kill the un-used
declaration in i915_drv.h.
Note: In review a question popped out why disable_rc6 also tears down
the backing object and why we should move that out - it's simply for
consistency with gen6+ rps code, which does it that way.
Cc: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This commit moves force wake support routines into intel_pm modules, and
exports the gen6_gt_check_fifodbg routine (used in I915_READ).
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For Haswell, on some of the early hardware revisions, it is possible to
run into issues when RC6 state is enabled and when pipes change state.
v2: add comment saying that this is for early revisions only.
v3: beautify as suggested by Daniel Vetter.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is based on Ivy Bridge clock gating for now, but is subject to
changes in the future.
Note: Compared to the ivb clock gating this drops the the IDICOS
medium uncore sharing tuned in
commit 208482232d
Author: Ben Widawsky <ben@bwidawsk.net>
Date: Fri May 4 18:58:59 2012 -0700
drm/i915: set IDICOS to medium uncore resources
Eugeni wants to benchmark the effect of this first.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
[danvet: added note]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We weren't disabling RC6 bits when bringing down RPS.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It should be working so let's turn it on by default and catch any possible
issues faster.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just a cosmetic change to simplify the if statement.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Most of the RPS and RC6 enabling functionality is similar to what we had
on Gen6/Gen7, so we preserve most of the registers.
Note that Haswell only has RC6, so account for that as well. As suggested
by Daniel Vetter, to reduce the amount of changes in the patch, we still
write the RC6p/RC6pp thresholds, but those are ignored on Haswell.
Note: Some discussion about the nature of the new tuning constants
popped up in review - the answer is that we don't know why they've
changed, but the guide from VPG with the magic numbers simply has
different values now.
v2: Squash fix for ?: vs | operation precende bug into this patch.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
[danvet: Added note to commit message. Squashed fix.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There is a different ACK register for force wake on Haswell, so account
for that.
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As a w/a to prevent reads sporadically returning 0, we need to wait for
the GT thread to return to TC0 before proceeding to read the registers.
v2: adapt for Haswell changes (Eugeni).
v3: use wait_for_atomic_us for thread status polling.
v3: *really* use wait_for_atomic for polling.
References: https://bugs.freedesktop.org/show_bug.cgi?id=50243
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Tidy up the routines for interacting with the GT (in particular the
forcewake dance) which are scattered throughout the code in a single
structure.
v2: use wait_for_atomic for polling.
v3: *really* use wait_for_atomic for polling.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Especially vesafb likes to map everything as uc- (yikes), and if that
mapping hangs around still while we try to map the gtt as wc the
kernel will downgrade our request to uc-, resulting in abyssal
performance.
Unfortunately we can't do this as early as readon does (i.e. as the
first thing we do when initializing the hw) because our fb/mmio space
region moves around on a per-gen basis. So I've had to move it below
the gtt initialization, but that seems to work, too. The important
thing is that we do this before we set up the gtt wc mapping.
Now an altogether different question is why people compile their
kernels with vesafb enabled, but I guess making things just work isn't
bad per se ...
v2:
- s/radeondrmfb/inteldrmfb/
- fix up error handling
v3: Kill #ifdef X86, this is Intel after all. Noticed by Ben Widawsky.
v4: Jani Nikula complained about the pointless bool primary
initialization.
v5: Don't oops if we can't allocate, noticed by Chris Wilson.
v6: Resolve conflicts with agp rework and fixup whitespace.
This is commit e188719a28 in drm-next.
Backport to 3.5 -fixes queue requested by Dave Airlie - due to grub
using vesa on fedora their initrd seems to load vesafb before loading
the real kms driver. So tons more people actually experience a
dead-slow gpu. Hence also the Cc: stable.
Cc: stable@vger.kernel.org
Reported-and-tested-by: "Kilarski, Bernard R" <bernard.r.kilarski@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel complained about this on initial review, but he graciously moved
the patches forward. As promised, I am delivering the desired cleanup
now.
Hopefully I didn't screw the trivial patch up ;-)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Looks like a copy/paste error.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The prep to remove the flushing list in
commit cc889e0f6c
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jun 13 20:45:19 2012 +0200
drm/i915: disable flushing_list/gpu_write_list
causes quite some decent regressions. We can fix this by setting the
CS_STALL bit to ensure that the following seqno write happens only
after the cache flush has completed. But only do that when the caller
actually wants the flush (and not also when we invalidate caches
before starting the next batch).
I've looked through all our ancient scrolls about gen6+ pipe control
workarounds, and this seems to be indeed a legal combination: We're
allowed to set the CS_STALL bit when we flush the render cache (which
we do).
While yelling at this code, also pass back the return value from
intel_emit_post_sync_nonzero_flush properly.
v2: Instead of emitting more pipe controls, set the CS_STALL bit on
the write flush as suggested by Chris Wilson. It seems to work, too.
Cc: Eric Anholt <eric@anholt.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51436
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51429
Tested-by: Lu Hua <huax.lu@intel.com>
Tested-by: 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>
Daniel writes:
New -next pull request. Highlights:
- Remaining vlv patches from Jesse et al.
- Some hw workarounds from Jesse
- hw context support from Ben
- full uncore sharing on ivb
- prep work to move the gtt code from intel-gtt.c to drm/i915 for gen6+
- some backlight code improvements
- leftovers for the timeout ioctl (we've forgotten the getparam)
- ibx transcoder workarounds
- some smaller fixlets and improvements
- the new version of the "dont rely on HPD exclusively for VGA" patch
Wrt regressions QA reported quite a few this time around.
- The piglit/kernel-test fallout all has patches that are just awaiting
review and merging into the next -next cycle.
- Which just leaves a bunch of bugs about new modelines that don't work.
It looks like these are all due to the new 16:9/16:10 modes in 3.5
(yeah, only in this manual testing cycle did the git branch used by QA
contain a backmerge of mainline with these patches). Although I haven't
yet confirmed this by letting our QA test the revert of that series.
- Wrt bugs in general I'm trying to fight down some of our long-standing
backlight issues (not regressions), but this seems to be a game of
"you move, you lose" ... :("
Dropped merge bits since this had an -rc4 merge in it to fix some ugly
conflicts.
This reverts commit f82cfb6bcd.
This breaks the backlight controls on my IVB asus zenbook with an eDP
panel.
I guess the right fix would be to read this bit and use either the pch
or the cpu register to frob the backlight values. But that is stuff
for -next.
