... and QUIRK_PIPEA_FORCE is not present.
I initially thought that case was impossible and just added a WARN on
it, but then I was told this case is possible due to
QUIRK_PIPEA_FORCE. So let's add a WARN that serves two purposes:
- tell us in case we have done something wrong;
- document the only case where we expect this.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Add a nice comment explaining why we shouldn't wait for a vblank on
all cases, wait based on the HW gen, and add a comment saying we
should probably skip that wait on some of the previous HW gens.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we pass struct intel_crtc as an argument, we can check for
DSI inside the function, removing one more of those confusing boolean
arguments.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we pass struct intel_crtc as an argument, there's no need for
it.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We want to remove those 3 boolean arguments. This is the first step.
The "pipe" passed as the argument is always intel_crtc->pipe.
Also adjust the function documentation.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When I forked haswell_crtc_enable I copied all the code from
ironlake_crtc_enable. The last piece of the function contains a big
comment with a call to intel_wait_for_vblank. After this fork, we
rearranged the Haswell code so that it enables the planes as the very
last step of the modeset sequence, so we're sure that we call
intel_enable_primary_plane after the pipe is really running, so the
vblank waiting functions work as expected. I really believe this is
what fixes the problem described by the big comment, so let's give it
a try and get rid of that intel_wait_for_vblank, saving around 16ms
per modeset (and init/resume). We can always revert if needed :)
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Because on Haswell, the pipe is never running at this point, so we hit
the 50ms timeout waiting for nothing. We already have two other places
where we wait for vblanks on haswell_crtc_enable, so we're safe.
This gets us rid of one instance of "vblank wait timed out" for each
mode set, which means driver init and resume are also 50ms faster.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Depending on the HW gen and the connector type, the pipe won't start
running right after we call intel_enable_pipe, so that
intel_wait_for_vblank call we currently have will just sit there for
the full 50ms timeout. So this patch adds an argument that will allow
us to avoid the vblank wait in case we want. Currently all the callers
still request for the vblank wait, so the behavior should still be the
same.
We also added a POSTING_READ on the register: previously
intel_wait_for_vblank was acting as a POSTING_READ, but now if
wait_for_vblank is false we'll stkip it, so we need an explicit
POSTING_READ.
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of modifying intel_panel in lvds_init_connector/dsi_init/
edp_init_connector, making changes to move intel_panel->downclock_mode
initialization to intel_panel_init()
v2: Jani's review comments incorporated
Removed downclock_mode local variable in dsi_init and
edp_init_connector
Signed-off-by: Vandana Kannan <vandana.kannan@intel.com>
Signed-off-by: Pradeep Bhat <pradeep.bhat@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Can be expanded up on to include all sorts of things (HDMI infoframe
data, more DP status, etc). Should be useful for bug reports to get a
baseline on the display config and info.
v2: use seq_putc (Rodrigo)
describe mode field names (Rodrigo)
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Just like we have for connector type etc.
v2: drop static array (Chris)
v3: add kdoc (Daniel)
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Acked-by: Dave Airlie <airlied@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
For use by get_plane_config.
v2: cleanup tile_height bits (Chris)
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In Jesse's patch to switch the fbdev framebuffer from an embedded
struct to a pointer the kfree in case of an error was missed. Fix this
up by using our own internal fb allocation helper directly instead of
reinventing that wheel.
We need a to_intel_framebuffer cast unfortunately since all the other
callers of _create still look better whith using a drm_framebuffer as
return pointer.
v2: Add an unlocked __intel_framebuffer_create function since our
dev->struct_mutex locking is too much a mess. With ppgtt we even need
it to take a look at the global gtt offset of pinned objects, since
the vma list might chance from underneath us. At least with the
current global gtt lookup functions. Reported by Mika.
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that it's a normally kmalloce buffer we can use the usual cleanup
paths. The upside here is that if we get the refcounting wrong will be
able to catch it, since the drm core will complain about leftover
framebuffers and kref about underflows.
v2: Kill intel_framebuffer_fini - no longer needed now that we
refcount all fbs properly and only confusing.
v3: We actually still need to call unregister_private to remove the fb
from the idr and drop the idr reference - the final unref doesn't do
that. So much for remembering my own fb liftime rules. Reported by
Imre Deak.
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org> (v2)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we can't actually determine at run-time we have a fused-off display,
provide at least an option to disable it.
v2: Move the i915.disable_display test in a separate check
(Daniel Vetter)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
FUSE_STRAP has a bit to inform us that the display has been fused off.
