summaryrefslogtreecommitdiff
path: root/drivers/misc
AgeCommit message (Collapse)AuthorFilesLines
2021-09-12Merge tag 'char-misc-5.15-rc1-lkdtm' of ↵Linus Torvalds2-11/+27
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc Pull misc driver fix from Greg KH: "Here is a single patch for 5.15-rc1, for the lkdtm misc driver. It resolves a build issue that many people were hitting with your current tree, and Kees and others felt would be good to get merged before -rc1 comes out, to prevent them from having to constantly hit it as many development trees restart on -rc1, not older -rc releases. It has NOT been in linux-next, but has passed 0-day testing and looks 'obviously correct' when reviewing it locally :)" * tag 'char-misc-5.15-rc1-lkdtm' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: lkdtm: Use init_uts_ns.name instead of macros
2021-09-10Merge tag 'char-misc-5.15-rc1-2' of ↵Linus Torvalds26-770/+3689
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc Pull habanalabs updates from Greg KH: "Here is another round of misc driver patches for 5.15-rc1. In here is only updates for the Habanalabs driver. This request is late because the previously-objected-to dma-buf patches are all removed and some fixes that you and others found are now included in here as well. All of these have been in linux-next for well over a week with no reports of problems, and they are all self-contained to only this one driver. Full details are in the shortlog" * tag 'char-misc-5.15-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (61 commits) habanalabs/gaudi: hwmon default card name habanalabs: add support for f/w reset habanalabs/gaudi: block ICACHE_BASE_ADDERESS_HIGH in TPC habanalabs: cannot sleep while holding spinlock habanalabs: never copy_from_user inside spinlock habanalabs: remove unnecessary device status check habanalabs: disable IRQ in user interrupts spinlock habanalabs: add "in device creation" status habanalabs/gaudi: invalidate PMMU mem cache on init habanalabs/gaudi: size should be printed in decimal habanalabs/gaudi: define DC POWER for secured PMC habanalabs/gaudi: unmask out of bounds SLM access interrupt habanalabs: add userptr_lookup node in debugfs habanalabs/gaudi: fetch TPC/MME ECC errors from F/W habanalabs: modify multi-CS to wait on stream masters habanalabs/gaudi: add monitored SOBs to state dump habanalabs/gaudi: restore user registers when context opens habanalabs/gaudi: increase boot fit timeout habanalabs: update to latest firmware headers habanalabs/gaudi: minimize number of register reads ...
2021-09-10lkdtm: Use init_uts_ns.name instead of macrosKees Cook2-11/+27
Using generated/compile.h triggered a full LKDTM rebuild with every build. Avoid this by using the exported strings instead. Fixes: b8661450bc7f ("lkdtm: Add kernel version to failure hints") Signed-off-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20210901233406.2571643-1-keescook@chromium.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-09-08Merge tag 'pci-v5.15-changes' of ↵Linus Torvalds1-0/+9
git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci Pull PCI updates from Bjorn Helgaas: "Enumeration: - Convert controller drivers to generic_handle_domain_irq() (Marc Zyngier) - Simplify VPD (Vital Product Data) access and search (Heiner Kallweit) - Update bnx2, bnx2x, bnxt, cxgb4, cxlflash, sfc, tg3 drivers to use simplified VPD interfaces (Heiner Kallweit) - Run Max Payload Size quirks before configuring MPS; work around ASMedia ASM1062 SATA MPS issue (Marek Behún) Resource management: - Refactor pci_ioremap_bar() and pci_ioremap_wc_bar() (Krzysztof Wilczyński) - Optimize pci_resource_len() to reduce kernel size (Zhen Lei) PCI device hotplug: - Fix a double unmap in ibmphp (Vishal Aslot) PCIe port driver: - Enable Bandwidth Notification only if port supports it (Stuart Hayes) Sysfs/proc/syscalls: - Add schedule point in proc_bus_pci_read() (Krzysztof Wilczyński) - Return ~0 data on pciconfig_read() CAP_SYS_ADMIN failure (Krzysztof Wilczyński) - Return "int" from pciconfig_read() syscall (Krzysztof Wilczyński) Virtualization: - Extend "pci=noats" to also turn on Translation Blocking to protect against some DMA attacks (Alex Williamson) - Add sysfs mechanism to control the type of reset used between device assignments