Otherwise next err_event_athub error cannot call gpu reset. And following
resume sequence will not be affected by this flag.
v2: create function to clear amdgpu_ras_in_intr for modularity of ras driver
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This athub fatal error can be recovered by baco without system-level reboot,
so add a mode to use baco for the recovery. Not affect the default psp reset
situations for now.
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Currently each XGMI node reset wq does not run in parrallel if bound to same
cpu. Make change to bound the xgmi_reset_work item to different cpus.
XGMI requires all nodes enter into baco within very close proximity before
any node exit baco. So schedule the xgmi_reset_work wq twice for enter/exit
baco respectively.
To use baco for XGMI, PMFW supported for baco on XGMI needs to be involved.
The case that PSP reset and baco reset coexist within an XGMI hive never exist
and is not in the consideration.
v2: define use_baco flag to simplify the code for xgmi baco sequence
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This operation is needed when baco entry/exit for ras recovery
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As will call unload kms when initialize fail, and the unload kms will
send event 3 and 4, so don't need event 3 and 4 in device init.
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Zhan Liu <zhan.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The documentation says the that PCI core handles this
for you unless you choose to implement it. Just rely
on the PCI core to handle the pci specific bits.
Reviewed-by: Zhan Liu <zhan.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Originally we only supported runtime pm on PX/HG laptops
so vga_switcheroo and runtime pm are sort of entangled.
Attempt to logically separate them.
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
BACO - Bus Active, Chip Off
Will be used for runtime pm. Entry will enter the BACO
state (chip off). Exit will exit the BACO state (chip on).
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
BACO - Bus Active, Chip Off
BOCO - Bus Off, Chip Off
To better match what we are checking for and to align with
amdgpu_device_supports_baco.
BOCO is used on PowerXpress/Hybrid Graphics systems and BACO
is used on desktop dGPU boards.
v2: fix typo in documentation
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
BACO - Bus Active, Chip Off
To check if a device supports BACO or not. This will be
used in determining when to enable runtime pm.
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is one regression from 042f3d7b745cd76aa
To put flush_delayed_work after adev->shutdown = true
which will make amdgpu_ih_process not response the irq
At last, all ib ring tests will be failed just like below
[drm] amdgpu: finishing device.
[drm] Fence fallback timer expired on ring gfx
[drm] Fence fallback timer expired on ring comp_1.0.0
[drm] Fence fallback timer expired on ring comp_1.1.0
[drm] Fence fallback timer expired on ring comp_1.2.0
[drm] Fence fallback timer expired on ring comp_1.3.0
[drm] Fence fallback timer expired on ring comp_1.0.1
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on comp_1.1.1 (-110).
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on comp_1.2.1 (-110).
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on comp_1.3.1 (-110).
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on sdma0 (-110).
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on sdma1 (-110).
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on uvd_enc_0.0 (-110).
amdgpu 0000:00:07.0: [drm:amdgpu_ib_ring_tests [amdgpu]] *ERROR* IB test failed on vce0 (-110).
[drm:amdgpu_device_delayed_init_work_handler [amdgpu]] *ERROR* ib ring test failed (-110).
v2: replace cancel_delayed_work_sync() with flush_delayed_work()
Signed-off-by: Yintian Tao <yttao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
By using JPEG IP block type
Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fixes gcc warning:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1954: warning: Function
parameter or member 'state' not described in 'amdgpu_device_set_cg_state'
Fixes: e3ecdffac9 ("drm/amdgpu: add documentation for amdgpu_device.c")
Signed-off-by: yu kuai <yukuai3@huawei.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Since dcn20 and dcn21 are under dcn1 it doesnt make sense to
have it named dcn1.
Change it to "dcn" to make it generic
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
DCN21 is stable enough to be build by default. So drop the flags.
[How]
Remove them using the unifdef tool. The following commands were executed
in sequence:
$ find -name '*.c' -exec unifdef -m -DCONFIG_DRM_AMD_DC_DCN2_1 -UCONFIG_TRIM_DRM_AMD_DC_DCN2_1 '{}' ';'
$ find -name '*.h' -exec unifdef -m -DCONFIG_DRM_AMD_DC_DCN2_1 -UCONFIG_TRIM_DRM_AMD_DC_DCN2_1 '{}' ';'
In addition:
* Remove from kconfig, and replace any dependencies with DCN1_0.