Use it to setup the definitive number of pipes at run-time.
v2: actually tweak num_pipes, not num_planes
v3: also tests SFUSE_STRAP bit 7
v4: rebase on top of drm-nightly
use DRM_INFO() for the message telling display is fused off
try to read the FUSE_LOCK bit to determine if PCH display is disabled
v5: Don't read SFUSE_STRAP (register on the PCH) if num_pipes is already 0
from the initial device info struct (to prevent hangs) (Daniel Vetter)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> (for v3)
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (for v3)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Arjan van de Ven reported that on his test machine that he was seeing
stalls of greater than 1 frame greatly impacting the user experience. He
tracked this down to being the locked flush during a pagefault as being
the culprit hogging the struct_mutex and so blocking any other user from
proceeding. Stalling on a pagefault is bad behaviour on userspace's
part, for one it means that they are ignoring the coherency rules on
pointer access through the GTT, but fortunately we can apply the same
trick as the set-to-domain ioctl to do a lightweight, nonblocking flush
of outstanding rendering first.
"Prior to the patch it looks like this
(this one testrun does not show the 20ms+ I've seen occasionally)
4.99 ms 2.36 ms 31360 __wait_seqno i915_wait_seqno i915_gem_object_wait_rendering i915_gem_object_set_to_gtt_domain i915_gem_fault __do_fault handle_
+pte_fault handle_mm_fault __do_page_fault do_page_fault page_fault
4.99 ms 2.75 ms 107751 __wait_seqno i915_gem_wait_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
4.99 ms 1.63 ms 1666 i915_mutex_lock_interruptible i915_gem_fault __do_fault handle_pte_fault handle_mm_fault __do_page_fault do_page_fault page_fa
+ult
4.93 ms 2.45 ms 980 i915_mutex_lock_interruptible intel_crtc_page_flip drm_mode_page_flip_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_
+sysret
4.89 ms 2.20 ms 3283 i915_mutex_lock_interruptible i915_gem_wait_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
4.34 ms 1.66 ms 1715 i915_mutex_lock_interruptible i915_gem_pwrite_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
3.73 ms 3.73 ms 49 i915_mutex_lock_interruptible i915_gem_set_domain_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
3.17 ms 0.33 ms 931 i915_mutex_lock_interruptible i915_gem_madvise_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
2.97 ms 0.43 ms 1029 i915_mutex_lock_interruptible i915_gem_busy_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
2.55 ms 0.51 ms 735 i915_gem_get_tiling drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
After the patch it looks like this:
4.99 ms 2.14 ms 22212 __wait_seqno i915_gem_wait_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
4.86 ms 0.99 ms 14170 __wait_seqno i915_gem_object_wait_rendering__nonblocking i915_gem_fault __do_fault handle_pte_fault handle_mm_fault __do_page_
+fault do_page_fault page_fault
3.59 ms 1.31 ms 325 i915_gem_get_tiling drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
3.37 ms 3.37 ms 65 i915_mutex_lock_interruptible i915_gem_wait_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
2.58 ms 2.58 ms 65 i915_mutex_lock_interruptible i915_gem_do_execbuffer.isra.23 i915_gem_execbuffer2 drm_ioctl i915_compat_ioctl compat_sys_ioctl
+ia32_sysret
2.19 ms 2.19 ms 65 i915_mutex_lock_interruptible intel_crtc_page_flip drm_mode_page_flip_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_
+sysret
2.18 ms 2.18 ms 65 i915_mutex_lock_interruptible i915_gem_busy_ioctl drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
1.66 ms 1.66 ms 65 i915_gem_set_tiling drm_ioctl i915_compat_ioctl compat_sys_ioctl ia32_sysret
It may not look like it, but this is quite a large difference, and I've
been unable to reproduce > 5 msec delays at all, while before they do
happen (just not in the trace above)."
gem_gtt_hog on an old Pineview (GMA3150),
before: 4969.119ms
after: 4122.749ms
Reported-by: Arjan van de Ven <arjan.van.de.ven@intel.com>
Testcase: igt/gem_gtt_hog
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Atm we call the handlers for pending pipestat interrupt events even if
they aren't explicitly enabled by i915_enable_pipestat(). This isn't an
issue for events other than the vblank start event, since those are
always enabled anyways. Otoh, we enable the vblank start event
on-demand, so we'll end up calling the vblank handler at times when they
are disabled.
