- Dec 26, 2021
-
-
Tomer Tayar authored
The reset flags used by the reset thread are currently a mix of hard-coded values and a specific flag which is passed from the context that initiates the reset. To make it easier to pass more flags in future from this context to the reset thread, modify it to pass all the original reset flags to the thread. Signed-off-by:
Tomer Tayar <ttayar@habana.ai> Reviewed-by:
Oded Gabbay <ogabbay@kernel.org> Signed-off-by:
-
Dani Liberman authored
Because info ioctl is used to retrieve data, some of its opcodes may be used during hard reset. Other ioctls should be blocked while device is not operational. Signed-off-by:
Dani Liberman <dliberman@habana.ai> Reviewed-by:
-
Dani Liberman authored
For debug purpose, add SOB address and SOB initial counter value before current submission to uAPI output. Using SOB address and initial counter, user can calculate how much of the submmision has been completed. Signed-off-by:
-
Ohad Sharabi authored
Reporting FW errors involves reading of the error registers. In case we have a corrupted FW descriptor we cannot do that since the dynamic scratchpad is potentially corrupted as well and may cause kernel crush when attempting access to a corrupted register offset. Signed-off-by:
Ohad Sharabi <osharabi@habana.ai> Reviewed-by:
-
Ofir Bitton authored
Driver should handle events during soft-reset as F/W is not going through reset and it keeps sending events towards host. Signed-off-by:
Ofir Bitton <obitton@habana.ai> Reviewed-by:
-
Ofir Bitton authored
Currently we dump the physical IRQ line index in host if an event is received during reset. This ID is confusing as it means nothing to the user. Signed-off-by:
-
Tomer Tayar authored
In new f/w versions, it is required to explicitly indicate the power information type when querying the F/W for power info. When getting the current power level it should be set to power_input. Signed-off-by:
-
Ofir Bitton authored
Some info ioctls can be served even if the device is disabled or in reset. Hence, we enable more info ioctls during reset, as these ioctls do not require any H/W nor F/W communication. Signed-off-by:
-
Dani Liberman authored
Race example scenario: 1. User have 2 threads that waits on multi CS: - thread_0 waits on QID 0 and uses multi CS context 0. - thread_1 waits on QID 1 and uses multi CS context 1. 2. thread_1 got completion and release multi CS context 1. 3. CS related to multi CS of thread_0 starts executing complete_multi_cs function, the first iteration of the loop completes the multi CS of thread_0, hence multi CS context 0 is released. 4. thread_1 waits on QID 1 and uses multi CS context 0. 5. thread_0 waits on QID 0 and uses multi CS context 1. 6. The second iterattion of the loop (from step 3) starts, which means, start checking multi CS context 1: - multi CS contetxt is being used by thread_0 waiting on QID 0. - The fence of the CS (still CS from step 3) has QID map the same as the multi CS context 1. - multi CS context 1 (thread_0) gets completion on CS that triggered already thread_0 (with multi CS context 0) and is no longer being waited on. Fixed by exiting the loop in complete_multi_cs after getting completion Signed-off-by: -
Ofir Bitton authored
As device boot warnings clears the indication from the error mask, they must be located together before the unknown error validation. Signed-off-by:
-
Oded Gabbay authored
GAUDI supports only hard-reset. Therefore, this function should return an error of operation not permitted. Signed-off-by: -
Oded Gabbay authored
The ASIC-specific soft_reset_late_init() is now called after either soft-reset or reset-upon-device-release. Therefore, it needs a more appropriate name. No need to split it to two functions, as an ASIC either supports soft-reset or reset-upon-device-release. Signed-off-by: -
Oded Gabbay authored
Reset upon device release is not a soft-reset from user/system point of view. As such, we shouldn't count that reset in the statistics we gather and expose to the monitoring applications. We also shouldn't print soft-reset when doing the reset upon device release. Signed-off-by: -
Rajaravi Krishna Katta authored
Changing the frequency automatically is only done in Goya. In future ASICs this is done inside the firmware. Therefore, move the common code into the Goya specific files. Main changes as part of the commit are: 1. The thread for setting frequency is moved from device_late_init to goya_late_init 2. hl_device_set_frequency is removed from hl_device_open as it is not relevant for other ASICs and for Goya it is taken care by the thread 3. hl_device_set_frequency is renamed as goya_set_frequency Signed-off-by:Rajaravi Krishna Katta <rkatta@habana.ai> Reviewed-by:
-
Oded Gabbay authored
Hard-reset is mutually exclusive with reset-on-device-release. Therefore, if such a request arrives to the reset function, abort the reset and return an error to the callee. Signed-off-by: -
Ofir Bitton authored
Currently there is a deadlock in driver in scenarios where MMU cache invalidation fails. The issue is basically device reset being performed without releasing the MMU mutex. The solution is to skip device reset as it is not necessary. In addition we introduce a slight code refactor that prints the invalidation error from a single location. Signed-off-by:
-
Ohad Sharabi authored
Getting the used PLL index with which to send the CPUPU packet relies on the CPUCP info packet. In case CPU queues are not enabled getting the PLL index will issue an error and in some ASICs will also fail the driver load. Signed-off-by:
-
Tomer Tayar authored
Move an entry in the debugfs documentation to align with the alphabetical order which is kept this file. Signed-off-by:
-
Oded Gabbay authored
If a device reset has started, there is a chance that the heartbeat function will fail because the device is disabled at the beginning of the reset function. In that case, we don't want the error message to appear in the log. Signed-off-by: -
Dani Liberman authored