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we ever hit the default case in the switch statement we'll return
from the function without freeing the memory we just allocated to
'intel_plane' (but that has not been used).
This patch gets rid of the leak by freeing the memory just before we
return.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We shouldn't hit this path anyway, but make it use the IVB sprite format
definition to avoid confusion.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
These are unintuitive. These are type bool and return -1 casted to true
on failure. Let's just make it return an int. The callers don't care,
but let's change this as a cleanup.
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
This is the quick&dirty way Dave Airlie suggested to workaround the
midlayer drm agp brain-damange. Note that i915_probe is only called
when the driver has ksm enabled, so no need to check for that.
We also need to move the intel_agp_enabled check at the right place.
Note that the only thing this does is enforce the correct module load
order (by using a symbol from intel-agp.ko) to ensure that the fake
agp driver is ready before the drm core tries to set up the agp stuff.
v2: Add a comment to explain why gen3 needs all this legacy fake agp
stuff - we've shipped an XvMC library with a kms-enabled ddx that
requires it (but only on gen3).
v3: Make it clear that this is only a gen3 issue in the comment.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This single leftover use is due to a patch that went into 3.5 through
-fixes. With the fake agp stuff on demise, at least for gen6+ we can't
use this any more.
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The enable functions grabbed dev->struct_mutex themselves, whereas
the disable functions expected dev->struct_mutex to be held by the
caller. Move the locking out to the (currently only) callsite of
intel_enable_gt_powersave to make this more consistent.
Originally this was prep work for future patches, but I've chased down
a totally wrong alley. Still, I think this is a sensible
clarification.
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of calling each one for each generation indiviudally.
Notice that we've already managed to be inconsistent, the resume path
is missing an IS_VLV check. As a nice benefit we can mark all the
platform specific enable/disable functions as static and hide them in
intel_pm.c
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.18 (GNU/Linux)
iQEcBAABAgAGBQJP53AxAAoJEHm+PkMAQRiGs2QH/RaqkXz96fwjhDcyiKpDqA3c
kGuS5mz5cOhnqKSmR88HFm6pwuhLux/qSJzeAmoQy1MC8a0ACx7AnANW0lfN3/qe
/HGYz8h60yCL/fhn8/bUYtdt9xsoDqoDcq/ooFl9mcsJGWbC6WeMSZU5dAUYqviE
qFrp5zjY07FG53CRGT0hFpezQNwNL+VLH30CF9LD+fJLPVEYum2zBNGXWM42rcw5
fxzGL/6SO8YqA/Upic1ht6HAd6s5LOrlST7qvnyXUMvRXN5z/Y92ueYJZefkS1Om
ohuLIKM2bv9/dJS67H8N2baSKGCzBdfSe5/5WaHdLYW9MiVju0wRl6HPJtAMrkk=
=H8t8
-----END PGP SIGNATURE-----
Merge tag 'v3.5-rc4' into drm-intel-next-queued
I want to merge the "no more fake agp on gen6+" patches into
drm-intel-next (well, the last pieces). But a patch in 3.5-rc4 also
adds a new use of dev->agp. Hence the backmarge to sort this out, for
otherwise drm-intel-next merged into Linus' tree would conflict in the
relevant code, things would compile but nicely OOPS at driver load :(
Conflicts in this merge are just simple cases of "both branches
changed/added lines at the same place". The only tricky part is to
keep the order correct wrt the unwind code in case of errors in
intel_ringbuffer.c (and the MI_DISPLAY_FLIP #defines in i915_reg.h
together, obviously).
Conflicts:
drivers/gpu/drm/i915/i915_reg.h
drivers/gpu/drm/i915/intel_ringbuffer.c
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch fixes the problem on some HP desktop machines with eDP
which give blank screens after S3 resume.
It turned out that BLC_PWM_CPU_CTL must be written after
BLC_PWM_CPU_CTL2. Otherwise it doesn't take effect on these
SNB machines.
Tested with 3.5-rc3 kernel.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=49233
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
After banging my head against this for the past few months, I still
don't see how this could possible race under the premise that once an
irq bit is masked in PM_IMR and reset in PM_IIR it won't show up again
until we unmask it in PM_IMR.
Still, we have reports of this being seen in the wild. Now Bspec has
this little bit of lovely language in the PMIIR register:
Public SNB Docs, Vol3Part2, 2.5.14 "PMIIR":
"For each bit, the IIR can store a second pending interrupt if two or
more of the same interrupt conditions occur before the first condition
is cleared. Upon clearing the interrupt, the IIR bit will momentarily
go low, then return high to indicate there is another interrupt
pending."
Now if we presume that PMIMR only prevent new interrupts from being
queued, we could easily end up masking an interrupt and clearing it,
but the 2nd pending interrupt setting the bit in PMIIR right away
again. Which leads, the next time the irq handler runs, to hitting the
WARN.
Also, no bad side effects of this have ever been reported. And we've
tracked down our issues with the gpu turbo getting stuck to bogus
interrupt generation limits in th RPLIMIT register.
So let's just rip out this WARN as bogus and call it a day. The only
shallow thing here is that this 2-deep irq queue in the hw makes you
wonder how racy the windows irq handler is ...
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42907
Cc: stable@vger.kernel.org
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This box claims to have an LVDS interface but doesn't
actually have one.
Signed-off-by: Sjoerd Simons <sjoerd.simons@collabora.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With the code in place, we can bind the driver, should make bisect possible.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Enable the on-chip messaging between the display engine and the GT.
v2: use bit definitions for DPFLIPSTAT reg
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And restructure the IRQ handling a little. We can use pipestat for most
things, and make sure we don't affect pipe events when enabling and
disabling vblank interupts.
We can leave vblank interrupts masked but enabled so we're not dependent
on the first client to toggle the disable timer. We can also mask all
render based interrupts, since the ring code will handle unmasking them
for us.
v2: roll in vblank masking, remove unneeded variable (Daniel)
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since the offsets have all moved around.
v2: switch IS_DISPLAYREG and IS_VALLEYVIEW checks around since the latter is
cheaper (Daniel)
bail out early in IS_DISPLAYREG if the reg is in the new range (Daniel)
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: Fixup if cascading fail that broke HAS_FORCEWAKE machines.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel Vetter writes:
rc2 is out the door so I've figured I'll annoy you with the first -next
pull request for 3.6 already. Highlights:
- new wait_rendring_timeout interface (Ben)
- l3 cache remapping and error uevent support (Ben)
- even more infoframes work from Paulo
- gen4 hotplug rework from Chris
- prep work to make Laurent Pincharts original mode constification for
connector->mode_fixup possible
QA reported a few new bugs this time around, but no regressions afact. For
3.5 the only thing I'm aware of is the edp vdd dmesg spam Linus originally
reported - it looks like that might have been introduced in 3.5. But
somehow my brain is routinely offline when I work on that issue, so things
seem to take forever (and atm I'm at patch v4 for that little problem).
