This patch adds robust reset handling for user queues (userq) to improve
recovery from queue failures. The key components include:
1. Queue detection and reset logic:
- amdgpu_userq_detect_and_reset_queues() identifies failed queues
- Per-IP detect_and_reset callbacks for targeted recovery
- Falls back to full GPU reset when needed
2. Reset infrastructure:
- Adds userq_reset_work workqueue for async reset handling
- Implements pre/post reset handlers for queue state management
- Integrates with existing GPU reset framework
3. Error handling improvements:
- Enhanced state tracking with HUNG state
- Automatic reset triggering on critical failures
- VRAM loss handling during recovery
4. Integration points:
- Added to device init/reset paths
- Called during queue destroy, suspend, and isolation events
- Handles both individual queue and full GPU resets
The reset functionality works with both gfx/compute and sdma queues,
providing better resilience against queue failures while minimizing
disruption to unaffected queues.
v2: add detection and reset calls when preemption/unmaped fails.
add a per device userq counter for each user queue type.(Alex)
v3: make sure we hold the adev->userq_mutex when we call amdgpu_userq_detect_and_reset_queues. (Alex)
warn if the adev->userq_mutex is not held.
v4: make sure we have all of the uqm->userq_mutex held.
warn if the uqm->userq_mutex is not held.
v5: Use array for user queue type counters.(Alex)
all of the uqm->userq_mutex need to be held when calling detect and reset. (Alex)
v6: fix lock dep warning in amdgpu_userq_fence_dence_driver_process
v7: add the queue types in an array and use a loop in amdgpu_userq_detect_and_reset_queues (Lijo)
v8: remove atomic_set(&userq_mgr->userq_count[i], 0).
it should already be 0 since we kzalloc the structure (Alex)
v9: For consistency with kernel queues, We may want something like:
amdgpu_userq_is_reset_type_supported (Alex)
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
commit 978fa2f6d0 ("drm/amd/display: Use scaling for non-native
resolutions on eDP") started using the GPU scaler hardware to scale
when a non-native resolution was picked on eDP. This scaling was done
to fill the screen instead of maintain aspect ratio.
The idea was supposed to be that if a different scaling behavior is
preferred then the compositor would request it. The not following
aspect ratio behavior however isn't desirable, so adjust it to follow
aspect ratio and still try to fill screen.
Note: This will lead to black bars in some cases for non-native
resolutions. Compositors can request the previous behavior if desired.
Fixes: 978fa2f6d0 ("drm/amd/display: Use scaling for non-native resolutions on eDP")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4538
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Properly Check for return values from calls to debug functions in
runtime_disable().
v2: storing the last non zero returned value from the loop.
Signed-off-by: Sunday Clement <Sunday.Clement@amd.com>
Reviewed-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If device suspend has failed, add a recovery flow that will attempt
to unwind the suspend and get things back up and running.
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4627
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If any hardware IPs involved with the second phase of suspend fail, unwind
all steps to restore back to original state.
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If any hardware IPs involved with the first phase of suspend fail, unwind
all steps to restore back to original state.
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For S3 on vangogh, PMFW needs to be notified before the
driver powers down RLC. This already happens in smu_disable_dpms()
so drop the superfluous call in amdgpu_device_suspend().
Co-developed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The severity of CPER for BP threshold exceed event should be set as
FATAL to match the OOB implementation.
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Correct valid_bits and ms_chk_bits of section info field for bad page
threshold exceed CPER to match OOB's behavior.
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Commit e6a8a000cf ("drm/amd/display: Rename dml2 to dml2_0 folder")
renames the directory dml2 to dml2_0 in ./drivers/gpu/drm/amd/display/dc,
but misses to adjust the file entry in AMD DISPLAY CORE - DML.
Adjust the file entry after this directory renaming.
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The contents of si_dpm.h seem to have been copied from the
old radeon driver, including a lot of structs and fields which
were only relevant to GPU generations even older than SI.
A lot of these can be deleted without causing much churn to the
actual SI DPM code. Let's delete them to make the code easier
to understand.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fill and publish GPU metrics in v1.9 format for SMUv13.0.6 SOCs
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add helper macros to define metrics struct definitions. It will define
structs with field type followed by actual field. A helper macro is also
added to initialize the field encoding for all fields and to initialize
the field members to 0xFFs.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Use the correct label to complete all cleanup work.
