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>
This should be cleared during every nbif uncorrectable error cleanup work.
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>
To fix issue that ras controller interrupt cannot be triggered anymore after
one time nbif uncorrectable error. And error count is stored in nbif ras object
for query.
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>
Change it to external interface.
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>
v2: add notification when ras controller interrupt generates
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>
The same workaround is used for gfx7.
Both PAL and Mesa use it for gfx8 too, so port this commit to
gfx_v8_0_ring_emit_fence_gfx.
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SPI limits total CS waves in flight per SE to no more than 32 * num_cu and
we need to stuff 40 waves on a CU to completely clean the SGPR. This is
accomplished in the WR by cleaning the SE in two steps, half of the CU per
step.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When security violation from new vbios happens, data fabric is
risky to stop working. So prevent the direct access to DF
mmFabricConfigAccessControl from the new vbios and onwards.
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Adjust the exposed function prototype so that the caller does not need
to know the MMHUB number.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Platform TAs will independently toggle DF Cstate.
for instance, get/set topology from xgmi ta. do error
injection from ras ta. In such case, PMFW needs to be
loaded before TAs so that all the subsequent Cstate
calls recieved by PSP FW can be routed to PMFW.
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
issue unload_ta_cmd to tOS to unload asd driver
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
asd shared memory is not needed since drivers doesn't
invoke any further cmd to asd directly after the asd
loading. trust application is the one who needs
to talk to asd after the initialization
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Evan Quan <evan.quan@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>
Added max hive/node info checks per supported ASIC
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
load the ta firmware for navi10/12/14.
This is already being done for raven/picasso and
is needed for supporting hdcp on navi
Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
still need to init csb even for SRIOV
v2:
drop init_pg() for gfx10 at all since
PG and GFX off feature will be fully controled
by RLC and SMU fw for gfx10
v3:
drop the flush_gpu_tlb lines since we consider
it is only usefull in emulation
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
To align with the scheme from gfx9
disabling GFX ring after VM shutdown could avoid
garbage data be fetched to GFX RB which may lead
to unnecessary screw up on GFX
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
since we don't have RLCG ucode loading and no SRlist as well
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
issue:
kernel would report a warning from a double unpin
during the driver unloading on the CSB bo
why:
we unpin it during hw_fini, and there will be another
unpin in sw_fini on CSB bo.
fix:
actually we don't need to pin/unpin it during
hw_init/fini since it is created with kernel pinned,
we only need to fullfill the CSB again during hw_init
to prevent CSB/VRAM lost after S3
v2:
get_csb in init_rlc so hw_init() will make CSIB content
back even after reset or s3
v3:
use bo_create_kernel instead of bo_create_reserved for CSB
otherwise the bo_free_kernel() on CSB is not aligned and
would lead to its internal reserve pending there forever
take care of gfx7/8 as well
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
otherwse the flush_gpu_tlb will hang if we unload the
KMD becuase the schedulers already stopped
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
For Arcturus, increase dispatch packet number to stress scheduler.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Clear SDMA and HDP EDC counter in GPR workarounds.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
srbm_mutex is to guarantee atomicity for r/w of gfx indexed registers
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>
Originally the last WREG32_SOC15() was a part of the if statement block
but the curly braces are on the wrong line.
Fixes: bb0db70f3f ("drm/amdgpu: separate JPEG1.0 code out from VCN1.0")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
VI/CIK BACO was inflight when this fix landed for SOC15/NV.
Add the fix to VI/CIK as well.
Acked-by: Evan Quan <evan.quan@amd.com>
Acked-by: Christian König <christian.koenig@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>
gfx memory should be initialized before enabling
DED and FUE field in mmGB_EDC_MODE
Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Currently ARCTURUS VF doesn't support jpeg ip block.
Skip jpeg ip block in case guest driver load fail.
Signed-off-by: Jack Zhang <Jack.Zhang1@amd.com>
Reviewed-by: Zhexi Zhang <zhexi.zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Be less pessimistic about estimated page table use for KFD. Most
allocations use 2MB pages and therefore need less VRAM for page
tables. This allows more VRAM to be used for applications especially
on large systems with many GPUs and hundreds of GB of system memory.
