commit 35e4079bf1 upstream.
When a CL/CSD job times out, we check if the GPU has made any progress
since the last timeout. If so, instead of resetting the hardware, we skip
the reset and let the timer get rearmed. This gives long-running jobs a
chance to complete.
However, when `timedout_job()` is called, the job in question is removed
from the pending list, which means it won't be automatically freed through
`free_job()`. Consequently, when we skip the reset and keep the job
running, the job won't be freed when it finally completes.
This situation leads to a memory leak, as exposed in [1] and [2].
Similarly to commit 704d3d60fe ("drm/etnaviv: don't block scheduler when
GPU is still active"), this patch ensures the job is put back on the
pending list when extending the timeout.
Cc: stable@vger.kernel.org # 6.0
Reported-by: Daivik Bhatia <dtgs1208@gmail.com>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/12227 [1]
Closes: https://github.com/raspberrypi/linux/issues/6817 [2]
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://lore.kernel.org/r/20250430210643.57924-1-mcanal@igalia.com
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 80cbee810e upstream.
The V3D driver still relies on `drm_sched_increase_karma()` and
`drm_sched_resubmit_jobs()` for resubmissions when a timeout occurs.
The function `drm_sched_increase_karma()` marks the job as guilty, while
`drm_sched_resubmit_jobs()` sets an error (-ECANCELED) in the DMA fence of
that guilty job.
Because of this, we must check whether the job’s DMA fence has been
flagged with an error before executing the job. Otherwise, the same guilty
job may be resubmitted indefinitely, causing repeated GPU resets.
This patch adds a check for an error on the job's fence to prevent running
a guilty job that was previously flagged when the GPU timed out.
Note that the CPU and CACHE_CLEAN queues do not require this check, as
their jobs are executed synchronously once the DRM scheduler starts them.
Cc: stable@vger.kernel.org
Fixes: d223f98f02 ("drm/v3d: Add support for compute shader dispatch.")
Fixes: 1584f16ca9 ("drm/v3d: Add support for submitting jobs to the TFU.")
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250313-v3d-gpu-reset-fixes-v4-1-c1e780d8e096@igalia.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 21f1435b1e upstream.
If the active performance monitor (`v3d->active_perfmon`) is being
destroyed, stop it first. Currently, the active perfmon is not
stopped during destruction, leaving the `v3d->active_perfmon` pointer
stale. This can lead to undefined behavior and instability.
This patch ensures that the active perfmon is stopped before being
destroyed, aligning with the behavior introduced in commit
7d1fd3638e ("drm/v3d: Stop the active perfmon before being destroyed").
Cc: stable@vger.kernel.org # v5.15+
Fixes: 26a4dc29b7 ("drm/v3d: Expose performance counters to userspace")
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118221948.1758130-1-christian.gmeiner@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit e4b5ccd392 ]
After a job completes, the corresponding pointer in the device must
be set to NULL. Failing to do so triggers a warning when unloading
the driver, as it appears the job is still active. To prevent this,
assign the job pointer to NULL after completing the job, indicating
the job has finished.
Fixes: 14d1d19086 ("drm/v3d: Remove the bad signaled() implementation.")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250113154741.67520-1-mcanal@igalia.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c98b10496b ]
On the Raspberry Pi 5, performance counters are not being cleared
when `v3d_perfmon_start()` is called, even though we write to the
CLR register. As a result, their values accumulate until they
overflow.
The expected behavior is for performance counters to reset to zero
at the start of a job. When the job finishes and the perfmon is
stopped, the counters should accurately reflect the values for that
specific job.
To ensure this behavior, the performance counters are now enabled
before being cleared. This allows the CLR register to function as
intended, zeroing the counter values when the job begins.
Fixes: 26a4dc29b7 ("drm/v3d: Expose performance counters to userspace")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241204122831.17015-1-mcanal@igalia.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit cf1becb7f9 ]
We must first flush the MMU cache and then, flush the TLB, not the other
way around. Currently, we can see a race condition between the MMU cache
and the TLB when running multiple rendering processes at the same time.
This is evidenced by MMU errors triggered by the IRQ.
