This was not strictly necessary, as page unpinning (ie. shrinker) only
cares about the resv. It did give us some extra sanity checking for
userspace controlled iova, and was useful to catch issues on kernel and
userspace side when enabling userspace iova. But if userspace screws
this up, it just corrupts it's own gpu buffers and/or gets iova faults.
So we can just let userspace shoot it's own foot and drop the extra per-
buffer SUBMIT overhead.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Patchwork: https://patchwork.freedesktop.org/patch/551023/
Split out pin_count incrementing and lru updating into a separate loop
so we can take the lru lock only once for all objs. Since we are still
holding the obj lock, it is safe to split this up.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/551025/
A fence id of zero is expected to be invalid, and is not removed from
the fence_idr table. If userspace is requesting to specify the fence
id with the FENCE_SN_IN flag, we need to reject a zero fence id value.
Fixes: 17154addc5 ("drm/msm: Add MSM_SUBMIT_FENCE_SN_IN")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/549180/
In an error path where the submit is free'd without the job being run,
the hw_fence pointer is simply a kzalloc'd block of memory. In this
case we should just kfree() it, rather than trying to decrement it's
reference count. Fortunately we can tell that this is the case by
checking for a zero refcount, since if the job was run, the submit would
be holding a reference to the hw_fence.
Fixes: f94e6a51e1 ("drm/msm: Pre-allocate hw_fence")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/547088/
Merge display-related changes targeting Qualcomm DRM MSM driver.
Notable changes:
DPU, DSI, MDSS:
- Support for SM8350, SM8450 SM8550 and SC8280XP platform
Core:
- Added bindings for SM8150 (driver support already present)
DPU:
- Partial support for DSC on SM8150 and SM8250
- Fixed color transformation matrix being lost on suspend/resume
DP:
- Support for DP on SDM845 and SC8280XP platforms
- HPD fixes
- Support for limiting DP link rate via DT property, this enables
support for HBR3 rates.
DSI:
- Validate display modes according to the DSI OPP table
- DSI PHY support for the SM6375 platform
- Fixed byte intf clock selection for 14nm PHYs
MDP5:
- Schema conversion to YAML
Misc fixes as usual
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
The workaround was initially necessary due to dma_resv having only a
single exclusive fence slot, yet whe don't necessarily know what order
the gpu scheduler will schedule jobs. Unfortunately this workaround
also has the result of forcing implicit sync, even when userspace does
not want it.
However, since commit 047a1b877e ("dma-buf & drm/amdgpu: remove
dma_resv workaround") the workaround is no longer needed. So remove
it. This effectively reverts commit f1b3f696a0 ("drm/msm: Don't
break exclusive fence ordering")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/509457/
Link: https://lore.kernel.org/r/20221101214051.159988-1-robdclark@gmail.com
The introduction of "drm/msm/gem: Evict active GEM objects when necessary"
exposes a problem with "drm/msm/gem: Unpin buffers earlier", in that we
need to keep the object pinned in the time the submit is queued up in the
gpu scheduler. Otherwise the shrinker will see it as a thing that can be
evicted if we wait for it to be signaled. But if the shrinker path is
waiting on it with the obj lock held, the job cannot be scheduled, as that
also requires briefly grabbing the obj lock, leading to deadlock. (Not to
mention, we don't want the shrinker to evict an obj queued up in gpu
scheduler.)
Fixes: f371bcc0c2 ("drm/msm/gem: Unpin buffers earlier")
Fixes: 025d27239a ("drm/msm/gem: Evict active GEM objects when necessary")
Closes: https://gitlab.freedesktop.org/drm/msm/-/issues/19
Signed-off-by: Rob Clark <robdclark@chromium.org>
Tested-by: Chia-I Wu <olvaffe@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/504528/
Link: https://lore.kernel.org/r/20220923224043.2449152-1-robdclark@gmail.com
Fixes for v5.19-rc5
- Fix to increment vsync_cnt before calling drm_crtc_handle_vblank so that
userspace sees the value *after* it is incremented if waiting for vblank
events
- Fix to reset drm_dev to NULL in dp_display_unbind to avoid a crash in
probe/bind error paths
- Fix to resolve the smatch error of de-referencing before NULL check in
dpu_encoder_phys_wb.c
- Fix error return to userspace if fence-id allocation fails in submit
ioctl
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvswNKdd02EYKYv5Zjv7f+mcqeWC7hHQ1SBjqYzN_ZHnA@mail.gmail.com
Fixes for v5.19-rc4
- Workaround for parade DSI bridge power sequencing
- Fix for multi-planar YUV format offsets
- Limiting WB modes to max sspp linewidth
- Fixing the supported rotations to add 180 back for IGT
- Fix to handle pm_runtime_get_sync() errors to avoid unclocked access
in the bind() path for dpu driver
- Fix the irq_free() without request issue which was a being hit frequently
in CI.
- Fix to add minimum ICC vote in the msm_mdss pm_resume path to address
bootup splats
- Fix to avoid dereferencing without checking in WB encoder
- Fix to avoid crash during suspend in DP driver by ensuring interrupt
mask bits are updated
- Remove unused code from dpu_encoder_virt_atomic_check()
- Fix to remove redundant init of dsc variable
- Fix to ensure mmap offset is initialized to avoid memory corruption
from unpin/evict
- Fix double runpm disable in probe-defer path
- VMA fenced-unpin fixes
- Fix for WB max-width
- Fix for rare dp resolution change issue
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvdsOF1-+WfTWyEyu33XPcvxOCU00G-dz7EF2J+fdyUHg@mail.gmail.com
Previously the BO_PINNED state in the submit was tracking two related
but different things: (1) that the buffer object was pinned, and (2)
that the vma (mapping within a set of pagetables) was pinned. But with
fenced vma unpin (needed so that userspace couldn't race with retire
path for releasing a vma) these two were decoupled. The fact that the
BO_PINNED flag was already cleared meant that we leaked the bo pin count
which should have been dropped when the submit was retired.