* tag 'drm-intel-next-2012-06-04' of git://people.freedesktop.org/~danvet/drm-intel: (39 commits)
drm/i915: add min freq control to debugfs
drm/i915: don't chnage the original mode in dp_mode_fixup
drm/i915: adjusted_mode->clock in the dp mode_fixup
drm/i915: compute the target_clock for edp directly
drm/i915: extract object active state flushing code
drm/i915: clarify IBX dp workaround
drm/i915: simplify sysfs setup code
drm/i915: initialize the parity work only once
drm/i915: ivybridge_handle_parity_error should be static
drm/i915: l3 parity sysfs interface
drm/i915: remap l3 on hw init
drm/i915: enable parity error interrupts
drm/i915: Dynamic Parity Detection handling
drm/i915: s/mdelay/msleep/ in the sdvo detect function
drm/i915: reuse the sdvo tv clock adjustment in ilk mode_set
drm/i915: there's no cxsr on ilk
drm/i915: add some barriers when changing DIPs
drm/i915: remove comment about HSW HDMI DIPs
drm/i915: don't set SDVO_BORDER_ENABLE when we're HDMI
drm/i915: don't write 0 to DIP control at HDMI init
...
ValleyView is similar to IbexPeak here, but with different register
offsets.
v2: use SDVOB instead ov VLV_HDMIB (Daniel)
drop unnecessary eDP check in DP_C init (Daniel)
eDP support will be coming later from Shobit.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Might be able to merge this back in at some point, but we're seeing bugs
with ADPA based detection, so keep it separate for now with explicit
hotplug trigger usage.
v2: drop superfluous debug message
v3: comment forced detection, need to debug (Eugeni)
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
VLV supports two dp panels, there are two set of panel power sequence
registers which needed to be programmed based on the configured
pipe. This patch add supports for the same
Acked-by: Acked-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Beeresh G <beeresh.g@intel.com>
Reviewed-by: Vijay Purushothaman <vijay.a.purushothaman@intel.com>
Reviewed-by: Jesse Barnes <jesse.barnes@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: Drop the lone hunk and only keep the register definitions - I
loathe incomplete bandaids. Also add a comment that this is for vlv.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Add some VLV limit structures and update the PLL code.
v2: resolve conflicts, Vijay to re-post with PLL valid checks and fixed limits
v3: re-add dpio write function
v4: squash in Vijay's fixes for the PLL limits and clean up the m/n finder
Signed-off-by: Shobhit Kumar <shobhit.kumar@intel.com>
Signed-off-by: Vijay Purushothaman <vijay.a.purushothaman@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is just the minimal patch to disable all this code so that we can
do decent amounts of QA before we rip it all out.
The complicating thing is that we need to flush the gpu caches after
the batchbuffer is emitted. Which is past the point of no return where
execbuffer can't fail any more (otherwise we risk submitting the same
batch multiple times).
Hence we need to add a flag to track whether any caches associated
with that ring are dirty. And emit the flush in add_request if that's
the case.
Note that this has a quite a few behaviour changes:
- Caches get flushed/invalidated unconditionally.
- Invalidation now happens after potential inter-ring sync.
I've bantered around a bit with Chris on irc whether this fixes
anything, and it might or might not. The only thing clear is that with
these changes it's much easier to reason about correctness.
Also rip out a lone get_next_request_seqno in the execbuffer
retire_commands function. I've dug around and I couldn't figure out
why that is still there, with the outstanding lazy request stuff it
shouldn't be necessary.
v2: Chris Wilson complained that I also invalidate the read caches
when flushing after a batchbuffer. Now optimized.
v3: Added some comments to explain the new flushing behaviour.
Cc: Eric Anholt <eric@anholt.net>
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>
It seems to blow up my ilk in all kinds of strange ways. And now that
we're no longer resetting the entire modeset state, it shouldn't be
necessary any longer.
This essentially reverts
commit f817586ceb
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Tue Apr 10 15:50:11 2012 +0200
drm/i915: re-init modeset hw state after gpu reset
safe for the introduction of modeset_init_hw, that one is nice to
prevent code duplication between driver load and resume.
v2: Add a comment to the code to warn future travellers of the dragon
dungeon ahead, suggested by Chris Wilson.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The idr code already passes us the pointer associated with that id, so
no need to look it up again. Also, we'll kill the idr right away, so
there's no issue with leaving these dangling pointers behind - the
current code does the same.
v2: Also drop the file argument, spotted by Ben Widawsky.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This is our customary "no such object" errno, not -EINVAL.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It doesn't hurt and it at least prevents us from OOPSing left and
right at quite a few places. This also allows us to simplify the code
a bit by folding the only line of context_open into the callsite.
We obviuosly also need to run the cleanup code unconditionally, too.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
commit 8e96d9c4d9
Author: Ben Widawsky <ben@bwidawsk.net>
Date: Mon Jun 4 14:42:56 2012 -0700
drm/i915: reset the GPU on context fini
broke module unload because it reset the gpu before we've stopped
touching it. Later on in the unload sequence the ringbuffer code
complained that the gpu would idle properly (because intel_gpu_reset
only resets the hw and not our sw state).
v2: Reorder things so that we reset the gpu _before_ we release the
backing storage of the default context.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51183
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Prevents a possible hang: WaDisableL3Bank2xClockGate.
v2: only apply to VLV, IVB doesn't need this anymore
References: https://bugs.freedesktop.org/show_bug.cgi?id=50245
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Another required workaround for a potential hang:
WaDisableTDLUnitClockGating.
v2: only apply this to VLV, IVB doesn't need it anymore (Eugeni)
References: https://bugs.freedesktop.org/show_bug.cgi?id=50245
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
According to the bspec for MBCTL:
Driver must set bit in the following scenarios:
- to realod teh h/w boot context every time it gets loaded through OS
- after an FLR clears the register (BIOS won't run afterwards)
References: https://bugs.freedesktop.org/show_bug.cgi?id=50237
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The RCBP workaround still applies on these chips, and we need VDS as well.
v2: remove MB boot fetch that snuck in (Daniel)
add workaround tags to comments for easier internal tracking (Daniel)
v3: only apply RCPB and VDS on SNB and VLV, IVB doesn't need them (Eugeni)
References: https://bugs.freedesktop.org/show_bug.cgi?id=50251
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I've added a bit of logic such that running the hangman test on chips
without any hw reset support at all doesn't wedge the gpu because the
reset failed. This relied on checking for non-null stop_rings.