Fix the MMU flush order by flushing the MMU cache and then the TLB.
Also, in order to address the race condition, wait for the MMU cache flush
to finish before starting the TLB flush.
Fixes: 57692c94dc ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240923141348.2422499-2-mcanal@igalia.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
A proposed update to clang's -Wconstant-logical-operand to warn when the
left hand side is a constant shows the following instance in
nsecs_to_jiffies_timeout() when NSEC_PER_SEC is not a multiple of HZ,
such as CONFIG_HZ=300:
In file included from drivers/gpu/drm/v3d/v3d_debugfs.c:12:
drivers/gpu/drm/v3d/v3d_drv.h:343:24: warning: use of logical '&&' with constant operand [-Wconstant-logical-operand]
343 | if (NSEC_PER_SEC % HZ &&
| ~~~~~~~~~~~~~~~~~ ^
drivers/gpu/drm/v3d/v3d_drv.h:343:24: note: use '&' for a bitwise operation
343 | if (NSEC_PER_SEC % HZ &&
| ^~
| &
drivers/gpu/drm/v3d/v3d_drv.h:343:24: note: remove constant to silence this warning
1 warning generated.
Turn this into an explicit comparison against zero to make the
expression a boolean to make it clear this should be a logical check,
not a bitwise one.
Link: https://reviews.llvm.org/D142609
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Maíra Canal <mairacanal@riseup.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20230718-nsecs_to_jiffies_timeout-constant-logical-operand-v1-1-36ed8fc8faea@kernel.org
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is (mostly) ignored
and this typically results in resource leaks. To improve here there is a
quest to make the remove callback return void. In the first step of this
quest all drivers are converted to .remove_new() which already returns
void.
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230507162616.1368908-52-u.kleine-koenig@pengutronix.de
When v3d_lookup_bos fails to `allocate validated BO pointers`,
job->bo_count was already set to args->bo_count, but job->bo points to
NULL. In this scenario, we must verify that job->bo is not NULL before
iterating on it to proper clean up a job. Also, drm_gem_object_put
already checks that the object passed is not NULL, doing the job->bo[i]
checker redundant.
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Maíra Canal <mcanal@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221205135538.3545051-2-mwen@igalia.com
v3d_perfmon_open_file() instantiates a mutex for a particular file
instance, but it never destroys it by calling mutex_destroy() in
v3d_perfmon_close_file().
Similarly, v3d_perfmon_create_ioctl() instantiates a mutex for a
particular perfmon, but it never destroys it by calling mutex_destroy()
in v3d_perfmon_destroy_ioctl().
So, add the missing mutex_destroy on both cases.
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221108175425.39819-3-mcanal@igalia.com
Rename "GEM CMA" helpers to "GEM DMA" helpers - considering the
hierarchy of APIs (mm/cma -> dma -> gem dma) calling them "GEM
DMA" seems to be more applicable.
Besides that, commit e57924d4ae ("drm/doc: Task to rename CMA helpers")
requests to rename the CMA helpers and implies that people seem to be
confused about the naming.
In order to do this renaming the following script was used:
```
#!/bin/bash
DIRS="drivers/gpu include/drm Documentation/gpu"
REGEX_SYM_UPPER="[0-9A-Z_\-]"
REGEX_SYM_LOWER="[0-9a-z_\-]"
REGEX_GREP_UPPER="(${REGEX_SYM_UPPER}*)(GEM)_CMA_(${REGEX_SYM_UPPER}*)"
REGEX_GREP_LOWER="(${REGEX_SYM_LOWER}*)(gem)_cma_(${REGEX_SYM_LOWER}*)"
REGEX_SED_UPPER="s/${REGEX_GREP_UPPER}/\1\2_DMA_\3/g"
REGEX_SED_LOWER="s/${REGEX_GREP_LOWER}/\1\2_dma_\3/g"
# Find all upper case 'CMA' symbols and replace them with 'DMA'.
for ff in $(grep -REHl "${REGEX_GREP_UPPER}" $DIRS)
