[ Upstream commit 4a9d36b0610aa7034340e976652e5b43320dd7c5 ]
While passing the A530-specific lm_setup func to A530 and A540
to !A530 was fine back when only these two were supported, it
certainly is not a good idea to send A540 specifics to smaller
GPUs like A508 and friends.
Signed-off-by: Konrad Dybcio <konrad.dybcio@somainline.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 8f03c30cb814213e36032084a01f49a9e604a3e3 ]
The PC_DBG_ECO_CNTL register on the Adreno A5xx family gets
programmed to some different values on a per-model basis.
At least, this is what we intend to do here;
Unfortunately, though, this register is being overwritten with a
static magic number, right after applying the GPU-specific
configuration (including the GPU-specific quirks) and that is
effectively nullifying the efforts.
Let's remove the redundant and wrong write to the PC_DBG_ECO_CNTL
register in order to retain the wanted configuration for the
target GPU.
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@somainline.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5f98b33b04c02c0d9088c7486c59d058696782f9 ]
Now that we're not racing with GPU setup, also fix races of timestamps
against other timestamps. In freedreno CI, we were seeing this path trigger
timeouts on setting the GMU bit, producing:
[drm:_a6xx_gmu_set_oob] *ERROR* Timeout waiting for GMU OOB set GPU_SET: 0x0
and this triggered especially on the first set of tests right after
boot (it's probably easier to lose the race than one might think,
given that we start many tests in parallel, and waiting for NFS to
page in code probably means that lots of tests hit the same point of
screen init at the same time). As of this patch, the message seems to
have completely gone away.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 4b565ca5a2 ("drm/msm: Add A6XX device support")
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 7a7cbf2a819740674455ad36155c662367261296 ]
We were using the same force-poweron bit in the two codepaths, so they
could race to have one of them lose GPU power early.
freedreno CI was seeing intermittent errors like:
[drm:_a6xx_gmu_set_oob] *ERROR* Timeout waiting for GMU OOB set GPU_SET: 0x0
and this issue could have contributed to it.
Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 4b565ca5a2 ("drm/msm: Add A6XX device support")
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 7cc29fcdfcc8784e97c5151c848e193800ec79ac ]
nr_rings is reset to 1, but when this function is called for a second
(and third!) time nr_rings > 1 is false, thus the else case is entered
to set up a buffer for the RPTR shadow and consequently written to
RB_RPTR_ADDR, hanging platforms without WHERE_AM_I firmware support.
Restructure the condition in such a way that shadow buffer setup only
ever happens when has_whereami is true; otherwise preemption is only
finalized when the number of ring buffers has not been reset to 1 yet.
Fixes: 8907afb476 ("drm/msm: Allow a5xx to mark the RPTR shadow as privileged")
Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
Tested-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@somainline.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5771de5d5b3bfaf279e5c262a113d4b6fbe54355 ]
Similar to the previous patch, clear shadow on suspend to avoid timeouts
waiting for ringbuffer space.
Fixes: 8907afb476 ("drm/msm: Allow a5xx to mark the RPTR shadow as privileged")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e8b0b994c3a5881f0648d53f90435120089c56ad ]
Clear the shadow rptr on suspend. Otherwise, when we resume, we can
have a stale value until CP_WHERE_AM_I executes. If we suspend near
the ringbuffer wraparound point, this can lead to a chicken/egg
situation where we are waiting for ringbuffer space to write the
CP_WHERE_AM_I (or CP_INIT) packet, because we mistakenly believe that
the ringbuffer is full (due to stale rptr value in the shadow).
Fixes errors like:
[drm:adreno_wait_ring [msm]] *ERROR* timeout waiting for space in ringbuffer 0
in the resume path.
Fixes: d3a569fccf ("drm/msm: a6xx: Use WHERE_AM_I for eligible targets")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
* DSI support for sm8150/sm8250
* Support for per-process GPU pagetables (finally!) for a6xx.
There are still some iommu/arm-smmu changes required to
enable, without which it will fallback to the current single
pgtable state. The first part (ie. what doesn't depend on
drm side patches) is queued up for v5.10[1].
* DisplayPort support. Userspace DP compliance tool support
is already merged in IGT[2]
* The usual assortment of smaller fixes/cleanups
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvqjuzH=Po_9EzzFsp2Xq3tqJUTKfsA2g09XY7_+6Ypfw@mail.gmail.com
Commit 604234f336 ("drm/msm: Enable expanded apriv support for a650")
was checking the result of adreno_is_a650() before the gpu revision
got probed in adreno_gpu_init() so it was always coming across as
false. Snoop into the revision ID ahead of time to correctly set the
hw_apriv flag so that it can be used by msm_gpu to properly setup
global buffers.
Fixes: 604234f336 ("drm/msm: Enable expanded apriv support for a650")
Reported-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Tested-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Rob Clark <robdclark@chromium.org>
As newer GPU families are added it makes less sense to maintain a
"generic" version functions for older families. Move adreno_submit()
and get_rptr() into the target specific code for a2xx, a3xx and a4xx.
