-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAl3IqJQeHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGOiUH+gOEDwid5OODaFAd
CggXugdFIlBZefKqGVNW5sjgX8pxFWHXuEMC8iNb6QXtQZdFrI6LFf9hhUDmzQtm
6y1LPxxEiTZjObMEsBNylb7tyzgujFHcAlp0Zro3w/HLCqmYTSP3FF46i2u6KZfL
XhkpM4X7R7qxlfpdhlfESv/ElRGocZe6SwXfC7pcPo5flFcmkdu9ijqhNd/6CZ/h
Nf9rTsD/wEDVUelFbgVN+LJzlaB0tsyc4Zbof07n8OsFZjhdEOop8gfM/kTBLcyY
6bh66SfDScdsNnC/l8csbPjSZRx+i+nQs67DyhGNnsSAFgHBZdC4Tb/2mDCwhCLR
dUvuYZc=
=1N6F
-----END PGP SIGNATURE-----
Merge v5.4-rc7 into drm-next
We have the i915 security fixes to backmerge, but first
let's clear the decks for other drivers to avoid a bigger
mess.
Signed-off-by: Dave Airlie <airlied@redhat.com>
In the impelementation of v3d_submit_cl_ioctl() there are two memory
leaks. One is when allocation for bin fails, and the other is when bin
initialization fails. If kcalloc fails to allocate memory for bin then
render->base should be put. Also, if v3d_job_init() fails to initialize
bin->base then allocated memory for bin should be released.
Fixes: a783a09ee7 ("drm/v3d: Refactor job management.")
Signed-off-by: Navid Emamdoost <navid.emamdoost@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20191021185250.26130-1-navid.emamdoost@gmail.com
Extends the user space ioctl for CL submissions so it can include a request
to flush the cache once the CL execution has completed. Fixes memory
write violation messages reported by the kernel in workloads involving
shader memory writes (SSBOs, shader images, scratch, etc) which sometimes
also lead to GPU resets during Piglit and CTS workloads.
v2: if v3d_job_init() fails we need to kfree() the job instead of
v3d_job_put() it (Eric Anholt).
v3 (Eric Anholt):
- Drop _FLAG suffix from the new flag name.
- Add a new param so userspace can tell whether cache flushing is
implemented in the kernel.
Signed-off-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919071016.4578-1-itoral@igalia.com
Be more consistent with the naming of the other DMA-buf objects.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/323401/
Drop use of the deprecated drmP.h header file.
Made v3d_drv.h self-contained with only sufficient
include files.
Fixed fallout in remaining files.
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Acked-by: Emil Velikov <emil.velikov@collabora.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20190716064220.18157-3-sam@ravnborg.org
Looking at a hang recently, I noticed these registers that might tell
me if something obvious was wrong. They didn't help in this case, but
keep it around for the future.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190419001014.23579-3-eric@anholt.net
Reviewed-by: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
It is the expectation of existing userspace (X11 + Mesa, in
particular) that jobs submitted to the kernel against a shared BO will
get implicitly synchronized by their submission order. If we want to
allow clever userspace to disable implicit synchronization, we should
do that under its own submit flag (as amdgpu and lima do).
Note that we currently only implicitly sync for the rendering pass,
not binning -- if you texture-from-pixmap in the binning vertex shader
(vertex coordinate generation), you'll miss out on synchronization.
Fixes flickering when multiple clients are running in parallel,
particularly GL apps and compositors.
v2: Fix a missing refcount on the CSD done fence for L2 cleaning.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190416225856.20264-6-eric@anholt.net
Acked-by: Rob Clark <robdclark@gmail.com>
The compute shader dispatch interface is pretty simple -- just pass in
the regs that userspace has passed us, with no CLs to run. However,
with no CL to run it means that we need to do manual cache flushing of
the L2 after the HW execution completes (for SSBO, atomic, and
image_load_store writes that are the output of compute shaders).
This doesn't yet expose the L2 cache's ability to have a region of the
address space not write back to memory (which could be used for
shared_var storage).