I haven't checked if this causes any real problem, but for consistency
and to remove some overhead we should still fix this by clearing /
handling only the enabled interrupt events. Also this is a dependency
for the upcoming VLV power domain patchset where we need to disable all
the pipestat interrupts whenever the display power well is off.
v2:
- inline the status->enable mask mapping (Ville)
- don't check for invalid PSR bit on platforms other than VLV (Ville)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Frob conflict due to different merge order.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
At least on VLV we can't get at the pipestat status bits by simply right
shifting the corresponding enable bits. The mapping between enable and
status bits for the sprite0,1 flip done and the PSR events don't follow
this rule, so we need to map them separately.
The PSR enable for pipe A is DPFLIPSTAT[22], but I haven't added support
for this, since there is no user of it atm. Until support is added WARN
if someone tries to enable PSR interrupts, or tries to enable the same
(1 << 6) bit on pipe B, which MBZ.
v2:
- inline the status->enable mask mapping (Ville)
- fix bogus use of status bits in enable mask (Ville)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There isn't any PSR interrupt enable bit for pipe A, so we couldn't
enable it through the current API. Passing the corresponding status bits
solves this and also makes the mapping between enable and status bits
simpler on VLV (addressed in an upcoming patch).
Except of checking for invalid status bit arguments, no functional
change.
v2: split out the low level parts of i915_enable_pipestat accepting
separate enabled and status masks, to make the non-standard mapping
between those masks stand out more (added in the next patch)
(Jesse,Daniel)
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Touching the VGA registers risks a hard machine hang, at least on this
ivb machine after removing a conflicting efifb. This is more than likely
related to the discovery that VGA IO decode on the more recent PCH
platforms is terminally broken.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This has very little effect other than log the errors in case of failure,
and we then hope for the best.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Allocate this struct instead, so we can re-use another allocated
elsewhere if needed.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: WARN_ON if there's no backing storage attached to an fb,
that's a bug.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we detect that the user passed along an invalid handle or object,
we emit a warning as an aide for debugging. Since these are indeed only
for debugging user triggerable errors (and the errors are reported back
to userspace by the errno), the messages should only be at the debug
level and not claiming that there is a catastrophic error in the
driver/hardware.
References: https://bugs.freedesktop.org/show_bug.cgi?id=74704
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We had 2 set of defines for the same register, so make it one.
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
And rename it to num_sprites as this value doesn't count the primary
plane.
This limit lives with num_pipes really, and now that dev_priv->info is
writable we can put it there instead.
While at it, introduce a intel_device_info_runtime_init() where we'll be
able to gather the device info fields at run-time.
v2: rename num_plane to num_sprites (Ville Syrjälä)
v3: rebase on top of latest drm-nightly
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> (for v2)
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (for v2)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Turns out it'd be nice to change some device information at run-time or simply
have some code to fill in the info struct instead of having to declare the
values in 30+ structures.
What prompted this change is handling fused out display/pipe and tweaking
num_pipes at run-time, but I'm quite sure we'll find other flags/limits to
stick into dev_priv->info.
Most of the changes were done with a sed:
sed -i -e 's/dev_priv->info->/dev_priv->info./g' drivers/gpu/drm/i915/*[ch]
with a few tweaks to make it all work:
- Change the field definition in struct drm_i915_private
- adjust i915_dump_device_info()
- adjust i915_driver_load()
- adjust the INTEL_INFO() macro
v2: cast the info pointer returned by INTEL_INFO() to be const to catch
uses that would modify the structure post-initialization.
(Ville Syrjälä)
v3: Redo the patch onto latest drm-nightly,
Keep the info field const to catch post initialization writes
instead of the v2 solution,
Use a direct structure copy for the initial info initialization to
use the compiler type safety (Ville Syrjälä)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> (for v2)
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com> (for v2)
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we make sure that all the dev_priv->info usages are wrapped by
INTEL_INFO(), we can easily modify the ->info field to be structure and
not a pointer while keeping the const protection in the INTEL_INFO()
macro.
v2: Rebased onto latest drm-nightly
Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
According to Bspec we need to disable SF pipelined attribute fetch
whenever SF outputs exceed 16 and normal clip mode is used. A quick
glance at Mesa suggests that these conditions could happen. So let's
just always set the magic bit.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
sysfs changes to rps min and max delay were only triggering an update
of the rps interrupt limits if the active delay required an update.
