| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Some names of events has been modified/added.
Signed-off-by: Ohad Sharabi <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
We expose this in order for user applications to know how much dram
is reserved for internal use.
Signed-off-by: Ofir Bitton <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Remove all '\n' from strings which are passed as arguments to
gaudi2_print_event(), because the newline character is added internally
in this function.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Now that CQ-completion based jobs do not trigger a reset upon failure,
failure of such jobs (e.g., MMU cache invalidation) should be handled
by the caller itself depending on the error code returned to it.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Since the err_cause register is unprivileged, we should read it from
the driver instead of using the param that came from the FW.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
- remove reset_sleep_ms arg from functions that don't use it.
- move the call msleep(reset_sleep_ms) from btm poll to gaudi2_hw_fini
as it is called from there already for other flow.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
In hw_fini callback, we use either the cpucp packet method or polling a
register. Currently we return error only in the case of cpucp packet
failure. In this patch we also return error if polling timed out.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Due to a firmware bug we need to increase reset poll timeout
or else we will timeout in secured environments.
Signed-off-by: Ofir Bitton <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Engines idle state can't always be verified between changes of
engine modes (e.g., stall/halt).
For example, if a CS is inflight when altering engine's mode,
idle state will return NOT idle, always.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Copy the most up-to-date interface files to the firmware.
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Ofir Bitton <[email protected]>
|
|
There is a spelling mistake in a dev_err message. Fix it.
Signed-off-by: Colin Ian King <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
This function is only called inside gaudi2.c file.
Reported-by: kernel test robot <[email protected]>
Link: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Ofir Bitton <[email protected]>
|
|
The module pointer in class_create() never actually did anything, and it
shouldn't have been requred to be set as a parameter even if it did
something. So just remove it and fix up all callers of the function in
the kernel tree at the same time.
Cc: "Rafael J. Wysocki" <[email protected]>
Acked-by: Benjamin Tissoires <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Greg Kroah-Hartman <[email protected]>
|
|
pci_enable_pcie_error_reporting() enables the device to send ERR_*
Messages. Since
commit f26e58bf6f54 ("PCI/AER: Enable error reporting when AER is native"),
the PCI core does this for all devices during enumeration, so the
driver doesn't need to do it itself.
Remove the redundant pci_enable_pcie_error_reporting() call from the
driver. Also remove the corresponding pci_disable_pcie_error_reporting()
from the driver .remove() path.
Note that this only controls ERR_* Messages from the device. An ERR_*
Message may cause the Root Port to generate an interrupt, depending on the
AER Root Error Command register managed by the AER service driver.
Signed-off-by: Bjorn Helgaas <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
The memory manager IDR is currently destroyed when user releases the
file descriptor.
However, at this point the user context might be still held, and memory
buffers might be still in use.
Later on, calls to release those buffers will fail due to not finding
their handles in the IDR, leading to a memory leak.
To avoid this leak, split the IDR destruction from the memory manager
fini, and postpone it to hpriv_release() when there is no user context
and no buffers are used.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
We plan to do soft-reset either by mmio or by using cpucp packet
depending on the FW version. We don't want to check FW version in two
different places for that (execute soft-reset and wait to soft-reset)
so move the waiting to gaudi2_execute_soft_reset. This also makes sense
because the cpucp also does the waiting.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
The user might want to stall/resume engines to perform power testing
for various scenarios. Because our current
HL_CS_FLAGS_ENGINE_CORE_COMMAND command only handles the engines' cores,
we need to add another opcode for handling entire engine and not just
its core.
The user supplies an array, where each entry holds the engine's ID and
the command to send to the engine. The size of the array is limited
by the number of engines in the ASIC (only Gaudi2 is currently
supported).
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
compose_device_in_use_info() was added to handle the snprintf() return
value in a single place.
However, the buffer size in print_device_in_use_info() is set such that
it would be enough for the max possible print, so
compose_device_in_use_info() is not really needed.
Moreover, scnprintf() can be used instead of snprintf(), to save the
check if the return value larger than the given size.
Cc: Stanislaw Gruszka <[email protected]>
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
print more informative message when failing in dirty state
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
There are two reasons why mutex is better here:
1. There's a critical section relatively long, where in
certain scenarios (e.g., multiple VM allocations) taking a spinlock
might cause noticeable performance degradation.
2. It will remove the incorrect usage of mutex under
spin_lock (where preemption is disabled).
Reported-by: Dan Carpenter <[email protected]>
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
We can allow userspace to query the dram usage during soft-reset.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
The PDMA/EDMA is_idle routines didn't check the correct CORE register
in order to get the accurate idle state.
Moreover, it's better to make the is_idle routine more robust by adding
additional checks (IS_HALTED) before announcing that the core is idle.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Is appears that the flag -
DCORE0_TPC0_CFG_STATUS_VECTOR_PIPE_EMPTY_MASK, has no actual use when
it comes to querying TPC idleness, since this flag's corresponding bit
turns-off after stalling the engine, and turns back on after resuming
it.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Run spell checker on the code and fix accordingly.
