summaryrefslogtreecommitdiffstats
path: root/drivers/misc
AgeCommit message (Collapse)AuthorFilesLines
2022-11-23misc: ocxl: fix possible name leak in ocxl_file_register_afu()Yang Yingliang1-2/+5
If device_register() returns error in ocxl_file_register_afu(), the name allocated by dev_set_name() need be freed. As comment of device_register() says, it should use put_device() to give up the reference in the error path. So fix this by calling put_device(), then the name can be freed in kobject_cleanup(), and info is freed in info_release(). Fixes: 75ca758adbaf ("ocxl: Create a clear delineation between ocxl backend & frontend") Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> Acked-by: Andrew Donnellan <ajd@linux.ibm.com> Acked-by: Frederic Barrat <fbarrat@linux.ibm.com> Link: https://lore.kernel.org/r/20221111145929.2429271-1-yangyingliang@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-11-23mei: bus-fixup: change pxp mode only if message was sentAlexander Usyskin1-3/+4
Move PXP mode state machine to SETUP mode only if memory ready message sent successfully to the firmware. Leave it in INIT mode otherwise to allow try to send message later. Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com> Link: https://lore.kernel.org/r/20221116124735.2493847-3-alexander.usyskin@intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-11-23mei: add timeout to sendAlexander Usyskin6-9/+46
When driver wakes up the firmware from the low power state, it is sending a memory ready message. The send is done via synchronous/blocking function to ensure that firmware is in ready state. However, in case of firmware undergoing reset send might be block forever. To address this issue a timeout is added to blocking write command on the internal bus. Introduce the __mei_cl_send_timeout function to use instead of __mei_cl_send in cases where timeout is required. The mei_cl_write has only two callers and there is no need to split it into two functions. Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com> Link: https://lore.kernel.org/r/20221116124735.2493847-2-alexander.usyskin@intel.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2022-11-23habanalabs: fix VA range calculationOhad Sharabi1-8/+4
Current implementation is fixing the page size to PAGE_SIZE whereas the input page size may be different. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fail driver load if EEPROM errors detectedOfir Bitton1-12/+11
In case EEPROM is not burned, firmware sets default EEPROM values. As this is not valid in production, driver should fail load upon any EEPROM error reported by firmware. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: make print of engines idle mask more readableTomer Tayar1-6/+21
The engines idle mask was increased to be an array of 4 u64 entries. To make the print of this mask more readable, remove the "0x" prefix, and zero-pad each u64 to 16 bytes if either it isn't zero or if any of the higher-order u64's is not zero. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: clear non-released encapsulated signalsTomer Tayar3-31/+71
Reserved encapsulated signals which were not released hold the context refcount, leading to a failure when killing the user process on device reset or device fini. Add the release of these left signals in the CS roll-back process. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: don't put context in hl_encaps_handle_do_release_sob()Tomer Tayar1-1/+0
hl_encaps_handle_do_release_sob() can be called only when the last reference to the context object is released and hl_ctx_do_release() is initiated, and therefore it shouldn't call hl_ctx_put(). Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: print context refcount value if hard reset failsTomer Tayar1-3/+15
Failing to kill a user process during a hard reset can be due to a reference to the user context which isn't released. To make it easier to understand if this the reason for the failure and not something else, add a print of the context refcount value. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: add RMWREG32_SHIFTED to set a val within a maskDafna Hirschfeld2-10/+6
This is similar to RMWREG32, but the given 'val' is already shifted according to the mask. This allows several 'ORed' vals and masks to be set at once The patch also fixes wrong usage of RMWREG32 by replacing it with RMWREG32_SHIFTED Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fix rc when new CPUCP opcodes are not supportedTomer Tayar1-0/+1
When the new CPUCP opcodes are not supported and a CPUCP packet fails, the return value is the F/W error resposone which is a positive value. If this packet is sent from IOCTL and the positive value is used, the ICOTL will not be considered as unsuccessful. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: added memset for the cq_size registerMarco Pagani1-0/+1
The clang-analyzer reported a warning: "Value stored to 'cq_size_addr' is never read". The cq_size register of dcore0 is not being zeroed using gaudi2_memset_device_lbw(), along with the other cq_* registers, even though the corresponding cq_size_addr variable is set. Signed-off-by: Marco Pagani <marpagan@redhat.com> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: added return value check for hl_fw_dynamic_send_clear_cmd()Marco Pagani1-0/+2
The clang-analyzer reported a warning: "Value stored to 'rc' is never read". The return value check for the first hl_fw_dynamic_send_clear_cmd() call in hl_fw_dynamic_send_protocol_cmd() appears to be missing. Signed-off-by: Marco Pagani <marpagan@redhat.com> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: increase the size of busy engines maskTomer Tayar1-4/+5
