Userspace is faced with a dilemma. The kernel requires implicit fencing
to manage resource usage (we always must wait for the GPU to finish
before releasing its PTE) and for third parties. However, userspace may
wish to avoid this serialisation if it is either using explicit fencing
between parties and wants more fine-grained access to buffers (e.g. it
may partition the buffer between uses and track fences on ranges rather
than the implicit fences tracking the whole object). It follows that
userspace needs a mechanism to avoid the kernel's serialisation on its
implicit fences before execbuf execution.
The next question is whether this is an object, execbuf or context flag.
Hybrid users (such as using explicit EGL_ANDROID_native_sync fencing on
shared winsys buffers, but implicit fencing on internal surfaces)
require a per-object level flag. Given that this flag need to be only
set once for the lifetime of the object, this reduces the convenience of
having an execbuf or context level flag (and avoids having multiple
pieces of uABI controlling the same feature).
Incorrect use of this flag will result in rendering corruption and GPU
hangs - but will not result in use-after-free or similar resource
tracking issues.
Serious caveat: write ordering is not strictly correct after setting
this flag on a render target on multiple engines. This affects all
subsequent GEM operations (execbuf, set-domain, pread) and shared
dma-buf operations. A fix is possible - but costly (both in terms of
further ABI changes and runtime overhead).
Testcase: igt/gem_exec_async
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Chad Versace <chadversary@chromium.org>
Link: http://patchwork.freedesktop.org/patch/msgid/20170127094008.27489-1-chris@chris-wilson.co.uk
The i915_stolen_to_physical() function has 'unsigned long' as its
return type but it returns the 'base' variable, which is of type
'u32'. The only place where this function is called assigns the
returned value to dev_priv->mm.stolen_base, which is of type
'phys_addr_t'. The return value is actually a physical address and
everything else in the stolen memory code seems to be using
phys_addr_t, so fix i915_stolen_to_physical() to use phys_addr_t.
v2: Add missing blank lines after declarations (Chris, checkpatch.pl).
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1485461947-16030-1-git-send-email-paulo.r.zanoni@intel.com
The intel_dp_autotest_video_pattern() function gets invoked through the
compliance test handler on a HPD short pulse if the test type is
set to DP_TEST_VIDEO_PATTERN. This performs the DPCD registers
reads to read the requested test pattern, video pattern resolution,
frame rate and bits per color value. The results of this analysis
are handed off to userspace so that the userspace app can set the
video pattern mode appropriately for the test result/response.
When the test is requested with specific BPC value, we read the BPC
value from the DPCD register. If this BPC value in intel_dp structure
has a non-zero value and we're on a display port connector, then we use
the value to calculate the bpp for the pipe. Also in this case if its
a 18bpp video pattern request, then we force the dithering on pipe to be
disabled since it causes CRC mismatches.
The compliance_test_active flag is set at the end of the individual
test handling functions. This is so that the kernel-side operations
can be completed without the risk of interruption from the userspace
app that is polling on that flag.
v5:
* Remove test_result variable
* Populate the compliance test data at the end of the function (Jani Nikula)
v4:
*Return TEST_NAK on read failures and invalid values (Jani Nikula)
* Address CRC mismatch errors
v3:
* Use the updated properly shifted bit definitions (Jani Nikula)
* Force dithering to be disabled on 18bpp compliance
test request (Manasi Navare)
v2:
* Updated the DPCD Register reads based on proper defines in header (Jani Nikula)
* Squahsed the patch that forced the pipe bpp to compliance test bpp (Jani Nikula)
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1485274909-17470-1-git-send-email-manasi.d.navare@intel.com
This patch adds support to handle automated DP compliance
link training test requests. This patch has been tested with
Unigraf DPR-120 DP Compliance device for testing Link
Training Compliance.
After we get a short pulse Compliance test request, test
request values are read and hotplug uevent is sent in order
to trigger another modeset during which the pipe is configured
and link is retrained and enabled for link parameters requested
by the test.
v5:
* Only modify the compliance structure after all validation
is done (Jani Nikula)
* Remove the variable test_result (Jani Nikula)
v4:
* Return TEST_NAK for read failures and invalid
values (Jani Nikula)
* Conver the test link BW to link rate before storing (Jani Nikula)
v3:
* Validate the test link rate and lane count as soon as
the request comes (Jani Nikula)
v2:
* Validate the test lane count before using it in
intel_dp_compute_config (Jani Nikula)
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1485274594-17361-1-git-send-email-manasi.d.navare@intel.com
Along with GLK it was introduced the .is_lp and IS_GEN9_LP.