This change ensures that interrupt limits are always updated.
v2: correct compile issue missed on rebase
v3: add igt testcases to signed-off-by section
Testcase: igt/pm_rps/min-max-config-idle
Testcase: igt/pm_rps/min-max-config-loaded
Signed-off-by: Jeff McGee <jeff.mcgee@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
A check of rps/rc6 state after i915_reset determined that the ring
MAX_IDLE registers were returned to their hardware defaults and that
the GEN6_PMIMR register was set to mask all interrupts. This change
restores those values to their pre-reset states by re-initializing
rps/rc6 in i915_reset. A full re-initialization was opted for versus
a targeted set of restore operations for simplicity and maintain-
ability. Note that the re-initialization is not done for Ironlake,
due to a past comment that it causes problems.
Also updated the rps initialization sequence to preserve existing
min/max values in the case of a re-init. We assume the values were
validated upon being set and do not do further range checking. The
debugfs interface for changing min/max was updated with range
checking to ensure this condition (already present in sysfs
interface).
v2: fix rps logging to output hw_max and hw_min, not rps.max_delay
and rps.min_delay which don't strictly represent hardware limits.
Add igt testcase to signed-off-by section.
Testcase: igt/pm_rps/reset
Signed-off-by: Jeff McGee <jeff.mcgee@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As the VM do not track activity of objects and instead use a large
hammer to forcibly idle and evict all of their associated objects when
one is released, it is possible for that to cause a recursion when we
need to wait for free space on a ring and call retire requests.
(intel_ring_begin -> intel_ring_wait_request ->
i915_gem_retire_requests_ring -> i915_gem_context_free ->
i915_gem_evict_vm -> i915_gpu_idle -> intel_ring_begin etc)
In order to remove the requirement for calling retire-requests from
intel_ring_wait_request, we have to inline a couple of steps from
retiring requests, notably we have to record the position of the request
we wait for and use that to update the available ring space.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We get a large number of bugs which have a, "hey I have that too"
because they see a GPU hang in dmesg. While two machines of the same
model having a GPU hang is indeed a coincidence, it is far from enough
evidence to suggest they are the same.
In order to reduce this effect, and hopefully get people to file new bug
reports, clearly the error message itself has been insufficient (see ref
at the bottom for a new bug report with this characteristic).
The algorithm is purposely pretty naive. I don't think we need much in
order to avoid the problem I am trying to solve, and keeping it naive
gives us some ability to make a decent test case.
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
References: https://bugs.freedesktop.org/show_bug.cgi?id=73276
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
s/FLIPDONE/FLIP_DONE/ to make all FLIP_DONE macro names consistent.
No functional change.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This will be used by other platforms too, so factor it out.
The only functional change is the reordeing of gmbus_irq_handler() wrt.
the hotplug handling, but since it only schedules a work, it isn't an
issue.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
[danvet: Don't keep on using the private_t typedef.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Bspec and the code suggests that the interrupt signaled by IIR[7,5]
(DISPLAY_PIPE_A/B_VBLANK) is a first level IRQ flag for the second
level PIPEA/BSTAT[2] (Start of Vertical Blank) interrupt. Measuring
the relative timings of when IIR[7] and PIPEASTAT[1,2] get set and
checking the effect of unmasking different pipestat and IIR events
shows that this isn't so:
First, ISR/IIR[7] gets set independently of PIPEASTAT[18] (Start of
Vertical Blank Enable) or any other pipestat enable bit, so it isn't
a first level IRQ bit showing the state of PIPEASTAT[2], but is
connected directly to the timing generator.
Second, setting only PIPEASTAT[18] and leaving all other pipestat events
disabled, IIR[6] (DISPLAY_PIPE_A_EVENT) gets set close to the moment when
PIPEASTAT[2] gets set, so the former is a first level interrupt flag for
the latter. The bspec is rather unclear about this, but I also assume
that IIR[6] signals all pipestat A events, except PIPEASTAT[31] (FIFO
Under-run Status).
Third, IIR[7] is set close to the moment when PIPEASTAT[1] (Framestart
Interrupt) gets set, in the mode I used about 12usec after PIPEASTAT[2]
and IIR[6] gets set. This means the IIR[7] isn't marking the start of
vblank, but rather signals the framestart event.