to VMs (Amey Narkhede) - Add support for ACPI _RST reset method (Shanker Donthineni) - Add ACS quirks for Cavium multi-function devices (George Cherian) - Add ACS quirks for NXP LX2xx0 and LX2xx2 platforms (Wasim Khan) - Allow HiSilicon AMBA devices that appear as fake PCI devices to use PASID and SVA (Zhangfei Gao) Endpoint framework: - Add support for SR-IOV Endpoint devices (Kishon Vijay Abraham I) - Zero-initialize endpoint test tool parameters so we don't use random parameters (Shunyong Yang) APM X-Gene PCIe controller driver: - Remove redundant dev_err() call in xgene_msi_probe() (ErKun Yang) Broadcom iProc PCIe controller driver: - Don't fail devm_pci_alloc_host_bridge() on missing 'ranges' because it's optional on BCMA devices (Rob Herring) - Fix BCMA probe resource handling (Rob Herring) Cadence PCIe driver: - Work around J7200 Link training electrical issue by increasing delays in LTSSM (Nadeem Athani) Intel IXP4xx PCI controller driver: - Depend on ARCH_IXP4XX to avoid useless config questions (Geert Uytterhoeven) Intel Keembay PCIe controller driver: - Add Intel Keem Bay PCIe controller (Srikanth Thokala) Marvell Aardvark PCIe controller driver: - Work around config space completion handling issues (Evan Wang) - Increase timeout for config access completions (Pali Rohár) - Emulate CRS Software Visibility bit (Pali Rohár) - Configure resources from DT 'ranges' property to fix I/O space access (Pali Rohár) - Serialize INTx mask/unmask (Pali Rohár) MediaTek PCIe controller driver: - Add MT7629 support in DT (Chuanjia Liu) - Fix an MSI issue (Chuanjia Liu) - Get syscon regmap ("mediatek,generic-pciecfg"), IRQ number ("pci_irq"), PCI domain ("linux,pci-domain") from DT properties if present (Chuanjia Liu) Microsoft Hyper-V host bridge driver: - Add ARM64 support (Boqun Feng) - Support "Create Interrupt v3" message (Sunil Muthuswamy) NVIDIA Tegra PCIe controller driver: - Use seq_puts(), move err_msg from stack to static, fix OF node leak (Christophe JAILLET) NVIDIA Tegra194 PCIe driver: - Disable suspend when in Endpoint mode (Om Prakash Singh) - Fix MSI-X address programming error (Om Prakash Singh) - Disable interrupts during suspend to avoid spurious AER link down (Om Prakash Singh) Renesas R-Car PCIe controller driver: - Work around hardware issue that prevents Link L1->L0 transition (Marek Vasut) - Fix runtime PM refcount leak (Dinghao Liu) Rockchip DesignWare PCIe controller driver: - Add Rockchip RK356X host controller driver (Simon Xue) TI J721E PCIe driver: - Add support for J7200 and AM64 (Kishon Vijay Abraham I) Toshiba Visconti PCIe controller driver: - Add Toshiba Visconti PCIe host controller driver (Nobuhiro Iwamatsu) Xilinx NWL PCIe controller driver: - Enable PCIe reference clock via CCF (Hyun Kwon) Miscellaneous: - Convert sta2x11 from 'pci_' to 'dma_' API (Christophe JAILLET) - Fix pci_dev_str_match_path() alloc while atomic bug (used for kernel parameters that specify devices) (Dan Carpenter) - Remove pointless Precision Time Management warning when PTM is present but not enabled (Jakub Kicinski) - Remove surplus "break" statements (Krzysztof Wilczyński)" * tag 'pci-v5.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (132 commits) PCI: ibmphp: Fix double unmap of io_mem x86/PCI: sta2x11: switch from 'pci_' to 'dma_' API PCI/VPD: Use unaligned access helpers PCI/VPD: Clean up public VPD defines and inline functions cxgb4: Use pci_vpd_find_id_string() to find VPD ID string PCI/VPD: Add pci_vpd_find_id_string() PCI/VPD: Include post-processing in pci_vpd_find_tag() PCI/VPD: Stop exporting pci_vpd_find_info_keyword() PCI/VPD: Stop exporting pci_vpd_find_tag() PCI: Set dma-can-stall for HiSilicon chips PCI: rockchip-dwc: Add Rockchip RK356X host controller driver PCI: dwc: Remove surplus break statement after return PCI: artpec6: Remove local code block from switch statement PCI: artpec6: Remove surplus break statement after return MAINTAINERS: Add entries for Toshiba Visconti PCIe controller PCI: visconti: Add Toshiba Visconti PCIe host controller driver PCI/portdrv: Enable Bandwidth Notification only if port supports it PCI: Allow PASID on fake PCIe devices without TLP prefixes PCI: mediatek: Use PCI domain to handle ports detection PCI: mediatek: Add new method to get irq number ...
