When the MMU is heavily used by the engines, unmapping might take a lot of
time due to a full MMU cache invalidation done as part of the unmap flow.
Hence we might not be able to kill all open processes before going to hard
reset the device, as it involves unmapping of all user memory.
In case of a failure in killing all open processes, we should stop the
hard reset flow as it might lead to a kernel crash - one thread (killing
of a process) is updating MMU structures that other thread (hard reset) is
freeing.
Stopping a hard reset flow leaves the device as nonoperational and the
user can then initiate a hard reset via sysfs to reinitialize the device.
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>
GAUDI does not support soft-reset as it leaves the NIC ports in an awkward
state, where their QMANs were reset but the NIC itself is still working.
In addition, there is not much sense in doing soft-reset when training is
done on multiple GAUDIs.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
A new sequence is introduced to invalidate the MMU cache in order to avoid
timeouts.
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>
It's the default.
Also so much for "we're not going to tell the graphics people how to
review their code", dma_fence is a pretty core piece of gpu driver
infrastructure. And it's very much uapi relevant, including piles of
corresponding userspace protocols and libraries for how to pass these
around.
Would be great if habanalabs would not use this (from a quick look
it's not needed at all), since open source the userspace and playing
by the usual rules isn't on the table. If that's not possible (because
it's actually using the uapi part of dma_fence to interact with gpu
drivers) then we have exactly what everyone promised we'd want to
avoid.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
rts5249_set_aspm() and rts5260_set_aspm() do nothing more than the default
rtsx_comm_set_aspm() does, so remove them and use the default. No
functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200521180545.1159896-7-helgaas@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Simplify rtsx_comm_set_aspm() and remove the now-unused
rtsx_pci_enable_aspm().
rtsx_pci_disable_aspm() is still used by rtsx_pci_init_hw().
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200521180545.1159896-6-helgaas@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Instead of using the driver-specific rtsx_pci_update_cfg_byte() to update
the PCIe Link Control Register, use pcie_capability_clear_and_set_word()
like the rest of the kernel does. This makes it easier to maintain ASPM
across the PCI core and drivers.
Remove the now-unused rtsx_pci_update_cfg_byte() and ASPM_MASK_NEG
definitions.
No functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200521180545.1159896-5-helgaas@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Use ASPM_MASK_NEG instead of hard-coded value, as other callers of
rtsx_pci_update_cfg_byte() do. No functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200521180545.1159896-4-helgaas@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The struct rtsx_cr_option.dev_aspm_mode member is never set to anything
other than DEV_ASPM_DYNAMIC (0). Remove it and code that tests it. No
functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20200521180545.1159896-3-helgaas@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Add Renesas R8A774C0 in pci_device_id table so that pci-epf-test can be
used for testing PCIe EP on RZ/G2E.
Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Link: https://lore.kernel.org/r/1589493809-2602-1-git-send-email-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This code was using get_user_pages*(), in a "Case 2" scenario
(DMA/RDMA), using the categorization from [1]. That means that it's
time to convert the get_user_pages*() + put_page() calls to
pin_user_pages*() + unpin_user_pages() calls.
There is some helpful background in [2]: basically, this is a small
part of fixing a long-standing disconnect between pinning pages, and
file systems' use of those pages.
[1] Documentation/core-api/pin_user_pages.rst
[2] "Explicit pinning of user-space pages":
https://lwn.net/Articles/807108/
Cc: Frank Haverkamp <haver@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Link: https://lore.kernel.org/r/20200518015237.1568940-1-jhubbard@nvidia.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This code was using get_user_pages*(), in a "Case 2" scenario
(DMA/RDMA), using the categorization from [1]. That means that it's
time to convert the get_user_pages*() + put_page() calls to
pin_user_pages*() + unpin_user_pages() calls.
There is some helpful background in [2]: basically, this is a small
part of fixing a long-standing disconnect between pinning pages, and
file systems' use of those pages.
Note that this effectively changes the code's behavior as well: it now
ultimately calls set_page_dirty_lock(), instead of SetPageDirty(). This
is probably more accurate.
As Christoph Hellwig put it, "set_page_dirty() is only safe if we are
dealing with a file backed page where we have reference on the inode it
hangs off." [3]
[1] Documentation/core-api/pin_user_pages.rst
[2] "Explicit pinning of user-space pages":
https://lwn.net/Articles/807108/
[3] https://lore.kernel.org/r/20190723153640.GB720@lst.de
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Link: https://lore.kernel.org/r/20200518041307.1987328-1-jhubbard@nvidia.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The patch_cb_size is not updated for Wreg32 in its validate function, so
updated in goya_validate_cb.
Signed-off-by: Rachel Stahl <rstahl@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Instead of writing similar event handling code for each ASIC, move the code
to the common firmware file. This code will be used for GAUDI and all
future ASICs.
In addition, add two new fields to the auto-generated events file: valid
and description. This will save the need to manually write the events
description in the source code and simplify the code.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Enable the GAUDI ASIC code in the pci probe callback of the driver so the
driver will handle GAUDI ASICs.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Add the GAUDI code to initialize the ASIC's profiler. The profile receives
its initialization values from the user, same as in Goya, but the code to
initialize is in the driver because the configuration space of the
device is not directly exposed to the user.