Unfortunately I've botched a rebase somewhere and stop_rings is still
cleared at the old place before the reset code.
Fix this up so that running the i-g-t tests on gen2/3 doesn't result
in a wedged gpu.
v2: Actually remove the lines instead of adding them twice ... my git
license should be revoked immediately.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I'm seeing about a 5% FPS improvement across various benchmarks on my
IVB i3. Rumor has it that the higher end parts show even more benefit.
This derives from a patch originally given to me by Bernard. The docs
are confusing about the definition names (ie. medium really seems like
max), but it would seem it gives more cache to the GT at the expense of
uncore. This configuration makes the split most in favor of the GT. I've
not tried the other IDICOS values.
Cc: "Kilarski, Bernard R" <bernard.r.kilarski@intel.com>
Acked-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This got dropped as a result of the last round of comments. I didn't
test it on unsupported HW (which this is likely the case).
Note that this prevents hw context from blowing up on any pre-gen6 hw.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=51142
[danvet: Added note and buglink.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Somehow this went unnoticed in the past reviews, but the condition would
never timeout properly.
This was initially introduced in the v2 of original SBI enabling patch.
Highly embarrassing.
Note that we now actually time out for the read, which resulted in gcc
complaining that we can now return unitialized garbage if that
happens. There's not much we can do here because there's not much
point in thread -EIO all the way down through these functions. Hence
simply shut up the compiler.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
[danvet: Added note and squashed uninitialized value shut-up into this
patch.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
They aren't going anywhere, and probing on DDC can cause the panel to
blank briefly, so read them up front and cache them for later queries.
v2: fix potential NULL derefs in intel_dp_get_edid_modes and
intel_dp_get_edid (Jani)
copy full EDID length, including extension blocks (Takashi)
free EDID on teardown (Takashi)
v3: malloc a new EDID buffer that's big enough for the memcpy (Chris)
v4: change handling of NULL EDIDs, just preserve the NULL behavior
across detects and mode list fetches rather than trying to re-fetch
the EDID (Chris)
v5: be glad that Chris is around to remind me to hit C-x C-s before
committing.
References: https://bugs.freedesktop.org/show_bug.cgi?id=46856
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This reverts commit 092945e11c.
This commit prevents a DP screen from properly training the link.
Oddly enough it works, once the machine has been warm-booted with an
older kernel.
According to DP docs this _should_ have been the right precharge time.
Also, the commit that originally introduces this was just general snb
DP enabling and didn't mention any specific reason for this special
value. Whatever, trust the reporter that this makes things worse and
let's just revert it.
v2: Less spelling fail.
Cc: Adam Jackson <ajax@redhat.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Reported-by: "Wouter M. Koolen" <W.M.Koolen-Wijkstra@cwi.nl>
Buglink: https://lkml.org/lkml/2012/6/14/301
Cc: stable@vger.kernel.org (only for 3.4)
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The new oui probe has been missing these.
This issue has been introduce in
commit 0d19832853
Author: Adam Jackson <ajax@redhat.com>
Date: Mon May 14 16:05:47 2012 -0400
drm/i915/dp: Probe branch/sink OUIs
v2: Do the eDP vdd dance of simply not probing the OUI on eDP panels
as suggested by Chris Wilson.
v3: Fix up the error path fail - I suck.
Cc: Adam Jackson <ajax@redhat.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50808
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Bugreport: http://permalink.gmane.org/gmane.comp.video.dri.devel/69695
Tested-by: Yang Guang <guang.a.yang@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This prevents the HDMI detect functions from poking at an eDP
connected panel, which can lead to trouble.
[danvet: Note that we have some other reports of DP vs. HDMI fighting,
but the general case is a much bigger fish to fry.]
References: https://bugs.freedesktop.org/show_bug.cgi?id=42278
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
VGA hotplug detection "works" by measuring the resistance across
certain pins. A lot of kvm switches fumble this and wire up cheap
resistors with the wrong resistance or don't bother at all.
To accomodate these, also try to detect a connected monitor by trying
to grab the edid. Contrary to !HAS_HOTPLUG platforms we don't bother
with an actual load-detection cycle when the output is life - that
would be actual work to implement because things moved around. This is
the big difference to Chris Wilson's original approach:
commit 9e612a008f
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu May 31 13:08:53 2012 +0100
drm/i915/crt: Do not rely upon the HPD presence pin
This blew up on Linus' machine because it errornously detected a vga
screen (without and edid and hence only the default modes), leading to
it's prompt removal:
commit 8f53369b75
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri Jun 8 14:53:06 2012 -0700
Revert "drm/i915/crt: Do not rely upon the HPD presence pin"
Some digging around in Bspec shows the reason why load detect doesn't work on
newer chips - the legacy VGA load detect bit isn't wired up any longer:
Public Snb Bspec, Vol3 Part1, 1.1.1 ST00 Input Status 0, bit4:
"RGB Comparator / Sense. This bit is here for compatibility and will
always return one. Monitor detection must be done be done through the
programming of registers in the MMIO space.
0 = Below threshold
1 = Above threshold"
v2: Add a comment in the code that load detect on hotplug capable
machines is broken and pimp the commit message with a quote of Bspec
to show why.
Reported-and-tested-by: Matthieu LAVIE <boiteamadmax@hotmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50501
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Use the rsvd1 field in execbuf2 to specify the context ID associated
with the workload. This will allow the driver to do the proper context
switch when/if needed.
v2: Add checks for context switches on rings not supporting contexts.
Before the code would silently ignore such requests.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Add the interfaces to allow user space to create and destroy contexts.
Contexts are destroyed automatically if the file descriptor for the dri
device is closed.
