reset cause is requested by customer as additional
info for gpu reset smi event.
v2: integerate reset sources suggested by Lijo Lazar
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
kfd_create_vcrat_image_gpu itself checks the avail_size at the start.
So the value of avail_size is at least VCRAT_SIZE_FOR_GPU(16384),
minus struct crat_header(40UL) and struct crat_subtype_compute(40UL) it cannot be less than 0.
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The expression caps | HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED
and caps | HSA_CAP_TRAP_DEBUG_PRECISE_ALU_OPERATIONS_SUPPORTED
are always 1/true regardless of the values of its operand.
Fixes: 9243240bed ("drm/amdkfd: enable single alu ops for gfx12")
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Suggested-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
A wavefront may deallocate its VGPRs at the end of a program while
waiting for memory transactions to complete. If it subsequently
receives a context save exception it will be unable to save,
since this requires VGPRs. In this case the trap handler should
terminate the wavefront.
Fixes intermittent VM faults under context switching load.
V2: Use S_ENDPGM instead of S_ENDPGM_SAVED for performance counters
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Lancelot Six <lancelot.six@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
The varible uncached set false, the condition uncached cannot be true.
So remove the dead code, mapping flags will set the flag AMDGPU_VM_MTYPE_UC in else.
Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Fix LDS size interpretation: 512 bytes (>= gfx12) vs 256 (< gfx12).
Ensure STATE_PRIV.BARRIER_COMPLETE cannot change after reading or
before writing. Other waves in the threadgroup may cause this field
to assert if they complete the barrier.
Do not overwrite EXCP_FLAG_PRIV.{SAVE_CONTEXT,HOST_TRAP} when
restoring this register. Both of these fields can assert while the
wavefront is running the trap handler.
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Lancelot Six <lancelot.six@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Newer assemblers reject S_WAITCNT. All instances of S_WAITCNT can be
replaced by S_WAITCNT 0 (< gfx12) or S_WAIT_IDLE (>= gfx12) since
there is no concurrency of different memory instruction classes.
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
Reviewed-by: Lancelot Six <lancelot.six@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
With commit 89773b8559
("drm/amdkfd: Let VRAM allocations go to GTT domain on small APUs")
big and small APU "VRAM" handling in KFD was unified. Since AMD_IS_APU
is set for both big and small APUs, we can simplify the checks in
the code.
v2: clean up a few more places (Lang)
Acked-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
It was an enablement vehicle for MES 11 and was never
productized. Remove it.
v2: drop additional checks in the GFX10 code.
v3: drop mes_api_def.h
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
gpu_id needs to be unique for user space to identify GPUs via KFD
interface. In the current implementation there is a very small
probability of having non unique gpu_ids.
v2: Add check to confirm if gpu_id is unique. If not unique, find one
Changed commit header to reflect the above
v3: Use crc16 as suggested-by: Lijo Lazar <lijo.lazar@amd.com>
Ensure that gpu_id != 0
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We are incorrectly passing the first XCC's MQD when
updating CU masks for other XCCs in the partition. Fix
this by passing the MQD for the XCC currently being
updated with CU mask to update_cu_mask function.
Fixes: fc6efed2c7 ("drm/amdkfd: Update CU masking for GFX 9.4.3")
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Analysis of code by Coverity, a static code analyser, has identified
a resource leak in the symbol hmm_range. This leak occurs when one of
the prior steps before it is released encounters an error.
Signed-off-by: Ramesh Errabolu <Ramesh.Errabolu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
On system with khugepaged enabled and user cases with THP buffer, the
hmm_range_fault may takes > 15 seconds to return -EBUSY, the arbitrary
timeout value is not accurate, cause memory allocation failure.
Remove the arbitrary timeout value, return EAGAIN to application if
hmm_range_fault return EBUSY, then userspace libdrm and Thunk will call
ioctl again.
Change EAGAIN to debug message as this is not error.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Currently oem_id is defined as uint8_t[6] and casted to uint64_t*
in some use case. This would lead code scanner to complain about
access beyond. Re-define it in union to enforce 8-byte size and
alignment to avoid potential issue.
Signed-off-by: Michael Chen <michael.chen@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
We don't get the right offset in that case. The GPU has
an unused 4K area of the register BAR space into which you can
remap registers. We remap the HDP flush registers into this
space to allow userspace (CPU or GPU) to flush the HDP when it
updates VRAM. However, on systems with >4K pages, we end up
exposing PAGE_SIZE of MMIO space.
Fixes: d8e408a827 ("drm/amdkfd: Expose HDP registers to user space")
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
In interrupt context, write dbg_ev_file will be run by work queue. It
will cause write dbg_ev_file execution after debug_trap_disable, which
will cause NULL pointer access.
v2: cancel work "debug_event_workarea" before set dbg_ev_file as NULL.
Signed-off-by: Lin.Cao <lincao12@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This reverts commit c37ce764cd.
RCCL library is currently not treating spatial partitions differently,
hence this change is causing issues. Revert temporarily till RCCL
implementation is ready for spatial partitions.
Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Small APUs(i.e., consumer, embedded products) usually have a small
carveout device memory which can't satisfy most compute workloads
memory allocation requirements.
We can't even run a Basic MNIST Example with a default 512MB carveout.
https://github.com/pytorch/examples/tree/main/mnist. Error Log:
"torch.cuda.OutOfMemoryError: HIP out of memory. Tried to allocate
84.00 MiB. GPU 0 has a total capacity of 512.00 MiB of which 0 bytes
is free. Of the allocated memory 103.83 MiB is allocated by PyTorch,
and 22.17 MiB is reserved by PyTorch but unallocated"
Though we can change BIOS settings to enlarge carveout size,
which is inflexible and may bring complaint. On the other hand,
the memory resource can't be effectively used between host and device.
The solution is MI300A approach, i.e., let VRAM allocations go to GTT.
Then device and host can flexibly and effectively share memory resource.
v2: Report local_mem_size_private as 0. (Felix)
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add new GFX12 PTE flag AMDGPU_PTE_IS_PTE to svm_range_get_pte_flags
function. This resolves the issues related to SVM enablement in GFX12.
Signed-off-by: Sreekant Somasekharan <sreekant.somasekharan@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
When trap_ctrl.trap_after_inst is set, it is possible for a wave to
enter the trap handler, after single-stepping an instruction and a
save_context is raised, with only save_context set in excp_flag_priv.
Because excp_flag_priv.trap_after_inst is not reliably set, we need to
use the missed single-step workaround for gfx12 as well.
Also add wave_start and wave_end as exceptions that should be handled
by the 2nd level trap handler.
Signed-off-by: Laurent Morichetti <laurent.morichetti@amd.com>
Tested-by: Lancelot Six <lancelot.six@amd.com>
Reviewed-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add support to save and restore the work group barrier state in gfx12
CWSR trap handler.
There is no support to directly restore the signal count of a barrier
state, so instead this patch repeatedly calls s_barrier_signal to
increment the signal count to the desired value.
In this patch, I have implemented the logic to restore the barrier at
the end of the block restoring the HWREGs. This process needs to be
done by exactly 1 wave per work group. To achieve this, the initial
value of s_restore_spi_init_hi (containing a FIRST_WAVE bit) needs to be
saved up until that point. An alternative could be restore the barrier
earlier in the process (around when LDS is restored, as the same wave
does both). Doing this would break the pattern that the restore
procedure follows the CWSR area layout.
Before restoring the barrier, this patch checks if the barrier was whose
state was saved has the "valid" bit set, even if I don't think this
barrier can be in an invalid state during context save. I expect this
test to always be true.
Signed-off-by: Lancelot SIX <lancelot.six@amd.com>
Reviewed-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Initial implementation, based on GFX11.
v2: Removed dbg_wa code as not needed on GFX12.
v3: squash in SDMA queue fixes (Alex)
v4: rebase (Alex)
Signed-off-by: David Belanger <david.belanger@amd.com>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
There is a race condition when re-creating a kfd_process for a process.
This has been observed when a process under the debugger executes
exec(3). In this scenario:
- The process executes exec.
- This will eventually release the process's mm, which will cause the
kfd_process object associated with the process to be freed
(kfd_process_free_notifier decrements the reference count to the
kfd_process to 0). This causes kfd_process_ref_release to enqueue
kfd_process_wq_release to the kfd_process_wq.
- The debugger receives the PTRACE_EVENT_EXEC notification, and tries to
re-enable AMDGPU traps (KFD_IOC_DBG_TRAP_ENABLE).
- When handling this request, KFD tries to re-create a kfd_process.
This eventually calls kfd_create_process and kobject_init_and_add.
At this point the call to kobject_init_and_add can fail because the
old kfd_process.kobj has not been freed yet by kfd_process_wq_release.
This patch proposes to avoid this race by making sure to drain
kfd_process_wq before creating a new kfd_process object. This way, we
know that any cleanup task is done executing when we reach
kobject_init_and_add.
Signed-off-by: Lancelot SIX <lancelot.six@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Queue buffer, though it is in system memory, has to be created using the
correct amdgpu device. Enforce this as the BO needs to mapped to the
GART for MES Hardware scheduler to access it.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Do VRAM accounting when doing migrations to vram to make sure
there is enough available VRAM and migrating to VRAM doesn't evict
other possible non-unified memory BOs. If migrating to VRAM fails,
driver can fall back to using system memory seamlessly.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Handle the case that the restore worker was already scheduled by another
eviction while the restore was in progress.
Fixes: 9a1c1339ab ("drm/amdkfd: Run restore_workers on freezable WQs")
Signed-off-by: Felix Kuehling <felix.kuehling@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Tested-by: Yunxiang Li <Yunxiang.Li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Linux 6.9-rc5
I've had a persistent msm failure on clang, and the fix is in fixes
so just pull it back to fix that.
Signed-off-by: Dave Airlie <airlied@redhat.com>