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>
Add the code to initialize the security module of GAUDI. Similar to Goya,
we have two dedicated mechanisms for security: Range Registers and
Protection bits. Those mechanisms protect sensitive memory and
configuration areas inside the device.
In addition, in Gaudi we moved to a 3-level security scheme, where the F/W
runs with the highest security level (Privileged), the driver runs with a
less secured level (Secured) and the user is neither privileged nor
secured. The security module in the driver configures the Secured parts so
the user won't be able to access them. The Privileged parts are configured
by the F/W.
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>
The hwmgr module is responsible for messages sent to GAUDI F/W that are
not common to all habanalabs ASICs.
In GAUDI, we provide the user a simplified mode of controlling the ASIC
clock frequency. Instead of three different clocks, we present a single
clock property that the user can configure via sysfs.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Add the ASIC-dependent code for GAUDI. Supply (almost) all of the function
callbacks that the driver's common code need to initialize, finalize and
submit workloads to the GAUDI ASIC.
It also contains the code to initialize the F/W of the GAUDI ASIC and to
receive events from the F/W.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Add the relevant GAUDI ASIC registers header files. These files are
generated automatically from a tool maintained by the VLSI engineers.
There are more files which are not upstreamed because only very few defines
from those files are used in the driver. For those files, we copied the
relevant defines into gaudi_regs.h and gaudi_masks.h, to reduce the size of
this patch.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
For Gaudi the driver gets two new additional properties from the F/W:
1. The card's type - PCI or PMC
2. The card's location in the Gaudi's box (relevant only for PMC).
The card's location is also passed to the user in the HW IP info structure
as it needs this property for establishing communication between Gaudis.
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>
In Gaudi there is a feature of clock gating certain engines.
Therefore, add this property to the device structure.
In addition, due to a limitation of this feature, the driver needs to
dynamically enable or disable this feature during run-time. Therefore, add
ASIC interface functions to enable/disable this function from the common
code.
Moreover, this feature must be turned off when the user wishes to debug the
ASIC by reading/writing registers and/or memory through the driver's
debugfs. Therefore, add an option to enable/disable clock gating via the
debugfs interface.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
For Gaudi, the driver doesn't change the PM profile automatically due to
device-controlled PM capabilities. Therefore, set the PM profile to auto
only for Goya so the driver's code to automatically change the profile
won't run on Gaudi.
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Gaudi requires longer waiting during reset due to closing of network ports.
Add this explanation to the relevant comment in the code and add a
dedicated define for this reset timeout period, instead of multiplying
another define.
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>
Coresight is not supported on simulator, therefore add a boolean for
checking that (currently used by un-upstreamed code).
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>
Add the following two operations to the CS IOCTL:
Signal:
The signal operation is basically a command submission, that is created by
the driver upon user request. It will be implemented using a dedicated PQE
that will increment a specific SOB. There will be a new flag:
HL_CS_FLAGS_SIGNAL. When the user set this flag in the CS IOCTL structure,
the driver will execute a dedicated code path that will prepare this
special PQE and submit it. The user only needs to provide a queue index on
which to put the signal.
Wait:
The wait operation is also a command submission that is created by the
driver upon user request. It will be implemented using a dedicated PQE that
will contain packets of "ARM a monitor" + FENCE packet. There will be a new
flag: HL_CS_FLAGS_WAIT. When the user set this flag in the CS structure,
the driver will execute a dedicated code path that will prepare this
special PQE and submit it.
The user needs to provide the following parameters:
1. queue ID
2. an array of signal_seq numbers and the number of signals to wait on
(the length of signal_seq_arr).
The IOCTL will return the CS sequence number of the wait it put on the
queue ID.
Currently, the code supports signal_seq_nr==1. But this API definition will
allow us to put a single PQE that waits on multiple signals.
To correctly configure the monitor and fence, the driver will need to
retrieve the specified signal CS object that contains the relevant SOB and
its expected value. In case the signal CS has already been completed, there
is no point of adding a wait operation. In this case, the driver will
return to the user *without* putting anything on the PQ. The return code
should reflect to the user that the signal was completed, as we won't
return a CS sequence number for this wait.
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>
Define a structure representing the h/w sync object (SOB).
a SOB can contain up to 2^15 values. Each signal CS will increment the SOB
by 1, so after some time we will reach the maximum number the SOB can
represent. When that happens, the driver needs to move to a different SOB
for the signal operation.
A SOB can be in 1 of 4 states:
1. Working state with value < 2^15
2. We reached a value of 2^15, but the signal operations weren't completed
yet OR there are pending waits on this signal. For the next submission, the
driver will move to another SOB.
3. ALL the signal operations on the SOB have finished AND there are no more
pending waits on the SOB AND we reached a value of 2^15 (This basically
means the refcnt of the SOB is 0 - see explanation below). When that
happens, the driver can clear the SOB by simply doing WREG32 0 to it and
set the refcnt back to 1.