2021-09-02Merge tag 'platform-drivers-x86-v5.15-1' of ↵Linus Torvalds1-1/+0
git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86 Pull x86 platform driver updates from Hans de Goede: "Highlights: - Move all the Intel drivers into their own subdir(s) (mostly Kate's work) - New meraki-mx100 platform driver - Asus WMI driver enhancements, including support for /sys/firmware/acpi/platform_profile - New BIOS SAR driver for Intel M.2 WWAM modems - Alder Lake support for the Intel PMC driver - A whole bunch of cleanups + fixes all over the place" * tag 'platform-drivers-x86-v5.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86: (65 commits) platform/x86: dell-smbios-wmi: Add missing kfree in error-exit from run_smbios_call platform/x86: dell-smbios-wmi: Avoid false-positive memcpy() warning platform/x86: ISST: use semi-colons instead of commas platform/x86: asus-wmi: Fix "unsigned 'retval' is never less than zero" smatch warning platform/x86: asus-wmi: Delete impossible condition platform/x86: hp_accel: Convert to be a platform driver platform/x86: hp_accel: Remove _INI method call platform/mellanox: mlxbf-pmc: fix kernel-doc notation platform/x86/intel: pmc/core: Add GBE Package C10 fix for Alder Lake PCH platform/x86/intel: pmc/core: Add Alder Lake low power mode support for pmc core platform/x86/intel: pmc/core: Add Latency Tolerance Reporting (LTR) support to Alder Lake platform/x86/intel: pmc/core: Add Alderlake support to pmc core driver platform/x86: intel-wmi-thunderbolt: Move to intel sub-directory platform/x86: intel-wmi-sbl-fw-update: Move to intel sub-directory platform/x86: intel-vbtn: Move to intel sub-directory platform/x86: intel_oaktrail: Move to intel sub-directory platform/x86: intel_int0002_vgpio: Move to intel sub-directory platform/x86: intel-hid: Move to intel sub-directory platform/x86: intel_atomisp2: Move to intel sub-directory platform/x86: intel_speed_select_if: Move to intel sub-directory ...
2021-09-02Merge branch 'remotes/lorenzo/pci/endpoint'Bjorn Helgaas1-0/+1
- Add max-virtual-functions to endpoint binding (Kishon Vijay Abraham I) - Add pci_epf_add_vepf() API to add virtual function to endpoint (Kishon Vijay Abraham I) - Add pci_epf_vepf_link() to link virtual function to endpoint physical function (Kishon Vijay Abraham I) - Add virtual function number to pci_epc_ops endpoint ops interfaces (Kishon Vijay Abraham I) - Simplify register base address computation for endpoint BAR configuration (Kishon Vijay Abraham I) - Add support to configure virtual functions in cadence endpoint driver (Kishon Vijay Abraham I) - Add SR-IOV configuration to endpoint test driver (Kishon Vijay Abraham I) - Document configfs usage to create virtual functions for endpoints (Kishon Vijay Abraham I) * remotes/lorenzo/pci/endpoint: Documentation: PCI: endpoint/pci-endpoint-cfs: Guide to use SR-IOV misc: pci_endpoint_test: Populate sriov_configure ops to configure SR-IOV device PCI: cadence: Add support to configure virtual functions PCI: cadence: Simplify code to get register base address for configuring BAR PCI: endpoint: Add virtual function number in pci_epc ops PCI: endpoint: Add support to link a physical function to a virtual function PCI: endpoint: Add support to add virtual function in endpoint core dt-bindings: PCI: pci-ep: Add binding to specify virtual function
2021-09-01Merge tag 'tty-5.15-rc1' of ↵Linus Torvalds1-4/+4