Fixes: 4d154b1ca5 ("drm/amd/pm: Add support for DPM policies")
Fixes: 25e82f2e2c ("drm/amd/pm: Add temperature metrics sysfs entry")
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
v1:
the driver should handle return value of smu_v13_0_6_printk_clk_levels()
to return the correct size for sysfs reads.
v2:
fix the issue of size calculation error in smu_v13_0_6_print_clks()
Fixes: cdfdec6f16 ("drm/amd/pm: Avoid writing nulls into `pp_od_clk_voltage`")
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The IPID register value for bad page threshold CPER holds socket_id info
now according to the latest definition.
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Check if we have an amdgpu_dm_connector->dc_sink first before
adding common modes for analog outputs. If we don't have a
sink yet we can safely skip this.
Fixes: 70181ad96e ("drm/amd/display: Add common modes to analog displays without EDID")
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove amdgpu_asic_flush_hdp & amdgpu_asic_invalidate_hdp functions and
directly use the mapped ones
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Read CPER raw data from debugfs node "/sys/kernel/debug/dri/*/
amdgpu_ring_cper".
Signed-off-by: Xiang Liu <xiang.liu@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move everything to the supported resets masks rather than
having an explicit misc checks for this.
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Update asic_invalidate_hdp and asic_flush_hdp function to check if ip
function exist, if not return void
v2: Use else/if (Kevin)
Update function name (Lijo)
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remove the NULL check from amdgpu_hmm_range_free for hmm_pfns
as caller is responsible not to call amdgpu_hmm_range_free
more than once.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
These were not set so soft recovery was inadvertantly
disabled.
Fixes: 6ac55eab4f ("drm/amdgpu: move reset support type checks into the caller")
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
a. hmm_range is either NULL or a valid pointer so we
do not need to set range to NULL ever.
b. keep the hmm_range_free in the end irrespective of
the other conditions to avoid some additional checks
and also avoid double free issue.
Signed-off-by: Sunil Khatri <sunil.khatri@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
More xe3p support (Harish, Brian, Balasubramani, Matt Roper)
Make panic support work on VRAM for display (Maarten)
Fix stolen size check (Shuicheng)
xe_pci_test update (Gustavo)
VF migration updates (Tomasz)
A couple of fixes around allocation and PM references (Matt Brost)
Migration update for the MEM_COPY instruction (Matt Auld)
Initial CRI support (Balasubramani, Matt Roper)
Use SVM range helpers in PT layer (Matt Brost)
Drop MAX_GT_TYPE_CHARS constant (Matt Roper)
Fix spelling and typos (Sanjay)
Fix VF FLR synchronization between all GTs (Michal)
Add a Workaround (Nitin)
Access VF's register using dedicated MMIO view (Michal)
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRskUM7w1oG5rx2IZO4FpNVCsYGvwUCaQClhwAKCRC4FpNVCsYG
v88YAQC7cmRpHNEaTPTSBHAtVzMfEG+4b6JWjXAbuhQzd6MZgwD/SXOO2xSc66ks
JFHMzpAi/W1d3UVuj/QiN4PL3NTsjQA=
=L+1S
-----END PGP SIGNATURE-----
Merge tag 'drm-xe-next-2025-10-28' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next
Driver Changes:
More xe3p support (Harish, Brian, Balasubramani, Matt Roper)
Make panic support work on VRAM for display (Maarten)
Fix stolen size check (Shuicheng)
xe_pci_test update (Gustavo)
VF migration updates (Tomasz)
A couple of fixes around allocation and PM references (Matt Brost)
Migration update for the MEM_COPY instruction (Matt Auld)
Initial CRI support (Balasubramani, Matt Roper)
Use SVM range helpers in PT layer (Matt Brost)
Drop MAX_GT_TYPE_CHARS constant (Matt Roper)
Fix spelling and typos (Sanjay)
Fix VF FLR synchronization between all GTs (Michal)
Add a Workaround (Nitin)
Access VF's register using dedicated MMIO view (Michal)
Signed-off-by: Simona Vetter <simona.vetter@ffwll.ch>
From: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Link: https://patch.msgid.link/aQCl9uJxN6CWJ8Vg@fedora
pm_runtime_put_autosuspend(), pm_runtime_put_sync_autosuspend(),
pm_runtime_autosuspend() and pm_request_autosuspend() now include a call
to pm_runtime_mark_last_busy(). Remove the now-redundant explicit call to
pm_runtime_mark_last_busy().