So, following the same simplification standard we can
put Skylake and Kabylake under the same bucket for most
of the things.
So let's add the IS_GEN9_BC for "Big Core" (non Atom based
platforms).
The i915_drv.c was let out of this patch on purpose
because that is really a decision per platform, just like
other cases where IS_KABYLAKE is different from IS_SKYLAKE.
v2: fix conflict with IS_LP and 3 new cases for this
big core bucket:
- intel_ddi.c: intel_ddi_get_link_dpll
- intel_fbc.c: find_compression_threshold
- i915_gem_gtt.c: gtt_write_workarounds
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Ander Conselvan de Oliveira <conselvan2@gmail.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1485196357-30599-2-git-send-email-rodrigo.vivi@intel.com
We need to prevent resubmission of the context immediately following an
initial resubmit (which does a lite-restore preemption). Currently we do
this by disabling all submission whilst the context is still active, but
we can improve this by limiting the restriction to only until we
receive notification from the context-switch interrupt that the
lite-restore preemption is complete.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170124110009.28947-2-chris@chris-wilson.co.uk
The GPU may be in an unknown state following resume and module load. The
previous occupant may have left contexts loaded, or other dangerous
state, which can cause an immediate GPU hang for us. The only save
course of action is to reset the GPU prior to using it - similarly to
how we reset the GPU prior to unload (before a second user may be
affected by our leftover state).
We need to reset the GPU very early in our load/resume sequence so that
any stale HW pointers are revoked prior to any resource allocations we
make (that may conflict).
A reset should only be a couple of milliseconds on a slow device, a cost
we should easily be able to absorb into our initialisation times.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170124110135.6418-2-chris@chris-wilson.co.uk
In order to reset the GPU early on in the module load sequence, we need
to allocate the basic engine structs (to populate the mmio offsets etc).
Currently, the engine initialisation allocates both the base struct and
also allocate auxiliary objects, which depend upon state setup quite
late in the load sequence. We split off the allocation callback for
later and allow ourselves to allocate the engine structs themselves
early.
v2: Different paint for the unwind following error.
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/20170124110135.6418-1-chris@chris-wilson.co.uk
Since tweaking i915_vma_compare() we allowed constructors to skip
clearing the ggtt_view believing that we didn't access the unused
members. That, as it turns out, was not entirely true. In particular,
i915_gem_fault() uses
ret = remap_io_mapping(area,
area->vm_start + (vma->ggtt_view.partial.offset << PAGE_SHIFT),
(ggtt->mappable_base + vma->node.start) >> PAGE_SHIFT,
min_t(u64, vma->size, area->vm_end - area->vm_start),
&ggtt->mappable);
i.e. the ggtt_view.partial for both normal and partial views. If we
allowed garbage into the normal vma->ggtt_view and then try userspace
tried to mmap it, we could explode in an unobvious fashion.
Fixes: 7b92c047ba ("drm/i915: Eliminate superfluous i915_ggtt_view_rotated")
Fixes: 3bf4d57519 ("drm/i915: Stop clearing i915_ggtt_view")
Reported-by: Matthew Auld <matthew.william.auld@gmail.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170123145245.3972-1-chris@chris-wilson.co.uk
Tested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
This reverts commit 527b6abe5f
(Revert "drm/i915: Use atomic commits for legacy page_flips")
and reapplies commit ee042aa40b.
("drm/i915: Use atomic commits for legacy page_flips")
The reason for the revert was because legacy cursor updates were
forced to wait for pending page flips and rendering after they
were converted to atomic.
Commit f79f26921e
(drm/i915: Add a cursor hack to allow converting legacy page flip to atomic, v3)
adds a fastpath to cursor updates, which fixes the stuttering issues.
With these changes I feel confident enough to re-enable cursor updates.
Legacy cursor update won't block in the following cases:
- Moving cursor
- Changing cursor fb
The legacy cursor update will still block in the following cases:
- Showing/hiding cursor.
- Cursor size or scaling changes.
- cursor update while cursor is invisible (could be fixed, if it turns out to be important).
- Cursor tiling changes (Not sure we support tiled cursors.)
- Last update was a modeset.
Cc: Steven Newbury <steve@snewbury.org.uk>
Cc: Rafael Ristovski <rafael.ristovski@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Tested-by: Rafael Ristovski <rafael.ristovski@gmail.com>
Testcase: igt/kms_cursor_legacy
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
