aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2022-07-12Merge tag 'misc-habanalabs-next-2022-07-12' of ↵Greg Kroah-Hartman210-1164/+159385
https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux into char-misc-next Oded writes: This tag contains habanalabs driver changes for v5.20: - Add Gaudi2 ASIC support. All the features required for Gaudi2 are included in this tag (except the networking aspect). - Add more events to the eventfd support in the driver. With the new code, we expose three events that the user can register to get notification about them. - re-factor soft reset code and replace its name to compute reset to better reflect the actual reset done in new ASICs - Change the way Gaudi2 triggers an MSI-X interrupt due to h/w bug. - Improve the code of the debugfs node that scrubs the device's memory. - Add mechanism for better compatibility with older f/w versions - Cleanup kernel log prints by moving some prints to debug and removing others. - Many small bug fixes and minor changes. * tag 'misc-habanalabs-next-2022-07-12' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux: (88 commits) habanalabs: move h/w dirty message to debug habanalabs: rename soft reset to compute reset habanalabs: add status of reset after device release habanalabs: fix update of is_in_soft_reset habanalabs: expose only valid debugfs nodes habanalabs/gaudi2: map virtual MSI-X doorbell memory for user habanalabs/gaudi2: modify decoder to use virtual MSI-X doorbell habanalabs/gaudi2: modify CS completion CQ to use virtual MSI-X doorbell habanalabs/gaudi2: replace defines for reserved sob/mob with enums habanalabs/gaudi2: configure virtual MSI-X doorbell interface habanalabs: add a value field to hl_fw_send_pci_access_msg() habanalabs: fixes to the poll-timeout macros habanalabs/gaudi2: use DIV_ROUND_UP_SECTOR_T instead of roundup habanalabs: initialize variable explicitly habanalabs: Use the bitmap API to allocate bitmaps habanalabs/gaudi2: remove unused defines habanalabs: make sure variable is set before used habanalabs: don't declare tmp twice in same function habanalabs: do not set max power on a secured device habanalabs/gaudi2: SM mask can only be 8-bit ...
2022-07-12drivers: mcb: directly use ida_alloc()/free()keliu1-2/+2
Use ida_alloc()/ida_free() instead of deprecated ida_simple_get()/ida_simple_remove() . Signed-off-by: keliu <[email protected]> Signed-off-by: Johannes Thumshirn <[email protected]> Link: https://lore.kernel.org/r/480676bee970da16bf1fa8565277240014395ba3.1657607743.git.johannes.thumshirn@wdc.com Signed-off-by: Greg Kroah-Hartman <[email protected]>
2022-07-12interconnect: qcom: icc-rpm: Set bandwidth and clock for bucket valuesLeo Yan1-14/+61
This commit uses buckets for support bandwidth and clock rates. It introduces a new function qcom_icc_bus_aggregate() to calculate the aggregate average and peak bandwidths for every bucket, and also it calculates the maximum value of aggregated average bandwidth across all buckets. The maximum aggregated average is used to calculate the final bandwidth requests. And we can set the clock rate per bucket, we use SLEEP bucket as default bucket if a platform doesn't enable the interconnect path tags in DT binding; otherwise, we use WAKE bucket to set active clock and use SLEEP bucket for other clocks. So far we don't use AMC bucket. Signed-off-by: Leo Yan <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Georgi Djakov <[email protected]>
2022-07-12interconnect: qcom: icc-rpm: Support multiple bucketsLeo Yan2-1/+56
The current interconnect rpm driver uses a single aggregate bandwidth to calculate the clock rates for both active and sleep clocks; therefore, it has no chance to separate bandwidth requests for these two kinds of clocks. This patch studies the implementation from interconnect rpmh driver to support multiple buckets. The rpmh driver provides three buckets for AMC, WAKE, and SLEEP; this driver only needs to use WAKE and SLEEP buckets, but we keep the same way with rpmh driver, this can allow us to reuse the DT binding and avoid to define duplicated data structures. This patch introduces two callbacks: qcom_icc_pre_bw_aggregate() is used to clean up bucket values before aggregate bandwidth requests, and qcom_icc_bw_aggregate() is to aggregate bandwidth for buckets. Signed-off-by: Leo Yan <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Georgi Djakov <[email protected]>
2022-07-12interconnect: qcom: icc-rpm: Change to use qcom_icc_xlate_extended()Leo Yan1-1/+2
This commit changes to use callback qcom_icc_xlate_extended(). This is a preparation for population path tags from the interconnect DT binding, it doesn't introduce functionality change for the existed DT binding without path tags. Signed-off-by: Leo Yan <[email protected]> Reviewed-by: Dmitry Baryshkov <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Georgi Djakov <[email protected]>
2022-07-12interconnect: qcom: Move qcom_icc_xlate_extended() to a common fileLeo Yan6-26/+52
since there have conflict between two headers icc-rpmh.h and icc-rpm.h, the function qcom_icc_xlate_extended() is declared in icc-rpmh.h thus it cannot be used by icc-rpm driver. Move the function to a new common file icc-common.c so that allow it to be called by multiple drivers. Signed-off-by: Leo Yan <[email protected]> Reviewed-by: Dmitry Baryshkov <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Georgi Djakov <[email protected]>