* Remove from any makefiles.
* Fix and cleanup Renoir definitions in dal_asic_id.h
* Expand DCN1 ifdef to include DCN21 code in the following files:
* clk_mgr/clk_mgr.c: dc_clk_mgr_create()
* core/dc_resources.c: dc_create_resource_pool()
* gpio/hw_factory.c: dal_hw_factory_init()
* gpio/hw_translate.c: dal_hw_translate_init()
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
[Why]
DCN2 and DSC are stable enough to be build by default. So drop the flags.
[How]
Remove them using the unifdef tool. The following commands were executed
in sequence:
$ find -name '*.c' -exec unifdef -m -DCONFIG_DRM_AMD_DC_DSC_SUPPORT -DCONFIG_DRM_AMD_DC_DCN2_0 -UCONFIG_TRIM_DRM_AMD_DC_DCN2_0 '{}' ';'
$ find -name '*.h' -exec unifdef -m -DCONFIG_DRM_AMD_DC_DSC_SUPPORT -DCONFIG_DRM_AMD_DC_DCN2_0 -UCONFIG_TRIM_DRM_AMD_DC_DCN2_0 '{}' ';'
In addition:
* Remove from kconfig, and replace any dependencies with DCN1_0.
* Remove from any makefiles.
* Fix and cleanup NV defninitions in dal_asic_id.h
* Expand DCN1 ifdef to include DCN2 code in the following files:
* clk_mgr/clk_mgr.c: dc_clk_mgr_create()
* core/dc_resources.c: dc_create_resource_pool()
* dce/dce_dmcu.c: dcn20_*lock_phy()
* dce/dce_dmcu.c: dcn20_funcs
* dce/dce_dmcu.c: dcn20_dmcu_create()
* gpio/hw_factory.c: dal_hw_factory_init()
* gpio/hw_translate.c: dal_hw_translate_init()
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
flush/cancel delayed works before doing finalization
to avoid concurrently requests.
Signed-off-by: Jesse Zhang <zhexi.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
P-state switch should be performed after all devices from the hive
get initialized.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Feifei Xu <Feifei.Xu@amd.com>
Reviewed-by: Jonathan Kim <Jonathan.Kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Otherwise, the feature enablement will be skipped due to wrong count.
Fixes: beff74bc6e ("drm/amdgpu: fix a race in GPU reset with IB test (v2)")
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Pstate settings should be performed after all device of the
XGMI setup get initialized.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
PSP lost connection when err_event_athub occurs. These cleanup work can be
skipped in BACO reset.
v2: squash in missing include (Alex)
Signed-off-by: Le Ma <le.ma@amd.com>
Reviewed-by: Hawking Zhang <hawking.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Correct the "_LENTH" mispelling in the AMDGPU_MAX_TIMEOUT_PARAM_LENGTH
constant.
Signed-off-by: Wambui Karuga <wambui.karugax@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For Arcturus the I2C traffic is done through SMU tables and so
we must postpone RAS recovery init to after they are ready
which is in amdgpu_device_ip_hw_init_phase2.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
add a generic helper function for accessing framebuffer via MMIO
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Tianci.Yin <tianci.yin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Move it into the caller. There are cases were we don't
want it. We need it for hibernation, but we don't need
it for runtime pm, so drop it for runtime pm.
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
for amdgpu_device_suspend. This follows the logic
in the resume path.
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When index is 1, need to set compute ring timeout for sriov and passthrough.
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It's only used in amdgpu_device.c and the naming also
reflects that. Move it there.
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Currently, every single piece of code in amdgpu that loops through
connectors does it incorrectly and doesn't use the proper list iteration
helpers, drm_connector_list_iter_begin() and
drm_connector_list_iter_end(). Yeesh.
So, do that.
Cc: Juston Li <juston.li@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Harry Wentland <hwentlan@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When compute fence did not signal, compute ring cannot detect hardware hang
because its timeout value is set to be infinite by default.
In SR-IOV and passthrough mode, if user does not declare custome timeout
value for compute ring, then use gfx ring timeout value as default. So
that when there is a ture hardware hang, compute ring can detect it.
