With the introduction of the reloc page cache, we are just one step away
from refactoring the relocation write functions into one. Not only does
it tidy the code (slightly), but it greatly simplifies the control logic
much to gcc's satisfaction.
v2: Add selftests to document the relationship between the clflush
flags, the KMAP bit and packing into the page-aligned pointer.
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/20160818161718.27187-13-chris@chris-wilson.co.uk
There is an improbable, but not impossible, case that if we leave the
pages unpin as we operate on the object, then somebody via the shrinker
may steal the lock (which lock? right now, it is struct_mutex, THE lock)
and change the cache domains after we have already inspected them.
(Whilst here, avail ourselves of the opportunity to take a couple of
steps to make the two functions look more similar.)
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/20160818161718.27187-11-chris@chris-wilson.co.uk
If we quickly switch from writing through the GTT to a read of the
physical page directly with the CPU (e.g. performing relocations through
the GTT and then running the command parser), we can observe that the
writes are not visible to the CPU. It is not a coherency problem, as
extensive investigations with clflush have demonstrated, but a mere
timing issue - we have to wait for the GTT to complete it's write before
we start our read from the CPU.
The issue can be illustrated in userspace with:
gtt = gem_mmap__gtt(fd, handle, 0, OBJECT_SIZE, PROT_READ | PROT_WRITE);
cpu = gem_mmap__cpu(fd, handle, 0, OBJECT_SIZE, PROT_READ | PROT_WRITE);
gem_set_domain(fd, handle, I915_GEM_DOMAIN_GTT, I915_GEM_DOMAIN_GTT);
for (i = 0; i < OBJECT_SIZE / 64; i++) {
int x = 16*i + (i%16);
gtt[x] = i;
clflush(&cpu[x], sizeof(cpu[x]));
assert(cpu[x] == i);
}
Experimenting with that shows that this behaviour is indeed limited to
recent Atom-class hardware.
Testcase: igt/gem_exec_flush/basic-batch-default-cmd #byt
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/20160818161718.27187-10-chris@chris-wilson.co.uk
This is a companion to i915_gem_obj_prepare_shmem_read() that prepares
the backing storage for direct writes. It first serialises with the GPU,
pins the backing storage and then indicates what clfushes are required in
order for the writes to be coherent.
Whilst here, fix support for ancient CPUs without clflush for which we
cannot do the GTT+clflush tricks.
v2: Add i915_gem_obj_finish_shmem_access() for symmetry
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/20160818161718.27187-8-chris@chris-wilson.co.uk
When doing relocations, we have to obtain a mapping to the page
containing the target address. This is either a kmap or iomap depending
on GPU and its cache coherency. Neighbouring relocation entries are
typically within the same page and so we can cache our kmapping between
them and avoid those pesky TLB flushes.
Note that there is some sleight-of-hand in how the slow relocate works
as the reloc_entry_cache implies pagefaults disabled (as we are inside a
kmap_atomic section). However, the slow relocate code is meant to be the
fallback from the atomic fast path failing. Fortunately it works as we
already have performed the copy_from_user for the relocation array (no
more pagefaults there) and the kmap_atomic cache is enabled after we
have waited upon an active buffer (so no more sleeping in atomic).
Magic!
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/20160818161718.27187-7-chris@chris-wilson.co.uk
If we cannot release the fence (for example if someone is inexplicably
trying to write into a tiled framebuffer that is currently pinned to the
display! *cough* kms_frontbuffer_tracking *cough*) fallback to using the
page-by-page pwrite/pread interface, rather than fail the syscall
entirely.
Since this is triggerable by the user (along pwrite) we have to remove
the WARN_ON(fence->pin_count).
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/20160818161718.27187-6-chris@chris-wilson.co.uk
For virtual display feature, by hardcoding 0 for the vblank counter and
-EINVAL for the scanout position return value, we signal to the core DRM code that there are
no hardware counters we can use for these.
