wireguard-openbsd/sys/arch/powerpc64/dev, branch master WireGuard implementation for the OpenBSD kernel https://git.zx2c4.com/wireguard-openbsd/atom/sys/arch/powerpc64/dev?h=master 2021-01-23T12:10:08Z OPAL implements firmware calls that abstract communicating with the BMC over 2021-01-23T12:10:08Z kettenis kettenis@openbsd.org 2021-01-23T12:10:08Z urn:sha1:c5fc2d4914929c0917173549b6372d64cb18ba33 IPMI. Use these calls to add support for impi(4) on PowerNV systems. ok dlg@ Enter power-saving mode on POWER9 (ISA v3) 2020-12-30T06:06:30Z gkoehler gkoehler@openbsd.org 2020-12-30T06:06:30Z urn:sha1:196daab381bbbbcb721d4c428764249109b38970 When opal(4) attaches, look in the device tree for a psscr value. In cpu_idle_cycle(), use this psscr value and the stop instruction to wait for the next interrupt. In mp kernels, cpu_unidle() now sends an interrupt. In "sysctl hw.sensors", the power and temperature sensors from opalsens(4) may show lower values. The cpu may exit stop at the system reset vector after losing user registers. If so, restore some registers. For now, ignore deeper stop states that would lose hypervisor registers. Our mp kernel uses only the first hardware thread of each core. Take the extra threads from the firmware and stop them forever; this may switch the core from SMT4 to single-thread mode and increase performance. partly by kettenis@, ok kettenis@ Fix typo. 2020-12-20T21:03:53Z kettenis kettenis@openbsd.org 2020-12-20T21:03:53Z urn:sha1:52287a62fecc8d5fc23f844a3a6bd7bdf0191664 The TCE table needs to be aligned on a boundary that is a multiple of its 2020-12-20T13:02:10Z kettenis kettenis@openbsd.org 2020-12-20T13:02:10Z urn:sha1:4fe7460678aaaf6f8129ca85ae7124ec3284eb04 size. Fixes booting on machines that have memory banks higher up in physical address space which needs a larger TCE table. Make sure we perform address translation to all elements of a DMA mapping. 2020-11-15T23:14:04Z kettenis kettenis@openbsd.org 2020-11-15T23:14:04Z urn:sha1:dfa9b95e21b6c17e7bae976f51deb34a8cdfd056 No need to print that we're the console device; wsdisplay(4) will do that 2020-10-30T13:36:45Z kettenis kettenis@openbsd.org 2020-10-30T13:36:45Z urn:sha1:cb96bc0b28ce6dc9da99fac1475813a47fadabb0 for us. Add a comment that explains why the major/minor of the device is set 2020-10-30T13:26:29Z kettenis kettenis@openbsd.org 2020-10-30T13:26:29Z urn:sha1:86eeef6eda3ae6b33a0f8a0acdb0353eb35ed6d9 unconditionally now that astfb(4) can be used as the console as well. Only print that we're the console if we actually are. Allow astfb(4) to become the console. At this point this is a "late" switch 2020-10-30T13:11:11Z kettenis kettenis@openbsd.org 2020-10-30T13:11:11Z urn:sha1:e6f8608cd5901b2fb72d4bb5eaa5c3e0af5fa11a and early kernel boot messages will appear on opalcons(4) until astfb(4) attaches. Implement a workaround for PCI devices that can't address the full 64-bit 2020-10-25T14:11:16Z kettenis kettenis@openbsd.org 2020-10-25T14:11:16Z urn:sha1:e584986b82f0fb81b4a179b81cb98f07d85cccb5 PCI address space. Needed for radeondrm(4) and amdgpu(4) since Radeon GPUs only implement 36, 40 or 44 bits of address space. Prefer 32-bit MSI even if the hardware supports 64-bit MSI to work 2020-10-24T14:38:46Z kettenis kettenis@openbsd.org 2020-10-24T14:38:46Z urn:sha1:bc16de6891e675be6cc80bbc764f45223f289e27 around buggy Radeon cards that advertise 64-bit MSI but only implement 40 bits.