summaryrefslogtreecommitdiff
path: root/drivers
AgeCommit message (Collapse)Author
2021-12-26hwmon: (jc42) Add support for ONSEMI N34TS04Guenter Roeck
N34TS04 is a JC42.4 compatible temperature sensor from ONSEMI. Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (k10temp) Support up to 12 CCDs on AMD Family of processorsBabu Moger
The current driver can read the temperatures from upto 8 CCDs (Core-Complex Die). The newer AMD Family 19h Models 10h-1Fh and A0h-AFh can support up to 12 CCDs. Update the driver to read up to 12 CCDs. Signed-off-by: Babu Moger <babu.moger@amd.com> Link: https://lore.kernel.org/r/163776976762.904164.5618896687524494215.stgit@bmoger-ubuntu Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (asus_wmi_sensors) Support X370 Asus WMI.Denis Pauk
Provides a Linux kernel module "asus_wmi_sensors" that provides sensor readouts via ASUS' WMI interface present in the UEFI of X370/X470/B450/X399 Ryzen motherboards. Supported motherboards: * ROG CROSSHAIR VI HERO, * PRIME X399-A, * PRIME X470-PRO, * ROG CROSSHAIR VI EXTREME, * ROG CROSSHAIR VI HERO (WI-FI AC), * ROG CROSSHAIR VII HERO, * ROG CROSSHAIR VII HERO (WI-FI), * ROG STRIX B450-E GAMING, * ROG STRIX B450-F GAMING, * ROG STRIX B450-I GAMING, * ROG STRIX X399-E GAMING, * ROG STRIX X470-F GAMING, * ROG STRIX X470-I GAMING, * ROG ZENITH EXTREME, * ROG ZENITH EXTREME ALPHA. Co-developed-by: Ed Brindley <kernel@maidavale.org> Signed-off-by: Ed Brindley <kernel@maidavale.org> Signed-off-by: Denis Pauk <pauk.denis@gmail.com> [groeck: Squashed: "hwmon: Fix warnings in asus_wmi_sensors.rst documetation."] Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (asus_wmi_ec_sensors) Support B550 Asus WMI.Denis Pauk
Linux HWMON sensors driver for ASUS motherboards to read sensors from the embedded controller. Many ASUS motherboards do not publish all the available sensors via the Super I/O chip but the missing ones are available through the embedded controller (EC) registers. This driver implements reading those sensor data via the WMI method BREC, which is known to be present in all ASUS motherboards based on the AMD 500 series chipsets (and probably is available in other models too). The driver needs to know exact register addresses for the sensors and thus support for each motherboard has to be added explicitly. The EC registers do not provide critical values for the sensors and as such they are not published to the HWMON. Supported motherboards: * PRIME X570-PRO * Pro WS X570-ACE * ROG CROSSHAIR VIII HERO * ROG CROSSHAIR VIII DARK HERO * ROG CROSSHAIR VIII FORMULA * ROG STRIX X570-E GAMING * ROG STRIX B550-I GAMING * ROG STRIX B550-E GAMING Co-developed-by: Eugene Shalygin <eugene.shalygin@gmail.com> Signed-off-by: Eugene Shalygin <eugene.shalygin@gmail.com> Co-developed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by: Denis Pauk <pauk.denis@gmail.com> Tested-by: Tor Vic <torvic9@mailbox.org> Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name> Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (f71882fg) Add F81966 supportMenghui Wu
This adds hardware monitor support the Fintek F81966 Super I/O chip. Testing was done on the Aaeon SSE-IPTI Signed-off-by: Menghui Wu <Menghui_Wu@aaeon.com.tw> Signed-off-by: Chia-Lin Kao (AceLan) <acelan.kao@canonical.com> Link: https://lore.kernel.org/r/20211117024320.2428144-1-acelan.kao@canonical.com Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (adm1021) Improve detection of LM84, MAX1617, and MAX1617AGuenter Roeck
The adm1021 driver is quite generous with its automatic chip detection and easily misdetects several chips. Strengthen detection of MAX1617, MAX1617A, and LM84 to make the driver less vulnerable to false matches. Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (tmp401) Hide register write address differences in regmap codeGuenter Roeck
Since we are using regmap access functions to write into chip registers, we can hide the difference in register write addresses within regmap code. By doing this we do not need to clear the regmap cache on register writes, and the high level code does not need to bother about different read/write register addresses. Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (tmp401) Use regmapGuenter Roeck
Use regmap for register accesses to be able to utilize its caching functionality. This also lets us hide register access differences in regmap code. Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (tmp401) Convert to _info APIGuenter Roeck
The new API is cleaner and reduces code size significantly. All chip accesses are 'hidden' in chip access to prepare for using regmap. Local caching code is removed, to be replaced by regmap based caching in a follow-up patch. Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (tmp401) Simplify temperature register arraysGuenter Roeck