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit d25bcfb8c2.
I somehow missed that it only compiles on arm64 and broke the driver
rather badly.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Build the legacy semaphore initialisation array using the engine
hardware ids instead of driver internal ones. This makes the
static array size dependent only on the number of gen6 semaphore
engines.
Also makes the per-engine semaphore wait and signal tables
hardware id indexed saving some more space.
v2: Refactor I915_GEN6_NUM_ENGINES to GEN6_SEMAPHORE_LAST. (Chris Wilson)
v3: More polish. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1471363461-9973-1-git-send-email-tvrtko.ursulin@linux.intel.com
Put the engine hardware id in the common header so they are
not only associated with the GuC since they are needed for
the legacy semaphores implementation.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
We seem to have a bit a mess in how to describe the bus formats, with
a multitude of competing ways. Might be best to consolidate it all and
use MEDIA_BUS_FMT_ also for the hdmi color formats and high color
modes.
Also move all the display_info related functions into drm_connector.c
(there's only one) to group it all together. I did decided against
also moving the edid related display info functions, they seem to fit
better in drm_edid.c. Instead sprinkle a few cross references around.
While at that reduce the kerneldoc for static functions, there's not
point in documenting internals with that much detail really.
v2: Fix typo and move misplaced hunk (Sean).
Cc: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471034937-651-19-git-send-email-daniel.vetter@ffwll.ch
They're only used internally within the dp helpers. Also nuke the
kerneldoc (we only document the driver interface in the drm shared
functions). And move the header file from the public include/
directory to the source files into drm_crtc_helper_internal.h, similar
to how we already have drm_crtc_internal.h.
While at it also move drm_fb_helper_modinit since that belongs in
there, too.
I noticed this all since I spotted kerneldoc which wasn't pulled into
the rst templates.
v2: Update Copyright date.
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471034937-651-16-git-send-email-daniel.vetter@ffwll.ch
There's not much point in kerneldoc if it's not included:
- It won't show up in the pretty html pages.
- The comments itself won't get parsed, which means 0day won't pick up
changes, resulting in stale docs fast.
Also, uapi really should be core, not helpers, so move drm_blend.c to
that. That also means that the zpos normilize function loses it's
helper status (and we might as well call it always). For that,
EXPORT_SYMBOL. Just spotted while integrating docs and noticing that
one was missing.
With sphinx there's really no excuse any more to not build the docs
and make sure it's all nice!
$ make DOCBOOKS="" htmldocs
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471034937-651-15-git-send-email-daniel.vetter@ffwll.ch
Pulls in quite a lot of connector related structures (cmdline mode,
force/status enums, display info), but I think that all makes perfect
sense.
Also had to move a few more core kms object stuff into drm_modeset.h.
And as a first cleanup remove the kerneldoc for the 2 connector IOCTL
- DRM core docs are aimed at drivers, no point documenting internal in
excruciating detail.
v2: And also pull in all the connector property code.
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471034937-651-14-git-send-email-daniel.vetter@ffwll.ch
Also start with drm_modeset.h with the core bits, since we need
to untangle this mess somehow. That allows us to move the drm_modes.h
include to the right spot, except for the temporary connector status
enum. That will get fixed as soon as drm_connector.h exists.
v2: Rebase.
v3: Move drm_crtc_force_disable_all back again, that wasn't meant to
be moved (Sean).
v4: Rebase.
Cc: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It doesn't make much sense to create bigger commands first which we then need
to split into smaller one again. Just make sure the commands we create aren't
to big in the first place.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Write the PTEs at the end of the IB instead of directly into the SDMA commands.
This can save quite some CPU cycles building the entries.
This doesn't change the DW estimation because PTEs where embedded into the IB
before as well. It just moves them to the end of the IB.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The pd/pt shadow bo will be used to backup page table, when gpu reset
happens, we can restore the page table by them.
V2:
Free shadow bo.
Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
