[Why]
Currently only a singular de-rate is used for all DPM levels.
The intent was to limit the bandwidth utilization at high DPMs
so the display requirements are not competing with other engines for bandwidth.
At lower DPMs, the de-rates could be more lenient so more bandwidth can be
utilized without the need to increase the DPM level and result in potential power savings.
i.e. DPM0 could be achieved on certain display configs instead of DPM1
if de-rates were a couple percentage points higher
The system average de-rates can be adjusted as needed as only urgent de-rates are defined for the SOC.
[How]
Update QOS parameters to have a table of derates with a per-DPM granularity
If the per-DPM value is provided, that will value be used.
Otherwise use the global value if there is no DPM specific value.
Reviewed-by: Jun Lei <jun.lei@amd.com>
Signed-off-by: Austin Zheng <Austin.Zheng@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In __set_dm_plane_colorop_shaper and __set_dm_plane_colorop_blend the
single colorop_state variable was reused sequentially: first to capture
the TF state, then (after mutating the colorop pointer) to capture the
LUT state.
Split into separate tf_state / lut_state pointers and introduce a
dedicated lut_colorop local. Resolve both pointers upfront before any
computation begins. This separates the concern of "find the states" from
"use the states" and makes the code easier to follow.
No functional change.
Assisted-by: Copilot:claude-opus-4.8
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
DRM core builds the curve_1d_type enum property with only the supported
TF values, so any curve_1d_type that reaches atomic_commit is already
guaranteed to be in the supported set. The per-colorop type field is
immutable — it cannot change between the loop that finds colorop_state
and the if block that uses it, so re-checking colorop->type there is
dead code.
Remove the redundant checks:
- colorop->type == DRM_COLOROP_1D_CURVE in the shaper TF if block
- colorop->type == DRM_COLOROP_1D_LUT in the shaper LUT if block
- colorop->type == DRM_COLOROP_1D_CURVE in the blend TF if block
- colorop->type == DRM_COLOROP_1D_LUT in the blend LUT if block
- BIT(colorop_state->curve_1d_type) & supported_blnd_tfs in the blend
TF if block (already guaranteed by the loop filter)
- BIT(colorop_state->curve_1d_type) & supported_blnd_tfs in the blend
LUT if block (nonsensical: a 1D_LUT colorop has no curve_1d_type)
No functional change.
Assisted-by: Copilot:claude-opus-4.8
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
Some resources that exist in the DCN block are not needed and shouldn't
be used.
[how]
Remove defines from register lists.
Reviewed-by: Ovidiu (Ovi) Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Matthew Stewart <Matthew.Stewart2@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
snprintf() and vsnprintf() return the number of bytes that would have
been written if the buffer were large enough, not the actual bytes
written. If truncation occurs, the accumulated length can exceed the
buffer size, causing kfifo_in() to read past the fifo_in[] stack buffer.
Switch to scnprintf() and vscnprintf() which return the actual number
of bytes written, excluding the null terminator. This prevents the
potential buffer over-read when calculating the offset for subsequent
writes.
Signed-off-by: William Palacek <William.Palacek@amd.com>
Reviewed-by: Alysa Liu <Alysa.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
DCN42 reuses dccg42_init, which causes problems due to undefined masks.
[how]
- Read res_pool to determine the quantities of the respective resources
- Remove the physymclk root_clock_optimization check, as it seems like
it shouldn't do anything (defaults to disabled already).
Reviewed-by: Ovidiu (Ovi) Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Matthew Stewart <Matthew.Stewart2@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
The register lists used on DCN42 variants are different. Some reused
codepaths are trying to access registers not used.
[how]
Add DISPCLK_FREQ_CHANGECNTL, HUBPREQ_DEBUG, and HDMISTREAMCLK_CNTL to
the register lists.
Reviewed-by: Ovidiu (Ovi) Bunea <ovidiu.bunea@amd.com>
Signed-off-by: Matthew Stewart <Matthew.Stewart2@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why & How]
'skip_frl_pretraining' was introduced and enabled along w/ HDMI 2.1
initial upstream, but is causing HDMI validation link training to be s
kipped on short hotplugs and compliance issues.
Remove this behaviour to force link training on all hotplugs for all
ASICs.
Reviewed-by: Relja (Reggie) Vojvodic <relja.vojvodic@amd.com>
Reviewed-by: Sun peng (Leo) Li <sunpeng.li@amd.com>
Signed-off-by: Ivan Lipski <ivan.lipski@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[WHY]
12bpc color ramp pattern was never implemented.
[HOW]
Add correct DPG_RAMP_CONTROL programming to match DP color ramp spec.
Reviewed-by: George Shen <george.shen@amd.com>
Signed-off-by: Michael Strauss <michael.strauss@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Reduces file fragmentation in the power module by consolidating
power_helpers.c . The helper file contained minimal
functionality (single utility function and shared includes) that
didn't warrant a separate compilation unit, leading to increased
build complexity and maintenance overhead.