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty Pull tty / serial updates from Greg KH: "Here is the "big" set of tty/serial driver patches for 5.15-rc1 Nothing major in here at all, just some driver updates and more cleanups on old tty apis and code that needed it that includes: - tty.h cleanup of things that didn't belong in it - other tty cleanups by Jiri - driver cleanups - rs485 support added to amba-pl011 driver - dts updates - stm32 serial driver updates - other minor fixes and driver updates All have been in linux-next for a while with no reported problems" * tag 'tty-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty: (83 commits) tty: serial: uartlite: Use read_poll_timeout for a polling loop tty: serial: uartlite: Use constants in early_uartlite_putc tty: Fix data race between tiocsti() and flush_to_ldisc() serial: vt8500: Use of_device_get_match_data serial: tegra: Use of_device_get_match_data serial: 8250_ingenic: Use of_device_get_match_data tty: serial: linflexuart: Remove redundant check to simplify the code tty: serial: fsl_lpuart: do software reset for imx7ulp and imx8qxp tty: serial: fsl_lpuart: enable two stop bits for lpuart32 tty: serial: fsl_lpuart: fix the wrong mapbase value mxser: use semi-colons instead of commas tty: moxa: use semi-colons instead of commas tty: serial: fsl_lpuart: check dma_tx_in_progress in tx dma callback tty: replace in_irq() with in_hardirq() serial: sh-sci: fix break handling for sysrq serial: stm32: use devm_platform_get_and_ioremap_resource() serial: stm32: use the defined variable to simplify code Revert "arm pl011 serial: support multi-irq request" tty: serial: samsung: Add Exynos850 SoC data tty: serial: samsung: Fix driver data macros style ...
2021-09-01Merge tag 'staging-5.15-rc1' of ↵Linus Torvalds3-0/+318
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging Pull IIO and staging driver updates from Greg KH: "Here is the big set of staging and IIO driver updates for 5.15-rc1. Also included in here are the counter driver subsystem updates as the IIO drivers needed them. Lots of churn in some staging drivers, we dropped the "old" rtl8188eu driver and replaced it with a newer version of the driver that had been maintained out-of-tree by Larry with the end goal of actually being able to get this driver out of staging eventually. Despite that driver being "newer" the line count of this pull request is going up. Some drivers moved out of staging as well, which is always nice to see, that is why there are additions to the mfc and misc driver subsystems. All of these were acked by the various subsystem maintainers involved. But by far, as normal, it's coding style cleanups all over the drivers/staging/ tree in here. Full details of these changes are in the shortlog. All of these have been in linux-next for a while with no reported problems" [ Note: the r8188eu merge clashed with commit 89939e890605 ("staging: rtlwifi: use siocdevprivate") from the networking tree. When resolving the issue, I noted that the whole r8188eu rtw_android code is dead since commit ae7471cae00a ("staging: r8188eu: remove rtw_ioctl function"). End result: the merge resolution was to throw all of that away, rather than do the mindless fixup to code that isn't actually reachable - Linus ] * tag 'staging-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging: (551 commits) staging: vt6655: Remove filenames in files staging: r8188eu: add extra TODO entries staging: vt6656: Remove filenames in files staging: wlan-ng: fix invalid assignment warning staging: r8188eu: rename fields of struct rtl_ps staging: r8188eu: remove ODM_DynamicPrimaryCCA_DupRTS() staging: r8188eu: rename fields of struct dyn_primary_cca staging: r8188eu: rename struct field Wifi_Error_Status staging: r8188eu: Provide a TODO file for this driver staging: r8188eu: remove unneeded variable staging: r8188eu: remove unneeded conversions to bool staging: r8188eu: remove {read,write}_macreg staging: r8188eu: core: remove condition with no effect staging: r8188eu: remove ethernet.h header file staging: r8188eu: remove ip.h header file staging: r8188eu: remove if_ether.h header file staging: r8188eu: make rtw_deinit_intf_priv return void staging: r8188eu: use is_multicast_ether_addr in os_dep/recv_linux.c staging: r8188eu: use is_multicast_ether_addr in hal/rtl8188eu_xmit.c staging: r8188eu: use is_multicast_ether_addr in core/rtw_xmit.c ...