Add a parameter to adreno_flush to pass the target specific WPTR register
instead of relying on the generic register.
All of this gets rid of the last of the REG_ADRENO offsets so remove all
all the register definitions and infrastructure.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Support the WHERE_AM_I opcode for the A618, A630 and A640 GPUs if the
microcode supports it. The WHERE_AM_I opcode allows the RPTR shadow
to be updated in priviliged memory which protects the shadow from being
read or written from user submissions.
A650 already supports extended APRIV have built in hardware support for
to access privilged memory from the CP and can go back to using the
hardware RPTR shadow feature.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Newer microcode versions have support for the CP_WHERE_AM_I opcode which
allows the RPTR shadow memory to be marked as privileged to protect it
from corruption. Move the RPTR shadow into its own buffer and protect it
it if the current microcode version supports the new feature.
We can also re-enable preemption for those targets that support
CP_WHERE_AM_I. Start out by preemptively assuming that we can enable
preemption and disable it in a5xx_hw_init if the microcode version comes
back as too old.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Use the aperture settings from the IOMMU domain to set up the virtual
address range for the GPU. This allows us to transparently deal with
IOMMU side features (like split pagetables).
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Now that we can get the ctx from the submitqueue, the extra arg is
redundant.
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
[split out of previous patch to reduce churny noise]
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
It's allocating an array of a6xx_gpu_state_obj structure rathor than
its pointers.
This patch fix it.
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@gmail.com>
Signed-off-by: Rob Clark <robdclark@chromium.org>
The function iommu_domain_alloc returns NULL on platforms without IOMMU
such as msm8974. This resulted in PTR_ERR(-ENODEV) being assigned to
gpu->aspace so the correct code path wasn't taken.
Fixes: ccac7ce373 ("drm/msm: Refactor address space initialization")
Signed-off-by: Luca Weiss <luca@z3ntu.xyz>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Technically the GMU specific one is a bit redundant, but it was useful
to track down a bug.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
XX_print like pfp_print/me_print/meq_print/roq_print are just
used in file a5xx_debugfs.c. And these function always return
0, this return value is meaningless.
This change is to make the code a bit more readable.
Signed-off-by: Bernard Zhao <bernard@vivo.com>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
a650 supports expanded apriv support that allows us to map critical buffers
(ringbuffer and memstore) as as privileged to protect them from corruption.
Cc: stable@vger.kernel.org
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
The main a5xx preemption record can be marked as privileged to
protect it from user access but the counters storage needs to be
remain unprivileged. Split the buffers and mark the critical memory
as privileged.
Cc: stable@vger.kernel.org
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Pull drm fixes from Dave Airlie:
"As expected a bit of an rc3 uptick, amdgpu and msm are the main ones,
one msm patch was from the merge window, but had dependencies and we
dropped it until the other tree had landed. Otherwise it's a couple of
fixes for core, and etnaviv, and single i915, exynos, omap fixes.
I'm still tracking the Sandybridge gpu relocations issue, if we don't
see much movement I might just queue up the reverts. I'll talk to
Daniel next week once he's back from holidays.
core:
- Take modeset bkl for legacy drivers
dp_mst:
- Allow null crtc in dp_mst
i915:
- Fix command parser desc matching with masks
amdgpu:
- Misc display fixes
- Backlight fixes
- MPO fix for DCN1
- Fixes for Sienna Cichlid
- Fixes for Navy Flounder
- Vega SW CTF fixes
- SMU fix for Raven
- Fix a possible overflow in INFO ioctl
- Gfx10 clockgating fix
msm:
- opp/bw scaling patch followup
- frequency restoring fux
- vblank in atomic commit fix
- dpu modesetting fixes
- fencing fix
etnaviv:
- scheduler interaction fix
- gpu init regression fix
exynos:
- Just drop __iommu annotation to fix sparse warning
omap:
- locking state fix"
* tag 'drm-fixes-2020-08-28' of git://anongit.freedesktop.org/drm/drm: (41 commits)
drm/amd/display: Fix memleak in amdgpu_dm_mode_config_init
drm/amdgpu: disable runtime pm for navy_flounder
drm/amd/display: Retry AUX write when fail occurs
drm/amdgpu: Fix buffer overflow in INFO ioctl
drm/amd/powerplay: Fix hardmins not being sent to SMU for RV
drm/amdgpu: use MODE1 reset for navy_flounder by default
drm/amd/pm: correct the thermal alert temperature limit settings
drm/amdgpu: add asd fw check before loading asd
drm/amd/display: Keep current gain when ABM disable immediately
drm/amd/display: Fix passive dongle mistaken as active dongle in EDID emulation
drm/amd/display: Revert HDCP disable sequence change
drm/amd/display: Send DISPLAY_OFF after power down on boot
drm/amdgpu/gfx10: refine mgcg setting
drm/amd/pm: correct Vega20 swctf limit setting
drm/amd/pm: correct Vega12 swctf limit setting
drm/amd/pm: correct Vega10 swctf limit setting
drm/amd/pm: set VCN pg per instances
drm/amd/pm: enable run_btc callback for sienna_cichlid
drivers: gpu: amd: Initialize amdgpu_dm_backlight_caps object to 0 in amdgpu_dm_update_backlight_caps
drm/amd/display: Reject overlay plane configurations in multi-display scenarios
...