So far, the Mesa side has been tested on V3D v4.2 simpenrose (passing
the ES31 tests), and on the kernel side on 7278 (failing atomic
compswap tests in a way that doesn't reproduce on simpenrose).
v2: Fix excessive allocation for the clean_job (reported by Dan
Carpenter). Keep refs on jobs until clean_job is finished, to
avoid spurious MMU errors if the output BOs are freed by userspace
before L2 cleaning is finished.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190416225856.20264-4-eric@anholt.net
Acked-by: Rob Clark <robdclark@gmail.com>
The CL submission had two jobs embedded in an exec struct. When I
added TFU support, I had to replicate some of the exec stuff and some
of the job stuff. As I went to add CSD, it became clear that actually
what was in exec should just be in the two CL jobs, and it would let
us share a lot more code between the 4 queues.
v2: Fix missing error path in TFU ioctl's bo[] allocation.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190416225856.20264-3-eric@anholt.net
Acked-by: Rob Clark <robdclark@gmail.com>
The new shmem helpers from Noralf and Rob abstract out a bunch of our
BO creation and mapping code.
v2: Use the new sgt getter, and flag pages as dirty before freeing.
v3: Remove the mismatched put_pages.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190314163451.13431-1-eric@anholt.net
Reviewed-by: Rob Herring <robh@kernel.org> (v2)
No compatible string for it yet, just the version-dependent changes.
They've now tied the hub and the core interrupt lines into a single
interrupt line coming out of the block. It also turns out I made a
mistake in modeling the V3D v3.3 and v4.1 bridge as a part of V3D
itself -- the bridge is going away in favor of an external reset
controller in a larger HW module.
v2: Use consistent checks for whether we're on 4.2, and fix a leak in
an error path.
v3: Use more general means of determining if the current 4.2 changes
are in place, as apparently other platforms may switch back (noted
by Dave). Update the binding doc.
v4: Improve error handling for IRQ init.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308174336.7866-2-eric@anholt.net
Reviewed-by: Dave Emett <david.emett@broadcom.com>
The old field is gone and the register now has a different field,
QRMAXCNT for how many TMU requests get serviced before thread switch.
We were accidentally reducing it from its default of 0x3 (4 requests)
to 0x0 (1).
v2: Skip setting the reg at all on 4.x, instead of trying to update
only the old field.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20190220233658.986-2-eric@anholt.net
Reviewed-by: Dave Emett <david.emett@broadcom.com>
Now that the base struct drm_gem_object has a reservation_object, use it
and remove the private BO one.
Cc: Eric Anholt <eric@anholt.net>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Rob Herring <robh@kernel.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20190202154158.10443-5-robh@kernel.org
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
According to Dave, once you've started an L2T flush, all L2T accesses
will be blocked until the flush completes. This fixes a consistent
3-4ms stall between the ioctl and running the job, and 3DMMES Taiji
goes from 27fps to 110fps.
v2: Leave a note about why we don't need to wait for completion.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 57692c94dc ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Reviewed-by: Dave Emett <david.emett@broadcom.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181203222438.25417-4-eric@anholt.net
This is the write combiner for TMU writes. You're supposed to flush
that at job end if you had dirtied any cachelines. Flushing it at job
start then doesn't make any sense.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 57692c94dc ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Reviewed-by: Dave Emett <david.emett@broadcom.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181203222438.25417-3-eric@anholt.net
I missed one case during the recent revert of the replace_fence
interface change.
Fixes: 0b258ed1a2 drm: revert "expand replace_fence to support timeline point v2"
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/266134/
This reverts commit 9a09a42369.
The whole interface isn't thought through. Since this function can't
fail we actually can't allocate an object to store the sync point.
Sorry, I should have taken the lead on this from the very beginning and
reviewed it more thoughtfully. Going to propose a new interface as a
follow up change.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Link: https://patchwork.freedesktop.org/patch/265580/
The core scheduler tells us when the job is pushed to the scheduler's
queue, and I had the job_run functions saying when they actually queue
the job to the hardware. By adding tracepoints for the very top of
the ioctls and the IRQs signaling job completion, "perf record -a -e
v3d:.\* -e gpu_scheduler:.\* <job>; perf script" gets you a pretty
decent timeline.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20181201005759.28093-5-eric@anholt.net
Reviewed-by: Dave Emett <david.emett@broadcom.com>
The TFU can copy from raster, UIF, and SAND input images to UIF output
images, with optional mipmap generation. This will certainly be
useful for media EGL image input, but is also useful immediately for
mipmap generation without bogging the V3D core down.