Signed-off-by: farah kassabri <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
In case the KDMA fails scrubbing the DCCMs (following a soft-reset
upon device release), the driver will only print failure until reset
flow ends, rather than escalating it into a hard-reset.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Add notifications to user in case of decoder abnormal interrupts, and
use the graceful reset mechanism if reset is required.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Since hw_fini return error code for failure indication, we should
check its return value. Currently it might only fail upon soft-reset
from hl_device_reset. Later patch will add hw_fini failure in case of
polling timeout in hard-reset.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
is_idle() was too long, so break it up for readability.
In addition, we can now use the new sub-routines from other places.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Compute driver threads names will start with hlX-*, when X is the
device id.
This will help distinguish them from the NIC thread names.
Signed-off-by: Sagiv Ozeri <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Add a helper function to search the vm hash for a node with a given
virtual address.
As opposed to the current code, this function explicitly returns NULL
when no node is found, instead of basing on the loop cursor object's
value.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
'irq_handler' in gaudi2_enable_msix(), is just assigned with a function
name and then used when calling request_threaded_irq().
Remove the variable and use the function name directly as an argument.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
We later use cpucp packet for soft reset which might fail
so we should be able propagate the failure case.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
Remove leading zeroes when printing the idle mask to make it clearer.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
Make the comments align with the order of the fields in the structure
Signed-off-by: Sagiv Ozeri <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
smatch reports
drivers/accel/habanalabs/common/device.c:2619:6: warning:
symbol 'hl_capture_hw_err' was not declared. Should it be static?
drivers/accel/habanalabs/common/device.c:2641:6: warning:
symbol 'hl_capture_fw_err' was not declared. Should it be static?
both are only used in device.c, so they should be static
Signed-off-by: Tom Rix <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
Building with clang W=2 has several similar warnings
drivers/accel/habanalabs/common/decoder.c:46:51: error: declaration shadows a variable in the global scope [-Werror,-Wshadow]
static void
dec_error_intr_work(struct hl_device *hdev, u32 base_addr, u32 core_id)
^
drivers/accel/habanalabs/common/security.h:13:26: note: previous declaration is here
extern struct hl_device *hdev;
^
There is no global definition of hdev, so the extern is not needed.
Searched with
grep -r '^struct' . | grep hl_dev
Change to an forward decl to resolve these issues
drivers/accel/habanalabs/common/mmu/../security.h:133:40: error: ‘struct hl_device’ declared inside parameter list will not be visible outside of this definition or declaration [-Werror]
133 | bool (*skip_block_hook)(struct hl_device *hdev,
| ^~~~~~~~~
Signed-off-by: Tom Rix <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
|
|
The cpu accessible dma allocations use the gen_pool api which actually
does not allocate new memory from the system but manages memory already
allocated before. When tracing this together with real dma
allocation/free it cause confusing logs like a '0' dma address and
a cpu address appearing twice etc.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
in the out_err flow, combine the two cases of soft-reset since
they have mostly common code. In addition unlock reset_info.lock
after touching reset count.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
Because this field is only used for debug print,
we can do more precise debug directly instead.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
To match their description above the function
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
Align assignment of reset_upon_device_release to the convention used
in this function.
Signed-off-by: Dafna Hirschfeld <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
hl_irq_handler_default() is not used and can be removed.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
"eq_base[eq->ci].hdr.ctl" is used directly in a print without a
le32_to_cpu() conversion.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
In order to allow TPC engines to raise an assert, we must expose
the relevant MSIX interrupt to the user so he will configure the engine
correctly. In addition, we implement the corresponding interrupt
handler that will notify the user upon such an event.
Signed-off-by: Ofir Bitton <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
In order for interrupt timestamp to be more accurate we should
capture it during the interrupt handling rather than in threaded
irq context.
Signed-off-by: Ofir Bitton <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
We prefer not to handle the user interrupt job inside the interrupt
context. Instead, use threaded IRQ to handle the user interrupts.
This will allow to avoid disabling interrupts when the user process
registers for a new event and to avoid long handling inside an
interrupt.
Signed-off-by: Tal Cohen <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
The policy file of the events reset has been modified.
This change is reflected in the autogenerated file.
Signed-off-by: Ohad Sharabi <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
When getting an event, add the ability to deduce the reset type from
the IRQ map table instead of using hard reset regardless.
Signed-off-by: Ohad Sharabi <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
The graceful reset mechanism is currently enabled only for reset
requests that will end up with hard-reset.
In future, reset requests due to errors in some device engines, are
going to be modified to request compute-reset, as the much longer
hard-reset is not really needed there.
To allow it, enable graceful reset also for compute-reset, and reset
after user releases the device won't be escalated to hard-reset in those
cases.
If watchdog expires and user didn't release the device, hard-reset will
be initiated in any case.
Signed-off-by: Tomer Tayar <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|
|
In case a compute reset has failed or a request for a hard reset has
just arrived, then we escalate current reset procedure from compute
to hard-reset.
In such a case, the FW should be aware of the updated error cause,
and if LKD is the one who performs the reset (rather than the FW),
then we ask the FW to disable PCI access.
We would also like to have relevant debug info and therefore
we print the currently escalating reset type.
Signed-off-by: Koby Elbaz <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
Reviewed-by: Stanislaw Gruszka <[email protected]>
|