Chris Wilson [Thu, 5 Jul 2012 22:49:40 +0000 (23:49 +0100)]
drm/i915: Disable the BLT on pre-production SNB hardware
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 6a233c78878
(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>
drm/i915: initialize power wells in modeset_init_hw
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>
Chris Wilson [Thu, 5 Jul 2012 14:02:17 +0000 (15:02 +0100)]
drm/i915: Only request PM interrupts for the events we handled
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>
Ben Widawsky [Wed, 18 Jul 2012 17:10:09 +0000 (10:10 -0700)]
drm/i915/context/: s/CTX/CXT
*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>
Daniel Vetter [Sun, 24 Jun 2012 17:57:24 +0000 (19:57 +0200)]
drm/sis: fixup sis_mm ioctl structs
Userspace uses long in quite a few places more than the kernel. Which
gives me neat proof that I'm the only guy on this side of the galaxy
who ever tried to run glxgears on a 64bit machine with sis graphics on
linux.
Note that the longs in drm_sis_mem_t aren't aligned properly, so this
won't even work with 32bit userspace on 64bit kernel as-is. Hence the
patch can't break that, either.
Nope, I'm not nuts enough to write the 32bit ioctl compat layer for
this and test it with some wine app. Even though hunting the ebay
dungeons for a sis card actually supported by the mesa drivers casts
some doubts on this ...
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel Vetter [Tue, 25 Oct 2011 22:53:57 +0000 (00:53 +0200)]
drm: ditch strange DRIVER_DMA_QUEUE only error bail-out
Only one driver (i810) even sets that flag. Now the actual locking
code uncoditionally promotes lock->context to an unsigned int.
Closer inspection of the userspace reveals that the drm lock context
is defined as an unsigned int (at least on linux). I suspect we just
have a strange case of signedness confusion going on.
Tested on my i815, doesn't seem to break anything.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel Vetter [Tue, 25 Oct 2011 22:14:15 +0000 (00:14 +0200)]
drm/savage: clean up reclaim_buffers
The reclaim_buffers function of the savage driver actually wants to run
with the hw_lock held - at least there are printks in the call-chain
to that effect. But the drm core only calls reclaim_buffers as used
by savage _after_ forcefully dropping the hwlock (in case it's still
hold by the closing fd).
So do the same idlelock dance as for the other dma drivers and hope
that papers over any issues.
v2: Don't let the idlelock linger around.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Tested-by: Tormod Volden <debian.tormod@gmail.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
My dear old i815 always hits the deadlocked on reclaim_buffers
warning. Switch over to the idlelock duct-tape on hope that
works better. I've fired up my i815 and now closing glxgears doesn't
take 5 seconds anymore. \o/
The original problem with that was that I've moved it ahead in the
series so that it could be included despite some patches not being
ready quite yet. The little problem is that this patch required some
of the previous rework to work correctly.
Now that everything is in the right order again, this actually works
on my i810 and does speed up closing gl apps as the original commit
claimed. Without hanging the machine, as the revert says.
Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel Vetter [Tue, 25 Oct 2011 21:37:09 +0000 (23:37 +0200)]
drm/via: clean up reclaim_buffers
A few things
- kill reclaim_buffers, it's never ever called because via does not set
DRIVER_HAVE_DMA
- inline the idlelock dance into the buffer reclaim logic and make it
a simple preclose cleanup function
- directly call the the dma_quiescent function and kill the needless
if check.
v2: Actually drop the idlelock when we take it. Reported by James
Simmons.
v3: Rebased onto latest drm-next.
v4: Fixup the refactor.
v5: More fixup the refactor - I've accidentally changed the check for
any master to checking whether the closing fd is the master.
v6: Don't forget to drop the idlelock in the early return path, too.
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Dave Airlie <airlied@redhat.com>
Michel Dänzer [Tue, 17 Jul 2012 17:02:09 +0000 (19:02 +0200)]
drm/radeon: Try harder to avoid HW cursor ending on a multiple of 128 columns.
This could previously fail if either of the enabled displays was using a
horizontal resolution that is a multiple of 128, and only the leftmost column
of the cursor was (supposed to be) visible at the right edge of that display.
The solution is to move the cursor one pixel to the left in that case.
Cc: stable@vger.kernel.org Signed-off-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
Daniel Vetter [Fri, 15 Jun 2012 09:01:22 +0000 (11:01 +0200)]
drm/fb-helper: delay hotplug handling when partially bound
Ok, this requires quite a dance to actually hit:
1) We plug in a 2nd screen, enable it in both X and (by vt-switching)
in the fbcon.
2) We disable that screen again in with xrandr.
3) We vt-switch again, so that fbcon displays on the 2nd screen, but X
on the first screen. This obviously needs a driver that doesn't switch
off unused functions when regaining the VT.
3) When X controls the vt, we unplug that screen.