Example: 8 GPUs with 32GB VRAM each + 256GB system memory = 512GB
Old page table reservation per GPU: 1GB
New page table reservation per GPU: 32MB
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: xinhui pan <xinhui.pan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Allow KFD applications to use more unpinned system memory through
HMM.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Yong Zhao <Yong.Zhao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Commit b0f3cd3191 ("drm/amdgpu: remove unnecessary JPEG2.0 code from
VCN2.0") introduced a new clang warning in the vcn_v2_0_stop function:
../drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c:1082:2: warning: variable 'r'
is used uninitialized whenever 'while' loop exits because its condition
is false [-Wsometimes-uninitialized]
SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7, r);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../drivers/gpu/drm/amd/amdgpu/../amdgpu/soc15_common.h:55:10: note:
expanded from macro 'SOC15_WAIT_ON_RREG'
while ((tmp_ & (mask)) != (expected_value)) { \
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c:1083:6: note: uninitialized use
occurs here
if (r)
^
../drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c:1082:2: note: remove the
condition if it is always true
SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7, r);
^
../drivers/gpu/drm/amd/amdgpu/../amdgpu/soc15_common.h:55:10: note:
expanded from macro 'SOC15_WAIT_ON_RREG'
while ((tmp_ & (mask)) != (expected_value)) { \
^
../drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c:1072:7: note: initialize the
variable 'r' to silence this warning
int r;
^
= 0
1 warning generated.
To prevent warnings like this from happening in the future, make the
SOC15_WAIT_ON_RREG macro initialize its ret variable before the while
loop that can time out. This macro's return value is always checked so
it should set ret in both the success and fail path.
Link: https://github.com/ClangBuiltLinux/linux/issues/776
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Config the translation retry behavior according to noretry
kernel parameter
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Suggested-by: Jay Cornwall <Jay.Cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It may lose gpuvm invalidate acknowldege state across power-gating off
cycle. To avoid this issue in gmc9/gmc10 invalidation, add semaphore acquire
before invalidation and semaphore release after invalidation.
After adding semaphore acquire before invalidation, the semaphore
register become read-only if another process try to acquire semaphore.
Then it will not be able to release this semaphore. Then it may cause
deadlock problem. If this deadlock problem happens, it needs a semaphore
firmware fix.
Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
SW must acquire/release one of the vm_invalidate_eng*_sem around the
invalidation req/ack. Through this way,it can avoid losing invalidate
acknowledge state across power-gating off cycle.
To use vm_invalidate_eng*_sem, it needs to initialize
vm_invalidate_eng*_sem firstly.
Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
After rlcg fw 2.1, kmd driver starts to load extra fw for
LIST_CNTL,GPM_MEM,SRM_MEM. We needs to skip the three fw
because all rlcg related fw have been loaded by host driver.
Guest driver would load the three fw fail without this change.
Signed-off-by: Jack Zhang <Jack.Zhang1@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Temporarily skip ras,dtm,hdcp initialize and terminate for arcturus VF
Currently the three features haven't been enabled at SRIOV, it would
trigger guest driver load fail with the bare-metal path of the three
features.
Signed-off-by: Jack Zhang <Jack.Zhang1@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This patch fixes 2nd baco reset failure with gfxoff enabled on navi1x.
clear state buffer (resides in vram) is corrupted after 1st baco reset,
upon gfxoff exit, CPF gets garbage header in CSIB and hangs.
Signed-off-by: Xiaojie Yuan <xiaojie.yuan@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Kevin Wang <kevin1.wang@amd.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The pointer write_frame is being initialized with a value that is
never read and it is being updated later with a new value. The
initialization is redundant and can be removed.
Addresses-Coverity: ("Unused value")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
In the standard _PR3 case, the pci core handles the pci state.
The driver only needs to handle it in the legacy ATPX case.
This may fix issues with runtime suspend/resume on certain
hybrid graphics laptops.
Acked-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Get mmhub error counter by accessing EDC_CNT registers.
v2: Add mmhub_v9_4_ prefix for local static variable and function
Signed-off-by: Dennis Li <dennis.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