Signed-off-by: Jesse Zhang <zhexi.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
except soc_bounding_box which is not integrated in discovery table yet
Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Set mp1 state properly for SW SMU suspend/reset routine.
Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
define sched_policy in case CONFIG_HSA_AMD is not
enabled, with this there is no need to check for CONFIG_HSA_AMD
else where in driver code.
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
If CONFIG_HSA_AMD is not set, build fails:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.o: In function `amdgpu_device_ip_early_init':
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1626: undefined reference to `sched_policy'
Use CONFIG_HSA_AMD to guard this.
Fixes: 1abb680ad371 ("drm/amdgpu: disable gfxoff while use no H/W scheduling policy")
Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
While gfxoff is enabled, the mmVM_XXX registers will be 0xfffffff while the GFX
is in "off" state. KFD queue creattion doesn't use ring based method, so it will
trigger a VM fault.
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
As more and more new asics start to reuse the old device IDs before
launch, there is a need to quickly override the existing asic type
corresponding to the reused device ID through a kernel parameter. With
this, engineers no longer need to rely on local hack patches,
facilitating cooperation across teams.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
ras recovery_init should be called after ttm init,
bad page reserve should be put in front of gpu reset since i2c
may be unstable during gpu reset.
add cleanup for recovery_init and recovery_fini
v2: add more comment and print.
remove cancel_work_sync in recovery_init.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This optimizes out the pci device id usage in KFD and makes the code
more maintainable.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In case of RAS error allow user configure auto system
reboot through ras_ctrl.
This is also part of the temproray work around for the RAS
hang problem.
v4: Use latest kernel API for disk sync.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Problem:
Under certain conditions, when some IP bocks take a RAS error,
we can get into a situation where a GPU reset is not possible
due to issues in RAS in SMU/PSP.
Temporary fix until proper solution in PSP/SMU is ready:
When uncorrectable error happens the DF will unconditionally
broadcast error event packets to all its clients/slave upon
receiving fatal error event and freeze all its outbound queues,
err_event_athub interrupt will be triggered.
In such case and we use this interrupt
to issue GPU reset. THe GPU reset code is modified for such case to avoid HW
reset, only stops schedulers, deatches all in progress and not yet scheduled
job's fences, set error code on them and signals.
Also reject any new incoming job submissions from user space.
All this is done to notify the applications of the problem.
v2:
Extract amdgpu_amdkfd_pre/post_reset from amdgpu_device_lock/unlock_adev
Move amdgpu_job_stop_all_jobs_on_sched to amdgpu_job.c
Remove print param from amdgpu_ras_query_error_count
v3:
Update based on prevoius bug fixing patch to properly call amdgpu_amdkfd_pre_reset
for other XGMI hive memebers.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Issue 1:
In XGMI case amdgpu_device_lock_adev for other devices in hive
was called to late, after access to their repsective schedulers.
So relocate the lock to the begining of accessing the other devs.
Issue 2:
Using amdgpu_device_ip_need_full_reset to switch the device list from
all devices in hive to the single 'master' device who owns this reset
call is wrong because when stopping schedulers we iterate all the devices
in hive but when restarting we will only reactivate the 'master' device.
Also, in case amdgpu_device_pre_asic_reset conlcudes that full reset IS
needed we then have to stop schedulers for all devices in hive and not
only the 'master' but with amdgpu_device_ip_need_full_reset we
already missed the opprotunity do to so. So just remove this logic and
always stop and start all schedulers for all devices in hive.
Also minor cleanup and print fix.
v4: Minor coding style fix.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This should be checked at all places job is accessed.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Enable DC support for renoir.
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Roman Li <Roman.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
for SOC15/vega10 the BACO reset & mode1 would introduce vram lost
in high end address range, current kmd's vram lost checking cannot
catch it since it only check very ahead visible frame buffer
v2:
cover NV as well
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Integrate the mode2 reset into rest sequence.
v2:
Check ppfuncs pointer for NULL
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch adds renoir support for gpu_info firmware and ip block setting.
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
atomic 64 bits REG operations are useless currently
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
what we really want is a read or write that is guaranteed to be 64 bits
at a time, atomic64 operations are supported on all architectures
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Le Ma