Based on the above, we don't need to unmask IIR[7] when waiting for
start of vblank events, but we can rely on IIR[6] being always unmasked,
which will signal when PIPEASTAT[2] gets set. Doing this will also get
rid of the overhead of getting an interrupt and servicing IIR[7], which
is atm raised always some time after IIR[6]/PIPEASTAT[2] is raised.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
RFCv2: Reorganize array indexing so that full offsets can be used as
is. It makes grepping for registers in i915_reg.h much easier. Also
move offset arrays to intel_device_info.
v1: Fixed offsets for VLV, proper eDP handling
v2: Fixed BCLRPAT, PIPESRC, PIPECONF and DSP* macros.
v3: Added EDP pipe comment, removed redundant offset arrays for
MSA_MISC and DDI_FUNC_CTL.
v4: Rename patch and report object size increase.
v5: Change location of commas, add PIPE_EDP into enum pipe
v6: Insert PIPE_EDP_OFFSET into pipe offset array
v7: Set I915_MAX_PIPES back to 3, change more registers accessors
to use the new macros, get rid of _PIPE_INC and add dev_priv
as a parameter where required by the new macros.
Upcoming hardware will not have the various display pipe register
ranges evenly spaced in memory. Change register address calculations
into array lookups.
Tested on SNB, VLV, IVB, Gen2 and HSW w/eDP.
I left the UMS cruft untouched.
Size differences:
text data bss dec hex filename
596431 4634 56 601121 92c21 i915.ko (new)
593199 4634 56 597889 91f81 i915.ko (old)
Signed-off-by: Antti Koskipaa <antti.koskipaa@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Since a purged buffer is one without any associated pages, attempting to
use it should generate EFAULT rather than EINVAL, as it is not strictly
an invalid parameter.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
EFAULT will be a possible return code where backing storage is
transient, such after it is purged by madvise. As such it is to be
expected and so should not trigger a WARN inside i915_gem_fault() but be
converted silently to SIGBUS.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we enter RC6 and GFX Clocks are off, the voltage remains higher
than Vmin. When we try to set the freq to RPn, it might fail since the
Gfx clocks are down. So to fix this in Gfx idle, Bring the GFX clock up
and set the freq to RPn then move GFx down.
v2: remove vlv_update_rps_cur_delay function. Update commit message (Daniel)
v3: Fix the timeout during wait for gfx clock (Jesse)
v4: addressed comments on set freq and punit wait (Ville)
v5: use wait_for while waiting for GFX clk to be up. (Daniel)
update cur_delay before requesting min_delay. (Ville)
v6: use wait_for while waiting for punit. (Ville)
Signed-off-by: Deepak S <deepak.s@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As we seek the guilty batch using request and hangcheck
score, this code is not needed anymore.
v2: Rebase. Passing dev_priv instead of getting it from last_ring
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With full ppgtt using acthd is not enough to find guilty
batch buffer. We get multiple false positives as acthd is
per vm.
Instead of scanning which vm was running on a ring,
to find corressponding context, use a different, simpler,
strategy of finding batches that caused gpu hang:
If hangcheck has declared ring to be hung, find first non complete
request on that ring and claim it was guilty.
v2: Rebase
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=73652
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Both Bspec and the W/A database state that WaDisablePSDDualDispatchEnable
is only needed for IVB GT1.
The only real confusion here is that the the W/A database also says to
write to the GT2 only register as well, which is strange if the W/A is
only for GT1.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
IVB GT2 has two registers for these things, and both must be written.
To add a bit more confusion both Bspec and the W/A database state that
WaDisablePSDDualDispatchEnable is only needed for IVB GT1, but the W/A
database also says to write even the second GT2 only register. So I
don't really know what the right thing here is.
Note that Bspec disagrees with the w/a database here, but Ville
confirmed (by asking Chris) that on gt1 the 2nd reg doesn't exist.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
[danvet: Add note as requested by Rodrigo.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We want to use the GTT for reading back objects upon an error so that we
have exactly the information that the GPU saw. However, it is verboten
to access snoopable pages through the GTT and causes my PineView GPU to
throw a page fault instead.
This has not been a problem in the past as we only dumped ringbuffers
and batchbuffers, both of which must be not snooped. However, the
introduction of HWS page dumping leads to a read of a snooped object
through the GTT. This was introduced by
commit f3ce382139
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu Jan 23 22:40:36 2014 +0000
drm/i915: Include HW status page in error capture
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet:s/uncached/not snooped/ for one case in the commit message as
requested by Chris.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
