If we want to know how many pages a VMA spans, we can use vma_pages() to
find out. We have one such invocation inside our faulthandler, so
convert it. (We have two other that want the size in bytes rather than
pages, food for future thought.)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20161011090656.29554-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
commit 1625e7e549 ("drm/i915: make compact dma scatter lists creation
work with SWIOTLB backend") took a heavy handed approach to undo the
scatterlist compaction in the face of SWIOTLB. (The compaction hit a bug
whereby we tried to pass a segment larger than SWIOTLB could handle.) We
can be a little more intelligent and try compacting the scatterlist up
to the maximum SWIOTLB segment size (when using SWIOTLB).
v2: Tidy sg_mark_end() and cpp
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
CC: Imre Deak <imre.deak@intel.com>
CC: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161011082021.14606-2-chris@chris-wilson.co.uk
When we notice the system under memory pressure, we try to evict some
driver pages before asking the VM to shrink all caches. As a final step
in that process, we tried to evict everything, including active buffers.
This is harming ourselves, and we can mix shrinking all caches as well
as our residual buffers (after the first pass of trying to shrink just
our own buffers).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161011082021.14606-1-chris@chris-wilson.co.uk
Along with the interrupt, we want to restore the fake-irq and
wait-timeout detection. If we use the breadcrumbs interface to setup the
interrupt as it wants, the auxiliary timers will also be restored.
v2: Cancel both timers as well, sanitize the IMR.
Fixes: 821ed7df6e ("drm/i915: Update reset path to fix incomplete requests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161007065327.24515-3-chris@chris-wilson.co.uk
If we run out of enough aperture space to fit the entire object, we
fallback to trying to insert a single page. However, if that also fails,
we currently fail to userspace with an unexpected ENOSPC. (ENOSPC means
to userspace that their batch could not be fitted within the GTT.) Prior
to commit e8cb909ac3 ("drm/i915: Fallback to single page GTT
mmappings for relocations") the approach is to fallback to using the
slow CPU relocation path in case of iomapping failure, and that is the
behaviour we need to restore.
Fixes: e8cb909ac3 ("drm/i915: Fallback to single page GTT mmappings...")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98101
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161007065327.24515-2-chris@chris-wilson.co.uk
In order not to trigger hangcheck on a idle-but-waiting engine, we need
to distinguish between the pending request queue and the actual
execution queue. This is done later in "drm/i915: Enable multiple
timelines" but for now we need a temporary fix to prevent blaming the
wrong engine for a GPU hang.
(Note that this causes a temporary subtle change in how we decide when
to allow a waitboost to be re-awarded back to the waiter, the temporary
effect is that if the wait is upon the most current execution the wait
is given for free, instead of checking to see if the client stalled
itself. This will be repaired in "drm/i915: Enable multiple timelines".)
Fixes: 0a046a0e93 ("drm/i915: Nonblocking request submission")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=98104
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161007065327.24515-1-chris@chris-wilson.co.uk
Intel DZ77BH-55K board doest't have a physical VGA connector,
and yet it always detects that something is connected there.
Add it to the DMI blacklist to ignore the spurious detection
results.
Allows me to drop 'video=VGA-1:d' from my kernel cmdline.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1474881646-1326-3-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Having a shadow VGA connector is useful for testing purposes. We
currently skip registering the connector on machines where the
CRT detect falsely reports it as connected. Let's instead move the
the blacklist check to the detect callback (and hpd setup) and
if we get a match we always report the connector as disconnected.
This way we get a shadow VGA connector to help with testing, while
we still avoid the user facing problems from the incorrect
detection results.
commit 8ca4013d70 ("CHROMIUM: i915: Add DMI override to skip CRT
initialization on ZGB") doesn't provide much in the way of details
as to why 'ACER ZGB' was added to the blacklist. Trying to trace it
further leads me to a chromeos bugreport I can't access. So based on
the fact that the commit added the
"/* Skip machines without VGA that falsely report hotplug events */"
comment, I'm going to assume that it was just spurious CRT detection.
So it should be safe to move the blacklist to just block the detection
and hpd without causing a regression on said machine.
In fact Stéphane confirmed on irc that the problem was indeed just
crappy hotplug detect:
"22:29 < marcheu> vsyrjala: the port isn't there, but the load detect is
improperly stubbed in hw
22:29 < marcheu> vsyrjala: so it floats"
so this change should be perfectly fine.
v2: Add irc quote from Stéphane
Cc: Duncan Laurie <dlaurie@chromium.org>
Cc: Olof Johansson <olofj@chromium.org>
Cc: Stéphane Marchesin <marcheu@chromium.org>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1474881646-1326-2-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Get rid of SEP_SEMICOLON and SEP_BLANK in DEV_INFO_FOR_EACH_FLAG.