Following convention as usual here causes checkpatch warnings.
v2: with is_initialized, no longer need to init at create
drop the context switch on create (daniel)
v3: Use interruptible lock (Chris)
return -ENODEV in !GEM case (Chris)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
To keep things as sane as possible, switch to the default context before
idling. This should help free context objects, as well as put things in
a more well defined state before suspending.
v2: remove seqno from context switch call (daniel)
return error on failed context switch instead of WARN+continue (daniel)
v3: move idling to i915_gpu idle (from i915_gem_idle) (Chris)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
With the code to do HW context switches in place have the driver load the
default context for the render ring when the driver loads.
The default context will be an ever present context that is available to
switch to at any time for the given ring.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
From http://intellinuxgraphics.org/documentation/SNB/IHD_OS_Vol1_Part3.pdf
[DevSNB] If Flush TLB invalidation Mode is enabled it's the driver's
responsibility to invalidate the TLBs at least once after the previous
context switch after any GTT mappings changed (including new GTT
entries). This can be done by a pipelined PIPE_CONTROL with TLB inv bit
set immediately before MI_SET_CONTEXT.
On GEN7 the invalidation mode is explicitly set, but this appears to be
lacking for GEN6. Since I don't know the history on this, I've decided
to dynamically read the value at ring init time, and use that value
throughout.
v2: better comment (daniel)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
This has showed up in several other patches. It's required for the next
context workaround.
I tested this one on its own and saw no differences in basic tests
(performance or otherwise). This patch is relatively likely to cause
regressions, hence why it's split out.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
The workaround itself applies to gen7 only (according to the docs) and
as Eric Anholt points out shouldn't be required since we don't use HW
scheduling features, and therefore arbitration. Though since it is a
small, and simple addition, and we don't really understand the issue,
just do it.
FWIW, I eventually want to play with some of the arbitration stuff, and
I'd hate to forget about this.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
This way round we don't introduce and ugly layering violations and use
the interface as I planned to use it.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Implement the context switch code as well as the interfaces to do the
context switch. This patch also doesn't match 1:1 with the RFC patches.
The main difference is that from Daniel's responses the last context
object is now stored instead of the last context. This aids in allows us
to free the context data structure, and context object independently.
There is room for optimization: this code will pin the context object
until the next context is active. The optimal way to do it is to
actually pin the object, move it to the active list, do the context
switch, and then unpin it. This allows the eviction code to actually
evict the context object if needed.
The context switch code is missing workarounds, they will be implemented
in future patches.
v2: actually do obj->dirty=1 in switch (daniel)
Modified comment around above
Remove flags to context switch (daniel)
Move mi_set_context code to i915_gem_context.c (daniel)
Remove seqno , use lazy request instead (daniel)
v3: use i915_gem_request_next_seqno instead of
outstanding_lazy_request (Daniel)
remove id's from trace events (Daniel)
Put the context BO in the instruction domain (Daniel)
Don't unref the BO is context switch fails (Chris)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Invent an abstraction for a hw context which is passed around through
the core functions. The main bit a hw context holds is the buffer object
which backs the context. The rest of the members are just helper
functions. Specifically the ring member, which could likely go away if
we decide to never implement whatever other hw context support exists.
Of note here is the introduction of the 64k alignment constraint for the
BO. If contexts become heavily used, we should consider tweaking this
down to 4k. Until the contexts are merged and tested a bit though, I
think 64k is a nice start (based on docs).
Since we don't yet switch contexts, there is really not much complexity
here. Creation/destruction works pretty much as one would expect. An idr
is used to generate the context id numbers which are unique per file
descriptor.
v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben)
convert a BUG_ON to WARN_ON, default destruction is still fatal (ben)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Very basic code for context setup/destruction in the driver.
Adds the file i915_gem_context.c This file implements HW context
support. On gen5+ a HW context consists of an opaque GPU object which is
referenced at times of context saves and restores. With RC6 enabled,
the context is also referenced as the GPU enters and exists from RC6
(GPU has it's own internal power context, except on gen5). Though
something like a context does exist for the media ring, the code only
supports contexts for the render ring.
In software, there is a distinction between contexts created by the
user, and the default HW context. The default HW context is used by GPU
clients that do not request setup of their own hardware context. The
default context's state is never restored to help prevent programming
errors. This would happen if a client ran and piggy-backed off another
clients GPU state. The default context only exists to give the GPU some
offset to load as the current to invoke a save of the context we
actually care about. In fact, the code could likely be constructed,
albeit in a more complicated fashion, to never use the default context,
though that limits the driver's ability to swap out, and/or destroy
other contexts.
All other contexts are created as a request by the GPU client. These
contexts store GPU state, and thus allow GPU clients to not re-emit
state (and potentially query certain state) at any time. The kernel
driver makes certain that the appropriate commands are inserted.
There are 4 entry points into the contexts, init, fini, open, close.
The names are self-explanatory except that init can be called during
reset, and also during pm thaw/resume. As we expect our context to be
preserved across these events, we do not reinitialize in this case.
As Adam Jackson pointed out, The cutoff of 1MB where a HW context is
considered too big is arbitrary. The reason for this is even though
context sizes are increasing with every generation, they have yet to
eclipse even 32k. If we somehow read back way more than that, it
probably means BIOS has done something strange, or we're running on a
platform that wasn't designed for this.
v2: rename load/unload to init/fini (daniel)
remove ILK support for get_size() (indirectly daniel)
add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel)
added comments (Ben)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
The GPUs can have different default context layouts, and the sizes could
vary based on platform or BIOS. In order to back the context object with
a properly sized BO, we must read this register in order to find out a
sufficient size.
Thankfully (sarcarm!), the register moves and changes meanings
throughout generations.
CTX and CXT differences are intentional as that is how it is in the
documentation (prior to GEN6 it was CXT).
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
The Lenovo Thinkpad T410 has the LVDS_PIPEB_SELECT bit set in the LVDS
register when booted with the lid closed, even though the LVDS hasn't
really been initialized. Ignore this bit so that the VBT value will be
used instead.
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we switch on/off the primary plane if it is completely obscured by an
overlapping video sprite, we also nee to make sure that we update the
FBC configuration at the same time.
v2: Not all crtcs are intel_crtcs, as spotted by Daniel.
v3: Boot testing rules.
References: https://bugs.freedesktop.org/show_bug.cgi?id=50238
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Especially vesafb likes to map everything as uc- (yikes), and if that
mapping hangs around still while we try to map the gtt as wc the
kernel will downgrade our request to uc-, resulting in abyssal
performance.