The difference between TMP431 and other chips of this series is that the TMP431 has an additional sensor. The register addresses for other sensors are the same for all chips. It is therefore unnecessary to maintain two different arrays for TMP431 and the other chips. Just use the same array for all chips and add the TMP431 register addresses as third column. Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: Driver for Texas Instruments INA238Nathan Rossi
The INA238 is a I2C power monitor similar to other INA2xx devices, providing shunt voltage, bus voltage, current, power and temperature measurements. Signed-off-by: Nathan Rossi <nathan.rossi@digi.com> Link: https://lore.kernel.org/r/20211102052754.817220-3-nathan@nathanrossi.com Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (k10temp) Add support for AMD Family 19h Models 10h-1Fh and A0h-AFhBabu Moger
Add thermal info support for AMD Family 19h Models 10h-1Fh and A0h-AFh. Thermal info is supported via a new PCI device ID at offset 0x300h. Signed-off-by: Babu Moger <babu.moger@amd.com> Link: https://lore.kernel.org/r/163640829419.955062.12539219969781039915.stgit@bmoger-ubuntu Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26hwmon: (k10temp) Remove unused definitionsBabu Moger
Usage of these definitions were removed after the commit 0a4e668b5d52 ("hwmon: (k10temp) Remove support for displaying voltage and current on Zen CPUs"). So, cleanup them up. Signed-off-by: Babu Moger <babu.moger@amd.com> Link: https://lore.kernel.org/r/163640828776.955062.15863375803675701204.stgit@bmoger-ubuntu Signed-off-by: Guenter Roeck <linux@roeck-us.net>
2021-12-26habanalabs: support hard-reset scheduling during soft-resetOfir Bitton
As hard-reset can be requested during soft-reset, driver must allow it or else critical events received during soft-reset will be ignored. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add a lock to protect multiple reset variablesOfir Bitton
Atomic operations during reset are replaced by a spinlock in order to have the ability to protect more than a single variable. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: refactor reset information variablesOfir Bitton
Unify variables related to device reset, which will help us to add some new reset functionality in future patches. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: handle skip multi-CS if handling not doneOhad Sharabi
This patch fixes issue in which we have timeout for multi-CS although the CS in the list actually completed. Example scenario (the two threads marked as WAIT for the thread that handles the wait_for_multi_cs and CMPL as the thread that signal completion for both CS and multi-CS): 1. Submit CS with sequence X 2. [WAIT]: call wait_for_multi_cs with single CS X 3. [CMPL]: CS X do invoke complete_all for both CS and multi-CS (multi_cs_completion_done still false) 4. [WAIT]: enter poll_fences, reinit the completion and find the CS as completed when asking on the fence but multi_cs_done is still false it returns that no CS actually completed 5. [CMPL]: set multi_cs_handling_done as true 6. [WAIT]: wait for completion but no CS to awake the wait context and hence wait till timeout Solution: if CS detected as completed in poll_fences but multi_cs_done is still false invoke complete_all to the multi-CS completion and so it will not go to sleep in wait_for_completion but rather will have a "second chance" to wait for multi_cs_completion_done. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add CPU-CP packet for engine core ASID cfgTomer Tayar
In some cases the driver cannot configure ASID of some engines due to the security level of the relevant registers. For this a new CPU-CP packet is introduced, which will allow the driver to ask the F/W to do this configuration instead. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26PCI: imx: Add the imx8mm pcie supportRichard Zhu
i.MX8MM PCIe works mostly like the i.MX8MQ one, but has a different PHY and allows to output the internal PHY reference clock via the refclk pad. Add the i.MX8MM PCIe support based on the standalone PHY driver. Link: https://lore.kernel.org/r/1640312885-31142-2-git-send-email-hongxing.zhu@nxp.com Tested-by: Marcel Ziswiler <marcel.ziswiler@toradex.com> Tested-by: Tim Harvey <tharvey@gateworks.com> Signed-off-by: Richard Zhu <hongxing.zhu@nxp.com> Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Reviewed-by: Tim Harvey <tharvey@gateworks.com>
2021-12-26habanalabs: replace some -ENOTTY with -EINVALOded Gabbay
-ENOTTY is returned in case of error in the ioctl arguments themselves, such as function that doesn't exists. In all other cases, where the error is in the arguments of the custom data structures that we define that are passed in the various ioctls, we need to return -EINVAL. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: fix comments according to kernel-docOfir Bitton