2021-09-01Merge tag 'driver-core-5.15-rc1' of ↵Linus Torvalds2-5/+2
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core Pull driver core updates from Greg KH: "Here is the big set of driver core patches for 5.15-rc1. These do change a number of different things across different subsystems, and because of that, there were 2 stable tags created that might have already come into your tree from different pulls that did the following - changed the bus remove callback to return void - sysfs iomem_get_mapping rework Other than those two things, there's only a few small things in here: - kernfs performance improvements for huge numbers of sysfs users at once - tiny api cleanups - other minor changes All of these have been in linux-next for a while with no reported problems, other than the before-mentioned merge issue" * tag 'driver-core-5.15-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (33 commits) MAINTAINERS: Add dri-devel for component.[hc] driver core: platform: Remove platform_device_add_properties() ARM: tegra: paz00: Handle device properties with software node API bitmap: extend comment to bitmap_print_bitmask/list_to_buf drivers/base/node.c: use bin_attribute to break the size limitation of cpumap ABI topology: use bin_attribute to break the size limitation of cpumap ABI lib: test_bitmap: add bitmap_print_bitmask/list_to_buf test cases cpumask: introduce cpumap_print_list/bitmask_to_buf to support large bitmask and list sysfs: Rename struct bin_attribute member to f_mapping sysfs: Invoke iomem_get_mapping() from the sysfs open callback debugfs: Return error during {full/open}_proxy_open() on rmmod zorro: Drop useless (and hardly used) .driver member in struct zorro_dev zorro: Simplify remove callback sh: superhyway: Simplify check in remove callback nubus: Simplify check in remove callback nubus: Make struct nubus_driver::remove return void kernfs: dont call d_splice_alias() under kernfs node lock kernfs: use i_lock to protect concurrent inode updates kernfs: switch kernfs to use an rwsem kernfs: use VFS negative dentry caching ...
2021-09-01habanalabs/gaudi: hwmon default card nameRajaravi Krishna Katta1-1/+1
This commit corrects CARD NAME for Gaudi as "HL205" Signed-off-by: Rajaravi Krishna Katta <rkatta@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: add support for f/w resetOded Gabbay5-35/+61
When the f/w runs in secured mode, it can reset the ASIC when certain events occur. In unsecured mode, the driver asks the f/w to reset the ASIC for those events. We need to perform the entire reset procedure but without accessing the ASIC. i.e. without halting the engines and without sending messages to the f/w. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: block ICACHE_BASE_ADDERESS_HIGH in TPCOded Gabbay1-0/+8
This register shouldn't be modified by user. Prefetch is disabled in Gaudi. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: cannot sleep while holding spinlockfarah kassabri2-3/+1
Fix 2 areas in the code where it's possible the code will go to sleep while holding a spinlock. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: never copy_from_user inside spinlockOded Gabbay1-23/+12
copy_from_user might sleep so we can never call it when we have a spinlock. Moreover, it is not necessary in waiting for user interrupt, because if multiple threads will call this function on the same interrupt, each one will have it's own fence object inside the driver. The user address might be the same, but it doesn't really matter to us, as we only read from it. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: remove unnecessary device status checkOded Gabbay1-4/+6
Checking if the device is operational when entering the function to wait for user interrupt is not something that is useful or necessary. It is not done in any other wait_for_cs ioctl path. If the device becomes non-operational during the wait, the reset function will make sure the process wait is interrupted. Instead, move the check to the beginning of hl_wait_ioctl(). It will block any attempt to wait on CS or user interrupt once the device is already marked as non-operational. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: disable IRQ in user interrupts spinlockOded Gabbay1-12/+13
Because this spinlock is taken in an interrupt handler, we must use the spin_lock_irqsave/irqrestore version to disable the interrupts on the local CPU. Otherwise, we can have a potential deadlock (if the interrupt handler is scheduled to run on the same cpu that the code who took the lock was running on). Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: add "in device creation" statusOmer Shpigelman4-16/+17
On init, the disabled state is cleared right before hw_init and that causes the device to report on "Operational" state before the device initialization is finished. Although the char device is not yet exposed to the user at this stage, the sysfs entries are exposed. This can cause errors in monitoring applications that use the sysfs entries. In order to avoid this, a new state "in device creation" is introduced to ne reported when the device is not disabled but is still in init flow. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: invalidate PMMU mem cache on initOded Gabbay1-0/+3
