Add support for more per-process flags starting with option to configure
MFMA precision for gfx 9.5
v2: Change flag name to KFD_PROC_FLAG_MFMA_HIGH_PRECISION
Remove unused else condition
v3: Bump the KFD API version
v4: Missed SH_MEM_CONFIG__PRECISION_MODE__SHIFT define. Added it.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Define set_cache_memory_policy() for these asics and move all static
changes from update_qpd() which is called each time a queue is created
to set_cache_memory_policy() which is called once during process
initialization
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Set per-process static sh_mem config only once during process
initialization. Move all static changes from update_qpd() which is
called each time a queue is created to set_cache_memory_policy() which
is called once during process initialization.
set_cache_memory_policy() is currently defined only for cik and vi
family. So this commit only focuses on these two. A separate commit will
address other asics.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Amber Lin <Amber.Lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add error handling to propagate amdgpu_cgs_create_device() failures
to the caller. When amdgpu_cgs_create_device() fails, release hwmgr
and return -ENOMEM to prevent null pointer dereference.
[v1]->[v2]: Change error code from -EINVAL to -ENOMEM. Free hwmgr.
Signed-off-by: Wentao Liang <vulab@iscas.ac.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Starting from 6.11, AMDGPU driver, while being loaded with amdgpu.dc=1,
due to lack of .is_two_pixels_per_container function in dce60_tg_funcs,
causes a NULL pointer dereference on PCs with old GPUs, such as R9 280X.
So this fix adds missing .is_two_pixels_per_container to dce60_tg_funcs.
Reported-by: Rosen Penev <rosenp@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3942
Fixes: e6a901a008 ("drm/amd/display: use even ODM slice width for two pixels per container")
Signed-off-by: Aliaksei Urbanski <aliaksei.urbanski@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We advertise DCC as supported for NV12/P010 formats on GFX12,
but it would fail on this check on atomic commit.
Signed-off-by: David Rosca <david.rosca@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Encode socket id to CPER record id to be unique across devices.
v2: add pointer check for adev->smuio.funcs->get_socket_id
v2: set 0 if adev->smuio.funcs->get_socket_id is NULL
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>
For gfx_v9_4_3 specifically, before regGB_ADDR_CONFIG is overwritten
in gfx hw_init it is read out to popluate the gb_addr_config_fields
in the sw_init stage, which causes mismatch.
Fix it by using the golden value in sw_init as well.
v2: This is a driver-set golden reg and keep as it is (Lijo)
Signed-off-by: Shiwu Zhang <shiwu.zhang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For default policy, driver will issue an RMA event when the number of
bad pages is greater than 8 physical rows, rather than reaches 8
physical rows, don't rely on threshold configurable parameters in
default mode.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
While the entry get in svm_range_unmap_from_cpu is the last entry, and
the entry is page fault, it also need to be dropped. So for equal case,
it also need to be dropped.
v2:
Only modify the svm_range_restore_pages.
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Xiaogang Chen<xiaogang.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aldebaran SRIOV VF cannot access the power brake feature regs.
The accesses can be skipped to avoid a dmesg warning.
v2: Remove redundant asic type check
Signed-off-by: Victor Lu <victorchengchi.lu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Aldebaran SRIOV VF does not have write permissions to GRBM_CTNL.
This access can be skipped to avoid a dmesg warning.
v2: Use GC IP version check instead of asic check
Signed-off-by: Victor Lu <victorchengchi.lu@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Null pointer dereference issue could occur when pipe_ctx->plane_state
is null. The fix adds a check to ensure 'pipe_ctx->plane_state' is not
null before accessing. This prevents a null pointer dereference.
Found by code review.
Fixes: 3be5262e35 ("drm/amd/display: Rename more dc_surface stuff to plane_state")
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 63e6a77ccf)
Cc: stable@vger.kernel.org
To reset hung SDMA queues on GFX 9.4+ for the GFX9 family, a soft reset
must be issued through SMU. Since soft resets will reset an entire SDMA
engine, use a common KGD call to do the reset as the KGD will handle
avoiding a reset of in flight GFX and paging queues on that engine.
In addition, create a common call for all reset types to simplify
the handling of module parameter settings that block gpu resets.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add support for CPERs on VFs.
VFs do not receive PMFW messages directly; as such, they need to
query them from the host. To avoid hitting host event guard,
CPER queries need to be rate limited. CPER queries share the same
RAS telemetry buffer as error count query, so a mutex protecting
the shared buffer was added as well.
For readability, the amdgpu_detect_virtualization was refactored
into multiple individual functions.
Signed-off-by: Tony Yi <Tony.Yi@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm_* macros are more helpful that DRM_* macros since the former
indicates the associated DRM device that prints the error, which maybe
helpful when debugging.
Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Update amdgv_sriovmsg.h and mxgpu_nv.h to add new definitions for
CPER support on VFs. PMFW ACA messages are not available on VFs,
and VFs must query CPERs from host.
Signed-off-by: Tony Yi <Tony.Yi@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
After a full device reset, shared memory region will clear out and it's
not possible to reliably save the region in case of RAS errors.
Reinitialize the flags if required.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Through KFD IOCTL Fuzzing we encountered a NULL pointer derefrence
when calling kfd_queue_acquire_buffers.
Fixes: 629568d25f ("drm/amdkfd: Validate queue cwsr area and eop buffer size")
Signed-off-by: Andrew Martin <Andrew.Martin@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Andrew Martin <Andrew.Martin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
DCE6 was missing soft reset, but it was easily identifiable under radeon.
This should be it, pretty much as it is done under DCE8 and DCE10.
Signed-off-by: Alexandre Demers <alexandre.f.demers@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For vcn_v_5_0_1, set power state to gating during hw fini. Also there may
be scenario where VCN engine hangs during a job execution, then it's not
safe to assume that set_pg_state works fine during hw_fini to put the state
to gated. After a reset, we can assume that it's in the default state,
therefore reset the driver maintained state. Put the default state as gated
during reset as per this assumption.
Signed-off-by: Asad Kamal <asad.kamal@amd.com>
Suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
pqm_get_kernel_queue() has been unused since 2022's
commit 5bdd3eb253 ("drm/amdkfd: Remove unused old debugger
implementation")
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
print__rq_dlg_params_st() was added in 2017 by
commit 061bfa06a4 ("drm/amdgpu/display: Add dml support for DCN")
but has remained unused.
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
pre_surface_trace() has been unused since 2017's
commit 745cc746da ("drm/amd/display: remove
dc_pre_update_surfaces_to_stream from dc use")
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
With phm_powerdown_uvd() gone in the previous patch, there's
now no longer anything that reads the powerdown_uvd member of the
pp_hwmgr_func.
Remove it.
There are a few assignments to it; a boring NULL which can just go,
and two functions, but those functions are called explicitly anyway
so the assignments to the member go.
One of those (smu7_powerdown_uvd) wasn't static previously;
make it static.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
phm_powerdown_uvd() has been unused since 2017's
commit 47047263c5 ("drm/amd/powerplay: delete eventmgr related files.")
Remove it.
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