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
pm_runtime_put_autosuspend(), pm_runtime_put_sync_autosuspend(),
pm_runtime_autosuspend() and pm_request_autosuspend() now include a call
to pm_runtime_mark_last_busy(). Remove the now-redundant explicit call to
pm_runtime_mark_last_busy().
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add gpu metrics definition which is only a set of gpu metrics
attributes. A field is encoded by its id, type and number of instances.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Now that DC supports analog connectors, there is nothing stopping
us from using it by default on Bonaire.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
VRR is not supported on analog signals.
Don't add freesync modes to analog displays or when
VRR is unsupported by DC.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When the EDID of an analog display is not available, we can't
know the possible modes supported by the display. However, we
still need to offer the user to select from a variety of common
modes. It will be up to the user to select the best one, though.
This is how it works on other operating systems as well as the
legacy display code path in amdgpu.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This feature is useful for analog connections without EDID:
- Really old monitors with a VGA connector
- Cheap DVI/VGA adapters that don't connect DDC pins
When a connection is established through DAC load detection,
the driver is supposed to fill in the supported modes for the
display, which we already do in amdgpu_dm_connector_get_modes.
Also, because the load detection causes visible glitches, do not
attempt to poll the connector again after it was detected this
way. Note that it will still be polled after sleep/resume or
when force is enabled, which is okay.
v2:
Add dc_connection_dac_load connection type.
Properly release sink when no display is connected.
Don't print error when EDID isn't read from an analog display.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
DAC_LoadDetection can be used to determine whether something
is connected to an analog connector by determining if there is
an analog load. This causes visible flickering on displays, so
we only resort to using this when the connected display doesn't
have an EDID.
For reference, see the legacy display code:
amdgpu_atombios_encoder_dac_load_detect
v2:
Only clear corresponding bit from BIOS_SCRATCH_0.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This will be reused by DAC load detection.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The BIOS uses this register to write the results of the
DAC_LoadDetection command, so we'll need to read this
in order to make DAC load detection work.
As a reference, I used the mmBIOS_SCRATCH_0 definition from
the amdgpu legacy display code.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
VGA connectors don't support any hotplug detection, so the kernel
needs to periodically poll them to see if a display is connected.
DVI-I connectors have hotplug detection for digital signals, and
some analog DVI cables pull up that pin to work with that.
However, in general not all DVI cables do this so we can't rely on
this feature, therefore we need to poll DVI-I connectors as well.
v2:
Call drm_kms_helper_poll_fini in amdgpu_dm_hpd_fini.
Disable/enable polling on suspend/resume.
Don't call full link detection when already connected.
v3:
Encounter CLANG build failure. Remove unused variable:
drivers/gpu/drm/amd/amdgpu/../display/amdgpu_dm/amdgpu_dm_irq.c:980:7:
error: variable 'use_polling' set but not used [-Werror,-Wunused-but-
set-variable]
980 | bool use_polling = false;
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Wayne Lin <wayne.lin@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Prepare for polling analog connectors.
Document the function better.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Analog displays typically have a DDC connection which can be
used by the GPU to read EDID. This commit adds the capability
to probe analog displays using DDC, reading the EDID header and
deciding whether the analog link is connected based on the data
that was read.
Note that VGA has no HPD (hotplug detection), so we need to
to do analog link detection for VGA before checking HPD.
In case of DVI-I, while the connector supports HPD, not all
analog cables connect the HPD pins, so we can't rely on HPD
either.
For reference, see the legacy display code:
amdgpu_connector_vga_detect
amdgpu_display_ddc_probe
DAC load detection will be implemented in a separate commit.
v2:
Fix crash / black screen on newer GPUs during link detection.
Ignore HPD pin for analog connectors.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The dce110_hwseq is used by all DCE hardware,
so add the DAC support here.
When enabling/disabling a stream for a RGB signal,
this will call the VBIOS to enable/disable the DAC.
Additionally, when applying the controller context,
call SelectCRTC_Source from VBIOS in order to
direct the CRTC output to the DAC.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We support two kinds of analog connections:
1. DVI-I, which allows both digital and analog signals:
The DC code base only allows 1 encoder per connector, and the
preferred engine type is still going to be digital. So, for DVI-I
to work, we need to make sure the pre-existing link encoder can
also work with analog signals.
1. VGA, which only supports analog signals:
For VGA, we need to create a link encoder that only works with the
DAC without perturbing any digital transmitter functionality.
Since dce110_link_encoder already supports analog DVI-I,
just reuse that code for VGA as well.
v2:
Reduce code churn by reusing same link encoder for VGA and DVI-I.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