Now drm_fb_helper_hotplug_event we noticed that that some crtcs are
bound, but because we still have the fbcon on the 2nd screeen we also
have bound set. Which means the fbcon wrongly assumes it's in control
of everything an happily disables the output on the 2nd screen, but
enables its fb on the first screen.
Work around this issue by counting how many crtcs are bound and how
many are bound to fbcon and assuming that when fbcon isn't bound to
all of them, it better not touch the output configuration.
Conceptually this is the same as only restoring the fbcon output
configuration on the driver's ->lastclose, when we're sure that no one
else is using kms. So this should be consistent with existing kms
drivers.
Chris has created a separate patch for the intel ddx, but I think we
should fix this issue here regardless - the fbcon messing with the
output config while it's not fully in control simply isn't a too
polite behaviour.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=50772 Tested-by: Maxim A. Nikulin <M.A.Nikulin@gmail.com> Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 20 Jul 2012 01:20:54 +0000 (21:20 -0400)]
Merge branch 'next' of git://people.freedesktop.org/~deathsimple/linux into drm-next
This contains all the radeon documentation rebased on top of the ib fixes.
* 'next' of git://people.freedesktop.org/~deathsimple/linux:
drm/radeon: fix SS setup for DCPLL
drm/radeon: fix up pll selection on DCE5/6
drm/radeon: start to document evergreen.c
drm/radeon: start to document the functions r100.c
drm/radeon: document VM functions in radeon_gart.c (v3)
drm/radeon: document non-VM functions in radeon_gart.c (v2)
drm/radeon: document radeon_ring.c (v4)
drm/radeon: document radeon_fence.c (v2)
drm/radeon: document radeon_asic.c
drm/radeon: document radeon_irq_kms.c
drm/radeon: document radeon_kms.c
drm/radeon: document radeon_device.c (v2)
drm/radeon: add rptr save support for r1xx-r5xx
drm/radeon: update rptr saving logic for memory buffers
drm/radeon: remove radeon_ring_index()
drm/radeon: update ib_execute for SI (v2)
drm/radeon: fix const IB handling v2
drm/radeon: let sa manager block for fences to wait for v2
drm/radeon: return an error if there is nothing to wait for
Alex Deucher [Tue, 17 Jul 2012 18:02:43 +0000 (14:02 -0400)]
drm/radeon: fix up pll selection on DCE5/6
Selecting ATOM_PPLL_INVALID should be equivalent as the
DCPLL or PPLL0 are already programmed for the DISPCLK, but
the preferred method is to always specify the PLL selected.
SetPixelClock will check the parameters and skip the
programming if the PLL is already set up.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
Alex Deucher [Tue, 17 Jul 2012 18:02:37 +0000 (14:02 -0400)]
drm/radeon: document radeon_fence.c (v2)
Adds documentation to most of the functions in
radeon_fence.c
v2: address Christian's comments:
- split common concept description into it's own comment
- fix description of intr parameter
- Improve description of -EDEADLK error
Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
Alex Deucher [Tue, 17 Jul 2012 18:02:29 +0000 (14:02 -0400)]
drm/radeon: update ib_execute for SI (v2)
When submitting a CONST_IB, emit a SWITCH_BUFFER
packet before the CONST_IB. This isn't strictly necessary
(the driver will work fine without it), but is good practice
and allows for more flexible DE/CE sychronization options
in the future. Current userspace drivers do not take
advantage of the CE yet.
v2: - clean up code flow a bit
- no need to flush caches for CONST IB
Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com>
Christian König [Mon, 9 Jul 2012 09:52:44 +0000 (11:52 +0200)]
drm/radeon: implement ring saving on reset v4
Try to save whatever is on the rings when
we encounter an lockup.
v2: Fix spelling error. Free saved ring data if reset fails.
Add documentation for the new functions.
v3: Some more spelling fixes
v4: It doesn't make sense to save anything if all fences
are signaled
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 6 Jul 2012 14:22:55 +0000 (16:22 +0200)]
drm/radeon: record what is next valid wptr for each ring v4
Before emitting any indirect buffer, emit the offset of the next
valid ring content if any. This allow code that want to resume
ring to resume ring right after ib that caused GPU lockup.
v2: use scratch registers instead of storing it into memory
v3: skip over the surface sync for ni and si as well
v4: use SET_CONFIG_REG instead of PACKET0
Signed-off-by: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 7 Jul 2012 10:47:58 +0000 (12:47 +0200)]
drm/radeon: move radeon_ib_ring_tests out of chipset code
Making it easier to control when it is executed.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 5 Jul 2012 12:32:00 +0000 (14:32 +0200)]
drm/radeon: remove vm_manager start/suspend
Just restore the page table instead. Addressing three
problem with this change:
1. Calling vm_manager_suspend in the suspend path is
problematic cause it wants to wait for the VM use
to end, which in case of a lockup never happens.
2. In case of a locked up memory controller
unbinding the VM seems to make it even more
unstable, creating an unrecoverable lockup
in the end.
