Add a new opcode to INFO IOCTL to retrieve aggregate H/W events. i.e. the
events counters are NOT cleared upon device reset, but count from the
loading of the driver.
Add the code to support it in the device event handling function.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>
Users and sysadmins usually want to know what is the device utilization as
a level 0 indication if they are efficiently using the device.
Add a new opcode to the INFO IOCTL that will return the device utilization
over the last period of 100-1000ms. The return value is 0-100,
representing as percentage the total utilization rate.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>
In some files the driver uses __le32_to_cpu while in other it uses
le32_to_cpu. Replace all __le32_to_cpu instances with le32_to_cpu for
consistency.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The HW IP information is relevant even if the device is disabled or in
reset, so always handle the corresponding INFO IOCTL opcode.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch fixes a possible kernel crash when a user provides a too small
input structure to the Debug IOCTL.
The fix sets a default input structure and copies to it the user data.
In case the user provided as input a too small structure, the code will
use the default values taken from the default structure.
Note that in contrary to the input structure, the user can provide an
output structure with changing size or no size at all. Therefore the user
output structure validation is already done in the Debug logic later on.
Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch changes the driver to create two char devices for each ASIC
it discovers. This is done to allow system/monitoring applications to
query the device for stats, information, idle state and more, while also
allowing the deep-learning application to send work to the ASIC.
One char device is the original device, hlX. IOCTL calls through this
device file can perform any task on the device (compute, memory, queries).
The open function for this device will fail if it was called before but
the file-descriptor it created was not completely released yet (the
release callback function is not called from the kernel until all
instances of that FD are closed). The driver needs to keep this behavior
to support backward compatibility with existing userspace, which count
that the open will fail if the device is "occupied".
The second char device is called "hl_controlDx", where x is the same index
of the main device with a minor number of the original char device + 1.
Applications that open this device can only call the INFO IOCTL. There is
no limitation on the number of applications opening this device.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When the user query the dram usage of a context, show it the dram usage of
its context, not the user context that is currently running on the device.
This has no effect right now as we only have a single process and a single
context, but this makes the code more ready for multiple process support.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The information which is currently provided as a response to the
"HL_INFO_HW_IDLE" IOCTL is merely a general boolean value.
This patch extends it and provides also a bitmask that indicates which
of the device engines are busy.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Command submissions sent to the device are composed of command buffers
which are targeted to different device engines, like DMA and compute
entities. When a command submission gets stuck, knowing in which engine
the stuck is, is crucial for debugging.
This patch adds a debugfs node that exports this information, by
displaying the engines' various registers that assemble their idle/busy
status.
The information retrieval is based on the is_device_idle ASIC function.
The printout in this function, of the first detected busy engine, is
removed because it becomes redundant in the presence of the more
elaborated info of the new debugfs node.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch changes the print of an error message about mis-configuration
of the debug infrastructure to be rate-limited, to prevent flooding of
kernel log, as these configuration requests can come at a high rate.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch adds the implementation of the HL_DEBUG_OP_SET_MODE opcode in
the DEBUG IOCTL.
It forces the user who wants to debug the device to set the device into
debug mode before he can configure the debug engines. The patch also makes
sure to disable debug mode upon user releasing FD, in case the user forgot
to disable debug mode.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
We cannot cast a 64-bit integer to a pointer on 32-bit architectures
without a warning:
drivers/misc/habanalabs/habanalabs_ioctl.c: In function 'debug_coresight':
drivers/misc/habanalabs/habanalabs_ioctl.c:143:23: error: cast to pointer from integer of different size [-Werror=int-to-pointer-cast]
input = memdup_user((const void __user *) args->input_ptr,
Use the macro that was defined for this purpose.
Fixes: 315bc055ed ("habanalabs: add new IOCTL for debug, tracing and profiling")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch makes some improvement in how IOCTLs behave when the device is
disabled or under reset.
The new code checks, at the start of every IOCTL, if the device is
disabled or in reset. If so, it prints an appropriate kernel message and
returns -EBUSY to user-space.
In addition, the code modifies the location of where the
hard_reset_pending flag is being set or cleared:
1. It is now cleared immediately after the reset *tear-down* flow is
finished but before the re-initialization flow begins.
2. It is being set in the remove function of the device, to make the
behavior the same with the hard-reset flow
There are two exceptions to the disable or in reset check:
1. The HL_INFO_DEVICE_STATUS opcode in the INFO IOCTL. This opcode allows
the user to inquire about the status of the device, whether it is
operational, in reset or malfunction (disabled). If the driver will
block this IOCTL, the user won't be able to retrieve the status in
case of malfunction or in reset.
2. The WAIT_FOR_CS IOCTL. This IOCTL allows the user to inquire about the
status of a CS. We want to allow the user to continue to do so, even if
we started a soft-reset process because it will allow the user to get
the correct error code for each CS he submitted.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Habanalabs ASICs use the ARM coresight infrastructure to support debug,
tracing and profiling of neural networks topologies.