So split this state into BO_OBJ_PINNED and BO_VMA_PINNED, so they can be
dropped independently.
Fixes: 95d1deb02a ("drm/msm/gem: Add fenced vma unpin")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Patchwork: https://patchwork.freedesktop.org/patch/487559/
Link: https://lore.kernel.org/r/20220527172341.2151005-1-robdclark@gmail.com
- Fourcc modifier for tiled but not compressed layouts
- Support for userspace allocated IOVA (GPU virtual address)
- Devfreq clamp_to_idle fix
- DPU: DSC (Display Stream Compression) support
- DPU: inline rotation support on SC7280
- DPU: update DP timings to follow vendor recommendations
- DP, DPU: add support for wide bus (on newer chipsets)
- DP: eDP support
- Merge DPU1 and MDP5 MDSS driver, make dpu/mdp device the master
component
- MDSS: optionally reset the IP block at the bootup to drop
bootloader state
- Properly register and unregister internal bridges in the DRM framework
- Complete DPU IRQ cleanup
- DP: conversion to use drm_bridge and drm_bridge_connector
- eDP: drop old eDP parts again
- DPU: writeback support
- Misc small fixes
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvJCr_1D8d0dgmyQC5HD4gmXeZw=bFV_CNCfceZbpMxRw@mail.gmail.com
With userspace allocated iova (next patch), we can have a race condition
where userspace observes the fence completion and deletes the vma before
retire_submit() gets around to unpinning the vma. To handle this, add a
fenced unpin which drops the refcount but tracks the fence, and update
msm_gem_vma_inuse() to check any previously unsignaled fences.
v2: Fix inuse underflow (duplicate unpin)
v3: Fix msm_job_run() vs submit_cleanup() race condition
Signed-off-by: Rob Clark <robdclark@chromium.org>
Link: https://lore.kernel.org/r/20220411215849.297838-10-robdclark@gmail.com
Signed-off-by: Rob Clark <robdclark@chromium.org>
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
Add a way for userspace to specify the sequence number fence used to
track completion of the submit. As the seqno fence is simply an
incrementing counter which is local to the submitqueue, it is easy for
userspace to know the next value.
This is useful for native userspace drivers in a vm guest, as the guest
to host roundtrip can have high latency. Assigning the fence seqno in
the guest userspace allows the guest to continue without waiting for
response from the host.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Link: https://lore.kernel.org/r/20220224222321.60653-1-robdclark@gmail.com
The overflow check does causes a warning from clang-14 when 'sz' is a type
that is smaller than size_t:
drivers/gpu/drm/msm/msm_gem_submit.c:217:10: error: result of comparison of constant 18446744073709551615 with expression of type 'unsigned int' is always false [-Werror,-Wtautological-constant-out-of-range-compare]
if (sz == SIZE_MAX) {
Change the type accordingly.
Fixes: 20224d715a ("drm/msm/submit: Move copy_from_user ahead of locking bos")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Link: https://lore.kernel.org/r/20210927113632.3849987-1-arnd@kernel.org
Signed-off-by: Rob Clark <robdclark@chromium.org>
Some userspace apps make assumptions that rendering against multiple
contexts within the same process (from the same thread, with appropriate
MakeCurrent() calls) provides sufficient synchronization without any
external synchronization (ie. glFenceSync()/glWaitSync()). Since a
submitqueue maps to a gl/vk context, having multiple sched entities of
the same priority only works with implicit sync enabled.
To fix this, limit things to a single sched entity per priority level
per process.
An alternative would be sharing submitqueues between contexts in
userspace, but tracking of per-context faults (ie. GL_EXT_robustness)
is already done at the submitqueue level, so this is not an option.
Signed-off-by: Rob Clark <robdclark@chromium.org>
There's only one exclusive slot, and we must not break the ordering.
Adding a new exclusive fence drops all previous fences from the
dma_resv. To avoid violating the signalling order we err on the side of
over-synchronizing by waiting for the existing fences, even if
userspace asked us to ignore them.
A better fix would be to us a dma_fence_chain or _array like e.g.
amdgpu now uses, but
- msm has a synchronous dma_fence_wait for anything from another
context, so doesn't seem to care much,
- and it probably makes sense to lift this into dma-resv.c code as a
proper concept, so that drivers don't have to hack up their own
solution each on their own.
v2: Improve commit message per Lucas' suggestion.
Cc: Lucas Stach <l.stach@pengutronix.de>
Acked-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Sean Paul <sean@poorly.run>
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-17-daniel.vetter@ffwll.ch
An early pull for v5.15 (there'll be more coming in a week or two),
consisting of the drm/scheduler conversion and a couple other small
series that one was based one. Mostly sending this now because IIUC
danvet wanted it in drm-next so he could rebase on it. (Daniel, if
you disagree then speak up, and I'll instead include this in the main
pull request once that is ready.)
This also has a core patch to drop drm_gem_object_put_locked() now
that the last use of it is removed.
[airlied: add NULL to drm_sched_init]
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGumRk7H88bqV=H9Fb1SM0zPBo5B7NsCU3jFFKBYxf5k+Q@mail.gmail.com