Consolidate the debug output so that instead of one huge line with
"cap1,cap2,capN" each capability is split to own line and displayed
as "capN: [yes|no]" to make the dumps more historically informative.
v2:
- Do not break auto-indent by keeping semicolon after macro (Jani)
- Consolidate and use yesno() in all locations (Chris)
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Allow returning "connected" or "unknown" connector status for DP branch
devices that don't have an EDID. Currently we'd claim the thing as
"disconnected" if there is no EDID.
This stuff used to broken already, I think, but it got more broken by
commit f21a21983e ("drm/i915: Splitting intel_dp_detect")
Cc: Damien Cassou <damien@cassou.me>
Cc: freedesktop.org@gp.mailgun.org
Cc: Arno <blouin.arno@gmail.com>
Cc: Shubhangi Shrivastava <shubhangi.shrivastava@intel.com>
Cc: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Cc: Ander Conselvan de Oliveira <conselvan2@gmail.com>
Cc: stable@vger.kernel.org
Tested-by: Arno <blouin.arno@gmail.com>
Fixes: f21a21983e ("drm/i915: Splitting intel_dp_detect")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83348
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1475481316-8194-2-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Ander Conselvan de Oliveira <conselvan2@gmail.com>
We can't rely on connector->status in the detect() hook if the long hpd
was already handled by the dig_port_work as that won't update
connector->status. Thus we have to defer the long hpd handling entirely
until the hotplug work runs to avoid the double long hpd handling
the "detect_done" flag is trying to prevent.
We'll start to depend on connector->status being up to date in a
following patch.
Cc: Damien Cassou <damien@cassou.me>
Cc: freedesktop.org@gp.mailgun.org
Cc: Arno <blouin.arno@gmail.com>
Cc: Shubhangi Shrivastava <shubhangi.shrivastava@intel.com>
Cc: Sivakumar Thulasimani <sivakumar.thulasimani@intel.com>
Cc: Ander Conselvan de Oliveira <conselvan2@gmail.com>
Cc: stable@vger.kernel.org
Tested-by: Arno <blouin.arno@gmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83348
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1475481316-8194-1-git-send-email-ville.syrjala@linux.intel.com
Reviewed-by: Ander Conselvan de Oliveira <conselvan2@gmail.com>
Knowing where the RINGs are pointing is extremely useful in diagnosing
if the engines are executing the ringbuffers you expect - and igt may be
suppressing the usual method of looking in the GPU error state.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-7-chris@chris-wilson.co.uk
Include the position of the active request in the ring, and display that
alongside the current RING registers (on a GPU hang).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-6-chris@chris-wilson.co.uk
Check that there was not a late recovery between us declaring the GPU
hung and processing the reset. If the GPU did recover by itself, let the
request remain on the active list and see if it hangs again!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-5-chris@chris-wilson.co.uk
Whilst we reset the GPU, we want to prevent execlists from submitting
new work (which it does via an interrupt handler). To achieve this we
disable the irq (and drain the irq tasklet) around the reset. When we
enable it again afters, the interrupt queue should be empty and we can
reinitialise from a known state without fear of the tasklet running
concurrently.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-4-chris@chris-wilson.co.uk
After a GPU reset, we want to replay our queue of requests. However, the
GPU reset clobbered the state and we only fixup the state for the guilty
request - and engines deemed innocent we try to leave untouched so that
we recover as completely as possible. However, we need to clear the sw
tracking of the ELSP ports even for innocent requests, so move the clear
to the common path of init_hw (from reset_hw).
Reported-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-3-chris@chris-wilson.co.uk
On Braswell, at least, we observe that the context image is written in
multiple phases. The first phase is to clear the register state, and
subsequently rewrite it. A GPU reset at the right moment can interrupt
the context update leaving it corrupt, and our update of the RING_HEAD
is not sufficient to restart the engine afterwards. To recover, we need
to reset the registers back to their original values. The context state
is lost. What we need is a better mechanism to serialise the reset with
pending flushes from the GPU.
Fixes: 821ed7df6e ("drm/i915: Update reset path to fix incomplete requests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-2-chris@chris-wilson.co.uk
Since both legacy and execlists want to populate the RING_CTL register,
share the computation of the right bits for the ring->size. We can then
stop masking errors and explicitly forbid them during creation!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161004201132.21801-1-chris@chris-wilson.co.uk
Fix sparse warning:
drivers/gpu/drm/i915/intel_pm.c:3970:1: warning: symbol
'skl_ddb_add_affected_planes' was not declared. Should it be static?