This must be done to clear the internal mem cache so we won't get ecc errors on the first invalidation. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: size should be printed in decimalOded Gabbay1-2/+2
It's more readable for the size to be in decimal. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: define DC POWER for secured PMCOded Gabbay2-1/+7
In secured mode, the CGM is disabled. Therefore, the DC power is higher. Without taking it into consideration, the utilization is 12-15% at idle. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: unmask out of bounds SLM access interruptTomer Tayar1-1/+1
The out of bounds SLM access TPC interrupt indicates a severe compiler bug and needs to be informed to user. This interrupt is currently masked so unmask it. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: add userptr_lookup node in debugfsYuri Nudelman3-19/+93
It is useful to have the ability to see which user address was pinned to which physical address during the initial mapping. We already have all that info stored, but no means to search this data (which may be quite large). Signed-off-by: Yuri Nudelman <ynudelman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: fetch TPC/MME ECC errors from F/WOfir Bitton1-0/+6
In case F/W security is enabled driver cannot access ECC registers, hence driver must fetch the ECC info from 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>
2021-09-01habanalabs: modify multi-CS to wait on stream mastersOhad Sharabi6-28/+77
During the integration, the multi-CS requirements were refined: - The multi CS call shall wait on "per-ASIC" predefined stream masters instead of set of streams. - Stream masters are set of QIDs used by the upper SW layers (synapse) for completion (must be an external/HW queue). Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: add monitored SOBs to state dumpAlon Mizrahi2-2/+37
Current "state dump" is lacking of monitored SOB IDs. Add for convenience. Signed-off-by: Alon Mizrahi <amizrahi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: restore user registers when context opensOded Gabbay1-2/+12
Because we don't have multiple contexts in GAUDI, and to minimize calls to is_idle function (which uses many register reads), move the call to clear the user registers to the opening of the single user context. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: increase boot fit timeoutOded Gabbay2-1/+5
Various f/w versions have different timeouts, so increase the default timeout to accommodate all the options. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: update to latest firmware headersOded Gabbay2-6/+121
Add several new packets between driver and firmware. Add matching compatibility bits for backward compatibility. Add support for 4K event types. Add information about pcie errors. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: minimize number of register readsOded Gabbay2-9/+11
Because the register reads might be trapped by the hypervisor in certain deployments, minimize the number of reads during runtime by moving static initializations to functions that occur during device initialization instead of context open. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: fix mmu node address resolution in debugfsYuri Nudelman1-1/+1
The address resolution via debugfs was not taking into consideration the page offset, resulting in a wrong address. Signed-off-by: Yuri Nudelman <ynudelman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: save pid per userptrYuri Nudelman3-4/+7
Currently userptr endpoint in debugfs prints out virtual addresses in the user process memory space, without specifying their owner process ID. User space virtual address is meaningless without knowing the owner process. Signed-off-by: Yuri Nudelman <ynudelman@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: move scrubbing to late initOded Gabbay1-5/+5
HW init is mostly about configuring registers. Therefore, it is better to activate DMAs only in late init and afterwards. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs/gaudi: scrub HBM to a specific valueOfir Bitton1-2/+7
In order to enhance debuggability, we will scrub the whole HBM to a specific value, in case HBM scrubbing is enabled. Scrubbing will be performed after reset and after user closes the FD. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: add validity check for event ID received from F/WOfir Bitton2-0/+12
Currently there is no validity check for event ID received from F/W, Thus exposing driver to memory overrun. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: clear msg_to_cpu_reg to avoid misread after resetKoby Elbaz1-16/+12
For some ASICs, the f/w reads the msg_to_cpu_reg value after reset, and for some it doesn't. Therefore, to be sure f/w doesn't read a wrong value after reset, we need to clear this register before the reset occurs. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: make set_pci_regions asic functionOhad Sharabi3-4/+8
In order to better support variants of the same ASIC the set_pci_regions function is now an ASIC function which allows each ASIC to implement it internally, thus keeping all definitions static to the file. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: convert PCI BAR offset to u64Ohad Sharabi1-1/+1
Done as the bar size can exceed 4GB. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-09-01habanalabs: expose server type in INFO IOCTLOded Gabbay6-1/+21