Increase the size of the busy engines mask in 'struct hl_info_hw_idle', for future ASICs with more than 128 engines. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: change memory scrub mechanismfarah kassabri1-46/+83
Currently the scrubbing mechanism used the EDMA engines by directly setting the engine core registers to scrub a chunk of memory. Due to a sporadic failure with this mechanism, it was decided to initiate the engines via its QMAN using LIN-DMA packets. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: extend process wait timeout in device fineOded Gabbay2-5/+12
Processes that use our device are likely to use at the same time other devices such as remote storage. In case our device is removed and a user process is still using the device, we need to kill the user process. However, if that process has a thread waiting for i/o to complete on remote storage, for example, the process won't terminate. Let's give it enough time to terminate before giving up. Signed-off-by: Oded Gabbay <ogabbay@kernel.org> Reviewed-by: Tomer Tayar <ttayar@habana.ai>
2022-11-23habanalabs: check schedule_hard_reset correctlyOded Gabbay1-12/+13
schedule_hard_reset can be true only if we didn't do hard-reset. Therefore, no point of checking it in case hard_reset is true. Signed-off-by: Oded Gabbay <ogabbay@kernel.org> Reviewed-by: Tomer Tayar <ttayar@habana.ai>
2022-11-23habanalabs: reset device if still in use when releasedTomer Tayar1-3/+4
If the device file is released while a context is still held, it won't be possible to reopen it until the context is eventually released. If that doesn't happen, only a device reset will revert it back to an operational state, i.e. need to wait for a CS timeout or an error, or to wait for an external intervention of injecting a reset via sysfs. At this stage, after the device was released by user, context is held either because of CS which were left running on the device and are not relevant anymore, or due to missing cleanup steps from user side. All of this is in any case handled in the device reset flow, so initiate the reset at this point instead of waiting for it. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: return to reset upon SM SEI BRESP errorTomer Tayar1-13/+6
Due to a H/W issue in the LBW path to the PCIE_DBI MSI-X doorbell, there were false sporadic error responses in SM when it was configured to write to there, and hence no reset was done as part of handling the relevant event. Now that the virtual MSI-X doorbell is used, such errors in SM are not expected and reset shouldn't be skipped. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: don't enable entries in the MSIX_GW tableTomer Tayar1-26/+0
User should use the virtual MSI-X doorbell to generate interrupts from the device, so there is no need to enable entries in the MSIX_GW table. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: remove redundant firmware version checkfarah kassabri1-2/+1
Firmware 1.7 is the first official firmware, so no need to check if we are running a version below it. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi: fix print for firmware-alive eventTomer Tayar1-3/+4
Add missing le{32,64}_to_cpu conversions. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fix print for out-of-sync and pkt-failure eventsTomer Tayar3-8/+8
Add missing le32_to_cpu() conversions, and use %d for the value returned from atomic_read(). Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: add page fault notify eventDani Liberman1-8/+9
Each time page fault happens, besides capturing its data, also notify the user about it. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: classify power/thermal events as infoOfir Bitton1-0/+1
As power and thermal envelope events are pure informative and not indicating an error, we reduce the print level to info only. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: skip events info ioctl if not supportedOhad Sharabi1-0/+4
Some ASICs haven't yet implemented this functionality and so the ioctl call should fail and the user should be notified of the reason. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fix firmware descriptor copy operationfarah kassabri1-2/+24
This is needed to allow adding more data to the lkd_fw_comms_desc structure. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: add razwi notify eventDani Liberman2-62/+82
Each time razwi (read-only zero, write ignored) event happens, besides capturing its data, also notify the user about it. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: implement fp32 not supported eventOfir Bitton3-1/+9
Due to binning, Gaudi2 does not always support fp32. We add support for such an event in case fp32 is used by the user in such a device. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi: add page fault notify eventDani Liberman3-3/+14
Each time page fault happens, besides capturing its data, also notify the user about it. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: use single threaded WQ for event handlingDani Liberman1-1/+1
Creating event queue workqueue using alloc_workqueue made it run in multi threaded mode, which caused parallel dumping of events as well as parallel events notifying to user, causing logs with multiple events to be out of order. Fixed by creating event queue workqueue as single threaded work queue. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi: add razwi notify eventDani Liberman3-18/+29
Each time razwi (read-only zero, write ignore) happens, besides capturing its data, also notify the user about it. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: add PCI revision 2 supportOfir Bitton9-17/+39