Unfortunately we can't do this as early as readon does (i.e. as the
first thing we do when initializing the hw) because our fb/mmio space
region moves around on a per-gen basis. So I've had to move it below
the gtt initialization, but that seems to work, too. The important
thing is that we do this before we set up the gtt wc mapping.
Now an altogether different question is why people compile their
kernels with vesafb enabled, but I guess making things just work isn't
bad per se ...
v2:
- s/radeondrmfb/inteldrmfb/
- fix up error handling
v3: Kill #ifdef X86, this is Intel after all. Noticed by Ben Widawsky.
v4: Jani Nikula complained about the pointless bool primary
initialization.
v5: Don't oops if we can't allocate, noticed by Chris Wilson.
v6: Resolve conflicts with agp rework and fixup whitespace.
Reported-and-tested-by: "Kilarski, Bernard R" <bernard.r.kilarski@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When drm/i915 is in control of the gtt, we need to call
the enable function at all the relevant places ourselves.
Reviewed-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
To be able to directly set up the intel-gtt code from drm/i915 and
avoid setting up the fake-agp driver we need to prepare a few things:
- pass both the bridge and gpu pci_dev to the probe function and add
code to handle the gpu pdev both being present (for drm/i915) and
not present (fake agp).
- add refcounting to the remove function so that unloading drm/i915
doesn't kill the fake agp driver
v2: Fix up the cleanup and refcount, noticed by Jani Nikula.
Reviewed-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For that to work we need to export the base address of the gtt
mmio window from intel-gtt. Also replace all other uses of
dev->agp by values we already have at hand.
Reviewed-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Given the havoc the missing backlight pipe select code might have
caused, let's try to re-enabled pipe A support for lvds on gen4 hw.
Just to see what all blows up ...
Note though that
commit 4add75c43f
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat Dec 4 17:49:46 2010 +0000
drm/i915: Allow LVDS to be on pipe A for Ironlake+
claims that this caused tons of spurious wakeups somehow.
More details can be found in the old revert:
commit 12e8ba25ef
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Sep 7 23:39:28 2010 +0100
Revert "drm/i915: Allow LVDS on pipe A on gen4+"
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=16307
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On gen4+ we have a bitfield to specify from which pipe the backlight
controller should take it's clock. For PCH split platforms we've
already set these up, but only at initialization time. And without
taking into account the 3rd pipe added with ivb.
For gen4, we've completely ignored these. Although we do restrict lvds
to the 2nd pipe, so this is only a problem on machines where we boot
up with the lvds on the first pipe.
So restructure the code to enable the backlight on the right pipe at
modeset time.
v2: For odd reasons panel_enable_backlight gets called twice in a
modeset, so we can't WARN_ON in there if the backlight controller is
switched on already.
v3: backlight enable can also be called through dpms on, so the check
in there is legit. Update the comment to reflect that.
Tested-By: Kamal Mostafa <kamal@canonical.com>
Bugzilla: https://bugs.launchpad.net/bugs/954661
Cc: Carsten Emde <C.Emde@osadl.org>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- Regroup definitions for BLC_PWM_CTL so that they're all together and
and ordered according to the bitfields.
- Add all missing definitions for BLC_PWM_CTL2.
- Use the BLM_ (for backlight modulation) prefix consistently.
- Note that combination mode (i.e. also taking the legacy backlight
control value from pci config space into account) is gen4 only.
- Move the new registers for PCH-split machines up, they're an almost
match for the gen4 defitions. Prefix the special PCH-only bits with
BLM_PCH_. Also add the pipe C select bit for ivb.
- Rip out the second pair of PCH polarity definitions - they're only
valid on early (pre-production) ilk silicon.
- Adapt the existing code to use the new definitions. This has the
nice benefit of killing a magic (1 << 30) left behind be Jesse
Barnes.
No functional changes in this patch.
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We already correctly ignore bit0 on gen < 4, now we also know why ;-)
I've decided that losing that single bit of precision isn't worth the
trouble to sprinkle IS_PINEVIEW checks all over the backlight control
code - that code is way too fragile imo.
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This function is supposed to be used at mode set time, so prevent
against future mistakes by adding a WARN().
Based on a patch by Paulo Zanoni, with the check extracted into a
little assert_hdmi_port_disabled helper added to make things self
documenting and move the assert stuff out of line.
[fixed up spelling goof-up while applying.]
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This reverts commit 9e612a008f.
It incorrectly finds VGA connectors where none are attached, apparently
not noticing that nothing replied to the EDID queries, and happily using
the default EDID modes that have nothing to do with actual hardware.
That in turn then causes X to fall down to the lowest common
denominator, which is usually the default 1024x768 mode that is in the
default EDID and pretty much anything supports).
I'd suggest that if not relying on the HDP pin, the code should at least
check whether it gets valid EDID data back, rather than just assume
there's something on the VGA connector.
Cc: Dave Airlie <airlied@linux.ie>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'drm-intel-fixes' of git://people.freedesktop.org/~danvet/drm-intel:
drm/i915: pch_irq_handler -> {ibx, cpt}_irq_handler
char/agp: add another Ironlake host bridge
drm/i915: fix up ivb plane 3 pageflips
drm/i915: hold forcewake around ring hw init
drm/i915: Mark the ringbuffers as being in the GTT domain
drm/i915/crt: Do not rely upon the HPD presence pin
drm/i915: Reset last_retired_head when resetting ring
Cougar/Panther Point redefine the bits in SDEIIR pretty completely.
This function is just debugging, but if we're debugging we probably want
to be told accurate things instead of lies.
I'm told Lynx Point changes this yet more, but I have no idea how...
Note from Eugeni's review:
"For the record and for future enabling efforts, for LPT, bits 28-31
and 1-14 are gone since CPT/PPT (e.g., those must be zero). And there
is the bit 15 as a new addition, but we are not using it yet and
probably won't be using in foreseeable future."
Signed-off-by: Adam Jackson <ajax@redhat.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=35103
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
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>
Change the ns_timeout parameter of the wait ioctl to a signed value.
Doing this allows the kernel to provide an infinite wait when a timeout
of less than 0 is provided. This mimics select/poll.
Initially the parameter was meant to match up with the GL spec 1:1, but
after being made aware of how much 2^64 - 1 nanoseconds actually is, I
do not think anyone will ever notice the loss of 1 bit.
The infinite timeout on waiting is similar to the existing i915
userspace interface with the exception that struct_mutex is dropped
while doing the wait in this ioctl.