Because the coresight is configured using register writes and reads, and
some of the registers hold sensitive information (e.g. the address in
the device's DRAM where the trace data is written to), the user must go
through the kernel driver to configure this mechanism.
This patch implements the common code of the IOCTL and calls the
ASIC-specific function for the actual H/W configuration.
The IOCTL supports configuration of seven coresight components:
ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP
The user specifies which component he wishes to configure and provides a
pointer to a structure (located in its process space) that contains the
relevant configuration.
The common code copies the relevant data from the user-space to kernel
space and then calls the ASIC-specific function to do the H/W
configuration.
After the configuration is done, which is usually composed
of several IOCTL calls depending on what the user wanted to trace, the
user can start executing the topology. The trace data will be written to
the user's area in the device's DRAM.
After the tracing operation is complete, and user will call the IOCTL
again to disable the tracing operation. The user also need to read
values from registers for some of the components (e.g. the size of the
trace data in the device's DRAM). In that case, the user will provide a
pointer to an "output" structure in user-space, which the IOCTL code will
fill according the to selected component.
Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This patch adds a new opcode to INFO IOCTL that returns the device status.
This will allow users to query the device status in order to avoid sending
command submissions while device is in reset.
Signed-off-by: Dalit Ben Zoor <dbenzoor@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Print the name of a busy engine when checking if a device is idle.
The change is done mainly to help a user to pinpoint problems in his
topology's recipe.
Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
At the start of some IOCTLs we check if the device is disabled or in reset.
If it is, we return -EBUSY and print a message to kernel log.
Because these IOCTLs can be called at very high frequency, use ratelimit
to avoid spamming the kernel log. Also use the same type of message -
dev_warn - in all the relevant IOCTLs.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Add __cpu_to_le16/32/64 and __le16/32/64_to_cpu where needed according to
sparse.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch implements the INFO IOCTL. That IOCTL is used by the user to
query information that is relevant/needed by the user in order to submit
deep learning jobs to Goya.
The information is divided into several categories, such as H/W IP, Events
that happened, DDR usage and more.
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch adds the Virtual Memory and MMU modules.
Goya has an internal MMU which provides process isolation on the internal
DDR. The internal MMU also performs translations for transactions that go
from Goya to the Host.
The driver is responsible for allocating and freeing memory on the DDR
upon user request. It also provides an interface to map and unmap DDR and
Host memory to the device address space.
The MMU in Goya supports 3-level and 4-level page tables. With 3-level, the
size of each page is 2MB, while with 4-level the size of each page is 4KB.
In the DDR, the physical pages are always 2MB.
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch adds the main flow for the user to submit work to the device.
Each work is described by a command submission object (CS). The CS contains
3 arrays of command buffers: One for execution, and two for context-switch
(store and restore).
For each CB, the user specifies on which queue to put that CB. In case of
an internal queue, the entry doesn't contain a pointer to the CB but the
address in the on-chip memory that the CB resides at.
The driver parses some of the CBs to enforce security restrictions.
The user receives a sequence number that represents the CS object. The user
can then query the driver regarding the status of the CS, using that
sequence number.
In case the CS doesn't finish before the timeout expires, the driver will
perform a soft-reset of the device.
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch adds support for doing various on-the-fly reset of Goya.
The driver supports two types of resets:
1. soft-reset
2. hard-reset
Soft-reset is done when the device detects a timeout of a command
submission that was given to the device. The soft-reset process only resets
the engines that are relevant for the submission of compute jobs, i.e. the
DMA channels, the TPCs and the MME. The purpose is to bring the device as
fast as possible to a working state.
Hard-reset is done in several cases:
1. After soft-reset is done but the device is not responding
2. When fatal errors occur inside the device, e.g. ECC error
3. When the driver is removed
Hard-reset performs a reset of the entire chip except for the PCI
controller and the PLLs. It is a much longer process then soft-reset but it
helps to recover the device without the need to reboot the Host.
After hard-reset, the driver will restore the max power attribute and in
case of manual power management, the frequencies that were set.
This patch also adds two entries to the sysfs, which allows the root user
to initiate a soft or hard reset.
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch adds the command buffer (CB) module, which allows the user to
create and destroy CBs and to map them to the user's process
address-space.
A command buffer is a memory blocks that reside in DMA-able address-space
and is physically contiguous so it can be accessed by the device without
MMU translation. The command buffer memory is allocated using the
coherent DMA API.
When creating a new CB, the IOCTL returns a handle of it, and the
user-space process needs to use that handle to mmap the buffer to get a VA
in the user's address-space.
Before destroying (freeing) a CB, the user must unmap the CB's VA using the
CB handle.
Each CB has a reference counter, which tracks its usage in command
submissions and also its mmaps (only a single mmap is allowed).
The driver maintains a pool of pre-allocated CBs in order to reduce
latency during command submissions. In case the pool is empty, the driver
will go to the slow-path of allocating a new CB, i.e. calling
dma_alloc_coherent.
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