Fixes: 7f60e200e2 ("drm/i915/gen9: only add the planes actually affected by ddb changes")
Cc: Lyude <cpaul@redhat.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1475573357-30562-1-git-send-email-jani.nikula@intel.com
Simply replace the linear search with the kernel's binary
search implementation. There is only six registers currently
in that table so this may not be that interesting. It adds a
function call so hopefully remains performance neutral for now.
v2: No need for manual conversion to bool for return.
(Joonas Lahtinen)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Also verify the order at runtime. This was we can start using
binary search on it in a following patch.
v2: Add comment on the sorted array and only check it when
debug option is enabled.
v3: Use IS_ENABLED. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> (v1)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
We notice two identical copies of the shadow register table and
following from that removal can also unify CHV and Gen9 write
mmio functions and macros into a single implementation.
v2: Name fwtable consistently and use HAS_FWTABLE. (Joonas Lahtinen)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
It is now obvious VLV, CHV and Gen9 mmio read fcuntions are
completely identical so we can remove the three copies and
just keep the newly named generic implementation.
v2: Use fwtable naming consistently. (Joonas Lahtinen)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Remove some macros which are now obviously identical.
v2: Added HAS_FWTABLE macro and simplified intel_uncore_forcewake_for_read.
(Joonas Lahtinen)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
If we store this in the uncore structure we are on a good way to
show more commonality between the per-platform implementations.
v2: Constify table pointer and correct coding style. (Chris Wilson)
v3: Rebase.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
If we insert blitter forcewake domain entries in the range
table we can eliminate that special case and simplify the
code in a few macros. This will enable more unification later.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Instead of the existing linear seach, now that we have sorted
range tables, we can do a binary search on them for some
potential miniscule performance gain, but more importantly
for elegance and code size. Hopefully the perfomance gain is
sufficient to offset the function calls which were not there
before.
v2: Removed const cast away.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Sorting the tables (verified at runtime to help during
development) is another prerequisite for interesting
work which will follow.
v2:
* Remove const away cast and improve comments. (Chris Wilson)
* Check tables only when debug option is enabled.
v3: Use IS_ENABLED. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Move finding the correct forcewake domains to take for
register access from code to a mapping table. This will
allow more interesting work in the following patches
and is easier to review if singled out early.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Once we know we need to take new forcewakes, that being
a slow operation, it does not make sense to inline that
code into every mmio accessor.
Move it to a separate function and save some code.
v2: Be explicit with noinline and remove stale comment.
(Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
There are current places in the code, and there will be more in the
future, which iterate the forcewake domains to find out which ones
are currently active.
To save them from doing this iteration, we can cheaply keep a mask
of active domains in dev_priv->uncore.fw_domains_active.
This has no cost in terms of object size, even manages to shrink it
overall by 368 bytes on my config.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: "Paneri, Praveen" <praveen.paneri@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
They are completely identical to gen6_write* ones.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Fix sparse warning:
drivers/gpu/drm/i915/intel_device_info.c:195:31: warning: Variable
length array is used.
In truth the array does have constant length, but sparse is too dumb to
realize. This is a bit ugly, but silence the warning no matter what.
Fixes: 91bedd34ab ("drm/i915/bdw: Check for slice, subslice and EU count for BDW")
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1475574853-4178-1-git-send-email-jani.nikula@intel.com
When decoding the semaphores inside hangcheck, we need to use the hw-id
and not the local array index.
Fixes: de1add3605 ("drm/i915: Decouple execbuf uAPI ...")
Testcase: igt/gem_exec_whisper/hang # gen6-7
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161003124516.12388-3-chris@chris-wilson.co.uk
We were previously adding all the planes owned by the CRTC even when
the ddb partitioning didn't change for them. As a consequence, a lot
of functions were being called when we were just moving the cursor
around the screen, such as skylake_update_primary_plane().
This was causing flickering on the primary plane when moving the
cursor. I'm not 100% sure which operation caused the flickering, but
we were writing to a lot of registers, so it could be any of these
writes. With this patch, just moving the mouse won't add the primary
plane to the commit since it won't trigger a change in DDB
partitioning.
v2: Use skl_ddb_entry_equal() (Lyude).
v3: Change Reported-and-bisected-by: to Reported-by: for checkpatch
Fixes: 05a76d3d6a ("drm/i915/skl: Ensure pipes with changed wms get added to the state")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=97888
Cc: Mike Lothian <mike@fireburn.co.uk>
Cc: stable@vger.kernel.org
Reported-by: Mike Lothian <mike@fireburn.co.uk>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Lyude <cpaul@redhat.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1475177808-29955-1-git-send-email-paulo.r.zanoni@intel.com