Add the server type property to the hl_info_hw_ip_info structure that is exposed to the user via the INFO IOCTL. This is needed by the userspace s/w stack to know the connections map of the internal links that connect the ASIC among themselves inside the server. The F/W will tell us, as part of the NIC information, the server type that the GAUDI is located in. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: remove redundant warning messageOded Gabbay1-3/+0
This warning is redundant as we will print a notice in case the device is still in use after the FD was closed. No need to print the same message per context. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: add support for encapsulated signals submissionfarah kassabri6-349/+308
This commit is the second part of the encapsulated signals feature. It contains the driver support for submission of cs with encapsulated signals and the wait for them. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: add support for encapsulated signals reservationfarah kassabri7-15/+371
The signaling from within encapsulated OP capability is merged into the existing stream architecture, such that one can trigger multiple signaling from an encapsulated op, according to the time the event was done in the graph execution and avoid the need to wait for the whole encapsulated OP execution to be complete before the stream can signal. This commit implements only the reserve/unreserve part. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: signal/wait change sync object reset flowfarah kassabri5-59/+141
Currently the SOB reset was in fence release function which happens only at the CS wraparound during the CS allocation time. In order to support the new encapsulated signals reservation feature, we need to move the SOB reset to an earlier phase because this SOB could reach it's max value very fast using the signal reservation. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: add wait-for-multi-CS uAPIOhad Sharabi7-3/+535
When user sends multiple CSs, waiting for each CS is not efficient as it involves many user-kernel context switches. In order to address this issue we add support to "wait on multiple CSs" using a new uAPI which can wait on maximum of 32 CSs. The new uAPI is defined using a new flag - WAIT_FOR_MULTI_CS - in the wait_for_cs IOCTL. The input parameters for this uAPI will be: @seq: user pointer to an array of up to 32 CS's sequence numbers. @seq_array_len: length of sequence array. @timeout_us: timeout for waiting for any CS. The output paramateres for this API will be: @status: multi CS ioctl completion status (dedicated status was added as well). @flags: bitmap of output flags of the CS. @cs_completion_map: bitmap for multi CS, if CS sequence that was placed in index N in input seq array has completed- the N-th bit in cs_completion_map will be 1, otherwise it will be 0. @timestamp_nsec: timestamp of the first completed CS Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: get multiple fences under same cs_lockOhad Sharabi3-51/+113
To add proper support for wait-for-multi-CS, locking the CS lock for each CS fence in the list is not efficient. Instead, this patch add support to lock the CS lock once to get all required fences. Signed-off-by: Ohad Sharabi <osharabi@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: revise prints on FD closeOded Gabbay2-3/+3
The driver quietly handles memory mappings that were not freed so no need to print a warning about that when user closes the FD. Accordingly, revise the text that is printed in case the device is still in use after the user process closed the FD. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs/goya: add missing initializationOded Gabbay1-0/+1
Need to initialize f/w Linux loaded indication to false to prevent wrong communication with the f/w. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: update firmware header to latest versionOded Gabbay1-1/+3
Add two new fields regarding interrupts communication between driver and f/w. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs: fix race between soft reset and heartbeatKoby Elbaz4-80/+67
There is a scenario where an ongoing soft reset would race with an ongoing heartbeat routine, eventually causing heartbeat to fail and thus to escalate into a hard reset. With this fix, soft-reset procedure will disable heartbeat CPU messages and flush the (ongoing) current one before continuing with reset code. Signed-off-by: Koby Elbaz <kelbaz@habana.ai> Reviewed-by: Oded Gabbay <ogabbay@kernel.org> Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs/gaudi: fix information printed on SM eventOded Gabbay1-11/+23
Print the SM name instead of index because it is more informational for the user to know the SM name instead of id when a SM interrupt occurs. In addition, the index that is printed is of the SOB group, not a specific SOB. Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
2021-08-29habanalabs/gaudi: trigger state dump in case of SM errorsOfir Bitton1-1/+6
State dump is relevant to the user in case of Sync Manager error, so we need to trigger it in that case as well. Signed-off-by: Ofir Bitton <obitton@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 2024-11-29 21:57:58 +0300