Fix missing fields, descriptions not according to kernel-doc style. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: fix endianness when reading cpld versionOfir Bitton
Current sysfs implementation does not take endianness into consideration when dumping the cpld version. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: change wait_for_interrupt implementationfarah kassabri
Currently the cq counters are allocated in userspace memory, and mapped by the driver to the device address space. A new requirement that is part of new future API related to this one, requires that cq counters will be allocated in kernel memory. We leverage the existing cb_create API with KERNEL_MAPPED flag set to allocate this memory. That way we gain two things: 1. The memory cannot be freed while in use since it's protected by refcount in driver. 2. No need to wake up the user thread upon each interrupt from CQ, because the kernel has direct access to the counter. Therefore, it can make comparison with the target value in the interrupt handler and wake up the user thread only if the counter reaches the target value. This is instead of waking the thread up to copy counter value from user then go sleep again if target value wasn't reached. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: prevent wait if CS in multi-CS list completedOhad Sharabi
By the original design we assumed that if we "miss" multi CS completion it is of no severe consequence as we'll just call wait_for_multi_cs again. Sequence of events for such scenario: 1. user submit CS with sequence N 2. user calls wait for multi-CS with only CS #N in the list 3. the multi CS call starts with poll of the CSs but find that none completed (while CS #N did not completed yet) 4. now, multi CS #N complete but multi CS CTX was not yet created for the above multi-CS. so, attempt to complete multi-CS fails (as no multi CS CTX exist) 5. wait_for_multi_cs call now does init_wait_multi_cs_completion (and for this create the multi-CS CTX) 6. wait_for_multi_cs wits on completion but will not get one as CS #N already completed To fix the issue we initialize the multi-CS CTX prior polling the fences. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: modify cpu boot status error printOfir Bitton
As BTL can be replaced by ROM we should modify relevant error print. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: clean MMU headers definitionsOhad Sharabi
During the MMU development the MMU header files were left with unclean definitions: - MMU "version specific" definitions that were left in the mmu_general file - unused definitions This patch attempts, where possible, to keep definitions that can serve multiple MMU versions (but that are not tightly bound with specific MMU arch) in the mmu_general header file (e.g. different definitions for number of HOPs). Otherwise, move MMU version specific definitions (e.g. HOPs masks and shifts) to the specific MMU version file. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: expose soft reset sysfs nodes for inference ASICOfir Bitton
As we allow soft-reset to be performed only on inference devices, having the sysfs nodes may cause a confusion. Hence, we remove those nodes on training ASICs. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: sysfs support for two infineon versionsOfir Bitton
Currently sysfs support dumping a single infineon version, in future asics we will have two infineon versions. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: keep control device alive during hard resetDani Liberman
Need to allow user retrieve data during reset and afterwards without the need to reopen the device. Did it by seperating the user peocesses list into two lists: 1. fpriv_list which contains list of user processes that opened the device (currently only one). 2. fpriv_ctrl_list which contains list of user processes that opened the control device. This processes in this list shall not be killed during reset, only when the device is suddenly removed from PCI chain. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: fix hwmon handling for legacy f/wOded Gabbay
In legacy f/w that use old hwmon.h file, the values of the hwmon enums are different than the values that are in newer kernels (5.6 and above). Therefore, to support working with those f/w, we need to do some fixup before registering with the hwmon subsystem and also when calling the functions that communicate with the f/w to retrieve sensors information. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add current PI value to cpu packetsOfir Bitton