[How]
Consolidated power_helpers.c content into the internal module
implementation. Moved macro outside
platform-specific conditional block for wider availability.
Reviewed-by: Josip Pavic <josip.pavic@amd.com>
Signed-off-by: Lohita Mudimela <lohita.mudimela@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
It is required by Security Guidance for All Software Components.
[How]
Change variable type to unsigned in dc\dml\dcn314\display_mode_vba_31.c
and dc\dml\dcn31\display_mode_vba_314.c.
Explicit cast to unsigned in dc\link\protocols\link_hdmi_frl.c.
Move warning from UNSOLVED set to SOLVED set.
Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Piotr Maziarz <piotr.maziarz@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
Enable PSR and Panel Replay on a DCN4 variant for display power
savings. On links without native I2C (no DDC pin), the AUX channel
must use aux_hw_inst to avoid NULL pointer access during PSR and
Replay setup.
[How]
Enable PSR and Replay in the DCN4 variant panel config defaults.
Add no_ddc_pin check in dp_setup_panel_replay(),
edp_setup_freesync_replay(), and fsft_send_msg_to_fw() to use
link->aux_hw_inst when dp_connector_no_native_i2c and no_ddc_pin
are set.
Reviewed-by: Matthew Stewart <matthew.stewart2@amd.com>
Signed-off-by: Gabe Teeger <gabe.teeger@amd.com>
Signed-off-by: George Zhang <george.zhang@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[why]
DCN42B was not using its own max_ip_caps table. Need to create a
separate soc_and_ip_translator in order to not reuse the DCN42 one.
[how]
Separate DCN42B into its own soc_and_ip_translator.c file to handle this.
Reviewed-by: Dillon Varone <dillon.varone@amd.com>
Signed-off-by: Matthew Stewart <Matthew.Stewart2@amd.com>
Tested-by: Dan Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Split amdgpu_gfx_mes_reset_queue_start() into reset+unmap now and queue
reinit later, and do the remap only after amdgpu_mes_resume(). Avoids
re-adding legacy queues while MES gangs are still suspended.
Suggested-by: Shaoyun Liu <shaoyun.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Call the new userq reset helper, and dispatch KQs first by ring_id
before falling back to the user-queue lookup.
v2: squash in fixes
Co-developed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
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>
If we get an interrupt for a bad user queue (bad opcode, etc.), add
a helper to handle the reset for user queues.
v2: squash in fixes
v3:
- schedule the reset via amdgpu_userq_start_hang_detect_work() instead
of open-coding mod_delayed_work()
- drop the per-queue guilty flag; always reset the queue the hang
detect work belongs to, matching the non-compute reset path
Co-developed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
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>
Pass flush_mes_queue=true in reset_queue_mes() to match the GFX
post-reset drop semantics.
Suggested-by: Shaoyun Liu <shaoyun.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Set remove_queue_after_reset=1 (MES >= 0x5a) so MES drops its internal
state instead of re-unmapping an already MMIO-reset queue, which can
timeout into a GPU reset.
Suggested-by: Shaoyun Liu <shaoyun.liu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
To avoid wraparound if the value is 0.
Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix a security vulnerability where malicious VCE command streams
with oversized dimensions (e.g. 65536×65536) cause 32-bit integer
overflow, wrapping the calculated buffer size to 0. This bypasses
validation and allows GPU firmware to perform out-of-bound memory
access.
The fix uses 64-bit arithmetic to detect overflow and rejects
invalid dimensions before they reach the hardware.
V2: remove redundant check
V3: modify max height value
V4: remove size64
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reuse the parameter length returned by
vcn_v4_0_enc_find_ib_param() instead of rereading it from
the IB.
This avoids a potential TOCTOU issue if the IB contents
change between reads.
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: David Rosca <david.rosca@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When width or height is less than 16, width_in_mb or height_in_mb
becomes 0, leading to fs_in_mb being 0. This causes a division by
zero when calculating num_dpb_buffer in H264 and H264 Perf decode
paths.
Add validation to reject frames with width < 16 or height < 16
before performing any calculations that depend on these values.
V2: Format change - move up all vaiable definitions.
V3: Use warn_once to avoid spam.
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
These adapters typically are only supported by Barco on the
Windows platform. However, with these changes in the linux
driver, multiple monitor support should work correctly.
Signed-off-by: Matthew Jacob <mjacob@feralsw.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
PTL is a special feature for gfxv9.4.4, but the warning is
always appearing on other ASICs when rocprof is running, it
causes confusion, so move hw_supported check earlier to
avoid it.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
struct kfd_signal_page now only wraps a single uint64_t *kernel_address
pointer. Drop the wrapper struct (and the page_slots() helper) and store
the signal page pointer directly in kfd_process::signal_page.