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>
Bspec Vol 3, Part 3, Section 3.8.1.1, bit 30:
"[DevIBX] Writing to this bit only takes effect when port is enabled.
Due to hardware issue it is required that this bit be cleared when port
is disabled. To clear this bit software must temporarily enable this
port on transcoder A."
Unfortunately the public Bspec misses totally out on the same language
for HDMIB. Internal Bspec also mentions that one of the bad
side-effects is that DPx can fail to light up on transcoder A if HDMIx
is disabled but using transcoder B.
I've found this while reviewing Bsepc. We already implement the same
workaround for the DP ports.
Also replace a magic 1 with PIPE_B I've found while looking through the
code.
v2: Implement suggestions from Chris Wilson:
- add pipe variable to cut down on code noise
- write the reg value twice to w/a hw issues (Bspec is unclear on
which bit actually require the write twice stuff, but better be
paranoid about it)
- untangle the if logic
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Or at least plug another gapping hole. Apparrently hw desingers only
moved the bit field, but did not bother ot re-enumerate the planes
when adding support for a 3rd pipe.
Discovered by i-g-t/flip_test.
This may or may not fix the reference bugzilla, because that one
smells like we have still larger fish to fry.
v2: Fixup the impossible case to catch programming errors, noticed by
Chris Wilson.
References: https://bugs.freedesktop.org/show_bug.cgi?id=50069
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Eugeni Dodonov <eugeni.dodonov@intel.com>
Cc: stable@vger.kernel.org
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This makes for easier benchmarking and testing. One can set a fixed
frequency by setting min and max to the same value.
v2: fix whitespace & comment (Eugeni)
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Eugeni Dodonov <eugeni@dodonov.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We should only frob adjusted_mode. This is in preparation of
a massive patch by Laurent Pinchart to make the mode argument
const.
After the previous two prep patches the only thing left is to clean up
things a bit. I've opted to pass in an adjust_mode param to
dp_adjust_dithering because that way we can be sure to avoid
duplicating this logic between mode_valid and mode_fixup - which was
the cause behind a dp link bw calculation bug in the past.
Also mark the mode argument of pch_panel_fitting const.
v2: Split up the mode->clock => adjusted_mode->clock change,
as suggested by Chris Wilson.
Reported-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of changing mode->clock, which we should leave as-is.
After the previous patch we only touch that if it's a panel, and then
adjusted mode->clock equals adjusted_mode->clock. Outside of
intel_dp.c we only use ajusted_mode->clock in the mode_set functions.
Within intel_dp.c we only use it to calculate the dp dithering
and link bw parameters, so that's the only thing we need to fix
up.
As a temporary ugliness (until the cleanup in the next patch) we
pass the adjusted_mode into dp_dither for both parameters (because
that one still looks at mode->clock).
Note that we do overwrite adjusted_mode->clock with the selected dp
link clock, but that only happens after we've calculated everything we
need based on the dotclock of the adjusted output configuration.
Outside of intel_dp.c only intel_display.c uses adjusted_mode->clock,
and that stays the same after this patch (still equals the selected dp
link clock). intel_display.c also needs the actual dotclock (as
target_clock), but that has been fixed up in the previous patch.
v2: Adjust the debug message to also use adjusted_mode->clock.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
... instead of abusing mode->clock by storing it in there - we
shouldn't touch that one at all. This patch is the first prep step to
constify the mode argument of the intel_dp_mode_fixup function.
The next patch will stop us from modifying mode->clock.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Empirical evidence suggests that we need to: On at least one ivb
machine when running the hangman i-g-t test, the rings don't properly
initialize properly - the RING_START registers seems to be stuck at
all zeros.
Holding forcewake around this register init sequences makes chip reset
reliable again. Note that this is not the first such issue:
commit f01db988ef
Author: Sean Paul <seanpaul@chromium.org>
Date: Fri Mar 16 12:43:22 2012 -0400
drm/i915: Add wait_for in init_ring_common
added delay loops to make RING_START and RING_CTL initialization
reliable on the blt ring at boot-up. So I guess it won't hurt if we do
this unconditionally for all force_wake needing gpus.
To avoid copy&pasting of the HAS_FORCE_WAKE check I've added a new
intel_info bit for that.
v2: Fixup missing commas in static struct and properly handling the
error case in init_ring_common, both noticed by Jani Nikula.
Cc: stable@vger.kernel.org
Reported-and-tested-by: Yang Guang <guang.a.yang@intel.com>
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50522
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
By correctly describing the rinbuffers as being in the GTT domain, it
appears that we are more careful with the management of the CPU cache
upon resume and so prevent some coherency issue when submitting commands
to the GPU later. A secondary effect is that the debug logs are then
consistent with the actual usage (i.e. they no longer describe the
ringbuffers as being in the CPU write domain when we are accessing them
through an wc iomapping.)
Reported-and-tested-by: Daniel Gnoutcheff <daniel@gnoutcheff.name>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=41092
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Both busy_ioctl and the new wait_ioct need to do the same dance (or at
least should). Some slight changes:
- busy_ioctl now unconditionally checks for olr. Before emitting a
require flush would have prevent the olr check and hence required a
second call to the busy ioctl to really emit the request.
- the timeout wait now also retires request. Not really required for
abi-reasons, but makes a notch more sense imo.
I've tested this by pimping the i-g-t test some more and also checking
the polling behviour of the wait_rendering_timeout ioctl versus what
busy_ioctl returns.
v2: Too many people complained about unplug, new color is
flush_active.
v3: Kill the comment about the unplug moniker.
v4: s/un-active/inactive/
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of checking for !CPT, check for IBX to make it clearer that
this is a IBX-specific workaround. No functional change because we
smash the PPT PCH into the HAS_PCH_CPT check and atm DP isn't enabled
on the haswell LPT PCH yet.
See Bspec Vol 3, Part 3, Section 4.[3-5].1 about DP[BCD], bit 30 for
details of this workaround.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We need the latest dma-buf code from Dave Airlie so that we can pimp
the backing storage handling code in drm/i915 with Chris Wilson's
unbound tracking and stolen mem backed gem object code.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Positively checking for the required feature/gen is simpler than build
a cascade of negative "we need to bail" checks. And the later won't
scale if we add more stuff that doesn't fit in nicely.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This fixes an (albeit really hard to hit) race resulting in an oops:
- The parity work get scheduled.