2022-07-12dt-bindings: interconnect: Update property for icc-rpm path tagLeo Yan1-1/+5
To support path tag in icc-rpm driver, the "#interconnect-cells" property is updated as enumerate values: 1 or 2. Setting to 1 means it is compatible with old DT binding that interconnect path only contains node id; if set to 2 for "#interconnect-cells" property, then the second specifier is used as a tag (e.g. vote for which buckets). Signed-off-by: Leo Yan <[email protected]> Acked-by: Krzysztof Kozlowski <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Georgi Djakov <[email protected]>
2022-07-12habanalabs: move h/w dirty message to debugOded Gabbay3-5/+3
H/W being dirty during initialization is completely expected in case f/w tools are used before loading the driver. As it is not an error, and as it doesn't give any meaningful information to the user, no point of printing it. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: rename soft reset to compute resetOded Gabbay8-30/+30
Doing compute reset can be the traditional inference soft reset that is supported only in Goya. Or it can be the new reset upon device release, which is supported in Gaudi2 and above. Therefore, wherever suitable, use the terminology of compute reset instead of soft reset. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add status of reset after device releaseOded Gabbay3-8/+20
The user might want to know the device is in reset after device release, which is not an erroneous event as a regular reset. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: fix update of is_in_soft_resetOded Gabbay1-5/+15
reset_info.is_in_soft_reset should be updated both before in_reset and inside the spin lock of the reset info structure. The reasons are: - When we are inside soft reset, it implies we are in reset. Therefore, if someone checks if we are in soft reset, he can deduce we are in reset, while the opposite is not correct and might be misleading. - Both these flags are changed together so they must be changed inside the reset info spinlock. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: expose only valid debugfs nodesOfir Bitton2-52/+66
In case security is enabled on the device, some debugfs nodes will fail. Hence, we do not expose them. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: map virtual MSI-X doorbell memory for userTomer Tayar2-2/+44
Upon the initialization of a user context, map the host memory page of the virtual MSI-X doorbell in the device MMU. A reserved VA is used for this purpose, so user can use it directly without any allocation/map operation. Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: modify decoder to use virtual MSI-X doorbellTomer Tayar4-11/+161
Modify the decoder wrapper blocks to generate interrupts using the virtual MSI-X doorbell. As a decoder wrapper block cannot write directly to HBW upon completion, it writes instead to SOB which is monitored by a master monitor. When resolved, this monitor will be the one to actually write to the virtual MSI-X doorbell. Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: modify CS completion CQ to use virtual MSI-X doorbellTomer Tayar1-3/+16
Modify the CQ which is used for CS completion, to use the virtual MSI-X doorbell. Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: replace defines for reserved sob/mob with enumsTomer Tayar3-32/+46
Following patches are going to add more reserved sync objects and monitors. To make the counting of these reserved resources simpler, replace the existing RESERVED_* defines with enumerations. Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: configure virtual MSI-X doorbell interfaceTomer Tayar3-3/+28
Due to a watchdog timer in the LBW path, writes to the MSI-X doorbell can return sporadic error responses. To work-around this issue, a virtual MSI-X doorbell on the HBW path is configured, using the MSI-X AXI slave interface in the PCIe controller. Upon an access to a configured HBW host address, the controller will generate MSI-X interrupt instead of treating the access as regular host memory access. This patch allocates the dedicate host memory page, and communicate the address to F/W, so it will configure the relevant address match registers in the controller, and will use this address to generate MSI-X interrupts for F/W events. Following patches will handle other initiators in the device, to move them to use the virtual MSI-X doorbell. Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add a value field to hl_fw_send_pci_access_msg()Tomer Tayar6-15/+14
For gaudi2 we need to send a value to F/W as part of the PCI_ACCESS packet. As a preparation, modify hl_fw_send_pci_access_msg() to have a 'value' field. Signed-off-by: Tomer Tayar <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: fixes to the poll-timeout macrosOhad Sharabi1-29/+90
- use conventional internal macro variables (double underscore prefix) - adjust address casting - on register poll using ELBI use ELBI read rather than BAR read on error condition - remove unused macro Signed-off-by: Ohad Sharabi <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: use DIV_ROUND_UP_SECTOR_T instead of roundupOhad Sharabi1-4/+5
