Oded writes:
This tag contains habanalabs driver changes for v6.2:
- New feature of graceful hard-reset. Instead of immediately killing the
user-process when a command submission times out, we wait a bit and give
the user-process notification and let it try to close things gracefully,
with the ability to retrieve debug information.
- Enhance the EventFD mechanism. Add new events such as access to illegal
address (RAZWI), page fault, device unavailable. In addition, change the
event workqueue to be handled in a single-threaded workqueue.
- Allow the control device to work during reset of the ASIC, to enable
monitoring applications to continue getting the data.
- Add handling for Gaudi2 with PCI revision 2.
- Reduce severity of prints due to power/thermal events.
- Change how we use the h/w to perform memory scrubbing in Gaudi2.
- Multiple bug fixes, refactors and renames.
* tag 'misc-habanalabs-next-2022-11-23' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux: (63 commits)
habanalabs: fix VA range calculation
habanalabs: fail driver load if EEPROM errors detected
habanalabs: make print of engines idle mask more readable
habanalabs: clear non-released encapsulated signals
habanalabs: don't put context in hl_encaps_handle_do_release_sob()
habanalabs: print context refcount value if hard reset fails
habanalabs: add RMWREG32_SHIFTED to set a val within a mask
habanalabs: fix rc when new CPUCP opcodes are not supported
habanalabs/gaudi2: added memset for the cq_size register
habanalabs: added return value check for hl_fw_dynamic_send_clear_cmd()
habanalabs: increase the size of busy engines mask
habanalabs/gaudi2: change memory scrub mechanism
habanalabs: extend process wait timeout in device fine
habanalabs: check schedule_hard_reset correctly
habanalabs: reset device if still in use when released
habanalabs/gaudi2: return to reset upon SM SEI BRESP error
habanalabs/gaudi2: don't enable entries in the MSIX_GW table
habanalabs/gaudi2: remove redundant firmware version check
habanalabs/gaudi: fix print for firmware-alive event
habanalabs: fix print for out-of-sync and pkt-failure events
...
In order to be able to start the adsp listener for audiopd using adsprpcd,
we need to add the corresponding ioctl for creating a static process.
On that ioctl call we need to allocate the heap. Allocating the heap needs
to be happening only once and needs to be kept between different device
open calls, so attach it to the channel context to make sure that remains
until the RPMSG driver is removed. Then, if there are any VMIDs associated
with the static ADSP process, do a call to SCM to assign it.
And then, send all the necessary info related to heap to the DSP.
Co-developed-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Abel Vesa <abel.vesa@linaro.org>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Link: https://lore.kernel.org/r/20221125071405.148786-8-srinivas.kandagatla@linaro.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Increase the size of the busy engines mask in 'struct hl_info_hw_idle',
for future ASICs with more than 128 engines.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Each time page fault happens, besides capturing its data, also notify
the user about it.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Each time razwi (read-only zero, write ignore) happens, besides
capturing its data, also notify the user about it.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Add support for Gaudi2 Device with PCI revision 2.
Functionality is exactly the same as revision 1, the only difference
is device name exposed to user.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Added function to calculate possible engines which caused
RAZWI (read-only zero, write ignored), from a given router id or
module index.
When getting RAZWI via PSOC IP, first the router id is calculated
and then the possible engines that caused the RAZWI are calculated.
There is a possibility that the RAZWI initiator is not an engine. In
that case, it will not be included in possible engines as it
doesn't have an engine id.
RAZWI information is captured when receiving event from engine or via
PSOC IP.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Only the first page fault will be saved.
Besides the address which caused the page fault, the driver captures
all of the mmu user mappings.
User can retrieve this data via the new uapi (new opcode in INFO ioctl).
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This event notification was compatible only with gaudi, where razwi
and page fault happens together.
To make it compatible with all ASICs, this refactor contains:
1. Razwi notification will only notify about razwi info.
New notification will be added in future patch, to retrieve data
about page fault error.
2. Changed razwi info structure to support all ASICs.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
User will provide a nonce via the ioctl, and will retrieve
secured attestation data of the boot, generated using given
nonce.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Add new notifier events that inform several device states.
General H/W error raised on device general H/W error occurs.
User engine error is raised when a device engine informs of an error.
Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In order for the user to know if he is running on a secured device
or not, we add it also to the hw_ip info ioctl.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The current flow of halting the engine cores is implemented by command
buffers built by the user space and sent towards the Driver.
This current flow is broken since the user space does not know when
the cores actually halt as sending a workload is async op.
Therefore the application can not free the memory that is mapped
to the engine cores.
This new API allows the user space to control the running mode. The
API call is sync (returns after the cores are set to the
requested mode).
Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Cosmetic change to move the eventfd events defines to a better
location in the file, closer to other INFO IOCTL defines.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Currently, to get engines status, user needed to read debugfs file
with root permissions.
This new uapi allows user apace apps retrieve status, so for example,
in case of failure, status can be retrieved immediately by the
application itself which runs without root permissions.
Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
To be compatible with accelerator devices of different
versions, 'UACCE_CMD_QM_SET_QP_INFO' ioctl is added to obtain
queue information in userspace, including queue depth and buffer
description size.
Signed-off-by: Weili Qian <qianweili@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
The user might want to know the device is in reset after device
release, which is not an erroneous event as a regular reset.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
User application should be able to get notification for any decoder
completion. Hence, we introduce a new interface in which a user
can wait for all current decoder pending interrupts.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Current naming convention can be misleading. Hence renaming some
variables and defines in order to be more explicit.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Add the new defines for GAUDI2 uapi interface.
It includes the following:
1. Enums of engines and PLLs.
2. New information in the info IOCTL that is retrieved by the driver.
3. Update comments regarding the CB/CS/wait for CS ioctls.
4. New fields in the debug IOCTL for configuring the profiler for
Gaudi2.
There is no new IOCTL.
Some of the changes are also relevant for Greco (which will be
upstreamed later this year). When ever it says "Greco and onwards",
it means it is also for Gaudi2.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The values in this enum are not used by h/w but are a contract
between userspace and the kernel driver so they must be defined
in the uapi file.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
When a device error occurs, user process would like to get some
indication on the error by reading some device HW info. If the
device is unavailable, user process can't perform any HW device
reading.
Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The Driver needs to inform the User process whenever one of its
CS is timed out. The Driver shall recognize the CS timeout and shall
send an eventfd notification, towards user space, whenever a timeout
is expired on a CS.
Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
