summaryrefslogtreecommitdiff
path: root/drivers/misc/habanalabs/common
AgeCommit message (Collapse)AuthorFilesLines
2021-06-18habanalabs: set memory scrubbing to disabled by defaultOded Gabbay1-2/+2
Scrubbing memory after every unmap is very costly in terms of performance. If a user wants it he can enable it but the default should prioritize performance. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs/gaudi: read GIC sts after FW is loadedKoby Elbaz1-7/+9
Reading of GIC privileged status will be done after F/W is loaded, because privileged GIC capability is only available with the correct ARMCP version, and after it's loaded. Such versions necessarily support COMMS, so GIC alternatives (SP regs) will be read directly from dynamic regs. As well, initiation of DMA QMANs will occur after F/W is loaded since it depends on GIC configuration. In case F/W isn't loaded there's no problem since either way there won't be any GIC IRQ handling. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: check if asic secured with asic typeOhad Sharabi1-1/+1
Fix issue in which the input to the function is_asic_secured was device PCI_IDS number instead of the asic_type enumeration. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs/gaudi: send hard reset cause to prebootKoby Elbaz5-5/+151
LKD should provide hard reset cause to preboot prior to loading any FW components (in case needed). Current implementation is based on the new FW 'COMMS' protocol In cased 'COMMS' is disabled - reset cause won't be sent. Currently, only 2 reset causes are shared: HEARTBEAT & TDR. Sending the reset cause will provide the missing watchdog info that the firmware needs to provide to the BMC. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: notify before f/w loadingOded Gabbay1-0/+3
An information print notifying on starting to load the f/w was removed by mistake when moving to the new dynamic f/w loading mechanism. Restore that print as the F/W loading usually takes between 10 to 20 seconds and this print helps the user know the status of the driver load. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs/gaudi: use scratchpad regs instead of GIC controllerKoby Elbaz2-0/+10
Due to new security restrictions, GIC controller can no longer be accessed from user/kernel. To monitor that, a new status bit will be read from preboot caps, indicating whether direct access to GIC is blocked. In case it is blocked, driver will use scratchpad registers instead of using GIC interface on two main scenarios: The first of which LKD triggers interrupts to F/W through GIC, and the second of when LKD configures all engines/QMANs to write to GIC when they want to report an error. From F/W perspective, it will poll on all SPs, and once IRQ number is retrieved, SP register is cleared, and it will perform the write to the GIC to trigger the IRQ handler. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: read f/w's 2-nd sts and err registersOhad Sharabi2-109/+248
Maintain both STS1 and ERR1 registers used for status communication with F/W. Those are not maintained as we currently have less than 31 statuses/error defined and so LKD did not refer to those register. The reason to read them now is to try to support future f/w versions with current driver. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: avoid using uninitialized pointerOhad Sharabi1-0/+1
When attempting to read FW component's version we should break if input FW component is invalid in order to avoid using uninitialized destination pointer. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: set dma mask from fw once fw done iatu configOhad Sharabi1-4/+6
When setting "DMA mask from FW" we are reading PSOC_GLOBAL_CONF register which is allowed only once FW has done it's iATU configuration. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: better error print for pin failureOded Gabbay1-1/+2
Print the user given pointer and error code on failure to get user pages for easier debugging. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: add missing space after castingOmer Shpigelman1-1/+1
Change casting code according to kernel coding style. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: ignore device unusable statusOded Gabbay1-3/+3
Some users might want to implement their own policy of when the device is unusable so we need to ignore this status in the driver and continue loading as normal. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: load linux image to deviceOhad Sharabi2-81/+234
Implementing dynamic linux image load to the device. This patch also implements the FW communication steps during the boot-fit. This patch also enables the dynamic protocol based on the compatibility flag. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: load boot fit to deviceOhad Sharabi2-65/+573
Implementing dynamic boot fit image load to the device. Note that some necessary adjustment were added to the static loader as well so that both loaders can co-exist. as this is not the final FW load stage the dynamic FW load is still forced to be non functional. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: use dev_dbg upon hint address failureOded Gabbay1-2/+4
Hint address failure that results in a valid mapping with an address that was allocated by the driver is not a real failure. Therefore, the driver shouldn't notify about this in kernel log. The user is responsible to check the returned address. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: modify progress status messagesGuy Nisan1-10/+10
Indicate "progress" instead of "error" when reporting progress status. Change "u-boot stopped by user" to "Cannot boot" message as CPU_BOOT_STATUS_UBOOT_NOT_READY may indicate a fatal error that prevent u-boot from loading firmware. Signed-off-by: Guy Nisan <gnisan@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: give FW a grace time for configuring iATUOfir Bitton1-0/+4