For now we only run the queue 1 job deep, and don't have any hang
recovery (though I don't think we should need it, with TFU). Queuing
multiple jobs in the HW will require synchronizing the YUV coefficient
regs updates since they don't get FIFOed with the job.
v2: Change the ioctl to IOW instead of IOWR, always set COEF0, explain
why TFU is AUTH, clarify the syncing docs, drop the unused TFU
interrupt regs (you're expected to use the hub's), don't take
&bo->base for NULL bos.
v3: Fix a little whitespace alignment (noticed by checkpatch), rebase
on drm_sched_job_cleanup() changes.
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Dave Emett <david.emett@broadcom.com> (v2)
Link: https://patchwork.freedesktop.org/patch/264607/
The extra to_v3d_bo() calls came from copying this from the vc4
driver, which stored the cma gem object in the structs.
v2: Fix an unused var warning
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20181108161654.19888-4-eric@anholt.net
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com> (v1)
Let's support simultaneous submissions to multiple engines.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Link: https://patchwork.kernel.org/patch/10626149/
flags can be used by driver to decide whether need to block wait submission.
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
SIgned-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.kernel.org/patch/10641339/
Once we push the job, the scheduler could run it and free it. So, if
we want to reference their fences, we need to grab them before then.
I haven't seen this happen in many days of conformance test runtime,
but let's still close the race.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 57692c94dc ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Link: https://patchwork.freedesktop.org/patch/254119/
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
we can place a fence to a timeline point after expanded.
v2: change func parameter order
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/246543/
we can fetch timeline point fence after expanded.
v2: The parameter fence is the result of the function and should come last.
Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Link: https://patchwork.freedesktop.org/patch/246541/
entity has a scheduler field and we don't need the sched argument
in any of the functions where entity is provided.
Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Since our seqno value comes from a counter associated with the GPU
ring, not the entity (aka client), they'll be completed out of order.
There's actually no need for this code at all, since we don't have
enable_signaling() and thus DMA_FENCE_SIGNALED_BIT will be set before
we could be called.
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605190302.18279-2-eric@anholt.net
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Between creation and queueing of a job, you need to prevent any other
job from being created and queued. Otherwise the scheduler's fences
may be signaled out of seqno order.
v2: move mutex unlock to the error label.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 57692c94dc ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Link: https://patchwork.freedesktop.org/patch/msgid/20180606174851.12433-1-eric@anholt.net
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
This driver will be used to support Mesa on the Broadcom 7268 and 7278
platforms.
V3D 3.3 introduces an MMU, which means we no longer need CMA or vc4's
complicated CL/shader validation scheme. This massively changes the
GEM behavior, so I've forked off to a new driver.
v2: Mark SUBMIT_CL as needing DRM_AUTH. coccinelle fixes from kbuild
test robot. Drop personal git link from MAINTAINERS. Don't
double-map dma-buf imported BOs. Add kerneldoc about needing MMU
eviction. Drop prime vmap/unmap stubs. Delay mmap offset setup
to mmap time. Use drm_dev_init instead of _alloc. Use
ktime_get() for wait_bo timeouts. Drop drm_can_sleep() usage,
since we don't modeset. Switch page tables back to WC (debug
change to coherent had slipped in). Switch
drm_gem_object_unreference_unlocked() to
drm_gem_object_put_unlocked(). Simplify overflow mem handling by
not sharing overflow mem between jobs.
v3: no changes
v4: align submit_cl to 64 bits (review by airlied), check zero flags in
other ioctls.
Signed-off-by: Eric Anholt <eric@anholt.net>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> (v4)
Acked-by: Dave Airlie <airlied@linux.ie> (v3, requested submit_cl change)
Link: https://patchwork.freedesktop.org/patch/msgid/20180430181058.30181-3-eric@anholt.net