- We re-init the irq state and call INIT_WORK again.
- The workqueue code tries to run the work item and stumbles over a
work item that should be on it's runlist.
Also initiliaze the work item unconditionally like all the others,
it's simpler.
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Whilst most monitors do wire up the HPD presence pin, it seems quite a
few KVM do not. Therefore if we simply rely on the HPD pin being
asserted to indicate a connected monitor we fail miserable, so fall back
to performing a DCC query for the EDID.
Reported-and-tested-by: Matthieu LAVIE <boiteamadmax@hotmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50501
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Dumb binary interfaces which allow root-only updates of the cache
remapping registers. As mentioned in a previous patch, software using
this interface needs to know about HW limits, and other programming
considerations as the kernel interface does no checking for these things
on the root-only interface.
v1: Drop extra posting reads (Chris)
Return negative values in the sysfs interfaces on errors (Chris)
v2: Return -EINVAL for offset % 4 (Jesse)
Move schizo userspace check out (Jesse)
Cleaner sysfs item initializers (Daniel)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If any l3 rows have been previously remapped, we must remap them after
GPU reset/resume too.
v2: Just return (no warn) on remapping init if not IVB (Jesse)
Move the check of schizo userspace to i915_gem_l3_remap (Jesse)
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The previous patch put all the code, and handlers in place. It should
now be safe to enable the parity error interrupt. The parity error must
be unmasked in both the GTIMR, and the CS IMR. Unfortunately, the docs
aren't clear about this; nevertheless it's the truth.
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On IVB hardware we are given an interrupt whenever a L3 parity error
occurs in the L3 cache. The L3 cache is used by internal GPU clients
only. This is a very rare occurrence (in fact to test this I need to
use specially instrumented silicon).
When a row in the L3 cache detects a parity error the HW generates an
interrupt. The interrupt is masked in GTIMR until we get a chance to
read some registers and alert userspace via a uevent. With this
information userspace can use a sysfs interface (follow-up patch) to
remap those rows.
Way above my level of understanding, but if a given row fails, it is
statistically more likely to fail again than a row which has not failed.
Therefore it is desirable for an operating system to maintain a lifelong
list of failing rows and always remap any bad rows on driver load.
Hardware limits the number of rows that are remappable per bank/subbank,
and should more than that many rows detect parity errors, software
should maintain a list of the most frequent errors, and remap those
rows.
V2: Drop WARN_ON(IS_GEN6) (Jesse)
DRM_DEBUG row/bank/subbank on errror (Jesse)
Comment updates (Jesse)
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A 30 ms delay is simply way too big to waste cpu cycles on.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Jesse extracted this nice helper in his i9xx_crtc_mode_set refactor,
but we have the identical code in ironlake_ccrtc_mode_set. And that
function is huge, so extracting some code full of magic numbers is
always nice.
Noticed while trying to get a handle on our dp clock code.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Already discovered in
commit 5a117db77e
Author: Eugeni Dodonov <eugeni.dodonov@intel.com>
Date: Thu Jan 5 09:34:29 2012 -0200
drm/i915: there is no pipe CxSR on ironlake
but we've failed to rip out the code from the ironlake specific code.
Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
On IVB and older, we basically have two registers: the control and the
data register. We write a few consecutitve times to the control
register, and we need these writes to arrive exactly in the specified
order.
Also, when we're changing the data register, we need to guarantee that
anything written to the control register already arrived (since
changing the control register can change where the data register
points to). Also, we need to make sure all the writes to the data
register happen exactly in the specified order, and we also *can't*
read the data register during this process, since reading and/or
writing it will change the place it points to.
So invoke the "better safe than sorry" rule and just be careful and
put barriers everywhere :)
On HSW we still have a control register that we write many times, but
we have many data registers.
Demanded-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
HSW support is now just like all the other generations: we send AVI
and SPD InfoFrames. There are other DIPs for HSW, but there are other
DIPs for the previous generations too. For each gen, we can see which
DIPs are missing by looking at the 'set_infoframes' function: we
explicitly disable the DIPs we're not using.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The register that controls the HDMI port can be used to control the
sDVO port. Some bits are defined only for sDVO, and SDVO_BORDER_ENABLE
is one of those: HDMI ports that can't be used in sDVO mode don't even
have this bit defined in their specifications.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
At this time, the HDMI port is enabled, and the DIP control register
specification says we need to disable the port *before* disabling the
DIPs. Also, while doing this we risk telling the HW to send the AVI
DIPs once (not every VSync), which really seems to confuse the HW and
trigger bugs where the DIPs are not sent.
This code was here just to set the DIP register to a 'known state'
before using it, but since now the set_infoframes functions already
set the control registers to a known state, this code can go away.
Also, the previous code disables *all* the DIP registers for *each*
HDMI port, so we end disabling each DIP register more than once.
This patch solves a problem I can reproduce on my IVB machine. When I
boot it with just a single HDMI monitor, the AVI InfoFrames are not
sent. With this patch, the InfoFrames are sent. Previously, I wrote a
patch to 'touch the DIP registers after we enable the HDMI port' to
solve this same problem, but that patch doesn't seem to be needed
anymore after this patch.
All this patch does is revert a chunk of the following commit:
commit 64a8fc0145
Author: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Thu Sep 22 11:16:00 2011 +0530
drm/i915: fix ILK+ infoframe support
So bugs that can be bisected to that commit may be fixed now.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=43256
Acked-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>
The register specification says we need to do this.
V2: Only write the register if the port is enabled.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From this point on, the 'set_infoframe' functions always set the DIP
registers to a known state, so anything done will always be undone at
the modeset.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This function is called when the pipe is disabled, so it always gets
the 50ms timeout.
This function is called once for each InfoFrame, so we actually get a
100ms timeout. Will be more if we add more InfoFrames.
Also, the spec says we need to "wait for a VSync to ensure completion
of any pending DIP transmissions", not for a VBlank. OTOH, the
register documentation suggests that the DIPs are sent *during* the
VSync, so shouldn't we be waiting until *after* the VSync to ensure
all DIPs are sent?
So this wait_for_vblank seems, besides useless, totally wrong.
If we ever want to change some specific InfoFrame on-the-fly (outside
of the modeset code), the code that changes the InfoFrame will have to
do the waiting itself, and properly.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
So the write_infoframe function can assume the DIP is on.
V2: Be more defensive and add WARN().
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Daniel Vetter