iATU (internal Address Translation Unit of the PCI controller) configuration is being done by FW right after driver enables the PCI device. Hence, driver must add a minor sleep afterwards in order to make sure FW finishes configuring iATU regions. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: update to latest f/w headersOded Gabbay2-4/+5
Update the common and GAUDI firmware header files to the latest version. The latest version use the correct endianness types so this commit also contains minor changes to the code to use the correct conversions when reading/writing to the firmware structures. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: expose ASIC specific PCI info to common codeOhad Sharabi2-0/+54
LKD has interfaces in which it receives device address. For instance the debugfs_read/write variants receives device address for CFG/SRAM/DRAM for read/write and need to translate to the mapped PCI BAR address. In addition, the dynamic FW load protocol dictates that the address to which the LKD will copy the image for the next FW component will be received as a device address and can be placed either in SRAM or DRAM. We need to distinguish those regions as the access methods to those regions are different (in DRAM we possibly need to set the BAR base). Looking forward this code will be used to remove duplicated code in the debugfs_read/write that search the memory region for the input device address. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: dynamic fw load reset protocolOhad Sharabi2-24/+304
First stage of the dynamic FW load protocol is to reset the protocol to avoid residues from former load cycles. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: use common fw_version readOhad Sharabi2-10/+62
Instead of using multiple ASIC specific copies of functions to read the FW version use single common one that gets ASIC specific arguments. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: use mmu cache range invalidationAlon Mizrahi2-4/+6
Use mmu cache range invalidation instead of entire cache invalidation because it yields better performance. In GOYA and GAUDI, always use entire cache invalidation because these ASICs don't support range invalidation. Signed-off-by: Alon Mizrahi <amizrahi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: refactor init device cpu codeOhad Sharabi2-14/+48
Replace multiple arguments to init device CPU function by passing firmware loader managing structure that is initialized per ASIC with the loader parameters. In addition, the FW loader management structure is now part of the habanalabs device, this way the loader parameters will be able to be communicated across various boot stages. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: request f/w in separate functionOhad Sharabi1-21/+44
This refactor is needed due to the dynamic FW load in which requesting the FW file (and getting its attributes) is not immediately followed by copying FW file content. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: prepare preboot stage to dynamic f/w loadOhad Sharabi2-15/+71
Start the skeleton for the dynamic F/W load by marking current preboot code path as legacy. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-06-18habanalabs: increase ELBI reset timeout for PLDMMoti Haimovski1-1/+1
On PLDM, in case of NIC hangs, the ELBI reset to take much longer than expected. As a result an increase in the ELBI reset timeout is required. Signed-off-by: Moti Haimovski <mhaimovski@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-05-08habanalabs: wait for interrupt wrong timeout calculationOfir Bitton1-1/+1
Wait for interrupt timeout calculation is wrong, hence timeout occurs when user waits on an interrupt with certain timeout values. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-05-08habanalabs: ignore f/w status errorOded Gabbay3-1/+16
In case firmware has a bug and erroneously reports a status error (e.g. device unusable) during boot, allow the user to tell the driver to continue the boot regardless of the error status. This will be done via kernel parameter which exposes a mask. The user that loads the driver can decide exactly which status error to ignore and which to take into account. The bitmask is according to defines in hl_boot_if.h Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-05-08habanalabs: change error level of security not readyOded Gabbay1-5/+2
This error indicates a problem in the security initialization inside the f/w so we need to stop the device loading because it won't be usable. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-05-08habanalabs: skip reading f/w errors on bad statusOded Gabbay1-2/+7
If we read all FF from the boot status register, then something is totally wrong and there is no point of reading specific errors. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-05-08habanalabs: expose ASIC specific PLL indexBharat Jauhari3-24/+30
Currently the user cannot interpret the PLL information based on index as its exposed as an integer. This commit exposes ASIC specific PLL indexes and maps it to a generic FW compatible index. Signed-off-by: Bharat Jauhari <bjauhari@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: print f/w boot unknown errorOded Gabbay1-16/+68
We need to print a message to the kernel log in case we encounter an unknown error in the f/w boot to help the user understand what happened. In addition, we shouldn't print unknown error in case of known errors. Moreover, in case of warnings/info, we shouldn't return -EIO that will fail the initialization and mark the device as disabled Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs/gaudi: skip iATU if F/W security is enabledOfir Bitton2-0/+55
As part of the securing GAUDI, the F/W will configure the PCI iATU regions. If the driver identifies a secured PCI ID, it will know to skip iATU configuration in a very early stage. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs/gaudi: derive security status from pci idOfir Bitton6-4/+35