roundup will create an error in 32-bit architectures as we use 64-bit variables. Reported-by: kernel test robot <[email protected]> Signed-off-by: Ohad Sharabi <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: initialize variable explicitlyOded Gabbay1-1/+1
Fix warning of "warning: ‘old_base’ may be used uninitialized in this function" Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: Use the bitmap API to allocate bitmapsChristophe JAILLET1-3/+2
Use bitmap_zalloc()/bitmap_free() instead of hand-writing them. It is less verbose and it improves the semantic. Signed-off-by: Christophe JAILLET <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: remove unused definesOded Gabbay3-13/+0
There were some defines that are unused in the current upstreamed code. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: make sure variable is set before usedOded Gabbay1-1/+1
timestamp could be unset in both _hl_interrupt_wait_ioctl() and _hl_interrupt_wait_ioctl_user_addr() so it is better to explicitly initialize it to 0 when declaring it. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: don't declare tmp twice in same functionOded Gabbay1-2/+2
tmp is declared in the scope of the function cs_do_release() and inside a block inside that function. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: do not set max power on a secured deviceOfir Bitton1-2/+4
Max power API is not supported in secured devices. Hence, we should skip setting it during boot. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: SM mask can only be 8-bitOded Gabbay1-1/+2
Otherwise, due to how we calculate it, we might fail in FIELD_PREP checks. Reported-by: kernel test robot <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: remove unused variableOded Gabbay1-7/+3
glbl_sts_clr_val was set but never used Reported-by: kernel test robot <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: allow detection of unsupported f/w packetsOded Gabbay1-4/+8
If we send a packet to the f/w, and that packet is unsupported, we want to be able to identify this situation and possibly ignore this. Therefore, if the f/w returned an error, we need to propagate it to the callers in the result value, if those callers were interested in it. In addition, no point of printing the error code here because each caller prints its own error with a specific message. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: save f/w preboot minor versionSagiv Ozeri2-9/+44
We need this property for backward compatibility against the f/w. Signed-off-by: Sagiv Ozeri <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add support for common decoder interruptsOfir Bitton5-6/+19
User application should be able to get notification for any decoder completion. Hence, we introduce a new interface in which a user can wait for all current decoder pending interrupts. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: naming refactor of user interrupt flowOfir Bitton5-18/+21
Current naming convention can be misleading. Hence renaming some variables and defines in order to be more explicit. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: wait for preboot ready after hard resetOhad Sharabi5-42/+107
Currently we are not waiting for preboot ready after hard reset. This leads to a race in which COMMs protocol begins but will get no response from the f/w. Signed-off-by: Ohad Sharabi <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: reset device upon critical ECC eventOfir Bitton2-11/+16
Correctable ECC events are not fatal, but as they accumulate, the f/w can decide that a hard-rest is required. This indication is propagated to the host using the existing ECC event interface. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: enable gaudi2 code in driverOded Gabbay3-7/+63
Enable the Gaudi2 ASIC code in the pci probe callback of the driver so the driver will handle Gaudi2 ASICs. Add the PCI ID to the PCI table and add the ASIC enum value to all relevant places. Fixup the device parameters initialization for Gaudi2. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add gaudi2 MMU supportMoti Haimovski7-33/+1064
Gaudi2 has new MMU units. A PMMU for device->host accesses, and HMMU for HBM accesses. The page tables of both MMUs are located in the host's memory (referred to in the code as host-resident pgt). Signed-off-by: Moti Haimovski <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add gaudi2 wait-for-CS supportOded Gabbay7-89/+210
In Gaudi2 we moved to a different wait for command submission completion model. Instead of receiving interrupt only on external queues, we use the device's sync manager to notify us when the entire command submission finishes. This enables us to remove the categorization of queues to external and internal, and treat each queue equally, without the need to parse and patch any command buffer. This change also requires refactoring to the IRQ handling of CS completions. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: add gaudi2 profiler moduleBenjamin Dotan4-2/+3792