3. If we want to backup/restore the leftover ring
content we must not unbind VMs in between.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Wed, 4 Jul 2012 19:36:53 +0000 (21:36 +0200)]
drm/radeon: make cp init on cayman more robust
It's not critical, but the current code isn't
100% correct.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Thu, 5 Jul 2012 11:33:41 +0000 (13:33 +0200)]
drm/radeon: remove FIXME comment from chipset suspend
For a normal suspend/resume we allready wait for
the rings to be empty, and for a suspend/reasume
in case of a lockup we REALLY don't want to wait
for anything.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 7 Jul 2012 11:10:39 +0000 (13:10 +0200)]
drm/radeon: fix fence init after resume
Start with last signaled fence number instead
of last emitted one.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Mon, 9 Jul 2012 08:52:39 +0000 (10:52 +0200)]
drm/radeon: fix fence value access
It is possible that radeon_fence_process is called
after writeback is disabled for suspend, leading
to an invalid read of register 0x0.
This fixes a problem for me where the fence value
is temporary incremented by 0x100000000 on
suspend/resume.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Sat, 7 Jul 2012 10:11:32 +0000 (12:11 +0200)]
drm/radeon: fix ring commit padding
We don't need to pad anything if the number of dwords
written to the ring already matches the requirements.
Fixes some "writting more dword to ring than expected"
warnings.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
drm/radeon: add an exclusive lock for GPU reset v2
GPU reset need to be exclusive, one happening at a time. For this
add a rw semaphore so that any path that trigger GPU activities
have to take the semaphore as a reader thus allowing concurency.
The GPU reset path take the semaphore as a writer ensuring that
no concurrent reset take place.
v2: init rw semaphore
Signed-off-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Tue, 3 Jul 2012 12:05:41 +0000 (14:05 +0200)]
drm/radeon: fix fence related segfault in CS
Don't return success if scheduling the IB fails, otherwise
we end up with an oops in ttm_eu_fence_buffer_objects.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
Christian König [Mon, 25 Jun 2012 13:13:50 +0000 (15:13 +0200)]
drm/radeon: add error handling to radeon_vm_unbind_locked
Waiting for a fence can fail for different reasons,
the most common is a deadlock.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christian König [Fri, 29 Jun 2012 09:33:12 +0000 (11:33 +0200)]
drm/radeon: add error handling to fence_wait_empty_locked
Instead of returning the error handle it directly
and while at it fix the comments about the ring lock.
Signed-off-by: Christian König <deathsimple@vodafone.de> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Chris Wilson [Tue, 10 Jul 2012 10:15:23 +0000 (11:15 +0100)]
drm: Add colouring to the range allocator
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>
Dave Airlie [Sat, 14 Jul 2012 08:15:21 +0000 (18:15 +1000)]
Merge tag 'drm-intel-next-2012-07-06' of git://people.freedesktop.org/~danvet/drm-intel into drm-next
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
...
Daniel Vetter [Thu, 5 Jul 2012 10:17:29 +0000 (12:17 +0200)]
drm/i915: introduce crtc->dspaddr_offset
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>
Daniel Vetter [Wed, 4 Jul 2012 20:52:50 +0000 (22:52 +0200)]
drm/i915: don't return a spurious -EIO from intel_ring_begin
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>
Daniel Vetter [Wed, 4 Jul 2012 20:18:42 +0000 (22:18 +0200)]
drm/i915: properly SIGBUS on I/O errors
... 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 ...
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>
Daniel Vetter [Wed, 4 Jul 2012 20:18:41 +0000 (22:18 +0200)]
drm/i915: don't hang userspace when the gpu reset is stuck
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
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>
Daniel Vetter [Wed, 4 Jul 2012 20:18:39 +0000 (22:18 +0200)]
drm/i915: don't trylock in the gpu reset code
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>
Eugeni Dodonov [Thu, 28 Jun 2012 18:55:35 +0000 (15:55 -0300)]
drm/i915: re-initialize DDI buffer translations after resume
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>
Paulo Zanoni [Tue, 3 Jul 2012 18:57:32 +0000 (15:57 -0300)]
drm/i915: get rid of dev_priv->info->has_pch_split
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>
Paulo Zanoni [Tue, 3 Jul 2012 21:48:16 +0000 (18:48 -0300)]
drm/i915: add PCH_NONE to enum intel_pch
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>
Jesse Barnes [Thu, 21 Jun 2012 22:13:50 +0000 (15:13 -0700)]
drm/i915: prefer wide & slow to fast & narrow in DP configs
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.
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>
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>
Chris Wilson [Mon, 2 Jul 2012 14:51:03 +0000 (11:51 -0300)]
drm/i915: Implement w/a for sporadic read failures on waking from rc6
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>
Chris Wilson [Mon, 2 Jul 2012 14:51:02 +0000 (11:51 -0300)]
drm/i915: Group the GT routines together in both code and vtable
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>
projects / linux-beck.git / log