As F/ security indication must be available before driver approaches PCI bus, F/W security should be derived from PCI id rather than be fetched during boot handshake with 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>
2021-04-09habanalabs: move dram scrub to free sequenceBharat Jauhari1-39/+48
DRAM scrubbing can take time hence it adds to latency during allocation. To minimize latency during initialization, scrubbing is moved to release call. In case scrubbing fails it means the device is in a bad state, hence HARD reset is initiated. Signed-off-by: Bharat Jauhari <bjauhari@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: send dynamic msi-x indexes to f/wOhad Sharabi2-0/+71
In order to minimize hard coded values between F/W and the driver, we send msi-x indexes dynamically to the F/W. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: support DEVICE_UNUSABLE error indication from FWKoby Elbaz1-0/+3
In case of multiple ECC errors, FW will set the DEVICE_UNUSABLE bit. On boot-up, the driver will therefore fail inserting the device. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: use strscpy instead of sprintf and strlcpyOded Gabbay1-2/+2
Prefer the use of strscpy when copying the ASIC name into a char array, to prevent accidentally exceeding the array's length. In addition, strlcpy is frowned upon so replace it. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs/gaudi: add debugfs to DMA from the deviceOded Gabbay2-5/+131
When trying to debug program, the user often needs to dump large parts of the device's DRAM, which can reach to tens of GBs. Because reading from the device's internal memory through the PCI BAR is extremely slow, the debug can take hours. Instead, we can provide the user to copy data through one of the DMA engines. This will make the operation much faster. Currently, only GAUDI is supported. In GAUDI, we need to find a PCI DMA engine that is IDLE and set the DMA as secured to be able to bypass our MMU as we currently don't map the temporary buffer to the MMU. Example bash one-line to dump entire HBM to file (~2 minutes): for (( i=0x0; i < 0x800000000; i+=0x8000000 )); do \ printf '0x%x\n' $i | sudo tee /sys/kernel/debug/habanalabs/hl0/addr ; \ echo 0x8000000 | sudo tee /sys/kernel/debug/habanalabs/hl0/dma_size ; \ sudo cat /sys/kernel/debug/habanalabs/hl0/data_dma >> hbm.txt ; done Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: add custom timeout flag per csAlon Mizrahi3-16/+23
There is a need to allow to user to send command submissions with custom timeout as some CS take longer than the max timeout that is used by default. Signed-off-by: Alon Mizrahi <amizrahi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: improve utilization calculationKoby Elbaz5-164/+19
The new approach is based on the notion that the relative current power consumption is in relation of proportionality to device's true utilization. Utilization info ranges between [0,100]% Currently, dc_power values are hard-coded. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: support legacy and new pll indexesOhad Sharabi3-11/+76
In order to use minimum of hard coded values common to LKD and F/W a dynamic method to work with PLLs is introduced in this patch. Formerly asic specific PLL numbering is now common for all asics. To be backward compatible a bit in dev status is defined, if the bit is not set LKD will keep working with old PLL numbering. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: move relevant datapath work outside cs lockOfir Bitton3-35/+68
In order to shorten the time cs lock is being held, we move any possible work outside of the cs lock. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: avoid soft lockup bug upon mapping errorfarah kassabri1-3/+17
Add a little sleep between page unmappings in case mapping of large number of host pages failed, in order to avoid soft lockup bug during the rollback. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: debugfs access to user mapped host addressesOfir Bitton3-25/+76
In order to have a better debuggability we allow debugfs access to user mmu mapped host memory. Non-user host memory access will be rejected. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: Switch to using the new API kobj_to_dev()Yang Li1-1/+1
fixed the following coccicheck: ./drivers/misc/habanalabs/common/sysfs.c:347:60-61: WARNING opportunity for kobj_to_dev() Reported-by: Abaci Robot <abaci@linux.alibaba.com> Signed-off-by: Yang Li <yang.lee@linux.alibaba.com> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: skip DISABLE PCI packet to FW on heartbeatOhad Sharabi5-17/+38
if reset is due to heartbeat, device CPU is no responsive in which case no point sending PCI disable message to it. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: replace GFP_ATOMIC with GFP_KERNELOfir Bitton4-12/+34
As there are incorrect assumptions in which some of the initialization and data path flows cannot sleep, most allocations are being done using GFP_ATOMIC. We modify the code to use GFP_ATOMIC only when realy needed, as sleepable flow should use GFP_KERNEL. In addition add a fallback to allocate memory using GFP_KERNEL, once ATOMIC allocation fails. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: return current power via INFO IOCTLSagiv Ozeri3-0/+46
Add driver implementation for reading the current power from the device CPU F/W. Signed-off-by: Sagiv Ozeri <sozeri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-04-09habanalabs: support HW blocks vm showSagiv Ozeri4-7/+112
Improve "vm" debugfs node to print also the virtual addresses which are currently mapped to HW blocks in the device. Signed-off-by: Sagiv Ozeri <sozeri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
generated by cgit v1.2.3 (git 2.39.0) at 2025-09-30 11:32:28 +0300