Add support for reporting GPU reset events through SMI. KFD
would report both pre and post GPU reset events.
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>
Event bitmask is a 64-bit mask with only 1 bit set. Sending this
event bitmask in KFD SMI event message is both wasteful of memory
and potentially limiting to only 64 events. Instead send event
index in SMI event message.
Please note this change does not break the ABI for the two event
types defined so far. The new index is identical to the mask used
before.
Signed-off-by: Mukul Joshi <mukul.joshi@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>
Add support for reporting thermal throttling events through SMI.
Also, add a counter to count the number of throttling interrupts
observed and report the count in the SMI event message.
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>
When the compute is malfunctioning or performance drops, the system admin
will use SMI (System Management Interface) tool to monitor/diagnostic what
went wrong. This patch provides an event watch interface for the user
space to register devices and subscribe events they are interested. After
registered, the user can use annoymous file descriptor's poll function
with wait-time specified and wait for events to happen. Once an event
happens, the user can use read() to retrieve information related to the
event.
VM fault event is done in this patch.
v2: - remove UNREGISTER and add event ENABLE/DISABLE
- correct kfifo usage
- move event message API to kfd_ioctl.h
v3: send the event msg in text than in binary
v4: support multiple clients
v5: move events enablement from ioctl to fd write
v6: sparse fix
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Add a new kfd ioctl to allocate queue GWS. Queue
GWS is released on queue destroy.
v2: re-introduce this API with the following fixes squashed in:
- drm/amdkfd: fix null pointer dereference on dev
- drm/amdkfd: Return proper error code for gws alloc API
- drm/amdkfd: Remove GPU ID in GWS queue creation
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Existing QUEUE_TYPE_SDMA means PCIe optimized SDMA queues.
Introduce a new QUEUE_TYPE_SDMA_XGMI, which is optimized
for non-PCIe transfer such as XGMI.
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Introduce a new memory type (KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) and
expose mmio page of HDP registers to user space through this new
memory type.
v2: moved remapped hdp regs to adev struct
v3: rename the new memory type to ALLOC_MEM_FLAGS_MMIO_REMAP
v4: use more generic function name
v5: Fail remapped mmio allocation for asics before gfx9
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Remap HDP_MEM_COHERENCY_FLUSH_CNTL and HDP_REG_COHERENCY_FLUSH_CNTL
to an empty page in mmio space. We will later map this page to process
space so application can flush hdp. This can't be done properly at
those registers' original location because it will expose more than
desired registers to process space.
v2: Use explicit register hole location
v3: Moved remapped hdp registers into adev struct
v4: Use more generic name for remapped page
Expose register offset in kfd_ioctl.h
v5: Move hdp register remap function to nbio ip function
v6: Fixed operator precedence issue and other bugs
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
RAS ECC event will combine with GPU reset event, due to
ECC interrupts are caused by uncorrectable error that triggers
GPU reset.
v2: Fix misleading-indentation warning
v3: fix build with CONFIG_HSA_AMD disabled
Signed-off-by: Eric Huang <JinhuiEric.Huang@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>
This is used for interoperability between ROCm compute and graphics
APIs. It allows importing graphics driver BOs into the ROCm SVM
address space for zero-copy GPU access.
The API is split into two steps (query and import) to allow user mode
to manage the virtual address space allocation for the imported buffer.
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Consistently use types provided by <linux/types.h> via <drm/drm.h>
to fix struct kfd_ioctl_get_queue_wave_state_args userspace compilation errors.
Fixes: 5df099e8bc ("drm/amdkfd: Add wavefront context save state retrieval ioctl")
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Consistently use types provided by <linux/types.h> via <drm/drm.h>
to fix the following linux/kfd_ioctl.h userspace compilation errors:
/usr/include/linux/kfd_ioctl.h:250:2: error: unknown type name 'uint32_t'
uint32_t reset_type;
/usr/include/linux/kfd_ioctl.h:251:2: error: unknown type name 'uint32_t'
uint32_t reset_cause;
/usr/include/linux/kfd_ioctl.h:252:2: error: unknown type name 'uint32_t'
uint32_t memory_lost;
/usr/include/linux/kfd_ioctl.h:253:2: error: unknown type name 'uint32_t'
uint32_t gpu_id;
Fixes: 0c119abad7 ("drm/amd: Add kfd ioctl defines for hw_exception event")
Cc: <stable@vger.kernel.org> # v4.19
Signed-off-by: Dmitry V. Levin <ldv@altlinux.org>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Wavefront context save data is of interest to userspace clients for
debugging static wavefront state. The MQD contains two parameters
required to parse the control stack and the control stack itself
is kept in the MQD from gfx9 onwards.
Add an ioctl to fetch the context save area and control stack offsets
and to copy the control stack to a userspace address if it is kept in
the MQD.
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
1. Pre-GFX9 the amdgpu ISR saves the vm-fault status and address per
per-vmid. amdkfd needs to get the information from amdgpu through the
new get_vm_fault_info interface. On GFX9 and later, all the required
information is in the IH ring
2. amdkfd unmaps all queues from the faulting process and create new
run-list without the guilty process
3. amdkfd notifies the runtime of the vm fault trap via EVENT_TYPE_MEMORY
Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
v2:
* Fix error handling after kfd_bind_process_to_device in
kfd_ioctl_map_memory_to_gpu
v3:
* Add ioctl to acquire VM from a DRM FD
v4:
* Return number of successful map/unmap operations in failure cases
* Facilitate partial retry after failed map/unmap
* Added comments with parameter descriptions to new APIs
* Defined AMDKFD_IOC_FREE_MEMORY_OF_GPU write-only
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Currently the number of GPUs is limited by aperture placement options
available on GFX7 and GFX8 hardware. This limitation is not necessary.
Scratch and LDS represent per-work-item and per-work-group storage
respectively. Different work-items and work-groups use the same virtual
address to access their own data. Work running on different GPUs is by
definition in different work-groups (different dispatches, in fact).
That means the same virtual addresses can be used for these apertures
on different GPUs.
Add a new AMDKFD_IOC_GET_PROCESS_APERTURES_NEW ioctl that removes the
artificial limitation on the number of GPUs that can be supported. The
new ioctl allows user mode to query the number of GPUs to allocate
enough memory for all GPUs to be reported.
This deprecates AMDKFD_IOC_GET_PROCESS_APERTURES.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
A second-level user mode trap handler can be installed. The CWSR trap
handler jumps to the secondary trap handler conditionally for any
conditions not handled by it. This can be used e.g. for debugging or
catching math exceptions.
When CWSR is disabled, the user mode trap handler is installed as
first level trap handler.
Signed-off-by: Shaoyun.liu <shaoyun.liu@amd.com>
Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