Since the signal page is the GTT BO mapping provided by user mode and is
not owned by the events code, no separate allocation/free is needed for
it, so shutdown_signal_page() goes away as well.
No functional change intended.
Signed-off-by: Yongqiang Sun <Yongqiang.Sun@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
atom_index_iio() parsed the IIO bytecode without bounds checks, allowing
out-of-bounds reads on a malformed VBIOS. Pass the BIOS size into
amdgpu_atom_parse() and bound the parse loops by it.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Assisted-by: Claude Code
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Internal US/DS switch may not be exposed in passthrough. Guard the
upstream port reads to avoid a NULL dereference.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When BT.2020 colorimetry is selected, the driver sends information using
VSC SDP but does not set "ignore MSA colorimetry" bit on older GPUs with
DCE-based IPs. This causes certain sinks to prefer colorimetry
information in DP MSA, resulting in terrible color rendering ("dull"
colors) when HDR is enabled.
This commit wires up the MISC1 bit 6 for GPUs with DCE 11.x based IPs to
correctly configure sinks to ignore colorimetry information in MSA,
resolving the color rendering issue.
Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/4849
Assisted-by: oh-my-pi:GPT-5.5
Signed-off-by: Leorize <leorize+oss@disroot.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Enable IP block soft reset as a GPU recovery method for GFX8
graphics and compute rings.
Tested with the "hard_reset_cp_wait" test case from the
Hang Test Suite created by Natalie Vock and Konstantin Seurer.
This Vulkan testcase waits for an event that never occurs,
effectively a WAIT_REG_MEM packet that intentionally hangs.
IP block soft reset can resolve that hang and allow
the rest of the system to move on and keep functioning
without needing a full ASIC reset.
Tested on the following chips:
Polaris 10 (Radeon RX 570)
Polaris 11 (Radeon RX 560)
Polaris 12 (Radeon RX 550)
Fiji (Radeon R9 Nano)
Tonga (Radeon R9 380X)
Carrizo (A8-9600)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Always reset everything in the GFX block at once as opposed
to trying to figure out which blocks need to be reset based
on their busy flags. This makes the reset more robust and
predictable.
Increase delays when waiting for the GRBM and SRBM soft reset
to complete.
Call IP block suspend/resume to ensure correct operation now
that we no longer have pre/post_soft_reset().
Call clock/powergating functions, otherwise power consumption
will increase after the GFX IP block is soft reset.
Return correct error code to signal failure in case not all
rings are functional after the IP block is soft reset.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When the compute queue is unavailable to run the IB,
return -EBUSY instead of silently failing.
Make sure the IB is always executed during reset:
Set preempt condition (may be cleared during reset),
and flush HDP cache so the GPU sees the updated value.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It is useful to minimize collateral damage during an IP block
soft reset. We can clear the COND_EXEC condition so that
only the currently executing submission is at risk.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The gfx_v8_0_cp_test_all_rings() function should return success
only when all ring tests were successful.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The only case when they may not go idle is when we are dealing
with a GPU hang, in which case we should just forcibly disable
these even when they aren't idle.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Implement IP block soft reset as a recovery method that fits into
the current GPU recovery code as opposed to being hacked into the
full GPU reset code path.
This can gracefully handle GPU hangs when other reset methods
are not available or have failed. It makes sure to minimize
collateral damage (ie. affected non-guilty jobs) and does a
backup and restore on all affected queues.
Note that some of the new helpers may be useful for other
reset types as well, which we can explore later.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
These functions were largely redundant with the respective
suspend() and resume() functions, the main difference being
that they were less used and therefore less likely to be
tested and correct.
Move anything relevant from pre/post_soft_reset()
that is not already done by suspend()/resume()
into the soft_reset() functions.
Note that future uses of soft_reset() will need to call
the suspend() / resume() functions and the necessary clock
and power gating functions.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
amdgpu_pm_info displayed power sensor readings with the wrong fractional unit.
It treated the low byte of the raw sensor value as the decimal part of watts,
while that field represents milliwatts in the decoded value. As a result,
debugfs could report misleading SoC power when the remainder was not already
a two-digit centiwatt value.
Example with query = 0x00000354:
raw field value
---------------------
query >> 8 3 W
query & 0xff 84 mW
decoded power 3084 mW
output value
---------------------
before 3.84 W
after 3.08 W
Fixes: f0b8f65b48 ("drm/amd/amdgpu: fix the GPU power print error in pm info")
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SCPM owns power feature control when enabled.
Make pp_features read-only during sysfs setup by clearing its write bits
and store callback.
Signed-off-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Asad Kamal <asad.kamal@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There's no need to crash the kernel for these cases.
Reviewed-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