In order to increase cpucp messaging reliability we will add the current PI value to the descriptor sent to F/W. F/W will wait for the PI value as an indication of a valid packet. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: remove in_debug check in device openOded Gabbay
The driver supports only a single user anyway, so there is no point in checking whether we are in_debug state when a user tries to open the device, because if we are in_debug, it means a user is already using the device. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: return correct clock throttling periodOfir Bitton
Current clock throttling period returned from driver was wrong due to wrong time comparison. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: wait again for multi-CS if no CS completedOhad Sharabi
The original multi-CS design assumption that stream masters are used exclusively (i.e. multi-CS with set of stream master QIDs will not get completed by CS not from the multi-CS set) is inaccurate. Thus multi-CS behavior is now modified not to treat such case as an error. Instead, if we have multi-CS completion but we detect that no CS from the list is actually completed we will do another multi-CS wait (with modified timeout). Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: remove compute context pointerOded Gabbay
It was an error to save the compute context's pointer in the device structure, as it allowed its use without proper ref-cnt. Change the variable to a flag that only indicates whether there is an active compute context. Code that needs the pointer will now be forced to use proper internal APIs to get the pointer. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add helper to get compute contextOded Gabbay
There are multiple places where the code needs to get the context's pointer and increment its ref cnt. This is the proper way instead of using the compute context pointer in the device structure. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: fix etr asid configurationOded Gabbay
Pass the user's context pointer into the etr configuration function to extract its ASID. Using the compute_ctx pointer is an error as it is just an indication of whether a user has opened the compute device. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: save ctx inside encaps signalOded Gabbay
Compute context pointer in hdev shouldn't be used for fetching the context's pointer. If an object needs the context's pointer, it should get it while incrementing its kref, and when the object is released, put it. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: remove redundant check on ctx_finiOded Gabbay
The driver supports only a single context. Therefore, no need to check if the user context that is closed is the compute context. The user context, if exists, is always the compute context. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: free signal handle on failureOded Gabbay
Fix a bug where in case of failure to allocate idr, the handle's memory wasn't freed as part of the error handling code. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add missing kernel-doc comments for hl_device fieldsTomer Tayar
Add missing kernel-doc comments for the "last_error" and "stream_master_qid_arr" fields of the "hl_device" structure". Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: pass reset flags to reset threadTomer Tayar
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: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: enable access to info ioctl during hard resetDani Liberman
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: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add SOB information to signal submission uAPIDani Liberman
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: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: skip read fw errors if dynamic descriptor invalidOhad Sharabi
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: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: handle events during soft-resetOfir Bitton
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: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: change misleading IRQ warning during resetOfir Bitton
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: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add power information type to POWER_GET packetTomer Tayar
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: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: add more info ioctls support during resetOfir Bitton
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: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-12-26habanalabs: fix race condition in multi CS completionDani Liberman
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: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
generated by cgit (git 2.34.1) at 2025-09-30 12:15:01 +0000