Add support for Gaudi2 Device with PCI revision 2. Functionality is exactly the same as revision 1, the only difference is device name exposed to user. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: remove redundant gaudi2_sec asic typeOfir Bitton5-9/+1
As Gaudi2 has a single PCI id, the secured asic type is redundant. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: add warning print upon a PCI errorOfir Bitton1-2/+7
In order to know if driver catches PCI errors correctly, we need to print a warning per each error. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fix PCIe access to SRAM via debugfsTomer Tayar1-3/+3
hl_access_sram_dram_region() uses a region base which is set within the hl_set_dram_bar() function. However, for SRAM access this function is not called, and we end up with a wrong value of region base and with a bad calculated address. Fix it by initializing the region base value independently of whether hl_set_dram_bar() is called or not. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: zero ts registration buff when allocatedfarah kassabri1-1/+1
To avoid memory corruption in kernel memory while using timestamp registration nodes, zero the kernel buff memory when its allocated. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: no consecutive err when user context is enabledTal Cohen1-0/+4
Consecutive error protects a device reset loop from being triggered due to h/w issues and enters the device into an unavailable state. When user may cause the error, an unavailable state will prevent the user from running its workloads. The commit prevents entering consecutive state when a user context is enabled. Signed-off-by: Tal Cohen <talcohen@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: use graceful hard reset for CS timeoutsTomer Tayar1-8/+8
Use graceful hard reset when detecting a CS timeout that requires a device reset. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: use graceful hard reset for F/W eventsTomer Tayar1-17/+10
Use graceful hard reset for F/W events on Gaudi2 device that require a device reset. While at it, do a small refactor of the checks and function calls, to simplify it and to avoid code duplication. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi: use graceful hard reset for F/W eventsTomer Tayar1-9/+7
Use graceful hard reset for F/W events on Gaudi device that require a device reset. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: add an option to control watchdog timeout via debugfsTomer Tayar1-0/+5
Add an option to control the timeout value for the driver's watchdog of the reset process. The timeout represents the amount of the user has to close his process once he gets a device reset notification from the driver. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: add support for graceful hard resetTomer Tayar2-15/+140
Calling hl_device_reset() for a hard reset will lead to a quite immediate device reset and to killing user process. For resets that follow errors, it disables the option to debug the errors on both the device side and the user application side. This patch adds a 'graceful hard reset' option and a new hl_device_cond_reset() function. Under some conditions, mainly if there is no user process or if he is not registered to driver notifications, this function will execute hard reset as usual. Otherwise, the reset will be postponed and a notification will be sent to user, to let him perform post-error actions and then to release the device, after which reset will take place. If device is not released by user in some defined time, a watchdog work will execute the reset in any case. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: avoid divide by zero in device utilizationOhad Sharabi1-2/+7
Currently there is no verification whether the divisor is legal. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fix user mappings calculation in case of page faultDani Liberman1-2/+7
As there are 2 types of user mappings, pmmu and hmmu, calculate only the relevant mappings for the requested type. Signed-off-by: Dani Liberman <dliberman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: remove configurations to access the MSI-X doorbellTomer Tayar1-31/+3
The virtual MSI-X doorbell is supported now in F/W, so all configurations to access the PCIE_DBI MSI-X doorbell can be removed. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: allow setting HBM BAR to other regionsOhad Sharabi2-13/+18
Up until now the use-case in the driver was that the HBM is accessed using the HBM BAR, yet the BAR sometimes cannot cover the whole HBM and so we needed to set the BAR to other HBM offset. Now we are facing the need to access other PCI memory regions that can be covered by the HBM BAR. To answer that we are allowing the caller to determine if the HBM BAR need to be set or not regardless of the PCI memory region. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: fix using freed pointerOhad Sharabi1-1/+4
The code uses the pointer for trace purpose (without actually dereference it) but still get static analysis warning. This patch eliminate the warning. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs/gaudi2: unsecure CBU_EARLY_BRESP registersDilip Puri1-0/+1
NIC ARCs need to have access to CBU_EARLY_BRESP, hence we unsecure those registers. Signed-off-by: Dilip Puri <dilipp@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2022-11-23habanalabs: verify no zero event is sentTal Cohen2-1/+8
The event notifier mechanism should not raise an empty event (event equals zero). Signed-off-by: Tal Cohen <talcohen@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-03 08:48:34 +0000