4. The SOB is cleared and can be used next time by the driver when it needs
to reuse an SOB.
Per SOB, the driver will maintain a single refcnt, that will be initialized
to 1. When a signal or wait operation on this SOB is submitted to the PQ,
the refcnt will be incremented. When a signal or wait operation on this SOB
completes, the refcnt will be decremented. After the submission of the
signal operation that increments the SOB to a value of 2^15, the refcnt is
also decremented.
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 feature requires handling h/w resources which are a bit different from
one ASIC to the other. Therefore, we need to define a set of interfaces the
ASIC code provides to the common code to signal, wait, reset sync object
and to reset and init a queue.
As this feature is not supported in Goya, provide an empty implementation
of those functions.
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 is a pre-requisite to upstreaming GAUDI support.
Signal/wait operations are done by the user to perform sync between two
Primary Queues (PQs). The sync is done using the sync manager and it is
usually resolved inside the device, but sometimes it can be resolved in the
host, i.e. the user should be able to wait in the host until a signal has
been completed.
The mechanism to define signal and wait operations is done by the driver
because it needs atomicity and serialization, which is already done in the
driver when submitting work to the different queues.
To implement this feature, the driver "takes" a couple of h/w resources,
and this is reflected by the defines added to the uapi file.
The signal/wait operations are done via the existing CS IOCTL, and they use
the same data structure. There is a difference in the meaning of some of
the parameters, and for that we added unions to make the code more
readable.
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>
PCI drivers should use this define to declare their PCI ID table.
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Make all the CB handles printed in the same way and not some as decimal and
some as hex numbers.
Signed-off-by: Dotan Barak <dbarak@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Update the mapping to the latest one used by the Firmware. No impact on the
driver in this update.
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Set the STMTCSR.COMPEN bit to enable leading-zero trace data
compression functionality for the extended stimulus ports.
Signed-off-by: Adam Aharon <aaharon@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Load CPU device boot loader during driver boot time in order to avoid flash
write for every boot loader update.
To preserve backward-compatibility, skip the device boot load if the device
doesn't request it.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
The user must leave space for 2xMSG_PROT in the external CB, so adjust the
define of max size accordingly. The driver, however, can still create a CB
with the maximum size of 2MB. Therefore, we need to add a check
specifically for the user requested size.
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Align the protection bits configuration of all TPC cores to be as of TPC
core 0.
Fixes: a513f9a7ec ("habanalabs: make tpc registers secured")
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>
Allow user access to TPC LFSR register, as it might be accessed by TPC
kernels.
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>
Add a new opcode to the INFO IOCTL that retrieves the device time
alongside the host time, to allow a user application that want to measure
device time together with host time (such as a profiler) to synchronize
these times.
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>
set function to be static as it is not called from outside its file.
Signed-off-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When we have DMA QMAN with multiple streams, we need to know whether the
command buffer contains at least one DMA packet in order to configure the
barriers correctly when adding the 2xMSG_PROT at the end of the JOB. If
there is no DMA packet, then there is no need to put engine barrier. This
is relevant only for GAUDI as GOYA doesn't have streams so the engine can't
be busy by another stream.
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Retrieve from the firmware the DMA mask value we need to set according to
the device's PCI controller configuration. This is needed when working on
POWER9 machines, as the device's PCI controller is configured in a
different way in those machines.
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Add comments for the various errors and states of the firmware during boot.
Add a mapping of a new register that will tell the driver whether the
firmware executed the request from the driver or if it has encountered an
error.
Add a new enum for the possible values of this register.
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When doing training, the DL framework (e.g. tensorflow) performs hundreds
of thousands of memory allocations and mappings. In case the driver needs
to perform hard-reset during training, the driver kills the application and
unmaps all those memory allocations. Unfortunately, because of that large
amount of mappings, the driver isn't able to do that in the current timeout
(5 seconds). Therefore, increase the timeout significantly to 30 seconds
to avoid situation where the driver resets the device with active mappings,
which sometime can cause a kernel bug.
BTW, it doesn't mean we will spend all the 30 seconds because the reset
thread checks every one second if the unmap operation is done.
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
When the system administrator asks the driver to soft or hard reset the
device through sysfs, the driver should display a warning in the kernel log
to explain why it suddenly resets the device.
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Move the code of device CPU initialization from being ASIC-Dependent to
common code. In addition, add support for the new error reporting feature
of the firmware boot code.
Reviewed-by: Omer Shpigelman <oshpigelman@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
We want to remove the following restrictions/assumptions in our driver:
1. The H/W queue index is also the completion queue index.
2. The H/W queue index is also the IRQ number of the completion queue.
3. All queues of the same type have consecutive indexes.
Therefore we add the support for H/W queues of the same type with
nonconsecutive indexes and completion queue index and IRQ number different
than the H/W queue index.
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>
Stop-on-error mode in DMA is useful as it stops the transaction
immediately upon error e.g. page fault.
But it may cause the next command submission to fail as is leaves the DMA
in unstable state.
Therefore we remove the stop-on-error configuration from the DMA.
Stop-on-err is still available for debug.
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>
