The code used the mmu mutex to protect access to the context's page
tables and invalidation of the MMU cache. Because pgt are per
context, the mmu mutex was a member of the context object.
The problem is that the device has a single MMU invalidation h/w
(per MMU). Therefore, the mmu mutex should not be a property of the
context but a property of the device.
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>
Current code does not takes into account the new DRAM region base
and so calculated address is wrong and can lead to crush.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Firmware now responds with a more detailed cpucp return codes.
Driver can now distinguish between error and debug return codes.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
F/W security status might change after every reset.
Add the reading of the preboot status to the hard reset sequence, which
among others reads this security indication.
As this preboot status reading includes the waiting for the preboot to
be ready, it can be removed from the CPU init which is done in a later
stage.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Current description is misleading hence we rename it to a more
suitable error description.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
cb_map_mem() uses gen_pool_alloc() to get virtual address for
mapping a CB.
The mapping is done in chunks of page size, so if the CB size is
larger, it is possible that the allocated virtual addresses won't
be consecutive.
User retrieves this device VA which returns the virtual address
in the first va_block. If there is a "hole" in the virtual addresses,
user can configure a HW block with a bad device VA.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
'Device activity open packet' should be sent outside of mutex as
there is no real necessity for a lock.
In addition 'device activity close packet' should be sent upon an
actual release of the device.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
As part of the RAS that is done by the f/w, we should send a message
to the f/w when a user either acquires or releases the device.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In order to improve debuggability, we add all available information
when a RAZWI event occur.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
When we have a storm of errors of HBM ECC SERR we can reach a situation
where driver start hard reset flow without logging the error cause
that caused the hard reset due to logs rate limiting.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
EEPROM errors reported by firmware are basically warnings and
should not fail the boot process.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Except Goya, none of our ASICs require context switch flow, hence we
enable this flow only where it is needed.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Set the addresses for userspace command buffer dynamically
instead of hard-coded. There is no reason for it to
be hard-coded.
Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This patch add tracepoints in the code for DMA allocation.
The main purpose is to be able to cross data with the map operations and
determine whether memory violation occurred, for example free DMA
allocation before unmapping it from device memory.
To achieve this the DMA alloc/free code flows were refactored so that a
single DMA tracepoint will catch many flows.
To get better understanding of what happened in the DMA allocations
the real allocating function is added to the trace as well.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This patch utilize the defined tracepoint to trace the MMU's pages
map/unmap operations.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This patch adds trace events for habanalabs driver to gain all the
benefits such an infrastructure can supply.
The following events were added:
- MMU map/unmap: to be able to track driver's memory allocations
- DMA alloc/free: to track our DMA allocation
the above trace points in conjunction will help us map the device memory
usage as well as to be able to track memory violations.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Acked-by: Oded Gabbay <ogabbay@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The calculation of the device DRAM base address before setting the
relevant PCIe BAR to point at it, has an assumption that this BAR is
used to access only the DRAM, and thus the covered DRAM size is a power
of 2.
In future ASICs it is not necessarily true, so need to update the
calculation to support also a non-power-of-2 size.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The original code tried to unmap a page that was not mapped as part of
the map page error path.
Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The driver is loading firmware to the device and we use the firmware
loading functions from the FW_LOADER module.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Instead of recalculating the cdev index, store it in a dedicated data
member. This data member is intended to be passed to other drivers using
the auxiliary bus infra and hence this new data member is necessary in
case that the calculation is changed in the future.
Signed-off-by: Omer Shpigelman <oshpigelman@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>
In order for the user to know if he is running on a secured device
or not, a sysfs node is added.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Secured PCI ID will not be supported in new asics because the
security status can always be read from the f/w.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Several munmap() calls can be done or a mapped H/W block that has a
larger size than a page size.
Releasing the object should be done only when all mapped range is
unmapped.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Since hwmon fini code is common for all asics, unified it to common
function.
Signed-off-by: Dani Liberman <dliberman@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>
On Gaudi2 the f/w always configures the PCIe iATU and allows access to
scratchpad registers. Therefore, we can know if the f/w is secured
by reading a status bit from the f/w registers.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
A common function that is called from multiple places can't be
located in degugfs.c because that file is only compiled if
debugfs is enabled in the kernel config file.
This can lead to undefined symbol compilation error.
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Add a missing lock in hl_device_resume() when it assigns a value to the
'in_reset' indication.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In hl_hw_block_mmap(), the vma's 'vm_private_data' and 'vm_ops' fields
are assigned before filling the content of the private data.
In between there is a call to the ASIC hw_block_mmap() function, and if
it fails, the vma close function will be called with a bad private data
value.
Fix the order of assignments to avoid this issue.
In hl_hw_block_mmap() the vma's 'vm_private_data and vm_ops are assigned
before setting the
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
map_block() sets the block id handle even if get_hw_block_id() fails,
and in this case it uses block id 0 which might be a valid id.
Modify it to set the handle only if get_hw_block_id() succeeds.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
When a CS is submitted, the ioctl handler checks the CS
flags and performs a sanity check, according to its value.
As new CS flags are added, the sanity check needs to be updated
according to the new flags.
Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Even when running with unsecured f/w, we should read the PLL div_sel
value from the f/w as this register is always privileged.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Print format was for int (%d) while variable is u32.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
F/W events are enabled in a late phase of the device init, so an event
for a PCIE access error during the init, can be received after the init
is already done and considered as successful.
A resulting device reset, which does the same H/W init, can end
similarly with this event right after the reset is done and considered
as successful, and a loop of this sequence can continue.
To avoid it mark the PCIE access error as a fatal event, so after 2
consecutive events no more resets will be done.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
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>
We don't use KDMA concurrently in the driver. The only use is through
debugfs and we don't protect concurrent access through it.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
The macro argument <val> is cast-ed to u32 in some of the places.
Because this arg can be some arithmetic computation (e.g. address +
offset) the cast should be on the whole expression.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Interrupt enumration has changed some time ago but the old mapping
was accidentally left in the driver.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In order to improve scalability and reduce host overhead, it is better
to increase the default TDR timeout of Gaudi1 from 30 seconds to
10 minutes.
This will allow the DL Framework (e.g. PyTorch, TensorFlow) to remove
the host sync they are using now and improve overall performance on
scaleout training.
Note that one can always set the timeout to a custom value via
a kernel module parameter given during driver load.
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Up until now the module iterator called void callback functions
and so caller activating callback that may fail suffered from 2 issues:
1. The need to "plant" return called in the private data. This is a
drawback since the iterator itself should not be aware of the private
data of the caller.
2. Due to 1 even in a failure the iterator would keep iterating instead
of break upon error.
To overcome this an optional rc field added to the iterator context.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Currently only part of the MMU SPI/SEI interrupts are enabled, although
there is no real reason to not enable all.
The only exception is "burst_fifo_full" which is expected for PMMU
because it has a 2 entries FIFO, and thus is it not enabled for it.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
In order to be more explicit we should use the term compute_reset
for describing the reset in which only the compute engines gets
reset.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
There is a spelling mistake in a dev_dbg message. Fix it.
Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