Add the Gaudi2 code to initialize the ASIC's profiler. The profile receives its initialization values from the user, same as in Gaudi2, but the code to initialize is in the driver because the configuration space of the device is not directly exposed to the user. Signed-off-by: Benjamin Dotan <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: add gaudi2 security moduleOfir Bitton4-2/+3867
Use the generic security module to block all registers in the ASIC and then open only those that are needed to be accessed by the user. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add generic security moduleOfir Bitton3-2/+671
As the ASICs become more complex and have many more registers, we need a better way to configure the security properties. As a reminder, we have two dedicated mechanisms for security: Range Registers and Protection bits. Those mechanisms protect sensitive memory and configuration areas inside the device. The generic module handles the low-level part of the configuration, because the configuration mechanism is identical in all ASICs. The difference is the address ranges and register names. Any ASIC that use this block should first block all the register blocks in the ASIC. Then, it should open only the registers that need to be accessed by the user (This is opposed to Goya and Gaudi, where we blocked only what should not be accesses by the user). The module contains several functions, to unblock single register, multiple registers, entire blocks, ranges, ranges with mask. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: remove obsolete device variables used for testingOded Gabbay5-173/+24
There are a couple of device variables that are used for testing purposes and they are set to fixed values. Remove the variables that are not relevant anymore and document the remaining variables. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: initialize new asic propertiesOded Gabbay3-14/+28
New asic properties were added for Gaudi2. We want to initialize and use them, when relevant, also for Goya and Gaudi. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add unsupported functionsOded Gabbay2-0/+42
There are a number of new ASIC-specific functions that were added for Gaudi2. To make the common code work, we need to define empty implementations of those functions for Goya and Gaudi. Some functions will return error if called with Goya/Gaudi. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: add gaudi2 asic-specific codeOded Gabbay23-98/+11165
Add the ASIC-specific code for Gaudi2. Supply (almost) all of the function callbacks that the driver's common code need to initialize, finalize and submit workloads to the Gaudi2 ASIC. It also contains the code to initialize the F/W of the Gaudi2 ASIC and to receive events from the F/W. It contains new debugfs entry to dump razwi events. razwi is a case where the device's engines create a transaction that reaches an invalid destination. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12uapi: habanalabs: add gaudi2 definesOded Gabbay1-20/+435
Add the new defines for GAUDI2 uapi interface. It includes the following: 1. Enums of engines and PLLs. 2. New information in the info IOCTL that is retrieved by the driver. 3. Update comments regarding the CB/CS/wait for CS ioctls. 4. New fields in the debug IOCTL for configuring the profiler for Gaudi2. There is no new IOCTL. Some of the changes are also relevant for Greco (which will be upstreamed later this year). When ever it says "Greco and onwards", it means it is also for Gaudi2. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi2: add asic registers header filesOded Gabbay168-2/+136492
Add the relevant GAUDI2 ASIC registers header files. These files are generated automatically from a tool maintained by the VLSI engineers. There are more files which are not upstreamed because only very few defines from those files are used in the driver. For those files, I copied the relevant defines into gaudi2_regs.h and gaudi2_masks.h, to reduce the size of this patch. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: remove redundant argument in access_dev_mem APIsOfir Bitton3-9/+7
Region structure is derived from region type, hence no need to pass it as an argument. Signed-off-by: Ofir Bitton <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: use %pa to print pci bar sizeOded Gabbay2-28/+22
PCI bar size is resource_size_t so we should use %pa to make it work correctly on all architectures. Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs/gaudi: replace hl_poll_timeout with while loopDafna Hirschfeld1-12/+11
in gaudi_scrub_device_mem, replace call to hl_poll_timeout with a while loop to avoid using dummy variables. Reported-by: kernel test robot <[email protected]> Signed-off-by: Dafna Hirschfeld <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2022-07-12habanalabs: communicate supported page sizes to userOhad Sharabi5-19/+6
Because in future ASICs the driver will allow the user to set the page size we need to make sure this data is propagated in all APIs. In addition, since this is already an ASIC property we no longer need ASIC function for it. Signed-off-by: Ohad Sharabi <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.