The patch reorganizing the set_freq function made it so the gmu resume
doesn't always set the frequency, because a6xx_gmu_set_freq() exits early
when the frequency hasn't been changed. Note this always happens when
resuming GMU after recovering from a hang.
Use a simple workaround to prevent this from happening.
Fixes: 1f60d11423 ("drm: msm: a6xx: send opp instead of a frequency")
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Rob Clark <robdclark@chromium.org>
For production devices, the debugbus sections will typically be fused
off and empty in the gpu device coredump. But since this may contain
data like cache contents, don't capture it by default.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
New Qualcomm firmware has changed a way it reports back the 'started'
event. Support new register values.
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
This patches replaces the previously used static DDR vote and uses
dev_pm_opp_set_bw() to scale GPU->DDR bandwidth along with scaling
GPU frequency. Also since the icc path voting is handled completely
in the opp driver, remove the icc_path handle and its usage in the
drm driver.
Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
Signed-off-by: Akhil P Oommen <akhilpo@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
We need to set it to the most recent completed fence, not the most
recent submitted. Otherwise we have races where we think we can retire
submits that the GPU is not finished with, if the GPU doesn't manage to
overwrite the seqno before we look at it.
This can show up with hang recovery if one of the submits after the
crashing submit also hangs after it is replayed.
Fixes: f97decac5f ("drm/msm: Support multiple ringbuffers")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Initialize hardware clock-gating registers on A640 and A650 GPUs.
At least for A650, this solves some performance issues.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Rob Clark <robdclark@chromium.org>
This will allow supporting different hwcg tables for a6xx.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Rob Clark <robdclark@chromium.org>
This is required for A640 and A650 to be able to share UBWC-compressed
images with other HW such as display, which expect this configuration.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Small cleanup, lets not open-code bits/bitfields that are properly
defined in the rnndb xml (and therefore have builders in the generated
headers)
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
This sets up bw tables for A640/A650 similar to A618/A630, 0 DDR bandwidth
vote, and the CNOC vote. A640 has the same CNOC addresses as A630 and was
working, but this is required for A650 to work.
Eventually the bw table should be filled by querying the interconnect
driver for each BW in the dts, but use these dummy tables for now.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
A650 has a separate RSCC region, so dump RSCC registers separately, reading
them from the RSCC base. Without this change a GPU hang will cause a system
reset if CONFIG_DEV_COREDUMP is enabled.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
On targets where GMU is available, GMU takes over the ownership of GX GDSC
during its initialization. So, move the refcount-get on GX PD before we
initialize the GMU. This ensures that nobody can collapse the GX GDSC
once GMU owns the GX GDSC. This patch fixes some GMU OOB errors seen
during GPU wake up during a system resume.
Reported-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Akhil P Oommen <akhilpo@codeaurora.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
This patch changes the plumbing to send the devfreq recommended opp rather
than the frequency. Also consolidate and rearrange the code in a6xx to set
the GPU frequency and the icc vote in preparation for the upcoming
changes for GPU->DDR scaling votes.
Signed-off-by: Sharat Masetty <smasetty@codeaurora.org>
Signed-off-by: Akhil P Oommen <akhilpo@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
If there is no interconnect-names, but there is an interconnects
property, then of_icc_get(dev, "gfx-mem"); would return an error
rather than NULL.
Also, if there is no interconnect-names property, there will never
be a ocmem path. But of_icc_get(dev, "ocmem") would return -EINVAL
instead of -ENODATA. Just don't bother trying in this case.
v2: explicity check for interconnect-names property
Fixes: 08af4769c7 ("drm/msm: handle for EPROBE_DEFER for of_icc_get")
Fixes: 00bb9243d3 ("drm/msm/gpu: add support for ocmem interconnect path")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@chromium.org>
Check for errors instead of silently not using icc if the msm driver
probes before the interconnect driver.
Allow ENODATA for ocmem path, as it is optional and this error
is returned when "gfx-mem" path is provided but not "ocmem".
Because msm_gpu_cleanup assumes msm_gpu_init has been called, the icc path
init needs to be after msm_gpu_init for the error path to work.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Rob Clark <robdclark@chromium.org>
adreno_gpu_init calls pm_runtime_enable, so adreno_gpu_cleanup needs to
call pm_runtime_disable.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Signed-off-by: Rob Clark <robdclark@chromium.org>
