Re: [git pull] habanalabs pull request for kernel 5.13
On Sat, Apr 10, 2021 at 11:01:42PM +0300, Oded Gabbay wrote: > Hi Greg, > > This is habanalabs pull request for the merge window of kernel 5.13. > It contains changes and new features, support for new firmware. > Details are in the tag. > > Thanks, > Oded > > The following changes since commit b195b20b7145bcae22ad261abc52d68336f5e913: > > Merge tag 'extcon-next-for-5.13' of > git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon into > char-misc-next (2021-04-08 08:45:30 +0200) Pulled and pushed out, thanks. greg k-h
[git pull] habanalabs pull request for kernel 5.13
Hi Greg, This is habanalabs pull request for the merge window of kernel 5.13. It contains changes and new features, support for new firmware. Details are in the tag. Thanks, Oded The following changes since commit b195b20b7145bcae22ad261abc52d68336f5e913: Merge tag 'extcon-next-for-5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/extcon into char-misc-next (2021-04-08 08:45:30 +0200) are available in the Git repository at: https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux.git tags/misc-habanalabs-next-2021-04-10 for you to fetch changes up to b575a7673e3d0396992fc72fce850723d39264e3: habanalabs: print f/w boot unknown error (2021-04-09 14:10:32 +0300) This tag contains habanalabs driver changes for v5.13: - Add support to reset device after the user closes the file descriptor. Because we support a single user, we can reset the device (if needs to) after a user closes its file descriptor to make sure the device is in idle and clean state for the next user. - Add a new feature to allow the user to wait on interrupt. This is needed for future ASICs - Replace GFP_ATOMIC with GFP_KERNEL wherever possible and add code to support failure of allocating with GFP_ATOMIC. - Update code to support the latest firmware image: - More security features are done in the firmware - Remove hard-coded assumptions and replace them with values that are sent to the firmware on loading. - Print device unusable error - Reset device in case the communication between driver and firmware gets out of sync. - Support new PCI device ids for secured GAUDI. - Expose current power draw through the INFO IOCTL. - Support resetting the device upon a request from the BMC (through F/W). - Always use only a single MSI in GAUDI, due to H/W limitation. - Improve data-path code by taking out code from spinlock protection. - Allow user to specify custom timeout per Command Submission. - Some enhancements to debugfs. - Various minor changes and improvements. Alon Mizrahi (1): habanalabs: add custom timeout flag per cs Bharat Jauhari (1): habanalabs: move dram scrub to free sequence Koby Elbaz (2): habanalabs: improve utilization calculation habanalabs: support DEVICE_UNUSABLE error indication from FW Oded Gabbay (11): habanalabs: reset after device is actually released habanalabs: fail reset if device is not idle habanalabs: reset_upon_device_release is for bring-up habanalabs: print if device is used on FD close habanalabs: change default CS timeout to 30 seconds habanalabs: use correct define for 32-bit max value habanalabs/gaudi: always use single-msi mode habanalabs/gaudi: add debugfs to DMA from the device habanalabs: remove the store jobs array from CS IOCTL habanalabs: use strscpy instead of sprintf and strlcpy habanalabs: print f/w boot unknown error Ofir Bitton (13): habanalabs: add reset support when user closes FD habanalabs: enable all IRQs for user interrupt support habanalabs: wait for interrupt support habanalabs: use a single FW loading bringup flag habanalabs/gaudi: update extended async event header habanalabs: replace GFP_ATOMIC with GFP_KERNEL habanalabs: debugfs access to user mapped host addresses habanalabs/gaudi: reset device upon BMC request habanalabs/gaudi: unsecure TPC cfg status registers habanalabs/gaudi: Update async events header habanalabs: move relevant datapath work outside cs lock habanalabs/gaudi: derive security status from pci id habanalabs/gaudi: skip iATU if F/W security is enabled Ohad Sharabi (6): habanalabs: reset device in case of sync error habanalabs: skip DISABLE PCI packet to FW on heartbeat habanalabs: update hl_boot_if.h habanalabs: support legacy and new pll indexes habanalabs: send dynamic msi-x indexes to f/w habanalabs: update to latest F/W communication header Sagiv Ozeri (2): habanalabs: support HW blocks vm show habanalabs: return current power via INFO IOCTL Tomer Tayar (1): habanalabs/gaudi: clear QM errors only if not in stop_on_err mode Yang Li (1): habanalabs: Switch to using the new API kobj_to_dev() farah kassabri (3): habanalabs: set max asid to 2 habanalabs: avoid soft lockup bug upon mapping error habanalabs/gaudi: sync stream add protection to SOB reset flow .../ABI/testing/debugfs-driver-habanalabs | 70 +++- drivers/misc/habanalabs/common/command_buffer.c| 12 +- .../misc/habanalabs/common/command_submission.c| 368 + drivers/misc/habanalabs/common/context.c | 14 +- drivers/misc/habanalabs/common/debugfs.c | 224 +++--