do
sed -i -E "$REGEX_SED_UPPER" $ff
done
# Find all lower case 'cma' symbols and replace them with 'dma'.
for ff in $(grep -REHl "${REGEX_GREP_LOWER}" $DIRS)
do
sed -i -E "$REGEX_SED_LOWER" $ff
done
# Replace all occurrences of 'CMA' / 'cma' in comments and
# documentation files with 'DMA' / 'dma'.
for ff in $(grep -RiHl " cma " $DIRS)
do
sed -i -E "s/ cma / dma /g" $ff
sed -i -E "s/ CMA / DMA /g" $ff
done
# Rename all 'cma_obj's to 'dma_obj'.
for ff in $(grep -RiHl "cma_obj" $DIRS)
do
sed -i -E "s/cma_obj/dma_obj/g" $ff
done
```
Only a few more manual modifications were needed, e.g. reverting the
following modifications in some DRM Kconfig files
- select CMA if HAVE_DMA_CONTIGUOUS
+ select DMA if HAVE_DMA_CONTIGUOUS
as well as manually picking the occurrences of 'CMA'/'cma' in comments and
documentation which relate to "GEM CMA", but not "FB CMA".
Also drivers/gpu/drm/Makefile was fixed up manually after renaming
drm_gem_cma_helper.c to drm_gem_dma_helper.c.
This patch is compile-time tested building a x86_64 kernel with
`make allyesconfig && make drivers/gpu/drm`.
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com> #drivers/gpu/drm/arm
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20220802000405.949236-4-dakr@redhat.com
idr_init_base(), implemented by commit 6ce711f275 ("idr: Make 1-based
IDRs more efficient"), let us set an arbitrary base other than
idr_init(), which uses base 0.
Since, for this IDR, no ID < 1 is ever requested/allocated, using
idr_init_base(&idr, 1) avoids unnecessary tree walks.
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Link: https://lore.kernel.org/r/20220701190227.284783-1-dakr@redhat.com
Instead of distingting between shared and exclusive fences specify
the fence usage while adding fences.
Rework all drivers to use this interface instead and deprecate the old one.
v2: some kerneldoc comments suggested by Daniel
v3: fix a missing case in radeon
v4: rebase on nouveau changes, fix lockdep and temporary disable warning
v5: more documentation updates
v6: separate internal dma_resv changes from this patch, avoids to
disable warning temporary, rebase on upstream changes
v7: fix missed case in lima driver, minimize changes to i915_gem_busy_ioctl
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220407085946.744568-3-christian.koenig@amd.com
linux/string_helpers.h provides a helper to return "yes"/"no" strings.
Replace the open coded versions with str_yes_no(). The places were
identified with the following semantic patch:
@@
expression b;
@@
- b ? "yes" : "no"
+ str_yes_no(b)
Then the includes were added, so we include-what-we-use, and parenthesis
adjusted in drivers/gpu/drm/v3d/v3d_debugfs.c. After the conversion we
still see the same binary sizes:
text data bss dec hex filename
51149 3295 212 54656 d580 virtio/virtio-gpu.ko.old
51149 3295 212 54656 d580 virtio/virtio-gpu.ko
1441491 60340 800 1502631 16eda7 radeon/radeon.ko.old
1441491 60340 800 1502631 16eda7 radeon/radeon.ko
6125369 328538 34000 6487907 62ff63 amd/amdgpu/amdgpu.ko.old
6125369 328538 34000 6487907 62ff63 amd/amdgpu/amdgpu.ko
411986 10490 6176 428652 68a6c drm.ko.old
411986 10490 6176 428652 68a6c drm.ko
98129 1636 264 100029 186bd dp/drm_dp_helper.ko.old
98129 1636 264 100029 186bd dp/drm_dp_helper.ko
1973432 109640 2352 2085424 1fd230 nouveau/nouveau.ko.old
1973432 109640 2352 2085424 1fd230 nouveau/nouveau.ko
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220126093951.1470898-10-lucas.demarchi@intel.com
GEM helper libraries use struct drm_driver.gem_create_object to let
drivers override GEM object allocation. On failure, the call returns
NULL.
Change the semantics to make the calls return a pointer-encoded error.