A new uAPI is added for debug purposes of the user-space to retrieve errors related data from previous session (before device reset was performed). Inforamtion is filled when a razwi or CS timeout happens and can contain one of the following: 1. Retrieve timestamp of last time the device was opened and razwi or CS timeout happened. 2. Retrieve information about last CS timeout. 3. Retrieve information about last razwi error. This information doesn't contain user data, so no danger of data leakage between users. Signed-off-by:
-
Ofir Bitton authored
AS TPM error indication is not fatal, driver should dump a warning and continue booting. Signed-off-by:
-
Ofir Bitton authored
I2C debugfs support is limited to 1 byte. We extend functionality to more than 1 byte by using one of the pad fields as a length. No backward compatibility issues as new F/W versions will treat 0 length as a 1 byte length transaction. Signed-off-by:
-
Oded Gabbay authored
Divide the code into 3 different parts: - Copy kernel parameters - Setting device behaivor per asic - Fixup of various device parameters according to the device behaivor. In addition, remove non-relevant code for upstream (simulator support). Signed-off-by: -
farah kassabri authored
Add implementation for new opcodes in the INFO IOCTL: 1. Retrieve the replaced DRAM rows from f/w. 2. Retrieve the pending DRAM rows from f/w. Signed-off-by:
farah kassabri <fkassabri@habana.ai> Reviewed-by:
-
Bharat Jauhari authored
Refactor the wait-for-user-interrupt routine to make it more generic for re-use for other user exposed h/w interfaces in future ASICs. Signed-off-by:
Bharat Jauhari <bjauhari@habana.ai> Reviewed-by:
-
farah kassabri authored
In Signaling-From-Graph case, the driver didn't set the hw_sob pointer at the right place, which is needed for the cs completion check prior to start sending all the master/slaves jobs to device. Signed-off-by:
-
Ofir Bitton authored
In addition to the clock throttling reason, user should be able to obtain also the start time and the duration of the throttling event. Signed-off-by:
-
Dani Liberman authored
In order to increase maximum wait-for-interrupt timeout, change it to 64 bit variable. This wait is used only by newer ASICs, so no problem in changing this interface at this time. Signed-off-by:
-
Bharat Jauhari authored
Rename reset flags for better readability as compared to HL_RESET_CAUSE* enum shared with the f/w. Signed-off-by:
-
Rajaravi Krishna Katta authored
CPUCP_PACKET_POWER_GET packet type was used for both hl_get_power() and hl_set_power(). To align with other sensor functions hl_set_power() should use CPUCP_PACKET_POWER_SET. This packet will only be used with newer ASICs, so need to add a compatibility flag to the asic properties to indicate whether to use this packet or the GET packet. Signed-off-by:
-
Bharat Jauhari authored
In case of device reset, the driver does a force trigger on all waiting users to release them from waiting. However, the driver does not handle error scenario while waiting. hl_interrupt_wait_ioctl() now exits the wait in case of an error with abort status. Signed-off-by:
-
Ohad Sharabi authored
Once we read indication of whether f/w is doing the reset, we don't want to clear it, until the next time we read this indication. Otherwise, we might be in a state of wrong indication. Signed-off-by:
-
Ohad Sharabi authored
Using a variable poll interval for fw loading allows us to support much slower environments (emulation) while changing only a single line in the code, instead of choosing a different interval in each function that polls. Signed-off-by:
-
Ohad Sharabi authored
Up until now the driver stored indication if Linux was loaded on the device CPU. This was needed in order to coordinate some tasks that are performed by the Linux. In future ASICs, many of those tasks will be performed by the boot fit, so now we need the same indication of boot fit load status. Signed-off-by:
-
Yuri Nudelman authored
The PCI MMU cache is two layered. The upper layer, memcache, uses cache lines, the bottom layer doesn't. Hence, after PMMU map operation we have to invalidate memcache, to avoid the situation where the new entry is already in the cache due to its cache line being fully in the cache. However, we do not have to invalidate the lower cache, and here we can optimize, since cache invalidation is time consuming. Signed-off-by:
Yuri Nudelman <ynudelman@habana.ai> Reviewed-by:
-
Yuri Nudelman authored
The enum vm_type was abused, used once as a value (indication memory type for map) and once as a flag (for cache invalidation). This makes it hard to add new and still keep it meaningful, hence it is better to split into one enum for values and one for flags. Signed-off-by:
-
Yuri Nudelman authored
Currently LAST_MASK is a global, but really it is an MMU implementation specific. We need this change for future ASICs. Signed-off-by:
-
Yuri Nudelman authored
VA blocks are currently stored in an inconsistent way. Sometimes block end is inclusive, sometimes exclusive. This leads to wrong size calculations in certain cases, plus could lead to a segmentation fault in case mapping process fails in the middle and we try to roll it back. Need to make this consistent - start inclusive till end inclusive. For example, the regions table may now look like this: 0x0000 - 0x1fff : allocated 0x2000 - 0x2fff : free 0x3000 - 0x3fff : allocated Signed-off-by: -
Guy Zadicario authored
Do not use a dma channel for debugfs requested transfer if it's QM is not idle. Signed-off-by:
Guy Zadicario <gzadicario@habana.ai> Reviewed-by:
-
Ohad Sharabi authored
The boot status flag "SRAM available" can be set by f/w Linux (in the general case) or by f/w uboot (in some specific debug scenario) but never by f/w preboot. Hence, when polling the boot status flags in the preboot stage we do not want to poll on "SRAM Avialable". The special case in which uboot set this flag is when we are running special debug scenario without Linux. In this case, at some point during the boot, the uboot relocates its code to the DRAM and then set the specified flag. Signed-off-by:
-