This aligns the callback with its callers. Fixes the ingenic driver,
which already returns an error pointer.
Also update the callers to handle the involved types more strictly.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Steven Price <steven.price@arm.com>
Acked-by: Maxime Ripard <maxime@cerno.tech>
Link: https://patchwork.freedesktop.org/patch/msgid/20211130095255.26710-1-tzimmermann@suse.de
Change all GEM SHMEM object functions that receive a GEM object
of type struct drm_gem_object to expect an object of type
struct drm_gem_shmem_object instead.
This change reduces the number of upcasts from struct drm_gem_object
by moving them into callers. The C compiler can now verify that the
GEM SHMEM functions are called with the correct type.
For consistency, the patch also renames drm_gem_shmem_free_object to
drm_gem_shmem_free. It further updates documentation for a number of
functions.
v3:
* fix docs for drm_gem_shmem_object_free()
v2:
* mention _object_ callbacks in docs (Daniel)
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20211108093149.7226-4-tzimmermann@suse.de
Using the generic extension from the previous patch, a specific multisync
extension enables more than one in/out binary syncobj per job submission.
Arrays of syncobjs are set in struct drm_v3d_multisync, that also cares
of determining the stage for sync (wait deps) according to the job
queue.
v2:
- subclass the generic extension struct (Daniel)
- simplify adding dependency conditions to make understandable (Iago)
v3:
- fix conditions to consider single or multiples in/out_syncs (Iago)
- remove irrelevant comment (Iago)
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ffd8b2e3dd2e0c686db441a0c0a4a0181ff85328.1633016479.git.mwen@igalia.com
Add support to attach generic extensions on job submission. This patch
is third prep work to enable multiple syncobjs on job submission. With
this work, when the job submission interface needs to be extended to
accommodate a new feature, we will use a generic extension struct where
an id determines the data type to be pointed. The first application is
to enable multiples in/out syncobj (next patch), but the base is
already done for future features. Therefore, to attach a new feature,
a specific extension struct should subclass drm_v3d_extension and
update the list of extensions in a job submission.
v2:
- remove redundant elements to subclass struct (Daniel)
v3:
- add comment for v3d_get_extensions
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ed53b1cd7e3125b76f18fe3fb995a04393639bc6.1633016479.git.mwen@igalia.com
Move job memory allocation to v3d_job_init function. This aim to facilitate
error handling in job initialization, since cleanup steps are similar for
all (struct v3d_job)-based types of job involved in a command submission.
To generalize v3d_job_init(), this change takes into account that all job
structs have the first element a struct v3d_job (bin, render, tfu, csd) or
it is a v3d_job itself (clean_job) for pointer casting.
v3:
- explicitly init job as NULL (Iago)
- fix pm failure handling on v3_job_init (Iago)
Suggested-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/4d12e07bd334d2cddb51cabd359e99edde595619.1633016479.git.mwen@igalia.com
In a cl submission, when bin job initialization fails, sched job resources
were already allocated for the render job. At this point,
drm_sched_job_init(render) was done in v3d_job_init but the render job is
aborted before drm_sched_job_arm (in v3d_job_push) happens; therefore, not
only v3d_job_put but also drm_sched_job_cleanup should be called (by
v3d_job_cleanup). A similar issue is addressed for csd and tfu submissions.
The issue was noticed from a review by Iago Toral in a patch that touches
the same part of the code.
Fixes: 916044fac8 ("drm/v3d: Move drm_sched_job_init to v3d_job_init")
Signed-off-by: Melissa Wen <mwen@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210916212726.2u2psq2egwy2mdva@mail.igalia.com
The hardware sets the TMUWCF bit back to 0 when the TMU write
combiner flush completes so we should be checking for that instead
of the L2TFLS bit.
v2 (Melissa Wen):
- Add Signed-off-by and Fixes tags.
- Change the error message for the timeout to be more clear.
Fixes spurious Vulkan CTS failures in:
dEQP-VK.binding_model.descriptorset_random.*
Fixes: d223f98f02 ("drm/v3d: Add support for compute shader dispatch.")
Signed-off-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210915100507.3945-1-itoral@igalia.com
